diff options
51 files changed, 5079 insertions, 1684 deletions
diff --git a/Documentation/ABI/testing/sysfs-driver-altera-cvp b/Documentation/ABI/testing/sysfs-driver-altera-cvp new file mode 100644 index 000000000000..8cde64a71edb --- /dev/null +++ b/Documentation/ABI/testing/sysfs-driver-altera-cvp @@ -0,0 +1,8 @@ +What: /sys/bus/pci/drivers/altera-cvp/chkcfg +Date: May 2017 +Kernel Version: 4.13 +Contact: Anatolij Gustschin <agust@denx.de> +Description: + Contains either 1 or 0 and controls if configuration + error checking in altera-cvp driver is turned on or + off. diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt index 6b71852dadc2..4ec843123cc3 100644 --- a/Documentation/admin-guide/devices.txt +++ b/Documentation/admin-guide/devices.txt @@ -3081,3 +3081,8 @@ 1 = /dev/osd1 Second OSD Device ... 255 = /dev/osd255 256th OSD Device + + 384-511 char RESERVED FOR DYNAMIC ASSIGNMENT + Character devices that request a dynamic allocation of major + number will take numbers starting from 511 and downward, + once the 234-254 range is full. diff --git a/Documentation/devicetree/bindings/fpga/altera-passive-serial.txt b/Documentation/devicetree/bindings/fpga/altera-passive-serial.txt new file mode 100644 index 000000000000..48478bc07e29 --- /dev/null +++ b/Documentation/devicetree/bindings/fpga/altera-passive-serial.txt @@ -0,0 +1,29 @@ +Altera Passive Serial SPI FPGA Manager + +Altera FPGAs support a method of loading the bitstream over what is +referred to as "passive serial". +The passive serial link is not technically SPI, and might require extra +circuits in order to play nicely with other SPI slaves on the same bus. + +See https://www.altera.com/literature/hb/cyc/cyc_c51013.pdf + +Required properties: +- compatible: Must be one of the following: + "altr,fpga-passive-serial", + "altr,fpga-arria10-passive-serial" +- reg: SPI chip select of the FPGA +- nconfig-gpios: config pin (referred to as nCONFIG in the manual) +- nstat-gpios: status pin (referred to as nSTATUS in the manual) + +Optional properties: +- confd-gpios: confd pin (referred to as CONF_DONE in the manual) + +Example: + fpga: fpga@0 { + compatible = "altr,fpga-passive-serial"; + spi-max-frequency = <20000000>; + reg = <0>; + nconfig-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>; + nstat-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>; + confd-gpios = <&gpio4 12 GPIO_ACTIVE_LOW>; + }; diff --git a/Documentation/devicetree/bindings/fpga/xilinx-pr-decoupler.txt b/Documentation/devicetree/bindings/fpga/xilinx-pr-decoupler.txt new file mode 100644 index 000000000000..8dcfba926bc7 --- /dev/null +++ b/Documentation/devicetree/bindings/fpga/xilinx-pr-decoupler.txt @@ -0,0 +1,36 @@ +Xilinx LogiCORE Partial Reconfig Decoupler Softcore + +The Xilinx LogiCORE Partial Reconfig Decoupler manages one or more +decouplers / fpga bridges. +The controller can decouple/disable the bridges which prevents signal +changes from passing through the bridge. The controller can also +couple / enable the bridges which allows traffic to pass through the +bridge normally. + +The Driver supports only MMIO handling. A PR region can have multiple +PR Decouplers which can be handled independently or chained via decouple/ +decouple_status signals. + +Required properties: +- compatible : Should contain "xlnx,pr-decoupler-1.00" followed by + "xlnx,pr-decoupler" +- regs : base address and size for decoupler module +- clocks : input clock to IP +- clock-names : should contain "aclk" + +Optional properties: +- bridge-enable : 0 if driver should disable bridge at startup + 1 if driver should enable bridge at startup + Default is to leave bridge in current state. + +See Documentation/devicetree/bindings/fpga/fpga-region.txt for generic bindings. + +Example: + fpga-bridge@100000450 { + compatible = "xlnx,pr-decoupler-1.00", + "xlnx-pr-decoupler"; + regs = <0x10000045 0x10>; + clocks = <&clkc 15>; + clock-names = "aclk"; + bridge-enable = <0>; + }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index daf465bef758..9deb2d12f0e3 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -175,6 +175,7 @@ kosagi Sutajio Ko-Usagi PTE Ltd. kyo Kyocera Corporation lacie LaCie lantiq Lantiq Semiconductor +lattice Lattice Semiconductor lego LEGO Systems A/S lenovo Lenovo Group Ltd. lg LG Corporation diff --git a/MAINTAINERS b/MAINTAINERS index 1c3feffb1c1c..58c3bb7fc615 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5341,10 +5341,11 @@ K: fmc_d.*register FPGA MANAGER FRAMEWORK M: Alan Tull <atull@kernel.org> -R: Moritz Fischer <moritz.fischer@ettus.com> +R: Moritz Fischer <mdf@kernel.org> L: linux-fpga@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/atull/linux-fpga.git +Q: http://patchwork.kernel.org/project/linux-fpga/list/ F: Documentation/fpga/ F: Documentation/devicetree/bindings/fpga/ F: drivers/fpga/ diff --git a/arch/arm/boot/dts/imx6q-evi.dts b/arch/arm/boot/dts/imx6q-evi.dts index 1f0f950dc11e..e0aea782c666 100644 --- a/arch/arm/boot/dts/imx6q-evi.dts +++ b/arch/arm/boot/dts/imx6q-evi.dts @@ -94,6 +94,15 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ecspi1 &pinctrl_ecspi1cs>; status = "okay"; + + fpga: fpga@0 { + compatible = "altr,fpga-passive-serial"; + spi-max-frequency = <20000000>; + reg = <0>; + pinctrl-0 = <&pinctrl_fpgaspi>; + nconfig-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>; + nstat-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>; + }; }; &ecspi3 { @@ -319,6 +328,13 @@ >; }; + pinctrl_fpgaspi: fpgaspigrp { + fsl,pins = < + MX6QDL_PAD_KEY_ROW1__GPIO4_IO09 0x1b0b0 + MX6QDL_PAD_KEY_ROW2__GPIO4_IO11 0x1b0b0 + >; + }; + pinctrl_gpminand: gpminandgrp { fsl,pins = < MX6QDL_PAD_NANDF_CLE__NAND_CLE 0xb0b1 diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 2b58c8c1eeaa..58b9291b46d8 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -28,6 +28,8 @@ struct ms_hyperv_info { u32 features; u32 misc_features; u32 hints; + u32 max_vp_index; + u32 max_lp_index; }; extern struct ms_hyperv_info ms_hyperv; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 70e717fccdd6..b3bf024fc4e0 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -184,9 +184,15 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("HyperV: features 0x%x, hints 0x%x\n", + pr_info("Hyper-V: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); + ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS); + ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS); + + pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", + ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); + /* * Extract host information. */ @@ -219,7 +225,7 @@ static void __init ms_hyperv_init_platform(void) rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); lapic_timer_frequency = hv_lapic_frequency; - pr_info("HyperV: LAPIC Timer Frequency: %#x\n", + pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n", lapic_timer_frequency); } @@ -253,7 +259,7 @@ static void __init ms_hyperv_init_platform(void) } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { - .name = "Microsoft HyperV", + .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, .init_platform = ms_hyperv_init_platform, }; diff --git a/block/genhd.c b/block/genhd.c index 7f520fa25d16..51c1d407d93c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -242,6 +242,7 @@ EXPORT_SYMBOL_GPL(disk_map_sector_rcu); * Can be deleted altogether. Later. * */ +#define BLKDEV_MAJOR_HASH_SIZE 255 static struct blk_major_name { struct blk_major_name *next; int major; @@ -259,12 +260,11 @@ void blkdev_show(struct seq_file *seqf, off_t offset) { struct blk_major_name *dp; - if (offset < BLKDEV_MAJOR_HASH_SIZE) { - mutex_lock(&block_class_lock); - for (dp = major_names[offset]; dp; dp = dp->next) + mutex_lock(&block_class_lock); + for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) + if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); - mutex_unlock(&block_class_lock); - } + mutex_unlock(&block_class_lock); } #endif /* CONFIG_PROC_FS */ @@ -309,6 +309,14 @@ int register_blkdev(unsigned int major, const char *name) ret = major; } + if (major >= BLKDEV_MAJOR_MAX) { + pr_err("register_blkdev: major requested (%d) is greater than the maximum (%d) for %s\n", + major, BLKDEV_MAJOR_MAX, name); + + ret = -EINVAL; + goto out; + } + p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL); if (p == NULL) { ret = -ENOMEM; diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig index 832e885349b1..4d4cdc1a6e25 100644 --- a/drivers/android/Kconfig +++ b/drivers/android/Kconfig @@ -22,7 +22,7 @@ config ANDROID_BINDER_IPC config ANDROID_BINDER_DEVICES string "Android Binder devices" depends on ANDROID_BINDER_IPC - default "binder,hwbinder" + default "binder,hwbinder,vndbinder" ---help--- Default value for the binder.devices parameter. diff --git a/drivers/android/Makefile b/drivers/android/Makefile index 3b7e4b072c58..4b7c726bb560 100644 --- a/drivers/android/Makefile +++ b/drivers/android/Makefile @@ -1,3 +1,3 @@ ccflags-y += -I$(src) # needed for trace events -obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o +obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o binder_alloc.o diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 831cdd7d197d..947eb7056fa7 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -15,6 +15,40 @@ * */ +/* + * Locking overview + * + * There are 3 main spinlocks which must be acquired in the + * order shown: + * + * 1) proc->outer_lock : protects binder_ref + * binder_proc_lock() and binder_proc_unlock() are + * used to acq/rel. + * 2) node->lock : protects most fields of binder_node. + * binder_node_lock() and binder_node_unlock() are + * used to acq/rel + * 3) proc->inner_lock : protects the thread and node lists + * (proc->threads, proc->nodes) and all todo lists associated + * with the binder_proc (proc->todo, thread->todo, + * proc->delivered_death and node->async_todo), as well as + * thread->transaction_stack + * binder_inner_proc_lock() and binder_inner_proc_unlock() + * are used to acq/rel + * + * Any lock under procA must never be nested under any lock at the same + * level or below on procB. + * + * Functions that require a lock held on entry indicate which lock + * in the suffix of the function name: + * + * foo_olocked() : requires node->outer_lock + * foo_nlocked() : requires node->lock + * foo_ilocked() : requires proc->inner_lock + * foo_oilocked(): requires proc->outer_lock and proc->inner_lock + * foo_nilocked(): requires node->lock and proc->inner_lock + * ... + */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/cacheflush.h> @@ -24,7 +58,6 @@ #include <linux/fs.h> #include <linux/list.h> #include <linux/miscdevice.h> -#include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/nsproxy.h> @@ -35,30 +68,31 @@ #include <linux/sched/mm.h> #include <linux/seq_file.h> #include <linux/uaccess.h> -#include <linux/vmalloc.h> -#include <linux/slab.h> #include <linux/pid_namespace.h> #include <linux/security.h> +#include <linux/spinlock.h> #ifdef CONFIG_ANDROID_BINDER_IPC_32BIT #define BINDER_IPC_32BIT 1 #endif #include <uapi/linux/android/binder.h> +#include "binder_alloc.h" #include "binder_trace.h" -static DEFINE_MUTEX(binder_main_lock); +static HLIST_HEAD(binder_deferred_list); static DEFINE_MUTEX(binder_deferred_lock); -static DEFINE_MUTEX(binder_mmap_lock); static HLIST_HEAD(binder_devices); static HLIST_HEAD(binder_procs); -static HLIST_HEAD(binder_deferred_list); +static DEFINE_MUTEX(binder_procs_lock); + static HLIST_HEAD(binder_dead_nodes); +static DEFINE_SPINLOCK(binder_dead_nodes_lock); static struct dentry *binder_debugfs_dir_entry_root; static struct dentry *binder_debugfs_dir_entry_proc; -static int binder_last_id; +static atomic_t binder_last_id; #define BINDER_DEBUG_ENTRY(name) \ static int binder_##name##_open(struct inode *inode, struct file *file) \ @@ -88,8 +122,6 @@ BINDER_DEBUG_ENTRY(proc); #define FORBIDDEN_MMAP_FLAGS (VM_WRITE) -#define BINDER_SMALL_BUF_SIZE (PAGE_SIZE * 64) - enum { BINDER_DEBUG_USER_ERROR = 1U << 0, BINDER_DEBUG_FAILED_TRANSACTION = 1U << 1, @@ -104,17 +136,13 @@ enum { BINDER_DEBUG_TRANSACTION_COMPLETE = 1U << 10, BINDER_DEBUG_FREE_BUFFER = 1U << 11, BINDER_DEBUG_INTERNAL_REFS = 1U << 12, - BINDER_DEBUG_BUFFER_ALLOC = 1U << 13, - BINDER_DEBUG_PRIORITY_CAP = 1U << 14, - BINDER_DEBUG_BUFFER_ALLOC_ASYNC = 1U << 15, + BINDER_DEBUG_PRIORITY_CAP = 1U << 13, + BINDER_DEBUG_SPINLOCKS = 1U << 14, }; static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR | BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION; module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO); -static bool binder_debug_no_lock; -module_param_named(proc_no_lock, binder_debug_no_lock, bool, S_IWUSR | S_IRUGO); - static char *binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES; module_param_named(devices, binder_devices_param, charp, 0444); @@ -171,26 +199,27 @@ enum binder_stat_types { }; struct binder_stats { - int br[_IOC_NR(BR_FAILED_REPLY) + 1]; - int bc[_IOC_NR(BC_REPLY_SG) + 1]; - int obj_created[BINDER_STAT_COUNT]; - int obj_deleted[BINDER_STAT_COUNT]; + atomic_t br[_IOC_NR(BR_FAILED_REPLY) + 1]; + atomic_t bc[_IOC_NR(BC_REPLY_SG) + 1]; + atomic_t obj_created[BINDER_STAT_COUNT]; + atomic_t obj_deleted[BINDER_STAT_COUNT]; }; static struct binder_stats binder_stats; static inline void binder_stats_deleted(enum binder_stat_types type) { - binder_stats.obj_deleted[type]++; + atomic_inc(&binder_stats.obj_deleted[type]); } static inline void binder_stats_created(enum binder_stat_types type) { - binder_stats.obj_created[type]++; + atomic_inc(&binder_stats.obj_created[type]); } struct binder_transaction_log_entry { int debug_id; + int debug_id_done; int call_type; int from_proc; int from_thread; @@ -200,11 +229,14 @@ struct binder_transaction_log_entry { int to_node; int data_size; int offsets_size; + int return_error_line; + uint32_t return_error; + uint32_t return_error_param; const char *context_name; }; struct binder_transaction_log { - int next; - int full; + atomic_t cur; + bool full; struct binder_transaction_log_entry entry[32]; }; static struct binder_transaction_log binder_transaction_log; @@ -214,19 +246,26 @@ static struct binder_transaction_log_entry *binder_transaction_log_add( struct binder_transaction_log *log) { struct binder_transaction_log_entry *e; + unsigned int cur = atomic_inc_return(&log->cur); - e = &log->entry[log->next]; - memset(e, 0, sizeof(*e)); - log->next++; - if (log->next == ARRAY_SIZE(log->entry)) { - log->next = 0; + if (cur >= ARRAY_SIZE(log->entry)) log->full = 1; - } + e = &log->entry[cur % ARRAY_SIZE(log->entry)]; + WRITE_ONCE(e->debug_id_done, 0); + /* + * write-barrier to synchronize access to e->debug_id_done. + * We make sure the initialized 0 value is seen before + * memset() other fields are zeroed by memset. + */ + smp_wmb(); + memset(e, 0, sizeof(*e)); return e; } struct binder_context { struct binder_node *binder_context_mgr_node; + struct mutex context_mgr_node_lock; + kuid_t binder_context_mgr_uid; const char *name; }; @@ -237,11 +276,20 @@ struct binder_device { struct binder_context context; }; +/** + * struct binder_work - work enqueued on a worklist + * @entry: node enqueued on list + * @type: type of work to be performed + * + * There are separate work lists for proc, thread, and node (async). + */ struct binder_work { struct list_head entry; + enum { BINDER_WORK_TRANSACTION = 1, BINDER_WORK_TRANSACTION_COMPLETE, + BINDER_WORK_RETURN_ERROR, BINDER_WORK_NODE, BINDER_WORK_DEAD_BINDER, BINDER_WORK_DEAD_BINDER_AND_CLEAR, @@ -249,8 +297,72 @@ struct binder_work { } type; }; +struct binder_error { + struct binder_work work; + uint32_t cmd; +}; + +/** + * struct binder_node - binder node bookkeeping + * @debug_id: unique ID for debugging + * (invariant after initialized) + * @lock: lock for node fields + * @work: worklist element for node work + * (protected by @proc->inner_lock) + * @rb_node: element for proc->nodes tree + * (protected by @proc->inner_lock) + * @dead_node: element for binder_dead_nodes list + * (protected by binder_dead_nodes_lock) + * @proc: binder_proc that owns this node + * (invariant after initialized) + * @refs: list of references on this node + * (protected by @lock) + * @internal_strong_refs: used to take strong references when + * initiating a transaction + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @local_weak_refs: weak user refs from local process + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @local_strong_refs: strong user refs from local process + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @tmp_refs: temporary kernel refs + * (protected by @proc->inner_lock while @proc + * is valid, and by binder_dead_nodes_lock + * if @proc is NULL. During inc/dec and node release + * it is also protected by @lock to provide safety + * as the node dies and @proc becomes NULL) + * @ptr: userspace pointer for node + * (invariant, no lock needed) + * @cookie: userspace cookie for node + * (invariant, no lock needed) + * @has_strong_ref: userspace notified of strong ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @pending_strong_ref: userspace has acked notification of strong ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @has_weak_ref: userspace notified of weak ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @pending_weak_ref: userspace has acked notification of weak ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @has_async_transaction: async transaction to node in progress + * (protected by @lock) + * @accept_fds: file descriptor operations supported for node + * (invariant after initialized) + * @min_priority: minimum scheduling priority + * (invariant after initialized) + * @async_todo: list of async work items + * (protected by @proc->inner_lock) + * + * Bookkeeping structure for binder nodes. + */ struct binder_node { int debug_id; + spinlock_t lock; struct binder_work work; union { struct rb_node rb_node; @@ -261,64 +373,153 @@ struct binder_node { int internal_strong_refs; int local_weak_refs; int local_strong_refs; + int tmp_refs; binder_uintptr_t ptr; binder_uintptr_t cookie; - unsigned has_strong_ref:1; - unsigned pending_strong_ref:1; - unsigned has_weak_ref:1; - unsigned pending_weak_ref:1; - unsigned has_async_transaction:1; - unsigned accept_fds:1; - unsigned min_priority:8; + struct { + /* + * bitfield elements protected by + * proc inner_lock + */ + u8 has_strong_ref:1; + u8 pending_strong_ref:1; + u8 has_weak_ref:1; + u8 pending_weak_ref:1; + }; + struct { + /* + * invariant after initialization + */ + u8 accept_fds:1; + u8 min_priority; + }; + bool has_async_transaction; struct list_head async_todo; }; struct binder_ref_death { + /** + * @work: worklist element for death notifications + * (protected by inner_lock of the proc that + * this ref belongs to) + */ struct binder_work work; binder_uintptr_t cookie; }; +/** + * struct binder_ref_data - binder_ref counts and id + * @debug_id: unique ID for the ref + * @desc: unique userspace handle for ref + * @strong: strong ref count (debugging only if not locked) + * @weak: weak ref count (debugging only if not locked) + * + * Structure to hold ref count and ref id information. Since + * the actual ref can only be accessed with a lock, this structure + * is used to return information about the ref to callers of + * ref inc/dec functions. + */ +struct binder_ref_data { + int debug_id; + uint32_t desc; + int strong; + int weak; +}; + +/** + * struct binder_ref - struct to track references on nodes + * @data: binder_ref_data containing id, handle, and current refcounts + * @rb_node_desc: node for lookup by @data.desc in proc's rb_tree + * @rb_node_node: node for lookup by @node in proc's rb_tree + * @node_entry: list entry for node->refs list in target node + * (protected by @node->lock) + * @proc: binder_proc containing ref + * @node: binder_node of target node. When cleaning up a + * ref for deletion in binder_cleanup_ref, a non-NULL + * @node indicates the node must be freed + * @death: pointer to death notification (ref_death) if requested + * (protected by @node->lock) + * + * Structure to track references from procA to target node (on procB). This + * structure is unsafe to access without holding @proc->outer_lock. + */ struct binder_ref { /* Lookups needed: */ /* node + proc => ref (transaction) */ /* desc + proc => ref (transaction, inc/dec ref) */ /* node => refs + procs (proc exit) */ - int debug_id; + struct binder_ref_data data; struct rb_node rb_node_desc; struct rb_node rb_node_node; struct hlist_node node_entry; struct binder_proc *proc; struct binder_node *node; - uint32_t desc; - int strong; - int weak; struct binder_ref_death *death; }; -struct binder_buffer { - struct list_head entry; /* free and allocated entries by address */ - struct rb_node rb_node; /* free entry by size or allocated entry */ - /* by address */ - unsigned free:1; - unsigned allow_user_free:1; - unsigned async_transaction:1; - unsigned debug_id:29; - - struct binder_transaction *transaction; - - struct binder_node *target_node; - size_t data_size; - size_t offsets_size; - size_t extra_buffers_size; - uint8_t data[0]; -}; - enum binder_deferred_state { BINDER_DEFERRED_PUT_FILES = 0x01, BINDER_DEFERRED_FLUSH = 0x02, BINDER_DEFERRED_RELEASE = 0x04, }; +/** + * struct binder_proc - binder process bookkeeping + * @proc_node: element for binder_procs list + * @threads: rbtree of binder_threads in this proc + * (protected by @inner_lock) + * @nodes: rbtree of binder nodes associated with + * this proc ordered by node->ptr + * (protected by @inner_lock) + * @refs_by_desc: rbtree of refs ordered by ref->desc + * (protected by @outer_lock) + * @refs_by_node: rbtree of refs ordered by ref->node + * (protected by @outer_lock) + * @pid PID of group_leader of process + * (invariant after initialized) + * @tsk task_struct for group_leader of process + * (invariant after initialized) + * @files files_struct for process + * (invariant after initialized) + * @deferred_work_node: element for binder_deferred_list + * (protected by binder_deferred_lock) + * @deferred_work: bitmap of deferred work to perform + * (protected by binder_deferred_lock) + * @is_dead: process is dead and awaiting free + * when outstanding transactions are cleaned up + * (protected by @inner_lock) + * @todo: list of work for this process + * (protected by @inner_lock) + * @wait: wait queue head to wait for proc work + * (invariant after initialized) + * @stats: per-process binder statistics + * (atomics, no lock needed) + * @delivered_death: list of delivered death notification + * (protected by @inner_lock) + * @max_threads: cap on number of binder threads + * (protected by @inner_lock) + * @requested_threads: number of binder threads requested but not + * yet started. In current implementation, can + * only be 0 or 1. + * (protected by @inner_lock) + * @requested_threads_started: number binder threads started + * (protected by @inner_lock) + * @ready_threads: number of threads waiting for proc work + * (protected by @inner_lock) + * @tmp_ref: temporary reference to indicate proc is in use + * (protected by @inner_lock) + * @default_priority: default scheduler priority + * (invariant after initialized) + * @debugfs_entry: debugfs node + * @alloc: binder allocator bookkeeping + * @context: binder_context for this proc + * (invariant after initialized) + * @inner_lock: can nest under outer_lock and/or node lock + * @outer_lock: no nesting under innor or node lock + * Lock order: 1) outer, 2) node, 3) inner + * + * Bookkeeping structure for binder processes + */ struct binder_proc { struct hlist_node proc_node; struct rb_root threads; @@ -326,23 +527,12 @@ struct binder_proc { struct rb_root refs_by_desc; struct rb_root refs_by_node; int pid; - struct vm_area_struct *vma; - struct mm_struct *vma_vm_mm; struct task_struct *tsk; struct files_struct *files; struct hlist_node deferred_work_node; int deferred_work; - void *buffer; - ptrdiff_t user_buffer_offset; - - struct list_head buffers; - struct rb_root free_buffers; - struct rb_root allocated_buffers; - size_t free_async_space; + bool is_dead; - struct page **pages; - size_t buffer_size; - uint32_t buffer_free; struct list_head todo; wait_queue_head_t wait; struct binder_stats stats; @@ -351,9 +541,13 @@ struct binder_proc { int requested_threads; int requested_threads_started; int ready_threads; + int tmp_ref; long default_priority; struct dentry *debugfs_entry; + struct binder_alloc alloc; struct binder_context *context; + spinlock_t inner_lock; + spinlock_t outer_lock; }; enum { @@ -362,22 +556,54 @@ enum { BINDER_LOOPER_STATE_EXITED = 0x04, BINDER_LOOPER_STATE_INVALID = 0x08, BINDER_LOOPER_STATE_WAITING = 0x10, - BINDER_LOOPER_STATE_NEED_RETURN = 0x20 }; +/** + * struct binder_thread - binder thread bookkeeping + * @proc: binder process for this thread + * (invariant after initialization) + * @rb_node: element for proc->threads rbtree + * (protected by @proc->inner_lock) + * @pid: PID for this thread + * (invariant after initialization) + * @looper: bitmap of looping state + * (only accessed by this thread) + * @looper_needs_return: looping thread needs to exit driver + * (no lock needed) + * @transaction_stack: stack of in-progress transactions for this thread + * (protected by @proc->inner_lock) + * @todo: list of work to do for this thread + * (protected by @proc->inner_lock) + * @return_error: transaction errors reported by this thread + * (only accessed by this thread) + * @reply_error: transaction errors reported by target thread + * (protected by @proc->inner_lock) + * @wait: wait queue for thread work + * @stats: per-thread statistics + * (atomics, no lock needed) + * @tmp_ref: temporary reference to indicate thread is in use + * (atomic since @proc->inner_lock cannot + * always be acquired) + * @is_dead: thread is dead and awaiting free + * when outstanding transactions are cleaned up + * (protected by @proc->inner_lock) + * + * Bookkeeping structure for binder threads. + */ struct binder_thread { struct binder_proc *proc; struct rb_node rb_node; int pid; - int looper; + int looper; /* only modified by this thread */ + bool looper_need_return; /* can