diff options
152 files changed, 3094 insertions, 525 deletions
@@ -3949,8 +3949,6 @@ E: [email protected] D: Ralink rt2x00 WLAN driver D: Minix V2 file-system D: Misc fixes -S: Geessinkweg 177 -S: 7544 TX Enschede S: The Netherlands N: Lars Wirzenius diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 498741737055..2a4a423d08e0 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -272,6 +272,22 @@ Description: Parameters for the CPU cache attributes the modified cache line is written to main memory only when it is replaced + +What: /sys/devices/system/cpu/cpu*/cache/index*/id +Date: September 2016 +Contact: Linux kernel mailing list <[email protected]> +Description: Cache id + + The id provides a unique number for a specific instance of + a cache of a particular type. E.g. there may be a level + 3 unified cache on each socket in a server and we may + assign them ids 0, 1, 2, ... + + Note that id value can be non-contiguous. E.g. level 1 + caches typically exist per core, but there may not be a + power of two cores on a socket, so these caches may be + numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ... + What: /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat diff --git a/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt b/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt index 750374fc9d94..c0f37cb41a9b 100644 --- a/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt +++ b/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt @@ -1,7 +1,9 @@ * Cadence SD/SDIO/eMMC Host Controller Required properties: -- compatible: should be "cdns,sd4hc". +- compatible: should be one of the following: + "cdns,sd4hc" - default of the IP + "socionext,uniphier-sd4hc" - for Socionext UniPhier SoCs - reg: offset and length of the register set for the device. - interrupts: a single interrupt specifier. - clocks: phandle to the input clock. @@ -19,7 +21,7 @@ if supported. See mmc.txt for details. Example: emmc: sdhci@5a000000 { - compatible = "cdns,sd4hc"; + compatible = "socionext,uniphier-sd4hc", "cdns,sd4hc"; reg = <0x5a000000 0x400>; interrupts = <0 78 4>; clocks = <&clk 4>; diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt new file mode 100644 index 000000000000..d918d268cd72 --- /dev/null +++ b/Documentation/x86/intel_rdt_ui.txt @@ -0,0 +1,214 @@ +User Interface for Resource Allocation in Intel Resource Director Technology + +Copyright (C) 2016 Intel Corporation + +Fenghua Yu <[email protected]> +Tony Luck <[email protected]> + +This feature is enabled by the CONFIG_INTEL_RDT_A Kconfig and the +X86 /proc/cpuinfo flag bits "rdt", "cat_l3" and "cdp_l3". + +To use the feature mount the file system: + + # mount -t resctrl resctrl [-o cdp] /sys/fs/resctrl + +mount options are: + +"cdp": Enable code/data prioritization in L3 cache allocations. + + +Info directory +-------------- + +The 'info' directory contains information about the enabled +resources. Each resource has its own subdirectory. The subdirectory +names reflect the resource names. Each subdirectory contains the +following files: + +"num_closids": The number of CLOSIDs which are valid for this + resource. The kernel uses the smallest number of + CLOSIDs of all enabled resources as limit. + +"cbm_mask": The bitmask which is valid for this resource. This + mask is equivalent to 100%. + +"min_cbm_bits": The minimum number of consecutive bits which must be + set when writing a mask. + + +Resource groups +--------------- +Resource groups are represented as directories in the resctrl file +system. The default group is the root directory. Other groups may be +created as desired by the system administrator using the "mkdir(1)" +command, and removed using "rmdir(1)". + +There are three files associated with each group: + +"tasks": A list of tasks that belongs to this group. Tasks can be + added to a group by writing the task ID to the "tasks" file + (which will automatically remove them from the previous + group to which they belonged). New tasks created by fork(2) + and clone(2) are added to the same group as their parent. + If a pid is not in any sub partition, it is in root partition + (i.e. default partition). + +"cpus": A bitmask of logical CPUs assigned to this group. Writing + a new mask can add/remove CPUs from this group. Added CPUs + are removed from their previous group. Removed ones are + given to the default (root) group. You cannot remove CPUs + from the default group. + +"schemata": A list of all the resources available to this group. + Each resource has its own line and format - see below for + details. + +When a task is running the following rules define which resources +are available to it: + +1) If the task is a member of a non-default group, then the schemata +for that group is used. + +2) Else if the task belongs to the default group, but is running on a +CPU that is assigned to some specific group, then the schemata for +the CPU's group is used. + +3) Otherwise the schemata for the default group is used. + + +Schemata files - general concepts +--------------------------------- +Each line in the file describes one resource. The line starts with +the name of the resource, followed by specific values to be applied +in each of the instances of that resource on the system. + +Cache IDs +--------- +On current generation systems there is one L3 cache per socket and L2 +caches are generally just shared by the hyperthreads on a core, but this +isn't an architectural requirement. We could have multiple separate L3 +caches on a socket, multiple cores could share an L2 cache. So instead +of using "socket" or "core" to define the set of logical cpus sharing +a resource we use a "Cache ID". At a given cache level this will be a +unique number across the whole system (but it isn't guaranteed to be a +contiguous sequence, there may be gaps). To find the ID for each logical +CPU look in /sys/devices/system/cpu/cpu*/cache/index*/id + +Cache Bit Masks (CBM) +--------------------- +For cache resources we describe the portion of the cache that is available +for allocation using a bitmask. The maximum value of the mask is defined +by each cpu model (and may be different for different cache levels). It +is found using CPUID, but is also provided in the "info" directory of +the resctrl file system in "info/{resource}/cbm_mask". X86 hardware +requires that these masks have all the '1' bits in a contiguous block. So +0x3, 0x6 and 0xC are legal 4-bit masks with two bits set, but 0x5, 0x9 +and 0xA are not. On a system with a 20-bit mask each bit represents 5% +of the capacity of the cache. You could partition the cache into four +equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000. + + +L3 details (code and data prioritization disabled) +-------------------------------------------------- +With CDP disabled the L3 schemata format is: + + L3:<cache_id0>=<cbm>;<cache_id1>=<cbm>;... + +L3 details (CDP enabled via mount option to resctrl) +---------------------------------------------------- +When CDP is enabled L3 control is split into two separate resources +so you can specify independent masks for code and data like this: + + L3data:<cache_id0>=<cbm>;<cache_id1>=<cbm>;... + L3code:<cache_id0>=<cbm>;<cache_id1>=<cbm>;... + +L2 details +---------- +L2 cache does not support code and data prioritization, so the +schemata format is always: + + L2:<cache_id0>=<cbm>;<cache_id1>=<cbm>;... + +Example 1 +--------- +On a two socket machine (one L3 cache per socket) with just four bits +for cache bit masks + +# mount -t resctrl resctrl /sys/fs/resctrl +# cd /sys/fs/resctrl +# mkdir p0 p1 +# echo "L3:0=3;1=c" > /sys/fs/resctrl/p0/schemata +# echo "L3:0=3;1=3" > /sys/fs/resctrl/p1/schemata + +The default resource group is unmodified, so we have access to all parts +of all caches (its schemata file reads "L3:0=f;1=f"). + +Tasks that are under the control of group "p0" may only allocate from the +"lower" 50% on cache ID 0, and the "upper" 50% of cache ID 1. +Tasks in group "p1" use the "lower" 50% of cache on both sockets. + +Example 2 +--------- +Again two sockets, but this time with a more realistic 20-bit mask. + +Two real time tasks pid=1234 running on processor 0 and pid=5678 running on +processor 1 on socket 0 on a 2-socket and dual core machine. To avoid noisy +neighbors, each of the two real-time tasks exclusively occupies one quarter +of L3 cache on socket 0. + +# mount -t resctrl resctrl /sys/fs/resctrl +# cd /sys/fs/resctrl + +First we reset the schemata for the default group so that the "upper" +50% of the L3 cache on socket 0 cannot be used by ordinary tasks: + +# echo "L3:0=3ff;1=fffff" > schemata + +Next we make a resource group for our first real time task and give +it access to the "top" 25% of the cache on socket 0. + +# mkdir p0 +# echo "L3:0=f8000;1=fffff" > p0/schemata + +Finally we move our first real time task into this resource group. We +also use taskset(1) to ensure the task always runs on a dedicated CPU +on socket 0. Most uses of resource groups will also constrain which +processors tasks run on. + +# echo 1234 > p0/tasks +# taskset -cp 1 1234 + +Ditto for the second real time task (with the remaining 25% of cache): + +# mkdir p1 +# echo "L3:0=7c00;1=fffff" > p1/schemata +# echo 5678 > p1/tasks +# taskset -cp 2 5678 + +Example 3 +--------- + +A single socket system which has real-time tasks running on core 4-7 and +non real-time workload assigned to core 0-3. The real-time tasks share text +and data, so a per task association is not required and due to interaction +with the kernel it's desired that the kernel on these cores shares L3 with +the tasks. + +# mount -t resctrl resctrl /sys/fs/resctrl +# cd /sys/fs/resctrl + +First we reset the schemata for the default group so that the "upper" +50% of the L3 cache on socket 0 cannot be used by ordinary tasks: + +# echo "L3:0=3ff" > schemata + +Next we make a resource group for our real time cores and give +it access to the "top" 50% of the cache on socket 0. + +# mkdir p0 +# echo "L3:0=ffc00;" > p0/schemata + +Finally we move core 4-7 over to the new group and make sure that the +kernel and the tasks running there get 50% of the cache. + +# echo C0 > p0/cpus diff --git a/MAINTAINERS b/MAINTAINERS index 9b279928461d..afb85976b1eb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1747,7 +1747,7 @@ F: drivers/staging/media/platform/s5p-cec/ ARM/SAMSUNG S5P SERIES JPEG CODEC SUPPORT M: Andrzej Pietrasiewicz <[email protected]> -M: Jacek Anaszewski <[email protected]> +M: Jacek Anaszewski <[email protected]> S: Maintained @@ -7229,7 +7229,7 @@ F: drivers/scsi/53c700* LED SUBSYSTEM M: Richard Purdie <[email protected]> -M: Jacek Anaszewski <[email protected]> +M: Jacek Anaszewski <[email protected]> M: Pavel Machek <[email protected]> T: git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git @@ -10332,6 +10332,14 @@ L: [email protected] S: Supported F: drivers/infiniband/sw/rdmavt +RDT - RESOURCE ALLOCATION +M: Fenghua Yu <[email protected]> +S: Supported +F: arch/x86/kernel/cpu/intel_rdt* +F: arch/x86/include/asm/intel_rdt* +F: Documentation/x86/intel_rdt* + READ-COPY UPDATE (RCU) M: "Paul E. McKenney" <[email protected]> M: Josh Triplett <[email protected]> diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index d0de0e032bc2..c1976c0adca7 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -29,7 +29,7 @@ /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI -/* ACPI table mapping after acpi_gbl_permanent_mmap is set */ +/* ACPI table mapping after acpi_permanent_mmap is set */ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 252a6d9c1da5..64d9cbd61678 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -132,14 +132,13 @@ static int __init acpi_fadt_sanity_check(void) struct acpi_table_header *table; struct acpi_table_fadt *fadt; acpi_status status; - acpi_size tbl_size; int ret = 0; /* * FADT is required on arm64; retrieve it to check its presence * and carry out revision and ACPI HW reduced compliancy tests */ - status = acpi_get_table_with_size(ACPI_SIG_FADT, 0, &table, &tbl_size); + status = acpi_get_table(ACPI_SIG_FADT, 0, &table); if (ACPI_FAILURE(status)) { const char *msg = acpi_format_exception(status); @@ -170,10 +169,10 @@ static int __init acpi_fadt_sanity_check(void) out: /* - * acpi_get_table_with_size() creates FADT table mapping that + * acpi_get_table() creates FADT table mapping that * should be released after parsing and before resuming boot */ - early_acpi_os_unmap_memory(table, tbl_size); + acpi_put_table(table); return ret; } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index a14b86587013..3a71f38cdc05 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -7,6 +7,7 @@ config PARISC select HAVE_FUNCTION_GRAPH_TRACER select HAVE_SYSCALL_TRACEPOINTS select ARCH_WANT_FRAME_POINTERS + select ARCH_HAS_ELF_RANDOMIZE select RTC_CLASS select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 78c9fd32c554..a6b2a421571e 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -348,9 +348,10 @@ struct pt_regs; /* forward declaration... */ #define ELF_HWCAP 0 -#define STACK_RND_MASK (is_32bit_task() ? \ - 0x7ff >> (PAGE_SHIFT - 12) : \ - 0x3ffff >> (PAGE_SHIFT - 12)) +/* Masks for stack and mmap randomization */ +#define BRK_RND_MASK (is_32bit_task() ? 0x07ffUL : 0x3ffffUL) +#define MMAP_RND_MASK (is_32bit_task() ? 0x1fffUL : 0x3ffffUL) +#define STACK_RND_MASK MMAP_RND_MASK struct mm_struct; extern unsigned long arch_randomize_brk(struct mm_struct *); diff --git a/arch/parisc/include/asm/pdcpat.h b/arch/parisc/include/asm/pdcpat.h index 47539f117958..e1d289092705 100644 --- a/arch/parisc/include/asm/pdcpat.h +++ b/arch/parisc/include/asm/pdcpat.h @@ -289,7 +289,7 @@ extern int pdc_pat_cell_get_number(struct pdc_pat_cell_num *cell_info); extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long mod, unsigned long view_type, void *mem_addr); extern int pdc_pat_cell_num_to_loc(void *, unsigned long); -extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, void *hpa); +extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa); extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset); diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index ca40741378be..a3661ee6b060 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -93,9 +93,7 @@ struct system_cpuinfo_parisc { /* Per CPU data structure - ie varies per CPU. */ struct cpuinfo_parisc { unsigned long it_value; /* Interval Timer at last timer Intr */ - unsigned long it_delta; /* Interval delta (tic_10ms / HZ * 100) */ unsigned long irq_count; /* number of IRQ's since boot */ - unsigned long irq_max_cr16; /* longest time to handle a single IRQ */ unsigned long cpuid; /* aka slot_number or set to NO_PROC_ID */ unsigned long hpa; /* Host Physical address */ unsigned long txn_addr; /* MMIO addr of EIR or id_eid */ @@ -103,8 +101,6 @@ struct cpuinfo_parisc { unsigned long pending_ipi; /* bitmap of type ipi_message_type */ #endif unsigned long bh_count; /* number of times bh was invoked */ - unsigned long prof_counter; /* per CPU profiling support */ - unsigned long prof_multiplier; /* per CPU profiling support */ unsigned long fp_rev; unsigned long fp_model; unsigned int state; diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 4fcff2dcc9c3..ad4cb1613c57 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -878,6 +878,9 @@ ENTRY_CFI(syscall_exit_rfi) STREG %r19,PT_SR7(%r16) intr_return: + /* NOTE: Need to enable interrupts incase we schedule. */ + ssm PSW_SM_I, %r0 + /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ @@ -904,11 +907,6 @@ intr_check_sig: LDREG PT_IASQ1(%r16), %r20 cmpib,COND(=),n 0,%r20,intr_restore /* backward */ - /* NOTE: We need to enable interrupts if we have to deliver - * signals. We used to do this earlier but it caused kernel - * stack overflows. */ - ssm PSW_SM_I, %r0 - copy %r0, %r25 /* long in_syscall = 0 */ #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ @@ -960,10 +958,6 @@ intr_do_resched: cmpib,COND(=) 0, %r20, intr_do_preempt nop - /* NOTE: We need to enable interrupts if we schedule. We used - * to do this earlier but it caused kernel stack overflows. */ - ssm PSW_SM_I, %r0 - #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index e5d71905cad5..9d797ae4fa22 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1258,7 +1258,7 @@ int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long * * Retrieve the cpu number for the cpu at the specified HPA. */ -int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, void *hpa) +int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa) { int retval; unsigned long flags; diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c index c05d1876d27c..c9789d9c73b4 100644 --- a/arch/parisc/kernel/inventory.c +++ b/arch/parisc/kernel/inventory.c @@ -216,9 +216,9 @@ pat_query_module(ulong pcell_loc, ulong mod_index) register_parisc_device(dev); /* advertise device */ #ifdef DEBUG_PAT - pdc_pat_cell_mod_maddr_block_t io_pdc_cell; /* dump what we see so far... */ switch (PAT_GET_ENTITY(dev->mod_info)) { + pdc_pat_cell_mod_maddr_block_t io_pdc_cell; unsigned long i; case PAT_ENTITY_PROC: @@ -259,9 +259,9 @@ pat_query_module(ulong pcell_loc, ulong mod_index) pa_pdc_cell->mod[4 + i * 3]); /* finish (ie end) */ printk(KERN_DEBUG " IO_VIEW %ld: 0x%016lx 0x%016lx 0x%016lx\n", - i, io_pdc_cell->mod[2 + i * 3], /* type */ - io_pdc_cell->mod[3 + i * 3], /* start */ - io_pdc_cell->mod[4 + i * 3]); /* finish (ie end) */ + i, io_pdc_cell.mod[2 + i * 3], /* type */ + io_pdc_cell.mod[3 + i * 3], /* start */ + io_pdc_cell.mod[4 + i * 3]); /* finish (ie end) */ } printk(KERN_DEBUG "\n"); break; diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index 518f4f5f1f43..6eabce62463b 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -301,7 +301,6 @@ static ssize_t perf_read(struct file *file, char __user *buf, size_t cnt, loff_t static ssize_t perf_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - int err; size_t image_size; uint32_t image_type; uint32_t interface_type; @@ -320,8 +319,8 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun if (count != sizeof(uint32_t)) return -EIO; - if ((err = copy_from_user(&image_type, buf, sizeof(uint32_t))) != 0) - return err; + if (copy_from_user(&image_type, buf, sizeof(uint32_t))) + return -EFAULT; /* Get the interface type and test type */ interface_type = (image_type >> 16) & 0xffff; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 40639439d8b3..ea6603ee8d24 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -276,11 +276,7 @@ void *dereference_function_descriptor(void *ptr) static inline unsigned long brk_rnd(void) { - /* 8MB for 32bit, 1GB for 64bit */ - if (is_32bit_task()) - return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; - else - return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT; + return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT; } unsigned long arch_randomize_brk(struct mm_struct *mm) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 0c2a94a0f751..85de47f4eb59 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -78,11 +78,6 @@ DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data); static void init_percpu_prof(unsigned long cpunum) { - struct cpuinfo_parisc *p; - - p = &per_cpu(cpu_data, cpunum); - p->prof_counter = 1; - p->prof_multiplier = 1; } @@ -99,6 +94,7 @@ static int processor_probe(struct parisc_device *dev) unsigned long txn_addr; unsigned long cpuid; struct cpuinfo_parisc *p; + struct pdc_pat_cpu_num cpu_info __maybe_unused; #ifdef CONFIG_SMP if (num_online_cpus() >= nr_cpu_ids) { @@ -123,10 +119,6 @@ static int processor_probe(struct parisc_device *dev) ulong status; unsigned long bytecnt; pdc_pat_cell_mod_maddr_block_t *pa_pdc_cell; -#undef USE_PAT_CPUID -#ifdef USE_PAT_CPUID - struct pdc_pat_cpu_num cpu_info; -#endif pa_pdc_cell = kmalloc(sizeof (*pa_pdc_cell), GFP_KERNEL); if (!pa_pdc_cell) @@ -145,22 +137,27 @@ static int processor_probe(struct parisc_device *dev) kfree(pa_pdc_cell); + /* get the cpu number */ + status = pdc_pat_cpu_get_number(&cpu_info, dev->hpa.start); + BUG_ON(PDC_OK != status); + + pr_info("Logical CPU #%lu is physical cpu #%lu at location " + "0x%lx with hpa %pa\n", + cpuid, cpu_info.cpu_num, cpu_info.cpu_loc, + &dev->hpa.start); + +#undef USE_PAT_CPUID #ifdef USE_PAT_CPUID /* We need contiguous numbers for cpuid. Firmware's notion * of cpuid is for physical CPUs and we just don't care yet. * We'll care when we need to query PAT PDC about a CPU *after* * boot time (ie shutdown a CPU from an OS perspective). */ - /* get the cpu number */ - status = pdc_pat_cpu_get_number(&cpu_info, dev->hpa.start); - - BUG_ON(PDC_OK != status); - if (cpu_info.cpu_num >= NR_CPUS) { - printk(KERN_WARNING "IGNORING CPU at 