diff options
154 files changed, 5153 insertions, 1543 deletions
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt index 701d39d3171a..56d6d8b796db 100644 --- a/Documentation/arm64/booting.txt +++ b/Documentation/arm64/booting.txt @@ -109,7 +109,13 @@ Header notes: 1 - 4K 2 - 16K 3 - 64K - Bits 3-63: Reserved. + Bit 3: Kernel physical placement + 0 - 2MB aligned base should be as close as possible + to the base of DRAM, since memory below it is not + accessible via the linear mapping + 1 - 2MB aligned base may be anywhere in physical + memory + Bits 4-63: Reserved. - When image_size is zero, a bootloader should attempt to keep as much memory as possible free for use by the kernel immediately after the @@ -117,14 +123,14 @@ Header notes: depending on selected features, and is effectively unbound. The Image must be placed text_offset bytes from a 2MB aligned base -address near the start of usable system RAM and called there. Memory -below that base address is currently unusable by Linux, and therefore it -is strongly recommended that this location is the start of system RAM. -The region between the 2 MB aligned base address and the start of the -image has no special significance to the kernel, and may be used for -other purposes. +address anywhere in usable system RAM and called there. The region +between the 2 MB aligned base address and the start of the image has no +special significance to the kernel, and may be used for other purposes. At least image_size bytes from the start of the image must be free for use by the kernel. +NOTE: versions prior to v4.6 cannot make use of memory below the +physical offset of the Image so it is recommended that the Image be +placed as close as possible to the start of system RAM. Any memory described to the kernel (even that below the start of the image) which is not marked as reserved from the kernel (e.g., with a diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt new file mode 100644 index 000000000000..58b71ddf9b60 --- /dev/null +++ b/Documentation/arm64/silicon-errata.txt @@ -0,0 +1,58 @@ + Silicon Errata and Software Workarounds + ======================================= + +Author: Will Deacon <will.deacon@arm.com> +Date : 27 November 2015 + +It is an unfortunate fact of life that hardware is often produced with +so-called "errata", which can cause it to deviate from the architecture +under specific circumstances. For hardware produced by ARM, these +errata are broadly classified into the following categories: + + Category A: A critical error without a viable workaround. + Category B: A significant or critical error with an acceptable + workaround. + Category C: A minor error that is not expected to occur under normal + operation. + +For more information, consult one of the "Software Developers Errata +Notice" documents available on infocenter.arm.com (registration +required). + +As far as Linux is concerned, Category B errata may require some special +treatment in the operating system. For example, avoiding a particular +sequence of code, or configuring the processor in a particular way. A +less common situation may require similar actions in order to declassify +a Category A erratum into a Category C erratum. These are collectively +known as "software workarounds" and are only required in the minority of +cases (e.g. those cases that both require a non-secure workaround *and* +can be triggered by Linux). + +For software workarounds that may adversely impact systems unaffected by +the erratum in question, a Kconfig entry is added under "Kernel +Features" -> "ARM errata workarounds via the alternatives framework". +These are enabled by default and patched in at runtime when an affected +CPU is detected. For less-intrusive workarounds, a Kconfig option is not +available and the code is structured (preferably with a comment) in such +a way that the erratum will not be hit. + +This approach can make it slightly onerous to determine exactly which +errata are worked around in an arbitrary kernel source tree, so this +file acts as a registry of software workarounds in the Linux Kernel and +will be updated when new workarounds are committed and backported to +stable kernels. + +| Implementor | Component | Erratum ID | Kconfig | ++----------------+-----------------+-----------------+-------------------------+ +| ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | +| ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | +| ARM | Cortex-A53 | #824069 | ARM64_ERRATUM_824069 | +| ARM | Cortex-A53 | #819472 | ARM64_ERRATUM_819472 | +| ARM | Cortex-A53 | #845719 | ARM64_ERRATUM_845719 | +| ARM | Cortex-A53 | #843419 | ARM64_ERRATUM_843419 | +| ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +| ARM | Cortex-A57 | #852523 | N/A | +| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| | | | | +| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | +| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt index 0cb44dc21f97..601256fe8c0d 100644 --- a/Documentation/devicetree/bindings/opp/opp.txt +++ b/Documentation/devicetree/bindings/opp/opp.txt @@ -45,21 +45,10 @@ Devices supporting OPPs must set their "operating-points-v2" property with phandle to a OPP table in their DT node. The OPP core will use this phandle to find the operating points for the device. -Devices may want to choose OPP tables at runtime and so can provide a list of -phandles here. But only *one* of them should be chosen at runtime. This must be -accompanied by a corresponding "operating-points-names" property, to uniquely -identify the OPP tables. - If required, this can be extended for SoC vendor specfic bindings. Such bindings should be documented as Documentation/devicetree/bindings/power/<vendor>-opp.txt and should have a compatible description like: "operating-points-v2-<vendor>". -Optional properties: -- operating-points-names: Names of OPP tables (required if multiple OPP - tables are present), to uniquely identify them. The same list must be present - for all the CPUs which are sharing clock/voltage rails and hence the OPP - tables. - * OPP Table Node This describes the OPPs belonging to a device. This node can have following @@ -100,6 +89,14 @@ Optional properties: Entries for multiple regulators must be present in the same order as regulators are specified in device's DT node. +- opp-microvolt-<name>: Named opp-microvolt property. This is exactly similar to + the above opp-microvolt property, but allows multiple voltage ranges to be + provided for the same OPP. At runtime, the platform can pick a <name> and + matching opp-microvolt-<name> property will be enabled for all OPPs. If the + platform doesn't pick a specific <name> or the <name> doesn't match with any + opp-microvolt-<name> properties, then opp-microvolt property shall be used, if + present. + - opp-microamp: The maximum current drawn by the device in microamperes considering system specific parameters (such as transients, process, aging, maximum operating temperature range etc.) as necessary. This may be used to @@ -112,6 +109,9 @@ Optional properties: for few regulators, then this should be marked as zero for them. If it isn't required for any regulator, then this property need not be present. +- opp-microamp-<name>: Named opp-microamp property. Similar to + opp-microvolt-<name> property, but for microamp instead. + - clock-latency-ns: Specifies the maximum possible transition latency (in nanoseconds) for switching to this OPP from any other OPP. @@ -123,6 +123,26 @@ Optional properties: - opp-suspend: Marks the OPP to be used during device suspend. Only one OPP in the table should have this. +- opp-supported-hw: This enables us to select only a subset of OPPs from the + larger OPP table, based on what version of the hardware we are running on. We + still can't have multiple nodes with the same opp-hz value in OPP table. + + It's an user defined array containing a hierarchy of hardware version numbers, + supported by the OPP. For example: a platform with hierarchy of three levels + of versions (A, B and C), this field should be like <X Y Z>, where X + corresponds to Version hierarchy A, Y corresponds to version hierarchy B and Z + corresponds to version hierarchy C. + + Each level of hierarchy is represented by a 32 bit value, and so there can be + only 32 different supported version per hierarchy. i.e. 1 bit per version. A + value of 0xFFFFFFFF will enable the OPP for all versions for that hierarchy + level. And a value of 0x00000000 will disable the OPP completely, and so we + never want that to happen. + + If 32 values aren't sufficient for a version hierarchy, than that version + hierarchy can be contained in multiple 32 bit values. i.e. <X Y Z1 Z2> in the + above example, Z1 & Z2 refer to the version hierarchy Z. + - status: Marks the node enabled/disabled. Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together. @@ -157,20 +177,20 @@ Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together. compatible = "operating-points-v2"; opp-shared; - opp00 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <970000 975000 985000>; opp-microamp = <70000>; clock-latency-ns = <300000>; opp-suspend; }; - opp01 { + opp@1100000000 { opp-hz = /bits/ 64 <1100000000>; opp-microvolt = <980000 1000000 1010000>; opp-microamp = <80000>; clock-latency-ns = <310000>; }; - opp02 { + opp@1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <1025000>; clock-latency-ns = <290000>; @@ -236,20 +256,20 @@ independently. * independently. */ - opp00 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <970000 975000 985000>; opp-microamp = <70000>; clock-latency-ns = <300000>; opp-suspend; }; - opp01 { + opp@1100000000 { opp-hz = /bits/ 64 <1100000000>; opp-microvolt = <980000 1000000 1010000>; opp-microamp = <80000>; clock-latency-ns = <310000>; }; - opp02 { + opp@1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <1025000>; opp-microamp = <90000; @@ -312,20 +332,20 @@ DVFS state together. compatible = "operating-points-v2"; opp-shared; - opp00 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <970000 975000 985000>; opp-microamp = <70000>; clock-latency-ns = <300000>; opp-suspend; }; - opp01 { + opp@1100000000 { opp-hz = /bits/ 64 <1100000000>; opp-microvolt = <980000 1000000 1010000>; opp-microamp = <80000>; clock-latency-ns = <310000>; }; - opp02 { + opp@1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <1025000>; opp-microamp = <90000>; @@ -338,20 +358,20 @@ DVFS state together. compatible = "operating-points-v2"; opp-shared; - opp10 { + opp@1300000000 { opp-hz = /bits/ 64 <1300000000>; opp-microvolt = <1045000 1050000 1055000>; opp-microamp = <95000>; clock-latency-ns = <400000>; opp-suspend; }; - opp11 { + opp@1400000000 { opp-hz = /bits/ 64 <1400000000>; opp-microvolt = <1075000>; opp-microamp = <100000>; clock-latency-ns = <400000>; }; - opp12 { + opp@1500000000 { opp-hz = /bits/ 64 <1500000000>; opp-microvolt = <1010000 1100000 1110000>; opp-microamp = <95000>; @@ -378,7 +398,7 @@ Example 4: Handling multiple regulators compatible = "operating-points-v2"; opp-shared; - opp00 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <970000>, /* Supply 0 */ <960000>, /* Supply 1 */ @@ -391,7 +411,7 @@ Example 4: Handling multiple regulators /* OR */ - opp00 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <970000 975000 985000>, /* Supply 0 */ <960000 965000 975000>, /* Supply 1 */ @@ -404,7 +424,7 @@ Example 4: Handling multiple regulators /* OR */ - opp00 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <970000 975000 985000>, /* Supply 0 */ <960000 965000 975000>, /* Supply 1 */ @@ -417,7 +437,8 @@ Example 4: Handling multiple regulators }; }; -Example 5: Multiple OPP tables +Example 5: opp-supported-hw +(example: three level hierarchy of versions: cuts, substrate and process) / { cpus { @@ -426,40 +447,73 @@ Example 5: Multiple OPP tables ... cpu-supply = <&cpu_supply> - operating-points-v2 = <&cpu0_opp_table_slow>, <&cpu0_opp_table_fast>; - operating-points-names = "slow", "fast"; + operating-points-v2 = <&cpu0_opp_table_slow>; }; }; - cpu0_opp_table_slow: opp_table_slow { + opp_table { compatible = "operating-points-v2"; status = "okay"; opp-shared; - opp00 { + opp@600000000 { + /* + * Supports all substrate and process versions for 0xF + * cuts, i.e. only first four cuts. + */ + opp-supported-hw = <0xF 0xFFFFFFFF 0xFFFFFFFF> opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <900000 915000 925000>; ... }; - opp01 { + opp@800000000 { + /* + * Supports: + * - cuts: only one, 6th cut (represented by 6th bit). + * - substrate: supports 16 different substrate versions + * - process: supports 9 different process versions + */ + opp-supported-hw = <0x20 0xff0000ff 0x0000f4f0> opp-hz = /bits/ 64 <800000000>; + opp-microvolt = <900000 915000 925000>; ... }; }; +}; + +Example 6: opp-microvolt-<name>, opp-microamp-<name>: +(example: device with two possible microvolt ranges: slow and fast) - cpu0_opp_table_fast: opp_table_fast { +/ { + cpus { + cpu@0 { + compatible = "arm,cortex-a7"; + ... + + operating-points-v2 = <&cpu0_opp_table>; + }; + }; + + cpu0_opp_table: opp_table0 { compatible = "operating-points-v2"; - status = "okay"; opp-shared; - opp10 { + opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - ... + opp-microvolt-slow = <900000 915000 925000>; + opp-microvolt-fast = <970000 975000 985000>; + opp-microamp-slow = <70000>; + opp-microamp-fast = <71000>; }; - opp11 { - opp-hz = /bits/ 64 <1100000000>; - ... + opp@1200000000 { + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt-slow = <900000 915000 925000>, /* Supply vcc0 */ + <910000 925000 935000>; /* Supply vcc1 */ + opp-microvolt-fast = <970000 975000 985000>, /* Supply vcc0 */ + <960000 965000 975000>; /* Supply vcc1 */ + opp-microamp = <70000>; /* Will be used for both slow/fast */ }; }; }; diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt index e63316239938..4199ffecc0ff 100644 --- a/Documentation/features/time/irq-time-acct/arch-support.txt +++ b/Documentation/features/time/irq-time-acct/arch-support.txt @@ -9,7 +9,7 @@ | alpha: | .. | | arc: | TODO | | arm: | ok | - | arm64: | .. | + | arm64: | ok | | avr32: | TODO | | blackfin: | TODO | | c6x: | TODO | diff --git a/Documentation/features/vm/huge-vmap/arch-support.txt b/Documentation/features/vm/huge-vmap/arch-support.txt index af6816bccb43..df1d1f3c9af2 100644 --- a/Documentation/features/vm/huge-vmap/arch-support.txt +++ b/Documentation/features/vm/huge-vmap/arch-support.txt @@ -9,7 +9,7 @@ | alpha: | TODO | | arc: | TODO | | arm: | TODO | - | arm64: | TODO | + | arm64: | ok | | avr32: | TODO | | blackfin: | TODO | | c6x: | TODO | diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 0e4102ae1a61..554f3844d499 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3409,6 +3409,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. ro [KNL] Mount root device read-only on boot + rodata= [KNL] + on Mark read-only kernel memory as read-only (default). + off Leave read-only kernel memory writable for debugging. + root= [KNL] Root filesystem See name_to_dev_t comment in init/do_mounts.c. diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d5525bfc7e3e..9156fc303afd 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -491,7 +491,6 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif #ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); void set_kernel_text_rw(void); void set_kernel_text_ro(void); #else diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 194c91b610ff..c35c349da069 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -79,6 +79,8 @@ #define rr_lo_hi(a1, a2) a1, a2 #endif +#define kvm_ksym_ref(kva) (kva) + #ifndef __ASSEMBLY__ struct kvm; struct kvm_vcpu; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index e06fd299de08..70e6d557c75f 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -969,7 +969,7 @@ static void cpu_init_hyp_mode(void *dummy) pgd_ptr = kvm_mmu_get_httbr(); stack_page = __this_cpu_read(kvm_arm_hyp_stack_page); hyp_stack_ptr = stack_page + PAGE_SIZE; - vector_ptr = (unsigned long)__kvm_hyp_vector; + vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector); __cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr); @@ -1061,7 +1061,8 @@ static int init_hyp_mode(void) /* * Map the Hyp-code called directly from the host */ - err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end); + err = create_hyp_mappings(kvm_ksym_ref(__kvm_hyp_code_start), + kvm_ksym_ref(__kvm_hyp_code_end)); if (err) { kvm_err("Cannot map world-switch code\n"); goto out_free_mappings; diff --git a/arch/arm/vdso/vdso.S b/arch/arm/vdso/vdso.S index b2b97e3e7bab..a62a7b64f49c 100644 --- a/arch/arm/vdso/vdso.S +++ b/arch/arm/vdso/vdso.S @@ -23,9 +23,8 @@ #include <linux/const.h> #include <asm/page.h> - __PAGE_ALIGNED_DATA - .globl vdso_start, vdso_end + .section .data..ro_after_init .balign PAGE_SIZE vdso_start: .incbin "arch/arm/vdso/vdso.so" diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 871f21783866..97583a1878db 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -13,6 +13,7 @@ config ARM64 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_COMPAT_IPC_PARSE_VERSION select ARCH_WANT_FRAME_POINTERS + select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA select ARM_ARCH_TIMER select ARM_GIC @@ -48,6 +49,7 @@ config ARM64 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE + select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KGDB @@ -70,6 +72,7 @@ config ARM64 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_MEMBLOCK select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS @@ -362,6 +365,7 @@ config ARM64_ERRATUM_843419 bool "Cortex-A53: 843419: A load or store might access an incorrect address" depends on MODULES default y + select ARM64_MODULE_CMODEL_LARGE help This option builds kernel modules using the large memory model in order to avoid the use of the ADRP instruction, which can cause @@ -506,6 +510,9 @@ config HOTPLUG_CPU source kernel/Kconfig.preempt source kernel/Kconfig.hz +config ARCH_SUPPORTS_DEBUG_PAGEALLOC + def_bool y + config ARCH_HAS_HOLES_MEMORYMODEL def_bool y if SPARSEMEM @@ -529,9 +536,6 @@ config HW_PERF_EVENTS config SYS_SUPPORTS_HUGETLBFS def_bool y -config ARCH_WANT_GENERAL_HUGETLB - def_bool y - config ARCH_WANT_HUGE_PMD_SHARE def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) @@ -704,10 +708,93 @@ config ARM64_LSE_ATOMICS endmenu +config ARM64_UAO + bool "Enable support for User Access Override (UAO)" + default y + help + User Access Override (UAO; part of the ARMv8.2 Extensions) + causes the 'unprivileged' variant of the load/store instructions to + be overriden to be privileged. + + This option changes get_user() and friends to use the 'unprivileged' + variant of the load/store instructions. This ensures that user-space + really did have access to the supplied memory. When addr_limit is + set to kernel memory the UAO bit will be set, allowing privileged + access to kernel memory. + + Choosing this option will cause copy_to_user() et al to use user-space + memory permissions. + + The feature is detected at runtime, the kernel will use the + regular load/store instructions if the cpu does not implement the + feature. + +config ARM64_MODULE_CMODEL_LARGE + bool + +config ARM64_MODULE_PLTS + bool + select ARM64_MODULE_CMODEL_LARGE + select HAVE_MOD_ARCH_SPECIFIC + +config RELOCATABLE + bool + help + This builds the kernel as a Position Independent Executable (PIE), + which retains all relocation metadata required to relocate the + kernel binary at runtime to a different virtual address than the + address it was linked at. + Since AArch64 uses the RELA relocation format, this requires a + relocation pass at runtime even if the kernel is loaded at the + same address it was linked at. + +config RANDOMIZE_BASE + bool "Randomize the address of the kernel image" + select ARM64_MODULE_PLTS + select RELOCATABLE + help + Randomizes the virtual address at which the kernel image is + loaded, as a security feature that deters exploit attempts + relying on knowledge of the location of kernel internals. + + It is the bootloader's job to provide entropy, by passing a + random u64 value in /chosen/kaslr-seed at kernel entry. + + When booting via the UEFI stub, it will invoke the firmware's + EFI_RNG_PROTOCOL implementation (if available) to supply entropy + to the kernel proper. In addition, it will randomise the physical + location of the kernel Image as well. + + If unsure, say N. + +config RANDOMIZE_MODULE_REGION_FULL + bool "Randomize the module region independently from the core kernel" + depends on RANDOMIZE_BASE + default y + help + Randomizes the location of the module region without considering the + location of the core kernel. This way, it is impossible for modules + to leak information about the location of core kernel data structures + but it does imply that function calls between modules and the core + kernel will need to be resolved via veneers in the module PLT. + + When this option is not set, the module region will be randomized over + a limited range that contains the [_stext, _etext] interval of the + core kernel, so branch relocations are always in range. + endmenu menu "Boot options" +config ARM64_ACPI_PARKING_PROTOCOL + bool "Enable support for the ARM64 ACPI parking protocol" + depends on ACPI + help + Enable support for the ARM64 ACPI parking protocol. If disabled + the kernel will not allow booting through the ARM64 ACPI parking + protocol even if the corresponding data is present in the ACPI + MADT table. + config CMDLINE string "Default kernel command string" default "" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index b6c90e5006e4..304dcc3da06f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -15,6 +15,10 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) OBJCOPYFLAGS :=-O binary -R .note -R .note.gnu.build-id -R .comment -S GZFLAGS :=-9 +ifneq ($(CONFIG_RELOCATABLE),) +LDFLAGS_vmlinux += -pie +endif + KBUILD_DEFCONFIG := defconfig # Check for binutils support for specific extensions @@ -28,6 +32,7 @@ endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_AFLAGS += $(lseinstr) ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) @@ -42,10 +47,14 @@ endif CHECKFLAGS += -D__aarch64__ -ifeq ($(CONFIG_ARM64_ERRATUM_843419), y) +ifeq ($(CONFIG_ARM64_MODULE_CMODEL_LARGE), y) KBUILD_CFLAGS_MODULE += -mcmodel=large endif +ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) +KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/arm64/kernel/module.lds +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index caafd63b8092..aee323b13802 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -87,9 +87,26 @@ void __init acpi_init_cpus(void); static inline void acpi_init_cpus(void) { } #endif /* CONFIG_ACPI */ +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL +bool acpi_parking_protocol_valid(int cpu); +void __init +acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor); +#else +static inline bool acpi_parking_protocol_valid(int cpu) { return false; } +static inline void +acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor) +{} +#endif + static inline const char *acpi_get_enable_method(int cpu) { - return acpi_psci_present() ? "psci" : NULL; + if (acpi_psci_present()) + return "psci"; + + if (acpi_parking_protocol_valid(cpu)) + return "parking-protocol"; + + return NULL; } #ifdef CONFIG_ACPI_APEI diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index d56ec0715157..beccbdefa106 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -1,6 +1,8 @@ #ifndef __ASM_ALTERNATIVE_H #define __ASM_ALTERNATIVE_H +#include <asm/cpufeature.h> + #ifndef __ASSEMBLY__ #include <linux/init.h> @@ -19,7 +21,6 @@ struct alt_instr { void __init apply_alternatives_all(void); void apply_alternatives(void *start, size_t length); -void free_alternatives_memory(void); #define ALTINSTR_ENTRY(feature) \ " .word 661b - .\n" /* label */ \ @@ -64,6 +65,8 @@ void free_alternatives_memory(void); #else +#include <asm/assembler.h> + .macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len .word \orig_offset - . .word \alt_offset - . @@ -137,6 +140,65 @@ void free_alternatives_memory(void); alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) +/* + * Generate the assembly for UAO alternatives with exception table entries. + * This is complicated as there is no post-increment or pair versions of the + * unprivileged instructions, and USER() only works for single instructions. + */ +#ifdef CONFIG_ARM64_UAO + .macro uao_ldp l, reg1, reg2, addr, post_inc + alternative_if_not ARM64_HAS_UAO +8888: ldp \reg1, \reg2, [\addr], \post_inc; +8889: nop; + nop; + alternative_else + ldtr \reg1, [\addr]; + ldtr \reg2, [\addr, #8]; + add \addr, \addr, \post_inc; + alternative_endif + + _asm_extable 8888b,\l; + _asm_extable 8889b,\l; + .endm + + .macro uao_stp l, reg1, reg2, addr, post_inc + alternative_if_not ARM64_HAS_UAO +8888: stp \reg1, \reg2, [\addr], \post_inc; +8889: nop; + nop; + alternative_else + sttr \reg1, [\addr]; + sttr \reg2, [\addr, #8]; + add \addr, \addr, \post_inc; + alternative_endif + + _asm_extable 8888b,\l; + _asm_extable 8889b,\l; + .endm + + .macro uao_user_alternative l, inst, alt_inst, reg, addr, post_inc + alternative_if_not ARM64_HAS_UAO +8888: \inst \reg, [\addr], \post_inc; + nop; + alternative_else + \alt_inst \reg, [\addr]; + add \addr, \addr, \post_inc; + alternative_endif + + _asm_extable 8888b,\l; + .endm +#else + .macro uao_ldp l, reg1, reg2, addr, post_inc + USER(\l, ldp \reg1, \reg2, [\addr], \post_inc) + .endm + .macro uao_stp l, reg1, reg2, addr, post_inc + USER(\l, stp \reg1, \reg2, [\addr], \post_inc) + .endm + .macro uao_user_alternative l, inst, alt_inst, reg, addr, post_inc + USER(\l, \inst \reg, [\addr], \post_inc) + .endm +#endif + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 12eff928ef8b..70f7b9e04598 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -94,12 +94,19 @@ dmb \opt .endm +/* + * Emit an entry into the exception table + */ + .macro _asm_extable, from, to + .pushsection __ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection + .endm + #define USER(l, x...) \ 9999: x; \ - .section __ex_table,"a"; \ - .align 3; \ - .quad 9999b,l; \ - .previous + _asm_extable 9999b, l /* * Register aliases. @@ -193,6 +200,17 @@ lr .req x30 // link register str \src, [\tmp, :lo12:\sym] .endm + /* + * @sym: The name of the per-cpu variable + * @reg: Result of per_cpu(sym, smp_processor_id()) + * @tmp: scratch register + */ + .macro this_cpu_ptr, sym, reg, tmp + adr_l \reg, \sym + mrs \tmp, tpidr_el1 + add \reg, \reg, \tmp + .endm + /* * Annotate a function as position independent, i.e., safe to be called before * the kernel virtual mapping is activated. @@ -204,4 +222,15 @@ lr .req x30 // link register .size __pi_##x, . - x; \ ENDPROC(x) + /* + * Emit a 64-bit absolute little endian symbol reference in a way that + * ensures that it will be resolved at build time, even when building a + * PIE binary. This requires cooperation from the linker script, which + * must emit the lo32/hi32 halves individually. + */ + .macro le64sym, sym + .long \sym\()_lo32 + .long \sym\()_hi32 + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 197e06afbf71..39c1d340fec5 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -36,7 +36,7 @@ static inline void atomic_andnot(int i, atomic_t *v) " stclr %w[i], %[v]\n") : [i] "+r" (w0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic_or(int i, atomic_t *v) @@ -48,7 +48,7 @@ static inline void atomic_or(int i, atomic_t *v) " stset %w[i], %[v]\n") : [i] "+r" (w0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic_xor(int i, atomic_t *v) @@ -60,7 +60,7 @@ static inline void atomic_xor(int i, atomic_t *v) " steor %w[i], %[v]\n") : [i] "+r" (w0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic_add(int i, atomic_t *v) @@ -72,7 +72,7 @@ static inline void atomic_add(int i, atomic_t *v) " stadd %w[i], %[v]\n") : [i] "+r" (w0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } #define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \ @@ -90,7 +90,7 @@ static inline int atomic_add_return##name(int i, atomic_t *v) \ " add %w[i], %w[i], w30") \ : [i] "+r" (w0), [v] "+Q" (v->counter) \ : "r" (x1) \ - : "x30" , ##cl); \ + : __LL_SC_CLOBBERS, ##cl); \ \ return w0; \ } @@ -116,7 +116,7 @@ static inline void atomic_and(int i, atomic_t *v) " stclr %w[i], %[v]") : [i] "+r" (w0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic_sub(int i, atomic_t *v) @@ -133,7 +133,7 @@ static inline void atomic_sub(int i, atomic_t *v) " stadd %w[i], %[v]") : [i] "+r" (w0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } #define ATOMIC_OP_SUB_RETURN(name, mb, cl...) \ @@ -153,7 +153,7 @@ static inline int atomic_sub_return##name(int i, atomic_t *v) \ " add %w[i], %w[i], w30") \ : [i] "+r" (w0), [v] "+Q" (v->counter) \ : "r" (x1) \ - : "x30" , ##cl); \ + : __LL_SC_CLOBBERS , ##cl); \ \ return w0; \ } @@ -177,7 +177,7 @@ static inline void atomic64_andnot(long i, atomic64_t *v) " stclr %[i], %[v]\n") : [i] "+r" (x0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic64_or(long i, atomic64_t *v) @@ -189,7 +189,7 @@ static inline void atomic64_or(long i, atomic64_t *v) " stset %[i], %[v]\n") : [i] "+r" (x0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic64_xor(long i, atomic64_t *v) @@ -201,7 +201,7 @@ static inline void atomic64_xor(long i, atomic64_t *v) " steor %[i], %[v]\n") : [i] "+r" (x0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic64_add(long i, atomic64_t *v) @@ -213,7 +213,7 @@ static inline void atomic64_add(long i, atomic64_t *v) " stadd %[i], %[v]\n") : [i] "+r" (x0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...) \ @@ -231,7 +231,7 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v) \ " add %[i], %[i], x30") \ : [i] "+r" (x0), [v] "+Q" (v->counter) \ : "r" (x1) \ - : "x30" , ##cl); \ + : __LL_SC_CLOBBERS, ##cl); \ \ return x0; \ } @@ -257,7 +257,7 @@ static inline void atomic64_and(long i, atomic64_t *v) " stclr %[i], %[v]") : [i] "+r" (x0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } static inline void atomic64_sub(long i, atomic64_t *v) @@ -274,7 +274,7 @@ static inline void atomic64_sub(long i, atomic64_t *v) " stadd %[i], %[v]") : [i] "+r" (x0), [v] "+Q" (v->counter) : "r" (x1) - : "x30"); + : __LL_SC_CLOBBERS); } #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...) \ @@ -294,7 +294,7 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v) \ " add %[i], %[i], x30") \ : [i] "+r" (x0), [v] "+Q" (v->counter) \ : "r" (x1) \ - : "x30" , ##cl); \ + : __LL_SC_CLOBBERS, ##cl); \ \ return x0; \ } @@ -330,7 +330,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) "2:") : [ret] "+&r" (x0), [v] "+Q" (v->counter) : - : "x30", "cc", "memory"); + : __LL_SC_CLOBBERS, "cc", "memory"); return x0; } @@ -359,7 +359,7 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ " mov %" #w "[ret], " #w "30") \ : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ : [old] "r" (x1), [new] "r" (x2) \ - : "x30" , ##cl); \ + : __LL_SC_CLOBBERS, ##cl); \ \ return x0; \ } @@ -416,7 +416,7 @@ static inline long __cmpxchg_double##name(unsigned long old1, \ [v] "+Q" (*(unsigned long *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ - : "x30" , ##cl); \ + : __LL_SC_CLOBBERS, ##cl); \ \ return x0; \ } diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h index 81151b67b26b..ebf2481889c3 100644 --- a/arch/arm64/include/asm/boot.h +++ b/arch/arm64/include/asm/boot.h @@ -11,4 +11,10 @@ #define MIN_FDT_ALIGN 8 #define MAX_FDT_SIZE SZ_2M +/* + * arm64 requires the kernel image to placed + * TEXT_OFFSET bytes beyond a 2 MB aligned base + */ +#define MIN_KIMG_ALIGN SZ_2M + #endif diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h new file mode 100644 index 000000000000..ed693c5bcec0 --- /dev/null +++ b/arch/arm64/include/asm/brk-imm.h @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2012 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_BRK_IMM_H +#define __ASM_BRK_IMM_H + +/* + * #imm16 values used for BRK instruction generation + * Allowed values for kgdb are 0x400 - 0x7ff + * 0x100: for triggering a fault on purpose (reserved) + * 0x400: for dynamic BRK instruction + * 0x401: for compile time BRK instruction + * 0x800: kernel-mode BUG() and WARN() traps + */ +#define FAULT_BRK_IMM 0x100 +#define KGDB_DYN_DBG_BRK_IMM 0x400 +#define KGDB_COMPILED_DBG_BRK_IMM 0x401 +#define BUG_BRK_IMM 0x800 + +#endif diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h index 4a748ce9ba1a..561190d15881 100644 --- a/arch/arm64/include/asm/bug.h +++ b/arch/arm64/include/asm/bug.h @@ -18,7 +18,7 @@ #ifndef _ARCH_ARM64_ASM_BUG_H #define _ARCH_ARM64_ASM_BUG_H -#include <asm/debug-monitors.h> +#include <asm/brk-imm.h> #ifdef CONFIG_GENERIC_BUG #define HAVE_ARCH_BUG diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 54efedaf331f..22dda613f9c9 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -68,6 +68,7 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); +extern void __clean_dcache_area_pou(void *addr, size_t len); extern long __flush_cache_user_range(unsigned long start, unsigned long end); static inline void flush_cache_mm(struct mm_struct *mm) @@ -155,8 +156,4 @@ int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); -#endif - #endif diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 9ea611ea69df..510c7b404454 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -19,7 +19,6 @@ #define __ASM_CMPXCHG_H #include <linux/bug.h> -#include <linux/mmdebug.h> #include <asm/atomic.h> #include <asm/barrier.h> diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index b5e9cee4b5f8..13a6103130cd 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -36,6 +36,7 @@ struct cpuinfo_arm64 { u64 reg_id_aa64isar1; u64 reg_id_aa64mmfr0; u64 reg_id_aa64mmfr1; + u64 reg_id_aa64mmfr2; u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 8f271b83f910..37a53fc6b384 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -30,8 +30,11 @@ #define ARM64_HAS_LSE_ATOMICS 5 #define ARM64_WORKAROUND_CAVIUM_23154 6 #define ARM64_WORKAROUND_834220 7 +#define ARM64_HAS_NO_HW_PREFETCH 8 +#define ARM64_HAS_UAO 9 +#define ARM64_ALT_PAN_NOT_UAO 10 -#define ARM64_NCAPS 8 +#define ARM64_NCAPS 11 #ifndef __ASSEMBLY__ @@ -176,7 +179,7 @@ u64 read_system_reg(u32 id); static inline bool cpu_supports_mixed_endian_el0(void) { - return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); + return id_aa64mmfr0_mixed_endian_el0(read_cpuid(SYS_ID_AA64MMFR0_EL1)); } static inline bool system_supports_mixed_endian_el0(void) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 1a5949364ed0..b3a83da152a7 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -32,12 +32,6 @@ #define MPIDR_AFFINITY_LEVEL(mpidr, level) \ ((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK) -#define read_cpuid(reg) ({ \ - u64 __val; \ - asm("mrs %0, " #reg : "=r" (__val)); \ - __val; \ -}) - #define MIDR_REVISION_MASK 0xf #define MIDR_REVISION(midr) ((midr) & MIDR_REVISION_MASK) #define MIDR_PARTNUM_SHIFT 4 @@ -57,11 +51,22 @@ #define MIDR_IMPLEMENTOR(midr) \ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) -#define MIDR_CPU_PART(imp, partnum) \ +#define MIDR_CPU_MODEL(imp, partnum) \ (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) +#define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ + MIDR_ARCHITECTURE_MASK) + +#define MIDR_IS_CPU_MODEL_RANGE(midr, model, rv_min, rv_max) \ +({ \ + u32 _model = (midr) & MIDR_CPU_MODEL_MASK; \ + u32 rv = (midr) & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK); \ + \ + _model == (model) && rv >= (rv_min) && rv <= (rv_max); \ + }) + #define ARM_CPU_IMP_ARM 0x41 #define ARM_CPU_IMP_APM 0x50 #define ARM_CPU_IMP_CAVIUM 0x43 @@ -75,8 +80,20 @@ #define CAVIUM_CPU_PART_THUNDERX 0x0A1 +#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) +#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) +#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) + #ifndef __ASSEMBLY__ +#include <asm/sysreg.h> + +#define read_cpuid(reg) ({ \ + u64 __val; \ + asm("mrs_s %0, " __stringify(reg) : "=r" (__val)); \ + __val; \ +}) + /* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID @@ -84,12 +101,12 @@ */ static inline u32 __attribute_const__ read_cpuid_id(void) { - return read_cpuid(MIDR_EL1); + return read_cpuid(SYS_MIDR_EL1); } static inline u64 __attribute_const__ read_cpuid_mpidr(void) { - return read_cpuid(MPIDR_EL1); + return read_cpuid(SYS_MPIDR_EL1); } static inline unsigned int __attribute_const__ read_cpuid_implementor(void) @@ -104,7 +121,7 @@ static inline unsigned int __attribute_const__ read_cpuid_part_number(void) static inline u32 __attribute_const__ read_cpuid_cachetype(void) { - return read_cpuid(CTR_EL0); + return read_cpuid(SYS_CTR_EL0); } #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 279c85b5ec09..2fcb9b7c876c 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -20,6 +20,7 @@ #include <linux/errno.h> #include <linux/types.h> +#include <asm/brk-imm.h> #include <asm/esr.h> #include <asm/insn.h> #include <asm/ptrace.h> @@ -47,19 +48,6 @@ #define BREAK_INSTR_SIZE AARCH64_INSN_SIZE /* - * #imm16 values used for BRK instruction generation - * Allowed values for kgbd are 0x400 - 0x7ff - * 0x100: for triggering a fault on purpose (reserved) - * 0x400: for dynamic BRK instruction - * 0x401: for compile time BRK instruction - * 0x800: kernel-mode BUG() and WARN() traps - */ -#define FAULT_BRK_IMM 0x100 -#define KGDB_DYN_DBG_BRK_IMM 0x400 -#define KGDB_COMPILED_DBG_BRK_IMM 0x401 -#define BUG_BRK_IMM 0x800 - -/* * BRK instruction encoding * The #imm16 value should be placed at bits[20:5] within BRK ins */ diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index faad6df49e5b..24ed037f09fd 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -24,15 +24,6 @@ #include <asm/ptrace.h> #include <asm/user.h> -typedef unsigned long elf_greg_t; - -#define ELF_NGREG (sizeof(struct user_pt_regs) / sizeof(elf_greg_t)) -#define ELF_CORE_COPY_REGS(dest, regs) \ - *(struct user_pt_regs *)&(dest) = (regs)->user_regs; - -typedef elf_greg_t elf_gregset_t[ELF_NGREG]; -typedef struct user_fpsimd_state elf_fpregset_t; - /* * AArch64 static relocation types. */ @@ -86,6 +77,8 @@ typedef struct user_fpsimd_state elf_fpregset_t; #define R_AARCH64_MOVW_PREL_G2_NC 292 #define R_AARCH64_MOVW_PREL_G3 293 +#define R_AARCH64_RELATIVE 1027 + /* * These are used to set parameters in the core dumps. */ @@ -127,6 +120,17 @@ typedef struct user_fpsimd_state elf_fpregset_t; */ #define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) +#ifndef __ASSEMBLY__ + +typedef unsigned long elf_greg_t; + +#define ELF_NGREG (sizeof(struct user_pt_regs) / sizeof(elf_greg_t)) +#define ELF_CORE_COPY_REGS(dest, regs) \ + *(struct user_pt_regs *)&(dest) = (regs)->user_regs; + +typedef elf_greg_t elf_gregset_t[ELF_NGREG]; +typedef struct user_fpsimd_state elf_fpregset_t; + /* * When the program starts, a1 contains a pointer to a function to be * registered with atexit, as per the SVR4 ABI. A value of 0 means we have no @@ -186,4 +190,6 @@ extern int aarch32_setup_vectors_page(struct linux_binprm *bprm, #endif /* CONFIG_COMPAT */ +#endif /* !