be written by other thread */ struct binder_transaction *transaction_stack; struct list_head todo; - uint32_t return_error; /* Write failed, return error code in read buf */ - uint32_t return_error2; /* Write failed, return error code in read */ - /* buffer. Used when sending a reply to a dead process that */ - /* we are also waiting on */ + struct binder_error return_error; + struct binder_error reply_error; wait_queue_head_t wait; struct binder_stats stats; + atomic_t tmp_ref; + bool is_dead; }; struct binder_transaction { @@ -397,10 +623,253 @@ struct binder_transaction { long priority; long saved_priority; kuid_t sender_euid; + /** + * @lock: protects @from, @to_proc, and @to_thread + * + * @from, @to_proc, and @to_thread can be set to NULL + * during thread teardown + */ + spinlock_t lock; }; +/** + * binder_proc_lock() - Acquire outer lock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Acquires proc->outer_lock. Used to protect binder_ref + * structures associated with the given proc. + */ +#define binder_proc_lock(proc) _binder_proc_lock(proc, __LINE__) +static void +_binder_proc_lock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&proc->outer_lock); +} + +/** + * binder_proc_unlock() - Release spinlock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Release lock acquired via binder_proc_lock() + */ +#define binder_proc_unlock(_proc) _binder_proc_unlock(_proc, __LINE__) +static void +_binder_proc_unlock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_unlock(&proc->outer_lock); +} + +/** + * binder_inner_proc_lock() - Acquire inner lock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Acquires proc->inner_lock. Used to protect todo lists + */ +#define binder_inner_proc_lock(proc) _binder_inner_proc_lock(proc, __LINE__) +static void +_binder_inner_proc_lock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&proc->inner_lock); +} + +/** + * binder_inner_proc_unlock() - Release inner lock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Release lock acquired via binder_inner_proc_lock() + */ +#define binder_inner_proc_unlock(proc) _binder_inner_proc_unlock(proc, __LINE__) +static void +_binder_inner_proc_unlock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_unlock(&proc->inner_lock); +} + +/** + * binder_node_lock() - Acquire spinlock for given binder_node + * @node: struct binder_node to acquire + * + * Acquires node->lock. Used to protect binder_node fields + */ +#define binder_node_lock(node) _binder_node_lock(node, __LINE__) +static void +_binder_node_lock(struct binder_node *node, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&node->lock); +} + +/** + * binder_node_unlock() - Release spinlock for given binder_proc + * @node: struct binder_node to acquire + * + * Release lock acquired via binder_node_lock() + */ +#define binder_node_unlock(node) _binder_node_unlock(node, __LINE__) +static void +_binder_node_unlock(struct binder_node *node, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_unlock(&node->lock); +} + +/** + * binder_node_inner_lock() - Acquire node and inner locks + * @node: struct binder_node to acquire + * + * Acquires node->lock. If node->proc also acquires + * proc->inner_lock. Used to protect binder_node fields + */ +#define binder_node_inner_lock(node) _binder_node_inner_lock(node, __LINE__) +static void +_binder_node_inner_lock(struct binder_node *node, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&node->lock); + if (node->proc) + binder_inner_proc_lock(node->proc); +} + +/** + * binder_node_unlock() - Release node and inner locks + * @node: struct binder_node to acquire + * + * Release lock acquired via binder_node_lock() + */ +#define binder_node_inner_unlock(node) _binder_node_inner_unlock(node, __LINE__) +static void +_binder_node_inner_unlock(struct binder_node *node, int line) +{ + struct binder_proc *proc = node->proc; + + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + if (proc) + binder_inner_proc_unlock(proc); + spin_unlock(&node->lock); +} + +static bool binder_worklist_empty_ilocked(struct list_head *list) +{ + return list_empty(list); +} + +/** + * binder_worklist_empty() - Check if no items on the work list + * @proc: binder_proc associated with list + * @list: list to check + * + * Return: true if there are no items on list, else false + */ +static bool binder_worklist_empty(struct binder_proc *proc, + struct list_head *list) +{ + bool ret; + + binder_inner_proc_lock(proc); + ret = binder_worklist_empty_ilocked(list); + binder_inner_proc_unlock(proc); + return ret; +} + +static void +binder_enqueue_work_ilocked(struct binder_work *work, + struct list_head *target_list) +{ + BUG_ON(target_list == NULL); + BUG_ON(work->entry.next && !list_empty(&work->entry)); + list_add_tail(&work->entry, target_list); +} + +/** + * binder_enqueue_work() - Add an item to the work list + * @proc: binder_proc associated with list + * @work: struct binder_work to add to list + * @target_list: list to add work to + * + * Adds the work to the specified list. Asserts that work + * is not already on a list. + */ +static void +binder_enqueue_work(struct binder_proc *proc, + struct binder_work *work, + struct list_head *target_list) +{ + binder_inner_proc_lock(proc); + binder_enqueue_work_ilocked(work, target_list); + binder_inner_proc_unlock(proc); +} + +static void +binder_dequeue_work_ilocked(struct binder_work *work) +{ + list_del_init(&work->entry); +} + +/** + * binder_dequeue_work() - Removes an item from the work list + * @proc: binder_proc associated with list + * @work: struct binder_work to remove from list + * + * Removes the specified work item from whatever list it is on. + * Can safely be called if work is not on any list. + */ +static void +binder_dequeue_work(struct binder_proc *proc, struct binder_work *work) +{ + binder_inner_proc_lock(proc); + binder_dequeue_work_ilocked(work); + binder_inner_proc_unlock(proc); +} + +static struct binder_work *binder_dequeue_work_head_ilocked( + struct list_head *list) +{ + struct binder_work *w; + + w = list_first_entry_or_null(list, struct binder_work, entry); + if (w) + list_del_init(&w->entry); + return w; +} + +/** + * binder_dequeue_work_head() - Dequeues the item at head of list + * @proc: binder_proc associated with list + * @list: list to dequeue head + * + * Removes the head of the list if there are items on the list + * + * Return: pointer dequeued binder_work, NULL if list was empty + */ +static struct binder_work *binder_dequeue_work_head( + struct binder_proc *proc, + struct list_head *list) +{ + struct binder_work *w; + + binder_inner_proc_lock(proc); + w = binder_dequeue_work_head_ilocked(list); + binder_inner_proc_unlock(proc); + return w; +} + static void binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer); +static void binder_free_thread(struct binder_thread *thread); +static void binder_free_proc(struct binder_proc *proc); +static void binder_inc_node_tmpref_ilocked(struct binder_node *node); static int task_get_unused_fd_flags(struct binder_proc *proc, int flags) { @@ -451,19 +920,6 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd) return retval; } -static inline void binder_lock(const char *tag) -{ - trace_binder_lock(tag); - mutex_lock(&binder_main_lock); - trace_binder_locked(tag); -} - -static inline void binder_unlock(const char *tag) -{ - trace_binder_unlock(tag); - mutex_unlock(&binder_main_lock); -} - static void binder_set_nice(long nice) { long min_nice; @@ -472,7 +928,7 @@ static void binder_set_nice(long nice) set_user_nice(current, nice); return; } - min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur); + min_nice = rlimit_to_nice(rlimit(RLIMIT_NICE)); binder_debug(BINDER_DEBUG_PRIORITY_CAP, "%d: nice value %ld not allowed use %ld instead\n", current->pid, nice, min_nice); @@ -482,453 +938,60 @@ static void binder_set_nice(long nice) binder_user_error("%d RLIMIT_NICE not set\n", current->pid); } -static size_t binder_buffer_size(struct binder_proc *proc, - struct binder_buffer *buffer) -{ - if (list_is_last(&buffer->entry, &proc->buffers)) - return proc->buffer + proc->buffer_size - (void *)buffer->data; - return (size_t)list_entry(buffer->entry.next, - struct binder_buffer, entry) - (size_t)buffer->data; -} - -static void binder_insert_free_buffer(struct binder_proc *proc, - struct binder_buffer *new_buffer) -{ - struct rb_node **p = &proc->free_buffers.rb_node; - struct rb_node *parent = NULL; - struct binder_buffer *buffer; - size_t buffer_size; - size_t new_buffer_size; - - BUG_ON(!new_buffer->free); - - new_buffer_size = binder_buffer_size(proc, new_buffer); - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: add free buffer, size %zd, at %p\n", - proc->pid, new_buffer_size, new_buffer); - - while (*p) { - parent = *p; - buffer = rb_entry(parent, struct binder_buffer, rb_node); - BUG_ON(!buffer->free); - - buffer_size = binder_buffer_size(proc, buffer); - - if (new_buffer_size < buffer_size) - p = &parent->rb_left; - else - p = &parent->rb_right; - } - rb_link_node(&new_buffer->rb_node, parent, p); - rb_insert_color(&new_buffer->rb_node, &proc->free_buffers); -} - -static void binder_insert_allocated_buffer(struct binder_proc *proc, - struct binder_buffer *new_buffer) -{ - struct rb_node **p = &proc->allocated_buffers.rb_node; - struct rb_node *parent = NULL; - struct binder_buffer *buffer; - - BUG_ON(new_buffer->free); - - while (*p) { - parent = *p; - buffer = rb_entry(parent, struct binder_buffer, rb_node); - BUG_ON(buffer->free); - - if (new_buffer < buffer) - p = &parent->rb_left; - else if (new_buffer > buffer) - p = &parent->rb_right; - else - BUG(); - } - rb_link_node(&new_buffer->rb_node, parent, p); - rb_insert_color(&new_buffer->rb_node, &proc->allocated_buffers); -} - -static struct binder_buffer *binder_buffer_lookup(struct binder_proc *proc, - uintptr_t user_ptr) -{ - struct rb_node *n = proc->allocated_buffers.rb_node; - struct binder_buffer *buffer; - struct binder_buffer *kern_ptr; - - kern_ptr = (struct binder_buffer *)(user_ptr - proc->user_buffer_offset - - offsetof(struct binder_buffer, data)); - - while (n) { - buffer = rb_entry(n, struct binder_buffer, rb_node); - BUG_ON(buffer->free); - - if (kern_ptr < buffer) - n = n->rb_left; - else if (kern_ptr > buffer) - n = n->rb_right; - else - return buffer; - } - return NULL; -} - -static int binder_update_page_range(struct binder_proc *proc, int allocate, - void *start, void *end, - struct vm_area_struct *vma) -{ - void *page_addr; - unsigned long user_page_addr; - struct page **page; - struct mm_struct *mm; - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: %s pages %p-%p\n", proc->pid, - allocate ? "allocate" : "free", start, end); - - if (end <= start) - return 0; - - trace_binder_update_page_range(proc, allocate, start, end); - - if (vma) - mm = NULL; - else - mm = get_task_mm(proc->tsk); - - if (mm) { - down_write(&mm->mmap_sem); - vma = proc->vma; - if (vma && mm != proc->vma_vm_mm) { - pr_err("%d: vma mm and task mm mismatch\n", - proc->pid); - vma = NULL; - } - } - - if (allocate == 0) - goto free_range; - - if (vma == NULL) { - pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n", - proc->pid); - goto err_no_vma; - } - - for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) { - int ret; - - page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE]; - - BUG_ON(*page); - *page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); - if (*page == NULL) { - pr_err("%d: binder_alloc_buf failed for page at %p\n", - proc->pid, page_addr); - goto err_alloc_page_failed; - } - ret = map_kernel_range_noflush((unsigned long)page_addr, - PAGE_SIZE, PAGE_KERNEL, page); - flush_cache_vmap((unsigned long)page_addr, - (unsigned long)page_addr + PAGE_SIZE); - if (ret != 1) { - pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n", - proc->pid, page_addr); - goto err_map_kernel_failed; - } - user_page_addr = - (uintptr_t)page_addr + proc->user_buffer_offset; - ret = vm_insert_page(vma, user_page_addr, page[0]); - if (ret) { - pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n", - proc->pid, user_page_addr); - goto err_vm_insert_page_failed; - } - /* vm_insert_page does not seem to increment the refcount */ - } - if (mm) { - up_write(&mm->mmap_sem); - mmput(mm); - } - return 0; - -free_range: - for (page_addr = end - PAGE_SIZE; page_addr >= start; - page_addr -= PAGE_SIZE) { - page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE]; - if (vma) - zap_page_range(vma, (uintptr_t)page_addr + - proc->user_buffer_offset, PAGE_SIZE); -err_vm_insert_page_failed: - unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); -err_map_kernel_failed: - __free_page(*page); - *page = NULL; -err_alloc_page_failed: - ; - } -err_no_vma: - if (mm) { - up_write(&mm->mmap_sem); - mmput(mm); - } - return -ENOMEM; -} - -static struct binder_buffer *binder_alloc_buf(struct binder_proc *proc, - size_t data_size, - size_t offsets_size, - size_t extra_buffers_size, - int is_async) +static struct binder_node *binder_get_node_ilocked(struct binder_proc *proc, + binder_uintptr_t ptr) { - struct rb_node *n = proc->free_buffers.rb_node; - struct binder_buffer *buffer; - size_t buffer_size; - struct rb_node *best_fit = NULL; - void *has_page_addr; - void *end_page_addr; - size_t size, data_offsets_size; - - if (proc->vma == NULL) { - pr_err("%d: binder_alloc_buf, no vma\n", - proc->pid); - return NULL; - } + struct rb_node *n = proc->nodes.rb_node; + struct binder_node *node; - data_offsets_size = ALIGN(data_size, sizeof(void *)) + - ALIGN(offsets_size, sizeof(void *)); - - if (data_offsets_size < data_size || data_offsets_size < offsets_size) { - binder_user_error("%d: got transaction with invalid size %zd-%zd\n", - proc->pid, data_size, offsets_size); - return NULL; - } - size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *)); - if (size < data_offsets_size || size < extra_buffers_size) { - binder_user_error("%d: got transaction with invalid extra_buffers_size %zd\n", - proc->pid, extra_buffers_size); - return NULL; - } - if (is_async && - proc->free_async_space < size + sizeof(struct binder_buffer)) { - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd failed, no async space left\n", - proc->pid, size); - return NULL; - } + BUG_ON(!spin_is_locked(&proc->inner_lock)); while (n) { - buffer = rb_entry(n, struct binder_buffer, rb_node); - BUG_ON(!buffer->free); - buffer_size = binder_buffer_size(proc, buffer); + node = rb_entry(n, struct binder_node, rb_node); - if (size < buffer_size) { - best_fit = n; + if (ptr < node->ptr) n = n->rb_left; - } else if (size > buffer_size) + else if (ptr > node->ptr) n = n->rb_right; else { - best_fit = n; - break; - } - } - if (best_fit == NULL) { - pr_err("%d: binder_alloc_buf size %zd failed, no address space\n", - proc->pid, size); - return NULL; - } - if (n == NULL) { - buffer = rb_entry(best_fit, struct binder_buffer, rb_node); - buffer_size = binder_buffer_size(proc, buffer); - } - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd got buffer %p size %zd\n", - proc->pid, size, buffer, buffer_size); - - has_page_addr = - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK); - if (n == NULL) { - if (size + sizeof(struct binder_buffer) + 4 >= buffer_size) - buffer_size = size; /* no room for other buffers */ - else - buffer_size = size + sizeof(struct binder_buffer); - } - end_page_addr = - (void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size); - if (end_page_addr > has_page_addr) - end_page_addr = has_page_addr; - if (binder_update_page_range(proc, 1, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL)) - return NULL; - - rb_erase(best_fit, &proc->free_buffers); - buffer->free = 0; - binder_insert_allocated_buffer(proc, buffer); - if (buffer_size != size) { - struct binder_buffer *new_buffer = (void *)buffer->data + size; - - list_add(&new_buffer->entry, &buffer->entry); - new_buffer->free = 1; - binder_insert_free_buffer(proc, new_buffer); - } - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd got %p\n", - proc->pid, size, buffer); - buffer->data_size = data_size; - buffer->offsets_size = offsets_size; - buffer->extra_buffers_size = extra_buffers_size; - buffer->async_transaction = is_async; - if (is_async) { - proc->free_async_space -= size + sizeof(struct binder_buffer); - binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, - "%d: binder_alloc_buf size %zd async free %zd\n", - proc->pid, size, proc->free_async_space); - } - - return buffer; -} - -static void *buffer_start_page(struct binder_buffer *buffer) -{ - return (void *)((uintptr_t)buffer & PAGE_MASK); -} - -static void *buffer_end_page(struct binder_buffer *buffer) -{ - return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK); -} - -static void binder_delete_free_buffer(struct binder_proc *proc, - struct binder_buffer *buffer) -{ - struct binder_buffer *prev, *next = NULL; - int free_page_end = 1; - int free_page_start = 1; - - BUG_ON(proc->buffers.next == &buffer->entry); - prev = list_entry(buffer->entry.prev, struct binder_buffer, entry); - BUG_ON(!prev->free); - if (buffer_end_page(prev) == buffer_start_page(buffer)) { - free_page_start = 0; - if (buffer_end_page(prev) == buffer_end_page(buffer)) - free_page_end = 0; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p share page with %p\n", - proc->pid, buffer, prev); - } - - if (!list_is_last(&buffer->entry, &proc->buffers)) { - next = list_entry(buffer->entry.next, - struct binder_buffer, entry); - if (buffer_start_page(next) == buffer_end_page(buffer)) { - free_page_end = 0; - if (buffer_start_page(next) == - buffer_start_page(buffer)) - free_page_start = 0; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p share page with %p\n", - proc->pid, buffer, prev); - } - } - list_del(&buffer->entry); - if (free_page_start || free_page_end) { - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p do not share page%s%s with %p or %p\n", - proc->pid, buffer, free_page_start ? "" : " end", - free_page_end ? "" : " start", prev, next); - binder_update_page_range(proc, 0, free_page_start ? - buffer_start_page(buffer) : buffer_end_page(buffer), - (free_page_end ? buffer_end_page(buffer) : - buffer_start_page(buffer)) + PAGE_SIZE, NULL); - } -} - -static void binder_free_buf(struct binder_proc *proc, - struct binder_buffer *buffer) -{ - size_t size, buffer_size; - - buffer_size = binder_buffer_size(proc, buffer); - - size = ALIGN(buffer->data_size, sizeof(void *)) + - ALIGN(buffer->offsets_size, sizeof(void *)) + - ALIGN(buffer->extra_buffers_size, sizeof(void *)); - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_free_buf %p size %zd buffer_size %zd\n", - proc->pid, buffer, size, buffer_size); - - BUG_ON(buffer->free); - BUG_ON(size > buffer_size); - BUG_ON(buffer->transaction != NULL); - BUG_ON((void *)buffer < proc->buffer); - BUG_ON((void *)buffer > proc->buffer + proc->buffer_size); - - if (buffer->async_transaction) { - proc->free_async_space += size + sizeof(struct binder_buffer); - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, - "%d: binder_free_buf size %zd async free %zd\n", - proc->pid, size, proc->free_async_space); - } - - binder_update_page_range(proc, 0, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK), - NULL); - rb_erase(&buffer->rb_node, &proc->allocated_buffers); - buffer->free = 1; - if (!list_is_last(&buffer->entry, &proc->buffers)) { - struct binder_buffer *next = list_entry(buffer->entry.next, - struct binder_buffer, entry); - - if (next->free) { - rb_erase(&next->rb_node, &proc->free_buffers); - binder_delete_free_buffer(proc, next); - } - } - if (proc->buffers.next != &buffer->entry) { - struct binder_buffer *prev = list_entry(buffer->entry.prev, - struct binder_buffer, entry); - - if (prev->free) { - binder_delete_free_buffer(proc, buffer); - rb_erase(&prev->rb_node, &proc->free_buffers); - buffer = prev; + /* + * take an implicit weak reference + * to ensure node stays alive until + * call to binder_put_node() + */ + binder_inc_node_tmpref_ilocked(node); + return node; } } - binder_insert_free_buffer(proc, buffer); + return NULL; } static struct binder_node *binder_get_node(struct binder_proc *proc, binder_uintptr_t ptr) { - struct rb_node *n = proc->nodes.rb_node; struct binder_node *node; - while (n) { - node = rb_entry(n, struct binder_node, rb_node); - - if (ptr < node->ptr) - n = n->rb_left; - else if (ptr > node->ptr) - n = n->rb_right; - else - return node; - } - return NULL; + binder_inner_proc_lock(proc); + node = binder_get_node_ilocked(proc, ptr); + binder_inner_proc_unlock(proc); + return node; } -static struct binder_node *binder_new_node(struct binder_proc *proc, - binder_uintptr_t ptr, - binder_uintptr_t cookie) +static struct binder_node *binder_init_node_ilocked( + struct binder_proc *proc, + struct binder_node *new_node, + struct flat_binder_object *fp) { struct rb_node **p = &proc->nodes.rb_node; struct rb_node *parent = NULL; struct binder_node *node; + binder_uintptr_t ptr = fp ? fp->binder : 0; + binder_uintptr_t cookie = fp ? fp->cookie : 0; + __u32 flags = fp ? fp->flags : 0; + BUG_ON(!spin_is_locked(&proc->inner_lock)); while (*p) { + parent = *p; node = rb_entry(parent, struct binder_node, rb_node); @@ -936,33 +999,74 @@ static struct binder_node *binder_new_node(struct binder_proc *proc, p = &(*p)->rb_left; else if (ptr > node->ptr) p = &(*p)->rb_right; - else - return NULL; + else { + /* + * A matching node is already in + * the rb tree. Abandon the init + * and return it. + */ + binder_inc_node_tmpref_ilocked(node); + return node; + } } - - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (node == NULL) - return NULL; + node = new_node; binder_stats_created(BINDER_STAT_NODE); + node->tmp_refs++; rb_link_node(&node->rb_node, parent, p); rb_insert_color(&node->rb_node, &proc->nodes); - node->debug_id = ++binder_last_id; + node->debug_id = atomic_inc_return(&binder_last_id); node->proc = proc; node->ptr = ptr; node->cookie = cookie; node->work.type = BINDER_WORK_NODE; + node->min_priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK; + node->accept_fds = !!(flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); + spin_lock_init(&node->lock); INIT_LIST_HEAD(&node->work.entry); INIT_LIST_HEAD(&node->async_todo); binder_debug(BINDER_DEBUG_INTERNAL_REFS, "%d:%d node %d u%016llx c%016llx created\n", proc->pid, current->pid, node->debug_id, (u64)node->ptr, (u64)node->cookie); + return node; } -static int binder_inc_node(struct binder_node *node, int strong, int internal, - struct list_head *target_list) +static struct binder_node *binder_new_node(struct binder_proc *proc, + struct flat_binder_object *fp) { + struct binder_node *node; + struct binder_node *new_node = kzalloc(sizeof(*node), GFP_KERNEL); + + if (!new_node) + return NULL; + binder_inner_proc_lock(proc); + node = binder_init_node_ilocked(proc, new_node, fp); + binder_inner_proc_unlock(proc); + if (node != new_node) + /* + * The node was already added by another thread + */ + kfree(new_node); + + return node; +} + +static void binder_free_node(struct binder_node *node) +{ + kfree(node); + binder_stats_deleted(BINDER_STAT_NODE); +} + +static int binder_inc_node_nilocked(struct binder_node *node, int strong, + int internal, + struct list_head *target_list) +{ + struct binder_proc *proc = node->proc; + + BUG_ON(!spin_is_locked(&node->lock)); + if (proc) + BUG_ON(!spin_is_locked(&proc->inner_lock)); if (strong) { if (internal) { if (target_list == NULL && @@ -978,8 +1082,8 @@ static int binder_inc_node(struct binder_node *node, int strong, int internal, } else node->local_strong_refs++; if (!node->has_strong_ref && target_list) { - list_del_init(&node->work.entry); - list_add_tail(&node->work.entry, target_list); + binder_dequeue_work_ilocked(&node->work); + binder_enqueue_work_ilocked(&node->work, target_list); } } else { if (!internal) @@ -990,58 +1094,169 @@ static int binder_inc_node(struct binder_node *node, int strong, int internal, node->debug_id); return -EINVAL; } - list_add_tail(&node->work.entry, target_list); + binder_enqueue_work_ilocked(&node->work, target_list); } } return 0; } -static int binder_dec_node(struct binder_node *node, int strong, int internal) +static int binder_inc_node(struct binder_node *node, int strong, int internal, + struct list_head *target_list) +{ + int ret; + + binder_node_inner_lock(node); + ret = binder_inc_node_nilocked(node, strong, internal, target_list); + binder_node_inner_unlock(node); + + return ret; +} + +static bool binder_dec_node_nilocked(struct binder_node *node, + int strong, int internal) { + struct binder_proc *proc = node->proc; + + BUG_ON(!spin_is_locked(&node->lock)); + if (proc) + BUG_ON(!spin_is_locked(&proc->inner_lock)); if (strong) { if (internal) node->internal_strong_refs--; else node->local_strong_refs--; if (node->local_strong_refs || node->internal_strong_refs) - return 0; + return false; } else { if (!internal) node->local_weak_refs--; - if (node->local_weak_refs || !hlist_empty(&node->refs)) - return 0; + if (node->local_weak_refs || node->tmp_refs || + !hlist_empty(&node->refs)) + return false; } - if (node->proc && (node->has_strong_ref || node->has_weak_ref)) { + + if (proc && (node->has_strong_ref || node->has_weak_ref)) { if (list_empty(&node->work.entry)) { - list_add_tail(&node->work.entry, &node->proc->todo); + binder_enqueue_work_ilocked(&node->work, &proc->todo); wake_up_interruptible(&node->proc->wait); } } else { if (hlist_empty(&node->refs) && !node->local_strong_refs && - !node->local_weak_refs) { - list_del_init(&node->work.entry); - if (node->proc) { - rb_erase(&node->rb_node, &node->proc->nodes); + !node->local_weak_refs && !node->tmp_refs) { + if (proc) { + binder_dequeue_work_ilocked(&node->work); + rb_erase(&node->rb_node, &proc->nodes); binder_debug(BINDER_DEBUG_INTERNAL_REFS, "refless node %d deleted\n", node->debug_id); } else { + BUG_ON(!list_empty(&node->work.entry)); + spin_lock(&binder_dead_nodes_lock); + /* + * tmp_refs could have changed so + * check it again + */ + if (node->tmp_refs) { + spin_unlock(&binder_dead_nodes_lock); + return false; + } hlist_del(&node->dead_node); + spin_unlock(&binder_dead_nodes_lock); binder_debug(BINDER_DEBUG_INTERNAL_REFS, "dead