0x%x," + printk(KERN_WARNING "IGNORING CPU at %pa," " cpu_slot_id > NR_CPUS" " (%ld > %d)\n", - dev->hpa.start, cpu_info.cpu_num, NR_CPUS); + &dev->hpa.start, cpu_info.cpu_num, NR_CPUS); /* Ignore CPU since it will only crash */ boot_cpu_data.cpu_count--; return 1; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 0a393a04e891..a81e177cac7b 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -225,19 +225,17 @@ static unsigned long mmap_rnd(void) { unsigned long rnd = 0; - /* - * 8 bits of randomness in 32bit mmaps, 20 address space bits - * 28 bits of randomness in 64bit mmaps, 40 address space bits - */ - if (current->flags & PF_RANDOMIZE) { - if (is_32bit_task()) - rnd = get_random_int() % (1<<8); - else - rnd = get_random_int() % (1<<28); - } + if (current->flags & PF_RANDOMIZE) + rnd = get_random_int() & MMAP_RND_MASK; + return rnd << PAGE_SHIFT; } +unsigned long arch_mmap_rnd(void) +{ + return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT; +} + static unsigned long mmap_legacy_base(void) { return TASK_UNMAPPED_BASE + mmap_rnd(); diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 325f30d82b64..4215f5596c8b 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -59,10 +59,9 @@ static unsigned long clocktick __read_mostly; /* timer cycles per tick */ */ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) { - unsigned long now, now2; + unsigned long now; unsigned long next_tick; - unsigned long cycles_elapsed, ticks_elapsed = 1; - unsigned long cycles_remainder; + unsigned long ticks_elapsed = 0; unsigned int cpu = smp_processor_id(); struct cpuinfo_parisc *cpuinfo = &per_cpu(cpu_data, cpu); @@ -71,102 +70,49 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) profile_tick(CPU_PROFILING); - /* Initialize next_tick to the expected tick time. */ + /* Initialize next_tick to the old expected tick time. */ next_tick = cpuinfo->it_value; - /* Get current cycle counter (Control Register 16). */ - now = mfctl(16); - - cycles_elapsed = now - next_tick; - - if ((cycles_elapsed >> 6) < cpt) { - /* use "cheap" math (add/subtract) instead - * of the more expensive div/mul method - */ - cycles_remainder = cycles_elapsed; - while (cycles_remainder > cpt) { - cycles_remainder -= cpt; - ticks_elapsed++; - } - } else { - /* TODO: Reduce this to one fdiv op */ - cycles_remainder = cycles_elapsed % cpt; - ticks_elapsed += cycles_elapsed / cpt; - } - - /* convert from "division remainder" to "remainder of clock tick" */ - cycles_remainder = cpt - cycles_remainder; - - /* Determine when (in CR16 cycles) next IT interrupt will fire. - * We want IT to fire modulo clocktick even if we miss/skip some. - * But those interrupts don't in fact get delivered that regularly. - */ - next_tick = now + cycles_remainder; + /* Calculate how many ticks have elapsed. */ + do { + ++ticks_elapsed; + next_tick += cpt; + now = mfctl(16); + } while (next_tick - now > cpt); + /* Store (in CR16 cycles) up to when we are accounting right now. */ cpuinfo->it_value = next_tick; - /* Program the IT when to deliver the next interrupt. - * Only bottom 32-bits of next_tick are writable in CR16! - */ - mtctl(next_tick, 16); + /* Go do system house keeping. */ + if (cpu == 0) + xtime_update(ticks_elapsed); + + update_process_times(user_mode(get_irq_regs())); - /* Skip one clocktick on purpose if we missed next_tick. + /* Skip clockticks on purpose if we know we would miss those. * The new CR16 must be "later" than current CR16 otherwise * itimer would not fire until CR16 wrapped - e.g 4 seconds * later on a 1Ghz processor. We'll account for the missed - * tick on the next timer interrupt. + * ticks on the next timer interrupt. + * We want IT to fire modulo clocktick even if we miss/skip some. + * But those interrupts don't in fact get delivered that regularly. * * "next_tick - now" will always give the difference regardless * if one or the other wrapped. If "now" is "bigger" we'll end up * with a very large unsigned number. */ - now2 = mfctl(16); - if (next_tick - now2 > cpt) - mtctl(next_tick+cpt, 16); + while (next_tick - mfctl(16) > cpt) + next_tick += cpt; -#if 1 -/* - * GGG: DEBUG code for how many cycles programming CR16 used. - */ - if (unlikely(now2 - now > 0x3000)) /* 12K cycles */ - printk (KERN_CRIT "timer_interrupt(CPU %d): SLOW! 0x%lx cycles!" - " cyc %lX rem %lX " - " next/now %lX/%lX\n", - cpu, now2 - now, cycles_elapsed, cycles_remainder, - next_tick, now ); -#endif - - /* Can we differentiate between "early CR16" (aka Scenario 1) and - * "long delay" (aka Scenario 3)? I don't think so. - * - * Timer_interrupt will be delivered at least a few hundred cycles - * after the IT fires. But it's arbitrary how much time passes - * before we call it "late". I've picked one second. - * - * It's important NO printk's are between reading CR16 and - * setting up the next value. May introduce huge variance. - */ - if (unlikely(ticks_elapsed > HZ)) { - /* Scenario 3: very long delay? bad in any case */ - printk (KERN_CRIT "timer_interrupt(CPU %d): delayed!" - " cycles %lX rem %lX " - " next/now %lX/%lX\n", - cpu, - cycles_elapsed, cycles_remainder, - next_tick, now ); - } - - /* Done mucking with unreliable delivery of interrupts. - * Go do system house keeping. + /* Program the IT when to deliver the next interrupt. + * Only bottom 32-bits of next_tick are writable in CR16! + * Timer interrupt will be delivered at least a few hundred cycles + * after the IT fires, so if we are too close (<= 500 cycles) to the + * next cycle, simply skip it. */ - - if (!--cpuinfo->prof_counter) { - cpuinfo->prof_counter = cpuinfo->prof_multiplier; - update_process_times(user_mode(get_irq_regs())); - } - - if (cpu == 0) - xtime_update(ticks_elapsed); + if (next_tick - mfctl(16) <= 500) + next_tick += cpt; + mtctl(next_tick, 16); return IRQ_HANDLED; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 64024c999531..e487493bbd47 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -412,6 +412,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH +config INTEL_RDT_A + bool "Intel Resource Director Technology Allocation support" + default n + depends on X86 && CPU_SUP_INTEL + select KERNFS + help + Select to enable resource allocation which is a sub-feature of + Intel Resource Director Technology(RDT). More information about + RDT can be found in the Intel x86 Architecture Software + Developer Manual. + + Say N if unsure. + if X86_32 config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c index 8f82b02934fa..0c45cc8e64ba 100644 --- a/arch/x86/events/intel/cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -7,9 +7,9 @@ #include <linux/perf_event.h> #include <linux/slab.h> #include <asm/cpu_device_id.h> +#include <asm/intel_rdt_common.h> #include "../perf_event.h" -#define MSR_IA32_PQR_ASSOC 0x0c8f #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d @@ -24,32 +24,13 @@ static unsigned int cqm_l3_scale; /* supposedly cacheline size */ static bool cqm_enabled, mbm_enabled; unsigned int mbm_socket_max; -/** - * struct intel_pqr_state - State cache for the PQR MSR - * @rmid: The cached Resource Monitoring ID - * @closid: The cached Class Of Service ID - * @rmid_usecnt: The usage counter for rmid - * - * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the - * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always - * contains both parts, so we need to cache them. - * - * The cache also helps to avoid pointless updates if the value does - * not change. - */ -struct intel_pqr_state { - u32 rmid; - u32 closid; - int rmid_usecnt; -}; - /* * The cached intel_pqr_state is strictly per CPU and can never be * updated from a remote CPU. Both functions which modify the state * (intel_cqm_event_start and intel_cqm_event_stop) are called with * interrupts disabled, which is sufficient for the protection. */ -static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); +DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); static struct hrtimer *mbm_timers; /** * struct sample - mbm event's (local or total) data diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6ccbf1aaa7ce..eafee3161d1c 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -189,6 +189,9 @@ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ @@ -222,6 +225,7 @@ #define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ #define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ #define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h new file mode 100644 index 000000000000..95ce5c85b009 --- /dev/null +++ b/arch/x86/include/asm/intel_rdt.h @@ -0,0 +1,224 @@ +#ifndef _ASM_X86_INTEL_RDT_H +#define _ASM_X86_INTEL_RDT_H + +#ifdef CONFIG_INTEL_RDT_A + +#include <linux/kernfs.h> +#include <linux/jump_label.h> + +#include <asm/intel_rdt_common.h> + +#define IA32_L3_QOS_CFG 0xc81 +#define IA32_L3_CBM_BASE 0xc90 +#define IA32_L2_CBM_BASE 0xd10 + +#define L3_QOS_CDP_ENABLE 0x01ULL + +/** + * struct rdtgroup - store rdtgroup's data in resctrl file system. + * @kn: kernfs node + * @rdtgroup_list: linked list for all rdtgroups + * @closid: closid for this rdtgroup + * @cpu_mask: CPUs assigned to this rdtgroup + * @flags: status bits + * @waitcount: how many cpus expect to find this + * group when they acquire rdtgroup_mutex + */ +struct rdtgroup { + struct kernfs_node *kn; + struct list_head rdtgroup_list; + int closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; +}; + +/* rdtgroup.flags */ +#define RDT_DELETED 1 + +/* List of all resource groups */ +extern struct list_head rdt_all_groups; + +int __init rdtgroup_init(void); + +/** + * struct rftype - describe each file in the resctrl file system + * @name: file name + * @mode: access mode + * @kf_ops: operations + * @seq_show: show content of the file + * @write: write to the file + */ +struct rftype { + char *name; + umode_t mode; + struct kernfs_ops *kf_ops; + + int (*seq_show)(struct kernfs_open_file *of, + struct seq_file *sf, void *v); + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +}; + +/** + * struct rdt_resource - attributes of an RDT resource + * @enabled: Is this feature enabled on this machine + * @capable: Is this feature available on this machine + * @name: Name to use in "schemata" file + * @num_closid: Number of CLOSIDs available + * @max_cbm: Largest Cache Bit Mask allowed + * @min_cbm_bits: Minimum number of consecutive bits to be set + * in a cache bit mask + * @domains: All domains for this resource + * @num_domains: Number of domains active + * @msr_base: Base MSR address for CBMs + * @tmp_cbms: Scratch space when updating schemata + * @num_tmp_cbms: Number of CBMs in tmp_cbms + * @cache_level: Which cache level defines scope of this domain + * @cbm_idx_multi: Multiplier of CBM index + * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: + * closid * cbm_idx_multi + cbm_idx_offset + */ +struct rdt_resource { + bool enabled; + bool capable; + char *name; + int num_closid; + int cbm_len; + int min_cbm_bits; + u32 max_cbm; + struct list_head domains; + int num_domains; + int msr_base; + u32 *tmp_cbms; + int num_tmp_cbms; + int cache_level; + int cbm_idx_multi; + int cbm_idx_offset; +}; + +/** + * struct rdt_domain - group of cpus sharing an RDT resource + * @list: all instances of this resource + * @id: unique id for this instance + * @cpu_mask: which cpus share this resource + * @cbm: array of cache bit masks (indexed by CLOSID) + */ +struct rdt_domain { + struct list_head list; + int id; + struct cpumask cpu_mask; + u32 *cbm; +}; + +/** + * struct msr_param - set a range of MSRs from a domain + * @res: The resource to use + * @low: Beginning index from base MSR + * @high: End index + */ +struct msr_param { + struct rdt_resource *res; + int low; + int high; +}; + +extern struct mutex rdtgroup_mutex; + +extern struct rdt_resource rdt_resources_all[]; +extern struct rdtgroup rdtgroup_default; +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); + +int __init rdtgroup_init(void); + +enum { + RDT_RESOURCE_L3, + RDT_RESOURCE_L3DATA, + RDT_RESOURCE_L3CODE, + RDT_RESOURCE_L2, + + /* Must be the last */ + RDT_NUM_RESOURCES, +}; + +#define for_each_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->capable) + +#define for_each_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->enabled) + +/* CPUID.(EAX=10H, ECX=ResID=1).EAX */ +union cpuid_0x10_1_eax { + struct { + unsigned int cbm_len:5; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID=1).EDX */ +union cpuid_0x10_1_edx { + struct { + unsigned int cos_max:16; + } split; + unsigned int full; +}; + +DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid); + +void rdt_cbm_update(void *arg); +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); +void rdtgroup_kn_unlock(struct kernfs_node *kn); +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); + +/* + * intel_rdt_sched_in() - Writes the task's CLOSid to IA32_PQR_MSR + * + * Following considerations are made so that this has minimal impact + * on scheduler hot path: + * - This will stay as no-op unless we are running on an Intel SKU + * which supports resource control and we enable by mounting the + * resctrl file system. + * - Caches the per cpu CLOSid values and does the MSR write only + * when a task with a different CLOSid is scheduled in. + * + * Must be called with preemption disabled. + */ +static inline void intel_rdt_sched_in(void) +{ + if (static_branch_likely(&rdt_enable_key)) { + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + int closid; + + /* + * If this task has a closid assigned, use it. + * Else use the closid assigned to this cpu. + */ + closid = current->closid; + if (closid == 0) + closid = this_cpu_read(cpu_closid); + + if (closid != state->closid) { + state->closid = closid; + wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, closid); + } + } +} + +#else + +static inline void intel_rdt_sched_in(void) {} + +#endif /* CONFIG_INTEL_RDT_A */ +#endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h new file mode 100644 index 000000000000..b31081b89407 --- /dev/null +++ b/arch/x86/include/asm/intel_rdt_common.h @@ -0,0 +1,27 @@ +#ifndef _ASM_X86_INTEL_RDT_COMMON_H +#define _ASM_X86_INTEL_RDT_COMMON_H + +#define MSR_IA32_PQR_ASSOC 0x0c8f + +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @rmid_usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 rmid; + u32 closid; + int rmid_usecnt; +}; + +DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); + +#endif /* _ASM_X86_INTEL_RDT_COMMON_H */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 33b63670bf09..52000010c62e 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -32,6 +32,8 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o +obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index be6337156502..0282b0df004a 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -153,6 +153,7 @@ struct _cpuid4_info_regs { union _cpuid4_leaf_eax eax; union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; + unsigned int id; unsigned long size; struct amd_northbridge *nb; }; @@ -894,6 +895,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index, static void ci_leaf_init(struct cacheinfo *this_leaf, struct _cpuid4_info_regs *base) { + this_leaf->id = base->id; + this_leaf->attributes = CACHE_ID; this_leaf->level = base->eax.split.level; this_leaf->type = cache_type_map[base->eax.split.type]; this_leaf->coherency_line_size = @@ -920,6 +923,22 @@ static int __init_cache_level(unsigned int cpu) return 0; } +/* + * The max shared threads number comes from CPUID.4:EAX[25-14] with input + * ECX as cache index. Then right shift apicid by the number's order to get + * cache id for this cache node. + */ +static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + unsigned long num_threads_sharing; + int index_msb; + + num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + id4_regs->id = c->apicid >> index_msb; +} + static int __populate_cache_leaves(unsigned int cpu) { unsigned int idx, ret; @@ -931,6 +950,7 @@ static int __populate_cache_leaves(unsigned int cpu) ret = cpuid4_cache_lookup_regs(idx, &id4_regs); if (ret) return ret; + get_cache_id(cpu, &id4_regs); ci_leaf_init(this_leaf++, &id4_regs); __cache_cpumap_setup(cpu, idx, &id4_regs); } diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c new file mode 100644 index 000000000000..5a533fefefa0 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -0,0 +1,403 @@ +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu <[email protected]> + * Tony Luck <[email protected]> + * Vikas Shivappa <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/cacheinfo.h> +#include <linux/cpuhotplug.h> + +#include <asm/intel-family.h> +#include <asm/intel_rdt.h> + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + +DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); + +#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) + +struct rdt_resource rdt_resources_all[] = { + { + .name = "L3", + .domains = domain_init(RDT_RESOURCE_L3), + .msr_base = IA32_L3_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 3, + .cbm_idx_multi = 1, + .cbm_idx_offset = 0 + }, + { + .name = "L3DATA", + .domains = domain_init(RDT_RESOURCE_L3DATA), + .msr_base = IA32_L3_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 3, + .cbm_idx_multi = 2, + .cbm_idx_offset = 0 + }, + { + .name = "L3CODE", + .domains = domain_init(RDT_RESOURCE_L3CODE), + .msr_base = IA32_L3_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 3, + .cbm_idx_multi = 2, + .cbm_idx_offset = 1 + }, + { + .name = "L2", + .domains = domain_init(RDT_RESOURCE_L2), + .msr_base = IA32_L2_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 2, + .cbm_idx_multi = 1, + .cbm_idx_offset = 0 + }, +}; + +static int cbm_idx(struct rdt_resource *r, int closid) +{ + return closid * r->cbm_idx_multi + r->cbm_idx_offset; +} + +/* + * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs + * as they do not have CPUID enumeration support for Cache allocation. + * The check for Vendor/Family/Model is not enough to guarantee that + * the MSRs won't #GP fault because only the following SKUs support + * CAT: + * Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz + * Intel(R) Xeon(R) CPU E5-2648L v3 @ 1.80GHz + * Intel(R) Xeon(R) CPU E5-2628L v3 @ 2.00GHz + * Intel(R) Xeon(R) CPU E5-2618L v3 @ 2.30GHz + * Intel(R) Xeon(R) CPU E5-2608L v3 @ 2.00GHz + * Intel(R) Xeon(R) CPU E5-2658A v3 @ 2.20GHz + * + * Probe by trying to write the first of the L3 cach mask registers + * and checking that the bits stick. Max CLOSids is always 4 and max cbm length + * is always 20 on hsw server parts. The minimum cache bitmask length + * allowed for HSW server is always 2 bits. Hardcode all of them. + */ +static inline bool cache_alloc_hsw_probe(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6 && + boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + u32 l, h, max_cbm = BIT_MASK(20) - 1; + + if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) + return false; + rdmsr(IA32_L3_CBM_BASE, l, h); + + /* If all the bits were set in MSR, return success */ + if (l != max_cbm) + return false; + + r->num_closid = 4; + r->cbm_len = 20; + r->max_cbm = max_cbm; + r->min_cbm_bits = 2; + r->capable = true; + r->enabled = true; + + return true; + } + + return false; +} + +static void rdt_get_config(int idx, struct rdt_resource *r) +{ + union cpuid_0x10_1_eax eax; + union cpuid_0x10_1_edx edx; + u32 ebx, ecx; + + cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max + 1; + r->cbm_len = eax.split.cbm_len + 1; + r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->capable = true; + r->enabled = true; +} + +static void rdt_get_cdp_l3_config(int type) +{ + struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_resource *r = &rdt_resources_all[type]; + + r->num_closid = r_l3->num_closid / 2; + r->cbm_len = r_l3->cbm_len; + r->max_cbm = r_l3->max_cbm; + r->capable = true; + /* + * By default, CDP is disabled. CDP can be enabled by mount parameter + * "cdp" during resctrl file system mount time. + */ + r->enabled = false; +} + +static inline bool get_rdt_resources(void) +{ + bool ret = false; + + if (cache_alloc_hsw_probe()) + return true; + + if (!boot_cpu_has(X86_FEATURE_RDT_A)) + return false; + + if (boot_cpu_has(X86_FEATURE_CAT_L3)) { + rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]); + if (boot_cpu_has(X86_FEATURE_CDP_L3)) { + rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA); + rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE); + } + ret = true; + } + if (boot_cpu_has(X86_FEATURE_CAT_L2)) { + /* CPUID 0x10.2 fields are same format at 0x10.1 */ + rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); + ret = true; + } + + return ret; +} + +static int get_cache_id(int cpu, int level) +{ + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); + int i; + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == level) + return ci->info_list[i].id; + } + + return -1; +} + +void rdt_cbm_update(void *arg) +{ + struct msr_param *m = (struct msr_param *)arg; + struct rdt_resource *r = m->res; + int i, cpu = smp_processor_id(); + struct rdt_domain *d; + + list_for_each_entry(d, &r->domains, list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->cpu_mask)) + goto found; + } + pr_info_once("cpu %d not found in any domain for resource %s\n", + cpu, r->name); + + return; + +found: + for (i = m->low; i < m->high; i++) { + int idx = cbm_idx(r, i); + + wrmsrl(r->msr_base + idx, d->cbm[i]); + } +} + +/* + * rdt_find_domain - Find a domain in a resource that matches input resource id + * + * Search resource r's domain list to find the resource id. If the resource + * id is found in a domain, return the domain. Otherwise, if requested by + * caller, return the first domain whose id is bigger than the input id. + * The domain list is sorted by id in ascending order. + */ +static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos) +{ + struct rdt_domain *d; + struct list_head *l; + + if (id < 0) + return ERR_PTR(id); + + list_for_each(l, &r->domains) { + d = list_entry(l, struct rdt_domain, list); + /* When id is found, return its domain. */ + if (id == d->id) + return d; + /* Stop searching when finding id's position in sorted list. */ + if (id < d->id) + break; + } + + if (pos) + *pos = l; + + return NULL; +} + +/* + * domain_add_cpu - Add a cpu to a resource's domain list. + * + * If an existing domain in the resource r's domain list matches the cpu's + * resource id, add the cpu in the domain. + * + * Otherwise, a new domain is allocated and inserted into the right position + * in the domain list sorted by id in ascending order. + * + * The order in the domain list is visible to users when we print entries + * in the schemata file and schemata input is validated to have the same order + * as this list. + */ +static void domain_add_cpu(int cpu, struct rdt_resource *r) +{ + int i, id = get_cache_id(cpu, r->cache_level); + struct list_head *add_pos = NULL; + struct rdt_domain *d; + + d = rdt_find_domain(r, id, &add_pos); + if (IS_ERR(d)) { + pr_warn("Could't find cache id for cpu %d\n", cpu); + return; + } + + if (d) { + cpumask_set_cpu(cpu, &d->cpu_mask); + return; + } + + d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); + if (!d) + return; + + d->id = id; + + d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL); + if (!d->cbm) { + kfree(d); + return; + } + + for (i = 0; i < r->num_closid; i++) { + int idx = cbm_idx(r, i); + + d->cbm[i] = r->max_cbm; + wrmsrl(r->msr_base + idx, d->cbm[i]); + } + + cpumask_set_cpu(cpu, &d->cpu_mask); + list_add_tail(&d->list, add_pos); + r->num_domains++; +} + +static void domain_remove_cpu(int cpu, struct rdt_resource *r) +{ + int id = get_cache_id(cpu, r->cache_level); + struct rdt_domain *d; + + d = rdt_find_domain(r, id, NULL); + if (IS_ERR_OR_NULL(d)) { + pr_warn("Could't find cache id for cpu %d\n", cpu); + return; + } + + cpumask_clear_cpu(cpu, &d->cpu_mask); + if (cpumask_empty(&d->cpu_mask)) { + r->num_domains--; + kfree(d->cbm); + list_del(&d->list); + kfree(d); + } +} + +static void clear_closid(int cpu) +{ + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + + per_cpu(cpu_closid, cpu) = 0; + state->closid = 0; + wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0); +} + +static int intel_rdt_online_cpu(unsigned int cpu) +{ + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + for_each_capable_rdt_resource(r) + domain_add_cpu(cpu, r); + /* The cpu is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + clear_closid(cpu); + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int intel_rdt_offline_cpu(unsigned int cpu) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + for_each_capable_rdt_resource(r) + domain_remove_cpu(cpu, r); + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) + break; + } + clear_closid(cpu); + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int __init intel_rdt_late_init(void) +{ + struct rdt_resource *r; + int state, ret; + + if (!get_rdt_resources()) + return -ENODEV; + + state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "x86/rdt/cat:online:", + intel_rdt_online_cpu, intel_rdt_offline_cpu); + if (state < 0) + return state; + + ret = rdtgroup_init(); + if (ret) { + cpuhp_remove_state(state); + return ret; + } + + for_each_capable_rdt_resource(r) + pr_info("Intel RDT %s allocation detected\n", r->name); + + return 0; +} + +late_initcall(intel_rdt_late_init); diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c new file mode 100644 index 000000000000..8af04afdfcb9 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -0,0 +1,1115 @@ +/* + * User interface for Resource Alloction in Resource Director Technology(RDT) + * + * Copyright (C) 2016 Intel Corporation + * + * Author: Fenghua Yu <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cpu.h> +#include <linux/fs.h> +#include <linux/sysfs.h> +#include <linux/kernfs.h> +#include <linux/seq_file.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <linux/task_work.h> + +#include <uapi/linux/magic.h> + +#include <asm/intel_rdt.h> +#include <asm/intel_rdt_common.h> + +DEFINE_STATIC_KEY_FALSE(rdt_enable_key); +struct kernfs_root *rdt_root; +struct rdtgroup rdtgroup_default; +LIST_HEAD(rdt_all_groups); + +/* Kernel fs node for "info" directory under root */ +static struct kernfs_node *kn_info; + +/* + * Trivial allocator for CLOSIDs. Since h/w only supports a small number, + * we can keep a bitmap of free CLOSIDs in a single integer. + * + * Using a global CLOSID across all resources has some advantages and + * some drawbacks: + * + We can simply set "current->closid" to assign a task to a resource + * group. + * + Context switch code can avoid extra memory references deciding which + * CLOSID to load into the PQR_ASSOC MSR + * - We give up some options in configuring resource groups across multi-socket + * systems. + * - Our choices on how to configure each resource become progressively more + * limited as the number of resources grows. + */ +static int closid_free_map; + +static void closid_init(void) +{ + struct rdt_resource *r; + int rdt_min_closid = 32; + + /* Compute rdt_min_closid across all resources */ + for_each_enabled_rdt_resource(r) + rdt_min_closid = min(rdt_min_closid, r->num_closid); + + closid_free_map = BIT_MASK(rdt_min_closid) - 1; + + /* CLOSID 0 is always reserved for the default group */ + closid_free_map &= ~1; +} + +int closid_alloc(void) +{ + int closid = ffs(closid_free_map); + + if (closid == 0) + return -ENOSPC; + closid--; + closid_free_map &= ~(1 << closid); + + return closid; +} + +static void closid_free(int closid) +{ + closid_free_map |= 1 << closid; +} + +/* set uid and gid of rdtgroup dirs and files to that of the creator */ +static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) +{ + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; + + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; + + return kernfs_setattr(kn, &iattr); +} + +static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) +{ + struct kernfs_node *kn; + int ret; + + kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, + 0, rft->kf_ops, rft, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } + + return 0; +} + +static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts, + int len) +{ + struct rftype *rft; + int ret; + + lockdep_assert_held(&rdtgroup_mutex); + + for (rft = rfts; rft < rfts + len; rft++) { + ret = rdtgroup_add_file(kn, rft); + if (ret) + goto error; + } + + return 0; +error: + pr_warn("Failed to add %s, err=%d\n", rft->name, ret); + while (--rft >= rfts) + kernfs_remove_by_name(kn, rft->name); + return ret; +} + +static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + struct rftype *rft = of->kn->priv; + + if (rft->seq_show) + return rft->seq_show(of, m, arg); + return 0; +} + +static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct rftype *rft = of->kn->priv; + + if (rft->write) + return rft->write(of, buf, nbytes, off); + + return -EINVAL; +} + +static struct kernfs_ops rdtgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .write = rdtgroup_file_write, + .seq_show = rdtgroup_seqfile_show, +}; + +static int rdtgroup_cpus_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) + seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +/* + * This is safe against intel_rdt_sched_in() called from __switch_to() + * because __switch_to() is executed with interrupts disabled. A local call + * from rdt_update_closid() is proteced against __switch_to() because + * preemption is disabled. + */ +static void rdt_update_cpu_closid(void *closid) +{ + if (closid) + this_cpu_write(cpu_closid, *(int *)closid); + /* + * We cannot unconditionally write the MSR because the current + * executing task might have its own closid selected. Just reuse + * the context switch code. + */ + intel_rdt_sched_in(); +} + +/* + * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, + * + * Per task closids must have been set up before calling this function. + * + * The per cpu closids are updated with the smp function call, when @closid + * is not NULL. If @closid is NULL then all affected percpu closids must + * have been set up before calling this function. + */ +static void +rdt_update_closid(const struct cpumask *cpu_mask, int *closid) +{ + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_update_cpu_closid(closid); + smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1); + put_cpu(); +} + +static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + cpumask_var_t tmpmask, newmask; + struct rdtgroup *rdtgrp, *r; + int ret; + + if (!buf) + return -EINVAL; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + return -ENOMEM; + } + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto unlock; + } + + ret = cpumask_parse(buf, newmask); + if (ret) + goto unlock; + + /* check that user didn't specify any offline cpus */ + cpumask_andnot(tmpmask, newmask, cpu_online_mask); + if (cpumask_weight(tmpmask)) { + ret = -EINVAL; + goto unlock; + } + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Can't drop from default group */ + if (rdtgrp == &rdtgroup_default) { + ret = -EINVAL; + goto unlock; + } + /* Give any dropped cpus to rdtgroup_default */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, tmpmask); + rdt_update_closid(tmpmask, &rdtgroup_default.closid); + } + + /* + * If we added cpus, remove them from previous group that owned them + * and update per-cpu closid + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { + if (r == rdtgrp) + continue; + cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask); + } + rdt_update_closid(tmpmask, &rdtgrp->closid); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + +unlock: + rdtgroup_kn_unlock(of->kn); + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + + return ret ?: nbytes; +} + +struct task_move_callback { + struct callback_head work; + struct rdtgroup *rdtgrp; +}; + +static void move_myself(struct callback_head *head) +{ + struct task_move_callback *callback; + struct rdtgroup *rdtgrp; + + callback = container_of(head, struct task_move_callback, work); + rdtgrp = callback->rdtgrp; + + /* + * If resource group was deleted before this task work callback + * was invoked, then assign the task to root group and free the + * resource group. + */ + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + current->closid = 0; + kfree(rdtgrp); + } + + preempt_disable(); + /* update PQR_ASSOC MSR to make resource group go into effect */ + intel_rdt_sched_in(); + preempt_enable(); + + kfree(callback); +} + +static int __rdtgroup_move_task(struct task_struct *tsk, + struct rdtgroup *rdtgrp) +{ + struct task_move_callback *callback; + int ret; + + callback = kzalloc(sizeof(*callback), GFP_KERNEL); + if (!callback) + return -ENOMEM; + callback->work.func = move_myself; + callback->rdtgrp = rdtgrp; + + /* + * Take a refcount, so rdtgrp cannot be freed before the + * callback has been invoked. + */ + atomic_inc(&rdtgrp->waitcount); + ret = task_work_add(tsk, &callback->work, true); + if (ret) { + /* + * Task is exiting. Drop the refcount and free the callback. + * No need to check the refcount as the group cannot be + * deleted before the write function unlocks rdtgroup_mutex. + */ + atomic_dec(&rdtgrp->waitcount); + kfree(callback); + } else { + tsk->closid = rdtgrp->closid; + } + return ret; +} + +static int rdtgroup_task_write_permission(struct task_struct *task, + struct kernfs_open_file *of) +{ + const struct cred *tcred = get_task_cred(task); + const struct cred *cred = current_cred(); + int ret = 0; + + /* + * Even if we're attaching all tasks in the thread group, we only + * need to check permissions on one of them. + */ + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) + ret = -EPERM; + + put_cred(tcred); + return ret; +} + +static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp, + struct kernfs_open_file *of) +{ + struct task_struct *tsk; + int ret; + + rcu_read_lock(); + if (pid) { + tsk = find_task_by_vpid(pid); + if (!tsk) { + rcu_read_unlock(); + return -ESRCH; + } + } else { + tsk = current; + } + + get_task_struct(tsk); + rcu_read_unlock(); + + ret = rdtgroup_task_write_permission(tsk, of); + if (!ret) + ret = __rdtgroup_move_task(tsk, rdtgrp); + + put_task_struct(tsk); + return ret; +} + +static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + pid_t pid; + + if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) + return -EINVAL; + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) + ret = rdtgroup_move_task(pid, rdtgrp, of); + else + ret = -ENOENT; + + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) +{ + struct task_struct *p, *t; + + rcu_read_lock(); + for_each_process_thread(p, t) { + if (t->closid == r->closid) + seq_printf(s, "%d\n", t->pid); + } + rcu_read_unlock(); +} + +static int rdtgroup_tasks_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + show_rdt_tasks(rdtgrp, s); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +/* Files in each rdtgroup */ +static struct rftype rdtgroup_base_files[] = { + { + .name = "cpus", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + }, + { + .name = "tasks", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_tasks_write, + .seq_show = rdtgroup_tasks_show, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + }, +}; + +static int rdt_num_closids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->num_closid); + + return 0; +} + +static int rdt_cbm_mask_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%x\n", r->max_cbm); + + return 0; +} + +static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->min_cbm_bits); + + return 0; +} + +/* rdtgroup information files for one cache resource. */ +static struct rftype res_info_files[] = { + { + .name = "num_closids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_closids_show, + }, + { + .name = "cbm_mask", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_cbm_mask_show, + }, + { + .name = "min_cbm_bits", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_min_cbm_bits_show, + }, +}; + +static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) +{ + struct kernfs_node *kn_subdir; + struct rdt_resource *r; + int ret; + + /* create the directory */ + kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); + if (IS_ERR(kn_info)) + return PTR_ERR(kn_info); + kernfs_get(kn_info); + + for_each_enabled_rdt_resource(r) { + kn_subdir = kernfs_create_dir(kn_info, r->name, + kn_info->mode, r); + if (IS_ERR(kn_subdir)) { + ret = PTR_ERR(kn_subdir); + goto out_destroy; + } + kernfs_get(kn_subdir); + ret = rdtgroup_kn_set_ugid(kn_subdir); + if (ret) + goto out_destroy; + ret = rdtgroup_add_files(kn_subdir, res_info_files, + ARRAY_SIZE(res_info_files)); + if (ret) + goto out_destroy; + kernfs_activate(kn_subdir); + } + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that @rdtgrp->kn is always accessible. + */ + kernfs_get(kn_info); + + ret = rdtgroup_kn_set_ugid(kn_info); + if (ret) + goto out_destroy; + + kernfs_activate(kn_info); + + return 0; + +out_destroy: + kernfs_remove(kn_info); + return ret; +} + +static void l3_qos_cfg_update(void *arg) +{ + bool *enable = arg; + + wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); +} + +static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) +{ + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + list_for_each_entry(d, &r->domains, list) { + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + } + cpu = get_cpu(); + /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + l3_qos_cfg_update(&enable); + /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +static int cdp_enable(void) +{ + struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; + int ret; + + if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) + return -EINVAL; + + ret = set_l3_qos_cfg(r_l3, true); + if (!ret) { + r_l3->enabled = false; + r_l3data->enabled = true; + r_l3code->enabled = true; + } + return ret; +} + +static void cdp_disable(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + + r->enabled = r->capable; + + if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) { + rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false; + rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false; + set_l3_qos_cfg(r, false); + } +} + +static int parse_rdtgroupfs_options(char *data) +{ + char *token, *o = data; + int ret = 0; + + while ((token = strsep(&o, ",")) != NULL) { + if (!*token) + return -EINVAL; + + if (!strcmp(token, "cdp")) + ret = cdp_enable(); + } + + return ret; +} + +/* + * We don't allow rdtgroup directories to be created anywhere + * except the root directory. Thus when looking for the rdtgroup + * structure for a kernfs node we are either looking at a directory, + * in which case the rdtgroup structure is pointed at by the "priv" + * field, otherwise we have a file, and need only look to the parent + * to find the rdtgroup. + */ +static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) +{ + if (kernfs_type(kn) == KERNFS_DIR) { + /* + * All the resource directories use "kn->priv" + * to point to the "struct rdtgroup" for the + * resource. "info" and its subdirectories don't + * have rdtgroup structures, so return NULL here. + */ + if (kn == kn_info || kn->parent == kn_info) + return NULL; + else + return kn->priv; + } else { + return kn->parent->priv; + } +} + +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return NULL; + + atomic_inc(&rdtgrp->waitcount); + kernfs_break_active_protection(kn); + + mutex_lock(&rdtgroup_mutex); + + /* Was this group deleted while we waited? */ + if (rdtgrp->flags & RDT_DELETED) + return NULL; + + return rdtgrp; +} + +void rdtgroup_kn_unlock(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return; + + mutex_unlock(&rdtgroup_mutex); + + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + kernfs_unbreak_active_protection(kn); + kernfs_put(kn); + kfree(rdtgrp); + } else { + kernfs_unbreak_active_protection(kn); + } +} + +static struct dentry *rdt_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data) +{ + struct dentry *dentry; + int ret; + + mutex_lock(&rdtgroup_mutex); + /* + * resctrl file system can only be mounted once. + */ + if (static_branch_unlikely(&rdt_enable_key)) { + dentry = ERR_PTR(-EBUSY); + goto out; + } + + ret = parse_rdtgroupfs_options(data); + if (ret) { + dentry = ERR_PTR(ret); + goto out_cdp; + } + + closid_init(); + + ret = rdtgroup_create_info_dir(rdtgroup_default.kn); + if (ret) { + dentry = ERR_PTR(ret); + goto out_cdp; + } + + dentry = kernfs_mount(fs_type, flags, rdt_root, + RDTGROUP_SUPER_MAGIC, NULL); + if (IS_ERR(dentry)) + goto out_cdp; + + static_branch_enable(&rdt_enable_key); + goto out; + +out_cdp: + cdp_disable(); +out: + mutex_unlock(&rdtgroup_mutex); + + return dentry; +} + +static int reset_all_cbms(struct rdt_resource *r) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int i, cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.res = r; + msr_param.low = 0; + msr_param.high = r->num_closid; + + /* + * Disable resource control for this resource by setting all + * CBMs in all domains to the maximum mask value. Pick one CPU + * from each domain to update the MSRs below. + */ + list_for_each_entry(d, &r->domains, list) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + + for (i = 0; i < r->num_closid; i++) + d->cbm[i] = r->max_cbm; + } + cpu = get_cpu(); + /* Update CBM on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_cbm_update(&msr_param); + /* Update CBM on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +/* + * Move tasks from one to the other group. If @from is NULL, then all tasks + * in the systems are moved unconditionally (used for teardown). + * + * If @mask is not NULL the cpus on which moved tasks are running are set + * in that mask so the update smp function call is restricted to affected + * cpus. + */ +static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, + struct cpumask *mask) +{ + struct task_struct *p, *t; + + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { + if (!from || t->closid == from->closid) { + t->closid = to->closid; +#ifdef CONFIG_SMP + /* + * This is safe on x86 w/o barriers as the ordering + * of writing to task_cpu() and t->on_cpu is + * reverse to the reading here. The detection is + * inaccurate as tasks might move or schedule + * before the smp function call takes place. In + * such a case the function call is pointless, but + * there is no other side effect. + */ + if (mask && t->on_cpu) + cpumask_set_cpu(task_cpu(t), mask); +#endif + } + } + read_unlock(&tasklist_lock); +} + +/* + * Forcibly remove all of subdirectories under root. + */ +static void rmdir_all_sub(void) +{ + struct rdtgroup *rdtgrp, *tmp; + + /* Move all tasks to the default resource group */ + rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); + + list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { + /* Remove each rdtgroup other than root */ + if (rdtgrp == &rdtgroup_default) + continue; + + /* + * Give any CPUs back to the default group. We cannot copy + * cpu_online_mask because a CPU might have executed the + * offline callback already, but is still marked online. + */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + + kernfs_remove(rdtgrp->kn); + list_del(&rdtgrp->rdtgroup_list); + kfree(rdtgrp); + } + /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ + get_online_cpus(); + rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid); + put_online_cpus(); + + kernfs_remove(kn_info); +} + +static void rdt_kill_sb(struct super_block *sb) +{ + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + + /*Put everything back to default values. */ + for_each_enabled_rdt_resource(r) + reset_all_cbms(r); + cdp_disable(); + rmdir_all_sub(); + static_branch_disable(&rdt_enable_key); + kernfs_kill_sb(sb); + mutex_unlock(&rdtgroup_mutex); +} + +static struct file_system_type rdt_fs_type = { + .name = "resctrl", + .mount = rdt_mount, + .kill_sb = rdt_kill_sb, +}; + +static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + struct rdtgroup *parent, *rdtgrp; + struct kernfs_node *kn; + int ret, closid; + + /* Only allow mkdir in the root directory */ + if (parent_kn != rdtgroup_default.kn) + return -EPERM; + + /* Do not accept '\n' to avoid unparsable situation. */ + if (strchr(name, '\n')) + return -EINVAL; + + parent = rdtgroup_kn_lock_live(parent_kn); + if (!parent) { + ret = -ENODEV; + goto out_unlock; + } + + ret = closid_alloc(); + if (ret < 0) + goto out_unlock; + closid = ret; + + /* allocate the rdtgroup. */ + rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); + if (!rdtgrp) { + ret = -ENOSPC; + goto out_closid_free; + } + rdtgrp->closid = closid; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + /* kernfs creates the directory for rdtgrp */ + kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); + goto out_cancel_ref; + } + rdtgrp->kn = kn; + + /* + * kernfs_remove() will drop the reference count on "kn" which + * will free it. But we still need it to stick around for the + * rdtgroup_kn_unlock(kn} call below. Take one extra reference + * here, which will be dropped inside rdtgroup_kn_unlock(). + */ + kernfs_get(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + ret = rdtgroup_add_files(kn, rdtgroup_base_files, + ARRAY_SIZE(rdtgroup_base_files)); + if (ret) + goto out_destroy; + + kernfs_activate(kn); + + ret = 0; + goto out_unlock; + +out_destroy: + kernfs_remove(rdtgrp->kn); +out_cancel_ref: + list_del(&rdtgrp->rdtgroup_list); + kfree(rdtgrp); +out_closid_free: + closid_free(closid); +out_unlock: + rdtgroup_kn_unlock(parent_kn); + return ret; +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + int ret, cpu, closid = rdtgroup_default.closid; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + rdtgrp = rdtgroup_kn_lock_live(kn); + if (!rdtgrp) { + ret = -EPERM; + goto out; + } + + /* Give any tasks back to the default group */ + rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); + + /* Give any CPUs back to the default group */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + + /* Update per cpu closid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) + per_cpu(cpu_closid, cpu) = closid; + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + rdt_update_closid(tmpmask, NULL); + + rdtgrp->flags = RDT_DELETED; + closid_free(rdtgrp->closid); + list_del(&rdtgrp->rdtgroup_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + ret = 0; +out: + rdtgroup_kn_unlock(kn); + free_cpumask_var(tmpmask); + return ret; +} + +static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) +{ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) + seq_puts(seq, ",cdp"); + return 0; +} + +static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { + .mkdir = rdtgroup_mkdir, + .rmdir = rdtgroup_rmdir, + .show_options = rdtgroup_show_options, +}; + +static int __init rdtgroup_setup_root(void) +{ + int ret; + + rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, + KERNFS_ROOT_CREATE_DEACTIVATED, + &rdtgroup_default); + if (IS_ERR(rdt_root)) + return PTR_ERR(rdt_root); + + mutex_lock(&rdtgroup_mutex); + + rdtgroup_default.closid = 0; + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); + + ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files, + ARRAY_SIZE(rdtgroup_base_files)); + if (ret) { + kernfs_destroy_root(rdt_root); + goto out; + } + + rdtgroup_default.kn = rdt_root->kn; + kernfs_activate(rdtgroup_default.kn); + +out: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} + +/* + * rdtgroup_init - rdtgroup initialization + * + * Setup resctrl file system including set up root, create mount point, + * register rdtgroup filesystem, and initialize files under root directory. + * + * Return: 0 on success or -errno + */ +int __init rdtgroup_init(void) +{ + int ret = 0; + + ret = rdtgroup_setup_root(); + if (ret) + return ret; + + ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + if (ret) + goto cleanup_root; + + ret = register_filesystem(&rdt_fs_type); + if (ret) + goto cleanup_mountpoint; + + return 0; + +cleanup_mountpoint: + sysfs_remove_mount_point(fs_kobj, "resctrl"); +cleanup_root: + kernfs_destroy_root(rdt_root); + + return ret; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c new file mode 100644 index 000000000000..f369cb8db0d5 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c @@ -0,0 +1,245 @@ +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu <[email protected]> + * Tony Luck <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernfs.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <asm/intel_rdt.h> + +/* + * Check whether a cache bit mask is valid. The SDM says: + * Please note that all (and only) contiguous '1' combinations + * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). + * Additionally Haswell requires at least two bits set. + */ +static bool cbm_validate(unsigned long var, struct rdt_resource *r) +{ + unsigned long first_bit, zero_bit; + + if (var == 0 || var > r->max_cbm) + return false; + + first_bit = find_first_bit(&var, r->cbm_len); + zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit); + + if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len) + return false; + + if ((zero_bit - first_bit) < r->min_cbm_bits) + return false; + return true; +} + +/* + * Read one cache bit mask (hex). Check that it is valid for the current + * resource type. + */ +static int parse_cbm(char *buf, struct rdt_resource *r) +{ + unsigned long data; + int ret; + + ret = kstrtoul(buf, 16, &data); + if (ret) + return ret; + if (!cbm_validate(data, r)) + return -EINVAL; + r->tmp_cbms[r->num_tmp_cbms++] = data; + + return 0; +} + +/* + * For each domain in this resource we expect to find a series of: + * id=mask + * separated by ";". The "id" is in decimal, and must appear in the + * right order. + */ +static int parse_line(char *line, struct rdt_resource *r) +{ + char *dom = NULL, *id; + struct rdt_domain *d; + unsigned long dom_id; + + list_for_each_entry(d, &r->domains, list) { + dom = strsep(&line, ";"); + if (!dom) + return -EINVAL; + id = strsep(&dom, "="); + if (kstrtoul(id, 10, &dom_id) || dom_id != d->id) + return -EINVAL; + if (parse_cbm(dom, r)) + return -EINVAL; + } + + /* Any garbage at the end of the line? */ + if (line && line[0]) + return -EINVAL; + return 0; +} + +static int update_domains(struct rdt_resource *r, int closid) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int cpu, idx = 0; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.low = closid; + msr_param.high = msr_param.low + 1; + msr_param.res = r; + + list_for_each_entry(d, &r->domains, list) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + d->cbm[msr_param.low] = r->tmp_cbms[idx++]; + } + cpu = get_cpu(); + /* Update CBM on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_cbm_update(&msr_param); + /* Update CBM on other cpus. */ + smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + char *tok, *resname; + int closid, ret = 0; + u32 *l3_cbms = NULL; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + closid = rdtgrp->closid; + + /* get scratch space to save all the masks while we validate input */ + for_each_enabled_rdt_resource(r) { + r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms), + GFP_KERNEL); + if (!r->tmp_cbms) { + ret = -ENOMEM; + goto out; + } + r->num_tmp_cbms = 0; + } + + while ((tok = strsep(&buf, "\n")) != NULL) { + resname = strsep(&tok, ":"); + if (!tok) { + ret = -EINVAL; + goto out; + } + for_each_enabled_rdt_resource(r) { + if (!strcmp(resname, r->name) && + closid < r->num_closid) { + ret = parse_line(tok, r); + if (ret) + goto out; + break; + } + } + if (!r->name) { + ret = -EINVAL; + goto out; + } + } + + /* Did the parser find all the masks we need? */ + for_each_enabled_rdt_resource(r) { + if (r->num_tmp_cbms != r->num_domains) { + ret = -EINVAL; + goto out; + } + } + + for_each_enabled_rdt_resource(r) { + ret = update_domains(r, closid); + if (ret) + goto out; + } + +out: + rdtgroup_kn_unlock(of->kn); + for_each_enabled_rdt_resource(r) { + kfree(r->tmp_cbms); + r->tmp_cbms = NULL; + } + return ret ?: nbytes; +} + +static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) +{ + struct rdt_domain *dom; + bool sep = false; + + seq_printf(s, "%s:", r->name); + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_puts(s, ";"); + seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]); + sep = true; + } + seq_puts(s, "\n"); +} + +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + int closid, ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) { + closid = rdtgrp->closid; + for_each_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } + } else { + ret = -ENOENT; + } + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index d1316f9c8329..d9794060fe22 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -20,12 +20,15 @@ struct cpuid_bit { /* Please keep the leaf sorted by cpuid_bit.level for faster search. */ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, - { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, + { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, - { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, - { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, + { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, + { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, + { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, + { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index d0d744108594..a0ac3e81518a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -53,6 +53,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> +#include <asm/intel_rdt.h> void __show_regs(struct pt_regs *regs, int all) { @@ -296,5 +297,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(current_task, next_p); + /* Load the Intel cache allocation PQR MSR. */ + intel_rdt_sched_in(); + return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a76b65e3e615..a61e141b6891 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -49,6 +49,7 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> +#include <asm/intel_rdt.h> __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); @@ -476,6 +477,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) loadsegment(ss, __KERNEL_DS); } + /* Load the Intel cache allocation PQR MSR. */ + intel_rdt_sched_in(); + return prev_p; } diff --git a/block/ioctl.c b/block/ioctl.c index f856963204f4..656c8c6ed206 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -45,6 +45,9 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user || pstart < 0 || plength < 0 || partno > 65535) return -EINVAL; } + /* check if partition is aligned to blocksize */ + if (p.start & (bdev_logical_block_size(bdev) - 1)) + return -EINVAL; mutex_lock(&bdev->bd_mutex); diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 0774799942e0..c6fee7437be4 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -182,6 +182,9 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) __set_bit(WRITE_16, filter->write_ok); __set_bit(WRITE_LONG, filter->write_ok); __set_bit(WRITE_LONG_2, filter->write_ok); + __set_bit(WRITE_SAME, filter->write_ok); + __set_bit(WRITE_SAME_16, filter->write_ok); + __set_bit(WRITE_SAME_32, filter->write_ok); __set_bit(ERASE, filter->write_ok); __set_bit(GPCMD_MODE_SELECT_10, filter->write_ok); __set_bit(MODE_SELECT, filter->write_ok); diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index 7dd527f8ca1d..94be8a8e6c08 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -166,6 +166,12 @@ acpi_tb_install_table_with_override(struct acpi_table_desc *new_table_desc, acpi_status acpi_tb_parse_root_table(acpi_physical_address rsdp_address); +acpi_status +acpi_tb_get_table(struct acpi_table_desc *table_desc, + struct acpi_table_header **out_table); + +void acpi_tb_put_table(struct acpi_table_desc *table_desc); + /* * tbxfload */ diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 5fb838e592dc..81473a4880ce 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -311,6 +311,8 @@ void acpi_tb_parse_fadt(void) { u32 length; struct acpi_table_header *table; + struct acpi_table_desc *fadt_desc; + acpi_status status; /* * The FADT has multiple versions with different lengths, @@ -319,14 +321,12 @@ void acpi_tb_parse_fadt(void) * Get a local copy of the FADT and convert it to a common format * Map entire FADT, assumed to be smaller than one page. */ - length = acpi_gbl_root_table_list.tables[acpi_gbl_fadt_index].length; - - table = - acpi_os_map_memory(acpi_gbl_root_table_list. - tables[acpi_gbl_fadt_index].address, length); - if (!table) { + fadt_desc = &acpi_gbl_root_table_list.tables[acpi_gbl_fadt_index]; + status = acpi_tb_get_table(fadt_desc, &table); + if (ACPI_FAILURE(status)) { return; } + length = fadt_desc->length; /* * Validate the FADT checksum before we copy the table. Ignore @@ -340,7 +340,7 @@ void acpi_tb_parse_fadt(void) /* All done with the real FADT, unmap it */ - acpi_os_unmap_memory(table, length); + acpi_tb_put_table(fadt_desc); /* Obtain the DSDT and FACS tables via their addresses within the FADT */ diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 51eb07cf9898..86854e846800 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -381,3 +381,88 @@ next_table: acpi_os_unmap_memory(table, length); return_ACPI_STATUS(AE_OK); } + +/******************************************************************************* + * + * FUNCTION: acpi_tb_get_table + * + * PARAMETERS: table_desc - Table descriptor + * out_table - Where the pointer to the table is returned + * + * RETURN: Status and pointer to the requested table + * + * DESCRIPTION: Increase a reference to a table descriptor and return the + * validated table pointer. + * If the table descriptor is an entry of the root table list, + * this API must be invoked with ACPI_MTX_TABLES acquired. + * + ******************************************************************************/ + +acpi_status +acpi_tb_get_table(struct acpi_table_desc *table_desc, + struct acpi_table_header **out_table) +{ + acpi_status status; + + ACPI_FUNCTION_TRACE(acpi_tb_get_table); + + if (table_desc->validation_count == 0) { + + /* Table need to be "VALIDATED" */ + + status = acpi_tb_validate_table(table_desc); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + } + + table_desc->validation_count++; + if (table_desc->validation_count == 0) { + ACPI_ERROR((AE_INFO, + "Table %p, Validation count is zero after increment\n", + table_desc)); + table_desc->validation_count--; + return_ACPI_STATUS(AE_LIMIT); + } + + *out_table = table_desc->pointer; + return_ACPI_STATUS(AE_OK); +} + +/******************************************************************************* + * + * FUNCTION: acpi_tb_put_table + * + * PARAMETERS: table_desc - Table descriptor + * + * RETURN: None + * + * DESCRIPTION: Decrease a reference to a table descriptor and release the + * validated table pointer if no references. + * If the table descriptor is an entry of the root table list, + * this API must be invoked with ACPI_MTX_TABLES acquired. + * + ******************************************************************************/ + +void acpi_tb_put_table(struct acpi_table_desc *table_desc) +{ + + ACPI_FUNCTION_TRACE(acpi_tb_put_table); + + if (table_desc->validation_count == 0) { + ACPI_WARNING((AE_INFO, + "Table %p, Validation count is zero before decrement\n", + table_desc)); + return_VOID; + } + table_desc->validation_count--; + + if (table_desc->validation_count == 0) { + + /* Table need to be "INVALIDATED" */ + + acpi_tb_invalidate_table(table_desc); + } + + return_VOID; +} diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c index d5adb7ac4684..7684707b254b 100644 --- a/drivers/acpi/acpica/tbxface.c +++ b/drivers/acpi/acpica/tbxface.c @@ -282,7 +282,7 @@ ACPI_EXPORT_SYMBOL(acpi_get_table_header) /******************************************************************************* * - * FUNCTION: acpi_get_table_with_size + * FUNCTION: acpi_get_table * * PARAMETERS: signature - ACPI signature of needed table * instance - Which instance (for SSDTs) @@ -292,16 +292,21 @@ ACPI_EXPORT_SYMBOL(acpi_get_table_header) * * DESCRIPTION: Finds and verifies an ACPI table. Table must be in the * RSDT/XSDT. + * Note that an early stage acpi_get_table() call must be paired + * with an early stage acpi_put_table() call. otherwise the table + * pointer mapped by the early stage mapping implementation may be + * erroneously unmapped by the late stage unmapping implementation + * in an acpi_put_table() invoked during the late stage. * ******************************************************************************/ acpi_status -acpi_get_table_with_size(char *signature, - u32 instance, struct acpi_table_header **out_table, - acpi_size *tbl_size) +acpi_get_table(char *signature, + u32 instance, struct acpi_table_header ** out_table) { u32 i; u32 j; - acpi_status status; + acpi_status status = AE_NOT_FOUND; + struct acpi_table_desc *table_desc; /* Parameter validation */ @@ -309,13 +314,22 @@ acpi_get_table_with_size(char *signature, return (AE_BAD_PARAMETER); } + /* + * Note that the following line is required by some OSPMs, they only + * check if the returned table is NULL instead of the returned status + * to determined if this function is succeeded. + */ + *out_table = NULL; + + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); + /* Walk the root table list */ for (i = 0, j = 0; i < acpi_gbl_root_table_list.current_table_count; i++) { - if (!ACPI_COMPARE_NAME - (&(acpi_gbl_root_table_list.tables[i].signature), - signature)) { + table_desc = &acpi_gbl_root_table_list.tables[i]; + + if (!ACPI_COMPARE_NAME(&table_desc->signature, signature)) { continue; } @@ -323,43 +337,65 @@ acpi_get_table_with_size(char *signature, continue; } - status = - acpi_tb_validate_table(&acpi_gbl_root_table_list.tables[i]); - if (ACPI_SUCCESS(status)) { - *out_table = acpi_gbl_root_table_list.tables[i].pointer; - *tbl_size = acpi_gbl_root_table_list.tables[i].length; - } - - if (!acpi_gbl_permanent_mmap) { - acpi_gbl_root_table_list.tables[i].pointer = NULL; - } - - return (status); + status = acpi_tb_get_table(table_desc, out_table); + break; } - return (AE_NOT_FOUND); + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); + return (status); } -ACPI_EXPORT_SYMBOL(acpi_get_table_with_size) +ACPI_EXPORT_SYMBOL(acpi_get_table) -acpi_status -acpi_get_table(char *signature, - u32 instance, struct acpi_table_header **out_table) +/******************************************************************************* + * + * FUNCTION: acpi_put_table + * + * PARAMETERS: table - The pointer to the table + * + * RETURN: None + * + * DESCRIPTION: Release a table returned by acpi_get_table() and its clones. + * Note that it is not safe if this function was invoked after an + * uninstallation happened to the original table descriptor. + * Currently there is no OSPMs' requirement to handle such + * situations. + * + ******************************************************************************/ +void acpi_put_table(struct acpi_table_header *table) { - acpi_size tbl_size; + u32 i; + struct acpi_table_desc *table_desc; + + ACPI_FUNCTION_TRACE(acpi_put_table); + + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); + + /* Walk the root table list */ + + for (i = 0; i < acpi_gbl_root_table_list.current_table_count; i++) { + table_desc = &acpi_gbl_root_table_list.tables[i]; - return acpi_get_table_with_size(signature, - instance, out_table, &tbl_size); + if (table_desc->pointer != table) { + continue; + } + + acpi_tb_put_table(table_desc); + break; + } + + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); + return_VOID; } -ACPI_EXPORT_SYMBOL(acpi_get_table) +ACPI_EXPORT_SYMBOL(acpi_put_table) /******************************************************************************* * * FUNCTION: acpi_get_table_by_index * * PARAMETERS: table_index - Table index - * table - Where the pointer to the table is returned + * out_table - Where the pointer to the table is returned * * RETURN: Status and pointer to the requested table * @@ -368,7 +404,7 @@ ACPI_EXPORT_SYMBOL(acpi_get_table) * ******************************************************************************/ acpi_status -acpi_get_table_by_index(u32 table_index, struct acpi_table_header **table) +acpi_get_table_by_index(u32 table_index, struct acpi_table_header **out_table) { acpi_status status; @@ -376,35 +412,33 @@ acpi_get_table_by_index(u32 table_index, struct acpi_table_header **table) /* Parameter validation */ - if (!table) { + if (!out_table) { return_ACPI_STATUS(AE_BAD_PARAMETER); } + /* + * Note that the following line is required by some OSPMs, they only + * check if the returned table is NULL instead of the returned status + * to determined if this function is succeeded. + */ + *out_table = NULL; + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); /* Validate index */ if (table_index >= acpi_gbl_root_table_list.current_table_count) { - (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); - return_ACPI_STATUS(AE_BAD_PARAMETER); + status = AE_BAD_PARAMETER; + goto unlock_and_exit; } - if (!acpi_gbl_root_table_list.tables[table_index].pointer) { - - /* Table is not mapped, map it */ + status = + acpi_tb_get_table(&acpi_gbl_root_table_list.tables[table_index], + out_table); - status = - acpi_tb_validate_table(&acpi_gbl_root_table_list. - tables[table_index]); - if (ACPI_FAILURE(status)) { - (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); - return_ACPI_STATUS(status); - } - } - - *table = acpi_gbl_root_table_list.tables[table_index].pointer; +unlock_and_exit: (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); - return_ACPI_STATUS(AE_OK); + return_ACPI_STATUS(status); } ACPI_EXPORT_SYMBOL(acpi_get_table_by_index) diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 5cbefd7621f0..95855cb9d6fb 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -974,7 +974,7 @@ void __init acpi_early_init(void) if (!acpi_strict) acpi_gbl_enable_interpreter_slack = TRUE; - acpi_gbl_permanent_mmap = 1; + acpi_permanent_mmap = true; /* * If the machine falls into the DMI check table, diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 312c4b4dc363..2f82b8eba360 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2806,12 +2806,13 @@ static int acpi_nfit_add(struct acpi_device *adev) acpi_size sz; int rc = 0; - status = acpi_get_table_with_size(ACPI_SIG_NFIT, 0, &tbl, &sz); + status = acpi_get_table(ACPI_SIG_NFIT, 0, &tbl); if (ACPI_FAILURE(status)) { /* This is ok, we could have an nvdimm hotplugged later */ dev_dbg(dev, "failed to find NFIT at startup\n"); return 0; } + sz = tbl->length; acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL); if (!acpi_desc) diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 9a4c6abee63e..a404ff4d7151 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -76,6 +76,7 @@ static struct workqueue_struct *kacpi_notify_wq; static struct workqueue_struct *kacpi_hotplug_wq; static bool acpi_os_initialized; unsigned int acpi_sci_irq = INVALID_ACPI_IRQ; +bool acpi_permanent_mmap = false; /* * This list of permanent mappings is for memory that may be accessed from @@ -306,7 +307,7 @@ static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr) * virtual address). If not found, map it, add it to that list and return a * pointer to it. * - * During early init (when acpi_gbl_permanent_mmap has not been set yet) this + * During early init (when acpi_permanent_mmap has not been set yet) this * routine simply calls __acpi_map_table() to get the job done. */ void __iomem *__ref @@ -322,7 +323,7 @@ acpi_os_map_iomem(acpi_physical_address phys, acpi_size size) return NULL; } - if (!acpi_gbl_permanent_mmap) + if (!acpi_permanent_mmap) return __acpi_map_table((unsigned long)phys, size); mutex_lock(&acpi_ioremap_lock); @@ -392,7 +393,7 @@ static void acpi_os_map_cleanup(struct acpi_ioremap *map) * mappings, drop a reference to it and unmap it if there are no more active * references to it. * - * During early init (when acpi_gbl_permanent_mmap has not been set yet) this + * During early init (when acpi_permanent_mmap has not been set yet) this * routine simply calls __acpi_unmap_table() to get the job done. Since * __acpi_unmap_table() is an __init function, the __ref annotation is needed * here. @@ -401,7 +402,7 @@ void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size) { struct acpi_ioremap *map; - if (!acpi_gbl_permanent_mmap) { + if (!acpi_permanent_mmap) { __acpi_unmap_table(virt, size); return; } @@ -426,12 +427,6 @@ void __ref acpi_os_unmap_memory(void *virt, acpi_size size) } EXPORT_SYMBOL_GPL(acpi_os_unmap_memory); -void __init early_acpi_os_unmap_memory(void __iomem *virt, acpi_size size) -{ - if (!acpi_gbl_permanent_mmap) - __acpi_unmap_table(virt, size); -} - int acpi_os_map_generic_address(struct acpi_generic_address *gas) { u64 addr; diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 5c78ee1860b0..611a5585a902 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -154,18 +154,16 @@ static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt, phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id) { struct acpi_table_madt *madt = NULL; - acpi_size tbl_size; phys_cpuid_t rv; - acpi_get_table_with_size(ACPI_SIG_MADT, 0, - (struct acpi_table_header **)&madt, - &tbl_size); + acpi_get_table(ACPI_SIG_MADT, 0, + (struct acpi_table_header **)&madt); if (!madt) return PHYS_CPUID_INVALID; rv = map_madt_entry(madt, 1, acpi_id, true); - early_acpi_os_unmap_memory(madt, tbl_size); + acpi_put_table((struct acpi_table_header *)madt); return rv; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 93b00cf4eb39..45dec874ea55 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1120,9 +1120,6 @@ acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context, ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found generic backlight " "support\n")); *cap |= ACPI_VIDEO_BACKLIGHT; - if (!acpi_has_method(handle, "_BQC")) - printk(KERN_WARNING FW_BUG PREFIX "No _BQC method, " - "cannot determine initial brightness\n"); /* We have backlight support, no need to scan further */ return AE_CTRL_TERMINATE; } diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index e8d7bc7d4da8..b8019c4c1d38 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -33,7 +33,6 @@ int __init parse_spcr(bool earlycon) { static char opts[64]; struct acpi_table_spcr *table; - acpi_size table_size; acpi_status status; char *uart; char *iotype; @@ -43,9 +42,8 @@ int __init parse_spcr(bool earlycon) if (acpi_disabled) return -ENODEV; - status = acpi_get_table_with_size(ACPI_SIG_SPCR, 0, - (struct acpi_table_header **)&table, - &table_size); + status = acpi_get_table(ACPI_SIG_SPCR, 0, + (struct acpi_table_header **)&table); if (ACPI_FAILURE(status)) return -ENOENT; @@ -106,6 +104,6 @@ int __init parse_spcr(bool earlycon) err = add_preferred_console(uart, 0, opts + strlen(uart) + 1); done: - early_acpi_os_unmap_memory((void __iomem *)table, table_size); + acpi_put_table((struct acpi_table_header *)table); return err; } diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index cdd56c4657e0..2604189d6cd1 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -333,7 +333,6 @@ acpi_table_parse_entries_array(char *id, unsigned int max_entries) { struct acpi_table_header *table_header = NULL; - acpi_size tbl_size; int count; u32 instance = 0; @@ -346,7 +345,7 @@ acpi_table_parse_entries_array(char *id, if (!strncmp(id, ACPI_SIG_MADT, 4)) instance = acpi_apic_instance; - acpi_get_table_with_size(id, instance, &table_header, &tbl_size); + acpi_get_table(id, instance, &table_header); if (!table_header) { pr_warn("%4.4s not present\n", id); return -ENODEV; @@ -355,7 +354,7 @@ acpi_table_parse_entries_array(char *id, count = acpi_parse_entries_array(id, table_size, table_header, proc, proc_num, max_entries); - early_acpi_os_unmap_memory((char *)table_header, tbl_size); + acpi_put_table(table_header); return count; } @@ -397,7 +396,6 @@ acpi_table_parse_madt(enum acpi_madt_type id, int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler) { struct acpi_table_header *table = NULL; - acpi_size tbl_size; if (acpi_disabled) return -ENODEV; @@ -406,13 +404,13 @@ int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler) return -EINVAL; if (strncmp(id, ACPI_SIG_MADT, 4) == 0) - acpi_get_table_with_size(id, acpi_apic_instance, &table, &tbl_size); + acpi_get_table(id, acpi_apic_instance, &table); else - acpi_get_table_with_size(id, 0, &table, &tbl_size); + acpi_get_table(id, 0, &table); if (table) { handler(table); - early_acpi_os_unmap_memory(table, tbl_size); + acpi_put_table(table); return 0; } else return -ENODEV; @@ -426,16 +424,15 @@ int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler) static void __init check_multiple_madt(void) { struct acpi_table_header *table = NULL; - acpi_size tbl_size; - acpi_get_table_with_size(ACPI_SIG_MADT, 2, &table, &tbl_size); + acpi_get_table(ACPI_SIG_MADT, 2, &table); if (table) { pr_warn("BIOS bug: multiple APIC/MADT found, using %d\n", acpi_apic_instance); pr_warn("If \"acpi_apic_instance=%d\" works better, " "notify [email protected]\n", acpi_apic_instance ? 0 : 2); - early_acpi_os_unmap_memory(table, tbl_size); + acpi_put_table(table); } else acpi_apic_instance = 0; diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index 1e3903d0d994..eb3af2739537 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -363,6 +363,7 @@ static ssize_t file_name##_show(struct device *dev, \ return sprintf(buf, "%u\n", this_leaf->object); \ } +show_one(id, id); show_one(level, level); show_one(coherency_line_size, coherency_line_size); show_one(number_of_sets, number_of_sets); @@ -444,6 +445,7 @@ static ssize_t write_policy_show(struct device *dev, return n; } +static DEVICE_ATTR_RO(id); static DEVICE_ATTR_RO(level); static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(coherency_line_size); @@ -457,6 +459,7 @@ static DEVICE_ATTR_RO(shared_cpu_list); static DEVICE_ATTR_RO(physical_line_partition); static struct attribute *cache_default_attrs[] = { + &dev_attr_id.attr, &dev_attr_type.attr, &dev_attr_level.attr, &dev_attr_shared_cpu_map.attr, @@ -480,6 +483,8 @@ cache_default_attrs_is_visible(struct kobject *kobj, const struct cpumask *mask = &this_leaf->shared_cpu_map; umode_t mode = attr->mode; + if ((attr == &dev_attr_id.attr) && (this_leaf->attributes & CACHE_ID)) + return mode; if ((attr == &dev_attr_type.attr) && this_leaf->type) return mode; if ((attr == &dev_attr_level.attr) && this_leaf->level) diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 3a98702b7445..3a2ca0f79daf 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -930,7 +930,7 @@ static void __init acpi_cpufreq_boost_init(void) static void acpi_cpufreq_boost_exit(void) { - if (acpi_cpufreq_online >= 0) + if (acpi_cpufreq_online > 0) cpuhp_remove_state_nocalls(acpi_cpufreq_online); } diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c index 176e84cc3991..0cb9040eca49 100644 --- a/drivers/cpufreq/s3c64xx-cpufreq.c +++ b/drivers/cpufreq/s3c64xx-cpufreq.c @@ -107,7 +107,7 @@ static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy, } #ifdef CONFIG_REGULATOR -static void __init s3c64xx_cpufreq_config_regulator(void) +static void s3c64xx_cpufreq_config_regulator(void) { int count, v, i, found; struct cpufreq_frequency_table *freq; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 4f973a9c7b87..8ec1967a850b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -305,8 +305,9 @@ static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev) GOP_VBIOS_CONTENT *vbios; VFCT_IMAGE_HEADER *vhdr; - if (!ACPI_SUCCESS(acpi_get_table_with_size("VFCT", 1, &hdr, &tbl_size))) + if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr))) return false; + tbl_size = hdr->length; if (tbl_size < sizeof(UEFI_ACPI_VFCT)) { DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n"); goto out_unmap; diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 21b6732425c5..c829cfb02fc4 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -603,8 +603,9 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) GOP_VBIOS_CONTENT *vbios; VFCT_IMAGE_HEADER *vhdr; - if (!ACPI_SUCCESS(acpi_get_table_with_size("VFCT", 1, &hdr, &tbl_size))) + if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr))) return false; + tbl_size = hdr->length; if (tbl_size < sizeof(UEFI_ACPI_VFCT)) { DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n"); goto out_unmap; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 971154cbbb03..6799cf9713f7 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -2209,14 +2209,13 @@ static void __init free_dma_resources(void) static int __init early_amd_iommu_init(void) { struct acpi_table_header *ivrs_base; - acpi_size ivrs_size; acpi_status status; int i, remap_cache_sz, ret = 0; if (!amd_iommu_detected) return -ENODEV; - status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + status = acpi_get_table("IVRS", 0, &ivrs_base); if (status == AE_NOT_FOUND) return -ENODEV; else if (ACPI_FAILURE(status)) { @@ -2338,7 +2337,7 @@ static int __init early_amd_iommu_init(void) out: /* Don't leak any ACPI memory */ - early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + acpi_put_table(ivrs_base); ivrs_base = NULL; return ret; @@ -2362,10 +2361,9 @@ out: static bool detect_ivrs(void) { struct acpi_table_header *ivrs_base; - acpi_size ivrs_size; acpi_status status; - status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + status = acpi_get_table("IVRS", 0, &ivrs_base); if (status == AE_NOT_FOUND) return false; else if (ACPI_FAILURE(status)) { @@ -2374,7 +2372,7 @@ static bool detect_ivrs(void) return false; } - early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + acpi_put_table(ivrs_base); /* Make sure ACS will be enabled during PCI probe */ pci_request_acs(); diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 8c53748a769d..a88576d50740 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -68,7 +68,6 @@ DECLARE_RWSEM(dmar_global_lock); LIST_HEAD(dmar_drhd_units); struct acpi_table_header * __initdata dmar_tbl; -static acpi_size dmar_tbl_size; static int dmar_dev_scope_status = 1; static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)]; @@ -543,9 +542,7 @@ static int __init dmar_table_detect(void) acpi_status status = AE_OK; /* if we could find DMAR table, then there are DMAR devices */ - status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0, - (struct acpi_table_header **)&dmar_tbl, - &dmar_tbl_size); + status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl); if (ACPI_SUCCESS(status) && !dmar_tbl) { pr_warn("Unable to map DMAR\n"); @@ -906,7 +903,7 @@ int __init detect_intel_iommu(void) x86_init.iommu.iommu_init = intel_iommu_init; #endif - early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size); + acpi_put_table(dmar_tbl); dmar_tbl = NULL; up_write(&dmar_global_lock); diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 1f32688c312d..dd9ecd354a3e 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -447,7 +447,6 @@ static int pcc_parse_subspace_irq(int id, */ static int __init acpi_pcc_probe(void) { - acpi_size pcct_tbl_header_size; struct acpi_table_header *pcct_tbl; struct acpi_subtable_header *pcct_entry; struct acpi_table_pcct *acpi_pcct_tbl; @@ -456,9 +455,7 @@ static int __init acpi_pcc_probe(void) acpi_status status = AE_OK; /* Search for PCCT */ - status = acpi_get_table_with_size(ACPI_SIG_PCCT, 0, - &pcct_tbl, - &pcct_tbl_header_size); + status = acpi_get_table(ACPI_SIG_PCCT, 0, &pcct_tbl); if (ACPI_FAILURE(status) || !pcct_tbl) { pr_warn("PCCT header not found.\n"); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 6b420a55c745..c3ea03c9a1a8 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -425,7 +425,7 @@ struct cache { * until a gc finishes - otherwise we could pointlessly burn a ton of * cpu */ - unsigned invalidate_needs_gc:1; + unsigned invalidate_needs_gc; bool discard; /* Get rid of? */ @@ -593,8 +593,8 @@ struct cache_set { /* Counts how many sectors bio_insert has added to the cache */ atomic_t sectors_to_gc; + wait_queue_head_t gc_wait; - wait_queue_head_t moving_gc_wait; struct keybuf moving_gc_keys; /* Number of moving GC bios in flight */ struct semaphore moving_in_flight; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 6fdd8e252760..a43eedd5804d 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1757,32 +1757,34 @@ static void bch_btree_gc(struct cache_set *c) bch_moving_gc(c); } -static int bch_gc_thread(void *arg) +static bool gc_should_run(struct cache_set *c) { - struct cache_set *c = arg; struct cache *ca; unsigned i; - while (1) { -again: - bch_btree_gc(c); + for_each_cache(ca, c, i) + if (ca->invalidate_needs_gc) + return true; - set_current_state(TASK_INTERRUPTIBLE); - if (kthread_should_stop()) - break; + if (atomic_read(&c->sectors_to_gc) < 0) + return true; - mutex_lock(&c->bucket_lock); + return false; +} - for_each_cache(ca, c, i) - if (ca->invalidate_needs_gc) { - mutex_unlock(&c->bucket_lock); - set_current_state(TASK_RUNNING); - goto again; - } +static int bch_gc_thread(void *arg) +{ + struct cache_set *c = arg; - mutex_unlock(&c->bucket_lock); + while (1) { + wait_event_interruptible(c->gc_wait, + kthread_should_stop() || gc_should_run(c)); - schedule(); + if (kthread_should_stop()) + break; + + set_gc_sectors(c); + bch_btree_gc(c); } return 0; @@ -1790,11 +1792,10 @@ again: int bch_gc_thread_start(struct cache_set *c) { - c->gc_thread = kthread_create(bch_gc_thread, c, "bcache_gc"); + c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc"); if (IS_ERR(c->gc_thread)) return PTR_ERR(c->gc_thread); - set_task_state(c->gc_thread, TASK_INTERRUPTIBLE); return 0; } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 5c391fa01bed..9b80417cd547 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -260,8 +260,7 @@ void bch_initial_mark_key(struct cache_set *, int, struct bkey *); static inline void wake_up_gc(struct cache_set *c) { - if (c->gc_thread) - wake_up_process(c->gc_thread); + wake_up(&c->gc_wait); } #define MAP_DONE 0 diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index f49c5417527d..76d20875503c 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -196,10 +196,8 @@ static void bch_data_insert_start(struct closure *cl) struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); struct bio *bio = op->bio, *n; - if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) { - set_gc_sectors(op->c); + if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) wake_up_gc(op->c); - } if (op->bypass) return bch_data_invalidate(cl); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 2fb5bfeb43e2..3a19cbc8b230 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -58,6 +58,7 @@ static wait_queue_head_t unregister_wait; struct workqueue_struct *bcache_wq; #define BTREE_MAX_PAGES (256 * 1024 / PAGE_SIZE) +#define BCACHE_MINORS 16 /* partition support */ /* Superblock */ @@ -783,8 +784,10 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, if (minor < 0) return minor; + minor *= BCACHE_MINORS; + if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) || - !