__ASSEMBLY__ */ + #endif diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 309704544d22..1a617d46fce9 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -62,6 +62,16 @@ enum fixed_addresses { FIX_BTMAP_END = __end_of_permanent_fixed_addresses, FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, + + /* + * Used for kernel page table creation, so unmapped memory may be used + * for tables. + */ + FIX_PTE, + FIX_PMD, + FIX_PUD, + FIX_PGD, + __end_of_fixed_addresses }; diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index c5534facf941..3c60f37e48ab 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -28,6 +28,8 @@ struct dyn_arch_ftrace { extern unsigned long ftrace_graph_call; +extern void return_to_handler(void); + static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 007a69fc4f40..f2585cdd32c2 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -42,10 +42,8 @@ "4: mov %w0, %w5\n" \ " b 3b\n" \ " .popsection\n" \ -" .pushsection __ex_table,\"a\"\n" \ -" .align 3\n" \ -" .quad 1b, 4b, 2b, 4b\n" \ -" .popsection\n" \ + _ASM_EXTABLE(1b, 4b) \ + _ASM_EXTABLE(2b, 4b) \ ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \ @@ -121,6 +119,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; asm volatile("// futex_atomic_cmpxchg_inatomic\n" +ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN) " prfm pstl1strm, %2\n" "1: ldxr %w1, %2\n" " sub %w3, %w1, %w4\n" @@ -133,10 +132,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, "4: mov %w0, %w6\n" " b 3b\n" " .popsection\n" -" .pushsection __ex_table,\"a\"\n" -" .align 3\n" -" .quad 1b, 4b, 2b, 4b\n" -" .popsection\n" + _ASM_EXTABLE(1b, 4b) + _ASM_EXTABLE(2b, 4b) +ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN) : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp) : "r" (oldval), "r" (newval), "Ir" (-EFAULT) : "memory"); diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index a57601f9d17c..8740297dac77 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 5 +#define NR_IPI 6 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index bb4052e85dba..bbc1e35aa601 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - set_pte_at(mm, addr, ptep, pte); -} - -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - ptep_clear_flush(vma, addr, ptep); -} - -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - ptep_set_wrprotect(mm, addr, ptep); -} -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - return ptep_get_and_clear(mm, addr, ptep); -} - -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - return ptep_set_access_flags(vma, addr, ptep, pte, dirty); -} static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, @@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page *page) clear_bit(PG_dcache_clean, &page->flags); } +extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable); +#define arch_make_huge_pte arch_make_huge_pte +extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); +extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); +extern void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); +extern void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index 8e8d30684392..b77197d941fc 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -1,10 +1,45 @@ #ifndef __ASM_IRQ_H #define __ASM_IRQ_H +#define IRQ_STACK_SIZE THREAD_SIZE +#define IRQ_STACK_START_SP THREAD_START_SP + +#ifndef __ASSEMBLER__ + +#include <linux/percpu.h> + #include <asm-generic/irq.h> +#include <asm/thread_info.h> struct pt_regs; +DECLARE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); + +/* + * The highest address on the stack, and the first to be used. Used to + * find the dummy-stack frame put down by el?_irq() in entry.S, which + * is structured as follows: + * + * ------------ + * | | <- irq_stack_ptr + * top ------------ + * | x19 | <- irq_stack_ptr - 0x08 + * ------------ + * | x29 | <- irq_stack_ptr - 0x10 + * ------------ + * + * where x19 holds a copy of the task stack pointer where the struct pt_regs + * from kernel_entry can be found. + * + */ +#define IRQ_STACK_PTR(cpu) ((unsigned long)per_cpu(irq_stack, cpu) + IRQ_STACK_START_SP) + +/* + * The offset from irq_stack_ptr where entry.S will store the original + * stack pointer. Used by unwind_frame() and dump_backtrace(). + */ +#define IRQ_STACK_TO_TASK_STACK(ptr) (*((unsigned long *)((ptr) - 0x08))) + extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); static inline int nr_legacy_irqs(void) @@ -12,4 +47,14 @@ static inline int nr_legacy_irqs(void) return 0; } +static inline bool on_irq_stack(unsigned long sp, int cpu) +{ + /* variable names the same as kernel/stacktrace.c */ + unsigned long low = (unsigned long)per_cpu(irq_stack, cpu); + unsigned long high = low + IRQ_STACK_START_SP; + + return (low <= sp && sp <= high); +} + +#endif /* !__ASSEMBLER__ */ #endif diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 2774fa384c47..71ad0f93eb71 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -7,13 +7,14 @@ #include <linux/linkage.h> #include <asm/memory.h> +#include <asm/pgtable-types.h> /* * KASAN_SHADOW_START: beginning of the kernel virtual addresses. * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/8 of kernel virtual addresses. */ #define KASAN_SHADOW_START (VA_START) -#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1UL << (VA_BITS - 3))) +#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) /* * This value is used to map an address to the corresponding shadow @@ -28,10 +29,12 @@ #define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << (64 - 3))) void kasan_init(void); +void kasan_copy_shadow(pgd_t *pgdir); asmlinkage void kasan_early_init(void); #else static inline void kasan_init(void) { } +static inline void kasan_copy_shadow(pgd_t *pgdir) { } #endif #endif diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index a459714ee29e..5c6375d8528b 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -79,5 +79,17 @@ #define SWAPPER_MM_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) #endif +/* + * To make optimal use of block mappings when laying out the linear + * mapping, round down the base of physical memory to a size that can + * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE + * (64k granule), or a multiple that can be mapped using contiguous bits + * in the page tables: 32 * PMD_SIZE (16k granule) + */ +#ifdef CONFIG_ARM64_64K_PAGES +#define ARM64_MEMSTART_ALIGN SZ_512M +#else +#define ARM64_MEMSTART_ALIGN SZ_1G +#endif #endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 5e377101f919..419bc6661b5c 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -102,6 +102,8 @@ #define KVM_ARM64_DEBUG_DIRTY_SHIFT 0 #define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT) +#define kvm_ksym_ref(sym) phys_to_virt((u64)&sym - kimage_voffset) + #ifndef __ASSEMBLY__ struct kvm; struct kvm_vcpu; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index a35ce7266aac..90c6368ad7c8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -222,7 +222,7 @@ static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, struct kvm_vcpu *kvm_arm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); -u64 kvm_call_hyp(void *hypfn, ...); +u64 __kvm_call_hyp(void *hypfn, ...); void force_vm_exit(const cpumask_t *mask); void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); @@ -243,8 +243,8 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr, * Call initialization code, and switch to the full blown * HYP code. */ - kvm_call_hyp((void *)boot_pgd_ptr, pgd_ptr, - hyp_stack_ptr, vector_ptr); + __kvm_call_hyp((void *)boot_pgd_ptr, pgd_ptr, + hyp_stack_ptr, vector_ptr); } static inline void kvm_arch_hardware_disable(void) {} @@ -258,4 +258,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); +#define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__) + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index 3de42d68611d..23acc00be32d 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -26,6 +26,7 @@ __asm__(".arch_extension lse"); /* Macro for constructing calls to out-of-line ll/sc atomics */ #define __LL_SC_CALL(op) "bl\t" __stringify(__LL_SC_PREFIX(op)) "\n" +#define __LL_SC_CLOBBERS "x16", "x17", "x30" /* In-line patching at runtime */ #define ARM64_LSE_ATOMIC_INSN(llsc, lse) \ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 853953cd1f08..12f8a00fb3f1 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -24,6 +24,7 @@ #include <linux/compiler.h> #include <linux/const.h> #include <linux/types.h> +#include <asm/bug.h> #include <asm/sizes.h> /* @@ -45,15 +46,15 @@ * VA_START - the first kernel virtual address. * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. - * The module space lives between the addresses given by TASK_SIZE - * and PAGE_OFFSET - it must be within 128MB of the kernel text. */ #define VA_BITS (CONFIG_ARM64_VA_BITS) #define VA_START (UL(0xffffffffffffffff) << VA_BITS) #define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1)) -#define MODULES_END (PAGE_OFFSET) -#define MODULES_VADDR (MODULES_END - SZ_64M) -#define PCI_IO_END (MODULES_VADDR - SZ_2M) +#define KIMAGE_VADDR (MODULES_END) +#define MODULES_END (MODULES_VADDR + MODULES_VSIZE) +#define MODULES_VADDR (VA_START + KASAN_SHADOW_SIZE) +#define MODULES_VSIZE (SZ_128M) +#define PCI_IO_END (PAGE_OFFSET - SZ_2M) #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) #define FIXADDR_TOP (PCI_IO_START - SZ_2M) #define TASK_SIZE_64 (UL(1) << VA_BITS) @@ -71,12 +72,27 @@ #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4)) /* + * The size of the KASAN shadow region. This should be 1/8th of the + * size of the entire kernel virtual address space. + */ +#ifdef CONFIG_KASAN +#define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - 3)) +#else +#define KASAN_SHADOW_SIZE (0) +#endif + +/* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. */ -#define __virt_to_phys(x) (((phys_addr_t)(x) - PAGE_OFFSET + PHYS_OFFSET)) -#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET + PAGE_OFFSET)) +#define __virt_to_phys(x) ({ \ + phys_addr_t __x = (phys_addr_t)(x); \ + __x & BIT(VA_BITS - 1) ? (__x & ~PAGE_OFFSET) + PHYS_OFFSET : \ + (__x - kimage_voffset); }) + +#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) +#define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* * Convert a page to/from a physical address @@ -100,19 +116,40 @@ #define MT_S2_NORMAL 0xf #define MT_S2_DEVICE_nGnRE 0x1 +#ifdef CONFIG_ARM64_4K_PAGES +#define IOREMAP_MAX_ORDER (PUD_SHIFT) +#else +#define IOREMAP_MAX_ORDER (PMD_SHIFT) +#endif + +#ifdef CONFIG_BLK_DEV_INITRD +#define __early_init_dt_declare_initrd(__start, __end) \ + do { \ + initrd_start = (__start); \ + initrd_end = (__end); \ + } while (0) +#endif + #ifndef __ASSEMBLY__ -extern phys_addr_t memstart_addr; +#include <linux/bitops.h> +#include <linux/mmdebug.h> + +extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ -#define PHYS_OFFSET ({ memstart_addr; }) +#define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) + +/* the virtual base of the kernel image (minus TEXT_OFFSET) */ +extern u64 kimage_vaddr; + +/* the offset between the kernel virtual and physical mappings */ +extern u64 kimage_voffset; /* - * The maximum physical address that the linear direct mapping - * of system RAM can cover. (PAGE_OFFSET can be interpreted as - * a 2's complement signed quantity and negated to derive the - * maximum size of the linear mapping.) + * Allow all memory at the discovery stage. We will clip it later. */ -#define MAX_MEMBLOCK_ADDR ({ memstart_addr - PAGE_OFFSET - 1; }) +#define MIN_MEMBLOCK_ADDR 0 +#define MAX_MEMBLOCK_ADDR U64_MAX /* * PFNs are used to describe any physical page; this means diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 24165784b803..a00f7cf35bbd 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -27,6 +27,7 @@ #include <asm-generic/mm_hooks.h> #include <asm/cputype.h> #include <asm/pgtable.h> +#include <asm/tlbflush.h> #ifdef CONFIG_PID_IN_CONTEXTIDR static inline void contextidr_thread_switch(struct task_struct *next) @@ -48,7 +49,7 @@ static inline void contextidr_thread_switch(struct task_struct *next) */ static inline void cpu_set_reserved_ttbr0(void) { - unsigned long ttbr = page_to_phys(empty_zero_page); + unsigned long ttbr = virt_to_phys(empty_zero_page); asm( " msr ttbr0_el1, %0 // set TTBR0\n" @@ -73,7 +74,7 @@ static inline bool __cpu_uses_extended_idmap(void) /* * Set TCR.T0SZ to its default value (based on VA_BITS) */ -static inline void cpu_set_default_tcr_t0sz(void) +static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) { unsigned long tcr; @@ -86,7 +87,62 @@ static inline void cpu_set_default_tcr_t0sz(void) " msr tcr_el1, %0 ;" " isb" : "=&r" (tcr) - : "r"(TCR_T0SZ(VA_BITS)), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH)); + : "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH)); +} + +#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS)) +#define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) + +/* + * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm. + * + * The idmap lives in the same VA range as userspace, but uses global entries + * and may use a different TCR_EL1.T0SZ. To avoid issues resulting from + * speculative TLB fetches, we must temporarily install the reserved page + * tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ. + * + * If current is a not a user task, the mm covers the TTBR1_EL1 page tables, + * which should not be installed in TTBR0_EL1. In this case we can leave the + * reserved page tables in place. + */ +static inline void cpu_uninstall_idmap(void) +{ + struct mm_struct *mm = current->active_mm; + + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + cpu_set_default_tcr_t0sz(); + + if (mm != &init_mm) + cpu_switch_mm(mm->pgd, mm); +} + +static inline void cpu_install_idmap(void) +{ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + cpu_set_idmap_tcr_t0sz(); + + cpu_switch_mm(idmap_pg_dir, &init_mm); +} + +/* + * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, + * avoiding the possibility of conflicting TLB entries being allocated. + */ +static inline void cpu_replace_ttbr1(pgd_t *pgd) +{ + typedef void (ttbr_replace_func)(phys_addr_t); + extern ttbr_replace_func idmap_cpu_replace_ttbr1; + ttbr_replace_func *replace_phys; + + phys_addr_t pgd_phys = virt_to_phys(pgd); + + replace_phys = (void *)virt_to_phys(idmap_cpu_replace_ttbr1); + + cpu_install_idmap(); + replace_phys(pgd_phys); + cpu_uninstall_idmap(); } /* diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index e80e232b730e..e12af6754634 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -20,4 +20,21 @@ #define MODULE_ARCH_VERMAGIC "aarch64" +#ifdef CONFIG_ARM64_MODULE_PLTS +struct mod_arch_specific { + struct elf64_shdr *plt; + int plt_num_entries; + int plt_max_entries; +}; +#endif + +u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela, + Elf64_Sym *sym); + +#ifdef CONFIG_RANDOMIZE_BASE +extern u64 module_alloc_base; +#else +#define module_alloc_base ((u64)_etext - MODULES_VSIZE) +#endif + #endif /* __ASM_MODULE_H */ diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index c15053902942..ff98585d085a 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -42,11 +42,20 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) free_page((unsigned long)pmd); } -static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) { - set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE)); + set_pud(pud, __pud(pmd | prot)); } +static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + __pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE); +} +#else +static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +{ + BUILD_BUG(); +} #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 @@ -62,11 +71,20 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) free_page((unsigned long)pud); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) { - set_pgd(pgd, __pgd(__pa(pud) | PUD_TYPE_TABLE)); + set_pgd(pgdp, __pgd(pud | prot)); } +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +{ + __pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE); +} +#else +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +{ + BUILD_BUG(); +} #endif /* CONFIG_PGTABLE_LEVELS > 3 */ extern pgd_t *pgd_alloc(struct mm_struct *mm); diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d6739e836f7b..5c25b831273d 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -90,7 +90,23 @@ /* * Contiguous page definitions. */ -#define CONT_PTES (_AC(1, UL) << CONT_SHIFT) +#ifdef CONFIG_ARM64_64K_PAGES +#define CONT_PTE_SHIFT 5 +#define CONT_PMD_SHIFT 5 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define CONT_PTE_SHIFT 7 +#define CONT_PMD_SHIFT 5 +#else +#define CONT_PTE_SHIFT 4 +#define CONT_PMD_SHIFT 4 +#endif + +#define CONT_PTES (1 << CONT_PTE_SHIFT) +#define CONT_PTE_SIZE (CONT_PTES * PAGE_SIZE) +#define CONT_PTE_MASK (~(CONT_PTE_SIZE - 1)) +#define CONT_PMDS (1 << CONT_PMD_SHIFT) +#define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE) +#define CONT_PMD_MASK (~(CONT_PMD_SIZE - 1)) /* the the numerical offset of the PTE within a range of CONT_PTES */ #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1)) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index c63868ae9a4a..c3c2518eecfe 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -36,19 +36,13 @@ * * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). - * VMALLOC_START: beginning of the kernel VA space + * VMALLOC_START: beginning of the kernel vmalloc space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ #define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) -#ifndef CONFIG_KASAN -#define VMALLOC_START (VA_START) -#else -#include <asm/kasan.h> -#define VMALLOC_START (KASAN_SHADOW_END + SZ_64K) -#endif - +#define VMALLOC_START (MODULES_END) #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define VMEMMAP_START (VMALLOC_END + SZ_64K) @@ -59,6 +53,7 @@ #ifndef __ASSEMBLY__ +#include <asm/fixmap.h> #include <linux/mmdebug.h> extern void __pte_error(const char *file, int line, unsigned long val); @@ -123,8 +118,8 @@ extern void __pgd_error(const char *file, int line, unsigned long val); * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern struct page *empty_zero_page; -#define ZERO_PAGE(vaddr) (empty_zero_page) +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; +#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page) #define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte)) @@ -136,16 +131,6 @@ extern struct page *empty_zero_page; #define pte_clear(mm,addr,ptep) set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) -/* Find an entry in the third-level page table. */ -#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) - -#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + pte_index(addr)) - -#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) -#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr)) -#define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) - /* * The following only work if pte_present(). Undefined behaviour otherwise. */ @@ -168,6 +153,16 @@ extern struct page *empty_zero_page; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) +#define pte_valid_young(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) + +/* + * Could the pte be present in the TLB? We must check mm_tlb_flush_pending + * so that we don't erroneously return false for pages that have been + * remapped as PROT_NONE but are yet to be flushed from the TLB. + */ +#define pte_accessible(mm, pte) \ + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { @@ -218,7 +213,8 @@ static inline pte_t pte_mkspecial(pte_t pte) static inline pte_t pte_mkcont(pte_t pte) { - return set_pte_bit(pte, __pgprot(PTE_CONT)); + pte = set_pte_bit(pte, __pgprot(PTE_CONT)); + return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); } static inline pte_t pte_mknoncont(pte_t pte) @@ -226,6 +222,11 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } +static inline pmd_t pmd_mkcont(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | PMD_SECT_CONT); +} + static inline void set_pte(pte_t *ptep, pte_t pte) { *ptep = pte; @@ -299,7 +300,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, /* * Hugetlb definitions. */ -#define HUGE_MAX_HSTATE 2 +#define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) @@ -353,6 +354,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK)) @@ -425,13 +427,31 @@ static inline void pmd_clear(pmd_t *pmdp) set_pmd(pmdp, __pmd(0)); } -static inline pte_t *pmd_page_vaddr(pmd_t pmd) +static inline phys_addr_t pmd_page_paddr(pmd_t pmd) { - return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK); + return pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK; } +/* Find an entry in the third-level page table. */ +#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + +#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t)) +#define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr)))) + +#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) +#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr)) +#define pte_unmap(pte) do { } while (0) +#define pte_unmap_nested(pte) do { } while (0) + +#define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr)) +#define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr)) +#define pte_clear_fixmap() clear_fixmap(FIX_PTE) + #define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) +/* use ONLY for statically allocated translation tables */ +#define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr)))) + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. @@ -458,21 +478,37 @@ static inline void pud_clear(pud_t *pudp) set_pud(pudp, __pud(0)); } -static inline pmd_t *pud_page_vaddr(pud_t pud) +static inline phys_addr_t pud_page_paddr(pud_t pud) { - return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK); + return pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK; } /* Find an entry in the second-level page table. */ #define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) -{ - return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr); -} +#define pmd_offset_phys(dir, addr) (pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t)) +#define pmd_offset(dir, addr) ((pmd_t *)__va(pmd_offset_phys((dir), (addr)))) + +#define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) +#define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr)) +#define pmd_clear_fixmap() clear_fixmap(FIX_PMD) #define pud_page(pud) pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK)) +/* use ONLY for statically allocated translation tables */ +#define pmd_offset_kimg(dir,addr) ((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr)))) + +#else + +#define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) + +/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ +#define pmd_set_fixmap(addr) NULL +#define pmd_set_fixmap_offset(pudp, addr) ((pmd_t *)pudp) +#define pmd_clear_fixmap() + +#define pmd_offset_kimg(dir,addr) ((pmd_t *)dir) + #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 @@ -494,21 +530,37 @@ static inline void pgd_clear(pgd_t *pgdp) set_pgd(pgdp, __pgd(0)); } -static inline pud_t *pgd_page_vaddr(pgd_t pgd) +static inline phys_addr_t pgd_page_paddr(pgd_t pgd) { - return __va(pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK); + return pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK; } /* Find an entry in the frst-level page table. */ #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) -{ - return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(addr); -} +#define pud_offset_phys(dir, addr) (pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t)) +#define pud_offset(dir, addr) ((pud_t *)__va(pud_offset_phys((dir), (addr)))) + +#define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) +#define pud_set_fixmap_offset(pgd, addr) pud_set_fixmap(pud_offset_phys(pgd, addr)) +#define pud_clear_fixmap() clear_fixmap(FIX_PUD) #define pgd_page(pgd) pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK)) +/* use ONLY for statically allocated translation tables */ +#define pud_offset_kimg(dir,addr) ((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr)))) + +#else + +#define pgd_page_paddr(pgd) ({ BUILD_BUG(); 0;}) + +/* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ +#define pud_set_fixmap(addr) NULL +#define pud_set_fixmap_offset(pgdp, addr) ((pud_t *)pgdp) +#define pud_clear_fixmap() + +#define pud_offset_kimg(dir,addr) ((pud_t *)dir) + #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd)) @@ -516,11 +568,16 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) /* to find an entry in a page-table-directory */ #define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) -#define pgd_offset(mm, addr) ((mm)->pgd+pgd_index(addr)) +#define pgd_offset_raw(pgd, addr) ((pgd) + pgd_index(addr)) + +#define pgd_offset(mm, addr) (pgd_offset_raw((mm)->pgd, (addr))) /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) +#define pgd_set_fixmap(addr) ((pgd_t *)set_fixmap_offset(FIX_PGD, addr)) +#define pgd_clear_fixmap() clear_fixmap(FIX_PGD) + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | @@ -666,7 +723,8 @@ extern int kern_addr_valid(unsigned long addr); #include <asm-generic/pgtable.h> -#define pgtable_cache_init() do { } while (0) +void pgd_cache_init(void); +#define pgtable_cache_init pgd_cache_init /* * On AArch64, the cache coherency is handled via the set_pte_at() function. diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 4acb7ca94fcd..cef1cf398356 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -29,8 +29,10 @@ #include <linux/string.h> +#include <asm/alternative.h> #include <asm/fpsimd.h> #include <asm/hw_breakpoint.h> +#include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> #include <asm/types.h> @@ -177,9 +179,11 @@ static inline void prefetchw(const void *ptr) } #define ARCH_HAS_SPINLOCK_PREFETCH -static inline void spin_lock_prefetch(const void *x) +static inline void spin_lock_prefetch(const void *ptr) { - prefetchw(x); + asm volatile(ARM64_LSE_ATOMIC_INSN( + "prfm pstl1strm, %a0", + "nop") : : "p" (ptr)); } #define HAVE_ARCH_PICK_MMAP_LAYOUT @@ -187,5 +191,6 @@ static inline void spin_lock_prefetch(const void *x) #endif void cpu_enable_pan(void *__unused); +void cpu_enable_uao(void *__unused); #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/shmparam.h b/arch/arm64/include/asm/shmparam.h index 4df608a8459e..e368a55ebd22 100644 --- a/arch/arm64/include/asm/shmparam.h +++ b/arch/arm64/include/asm/shmparam.h @@ -21,7 +21,7 @@ * alignment value. Since we don't have aliasing D-caches, the rest of * the time we can safely use PAGE_SIZE. */ -#define COMPAT_SHMLBA 0x4000 +#define COMPAT_SHMLBA (4 * PAGE_SIZE) #include <asm-generic/shmparam.h> diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index d9c3d6a6100a..2013a4dc5124 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -64,6 +64,15 @@ extern void secondary_entry(void); extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL +extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask); +#else +static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask) +{ + BUILD_BUG(); +} +#endif + extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index c85e96d174a5..fc9682bfe002 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -26,9 +26,28 @@ * The memory barriers are implicit with the load-acquire and store-release * instructions. */ +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + unsigned int tmp; + arch_spinlock_t lockval; -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + asm volatile( +" sevl\n" +"1: wfe\n" +"2: ldaxr %w0, %2\n" +" eor %w1, %w0, %w0, ror #16\n" +" cbnz %w1, 1b\n" + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ +" stxr %w1, %w0, %2\n" +" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */ + /* LSE atomics */ +" nop\n" +" nop\n") + : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) + : + : "memory"); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 7318f6d54aa9..801a16dbbdf6 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -16,14 +16,19 @@ #ifndef __ASM_STACKTRACE_H #define __ASM_STACKTRACE_H +struct task_struct; + struct stackframe { unsigned long fp; unsigned long sp; unsigned long pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + unsigned int graph; +#endif }; -extern int unwind_frame(struct stackframe *frame); -extern void walk_stackframe(struct stackframe *frame, +extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); +extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index d48ab5b41f52..b9fd8ec79033 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -70,15 +70,19 @@ #define SYS_ID_AA64MMFR0_EL1 sys_reg(3, 0, 0, 7, 0) #define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1) +#define SYS_ID_AA64MMFR2_EL1 sys_reg(3, 0, 0, 7, 2) #define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0) #define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) #define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7) #define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4) +#define REG_PSTATE_UAO_IMM sys_reg(0, 0, 4, 0, 3) #define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\ (!!x)<<8 | 0x1f) +#define SET_PSTATE_UAO(x) __inst_arm(0xd5000000 | REG_PSTATE_UAO_IMM |\ + (!!x)<<8 | 0x1f) /* SCTLR_EL1 */ #define SCTLR_EL1_CP15BEN (0x1 << 5) @@ -135,6 +139,9 @@ #define ID_AA64MMFR1_VMIDBITS_SHIFT 4 #define ID_AA64MMFR1_HADBS_SHIFT 0 +/* id_aa64mmfr2 */ +#define ID_AA64MMFR2_UAO_SHIFT 4 + /* id_aa64dfr0 */ #define ID_AA64DFR0_CTX_CMPS_SHIFT 28 #define ID_AA64DFR0_WRPS_SHIFT 20 @@ -194,32 +201,32 @@ #ifdef __ASSEMBLY__ .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30 - .equ __reg_num_x\num, \num + .equ .L__reg_num_x\num, \num .endr - .equ __reg_num_xzr, 31 + .equ .L__reg_num_xzr, 31 .macro mrs_s, rt, sreg - .inst 0xd5200000|(\sreg)|(__reg_num_\rt) + .inst 0xd5200000|(\sreg)|(.L__reg_num_\rt) .endm .macro msr_s, sreg, rt - .inst 0xd5000000|(\sreg)|(__reg_num_\rt) + .inst 0xd5000000|(\sreg)|(.L__reg_num_\rt) .endm #else asm( " .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" -" .equ __reg_num_x\\num, \\num\n" +" .equ .L__reg_num_x\\num, \\num\n" " .endr\n" -" .equ __reg_num_xzr, 31\n" +" .equ .L__reg_num_xzr, 31\n" "\n" " .macro mrs_s, rt, sreg\n" -" .inst 0xd5200000|(\\sreg)|(__reg_num_\\rt)\n" +" .inst 0xd5200000|(\\sreg)|(.L__reg_num_\\rt)\n" " .endm\n" "\n" " .macro msr_s, sreg, rt\n" -" .inst 0xd5000000|(\\sreg)|(__reg_num_\\rt)\n" +" .inst 0xd5000000|(\\sreg)|(.L__reg_num_\\rt)\n" " .endm\n" ); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 90c7ff233735..abd64bd1f6d9 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -73,10 +73,16 @@ register unsigned long current_stack_pointer asm ("sp"); */ static inline struct thread_info *current_thread_info(void) __attribute_const__; +/* + * struct thread_info can be accessed directly via sp_el0. + */ static inline struct thread_info *current_thread_info(void) { - return (struct thread_info *) - (current_stack_pointer & ~(THREAD_SIZE - 1)); + unsigned long sp_el0; + + asm ("mrs %0, sp_el0" : "=r" (sp_el0)); + + return (struct thread_info *)sp_el0; } #define thread_saved_pc(tsk) \ diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index b2ede967fe7d..0685d74572af 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -36,11 +36,11 @@ #define VERIFY_WRITE 1 /* - * The exception table consists of pairs of addresses: the first is the - * address of an instruction that is allowed to fault, and the second is - * the address at which the program should continue. No registers are - * modified, so it is entirely up to the continuation code to figure out - * what to do. + * The exception table consists of pairs of relative offsets: the first + * is the relative offset to an instruction that is allowed to fault, + * and the second is the relative offset at which the program should + * continue. No registers are modified, so it is entirely up to the + * continuation code to figure out what to do. * * All the routines below use bits of fixup code that are out of line * with the main instruction path. This means when everything is well, @@ -50,9 +50,11 @@ struct exception_table_entry { - unsigned long insn, fixup; + int insn, fixup; }; +#define ARCH_HAS_RELATIVE_EXTABLE + extern int fixup_exception(struct pt_regs *regs); #define KERNEL_DS (-1UL) @@ -64,6 +66,16 @@ extern int fixup_exception(struct pt_regs *regs); static inline void set_fs(mm_segment_t fs) { current_thread_info()->addr_limit = fs; + + /* + * Enable/disable UAO so that copy_to_user() etc can access + * kernel memory with the unprivileged instructions. + */ + if (IS_ENABLED(CONFIG_ARM64_UAO) && fs == KERNEL_DS) + asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO)); + else + asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO, + CONFIG_ARM64_UAO)); } #define segment_eq(a, b) ((a) == (b)) @@ -105,6 +117,12 @@ static inline void set_fs(mm_segment_t fs) #define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs +#define _ASM_EXTABLE(from, to) \ + " .pushsection __ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + /* * The "__xxx" versions of the user access functions do not verify the address * space - it must have been done previously with a separate "access_ok()" @@ -113,9 +131,10 @@ static inline void set_fs(mm_segment_t fs) * The "__xxx_error" versions set the third argument to -EFAULT if an error * occurs, and leave it unchanged on success. */ -#define __get_user_asm(instr, reg, x, addr, err) \ +#define __get_user_asm(instr, alt_instr, reg, x, addr, err, feature) \ asm volatile( \ - "1: " instr " " reg "1, [%2]\n" \ + "1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \ + alt_instr " " reg "1, [%2]\n", feature) \ "2:\n" \ " .section .fixup, \"ax\"\n" \ " .align 2\n" \ @@ -123,10 +142,7 @@ static inline void set_fs(mm_segment_t fs) " mov %1, #0\n" \ " b 2b\n" \ " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .quad 1b, 3b\n" \ - " .previous" \ + _ASM_EXTABLE(1b, 3b) \ : "+r" (err), "=&r" (x) \ : "r" (addr), "i" (-EFAULT)) @@ -134,26 +150,30 @@ static inline void set_fs(mm_segment_t fs) do { \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ - asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\ CONFIG_ARM64_PAN)); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm("ldrb", "%w", __gu_val, (ptr), (err)); \ + __get_user_asm("ldrb", "ldtrb", "%w", __gu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ case 2: \ - __get_user_asm("ldrh", "%w", __gu_val, (ptr), (err)); \ + __get_user_asm("ldrh", "ldtrh", "%w", __gu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ case 4: \ - __get_user_asm("ldr", "%w", __gu_val, (ptr), (err)); \ + __get_user_asm("ldr", "ldtr", "%w", __gu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ case 8: \ - __get_user_asm("ldr", "%", __gu_val, (ptr), (err)); \ + __get_user_asm("ldr", "ldtr", "%", __gu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ default: \ BUILD_BUG(); \ } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ - asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\ CONFIG_ARM64_PAN)); \ } while (0) @@ -181,19 +201,17 @@ do { \ ((x) = 0, -EFAULT); \ }) -#define __put_user_asm(instr, reg, x, addr, err) \ +#define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature) \ asm volatile( \ - "1: " instr " " reg "1, [%2]\n" \ + "1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \ + alt_instr " " reg "1, [%2]\n", feature) \ "2:\n" \ " .section .fixup,\"ax\"\n" \ " .align 2\n" \ "3: mov %w0, %3\n" \ " b 2b\n" \ " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .quad 1b, 3b\n" \ - " .previous" \ + _ASM_EXTABLE(1b, 3b) \ : "+r" (err) \ : "r" (x), "r" (addr), "i" (-EFAULT)) @@ -201,25 +219,29 @@ do { \ do { \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ - asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\ CONFIG_ARM64_PAN)); \ switch (sizeof(*(ptr))) { \ case 1: \ - __put_user_asm("strb", "%w", __pu_val, (ptr), (err)); \ + __put_user_asm("strb", "sttrb", "%w", __pu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ case 2: \ - __put_user_asm("strh", "%w", __pu_val, (ptr), (err)); \ + __put_user_asm("strh", "sttrh", "%w", __pu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ case 4: \ - __put_user_asm("str", "%w", __pu_val, (ptr), (err)); \ + __put_user_asm("str", "sttr", "%w", __pu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ case 8: \ - __put_user_asm("str", "%", __pu_val, (ptr), (err)); \ + __put_user_asm("str", "sttr", "%", __pu_val, (ptr), \ + (err), ARM64_HAS_UAO); \ break; \ default: \ BUILD_BUG(); \ } \ - asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\ CONFIG_ARM64_PAN)); \ } while (0) diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h index aab5bf09e9d9..2b79b8a89457 100644 --- a/arch/arm64/include/asm/word-at-a-time.h +++ b/arch/arm64/include/asm/word-at-a-time.h @@ -16,6 +16,8 @@ #ifndef __ASM_WORD_AT_A_TIME_H #define __ASM_WORD_AT_A_TIME_H +#include <asm/uaccess.h> + #ifndef __AARCH64EB__ #include <linux/kernel.h> @@ -81,10 +83,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) #endif " b 2b\n" " .popsection\n" - " .pushsection __ex_table,\"a\"\n" - " .align 3\n" - " .quad 1b, 3b\n" - " .popsection" + _ASM_EXTABLE(1b, 3b) : "=&r" (ret), "=&r" (offset) : "r" (addr), "Q" (*(unsigned long *)addr)); diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 208db3df135a..b5c3933ed441 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -45,6 +45,7 @@ #define PSR_A_BIT 0x00000100 #define PSR_D_BIT 0x00000200 #define PSR_PAN_BIT 0x00400000 +#define PSR_UAO_BIT 0x00800000 #define PSR_Q_BIT 0x08000000 #define PSR_V_BIT 0x10000000 #define PSR_C_BIT 0x20000000 diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 474691f8b13a..49a2430b0786 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -30,6 +30,7 @@ arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ ../../arm/kernel/opcodes.