node %d deleted\n", node->debug_id); } - kfree(node); - binder_stats_deleted(BINDER_STAT_NODE); + return true; } } + return false; +} - return 0; +static void binder_dec_node(struct binder_node *node, int strong, int internal) +{ + bool free_node; + + binder_node_inner_lock(node); + free_node = binder_dec_node_nilocked(node, strong, internal); + binder_node_inner_unlock(node); + if (free_node) + binder_free_node(node); +} + +static void binder_inc_node_tmpref_ilocked(struct binder_node *node) +{ + /* + * No call to binder_inc_node() is needed since we + * don't need to inform userspace of any changes to + * tmp_refs + */ + node->tmp_refs++; +} + +/** + * binder_inc_node_tmpref() - take a temporary reference on node + * @node: node to reference + * + * Take reference on node to prevent the node from being freed + * while referenced only by a local variable. The inner lock is + * needed to serialize with the node work on the queue (which + * isn't needed after the node is dead). If the node is dead + * (node->proc is NULL), use binder_dead_nodes_lock to protect + * node->tmp_refs against dead-node-only cases where the node + * lock cannot be acquired (eg traversing the dead node list to + * print nodes) + */ +static void binder_inc_node_tmpref(struct binder_node *node) +{ + binder_node_lock(node); + if (node->proc) + binder_inner_proc_lock(node->proc); + else + spin_lock(&binder_dead_nodes_lock); + binder_inc_node_tmpref_ilocked(node); + if (node->proc) + binder_inner_proc_unlock(node->proc); + else + spin_unlock(&binder_dead_nodes_lock); + binder_node_unlock(node); +} + +/** + * binder_dec_node_tmpref() - remove a temporary reference on node + * @node: node to reference + * + * Release temporary reference on node taken via binder_inc_node_tmpref() + */ +static void binder_dec_node_tmpref(struct binder_node *node) +{ + bool free_node; + + binder_node_inner_lock(node); + if (!node->proc) + spin_lock(&binder_dead_nodes_lock); + node->tmp_refs--; + BUG_ON(node->tmp_refs < 0); + if (!node->proc) + spin_unlock(&binder_dead_nodes_lock); + /* + * Call binder_dec_node() to check if all refcounts are 0 + * and cleanup is needed. Calling with strong=0 and internal=1 + * causes no actual reference to be released in binder_dec_node(). + * If that changes, a change is needed here too. + */ + free_node = binder_dec_node_nilocked(node, 0, 1); + binder_node_inner_unlock(node); + if (free_node) + binder_free_node(node); } +static void binder_put_node(struct binder_node *node) +{ + binder_dec_node_tmpref(node); +} -static struct binder_ref *binder_get_ref(struct binder_proc *proc, - u32 desc, bool need_strong_ref) +static struct binder_ref *binder_get_ref_olocked(struct binder_proc *proc, + u32 desc, bool need_strong_ref) { struct rb_node *n = proc->refs_by_desc.rb_node; struct binder_ref *ref; @@ -1049,11 +1264,11 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc, while (n) { ref = rb_entry(n, struct binder_ref, rb_node_desc); - if (desc < ref->desc) { + if (desc < ref->data.desc) { n = n->rb_left; - } else if (desc > ref->desc) { + } else if (desc > ref->data.desc) { n = n->rb_right; - } else if (need_strong_ref && !ref->strong) { + } else if (need_strong_ref && !ref->data.strong) { binder_user_error("tried to use weak ref as strong ref\n"); return NULL; } else { @@ -1063,14 +1278,34 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc, return NULL; } -static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc, - struct binder_node *node) +/** + * binder_get_ref_for_node_olocked() - get the ref associated with given node + * @proc: binder_proc that owns the ref + * @node: binder_node of target + * @new_ref: newly allocated binder_ref to be initialized or %NULL + * + * Look up the ref for the given node and return it if it exists + * + * If it doesn't exist and the caller provides a newly allocated + * ref, initialize the fields of the newly allocated ref and insert + * into the given proc rb_trees and node refs list. + * + * Return: the ref for node. It is possible that another thread + * allocated/initialized the ref first in which case the + * returned ref would be different than the passed-in + * new_ref. new_ref must be kfree'd by the caller in + * this case. + */ +static struct binder_ref *binder_get_ref_for_node_olocked( + struct binder_proc *proc, + struct binder_node *node, + struct binder_ref *new_ref) { - struct rb_node *n; + struct binder_context *context = proc->context; struct rb_node **p = &proc->refs_by_node.rb_node; struct rb_node *parent = NULL; - struct binder_ref *ref, *new_ref; - struct binder_context *context = proc->context; + struct binder_ref *ref; + struct rb_node *n; while (*p) { parent = *p; @@ -1083,22 +1318,22 @@ static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc, else return ref; } - new_ref = kzalloc(sizeof(*ref), GFP_KERNEL); - if (new_ref == NULL) + if (!new_ref) return NULL; + binder_stats_created(BINDER_STAT_REF); - new_ref->debug_id = ++binder_last_id; + new_ref->data.debug_id = atomic_inc_return(&binder_last_id); new_ref->proc = proc; new_ref->node = node; rb_link_node(&new_ref->rb_node_node, parent, p); rb_insert_color(&new_ref->rb_node_node, &proc->refs_by_node); - new_ref->desc = (node == context->binder_context_mgr_node) ? 0 : 1; + new_ref->data.desc = (node == context->binder_context_mgr_node) ? 0 : 1; for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) { ref = rb_entry(n, struct binder_ref, rb_node_desc); - if (ref->desc > new_ref->desc) + if (ref->data.desc > new_ref->data.desc) break; - new_ref->desc = ref->desc + 1; + new_ref->data.desc = ref->data.desc + 1; } p = &proc->refs_by_desc.rb_node; @@ -1106,121 +1341,423 @@ static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc, parent = *p; ref = rb_entry(parent, struct binder_ref, rb_node_desc); - if (new_ref->desc < ref->desc) + if (new_ref->data.desc < ref->data.desc) p = &(*p)->rb_left; - else if (new_ref->desc > ref->desc) + else if (new_ref->data.desc > ref->data.desc) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new_ref->rb_node_desc, parent, p); rb_insert_color(&new_ref->rb_node_desc, &proc->refs_by_desc); - if (node) { - hlist_add_head(&new_ref->node_entry, &node->refs); - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d new ref %d desc %d for node %d\n", - proc->pid, new_ref->debug_id, new_ref->desc, - node->debug_id); - } else { - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d new ref %d desc %d for dead node\n", - proc->pid, new_ref->debug_id, new_ref->desc); - } + binder_node_lock(node); + hlist_add_head(&new_ref->node_entry, &node->refs); + + binder_debug(BINDER_DEBUG_INTERNAL_REFS, + "%d new ref %d desc %d for node %d\n", + proc->pid, new_ref->data.debug_id, new_ref->data.desc, + node->debug_id); + binder_node_unlock(node); return new_ref; } -static void binder_delete_ref(struct binder_ref *ref) +static void binder_cleanup_ref_olocked(struct binder_ref *ref) { + bool delete_node = false; + binder_debug(BINDER_DEBUG_INTERNAL_REFS, "%d delete ref %d desc %d for node %d\n", - ref->proc->pid, ref->debug_id, ref->desc, + ref->proc->pid, ref->data.debug_id, ref->data.desc, ref->node->debug_id); rb_erase(&ref->rb_node_desc, &ref->proc->refs_by_desc); rb_erase(&ref->rb_node_node, &ref->proc->refs_by_node); - if (ref->strong) - binder_dec_node(ref->node, 1, 1); + + binder_node_inner_lock(ref->node); + if (ref->data.strong) + binder_dec_node_nilocked(ref->node, 1, 1); + hlist_del(&ref->node_entry); - binder_dec_node(ref->node, 0, 1); + delete_node = binder_dec_node_nilocked(ref->node, 0, 1); + binder_node_inner_unlock(ref->node); + /* + * Clear ref->node unless we want the caller to free the node + */ + if (!delete_node) { + /* + * The caller uses ref->node to determine + * whether the node needs to be freed. Clear + * it since the node is still alive. + */ + ref->node = NULL; + } + if (ref->death) { binder_debug(BINDER_DEBUG_DEAD_BINDER, "%d delete ref %d desc %d has death notification\n", - ref->proc->pid, ref->debug_id, ref->desc); - list_del(&ref->death->work.entry); - kfree(ref->death); + ref->proc->pid, ref->data.debug_id, + ref->data.desc); + binder_dequeue_work(ref->proc, &ref->death->work); binder_stats_deleted(BINDER_STAT_DEATH); } - kfree(ref); binder_stats_deleted(BINDER_STAT_REF); } -static int binder_inc_ref(struct binder_ref *ref, int strong, - struct list_head *target_list) +/** + * binder_inc_ref_olocked() - increment the ref for given handle + * @ref: ref to be incremented + * @strong: if true, strong increment, else weak + * @target_list: list to queue node work on + * + * Increment the ref. @ref->proc->outer_lock must be held on entry + * + * Return: 0, if successful, else errno + */ +static int binder_inc_ref_olocked(struct binder_ref *ref, int strong, + struct list_head *target_list) { int ret; if (strong) { - if (ref->strong == 0) { + if (ref->data.strong == 0) { ret = binder_inc_node(ref->node, 1, 1, target_list); if (ret) return ret; } - ref->strong++; + ref->data.strong++; } else { - if (ref->weak == 0) { + if (ref->data.weak == 0) { ret = binder_inc_node(ref->node, 0, 1, target_list); if (ret) return ret; } - ref->weak++; + ref->data.weak++; } return 0; } - -static int binder_dec_ref(struct binder_ref *ref, int strong) +/** + * binder_dec_ref() - dec the ref for given handle + * @ref: ref to be decremented + * @strong: if true, strong decrement, else weak + * + * Decrement the ref. + * + * Return: true if ref is cleaned up and ready to be freed + */ +static bool binder_dec_ref_olocked(struct binder_ref *ref, int strong) { if (strong) { - if (ref->strong == 0) { + if (ref->data.strong == 0) { binder_user_error("%d invalid dec strong, ref %d desc %d s %d w %d\n", - ref->proc->pid, ref->debug_id, - ref->desc, ref->strong, ref->weak); - return -EINVAL; - } - ref->strong--; - if (ref->strong == 0) { - int ret; - - ret = binder_dec_node(ref->node, strong, 1); - if (ret) - return ret; + ref->proc->pid, ref->data.debug_id, + ref->data.desc, ref->data.strong, + ref->data.weak); + return false; } + ref->data.strong--; + if (ref->data.strong == 0) + binder_dec_node(ref->node, strong, 1); } else { - if (ref->weak == 0) { + if (ref->data.weak == 0) { binder_user_error("%d invalid dec weak, ref %d desc %d s %d w %d\n", - ref->proc->pid, ref->debug_id, - ref->desc, ref->strong, ref->weak); - return -EINVAL; + ref->proc->pid, ref->data.debug_id, + ref->data.desc, ref->data.strong, + ref->data.weak); + return false; } - ref->weak--; + ref->data.weak--; } - if (ref->strong == 0 && ref->weak == 0) - binder_delete_ref(ref); - return 0; + if (ref->data.strong == 0 && ref->data.weak == 0) { + binder_cleanup_ref_olocked(ref); + return true; + } + return false; } -static void binder_pop_transaction(struct binder_thread *target_thread, - struct binder_transaction *t) +/** + * binder_get_node_from_ref() - get the node from the given proc/desc + * @proc: proc containing the ref + * @desc: the handle associated with the ref + * @need_strong_ref: if true, only return node if ref is strong + * @rdata: the id/refcount data for the ref + * + * Given a proc and ref handle, return the associated binder_node + * + * Return: a binder_node or NULL if not found or not strong when strong required + */ +static struct binder_node *binder_get_node_from_ref( + struct binder_proc *proc, + u32 desc, bool need_strong_ref, + struct binder_ref_data *rdata) { - if (target_thread) { - BUG_ON(target_thread->transaction_stack != t); - BUG_ON(target_thread->transaction_stack->from != target_thread); - target_thread->transaction_stack = - target_thread->transaction_stack->from_parent; - t->from = NULL; + struct binder_node *node; + struct binder_ref *ref; + + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, desc, need_strong_ref); + if (!ref) + goto err_no_ref; + node = ref->node; + /* + * Take an implicit reference on the node to ensure + * it stays alive until the call to binder_put_node() + */ + binder_inc_node_tmpref(node); + if (rdata) + *rdata = ref->data; + binder_proc_unlock(proc); + + return node; + +err_no_ref: + binder_proc_unlock(proc); + return NULL; +} + +/** + * binder_free_ref() - free the binder_ref + * @ref: ref to free + * + * Free the binder_ref. Free the binder_node indicated by ref->node + * (if non-NULL) and the binder_ref_death indicated by ref->death. + */ +static void binder_free_ref(struct binder_ref *ref) +{ + if (ref->node) + binder_free_node(ref->node); + kfree(ref->death); + kfree(ref); +} + +/** + * binder_update_ref_for_handle() - inc/dec the ref for given handle + * @proc: proc containing the ref + * @desc: the handle associated with the ref + * @increment: true=inc reference, false=dec reference + * @strong: true=strong reference, false=weak reference + * @rdata: the id/refcount data for the ref + * + * Given a proc and ref handle, increment or decrement the ref + * according to "increment" arg. + * + * Return: 0 if successful, else errno + */ +static int binder_update_ref_for_handle(struct binder_proc *proc, + uint32_t desc, bool increment, bool strong, + struct binder_ref_data *rdata) +{ + int ret = 0; + struct binder_ref *ref; + bool delete_ref = false; + + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, desc, strong); + if (!ref) { + ret = -EINVAL; + goto err_no_ref; + } + if (increment) + ret = binder_inc_ref_olocked(ref, strong, NULL); + else + delete_ref = binder_dec_ref_olocked(ref, strong); + + if (rdata) + *rdata = ref->data; + binder_proc_unlock(proc); + + if (delete_ref) + binder_free_ref(ref); + return ret; + +err_no_ref: + binder_proc_unlock(proc); + return ret; +} + +/** + * binder_dec_ref_for_handle() - dec the ref for given handle + * @proc: proc containing the ref + * @desc: the handle associated with the ref + * @strong: true=strong reference, false=weak reference + * @rdata: the id/refcount data for the ref + * + * Just calls binder_update_ref_for_handle() to decrement the ref. + * + * Return: 0 if successful, else errno + */ +static int binder_dec_ref_for_handle(struct binder_proc *proc, + uint32_t desc, bool strong, struct binder_ref_data *rdata) +{ + return binder_update_ref_for_handle(proc, desc, false, strong, rdata); +} + + +/** + * binder_inc_ref_for_node() - increment the ref for given proc/node + * @proc: proc containing the ref + * @node: target node + * @strong: true=strong reference, false=weak reference + * @target_list: worklist to use if node is incremented + * @rdata: the id/refcount data for the ref + * + * Given a proc and node, increment the ref. Create the ref if it + * doesn't already exist + * + * Return: 0 if successful, else errno + */ +static int binder_inc_ref_for_node(struct binder_proc *proc, + struct binder_node *node, + bool strong, + struct list_head *target_list, + struct binder_ref_data *rdata) +{ + struct binder_ref *ref; + struct binder_ref *new_ref = NULL; + int ret = 0; + + binder_proc_lock(proc); + ref = binder_get_ref_for_node_olocked(proc, node, NULL); + if (!ref) { + binder_proc_unlock(proc); + new_ref = kzalloc(sizeof(*ref), GFP_KERNEL); + if (!new_ref) + return -ENOMEM; + binder_proc_lock(proc); + ref = binder_get_ref_for_node_olocked(proc, node, new_ref); + } + ret = binder_inc_ref_olocked(ref, strong, target_list); + *rdata = ref->data; + binder_proc_unlock(proc); + if (new_ref && ref != new_ref) + /* + * Another thread created the ref first so + * free the one we allocated + */ + kfree(new_ref); + return ret; +} + +static void binder_pop_transaction_ilocked(struct binder_thread *target_thread, + struct binder_transaction *t) +{ + BUG_ON(!target_thread); + BUG_ON(!spin_is_locked(&target_thread->proc->inner_lock)); + BUG_ON(target_thread->transaction_stack != t); + BUG_ON(target_thread->transaction_stack->from != target_thread); + target_thread->transaction_stack = + target_thread->transaction_stack->from_parent; + t->from = NULL; +} + +/** + * binder_thread_dec_tmpref() - decrement thread->tmp_ref + * @thread: thread to decrement + * + * A thread needs to be kept alive while being used to create or + * handle a transaction. binder_get_txn_from() is used to safely + * extract t->from from a binder_transaction and keep the thread + * indicated by t->from from being freed. When done with that + * binder_thread, this function is called to decrement the + * tmp_ref and free if appropriate (thread has been released + * and no transaction being processed by the driver) + */ +static void binder_thread_dec_tmpref(struct binder_thread *thread) +{ + /* + * atomic is used to protect the counter value while + * it cannot reach zero or thread->is_dead is false + */ + binder_inner_proc_lock(thread->proc); + atomic_dec(&thread->tmp_ref); + if (thread->is_dead && !atomic_read(&thread->tmp_ref)) { + binder_inner_proc_unlock(thread->proc); + binder_free_thread(thread); + return; + } + binder_inner_proc_unlock(thread->proc); +} + +/** + * binder_proc_dec_tmpref() - decrement proc->tmp_ref + * @proc: proc to decrement + * + * A binder_proc needs to be kept alive while being used to create or + * handle a transaction. proc->tmp_ref is incremented when + * creating a new transaction or the binder_proc is currently in-use + * by threads that are being released. When done with the binder_proc, + * this function is called to decrement the counter and free the + * proc if appropriate (proc has been released, all threads have + * been released and not currenly in-use to process a transaction). + */ +static void binder_proc_dec_tmpref(struct binder_proc *proc) +{ + binder_inner_proc_lock(proc); + proc->tmp_ref--; + if (proc->is_dead && RB_EMPTY_ROOT(&proc->threads) && + !proc->tmp_ref) { + binder_inner_proc_unlock(proc); + binder_free_proc(proc); + return; + } + binder_inner_proc_unlock(proc); +} + +/** + * binder_get_txn_from() - safely extract the "from" thread in transaction + * @t: binder transaction for t->from + * + * Atomically return the "from" thread and increment the tmp_ref + * count for the thread to ensure it stays alive until + * binder_thread_dec_tmpref() is called. + * + * Return: the value of t->from + */ +static struct binder_thread *binder_get_txn_from( + struct binder_transaction *t) +{ + struct binder_thread *from; + + spin_lock(&t->lock); + from = t->from; + if (from) + atomic_inc(&from->tmp_ref); + spin_unlock(&t->lock); + return from; +} + +/** + * binder_get_txn_from_and_acq_inner() - get t->from and acquire inner lock + * @t: binder transaction for t->from + * + * Same as binder_get_txn_from() except it also acquires the proc->inner_lock + * to guarantee that the thread cannot be released while operating on it. + * The caller must call binder_inner_proc_unlock() to release the inner lock + * as well as call binder_dec_thread_txn() to release the reference. + * + * Return: the value of t->from + */ +static struct binder_thread *binder_get_txn_from_and_acq_inner( + struct binder_transaction *t) +{ + struct binder_thread *from; + + from = binder_get_txn_from(t); + if (!from) + return NULL; + binder_inner_proc_lock(from->proc); + if (t->from) { + BUG_ON(from != t->from); + return from; } - t->need_reply = 0; + binder_inner_proc_unlock(from->proc); + binder_thread_dec_tmpref(from); + return NULL; +} + +static void binder_free_transaction(struct binder_transaction *t) +{ if (t->buffer) t->buffer->transaction = NULL; kfree(t); @@ -1235,30 +1772,28 @@ static void binder_send_failed_reply(struct binder_transaction *t, BUG_ON(t->flags & TF_ONE_WAY); while (1) { - target_thread = t->from; + target_thread = binder_get_txn_from_and_acq_inner(t); if (target_thread) { - if (target_thread->return_error != BR_OK && - target_thread->return_error2 == BR_OK) { - target_thread->return_error2 = - target_thread->return_error; - target_thread->return_error = BR_OK; - } - if (target_thread->return_error == BR_OK) { - binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "send failed reply for transaction %d to %d:%d\n", - t->debug_id, - target_thread->proc->pid, - target_thread->pid); - - binder_pop_transaction(target_thread, t); - target_thread->return_error = error_code; + binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, + "send failed reply for transaction %d to %d:%d\n", + t->debug_id, + target_thread->proc->pid, + target_thread->pid); + + binder_pop_transaction_ilocked(target_thread, t); + if (target_thread->reply_error.cmd == BR_OK) { + target_thread->reply_error.cmd = error_code; + binder_enqueue_work_ilocked( + &target_thread->reply_error.work, + &target_thread->todo); wake_up_interruptible(&target_thread->wait); } else { - pr_err("reply failed, target thread, %d:%d, has error code %d already\n", - target_thread->proc->pid, - target_thread->pid, - target_thread->return_error); + WARN(1, "Unexpected reply error: %u\n", + target_thread->reply_error.cmd); } + binder_inner_proc_unlock(target_thread->proc); + binder_thread_dec_tmpref(target_thread); + binder_free_transaction(t); return; } next = t->from_parent; @@ -1267,7 +1802,7 @@ static void binder_send_failed_reply(struct binder_transaction *t, "send failed reply for transaction %d, target dead\n", t->debug_id); - binder_pop_transaction(target_thread, t); + binder_free_transaction(t); if (next == NULL) { binder_debug(BINDER_DEBUG_DEAD_BINDER, "reply failed, no target thread at root\n"); @@ -1476,24 +2011,26 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, node->debug_id, (u64)node->ptr); binder_dec_node(node, hdr->type == BINDER_TYPE_BINDER, 0); + binder_put_node(node); } break; case BINDER_TYPE_HANDLE: case BINDER_TYPE_WEAK_HANDLE: { struct flat_binder_object *fp; - struct binder_ref *ref; + struct binder_ref_data rdata; + int ret; fp = to_flat_binder_object(hdr); - ref = binder_get_ref(proc, fp->handle, - hdr->type == BINDER_TYPE_HANDLE); - if (ref == NULL) { - pr_err("transaction release %d bad handle %d\n", - debug_id, fp->handle); + ret = binder_dec_ref_for_handle(proc, fp->handle, + hdr->type == BINDER_TYPE_HANDLE, &rdata); + + if (ret) { + pr_err("transaction release %d bad handle %d, ret = %d\n", + debug_id, fp->handle, ret); break; } binder_debug(BINDER_DEBUG_TRANSACTION, - " ref %d desc %d (node %d)\n", - ref->debug_id, ref->desc, ref->node->debug_id); - binder_dec_ref(ref, hdr->type == BINDER_TYPE_HANDLE); + " ref %d desc %d\n", + rdata.debug_id, rdata.desc); } break; case BINDER_TYPE_FD: { @@ -1532,7 +2069,8 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, * back to kernel address space to access it */ parent_buffer = parent->buffer - - proc->user_buffer_offset; + binder_alloc_get_user_buffer_offset( + &proc->alloc); fd_buf_size = sizeof(u32) * fda->num_fds; if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { @@ -1564,102 +2102,122 @@ static int binder_translate_binder(struct flat_binder_object *fp, struct binder_thread *thread) { struct binder_node *node; - struct binder_ref *ref; struct binder_proc *proc = thread->proc; struct binder_proc *target_proc = t->to_proc; + struct binder_ref_data rdata; + int ret = 0; node = binder_get_node(proc, fp->binder); if (!node) { - node = binder_new_node(proc, fp->binder, fp->cookie); + node = binder_new_node(proc, fp); if (!node) return -ENOMEM; - - node->min_priority = fp->flags & FLAT_BINDER_FLAG_PRIORITY_MASK; - node->accept_fds = !!(fp->flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); } if (fp->cookie != node->cookie) { binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n", proc->pid, thread->pid, (u64)fp->binder, node->debug_id, (u64)fp->cookie, (u64)node->cookie); - return -EINVAL; + ret = -EINVAL; + goto done; + } + if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + ret = -EPERM; + goto done; } - if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) - return -EPERM; - ref = binder_get_ref_for_node(target_proc, node); - if (!ref) - return -EINVAL; + ret = binder_inc_ref_for_node(target_proc, node, + fp->hdr.type == BINDER_TYPE_BINDER, + &thread->todo, &rdata); + if (ret) + goto done; if (fp->hdr.type == BINDER_TYPE_BINDER) fp->hdr.type = BINDER_TYPE_HANDLE; else fp->hdr.type = BINDER_TYPE_WEAK_HANDLE; fp->binder = 0; - fp->handle = ref->desc; + fp->handle = rdata.desc; fp->cookie = 0; - binder_inc_ref(ref, fp->hdr.type == BINDER_TYPE_HANDLE, &thread->todo); - trace_binder_transaction_node_to_ref(t, node, ref); + trace_binder_transaction_node_to_ref(t, node, &rdata); binder_debug(BINDER_DEBUG_TRANSACTION, " node %d u%016llx -> ref %d desc %d\n", node->debug_id, (u64)node->ptr, - ref->debug_id, ref->desc); - - return 0; + rdata.debug_id, rdata.desc); +done: + binder_put_node(node); + return ret; } static int binder_translate_handle(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) { - struct binder_ref *ref; struct binder_proc *proc = thread->proc; struct binder_proc *target_proc = t->to_proc; + struct binder_node *node; + struct binder_ref_data src_rdata; + int ret = 0; - ref = binder_get_ref(proc, fp->handle, - fp->hdr.type == BINDER_TYPE_HANDLE); - if (!ref) { + node = binder_get_node_from_ref(proc, fp->handle, + fp->hdr.type == BINDER_TYPE_HANDLE, &src_rdata); + if (!node) { binder_user_error("%d:%d got transaction with invalid handle, %d\n", proc->pid, thread->pid, fp->handle); return -EINVAL; } - if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) - return -EPERM; + if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + ret = -EPERM; + goto done; + } - if (ref->node->proc == target_proc) { + binder_node_lock(node); + if (node->proc == target_proc) { if (fp->hdr.type == BINDER_TYPE_HANDLE) fp->hdr.type = BINDER_TYPE_BINDER; else fp->hdr.type = BINDER_TYPE_WEAK_BINDER; - fp->binder = ref->node->ptr; - fp->cookie = ref->node->cookie; - binder_inc_node(ref->node, fp->hdr.type == BINDER_TYPE_BINDER, - 0, NULL); - trace_binder_transaction_ref_to_node(t, ref); + fp->binder = node->ptr; + fp->cookie = node->cookie; + if (node->proc) + binder_inner_proc_lock(node->proc); + binder_inc_node_nilocked(node, + fp->hdr.type == BINDER_TYPE_BINDER, + 0, NULL); + if (node->proc) + binder_inner_proc_unlock(node->proc); + trace_binder_transaction_ref_to_node(t, node, &src_rdata); binder_debug(BINDER_DEBUG_TRANSACTION, " ref %d desc %d -> node %d u%016llx\n", - ref->debug_id, ref->desc, ref->node->debug_id, - (u64)ref->node->ptr); + src_rdata.debug_id, src_rdata.desc, node->debug_id, + (u64)node->ptr); + binder_node_unlock(node); } else { - struct binder_ref *new_ref; + int ret; + struct binder_ref_data dest_rdata; - new_ref = binder_get_ref_for_node(target_proc, ref->node); - if (!new_ref) - return -EINVAL; + binder_node_unlock(node); + ret = binder_inc_ref_for_node(target_proc, node, + fp->hdr.type == BINDER_TYPE_HANDLE, + NULL, &dest_rdata); + if (ret) + goto done; fp->binder = 0; - fp->handle = new_ref->desc; + fp->handle = dest_rdata.desc; fp->cookie = 0; - binder_inc_ref(new_ref, fp->hdr.type == BINDER_TYPE_HANDLE, - NULL); - trace_binder_transaction_ref_to_ref(t, ref, new_ref); + trace_binder_transaction_ref_to_ref(t, node, &src_rdata, + &dest_rdata); binder_debug(BINDER_DEBUG_TRANSACTION, " ref %d desc %d -> ref %d desc %d (node %d)\n", - ref->debug_id, ref->desc, new_ref->debug_id, - new_ref->desc, ref->node->debug_id); + src_rdata.debug_id, src_rdata.desc, + dest_rdata.debug_id, dest_rdata.desc, + node->debug_id); } - return 0; +done: + binder_put_node(node); + return ret; } static int binder_translate_fd(int fd, @@ -1750,7 +2308,8 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, * Since the parent was already fixed up, convert it * back to the kernel address space to access it */ - parent_buffer = parent->buffer - target_proc->user_buffer_offset; + parent_buffer = parent->buffer - + binder_alloc_get_user_buffer_offset(&target_proc->alloc); fd_array = (u32 *)(parent_buffer + fda->parent_offset); if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) { binder_user_error("%d:%d parent offset not aligned correctly.