(d->disk = alloc_disk(1))) { + !(d->disk = alloc_disk(BCACHE_MINORS))) { ida_simple_remove(&bcache_minor, minor); return -ENOMEM; } @@ -1489,6 +1492,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); init_waitqueue_head(&c->bucket_wait); + init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); spin_lock_init(&c->btree_gc_time.lock); @@ -1548,6 +1552,7 @@ static void run_cache_set(struct cache_set *c) for_each_cache(ca, c, i) c->nbuckets += ca->sb.nbuckets; + set_gc_sectors(c); if (CACHE_SYNC(&c->sb)) { LIST_HEAD(journal); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 543eadd230e5..1076b9d89df3 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -496,8 +496,7 @@ static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq) * Returns enum mmc_blk_status after checking errors. */ static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host, - struct mmc_request *mrq, - struct mmc_async_req *next_req) + struct mmc_request *mrq) { struct mmc_command *cmd; struct mmc_context_info *context_info = &host->context_info; @@ -507,7 +506,7 @@ static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host, wait_event_interruptible(context_info->wait, (context_info->is_done_rcv || context_info->is_new_req)); - context_info->is_waiting_last_req = false; + if (context_info->is_done_rcv) { context_info->is_done_rcv = false; cmd = mrq->cmd; @@ -527,10 +526,9 @@ static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host, __mmc_start_request(host, mrq); continue; /* wait for done/new event again */ } - } else if (context_info->is_new_req) { - if (!next_req) - return MMC_BLK_NEW_REQUEST; } + + return MMC_BLK_NEW_REQUEST; } mmc_retune_release(host); return status; @@ -660,7 +658,7 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host, mmc_pre_req(host, areq->mrq); if (host->areq) { - status = mmc_wait_for_data_req_done(host, host->areq->mrq, areq); + status = mmc_wait_for_data_req_done(host, host->areq->mrq); if (status == MMC_BLK_NEW_REQUEST) { if (ret_stat) *ret_stat = status; diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index deb90c2ff6b4..a614f37faf27 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -223,6 +223,7 @@ static int mmc_decode_scr(struct mmc_card *card) static int mmc_read_ssr(struct mmc_card *card) { unsigned int au, es, et, eo; + u32 *raw_ssr; int i; if (!(card->csd.cmdclass & CCC_APP_SPEC)) { @@ -231,14 +232,21 @@ static int mmc_read_ssr(struct mmc_card *card) return 0; } - if (mmc_app_sd_status(card, card->raw_ssr)) { + raw_ssr = kmalloc(sizeof(card->raw_ssr), GFP_KERNEL); + if (!raw_ssr) + return -ENOMEM; + + if (mmc_app_sd_status(card, raw_ssr)) { pr_warn("%s: problem reading SD Status register\n", mmc_hostname(card->host)); + kfree(raw_ssr); return 0; } for (i = 0; i < 16; i++) - card->raw_ssr[i] = be32_to_cpu(card->raw_ssr[i]); + card->raw_ssr[i] = be32_to_cpu(raw_ssr[i]); + + kfree(raw_ssr); /* * UNSTUFF_BITS only works with four u32s so we have to offset the diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c index 1501cfdac473..4b0ecb981842 100644 --- a/drivers/mmc/host/sdhci-cadence.c +++ b/drivers/mmc/host/sdhci-cadence.c @@ -262,6 +262,7 @@ disable_clk: } static const struct of_device_id sdhci_cdns_match[] = { + { .compatible = "socionext,uniphier-sd4hc" }, { .compatible = "cdns,sd4hc" }, { /* sentinel */ } }; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 111991e5b9a0..23909804ffb8 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1576,6 +1576,9 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) unsigned long flags; u8 ctrl; + if (ios->power_mode == MMC_POWER_UNDEFINED) + return; + spin_lock_irqsave(&host->lock, flags); if (host->flags & SDHCI_DEVICE_DEAD) { @@ -2938,22 +2941,24 @@ int sdhci_runtime_resume_host(struct sdhci_host *host) sdhci_init(host, 0); - /* Force clock and power re-program */ - host->pwr = 0; - host->clock = 0; - mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios); - mmc->ops->set_ios(mmc, &mmc->ios); + if (mmc->ios.power_mode != MMC_POWER_UNDEFINED) { + /* Force clock and power re-program */ + host->pwr = 0; + host->clock = 0; + mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios); + mmc->ops->set_ios(mmc, &mmc->ios); - if ((host_flags & SDHCI_PV_ENABLED) && - !(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN)) { - spin_lock_irqsave(&host->lock, flags); - sdhci_enable_preset_value(host, true); - spin_unlock_irqrestore(&host->lock, flags); - } + if ((host_flags & SDHCI_PV_ENABLED) && + !(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN)) { + spin_lock_irqsave(&host->lock, flags); + sdhci_enable_preset_value(host, true); + spin_unlock_irqrestore(&host->lock, flags); + } - if ((mmc->caps2 & MMC_CAP2_HS400_ES) && - mmc->ops->hs400_enhanced_strobe) - mmc->ops->hs400_enhanced_strobe(mmc, &mmc->ios); + if ((mmc->caps2 & MMC_CAP2_HS400_ES) && + mmc->ops->hs400_enhanced_strobe) + mmc->ops->hs400_enhanced_strobe(mmc, &mmc->ios); + } spin_lock_irqsave(&host->lock, flags); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 151ce59f4ffb..19beeb7b2ac2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1342,7 +1342,7 @@ static ssize_t nvme_cmb_show(struct device *dev, { struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev)); - return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz : x%08x\n", + return scnprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz : x%08x\n", ndev->cmbloc, ndev->cmbsz); } static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL); diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index c9fa3565c671..2583e8b50b21 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -30,6 +30,7 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/string.h> +#include <linux/delay.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h index 98b0ca79a5c5..65c6189885ab 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h @@ -26,6 +26,7 @@ #ifndef __H_IBMVSCSI_TGT #define __H_IBMVSCSI_TGT +#include <linux/interrupt.h> #include "libsrp.h" #define SYS_ID_NAME_LEN 64 diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 19f18485a854..d8efddf6f312 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -9,6 +9,7 @@ #include <linux/delay.h> #include <linux/slab.h> +#include <linux/t10-pi.h> #include <scsi/scsi_tcq.h> #include <scsi/scsi_bsg_fc.h> #include <scsi/scsi_eh.h> diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index d02bf58aea6d..8bcb9b71f764 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -9,6 +9,7 @@ #include <linux/workqueue.h> #include <linux/kthread.h> #include <asm/unaligned.h> +#include <net/tcp.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> #include "cxgbit.h" diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index b7d747e92c7a..da2c73a255de 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -23,7 +23,9 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/idr.h> +#include <linux/delay.h> #include <asm/unaligned.h> +#include <net/ipv6.h> #include <scsi/scsi_proto.h> #include <scsi/iscsi_proto.h> #include <scsi/scsi_tcq.h> diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h index 4cf2c0f2ba2f..e0db2ceb0f87 100644 --- a/drivers/target/iscsi/iscsi_target.h +++ b/drivers/target/iscsi/iscsi_target.h @@ -1,6 +1,18 @@ #ifndef ISCSI_TARGET_H #define ISCSI_TARGET_H +#include <linux/types.h> +#include <linux/spinlock.h> + +struct iscsi_cmd; +struct iscsi_conn; +struct iscsi_np; +struct iscsi_portal_group; +struct iscsi_session; +struct iscsi_tpg_np; +struct kref; +struct sockaddr_storage; + extern struct iscsi_tiqn *iscsit_get_tiqn_for_login(unsigned char *); extern struct iscsi_tiqn *iscsit_get_tiqn(unsigned char *, int); extern void iscsit_put_tiqn_for_login(struct iscsi_tiqn *); diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index e116f0e845c0..903b667f8e01 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -20,8 +20,8 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/err.h> +#include <linux/random.h> #include <linux/scatterlist.h> - #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_nego.h" #include "iscsi_target_auth.h" diff --git a/drivers/target/iscsi/iscsi_target_auth.h b/drivers/target/iscsi/iscsi_target_auth.h index d22f7b96a06c..1b91c13cc965 100644 --- a/drivers/target/iscsi/iscsi_target_auth.h +++ b/drivers/target/iscsi/iscsi_target_auth.h @@ -1,6 +1,8 @@ #ifndef _ISCSI_CHAP_H_ #define _ISCSI_CHAP_H_ +#include <linux/types.h> + #define CHAP_DIGEST_UNKNOWN 0 #define CHAP_DIGEST_MD5 5 #define CHAP_DIGEST_SHA 6 @@ -18,6 +20,9 @@ #define CHAP_STAGE_CLIENT_NRIC 4 #define CHAP_STAGE_SERVER_NR 5 +struct iscsi_node_auth; +struct iscsi_conn; + extern u32 chap_main_loop(struct iscsi_conn *, struct iscsi_node_auth *, char *, char *, int *, int *); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 923c032f0b95..bf40f03755dd 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -21,10 +21,11 @@ #include <linux/ctype.h> #include <linux/export.h> #include <linux/inet.h> +#include <linux/module.h> +#include <net/ipv6.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> #include <target/iscsi/iscsi_transport.h> - #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_parameters.h" #include "iscsi_target_device.h" @@ -100,8 +101,10 @@ static ssize_t lio_target_np_driver_store(struct config_item *item, tpg_np_new = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr, tpg_np, type); - if (IS_ERR(tpg_np_new)) + if (IS_ERR(tpg_np_new)) { + rc = PTR_ERR(tpg_np_new); goto out; + } } else { tpg_np_new = iscsit_tpg_locate_child_np(tpg_np, type); if (tpg_np_new) { diff --git a/drivers/target/iscsi/iscsi_target_datain_values.c b/drivers/target/iscsi/iscsi_target_datain_values.c index 647d4a5dca52..173ddd93c757 100644 --- a/drivers/target/iscsi/iscsi_target_datain_values.c +++ b/drivers/target/iscsi/iscsi_target_datain_values.c @@ -16,8 +16,8 @@ * GNU General Public License for more details. ******************************************************************************/ +#include <linux/slab.h> #include <scsi/iscsi_proto.h> - #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_seq_pdu_list.h" #include "iscsi_target_erl1.h" diff --git a/drivers/target/iscsi/iscsi_target_datain_values.h b/drivers/target/iscsi/iscsi_target_datain_values.h index 646429ac5a02..16edeeeb7777 100644 --- a/drivers/target/iscsi/iscsi_target_datain_values.h +++ b/drivers/target/iscsi/iscsi_target_datain_values.h @@ -1,6 +1,9 @@ #ifndef ISCSI_TARGET_DATAIN_VALUES_H #define ISCSI_TARGET_DATAIN_VALUES_H +struct iscsi_cmd; +struct iscsi_datain; + extern struct iscsi_datain_req *iscsit_allocate_datain_req(void); extern void iscsit_attach_datain_req(struct iscsi_cmd *, struct iscsi_datain_req *); extern void iscsit_free_datain_req(struct iscsi_cmd *, struct iscsi_datain_req *); diff --git a/drivers/target/iscsi/iscsi_target_device.h b/drivers/target/iscsi/iscsi_target_device.h index a0e2df9e8090..06dbff5cd520 100644 --- a/drivers/target/iscsi/iscsi_target_device.h +++ b/drivers/target/iscsi/iscsi_target_device.h @@ -1,6 +1,9 @@ #ifndef ISCSI_TARGET_DEVICE_H #define ISCSI_TARGET_DEVICE_H +struct iscsi_cmd; +struct iscsi_session; + extern void iscsit_determine_maxcmdsn(struct iscsi_session *); extern void iscsit_increment_maxcmdsn(struct iscsi_cmd *, struct iscsi_session *); diff --git a/drivers/target/iscsi/iscsi_target_erl0.h b/drivers/target/iscsi/iscsi_target_erl0.h index a9e2f9497fb2..60e69e2af6ed 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.h +++ b/drivers/target/iscsi/iscsi_target_erl0.h @@ -1,6 +1,12 @@ #ifndef ISCSI_TARGET_ERL0_H #define ISCSI_TARGET_ERL0_H +#include <linux/types.h> + +struct iscsi_cmd; +struct iscsi_conn; +struct iscsi_session; + extern void iscsit_set_dataout_sequence_values(struct iscsi_cmd *); extern int iscsit_check_pre_dataout(struct iscsi_cmd *, unsigned char *); extern int iscsit_check_post_dataout(struct iscsi_cmd *, unsigned char *, u8); diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c index 9214c9dafa2b..fe9b7f1e44ac 100644 --- a/drivers/target/iscsi/iscsi_target_erl1.c +++ b/drivers/target/iscsi/iscsi_target_erl1.c @@ -17,6 +17,7 @@ ******************************************************************************/ #include <linux/list.h> +#include <linux/slab.h> #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/target/iscsi/iscsi_target_erl1.h b/drivers/target/iscsi/iscsi_target_erl1.h index 2a3ebf118a34..54d36bd25bea 100644 --- a/drivers/target/iscsi/iscsi_target_erl1.h +++ b/drivers/target/iscsi/iscsi_target_erl1.h @@ -1,6 +1,16 @@ #ifndef ISCSI_TARGET_ERL1_H #define ISCSI_TARGET_ERL1_H +#include <linux/types.h> +#include <scsi/iscsi_proto.h> /* itt_t */ + +struct iscsi_cmd; +struct iscsi_conn; +struct iscsi_datain_req; +struct iscsi_ooo_cmdsn; +struct iscsi_pdu; +struct iscsi_session; + extern int iscsit_dump_data_payload(struct iscsi_conn *, u32, int); extern int iscsit_create_recovery_datain_values_datasequenceinorder_yes( struct iscsi_cmd *, struct iscsi_datain_req *); diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c index e24f1c7c5862..faf9ae014b30 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.c +++ b/drivers/target/iscsi/iscsi_target_erl2.c @@ -17,6 +17,7 @@ * GNU General Public License for more details. ******************************************************************************/ +#include <linux/slab.h> #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/target/iscsi/iscsi_target_erl2.h b/drivers/target/iscsi/iscsi_target_erl2.h index 63f2501f3fe0..7965f1e86506 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.h +++ b/drivers/target/iscsi/iscsi_target_erl2.h @@ -1,6 +1,13 @@ #ifndef ISCSI_TARGET_ERL2_H #define ISCSI_TARGET_ERL2_H +#include <linux/types.h> + +struct iscsi_cmd; +struct iscsi_conn; +struct iscsi_conn_recovery; +struct iscsi_session; + extern void iscsit_create_conn_recovery_datain_values(struct iscsi_cmd *, __be32); extern void iscsit_create_conn_recovery_dataout_values(struct iscsi_cmd *); extern struct iscsi_conn_recovery *iscsit_get_inactive_connection_recovery_entry( diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 15f79a2ca34a..450f51deb2a2 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -20,6 +20,8 @@ #include <linux/string.h> #include <linux/kthread.h> #include <linux/idr.h> +#include <linux/tcp.h> /* TCP_NODELAY */ +#include <net/ipv6.h> /* ipv6_addr_v4mapped() */ #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index b597aa2c61a1..0e1fd6cedd54 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -1,6 +1,13 @@ #ifndef ISCSI_TARGET_LOGIN_H #define ISCSI_TARGET_LOGIN_H +#include <linux/types.h> + +struct iscsi_conn; +struct iscsi_login; +struct iscsi_np; +struct sockaddr_storage; + extern int iscsi_login_setup_crypto(struct iscsi_conn *); extern int iscsi_check_for_session_reinstatement(struct iscsi_conn *); extern int iscsi_login_post_auth_non_zero_tsih(struct iscsi_conn *, u16, u32); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 89d34bd6d87f..46388c9e08da 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -18,6 +18,8 @@ #include <linux/ctype.h> #include <linux/kthread.h> +#include <linux/slab.h> +#include <net/sock.h> #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> diff --git a/drivers/target/iscsi/iscsi_target_nego.h b/drivers/target/iscsi/iscsi_target_nego.h index f021cbd330e5..53438bfca4c6 100644 --- a/drivers/target/iscsi/iscsi_target_nego.h +++ b/drivers/target/iscsi/iscsi_target_nego.h @@ -4,6 +4,10 @@ #define DECIMAL 0 #define HEX 1 +struct iscsi_conn; +struct iscsi_login; +struct iscsi_np; + extern void convert_null_to_semi(char *, int); extern int extract_param(const char *, const char *, unsigned int, char *, unsigned char *); diff --git a/drivers/target/iscsi/iscsi_target_nodeattrib.h b/drivers/target/iscsi/iscsi_target_nodeattrib.h index 0c69a46a62ec..79cdf06ade48 100644 --- a/drivers/target/iscsi/iscsi_target_nodeattrib.h +++ b/drivers/target/iscsi/iscsi_target_nodeattrib.h @@ -1,6 +1,11 @@ #ifndef ISCSI_TARGET_NODEATTRIB_H #define ISCSI_TARGET_NODEATTRIB_H +#include <linux/types.h> + +struct iscsi_node_acl; +struct iscsi_portal_group; + extern void iscsit_set_default_node_attribues(struct iscsi_node_acl *, struct iscsi_portal_group *); extern int iscsit_na_dataout_timeout(struct iscsi_node_acl *, u32); diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 0efa80bb8962..e65bf78ceef3 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -17,7 +17,7 @@ ******************************************************************************/ #include <linux/slab.h> - +#include <linux/uio.h> /* struct kvec */ #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_util.h" #include "iscsi_target_parameters.h" diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h index a0751e3f0813..9962ccf0ccd7 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.h +++ b/drivers/target/iscsi/iscsi_target_parameters.h @@ -1,6 +1,7 @@ #ifndef ISCSI_PARAMETERS_H #define ISCSI_PARAMETERS_H +#include <linux/types.h> #include <scsi/iscsi_proto.h> struct iscsi_extra_response { @@ -23,6 +24,11 @@ struct iscsi_param { struct list_head p_list; } ____cacheline_aligned; +struct iscsi_conn; +struct iscsi_conn_ops; +struct iscsi_param_list; +struct iscsi_sess_ops; + extern int iscsi_login_rx_data(struct iscsi_conn *, char *, int); extern int iscsi_login_tx_data(struct iscsi_conn *, char *, char *, int); extern void iscsi_dump_conn_ops(struct iscsi_conn_ops *); diff --git a/drivers/target/iscsi/iscsi_target_seq_pdu_list.h b/drivers/target/iscsi/iscsi_target_seq_pdu_list.h index d5b153751a8d..be1234362271 100644 --- a/drivers/target/iscsi/iscsi_target_seq_pdu_list.h +++ b/drivers/target/iscsi/iscsi_target_seq_pdu_list.h @@ -1,6 +1,9 @@ #ifndef ISCSI_SEQ_AND_PDU_LIST_H #define ISCSI_SEQ_AND_PDU_LIST_H +#include <linux/types.h> +#include <linux/cache.h> + /* struct iscsi_pdu->status */ #define DATAOUT_PDU_SENT 1 @@ -78,6 +81,8 @@ struct iscsi_seq { u32 xfer_len; } ____cacheline_aligned; +struct iscsi_cmd; + extern int iscsit_build_pdu_and_seq_lists(struct iscsi_cmd *, u32); extern struct iscsi_pdu *iscsit_get_pdu_holder(struct iscsi_cmd *, u32, u32); extern struct iscsi_pdu *iscsit_get_pdu_holder_for_seq(struct iscsi_cmd *, struct iscsi_seq *); diff --git a/drivers/target/iscsi/iscsi_target_tmr.h b/drivers/target/iscsi/iscsi_target_tmr.h index 142e992cb097..64cc5c07e47c 100644 --- a/drivers/target/iscsi/iscsi_target_tmr.h +++ b/drivers/target/iscsi/iscsi_target_tmr.h @@ -1,6 +1,12 @@ #ifndef ISCSI_TARGET_TMR_H #define ISCSI_TARGET_TMR_H +#include <linux/types.h> + +struct iscsi_cmd; +struct iscsi_conn; +struct iscsi_tmr_req; + extern u8 iscsit_tmr_abort_task(struct iscsi_cmd *, unsigned char *); extern int iscsit_tmr_task_warm_reset(struct iscsi_conn *, struct iscsi_tmr_req *, unsigned char *); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 0814e5894a96..2e7e08dbda48 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -16,9 +16,9 @@ * GNU General Public License for more details. ******************************************************************************/ +#include <linux/slab.