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o +arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o @@ -41,6 +42,8 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o arm64-obj-$(CONFIG_PCI) += pci.o arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o arm64-obj-$(CONFIG_ACPI) += acpi.o +arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o +arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c new file mode 100644 index 000000000000..4b1e5a7a98da --- /dev/null +++ b/arch/arm64/kernel/acpi_parking_protocol.c @@ -0,0 +1,153 @@ +/* + * ARM64 ACPI Parking Protocol implementation + * + * Authors: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#include <linux/acpi.h> +#include <linux/types.h> + +#include <asm/cpu_ops.h> + +struct cpu_mailbox_entry { + phys_addr_t mailbox_addr; + u8 version; + u8 gic_cpu_id; +}; + +static struct cpu_mailbox_entry cpu_mailbox_entries[NR_CPUS]; + +void __init acpi_set_mailbox_entry(int cpu, + struct acpi_madt_generic_interrupt *p) +{ + struct cpu_mailbox_entry *cpu_entry = &cpu_mailbox_entries[cpu]; + + cpu_entry->mailbox_addr = p->parked_address; + cpu_entry->version = p->parking_version; + cpu_entry->gic_cpu_id = p->cpu_interface_number; +} + +bool acpi_parking_protocol_valid(int cpu) +{ + struct cpu_mailbox_entry *cpu_entry = &cpu_mailbox_entries[cpu]; + + return cpu_entry->mailbox_addr && cpu_entry->version; +} + +static int acpi_parking_protocol_cpu_init(unsigned int cpu) +{ + pr_debug("%s: ACPI parked addr=%llx\n", __func__, + cpu_mailbox_entries[cpu].mailbox_addr); + + return 0; +} + +static int acpi_parking_protocol_cpu_prepare(unsigned int cpu) +{ + return 0; +} + +struct parking_protocol_mailbox { + __le32 cpu_id; + __le32 reserved; + __le64 entry_point; +}; + +static int acpi_parking_protocol_cpu_boot(unsigned int cpu) +{ + struct cpu_mailbox_entry *cpu_entry = &cpu_mailbox_entries[cpu]; + struct parking_protocol_mailbox __iomem *mailbox; + __le32 cpu_id; + + /* + * Map mailbox memory with attribute device nGnRE (ie ioremap - + * this deviates from the parking protocol specifications since + * the mailboxes are required to be mapped nGnRnE; the attribute + * discrepancy is harmless insofar as the protocol specification + * is concerned). + * If the mailbox is mistakenly allocated in the linear mapping + * by FW ioremap will fail since the mapping will be prevented + * by the kernel (it clashes with the linear mapping attributes + * specifications). + */ + mailbox = ioremap(cpu_entry->mailbox_addr, sizeof(*mailbox)); + if (!mailbox) + return -EIO; + + cpu_id = readl_relaxed(&mailbox->cpu_id); + /* + * Check if firmware has set-up the mailbox entry properly + * before kickstarting the respective cpu. + */ + if (cpu_id != ~0U) { + iounmap(mailbox); + return -ENXIO; + } + + /* + * We write the entry point and cpu id as LE regardless of the + * native endianness of the kernel. Therefore, any boot-loaders + * that read this address need to convert this address to the + * Boot-Loader's endianness before jumping. + */ + writeq_relaxed(__pa(secondary_entry), &mailbox->entry_point); + writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id); + + arch_send_wakeup_ipi_mask(cpumask_of(cpu)); + + iounmap(mailbox); + + return 0; +} + +static void acpi_parking_protocol_cpu_postboot(void) +{ + int cpu = smp_processor_id(); + struct cpu_mailbox_entry *cpu_entry = &cpu_mailbox_entries[cpu]; + struct parking_protocol_mailbox __iomem *mailbox; + __le64 entry_point; + + /* + * Map mailbox memory with attribute device nGnRE (ie ioremap - + * this deviates from the parking protocol specifications since + * the mailboxes are required to be mapped nGnRnE; the attribute + * discrepancy is harmless insofar as the protocol specification + * is concerned). + * If the mailbox is mistakenly allocated in the linear mapping + * by FW ioremap will fail since the mapping will be prevented + * by the kernel (it clashes with the linear mapping attributes + * specifications). + */ + mailbox = ioremap(cpu_entry->mailbox_addr, sizeof(*mailbox)); + if (!mailbox) + return; + + entry_point = readl_relaxed(&mailbox->entry_point); + /* + * Check if firmware has cleared the entry_point as expected + * by the protocol specification. + */ + WARN_ON(entry_point); + + iounmap(mailbox); +} + +const struct cpu_operations acpi_parking_protocol_ops = { + .name = "parking-protocol", + .cpu_init = acpi_parking_protocol_cpu_init, + .cpu_prepare = acpi_parking_protocol_cpu_prepare, + .cpu_boot = acpi_parking_protocol_cpu_boot, + .cpu_postboot = acpi_parking_protocol_cpu_postboot +}; diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index ab9db0e9818c..d2ee1b21a10d 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -158,9 +158,3 @@ void apply_alternatives(void *start, size_t length) __apply_alternatives(®ion); } - -void free_alternatives_memory(void) -{ - free_reserved_area(__alt_instructions, __alt_instructions_end, - 0, "alternatives"); -} diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 937f5e58a4d3..c37202c0c838 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -62,7 +62,7 @@ struct insn_emulation { }; static LIST_HEAD(insn_emulation); -static int nr_insn_emulated; +static int nr_insn_emulated __initdata; static DEFINE_RAW_SPINLOCK(insn_emulation_lock); static void register_emulation_hooks(struct insn_emulation_ops *ops) @@ -173,7 +173,7 @@ static int update_insn_emulation_mode(struct insn_emulation *insn, return ret; } -static void register_insn_emulation(struct insn_emulation_ops *ops) +static void __init register_insn_emulation(struct insn_emulation_ops *ops) { unsigned long flags; struct insn_emulation *insn; @@ -237,7 +237,7 @@ static struct ctl_table ctl_abi[] = { { } }; -static void register_insn_emulation_sysctl(struct ctl_table *table) +static void __init register_insn_emulation_sysctl(struct ctl_table *table) { unsigned long flags; int i = 0; @@ -297,11 +297,8 @@ static void register_insn_emulation_sysctl(struct ctl_table *table) "4: mov %w0, %w5\n" \ " b 3b\n" \ " .popsection" \ - " .pushsection __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .quad 0b, 4b\n" \ - " .quad 1b, 4b\n" \ - " .popsection\n" \ + _ASM_EXTABLE(0b, 4b) \ + _ASM_EXTABLE(1b, 4b) \ ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ : "=&r" (res), "+r" (data), "=&r" (temp) \ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index feb6b4efa641..e6bc988e8dbf 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -21,24 +21,12 @@ #include <asm/cputype.h> #include <asm/cpufeature.h> -#define MIDR_CORTEX_A53 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) -#define MIDR_CORTEX_A57 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) -#define MIDR_THUNDERX MIDR_CPU_PART(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) - -#define CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ - MIDR_ARCHITECTURE_MASK) - static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry) { - u32 midr = read_cpuid_id(); - - if ((midr & CPU_MODEL_MASK) != entry->midr_model) - return false; - - midr &= MIDR_REVISION_MASK | MIDR_VARIANT_MASK; - - return (midr >= entry->midr_range_min && midr <= entry->midr_range_max); + return MIDR_IS_CPU_MODEL_RANGE(read_cpuid_id(), entry->midr_model, + entry->midr_range_min, + entry->midr_range_max); } #define MIDR_RANGE(model, min, max) \ diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c index b6bd7d447768..c7cfb8fe06f9 100644 --- a/arch/arm64/kernel/cpu_ops.c +++ b/arch/arm64/kernel/cpu_ops.c @@ -25,19 +25,30 @@ #include <asm/smp_plat.h> extern const struct cpu_operations smp_spin_table_ops; +extern const struct cpu_operations acpi_parking_protocol_ops; extern const struct cpu_operations cpu_psci_ops; const struct cpu_operations *cpu_ops[NR_CPUS]; -static const struct cpu_operations *supported_cpu_ops[] __initconst = { +static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = { &smp_spin_table_ops, &cpu_psci_ops, NULL, }; +static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = { +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL + &acpi_parking_protocol_ops, +#endif + &cpu_psci_ops, + NULL, +}; + static const struct cpu_operations * __init cpu_get_ops(const char *name) { - const struct cpu_operations **ops = supported_cpu_ops; + const struct cpu_operations **ops; + + ops = acpi_disabled ? dt_supported_cpu_ops : acpi_supported_cpu_ops; while (*ops) { if (!strcmp(name, (*ops)->name)) @@ -75,8 +86,16 @@ static const char *__init cpu_read_enable_method(int cpu) } } else { enable_method = acpi_get_enable_method(cpu); - if (!enable_method) - pr_err("Unsupported ACPI enable-method\n"); + if (!enable_method) { + /* + * In ACPI systems the boot CPU does not require + * checking the enable method since for some + * boot protocol (ie parking protocol) it need not + * be initialized. Don't warn spuriously. + */ + if (cpu != 0) + pr_err("Unsupported ACPI enable-method\n"); + } } return enable_method; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0669c63281ea..7566cad9fa1d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -67,6 +67,10 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); .width = 0, \ } +/* meta feature for alternatives */ +static bool __maybe_unused +cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry); + static struct arm64_ftr_bits ftr_id_aa64isar0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), @@ -123,6 +127,11 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { ARM64_FTR_END, }; +static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static struct arm64_ftr_bits ftr_ctr[] = { U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0), @@ -284,6 +293,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = { /* Op1 = 0, CRn = 0, CRm = 7 */ ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1), + ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), /* Op1 = 3, CRn = 0, CRm = 0 */ ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr), @@ -408,6 +418,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1); init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); + init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2); init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0); @@ -517,6 +528,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64mmfr0, boot->reg_id_aa64mmfr0); taint |= check_update_ftr_reg(SYS_ID_AA64MMFR1_EL1, cpu, info->reg_id_aa64mmfr1, boot->reg_id_aa64mmfr1); + taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, + info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); /* * EL3 is not our concern. @@ -621,6 +634,18 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry) return has_sre; } +static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry) +{ + u32 midr = read_cpuid_id(); + u32 rv_min, rv_max; + + /* Cavium ThunderX pass 1.x and 2.x */ + rv_min = 0; + rv_max = (1 << MIDR_VARIANT_SHIFT) | MIDR_REVISION_MASK; + + return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX, rv_min, rv_max); +} + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -651,6 +676,28 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = 2, }, #endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ + { + .desc = "Software prefetching using PRFM", + .capability = ARM64_HAS_NO_HW_PREFETCH, + .matches = has_no_hw_prefetch, + }, +#ifdef CONFIG_ARM64_UAO + { + .desc = "User Access Override", + .capability = ARM64_HAS_UAO, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64MMFR2_EL1, + .field_pos = ID_AA64MMFR2_UAO_SHIFT, + .min_field_value = 1, + .enable = cpu_enable_uao, + }, +#endif /* CONFIG_ARM64_UAO */ +#ifdef CONFIG_ARM64_PAN + { + .capability = ARM64_ALT_PAN_NOT_UAO, + .matches = cpufeature_pan_not_uao, + }, +#endif /* CONFIG_ARM64_PAN */ {}, }; @@ -684,7 +731,7 @@ static const struct arm64_cpu_capabilities arm64_hwcaps[] = { {}, }; -static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap) +static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap) { switch (cap->hwcap_type) { case CAP_HWCAP: @@ -729,12 +776,12 @@ static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities * return rc; } -static void setup_cpu_hwcaps(void) +static void __init setup_cpu_hwcaps(void) { int i; const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps; - for (i = 0; hwcaps[i].desc; i++) + for (i = 0; hwcaps[i].matches; i++) if (hwcaps[i].matches(&hwcaps[i])) cap_set_hwcap(&hwcaps[i]); } @@ -744,11 +791,11 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, { int i; - for (i = 0; caps[i].desc; i++) { + for (i = 0; caps[i].matches; i++) { if (!caps[i].matches(&caps[i])) continue; - if (!cpus_have_cap(caps[i].capability)) + if (!cpus_have_cap(caps[i].capability) && caps[i].desc) pr_info("%s %s\n", info, caps[i].desc); cpus_set_cap(caps[i].capability); } @@ -758,11 +805,12 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, * Run through the enabled capabilities and enable() it on all active * CPUs */ -static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +static void __init +enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { int i; - for (i = 0; caps[i].desc; i++) + for (i = 0; caps[i].matches; i++) if (caps[i].enable && cpus_have_cap(caps[i].capability)) on_each_cpu(caps[i].enable, NULL, true); } @@ -790,35 +838,36 @@ static inline void set_sys_caps_initialised(void) static u64 __raw_read_system_reg(u32 sys_id) { switch (sys_id) { - case SYS_ID_PFR0_EL1: return (u64)read_cpuid(ID_PFR0_EL1); - case SYS_ID_PFR1_EL1: return (u64)read_cpuid(ID_PFR1_EL1); - case SYS_ID_DFR0_EL1: return (u64)read_cpuid(ID_DFR0_EL1); - case SYS_ID_MMFR0_EL1: return (u64)read_cpuid(ID_MMFR0_EL1); - case SYS_ID_MMFR1_EL1: return (u64)read_cpuid(ID_MMFR1_EL1); - case SYS_ID_MMFR2_EL1: return (u64)read_cpuid(ID_MMFR2_EL1); - case SYS_ID_MMFR3_EL1: return (u64)read_cpuid(ID_MMFR3_EL1); - case SYS_ID_ISAR0_EL1: return (u64)read_cpuid(ID_ISAR0_EL1); - case SYS_ID_ISAR1_EL1: return (u64)read_cpuid(ID_ISAR1_EL1); - case SYS_ID_ISAR2_EL1: return (u64)read_cpuid(ID_ISAR2_EL1); - case SYS_ID_ISAR3_EL1: return (u64)read_cpuid(ID_ISAR3_EL1); - case SYS_ID_ISAR4_EL1: return (u64)read_cpuid(ID_ISAR4_EL1); - case SYS_ID_ISAR5_EL1: return (u64)read_cpuid(ID_ISAR4_EL1); - case SYS_MVFR0_EL1: return (u64)read_cpuid(MVFR0_EL1); - case SYS_MVFR1_EL1: return (u64)read_cpuid(MVFR1_EL1); - case SYS_MVFR2_EL1: return (u64)read_cpuid(MVFR2_EL1); - - case SYS_ID_AA64PFR0_EL1: return (u64)read_cpuid(ID_AA64PFR0_EL1); - case SYS_ID_AA64PFR1_EL1: return (u64)read_cpuid(ID_AA64PFR0_EL1); - case SYS_ID_AA64DFR0_EL1: return (u64)read_cpuid(ID_AA64DFR0_EL1); - case SYS_ID_AA64DFR1_EL1: return (u64)read_cpuid(ID_AA64DFR0_EL1); - case SYS_ID_AA64MMFR0_EL1: return (u64)read_cpuid(ID_AA64MMFR0_EL1); - case SYS_ID_AA64MMFR1_EL1: return (u64)read_cpuid(ID_AA64MMFR1_EL1); - case SYS_ID_AA64ISAR0_EL1: return (u64)read_cpuid(ID_AA64ISAR0_EL1); - case SYS_ID_AA64ISAR1_EL1: return (u64)read_cpuid(ID_AA64ISAR1_EL1); - - case SYS_CNTFRQ_EL0: return (u64)read_cpuid(CNTFRQ_EL0); - case SYS_CTR_EL0: return (u64)read_cpuid(CTR_EL0); - case SYS_DCZID_EL0: return (u64)read_cpuid(DCZID_EL0); + case SYS_ID_PFR0_EL1: return read_cpuid(SYS_ID_PFR0_EL1); + case SYS_ID_PFR1_EL1: return read_cpuid(SYS_ID_PFR1_EL1); + case SYS_ID_DFR0_EL1: return read_cpuid(SYS_ID_DFR0_EL1); + case SYS_ID_MMFR0_EL1: return read_cpuid(SYS_ID_MMFR0_EL1); + case SYS_ID_MMFR1_EL1: return read_cpuid(SYS_ID_MMFR1_EL1); + case SYS_ID_MMFR2_EL1: return read_cpuid(SYS_ID_MMFR2_EL1); + case SYS_ID_MMFR3_EL1: return read_cpuid(SYS_ID_MMFR3_EL1); + case SYS_ID_ISAR0_EL1: return read_cpuid(SYS_ID_ISAR0_EL1); + case SYS_ID_ISAR1_EL1: return read_cpuid(SYS_ID_ISAR1_EL1); + case SYS_ID_ISAR2_EL1: return read_cpuid(SYS_ID_ISAR2_EL1); + case SYS_ID_ISAR3_EL1: return read_cpuid(SYS_ID_ISAR3_EL1); + case SYS_ID_ISAR4_EL1: return read_cpuid(SYS_ID_ISAR4_EL1); + case SYS_ID_ISAR5_EL1: return read_cpuid(SYS_ID_ISAR4_EL1); + case SYS_MVFR0_EL1: return read_cpuid(SYS_MVFR0_EL1); + case SYS_MVFR1_EL1: return read_cpuid(SYS_MVFR1_EL1); + case SYS_MVFR2_EL1: return read_cpuid(SYS_MVFR2_EL1); + + case SYS_ID_AA64PFR0_EL1: return read_cpuid(SYS_ID_AA64PFR0_EL1); + case SYS_ID_AA64PFR1_EL1: return read_cpuid(SYS_ID_AA64PFR0_EL1); + case SYS_ID_AA64DFR0_EL1: return read_cpuid(SYS_ID_AA64DFR0_EL1); + case SYS_ID_AA64DFR1_EL1: return read_cpuid(SYS_ID_AA64DFR0_EL1); + case SYS_ID_AA64MMFR0_EL1: return read_cpuid(SYS_ID_AA64MMFR0_EL1); + case SYS_ID_AA64MMFR1_EL1: return read_cpuid(SYS_ID_AA64MMFR1_EL1); + case SYS_ID_AA64MMFR2_EL1: return read_cpuid(SYS_ID_AA64MMFR2_EL1); + case SYS_ID_AA64ISAR0_EL1: return read_cpuid(SYS_ID_AA64ISAR0_EL1); + case SYS_ID_AA64ISAR1_EL1: return read_cpuid(SYS_ID_AA64ISAR1_EL1); + + case SYS_CNTFRQ_EL0: return read_cpuid(SYS_CNTFRQ_EL0); + case SYS_CTR_EL0: return read_cpuid(SYS_CTR_EL0); + case SYS_DCZID_EL0: return read_cpuid(SYS_DCZID_EL0); default: BUG(); return 0; @@ -868,7 +917,7 @@ void verify_local_cpu_capabilities(void) return; caps = arm64_features; - for (i = 0; caps[i].desc; i++) { + for (i = 0; caps[i].matches; i++) { if (!cpus_have_cap(caps[i].capability) || !caps[i].sys_reg) continue; /* @@ -881,7 +930,7 @@ void verify_local_cpu_capabilities(void) caps[i].enable(NULL); } - for (i = 0, caps = arm64_hwcaps; caps[i].desc; i++) { + for (i = 0, caps = arm64_hwcaps; caps[i].matches; i++) { if (!cpus_have_hwcap(&caps[i])) continue; if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) @@ -897,7 +946,7 @@ static inline void set_sys_caps_initialised(void) #endif /* CONFIG_HOTPLUG_CPU */ -static void setup_feature_capabilities(void) +static void __init setup_feature_capabilities(void) { update_cpu_capabilities(arm64_features, "detected feature:"); enable_cpu_capabilities(arm64_features); @@ -927,3 +976,9 @@ void __init setup_cpu_features(void) pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n", L1_CACHE_BYTES, cls); } + +static bool __maybe_unused +cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry) +{ + return (cpus_have_cap(ARM64_HAS_PAN) && !cpus_have_cap(ARM64_HAS_UAO)); +} diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 212ae6361d8b..966fbd52550b 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -201,35 +201,36 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) { info->reg_cntfrq = arch_timer_get_cntfrq(); info->reg_ctr = read_cpuid_cachetype(); - info->reg_dczid = read_cpuid(DCZID_EL0); + info->reg_dczid = read_cpuid(SYS_DCZID_EL0); info->reg_midr = read_cpuid_id(); - info->reg_id_aa64dfr0 = read_cpuid(ID_AA64DFR0_EL1); - info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1); - info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1); - info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1); - info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); - info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); - info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); - info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); - - info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1); - info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1); - info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1); - info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1); - info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1); - info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1); - info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1); - info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1); - info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1); - info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1); - info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1); - info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1); - info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1); - - info->reg_mvfr0 = read_cpuid(MVFR0_EL1); - info->reg_mvfr1 = read_cpuid(MVFR1_EL1); - info->reg_mvfr2 = read_cpuid(MVFR2_EL1); + info->reg_id_aa64dfr0 = read_cpuid(SYS_ID_AA64DFR0_EL1); + info->reg_id_aa64dfr1 = read_cpuid(SYS_ID_AA64DFR1_EL1); + info->reg_id_aa64isar0 = read_cpuid(SYS_ID_AA64ISAR0_EL1); + info->reg_id_aa64isar1 = read_cpuid(SYS_ID_AA64ISAR1_EL1); + info->reg_id_aa64mmfr0 = read_cpuid(SYS_ID_AA64MMFR0_EL1); + info->reg_id_aa64mmfr1 = read_cpuid(SYS_ID_AA64MMFR1_EL1); + info->reg_id_aa64mmfr2 = read_cpuid(SYS_ID_AA64MMFR2_EL1); + info->reg_id_aa64pfr0 = read_cpuid(SYS_ID_AA64PFR0_EL1); + info->reg_id_aa64pfr1 = read_cpuid(SYS_ID_AA64PFR1_EL1); + + info->reg_id_dfr0 = read_cpuid(SYS_ID_DFR0_EL1); + info->reg_id_isar0 = read_cpuid(SYS_ID_ISAR0_EL1); + info->reg_id_isar1 = read_cpuid(SYS_ID_ISAR1_EL1); + info->reg_id_isar2 = read_cpuid(SYS_ID_ISAR2_EL1); + info->reg_id_isar3 = read_cpuid(SYS_ID_ISAR3_EL1); + info->reg_id_isar4 = read_cpuid(SYS_ID_ISAR4_EL1); + info->reg_id_isar5 = read_cpuid(SYS_ID_ISAR5_EL1); + info->reg_id_mmfr0 = read_cpuid(SYS_ID_MMFR0_EL1); + info->reg_id_mmfr1 = read_cpuid(SYS_ID_MMFR1_EL1); + info->reg_id_mmfr2 = read_cpuid(SYS_ID_MMFR2_EL1); + info->reg_id_mmfr3 = read_cpuid(SYS_ID_MMFR3_EL1); + info->reg_id_pfr0 = read_cpuid(SYS_ID_PFR0_EL1); + info->reg_id_pfr1 = read_cpuid(SYS_ID_PFR1_EL1); + + info->reg_mvfr0 = read_cpuid(SYS_MVFR0_EL1); + info->reg_mvfr1 = read_cpuid(SYS_MVFR1_EL1); + info->reg_mvfr2 = read_cpuid(SYS_MVFR2_EL1); cpuinfo_detect_icache_policy(info); diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S index a773db92908b..f82036e02485 100644 --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -61,7 +61,7 @@ ENTRY(entry) */ mov x20, x0 // DTB address ldr x0, [sp, #16] // relocated _text address - ldr x21, =stext_offset + movz x21, #:abs_g0:stext_offset add x21, x0, x21 /* diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7ed3d75f6304..1f7f5a2b61bf 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -27,6 +27,7 @@ #include <asm/cpufeature.h> #include <asm/errno.h> #include <asm/esr.h> +#include <asm/irq.h> #include <asm/thread_info.h> #include <asm/unistd.h> @@ -88,9 +89,12 @@ .if \el == 0 mrs x21, sp_el0 - get_thread_info tsk // Ensure MDSCR_EL1.SS is clear, + mov tsk, sp + and tsk, tsk, #~(THREAD_SIZE - 1) // Ensure MDSCR_EL1.SS is clear, ldr x19, [tsk, #TI_FLAGS] // since we can unmask debug disable_step_tsk x19, x20 // exceptions when scheduling. + + mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE .endif @@ -108,6 +112,13 @@ .endif /* + * Set sp_el0 to current thread_info. + */ + .if \el == 0 + msr sp_el0, tsk + .endif + + /* * Registers that may be useful after this macro is invoked: * * x21 - aborted SP @@ -164,8 +175,44 @@ alternative_endif .endm .macro get_thread_info, rd - mov \rd, sp - and \rd, \rd, #~(THREAD_SIZE - 1) // top of stack + mrs \rd, sp_el0 + .endm + + .macro irq_stack_entry + mov x19, sp // preserve the original sp + + /* + * Compare sp with the current thread_info, if the top + * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and + * should switch to the irq stack. + */ + and x25, x19, #~(THREAD_SIZE - 1) + cmp x25, tsk + b.ne 9998f + + this_cpu_ptr irq_stack, x25, x26 + mov x26, #IRQ_STACK_START_SP + add x26, x25, x26 + + /* switch to the irq stack */ + mov sp, x26 + + /* + * Add a dummy stack frame, this non-standard format is fixed up + * by unwind_frame() + */ + stp x29, x19, [sp, #-16]! + mov x29, sp + +9998: + .endm + + /* + * x19 should be preserved between irq_stack_entry and + * irq_stack_exit. + */ + .macro irq_stack_exit + mov sp, x19 .endm /* @@ -183,10 +230,11 @@ tsk .req x28 // current thread_info * Interrupt handling. */ .macro irq_handler - adrp x1, handle_arch_irq - ldr x1, [x1, #:lo12:handle_arch_irq] + ldr_l x1, handle_arch_irq mov x0, sp + irq_stack_entry blr x1 + irq_stack_exit .endm .text @@ -358,10 +406,10 @@ el1_irq: bl trace_hardirqs_off #endif + get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT - get_thread_info tsk ldr w24, [tsk, #TI_PREEMPT] // get preempt count cbnz w24, 1f // preempt count != 0 ldr x0, [tsk, #TI_FLAGS] // get flags @@ -599,6 +647,8 @@ ENTRY(cpu_switch_to) ldp x29, x9, [x8], #16 ldr lr, [x8] mov sp, x9 + and x9, x9, #~(THREAD_SIZE - 1) + msr sp_el0, x9 ret ENDPROC(cpu_switch_to) @@ -626,14 +676,14 @@ ret_fast_syscall_trace: work_pending: tbnz x1, #TIF_NEED_RESCHED, work_resched /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ - ldr x2, [sp, #S_PSTATE] mov x0, sp // 'regs' - tst x2, #PSR_MODE_MASK // user mode regs? - b.ne no_work_pending // returning to kernel enable_irq // enable interrupts for do_notify_resume() bl do_notify_resume b ret_to_user work_resched: +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off // the IRQs are off here, inform the tracing code +#endif bl schedule /* @@ -645,7 +695,6 @@ ret_to_user: and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending enable_step_tsk x1, x2 -no_work_pending: kernel_exit 0 ENDPROC(ret_to_user) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4c46c54a3ad7..acc1afd5c749 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -289,7 +289,7 @@ static struct notifier_block fpsimd_cpu_pm_notifier_block = { .notifier_call = fpsimd_cpu_pm_notifier, }; -static void fpsimd_pm_init(void) +static void __init fpsimd_pm_init(void) { cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block); } diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index c851be795080..ebecf9aa33d1 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -29,12 +29,11 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, /* * Note: - * Due to modules and __init, code can disappear and change, - * we need to protect against faulting as well as code changing. - * We do this by aarch64_insn_*() which use the probe_kernel_*(). - * - * No lock is held here because all the modifications are run - * through stop_machine(). + * We are paranoid about modifying text, as if a bug were to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with aarch64_insn_*() which uses + * probe_kernel_*(), and make sure what we read is what we expected it + * to be before modifying it. */ if (validate) { if (aarch64_insn_read((void *)pc, &replaced)) @@ -93,6 +92,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return ftrace_modify_code(pc, old, new, true); } +void arch_ftrace_update_code(int command) +{ + ftrace_modify_all_code(command); +} + int __init ftrace_dyn_arch_init(void) { return 0; @@ -125,23 +129,20 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, * on other archs. It's unlikely on AArch64. */ old = *parent; - *parent = return_hooker; trace.func = self_addr; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - *parent = old; + if (!ftrace_graph_entry(&trace)) return; - } err = ftrace_push_return_trace(old, self_addr, &trace.depth, frame_pointer); - if (err == -EBUSY) { - *parent = old; + if (err == -EBUSY) return; - } + else + *parent = return_hooker; } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b685257926f0..a88a15447c3b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -29,6 +29,7 @@ #include <asm/asm-offsets.h> #include <asm/cache.h> #include <asm/cputype.h> +#include <asm/elf.h> #include <asm/kernel-pgtable.h> #include <asm/memory.h> #include <asm/pgtable-hwdef.h> @@ -67,12 +68,11 @@ * in the entry routines. */ __HEAD - +_head: /* * DO NOT MODIFY. Image header expected by Linux boot-loaders. */ #ifdef CONFIG_EFI -efi_head: /* * This add instruction has no meaningful effect except that * its opcode forms the magic "MZ" signature required by UEFI. @@ -83,9 +83,9 @@ efi_head: b stext // branch to kernel start, magic .long 0 // reserved #endif - .quad _kernel_offset_le // Image load offset from start of RAM, little-endian - .quad _kernel_size_le // Effective size of kernel image, little-endian - .quad _kernel_flags_le // Informative flags, little-endian + le64sym _kernel_offset_le // Image load offset from start of RAM, little-endian + le64sym _kernel_size_le // Effective size of kernel image, little-endian + le64sym _kernel_flags_le // Informative flags, little-endian .quad 0 // reserved .quad 0 // reserved .quad 0 // reserved @@ -94,14 +94,14 @@ efi_head: .byte 0x4d .byte 0x64 #ifdef CONFIG_EFI - .long pe_header - efi_head // Offset to the PE header. + .long pe_header - _head // Offset to the PE header. #else .word 0 // reserved #endif #ifdef CONFIG_EFI .globl __efistub_stext_offset - .set __efistub_stext_offset, stext - efi_head + .set __efistub_stext_offset, stext - _head .align 3 pe_header: .ascii "PE" @@ -124,7 +124,7 @@ optional_header: .long _end - stext // SizeOfCode .long 0 // SizeOfInitializedData .long 0 // SizeOfUninitializedData - .long __efistub_entry - efi_head // AddressOfEntryPoint + .long __efistub_entry - _head // AddressOfEntryPoint .long __efistub_stext_offset // BaseOfCode extra_header_fields: @@ -139,7 +139,7 @@ extra_header_fields: .short 0 // MinorSubsystemVersion .long 0 // Win32VersionValue - .long _end - efi_head // SizeOfImage + .long _end - _head // SizeOfImage // Everything before the kernel image is considered part of the header .long __efistub_stext_offset // SizeOfHeaders @@ -210,6 +210,7 @@ section_table: ENTRY(stext) bl preserve_boot_args bl el2_setup // Drop to EL1, w20=cpu_boot_mode + mov x23, xzr // KASLR offset, defaults to 0 adrp x24, __PHYS_OFFSET bl set_cpu_boot_mode_flag bl __create_page_tables // x25=TTBR0, x26=TTBR1 @@ -219,11 +220,13 @@ ENTRY(stext) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ - ldr x27, =__mmap_switched // address to jump to after + ldr x27, 0f // address to jump to after // MMU has been enabled adr_l lr, __enable_mmu // return (PIC) address b __cpu_setup // initialise processor ENDPROC(stext) + .align 3 +0: .quad __mmap_switched - (_head - TEXT_OFFSET) + KIMAGE_VADDR /* * Preserve the arguments passed by the bootloader in x0 .. x3 @@ -311,7 +314,7 @@ ENDPROC(preserve_boot_args) __create_page_tables: adrp x25, idmap_pg_dir adrp x26, swapper_pg_dir - mov x27, lr + mov x28, lr /* * Invalidate the idmap and swapper page tables to avoid potential @@ -389,9 +392,11 @@ __create_page_tables: * Map the kernel image (starting with PHYS_OFFSET). */ mov x0, x26 // swapper_pg_dir - mov x5, #PAGE_OFFSET + ldr x5, =KIMAGE_VADDR + add x5, x5, x23 // add KASLR displacement create_pgd_entry x0, x5, x3, x6 - ldr x6, =KERNEL_END // __va(KERNEL_END) + ldr w6, kernel_img_size + add x6, x6, x5 mov x3, x24 // phys offset create_block_map x0, x7, x3, x5, x6 @@ -405,9 +410,11 @@ __create_page_tables: dmb sy bl __inval_cache_range - mov lr, x27 - ret + ret x28 ENDPROC(__create_page_tables) + +kernel_img_size: + .long _end - (_head - TEXT_OFFSET) .ltorg /* @@ -415,21 +422,81 @@ ENDPROC(__create_page_tables) */ .set initial_sp, init_thread_union + THREAD_START_SP __mmap_switched: - adr_l x6, __bss_start - adr_l x7, __bss_stop + mov x28, lr // preserve LR + adr_l x8, vectors // load VBAR_EL1 with virtual + msr vbar_el1, x8 // vector table address + isb -1: cmp x6, x7 + // Clear BSS + adr_l x0, __bss_start + mov x1, xzr + adr_l x2, __bss_stop + sub x2, x2, x0 + bl __pi_memset + dsb ishst // Make zero page visible to PTW + +#ifdef CONFIG_RELOCATABLE + + /* + * Iterate over each entry in the relocation table, and apply the + * relocations in place. + */ + adr_l x8, __dynsym_start // start of symbol table + adr_l x9, __reloc_start // start of reloc table + adr_l x10, __reloc_end // end of reloc table + +0: cmp x9, x10 b.hs 2f - str xzr, [x6], #8 // Clear BSS - b 1b -2: + ldp x11, x12, [x9], #24 + ldr x13, [x9, #-8] + cmp w12, #R_AARCH64_RELATIVE + b.ne 1f + add x13, x13, x23 // relocate + str x13, [x11, x23] + b 0b + +1: cmp w12, #R_AARCH64_ABS64 + b.ne 0b + add x12, x12, x12, lsl #1 // symtab offset: 24x top word + add x12, x8, x12, lsr #(32 - 3) // ... shifted into bottom word + ldrsh w14, [x12, #6] // Elf64_Sym::st_shndx + ldr x15, [x12, #8] // Elf64_Sym::st_value + cmp w14, #-0xf // SHN_ABS (0xfff1) ? + add x14, x15, x23 // relocate + csel x15, x14, x15, ne + add x15, x13, x15 + str x15, [x11, x23] + b 0b + +2: adr_l x8, kimage_vaddr // make relocated kimage_vaddr + dc cvac, x8 // value visible to secondaries + dsb sy // with MMU off +#endif + adr_l sp, initial_sp, x4 + mov x4, sp + and x4, x4, #~(THREAD_SIZE - 1) + msr sp_el0, x4 // Save thread_info str_l x21, __fdt_pointer, x5 // Save FDT pointer - str_l x24, memstart_addr, x6 // Save PHYS_OFFSET + + ldr_l x4, kimage_vaddr // Save the offset between + sub x4, x4, x24 // the kernel virtual and + str_l x4, kimage_voffset, x5 // physical mappings + mov x29, #0 #ifdef CONFIG_KASAN bl kasan_early_init #endif +#ifdef CONFIG_RANDOMIZE_BASE + cbnz x23, 0f // already running randomized? + mov x0, x21 // pass FDT address in x0 + bl kaslr_early_init // parse FDT for KASLR options + cbz x0, 0f // KASLR disabled? just proceed + mov x23, x0 // record KASLR offset + ret x28 // we must enable KASLR, return + // to __enable_mmu() +0: +#endif b start_kernel ENDPROC(__mmap_switched) @@ -438,6 +505,10 @@ ENDPROC(__mmap_switched) * hotplug and needs to have the same protections as the text region */ .section ".text","ax" + +ENTRY(kimage_vaddr) + .quad _text - TEXT_OFFSET + /* * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. @@ -603,14 +674,22 @@ ENTRY(secondary_startup) adrp x26, swapper_pg_dir bl __cpu_setup // initialise processor - ldr x21, =secondary_data - ldr x27, =__secondary_switched // address to jump to after enabling the MMU + ldr x8, kimage_vaddr + ldr w9, 0f + sub x27, x8, w9, sxtw // address to jump to after enabling the MMU b __enable_mmu ENDPROC(secondary_startup) +0: .long (_text - TEXT_OFFSET) - __secondary_switched ENTRY(__secondary_switched) - ldr x0, [x21] // get secondary_data.stack + adr_l x5, vectors + msr vbar_el1, x5 + isb + + ldr_l x0, secondary_data // get secondary_data.stack mov sp, x0 + and x0, x0, #~(THREAD_SIZE - 1) + msr sp_el0, x0 // save thread_info mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) @@ -628,12 +707,11 @@ ENDPROC(__secondary_switched) */ .section ".idmap.text", "ax" __enable_mmu: + mrs x18, sctlr_el1 // preserve old SCTLR_EL1 value mrs x1, ID_AA64MMFR0_EL1 ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4 cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED b.ne __no_granule_support - ldr x5, =vectors - msr vbar_el1, x5 msr ttbr0_el1, x25 // load TTBR0 msr ttbr1_el1, x26 // load TTBR1 isb @@ -647,6 +725,26 @@ __enable_mmu: ic iallu dsb nsh isb +#ifdef CONFIG_RANDOMIZE_BASE + mov x19, x0 // preserve new SCTLR_EL1 value + blr x27 + + /* + * If we return here, we have a KASLR displacement in x23 which we need + * to take into account by discarding the current kernel mapping and + * creating a new one. + */ + msr sctlr_el1, x18 // disable the MMU + isb + bl __create_page_tables // recreate kernel mapping + + msr sctlr_el1, x19 // re-enable the MMU + isb + ic iallu // flush instructions fetched + dsb nsh // via old mapping + isb + add x27, x27, x23 // relocated __mmap_switched +#endif br x27 ENDPROC(__enable_mmu) diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index bc2abb8b1599..db1bf57948f1 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -26,31 +26,40 @@ * There aren't any ELF relocations we can use to endian-swap values known only * at link time (e.g. the subtraction of two symbol addresses), so we must get * the linker to endian-swap certain values before emitting them. + * + * Note that, in order for this to work when building the ELF64 PIE executable + * (for KASLR), these values should not be referenced via R_AARCH64_ABS64 + * relocations, since these are fixed up at runtime rather than at build time + * when PIE is in effect. So we need to split them up in 32-bit high and low + * words. */ #ifdef CONFIG_CPU_BIG_ENDIAN -#define DATA_LE64(data) \ - ((((data) & 0x00000000000000ff) << 56) | \ - (((data) & 0x000000000000ff00) << 40) | \ - (((data) & 0x0000000000ff0000) << 24) | \ - (((data) & 0x00000000ff000000) << 8) | \ - (((data) & 0x000000ff00000000) >> 8) | \ - (((data) & 0x0000ff0000000000) >> 24) | \ - (((data) & 0x00ff000000000000) >> 40) | \ - (((data) & 0xff00000000000000) >> 56)) +#define DATA_LE32(data) \ + ((((data) & 0x000000ff) << 24) | \ + (((data) & 0x0000ff00) << 8) | \ + (((data) & 0x00ff0000) >> 8) | \ + (((data) & 0xff000000) >> 24)) #else -#define DATA_LE64(data) ((data) & 0xffffffffffffffff) +#define DATA_LE32(data) ((data) & 0xffffffff) #endif +#define DEFINE_IMAGE_LE64(sym, data) \ + sym##_lo32 = DATA_LE32((data) & 0xffffffff); \ + sym##_hi32 = DATA_LE32((data) >> 32) + #ifdef CONFIG_CPU_BIG_ENDIAN -#define __HEAD_FLAG_BE 1 +#define __HEAD_FLAG_BE 1 #else -#define __HEAD_FLAG_BE 0 +#define __HEAD_FLAG_BE 0 #endif -#define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2) +#define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2) + +#define __HEAD_FLAG_PHYS_BASE 1 -#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \ - (__HEAD_FLAG_PAGE_SIZE << 1)) +#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \ + (__HEAD_FLAG_PAGE_SIZE << 1) | \ + (__HEAD_FLAG_PHYS_BASE << 3)) /* * These will output as part of the Image header, which should be little-endian @@ -58,13 +67,23 @@ * endian swapped in head.S, all are done here for consistency. */ #define HEAD_SYMBOLS \ - _kernel_size_le = DATA_LE64(_end - _text); \ - _kernel_offset_le = DATA_LE64(TEXT_OFFSET); \ - _kernel_flags_le = DATA_LE64(__HEAD_FLAGS); + DEFINE_IMAGE_LE64(_kernel_size_le, _end - _text); \ + DEFINE_IMAGE_LE64(_kernel_offset_le, TEXT_OFFSET); \ + DEFINE_IMAGE_LE64(_kernel_flags_le, __HEAD_FLAGS); #ifdef CONFIG_EFI /* + * Prevent the symbol aliases below from being emitted into the kallsyms + * table, by forcing them to be absolute symbols (which are conveniently + * ignored by scripts/kallsyms) rather than section relative symbols. + * The distinction is only relevant for partial linking, and only for symbols + * that are defined within a section declaration (which is not the case for + * the definitions below) so the resulting values will be identical. + */ +#define KALLSYMS_HIDE(sym) ABSOLUTE(sym) + +/* * The EFI stub has its own symbol namespace prefixed by __efistub_, to * isolate it from the kernel proper. The following symbols are legally * accessed by the stub, so provide some aliases to make them accessible. @@ -73,25 +92,25 @@ * linked at. The routines below are all implemented in assembler in a * position independent manner */ -__efistub_memcmp = __pi_memcmp; -__efistub_memchr = __pi_memchr; -__efistub_memcpy = __pi_memcpy; -__efistub_memmove = __pi_memmove; -__efistub_memset = __pi_memset; -__efistub_strlen = __pi_strlen; -__efistub_strcmp = __pi_strcmp; -__efistub_strncmp = __pi_strncmp; -__efistub___flush_dcache_area = __pi___flush_dcache_area; +__efistub_memcmp = KALLSYMS_HIDE(__pi_memcmp); +__efistub_memchr = KALLSYMS_HIDE(__pi_memchr); +__efistub_memcpy = KALLSYMS_HIDE(__pi_memcpy); +__efistub_memmove = KALLSYMS_HIDE(__pi_memmove); +__efistub_memset = KALLSYMS_HIDE(__pi_memset); +__efistub_strlen = KALLSYMS_HIDE(__pi_strlen); +__efistub_strcmp = KALLSYMS_HIDE(__pi_strcmp); +__efistub_strncmp = KALLSYMS_HIDE(__pi_strncmp); +__efistub___flush_dcache_area = KALLSYMS_HIDE(__pi___flush_dcache_area); #ifdef CONFIG_KASAN -__efistub___memcpy = __pi_memcpy; -__efistub___memmove = __pi_memmove; -__efistub___memset = __pi_memset; +__efistub___memcpy = KALLSYMS_HIDE(__pi_memcpy); +__efistub___memmove = KALLSYMS_HIDE(__pi_memmove); +__efistub___memset = KALLSYMS_HIDE(__pi_memset); #endif -__efistub__text = _text; -__efistub__end = _end; -__efistub__edata = _edata; +__efistub__text = KALLSYMS_HIDE(_text); +__efistub__end = KALLSYMS_HIDE(_end); +__efistub__edata = KALLSYMS_HIDE(_edata); #endif diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 9f17ec071ee0..2386b26c0712 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -30,6 +30,9 @@ unsigned long irq_err_count; +/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ +DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16); + int arch_show_interrupts(struct seq_file *p, int prec) { show_ipi_list(p, prec); diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c new file mode 100644 index 000000000000..582983920054 --- /dev/null +++ b/arch/arm64/kernel/kaslr.c @@ -0,0 +1,177 @@ +/* + * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/crc32.h> +#include <linux/init.h> +#include <linux/libfdt.h> +#include <linux/mm_types.h> +#include <linux/sched.h> +#include <linux/types.h> + +#include <asm/fixmap.h> +#include <asm/kernel-pgtable.h> +#include <asm/memory.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/sections.h> + +u64 __read_mostly module_alloc_base; +u16 __initdata memstart_offset_seed; + +static __init u64 get_kaslr_seed(void *fdt) +{ + int node, len; + u64 *prop; + u64 ret; + + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + return 0; + + prop = fdt_getprop_w(fdt, node, "kaslr-seed", &len); + if (!prop || len != sizeof(u64)) + return 0; + + ret = fdt64_to_cpu(*prop); + *prop = 0; + return ret; +} + +static __init const u8 *get_cmdline(void *fdt) +{ + static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE; + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { + int node; + const u8 *prop; + + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + goto out; + + prop = fdt_getprop(fdt, node, "bootargs", NULL); + if (!prop) + goto out; + return prop; + } +out: + return default_cmdline; +} + +extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, + pgprot_t prot); + +/* + * This routine will be executed with the kernel mapped at its default virtual + * address, and if it returns successfully, the kernel will be remapped, and + * start_kernel() will be executed from a randomized virtual offset. The + * relocation will result in all absolute references (e.g., static variables + * containing function pointers) to be reinitialized, and zero-initialized + * .bss variables will be reset to 0. + */ +u64 __init kaslr_early_init(u64 dt_phys) +{ + void *fdt; + u64 seed, offset, mask, module_range; + const u8 *cmdline, *str; + int size; + + /* + * Set a reasonable default for module_alloc_base in case + * we end up running with module randomization disabled. + */ + module_alloc_base = (u64)_etext - MODULES_VSIZE; + + /* + * Try to map the FDT early. If this fails, we simply bail, + * and proceed with KASLR disabled. We will make another + * attempt at mapping the FDT in setup_machine() + */ + early_fixmap_init(); + fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); + if (!fdt) + return 0; + + /* + * Retrieve (and wipe) the seed from the FDT + */ + seed = get_kaslr_seed(fdt); + if (!seed) + return 0; + + /* + * Check if 'nokaslr' appears on the command line, and + * return 0 if that is the case. + */ + cmdline = get_cmdline(fdt); + str = strstr(cmdline, "nokaslr"); + if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) + return 0; + + /* + * OK, so we are proceeding with KASLR enabled. Calculate a suitable + * kernel image offset from the seed. Let's place the kernel in the + * lower half of the VMALLOC area (VA_BITS - 2). + * Even if we could randomize at page granularity for 16k and 64k pages, + * let's always round to 2 MB so we don't interfere with the ability to + * map using contiguous PTEs + */ + mask = ((1UL << (VA_BITS - 2)) - 1) & ~(SZ_2M - 1); + offset = seed & mask; + + /* use the top 16 bits to randomize the linear region */ + memstart_offset_seed = seed >> 48; + + /* + * The kernel Image should not extend across a 1GB/32MB/512MB alignment + * boundary (for 4KB/16KB/64KB granule kernels, respectively). If this + * happens, increase the KASLR offset by the size of the kernel image. + */ + if ((((u64)_text + offset) >> SWAPPER_TABLE_SHIFT) != + (((u64)_end + offset) >> SWAPPER_TABLE_SHIFT)) + offset = (offset + (u64)(_end - _text)) & mask; + + if (IS_ENABLED(CONFIG_KASAN)) + /* + * KASAN does not expect the module region to intersect the + * vmalloc region, since shadow memory is allocated for each + * module at load time, whereas the vmalloc region is shadowed + * by KASAN zero pages. So keep modules out of the vmalloc + * region if KASAN is enabled. + */ + return offset; + + if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { + /* + * Randomize the module region independently from the core + * kernel. This prevents modules from leaking any information + * about the address of the kernel itself, but results in + * branches between modules and the core kernel that are + * resolved via PLTs. (Branches between modules will be + * resolved normally.) + */ + module_range = VMALLOC_END - VMALLOC_START - MODULES_VSIZE; + module_alloc_base = VMALLOC_START; + } else { + /* + * Randomize the module region by setting module_alloc_base to + * a PAGE_SIZE multiple in the range [_etext - MODULES_VSIZE, + * _stext) . This guarantees that the resulting region still + * covers [_stext, _etext], and that all relative branches can + * be resolved without veneers. + */ + module_range = MODULES_VSIZE - (u64)(_etext - _stext); + module_alloc_base = (u64)_etext + offset - MODULES_VSIZE; + } + + /* use the lower 21 bits to randomize the base of the module region */ + module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21; + module_alloc_base &= PAGE_MASK; + + return offset; +} diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c new file mode 100644 index 000000000000..1ce90d8450ae --- /dev/null +++ b/arch/arm64/kernel/module-plts.c @@ -0,0 +1,201 @@ +/* + * Copyright (C) 2014-2016 Linaro Ltd. <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/elf.