\n", @@ -1818,7 +2377,8 @@ static int binder_fixup_parent(struct binder_transaction *t, return -EINVAL; } parent_buffer = (u8 *)(parent->buffer - - target_proc->user_buffer_offset); + binder_alloc_get_user_buffer_offset( + &target_proc->alloc)); *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer; return 0; @@ -1835,19 +2395,23 @@ static void binder_transaction(struct binder_proc *proc, binder_size_t *offp, *off_end, *off_start; binder_size_t off_min; u8 *sg_bufp, *sg_buf_end; - struct binder_proc *target_proc; + struct binder_proc *target_proc = NULL; struct binder_thread *target_thread = NULL; struct binder_node *target_node = NULL; struct list_head *target_list; wait_queue_head_t *target_wait; struct binder_transaction *in_reply_to = NULL; struct binder_transaction_log_entry *e; - uint32_t return_error; + uint32_t return_error = 0; + uint32_t return_error_param = 0; + uint32_t return_error_line = 0; struct binder_buffer_object *last_fixup_obj = NULL; binder_size_t last_fixup_min_off = 0; struct binder_context *context = proc->context; + int t_debug_id = atomic_inc_return(&binder_last_id); e = binder_transaction_log_add(&binder_transaction_log); + e->debug_id = t_debug_id; e->call_type = reply ? 2 : !!(tr->flags & TF_ONE_WAY); e->from_proc = proc->pid; e->from_thread = thread->pid; @@ -1857,29 +2421,40 @@ static void binder_transaction(struct binder_proc *proc, e->context_name = proc->context->name; if (reply) { + binder_inner_proc_lock(proc); in_reply_to = thread->transaction_stack; if (in_reply_to == NULL) { + binder_inner_proc_unlock(proc); binder_user_error("%d:%d got reply transaction with no transaction stack\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; goto err_empty_call_stack; } - binder_set_nice(in_reply_to->saved_priority); if (in_reply_to->to_thread != thread) { + spin_lock(&in_reply_to->lock); binder_user_error("%d:%d got reply transaction with bad transaction stack, transaction %d has target %d:%d\n", proc->pid, thread->pid, in_reply_to->debug_id, in_reply_to->to_proc ? in_reply_to->to_proc->pid : 0, in_reply_to->to_thread ? in_reply_to->to_thread->pid : 0); + spin_unlock(&in_reply_to->lock); + binder_inner_proc_unlock(proc); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; in_reply_to = NULL; goto err_bad_call_stack; } thread->transaction_stack = in_reply_to->to_parent; - target_thread = in_reply_to->from; + binder_inner_proc_unlock(proc); + binder_set_nice(in_reply_to->saved_priority); + target_thread = binder_get_txn_from_and_acq_inner(in_reply_to); if (target_thread == NULL) { return_error = BR_DEAD_REPLY; + return_error_line = __LINE__; goto err_dead_binder; } if (target_thread->transaction_stack != in_reply_to) { @@ -1888,61 +2463,111 @@ static void binder_transaction(struct binder_proc *proc, target_thread->transaction_stack ? target_thread->transaction_stack->debug_id : 0, in_reply_to->debug_id); + binder_inner_proc_unlock(target_thread->proc); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; in_reply_to = NULL; target_thread = NULL; goto err_dead_binder; } target_proc = target_thread->proc; + target_proc->tmp_ref++; + binder_inner_proc_unlock(target_thread->proc); } else { if (tr->target.handle) { struct binder_ref *ref; - ref = binder_get_ref(proc, tr->target.handle, true); - if (ref == NULL) { + /* + * There must already be a strong ref + * on this node. If so, do a strong + * increment on the node to ensure it + * stays alive until the transaction is + * done. + */ + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, tr->target.handle, + true); + if (ref) { + binder_inc_node(ref->node, 1, 0, NULL); + target_node = ref->node; + } + binder_proc_unlock(proc); + if (target_node == NULL) { binder_user_error("%d:%d got transaction to invalid handle\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_invalid_target_handle; } - target_node = ref->node; } else { + mutex_lock(&context->context_mgr_node_lock); target_node = context->binder_context_mgr_node; if (target_node == NULL) { return_error = BR_DEAD_REPLY; + mutex_unlock(&context->context_mgr_node_lock); + return_error_line = __LINE__; goto err_no_context_mgr_node; } + binder_inc_node(target_node, 1, 0, NULL); + mutex_unlock(&context->context_mgr_node_lock); } e->to_node = target_node->debug_id; + binder_node_lock(target_node); target_proc = target_node->proc; if (target_proc == NULL) { + binder_node_unlock(target_node); return_error = BR_DEAD_REPLY; + return_error_line = __LINE__; goto err_dead_binder; } + binder_inner_proc_lock(target_proc); + target_proc->tmp_ref++; + binder_inner_proc_unlock(target_proc); + binder_node_unlock(target_node); if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) { return_error = BR_FAILED_REPLY; + return_error_param = -EPERM; + return_error_line = __LINE__; goto err_invalid_target_handle; } + binder_inner_proc_lock(proc); if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) { struct binder_transaction *tmp; tmp = thread->transaction_stack; if (tmp->to_thread != thread) { + spin_lock(&tmp->lock); binder_user_error("%d:%d got new transaction with bad transaction stack, transaction %d has target %d:%d\n", proc->pid, thread->pid, tmp->debug_id, tmp->to_proc ? tmp->to_proc->pid : 0, tmp->to_thread ? tmp->to_thread->pid : 0); + spin_unlock(&tmp->lock); + binder_inner_proc_unlock(proc); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; goto err_bad_call_stack; } while (tmp) { - if (tmp->from && tmp->from->proc == target_proc) - target_thread = tmp->from; + struct binder_thread *from; + + spin_lock(&tmp->lock); + from = tmp->from; + if (from && from->proc == target_proc) { + atomic_inc(&from->tmp_ref); + target_thread = from; + spin_unlock(&tmp->lock); + break; + } + spin_unlock(&tmp->lock); tmp = tmp->from_parent; } } + binder_inner_proc_unlock(proc); } if (target_thread) { e->to_thread = target_thread->pid; @@ -1958,19 +2583,23 @@ static void binder_transaction(struct binder_proc *proc, t = kzalloc(sizeof(*t), GFP_KERNEL); if (t == NULL) { return_error = BR_FAILED_REPLY; + return_error_param = -ENOMEM; + return_error_line = __LINE__; goto err_alloc_t_failed; } binder_stats_created(BINDER_STAT_TRANSACTION); + spin_lock_init(&t->lock); tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL); if (tcomplete == NULL) { return_error = BR_FAILED_REPLY; + return_error_param = -ENOMEM; + return_error_line = __LINE__; goto err_alloc_tcomplete_failed; } binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE); - t->debug_id = ++binder_last_id; - e->debug_id = t->debug_id; + t->debug_id = t_debug_id; if (reply) binder_debug(BINDER_DEBUG_TRANSACTION, @@ -2004,11 +2633,18 @@ static void binder_transaction(struct binder_proc *proc, trace_binder_transaction(reply, t, target_node); - t->buffer = binder_alloc_buf(target_proc, tr->data_size, + t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size, tr->offsets_size, extra_buffers_size, !reply && (t->flags & TF_ONE_WAY)); - if (t->buffer == NULL) { - return_error = BR_FAILED_REPLY; + if (IS_ERR(t->buffer)) { + /* + * -ESRCH indicates VMA cleared. The target is dying. + */ + return_error_param = PTR_ERR(t->buffer); + return_error = return_error_param == -ESRCH ? + BR_DEAD_REPLY : BR_FAILED_REPLY; + return_error_line = __LINE__; + t->buffer = NULL; goto err_binder_alloc_buf_failed; } t->buffer->allow_user_free = 0; @@ -2016,9 +2652,6 @@ static void binder_transaction(struct binder_proc *proc, t->buffer->transaction = t; t->buffer->target_node = target_node; trace_binder_transaction_alloc_buf(t->buffer); - if (target_node) - binder_inc_node(target_node, 1, 0, NULL); - off_start = (binder_size_t *)(t->buffer->data + ALIGN(tr->data_size, sizeof(void *))); offp = off_start; @@ -2028,6 +2661,8 @@ static void binder_transaction(struct binder_proc *proc, binder_user_error("%d:%d got transaction with invalid data ptr\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EFAULT; + return_error_line = __LINE__; goto err_copy_data_failed; } if (copy_from_user(offp, (const void __user *)(uintptr_t) @@ -2035,12 +2670,16 @@ static void binder_transaction(struct binder_proc *proc, binder_user_error("%d:%d got transaction with invalid offsets ptr\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EFAULT; + return_error_line = __LINE__; goto err_copy_data_failed; } if (!IS_ALIGNED(tr->offsets_size, sizeof(binder_size_t))) { binder_user_error("%d:%d got transaction with invalid offsets size, %lld\n", proc->pid, thread->pid, (u64)tr->offsets_size); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_offset; } if (!IS_ALIGNED(extra_buffers_size, sizeof(u64))) { @@ -2048,6 +2687,8 @@ static void binder_transaction(struct binder_proc *proc, proc->pid, thread->pid, (u64)extra_buffers_size); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_offset; } off_end = (void *)off_start + tr->offsets_size; @@ -2064,6 +2705,8 @@ static void binder_transaction(struct binder_proc *proc, (u64)off_min, (u64)t->buffer->data_size); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_offset; } @@ -2078,6 +2721,8 @@ static void binder_transaction(struct binder_proc *proc, ret = binder_translate_binder(fp, t, thread); if (ret < 0) { return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; goto err_translate_failed; } } break; @@ -2089,6 +2734,8 @@ static void binder_transaction(struct binder_proc *proc, ret = binder_translate_handle(fp, t, thread); if (ret < 0) { return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; goto err_translate_failed; } } break; @@ -2100,6 +2747,8 @@ static void binder_transaction(struct binder_proc *proc, if (target_fd < 0) { return_error = BR_FAILED_REPLY; + return_error_param = target_fd; + return_error_line = __LINE__; goto err_translate_failed; } fp->pad_binder = 0; @@ -2116,6 +2765,8 @@ static void binder_transaction(struct binder_proc *proc, binder_user_error("%d:%d got transaction with invalid parent offset or type\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_parent; } if (!binder_validate_fixup(t->buffer, off_start, @@ -2125,12 +2776,16 @@ static void binder_transaction(struct binder_proc *proc, binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_parent; } ret = binder_translate_fd_array(fda, parent, t, thread, in_reply_to); if (ret < 0) { return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; goto err_translate_failed; } last_fixup_obj = parent; @@ -2146,6 +2801,8 @@ static void binder_transaction(struct binder_proc *proc, binder_user_error("%d:%d got transaction with too large buffer\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_offset; } if (copy_from_user(sg_bufp, @@ -2153,12 +2810,15 @@ static void binder_transaction(struct binder_proc *proc, bp->buffer, bp->length)) { binder_user_error("%d:%d got transaction with invalid offsets ptr\n", proc->pid, thread->pid); + return_error_param = -EFAULT; return_error = BR_FAILED_REPLY; + return_error_line = __LINE__; goto err_copy_data_failed; } /* Fixup buffer pointer to target proc address space */ bp->buffer = (uintptr_t)sg_bufp + - target_proc->user_buffer_offset; + binder_alloc_get_user_buffer_offset( + &target_proc->alloc); sg_bufp += ALIGN(bp->length, sizeof(u64)); ret = binder_fixup_parent(t, thread, bp, off_start, @@ -2167,6 +2827,8 @@ static void binder_transaction(struct binder_proc *proc, last_fixup_min_off); if (ret < 0) { return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; goto err_translate_failed; } last_fixup_obj = bp; @@ -2176,38 +2838,89 @@ static void binder_transaction(struct binder_proc *proc, binder_user_error("%d:%d got transaction with invalid object type, %x\n", proc->pid, thread->pid, hdr->type); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_object_type; } } + tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; + binder_enqueue_work(proc, tcomplete, &thread->todo); + t->work.type = BINDER_WORK_TRANSACTION; + if (reply) { + binder_inner_proc_lock(target_proc); + if (target_thread->is_dead) { + binder_inner_proc_unlock(target_proc); + goto err_dead_proc_or_thread; + } BUG_ON(t->buffer->async_transaction != 0); - binder_pop_transaction(target_thread, in_reply_to); + binder_pop_transaction_ilocked(target_thread, in_reply_to); + binder_enqueue_work_ilocked(&t->work, target_list); + binder_inner_proc_unlock(target_proc); + binder_free_transaction(in_reply_to); } else if (!(t->flags & TF_ONE_WAY)) { BUG_ON(t->buffer->async_transaction != 0); + binder_inner_proc_lock(proc); t->need_reply = 1; t->from_parent = thread->transaction_stack; thread->transaction_stack = t; + binder_inner_proc_unlock(proc); + binder_inner_proc_lock(target_proc); + if (target_proc->is_dead || + (target_thread && target_thread->is_dead)) { + binder_inner_proc_unlock(target_proc); + binder_inner_proc_lock(proc); + binder_pop_transaction_ilocked(thread, t); + binder_inner_proc_unlock(proc); + goto err_dead_proc_or_thread; + } + binder_enqueue_work_ilocked(&t->work, target_list); + binder_inner_proc_unlock(target_proc); } else { BUG_ON(target_node == NULL); BUG_ON(t->buffer->async_transaction != 1); + binder_node_lock(target_node); if (target_node->has_async_transaction) { target_list = &target_node->async_todo; target_wait = NULL; } else target_node->has_async_transaction = 1; + /* + * Test/set of has_async_transaction + * must be atomic with enqueue on + * async_todo + */ + binder_inner_proc_lock(target_proc); + if (target_proc->is_dead || + (target_thread && target_thread->is_dead)) { + binder_inner_proc_unlock(target_proc); + binder_node_unlock(target_node); + goto err_dead_proc_or_thread; + } + binder_enqueue_work_ilocked(&t->work, target_list); + binder_inner_proc_unlock(target_proc); + binder_node_unlock(target_node); } - t->work.type = BINDER_WORK_TRANSACTION; - list_add_tail(&t->work.entry, target_list); - tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; - list_add_tail(&tcomplete->entry, &thread->todo); if (target_wait) { - if (reply || !(t->flags & TF_ONE_WAY)) + if (reply || !(tr->flags & TF_ONE_WAY)) wake_up_interruptible_sync(target_wait); else wake_up_interruptible(target_wait); } + if (target_thread) + binder_thread_dec_tmpref(target_thread); + binder_proc_dec_tmpref(target_proc); + /* + * write barrier to synchronize with initialization + * of log entry + */ + smp_wmb(); + WRITE_ONCE(e->debug_id_done, t_debug_id); return; +err_dead_proc_or_thread: + return_error = BR_DEAD_REPLY; + return_error_line = __LINE__; err_translate_failed: err_bad_object_type: err_bad_offset: @@ -2215,8 +2928,9 @@ err_bad_parent: err_copy_data_failed: trace_binder_transaction_failed_buffer_release(t->buffer); binder_transaction_buffer_release(target_proc, t->buffer, offp); + target_node = NULL; t->buffer->transaction = NULL; - binder_free_buf(target_proc, t->buffer); + binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); @@ -2229,24 +2943,49 @@ err_empty_call_stack: err_dead_binder: err_invalid_target_handle: err_no_context_mgr_node: + if (target_thread) + binder_thread_dec_tmpref(target_thread); + if (target_proc) + binder_proc_dec_tmpref(target_proc); + if (target_node) + binder_dec_node(target_node, 1, 0); + binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "%d:%d transaction failed %d, size %lld-%lld\n", - proc->pid, thread->pid, return_error, - (u64)tr->data_size, (u64)tr->offsets_size); + "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n", + proc->pid, thread->pid, return_error, return_error_param, + (u64)tr->data_size, (u64)tr->offsets_size, + return_error_line); { struct binder_transaction_log_entry *fe; + e->return_error = return_error; + e->return_error_param = return_error_param; + e->return_error_line = return_error_line; fe = binder_transaction_log_add(&binder_transaction_log_failed); *fe = *e; + /* + * write barrier to synchronize with initialization + * of log entry + */ + smp_wmb(); + WRITE_ONCE(e->debug_id_done, t_debug_id); + WRITE_ONCE(fe->debug_id_done, t_debug_id); } - BUG_ON(thread->return_error != BR_OK); + BUG_ON(thread->return_error.cmd != BR_OK); if (in_reply_to) { - thread->return_error = BR_TRANSACTION_COMPLETE; + thread->return_error.cmd = BR_TRANSACTION_COMPLETE; + binder_enqueue_work(thread->proc, + &thread->return_error.work, + &thread->todo); binder_send_failed_reply(in_reply_to, return_error); - } else - thread->return_error = return_error; + } else { + thread->return_error.cmd = return_error; + binder_enqueue_work(thread->proc, + &thread->return_error.work, + &thread->todo); + } } static int binder_thread_write(struct binder_proc *proc, @@ -2260,15 +2999,17 @@ static int binder_thread_write(struct binder_proc *proc, void __user *ptr = buffer + *consumed; void __user *end = buffer + size; - while (ptr < end && thread->return_error == BR_OK) { + while (ptr < end && thread->return_error.cmd == BR_OK) { + int ret; + if (get_user(cmd, (uint32_t __user *)ptr)) return -EFAULT; ptr += sizeof(uint32_t); trace_binder_command(cmd); if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) { - binder_stats.bc[_IOC_NR(cmd)]++; - proc->stats.bc[_IOC_NR(cmd)]++; - thread->stats.bc[_IOC_NR(cmd)]++; + atomic_inc(&binder_stats.bc[_IOC_NR(cmd)]); + atomic_inc(&proc->stats.bc[_IOC_NR(cmd)]); + atomic_inc(&thread->stats.bc[_IOC_NR(cmd)]); } switch (cmd) { case BC_INCREFS: @@ -2276,53 +3017,61 @@ static int binder_thread_write(struct binder_proc *proc, case BC_RELEASE: case BC_DECREFS: { uint32_t target; - struct binder_ref *ref; const char *debug_string; + bool strong = cmd == BC_ACQUIRE || cmd == BC_RELEASE; + bool increment = cmd == BC_INCREFS || cmd == BC_ACQUIRE; + struct binder_ref_data rdata; if (get_user(target, (uint32_t __user *)ptr)) return -EFAULT; + ptr += sizeof(uint32_t); - if (target == 0 && context->binder_context_mgr_node && - (cmd == BC_INCREFS || cmd == BC_ACQUIRE)) { - ref = binder_get_ref_for_node(proc, - context->binder_context_mgr_node); - if (ref->desc != target) { - binder_user_error("%d:%d tried to acquire reference to desc 0, got %d instead\n", - proc->pid, thread->pid, - ref->desc); - } - } else - ref = binder_get_ref(proc, target, - cmd == BC_ACQUIRE || - cmd == BC_RELEASE); - if (ref == NULL) { - binder_user_error("%d:%d refcount change on invalid ref %d\n", - proc->pid, thread->pid, target); - break; + ret = -1; + if (increment && !target) { + struct binder_node *ctx_mgr_node; + mutex_lock(&context->context_mgr_node_lock); + ctx_mgr_node = context->binder_context_mgr_node; + if (ctx_mgr_node) + ret = binder_inc_ref_for_node( + proc, ctx_mgr_node, + strong, NULL, &rdata); + mutex_unlock(&context->context_mgr_node_lock); + } + if (ret) + ret = binder_update_ref_for_handle( + proc, target, increment, strong, + &rdata); + if (!ret && rdata.desc != target) { + binder_user_error("%d:%d tried to acquire reference to desc %d, got %d instead\n", + proc->pid, thread->pid, + target, rdata.desc); } switch (cmd) { case BC_INCREFS: debug_string = "IncRefs"; - binder_inc_ref(ref, 0, NULL); break; case BC_ACQUIRE: debug_string = "Acquire"; - binder_inc_ref(ref, 1, NULL); break; case BC_RELEASE: debug_string = "Release"; - binder_dec_ref(ref, 1); break; case BC_DECREFS: default: debug_string = "DecRefs"; - binder_dec_ref(ref, 0); + break; + } + if (ret) { + binder_user_error("%d:%d %s %d refcount change on invalid ref %d ret %d\n", + proc->pid, thread->pid, debug_string, + strong, target, ret); break; } binder_debug(BINDER_DEBUG_USER_REFS, - "%d:%d %s ref %d desc %d s %d w %d for node %d\n", - proc->pid, thread->pid, debug_string, ref->debug_id, - ref->desc, ref->strong, ref->weak, ref->node->debug_id); + "%d:%d %s ref %d desc %d s %d w %d\n", + proc->pid, thread->pid, debug_string, + rdata.debug_id, rdata.desc, rdata.strong, + rdata.weak); break; } case BC_INCREFS_DONE: @@ -2330,6 +3079,7 @@ static int binder_thread_write(struct binder_proc *proc, binder_uintptr_t node_ptr; binder_uintptr_t cookie; struct binder_node *node; + bool free_node; if (get_user(node_ptr, (binder_uintptr_t __user *)ptr)) return -EFAULT; @@ -2354,13 +3104,17 @@ static int binder_thread_write(struct binder_proc *proc, "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE", (u64)node_ptr, node->debug_id, (u64)cookie, (u64)node->cookie); + binder_put_node(node); break; } + binder_node_inner_lock(node); if (cmd == BC_ACQUIRE_DONE) { if (node->pending_strong_ref == 0) { binder_user_error("%d:%d BC_ACQUIRE_DONE node %d has no pending acquire request\n", proc->pid, thread->pid, node->debug_id); + binder_node_inner_unlock(node); + binder_put_node(node); break; } node->pending_strong_ref = 0; @@ -2369,16 +3123,23 @@ static int binder_thread_write(struct binder_proc *proc, binder_user_error("%d:%d BC_INCREFS_DONE node %d has no pending increfs request\n", proc->pid, thread->pid, node->debug_id); + binder_node_inner_unlock(node); + binder_put_node(node); break; } node->pending_weak_ref = 0; } - binder_dec_node(node, cmd == BC_ACQUIRE_DONE, 0); + free_node = binder_dec_node_nilocked(node, + cmd == BC_ACQUIRE_DONE, 0); + WARN_ON(free_node); binder_debug(BINDER_DEBUG_USER_REFS, - "%d:%d %s node %d ls %d lw %d\n", + "%d:%d %s node %d ls %d lw %d tr %d\n", proc->pid, thread->pid, cmd == BC_INCREFS_DONE ? "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE", - node->debug_id, node->local_strong_refs, node->local_weak_refs); + node->debug_id, node->local_strong_refs, + node->local_weak_refs, node->tmp_refs); + binder_node_inner_unlock(node); + binder_put_node(node); break; } case BC_ATTEMPT_ACQUIRE: @@ -2396,7 +3157,8 @@ static int binder_thread_write(struct binder_proc *proc, return -EFAULT; ptr += sizeof(binder_uintptr_t); - buffer = binder_buffer_lookup(proc, data_ptr); + buffer = binder_alloc_prepare_to_free(&proc->alloc, + data_ptr); if (buffer == NULL) { binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n", proc->pid, thread->pid, (u64)data_ptr); @@ -2418,15 +3180,25 @@ static int binder_thread_write(struct binder_proc *proc, buffer->transaction = NULL; } if (buffer->async_transaction && buffer->target_node) { - BUG_ON(!buffer->target_node->has_async_transaction); - if (list_empty(&buffer->target_node->async_todo)) - buffer->target_node->has_async_transaction = 0; + struct binder_node *buf_node; + struct binder_work *w; + + buf_node = buffer->target_node; + binder_node_inner_lock(buf_node); + BUG_ON(!buf_node->has_async_transaction); + BUG_ON(buf_node->proc != proc); + w = binder_dequeue_work_head_ilocked( + &buf_node->async_todo); + if (!w) + buf_node->has_async_transaction = 0; else - list_move_tail(buffer->target_node->async_todo.next, &thread->todo); + binder_enqueue_work_ilocked( + w, &thread->todo); + binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); binder_transaction_buffer_release(proc, buffer, NULL); - binder_free_buf(proc, buffer); + binder_alloc_free_buf(&proc->alloc, buffer); break; } @@ -2457,6 +3229,7 @@ static int binder_thread_write(struct binder_proc *proc, binder_debug(BINDER_DEBUG_THREADS, "%d:%d BC_REGISTER_LOOPER\n", proc->pid, thread->pid); + binder_inner_proc_lock(proc); if (thread->looper & BINDER_LOOPER_STATE_ENTERED) { thread->looper |= BINDER_LOOPER_STATE_INVALID; binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called after BC_ENTER_LOOPER\n", @@ -2470,6 +3243,7 @@ static int binder_thread_write(struct binder_proc *proc, proc->requested_threads_started++; } thread->looper |= BINDER_LOOPER_STATE_REGISTERED; + binder_inner_proc_unlock(proc); break; case BC_ENTER_LOOPER: binder_debug(BINDER_DEBUG_THREADS, @@ -2494,7 +3268,7 @@ static int binder_thread_write(struct binder_proc *proc, uint32_t target; binder_uintptr_t cookie; struct binder_ref *ref; - struct binder_ref_death *death; + struct binder_ref_death *death = NULL; if (get_user(target, (uint32_t __user *)ptr)) return -EFAULT; @@ -2502,7 +3276,29 @@ static int binder_thread_write(struct binder_proc *proc, if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; ptr += sizeof(binder_uintptr_t); - ref = binder_get_ref(proc, target, false); + if (cmd == BC_REQUEST_DEATH_NOTIFICATION) { + /* + * Allocate memory for death notification + * before taking lock + */ + death = kzalloc(sizeof(*death), GFP_KERNEL); + if (death == NULL) { + WARN_ON(thread->return_error.cmd != + BR_OK); + thread->return_error.cmd = BR_ERROR; + binder_enqueue_work( + thread->proc, + &thread->return_error.work, + &thread->todo); + binder_debug( + BINDER_DEBUG_FAILED_TRANSACTION, + "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n", + proc->pid, thread->pid); + break; + } + } + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, target, false); if (ref == NULL) { binder_user_error("%d:%d %s invalid ref %d\n", proc->pid, thread->pid, @@ -2510,6 +3306,8 @@ static int binder_thread_write(struct binder_proc *proc, "BC_REQUEST_DEATH_NOTIFICATION" : "BC_CLEAR_DEATH_NOTIFICATION", target); + binder_proc_unlock(proc); + kfree(death); break; } @@ -2519,21 +3317,18 @@ static int binder_thread_write(struct binder_proc *proc, cmd == BC_REQUEST_DEATH_NOTIFICATION ? "BC_REQUEST_DEATH_NOTIFICATION" : "BC_CLEAR_DEATH_NOTIFICATION", - (u64)cookie, ref->debug_id, ref->desc, - ref->strong, ref->weak, ref->node->debug_id); + (u64)cookie, ref->data.debug_id, + ref->data.desc, ref->data.strong, + ref->data.weak, ref->node->debug_id); + binder_node_lock(ref->node); if (cmd == BC_REQUEST_DEATH_NOTIFICATION) { if (ref->death) { binder_user_error("%d:%d BC_REQUEST_DEATH_NOTIFICATION death notification already set\n", proc->pid, thread->pid); - break; - } - death = kzalloc(sizeof(*death), GFP_KERNEL); - if (death == NULL) { - thread->return_error = BR_ERROR; - binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n", - proc->pid, thread->pid); + binder_node_unlock(ref->node); + binder_proc_unlock(proc); + kfree(death); break; } binder_stats_created(BINDER_STAT_DEATH); @@ -2542,17 +3337,28 @@ static int binder_thread_write(struct binder_proc *proc, ref->death = death; if (ref->node->proc == NULL) { ref->death->work.type = BINDER_WORK_DEAD_BINDER; - if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) { - list_add_tail(&ref->death->work.entry, &thread->todo); - } else { - list_add_tail(&ref->death->work.entry, &proc->todo); - wake_up_interruptible(&proc->wait); + if (thread->looper & + (BINDER_LOOPER_STATE_REGISTERED | + BINDER_LOOPER_STATE_ENTERED)) + binder_enqueue_work( + proc, + &ref->death->work, + &thread->todo); + else { + binder_enqueue_work( + proc, + &ref->death->work, + &proc->todo); + wake_up_interruptible( + &proc->wait); } } } else { if (ref->death == NULL) { binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification not active\n", proc->pid, thread->pid); + binder_node_unlock(ref->node); + binder_proc_unlock(proc); break; } death = ref->death; @@ -2561,22 +3367,35 @@ static int binder_thread_write(struct binder_proc *proc, proc->pid, thread->pid, (u64)death->cookie, (u64)cookie); + binder_node_unlock(ref->node); + binder_proc_unlock(proc); break; } ref->death = NULL; + binder_inner_proc_lock(proc); if (list_empty(&death->work.entry)) { death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION; - if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) { - list_add_tail(&death->work.entry, &thread->todo); - } else { - list_add_tail(&death->work.entry, &proc->todo); - wake_up_interruptible(&proc->wait); + if (thread->looper & + (BINDER_LOOPER_STATE_REGISTERED | + BINDER_LOOPER_STATE_ENTERED)) + binder_enqueue_work_ilocked( + &death->work, + &thread->todo); + else { + binder_enqueue_work_ilocked( + &death->work, + &proc->todo); + wake_up_interruptible( + &proc->wait); } } else { BUG_ON(death->work.type != BINDER_WORK_DEAD_BINDER); death->work.type = BINDER_WORK_DEAD_BINDER_AND_CLEAR; } + binder_inner_proc_unlock(proc); } + binder_node_unlock(ref->node); + binder_proc_unlock(proc); } break; case BC_DEAD_BINDER_DONE: { struct binder_work *w; @@ -2587,8 +3406,13 @@ static int binder_thread_write(struct binder_proc *proc, return -EFAULT; ptr += sizeof(cookie); - list_for_each_entry(w, &proc->delivered_death, entry) { - struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); + binder_inner_proc_lock(proc); + list_for_each_entry(w, &proc->delivered_death, + entry) { + struct binder_ref_death *tmp_death = + container_of(w, + struct binder_ref_death, + work); if (tmp_death->cookie == cookie) { death = tmp_death; @@ -2602,19 +3426,25 @@ static int binder_thread_write(struct binder_proc *proc, if (death == NULL) { binder_user_error("%d:%d BC_DEAD_BINDER_DONE %016llx not found\n", proc->pid, thread->pid, (u64)cookie); + binder_inner_proc_unlock(proc); break; } - - list_del_init(&death->work.entry); + binder_dequeue_work_ilocked(&death->work); if (death->work.type == BINDER_WORK_DEAD_BINDER_AND_CLEAR) { death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION; - if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) { - list_add_tail(&death->work.entry, &thread->todo); - } else { - list_add_tail(&death->work.entry, &proc->todo); + if (thread->looper & + (BINDER_LOOPER_STATE_REGISTERED | + BINDER_LOOPER_STATE_ENTERED)) + binder_enqueue_work_ilocked( + &death->work, &thread->todo); + else { + binder_enqueue_work_ilocked( + &death->work, + &proc->todo); wake_up_interruptible(&proc->wait); } } + binder_inner_proc_unlock(proc); } break; default: @@ -2632,23 +3462,54 @@ static void binder_stat_br(struct binder_proc *proc, { trace_binder_return(cmd); if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) { - binder_stats.br[_IOC_NR(cmd)]++; - proc->stats.br[_IOC_NR(cmd)]++; - thread->stats.br[_IOC_NR(cmd)]++; + atomic_inc(&binder_stats.br[_IOC_NR(cmd)]); + atomic_inc(&proc->stats.br[_IOC_NR(cmd)]); + atomic_inc(&thread->stats.br[_IOC_NR(cmd)]); } } static int binder_has_proc_work(struct binder_proc *proc, struct binder_thread *thread) { - return !list_empty(&proc->todo) || - (thread->looper & BINDER_LOOPER_STATE_NEED_RETURN); + return !binder_worklist_empty(proc, &proc->todo) || + thread->looper_need_return; } static int binder_has_thread_work(struct binder_thread *thread) { - return !list_empty(&thread->todo) || thread->return_error != BR_OK || - (thread->looper & BINDER_LOOPER_STATE_NEED_RETURN); + return !binder_worklist_empty(thread->proc, &thread->todo) || + thread->looper_need_return; +} + +static int binder_put_node_cmd(struct binder_proc *proc, + struct binder_thread *thread, + void __user **ptrp, + binder_uintptr_t node_ptr, + binder_uintptr_t node_cookie, + int node_debug_id, + uint32_t cmd, const char *cmd_name) +{ + void __user *ptr = *ptrp; + + if (put_user(cmd, (uint32_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(uint32_t); + + if (put_user(node_ptr, (binder_uintptr_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(binder_uintptr_t); + + if (put_user(node_cookie, (binder_uintptr_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(binder_uintptr_t); + + binder_stat_br(proc, thread, cmd); + binder_debug(BINDER_DEBUG_USER_REFS, "%d:%d %s %d u%016llx c%016llx\n", + proc->pid, thread->pid, cmd_name, node_debug_id, + (u64)node_ptr, (u64)node_cookie); + + *ptrp = ptr; + return 0; } static int binder_thread_read(struct binder_proc *proc, @@ -2670,37 +3531,18 @@ static int binder_thread_read(struct binder_proc *proc, } retry: + binder_inner_proc_lock(proc); wait_for_proc_work = thread->transaction_stack == NULL && - list_empty(&thread->todo); - - if (thread->return_error != BR_OK && ptr < end) { - if (thread->return_error2 != BR_OK) { - if (put_user(thread->return_error2, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - binder_stat_br(proc, thread, thread->return_error2); - if (ptr == end) - goto done; - thread->return_error2 = BR_OK; - } - if (put_user(thread->return_error, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - binder_stat_br(proc, thread, thread->return_error); - thread->return_error = BR_OK; - goto done; - } - - - thread->looper |= BINDER_LOOPER_STATE_WAITING; + binder_worklist_empty_ilocked(&thread->todo); if (wait_for_proc_work) proc->ready_threads++; + binder_inner_proc_unlock(proc); - binder_unlock(__func__); + thread->looper |= BINDER_LOOPER_STATE_WAITING; trace_binder_wait_for_work(wait_for_proc_work, !!thread->transaction_stack, - !list_empty(&thread->todo)); + !binder_worklist_empty(proc, &thread->todo)); if (wait_for_proc_work) { if (!(thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED))) { @@ -2723,10 +3565,10 @@ retry: ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread)); } - binder_lock(__func__); - + binder_inner_proc_lock(proc); if (wait_for_proc_work) proc->ready_threads--; + binder_inner_proc_unlock(proc); thread->looper &= ~BINDER_LOOPER_STATE_WAITING; if (ret) @@ -2735,31 +3577,52 @@ retry: while (1) { uint32_t cmd; struct binder_transaction_data tr; - struct binder_work *w; + struct binder_work *w = NULL; + struct list_head *list = NULL; struct binder_transaction *t = NULL; + struct binder_thread *t_from; + + binder_inner_proc_lock(proc); + if (!binder_worklist_empty_ilocked(&thread->todo)) + list = &thread->todo; + else if (!binder_worklist_empty_ilocked(&proc->todo) && + wait_for_proc_work) + list = &proc->todo; + else { + binder_inner_proc_unlock(proc); - if (!list_empty(&thread->todo)) { - w = list_first_entry(&thread->todo, struct binder_work, - entry); - } else if (!list_empty(&proc->todo) && wait_for_proc_work) { - w = list_first_entry(&proc->todo, struct binder_work, - entry); - } else { /* no data added */ - if (ptr - buffer == 4 && - !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN)) + if (ptr - buffer == 4 && !thread->looper_need_return) goto retry; break; } - if (end - ptr < sizeof(tr) + 4) + if (end - ptr < sizeof(tr) + 4) { + binder_inner_proc_unlock(proc); break; + } + w = binder_dequeue_work_head_ilocked(list); switch (w->type) { case BINDER_WORK_TRANSACTION: { + binder_inner_proc_unlock(proc); t = container_of(w, struct binder_transaction, work); } break; + case BINDER_WORK_RETURN_ERROR: { + struct binder_error *e = container_of( + w, struct binder_error, work); + + WARN_ON(e->cmd == BR_OK); + binder_inner_proc_unlock(proc); + if (put_user(e->cmd, (uint32_t __user *)ptr)) + return -EFAULT; + e->cmd = BR_OK; + ptr += sizeof(uint32_t); + + binder_stat_br(proc, thread, e->cmd); + } break; case BINDER_WORK_TRANSACTION_COMPLETE: { + binder_inner_proc_unlock(proc); cmd = BR_TRANSACTION_COMPLETE; if (put_user(cmd, (uint32_t __user *)ptr)) return -EFAULT; @@ -2769,113 +3632,134 @@ retry: binder_debug(BINDER_DEBUG_TRANSACTION_COMPLETE, "%d:%d BR_TRANSACTION_COMPLETE\n", proc->pid, thread->pid); - - list_del(&w->entry); kfree(w); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); } break; case BINDER_WORK_NODE: { struct binder_node *node = container_of(w, struct binder_node, work); - uint32_t cmd = BR_NOOP; - const char *cmd_name; - int strong = node->internal_strong_refs || node->local_strong_refs; - int weak = !hlist_empty(&node->refs) || node->local_weak_refs || strong; - - if (weak && !node->has_weak_ref) { - cmd = BR_INCREFS; - cmd_name = "BR_INCREFS"; + int strong, weak; + binder_uintptr_t node_ptr = node->ptr; + binder_uintptr_t node_cookie = node->cookie; + int node_debug_id = node->debug_id; + int has_weak_ref; + int has_strong_ref; + void __user *orig_ptr = ptr; + + BUG_ON(proc != node->proc); + strong = node->internal_strong_refs || + node->local_strong_refs; + weak = !hlist_empty(&node->refs) || + node->local_weak_refs || + node->tmp_refs || strong; + has_strong_ref = node->has_strong_ref; + has_weak_ref = node->has_weak_ref; + + if (weak && !has_weak_ref) { node->has_weak_ref = 1; node->pending_weak_ref = 1; node->local_weak_refs++; - } else if (strong && !node->has_strong_ref) { - cmd = BR_ACQUIRE; - cmd_name = "BR_ACQUIRE"; + } + if (strong && !has_strong_ref) { node->has_strong_ref = 1; node->pending_strong_ref = 1; node->local_strong_refs++; - } else if (!strong && node->has_strong_ref) { - cmd = BR_RELEASE; - cmd_name = "BR_RELEASE"; + } + if (!strong && has_strong_ref) node->has_strong_ref = 0; - } else if (!weak && node->has_weak_ref) { - cmd = BR_DECREFS; - cmd_name = "BR_DECREFS"; + if (!weak && has_weak_ref) node->has_weak_ref = 0; - } - if (cmd != BR_NOOP) { - if (put_user(cmd, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - if (put_user(node->ptr, - (binder_uintptr_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(binder_uintptr_t); - if (put_user(node->cookie, - (binder_uintptr_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(binder_uintptr_t); - - binder_stat_br(proc, thread, cmd); - binder_debug(BINDER_DEBUG_USER_REFS, - "%d:%d %s %d u%016llx c%016llx\n", - proc->pid, thread->pid, cmd_name, - node->debug_id, - (u64)node->ptr, (u64)node->cookie); - } else { - list_del_init(&w->entry); - if (!weak && !strong) { - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d:%d node %d u%016llx c%016llx deleted\n", - proc->pid, thread->pid, - node->debug_id, - (u64)node->ptr, - (u64)node->cookie); - rb_erase(&node->rb_node, &proc->nodes); - kfree(node); - binder_stats_deleted(BINDER_STAT_NODE); - } else { - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d:%d node %d u%016llx c%016llx state unchanged\n", - proc->pid, thread->pid, - node->debug_id, - (u64)node->ptr, - (u64)node->cookie); - } - } + if (!weak && !strong) { + binder_debug(BINDER_DEBUG_INTERNAL_REFS, + "%d:%d node %d u%016llx c%016llx deleted\n", + proc->pid, thread->pid, + node_debug_id, + (u64)node_ptr, + (u64)node_cookie); + rb_erase(&node->rb_node, &proc->nodes); + binder_inner_proc_unlock(proc); + binder_node_lock(node); + /* + * Acquire the node lock before freeing the + * node to serialize with other threads that + * may have been holding the node lock while + * decrementing this node (avoids race where + * this thread frees while the other thread + * is unlocking the node after the final + * decrement) + */ + binder_node_unlock(node); + binder_free_node(node); + } else + binder_inner_proc_unlock(proc); + + if (weak && !has_weak_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_INCREFS, "BR_INCREFS"); + if (!ret && strong && !has_strong_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_ACQUIRE, "BR_ACQUIRE"); + if (!ret && !strong && has_strong_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_RELEASE, "BR_RELEASE"); + if (!ret && !weak && has_weak_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_DECREFS, "BR_DECREFS"); + if (orig_ptr == ptr) + binder_debug(BINDER_DEBUG_INTERNAL_REFS, + "%d:%d node %d u%016llx c%016llx state unchanged\n", + proc->pid, thread->pid, + node_debug_id, + (u64)node_ptr, + (u64)node_cookie); + if (ret) + return ret; } break; case BINDER_WORK_DEAD_BINDER: case BINDER_WORK_DEAD_BINDER_AND_CLEAR: case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: { struct binder_ref_death *death; uint32_t cmd; + binder_uintptr_t cookie; death = container_of(w, struct binder_ref_death, work); if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) cmd = BR_CLEAR_DEATH_NOTIFICATION_DONE; else cmd = BR_DEAD_BINDER; - if (put_user(cmd, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - if (put_user(death->cookie, - (binder_uintptr_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(binder_uintptr_t); - binder_stat_br(proc, thread, cmd); + cookie = death->cookie; + binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION, "%d:%d %s %016llx\n", proc->pid, thread->pid, cmd == BR_DEAD_BINDER ? "BR_DEAD_BINDER" : "BR_CLEAR_DEATH_NOTIFICATION_DONE", - (u64)death->cookie); - + (u64)cookie); if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) { - list_del(&w->entry); + binder_inner_proc_unlock(proc); kfree(death); binder_stats_deleted(BINDER_STAT_DEATH); - } else - list_move(&w->entry, &proc->delivered_death); + } else { + binder_enqueue_work_ilocked( + w, &proc->delivered_death); + binder_inner_proc_unlock(proc); + } + if (put_user(cmd, (uint32_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(uint32_t); + if (put_user(cookie, + (binder_uintptr_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(binder_uintptr_t); + binder_stat_br(proc, thread, cmd); if (cmd == BR_DEAD_BINDER) goto done; /* DEAD_BINDER notifications can cause transactions */ } break; @@ -2907,8 +3791,9 @@ retry: tr.flags = t->flags; tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid); - if (t->from) { - struct task_struct *sender = t->from->proc->tsk; + t_from = binder_get_txn_from(t); + if (t_from) { + struct task_struct *sender = t_from->proc->tsk; tr.sender_pid = task_tgid_nr_ns(sender, task_active_pid_ns(current)); @@ -2918,18 +3803,24 @@ retry: tr.data_size = t->buffer->data_size; tr.offsets_size = t->buffer->offsets_size; - tr.data.ptr.buffer = (binder_uintptr_t)( - (uintptr_t)t->buffer->data + - proc->user_buffer_offset); + tr.data.ptr.buffer = (binder_uintptr_t) + ((uintptr_t)t->buffer->data + + binder_alloc_get_user_buffer_offset(&proc->alloc)); tr.data.ptr.offsets = tr.data.ptr.buffer + ALIGN(t->buffer->data_size, sizeof(void *)); - if (put_user(cmd, (uint32_t __user *)ptr)) + if (put_user(cmd, (uint32_t __user *)ptr)) { + if (t_from) + binder_thread_dec_tmpref(t_from); return -EFAULT; + } ptr += sizeof(uint32_t); - if (copy_to_user(ptr, &tr, sizeof(tr))) + if (copy_to_user(ptr, &tr, sizeof(tr))) { + if (t_from) + binder_thread_dec_tmpref(t_from); return -EFAULT; + } ptr += sizeof(tr); trace_binder_transaction_received(t); @@ -2939,21 +3830,22 @@ retry: proc->pid, thread->pid, (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" : "BR_REPLY", - t->debug_id, t->from ? t->from->proc->pid : 0, - t->from ? t->from->pid : 0, cmd, + t->debug_id, t_from ? t_from->proc->pid : 0, + t_from ? t_from->pid : 0, cmd, t->buffer->data_size, t->buffer->offsets_size, (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets); - list_del(&t->work.entry); + if (t_from) + binder_thread_dec_tmpref(t_from); t->buffer->allow_user_free = 1; if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) { + binder_inner_proc_lock(thread->proc); t->to_parent = thread->transaction_stack; t->to_thread = thread; thread->transaction_stack = t; + binder_inner_proc_unlock(thread->proc); } else { - t->buffer->transaction = NULL; - kfree(t); - binder_stats_deleted(BINDER_STAT_TRANSACTION); + binder_free_transaction(t); } break; } @@ -2961,29 +3853,35 @@ retry: done: *consumed = ptr - buffer; + binder_inner_proc_lock(proc); if (proc->requested_threads + proc->ready_threads == 0 && proc->requested_threads_started < proc->max_threads && (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) /* the user-space code fails to */ /*spawn a new thread if we leave this out */) { proc->requested_threads++; + binder_inner_proc_unlock(proc); binder_debug(BINDER_DEBUG_THREADS, "%d:%d BR_SPAWN_LOOPER\n", proc->pid, thread->pid); if (put_user(BR_SPAWN_LOOPER, (uint32_t __user *)buffer)) return -EFAULT; binder_stat_br(proc, thread, BR_SPAWN_LOOPER); - } + } else + binder_inner_proc_unlock(proc); return 0; } -static void binder_release_work(struct list_head *list) +static void binder_release_work(struct binder_proc *proc, + struct list_head *list) { struct binder_work *w; - while (!list_empty(list)) { - w = list_first_entry(list, struct binder_work, entry); - list_del_init(&w->entry); + while (1) { + w = binder_dequeue_work_head(proc, list); + if (!w) + return; + switch (w->type) { case BINDER_WORK_TRANSACTION: { struct binder_transaction *t; @@ -2996,11 +3894,17 @@ static void binder_release_work(struct list_head *list) binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "undelivered transaction %d\n", t->debug_id); - t->buffer->transaction = NULL; - kfree(t); - binder_stats_deleted(BINDER_STAT_TRANSACTION); + binder_free_transaction(t); } } break; + case BINDER_WORK_RETURN_ERROR: { + struct binder_error *e = container_of( + w, struct binder_error, work); + + binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, + "undelivered TRANSACTION_ERROR: %u\n", + e->cmd); + } break; case BINDER_WORK_TRANSACTION_COMPLETE: { binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "undelivered TRANSACTION_COMPLETE\n"); @@ -3027,7 +3931,8 @@ static void binder_release_work(struct list_head *list) } -static struct binder_thread *binder_get_thread(struct binder_proc *proc) +static struct binder_thread *binder_get_thread_ilocked( + struct binder_proc *proc, struct binder_thread *new_thread) { struct binder_thread *thread = NULL; struct rb_node *parent = NULL; @@ -3042,38 +3947,99 @@ static struct binder_thread *binder_get_thread(struct binder_proc *proc) else if (current->pid > thread->pid) p = &(*p)->rb_right; else - break; + return thread; } - if (*p == NULL) { - thread = kzalloc(sizeof(*thread), GFP_KERNEL); - if (thread == NULL) + if (!new_thread) + return NULL; + thread = new_thread; + binder_stats_created(BINDER_STAT_THREAD); + thread->proc = proc; + thread->pid = current->pid; + atomic_set(&thread->tmp_ref, 0); + init_waitqueue_head(&thread->wait); + INIT_LIST_HEAD(&thread->todo); + rb_link_node(&thread->rb_node, parent, p); + rb_insert_color(&thread->rb_node, &proc->threads); + thread->looper_need_return = true; + thread->return_error.work.type = BINDER_WORK_RETURN_ERROR; + thread->return_error.cmd = BR_OK; + thread->reply_error.work.type = BINDER_WORK_RETURN_ERROR; + thread->reply_error.cmd = BR_OK; + + return thread; +} + +static struct binder_thread *binder_get_thread(struct binder_proc *proc) +{ + struct binder_thread *thread; + struct binder_thread *new_thread; + + binder_inner_proc_lock(proc); + thread = binder_get_thread_ilocked(proc, NULL); + binder_inner_proc_unlock(proc); + if (!thread) { + new_thread = kzalloc(sizeof(*thread), GFP_KERNEL); + if (new_thread == NULL) return NULL; - binder_stats_created(BINDER_STAT_THREAD); - thread->proc = proc; - thread->pid = current->pid; - init_waitqueue_head(&thread->wait); - INIT_LIST_HEAD(&thread->todo); - rb_link_node(&thread->rb_node, parent, p); - rb_insert_color(&thread->rb_node, &proc->threads); - thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN; - thread->return_error = BR_OK; - thread->return_error2 = BR_OK; + binder_inner_proc_lock(proc); + thread = binder_get_thread_ilocked(proc, new_thread); + binder_inner_proc_unlock(proc); + if (thread != new_thread) + kfree(new_thread); } return thread; } -static int binder_free_thread(struct binder_proc *proc, - struct binder_thread *thread) +static void binder_free_proc(struct binder_proc *proc) +{ + BUG_ON(!list_empty(&proc->todo)); + BUG_ON(!list_empty(&proc->delivered_death)); + binder_alloc_deferred_release(&proc->alloc); + put_task_struct(proc->tsk); + binder_stats_deleted(BINDER_STAT_PROC); + kfree(proc); +} + +static void binder_free_thread(struct binder_thread *thread) +{ + BUG_ON(!list_empty(&thread->todo)); + binder_stats_deleted(BINDER_STAT_THREAD); + binder_proc_dec_tmpref(thread->proc); + kfree(thread); +} + +static int binder_thread_release(struct binder_proc *proc, + struct binder_thread *thread) { struct binder_transaction *t; struct binder_transaction *send_reply = NULL; int active_transactions = 0; + struct binder_transaction *last_t = NULL; + binder_inner_proc_lock(thread->proc); + /* + * take a ref on the proc so it survives + * after we remove this thread from proc->threads. + * The corresponding dec is when we actually + * free the thread in binder_free_thread() + */ + proc->tmp_ref++; + /* + * take a ref on this thread to ensure it + * survives while we are releasing it + */ + atomic_inc(&thread->tmp_ref); rb_erase(&thread->rb_node, &proc->threads); t = thread->transaction_stack; - if (t && t->to_thread == thread) - send_reply = t; + if (t) { + spin_lock(&t->lock); + if (t->to_thread == thread) + send_reply = t; + } + thread->is_dead = true; + while (t) { + last_t = t; active_transactions++; binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "release %d:%d transaction %d %s, still active\n", @@ -3094,12 +4060,16 @@ static int binder_free_thread(struct binder_proc *proc, t = t->from_parent; } else BUG(); + spin_unlock(&last_t->lock); + if (t) + spin_lock(&t->lock); } + binder_inner_proc_unlock(thread->proc); + if (send_reply) binder_send_failed_reply(send_reply, BR_DEAD_REPLY); - binder_release_work(&thread->todo); - kfree(thread); - binder_stats_deleted(BINDER_STAT_THREAD); + binder_release_work(proc, &thread->todo); + binder_thread_dec_tmpref(thread); return active_transactions; } @@ -3110,14 +4080,12 @@ static unsigned int binder_poll(struct file *filp, struct binder_thread *thread = NULL; int wait_for_proc_work; - binder_lock(__func__); - thread = binder_get_thread(proc); + binder_inner_proc_lock(thread->proc); wait_for_proc_work = thread->transaction_stack == NULL && - list_empty(&thread->todo) && thread->return_error == BR_OK; - - binder_unlock(__func__); + binder_worklist_empty_ilocked(&thread->todo); + binder_inner_proc_unlock(thread->proc); if (wait_for_proc_work) { if (binder_has_proc_work(proc, thread)) @@ -3178,7 +4146,7 @@ static int binder_ioctl_write_read(struct file *filp, &bwr.read_consumed, filp->f_flags & O_NONBLOCK); trace_binder_read_done(ret); - if (!list_empty(&proc->todo)) + if (!binder_worklist_empty(proc, &proc->todo)) wake_up_interruptible(&proc->wait); if (ret < 0) { if (copy_to_user(ubuf, &bwr, sizeof(bwr))) @@ -3204,9 +4172,10 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp) int ret = 0; struct binder_proc *proc = filp->private_data; struct binder_context *context = proc->context; - + struct binder_node *new_node; kuid_t curr_euid = current_euid(); + mutex_lock(&context->context_mgr_node_lock); if (context->binder_context_mgr_node) { pr_err("BINDER_SET_CONTEXT_MGR already set\n"); ret = -EBUSY; @@ -3227,16 +4196,21 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp) } else { context->binder_context_mgr_uid = curr_euid; } - context->binder_context_mgr_node = binder_new_node(proc, 0, 0); - if (!context->binder_context_mgr_node) { + new_node = binder_new_node(proc, NULL); + if (!new_node) { ret = -ENOMEM; goto out; } - context->binder_context_mgr_node->local_weak_refs++; - context->binder_context_mgr_node->local_strong_refs++; - context->binder_context_mgr_node->has_strong_ref = 1; - context->binder_context_mgr_node->has_weak_ref = 1; + binder_node_lock(new_node); + new_node->local_weak_refs++; + new_node->local_strong_refs++; + new_node->has_strong_ref = 1; + new_node->has_weak_ref = 1; + context->binder_context_mgr_node = new_node; + binder_node_unlock(new_node); + binder_put_node(new_node); out: + mutex_unlock(&context->context_mgr_node_lock); return ret; } @@ -3257,7 +4231,6 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (ret) goto err_unlocked; - binder_lock(__func__); thread = binder_get_thread(proc); if (thread == NULL) { ret = -ENOMEM; @@ -3270,12 +4243,19 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (ret) goto err; break; - case BINDER_SET_MAX_THREADS: - if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) { + case BINDER_SET_MAX_THREADS: { + int max_threads; + + if (copy_from_user(&max_threads, ubuf, + sizeof(max_threads))) { ret = -EINVAL; goto err; } + binder_inner_proc_lock(proc); + proc->max_threads = max_threads; + binder_inner_proc_unlock(proc); break; + } case BINDER_SET_CONTEXT_MGR: ret = binder_ioctl_set_ctx_mgr(filp); if (ret) @@ -3284,7 +4264,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case BINDER_THREAD_EXIT: binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n", proc->pid, thread->pid); - binder_free_thread(proc, thread); + binder_thread_release(proc, thread); thread = NULL; break; case BINDER_VERSION: { @@ -3308,8 +4288,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) ret = 0; err: if (thread) - thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN; - binder_unlock(__func__); + thread->looper_need_return = false; wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); if (ret && ret != -ERESTARTSYS) pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret); @@ -3338,8 +4317,7 @@ static void binder_vma_close(struct vm_area_struct *vma) proc->pid, vma->vm_start, vma->vm_end, (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags, (unsigned long)pgprot_val(vma->vm_page_prot)); - proc->vma = NULL; - proc->vma_vm_mm = NULL; + binder_alloc_vma_close(&proc->alloc); binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES); } @@ -3357,10 +4335,8 @@ static const struct vm_operations_struct binder_vm_ops = { static int binder_mmap(struct file *filp, struct vm_area_struct *vma) { int ret; - struct vm_struct *area; struct binder_proc *proc = filp->private_data; const char *failure_string; - struct binder_buffer *buffer; if (proc->tsk != current->group_leader) return -EINVAL; @@ -3369,8 +4345,8 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_end = vma->vm_start + SZ_4M; binder_debug(BINDER_DEBUG_OPEN_CLOSE, - "binder_mmap: %d %lx-%lx (%ld K) vma %lx pagep %lx\n", - proc->pid, vma->vm_start, vma->vm_end, + "%s: %d %lx-%lx (%ld K) vma %lx pagep %lx\n", + __func__, proc->pid, vma->vm_start, vma->vm_end, (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags, (unsigned long)pgprot_val(vma->vm_page_prot)); @@ -3380,73 +4356,15 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) goto err_bad_arg; } vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE; - - mutex_lock(&binder_mmap_lock); - if (proc->buffer) { - ret = -EBUSY; - failure_string = "already mapped"; - goto err_already_mapped; - } - - area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP); - if (area == NULL) { - ret = -ENOMEM; - failure_string = "get_vm_area"; - goto err_get_vm_area_failed; - } - proc->buffer = area->addr; - proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer; - mutex_unlock(&binder_mmap_lock); - -#ifdef CONFIG_CPU_CACHE_VIPT - if (cache_is_vipt_aliasing()) { - while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) { - pr_info("binder_mmap: %d %lx-%lx maps %p bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer); - vma->vm_start += PAGE_SIZE; - } - } -#endif - proc->pages = kzalloc(sizeof(proc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL); - if (proc->pages == NULL) { - ret = -ENOMEM; - failure_string = "alloc page array"; - goto err_alloc_pages_failed; - } - proc->buffer_size = vma->vm_end - vma->vm_start; - vma->vm_ops = &binder_vm_ops; vma->vm_private_data = proc; - if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) { - ret = -ENOMEM; - failure_string = "alloc small buf"; - goto err_alloc_small_buf_failed; - } - buffer = proc->buffer; - INIT_LIST_HEAD(&proc->buffers); - list_add(&buffer->entry, &proc->buffers); - buffer->free = 1; - binder_insert_free_buffer(proc, buffer); - proc->free_async_space = proc->buffer_size / 2; - barrier(); + ret = binder_alloc_mmap_handler(&proc->alloc, vma); + if (ret) + return ret; proc->files = get_files_struct(current); - proc->vma = vma; - proc->vma_vm_mm = vma->vm_mm; - - /*pr_info("binder_mmap: %d %lx-%lx maps %p\n", - proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/ return 0; -err_alloc_small_buf_failed: - kfree(proc->pages); - proc->pages = NULL; -err_alloc_pages_failed: - mutex_lock(&binder_mmap_lock); - vfree(proc->buffer); - proc->buffer = NULL; -err_get_vm_area_failed: -err_already_mapped: - mutex_unlock(&binder_mmap_lock); err_bad_arg: pr_err("binder_mmap: %d %lx-%lx %s failed %d\n", proc->pid, vma->vm_start, vma->vm_end, failure_string, ret); @@ -3464,6 +4382,8 @@ static int binder_open(struct inode *nodp, struct file *filp) proc = kzalloc(sizeof(*proc), GFP_KERNEL); if (proc == NULL) return -ENOMEM; + spin_lock_init(&proc->inner_lock); + spin_lock_init(&proc->outer_lock); get_task_struct(current->group_leader); proc->tsk = current->group_leader; INIT_LIST_HEAD(&proc->todo); @@ -3472,16 +4392,16 @@ static int binder_open(struct inode *nodp, struct file *filp) binder_dev = container_of(filp->private_data, struct binder_device, miscdev); proc->context = &binder_dev->context; - - binder_lock(__func__); + binder_alloc_init(&proc->alloc); binder_stats_created(BINDER_STAT_PROC); - hlist_add_head(&proc->proc_node, &binder_procs); proc->pid = current->group_leader->pid; INIT_LIST_HEAD(&proc->delivered_death); filp->private_data = proc; - binder_unlock(__func__); + mutex_lock(&binder_procs_lock); + hlist_add_head(&proc->proc_node, &binder_procs); + mutex_unlock(&binder_procs_lock); if (binder_debugfs_dir_entry_proc) { char strbuf[11]; @@ -3517,15 +4437,17 @@ static void binder_deferred_flush(struct binder_proc *proc) struct rb_node *n; int wake_count = 0; + binder_inner_proc_lock(proc); for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) { struct binder_thread *thread = rb_entry(n, struct binder_thread, rb_node); - thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN; + thread->looper_need_return = true; if (thread->looper & BINDER_LOOPER_STATE_WAITING) { wake_up_interruptible(&thread->wait); wake_count++; } } + binder_inner_proc_unlock(proc); wake_up_interruptible_all(&proc->wait); binder_debug(BINDER_DEBUG_OPEN_CLOSE, @@ -3547,13 +4469,21 @@ static int binder_node_release(struct binder_node *node, int refs) { struct binder_ref *ref; int death = 0; + struct binder_proc *proc = node->proc; - list_del_init(&node->work.entry); - binder_release_work(&node->async_todo); + binder_release_work(proc, &node->async_todo); - if (hlist_empty(&node->refs)) { - kfree(node); - binder_stats_deleted(BINDER_STAT_NODE); + binder_node_lock(node); + binder_inner_proc_lock(proc); + binder_dequeue_work_ilocked(&node->work); + /* + * The caller must have taken a temporary ref on the node, + */ + BUG_ON(!node->tmp_refs); + if (hlist_empty(&node->refs) && node->tmp_refs == 1) { + binder_inner_proc_unlock(proc); + binder_node_unlock(node); + binder_free_node(node); return refs; } @@ -3561,45 +4491,58 @@ static int binder_node_release(struct binder_node *node, int refs) node->proc = NULL; node->local_strong_refs = 0; node->local_weak_refs = 0; + binder_inner_proc_unlock(proc); + + spin_lock(&binder_dead_nodes_lock); hlist_add_head(&node->dead_node, &binder_dead_nodes); + spin_unlock(&binder_dead_nodes_lock); hlist_for_each_entry(ref, &node->refs, node_entry) { refs++; - - if (!ref->death) + /* + * Need the node lock to synchronize + * with new notification requests and the + * inner lock to synchronize with queued + * death notifications. + */ + binder_inner_proc_lock(ref->proc); + if (!ref->death) { + binder_inner_proc_unlock(ref->proc); continue; + } death++; - if (list_empty(&ref->death->work.entry)) { - ref->death->work.type = BINDER_WORK_DEAD_BINDER; - list_add_tail(&ref->death->work.entry, - &ref->proc->todo); - wake_up_interruptible(&ref->proc->wait); - } else - BUG(); + BUG_ON(!list_empty(&ref->death->work.entry)); + ref->death->work.type = BINDER_WORK_DEAD_BINDER; + binder_enqueue_work_ilocked(&ref->death->work, + &ref->proc->todo); + wake_up_interruptible(&ref->proc->wait); + binder_inner_proc_unlock(ref->proc); } binder_debug(BINDER_DEBUG_DEAD_BINDER, "node %d now dead, refs %d, death %d\n", node->debug_id, refs, death); + binder_node_unlock(node); + binder_put_node(node); return refs; } static void binder_deferred_release(struct binder_proc *proc) { - struct binder_transaction *t; struct binder_context *context = proc->context; struct rb_node *n; - int threads, nodes, incoming_refs, outgoing_refs, buffers, - active_transactions, page_count; + int threads, nodes, incoming_refs, outgoing_refs, active_transactions; - BUG_ON(proc->vma); BUG_ON(proc->files); + mutex_lock(&binder_procs_lock); hlist_del(&proc->proc_node); + mutex_unlock(&binder_procs_lock); + mutex_lock(&context->context_mgr_node_lock); if (context->binder_context_mgr_node && context->binder_context_mgr_node->proc == proc) { binder_debug(BINDER_DEBUG_DEAD_BINDER, @@ -3607,15 +4550,25 @@ static void binder_deferred_release(struct binder_proc *proc) __func__, proc->pid); context->binder_context_mgr_node = NULL; } + mutex_unlock(&context->context_mgr_node_lock); + binder_inner_proc_lock(proc); + /* + * Make sure proc stays alive after we + * remove all the threads + */ + proc->tmp_ref++; + proc->is_dead = true; threads = 0; active_transactions = 0; while ((n = rb_first(&proc->threads))) { struct binder_thread *thread; thread = rb_entry(n, struct binder_thread, rb_node); + binder_inner_proc_unlock(proc); threads++; - active_transactions += binder_free_thread(proc, thread); + active_transactions += binder_thread_release(proc, thread); + binder_inner_proc_lock(proc); } nodes = 0; @@ -3625,73 +4578,42 @@ static void binder_deferred_release(struct binder_proc *proc) node = rb_entry(n, struct binder_node, rb_node); nodes++; + /* + * take a temporary ref on the node before + * calling binder_node_release() which will either + * kfree() the node or call binder_put_node() + */ + binder_inc_node_tmpref_ilocked(node); rb_erase(&node->rb_node, &proc->nodes); + binder_inner_proc_unlock(proc); incoming_refs = binder_node_release(node, incoming_refs); + binder_inner_proc_lock(proc); } + binder_inner_proc_unlock(proc); outgoing_refs = 0; + binder_proc_lock(proc); while ((n = rb_first(&proc->refs_by_desc))) { struct binder_ref *ref; ref = rb_entry(n, struct binder_ref, rb_node_desc); outgoing_refs++; - binder_delete_ref(ref); + binder_cleanup_ref_olocked(ref); + binder_proc_unlock(proc); + binder_free_ref(ref); + binder_proc_lock(proc); } + binder_proc_unlock(proc); - binder_release_work(&proc->todo); - binder_release_work(&proc->delivered_death); - - buffers = 0; - while ((n = rb_first(&proc->allocated_buffers))) { - struct binder_buffer *buffer; - - buffer = rb_entry(n, struct binder_buffer, rb_node); - - t = buffer->transaction; - if (t) { - t->buffer = NULL; - buffer->transaction = NULL; - pr_err("release proc %d, transaction %d, not freed\n", - proc->pid, t->debug_id); - /*BUG();*/ - } - - binder_free_buf(proc, buffer); - buffers++; - } - - binder_stats_deleted(BINDER_STAT_PROC); - - page_count = 0; - if (proc->pages) { - int i; - - for (i = 0; i < proc->buffer_size / PAGE_SIZE; i++) { - void *page_addr; - - if (!proc->pages[i]) - continue; - - page_addr = proc->buffer + i * PAGE_SIZE; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%s: %d: page %d at %p not freed\n", - __func__, proc->pid, i, page_addr); - unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); - __free_page(proc->pages[i]); - page_count++; - } - kfree(proc->pages); - vfree(proc->buffer); - } - - put_task_struct(proc->tsk); + binder_release_work(proc, &proc->todo); + binder_release_work(proc, &proc->delivered_death); binder_debug(BINDER_DEBUG_OPEN_CLOSE, - "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d, buffers %d, pages %d\n", + "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d\n", __func__, proc->pid, threads, nodes, incoming_refs, - outgoing_refs, active_transactions, buffers, page_count); + outgoing_refs, active_transactions); - kfree(proc); + binder_proc_dec_tmpref(proc); } static void binder_deferred_func(struct work_struct *work) @@ -3702,7 +4624,6 @@ static void binder_deferred_func(struct work_struct *work) int defer; do { - binder_lock(__func__); mutex_lock(&binder_deferred_lock); if (!hlist_empty(&binder_deferred_list)) { proc = hlist_entry(binder_deferred_list.first, @@ -3729,7 +4650,6 @@ static void binder_deferred_func(struct work_struct *work) if (defer & BINDER_DEFERRED_RELEASE) binder_deferred_release(proc); /* frees proc */ - binder_unlock(__func__); if (files) put_files_struct(files); } while (proc); @@ -3749,41 +4669,52 @@ binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer) mutex_unlock(&binder_deferred_lock); } -static void print_binder_transaction(struct seq_file *m, const char *prefix, - struct binder_transaction *t) +static void print_binder_transaction_ilocked(struct seq_file *m, + struct binder_proc *proc, + const char *prefix, + struct binder_transaction *t) { + struct binder_proc *to_proc; + struct binder_buffer *buffer = t->buffer; + + WARN_ON(!spin_is_locked(&proc->inner_lock)); + spin_lock(&t->lock); + to_proc = t->to_proc; seq_printf(m, "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d", prefix, t->debug_id, t, t->from ? t->from->proc->pid : 0, t->from ? t->from->pid : 0, - t->to_proc ? t->to_proc->pid : 0, + to_proc ? to_proc->pid : 0, t->to_thread ? t->to_thread->pid : 0, t->code, t->flags, t->priority, t->need_reply); - if (t->buffer == NULL) { + spin_unlock(&t->lock); + + if (proc != to_proc) { + /* + * Can only safely deref buffer if we are holding the + * correct proc inner lock for this node + */ + seq_puts(m, "\n"); + return; + } + + if (buffer == NULL) { seq_puts(m, " buffer free\n"); return; } - if (t->buffer->target_node) - seq_printf(m, " node %d", - t->buffer->target_node->debug_id); + if (buffer->target_node) + seq_printf(m, " node %d", buffer->target_node->debug_id); seq_printf(m, " size %zd:%zd data %p\n", - t->buffer->data_size, t->buffer->offsets_size, - t->buffer->data); -} - -static void print_binder_buffer(struct seq_file *m, const char *prefix, - struct binder_buffer *buffer) -{ - seq_printf(m, "%s %d: %p size %zd:%zd %s\n", - prefix, buffer->debug_id, buffer->data, buffer->data_size, buffer->offsets_size, - buffer->transaction ? "active" : "delivered"); + buffer->data); } -static void print_binder_work(struct seq_file *m, const char *prefix, - const char *transaction_prefix, - struct binder_work *w) +static void print_binder_work_ilocked(struct seq_file *m, + struct binder_proc *proc, + const char *prefix, + const char *transaction_prefix, + struct binder_work *w) { struct binder_node *node; struct binder_transaction *t; @@ -3791,8 +4722,16 @@ static void print_binder_work(struct seq_file *m, const char *prefix, switch (w->type) { case BINDER_WORK_TRANSACTION: t = container_of(w, struct binder_transaction, work); - print_binder_transaction(m, transaction_prefix, t); + print_binder_transaction_ilocked( + m, proc, transaction_prefix, t); break; + case BINDER_WORK_RETURN_ERROR: { + struct binder_error *e = container_of( + w, struct binder_error, work); + + seq_printf(m, "%stransaction error: %u\n", + prefix, e->cmd); + } break; case BINDER_WORK_TRANSACTION_COMPLETE: seq_printf(m, "%stransaction complete\n", prefix); break; @@ -3817,70 +4756,89 @@ static void print_binder_work(struct seq_file *m, const char *prefix, } } -static void print_binder_thread(struct seq_file *m, - struct binder_thread *thread, - int print_always) +static void print_binder_thread_ilocked(struct seq_file *m, + struct binder_thread *thread, + int print_always) { struct binder_transaction *t; struct binder_work *w; size_t start_pos = m->count; size_t header_pos; - seq_printf(m, " thread %d: l %02x\n", thread->pid, thread->looper); + WARN_ON(!spin_is_locked(&thread->proc->inner_lock)); + seq_printf(m, " thread %d: l %02x need_return %d tr %d\n", + thread->pid, thread->looper, + thread->looper_need_return, + atomic_read(&thread->tmp_ref)); header_pos = m->count; t = thread->transaction_stack; while (t) { if (t->from == thread) { - print_binder_transaction(m, - " outgoing transaction", t); + print_binder_transaction_ilocked(m, thread->proc, + " outgoing transaction", t); t = t->from_parent; } else if (t->to_thread == thread) { - print_binder_transaction(m, + print_binder_transaction_ilocked(m, thread->proc, " incoming transaction", t); t = t->to_parent; } else { - print_binder_transaction(m, " bad transaction", t); + print_binder_transaction_ilocked(m, thread->proc, + " bad transaction", t); t = NULL; } } list_for_each_entry(w, &thread->todo, entry) { - print_binder_work(m, " ", " pending transaction", w); + print_binder_work_ilocked(m, thread->proc, " ", + " pending transaction", w); } if (!print_always && m->count == header_pos) m->count = start_pos; } -static void print_binder_node(struct seq_file *m, struct binder_node *node) +static void print_binder_node_nilocked(struct seq_file *m, + struct binder_node *node) { struct binder_ref *ref; struct binder_work *w; int count; + WARN_ON(!spin_is_locked(&node->lock)); + if (node->proc) + WARN_ON(!spin_is_locked(&node->proc->inner_lock)); + count = 0; hlist_for_each_entry(ref, &node->refs, node_entry) count++; - seq_printf(m, " node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d", + seq_printf(m, " node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d tr %d", node->debug_id, (u64)node->ptr, (u64)node->cookie, node->has_strong_ref, node->has_weak_ref, node->local_strong_refs, node->local_weak_refs, - node->internal_strong_refs, count); + node->internal_strong_refs, count, node->tmp_refs); if (count) { seq_puts(m, " proc"); hlist_for_each_entry(ref, &node->refs, node_entry) seq_printf(m, " %d", ref->proc->pid); } seq_puts(m, "\n"); - list_for_each_entry(w, &node->async_todo, entry) - print_binder_work(m, " ", - " pending async transaction", w); + if (node->proc) { + list_for_each_entry(w, &node->async_todo, entry) + print_binder_work_ilocked(m, node->proc, " ", + " pending async transaction", w); + } } -static void print_binder_ref(struct seq_file *m, struct binder_ref *ref) +static void print_binder_ref_olocked(struct seq_file *m, + struct binder_ref *ref) { - seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %p\n", - ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ", - ref->node->debug_id, ref->strong, ref->weak, ref->death); + WARN_ON(!spin_is_locked(&ref->proc->outer_lock)); + binder_node_lock(ref->node); + seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %pK\n", + ref->data.debug_id, ref->data.desc, + ref->node->proc ? "" : "dead ", + ref->node->debug_id, ref->data.strong, + ref->data.weak, ref->death); + binder_node_unlock(ref->node); } static void print_binder_proc(struct seq_file *m, @@ -3890,36 +4848,60 @@ static void print_binder_proc(struct seq_file *m, struct rb_node *n; size_t start_pos = m->count; size_t header_pos; + struct binder_node *last_node = NULL; seq_printf(m, "proc %d\n", proc->pid); seq_printf(m, "context %s\n", proc->context->name); header_pos = m->count; + binder_inner_proc_lock(proc); for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) - print_binder_thread(m, rb_entry(n, struct binder_thread, + print_binder_thread_ilocked(m, rb_entry(n, struct binder_thread, rb_node), print_all); + for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) { struct binder_node *node = rb_entry(n, struct binder_node, rb_node); - if (print_all || node->has_async_transaction) - print_binder_node(m, node); - } + /* + * take a temporary reference on the node so it + * survives and isn't removed from the tree + * while we print it. + */ + binder_inc_node_tmpref_ilocked(node); + /* Need to drop inner lock to take node lock */ + binder_inner_proc_unlock(proc); + if (last_node) + binder_put_node(last_node); + binder_node_inner_lock(node); + print_binder_node_nilocked(m, node); + binder_node_inner_unlock(node); + last_node = node; + binder_inner_proc_lock(proc); + } + binder_inner_proc_unlock(proc); + if (last_node) + binder_put_node(last_node); + if (print_all) { + binder_proc_lock(proc); for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) - print_binder_ref(m, rb_entry(n, struct binder_ref, - rb_node_desc)); + print_binder_ref_olocked(m, rb_entry(n, + struct binder_ref, + rb_node_desc)); + binder_proc_unlock(proc); } - for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n)) - print_binder_buffer(m, " buffer", - rb_entry(n, struct binder_buffer, rb_node)); + binder_alloc_print_allocated(m, &proc->alloc); + binder_inner_proc_lock(proc); list_for_each_entry(w, &proc->todo, entry) - print_binder_work(m, " ", " pending transaction", w); + print_binder_work_ilocked(m, proc, " ", + " pending transaction", w); list_for_each_entry(w, &proc->delivered_death, entry) { seq_puts(m, " has delivered dead binder\n"); break; } + binder_inner_proc_unlock(proc); if (!print_all && m->count == header_pos) m->count = start_pos; } @@ -3985,17 +4967,21 @@ static void print_binder_stats(struct seq_file *m, const char *prefix, BUILD_BUG_ON(ARRAY_SIZE(stats->bc) != ARRAY_SIZE(binder_command_strings)); for (i = 0; i < ARRAY_SIZE(stats->bc); i++) { - if (stats->bc[i]) + int temp = atomic_read(&stats->bc[i]); + + if (temp) seq_printf(m, "%s%s: %d\n", prefix, - binder_command_strings[i], stats->bc[i]); + binder_command_strings[i], temp); } BUILD_BUG_ON(ARRAY_SIZE(stats->br) != ARRAY_SIZE(binder_return_strings)); for (i = 0; i < ARRAY_SIZE(stats->br); i++) { - if (stats->br[i]) + int temp = atomic_read(&stats->br[i]); + + if (temp) seq_printf(m, "%s%s: %d\n", prefix, - binder_return_strings[i], stats->br[i]); + binder_return_strings[i], temp); } BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) != @@ -4003,11 +4989,15 @@ static void print_binder_stats(struct seq_file *m, const char *prefix, BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) != ARRAY_SIZE(stats->obj_deleted)); for (i = 0; i < ARRAY_SIZE(stats->obj_created); i++) { - if (stats->obj_created[i] || stats->obj_deleted[i]) - seq_printf(m, "%s%s: active %d total %d\n", prefix, + int created = atomic_read(&stats->obj_created[i]); + int deleted = atomic_read(&stats->obj_deleted[i]); + + if (created || deleted) + seq_printf(m, "%s%s: active %d total %d\n", + prefix, binder_objstat_strings[i], - stats->obj_created[i] - stats->obj_deleted[i], - stats->obj_created[i]); + created - deleted, + created); } } @@ -4017,10 +5007,13 @@ static void print_binder_proc_stats(struct seq_file *m, struct binder_work *w; struct rb_node *n; int count, strong, weak; + size_t free_async_space = + binder_alloc_get_free_async_space(&proc->alloc); seq_printf(m, "proc %d\n", proc->pid); seq_printf(m, "context %s\n", proc->context->name); count = 0; + binder_inner_proc_lock(proc); for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) count++; seq_printf(m, " threads: %d\n", count); @@ -4028,38 +5021,37 @@ static void print_binder_proc_stats(struct seq_file *m, " ready threads %d\n" " free async space %zd\n", proc->requested_threads, proc->requested_threads_started, proc->max_threads, - proc->ready_threads, proc->free_async_space); + proc->ready_threads, + free_async_space); count = 0; for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) count++; + binder_inner_proc_unlock(proc); seq_printf(m, " nodes: %d\n", count); count = 0; strong = 0; weak = 0; + binder_proc_lock(proc); for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) { struct binder_ref *ref = rb_entry(n, struct binder_ref, rb_node_desc); count++; - strong += ref->strong; - weak += ref->weak; + strong += ref->data.strong; + weak += ref->data.weak; } + binder_proc_unlock(proc); seq_printf(m, " refs: %d s %d w %d\n", count, strong, weak); - count = 0; - for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n)) - count++; + count = binder_alloc_get_allocated_count(&proc->alloc); seq_printf(m, " buffers: %d\n", count); count = 0; + binder_inner_proc_lock(proc); list_for_each_entry(w, &proc->todo, entry) { - switch (w->type) { - case BINDER_WORK_TRANSACTION: + if (w->type == BINDER_WORK_TRANSACTION) count++; - break; - default: - break; - } } + binder_inner_proc_unlock(proc); seq_printf(m, " pending transactions: %d\n", count); print_binder_stats(m, " ", &proc->stats); @@ -4070,57 +5062,67 @@ static int binder_state_show(struct seq_file *m, void *unused) { struct binder_proc *proc; struct binder_node *node; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); + struct binder_node *last_node = NULL; seq_puts(m, "binder state:\n"); + spin_lock(&binder_dead_nodes_lock); if (!hlist_empty(&binder_dead_nodes)) seq_puts(m, "dead nodes:\n"); - hlist_for_each_entry(node, &binder_dead_nodes, dead_node) - print_binder_node(m, node); - + hlist_for_each_entry(node, &binder_dead_nodes, dead_node) { + /* + * take a temporary reference on the node so it + * survives and isn't removed from the list + * while we print it. + */ + node->tmp_refs++; + spin_unlock(&binder_dead_nodes_lock); + if (last_node) + binder_put_node(last_node); + binder_node_lock(node); + print_binder_node_nilocked(m, node); + binder_node_unlock(node); + last_node = node; + spin_lock(&binder_dead_nodes_lock); + } + spin_unlock(&binder_dead_nodes_lock); + if (last_node) + binder_put_node(last_node); + + mutex_lock(&binder_procs_lock); hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc(m, proc, 1); - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static int binder_stats_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); seq_puts(m, "binder stats:\n"); print_binder_stats(m, "", &binder_stats); + mutex_lock(&binder_procs_lock); hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc_stats(m, proc); - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static int binder_transactions_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); seq_puts(m, "binder transactions:\n"); + mutex_lock(&binder_procs_lock); hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc(m, proc, 0); - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } @@ -4128,44 +5130,63 @@ static int binder_proc_show(struct seq_file *m, void *unused) { struct binder_proc *itr; int pid = (unsigned long)m->private; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); + mutex_lock(&binder_procs_lock); hlist_for_each_entry(itr, &binder_procs, proc_node) { if (itr->pid == pid) { seq_puts(m, "binder proc state:\n"); print_binder_proc(m, itr, 1); } } - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static void print_binder_transaction_log_entry(struct seq_file *m, struct binder_transaction_log_entry *e) { + int debug_id = READ_ONCE(e->debug_id_done); + /* + * read barrier to guarantee debug_id_done read before + * we print the log values + */ + smp_rmb(); seq_printf(m, - "%d: %s from %d:%d to %d:%d context %s node %d handle %d size %d:%d\n", + "%d: %s from %d:%d to %d:%d context %s node %d handle %d size %d:%d ret %d/%d l=%d", e->debug_id, (e->call_type == 2) ? "reply" : ((e->call_type == 1) ? "async" : "call "), e->from_proc, e->from_thread, e->to_proc, e->to_thread, e->context_name, - e->to_node, e->target_handle, e->data_size, e->offsets_size); + e->to_node, e->target_handle, e->data_size, e->offsets_size, + e->return_error, e->return_error_param, + e->return_error_line); + /* + * read-barrier to guarantee read of debug_id_done after + * done printing the fields of the entry + */ + smp_rmb(); + seq_printf(m, debug_id && debug_id == READ_ONCE(e->debug_id_done) ? + "\n" : " (incomplete)\n"); } static int binder_transaction_log_show(struct seq_file *m, void *unused) { struct binder_transaction_log *log = m->private; + unsigned int log_cur = atomic_read(&log->cur); + unsigned int count; + unsigned int cur; int i; - if (log->full) { - for (i = log->next; i < ARRAY_SIZE(log->entry); i++) - print_binder_transaction_log_entry(m, &log->entry[i]); + count = log_cur + 1; + cur = count < ARRAY_SIZE(log->entry) && !log->full ? + 0 : count % ARRAY_SIZE(log->entry); + if (count > ARRAY_SIZE(log->entry) || log->full) + count = ARRAY_SIZE(log->entry); + for (i = 0; i < count; i++) { + unsigned int index = cur++ % ARRAY_SIZE(log->entry); + + print_binder_transaction_log_entry(m, &log->entry[index]); } - for (i = 0; i < log->next; i++) - print_binder_transaction_log_entry(m, &log->entry[i]); return 0; } @@ -4200,6 +5221,7 @@ static int __init init_binder_device(const char *name) binder_device->context.binder_context_mgr_uid = INVALID_UID; binder_device->context.name = name; + mutex_init(&binder_device->context.context_mgr_node_lock); ret = misc_register(&binder_device->miscdev); if (ret < 0) { @@ -4215,10 +5237,13 @@ static int __init init_binder_device(const char *name) static int __init binder_init(void) { int ret; - char *device_name, *device_names; + char *device_name, *device_names, *device_tmp; struct binder_device *device; struct hlist_node *tmp; + atomic_set(&binder_transaction_log.cur, ~0U); + atomic_set(&binder_transaction_log_failed.cur, ~0U); + binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL); if (binder_debugfs_dir_entry_root) binder_debugfs_dir_entry_proc = debugfs_create_dir("proc", @@ -4263,7 +5288,8 @@ static int __init binder_init(void) } strcpy(device_names, binder_devices_param); - while ((device_name = strsep(&device_names, ","))) { + device_tmp = device_names; + while ((device_name = strsep(&device_tmp, ","))) { ret = init_binder_device(device_name); if (ret) goto err_init_binder_device_failed; @@ -4277,6 +5303,9 @@ err_init_binder_device_failed: hlist_del(&device->hlist); kfree(device); } + + kfree(device_names); + err_alloc_device_names_failed: debugfs_remove_recursive(binder_debugfs_dir_entry_root); diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c new file mode 100644 index 000000000000..40f31df60580 --- /dev/null +++ b/drivers/android/binder_alloc.c @@ -0,0 +1,802 @@ +/* binder_alloc.c + * + * Android IPC Subsystem + * + * Copyright (C) 2007-2017 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <asm/cacheflush.h> +#include <linux/list.h> +#include <linux/sched/mm.h> +#include <linux/module.h> +#include <linux/rtmutex.h> +#include <linux/rbtree.h> +#include <linux/seq_file.