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> - #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_erl0.h" #include "iscsi_target_login.h" @@ -260,7 +260,6 @@ err_out: iscsi_release_param_list(tpg->param_list); tpg->param_list = NULL; } - kfree(tpg); return -ENOMEM; } diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index 2da211920c18..ceba29851167 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -1,6 +1,15 @@ #ifndef ISCSI_TARGET_TPG_H #define ISCSI_TARGET_TPG_H +#include <linux/types.h> + +struct iscsi_np; +struct iscsi_session; +struct iscsi_tiqn; +struct iscsi_tpg_np; +struct se_node_acl; +struct sockaddr_storage; + extern struct iscsi_portal_group *iscsit_alloc_portal_group(struct iscsi_tiqn *, u16); extern int iscsit_load_discovery_tpg(void); extern void iscsit_release_discovery_tpg(void); diff --git a/drivers/target/iscsi/iscsi_target_transport.c b/drivers/target/iscsi/iscsi_target_transport.c index 08217d62fb0d..c4eb141c6435 100644 --- a/drivers/target/iscsi/iscsi_target_transport.c +++ b/drivers/target/iscsi/iscsi_target_transport.c @@ -1,5 +1,6 @@ #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/module.h> #include <target/iscsi/iscsi_transport.h> static LIST_HEAD(g_transport_list); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 1f38177207e0..b5a1b4ccba12 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -18,6 +18,7 @@ #include <linux/list.h> #include <linux/percpu_ida.h> +#include <net/ipv6.h> /* ipv6_addr_equal() */ #include <scsi/scsi_tcq.h> #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 995f1cb29d0e..8ff08856516a 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -1,8 +1,16 @@ #ifndef ISCSI_TARGET_UTIL_H #define ISCSI_TARGET_UTIL_H +#include <linux/types.h> +#include <scsi/iscsi_proto.h> /* itt_t */ + #define MARKER_SIZE 8 +struct iscsi_cmd; +struct iscsi_conn; +struct iscsi_conn_recovery; +struct iscsi_session; + extern int iscsit_add_r2t_to_list(struct iscsi_cmd *, u32, u32, int, u32); extern struct iscsi_r2t *iscsit_get_r2t_for_eos(struct iscsi_cmd *, u32, u32); extern struct iscsi_r2t *iscsit_get_r2t_from_list(struct iscsi_cmd *); diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h index 4346462094a1..a8a230b4e6b5 100644 --- a/drivers/target/loopback/tcm_loop.h +++ b/drivers/target/loopback/tcm_loop.h @@ -1,3 +1,7 @@ +#include <linux/types.h> +#include <linux/device.h> +#include <target/target_core_base.h> /* struct se_cmd */ + #define TCM_LOOP_VERSION "v2.1-rc2" #define TL_WWN_ADDR_LEN 256 #define TL_TPGS_PER_HBA 32 diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 58bb6ed18185..e5c3e5f827d0 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -28,6 +28,7 @@ #include <linux/string.h> #include <linux/configfs.h> #include <linux/ctype.h> +#include <linux/delay.h> #include <linux/firewire.h> #include <linux/firewire-constants.h> #include <scsi/scsi_proto.h> @@ -928,7 +929,7 @@ static struct sbp_target_request *sbp_mgt_get_req(struct sbp_session *sess, struct sbp_target_request *req; int tag; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC); + tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); if (tag < 0) return ERR_PTR(-ENOMEM); diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index 4c82bbe19003..f5e330099bfc 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -26,8 +26,11 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/configfs.h> +#include <linux/delay.h> #include <linux/export.h> +#include <linux/fcntl.h> #include <linux/file.h> +#include <linux/fs.h> #include <scsi/scsi_proto.h> #include <asm/unaligned.h> diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h index 9b250f9b33bf..c69c11baf07f 100644 --- a/drivers/target/target_core_alua.h +++ b/drivers/target/target_core_alua.h @@ -1,6 +1,8 @@ #ifndef TARGET_CORE_ALUA_H #define TARGET_CORE_ALUA_H +#include <target/target_core_base.h> + /* * INQUIRY response data, TPGS Field * diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index a35a347ec357..54b36c9835be 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -144,12 +144,12 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item, return -EINVAL; } if (!S_ISDIR(file_inode(fp)->i_mode)) { - filp_close(fp, 0); + filp_close(fp, NULL); mutex_unlock(&g_tf_lock); pr_err("db_root: not a directory: %s\n", db_root_stage); return -EINVAL; } - filp_close(fp, 0); + filp_close(fp, NULL); strncpy(db_root, db_root_stage, read_bytes); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 6b423485c5d6..1ebd13ef7bd3 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -33,6 +33,7 @@ #include <linux/kthread.h> #include <linux/in.h> #include <linux/export.h> +#include <linux/t10-pi.h> #include <asm/unaligned.h> #include <net/sock.h> #include <net/tcp.h> diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index d545993df18b..87aa376a1a1a 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/falloc.h> +#include <linux/uio.h> #include <scsi/scsi_proto.h> #include <asm/unaligned.h> diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h index 068966fce308..526595a072de 100644 --- a/drivers/target/target_core_file.h +++ b/drivers/target/target_core_file.h @@ -1,6 +1,8 @@ #ifndef TARGET_CORE_FILE_H #define TARGET_CORE_FILE_H +#include <target/target_core_base.h> + #define FD_VERSION "4.0" #define FD_MAX_DEV_NAME 256 diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h index 01c2afd81500..718d3fcd3e7c 100644 --- a/drivers/target/target_core_iblock.h +++ b/drivers/target/target_core_iblock.h @@ -1,6 +1,9 @@ #ifndef TARGET_CORE_IBLOCK_H #define TARGET_CORE_IBLOCK_H +#include <linux/atomic.h> +#include <target/target_core_base.h> + #define IBLOCK_VERSION "4.0" #define IBLOCK_MAX_CDBS 16 diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index e2c970a9d61c..9ab7090f7c83 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -1,6 +1,11 @@ #ifndef TARGET_CORE_INTERNAL_H #define TARGET_CORE_INTERNAL_H +#include <linux/configfs.h> +#include <linux/list.h> +#include <linux/types.h> +#include <target/target_core_base.h> + #define TARGET_CORE_NAME_MAX_LEN 64 #define TARGET_FABRIC_NAME_SIZE 32 diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 47463c99c318..d761025144f9 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -29,6 +29,8 @@ #include <linux/list.h> #include <linux/vmalloc.h> #include <linux/file.h> +#include <linux/fcntl.h> +#include <linux/fs.h> #include <scsi/scsi_proto.h> #include <asm/unaligned.h> @@ -253,8 +255,7 @@ target_scsi2_reservation_reserve(struct se_cmd *cmd) if ((cmd->t_task_cdb[1] & 0x01) && (cmd->t_task_cdb[1] & 0x02)) { - pr_err("LongIO and Obselete Bits set, returning" - " ILLEGAL_REQUEST\n"); + pr_err("LongIO and Obsolete Bits set, returning ILLEGAL_REQUEST\n"); return TCM_UNSUPPORTED_SCSI_OPCODE; } /* diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h index e3d26e9126a0..847bd470339c 100644 --- a/drivers/target/target_core_pr.h +++ b/drivers/target/target_core_pr.h @@ -1,5 +1,9 @@ #ifndef TARGET_CORE_PR_H #define TARGET_CORE_PR_H + +#include <linux/types.h> +#include <target/target_core_base.h> + /* * PERSISTENT_RESERVE_OUT service action codes * diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h index 6d2007e35df6..8a02fa47c7e8 100644 --- a/drivers/target/target_core_pscsi.h +++ b/drivers/target/target_core_pscsi.h @@ -15,11 +15,12 @@ #define PS_TIMEOUT_DISK (15*HZ) #define PS_TIMEOUT_OTHER (500*HZ) -#include <linux/device.h> -#include <linux/kref.h> -#include <linux/kobject.h> +#include <linux/cache.h> /* ___cacheline_aligned */ +#include <target/target_core_base.h> /* struct se_device */ +struct block_device; struct scsi_device; +struct Scsi_Host; struct pscsi_plugin_task { unsigned char pscsi_sense[TRANSPORT_SENSE_BUFFER]; diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 24b36fd785f1..ddc216c9f1f6 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -26,7 +26,9 @@ #include <linux/string.h> #include <linux/parser.h> +#include <linux/highmem.h> #include <linux/timer.h> +#include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <scsi/scsi_proto.h> diff --git a/drivers/target/target_core_rd.h b/drivers/target/target_core_rd.h index cc46a6a89b38..91fc1a34791d 100644 --- a/drivers/target/target_core_rd.h +++ b/drivers/target/target_core_rd.h @@ -1,6 +1,10 @@ #ifndef TARGET_CORE_RD_H #define TARGET_CORE_RD_H +#include <linux/module.h> +#include <linux/types.h> +#include <target/target_core_base.h> + #define RD_HBA_VERSION "v4.0" #define RD_MCP_VERSION "4.0" diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 04f616b3ba0a..4879e70e2eef 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -24,6 +24,7 @@ #include <linux/module.h> #include <linux/ratelimit.h> #include <linux/crc-t10dif.h> +#include <linux/t10-pi.h> #include <asm/unaligned.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_tcq.h> diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h index bd6e78ba153d..97402856a8f0 100644 --- a/drivers/target/target_core_ua.h +++ b/drivers/target/target_core_ua.h @@ -1,6 +1,8 @@ #ifndef TARGET_CORE_UA_H #define TARGET_CORE_UA_H +#include <target/target_core_base.h> + /* * From spc4r17, Table D.1: ASC and ASCQ Assignement */ diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 2b3c8564ace8..8041710b6972 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -27,6 +27,7 @@ #include <linux/uio_driver.h> #include <linux/stringify.h> #include <linux/bitops.h> +#include <linux/highmem.h> #include <net/genetlink.h> #include <scsi/scsi_common.h> #include <scsi/scsi_proto.h> @@ -537,7 +538,7 @@ tcmu_queue_cmd(struct se_cmd *se_cmd) struct se_device *se_dev = se_cmd->se_dev; struct tcmu_dev *udev = TCMU_DEV(se_dev); struct tcmu_cmd *tcmu_cmd; - int ret; + sense_reason_t ret; tcmu_cmd = tcmu_alloc_cmd(se_cmd); if (!tcmu_cmd) @@ -685,8 +686,6 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data) target_complete_cmd(cmd->se_cmd, SAM_STAT_CHECK_CONDITION); cmd->se_cmd = NULL; - kmem_cache_free(tcmu_cmd_cache, cmd); - return 0; } diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 094a1440eacb..37d5caebffa6 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -25,6 +25,7 @@ #include <linux/spinlock.h> #include <linux/list.h> #include <linux/configfs.h> +#include <linux/ratelimit.h> #include <scsi/scsi_proto.h> #include <asm/unaligned.h> diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h index 700a981c7b41..4d3d4dd060f2 100644 --- a/drivers/target/target_core_xcopy.h +++ b/drivers/target/target_core_xcopy.h @@ -1,3 +1,5 @@ +#include <target/target_core_base.h> + #define XCOPY_TARGET_DESC_LEN 32 #define XCOPY_SEGMENT_DESC_LEN 28 #define XCOPY_NAA_IEEE_REGEX_LEN 16 diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h index e28209b99b59..11d27b93b413 100644 --- a/drivers/target/tcm_fc/tcm_fc.h +++ b/drivers/target/tcm_fc/tcm_fc.h @@ -17,6 +17,9 @@ #ifndef __TCM_FC_H__ #define __TCM_FC_H__ +#include <linux/types.h> +#include <target/target_core_base.h> + #define FT_VERSION "0.4" #define FT_NAMELEN 32 /* length of ASCII WWPNs including pad */ diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 197f73386fac..d2351139342f 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1073,7 +1073,7 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu, struct usbg_cmd *cmd; int tag; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC); + tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); if (tag < 0) return ERR_PTR(-ENOMEM); diff --git a/fs/block_dev.c b/fs/block_dev.c index 7c4507224ed6..206a92aab52e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -328,6 +328,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct file *file = iocb->ki_filp; struct inode *inode = bdev_file_inode(file); struct block_device *bdev = I_BDEV(inode); + struct blk_plug plug; struct blkdev_dio *dio; struct bio *bio; bool is_read = (iov_iter_rw(iter) == READ); @@ -353,6 +354,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) dio->multi_bio = false; dio->should_dirty = is_read && (iter->type == ITER_IOVEC); + blk_start_plug(&plug); for (;;) { bio->bi_bdev = bdev; bio->bi_iter.bi_sector = pos >> 9; @@ -394,6 +396,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) submit_bio(bio); bio = bio_alloc(GFP_KERNEL, nr_pages); } + blk_finish_plug(&plug); if (!dio->is_sync) return -EIOCBQUEUED; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index cb22a9f9ae7e..fad81041f5ab 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1273,8 +1273,8 @@ out_error: */ static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags) { - int error; struct inode *inode = d_inode(dentry); + int error = 0; /* * I believe we can only get a negative dentry here in the case of a @@ -1293,7 +1293,8 @@ static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags) return 0; } - error = nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (nfs_mapping_need_revalidate_inode(inode)) + error = __nfs_revalidate_inode(NFS_SERVER(inode), inode); dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n", __func__, inode->i_ino, error ? "invalid" : "valid"); return !error; @@ -2285,8 +2286,7 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str if (cache == NULL) goto out; /* Found an entry, is our attribute cache valid? */ - if (!nfs_attribute_cache_expired(inode) && - !(nfsi->cache_validity & NFS_INO_INVALID_ATTR)) + if (!nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) break; err = -ECHILD; if (!may_block) @@ -2334,12 +2334,12 @@ static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred, cache = NULL; if (cache == NULL) goto out; - err = nfs_revalidate_inode_rcu(NFS_SERVER(inode), inode); - if (err) + if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; res->jiffies = cache->jiffies; res->cred = cache->cred; res->mask = cache->mask; + err = 0; out: rcu_read_unlock(); return err; @@ -2491,12 +2491,13 @@ EXPORT_SYMBOL_GPL(nfs_may_open); static int nfs_execute_ok(struct inode *inode, int mask) { struct nfs_server *server = NFS_SERVER(inode); - int ret; + int ret = 0; - if (mask & MAY_NOT_BLOCK) - ret = nfs_revalidate_inode_rcu(server, inode); - else - ret = nfs_revalidate_inode(server, inode); + if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) { + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + ret = __nfs_revalidate_inode(server, inode); + } if (ret == 0 && !execute_ok(inode)) ret = -EACCES; return ret; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 55208b9b3c11..157cb43ce9db 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -101,21 +101,11 @@ EXPORT_SYMBOL_GPL(nfs_file_release); static int nfs_revalidate_file_size(struct inode *inode, struct file *filp) { struct nfs_server *server = NFS_SERVER(inode); - struct nfs_inode *nfsi = NFS_I(inode); - const unsigned long force_reval = NFS_INO_REVAL_PAGECACHE|NFS_INO_REVAL_FORCED; - unsigned long cache_validity = nfsi->cache_validity; - - if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) && - (cache_validity & force_reval) != force_reval) - goto out_noreval; if (filp->f_flags & O_DIRECT) goto force_reval; - if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) - goto force_reval; - if (nfs_attribute_timeout(inode)) + if (nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE)) goto force_reval; -out_noreval: return 0; force_reval: return __nfs_revalidate_inode(server, inode); diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index a5589b791439..f956ca20a8a3 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -282,7 +282,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) s->nfs_client->cl_minorversion); out_test_devid: - if (filelayout_test_devid_unavailable(devid)) + if (ret->ds_clp == NULL || + filelayout_test_devid_unavailable(devid)) ret = NULL; out: return ret; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 9e111d07f667..45962fe5098c 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1126,7 +1126,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, case -EPIPE: dprintk("%s DS connection error %d\n", __func__, task->tk_status); - nfs4_mark_deviceid_unavailable(devid); + nfs4_delete_deviceid(devid->ld, devid->nfs_client, + &devid->deviceid); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: @@ -1175,7 +1176,8 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task, default: dprintk("%s DS connection error %d\n", __func__, task->tk_status); - nfs4_mark_deviceid_unavailable(devid); + nfs4_delete_deviceid(devid->ld, devid->nfs_client, + &devid->deviceid); } /* FIXME: Need to prevent infinite looping here. */ return -NFS4ERR_RESET_TO_PNFS; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 3cc39d1c1206..e5a6f248697b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -177,7 +177,7 @@ out_err: static void ff_layout_mark_devid_invalid(struct pnfs_layout_segment *lseg, struct nfs4_deviceid_node *devid) { - nfs4_mark_deviceid_unavailable(devid); + nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid); if (!ff_layout_has_available_ds(lseg)) pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, lseg); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 5864146e05e6..011e4f8c1e01 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -160,6 +160,43 @@ int nfs_sync_mapping(struct address_space *mapping) return ret; } +static int nfs_attribute_timeout(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); +} + +static bool nfs_check_cache_invalid_delegated(struct inode *inode, unsigned long flags) +{ + unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); + + /* Special case for the pagecache or access cache */ + if (flags == NFS_INO_REVAL_PAGECACHE && + !(cache_validity & NFS_INO_REVAL_FORCED)) + return false; + return (cache_validity & flags) != 0; +} + +static bool nfs_check_cache_invalid_not_delegated(struct inode *inode, unsigned long flags) +{ + unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); + + if ((cache_validity & flags) != 0) + return true; + if (nfs_attribute_timeout(inode)) + return true; + return false; +} + +bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) +{ + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) + return nfs_check_cache_invalid_delegated(inode, flags); + + return nfs_check_cache_invalid_not_delegated(inode, flags); +} + static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); @@ -795,6 +832,8 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) if (!is_sync) return; inode = d_inode(ctx->dentry); + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) + return; nfsi = NFS_I(inode); if (inode->i_mapping->nrpages == 0) return; @@ -1044,13 +1083,6 @@ out: return status; } -int nfs_attribute_timeout(struct inode *inode) -{ - struct nfs_inode *nfsi = NFS_I(inode); - - return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); -} - int nfs_attribute_cache_expired(struct inode *inode) { if (nfs_have_delegated_attributes(inode)) @@ -1073,15 +1105,6 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) } EXPORT_SYMBOL_GPL(nfs_revalidate_inode); -int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode) -{ - if (!(NFS_I(inode)->cache_validity & - (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) - && !nfs_attribute_cache_expired(inode)) - return NFS_STALE(inode) ? -ESTALE : 0; - return -ECHILD; -} - static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { struct nfs_inode *nfsi = NFS_I(inode); @@ -1114,17 +1137,8 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map bool nfs_mapping_need_revalidate_inode(struct inode *inode) { - unsigned long cache_validity = NFS_I(inode)->cache_validity; - - if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) { - const unsigned long force_reval = - NFS_INO_REVAL_PAGECACHE|NFS_INO_REVAL_FORCED; - return (cache_validity & force_reval) == force_reval; - } - - return (cache_validity & NFS_INO_REVAL_PAGECACHE) - || nfs_attribute_timeout(inode) - || NFS_STALE(inode); + return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) || + NFS_STALE(inode); } int nfs_revalidate_mapping_rcu(struct inode *inode) @@ -1536,13 +1550,6 @@ static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr { unsigned long invalid = NFS_INO_INVALID_ATTR; - /* - * Don't revalidate the pagecache if we hold a delegation, but do - * force an attribute update - */ - if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) - invalid = NFS_INO_INVALID_ATTR|NFS_INO_REVAL_FORCED; - if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 6b79c2ca9b9a..09ca5095c04e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -381,6 +381,7 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); +extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); extern int nfs_wait_atomic_killable(atomic_t *p); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d33242c8d95d..6dcbc5defb7a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1089,8 +1089,15 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) spin_lock(&dir->i_lock); nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; - if (!cinfo->atomic || cinfo->before != dir->i_version) + if (cinfo->atomic && cinfo->before == dir->i_version) { + nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE; + nfsi->attrtimeo_timestamp = jiffies; + } else { nfs_force_lookup_revalidate(dir); + if (cinfo->before != dir->i_version) + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL; + } dir->i_version = cinfo->after; nfsi->attr_gencount = nfs_inc_attr_generation_counter(); nfs_fscache_invalidate(dir); @@ -3115,6 +3122,16 @@ static void nfs4_close_done(struct rpc_task *task, void *data) res_stateid = &calldata->res.stateid; renew_lease(server, calldata->timestamp); break; + case -NFS4ERR_ACCESS: + if (calldata->arg.bitmask != NULL) { + calldata->arg.bitmask = NULL; + calldata->res.fattr = NULL; + task->tk_status = 0; + rpc_restart_call_prepare(task); + goto out_release; + + } + break; case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: @@ -3140,7 +3157,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data) res_stateid, calldata->arg.fmode); out_release: nfs_release_seqid(calldata->arg.seqid); - nfs_refresh_inode(calldata->inode, calldata->res.fattr); + nfs_refresh_inode(calldata->inode, &calldata->fattr); dprintk("%s: done, ret = %d!