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sort.h> + +struct plt_entry { + /* + * A program that conforms to the AArch64 Procedure Call Standard + * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or + * IP1 (x17) may be inserted at any branch instruction that is + * exposed to a relocation that supports long branches. Since that + * is exactly what we are dealing with here, we are free to use x16 + * as a scratch register in the PLT veneers. + */ + __le32 mov0; /* movn x16, #0x.... */ + __le32 mov1; /* movk x16, #0x...., lsl #16 */ + __le32 mov2; /* movk x16, #0x...., lsl #32 */ + __le32 br; /* br x16 */ +}; + +u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela, + Elf64_Sym *sym) +{ + struct plt_entry *plt = (struct plt_entry *)mod->arch.plt->sh_addr; + int i = mod->arch.plt_num_entries; + u64 val = sym->st_value + rela->r_addend; + + /* + * We only emit PLT entries against undefined (SHN_UNDEF) symbols, + * which are listed in the ELF symtab section, but without a type + * or a size. + * So, similar to how the module loader uses the Elf64_Sym::st_value + * field to store the resolved addresses of undefined symbols, let's + * borrow the Elf64_Sym::st_size field (whose value is never used by + * the module loader, even for symbols that are defined) to record + * the address of a symbol's associated PLT entry as we emit it for a + * zero addend relocation (which is the only kind we have to deal with + * in practice). This allows us to find duplicates without having to + * go through the table every time. + */ + if (rela->r_addend == 0 && sym->st_size != 0) { + BUG_ON(sym->st_size < (u64)plt || sym->st_size >= (u64)&plt[i]); + return sym->st_size; + } + + mod->arch.plt_num_entries++; + BUG_ON(mod->arch.plt_num_entries > mod->arch.plt_max_entries); + + /* + * MOVK/MOVN/MOVZ opcode: + * +--------+------------+--------+-----------+-------------+---------+ + * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] | + * +--------+------------+--------+-----------+-------------+---------+ + * + * Rd := 0x10 (x16) + * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32) + * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ) + * sf := 1 (64-bit variant) + */ + plt[i] = (struct plt_entry){ + cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5), + cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5), + cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5), + cpu_to_le32(0xd61f0200) + }; + + if (rela->r_addend == 0) + sym->st_size = (u64)&plt[i]; + + return (u64)&plt[i]; +} + +#define cmp_3way(a,b) ((a) < (b) ? -1 : (a) > (b)) + +static int cmp_rela(const void *a, const void *b) +{ + const Elf64_Rela *x = a, *y = b; + int i; + + /* sort by type, symbol index and addend */ + i = cmp_3way(ELF64_R_TYPE(x->r_info), ELF64_R_TYPE(y->r_info)); + if (i == 0) + i = cmp_3way(ELF64_R_SYM(x->r_info), ELF64_R_SYM(y->r_info)); + if (i == 0) + i = cmp_3way(x->r_addend, y->r_addend); + return i; +} + +static bool duplicate_rel(const Elf64_Rela *rela, int num) +{ + /* + * Entries are sorted by type, symbol index and addend. That means + * that, if a duplicate entry exists, it must be in the preceding + * slot. + */ + return num > 0 && cmp_rela(rela + num, rela + num - 1) == 0; +} + +static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num) +{ + unsigned int ret = 0; + Elf64_Sym *s; + int i; + + for (i = 0; i < num; i++) { + switch (ELF64_R_TYPE(rela[i].r_info)) { + case R_AARCH64_JUMP26: + case R_AARCH64_CALL26: + /* + * We only have to consider branch targets that resolve + * to undefined symbols. This is not simply a heuristic, + * it is a fundamental limitation, since the PLT itself + * is part of the module, and needs to be within 128 MB + * as well, so modules can never grow beyond that limit. + */ + s = syms + ELF64_R_SYM(rela[i].r_info); + if (s->st_shndx != SHN_UNDEF) + break; + + /* + * Jump relocations with non-zero addends against + * undefined symbols are supported by the ELF spec, but + * do not occur in practice (e.g., 'jump n bytes past + * the entry point of undefined function symbol f'). + * So we need to support them, but there is no need to + * take them into consideration when trying to optimize + * this code. So let's only check for duplicates when + * the addend is zero: this allows us to record the PLT + * entry address in the symbol table itself, rather than + * having to search the list for duplicates each time we + * emit one. + */ + if (rela[i].r_addend != 0 || !duplicate_rel(rela, i)) + ret++; + break; + } + } + return ret; +} + +int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *mod) +{ + unsigned long plt_max_entries = 0; + Elf64_Sym *syms = NULL; + int i; + + /* + * Find the empty .plt section so we can expand it to store the PLT + * entries. Record the symtab address as well. + */ + for (i = 0; i < ehdr->e_shnum; i++) { + if (strcmp(".plt", secstrings + sechdrs[i].sh_name) == 0) + mod->arch.plt = sechdrs + i; + else if (sechdrs[i].sh_type == SHT_SYMTAB) + syms = (Elf64_Sym *)sechdrs[i].sh_addr; + } + + if (!mod->arch.plt) { + pr_err("%s: module PLT section missing\n", mod->name); + return -ENOEXEC; + } + if (!syms) { + pr_err("%s: module symtab section missing\n", mod->name); + return -ENOEXEC; + } + + for (i = 0; i < ehdr->e_shnum; i++) { + Elf64_Rela *rels = (void *)ehdr + sechdrs[i].sh_offset; + int numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela); + Elf64_Shdr *dstsec = sechdrs + sechdrs[i].sh_info; + + if (sechdrs[i].sh_type != SHT_RELA) + continue; + + /* ignore relocations that operate on non-exec sections */ + if (!(dstsec->sh_flags & SHF_EXECINSTR)) + continue; + + /* sort by type, symbol index and addend */ + sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL); + + plt_max_entries += count_plts(syms, rels, numrels); + } + + mod->arch.plt->sh_type = SHT_NOBITS; + mod->arch.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + mod->arch.plt->sh_addralign = L1_CACHE_BYTES; + mod->arch.plt->sh_size = plt_max_entries * sizeof(struct plt_entry); + mod->arch.plt_num_entries = 0; + mod->arch.plt_max_entries = plt_max_entries; + return 0; +} diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f4bc779e62e8..7f316982ce00 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -30,17 +30,30 @@ #include <asm/insn.h> #include <asm/sections.h> -#define AARCH64_INSN_IMM_MOVNZ AARCH64_INSN_IMM_MAX -#define AARCH64_INSN_IMM_MOVK AARCH64_INSN_IMM_16 - void *module_alloc(unsigned long size) { void *p; - p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, + p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, + module_alloc_base + MODULES_VSIZE, GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0)); + if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && + !IS_ENABLED(CONFIG_KASAN)) + /* + * KASAN can only deal with module allocations being served + * from the reserved module region, since the remainder of + * the vmalloc region is already backed by zero shadow pages, + * and punching holes into it is non-trivial. Since the module + * region is not randomized when KASAN is enabled, it is even + * less likely that the module region gets exhausted, so we + * can simply omit this fallback in that case. + */ + p = __vmalloc_node_range(size, MODULE_ALIGN, VMALLOC_START, + VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_EXEC, 0, + NUMA_NO_NODE, __builtin_return_address(0)); + if (p && (kasan_module_alloc(p, size) < 0)) { vfree(p); return NULL; @@ -75,15 +88,18 @@ static u64 do_reloc(enum aarch64_reloc_op reloc_op, void *place, u64 val) static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) { - u64 imm_mask = (1 << len) - 1; s64 sval = do_reloc(op, place, val); switch (len) { case 16: *(s16 *)place = sval; + if (sval < S16_MIN || sval > U16_MAX) + return -ERANGE; break; case 32: *(s32 *)place = sval; + if (sval < S32_MIN || sval > U32_MAX) + return -ERANGE; break; case 64: *(s64 *)place = sval; @@ -92,34 +108,23 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) pr_err("Invalid length (%d) for data relocation\n", len); return 0; } - - /* - * Extract the upper value bits (including the sign bit) and - * shift them to bit 0. - */ - sval = (s64)(sval & ~(imm_mask >> 1)) >> (len - 1); - - /* - * Overflow has occurred if the value is not representable in - * len bits (i.e the bottom len bits are not sign-extended and - * the top bits are not all zero). - */ - if ((u64)(sval + 1) > 2) - return -ERANGE; - return 0; } +enum aarch64_insn_movw_imm_type { + AARCH64_INSN_IMM_MOVNZ, + AARCH64_INSN_IMM_MOVKZ, +}; + static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, - int lsb, enum aarch64_insn_imm_type imm_type) + int lsb, enum aarch64_insn_movw_imm_type imm_type) { - u64 imm, limit = 0; + u64 imm; s64 sval; u32 insn = le32_to_cpu(*(u32 *)place); sval = do_reloc(op, place, val); - sval >>= lsb; - imm = sval & 0xffff; + imm = sval >> lsb; if (imm_type == AARCH64_INSN_IMM_MOVNZ) { /* @@ -128,7 +133,7 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, * immediate is less than zero. */ insn &= ~(3 << 29); - if ((s64)imm >= 0) { + if (sval >= 0) { /* >=0: Set the instruction to MOVZ (opcode 10b). */ insn |= 2 << 29; } else { @@ -140,29 +145,13 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, */ imm = ~imm; } - imm_type = AARCH64_INSN_IMM_MOVK; } /* Update the instruction with the new encoding. */ - insn = aarch64_insn_encode_immediate(imm_type, insn, imm); + insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm); *(u32 *)place = cpu_to_le32(insn); - /* Shift out the immediate field. */ - sval >>= 16; - - /* - * For unsigned immediates, the overflow check is straightforward. - * For signed immediates, the sign bit is actually the bit past the - * most significant bit of the field. - * The AARCH64_INSN_IMM_16 immediate type is unsigned. - */ - if (imm_type != AARCH64_INSN_IMM_16) { - sval++; - limit++; - } - - /* Check the upper bits depending on the sign of the immediate. */ - if ((u64)sval > limit) + if (imm > U16_MAX) return -ERANGE; return 0; @@ -267,25 +256,25 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, overflow_check = false; case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G3: /* We're using the top bits so we can't overflow. */ overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_SABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, @@ -302,7 +291,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G0_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G0: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0, @@ -311,7 +300,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G1_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G1: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16, @@ -320,7 +309,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G2_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G2: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32, @@ -388,6 +377,13 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_CALL26: ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26, AARCH64_INSN_IMM_26); + + if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && + ovf == -ERANGE) { + val = module_emit_plt_entry(me, &rel[i], sym); + ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, + 26, AARCH64_INSN_IMM_26); + } break; default: diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds new file mode 100644 index 000000000000..8949f6c6f729 --- /dev/null +++ b/arch/arm64/kernel/module.lds @@ -0,0 +1,3 @@ +SECTIONS { + .plt (NOLOAD) : { BYTE(0) } +} diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 3aa74830cc69..ff4665462a02 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -164,8 +164,11 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, frame.fp = regs->regs[29]; frame.sp = regs->sp; frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif - walk_stackframe(&frame, callchain_trace, entry); + walk_stackframe(current, &frame, callchain_trace, entry); } unsigned long perf_instruction_pointer(struct pt_regs *regs) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index f75b540bc3b4..80624829db61 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -46,6 +46,7 @@ #include <linux/notifier.h> #include <trace/events/power.h> +#include <asm/alternative.h> #include <asm/compat.h> #include <asm/cacheflush.h> #include <asm/fpsimd.h> @@ -280,6 +281,9 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, } else { memset(childregs, 0, sizeof(struct pt_regs)); childregs->pstate = PSR_MODE_EL1h; + if (IS_ENABLED(CONFIG_ARM64_UAO) && + cpus_have_cap(ARM64_HAS_UAO)) + childregs->pstate |= PSR_UAO_BIT; p->thread.cpu_context.x19 = stack_start; p->thread.cpu_context.x20 = stk_sz; } @@ -308,6 +312,17 @@ static void tls_thread_switch(struct task_struct *next) : : "r" (tpidr), "r" (tpidrro)); } +/* Restore the UAO state depending on next's addr_limit */ +static void uao_thread_switch(struct task_struct *next) +{ + if (IS_ENABLED(CONFIG_ARM64_UAO)) { + if (task_thread_info(next)->addr_limit == KERNEL_DS) + asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO)); + else + asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO)); + } +} + /* * Thread switching. */ @@ -320,6 +335,7 @@ struct task_struct *__switch_to(struct task_struct *prev, tls_thread_switch(next); hw_breakpoint_thread_switch(next); contextidr_thread_switch(next); + uao_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case @@ -344,11 +360,14 @@ unsigned long get_wchan(struct task_struct *p) frame.fp = thread_saved_fp(p); frame.sp = thread_saved_sp(p); frame.pc = thread_saved_pc(p); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = p->curr_ret_stack; +#endif stack_page = (unsigned long)task_stack_page(p); do { if (frame.sp < stack_page || frame.sp >= stack_page + THREAD_SIZE || - unwind_frame(&frame)) + unwind_frame(p, &frame)) return 0; if (!in_sched_functions(frame.pc)) return frame.pc; diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index 6c4fd2810ecb..1718706fde83 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -43,8 +43,11 @@ void *return_address(unsigned int level) frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; frame.pc = (unsigned long)return_address; /* dummy */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif - walk_stackframe(&frame, save_return_addr, &data); + walk_stackframe(current, &frame, save_return_addr, &data); if (!data.level) return data.addr; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 8119479147db..42371f69def3 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -62,6 +62,7 @@ #include <asm/memblock.h> #include <asm/efi.h> #include <asm/xen/hypervisor.h> +#include <asm/mmu_context.h> phys_addr_t __fdt_pointer __initdata; @@ -313,6 +314,12 @@ void __init setup_arch(char **cmdline_p) */ local_async_enable(); + /* + * TTBR0 is only used for the identity mapping at this stage. Make it + * point to zero page to avoid speculatively fetching new entries. + */ + cpu_uninstall_idmap(); + efi_init(); arm64_memblock_init(); @@ -381,3 +388,32 @@ static int __init topology_init(void) return 0; } subsys_initcall(topology_init); + +/* + * Dump out kernel offset information on panic. + */ +static int dump_kernel_offset(struct notifier_block *self, unsigned long v, + void *p) +{ + u64 const kaslr_offset = kimage_vaddr - KIMAGE_VADDR; + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset > 0) { + pr_emerg("Kernel Offset: 0x%llx from 0x%lx\n", + kaslr_offset, KIMAGE_VADDR); + } else { + pr_emerg("Kernel Offset: disabled\n"); + } + return 0; +} + +static struct notifier_block kernel_offset_notifier = { + .notifier_call = dump_kernel_offset +}; + +static int __init register_kernel_offset_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_offset_notifier); + return 0; +} +__initcall(register_kernel_offset_dumper); diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index f586f7c875e2..e33fe33876ab 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -173,6 +173,9 @@ ENTRY(cpu_resume) /* load physical address of identity map page table in x1 */ adrp x1, idmap_pg_dir mov sp, x2 + /* save thread_info */ + and x2, x2, #~(THREAD_SIZE - 1) + msr sp_el0, x2 /* * cpu_do_resume expects x0 to contain context physical address * pointer and x1 to contain physical address of 1:1 page tables diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index b1adc51b2c2e..24cb4f800033 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -70,6 +70,7 @@ enum ipi_msg_type { IPI_CPU_STOP, IPI_TIMER, IPI_IRQ_WORK, + IPI_WAKEUP }; /* @@ -149,9 +150,7 @@ asmlinkage void secondary_start_kernel(void) * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. */ - cpu_set_reserved_ttbr0(); - local_flush_tlb_all(); - cpu_set_default_tcr_t0sz(); + cpu_uninstall_idmap(); preempt_disable(); trace_hardirqs_off(); @@ -445,6 +444,17 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) /* map the logical cpu id to cpu MPIDR */ cpu_logical_map(cpu_count) = hwid; + /* + * Set-up the ACPI parking protocol cpu entries + * while initializing the cpu_logical_map to + * avoid parsing MADT entries multiple times for + * nothing (ie a valid cpu_logical_map entry should + * contain a valid parking protocol data set to + * initialize the cpu if the parking protocol is + * the only available enable method). + */ + acpi_set_mailbox_entry(cpu_count, processor); + cpu_count++; } @@ -627,6 +637,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { S(IPI_CPU_STOP, "CPU stop interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), S(IPI_IRQ_WORK, "IRQ work interrupts"), + S(IPI_WAKEUP, "CPU wake-up interrupts"), }; static void smp_cross_call(const struct cpumask *target, unsigned int ipinr) @@ -670,6 +681,13 @@ void arch_send_call_function_single_ipi(int cpu) smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC); } +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL +void arch_send_wakeup_ipi_mask(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_WAKEUP); +} +#endif + #ifdef CONFIG_IRQ_WORK void arch_irq_work_raise(void) { @@ -747,6 +765,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) break; #endif +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL + case IPI_WAKEUP: + WARN_ONCE(!acpi_parking_protocol_valid(cpu), + "CPU%u: Wake-up IPI outside the ACPI parking protocol\n", + cpu); + break; +#endif + default: pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); break; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index ccb6078ed9f2..cfd46c227c8c 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -17,9 +17,11 @@ */ #include <linux/kernel.h> #include <linux/export.h> +#include <linux/ftrace.h> #include <linux/sched.h> #include <linux/stacktrace.h> +#include <asm/irq.h> #include <asm/stacktrace.h> /* @@ -35,25 +37,82 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ -int notrace unwind_frame(struct stackframe *frame) +int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) { unsigned long high, low; unsigned long fp = frame->fp; + unsigned long irq_stack_ptr; + + /* + * Switching between stacks is valid when tracing current and in + * non-preemptible context. + */ + if (tsk == current && !preemptible()) + irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + else + irq_stack_ptr = 0; low = frame->sp; - high = ALIGN(low, THREAD_SIZE); + /* irq stacks are not THREAD_SIZE aligned */ + if (on_irq_stack(frame->sp, raw_smp_processor_id())) + high = irq_stack_ptr; + else + high = ALIGN(low, THREAD_SIZE) - 0x20; - if (fp < low || fp > high - 0x18 || fp & 0xf) + if (fp < low || fp > high || fp & 0xf) return -EINVAL; frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); frame->pc = *(unsigned long *)(fp + 8); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (tsk && tsk->ret_stack && + (frame->pc == (unsigned long)return_to_handler)) { + /* + * This is a case where function graph tracer has + * modified a return address (LR) in a stack frame + * to hook a function return. + * So replace it to an original value. + */ + frame->pc = tsk->ret_stack[frame->graph--].ret; + } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + /* + * Check whether we are going to walk through from interrupt stack + * to task stack. + * If we reach the end of the stack - and its an interrupt stack, + * unpack the dummy frame to find the original elr. + * + * Check the frame->fp we read from the bottom of the irq_stack, + * and the original task stack pointer are both in current->stack. + */ + if (frame->sp == irq_stack_ptr) { + struct pt_regs *irq_args; + unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); + + if (object_is_on_stack((void *)orig_sp) && + object_is_on_stack((void *)frame->fp)) { + frame->sp = orig_sp; + + /* orig_sp is the saved pt_regs, find the elr */ + irq_args = (struct pt_regs *)orig_sp; + frame->pc = irq_args->pc; + } else { + /* + * This frame has a non-standard format, and we + * didn't fix it, because the data looked wrong. + * Refuse to output this frame. + */ + return -EINVAL; + } + } + return 0; } -void notrace walk_stackframe(struct stackframe *frame, +void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) { while (1) { @@ -61,7 +120,7 @@ void notrace walk_stackframe(struct stackframe *frame, if (fn(frame, data)) break; - ret = unwind_frame(frame); + ret = unwind_frame(tsk, frame); if (ret < 0) break; } @@ -112,8 +171,11 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) frame.sp = current_stack_pointer; frame.pc = (unsigned long)save_stack_trace_tsk; } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = tsk->curr_ret_stack; +#endif - walk_stackframe(&frame, save_trace, &data); + walk_stackframe(tsk, &frame, save_trace, &data); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 1095aa483a1c..66055392f445 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -60,7 +60,6 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) */ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { - struct mm_struct *mm = current->active_mm; int ret; unsigned long flags; @@ -87,22 +86,11 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) ret = __cpu_suspend_enter(arg, fn); if (ret == 0) { /* - * We are resuming from reset with TTBR0_EL1 set to the - * idmap to enable the MMU; set the TTBR0 to the reserved - * page tables to prevent speculative TLB allocations, flush - * the local tlb and set the default tcr_el1.t0sz so that - * the TTBR0 address space set-up is properly restored. - * If the current active_mm != &init_mm we entered cpu_suspend - * with mappings in TTBR0 that must be restored, so we switch - * them back to complete the address space configuration - * restoration before returning. + * We are resuming from reset with the idmap active in TTBR0_EL1. + * We must uninstall the idmap and restore the expected MMU + * state before we can possibly return to userspace. */ - cpu_set_reserved_ttbr0(); - local_flush_tlb_all(); - cpu_set_default_tcr_t0sz(); - - if (mm != &init_mm) - cpu_switch_mm(mm->pgd, mm); + cpu_uninstall_idmap(); /* * Restore per-cpu offset before any kernel diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 13339b6ffc1a..59779699a1a4 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,8 +52,11 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.sp = regs->sp; frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = -1; /* no task info */ +#endif do { - int ret = unwind_frame(&frame); + int ret = unwind_frame(NULL, &frame); if (ret < 0) return 0; } while (in_lock_functions(frame.pc)); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index e9b9b5364393..c5392081b49b 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -146,17 +146,24 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; + unsigned long irq_stack_ptr; + int skip; + + /* + * Switching between stacks is valid when tracing current and in + * non-preemptible context. + */ + if (tsk == current && !preemptible()) + irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + else + irq_stack_ptr = 0; pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); if (!tsk) tsk = current; - if (regs) { - frame.fp = regs->regs[29]; - frame.sp = regs->sp; - frame.pc = regs->pc; - } else if (tsk == current) { + if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; frame.pc = (unsigned long)dump_backtrace; @@ -168,21 +175,49 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.sp = thread_saved_sp(tsk); frame.pc = thread_saved_pc(tsk); } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = tsk->curr_ret_stack; +#endif - pr_emerg("Call trace:\n"); + skip = !!regs; + printk("Call trace:\n"); while (1) { unsigned long where = frame.pc; unsigned long stack; int ret; - dump_backtrace_entry(where); - ret = unwind_frame(&frame); + /* skip until specified stack frame */ + if (!skip) { + dump_backtrace_entry(where); + } else if (frame.fp == regs->regs[29]) { + skip = 0; + /* + * Mostly, this is the case where this function is + * called in panic/abort. As exception handler's + * stack frame does not contain the corresponding pc + * at which an exception has taken place, use regs->pc + * instead. + */ + dump_backtrace_entry(regs->pc); + } + ret = unwind_frame(tsk, &frame); if (ret < 0) break; stack = frame.sp; - if (in_exception_text(where)) + if (in_exception_text(where)) { + /* + * If we switched to the irq_stack before calling this + * exception handler, then the pt_regs will be on the + * task stack. The easiest way to tell is if the large + * pt_regs would overlap with the end of the irq_stack. + */ + if (stack < irq_stack_ptr && + (stack + sizeof(struct pt_regs)) > irq_stack_ptr) + stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); + dump_mem("", "Exception stack", stack, stack + sizeof(struct pt_regs), false); + } } } @@ -456,22 +491,22 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) void __pte_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pte %016lx.\n", file, line, val); + pr_err("%s:%d: bad pte %016lx.\n", file, line, val); } void __pmd_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val); + pr_err("%s:%d: bad pmd %016lx.\n", file, line, val); } void __pud_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pud %016lx.\n", file, line, val); + pr_err("%s:%d: bad pud %016lx.\n", file, line, val); } void __pgd_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val); + pr_err("%s:%d: bad pgd %016lx.\n", file, line, val); } /* GENERIC_BUG traps */ diff --git a/arch/arm64/kernel/vdso/vdso.S b/arch/arm64/kernel/vdso/vdso.S index 60c1db54b41a..82379a70ef03 100644 --- a/arch/arm64/kernel/vdso/vdso.S +++ b/arch/arm64/kernel/vdso/vdso.S @@ -21,9 +21,8 @@ #include <linux/const.h> #include <asm/page.h> - __PAGE_ALIGNED_DATA - .globl vdso_start, vdso_end + .section .rodata .balign PAGE_SIZE vdso_start: .incbin "arch/arm64/kernel/vdso/vdso.so" diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 71426a78db12..e3f6cd740ea3 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -87,15 +87,16 @@ SECTIONS EXIT_CALL *(.discard) *(.discard.*) + *(.interp .dynamic) } - . = PAGE_OFFSET + TEXT_OFFSET; + . = KIMAGE_VADDR + TEXT_OFFSET; .head.text : { _text = .; HEAD_TEXT } - ALIGN_DEBUG_RO + ALIGN_DEBUG_RO_MIN(PAGE_SIZE) .text : { /* Real text segment */ _stext = .; /* Text and read-only data */ __exception_text_start = .; @@ -113,14 +114,12 @@ SECTIONS *(.got) /* Global offset table */ } - ALIGN_DEBUG_RO RO_DATA(PAGE_SIZE) EXCEPTION_TABLE(8) NOTES - ALIGN_DEBUG_RO - _etext = .; /* End of text and rodata section */ ALIGN_DEBUG_RO_MIN(PAGE_SIZE) + _etext = .; /* End of text and rodata section */ __init_begin = .; INIT_TEXT_SECTION(8) @@ -128,7 +127,6 @@ SECTIONS ARM_EXIT_KEEP(EXIT_TEXT) } - ALIGN_DEBUG_RO_MIN(16) .init.data : { INIT_DATA INIT_SETUP(16) @@ -143,9 +141,6 @@ SECTIONS PERCPU_SECTION(L1_CACHE_BYTES) - . = ALIGN(PAGE_SIZE); - __init_end = .; - . = ALIGN(4); .altinstructions : { __alt_instructions = .; @@ -155,8 +150,25 @@ SECTIONS .altinstr_replacement : { *(.altinstr_replacement) } + .rela : ALIGN(8) { + __reloc_start = .; + *(.rela .rela*) + __reloc_end = .; + } + .dynsym : ALIGN(8) { + __dynsym_start = .; + *(.dynsym) + } + .dynstr : { + *(.dynstr) + } + .hash : { + *(.hash) + } . = ALIGN(PAGE_SIZE); + __init_end = .; + _data = .; _sdata = .; RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) @@ -190,4 +202,4 @@ ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K, /* * If padding is applied before .head.text, virt<->phys conversions will fail. */ -ASSERT(_text == (PAGE_OFFSET + TEXT_OFFSET), "HEAD is misaligned") +ASSERT(_text == (KIMAGE_VADDR + TEXT_OFFSET), "HEAD is misaligned") diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 86c289832272..309e3479dc2c 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -923,7 +923,7 @@ __hyp_panic_str: .align 2 /* - * u64 kvm_call_hyp(void *hypfn, ...); + * u64 __kvm_call_hyp(void *hypfn, ...); * * This is not really a variadic function in the classic C-way and care must * be taken when calling this to ensure parameters are passed in registers @@ -940,10 +940,10 @@ __hyp_panic_str: * used to implement __hyp_get_vectors in the same way as in * arch/arm64/kernel/hyp_stub.S. */ -ENTRY(kvm_call_hyp) +ENTRY(__kvm_call_hyp) hvc #0 ret -ENDPROC(kvm_call_hyp) +ENDPROC(__kvm_call_hyp) .macro invalid_vector label, target .align 2 diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 1a811ecf71da..c86b7909ef31 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -4,15 +4,16 @@ lib-y := bitops.o clear_user.o delay.o copy_from_user.o \ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ strchr.o strrchr.o -# Tell the compiler to treat all general purpose registers as -# callee-saved, which allows for efficient runtime patching of the bl -# instruction in the caller with an atomic instruction when supported by -# the CPU. Result and argument registers are handled correctly, based on -# the function prototype. +# Tell the compiler to treat all general purpose registers (with the +# exception of the IP registers, which are already handled by the caller +# in case of a PLT) as callee-saved, which allows for efficient runtime +# patching of the bl instruction in the caller with an atomic instruction +# when supported by the CPU. Result and argument registers are handled +# correctly, based on the function prototype. lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o CFLAGS_atomic_ll_sc.o := -fcall-used-x0 -ffixed-x1 -ffixed-x2 \ -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6 \ -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9 \ -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \ -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \ - -fcall-saved-x16 -fcall-saved-x17 -fcall-saved-x18 + -fcall-saved-x18 diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index a9723c71c52b..5d1cad3ce6d6 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -33,28 +33,28 @@ * Alignment fixed up by hardware. */ ENTRY(__clear_user) -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f 1: -USER(9f, str xzr, [x0], #8 ) +uao_user_alternative 9f, str, sttr, xzr, x0, 8 subs x1, x1, #8 b.pl 1b 2: adds x1, x1, #4 b.mi 3f -USER(9f, str wzr, [x0], #4 ) +uao_user_alternative 9f, str, sttr, wzr, x0, 4 sub x1, x1, #4 3: adds x1, x1, #2 b.mi 4f -USER(9f, strh wzr, [x0], #2 ) +uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 sub x1, x1, #2 4: adds x1, x1, #1 b.mi 5f -USER(9f, strb wzr, [x0] ) +uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) ret ENDPROC(__clear_user) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 4699cd74f87e..17e8306dca29 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -34,7 +34,7 @@ */ .macro ldrb1 ptr, regB, val - USER(9998f, ldrb \ptr, [\regB], \val) + uao_user_alternative 9998f, ldrb, ldtrb, \ptr, \regB, \val .endm .macro strb1 ptr, regB, val @@ -42,7 +42,7 @@ .endm .macro ldrh1 ptr, regB, val - USER(9998f, ldrh \ptr, [\regB], \val) + uao_user_alternative 9998f, ldrh, ldtrh, \ptr, \regB, \val .endm .macro strh1 ptr, regB, val @@ -50,7 +50,7 @@ .endm .macro ldr1 ptr, regB, val - USER(9998f, ldr \ptr, [\regB], \val) + uao_user_alternative 9998f, ldr, ldtr, \ptr, \regB, \val .endm .macro str1 ptr, regB, val @@ -58,7 +58,7 @@ .endm .macro ldp1 ptr, regB, regC, val - USER(9998f, ldp \ptr, \regB, [\regC], \val) + uao_ldp 9998f, \ptr, \regB, \regC, \val .endm .macro stp1 ptr, regB, regC, val @@ -67,11 +67,11 @@ end .req x5 ENTRY(__copy_from_user) -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) add end, x0, x2 #include "copy_template.S" -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) mov x0, #0 // Nothing to copy ret diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 81c8fc93c100..f7292dd08c84 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -35,44 +35,44 @@ * x0 - bytes not copied */ .macro ldrb1 ptr, regB, val - USER(9998f, ldrb \ptr, [\regB], \val) + uao_user_alternative 9998f, ldrb, ldtrb, \ptr, \regB, \val .endm .macro strb1 ptr, regB, val - USER(9998f, strb \ptr, [\regB], \val) + uao_user_alternative 9998f, strb, sttrb, \ptr, \regB, \val .endm .macro ldrh1 ptr, regB, val - USER(9998f, ldrh \ptr, [\regB], \val) + uao_user_alternative 9998f, ldrh, ldtrh, \ptr, \regB, \val .endm .macro strh1 ptr, regB, val - USER(9998f, strh \ptr, [\regB], \val) + uao_user_alternative 9998f, strh, sttrh, \ptr, \regB, \val .endm .macro ldr1 ptr, regB, val - USER(9998f, ldr \ptr, [\regB], \val) + uao_user_alternative 9998f, ldr, ldtr, \ptr, \regB, \val .endm .macro str1 ptr, regB, val - USER(9998f, str \ptr, [\regB], \val) + uao_user_alternative 9998f, str, sttr, \ptr, \regB, \val .endm .macro ldp1 ptr, regB, regC, val - USER(9998f, ldp \ptr, \regB, [\regC], \val) + uao_ldp 9998f, \ptr, \regB, \regC, \val .endm .macro stp1 ptr, regB, regC, val - USER(9998f, stp \ptr, \regB, [\regC], \val) + uao_stp 9998f, \ptr, \regB, \regC, \val .endm end .req x5 ENTRY(__copy_in_user) -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) add end, x0, x2 #include "copy_template.S" -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) mov x0, #0 ret diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S index 512b9a7b980e..4c1e700840b6 100644 --- a/arch/arm64/lib/copy_page.S +++ b/arch/arm64/lib/copy_page.S @@ -18,6 +18,8 @@ #include <linux/const.h> #include <asm/assembler.h> #include <asm/page.h> +#include <asm/cpufeature.h> +#include <asm/alternative.h> /* * Copy a page from src to dest (both are page aligned) @@ -27,20 +29,65 @@ * x1 - src */ ENTRY(copy_page) - /* Assume cache line size is 64 bytes. */ - prfm pldl1strm, [x1, #64] -1: ldp x2, x3, [x1] +alternative_if_not ARM64_HAS_NO_HW_PREFETCH + nop + nop +alternative_else + # Prefetch two cache lines ahead. + prfm pldl1strm, [x1, #128] + prfm pldl1strm, [x1, #256] +alternative_endif + + ldp x2, x3, [x1] ldp x4, x5, [x1, #16] ldp x6, x7, [x1, #32] ldp x8, x9, [x1, #48] - add x1, x1, #64 - prfm pldl1strm, [x1, #64] + ldp x10, x11, [x1, #64] + ldp x12, x13, [x1, #80] + ldp x14, x15, [x1, #96] + ldp x16, x17, [x1, #112] + + mov x18, #(PAGE_SIZE - 128) + add x1, x1, #128 +1: + subs x18, x18, #128 + +alternative_if_not ARM64_HAS_NO_HW_PREFETCH + nop +alternative_else + prfm pldl1strm, [x1, #384] +alternative_endif + stnp x2, x3, [x0] + ldp x2, x3, [x1] stnp x4, x5, [x0, #16] + ldp x4, x5, [x1, #16] stnp x6, x7, [x0, #32] + ldp x6, x7, [x1, #32] stnp x8, x9, [x0, #48] - add x0, x0, #64 - tst x1, #(PAGE_SIZE - 1) - b.ne 1b + ldp x8, x9, [x1, #48] + stnp x10, x11, [x0, #64] + ldp x10, x11, [x1, #64] + stnp x12, x13, [x0, #80] + ldp x12, x13, [x1, #80] + stnp x14, x15, [x0, #96] + ldp x14, x15, [x1, #96] + stnp x16, x17, [x0, #112] + ldp x16, x17, [x1, #112] + + add x0, x0, #128 + add x1, x1, #128 + + b.gt 1b + + stnp x2, x3, [x0] + stnp x4, x5, [x0, #16] + stnp x6, x7, [x0, #32] + stnp x8, x9, [x0, #48] + stnp x10, x11, [x0, #64] + stnp x12, x13, [x0, #80] + stnp x14, x15, [x0, #96] + stnp x16, x17, [x0, #112] + ret ENDPROC(copy_page) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 7512bbbc07ac..21faae60f988 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -37,7 +37,7 @@ .endm .macro strb1 ptr, regB, val - USER(9998f, strb \ptr, [\regB], \val) + uao_user_alternative 9998f, strb, sttrb, \ptr, \regB, \val .endm .macro ldrh1 ptr, regB, val @@ -45,7 +45,7 @@ .endm .macro strh1 ptr, regB, val - USER(9998f, strh \ptr, [\regB], \val) + uao_user_alternative 9998f, strh, sttrh, \ptr, \regB, \val .endm .macro ldr1 ptr, regB, val @@ -53,7 +53,7 @@ .endm .macro str1 ptr, regB, val - USER(9998f, str \ptr, [\regB], \val) + uao_user_alternative 9998f, str, sttr, \ptr, \regB, \val .endm .macro ldp1 ptr, regB, regC, val @@ -61,16 +61,16 @@ .endm .macro stp1 ptr, regB, regC, val - USER(9998f, stp \ptr, \regB, [\regC], \val) + uao_stp 9998f, \ptr, \regB, \regC, \val .endm end .req x5 ENTRY(__copy_to_user) -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) add end, x0, x2 #include "copy_template.S" -ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) mov x0, #0 ret diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index cfa44a6adc0a..6df07069a025 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -81,26 +81,32 @@ ENDPROC(__flush_cache_user_range) /* * __flush_dcache_area(kaddr, size) * - * Ensure that the data held in the page kaddr is written back to the - * page in question. + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned and invalidated to the PoC. * * - kaddr - kernel address * - size - size in question */ ENTRY(__flush_dcache_area) - dcache_line_size x2, x3 - add x1, x0, x1 - sub x3, x2, #1 - bic x0, x0, x3 -1: dc civac, x0 // clean & invalidate D line / unified line - add x0, x0, x2 - cmp x0, x1 - b.lo 1b - dsb sy + dcache_by_line_op civac, sy, x0, x1, x2, x3 ret ENDPIPROC(__flush_dcache_area) /* + * __clean_dcache_area_pou(kaddr, size) + * + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned to the PoU. + * + * - kaddr - kernel address + * - size - size in question + */ +ENTRY(__clean_dcache_area_pou) + dcache_by_line_op cvau, ish, x0, x1, x2, x3 + ret +ENDPROC(__clean_dcache_area_pou) + +/* * __inval_cache_range(start, end) * - start - start address of region * - end - end address of region diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index e87f53ff5f58..7275628ba59f 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -187,7 +187,7 @@ switch_mm_fastpath: static int asids_init(void) { - int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4); + int fld = cpuid_feature_extract_field(read_cpuid(SYS_ID_AA64MMFR0_EL1), 4); switch (fld) { default: diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 13bbc3be6f5a..22e4cb4d6f53 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -24,8 +24,9 @@ void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr) { + struct page *page = virt_to_page(kto); copy_page(kto, kfrom); - __flush_dcache_area(kto, PAGE_SIZE); + flush_dcache_page(page); } EXPORT_SYMBOL_GPL(__cpu_copy_user_page); diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 354144e33218..a6e757cbab77 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -40,7 +40,7 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, static struct gen_pool *atomic_pool; #define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K -static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE; +static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; static int __init early_coherent_pool(char *p) { @@ -896,7 +896,7 @@ static int __iommu_attach_notifier(struct notifier_block *nb, return 0; } -static int register_iommu_dma_ops_notifier(struct bus_type *bus) +static int __init register_iommu_dma_ops_notifier(struct bus_type *bus) { struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL); int ret; diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 5a22a119a74c..6be918478f85 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -35,7 +35,9 @@ struct addr_marker { }; enum address_markers_idx { - VMALLOC_START_NR = 0, + MODULES_START_NR = 0, + MODULES_END_NR, + VMALLOC_START_NR, VMALLOC_END_NR, #ifdef CONFIG_SPARSEMEM_VMEMMAP VMEMMAP_START_NR, @@ -45,12 +47,12 @@ enum address_markers_idx { FIXADDR_END_NR, PCI_START_NR, PCI_END_NR, - MODULES_START_NR, - MODUELS_END_NR, KERNEL_SPACE_NR, }; static struct addr_marker address_markers[] = { + { MODULES_VADDR, "Modules start" }, + { MODULES_END, "Modules end" }, { VMALLOC_START, "vmalloc() Area" }, { VMALLOC_END, "vmalloc() End" }, #ifdef CONFIG_SPARSEMEM_VMEMMAP @@ -61,9 +63,7 @@ static struct addr_marker address_markers[] = { { FIXADDR_TOP, "Fixmap end" }, { PCI_IO_START, "PCI I/O start" }, { PCI_IO_END, "PCI I/O end" }, - { MODULES_VADDR, "Modules start" }, - { MODULES_END, "Modules end" }, - { PAGE_OFFSET, "Kernel Mapping" }, + { PAGE_OFFSET, "Linear Mapping" }, { -1, NULL }, }; @@ -90,6 +90,11 @@ struct prot_bits { static const struct prot_bits pte_bits[] = { { + .mask = PTE_VALID, + .val = PTE_VALID, + .set = " ", + .clear = "F", + }, { .mask = PTE_USER, .val = PTE_USER, .set = "USR", diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c index 79444279ba8c..81acd4706878 100644 --- a/arch/arm64/mm/extable.c +++ b/arch/arm64/mm/extable.c @@ -11,7 +11,7 @@ int fixup_exception(struct pt_regs *regs) fixup = search_exception_tables(instruction_pointer(regs)); if (fixup) - regs->pc = fixup->fixup; + regs->pc = (unsigned long)&fixup->fixup + fixup->fixup; return fixup != NULL; } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 92ddac1e8ca2..44e56de23f79 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -192,6 +192,14 @@ out: return fault; } +static inline int permission_fault(unsigned int esr) +{ + unsigned int ec = (esr & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT; + unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; + + return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); +} + static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -225,12 +233,13 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } - /* - * PAN bit set implies the fault happened in kernel space, but not - * in the arch's user access functions. - */ - if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT)) - goto no_context; + if (permission_fault(esr) && (addr < USER_DS)) { + if (get_fs() == KERNEL_DS) + die("Accessing user space memory with fs=KERNEL_DS", regs, esr); + + if (!search_exception_tables(regs->pc)) + die("Accessing user space memory outside uaccess.h routines", regs, esr); + } /* * As per x86, we may deadlock here. However, since the kernel only @@ -561,3 +570,16 @@ void cpu_enable_pan(void *__unused) config_sctlr_el1(SCTLR_EL1_SPAN, 0); } #endif /* CONFIG_ARM64_PAN */ + +#ifdef CONFIG_ARM64_UAO +/* + * Kernel threads have fs=KERNEL_DS by default, and don't need to call + * set_fs(), devtmpfs in particular relies on this behaviour. + * We need to enable the feature at runtime (instead of adding it to + * PSR_MODE_EL1h) as the feature may not be implemented by the cpu. + */ +void cpu_enable_uao(void *__unused) +{ + asm(SET_PSTATE_UAO(1)); +} +#endif /* CONFIG_ARM64_UAO */ diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index c26b804015e8..46649d6e6c5a 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -34,19 +34,24 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, __flush_icache_all(); } +static void sync_icache_aliases(void *kaddr, unsigned long len) +{ + unsigned long addr = (unsigned long)kaddr; + + if (icache_is_aliasing()) { + __clean_dcache_area_pou(kaddr, len); + __flush_icache_all(); + } else { + flush_icache_range(addr, addr + len); + } +} + static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *kaddr, unsigned long len) { - if (vma->vm_flags & VM_EXEC) { - unsigned long addr = (unsigned long)kaddr; - if (icache_is_aliasing()) { - __flush_dcache_area(kaddr, len); - __flush_icache_all(); - } else { - flush_icache_range(addr, addr + len); - } - } + if (vma->vm_flags & VM_EXEC) + sync_icache_aliases(kaddr, len); } /* @@ -74,13 +79,11 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) if (!page_mapping(page)) return; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) { - __flush_dcache_area(page_address(page), - PAGE_SIZE << compound_order(page)); + if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + sync_icache_aliases(page_address(page), + PAGE_SIZE << compound_order(page)); + else if (icache_is_aivivt()) __flush_icache_all(); - } else if (icache_is_aivivt()) { - __flush_icache_all(); - } } /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 383b03ff38f8..da30529bb1f6 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -41,15 +41,273 @@ int pud_huge(pud_t pud) #endif } +static int find_num_contig(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, size_t *pgsize) +{ + pgd_t *pgd = pgd_offset(mm, addr); + pud_t *pud; + pmd_t *pmd; + + *pgsize = PAGE_SIZE; + if (!pte_cont(pte)) + return 1; + if (!pgd_present(*pgd)) { + VM_BUG_ON(!pgd_present(*pgd)); + return 1; + } + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) { + VM_BUG_ON(!pud_present(*pud)); + return 1; + } + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + VM_BUG_ON(!pmd_present(*pmd)); + return 1; + } + if ((pte_t *)pmd == ptep) { + *pgsize = PMD_SIZE; + return CONT_PMDS; + } + return CONT_PTES; +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + size_t pgsize; + int i; + int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize); + unsigned long pfn; + pgprot_t hugeprot; + + if (ncontig == 1) { + set_pte_at(mm, addr, ptep, pte); + return; + } + + pfn = pte_pfn(pte); + hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); + for (i = 0; i < ncontig; i++) { + pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, + pte_val(pfn_pte(pfn, hugeprot))); + set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); + ptep++; + pfn += pgsize >> PAGE_SHIFT; + addr += pgsize; + } +} + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pte_t *pte = NULL; + + pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return NULL; + + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else if (sz == (PAGE_SIZE * CONT_PTES)) { + pmd_t *pmd = pmd_alloc(mm, pud, addr); + + WARN_ON(addr & (sz - 1)); + /* + * Note that if this code were ever ported to the + * 32-bit arm platform then it will cause trouble in + * the case where CONFIG_HIGHPTE is set, since there + * will be no pte_unmap() to correspond with this + * pte_alloc_map(). + */ + pte = pte_alloc_map(mm, NULL, pmd, addr); + } else if (sz == PMD_SIZE) { + if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && + pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } else if (sz == (PMD_SIZE * CONT_PMDS)) { + pmd_t *pmd; + + pmd = pmd_alloc(mm, pud, addr); + WARN_ON(addr & (sz - 1)); + return (pte_t *)pmd; + } + + pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, + sz, pte, pte_val(*pte)); + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); + if (!pgd_present(*pgd)) + return NULL; + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) + return NULL; + + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + return NULL; + + if (pte_cont(pmd_pte(*pmd))) { + pmd = pmd_offset( + pud, (addr & CONT_PMD_MASK)); + return (pte_t *)pmd; + } + if (pmd_huge(*pmd)) + return (pte_t *)pmd; + pte = pte_offset_kernel(pmd, addr); + if (pte_present(*pte) && pte_cont(*pte)) { + pte = pte_offset_kernel( + pmd, (addr & CONT_PTE_MASK)); + return pte; + } + return NULL; +} + +pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable) +{ + size_t pagesize = huge_page_size(hstate_vma(vma)); + + if (pagesize == CONT_PTE_SIZE) { + entry = pte_mkcont(entry); + } else if (pagesize == CONT_PMD_SIZE) { + entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); + } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { + pr_warn("%s: unrecognized huge page size 0x%lx\n", + __func__, pagesize); + } + return entry; +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t pte; + + if (pte_cont(*ptep)) { + int ncontig, i; + size_t pgsize; + pte_t *cpte; + bool is_dirty = false; + + cpte = huge_pte_offset(mm, addr); + ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); + /* save the 1st pte to return */ + pte = ptep_get_and_clear(mm, addr, cpte); + for (i = 1; i < ncontig; ++i) { + /* + * If HW_AFDBM is enabled, then the HW could + * turn on the dirty bit for any of the page + * in the set, so check them all. + */ + ++cpte; + if (pte_dirty(ptep_get_and_clear(mm, addr, cpte))) + is_dirty = true; + } + if (is_dirty) + return pte_mkdirty(pte); + else + return pte; + } else { + return ptep_get_and_clear(mm, addr, ptep); + } +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + pte_t *cpte; + + if (pte_cont(pte)) { + int ncontig, i, changed = 0; + size_t pgsize = 0; + unsigned long pfn = pte_pfn(pte); + /* Select all bits except the pfn */ + pgprot_t hugeprot = + __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ + pte_val(pte)); + + cpte = huge_pte_offset(vma->vm_mm, addr); + pfn = pte_pfn(*cpte); + ncontig = find_num_contig(vma->vm_mm, addr, cpte, + *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) { + changed = ptep_set_access_flags(vma, addr, cpte, + pfn_pte(pfn, + hugeprot), + dirty); + pfn += pgsize >> PAGE_SHIFT; + } + return changed; + } else { + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + } +} + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + if (pte_cont(*ptep)) { + int ncontig, i; + pte_t *cpte; + size_t pgsize = 0; + + cpte = huge_pte_offset(mm, addr); + ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) + ptep_set_wrprotect(mm, addr, cpte); + } else { + ptep_set_wrprotect(mm, addr, ptep); + } +} + +void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + if (pte_cont(*ptep)) { + int ncontig, i; + pte_t *cpte; + size_t pgsize = 0; + + cpte = huge_pte_offset(vma->vm_mm, addr); + ncontig = find_num_contig(vma->vm_mm, addr, cpte, + *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) + ptep_clear_flush(vma, addr, cpte); + } else { + ptep_clear_flush(vma, addr, ptep); + } +} + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); } else { - pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); + pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); return 0; } return 1; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 4cb98aa8c27b..9db46dfb6afb 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -35,7 +35,10 @@ #include <linux/efi.h> #include <linux/swiotlb.h> +#include <asm/boot.h> #include <asm/fixmap.h> +#include <asm/kasan.h> +#include <asm/kernel-pgtable.h> #include <asm/memory.h> #include <asm/sections.h> #include <asm/setup.h> @@ -45,7 +48,13 @@ #include "mm.h" -phys_addr_t memstart_addr __read_mostly = 0; +/* + * We need to be able to catch inadvertent references to memstart_addr + * that occur (potentially in generic code) before arm64_memblock_init() + * executes, which assigns it its actual value. So use a default value + * that cannot be mistaken for a real physical address. + */ +s64 memstart_addr __read_mostly = -1; phys_addr_t arm64_dma_phys_limit __read_mostly; #ifdef CONFIG_BLK_DEV_INITRD @@ -58,8 +67,8 @@ static int __init early_initrd(char *p) if (*endp == ',') { size = memparse(endp + 1, NULL); - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(start + size); + initrd_start = start; + initrd_end = start + size; } return 0; } @@ -71,7 +80,7 @@ early_param("initrd", early_initrd); * currently assumes that for memory starting above 4G, 32-bit devices will * use a DMA offset. */ -static phys_addr_t max_zone_dma_phys(void) +static phys_addr_t __init max_zone_dma_phys(void) { phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); return min(offset + (1ULL << 32), memblock_end_of_DRAM()); @@ -126,11 +135,11 @@ EXPORT_SYMBOL(pfn_valid); #endif #ifndef CONFIG_SPARSEMEM -static void arm64_memory_present(void) +static void __init arm64_memory_present(void) { } #else -static void arm64_memory_present(void) +static void __init arm64_memory_present(void) { struct memblock_region *reg; @@ -159,7 +168,57 @@ early_param("mem", early_mem); void __init arm64_memblock_init(void) { - memblock_enforce_memory_limit(memory_limit); + const s64 linear_region_size = -(s64)PAGE_OFFSET; + + /* + * Ensure that the linear region takes up exactly half of the kernel + * virtual address space. This way, we can distinguish a linear address + * from a kernel/module/vmalloc address by testing a single bit. + */ + BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1)); + + /* + * Select a suitable value for the base of physical memory. + */ + memstart_addr = round_down(memblock_start_of_DRAM(), + ARM64_MEMSTART_ALIGN); + + /* + * Remove the memory that we will not be able to cover with the + * linear mapping. Take care not to clip the kernel which may be + * high in memory. + */ + memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa(_end)), + ULLONG_MAX); + if (memblock_end_of_DRAM() > linear_region_size) + memblock_remove(0, memblock_end_of_DRAM() - linear_region_size); + + /* + * Apply the memory limit if it was set. Since the kernel may be loaded + * high up in memory, add back the kernel region that must be accessible + * via the linear mapping. + */ + if (memory_limit != (phys_addr_t)ULLONG_MAX) { + memblock_enforce_memory_limit(memory_limit); + memblock_add(__pa(_text), (u64)(_end - _text)); + } + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + extern u16 memstart_offset_seed; + u64 range = linear_region_size - + (memblock_end_of_DRAM() - memblock_start_of_DRAM()); + + /* + * If the size of the linear region exceeds, by a sufficient + * margin, the size of the region that the available physical + * memory spans, randomize the linear region as well. + */ + if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) { + range = range / ARM64_MEMSTART_ALIGN + 1; + memstart_addr -= ARM64_MEMSTART_ALIGN * + ((range * memstart_offset_seed) >> 16); + } + } /* * Register the kernel text, kernel data, initrd, and initial @@ -167,8 +226,13 @@ void __init arm64_memblock_init(void) */ memblock_reserve(__pa(_text), _end - _text); #ifdef CONFIG_BLK_DEV_INITRD - if (initrd_start) - memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start); + if (initrd_start) { + memblock_reserve(initrd_start, initrd_end - initrd_start); + + /* the generic initrd code expects virtual addresses */ + initrd_start = __phys_to_virt(initrd_start); + initrd_end = __phys_to_virt(initrd_end); + } #endif early_init_fdt_scan_reserved_mem(); @@ -302,35 +366,36 @@ void __init mem_init(void) #ifdef CONFIG_KASAN " kasan : 0x%16lx - 0x%16lx (%6ld GB)\n" #endif + " modules : 0x%16lx - 0x%16lx (%6ld MB)\n" " vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n" + " .init : 0x%p" " - 0x%p" " (%6ld KB)\n" + " .text : 0x%p" " - 0x%p" " (%6ld KB)\n" + " .data : 0x%p" " - 0x%p" " (%6ld KB)\n" #ifdef CONFIG_SPARSEMEM_VMEMMAP " vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n" " 0x%16lx - 0x%16lx (%6ld MB actual)\n" #endif " fixed : 0x%16lx - 0x%16lx (%6ld KB)\n" " PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n" - " modules : 0x%16lx - 0x%16lx (%6ld MB)\n" - " memory : 0x%16lx - 0x%16lx (%6ld MB)\n" - " .init : 0x%p" " - 0x%p" " (%6ld KB)\n" - " .text : 0x%p" " - 0x%p" " (%6ld KB)\n" - " .data : 0x%p" " - 0x%p" " (%6ld KB)\n", + " memory : 0x%16lx - 0x%16lx (%6ld MB)\n", #ifdef CONFIG_KASAN MLG(KASAN_SHADOW_START, KASAN_SHADOW_END), #endif + MLM(MODULES_VADDR, MODULES_END), MLG(VMALLOC_START, VMALLOC_END), + MLK_ROUNDUP(__init_begin, __init_end), + MLK_ROUNDUP(_text, _etext), + MLK_ROUNDUP(_sdata, _edata), #ifdef CONFIG_SPARSEMEM_VMEMMAP MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE), - MLM((unsigned long)virt_to_page(PAGE_OFFSET), + MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()), (unsigned long)virt_to_page(high_memory)), #endif MLK(FIXADDR_START, FIXADDR_TOP), MLM(PCI_IO_START, PCI_IO_END), - MLM(MODULES_VADDR, MODULES_END), - MLM(PAGE_OFFSET, (unsigned long)high_memory), - MLK_ROUNDUP(__init_begin, __init_end), - MLK_ROUNDUP(_text, _etext), - MLK_ROUNDUP(_sdata, _edata)); + MLM(__phys_to_virt(memblock_start_of_DRAM()), + (unsigned long)high_memory)); #undef MLK #undef MLM @@ -358,9 +423,8 @@ void __init mem_init(void) void free_initmem(void) { - fixup_init(); free_initmem_default(0); - free_alternatives_memory(); + fixup_init(); } #ifdef CONFIG_BLK_DEV_INITRD @@ -381,3 +445,28 @@ static int __init keepinitrd_setup(char *__unused) __setup("keepinitrd", keepinitrd_setup); #endif + +/* + * Dump out memory limit information on panic. + */ +static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p) +{ + if (memory_limit != (phys_addr_t)ULLONG_MAX) { + pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20); + } else { + pr_emerg("Memory Limit: none\n"); + } + return 0; +} + +static struct notifier_block mem_limit_notifier = { + .notifier_call = dump_mem_limit, +}; + +static int __init register_mem_limit_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &mem_limit_notifier); + return 0; +} +__initcall(register_mem_limit_dumper); diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index cf038c7d9fa9..757009daa9ed 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -16,9 +16,12 @@ #include <linux/memblock.h> #include <linux/start_kernel.h> +#include <asm/mmu_context.h> +#include <asm/kernel-pgtable.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> +#include <asm/sections.h> #include <asm/tlbflush.h> static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); @@ -32,7 +35,7 @@ static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, if (pmd_none(*pmd)) pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); - pte = pte_offset_kernel(pmd, addr); + pte = pte_offset_kimg(pmd, addr); do { next = addr + PAGE_SIZE; set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page), @@ -50,7 +53,7 @@ static void __init kasan_early_pmd_populate(pud_t *pud, if (pud_none(*pud)) pud_populate(&init_mm, pud, kasan_zero_pmd); - pmd = pmd_offset(pud, addr); + pmd = pmd_offset_kimg(pud, addr); do { next = pmd_addr_end(addr, end); kasan_early_pte_populate(pmd, addr, next); @@ -67,7 +70,7 @@ static void __init kasan_early_pud_populate(pgd_t *pgd, if (pgd_none(*pgd)) pgd_populate(&init_mm, pgd, kasan_zero_pud); - pud = pud_offset(pgd, addr); + pud = pud_offset_kimg(pgd, addr); do { next = pud_addr_end(addr, end); kasan_early_pmd_populate(pud, addr, next); @@ -96,6 +99,21 @@ asmlinkage void __init kasan_early_init(void) kasan_map_early_shadow(); } +/* + * Copy the current shadow region into a new pgdir. + */ +void __init kasan_copy_shadow(pgd_t *pgdir) +{ + pgd_t *pgd, *pgd_new, *pgd_end; + + pgd = pgd_offset_k(KASAN_SHADOW_START); + pgd_end = pgd_offset_k(KASAN_SHADOW_END); + pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); + do { + set_pgd(pgd_new, *pgd); + } while (pgd++, pgd_new++, pgd != pgd_end); +} + static void __init clear_pgds(unsigned long start, unsigned long end) { @@ -108,18 +126,18 @@ static void __init clear_pgds(unsigned long start, set_pgd(pgd_offset_k(start), __pgd(0)); } -static void __init cpu_set_ttbr1(unsigned long ttbr1) -{ - asm( - " msr ttbr1_el1, %0\n" - " isb" - : - : "r" (ttbr1)); -} - void __init kasan_init(void) { + u64 kimg_shadow_start, kimg_shadow_end; + u64 mod_shadow_start, mod_shadow_end; struct memblock_region *reg; + int i; + + kimg_shadow_start = (u64)kasan_mem_to_shadow(_text); + kimg_shadow_end = (u64)kasan_mem_to_shadow(_end); + + mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR); + mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END); /* * We are going to perform proper setup of shadow memory. @@ -129,13 +147,33 @@ void __init kasan_init(void) * setup will be finished. */ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); - cpu_set_ttbr1(__pa(tmp_pg_dir)); - flush_tlb_all(); + dsb(ishst); + cpu_replace_ttbr1(tmp_pg_dir); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + vmemmap_populate(kimg_shadow_start, kimg_shadow_end, + pfn_to_nid(virt_to_pfn(_text))); + + /* + * vmemmap_populate() has populated the shadow region that covers the + * kernel image with SWAPPER_BLOCK_SIZE mappings, so we have to round + * the start and end addresses to SWAPPER_BLOCK_SIZE as well, to prevent + * kasan_populate_zero_shadow() from replacing the page table entries + * (PMD or PTE) at the edges of the shadow region for the kernel + * image. + */ + kimg_shadow_start = round_down(kimg_shadow_start, SWAPPER_BLOCK_SIZE); + kimg_shadow_end = round_up(kimg_shadow_end, SWAPPER_BLOCK_SIZE); + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, - kasan_mem_to_shadow((void *)MODULES_VADDR)); + (void *)mod_shadow_start); + kasan_populate_zero_shadow((void *)kimg_shadow_end, + kasan_mem_to_shadow((void *)PAGE_OFFSET)); + + if (kimg_shadow_start > mod_shadow_end) + kasan_populate_zero_shadow((void *)mod_shadow_end, + (void *)kimg_shadow_start); for_each_memblock(memory, reg) { void *start = (void *)__phys_to_virt(reg->base); @@ -155,9 +193,16 @@ void __init kasan_init(void) pfn_to_nid(virt_to_pfn(start))); } + /* + * KAsan may reuse the contents of kasan_zero_pte directly, so we + * should make sure that it maps the zero page read-only. + */ + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(&kasan_zero_pte[i], + pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); + memset(kasan_zero_page, 0, PAGE_SIZE); - cpu_set_ttbr1(__pa(swapper_pg_dir)); - flush_tlb_all(); + cpu_replace_ttbr1(swapper_pg_dir); /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 116ad654dd59..41421c724fb9 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -30,8 +30,10 @@ #include <linux/slab.h> #include <linux/stop_machine.h> +#include <asm/barrier.h> #include <asm/cputype.h> #include <asm/fixmap.h> +#include <asm/kasan.h> #include <asm/kernel-pgtable.h> #include <asm/sections.h> #include <asm/setup.h> @@ -44,13 +46,20 @@ u64 idmap_t0sz = TCR_T0SZ(VA_BITS); +u64 kimage_voffset __read_mostly; +EXPORT_SYMBOL(kimage_voffset); + /* * Empty_zero_page is a special page that is used for zero-initialized data * and COW. */ -struct page *empty_zero_page; +unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); +static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; +static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; +static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; + pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -62,16 +71,30 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, } EXPORT_SYMBOL(phys_mem_access_prot); -static void __init *early_alloc(unsigned long sz) +static phys_addr_t __init early_pgtable_alloc(void) { phys_addr_t phys; void *ptr; - phys = memblock_alloc(sz, sz); + phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE); BUG_ON(!phys); - ptr = __va(phys); - memset(ptr, 0, sz); - return ptr; + + /* + * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE + * slot will be free, so we can (ab)use the FIX_PTE slot to initialise + * any level of table. + */ + ptr = pte_set_fixmap(phys); + + memset(ptr, 0, PAGE_SIZE); + + /* + * Implicit barriers also ensure the zeroed page is visible to the page + * table walker + */ + pte_clear_fixmap(); + + return phys; } /* @@ -95,24 +118,30 @@ static void split_pmd(pmd_t *pmd, pte_t *pte) static void alloc_init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { pte_t *pte; if (pmd_none(*pmd) || pmd_sect(*pmd)) { - pte = alloc(PTRS_PER_PTE * sizeof(pte_t)); + phys_addr_t pte_phys; + BUG_ON(!pgtable_alloc); + pte_phys = pgtable_alloc(); + pte = pte_set_fixmap(pte_phys); if (pmd_sect(*pmd)) split_pmd(pmd, pte); - __pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE); + __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); flush_tlb_all(); + pte_clear_fixmap(); } BUG_ON(pmd_bad(*pmd)); - pte = pte_offset_kernel(pmd, addr); + pte = pte_set_fixmap_offset(pmd, addr); do { set_pte(pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); + + pte_clear_fixmap(); } static void split_pud(pud_t *old_pud, pmd_t *pmd) @@ -127,10 +156,29 @@ static void split_pud(pud_t *old_pud, pmd_t *pmd) } while (pmd++, i++, i < PTRS_PER_PMD); } -static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end, +#ifdef CONFIG_DEBUG_PAGEALLOC +static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) +{ + + /* + * If debug_page_alloc is enabled we must map the linear map + * using pages. However, other mappings created by + * create_mapping_noalloc must use sections in some cases. Allow + * sections to be used in those cases, where no pgtable_alloc + * function is provided. + */ + return !pgtable_alloc || !debug_pagealloc_enabled(); +} +#else +static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) +{ + return true; +} +#endif + +static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { pmd_t *pmd; unsigned long next; @@ -139,7 +187,10 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, * Check for initial section mappings in the pgd/pud and remove them. */ if (pud_none(*pud) || pud_sect(*pud)) { - pmd = alloc(PTRS_PER_PMD * sizeof(pmd_t)); + phys_addr_t pmd_phys; + BUG_ON(!pgtable_alloc); + pmd_phys = pgtable_alloc(); + pmd = pmd_set_fixmap(pmd_phys); if (pud_sect(*pud)) { /* * need to have the 1G of mappings continue to be @@ -147,19 +198,20 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, */ split_pud(pud, pmd); } - pud_populate(mm, pud, pmd); + __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); flush_tlb_all(); + pmd_clear_fixmap(); } BUG_ON(pud_bad(*pud)); - pmd = pmd_offset(pud, addr); + pmd = pmd_set_fixmap_offset(pud, addr); do { next = pmd_addr_end(addr, end); /* try section mapping first */ - if (((addr | next | phys) & ~SECTION_MASK) == 0) { + if (((addr | next | phys) & ~SECTION_MASK) == 0 && + block_mappings_allowed(pgtable_alloc)) { pmd_t old_pmd =*pmd; - set_pmd(pmd, __pmd(phys | - pgprot_val(mk_sect_prot(prot)))); + pmd_set_huge(pmd, phys, prot); /* * Check for previous table entries created during * boot (__create_page_tables) and flush them. @@ -167,17 +219,19 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, if (!pmd_none(old_pmd)) { flush_tlb_all(); if (pmd_table(old_pmd)) { - phys_addr_t table = __pa(pte_offset_map(&old_pmd, 0)); + phys_addr_t table = pmd_page_paddr(old_pmd); if (!WARN_ON_ONCE(slab_is_available())) memblock_free(table, PAGE_SIZE); } } } else { alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), - prot, alloc); + prot, pgtable_alloc); } phys += next - addr; } while (pmd++, addr = next, addr != end); + + pmd_clear_fixmap(); } static inline bool use_1G_block(unsigned long addr, unsigned long next, @@ -192,31 +246,32 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, return true; } -static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end, +static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { pud_t *pud; unsigned long next; if (pgd_none(*pgd)) { - pud = alloc(PTRS_PER_PUD * sizeof(pud_t)); - pgd_populate(mm, pgd, pud); + phys_addr_t pud_phys; + BUG_ON(!pgtable_alloc); + pud_phys = pgtable_alloc(); + __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); } BUG_ON(pgd_bad(*pgd)); - pud = pud_offset(pgd, addr); + pud = pud_set_fixmap_offset(pgd, addr); do { next = pud_addr_end(addr, end); /* * For 4K granule only, attempt to put down a 1GB block */ - if (use_1G_block(addr, next, phys)) { + if (use_1G_block(addr, next, phys) && + block_mappings_allowed(pgtable_alloc)) { pud_t old_pud = *pud; - set_pud(pud, __pud(phys | - pgprot_val(mk_sect_prot(prot)))); + pud_set_huge(pud, phys, prot); /* * If we have an old value for a pud, it will @@ -228,51 +283,74 @@ static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, if (!pud_none(old_pud)) { flush_tlb_all(); if (pud_table(old_pud)) { - phys_addr_t table = __pa(pmd_offset(&old_pud, 0)); + phys_addr_t table = pud_page_paddr(old_pud); if (!WARN_ON_ONCE(slab_is_available())) memblock_free(table, PAGE_SIZE); } } } else { - alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc); + alloc_init_pmd(pud, addr, next, phys, prot, + pgtable_alloc); } phys += next - addr; } while (pud++, addr = next, addr != end); + + pud_clear_fixmap(); } /* * Create the page directory entries and any necessary page tables for the * mapping specified by 'md'. */ -static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, - phys_addr_t phys, unsigned long virt, +static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { unsigned long addr, length, end, next; + /* + * If the virtual and physical address don't have the same offset + * within a page, we cannot map the region as the caller expects. + */ + if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) + return; + + phys &= PAGE_MASK; addr = virt & PAGE_MASK; length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(mm, pgd, addr, next, phys, prot, alloc); + alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc); phys += next - addr; } while (pgd++, addr = next, addr != end); } -static void *late_alloc(unsigned long size) +static phys_addr_t late_pgtable_alloc(void) { - void *ptr; - - BUG_ON(size > PAGE_SIZE); - ptr = (void *)__get_free_page(PGALLOC_GFP); + void *ptr = (void *)__get_free_page(PGALLOC_GFP); BUG_ON(!ptr); - return ptr; + + /* Ensure the zeroed page is visible to the page table walker */ + dsb(ishst); + return __pa(ptr); +} + +static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*alloc)(void)) +{ + init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc); } -static void __init create_mapping(phys_addr_t phys, unsigned long virt, +/* + * This function can only be used to modify existing table entries, + * without allocating new levels of table. Note that this permits the + * creation of new section or page entries. + */ +static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < VMALLOC_START) { @@ -280,16 +358,16 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt, - size, prot, early_alloc); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, + NULL); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - __create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot, - late_alloc); + __create_pgd_mapping(mm->pgd, phys, virt, size, prot, + late_pgtable_alloc); } static void create_mapping_late(phys_addr_t phys, unsigned long virt, @@ -301,69 +379,57 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, return; } - return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), - phys, virt, size, prot, late_alloc); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, + late_pgtable_alloc); } -#ifdef CONFIG_DEBUG_RODATA -static void __init __map_memblock(phys_addr_t start, phys_addr_t end) +static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) { + unsigned long kernel_start = __pa(_stext); + unsigned long kernel_end = __pa(_etext); + /* - * Set up the executable regions using the existing section mappings - * for now. This will get more fine grained later once all memory - * is mapped + * Take care not to create a writable alias for the + * read-only text and rodata sections of the kernel image. */ - unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); - unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); - - if (end < kernel_x_start) { - create_mapping(start, __phys_to_virt(start), - end - start, PAGE_KERNEL); - } else if (start >= kernel_x_end) { - create_mapping(start, __phys_to_virt(start), - end - start, PAGE_KERNEL); - } else { - if (start < kernel_x_start) - create_mapping(start, __phys_to_virt(start), - kernel_x_start - start, - PAGE_KERNEL); - create_mapping(kernel_x_start, - __phys_to_virt(kernel_x_start), - kernel_x_end - kernel_x_start, - PAGE_KERNEL_EXEC); - if (kernel_x_end < end) - create_mapping(kernel_x_end, - __phys_to_virt(kernel_x_end), - end - kernel_x_end, - PAGE_KERNEL); + + /* No overlap with the kernel text */ + if (end < kernel_start || start >= kernel_end) { + __create_pgd_mapping(pgd, start, __phys_to_virt(start), + end - start, PAGE_KERNEL, + early_pgtable_alloc); + return; } + /* + * This block overlaps the kernel text mapping. + * Map the portion(s) which don't overlap. + */ + if (start < kernel_start) + __create_pgd_mapping(pgd, start, + __phys_to_virt(start), + kernel_start - start, PAGE_KERNEL, + early_pgtable_alloc); + if (kernel_end < end) + __create_pgd_mapping(pgd, kernel_end, + __phys_to_virt(kernel_end), + end - kernel_end, PAGE_KERNEL, + early_pgtable_alloc); + + /* + * Map the linear alias of the [_stext, _etext) interval as + * read-only/non-executable. This makes the contents of the + * region accessible to subsystems such as hibernate, but + * protects it from inadvertent modification or execution. + */ + __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start), + kernel_end - kernel_start, PAGE_KERNEL_RO, + early_pgtable_alloc); } -#else -static void __init __map_memblock(phys_addr_t start, phys_addr_t end) -{ - create_mapping(start, __phys_to_virt(start), end - start, - PAGE_KERNEL_EXEC); -} -#endif -static void __init map_mem(void) +static void __init map_mem(pgd_t *pgd) { struct memblock_region *reg; - phys_addr_t limit; - - /* - * Temporarily limit the memblock range. We need to do this as - * create_mapping requires puds, pmds and ptes to be allocated from - * memory addressable from the initial direct kernel mapping. - * - * The initial direct kernel mapping, located at swapper_pg_dir, gives - * us PUD_SIZE (with SECTION maps) or PMD_SIZE (without SECTION maps, - * memory starting from PHYS_OFFSET (which must be aligned to 2MB as - * per Documentation/arm64/booting.txt). - */ - limit = PHYS_OFFSET + SWAPPER_INIT_MAP_SIZE; - memblock_set_current_limit(limit); /* map all the memory banks */ for_each_memblock(memory, reg) { @@ -373,69 +439,87 @@ static void __init map_mem(void) if (start >= end) break; - if (ARM64_SWAPPER_USES_SECTION_MAPS) { - /* - * For the first memory bank align the start address and - * current memblock limit to prevent create_mapping() from - * allocating pte page tables from unmapped memory. With - * the section maps, if the first block doesn't end on section - * size boundary, create_mapping() will try to allocate a pte - * page, which may be returned from an unmapped area. - * When section maps are not used, the pte page table for the - * current limit is already present in swapper_pg_dir. - */ - if (start < limit) - start = ALIGN(start, SECTION_SIZE); - if (end < limit) { - limit = end & SECTION_MASK; - memblock_set_current_limit(limit); - } - } - __map_memblock(start, end); + __map_memblock(pgd, start, end); } - - /* Limit no longer required. */ - memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } -static void __init fixup_executable(void) +void mark_rodata_ro(void) { -#ifdef CONFIG_DEBUG_RODATA - /* now that we are actually fully mapped, make the start/end more fine grained */ - if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { - unsigned long aligned_start = round_down(__pa(_stext), - SWAPPER_BLOCK_SIZE); + if (!IS_ENABLED(CONFIG_DEBUG_RODATA)) + return; - create_mapping(aligned_start, __phys_to_virt(aligned_start), - __pa(_stext) - aligned_start, - PAGE_KERNEL); - } + create_mapping_late(__pa(_stext), (unsigned long)_stext, + (unsigned long)_etext - (unsigned long)_stext, + PAGE_KERNEL_ROX); +} - if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { - unsigned long aligned_end = round_up(__pa(__init_end), - SWAPPER_BLOCK_SIZE); - create_mapping(__pa(__init_end), (unsigned long)__init_end, - aligned_end - __pa(__init_end), - PAGE_KERNEL); - } -#endif +void fixup_init(void) +{ + /* + * Unmap the __init region but leave the VM area in place. This + * prevents the region from being reused for kernel modules, which + * is not supported by kallsyms. + */ + unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void) +static void __init map_kernel_chunk(pgd_t *pgd, void *va_start, void *va_end, + pgprot_t prot, struct vm_struct *vma) { - create_mapping_late(__pa(_stext), (unsigned long)_stext, - (unsigned long)_etext - (unsigned long)_stext, - PAGE_KERNEL_ROX); + phys_addr_t pa_start = __pa(va_start); + unsigned long size = va_end - va_start; + + BUG_ON(!PAGE_ALIGNED(pa_start)); + BUG_ON(!PAGE_ALIGNED(size)); + + __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, + early_pgtable_alloc); + vma->addr = va_start; + vma->phys_addr = pa_start; + vma->size = size; + vma->flags = VM_MAP; + vma->caller = __builtin_return_address(0); + + vm_area_add_early(vma); } -#endif -void fixup_init(void) +/* + * Create fine-grained mappings for the kernel. + */ +static void __init map_kernel(pgd_t *pgd) { - create_mapping_late(__pa(__init_begin), (unsigned long)__init_begin, - (unsigned long)__init_end - (unsigned long)__init_begin, - PAGE_KERNEL); + static struct vm_struct vmlinux_text, vmlinux_init, vmlinux_data; + + map_kernel_chunk(pgd, _stext, _etext, PAGE_KERNEL_EXEC, &vmlinux_text); + map_kernel_chunk(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC, + &vmlinux_init); + map_kernel_chunk(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data); + + if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { + /* + * The fixmap falls in a separate pgd to the kernel, and doesn't + * live in the carveout for the swapper_pg_dir. We can simply + * re-use the existing dir for the fixmap. + */ + set_pgd(pgd_offset_raw(pgd, FIXADDR_START), + *pgd_offset_k(FIXADDR_START)); + } else if (CONFIG_PGTABLE_LEVELS > 3) { + /* + * The fixmap shares its top level pgd entry with the kernel + * mapping. This can really only occur when we are running + * with 16k/4 levels, so we can simply reuse the pud level + * entry instead. + */ + BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); + set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START), + __pud(__pa(bm_pmd) | PUD_TYPE_TABLE)); + pud_clear_fixmap(); + } else { + BUG(); + } + + kasan_copy_shadow(pgd); } /* @@ -444,28 +528,35 @@ void fixup_init(void) */ void __init paging_init(void) { - void *zero_page; + phys_addr_t pgd_phys = early_pgtable_alloc(); + pgd_t *pgd = pgd_set_fixmap(pgd_phys); - map_mem(); - fixup_executable(); + map_kernel(pgd); + map_mem(pgd); - /* allocate the zero page. */ - zero_page = early_alloc(PAGE_SIZE); - - bootmem_init(); - - empty_zero_page = virt_to_page(zero_page); + /* + * We want to reuse the original swapper_pg_dir so we don't have to + * communicate the new address to non-coherent secondaries in + * secondary_entry, and so cpu_switch_mm can generate the address with + * adrp+add rather than a load from some global variable. + * + * To do this we need to go via a temporary pgd. + */ + cpu_replace_ttbr1(__va(pgd_phys)); + memcpy(swapper_pg_dir, pgd, PAGE_SIZE); + cpu_replace_ttbr1(swapper_pg_dir); - /* Ensure the zero page is visible to the page table walker */ - dsb(ishst); + pgd_clear_fixmap(); + memblock_free(pgd_phys, PAGE_SIZE); /* - * TTBR0 is only used for the identity mapping at this stage. Make it - * point to zero page to avoid speculatively fetching new entries. + * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd + * allocated with it. */ - cpu_set_reserved_ttbr0(); - local_flush_tlb_all(); - cpu_set_default_tcr_t0sz(); + memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE, + SWAPPER_DIR_SIZE - PAGE_SIZE); + + bootmem_init(); } /* @@ -552,21 +643,13 @@ void vmemmap_free(unsigned long start, unsigned long end) } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; -#if CONFIG_PGTABLE_LEVELS > 2 -static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss; -#endif -#if CONFIG_PGTABLE_LEVELS > 3 -static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss; -#endif - static inline pud_t * fixmap_pud(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); - return pud_offset(pgd, addr); + return pud_offset_kimg(pgd, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) @@ -575,16 +658,12 @@ static inline pmd_t * fixmap_pmd(unsigned long addr) BUG_ON(pud_none(*pud) || pud_bad(*pud)); - return pmd_offset(pud, addr); + return pmd_offset_kimg(pud, addr); } static inline pte_t * fixmap_pte(unsigned long addr) { - pmd_t *pmd = fixmap_pmd(addr); - - BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd)); - - return pte_offset_kernel(pmd, addr); + return &bm_pte[pte_index(addr)]; } void __init early_fixmap_init(void) @@ -595,15 +674,26 @@ void __init early_fixmap_init(void) unsigned long addr = FIXADDR_START; pgd = pgd_offset_k(addr); - pgd_populate(&init_mm, pgd, bm_pud); - pud = pud_offset(pgd, addr); + if (CONFIG_PGTABLE_LEVELS > 3 && + !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa(bm_pud))) { + /* + * We only end up here if the kernel mapping and the fixmap + * share the top level pgd entry, which should only happen on + * 16k/4 levels configurations. + */ + BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); + pud = pud_offset_kimg(pgd, addr); + } else { + pgd_populate(&init_mm, pgd, bm_pud); + pud = fixmap_pud(addr); + } pud_populate(&init_mm, pud, bm_pmd); - pmd = pmd_offset(pud, addr); + pmd = fixmap_pmd(addr); pmd_populate_kernel(&init_mm, pmd, bm_pte); /* * The boot-ioremap range spans multiple pmds, for which - * we are not preparted: + * we are not prepared: */ BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); @@ -642,11 +732,10 @@ void __set_fixmap(enum fixed_addresses idx, } } -void *__init fixmap_remap_fdt(phys_addr_t dt_phys) +void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); - pgprot_t prot = PAGE_KERNEL_RO; - int size, offset; + int offset; void *dt_virt; /* @@ -663,7 +752,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) /* * Make sure that the FDT region can be mapped without the need to * allocate additional translation table pages, so that it is safe - * to call create_mapping() this early. + * to call create_mapping_noalloc() this early. * * On 64k pages, the FDT will be mapped using PTEs, so we need to * be in the same PMD as the rest of the fixmap. @@ -679,21 +768,73 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ - create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, - SWAPPER_BLOCK_SIZE, prot); + create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), + dt_virt_base, SWAPPER_BLOCK_SIZE, prot); if (fdt_check_header(dt_virt) != 0) return NULL; - size = fdt_totalsize(dt_virt); - if (size > MAX_FDT_SIZE) + *size = fdt_totalsize(dt_virt); + if (*size > MAX_FDT_SIZE) return NULL; - if (offset + size > SWAPPER_BLOCK_SIZE) - create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, - round_up(offset + size, SWAPPER_BLOCK_SIZE), prot); + if (offset + *size > SWAPPER_BLOCK_SIZE) + create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + round_up(offset + *size, SWAPPER_BLOCK_SIZE), prot); - memblock_reserve(dt_phys, size); + return dt_virt; +} +void *__init fixmap_remap_fdt(phys_addr_t dt_phys) +{ + void *dt_virt; + int size; + + dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); + if (!dt_virt) + return NULL; + + memblock_reserve(dt_phys, size); return dt_virt; } + +int __init arch_ioremap_pud_supported(void) +{ + /* only 4k granule supports level 1 block mappings */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES); +} + +int __init arch_ioremap_pmd_supported(void) +{ + return 1; +} + +int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +{ + BUG_ON(phys & ~PUD_MASK); + set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot)))); + return 1; +} + +int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +{ + BUG_ON(phys & ~PMD_MASK); + set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot)))); + return 1; +} + +int pud_clear_huge(pud_t *pud) +{ + if (!pud_sect(*pud)) + return 0; + pud_clear(pud); + return 1; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + if (!pmd_sect(*pmd)) + return 0; + pmd_clear(pmd); + return 1; +} diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index cf6240741134..ca6d268e3313 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/sched.h> +#include <linux/vmalloc.