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include "binder_alloc.h" +#include "binder_trace.h" + +static DEFINE_MUTEX(binder_alloc_mmap_lock); + +enum { + BINDER_DEBUG_OPEN_CLOSE = 1U << 1, + BINDER_DEBUG_BUFFER_ALLOC = 1U << 2, + BINDER_DEBUG_BUFFER_ALLOC_ASYNC = 1U << 3, +}; +static uint32_t binder_alloc_debug_mask; + +module_param_named(debug_mask, binder_alloc_debug_mask, + uint, 0644); + +#define binder_alloc_debug(mask, x...) \ + do { \ + if (binder_alloc_debug_mask & mask) \ + pr_info(x); \ + } while (0) + +static size_t binder_alloc_buffer_size(struct binder_alloc *alloc, + struct binder_buffer *buffer) +{ + if (list_is_last(&buffer->entry, &alloc->buffers)) + return alloc->buffer + + alloc->buffer_size - (void *)buffer->data; + return (size_t)list_entry(buffer->entry.next, + struct binder_buffer, entry) - (size_t)buffer->data; +} + +static void binder_insert_free_buffer(struct binder_alloc *alloc, + struct binder_buffer *new_buffer) +{ + struct rb_node **p = &alloc->free_buffers.rb_node; + struct rb_node *parent = NULL; + struct binder_buffer *buffer; + size_t buffer_size; + size_t new_buffer_size; + + BUG_ON(!new_buffer->free); + + new_buffer_size = binder_alloc_buffer_size(alloc, new_buffer); + + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: add free buffer, size %zd, at %pK\n", + alloc->pid, new_buffer_size, new_buffer); + + while (*p) { + parent = *p; + buffer = rb_entry(parent, struct binder_buffer, rb_node); + BUG_ON(!buffer->free); + + buffer_size = binder_alloc_buffer_size(alloc, buffer); + + if (new_buffer_size < buffer_size) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node(&new_buffer->rb_node, parent, p); + rb_insert_color(&new_buffer->rb_node, &alloc->free_buffers); +} + +static void binder_insert_allocated_buffer_locked( + struct binder_alloc *alloc, struct binder_buffer *new_buffer) +{ + struct rb_node **p = &alloc->allocated_buffers.rb_node; + struct rb_node *parent = NULL; + struct binder_buffer *buffer; + + BUG_ON(new_buffer->free); + + while (*p) { + parent = *p; + buffer = rb_entry(parent, struct binder_buffer, rb_node); + BUG_ON(buffer->free); + + if (new_buffer < buffer) + p = &parent->rb_left; + else if (new_buffer > buffer) + p = &parent->rb_right; + else + BUG(); + } + rb_link_node(&new_buffer->rb_node, parent, p); + rb_insert_color(&new_buffer->rb_node, &alloc->allocated_buffers); +} + +static struct binder_buffer *binder_alloc_prepare_to_free_locked( + struct binder_alloc *alloc, + uintptr_t user_ptr) +{ + struct rb_node *n = alloc->allocated_buffers.rb_node; + struct binder_buffer *buffer; + struct binder_buffer *kern_ptr; + + kern_ptr = (struct binder_buffer *)(user_ptr - alloc->user_buffer_offset + - offsetof(struct binder_buffer, data)); + + while (n) { + buffer = rb_entry(n, struct binder_buffer, rb_node); + BUG_ON(buffer->free); + + if (kern_ptr < buffer) + n = n->rb_left; + else if (kern_ptr > buffer) + n = n->rb_right; + else { + /* + * Guard against user threads attempting to + * free the buffer twice + */ + if (buffer->free_in_progress) { + pr_err("%d:%d FREE_BUFFER u%016llx user freed buffer twice\n", + alloc->pid, current->pid, (u64)user_ptr); + return NULL; + } + buffer->free_in_progress = 1; + return buffer; + } + } + return NULL; +} + +/** + * binder_alloc_buffer_lookup() - get buffer given user ptr + * @alloc: binder_alloc for this proc + * @user_ptr: User pointer to buffer data + * + * Validate userspace pointer to buffer data and return buffer corresponding to + * that user pointer. Search the rb tree for buffer that matches user data + * pointer. + * + * Return: Pointer to buffer or NULL + */ +struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc, + uintptr_t user_ptr) +{ + struct binder_buffer *buffer; + + mutex_lock(&alloc->mutex); + buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr); + mutex_unlock(&alloc->mutex); + return buffer; +} + +static int binder_update_page_range(struct binder_alloc *alloc, int allocate, + void *start, void *end, + struct vm_area_struct *vma) +{ + void *page_addr; + unsigned long user_page_addr; + struct page **page; + struct mm_struct *mm; + + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: %s pages %pK-%pK\n", alloc->pid, + allocate ? "allocate" : "free", start, end); + + if (end <= start) + return 0; + + trace_binder_update_page_range(alloc, allocate, start, end); + + if (vma) + mm = NULL; + else + mm = get_task_mm(alloc->tsk); + + if (mm) { + down_write(&mm->mmap_sem); + vma = alloc->vma; + if (vma && mm != alloc->vma_vm_mm) { + pr_err("%d: vma mm and task mm mismatch\n", + alloc->pid); + vma = NULL; + } + } + + if (allocate == 0) + goto free_range; + + if (vma == NULL) { + pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n", + alloc->pid); + goto err_no_vma; + } + + for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) { + int ret; + + page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE]; + + BUG_ON(*page); + *page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + if (*page == NULL) { + pr_err("%d: binder_alloc_buf failed for page at %pK\n", + alloc->pid, page_addr); + goto err_alloc_page_failed; + } + ret = map_kernel_range_noflush((unsigned long)page_addr, + PAGE_SIZE, PAGE_KERNEL, page); + flush_cache_vmap((unsigned long)page_addr, + (unsigned long)page_addr + PAGE_SIZE); + if (ret != 1) { + pr_err("%d: binder_alloc_buf failed to map page at %pK in kernel\n", + alloc->pid, page_addr); + goto err_map_kernel_failed; + } + user_page_addr = + (uintptr_t)page_addr + alloc->user_buffer_offset; + ret = vm_insert_page(vma, user_page_addr, page[0]); + if (ret) { + pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n", + alloc->pid, user_page_addr); + goto err_vm_insert_page_failed; + } + /* vm_insert_page does not seem to increment the refcount */ + } + if (mm) { + up_write(&mm->mmap_sem); + mmput(mm); + } + return 0; + +free_range: + for (page_addr = end - PAGE_SIZE; page_addr >= start; + page_addr -= PAGE_SIZE) { + page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE]; + if (vma) + zap_page_range(vma, (uintptr_t)page_addr + + alloc->user_buffer_offset, PAGE_SIZE); +err_vm_insert_page_failed: + unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); +err_map_kernel_failed: + __free_page(*page); + *page = NULL; +err_alloc_page_failed: + ; + } +err_no_vma: + if (mm) { + up_write(&mm->mmap_sem); + mmput(mm); + } + return vma ? -ENOMEM : -ESRCH; +} + +struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, + size_t data_size, + size_t offsets_size, + size_t extra_buffers_size, + int is_async) +{ + struct rb_node *n = alloc->free_buffers.rb_node; + struct binder_buffer *buffer; + size_t buffer_size; + struct rb_node *best_fit = NULL; + void *has_page_addr; + void *end_page_addr; + size_t size, data_offsets_size; + int ret; + + if (alloc->vma == NULL) { + pr_err("%d: binder_alloc_buf, no vma\n", + alloc->pid); + return ERR_PTR(-ESRCH); + } + + data_offsets_size = ALIGN(data_size, sizeof(void *)) + + ALIGN(offsets_size, sizeof(void *)); + + if (data_offsets_size < data_size || data_offsets_size < offsets_size) { + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: got transaction with invalid size %zd-%zd\n", + alloc->pid, data_size, offsets_size); + return ERR_PTR(-EINVAL); + } + size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *)); + if (size < data_offsets_size || size < extra_buffers_size) { + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: got transaction with invalid extra_buffers_size %zd\n", + alloc->pid, extra_buffers_size); + return ERR_PTR(-EINVAL); + } + if (is_async && + alloc->free_async_space < size + sizeof(struct binder_buffer)) { + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: binder_alloc_buf size %zd failed, no async space left\n", + alloc->pid, size); + return ERR_PTR(-ENOSPC); + } + + while (n) { + buffer = rb_entry(n, struct binder_buffer, rb_node); + BUG_ON(!buffer->free); + buffer_size = binder_alloc_buffer_size(alloc, buffer); + + if (size < buffer_size) { + best_fit = n; + n = n->rb_left; + } else if (size > buffer_size) + n = n->rb_right; + else { + best_fit = n; + break; + } + } + if (best_fit == NULL) { + size_t allocated_buffers = 0; + size_t largest_alloc_size = 0; + size_t total_alloc_size = 0; + size_t free_buffers = 0; + size_t largest_free_size = 0; + size_t total_free_size = 0; + + for (n = rb_first(&alloc->allocated_buffers); n != NULL; + n = rb_next(n)) { + buffer = rb_entry(n, struct binder_buffer, rb_node); + buffer_size = binder_alloc_buffer_size(alloc, buffer); + allocated_buffers++; + total_alloc_size += buffer_size; + if (buffer_size > largest_alloc_size) + largest_alloc_size = buffer_size; + } + for (n = rb_first(&alloc->free_buffers); n != NULL; + n = rb_next(n)) { + buffer = rb_entry(n, struct binder_buffer, rb_node); + buffer_size = binder_alloc_buffer_size(alloc, buffer); + free_buffers++; + total_free_size += buffer_size; + if (buffer_size > largest_free_size) + largest_free_size = buffer_size; + } + pr_err("%d: binder_alloc_buf size %zd failed, no address space\n", + alloc->pid, size); + pr_err("allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n", + total_alloc_size, allocated_buffers, largest_alloc_size, + total_free_size, free_buffers, largest_free_size); + return ERR_PTR(-ENOSPC); + } + if (n == NULL) { + buffer = rb_entry(best_fit, struct binder_buffer, rb_node); + buffer_size = binder_alloc_buffer_size(alloc, buffer); + } + + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n", + alloc->pid, size, buffer, buffer_size); + + has_page_addr = + (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK); + if (n == NULL) { + if (size + sizeof(struct binder_buffer) + 4 >= buffer_size) + buffer_size = size; /* no room for other buffers */ + else + buffer_size = size + sizeof(struct binder_buffer); + } + end_page_addr = + (void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size); + if (end_page_addr > has_page_addr) + end_page_addr = has_page_addr; + ret = binder_update_page_range(alloc, 1, + (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL); + if (ret) + return ERR_PTR(ret); + + rb_erase(best_fit, &alloc->free_buffers); + buffer->free = 0; + buffer->free_in_progress = 0; + binder_insert_allocated_buffer_locked(alloc, buffer); + if (buffer_size != size) { + struct binder_buffer *new_buffer = (void *)buffer->data + size; + + list_add(&new_buffer->entry, &buffer->entry); + new_buffer->free = 1; + binder_insert_free_buffer(alloc, new_buffer); + } + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: binder_alloc_buf size %zd got %pK\n", + alloc->pid, size, buffer); + buffer->data_size = data_size; + buffer->offsets_size = offsets_size; + buffer->async_transaction = is_async; + buffer->extra_buffers_size = extra_buffers_size; + if (is_async) { + alloc->free_async_space -= size + sizeof(struct binder_buffer); + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, + "%d: binder_alloc_buf size %zd async free %zd\n", + alloc->pid, size, alloc->free_async_space); + } + return buffer; +} + +/** + * binder_alloc_new_buf() - Allocate a new binder buffer + * @alloc: binder_alloc for this proc + * @data_size: size of user data buffer + * @offsets_size: user specified buffer offset + * @extra_buffers_size: size of extra space for meta-data (eg, security context) + * @is_async: buffer for async transaction + * + * Allocate a new buffer given the requested sizes. Returns + * the kernel version of the buffer pointer. The size allocated + * is the sum of the three given sizes (each rounded up to + * pointer-sized boundary) + * + * Return: The allocated buffer or %NULL if error + */ +struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, + size_t data_size, + size_t offsets_size, + size_t extra_buffers_size, + int is_async) +{ + struct binder_buffer *buffer; + + mutex_lock(&alloc->mutex); + buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size, + extra_buffers_size, is_async); + mutex_unlock(&alloc->mutex); + return buffer; +} + +static void *buffer_start_page(struct binder_buffer *buffer) +{ + return (void *)((uintptr_t)buffer & PAGE_MASK); +} + +static void *buffer_end_page(struct binder_buffer *buffer) +{ + return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK); +} + +static void binder_delete_free_buffer(struct binder_alloc *alloc, + struct binder_buffer *buffer) +{ + struct binder_buffer *prev, *next = NULL; + int free_page_end = 1; + int free_page_start = 1; + + BUG_ON(alloc->buffers.next == &buffer->entry); + prev = list_entry(buffer->entry.prev, struct binder_buffer, entry); + BUG_ON(!prev->free); + if (buffer_end_page(prev) == buffer_start_page(buffer)) { + free_page_start = 0; + if (buffer_end_page(prev) == buffer_end_page(buffer)) + free_page_end = 0; + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: merge free, buffer %pK share page with %pK\n", + alloc->pid, buffer, prev); + } + + if (!list_is_last(&buffer->entry, &alloc->buffers)) { + next = list_entry(buffer->entry.next, + struct binder_buffer, entry); + if (buffer_start_page(next) == buffer_end_page(buffer)) { + free_page_end = 0; + if (buffer_start_page(next) == + buffer_start_page(buffer)) + free_page_start = 0; + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: merge free, buffer %pK share page with %pK\n", + alloc->pid, buffer, prev); + } + } + list_del(&buffer->entry); + if (free_page_start || free_page_end) { + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: merge free, buffer %pK do not share page%s%s with %pK or %pK\n", + alloc->pid, buffer, free_page_start ? "" : " end", + free_page_end ? "" : " start", prev, next); + binder_update_page_range(alloc, 0, free_page_start ? + buffer_start_page(buffer) : buffer_end_page(buffer), + (free_page_end ? buffer_end_page(buffer) : + buffer_start_page(buffer)) + PAGE_SIZE, NULL); + } +} + +static void binder_free_buf_locked(struct binder_alloc *alloc, + struct binder_buffer *buffer) +{ + size_t size, buffer_size; + + buffer_size = binder_alloc_buffer_size(alloc, buffer); + + size = ALIGN(buffer->data_size, sizeof(void *)) + + ALIGN(buffer->offsets_size, sizeof(void *)) + + ALIGN(buffer->extra_buffers_size, sizeof(void *)); + + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%d: binder_free_buf %pK size %zd buffer_size %zd\n", + alloc->pid, buffer, size, buffer_size); + + BUG_ON(buffer->free); + BUG_ON(size > buffer_size); + BUG_ON(buffer->transaction != NULL); + BUG_ON((void *)buffer < alloc->buffer); + BUG_ON((void *)buffer > alloc->buffer + alloc->buffer_size); + + if (buffer->async_transaction) { + alloc->free_async_space += size + sizeof(struct binder_buffer); + + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, + "%d: binder_free_buf size %zd async free %zd\n", + alloc->pid, size, alloc->free_async_space); + } + + binder_update_page_range(alloc, 0, + (void *)PAGE_ALIGN((uintptr_t)buffer->data), + (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK), + NULL); + + rb_erase(&buffer->rb_node, &alloc->allocated_buffers); + buffer->free = 1; + if (!list_is_last(&buffer->entry, &alloc->buffers)) { + struct binder_buffer *next = list_entry(buffer->entry.next, + struct binder_buffer, entry); + + if (next->free) { + rb_erase(&next->rb_node, &alloc->free_buffers); + binder_delete_free_buffer(alloc, next); + } + } + if (alloc->buffers.next != &buffer->entry) { + struct binder_buffer *prev = list_entry(buffer->entry.prev, + struct binder_buffer, entry); + + if (prev->free) { + binder_delete_free_buffer(alloc, buffer); + rb_erase(&prev->rb_node, &alloc->free_buffers); + buffer = prev; + } + } + binder_insert_free_buffer(alloc, buffer); +} + +/** + * binder_alloc_free_buf() - free a binder buffer + * @alloc: binder_alloc for this proc + * @buffer: kernel pointer to buffer + * + * Free the buffer allocated via binder_alloc_new_buffer() + */ +void binder_alloc_free_buf(struct binder_alloc *alloc, + struct binder_buffer *buffer) +{ + mutex_lock(&alloc->mutex); + binder_free_buf_locked(alloc, buffer); + mutex_unlock(&alloc->mutex); +} + +/** + * binder_alloc_mmap_handler() - map virtual address space for proc + * @alloc: alloc structure for this proc + * @vma: vma passed to mmap() + * + * Called by binder_mmap() to initialize the space specified in + * vma for allocating binder buffers + * + * Return: + * 0 = success + * -EBUSY = address space already mapped + * -ENOMEM = failed to map memory to given address space + */ +int binder_alloc_mmap_handler(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + int ret; + struct vm_struct *area; + const char *failure_string; + struct binder_buffer *buffer; + + mutex_lock(&binder_alloc_mmap_lock); + if (alloc->buffer) { + ret = -EBUSY; + failure_string = "already mapped"; + goto err_already_mapped; + } + + area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP); + if (area == NULL) { + ret = -ENOMEM; + failure_string = "get_vm_area"; + goto err_get_vm_area_failed; + } + alloc->buffer = area->addr; + alloc->user_buffer_offset = + vma->vm_start - (uintptr_t)alloc->buffer; + mutex_unlock(&binder_alloc_mmap_lock); + +#ifdef CONFIG_CPU_CACHE_VIPT + if (cache_is_vipt_aliasing()) { + while (CACHE_COLOUR( + (vma->vm_start ^ (uint32_t)alloc->buffer))) { + pr_info("%s: %d %lx-%lx maps %pK bad alignment\n", + __func__, alloc->pid, vma->vm_start, + vma->vm_end, alloc->buffer); + vma->vm_start += PAGE_SIZE; + } + } +#endif + alloc->pages = kzalloc(sizeof(alloc->pages[0]) * + ((vma->vm_end - vma->vm_start) / PAGE_SIZE), + GFP_KERNEL); + if (alloc->pages == NULL) { + ret = -ENOMEM; + failure_string = "alloc page array"; + goto err_alloc_pages_failed; + } + alloc->buffer_size = vma->vm_end - vma->vm_start; + + if (binder_update_page_range(alloc, 1, alloc->buffer, + alloc->buffer + PAGE_SIZE, vma)) { + ret = -ENOMEM; + failure_string = "alloc small buf"; + goto err_alloc_small_buf_failed; + } + buffer = alloc->buffer; + INIT_LIST_HEAD(&alloc->buffers); + list_add(&buffer->entry, &alloc->buffers); + buffer->free = 1; + binder_insert_free_buffer(alloc, buffer); + alloc->free_async_space = alloc->buffer_size / 2; + barrier(); + alloc->vma = vma; + alloc->vma_vm_mm = vma->vm_mm; + + return 0; + +err_alloc_small_buf_failed: + kfree(alloc->pages); + alloc->pages = NULL; +err_alloc_pages_failed: + mutex_lock(&binder_alloc_mmap_lock); + vfree(alloc->buffer); + alloc->buffer = NULL; +err_get_vm_area_failed: +err_already_mapped: + mutex_unlock(&binder_alloc_mmap_lock); + pr_err("%s: %d %lx-%lx %s failed %d\n", __func__, + alloc->pid, vma->vm_start, vma->vm_end, failure_string, ret); + return ret; +} + + +void binder_alloc_deferred_release(struct binder_alloc *alloc) +{ + struct rb_node *n; + int buffers, page_count; + + BUG_ON(alloc->vma); + + buffers = 0; + mutex_lock(&alloc->mutex); + while ((n = rb_first(&alloc->allocated_buffers))) { + struct binder_buffer *buffer; + + buffer = rb_entry(n, struct binder_buffer, rb_node); + + /* Transaction should already have been freed */ + BUG_ON(buffer->transaction); + + binder_free_buf_locked(alloc, buffer); + buffers++; + } + + page_count = 0; + if (alloc->pages) { + int i; + + for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + void *page_addr; + + if (!alloc->pages[i]) + continue; + + page_addr = alloc->buffer + i * PAGE_SIZE; + binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, + "%s: %d: page %d at %pK not freed\n", + __func__, alloc->pid, i, page_addr); + unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); + __free_page(alloc->pages[i]); + page_count++; + } + kfree(alloc->pages); + vfree(alloc->buffer); + } + mutex_unlock(&alloc->mutex); + + binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE, + "%s: %d buffers %d, pages %d\n", + __func__, alloc->pid, buffers, page_count); +} + +static void print_binder_buffer(struct seq_file *m, const char *prefix, + struct binder_buffer *buffer) +{ + seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n", + prefix, buffer->debug_id, buffer->data, + buffer->data_size, buffer->offsets_size, + buffer->extra_buffers_size, + buffer->transaction ? "active" : "delivered"); +} + +/** + * binder_alloc_print_allocated() - print buffer info + * @m: seq_file for output via seq_printf() + * @alloc: binder_alloc for this proc + * + * Prints information about every buffer associated with + * the binder_alloc state to the given seq_file + */ +void binder_alloc_print_allocated(struct seq_file *m, + struct binder_alloc *alloc) +{ + struct rb_node *n; + + mutex_lock(&alloc->mutex); + for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n)) + print_binder_buffer(m, " buffer", + rb_entry(n, struct binder_buffer, rb_node)); + mutex_unlock(&alloc->mutex); +} + +/** + * binder_alloc_get_allocated_count() - return count of buffers + * @alloc: binder_alloc for this proc + * + * Return: count of allocated buffers + */ +int binder_alloc_get_allocated_count(struct binder_alloc *alloc) +{ + struct rb_node *n; + int count = 0; + + mutex_lock(&alloc->mutex); + for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n)) + count++; + mutex_unlock(&alloc->mutex); + return count; +} + + +/** + * binder_alloc_vma_close() - invalidate address space + * @alloc: binder_alloc for this proc + * + * Called from binder_vma_close() when releasing address space. + * Clears alloc->vma to prevent new incoming transactions from + * allocating more buffers. + */ +void binder_alloc_vma_close(struct binder_alloc *alloc) +{ + WRITE_ONCE(alloc->vma, NULL); + WRITE_ONCE(alloc->vma_vm_mm, NULL); +} + +/** + * binder_alloc_init() - called by binder_open() for per-proc initialization + * @alloc: binder_alloc for this proc + * + * Called from binder_open() to initialize binder_alloc fields for + * new binder proc + */ +void binder_alloc_init(struct binder_alloc *alloc) +{ + alloc->tsk = current->group_leader; + alloc->pid = current->group_leader->pid; + mutex_init(&alloc->mutex); +} + diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h new file mode 100644 index 000000000000..088e4ffc6230 --- /dev/null +++ b/drivers/android/binder_alloc.h @@ -0,0 +1,163 @@ +/* + * Copyright (C) 2017 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_BINDER_ALLOC_H +#define _LINUX_BINDER_ALLOC_H + +#include <linux/rbtree.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/rtmutex.