\n", __func__, task->tk_status); } @@ -3193,9 +3210,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_wait; } - if (calldata->arg.fmode == 0) { + if (calldata->arg.fmode == 0) task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE]; + if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) { /* Close-to-open cache consistency revalidation */ if (!nfs4_have_delegation(inode, FMODE_READ)) calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask; @@ -3207,7 +3225,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) nfs4_map_atomic_open_share(NFS_SERVER(inode), calldata->arg.fmode, 0); - nfs_fattr_init(calldata->res.fattr); + if (calldata->res.fattr == NULL) + calldata->arg.bitmask = NULL; + else if (calldata->arg.bitmask == NULL) + calldata->res.fattr = NULL; calldata->timestamp = jiffies; if (nfs4_setup_sequence(NFS_SERVER(inode), &calldata->arg.seq_args, @@ -3274,6 +3295,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->arg.seqid = alloc_seqid(&state->owner->so_seqid, gfp_mask); if (IS_ERR(calldata->arg.seqid)) goto out_free_calldata; + nfs_fattr_init(&calldata->fattr); calldata->arg.fmode = 0; calldata->lr.arg.ld_private = &calldata->lr.ld_private; calldata->res.fattr = &calldata->fattr; @@ -5673,6 +5695,14 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) case -NFS4ERR_STALE_STATEID: task->tk_status = 0; break; + case -NFS4ERR_ACCESS: + if (data->args.bitmask) { + data->args.bitmask = NULL; + data->res.fattr = NULL; + task->tk_status = 0; + rpc_restart_call_prepare(task); + return; + } default: if (nfs4_async_handle_error(task, data->res.server, NULL, NULL) == -EAGAIN) { @@ -5692,6 +5722,7 @@ static void nfs4_delegreturn_release(void *calldata) if (data->lr.roc) pnfs_roc_release(&data->lr.arg, &data->lr.res, data->res.lr_ret); + nfs_post_op_update_inode_force_wcc(inode, &data->fattr); nfs_iput_and_deactive(inode); } kfree(calldata); @@ -5780,10 +5811,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co if (status != 0) goto out; status = data->rpc_status; - if (status == 0) - nfs_post_op_update_inode_force_wcc(inode, &data->fattr); - else - nfs_refresh_inode(inode, &data->fattr); out: rpc_put_task(task); return status; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 95baf7d340f0..1d152f4470cd 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -494,21 +494,18 @@ nfs4_alloc_state_owner(struct nfs_server *server, } static void -nfs4_drop_state_owner(struct nfs4_state_owner *sp) -{ - struct rb_node *rb_node = &sp->so_server_node; - - if (!RB_EMPTY_NODE(rb_node)) { - struct nfs_server *server = sp->so_server; - struct nfs_client *clp = server->nfs_client; - - spin_lock(&clp->cl_lock); - if (!RB_EMPTY_NODE(rb_node)) { - rb_erase(rb_node, &server->state_owners); - RB_CLEAR_NODE(rb_node); - } - spin_unlock(&clp->cl_lock); - } +nfs4_reset_state_owner(struct nfs4_state_owner *sp) +{ + /* This state_owner is no longer usable, but must + * remain in place so that state recovery can find it + * and the opens associated with it. + * It may also be used for new 'open' request to + * return a delegation to the server. + * So update the 'create_time' so that it looks like + * a new state_owner. This will cause the server to + * request an OPEN_CONFIRM to start a new sequence. + */ + sp->so_seqid.create_time = ktime_get(); } static void nfs4_free_state_owner(struct nfs4_state_owner *sp) @@ -797,21 +794,33 @@ void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode) /* * Search the state->lock_states for an existing lock_owner - * that is compatible with current->files + * that is compatible with either of the given owners. + * If the second is non-zero, then the first refers to a Posix-lock + * owner (current->files) and the second refers to a flock/OFD + * owner (struct file*). In that case, prefer a match for the first + * owner. + * If both sorts of locks are held on the one file we cannot know + * which stateid was intended to be used, so a "correct" choice cannot + * be made. Failing that, a "consistent" choice is preferable. The + * consistent choice we make is to prefer the first owner, that of a + * Posix lock. */ static struct nfs4_lock_state * __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, fl_owner_t fl_owner2) { - struct nfs4_lock_state *pos; + struct nfs4_lock_state *pos, *ret = NULL; list_for_each_entry(pos, &state->lock_states, ls_locks) { - if (pos->ls_owner != fl_owner && - pos->ls_owner != fl_owner2) - continue; - atomic_inc(&pos->ls_count); - return pos; + if (pos->ls_owner == fl_owner) { + ret = pos; + break; + } + if (pos->ls_owner == fl_owner2) + ret = pos; } - return NULL; + if (ret) + atomic_inc(&ret->ls_count); + return ret; } /* @@ -1101,7 +1110,7 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid) sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid); if (status == -NFS4ERR_BAD_SEQID) - nfs4_drop_state_owner(sp); + nfs4_reset_state_owner(sp); if (!nfs4_has_session(sp->so_server->nfs_client)) nfs_increment_seqid(status, seqid); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1af6268a7d8c..e9255cb453e6 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -502,11 +502,13 @@ static int nfs4_stat_to_errno(int); (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ + encode_layoutreturn_maxsz + \ encode_open_downgrade_maxsz) #define NFS4_dec_open_downgrade_sz \ (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ + decode_layoutreturn_maxsz + \ decode_open_downgrade_maxsz) #define NFS4_enc_close_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ @@ -2277,9 +2279,9 @@ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, encode_putfh(xdr, args->fh, &hdr); if (args->lr_args) encode_layoutreturn(xdr, args->lr_args, &hdr); - encode_close(xdr, args, &hdr); if (args->bitmask != NULL) encode_getfattr(xdr, args->bitmask, &hdr); + encode_close(xdr, args, &hdr); encode_nops(&hdr); } @@ -2356,6 +2358,8 @@ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); + if (args->lr_args) + encode_layoutreturn(xdr, args->lr_args, &hdr); encode_open_downgrade(xdr, args, &hdr); encode_nops(&hdr); } @@ -2701,7 +2705,8 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, encode_putfh(xdr, args->fhandle, &hdr); if (args->lr_args) encode_layoutreturn(xdr, args->lr_args, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); + if (args->bitmask) + encode_getfattr(xdr, args->bitmask, &hdr); encode_delegreturn(xdr, args->stateid, &hdr); encode_nops(&hdr); } @@ -6151,6 +6156,12 @@ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, status = decode_putfh(xdr); if (status) goto out; + if (res->lr_res) { + status = decode_layoutreturn(xdr, res->lr_res); + res->lr_ret = status; + if (status) + goto out; + } status = decode_open_downgrade(xdr, res); out: return status; @@ -6484,16 +6495,12 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; } + if (res->fattr != NULL) { + status = decode_getfattr(xdr, res->fattr, res->server); + if (status != 0) + goto out; + } status = decode_close(xdr, res); - if (status != 0) - goto out; - /* - * Note: Server may do delete on close for this file - * in which case the getattr call will fail with - * an ESTALE error. Shouldn't be a problem, - * though, since fattr->valid will remain unset. - */ - decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6966,9 +6973,11 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, if (status) goto out; } - status = decode_getfattr(xdr, res->fattr, res->server); - if (status != 0) - goto out; + if (res->fattr) { + status = decode_getfattr(xdr, res->fattr, res->server); + if (status != 0) + goto out; + } status = decode_delegreturn(xdr); out: return status; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 896df7bdf85f..59554f3adf29 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1251,6 +1251,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; + bool skip_read = false; if (!nfs_have_layout(ino)) return false; @@ -1270,18 +1271,27 @@ retry: } /* no roc if we hold a delegation */ - if (nfs4_check_delegation(ino, FMODE_READ)) - goto out_noroc; + if (nfs4_check_delegation(ino, FMODE_READ)) { + if (nfs4_check_delegation(ino, FMODE_WRITE)) + goto out_noroc; + skip_read = true; + } list_for_each_entry(ctx, &nfsi->open_files, list) { state = ctx->state; + if (state == NULL) + continue; /* Don't return layout if there is open file state */ - if (state != NULL && state->state != 0) + if (state->state & FMODE_WRITE) goto out_noroc; + if (state->state & FMODE_READ) + skip_read = true; } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { + if (skip_read && lseg->pls_range.iomode == IOMODE_READ) + continue; /* If we are sending layoutreturn, invalidate all valid lsegs */ if (!test_and_clear_bit(NFS_LSEG_ROC, &lseg->pls_flags)) continue; diff --git a/fs/splice.c b/fs/splice.c index 8ed7c9d8c0fb..873d83104e79 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1087,7 +1087,13 @@ EXPORT_SYMBOL(do_splice_direct); static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) { - while (pipe->nrbufs == pipe->buffers) { + for (;;) { + if (unlikely(!pipe->readers)) { + send_sig(SIGPIPE, current, 0); + return -EPIPE; + } + if (pipe->nrbufs != pipe->buffers) + return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) @@ -1096,7 +1102,6 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) pipe_wait(pipe); pipe->waiting_writers--; } - return 0; } static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h index d7d0f495a34e..303315b9693f 100644 --- a/include/acpi/acpi_io.h +++ b/include/acpi/acpi_io.h @@ -13,6 +13,8 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, } #endif +extern bool acpi_permanent_mmap; + void __iomem *__ref acpi_os_map_iomem(acpi_physical_address phys, acpi_size size); void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size); diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 5c7356adc10b..f5e10dd8e86b 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -513,10 +513,12 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_get_table(acpi_string signature, u32 instance, struct acpi_table_header **out_table)) +ACPI_EXTERNAL_RETURN_VOID(void acpi_put_table(struct acpi_table_header *table)) + ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_get_table_by_index(u32 table_index, - struct acpi_table_header - **out_table)) + acpi_get_table_by_index(u32 table_index, + struct acpi_table_header + **out_table)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_install_table_handler(acpi_table_handler handler, void *context)) @@ -965,15 +967,6 @@ void acpi_terminate_debugger(void); /* * Divergences */ -ACPI_GLOBAL(u8, acpi_gbl_permanent_mmap); - -ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_get_table_with_size(acpi_string signature, - u32 instance, - struct acpi_table_header - **out_table, - acpi_size *tbl_size)) - ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_get_data_full(acpi_handle object, acpi_object_handler handler, diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index c19700e2a2fe..da5708caf8a1 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -371,6 +371,7 @@ struct acpi_table_desc { union acpi_name_union signature; acpi_owner_id owner_id; u8 flags; + u16 validation_count; }; /* Masks for Flags field above */ diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index a5509d87230a..7dbb1141f546 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -142,7 +142,6 @@ static inline void acpi_os_terminate_command_signals(void) /* * OSL interfaces added by Linux */ -void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size); #endif /* __KERNEL__ */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 286b2a264383..83695641bd5e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -288,7 +288,6 @@ enum blk_queue_state { struct blk_queue_tag { struct request **tag_index; /* map of busy tags */ unsigned long *tag_map; /* bit map of free/busy tags */ - int busy; /* current depth */ int max_depth; /* what we will send to device */ int real_max_depth; /* what the array can hold */ atomic_t refcnt; /* map can be shared */ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index a951fd10aaaa..6a524bf6a06d 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -18,6 +18,7 @@ enum cache_type { /** * struct cacheinfo - represent a cache leaf node + * @id: This cache's id. It is unique among caches with the same (type, level). * @type: type of the cache - data, inst or unified * @level: represents the hierarchy in the multi-level cache * @coherency_line_size: size of each cache line usually representing @@ -44,6 +45,7 @@ enum cache_type { * keeping, the remaining members form the core properties of the cache */ struct cacheinfo { + unsigned int id; enum cache_type type; unsigned int level; unsigned int coherency_line_size; @@ -61,6 +63,7 @@ struct cacheinfo { #define CACHE_WRITE_ALLOCATE BIT(3) #define CACHE_ALLOCATE_POLICY_MASK \ (CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE) +#define CACHE_ID BIT(4) struct device_node *of_node; bool disable_sysfs; diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 9a30b921f740..2319b8c108e8 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -35,14 +35,11 @@ #ifndef _CONFIGFS_H_ #define _CONFIGFS_H_ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/list.h> -#include <linux/kref.h> -#include <linux/mutex.h> -#include <linux/err.h> - -#include <linux/atomic.h> +#include <linux/stat.h> /* S_IRUGO */ +#include <linux/types.h> /* ssize_t */ +#include <linux/list.h> /* struct list_head */ +#include <linux/kref.h> /* struct kref */ +#include <linux/mutex.h> /* struct mutex */ #define CONFIGFS_ITEM_NAME_LEN 20 diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e0341af6950e..76f39754e7b0 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -146,15 +146,6 @@ enum { DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ }; -#define BLK_SCSI_MAX_CMDS (256) -#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) - -struct blk_scsi_cmd_filter { - unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; - unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; - struct kobject kobj; -}; - struct disk_part_tbl { struct rcu_head rcu_head; int len; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index cb631973839a..f1da8c8dd473 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -340,10 +340,8 @@ extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); -extern int nfs_attribute_timeout(struct inode *inode); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); -extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); diff --git a/include/linux/sched.h b/include/linux/sched.h index a440cf178191..4d1905245c7a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1821,6 +1821,9 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock */ struct list_head cg_list; #endif +#ifdef CONFIG_INTEL_RDT_A + int closid; +#endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 4ac24f5a3308..275581d483dd 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -1,12 +1,14 @@ #ifndef ISCSI_TARGET_CORE_H #define ISCSI_TARGET_CORE_H -#include <linux/in.h> -#include <linux/configfs.h> -#include <net/sock.h> -#include <net/tcp.h> -#include <scsi/iscsi_proto.h> -#include <target/target_core_base.h> +#include <linux/dma-direction.h> /* enum dma_data_direction */ +#include <linux/list.h> /* struct list_head */ +#include <linux/socket.h> /* struct sockaddr_storage */ +#include <linux/types.h> /* u8 */ +#include <scsi/iscsi_proto.h> /* itt_t */ +#include <target/target_core_base.h> /* struct se_cmd */ + +struct sock; #define ISCSIT_VERSION "v4.1.0" #define ISCSI_MAX_DATASN_MISSING_COUNT 16 diff --git a/include/target/iscsi/iscsi_target_stat.h b/include/target/iscsi/iscsi_target_stat.h index e615bb485d0b..c27dd471656d 100644 --- a/include/target/iscsi/iscsi_target_stat.h +++ b/include/target/iscsi/iscsi_target_stat.h @@ -1,6 +1,10 @@ #ifndef ISCSI_TARGET_STAT_H #define ISCSI_TARGET_STAT_H +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/socket.h> + /* * For struct iscsi_tiqn->tiqn_wwn default groups */ diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 40ac7cd80150..1277e9ba0318 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -1,6 +1,6 @@ -#include <linux/module.h> -#include <linux/list.h> -#include "iscsi_target_core.h" +#include "iscsi_target_core.h" /* struct iscsi_cmd */ + +struct sockaddr_storage; struct iscsit_transport { #define ISCSIT_TRANSPORT_NAME 16 diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index f6f3bc52c1ac..b54b98dc2d4a 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -1,8 +1,14 @@ #ifndef TARGET_CORE_BACKEND_H #define TARGET_CORE_BACKEND_H +#include <linux/types.h> +#include <target/target_core_base.h> + #define TRANSPORT_FLAG_PASSTHROUGH 1 +struct request_queue; +struct scatterlist; + struct target_backend_ops { char name[16]; char inquiry_prod[16]; diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 00558287936d..29e6858bb164 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -1,14 +1,10 @@ #ifndef TARGET_CORE_BASE_H #define TARGET_CORE_BASE_H -#include <linux/in.h> -#include <linux/configfs.h> -#include <linux/dma-mapping.h> -#include <linux/blkdev.h> -#include <linux/percpu_ida.h> -#include <linux/t10-pi.h> -#include <net/sock.h> -#include <net/tcp.h> +#include <linux/configfs.h> /* struct config_group */ +#include <linux/dma-direction.h> /* enum dma_data_direction */ +#include <linux/percpu_ida.h> /* struct percpu_ida */ +#include <linux/semaphore.h> /* struct semaphore */ #define TARGET_CORE_VERSION "v5.0" diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 5cd6faa6e0d1..358041bad1da 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -1,6 +1,10 @@ #ifndef TARGET_CORE_FABRIC_H #define TARGET_CORE_FABRIC_H +#include <linux/configfs.h> +#include <linux/types.h> +#include <target/target_core_base.h> + struct target_core_fabric_ops { struct module *module; const char *name; diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 9bd559472c92..e230af2e6855 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -57,6 +57,7 @@ #define CGROUP_SUPER_MAGIC 0x27e0eb #define CGROUP2_SUPER_MAGIC 0x63677270 +#define RDTGROUP_SUPER_MAGIC 0x7655821 #define STACK_END_MAGIC 0x57AC6E9D diff --git a/scripts/selinux/genheaders/Makefile b/scripts/selinux/genheaders/Makefile index 1d1ac51359e3..6fc2b8789a0b 100644 --- a/scripts/selinux/genheaders/Makefile +++ b/scripts/selinux/genheaders/Makefile @@ -1,4 +1,6 @@ hostprogs-y := genheaders -HOST_EXTRACFLAGS += -Isecurity/selinux/include +HOST_EXTRACFLAGS += \ + -I$(srctree)/include/uapi -I$(srctree)/include \ + -I$(srctree)/security/selinux/include always := $(hostprogs-y) diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c index 539855ff31f9..f4dd41f900d5 100644 --- a/scripts/selinux/genheaders/genheaders.c +++ b/scripts/selinux/genheaders/genheaders.c @@ -1,3 +1,7 @@ + +/* NOTE: we really do want to use the kernel headers here */ +#define __EXPORTED_HEADERS__ + #include <stdio.h> #include <stdlib.h> #include <unistd.h> diff --git a/scripts/selinux/mdp/Makefile b/scripts/selinux/mdp/Makefile index dba7eff69a00..d6a83cafe59f 100644 --- a/scripts/selinux/mdp/Makefile +++ b/scripts/selinux/mdp/Makefile @@ -1,5 +1,7 @@ hostprogs-y := mdp -HOST_EXTRACFLAGS += -Isecurity/selinux/include +HOST_EXTRACFLAGS += \ + -I$(srctree)/include/uapi -I$(srctree)/include \ + -I$(srctree)/security/selinux/include always := $(hostprogs-y) clean-files := policy.* file_contexts diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c index e10beb11b696..c29fa4a6228d 100644 --- a/scripts/selinux/mdp/mdp.c +++ b/scripts/selinux/mdp/mdp.c @@ -24,6 +24,10 @@ * Authors: Serge E. Hallyn <[email protected]> */ + +/* NOTE: we really do want to use the kernel headers here */ +#define __EXPORTED_HEADERS__ + #include <stdio.h> #include <stdlib.h> #include <unistd.h> diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index e2d4ad3a4b4c..13ae49b0baa0 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -1,3 +1,5 @@ +#include <linux/capability.h> + #define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \ "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append" diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index a2cdf3370afe..15d1d5c63c3c 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -384,9 +384,6 @@ static void snd_complete_urb(struct urb *urb) if (unlikely(atomic_read(&ep->chip->shutdown))) goto exit_clear; - if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags))) - goto exit_clear; - if (usb_pipeout(ep->pipe)) { retire_outbound_urb(ep, ctx); /* can be stopped during retire callback */ @@ -537,11 +534,6 @@ static int wait_clear_urbs(struct snd_usb_endpoint *ep) alive, ep->ep_num); clear_bit(EP_FLAG_STOPPING, &ep->flags); - ep->data_subs = NULL; - ep->sync_slave = NULL; - ep->retire_data_urb = NULL; - ep->prepare_data_urb = NULL; - return 0; } @@ -1028,6 +1020,10 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep) if (--ep->use_count == 0) { deactivate_urbs(ep, false); + ep->data_subs = NULL; + ep->sync_slave = NULL; + ep->retire_data_urb = NULL; + ep->prepare_data_urb = NULL; set_bit(EP_FLAG_STOPPING, &ep->flags); } } |