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -36,14 +37,32 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, return 0; } +/* + * This function assumes that the range is mapped with PAGE_SIZE pages. + */ +static int __change_memory_common(unsigned long start, unsigned long size, + pgprot_t set_mask, pgprot_t clear_mask) +{ + struct page_change_data data; + int ret; + + data.set_mask = set_mask; + data.clear_mask = clear_mask; + + ret = apply_to_page_range(&init_mm, start, size, change_page_range, + &data); + + flush_tlb_kernel_range(start, start + size); + return ret; +} + static int change_memory_common(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) { unsigned long start = addr; unsigned long size = PAGE_SIZE*numpages; unsigned long end = start + size; - int ret; - struct page_change_data data; + struct vm_struct *area; if (!PAGE_ALIGNED(addr)) { start &= PAGE_MASK; @@ -51,23 +70,29 @@ static int change_memory_common(unsigned long addr, int numpages, WARN_ON_ONCE(1); } - if (start < MODULES_VADDR || start >= MODULES_END) - return -EINVAL; - - if (end < MODULES_VADDR || end >= MODULES_END) + /* + * Kernel VA mappings are always live, and splitting live section + * mappings into page mappings may cause TLB conflicts. This means + * we have to ensure that changing the permission bits of the range + * we are operating on does not result in such splitting. + * + * Let's restrict ourselves to mappings created by vmalloc (or vmap). + * Those are guaranteed to consist entirely of page mappings, and + * splitting is never needed. + * + * So check whether the [addr, addr + size) interval is entirely + * covered by precisely one VM area that has the VM_ALLOC flag set. + */ + area = find_vm_area((void *)addr); + if (!area || + end > (unsigned long)area->addr + area->size || + !(area->flags & VM_ALLOC)) return -EINVAL; if (!numpages) return 0; - data.set_mask = set_mask; - data.clear_mask = clear_mask; - - ret = apply_to_page_range(&init_mm, start, size, change_page_range, - &data); - - flush_tlb_kernel_range(start, end); - return ret; + return __change_memory_common(start, size, set_mask, clear_mask); } int set_memory_ro(unsigned long addr, int numpages) @@ -99,3 +124,19 @@ int set_memory_x(unsigned long addr, int numpages) __pgprot(PTE_PXN)); } EXPORT_SYMBOL_GPL(set_memory_x); + +#ifdef CONFIG_DEBUG_PAGEALLOC +void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + unsigned long addr = (unsigned long) page_address(page); + + if (enable) + __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(PTE_VALID), + __pgprot(0)); + else + __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(0), + __pgprot(PTE_VALID)); +} +#endif diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index cb3ba1b812e7..ae11d4e03d0e 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -46,14 +46,14 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } -static int __init pgd_cache_init(void) +void __init pgd_cache_init(void) { + if (PGD_SIZE == PAGE_SIZE) + return; + /* * Naturally aligned pgds required by the architecture. */ - if (PGD_SIZE != PAGE_SIZE) - pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, - SLAB_PANIC, NULL); - return 0; + pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, + SLAB_PANIC, NULL); } -core_initcall(pgd_cache_init); diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index d69dffffaa89..984edcda1850 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -74,3 +74,25 @@ msr pmuserenr_el0, xzr // Disable PMU access from EL0 9000: .endm + +/* + * Macro to perform a data cache maintenance for the interval + * [kaddr, kaddr + size) + * + * op: operation passed to dc instruction + * domain: domain used in dsb instruciton + * kaddr: starting virtual address of the region + * size: size of the region + * Corrupts: kaddr, size, tmp1, tmp2 + */ + .macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2 + dcache_line_size \tmp1, \tmp2 + add \size, \kaddr, \size + sub \tmp2, \tmp1, #1 + bic \kaddr, \kaddr, \tmp2 +9998: dc \op, \kaddr + add \kaddr, \kaddr, \tmp1 + cmp \kaddr, \size + b.lo 9998b + dsb \domain + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index b8f04b3f2786..0c19534a901e 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -140,7 +140,33 @@ ENTRY(cpu_do_switch_mm) ret ENDPROC(cpu_do_switch_mm) - .section ".text.init", #alloc, #execinstr + .pushsection ".idmap.text", "ax" +/* + * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd) + * + * This is the low-level counterpart to cpu_replace_ttbr1, and should not be + * called by anything else. It can only be executed from a TTBR0 mapping. + */ +ENTRY(idmap_cpu_replace_ttbr1) + mrs x2, daif + msr daifset, #0xf + + adrp x1, empty_zero_page + msr ttbr1_el1, x1 + isb + + tlbi vmalle1 + dsb nsh + isb + + msr ttbr1_el1, x0 + isb + + msr daif, x2 + + ret +ENDPROC(idmap_cpu_replace_ttbr1) + .popsection /* * __cpu_setup diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 729f89163bc3..d2256fa97ea0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -11,6 +11,7 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG + select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS select GENERIC_ATOMIC64 if !64BIT select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index b3069fd83468..60e6f07b7e32 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -523,7 +523,7 @@ */ #define ASM_EXCEPTIONTABLE_ENTRY(fault_addr, except_addr) \ .section __ex_table,"aw" ! \ - ASM_ULONG_INSN fault_addr, except_addr ! \ + .word (fault_addr - .), (except_addr - .) ! \ .previous diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 3d0e17bcc8e9..df0f52bd18b4 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -22,6 +22,9 @@ #define __read_mostly __attribute__((__section__(".data..read_mostly"))) +/* Read-only memory is marked before mark_rodata_ro() is called. */ +#define __ro_after_init __read_mostly + void parisc_cache_init(void); /* initializes cache-flushing */ void disable_sr_hashing_asm(int); /* low level support for above */ void disable_sr_hashing(void); /* turns off space register hashing */ diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 845272ce9cc5..7bd69bd43a01 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -121,10 +121,6 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma } } -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); -#endif - #include <asm/kmap_types.h> #define ARCH_HAS_KMAP diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 1960b87c1c8b..6f893d29f1b2 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -60,14 +60,15 @@ static inline long access_ok(int type, const void __user * addr, * use a 32bit (unsigned int) address here. */ +#define ARCH_HAS_RELATIVE_EXTABLE struct exception_table_entry { - unsigned long insn; /* address of insn that is allowed to fault. */ - unsigned long fixup; /* fixup routine */ + int insn; /* relative address of insn that is allowed to fault. */ + int fixup; /* relative address of fixup routine */ }; #define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\ ".section __ex_table,\"aw\"\n" \ - ASM_WORD_INSN #fault_addr ", " #except_addr "\n\t" \ + ".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \ ".previous\n" /* diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f9064449908a..16dbe81c97c9 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -140,12 +140,6 @@ int fixup_exception(struct pt_regs *regs) { const struct exception_table_entry *fix; - /* If we only stored 32bit addresses in the exception table we can drop - * out if we faulted on a 64bit address. */ - if ((sizeof(regs->iaoq[0]) > sizeof(fix->insn)) - && (regs->iaoq[0] >> 32)) - return 0; - fix = search_exception_tables(regs->iaoq[0]); if (fix) { struct exception_data *d; @@ -155,7 +149,8 @@ int fixup_exception(struct pt_regs *regs) d->fault_space = regs->isr; d->fault_addr = regs->ior; - regs->iaoq[0] = ((fix->fixup) & ~3); + regs->iaoq[0] = (unsigned long)&fix->fixup + fix->fixup; + regs->iaoq[0] &= ~3; /* * NOTE: In some cases the faulting instruction * may be in the delay slot of a branch. We diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 436639a31624..9d5e3a27bef2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -289,6 +289,9 @@ config ARCH_SUPPORTS_UPROBES config FIX_EARLYCON_MEM def_bool y +config DEBUG_RODATA + def_bool y + config PGTABLE_LEVELS int default 4 if X86_64 diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 137dfa96aa14..1f6c306a9a00 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -91,28 +91,16 @@ config EFI_PGT_DUMP issues with the mapping of the EFI runtime regions into that table. -config DEBUG_RODATA - bool "Write protect kernel read-only data structures" - default y - depends on DEBUG_KERNEL - ---help--- - Mark the kernel read-only data as write-protected in the pagetables, - in order to catch accidental (and incorrect) writes to such const - data. This is recommended so that we can catch kernel bugs sooner. - If in doubt, say "Y". - config DEBUG_RODATA_TEST - bool "Testcase for the DEBUG_RODATA feature" - depends on DEBUG_RODATA + bool "Testcase for the marking rodata read-only" default y ---help--- - This option enables a testcase for the DEBUG_RODATA - feature as well as for the change_page_attr() infrastructure. + This option enables a testcase for the setting rodata read-only + as well as for the change_page_attr() infrastructure. If in doubt, say "N" config DEBUG_WX bool "Warn on W+X mappings at boot" - depends on DEBUG_RODATA select X86_PTDUMP_CORE ---help--- Generate a warning if any W+X mappings are found at boot. diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 0224987556ce..3f69326ed545 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -140,7 +140,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, fprintf(outfile, "#include <asm/vdso.h>\n"); fprintf(outfile, "\n"); fprintf(outfile, - "static unsigned char raw_data[%lu] __page_aligned_data = {", + "static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {", mapping_size); for (j = 0; j < stripped_len; j++) { if (j % 10 == 0) diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index e63aa38e85fb..61518cf79437 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size); #define mmio_flush_range(addr, size) clflush_cache_range(addr, size) -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); extern const int rodata_test_data; extern int kernel_set_to_readonly; void set_kernel_text_rw(void); void set_kernel_text_ro(void); -#else -static inline void set_kernel_text_rw(void) { } -static inline void set_kernel_text_ro(void) { } -#endif #ifdef CONFIG_DEBUG_RODATA_TEST int rodata_test(void); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 0010c78c4998..08b1f2f6ea50 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -25,6 +25,8 @@ #define EFI32_LOADER_SIGNATURE "EL32" #define EFI64_LOADER_SIGNATURE "EL64" +#define MAX_CMDLINE_ADDRESS UINT_MAX + #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c1adf33fdd0d..bc62e7cbf1b1 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void) } #endif /* CONFIG_KVM_GUEST */ -#ifdef CONFIG_DEBUG_RODATA #define KVM_HYPERCALL \ ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL) -#else -/* On AMD processors, vmcall will generate a trap that we will - * then rewrite to the appropriate instruction. - */ -#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" -#endif /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall * instruction. The hypervisor may replace it with something else but only the diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 0a5242428659..13b6cdd0af57 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -7,7 +7,7 @@ extern char __brk_base[], __brk_limit[]; extern struct exception_table_entry __stop___ex_table[]; -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 311bcf338f07..eb6bd34582c6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -81,9 +81,9 @@ within(unsigned long addr, unsigned long start, unsigned long end) static unsigned long text_ip_addr(unsigned long ip) { /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. + * On x86_64, kernel text mappings are mapped read-only, so we use + * the kernel identity mapping instead of the kernel text mapping + * to modify the kernel text. * * For 32bit kernels, these mappings are same and we can use * kernel identity mapping to modify code. diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 44256a62702b..ed15cd486d06 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -750,9 +750,7 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { int err; -#ifdef CONFIG_DEBUG_RODATA char opc[BREAK_INSTR_SIZE]; -#endif /* CONFIG_DEBUG_RODATA */ bpt->type = BP_BREAKPOINT; err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, @@ -761,7 +759,6 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) return err; err = probe_kernel_write((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); -#ifdef CONFIG_DEBUG_RODATA if (!err) return err; /* @@ -778,13 +775,12 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE)) return -EINVAL; bpt->type = BP_POKE_BREAKPOINT; -#endif /* CONFIG_DEBUG_RODATA */ + return err; } int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) { -#ifdef CONFIG_DEBUG_RODATA int err; char opc[BREAK_INSTR_SIZE]; @@ -801,8 +797,8 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE)) goto knl_write; return err; + knl_write: -#endif /* CONFIG_DEBUG_RODATA */ return probe_kernel_write((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c index 3f92ce07e525..27538f183c3b 100644 --- a/arch/x86/kernel/test_nx.c +++ b/arch/x86/kernel/test_nx.c @@ -142,7 +142,6 @@ static int test_NX(void) * by the error message */ -#ifdef CONFIG_DEBUG_RODATA /* Test 3: Check if the .rodata section is executable */ if (rodata_test_data != 0xC3) { printk(KERN_ERR "test_nx: .rodata marker has invalid value\n"); @@ -151,7 +150,6 @@ static int test_NX(void) printk(KERN_ERR "test_nx: .rodata section is executable\n"); ret = -ENODEV; } -#endif #if 0 /* Test 4: Check if the .data section of a module is executable */ diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c index 5ecbfe5099da..cb4a01b41e27 100644 --- a/arch/x86/kernel/test_rodata.c +++ b/arch/x86/kernel/test_rodata.c @@ -76,5 +76,5 @@ int rodata_test(void) } MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Testcase for the DEBUG_RODATA infrastructure"); +MODULE_DESCRIPTION("Testcase for marking rodata as read-only"); MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 74e4bf11f562..fe133b710bef 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -41,29 +41,28 @@ ENTRY(phys_startup_64) jiffies_64 = jiffies; #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) /* - * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA - * we retain large page mappings for boundaries spanning kernel text, rodata - * and data sections. + * On 64-bit, align RODATA to 2MB so we retain large page mappings for + * boundaries spanning kernel text, rodata and data sections. * * However, kernel identity mappings will have different RWX permissions * to the pages mapping to text and to the pages padding (which are freed) the * text section. Hence kernel identity mappings will be broken to smaller * pages. For 64-bit, kernel text and kernel identity mappings are different, - * so we can enable protection checks that come with CONFIG_DEBUG_RODATA, - * as well as retain 2MB large page mappings for kernel text. + * so we can enable protection checks as well as retain 2MB large page + * mappings for kernel text. */ -#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); +#define X64_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); -#define X64_ALIGN_DEBUG_RODATA_END \ +#define X64_ALIGN_RODATA_END \ . = ALIGN(HPAGE_SIZE); \ __end_rodata_hpage_align = .; #else -#define X64_ALIGN_DEBUG_RODATA_BEGIN -#define X64_ALIGN_DEBUG_RODATA_END +#define X64_ALIGN_RODATA_BEGIN +#define X64_ALIGN_RODATA_END #endif @@ -112,13 +111,11 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 -#if defined(CONFIG_DEBUG_RODATA) /* .text should occupy whole number of pages */ . = ALIGN(PAGE_SIZE); -#endif - X64_ALIGN_DEBUG_RODATA_BEGIN + X64_ALIGN_RODATA_BEGIN RO_DATA(PAGE_SIZE) - X64_ALIGN_DEBUG_RODATA_END + X64_ALIGN_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index cb4ef3de61f9..2ebfbaf61142 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -871,7 +871,6 @@ static noinline int do_test_wp_bit(void) return flag; } -#ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); @@ -960,5 +959,3 @@ void mark_rodata_ro(void) if (__supported_pte_mask & _PAGE_NX) debug_checkwx(); } -#endif - diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec081fe0ce2c..e08d141844ee 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1062,7 +1062,6 @@ void __init mem_init(void) mem_init_print_info(NULL); } -#ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); @@ -1154,8 +1153,6 @@ void mark_rodata_ro(void) debug_checkwx(); } -#endif - int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index b599a780a5a9..4540e8880cd9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -278,7 +278,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, __pa_symbol(__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) /* * Once the kernel maps the text as RO (kernel_set_to_readonly is set), * kernel text mappings for the large page aligned text, rodata sections diff --git a/drivers/base/power/opp/Makefile b/drivers/base/power/opp/Makefile index 33c1e18c41a4..19837ef04d8e 100644 --- a/drivers/base/power/opp/Makefile +++ b/drivers/base/power/opp/Makefile @@ -1,2 +1,3 @@ ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG obj-y += core.o cpu.o +obj-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index f8580900c273..433b60092972 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -13,50 +13,52 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/clk.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/device.h> #include <linux/of.h> #include <linux/export.h> +#include <linux/regulator/consumer.h> #include "opp.h" /* - * The root of the list of all devices. All device_opp structures branch off - * from here, with each device_opp containing the list of opp it supports in + * The root of the list of all opp-tables. All opp_table structures branch off + * from here, with each opp_table containing the list of opps it supports in * various states of availability. */ -static LIST_HEAD(dev_opp_list); +static LIST_HEAD(opp_tables); /* Lock to allow exclusive modification to the device and opp lists */ -DEFINE_MUTEX(dev_opp_list_lock); +DEFINE_MUTEX(opp_table_lock); #define opp_rcu_lockdep_assert() \ do { \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ - !lockdep_is_held(&dev_opp_list_lock), \ - "Missing rcu_read_lock() or " \ - "dev_opp_list_lock protection"); \ + !lockdep_is_held(&opp_table_lock), \ + "Missing rcu_read_lock() or " \ + "opp_table_lock protection"); \ } while (0) -static struct device_list_opp *_find_list_dev(const struct device *dev, - struct device_opp *dev_opp) +static struct opp_device *_find_opp_dev(const struct device *dev, + struct opp_table *opp_table) { - struct device_list_opp *list_dev; + struct opp_device *opp_dev; - list_for_each_entry(list_dev, &dev_opp->dev_list, node) - if (list_dev->dev == dev) - return list_dev; + list_for_each_entry(opp_dev, &opp_table->dev_list, node) + if (opp_dev->dev == dev) + return opp_dev; return NULL; } -static struct device_opp *_managed_opp(const struct device_node *np) +static struct opp_table *_managed_opp(const struct device_node *np) { - struct device_opp *dev_opp; + struct opp_table *opp_table; - list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) { - if (dev_opp->np == np) { + list_for_each_entry_rcu(opp_table, &opp_tables, node) { + if (opp_table->np == np) { /* * Multiple devices can point to the same OPP table and * so will have same node-pointer, np. @@ -64,7 +66,7 @@ static struct device_opp *_managed_opp(const struct device_node *np) * But the OPPs will be considered as shared only if the * OPP table contains a "opp-shared" property. */ - return dev_opp->shared_opp ? dev_opp : NULL; + return opp_table->shared_opp ? opp_table : NULL; } } @@ -72,24 +74,24 @@ static struct device_opp *_managed_opp(const struct device_node *np) } /** - * _find_device_opp() - find device_opp struct using device pointer - * @dev: device pointer used to lookup device OPPs + * _find_opp_table() - find opp_table struct using device pointer + * @dev: device pointer used to lookup OPP table * - * Search list of device OPPs for one containing matching device. Does a RCU - * reader operation to grab the pointer needed. + * Search OPP table for one containing matching device. Does a RCU reader + * operation to grab the pointer needed. * - * Return: pointer to 'struct device_opp' if found, otherwise -ENODEV or + * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or * -EINVAL based on type of error. * * Locking: For readers, this function must be called under rcu_read_lock(). - * device_opp is a RCU protected pointer, which means that device_opp is valid + * opp_table is a RCU protected pointer, which means that opp_table is valid * as long as we are under RCU lock. * - * For Writers, this function must be called with dev_opp_list_lock held. + * For Writers, this function must be called with opp_table_lock held. */ -struct device_opp *_find_device_opp(struct device *dev) +struct opp_table *_find_opp_table(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; opp_rcu_lockdep_assert(); @@ -98,9 +100,9 @@ struct device_opp *_find_device_opp(struct device *dev) return ERR_PTR(-EINVAL); } - list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) - if (_find_list_dev(dev, dev_opp)) - return dev_opp; + list_for_each_entry_rcu(opp_table, &opp_tables, node) + if (_find_opp_dev(dev, opp_table)) + return opp_table; return ERR_PTR(-ENODEV); } @@ -213,16 +215,16 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo); */ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; unsigned long clock_latency_ns; rcu_read_lock(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) clock_latency_ns = 0; else - clock_latency_ns = dev_opp->clock_latency_ns_max; + clock_latency_ns = opp_table->clock_latency_ns_max; rcu_read_unlock(); return clock_latency_ns; @@ -230,6 +232,82 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); /** + * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds + * @dev: device for which we do this operation + * + * Return: This function returns the max voltage latency in nanoseconds. + * + * Locking: This function takes rcu_read_lock(). + */ +unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) +{ + struct opp_table *opp_table; + struct dev_pm_opp *opp; + struct regulator *reg; + unsigned long latency_ns = 0; + unsigned long min_uV = ~0, max_uV = 0; + int ret; + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + rcu_read_unlock(); + return 0; + } + + reg = opp_table->regulator; + if (IS_ERR(reg)) { + /* Regulator may not be required for device */ + if (reg) + dev_err(dev, "%s: Invalid regulator (%ld)\n", __func__, + PTR_ERR(reg)); + rcu_read_unlock(); + return 0; + } + + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { + if (!opp->available) + continue; + + if (opp->u_volt_min < min_uV) + min_uV = opp->u_volt_min; + if (opp->u_volt_max > max_uV) + max_uV = opp->u_volt_max; + } + + rcu_read_unlock(); + + /* + * The caller needs to ensure that opp_table (and hence the regulator) + * isn't freed, while we are executing this routine. + */ + ret = regulator_set_voltage_time(reg, min_uV, max_uV); + if (ret > 0) + latency_ns = ret * 1000; + + return latency_ns; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_volt_latency); + +/** + * dev_pm_opp_get_max_transition_latency() - Get max transition latency in + * nanoseconds + * @dev: device for which we do this operation + * + * Return: This function returns the max transition latency, in nanoseconds, to + * switch from one OPP to other. + * + * Locking: This function takes rcu_read_lock(). + */ +unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev) +{ + return dev_pm_opp_get_max_volt_latency(dev) + + dev_pm_opp_get_max_clock_latency(dev); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency); + +/** * dev_pm_opp_get_suspend_opp() - Get suspend opp * @dev: device for which we do this operation * @@ -244,21 +322,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); */ struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; opp_rcu_lockdep_assert(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp) || !dev_opp->suspend_opp || - !dev_opp->suspend_opp->available) + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table) || !opp_table->suspend_opp || + !opp_table->suspend_opp->available) return NULL; - return dev_opp->suspend_opp; + return opp_table->suspend_opp; } EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp); /** - * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list + * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table * @dev: device for which we do this operation * * Return: This function returns the number of available opps if there are any, @@ -268,21 +346,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp); */ int dev_pm_opp_get_opp_count(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp; int count = 0; rcu_read_lock(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - count = PTR_ERR(dev_opp); - dev_err(dev, "%s: device OPP not found (%d)\n", + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + count = PTR_ERR(opp_table); + dev_err(dev, "%s: OPP table not found (%d)\n", __func__, count); goto out_unlock; } - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available) count++; } @@ -299,7 +377,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count); * @freq: frequency to search for * @available: true/false - match for available opp * - * Return: Searches for exact match in the opp list and returns pointer to the + * Return: Searches for exact match in the opp table and returns pointer to the * matching opp if found, else returns ERR_PTR in case of error and should * be handled using IS_ERR. Error return values can be: * EINVAL: for bad pointer @@ -323,19 +401,20 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); opp_rcu_lockdep_assert(); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - int r = PTR_ERR(dev_opp); - dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + int r = PTR_ERR(opp_table); + + dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r); return ERR_PTR(r); } - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available == available && temp_opp->rate == freq) { opp = temp_opp; @@ -371,7 +450,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact); struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); opp_rcu_lockdep_assert(); @@ -381,11 +460,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-EINVAL); } - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) - return ERR_CAST(dev_opp); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available && temp_opp->rate >= *freq) { opp = temp_opp; *freq = opp->rate; @@ -421,7 +500,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil); struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); opp_rcu_lockdep_assert(); @@ -431,11 +510,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, return ERR_PTR(-EINVAL); } - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) - return ERR_CAST(dev_opp); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); - list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) { if (temp_opp->available) { /* go to the next node, before choosing prev */ if (temp_opp->rate > *freq) @@ -451,116 +530,343 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor); -/* List-dev Helpers */ -static void _kfree_list_dev_rcu(struct rcu_head *head) +/* + * The caller needs to ensure that opp_table (and hence the clk) isn't freed, + * while clk returned here is used. + */ +static struct clk *_get_opp_clk(struct device *dev) { - struct device_list_opp *list_dev; + struct opp_table *opp_table; + struct clk *clk; + + rcu_read_lock(); - list_dev = container_of(head, struct device_list_opp, rcu_head); - kfree_rcu(list_dev, rcu_head); + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "%s: device opp doesn't exist\n", __func__); + clk = ERR_CAST(opp_table); + goto unlock; + } + + clk = opp_table->clk; + if (IS_ERR(clk)) + dev_err(dev, "%s: No clock available for the device\n", + __func__); + +unlock: + rcu_read_unlock(); + return clk; } -static void _remove_list_dev(struct device_list_opp *list_dev, - struct device_opp *dev_opp) +static int _set_opp_voltage(struct device *dev, struct regulator *reg, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) { - list_del(&list_dev->node); - call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head, - _kfree_list_dev_rcu); + int ret; + + /* Regulator not available for device */ + if (IS_ERR(reg)) { + dev_dbg(dev, "%s: regulator not available: %ld\n", __func__, + PTR_ERR(reg)); + return 0; + } + + dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, u_volt_min, + u_volt, u_volt_max); + + ret = regulator_set_voltage_triplet(reg, u_volt_min, u_volt, + u_volt_max); + if (ret) + dev_err(dev, "%s: failed to set voltage (%lu %lu %lu mV): %d\n", + __func__, u_volt_min, u_volt, u_volt_max, ret); + + return ret; } -struct device_list_opp *_add_list_dev(const struct device *dev, - struct device_opp *dev_opp) +/** + * dev_pm_opp_set_rate() - Configure new OPP based on frequency + * @dev: device for which we do this operation + * @target_freq: frequency to achieve + * + * This configures the power-supplies and clock source to the levels specified + * by the OPP corresponding to the target_freq. + * + * Locking: This function takes rcu_read_lock(). + */ +int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { - struct device_list_opp *list_dev; + struct opp_table *opp_table; + struct dev_pm_opp *old_opp, *opp; + struct regulator *reg; + struct clk *clk; + unsigned long freq, old_freq; + unsigned long u_volt, u_volt_min, u_volt_max; + unsigned long ou_volt, ou_volt_min, ou_volt_max; + int ret; + + if (unlikely(!target_freq)) { + dev_err(dev, "%s: Invalid target frequency %lu\n", __func__, + target_freq); + return -EINVAL; + } + + clk = _get_opp_clk(dev); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + freq = clk_round_rate(clk, target_freq); + if ((long)freq <= 0) + freq = target_freq; + + old_freq = clk_get_rate(clk); + + /* Return early if nothing to do */ + if (old_freq == freq) { + dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", + __func__, freq); + return 0; + } + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "%s: device opp doesn't exist\n", __func__); + rcu_read_unlock(); + return PTR_ERR(opp_table); + } + + old_opp = dev_pm_opp_find_freq_ceil(dev, &old_freq); + if (!IS_ERR(old_opp)) { + ou_volt = old_opp->u_volt; + ou_volt_min = old_opp->u_volt_min; + ou_volt_max = old_opp->u_volt_max; + } else { + dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n", + __func__, old_freq, PTR_ERR(old_opp)); + } + + opp = dev_pm_opp_find_freq_ceil(dev, &freq); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); + dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n", + __func__, freq, ret); + rcu_read_unlock(); + return ret; + } - list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL); - if (!list_dev) + u_volt = opp->u_volt; + u_volt_min = opp->u_volt_min; + u_volt_max = opp->u_volt_max; + + reg = opp_table->regulator; + + rcu_read_unlock(); + + /* Scaling up? Scale voltage before frequency */ + if (freq > old_freq) { + ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, + u_volt_max); + if (ret) + goto restore_voltage; + } + + /* Change frequency */ + + dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", + __func__, old_freq, freq); + + ret = clk_set_rate(clk, freq); + if (ret) { + dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, + ret); + goto restore_voltage; + } + + /* Scaling down? Scale voltage after frequency */ + if (freq < old_freq) { + ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, + u_volt_max); + if (ret) + goto restore_freq; + } + + return 0; + +restore_freq: + if (clk_set_rate(clk, old_freq)) + dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", + __func__, old_freq); +restore_voltage: + /* This shouldn't harm even if the voltages weren't updated earlier */ + if (!IS_ERR(old_opp)) + _set_opp_voltage(dev, reg, ou_volt, ou_volt_min, ou_volt_max); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); + +/* OPP-dev Helpers */ +static void _kfree_opp_dev_rcu(struct rcu_head *head) +{ + struct opp_device *opp_dev; + + opp_dev = container_of(head, struct opp_device, rcu_head); + kfree_rcu(opp_dev, rcu_head); +} + +static void _remove_opp_dev(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ + opp_debug_unregister(opp_dev, opp_table); + list_del(&opp_dev->node); + call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head, + _kfree_opp_dev_rcu); +} + +struct opp_device *_add_opp_dev(const struct device *dev, + struct opp_table *opp_table) +{ + struct opp_device *opp_dev; + int ret; + + opp_dev = kzalloc(sizeof(*opp_dev), GFP_KERNEL); + if (!opp_dev) return NULL; - /* Initialize list-dev */ - list_dev->dev = dev; - list_add_rcu(&list_dev->node, &dev_opp->dev_list); + /* Initialize opp-dev */ + opp_dev->dev = dev; + list_add_rcu(&opp_dev->node, &opp_table->dev_list); + + /* Create debugfs entries for the opp_table */ + ret = opp_debug_register(opp_dev, opp_table); + if (ret) + dev_err(dev, "%s: Failed to register opp debugfs (%d)\n", + __func__, ret); - return list_dev; + return opp_dev; } /** - * _add_device_opp() - Find device OPP table or allocate a new one + * _add_opp_table() - Find OPP table or allocate a new one * @dev: device for which we do this operation * * It tries to find an existing table first, if it couldn't find one, it * allocates a new OPP table and returns that. * - * Return: valid device_opp pointer if success, else NULL. + * Return: valid opp_table pointer if success, else NULL. */ -static struct device_opp *_add_device_opp(struct device *dev) +static struct opp_table *_add_opp_table(struct device *dev) { - struct device_opp *dev_opp; - struct device_list_opp *list_dev; + struct opp_table *opp_table; + struct opp_device *opp_dev; + struct device_node *np; + int ret; - /* Check for existing list for 'dev' first */ - dev_opp = _find_device_opp(dev); - if (!IS_ERR(dev_opp)) - return dev_opp; + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (!IS_ERR(opp_table)) + return opp_table; /* - * Allocate a new device OPP table. In the infrequent case where a new + * Allocate a new OPP table. In the infrequent case where a new * device is needed to be added, we pay this penalty. */ - dev_opp = kzalloc(sizeof(*dev_opp), GFP_KERNEL); - if (!dev_opp) + opp_table = kzalloc(sizeof(*opp_table), GFP_KERNEL); + if (!opp_table) return NULL; - INIT_LIST_HEAD(&dev_opp->dev_list); + INIT_LIST_HEAD(&opp_table->dev_list); - list_dev = _add_list_dev(dev, dev_opp); - if (!list_dev) { - kfree(dev_opp); + opp_dev = _add_opp_dev(dev, opp_table); + if (!opp_dev) { + kfree(opp_table); return NULL; } - srcu_init_notifier_head(&dev_opp->srcu_head); - INIT_LIST_HEAD(&dev_opp->opp_list); + /* + * Only required for backward compatibility with v1 bindings, but isn't + * harmful for other cases. And so we do it unconditionally. + */ + np = of_node_get(dev->of_node); + if (np) { + u32 val; + + if (!of_property_read_u32(np, "clock-latency", &val)) + opp_table->clock_latency_ns_max = val; + of_property_read_u32(np, "voltage-tolerance", + &opp_table->voltage_tolerance_v1); + of_node_put(np); + } + + /* Set regulator to a non-NULL error value */ + opp_table->regulator = ERR_PTR(-ENXIO); + + /* Find clk for the device */ + opp_table->clk = clk_get(dev, NULL); + if (IS_ERR(opp_table->clk)) { + ret = PTR_ERR(opp_table->clk); + if (ret != -EPROBE_DEFER) + dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, + ret); + } - /* Secure the device list modification */ - list_add_rcu(&dev_opp->node, &dev_opp_list); - return dev_opp; + srcu_init_notifier_head(&opp_table->srcu_head); + INIT_LIST_HEAD(&opp_table->opp_list); + + /* Secure the device table modification */ + list_add_rcu(&opp_table->node, &opp_tables); + return opp_table; } /** - * _kfree_device_rcu() - Free device_opp RCU handler + * _kfree_device_rcu() - Free opp_table RCU handler * @head: RCU head */ static void _kfree_device_rcu(struct rcu_head *head) { - struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head); + struct opp_table *opp_table = container_of(head, struct opp_table, + rcu_head); - kfree_rcu(device_opp, rcu_head); + kfree_rcu(opp_table, rcu_head); } /** - * _remove_device_opp() - Removes a device OPP table - * @dev_opp: device OPP table to be removed. + * _remove_opp_table() - Removes a OPP table + * @opp_table: OPP table to be removed. * - * Removes/frees device OPP table it it doesn't contain any OPPs. + * Removes/frees OPP table if it doesn't contain any OPPs. */ -static void _remove_device_opp(struct device_opp *dev_opp) +static void _remove_opp_table(struct opp_table *opp_table) { - struct device_list_opp *list_dev; + struct opp_device *opp_dev; + + if (!list_empty(&opp_table->opp_list)) + return; + + if (opp_table->supported_hw) + return; - if (!list_empty(&dev_opp->opp_list)) + if (opp_table->prop_name) return; - list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp, - node); + if (!IS_ERR(opp_table->regulator)) + return; + + /* Release clk */ + if (!IS_ERR(opp_table->clk)) + clk_put(opp_table->clk); + + opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device, + node); - _remove_list_dev(list_dev, dev_opp); + _remove_opp_dev(opp_dev, opp_table); /* dev_list must be empty now */ - WARN_ON(!list_empty(&dev_opp->dev_list)); + WARN_ON(!list_empty(&opp_table->dev_list)); - list_del_rcu(&dev_opp->node); - call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head, + list_del_rcu(&opp_table->node); + call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head, _kfree_device_rcu); } @@ -577,17 +883,17 @@ static void _kfree_opp_rcu(struct rcu_head *head) /** * _opp_remove() - Remove an OPP from a table definition - * @dev_opp: points back to the device_opp struct this opp belongs to + * @opp_table: points back to the opp_table struct this opp belongs to * @opp: pointer to the OPP to remove * @notify: OPP_EVENT_REMOVE notification should be sent or not * - * This function removes an opp definition from the opp list. + * This function removes an opp definition from the opp table. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * It is assumed that the caller holds required mutex for an RCU updater * strategy. */ -static void _opp_remove(struct device_opp *dev_opp, +static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify) { /* @@ -595,21 +901,23 @@ static void _opp_remove(struct device_opp *dev_opp, * frequency/voltage list. */ if (notify) - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp); + srcu_notifier_call_chain(&opp_table->srcu_head, + OPP_EVENT_REMOVE, opp); + opp_debug_remove_one(opp); list_del_rcu(&opp->node); - call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); + call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); - _remove_device_opp(dev_opp); + _remove_opp_table(opp_table); } /** - * dev_pm_opp_remove() - Remove an OPP from OPP list + * dev_pm_opp_remove() - Remove an OPP from OPP table * @dev: device for which we do this operation * @freq: OPP to remove with matching 'freq' * - * This function removes an opp from the opp list. + * This function removes an opp from the opp table. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -618,17 +926,17 @@ static void _opp_remove(struct device_opp *dev_opp, void dev_pm_opp_remove(struct device *dev, unsigned long freq) { struct dev_pm_opp *opp; - struct device_opp *dev_opp; + struct opp_table *opp_table; bool found = false; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) goto unlock; - list_for_each_entry(opp, &dev_opp->opp_list, node) { + list_for_each_entry(opp, &opp_table->opp_list, node) { if (opp->rate == freq) { found = true; break; @@ -641,14 +949,14 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) goto unlock; } - _opp_remove(dev_opp, opp, true); + _opp_remove(opp_table, opp, true); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_remove); static struct dev_pm_opp *_allocate_opp(struct device *dev, - struct device_opp **dev_opp) + struct opp_table **opp_table) { struct dev_pm_opp *opp; @@ -659,8 +967,8 @@ static struct dev_pm_opp *_allocate_opp(struct device *dev, INIT_LIST_HEAD(&opp->node); - *dev_opp = _add_device_opp(dev); - if (!*dev_opp) { + *opp_table = _add_opp_table(dev); + if (!*opp_table) { kfree(opp); return NULL; } @@ -668,21 +976,38 @@ static struct dev_pm_opp *_allocate_opp(struct device *dev, return opp; } +static bool _opp_supported_by_regulators(struct dev_pm_opp *opp, + struct opp_table *opp_table) +{ + struct regulator *reg = opp_table->regulator; + + if (!IS_ERR(reg) && + !regulator_is_supported_voltage(reg, opp->u_volt_min, + opp->u_volt_max)) { + pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n", + __func__, opp->u_volt_min, opp->u_volt_max); + return false; + } + + return true; +} + static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, - struct device_opp *dev_opp) + struct opp_table *opp_table) { struct dev_pm_opp *opp; - struct list_head *head = &dev_opp->opp_list; + struct list_head *head = &opp_table->opp_list; + int ret; /* * Insert new OPP in order of increasing frequency and discard if * already present. * - * Need to use &dev_opp->opp_list in the condition part of the 'for' + * Need to use &opp_table->opp_list in the condition part of the 'for' * loop, don't replace it with head otherwise it will become an infinite * loop. */ - list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) { + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { if (new_opp->rate > opp->rate) { head = &opp->node; continue; @@ -700,9 +1025,20 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, 0 : -EEXIST; } - new_opp->dev_opp = dev_opp; + new_opp->opp_table = opp_table; list_add_rcu(&new_opp->node, head); + ret = opp_debug_create_one(new_opp, opp_table); + if (ret) + dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n", + __func__, ret); + + if (!_opp_supported_by_regulators(new_opp, opp_table)) { + new_opp->available = false; + dev_warn(dev, "%s: OPP not supported by regulators (%lu)\n", + __func__, new_opp->rate); + } + return 0; } @@ -713,14 +1049,14 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, * @u_volt: Voltage in uVolts for this OPP * @dynamic: Dynamically added OPPs. * - * This function adds an opp definition to the opp list and returns status. + * This function adds an opp definition to the opp table and returns status. * The opp is made available by default and it can be controlled using * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove. * * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table * and freed by dev_pm_opp_of_remove_table. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -736,14 +1072,15 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *new_opp; + unsigned long tol; int ret; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - new_opp = _allocate_opp(dev, &dev_opp); + new_opp = _allocate_opp(dev, &opp_table); if (!new_opp) { ret = -ENOMEM; goto unlock; @@ -751,60 +1088,77 @@ static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, /* populate the opp table */ new_opp->rate = freq; + tol = u_volt * opp_table->voltage_tolerance_v1 / 100; new_opp->u_volt = u_volt; + new_opp->u_volt_min = u_volt - tol; + new_opp->u_volt_max = u_volt + tol; new_opp->available = true; new_opp->dynamic = dynamic; - ret = _opp_add(dev, new_opp, dev_opp); + ret = _opp_add(dev, new_opp, opp_table); if (ret) goto free_opp; - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); /* * Notify the changes in the availability of the operable * frequency/voltage list. */ - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp); return 0; free_opp: - _opp_remove(dev_opp, new_opp, false); + _opp_remove(opp_table, new_opp, false); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } /* TODO: Support multiple regulators */ -static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev) +static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, + struct opp_table *opp_table) { u32 microvolt[3] = {0}; u32 val; int count, ret; + struct property *prop = NULL; + char name[NAME_MAX]; + + /* Search for "opp-microvolt-<name>" */ + if (opp_table->prop_name) { + snprintf(name, sizeof(name), "opp-microvolt-%s", + opp_table->prop_name); + prop = of_find_property(opp->np, name, NULL); + } - /* Missing property isn't a problem, but an invalid entry is */ - if (!of_find_property(opp->np, "opp-microvolt", NULL)) - return 0; + if (!prop) { + /* Search for "opp-microvolt" */ + sprintf(name, "opp-microvolt"); + prop = of_find_property(opp->np, name, NULL); - count = of_property_count_u32_elems(opp->np, "opp-microvolt"); + /* Missing property isn't a problem, but an invalid entry is */ + if (!prop) + return 0; + } + + count = of_property_count_u32_elems(opp->np, name); if (count < 0) { - dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n", - __func__, count); + dev_err(dev, "%s: Invalid %s property (%d)\n", + __func__, name, count); return count; } /* There can be one or three elements here */ if (count != 1 && count != 3) { - dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n", - __func__, count); + dev_err(dev, "%s: Invalid number of elements in %s property (%d)\n", + __func__, name, count); return -EINVAL; } - ret = of_property_read_u32_array(opp->np, "opp-microvolt", microvolt, - count); + ret = of_property_read_u32_array(opp->np, name, microvolt, count); if (ret) { - dev_err(dev, "%s: error parsing opp-microvolt: %d\n", __func__, - ret); + dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret); return -EINVAL; } @@ -818,22 +1172,391 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev) opp->u_volt_max = microvolt[2]; } - if (!of_property_read_u32(opp->np, "opp-microamp", &val)) + /* Search for "opp-microamp-<name>" */ + prop = NULL; + if (opp_table->prop_name) { + snprintf(name, sizeof(name), "opp-microamp-%s", + opp_table->prop_name); + prop = of_find_property(opp->np, name, NULL); + } + + if (!prop) { + /* Search for "opp-microamp" */ + sprintf(name, "opp-microamp"); + prop = of_find_property(opp->np, name, NULL); + } + + if (prop && !of_property_read_u32(opp->np, name, &val)) opp->u_amp = val; return 0; } /** + * dev_pm_opp_set_supported_hw() - Set supported platforms + * @dev: Device for which supported-hw has to be set. + * @versions: Array of hierarchy of versions to match. + * @count: Number of elements in the array. + * + * This is required only for the V2 bindings, and it enables a platform to + * specify the hierarchy of versions it supports. OPP layer will then enable + * OPPs, which are available for those versions, based on its 'opp-supported-hw' + * property. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, + unsigned int count) +{ + struct opp_table *opp_table; + int ret = 0; + + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); + + opp_table = _add_opp_table(dev); + if (!opp_table) { + ret = -ENOMEM; + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + /* Do we already have a version hierarchy associated with opp_table? */ + if (opp_table->supported_hw) { + dev_err(dev, "%s: Already have supported hardware list\n", + __func__); + ret = -EBUSY; + goto err; + } + + opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions), + GFP_KERNEL); + if (!opp_table->supported_hw) { + ret = -ENOMEM; + goto err; + } + + opp_table->supported_hw_count = count; + mutex_unlock(&opp_table_lock); + return 0; + +err: + _remove_opp_table(opp_table); +unlock: + mutex_unlock(&opp_table_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw); + +/** + * dev_pm_opp_put_supported_hw() - Releases resources blocked for supported hw + * @dev: Device for which supported-hw has to be put. + * + * This is required only for the V2 bindings, and is called for a matching + * dev_pm_opp_set_supported_hw(). Until this is called, the opp_table structure + * will not be freed. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +void dev_pm_opp_put_supported_hw(struct device *dev) +{ + struct opp_table *opp_table; + + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); + + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "Failed to find opp_table: %ld\n", + PTR_ERR(opp_table)); + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + if (!opp_table->supported_hw) { + dev_err(dev, "%s: Doesn't have supported hardware list\n", + __func__); + goto unlock; + } + + kfree(opp_table->supported_hw); + opp_table->supported_hw = NULL; + opp_table->supported_hw_count = 0; + + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); + +unlock: + mutex_unlock(&opp_table_lock); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw); + +/** + * dev_pm_opp_set_prop_name() - Set prop-extn name + * @dev: Device for which the prop-name has to be set. + * @name: name to postfix to properties. + * + * This is required only for the V2 bindings, and it enables a platform to + * specify the extn to be used for certain property names. The properties to + * which the extension will apply are opp-microvolt and opp-microamp. OPP core + * should postfix the property name with -<name> while looking for them. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +int dev_pm_opp_set_prop_name(struct device *dev, const char *name) +{ + struct opp_table *opp_table; + int ret = 0; + + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); + + opp_table = _add_opp_table(dev); + if (!opp_table) { + ret = -ENOMEM; + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + /* Do we already have a prop-name associated with opp_table? */ + if (opp_table->prop_name) { + dev_err(dev, "%s: Already have prop-name %s\n", __func__, + opp_table->prop_name); + ret = -EBUSY; + goto err; + } + + opp_table->prop_name = kstrdup(name, GFP_KERNEL); + if (!opp_table->prop_name) { + ret = -ENOMEM; + goto err; + } + + mutex_unlock(&opp_table_lock); + return 0; + +err: + _remove_opp_table(opp_table); +unlock: + mutex_unlock(&opp_table_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name); + +/** + * dev_pm_opp_put_prop_name() - Releases resources blocked for prop-name + * @dev: Device for which the prop-name has to be put. + * + * This is required only for the V2 bindings, and is called for a matching + * dev_pm_opp_set_prop_name(). Until this is called, the opp_table structure + * will not be freed. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +void dev_pm_opp_put_prop_name(struct device *dev) +{ + struct opp_table *opp_table; + + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); + + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "Failed to find opp_table: %ld\n", + PTR_ERR(opp_table)); + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + if (!opp_table->prop_name) { + dev_err(dev, "%s: Doesn't have a prop-name\n", __func__); + goto unlock; + } + + kfree(opp_table->prop_name); + opp_table->prop_name = NULL; + + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); + +unlock: + mutex_unlock(&opp_table_lock); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); + +/** + * dev_pm_opp_set_regulator() - Set regulator name for the device + * @dev: Device for which regulator name is being set. + * @name: Name of the regulator. + * + * In order to support OPP switching, OPP layer needs to know the name of the + * device's regulator, as the core would be required to switch voltages as well. + * + * This must be called before any OPPs are initialized for the device. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +int dev_pm_opp_set_regulator(struct device *dev, const char *name) +{ + struct opp_table *opp_table; + struct regulator *reg; + int ret; + + mutex_lock(&opp_table_lock); + + opp_table = _add_opp_table(dev); + if (!opp_table) { + ret = -ENOMEM; + goto unlock; + } + + /* This should be called before OPPs are initialized */ + if (WARN_ON(!list_empty(&opp_table->opp_list))) { + ret = -EBUSY; + goto err; + } + + /* Already have a regulator set */ + if (WARN_ON(!IS_ERR(opp_table->regulator))) { + ret = -EBUSY; + goto err; + } + /* Allocate the regulator */ + reg = regulator_get_optional(dev, name); + if (IS_ERR(reg)) { + ret = PTR_ERR(reg); + if (ret != -EPROBE_DEFER) + dev_err(dev, "%s: no regulator (%s) found: %d\n", + __func__, name, ret); + goto err; + } + + opp_table->regulator = reg; + + mutex_unlock(&opp_table_lock); + return 0; + +err: + _remove_opp_table(opp_table); +unlock: + mutex_unlock(&opp_table_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator); + +/** + * dev_pm_opp_put_regulator() - Releases resources blocked for regulator + * @dev: Device for which regulator was set. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +void dev_pm_opp_put_regulator(struct device *dev) +{ + struct opp_table *opp_table; + + mutex_lock(&opp_table_lock); + + /* Check for existing table for 'dev' first */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "Failed to find opp_table: %ld\n", + PTR_ERR(opp_table)); + goto unlock; + } + + if (IS_ERR(opp_table->regulator)) { + dev_err(dev, "%s: Doesn't have regulator set\n", __func__); + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + regulator_put(opp_table->regulator); + opp_table->regulator = ERR_PTR(-ENXIO); + + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); + +unlock: + mutex_unlock(&opp_table_lock); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator); + +static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table, + struct device_node *np) +{ + unsigned int count = opp_table->supported_hw_count; + u32 version; + int ret; + + if (!opp_table->supported_hw) + return true; + + while (count--) { + ret = of_property_read_u32_index(np, "opp-supported-hw", count, + &version); + if (ret) { + dev_warn(dev, "%s: failed to read opp-supported-hw property at index %d: %d\n", + __func__, count, ret); + return false; + } + + /* Both of these are bitwise masks of the versions */ + if (!(version & opp_table->supported_hw[count])) + return false; + } + + return true; +} + +/** * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings) * @dev: device for which we do this operation * @np: device node * - * This function adds an opp definition to the opp list and returns status. The + * This function adds an opp definition to the opp table and returns status. The * opp can be controlled using dev_pm_opp_enable/disable functions and may be * removed by dev_pm_opp_remove. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -849,16 +1572,16 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev) */ static int _opp_add_static_v2(struct device *dev, struct device_node *np) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *new_opp; u64 rate; u32 val; int ret; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - new_opp = _allocate_opp(dev, &dev_opp); + new_opp = _allocate_opp(dev, &opp_table); if (!new_opp) { ret = -ENOMEM; goto unlock; @@ -870,6 +1593,12 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) goto free_opp; } + /* Check if the OPP supports hardware's hierarchy of versions or not */ + if (!_opp_is_supported(dev, opp_table, np)) { + dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate); + goto free_opp; + } + /* * Rate is defined as an unsigned long in clk API, and so casting * explicitly to its type. Must be fixed once rate is 64 bit @@ -885,28 +1614,30 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) if (!of_property_read_u32(np, "clock-latency-ns", &val)) new_opp->clock_latency_ns = val; - ret = opp_parse_supplies(new_opp, dev); + ret = opp_parse_supplies(new_opp, dev, opp_table); if (ret) goto free_opp; - ret = _opp_add(dev, new_opp, dev_opp); + ret = _opp_add(dev, new_opp, opp_table); if (ret) goto free_opp; /* OPP to select on device suspend */ if (of_property_read_bool(np, "opp-suspend")) { - if (dev_opp->suspend_opp) + if (opp_table->suspend_opp) { dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n", - __func__, dev_opp->suspend_opp->rate, + __func__, opp_table->suspend_opp->rate, new_opp->rate); - else - dev_opp->suspend_opp = new_opp; + } else { + new_opp->suspend = true; + opp_table->suspend_opp = new_opp; + } } - if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max) - dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns; + if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max) + opp_table->clock_latency_ns_max = new_opp->clock_latency_ns; - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n", __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt, @@ -917,13 +1648,13 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) * Notify the changes in the availability of the operable * frequency/voltage list. */ - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp); return 0; free_opp: - _opp_remove(dev_opp, new_opp, false); + _opp_remove(opp_table, new_opp, false); unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } @@ -933,11 +1664,11 @@ unlock: * @freq: Frequency in Hz for this OPP * @u_volt: Voltage in uVolts for this OPP * - * This function adds an opp definition to the opp list and returns status. + * This function adds an opp definition to the opp table and returns status. * The opp is made available by default and it can be controlled using * dev_pm_opp_enable/disable functions. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -969,7 +1700,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add); * copy operation, returns 0 if no modification was done OR modification was * successful. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks to * keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -978,7 +1709,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add); static int _opp_set_availability(struct device *dev, unsigned long freq, bool availability_req) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV); int r = 0; @@ -987,18 +1718,18 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, if (!new_opp) return -ENOMEM; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - /* Find the device_opp */ - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - r = PTR_ERR(dev_opp); + /* Find the opp_table */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + r = PTR_ERR(opp_table); dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); goto unlock; } /* Do we have the frequency? */ - list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) { + list_for_each_entry(tmp_opp, &opp_table->opp_list, node) { if (tmp_opp->rate == freq) { opp = tmp_opp; break; @@ -1019,21 +1750,21 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, new_opp->available = availability_req; list_replace_rcu(&opp->node, &new_opp->node); - mutex_unlock(&dev_opp_list_lock); - call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); + mutex_unlock(&opp_table_lock); + call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); /* Notify the change of the OPP availability */ if (availability_req) - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ENABLE, - new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, + OPP_EVENT_ENABLE, new_opp); else - srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_DISABLE, - new_opp); + srcu_notifier_call_chain(&opp_table->srcu_head, + OPP_EVENT_DISABLE, new_opp); return 0; unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); kfree(new_opp); return r; } @@ -1047,7 +1778,7 @@ unlock: * corresponding error value. It is meant to be used for users an OPP available * after being temporarily made unavailable with dev_pm_opp_disable. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU and mutex locks to keep the * integrity of the internal data structures. Callers should ensure that * this function is *NOT* called under RCU protection or in contexts where @@ -1073,7 +1804,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable); * control by users to make this OPP not available until the circumstances are * right to make it available again (with a call to dev_pm_opp_enable). * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU and mutex locks to keep the * integrity of the internal data structures. Callers should ensure that * this function is *NOT* called under RCU protection or in contexts where @@ -1091,26 +1822,26 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_disable); /** * dev_pm_opp_get_notifier() - find notifier_head of the device with opp - * @dev: device pointer used to lookup device OPPs. + * @dev: device pointer used to lookup OPP table. * * Return: pointer to notifier head if found, otherwise -ENODEV or * -EINVAL based on type of error casted as pointer. value must be checked * with IS_ERR to determine valid pointer or error result. * - * Locking: This function must be called under rcu_read_lock(). dev_opp is a RCU - * protected pointer. The reason for the same is that the opp pointer which is - * returned will remain valid for use with opp_get_{voltage, freq} only while + * Locking: This function must be called under rcu_read_lock(). opp_table is a + * RCU protected pointer. The reason for the same is that the opp pointer which + * is returned will remain valid for use with opp_get_{voltage, freq} only while * under the locked area. The pointer returned must be used prior to unlocking * with rcu_read_unlock() to maintain the integrity of the pointer. */ struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev) { - struct device_opp *dev_opp = _find_device_opp(dev); + struct opp_table *opp_table = _find_opp_table(dev); - if (IS_ERR(dev_opp)) - return ERR_CAST(dev_opp); /* matching type */ + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); /* matching type */ - return &dev_opp->srcu_head; + return &opp_table->srcu_head; } EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); @@ -1118,11 +1849,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); /** * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT * entries - * @dev: device pointer used to lookup device OPPs. + * @dev: device pointer used to lookup OPP table. * * Free OPPs created using static entries present in DT. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where @@ -1130,38 +1861,38 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); */ void dev_pm_opp_of_remove_table(struct device *dev) { - struct device_opp *dev_opp; + struct opp_table *opp_table; struct dev_pm_opp *opp, *tmp; - /* Hold our list modification lock here */ - mutex_lock(&dev_opp_list_lock); + /* Hold our table modification lock here */ + mutex_lock(&opp_table_lock); - /* Check for existing list for 'dev' */ - dev_opp = _find_device_opp(dev); - if (IS_ERR(dev_opp)) { - int error = PTR_ERR(dev_opp); + /* Check for existing table for 'dev' */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + int error = PTR_ERR(opp_table); if (error != -ENODEV) - WARN(1, "%s: dev_opp: %d\n", + WARN(1, "%s: opp_table: %d\n", IS_ERR_OR_NULL(dev) ? "Invalid device" : dev_name(dev), error); goto unlock; } - /* Find if dev_opp manages a single device */ - if (list_is_singular(&dev_opp->dev_list)) { + /* Find if opp_table manages a single device */ + if (list_is_singular(&opp_table->dev_list)) { /* Free static OPPs */ - list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) { + list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { if (!opp->dynamic) - _opp_remove(dev_opp, opp, true); + _opp_remove(opp_table, opp, true); } } else { - _remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp); + _remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table); } unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table); @@ -1182,22 +1913,22 @@ struct device_node *_of_get_opp_desc_node(struct device *dev) static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) { struct device_node *np; - struct device_opp *dev_opp; + struct opp_table *opp_table; int ret = 0, count = 0; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - dev_opp = _managed_opp(opp_np); - if (dev_opp) { + opp_table = _managed_opp(opp_np); + if (opp_table) { /* OPPs are already managed */ - if (!_add_list_dev(dev, dev_opp)) + if (!_add_opp_dev(dev, opp_table)) ret = -ENOMEM; - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); - /* We have opp-list node now, iterate over it and add OPPs */ + /* We have opp-table node now, iterate over it and add OPPs */ for_each_available_child_of_node(opp_np, np) { count++; @@ -1213,19 +1944,19 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) if (WARN_ON(!count)) return -ENOENT; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - dev_opp = _find_device_opp(dev); - if (WARN_ON(IS_ERR(dev_opp))) { - ret = PTR_ERR(dev_opp); - mutex_unlock(&dev_opp_list_lock); + opp_table = _find_opp_table(dev); + if (WARN_ON(IS_ERR(opp_table))) { + ret = PTR_ERR(opp_table); + mutex_unlock(&opp_table_lock); goto free_table; } - dev_opp->np = opp_np; - dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared"); + opp_table->np = opp_np; + opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared"); - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return 0; @@ -1254,7 +1985,7 @@ static int _of_add_opp_table_v1(struct device *dev) */ nr = prop->length / sizeof(u32); if (nr % 2) { - dev_err(dev, "%s: Invalid OPP list\n", __func__); + dev_err(dev, "%s: Invalid OPP table\n", __func__); return -EINVAL; } @@ -1274,11 +2005,11 @@ static int _of_add_opp_table_v1(struct device *dev) /** * dev_pm_opp_of_add_table() - Initialize opp table from device tree - * @dev: device pointer used to lookup device OPPs. + * @dev: device pointer used to lookup OPP table. * * Register the initial OPP table with the OPP library for given device. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function indirectly uses RCU updater strategy with mutex locks * to keep the integrity of the internal data structures. Callers should ensure * that this function is *NOT* called under RCU protection or in contexts where diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c index 7b445e88a0d5..ba2bdbd932ef 100644 --- a/drivers/base/power/opp/cpu.c +++ b/drivers/base/power/opp/cpu.c @@ -31,7 +31,7 @@ * @table: Cpufreq table returned back to caller * * Generate a cpufreq table for a provided device- this assumes that the - * opp list is already initialized and ready for usage. + * opp table is already initialized and ready for usage. * * This function allocates required memory for the cpufreq table. It is * expected that the caller does the required maintenance such as freeing @@ -44,7 +44,7 @@ * WARNING: It is important for the callers to ensure refreshing their copy of * the table if any of the mentioned functions have been invoked in the interim. * - * Locking: The internal device_opp and opp structures are RCU protected. + * Locking: The internal opp_table and opp structures are RCU protected. * Since we just use the regular accessor functions to access the internal data * structures, we use RCU read lock inside this function. As a result, users of * this function DONOT need to use explicit locks for invoking. @@ -122,15 +122,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table); /* Required only for V1 bindings, as v2 can manage it from DT itself */ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) { - struct device_list_opp *list_dev; - struct device_opp *dev_opp; + struct opp_device *opp_dev; + struct opp_table *opp_table; struct device *dev; int cpu, ret = 0; - mutex_lock(&dev_opp_list_lock); + mutex_lock(&opp_table_lock); - dev_opp = _find_device_opp(cpu_dev); - if (IS_ERR(dev_opp)) { + opp_table = _find_opp_table(cpu_dev); + if (IS_ERR(opp_table)) { ret = -EINVAL; goto unlock; } @@ -146,15 +146,15 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) continue; } - list_dev = _add_list_dev(dev, dev_opp); - if (!list_dev) { - dev_err(dev, "%s: failed to add list-dev for cpu%d device\n", + opp_dev = _add_opp_dev(dev, opp_table); + if (!opp_dev) { + dev_err(dev, "%s: failed to add opp-dev for cpu%d device\n", __func__, cpu); continue; } } unlock: - mutex_unlock(&dev_opp_list_lock); + mutex_unlock(&opp_table_lock); return ret; } @@ -214,7 +214,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table); /* * Works only for OPP v2 bindings. * - * cpumask should be already set to mask of cpu_dev->id. * Returns -ENOENT if operating-points-v2 bindings aren't supported. */ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) @@ -230,6 +229,8 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask return -ENOENT; } + cpumask_set_cpu(cpu_dev->id, cpumask); + /* OPPs are shared ? */ if (!of_property_read_bool(np, "opp-shared")) goto put_cpu_node; diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c new file mode 100644 index 000000000000..ef1ae6b52042 --- /dev/null +++ b/drivers/base/power/opp/debugfs.c @@ -0,0 +1,218 @@ +/* + * Generic OPP debugfs interface + * + * Copyright (C) 2015-2016 Viresh Kumar <viresh.kumar@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/limits.h> + +#include "opp.h" + +static struct dentry *rootdir; + +static void opp_set_dev_name(const struct device *dev, char *name) +{ + if (dev->parent) + snprintf(name, NAME_MAX, "%s-%s", dev_name(dev->parent), + dev_name(dev)); + else + snprintf(name, NAME_MAX, "%s", dev_name(dev)); +} + +void opp_debug_remove_one(struct dev_pm_opp *opp) +{ + debugfs_remove_recursive(opp->dentry); +} + +int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) +{ + struct dentry *pdentry = opp_table->dentry; + struct dentry *d; + char name[25]; /* 20 chars for 64 bit value + 5 (opp:\0) */ + + /* Rate is unique to each OPP, use it to give opp-name */ + snprintf(name, sizeof(name), "opp:%lu", opp->rate); + + /* Create per-opp directory */ + d = debugfs_create_dir(name, pdentry); + if (!d) + return -ENOMEM; + + if (!debugfs_create_bool("available", S_IRUGO, d, &opp->available)) + return -ENOMEM; + + if (!debugfs_create_bool("dynamic", S_IRUGO, d, &opp->dynamic)) + return -ENOMEM; + + if (!debugfs_create_bool("turbo", S_IRUGO, d, &opp->turbo)) + return -ENOMEM; + + if (!debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend)) + return -ENOMEM; + + if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate)) + return -ENOMEM; + + if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->u_volt)) + return -ENOMEM; + + if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->u_volt_min)) + return -ENOMEM; + + if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->u_volt_max)) + return -ENOMEM; + + if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->u_amp)) + return -ENOMEM; + + if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d, + &opp->clock_latency_ns)) + return -ENOMEM; + + opp->dentry = d; + return 0; +} + +static int opp_list_debug_create_dir(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ + const struct device *dev = opp_dev->dev; + struct dentry *d; + + opp_set_dev_name(dev, opp_table->dentry_name); + + /* Create device specific directory */ + d = debugfs_create_dir(opp_table->dentry_name, rootdir); + if (!d) { + dev_err(dev, "%s: Failed to create debugfs dir\n", __func__); + return -ENOMEM; + } + + opp_dev->dentry = d; + opp_table->dentry = d; + + return 0; +} + +static int opp_list_debug_create_link(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ + const struct device *dev = opp_dev->dev; + char name[NAME_MAX]; + struct dentry *d; + + opp_set_dev_name(opp_dev->dev, name); + + /* Create device specific directory link */ + d = debugfs_create_symlink(name, rootdir, opp_table->dentry_name); + if (!d) { + dev_err(dev, "%s: Failed to create link\n", __func__); + return -ENOMEM; + } + + opp_dev->dentry = d; + + return 0; +} + +/** + * opp_debug_register - add a device opp node to the debugfs 'opp' directory + * @opp_dev: opp-dev pointer for device + * @opp_table: the device-opp being added + * + * Dynamically adds device specific directory in debugfs 'opp' directory. If the + * device-opp is shared with other devices, then links will be created for all + * devices except the first. + * + * Return: 0 on success, otherwise negative error. + */ +int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table) +{ + if (!rootdir) { + pr_debug("%s: Uninitialized rootdir\n", __func__); + return -EINVAL; + } + + if (opp_table->dentry) + return opp_list_debug_create_link(opp_dev, opp_table); + + return opp_list_debug_create_dir(opp_dev, opp_table); +} + +static void opp_migrate_dentry(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ + struct opp_device *new_dev; + const struct device *dev; + struct dentry *dentry; + + /* Look for next opp-dev */ + list_for_each_entry(new_dev, &opp_table->dev_list, node) + if (new_dev != opp_dev) + break; + + /* new_dev is guaranteed to be valid here */ + dev = new_dev->dev; + debugfs_remove_recursive(new_dev->dentry); + + opp_set_dev_name(dev, opp_table->dentry_name); + + dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir, + opp_table->dentry_name); + if (!dentry) { + dev_err(dev, "%s: Failed to rename link from: %s to %s\n", + __func__, dev_name(opp_dev->dev), dev_name(dev)); + return; + } + + new_dev->dentry = dentry; + opp_table->dentry = dentry; +} + +/** + * opp_debug_unregister - remove a device opp node from debugfs opp directory + * @opp_dev: opp-dev pointer for device + * @opp_table: the device-opp being removed + * + * Dynamically removes device specific directory from debugfs 'opp' directory. + */ +void opp_debug_unregister(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ + if (opp_dev->dentry == opp_table->dentry) { + /* Move the real dentry object under another device */ + if (!list_is_singular(&opp_table->dev_list)) { + opp_migrate_dentry(opp_dev, opp_table); + goto out; + } + opp_table->dentry = NULL; + } + + debugfs_remove_recursive(opp_dev->dentry); + +out: + opp_dev->dentry = NULL; +} + +static int __init opp_debug_init(void) +{ + /* Create /sys/kernel/debug/opp directory */ + rootdir = debugfs_create_dir("opp", NULL); + if (!rootdir) { + pr_err("%s: Failed to create root directory\n", __func__); + return -ENOMEM; + } + + return 0; +} +core_initcall(opp_debug_init); diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index 7366b2aa8997..f67f806fcf3a 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -17,17 +17,21 @@ #include <linux/device.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/limits.h> #include <linux/pm_opp.h> #include <linux/rculist.h> #include <linux/rcupdate.h> +struct clk; +struct regulator; + /* Lock to allow exclusive modification to the device and opp lists */ -extern struct mutex dev_opp_list_lock; +extern struct mutex opp_table_lock; /* * Internal data structure organization with the OPP layer library is as * follows: - * dev_opp_list (root) + * opp_tables (root) * |- device 1 (represents voltage domain 1) * | |- opp 1 (availability, freq, voltage) * | |- opp 2 .. @@ -36,23 +40,24 @@ extern struct mutex dev_opp_list_lock; * |- device 2 (represents the next voltage domain) * ... * `- device m (represents mth voltage domain) - * device 1, 2.. are represented by dev_opp structure while each opp + * device 1, 2.. are represented by opp_table structure while each opp * is represented by the opp structure. */ /** * struct dev_pm_opp - Generic OPP description structure - * @node: opp list node. The nodes are maintained throughout the lifetime + * @node: opp table node. The nodes are maintained throughout the lifetime * of boot. It is expected only an optimal set of OPPs are * added to the library by the SoC framework. - * RCU usage: opp list is traversed with RCU locks. node + * RCU usage: opp table is traversed with RCU locks. node * modification is possible realtime, hence the modifications - * are protected by the dev_opp_list_lock for integrity. + * are protected by the opp_table_lock for integrity. * IMPORTANT: the opp nodes should be maintained in increasing * order. - * @dynamic: not-created from static DT entries. * @available: true/false - marks if this OPP as available or not + * @dynamic: not-created from static DT entries. * @turbo: true if turbo (boost) OPP + * @suspend: true if suspend OPP * @rate: Frequency in hertz * @u_volt: Target voltage in microvolts corresponding to this OPP * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP @@ -60,9 +65,10 @@ extern struct mutex dev_opp_list_lock; * @u_amp: Maximum current drawn by the device in microamperes * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's * frequency from any other OPP's frequency. - * @dev_opp: points back to the device_opp struct this opp belongs to + * @opp_table: points back to the opp_table struct this opp belongs to * @rcu_head: RCU callback head used for deferred freeing * @np: OPP's device node. + * @dentry: debugfs dentry pointer (per opp) * * This structure stores the OPP information for a given device. */ @@ -72,6 +78,7 @@ struct dev_pm_opp { bool available; bool dynamic; bool turbo; + bool suspend; unsigned long rate; unsigned long u_volt; @@ -80,40 +87,60 @@ struct dev_pm_opp { unsigned long u_amp; unsigned long clock_latency_ns; - struct device_opp *dev_opp; + struct opp_table *opp_table; struct rcu_head rcu_head; struct device_node *np; + +#ifdef CONFIG_DEBUG_FS + struct dentry *dentry; +#endif }; /** - * struct device_list_opp - devices managed by 'struct device_opp' + * struct opp_device - devices managed by 'struct opp_table' * @node: list node * @dev: device to which the struct object belongs * @rcu_head: RCU callback head used for deferred freeing + * @dentry: debugfs dentry pointer (per device) * - * This is an internal data structure maintaining the list of devices that are - * managed by 'struct device_opp'. + * This is an internal data structure maintaining the devices that are managed + * by 'struct opp_table'. */ -struct device_list_opp { +struct opp_device { struct list_head node; const struct device *dev; struct rcu_head rcu_head; + +#ifdef CONFIG_DEBUG_FS + struct dentry *dentry; +#endif }; /** - * struct device_opp - Device opp structure - * @node: list node - contains the devices with OPPs that + * struct opp_table - Device opp structure + * @node: table node - contains the devices with OPPs that * have been registered. Nodes once added are not modified in this - * list. - * RCU usage: nodes are not modified in the list of device_opp, - * however addition is possible and is secured by dev_opp_list_lock + * table. + * RCU usage: nodes are not modified in the table of opp_table, + * however addition is possible and is secured by opp_table_lock * @srcu_head: notifier head to notify the OPP availability changes. * @rcu_head: RCU callback head used for deferred freeing * @dev_list: list of devices that share these OPPs - * @opp_list: list of opps + * @opp_list: table of opps * @np: struct device_node pointer for opp's DT node. + * @clock_latency_ns_max: Max clock latency in nanoseconds. * @shared_opp: OPP is shared between multiple devices. + * @suspend_opp: Pointer to OPP to be used during device suspend. + * @supported_hw: Array of version number to support. + * @supported_hw_count: Number of elements in supported_hw array. + * @prop_name: A name to postfix to many DT properties, while parsing them. + * @clk: Device's clock handle + * @regulator: Supply regulator + * @dentry: debugfs dentry pointer of the real device directory (not links). + * @dentry_name: Name of the real dentry. + * + * @voltage_tolerance_v1: In percentage, for v1 bindings only. * * This is an internal data structure maintaining the link to opps attached to * a device. This structure is not meant to be shared to users as it is @@ -123,7 +150,7 @@ struct device_list_opp { * need to wait for the grace period of both of them before freeing any * resources. And so we have used kfree_rcu() from within call_srcu() handlers. */ -struct device_opp { +struct opp_table { struct list_head node; struct srcu_notifier_head srcu_head; @@ -133,14 +160,48 @@ struct device_opp { struct device_node *np; unsigned long clock_latency_ns_max; + + /* For backward compatibility with v1 bindings */ + unsigned int voltage_tolerance_v1; + bool shared_opp; struct dev_pm_opp *suspend_opp; + + unsigned int *supported_hw; + unsigned int supported_hw_count; + const char *prop_name; + struct clk *clk; + struct regulator *regulator; + +#ifdef CONFIG_DEBUG_FS + struct dentry *dentry; + char dentry_name[NAME_MAX]; +#endif }; /* Routines internal to opp core */ -struct device_opp *_find_device_opp(struct device *dev); -struct device_list_opp *_add_list_dev(const struct device *dev, - struct device_opp *dev_opp); +struct opp_table *_find_opp_table(struct device *dev); +struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table); struct device_node *_of_get_opp_desc_node(struct device *dev); +#ifdef CONFIG_DEBUG_FS +void opp_debug_remove_one(struct dev_pm_opp *opp); +int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table); +int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table); +void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table); +#else +static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {} + +static inline int opp_debug_create_one(struct dev_pm_opp *opp, + struct opp_table *opp_table) +{ return 0; } +static inline int opp_debug_register(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ return 0; } + +static inline void opp_debug_unregister(struct opp_device *opp_dev, + struct opp_table *opp_table) +{ } +#endif /* DEBUG_FS */ + #endif /* __DRIVER_OPP_H__ */ diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 90d64081ddb3..f951f911786e 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -31,9 +31,8 @@ struct private_data { struct device *cpu_dev; - struct regulator *cpu_reg; struct thermal_cooling_device *cdev; - unsigned int voltage_tolerance; /* in percentage */ + const char *reg_name; }; static struct freq_attr *cpufreq_dt_attr[] = { @@ -44,175 +43,128 @@ static struct freq_attr *cpufreq_dt_attr[] = { static int set_target(struct cpufreq_policy *policy, unsigned int index) { - struct dev_pm_opp *opp; - struct cpufreq_frequency_table *freq_table = policy->freq_table; - struct clk *cpu_clk = policy->clk; struct private_data *priv = policy->driver_data; - struct device *cpu_dev = priv->cpu_dev; - struct regulator *cpu_reg = priv->cpu_reg; - unsigned long volt = 0, volt_old = 0, tol = 0; - unsigned int old_freq, new_freq; - long freq_Hz, freq_exact; - int ret; - - freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000); - if (freq_Hz <= 0) - freq_Hz = freq_table[index].frequency * 1000; - freq_exact = freq_Hz; - new_freq = freq_Hz / 1000; - old_freq = clk_get_rate(cpu_clk) / 1000; + return dev_pm_opp_set_rate(priv->cpu_dev, + policy->freq_table[index].frequency * 1000); +} - if (!IS_ERR(cpu_reg)) { - unsigned long opp_freq; +/* + * An earlier version of opp-v1 bindings used to name the regulator + * "cpu0-supply", we still need to handle that for backwards compatibility. + */ +static const char *find_supply_name(struct device *dev) +{ + struct device_node *np; + struct property *pp; + int cpu = dev->id; + const char *name = NULL; - rcu_read_lock(); - opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz); - if (IS_ERR(opp)) { - rcu_read_unlock(); - dev_err(cpu_dev, "failed to find OPP for %ld\n", - freq_Hz); - return PTR_ERR(opp); - } - volt = dev_pm_opp_get_voltage(opp); - opp_freq = dev_pm_opp_get_freq(opp); - rcu_read_unlock(); - tol = volt * priv->voltage_tolerance / 100; - volt_old = regulator_get_voltage(cpu_reg); - dev_dbg(cpu_dev, "Found OPP: %ld kHz, %ld uV\n", - opp_freq / 1000, volt); - } + np = of_node_get(dev->of_node); - dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n", - old_freq / 1000, (volt_old > 0) ? volt_old / 1000 : -1, - new_freq / 1000, volt ? volt / 1000 : -1); + /* This must be valid for sure */ + if (WARN_ON(!np)) + return NULL; - /* scaling up? scale voltage before frequency */ - if (!IS_ERR(cpu_reg) && new_freq > old_freq) { - ret = regulator_set_voltage_tol(cpu_reg, volt, tol); - if (ret) { - dev_err(cpu_dev, "failed to scale voltage up: %d\n", - ret); - return ret; + /* Try "cpu0" for older DTs */ + if (!cpu) { + pp = of_find_property(np, "cpu0-supply", NULL); + if (pp) { + name = "cpu0"; + goto node_put; } } - ret = clk_set_rate(cpu_clk, freq_exact); - if (ret) { - dev_err(cpu_dev, "failed to set clock rate: %d\n", ret); - if (!IS_ERR(cpu_reg) && volt_old > 0) - regulator_set_voltage_tol(cpu_reg, volt_old, tol); - return ret; + pp = of_find_property(np, "cpu-supply", NULL); + if (pp) { + name = "cpu"; + goto node_put; } - /* scaling down? scale voltage after frequency */ - if (!IS_ERR(cpu_reg) && new_freq < old_freq) { - ret = regulator_set_voltage_tol(cpu_reg, volt, tol); - if (ret) { - dev_err(cpu_dev, "failed to scale voltage down: %d\n", - ret); - clk_set_rate(cpu_clk, old_freq * 1000); - } - } - - return ret; + dev_dbg(dev, "no regulator for cpu%d\n", cpu); +node_put: + of_node_put(np); + return name; } -static int allocate_resources(int cpu, struct device **cdev, - struct regulator **creg, struct clk **cclk) +static int resources_available(void) { struct device *cpu_dev; struct regulator *cpu_reg; struct clk *cpu_clk; int ret = 0; - char *reg_cpu0 = "cpu0", *reg_cpu = "cpu", *reg; + const char *name; - cpu_dev = get_cpu_device(cpu); + cpu_dev = get_cpu_device(0); if (!cpu_dev) { - pr_err("failed to get cpu%d device\n", cpu); + pr_err("failed to get cpu0 device\n"); return -ENODEV; } - /* Try "cpu0" for older DTs */ - if (!cpu) - reg = reg_cpu0; - else - reg = reg_cpu; - -try_again: - cpu_reg = regulator_get_optional(cpu_dev, reg); - if (IS_ERR(cpu_reg)) { + cpu_clk = clk_get(cpu_dev, NULL); + ret = PTR_ERR_OR_ZERO(cpu_clk); + if (ret) { /* - * If cpu's regulator supply node is present, but regulator is - * not yet registered, we should try defering probe. + * If cpu's clk node is present, but clock is not yet + * registered, we should try defering probe. */ - if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) { - dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n", - cpu); - return -EPROBE_DEFER; - } - - /* Try with "cpu-supply" */ - if (reg == reg_cpu0) { - reg = reg_cpu; - goto try_again; - } + if (ret == -EPROBE_DEFER) + dev_dbg(cpu_dev, "clock not ready, retry\n"); + else + dev_err(cpu_dev, "failed to get clock: %d\n", ret); - dev_dbg(cpu_dev, "no regulator for cpu%d: %ld\n", - cpu, PTR_ERR(cpu_reg)); + return ret; } - cpu_clk = clk_get(cpu_dev, NULL); - if (IS_ERR(cpu_clk)) { - /* put regulator */ - if (!IS_ERR(cpu_reg)) - regulator_put(cpu_reg); + clk_put(cpu_clk); - ret = PTR_ERR(cpu_clk); + name = find_supply_name(cpu_dev); + /* Platform doesn't require regulator */ + if (!name) + return 0; + cpu_reg = regulator_get_optional(cpu_dev, name); + ret = PTR_ERR_OR_ZERO(cpu_reg); + if (ret) { /* - * If cpu's clk node is present, but clock is not yet - * registered, we should try defering probe. + * If cpu's regulator supply node is present, but regulator is + * not yet registered, we should try defering probe. */ if (ret == -EPROBE_DEFER) - dev_dbg(cpu_dev, "cpu%d clock not ready, retry\n", cpu); + dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n"); else - dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", cpu, - ret); - } else { - *cdev = cpu_dev; - *creg = cpu_reg; - *cclk = cpu_clk; + dev_dbg(cpu_dev, "no regulator for cpu0: %d\n", ret); + + return ret; } - return ret; + regulator_put(cpu_reg); + return 0; } static int cpufreq_init(struct cpufreq_policy *policy) { struct cpufreq_frequency_table *freq_table; - struct device_node *np; struct private_data *priv; struct device *cpu_dev; - struct regulator *cpu_reg; struct clk *cpu_clk; struct dev_pm_opp *suspend_opp; - unsigned long min_uV = ~0, max_uV = 0; unsigned int transition_latency; - bool need_update = false; + bool opp_v1 = false; + const char *name; int ret; - ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk); - if (ret) { - pr_err("%s: Failed to allocate resources: %d\n", __func__, ret); - return ret; + cpu_dev = get_cpu_device(policy->cpu); + if (!cpu_dev) { + pr_err("failed to get cpu%d device\n", policy->cpu); + return -ENODEV; } - np = of_node_get(cpu_dev->of_node); - if (!np) { - dev_err(cpu_dev, "failed to find cpu%d node\n", policy->cpu); - ret = -ENOENT; - goto out_put_reg_clk; + cpu_clk = clk_get(cpu_dev, NULL); + if (IS_ERR(cpu_clk)) { + ret = PTR_ERR(cpu_clk); + dev_err(cpu_dev, "%s: failed to get clk: %d\n", __func__, ret); + return ret; } /* Get OPP-sharing information from "operating-points-v2" bindings */ @@ -223,9 +175,23 @@ static int cpufreq_init(struct cpufreq_policy *policy) * finding shared-OPPs for backward compatibility. */ if (ret == -ENOENT) - need_update = true; + opp_v1 = true; else - goto out_node_put; + goto out_put_clk; + } + + /* + * OPP layer will be taking care of regulators now, but it needs to know + * the name of the regulator first. + */ + name = find_supply_name(cpu_dev); + if (name) { + ret = dev_pm_opp_set_regulator(cpu_dev, name); + if (ret) { + dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n", + policy->cpu, ret); + goto out_put_clk; + } } /* @@ -246,12 +212,12 @@ static int cpufreq_init(struct cpufreq_policy *policy) */ ret = dev_pm_opp_get_opp_count(cpu_dev); if (ret <= 0) { - pr_debug("OPP table is not ready, deferring probe\n"); + dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n"); ret = -EPROBE_DEFER; goto out_free_opp; } - if (need_update) { + if (opp_v1) { struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data(); if (!pd || !pd->independent_clocks) @@ -265,10 +231,6 @@ static int cpufreq_init(struct cpufreq_policy *policy) if (ret) dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n", __func__, ret); - - of_property_read_u32(np, "clock-latency", &transition_latency); - } else { - transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev); } priv = kzalloc(sizeof(*priv), GFP_KERNEL); @@ -277,62 +239,16 @@ static int cpufreq_init(struct cpufreq_policy *policy) goto out_free_opp; } - of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance); - - if (!transition_latency) - transition_latency = CPUFREQ_ETERNAL; - - if (!IS_ERR(cpu_reg)) { - unsigned long opp_freq = 0; - - /* - * Disable any OPPs where the connected regulator isn't able to - * provide the specified voltage and record minimum and maximum - * voltage levels. - */ - while (1) { - struct dev_pm_opp *opp; - unsigned long opp_uV, tol_uV; - - rcu_read_lock(); - opp = dev_pm_opp_find_freq_ceil(cpu_dev, &opp_freq); - if (IS_ERR(opp)) { - rcu_read_unlock(); - break; - } - opp_uV = dev_pm_opp_get_voltage(opp); - rcu_read_unlock(); - - tol_uV = opp_uV * priv->voltage_tolerance / 100; - if (regulator_is_supported_voltage(cpu_reg, - opp_uV - tol_uV, - opp_uV + tol_uV)) { - if (opp_uV < min_uV) - min_uV = opp_uV; - if (opp_uV > max_uV) - max_uV = opp_uV; - } else { - dev_pm_opp_disable(cpu_dev, opp_freq); - } - - opp_freq++; - } - - ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV); - if (ret > 0) - transition_latency += ret * 1000; - } + priv->reg_name = name; ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { - pr_err("failed to init cpufreq table: %d\n", ret); + dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret); goto out_free_priv; } priv->cpu_dev = cpu_dev; - priv->cpu_reg = cpu_reg; policy->driver_data = priv; - policy->clk = cpu_clk; rcu_read_lock(); @@ -357,9 +273,11 @@ static int cpufreq_init(struct cpufreq_policy *policy) cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs; } - policy->cpuinfo.transition_latency = transition_latency; + transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev); + if (!transition_latency) + transition_latency = CPUFREQ_ETERNAL; - of_node_put(np); + policy->cpuinfo.transition_latency = transition_latency; return 0; @@ -369,12 +287,10 @@ out_free_priv: kfree(priv); out_free_opp: dev_pm_opp_of_cpumask_remove_table(policy->cpus); -out_node_put: - of_node_put(np); -out_put_reg_clk: + if (name) + dev_pm_opp_put_regulator(cpu_dev); +out_put_clk: clk_put(cpu_clk); - if (!IS_ERR(cpu_reg)) - regulator_put(cpu_reg); return ret; } @@ -386,9 +302,10 @@ static int cpufreq_exit(struct cpufreq_policy *policy) cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); + if (priv->reg_name) + dev_pm_opp_put_regulator(priv->cpu_dev); + clk_put(policy->clk); - if (!IS_ERR(priv->cpu_reg)) - regulator_put(priv->cpu_reg); kfree(priv); return 0; @@ -407,8 +324,13 @@ static void cpufreq_ready(struct cpufreq_policy *policy) * thermal DT code takes care of matching them. */ if (of_find_property(np, "#cooling-cells", NULL)) { - priv->cdev = of_cpufreq_cooling_register(np, - policy->related_cpus); + u32 power_coefficient = 0; + + of_property_read_u32(np, "dynamic-power-coefficient", + &power_coefficient); + + priv->cdev = of_cpufreq_power_cooling_register(np, + policy->related_cpus, power_coefficient, NULL); if (IS_ERR(priv->cdev)) { dev_err(priv->cpu_dev, "running cpufreq without cooling device: %ld\n", @@ -436,9 +358,6 @@ static struct cpufreq_driver dt_cpufreq_driver = { static int dt_cpufreq_probe(struct platform_device *pdev) { - struct device *cpu_dev; - struct regulator *cpu_reg; - struct clk *cpu_clk; int ret; /* @@ -448,19 +367,15 @@ static int dt_cpufreq_probe(struct platform_device *pdev) * * FIXME: Is checking this only for CPU0 sufficient ? */ - ret = allocate_resources(0, &cpu_dev, &cpu_reg, &cpu_clk); + ret = resources_available(); if (ret) return ret; - clk_put(cpu_clk); - if (!IS_ERR(cpu_reg)) - regulator_put(cpu_reg); - dt_cpufreq_driver.driver_data = dev_get_platdata(&pdev->dev); ret = cpufreq_register_driver(&dt_cpufreq_driver); if (ret) - dev_err(cpu_dev, "failed register driver: %d\n", ret); + dev_err(&pdev->dev, "failed register driver: %d\n", ret); return ret; } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 3c0467d3688c..c4098748e1fe 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -8,7 +8,7 @@ cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \ -fPIC -fno-strict-aliasing -mno-red-zone \ - -mno-mmx -mno-sse -DDISABLE_BRANCH_PROFILING + -mno-mmx -mno-sse cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS)) cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ @@ -16,7 +16,7 @@ cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt -KBUILD_CFLAGS := $(cflags-y) \ +KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ $(call cc-option,-ffreestanding) \ $(call cc-option,-fno-stack-protector) @@ -34,7 +34,8 @@ $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o string.o \ $(patsubst %.c,lib-%.o,$(arm-deps)) -lib-$(CONFIG_ARM64) += arm64-stub.o +lib-$(CONFIG_ARM) += arm32-stub.o +lib-$(CONFIG_ARM64) += arm64-stub.o random.o CFLAGS_arm64-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) # diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 950c87f5d279..d5aa1d16154f 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -18,6 +18,8 @@ #include "efistub.h" +bool __nokaslr; + static int efi_secureboot_enabled(efi_system_table_t *sys_table_arg) { static efi_guid_t const var_guid = EFI_GLOBAL_VARIABLE_GUID; @@ -207,14 +209,6 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, pr_efi_err(sys_table, "Failed to find DRAM base\n"); goto fail; } - status = handle_kernel_image(sys_table, image_addr, &image_size, - &reserve_addr, - &reserve_size, - dram_base, image); - if (status != EFI_SUCCESS) { - pr_efi_err(sys_table, "Failed to relocate kernel\n"); - goto fail; - } /* * Get the command line from EFI, using the LOADED_IMAGE @@ -224,7 +218,28 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size); if (!cmdline_ptr) { pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n"); - goto fail_free_image; + goto fail; + } + + /* check whether 'nokaslr' was passed on the command line */ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + static const u8 default_cmdline[] = CONFIG_CMDLINE; + const u8 *str, *cmdline = cmdline_ptr; + + if (IS_ENABLED(CONFIG_CMDLINE_FORCE)) + cmdline = default_cmdline; + str = strstr(cmdline, "nokaslr"); + if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) + __nokaslr = true; + } + + status = handle_kernel_image(sys_table, image_addr, &image_size, + &reserve_addr, + &reserve_size, + dram_base, image); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to relocate kernel\n"); + goto fail_free_cmdline; } status = efi_parse_options(cmdline_ptr); @@ -244,7 +259,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, if (status != EFI_SUCCESS) { pr_efi_err(sys_table, "Failed to load device tree!\n"); - goto fail_free_cmdline; + goto fail_free_image; } } @@ -286,12 +301,11 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, efi_free(sys_table, initrd_size, initrd_addr); efi_free(sys_table, fdt_size, fdt_addr); -fail_free_cmdline: - efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr); - fail_free_image: efi_free(sys_table, image_size, *image_addr); efi_free(sys_table, reserve_size, reserve_addr); +fail_free_cmdline: + efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr); fail: return EFI_ERROR; } diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 78dfbd34b6bf..e0e6b74fef8f 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -13,6 +13,10 @@ #include <asm/efi.h> #include <asm/sections.h> +#include "efistub.h" + +extern bool __nokaslr; + efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, unsigned long *image_addr, unsigned long *image_size, @@ -23,26 +27,52 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, { efi_status_t status; unsigned long kernel_size, kernel_memsize = 0; - unsigned long nr_pages; void *old_image_addr = (void *)*image_addr; unsigned long preferred_offset; + u64 phys_seed = 0; + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + if (!__nokaslr) { + status = efi_get_random_bytes(sys_table_arg, + sizeof(phys_seed), + (u8 *)&phys_seed); + if (status == EFI_NOT_FOUND) { + pr_efi(sys_table_arg, "EFI_RNG_PROTOCOL unavailable, no randomness supplied\n"); + } else if (status != EFI_SUCCESS) { + pr_efi_err(sys_table_arg, "efi_get_random_bytes() failed\n"); + return status; + } + } else { + pr_efi(sys_table_arg, "KASLR disabled on kernel command line\n"); + } + } /* * The preferred offset of the kernel Image is TEXT_OFFSET bytes beyond * a 2 MB aligned base, which itself may be lower than dram_base, as * long as the resulting offset equals or exceeds it. */ - preferred_offset = round_down(dram_base, SZ_2M) + TEXT_OFFSET; + preferred_offset = round_down(dram_base, MIN_KIMG_ALIGN) + TEXT_OFFSET; if (preferred_offset < dram_base) - preferred_offset += SZ_2M; + preferred_offset += MIN_KIMG_ALIGN; - /* Relocate the image, if required. */ kernel_size = _edata - _text; - if (*image_addr != preferred_offset) { - kernel_memsize = kernel_size + (_end - _edata); + kernel_memsize = kernel_size + (_end - _edata); + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) { + /* + * If KASLR is enabled, and we have some randomness available, + * locate the kernel at a randomized offset in physical memory. + */ + *reserve_size = kernel_memsize + TEXT_OFFSET; + status = efi_random_alloc(sys_table_arg, *reserve_size, + MIN_KIMG_ALIGN, reserve_addr, + phys_seed); + *image_addr = *reserve_addr + TEXT_OFFSET; + } else { /* - * First, try a straight allocation at the preferred offset. + * Else, try a straight allocation at the preferred offset. * This will work around the issue where, if dram_base == 0x0, * efi_low_alloc() refuses to allocate at 0x0 (to prevent the * address of the allocation to be mistaken for a FAIL return @@ -52,27 +82,31 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, * Mustang), we can still place the kernel at the address * 'dram_base + TEXT_OFFSET'. */ + if (*image_addr == preferred_offset) + return EFI_SUCCESS; + *image_addr = *reserve_addr = preferred_offset; - nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) / - EFI_PAGE_SIZE; + *reserve_size = round_up(kernel_memsize, EFI_ALLOC_ALIGN); + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, - EFI_LOADER_DATA, nr_pages, + EFI_LOADER_DATA, + *reserve_size / EFI_PAGE_SIZE, (efi_physical_addr_t *)reserve_addr); - if (status != EFI_SUCCESS) { - kernel_memsize += TEXT_OFFSET; - status = efi_low_alloc(sys_table_arg, kernel_memsize, - SZ_2M, reserve_addr); + } - if (status != EFI_SUCCESS) { - pr_efi_err(sys_table_arg, "Failed to relocate kernel\n"); - return status; - } - *image_addr = *reserve_addr + TEXT_OFFSET; + if (status != EFI_SUCCESS) { + *reserve_size = kernel_memsize + TEXT_OFFSET; + status = efi_low_alloc(sys_table_arg, *reserve_size, + MIN_KIMG_ALIGN, reserve_addr); + + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table_arg, "Failed to relocate kernel\n"); + *reserve_size = 0; + return status; } - memcpy((void *)*image_addr, old_image_addr, kernel_size); - *reserve_size = kernel_memsize; + *image_addr = *reserve_addr + TEXT_OFFSET; } - + memcpy((void *)*image_addr, old_image_addr, kernel_size); return EFI_SUCCESS; } diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index f07d4a67fa76..29ed2f9b218c 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -649,6 +649,10 @@ static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n) return dst; } +#ifndef MAX_CMDLINE_ADDRESS +#define MAX_CMDLINE_ADDRESS ULONG_MAX +#endif + /* * Convert the unicode UEFI command line to ASCII to pass to kernel. * Size of memory allocated return in *cmd_line_len. @@ -684,7 +688,8 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, options_bytes++; /* NUL termination */ - status = efi_low_alloc(sys_table_arg, options_bytes, 0, &cmdline_addr); + status = efi_high_alloc(sys_table_arg, options_bytes, 0, + &cmdline_addr, MAX_CMDLINE_ADDRESS); if (status != EFI_SUCCESS) return NULL; diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 6b6548fda089..5ed3d3f38166 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -43,4 +43,11 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size, unsigned long desc_size, efi_memory_desc_t *runtime_map, int *count); +efi_status_t efi_get_random_bytes(efi_system_table_t *sys_table, + unsigned long size, u8 *out); + +efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr, unsigned long random_seed); + #endif diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index b62e2f5dcab3..b1c22cf18f7d 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -147,6 +147,20 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, if (status) goto fdt_set_fail; + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + efi_status_t efi_status; + + efi_status = efi_get_random_bytes(sys_table, sizeof(fdt_val64), + (u8 *)&fdt_val64); + if (efi_status == EFI_SUCCESS) { + status = fdt_setprop(fdt, node, "kaslr-seed", + &fdt_val64, sizeof(fdt_val64)); + if (status) + goto fdt_set_fail; + } else if (efi_status != EFI_NOT_FOUND) { + return efi_status; + } + } return EFI_SUCCESS; fdt_set_fail: diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c new file mode 100644 index 000000000000..53f6d3fe6d86 --- /dev/null +++ b/drivers/firmware/efi/libstub/random.c @@ -0,0 +1,135 @@ +/* + * Copyright (C) 2016 Linaro Ltd; <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/efi.h> +#include <asm/efi.h> + +#include "efistub.h" + +struct efi_rng_protocol { + efi_status_t (*get_info)(struct efi_rng_protocol *, + unsigned long *, efi_guid_t *); + efi_status_t (*get_rng)(struct efi_rng_protocol *, + efi_guid_t *, unsigned long, u8 *out); +}; + +efi_status_t efi_get_random_bytes(efi_system_table_t *sys_table_arg, + unsigned long size, u8 *out) +{ + efi_guid_t rng_proto = EFI_RNG_PROTOCOL_GUID; + efi_status_t status; + struct efi_rng_protocol *rng; + + status = efi_call_early(locate_protocol, &rng_proto, NULL, + (void **)&rng); + if (status != EFI_SUCCESS) + return status; + + return rng->get_rng(rng, NULL, size, out); +} + +/* + * Return the number of slots covered by this entry, i.e., the number of + * addresses it covers that are suitably aligned and supply enough room + * for the allocation. + */ +static unsigned long get_entry_num_slots(efi_memory_desc_t *md, + unsigned long size, + unsigned long align) +{ + u64 start, end; + + if (md->type != EFI_CONVENTIONAL_MEMORY) + return 0; + + start = round_up(md->phys_addr, align); + end = round_down(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - size, + align); + + if (start > end) + return 0; + + return (end - start + 1) / align; +} + +/* + * The UEFI memory descriptors have a virtual address field that is only used + * when installing the virtual mapping using SetVirtualAddressMap(). Since it + * is unused here, we can reuse it to keep track of each descriptor's slot + * count. + */ +#define MD_NUM_SLOTS(md) ((md)->virt_addr) + +efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg, + unsigned long size, + unsigned long align, + unsigned long *addr, + unsigned long random_seed) +{ + unsigned long map_size, desc_size, total_slots = 0, target_slot; + efi_status_t status; + efi_memory_desc_t *memory_map; + int map_offset; + + status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size, + &desc_size, NULL, NULL); + if (status != EFI_SUCCESS) + return status; + + if (align < EFI_ALLOC_ALIGN) + align = EFI_ALLOC_ALIGN; + + /* count the suitable slots in each memory map entry */ + for (map_offset = 0; map_offset < map_size; map_offset += desc_size) { + efi_memory_desc_t *md = (void *)memory_map + map_offset; + unsigned long slots; + + slots = get_entry_num_slots(md, size, align); + MD_NUM_SLOTS(md) = slots; + total_slots += slots; + } + + /* find a random number between 0 and total_slots */ + target_slot = (total_slots * (u16)random_seed) >> 16; + + /* + * target_slot is now a value in the range [0, total_slots), and so + * it corresponds with exactly one of the suitable slots we recorded + * when iterating over the memory map the first time around. + * + * So iterate over the memory map again, subtracting the number of + * slots of each entry at each iteration, until we have found the entry + * that covers our chosen slot. Use the residual value of target_slot + * to calculate the randomly chosen address, and allocate it directly + * using EFI_ALLOCATE_ADDRESS. + */ + for (map_offset = 0; map_offset < map_size; map_offset += desc_size) { + efi_memory_desc_t *md = (void *)memory_map + map_offset; + efi_physical_addr_t target; + unsigned long pages; + + if (target_slot >= MD_NUM_SLOTS(md)) { + target_slot -= MD_NUM_SLOTS(md); + continue; + } + + target = round_up(md->phys_addr, align) + target_slot * align; + pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; + + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, + EFI_LOADER_DATA, pages, &target); + if (status == EFI_SUCCESS) + *addr = target; + break; + } + + efi_call_early(free_pool, memory_map); + + return status; +} diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c index 11fdadc68e53..2a6eaf1122b4 100644 --- a/drivers/misc/lkdtm.c +++ b/drivers/misc/lkdtm.c @@ -103,6 +103,7 @@ enum ctype { CT_EXEC_USERSPACE, CT_ACCESS_USERSPACE, CT_WRITE_RO, + CT_WRITE_RO_AFTER_INIT, CT_WRITE_KERN, }; @@ -140,6 +141,7 @@ static char* cp_type[] = { "EXEC_USERSPACE", "ACCESS_USERSPACE", "WRITE_RO", + "WRITE_RO_AFTER_INIT", "WRITE_KERN", }; @@ -162,6 +164,7 @@ static DEFINE_SPINLOCK(lock_me_up); static u8 data_area[EXEC_SIZE]; static const unsigned long rodata = 0xAA55AA55; +static unsigned long ro_after_init __ro_after_init = 0x55AA5500; module_param(recur_count, int, 0644); MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test"); @@ -503,11 +506,28 @@ static void lkdtm_do_action(enum ctype which) break; } case CT_WRITE_RO: { - unsigned long *ptr; + /* Explicitly cast away "const" for the test. */ + unsigned long *ptr = (unsigned long *)&rodata; - ptr = (unsigned long *)&rodata; + pr_info("attempting bad rodata write at %p\n", ptr); + *ptr ^= 0xabcd1234; - pr_info("attempting bad write at %p\n", ptr); + break; + } + case CT_WRITE_RO_AFTER_INIT: { + unsigned long *ptr = &ro_after_init; + + /* + * Verify we were written to during init. Since an Oops + * is considered a "success", a failure is to just skip the + * real test. + */ + if ((*ptr & 0xAA) != 0xAA) { + pr_info("%p was NOT written during init!?\n", ptr); + break; + } + + pr_info("attempting bad ro_after_init write at %p\n", ptr); *ptr ^= 0xabcd1234; break; @@ -817,6 +837,9 @@ static int __init lkdtm_module_init(void) int n_debugfs_entries = 1; /* Assume only the direct entry */ int i; + /* Make sure we can write to __ro_after_init values during __init */ + ro_after_init |= 0xAA; + /* Register debugfs interface */ lkdtm_debugfs_root = debugfs_create_dir("provoke-crash", NULL); if (!lkdtm_debugfs_root) { diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 655f79db7899..3e90bce70545 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -760,6 +760,16 @@ const void * __init of_flat_dt_match_machine(const void *default_match, } #ifdef CONFIG_BLK_DEV_INITRD +#ifndef __early_init_dt_declare_initrd +static void __early_init_dt_declare_initrd(unsigned long start, + unsigned long end) +{ + initrd_start = (unsigned long)__va(start); + initrd_end = (unsigned long)__va(end); + initrd_below_start_ok = 1; +} +#endif + /** * early_init_dt_check_for_initrd - Decode initrd location from flat tree * @node: reference to node containing initrd location ('chosen') @@ -782,9 +792,7 @@ static void __init early_init_dt_check_for_initrd(unsigned long node) return; end = of_read_number(prop, len/4); - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(end); - initrd_below_start_ok = 1; + __early_init_dt_declare_initrd(start, end); pr_debug("initrd_start=0x%llx initrd_end=0x%llx\n", (unsigned long long)start, (unsigned long long)end); @@ -976,13 +984,16 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, } #ifdef CONFIG_HAVE_MEMBLOCK +#ifndef MIN_MEMBLOCK_ADDR +#define MIN_MEMBLOCK_ADDR __pa(PAGE_OFFSET) +#endif #ifndef MAX_MEMBLOCK_ADDR #define MAX_MEMBLOCK_ADDR ((phys_addr_t)~0) #endif void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) { - const u64 phys_offset = __pa(PAGE_OFFSET); + const u64 phys_offset = MIN_MEMBLOCK_ADDR; if (!PAGE_ALIGNED(base)) { if (size < PAGE_SIZE - (base & ~PAGE_MASK)) { diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h index 1cbb8338edf3..827e4d3bbc7a 100644 --- a/include/asm-generic/fixmap.h +++ b/include/asm-generic/fixmap.h @@ -70,12 +70,12 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) #endif /* Return a pointer with offset calculated */ -#define __set_fixmap_offset(idx, phys, flags) \ -({ \ - unsigned long addr; \ - __set_fixmap(idx, phys, flags); \ - addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1)); \ - addr; \ +#define __set_fixmap_offset(idx, phys, flags) \ +({ \ + unsigned long ________addr; \ + __set_fixmap(idx, phys, flags); \ + ________addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1)); \ + ________addr; \ }) #define set_fixmap_offset(idx, phys) \ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c4bd0e2c173c..772c784ba763 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -256,6 +256,7 @@ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_rodata) = .; \ *(.rodata) *(.rodata.*) \ + *(.data..ro_after_init) /* Read only after init */ \ *(__vermagic) /* Kernel version magic */ \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \ diff --git a/include/linux/cache.h b/include/linux/cache.h index 17e7e82d2aa7..1be04f8c563a 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -12,10 +12,24 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif +/* + * __read_mostly is used to keep rarely changing variables out of frequently + * updated cachelines. If an architecture doesn't support it, ignore the + * hint. + */ #ifndef __read_mostly #define __read_mostly #endif +/* + * __ro_after_init is used to mark things that are read-only after init (i.e. + * after mark_rodata_ro() has been called). These are effectively read-only, + * but may get written to during init, so can't live in .rodata (via "const"). + */ +#ifndef __ro_after_init +#define __ro_after_init __attribute__((__section__(".data..ro_after_init"))) +#endif + #ifndef ____cacheline_aligned #define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 47be3ad7d3e5..333d0ca6940f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -299,7 +299,7 @@ typedef struct { void *open_protocol_information; void *protocols_per_handle; void *locate_handle_buffer; - void *locate_protocol; + efi_status_t (*locate_protocol)(efi_guid_t *, void *, void **); void *install_multiple_protocol_interfaces; void *uninstall_multiple_protocol_interfaces; void *calculate_crc32; @@ -599,6 +599,10 @@ void efi_native_runtime_setup(void); #define EFI_PROPERTIES_TABLE_GUID \ EFI_GUID( 0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5 ) +#define EFI_RNG_PROTOCOL_GUID \ + EFI_GUID(0x3152bca5, 0xeade, 0x433d, \ + 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) + typedef struct { efi_guid_t guid; u64 table; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 685c262e0be8..b0eb06423d5e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -96,9 +96,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, struct address_space *mapping, pgoff_t idx, unsigned long address); -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); -#endif extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; diff --git a/include/linux/init.h b/include/linux/init.h index b449f378f995..aedb254abc37 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -142,6 +142,10 @@ void prepare_namespace(void); void __init load_default_modules(void); int __init init_rootfs(void); +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void); +#endif + extern void (*late_time_init)(void); extern bool initcall_debug; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 9a2e50337af9..cccaf4a29e9f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -34,6 +34,8 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev); struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, @@ -55,6 +57,14 @@ int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev); +int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, + unsigned int count); +void dev_pm_opp_put_supported_hw(struct device *dev); +int dev_pm_opp_set_prop_name(struct device *dev, const char *name); +void dev_pm_opp_put_prop_name(struct device *dev); +int dev_pm_opp_set_regulator(struct device *dev, const char *name); +void dev_pm_opp_put_regulator(struct device *dev); +int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -81,6 +91,16 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) return 0; } +static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) +{ + return 0; +} + +static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev) +{ + return 0; +} + static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) { return NULL; @@ -129,6 +149,35 @@ static inline struct srcu_notifier_head *dev_pm_opp_get_notifier( { return ERR_PTR(-EINVAL); } + +static inline int dev_pm_opp_set_supported_hw(struct device *dev, + const u32 *versions, + unsigned int count) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} + +static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_prop_name(struct device *dev) {} + +static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_regulator(struct device *dev) {} + +static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) +{ + return -EINVAL; +} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) diff --git a/init/main.c b/init/main.c index 9e64d7097f1a..fbafa271531c 100644 --- a/init/main.c +++ b/init/main.c @@ -93,9 +93,6 @@ static int kernel_init(void *); extern void init_IRQ(void); extern void fork_init(void); extern void radix_tree_init(void); -#ifndef CONFIG_DEBUG_RODATA -static inline void mark_rodata_ro(void) { } -#endif /* * Debug helper: via this flag we know that we are in 'early bootup code' @@ -929,6 +926,28 @@ static int try_to_run_init_process(const char *init_filename) static noinline void __init kernel_init_freeable(void); +#ifdef CONFIG_DEBUG_RODATA +static bool rodata_enabled = true; +static int __init set_debug_rodata(char *str) +{ + return strtobool(str, &rodata_enabled); +} +__setup("rodata=", set_debug_rodata); + +static void mark_readonly(void) +{ + if (rodata_enabled) + mark_rodata_ro(); + else + pr_info("Kernel memory protection disabled.\n"); +} +#else +static inline void mark_readonly(void) +{ + pr_warn("This architecture does not have kernel memory protection.\n"); +} +#endif + static int __ref kernel_init(void *unused) { int ret; @@ -937,7 +956,7 @@ static int __ref kernel_init(void *unused) /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); free_initmem(); - mark_rodata_ro(); + mark_readonly(); system_state = SYSTEM_RUNNING; numa_default_policy(); diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index e1dbf4a2c69e..90ff129c88a2 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) } else { kdb_printf("%s: failed to set breakpoint at 0x%lx\n", __func__, bp->bp_addr); -#ifdef CONFIG_DEBUG_RODATA if (!bp->bp_type) { kdb_printf("Software breakpoints are unavailable.\n" - " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " Boot the kernel with rodata=off\n" " OR use hw breaks: help bph\n"); } -#endif return 1; } return 0; diff --git a/lib/extable.c b/lib/extable.c index 4cac81ec225e..0be02ad561e9 100644 --- a/lib/extable.c +++ b/lib/extable.c @@ -14,7 +14,37 @@ #include <linux/sort.h> #include <asm/uaccess.h> +#ifndef ARCH_HAS_RELATIVE_EXTABLE +#define ex_to_insn(x) ((x)->insn) +#else +static inline unsigned long ex_to_insn(const struct exception_table_entry *x) +{ + return (unsigned long)&x->insn + x->insn; +} +#endif + #ifndef ARCH_HAS_SORT_EXTABLE +#ifndef ARCH_HAS_RELATIVE_EXTABLE +#define swap_ex NULL +#else +static void swap_ex(void *a, void *b, int size) +{ + struct exception_table_entry *x = a, *y = b, tmp; + int delta = b - a; + + tmp = *x; + x->insn = y->insn + delta; + y->insn = tmp.insn - delta; + +#ifdef swap_ex_entry_fixup + swap_ex_entry_fixup(x, y, tmp, delta); +#else + x->fixup = y->fixup + delta; + y->fixup = tmp.fixup - delta; +#endif +} +#endif /* ARCH_HAS_RELATIVE_EXTABLE */ + /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. @@ -26,9 +56,9 @@ static int cmp_ex(const void *a, const void *b) const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ - if (x->insn > y->insn) + if (ex_to_insn(x) > ex_to_insn(y)) return 1; - if (x->insn < y->insn) + if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } @@ -37,7 +67,7 @@ void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), - cmp_ex, NULL); + cmp_ex, swap_ex); } #ifdef CONFIG_MODULES @@ -48,13 +78,15 @@ void sort_extable(struct exception_table_entry *start, void trim_init_extable(struct module *m) { /*trim the beginning*/ - while (m->num_exentries && within_module_init(m->extable[0].insn, m)) { + while (m->num_exentries && + within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && - within_module_init(m->extable[m->num_exentries-1].insn, m)) + within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), + m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ @@ -81,13 +113,13 @@ search_extable(const struct exception_table_entry *first, * careful, the distance between value and insn * can be larger than MAX_LONG: */ - if (mid->insn < value) + if (ex_to_insn(mid) < value) first = mid + 1; - else if (mid->insn > value) + else if (ex_to_insn(mid) > value) last = mid - 1; else return mid; - } - return NULL; + } + return NULL; } #endif diff --git a/scripts/sortextable.c b/scripts/sortextable.c index c2423d913b46..a2c0d620ca80 100644 --- a/scripts/sortextable.c +++ b/scripts/sortextable.c @@ -266,9 +266,9 @@ do_file(char const *const fname) break; } /* end switch */ if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 - || r2(&ehdr->e_type) != ET_EXEC + || (r2(&ehdr->e_type) != ET_EXEC && r2(&ehdr->e_type) != ET_DYN) || ehdr->e_ident[EI_VERSION] != EV_CURRENT) { - fprintf(stderr, "unrecognized ET_EXEC file %s\n", fname); + fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file %s\n", fname); fail_file(); } @@ -282,12 +282,13 @@ do_file(char const *const fname) case EM_386: case EM_X86_64: case EM_S390: + case EM_AARCH64: + case EM_PARISC: custom_sort = sort_relative_table; break; case EM_ARCOMPACT: case EM_ARCV2: case EM_ARM: - case EM_AARCH64: case EM_MICROBLAZE: case EM_MIPS: case EM_XTENSA: @@ -304,7 +305,7 @@ do_file(char const *const fname) if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) || r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { fprintf(stderr, - "unrecognized ET_EXEC file: %s\n", fname); + "unrecognized ET_EXEC/ET_DYN file: %s\n", fname); fail_file(); } do32(ehdr, fname, custom_sort); @@ -314,7 +315,7 @@ do_file(char const *const fname) if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr) || r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) { fprintf(stderr, - "unrecognized ET_EXEC file: %s\n", fname); + "unrecognized ET_EXEC/ET_DYN file: %s\n", fname); fail_file(); } do64(ghdr, fname, custom_sort); |