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> + +struct binder_transaction; + +/** + * struct binder_buffer - buffer used for binder transactions + * @entry: entry alloc->buffers + * @rb_node: node for allocated_buffers/free_buffers rb trees + * @free: true if buffer is free + * @allow_user_free: describe the second member of struct blah, + * @async_transaction: describe the second member of struct blah, + * @debug_id: describe the second member of struct blah, + * @transaction: describe the second member of struct blah, + * @target_node: describe the second member of struct blah, + * @data_size: describe the second member of struct blah, + * @offsets_size: describe the second member of struct blah, + * @extra_buffers_size: describe the second member of struct blah, + * @data:i describe the second member of struct blah, + * + * Bookkeeping structure for binder transaction buffers + */ +struct binder_buffer { + struct list_head entry; /* free and allocated entries by address */ + struct rb_node rb_node; /* free entry by size or allocated entry */ + /* by address */ + unsigned free:1; + unsigned allow_user_free:1; + unsigned async_transaction:1; + unsigned free_in_progress:1; + unsigned debug_id:28; + + struct binder_transaction *transaction; + + struct binder_node *target_node; + size_t data_size; + size_t offsets_size; + size_t extra_buffers_size; + uint8_t data[0]; +}; + +/** + * struct binder_alloc - per-binder proc state for binder allocator + * @vma: vm_area_struct passed to mmap_handler + * (invarient after mmap) + * @tsk: tid for task that called init for this proc + * (invariant after init) + * @vma_vm_mm: copy of vma->vm_mm (invarient after mmap) + * @buffer: base of per-proc address space mapped via mmap + * @user_buffer_offset: offset between user and kernel VAs for buffer + * @buffers: list of all buffers for this proc + * @free_buffers: rb tree of buffers available for allocation + * sorted by size + * @allocated_buffers: rb tree of allocated buffers sorted by address + * @free_async_space: VA space available for async buffers. This is + * initialized at mmap time to 1/2 the full VA space + * @pages: array of physical page addresses for each + * page of mmap'd space + * @buffer_size: size of address space specified via mmap + * @pid: pid for associated binder_proc (invariant after init) + * + * Bookkeeping structure for per-proc address space management for binder + * buffers. It is normally initialized during binder_init() and binder_mmap() + * calls. The address space is used for both user-visible buffers and for + * struct binder_buffer objects used to track the user buffers + */ +struct binder_alloc { + struct mutex mutex; + struct task_struct *tsk; + struct vm_area_struct *vma; + struct mm_struct *vma_vm_mm; + void *buffer; + ptrdiff_t user_buffer_offset; + struct list_head buffers; + struct rb_root free_buffers; + struct rb_root allocated_buffers; + size_t free_async_space; + struct page **pages; + size_t buffer_size; + uint32_t buffer_free; + int pid; +}; + +extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, + size_t data_size, + size_t offsets_size, + size_t extra_buffers_size, + int is_async); +extern void binder_alloc_init(struct binder_alloc *alloc); +extern void binder_alloc_vma_close(struct binder_alloc *alloc); +extern struct binder_buffer * +binder_alloc_prepare_to_free(struct binder_alloc *alloc, + uintptr_t user_ptr); +extern void binder_alloc_free_buf(struct binder_alloc *alloc, + struct binder_buffer *buffer); +extern int binder_alloc_mmap_handler(struct binder_alloc *alloc, + struct vm_area_struct *vma); +extern void binder_alloc_deferred_release(struct binder_alloc *alloc); +extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc); +extern void binder_alloc_print_allocated(struct seq_file *m, + struct binder_alloc *alloc); + +/** + * binder_alloc_get_free_async_space() - get free space available for async + * @alloc: binder_alloc for this proc + * + * Return: the bytes remaining in the address-space for async transactions + */ +static inline size_t +binder_alloc_get_free_async_space(struct binder_alloc *alloc) +{ + size_t free_async_space; + + mutex_lock(&alloc->mutex); + free_async_space = alloc->free_async_space; + mutex_unlock(&alloc->mutex); + return free_async_space; +} + +/** + * binder_alloc_get_user_buffer_offset() - get offset between kernel/user addrs + * @alloc: binder_alloc for this proc + * + * Return: the offset between kernel and user-space addresses to use for + * virtual address conversion + */ +static inline ptrdiff_t +binder_alloc_get_user_buffer_offset(struct binder_alloc *alloc) +{ + /* + * user_buffer_offset is constant if vma is set and + * undefined if vma is not set. It is possible to + * get here with !alloc->vma if the target process + * is dying while a transaction is being initiated. + * Returning the old value is ok in this case and + * the transaction will fail. + */ + return alloc->user_buffer_offset; +} + +#endif /* _LINUX_BINDER_ALLOC_H */ + diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h index 7f20f3dc8369..7967db16ba5a 100644 --- a/drivers/android/binder_trace.h +++ b/drivers/android/binder_trace.h @@ -23,7 +23,8 @@ struct binder_buffer; struct binder_node; struct binder_proc; -struct binder_ref; +struct binder_alloc; +struct binder_ref_data; struct binder_thread; struct binder_transaction; @@ -146,8 +147,8 @@ TRACE_EVENT(binder_transaction_received, TRACE_EVENT(binder_transaction_node_to_ref, TP_PROTO(struct binder_transaction *t, struct binder_node *node, - struct binder_ref *ref), - TP_ARGS(t, node, ref), + struct binder_ref_data *rdata), + TP_ARGS(t, node, rdata), TP_STRUCT__entry( __field(int, debug_id) @@ -160,8 +161,8 @@ TRACE_EVENT(binder_transaction_node_to_ref, __entry->debug_id = t->debug_id; __entry->node_debug_id = node->debug_id; __entry->node_ptr = node->ptr; - __entry->ref_debug_id = ref->debug_id; - __entry->ref_desc = ref->desc; + __entry->ref_debug_id = rdata->debug_id; + __entry->ref_desc = rdata->desc; ), TP_printk("transaction=%d node=%d src_ptr=0x%016llx ==> dest_ref=%d dest_desc=%d", __entry->debug_id, __entry->node_debug_id, @@ -170,8 +171,9 @@ TRACE_EVENT(binder_transaction_node_to_ref, ); TRACE_EVENT(binder_transaction_ref_to_node, - TP_PROTO(struct binder_transaction *t, struct binder_ref *ref), - TP_ARGS(t, ref), + TP_PROTO(struct binder_transaction *t, struct binder_node *node, + struct binder_ref_data *rdata), + TP_ARGS(t, node, rdata), TP_STRUCT__entry( __field(int, debug_id) @@ -182,10 +184,10 @@ TRACE_EVENT(binder_transaction_ref_to_node, ), TP_fast_assign( __entry->debug_id = t->debug_id; - __entry->ref_debug_id = ref->debug_id; - __entry->ref_desc = ref->desc; - __entry->node_debug_id = ref->node->debug_id; - __entry->node_ptr = ref->node->ptr; + __entry->ref_debug_id = rdata->debug_id; + __entry->ref_desc = rdata->desc; + __entry->node_debug_id = node->debug_id; + __entry->node_ptr = node->ptr; ), TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%016llx", __entry->debug_id, __entry->node_debug_id, @@ -194,9 +196,10 @@ TRACE_EVENT(binder_transaction_ref_to_node, ); TRACE_EVENT(binder_transaction_ref_to_ref, - TP_PROTO(struct binder_transaction *t, struct binder_ref *src_ref, - struct binder_ref *dest_ref), - TP_ARGS(t, src_ref, dest_ref), + TP_PROTO(struct binder_transaction *t, struct binder_node *node, + struct binder_ref_data *src_ref, + struct binder_ref_data *dest_ref), + TP_ARGS(t, node, src_ref, dest_ref), TP_STRUCT__entry( __field(int, debug_id) @@ -208,7 +211,7 @@ TRACE_EVENT(binder_transaction_ref_to_ref, ), TP_fast_assign( __entry->debug_id = t->debug_id; - __entry->node_debug_id = src_ref->node->debug_id; + __entry->node_debug_id = node->debug_id; __entry->src_ref_debug_id = src_ref->debug_id; __entry->src_ref_desc = src_ref->desc; __entry->dest_ref_debug_id = dest_ref->debug_id; @@ -268,9 +271,9 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release, TP_ARGS(buffer)); TRACE_EVENT(binder_update_page_range, - TP_PROTO(struct binder_proc *proc, bool allocate, + TP_PROTO(struct binder_alloc *alloc, bool allocate, void *start, void *end), - TP_ARGS(proc, allocate, start, end), + TP_ARGS(alloc, allocate, start, end), TP_STRUCT__entry( __field(int, proc) __field(bool, allocate) @@ -278,9 +281,9 @@ TRACE_EVENT(binder_update_page_range, __field(size_t, size) ), TP_fast_assign( - __entry->proc = proc->pid; + __entry->proc = alloc->pid; __entry->allocate = allocate; - __entry->offset = start - proc->buffer; + __entry->offset = start - alloc->buffer; __entry->size = end - start; ), TP_printk("proc=%d allocate=%d offset=%zu size=%zu", diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index 7a8b8fb2f572..df126dcdaf18 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -877,21 +877,21 @@ static void lcd_clear_fast_tilcd(struct charlcd *charlcd) spin_unlock_irq(&pprt_lock); } -static struct charlcd_ops charlcd_serial_ops = { +static const struct charlcd_ops charlcd_serial_ops = { .write_cmd = lcd_write_cmd_s, .write_data = lcd_write_data_s, .clear_fast = lcd_clear_fast_s, .backlight = lcd_backlight, }; -static struct charlcd_ops charlcd_parallel_ops = { +static const struct charlcd_ops charlcd_parallel_ops = { .write_cmd = lcd_write_cmd_p8, .write_data = lcd_write_data_p8, .clear_fast = lcd_clear_fast_p8, .backlight = lcd_backlight, }; -static struct charlcd_ops charlcd_tilcd_ops = { +static const struct charlcd_ops charlcd_tilcd_ops = { .write_cmd = lcd_write_cmd_tilcd, .write_data = lcd_write_data_tilcd, .clear_fast = lcd_clear_fast_tilcd, diff --git a/drivers/char/mwave/smapi.c b/drivers/char/mwave/smapi.c index 8c5411a8f33f..691f5898bb32 100644 --- a/drivers/char/mwave/smapi.c +++ b/drivers/char/mwave/smapi.c @@ -128,10 +128,11 @@ int smapi_query_DSP_cfg(SMAPI_DSP_SETTINGS * pSettings) { int bRC = -EIO; unsigned short usAX, usBX, usCX, usDX, usDI, usSI; - unsigned short ausDspBases[] = { 0x0030, 0x4E30, 0x8E30, 0xCE30, 0x0130, 0x0350, 0x0070, 0x0DB0 }; - unsigned short ausUartBases[] = { 0x03F8, 0x02F8, 0x03E8, 0x02E8 }; - unsigned short numDspBases = 8; - unsigned short numUartBases = 4; + static const unsigned short ausDspBases[] = { + 0x0030, 0x4E30, 0x8E30, 0xCE30, + 0x0130, 0x0350, 0x0070, 0x0DB0 }; + static const unsigned short ausUartBases[] = { + 0x03F8, 0x02F8, 0x03E8, 0x02E8 }; PRINTK_1(TRACE_SMAPI, "smapi::smapi_query_DSP_cfg entry\n"); @@ -148,7 +149,7 @@ int smapi_query_DSP_cfg(SMAPI_DSP_SETTINGS * pSettings) pSettings->bDSPEnabled = ((usCX & 0x0001) != 0); pSettings->usDspIRQ = usSI & 0x00FF; pSettings->usDspDMA = (usSI & 0xFF00) >> 8; - if ((usDI & 0x00FF) < numDspBases) { + if ((usDI & 0x00FF) < ARRAY_SIZE(ausDspBases)) { pSettings->usDspBaseIO = ausDspBases[usDI & 0x00FF]; } else { pSettings->usDspBaseIO = 0; @@ -176,7 +177,7 @@ int smapi_query_DSP_cfg(SMAPI_DSP_SETTINGS * pSettings) pSettings->bModemEnabled = ((usCX & 0x0001) != 0); pSettings->usUartIRQ = usSI & 0x000F; - if (((usSI & 0xFF00) >> 8) < numUartBases) { + if (((usSI & 0xFF00) >> 8) < ARRAY_SIZE(ausUartBases)) { pSettings->usUartBaseIO = ausUartBases[(usSI & 0xFF00) >> 8]; } else { pSettings->usUartBaseIO = 0; @@ -205,15 +206,16 @@ int smapi_set_DSP_cfg(void) int bRC = -EIO; int i; unsigned short usAX, usBX, usCX, usDX, usDI, usSI; - unsigned short ausDspBases[] = { 0x0030, 0x4E30, 0x8E30, 0xCE30, 0x0130, 0x0350, 0x0070, 0x0DB0 }; - unsigned short ausUartBases[] = { 0x03F8, 0x02F8, 0x03E8, 0x02E8 }; - unsigned short ausDspIrqs[] = { 5, 7, 10, 11, 15 }; - unsigned short ausUartIrqs[] = { 3, 4 }; - - unsigned short numDspBases = 8; - unsigned short numUartBases = 4; - unsigned short numDspIrqs = 5; - unsigned short numUartIrqs = 2; + static const unsigned short ausDspBases[] = { + 0x0030, 0x4E30, 0x8E30, 0xCE30, + 0x0130, 0x0350, 0x0070, 0x0DB0 }; + static const unsigned short ausUartBases[] = { + 0x03F8, 0x02F8, 0x03E8, 0x02E8 }; + static const unsigned short ausDspIrqs[] = { + 5, 7, 10, 11, 15 }; + static const unsigned short ausUartIrqs[] = { + 3, 4 }; + unsigned short dspio_index = 0, uartio_index = 0; PRINTK_5(TRACE_SMAPI, @@ -221,11 +223,11 @@ int smapi_set_DSP_cfg(void) mwave_3780i_irq, mwave_3780i_io, mwave_uart_irq, mwave_uart_io); if (mwave_3780i_io) { - for (i = 0; i < numDspBases; i++) { + for (i = 0; i < ARRAY_SIZE(ausDspBases); i++) { if (mwave_3780i_io == ausDspBases[i]) break; } - if (i == numDspBases) { + if (i == ARRAY_SIZE(ausDspBases)) { PRINTK_ERROR(KERN_ERR_MWAVE "smapi::smapi_set_DSP_cfg: Error: Invalid mwave_3780i_io address %x. Aborting.\n", mwave_3780i_io); return bRC; } @@ -233,22 +235,22 @@ int smapi_set_DSP_cfg(void) } if (mwave_3780i_irq) { - for (i = 0; i < numDspIrqs; i++) { + for (i = 0; i < ARRAY_SIZE(ausDspIrqs); i++) { if (mwave_3780i_irq == ausDspIrqs[i]) break; } - if (i == numDspIrqs) { + if (i == ARRAY_SIZE(ausDspIrqs)) { PRINTK_ERROR(KERN_ERR_MWAVE "smapi::smapi_set_DSP_cfg: Error: Invalid mwave_3780i_irq %x. Aborting.\n", mwave_3780i_irq); return bRC; } } if (mwave_uart_io) { - for (i = 0; i < numUartBases; i++) { + for (i = 0; i < ARRAY_SIZE(ausUartBases); i++) { if (mwave_uart_io == ausUartBases[i]) break; } - if (i == numUartBases) { + if (i == ARRAY_SIZE(ausUartBases)) { PRINTK_ERROR(KERN_ERR_MWAVE "smapi::smapi_set_DSP_cfg: Error: Invalid mwave_uart_io address %x. Aborting.\n", mwave_uart_io); return bRC; } @@ -257,11 +259,11 @@ int smapi_set_DSP_cfg(void) if (mwave_uart_irq) { - for (i = 0; i < numUartIrqs; i++) { + for (i = 0; i < ARRAY_SIZE(ausUartIrqs); i++) { if (mwave_uart_irq == ausUartIrqs[i]) break; } - if (i == numUartIrqs) { + if (i == ARRAY_SIZE(ausUartIrqs)) { PRINTK_ERROR(KERN_ERR_MWAVE "smapi::smapi_set_DSP_cfg: Error: Invalid mwave_uart_irq %x. Aborting.\n", mwave_uart_irq); return bRC; } diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index 3e73bcdf9e65..d256110ba672 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -101,9 +101,6 @@ static DEFINE_IDA(ida_index); #define PP_BUFFER_SIZE 1024 #define PARDEVICE_MAX 8 -/* ROUND_UP macro from fs/select.c */ -#define ROUND_UP(x,y) (((x)+(y)-1)/(y)) - static DEFINE_MUTEX(pp_do_mutex); /* define fixed sized ioctl cmd for y2038 migration */ diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 161ba9dccede..ad5448f718b3 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -2,9 +2,7 @@ # FPGA framework configuration # -menu "FPGA Configuration Support" - -config FPGA +menuconfig FPGA tristate "FPGA Configuration Framework" help Say Y here if you want support for configuring FPGAs from the @@ -26,6 +24,20 @@ config FPGA_MGR_ICE40_SPI help FPGA manager driver support for Lattice iCE40 FPGAs over SPI. +config FPGA_MGR_ALTERA_CVP + tristate "Altera Arria-V/Cyclone-V/Stratix-V CvP FPGA Manager" + depends on PCI + help + FPGA manager driver support for Arria-V, Cyclone-V, Stratix-V + and Arria 10 Altera FPGAs using the CvP interface over PCIe. + +config FPGA_MGR_ALTERA_PS_SPI + tristate "Altera FPGA Passive Serial over SPI" + depends on SPI + help + FPGA manager driver support for Altera Arria/Cyclone/Stratix + using the passive serial interface over SPI. + config FPGA_MGR_SOCFPGA tristate "Altera SOCFPGA FPGA Manager" depends on ARCH_SOCFPGA || COMPILE_TEST @@ -106,5 +118,3 @@ config XILINX_PR_DECOUPLER being reprogrammed during partial reconfig. endif # FPGA - -endmenu diff --git a/drivers/fpga/Makefile b/drivers/fpga/Makefile index 2a4f0218145c..e09895f0525b 100644 --- a/drivers/fpga/Makefile +++ b/drivers/fpga/Makefile @@ -6,6 +6,8 @@ obj-$(CONFIG_FPGA) += fpga-mgr.o # FPGA Manager Drivers +obj-$(CONFIG_FPGA_MGR_ALTERA_CVP) += altera-cvp.o +obj-$(CONFIG_FPGA_MGR_ALTERA_PS_SPI) += altera-ps-spi.o obj-$(CONFIG_FPGA_MGR_ICE40_SPI) += ice40-spi.o obj-$(CONFIG_FPGA_MGR_SOCFPGA) += socfpga.o obj-$(CONFIG_FPGA_MGR_SOCFPGA_A10) += socfpga-a10.o diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c new file mode 100644 index 000000000000..08629ee69d11 --- /dev/null +++ b/drivers/fpga/altera-cvp.c @@ -0,0 +1,500 @@ +/* + * FPGA Manager Driver for Altera Arria/Cyclone/Stratix CvP + * + * Copyright (C) 2017 DENX Software Engineering + * + * Anatolij Gustschin <agust@denx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Manage Altera FPGA firmware using PCIe CvP. + * Firmware must be in binary "rbf" format. + */ + +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/fpga/fpga-mgr.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/sizes.h> + +#define CVP_BAR 0 /* BAR used for data transfer in memory mode */ +#define CVP_DUMMY_WR 244 /* dummy writes to clear CvP state machine */ +#define TIMEOUT_US 2000 /* CVP STATUS timeout for USERMODE polling */ + +/* Vendor Specific Extended Capability Registers */ +#define VSE_PCIE_EXT_CAP_ID 0x200 +#define VSE_PCIE_EXT_CAP_ID_VAL 0x000b /* 16bit */ + +#define VSE_CVP_STATUS 0x21c /* 32bit */ +#define VSE_CVP_STATUS_CFG_RDY BIT(18) /* CVP_CONFIG_READY */ +#define VSE_CVP_STATUS_CFG_ERR BIT(19) /* CVP_CONFIG_ERROR */ +#define VSE_CVP_STATUS_CVP_EN BIT(20) /* ctrl block is enabling CVP */ +#define VSE_CVP_STATUS_USERMODE BIT(21) /* USERMODE */ +#define VSE_CVP_STATUS_CFG_DONE BIT(23) /* CVP_CONFIG_DONE */ +#define VSE_CVP_STATUS_PLD_CLK_IN_USE BIT(24) /* PLD_CLK_IN_USE */ + +#define VSE_CVP_MODE_CTRL 0x220 /* 32bit */ +#define VSE_CVP_MODE_CTRL_CVP_MODE BIT(0) /* CVP (1) or normal mode (0) */ +#define VSE_CVP_MODE_CTRL_HIP_CLK_SEL BIT(1) /* PMA (1) or fabric clock (0) */ +#define VSE_CVP_MODE_CTRL_NUMCLKS_OFF 8 /* NUMCLKS bits offset */ +#define VSE_CVP_MODE_CTRL_NUMCLKS_MASK GENMASK(15, 8) + +#define VSE_CVP_DATA 0x228 /* 32bit */ +#define VSE_CVP_PROG_CTRL 0x22c /* 32bit */ +#define VSE_CVP_PROG_CTRL_CONFIG BIT(0) +#define VSE_CVP_PROG_CTRL_START_XFER BIT(1) + +#define VSE_UNCOR_ERR_STATUS 0x234 /* 32bit */ +#define VSE_UNCOR_ERR_CVP_CFG_ERR BIT(5) /* CVP_CONFIG_ERROR_LATCHED */ + +#define DRV_NAME "altera-cvp" +#define ALTERA_CVP_MGR_NAME "Altera CvP FPGA Manager" + +/* Optional CvP config error status check for debugging */ +static bool altera_cvp_chkcfg; + +struct altera_cvp_conf { + struct fpga_manager *mgr; + struct pci_dev *pci_dev; + void __iomem *map; + void (*write_data)(struct altera_cvp_conf *, u32); + char mgr_name[64]; + u8 numclks; +}; + +static enum fpga_mgr_states altera_cvp_state(struct fpga_manager *mgr) +{ + struct altera_cvp_conf *conf = mgr->priv; + u32 status; + + pci_read_config_dword(conf->pci_dev, VSE_CVP_STATUS, &status); + + if (status & VSE_CVP_STATUS_CFG_DONE) + return FPGA_MGR_STATE_OPERATING; + + if (status & VSE_CVP_STATUS_CVP_EN) + return FPGA_MGR_STATE_POWER_UP; + + return FPGA_MGR_STATE_UNKNOWN; +} + +static void altera_cvp_write_data_iomem(struct altera_cvp_conf *conf, u32 val) +{ + writel(val, conf->map); +} + +static void altera_cvp_write_data_config(struct altera_cvp_conf *conf, u32 val) +{ + pci_write_config_dword(conf->pci_dev, VSE_CVP_DATA, val); +} + +/* switches between CvP clock and internal clock */ +static void altera_cvp_dummy_write(struct altera_cvp_conf *conf) +{ + unsigned int i; + u32 val; + + /* set 1 CVP clock cycle for every CVP Data Register Write */ + pci_read_config_dword(conf->pci_dev, VSE_CVP_MODE_CTRL, &val); + val &= ~VSE_CVP_MODE_CTRL_NUMCLKS_MASK; + val |= 1 << VSE_CVP_MODE_CTRL_NUMCLKS_OFF; + pci_write_config_dword(conf->pci_dev, VSE_CVP_MODE_CTRL, val); + + for (i = 0; i < CVP_DUMMY_WR; i++) + conf->write_data(conf, 0); /* dummy data, could be any value */ +} + +static int altera_cvp_wait_status(struct altera_cvp_conf *conf, u32 status_mask, + u32 status_val, int timeout_us) +{ + unsigned int retries; + u32 val; + + retries = timeout_us / 10; + if (timeout_us % 10) + retries++; + + do { + pci_read_config_dword(conf->pci_dev, VSE_CVP_STATUS, &val); + if ((val & status_mask) == status_val) + return 0; + + /* use small usleep value to re-check and break early */ + usleep_range(10, 11); + } while (--retries); + + return -ETIMEDOUT; +} + +static int altera_cvp_teardown(struct fpga_manager *mgr, + struct fpga_image_info *info) +{ + struct altera_cvp_conf *conf = mgr->priv; + struct pci_dev *pdev = conf->pci_dev; + int ret; + u32 val; + + /* STEP 12 - reset START_XFER bit */ + pci_read_config_dword(pdev, VSE_CVP_PROG_CTRL, &val); + val &= ~VSE_CVP_PROG_CTRL_START_XFER; + pci_write_config_dword(pdev, VSE_CVP_PROG_CTRL, val); + + /* STEP 13 - reset CVP_CONFIG bit */ + val &= ~VSE_CVP_PROG_CTRL_CONFIG; + pci_write_config_dword(pdev, VSE_CVP_PROG_CTRL, val); + + /* + * STEP 14 + * - set CVP_NUMCLKS to 1 and then issue CVP_DUMMY_WR dummy + * writes to the HIP + */ + altera_cvp_dummy_write(conf); /* from CVP clock to internal clock */ + + /* STEP 15 - poll CVP_CONFIG_READY bit for 0 with 10us timeout */ + ret = altera_cvp_wait_status(conf, VSE_CVP_STATUS_CFG_RDY, 0, 10); + if (ret) + dev_err(&mgr->dev, "CFG_RDY == 0 timeout\n"); + + return ret; +} + +static int altera_cvp_write_init(struct fpga_manager *mgr, + struct fpga_image_info *info, + const char *buf, size_t count) +{ + struct altera_cvp_conf *conf = mgr->priv; + struct pci_dev *pdev = conf->pci_dev; + u32 iflags, val; + int ret; + + iflags = info ? info->flags : 0; + + if (iflags & FPGA_MGR_PARTIAL_RECONFIG) { + dev_err(&mgr->dev, "Partial reconfiguration not supported.\n"); + return -EINVAL; + } + + /* Determine allowed clock to data ratio */ + if (iflags & FPGA_MGR_COMPRESSED_BITSTREAM) + conf->numclks = 8; /* ratio for all compressed images */ + else if (iflags & FPGA_MGR_ENCRYPTED_BITSTREAM) + conf->numclks = 4; /* for uncompressed and encrypted images */ + else + conf->numclks = 1; /* for uncompressed and unencrypted images */ + + /* STEP 1 - read CVP status and check CVP_EN flag */ + pci_read_config_dword(pdev, VSE_CVP_STATUS, &val); + if (!(val & VSE_CVP_STATUS_CVP_EN)) { + dev_err(&mgr->dev, "CVP mode off: 0x%04x\n", val); + return -ENODEV; + } + + if (val & VSE_CVP_STATUS_CFG_RDY) { + dev_warn(&mgr->dev, "CvP already started, teardown first\n"); + ret = altera_cvp_teardown(mgr, info); + if (ret) + return ret; + } + + /* + * STEP 2 + * - set HIP_CLK_SEL and CVP_MODE (must be set in the order mentioned) + */ + /* switch from fabric to PMA clock */ + pci_read_config_dword(pdev, VSE_CVP_MODE_CTRL, &val); + val |= VSE_CVP_MODE_CTRL_HIP_CLK_SEL; + pci_write_config_dword(pdev, VSE_CVP_MODE_CTRL, val); + + /* set CVP mode */ + pci_read_config_dword(pdev, VSE_CVP_MODE_CTRL, &val); + val |= VSE_CVP_MODE_CTRL_CVP_MODE; + pci_write_config_dword(pdev, VSE_CVP_MODE_CTRL, val); + + /* + * STEP 3 + * - set CVP_NUMCLKS to 1 and issue CVP_DUMMY_WR dummy writes to the HIP + */ + altera_cvp_dummy_write(conf); + + /* STEP 4 - set CVP_CONFIG bit */ + pci_read_config_dword(pdev, VSE_CVP_PROG_CTRL, &val); + /* request control block to begin transfer using CVP */ + val |= VSE_CVP_PROG_CTRL_CONFIG; + pci_write_config_dword(pdev, VSE_CVP_PROG_CTRL, val); + + /* STEP 5 - poll CVP_CONFIG READY for 1 with 10us timeout */ + ret = altera_cvp_wait_status(conf, VSE_CVP_STATUS_CFG_RDY, + VSE_CVP_STATUS_CFG_RDY, 10); + if (ret) { + dev_warn(&mgr->dev, "CFG_RDY == 1 timeout\n"); + return ret; + } + + /* + * STEP 6 + * - set CVP_NUMCLKS to 1 and issue CVP_DUMMY_WR dummy writes to the HIP + */ + altera_cvp_dummy_write(conf); + + /* STEP 7 - set START_XFER */ + pci_read_config_dword(pdev, VSE_CVP_PROG_CTRL, &val); + val |= VSE_CVP_PROG_CTRL_START_XFER; + pci_write_config_dword(pdev, VSE_CVP_PROG_CTRL, val); + + /* STEP 8 - start transfer (set CVP_NUMCLKS for bitstream) */ + pci_read_config_dword(pdev, VSE_CVP_MODE_CTRL, &val); + val &= ~VSE_CVP_MODE_CTRL_NUMCLKS_MASK; + val |= conf->numclks << VSE_CVP_MODE_CTRL_NUMCLKS_OFF; + pci_write_config_dword(pdev, VSE_CVP_MODE_CTRL, val); + + return 0; +} + +static inline int altera_cvp_chk_error(struct fpga_manager *mgr, size_t bytes) +{ + struct altera_cvp_conf *conf = mgr->priv; + u32 val; + + /* STEP 10 (optional) - check CVP_CONFIG_ERROR flag */ + pci_read_config_dword(conf->pci_dev, VSE_CVP_STATUS, &val); + if (val & VSE_CVP_STATUS_CFG_ERR) { + dev_err(&mgr->dev, "CVP_CONFIG_ERROR after %zu bytes!\n", + bytes); + return -EPROTO; + } + return 0; +} + +static int altera_cvp_write(struct fpga_manager *mgr, const char *buf, + size_t count) +{ + struct altera_cvp_conf *conf = mgr->priv; + const u32 *data; + size_t done, remaining; + int status = 0; + u32 mask; + + /* STEP 9 - write 32-bit data from RBF file to CVP data register */ + data = (u32 *)buf; + remaining = count; + done = 0; + + while (remaining >= 4) { + conf->write_data(conf, *data++); + done += 4; + remaining -= 4; + + /* + * STEP 10 (optional) and STEP 11 + * - check error flag + * - loop until data transfer completed + * Config images can be huge (more than 40 MiB), so + * only check after a new 4k data block has been written. + * This reduces the number of checks and speeds up the + * configuration process. + */ + if (altera_cvp_chkcfg && !(done % SZ_4K)) { + status = altera_cvp_chk_error(mgr, done); + if (status < 0) + return status; + } + } + + /* write up to 3 trailing bytes, if any */ + mask = BIT(remaining * 8) - 1; + if (mask) + conf->write_data(conf, *data & mask); + + if (altera_cvp_chkcfg) + status = altera_cvp_chk_error(mgr, count); + + return status; +} + +static int altera_cvp_write_complete(struct fpga_manager *mgr, + struct fpga_image_info *info) +{ + struct altera_cvp_conf *conf = mgr->priv; + struct pci_dev *pdev = conf->pci_dev; + int ret; + u32 mask; + u32 val; + + ret = altera_cvp_teardown(mgr, info); + if (ret) + return ret; + + /* STEP 16 - check CVP_CONFIG_ERROR_LATCHED bit */ + pci_read_config_dword(pdev, VSE_UNCOR_ERR_STATUS, &val); + if (val & VSE_UNCOR_ERR_CVP_CFG_ERR) { + dev_err(&mgr->dev, "detected CVP_CONFIG_ERROR_LATCHED!\n"); + return -EPROTO; + } + + /* STEP 17 - reset CVP_MODE and HIP_CLK_SEL bit */ + pci_read_config_dword(pdev, VSE_CVP_MODE_CTRL, &val); + val &= ~VSE_CVP_MODE_CTRL_HIP_CLK_SEL; + val &= ~VSE_CVP_MODE_CTRL_CVP_MODE; + pci_write_config_dword(pdev, VSE_CVP_MODE_CTRL, val); + + /* STEP 18 - poll PLD_CLK_IN_USE and USER_MODE bits */ + mask = VSE_CVP_STATUS_PLD_CLK_IN_USE | VSE_CVP_STATUS_USERMODE; + ret = altera_cvp_wait_status(conf, mask, mask, TIMEOUT_US); + if (ret) + dev_err(&mgr->dev, "PLD_CLK_IN_USE|USERMODE timeout\n"); + + return ret; +} + +static const struct fpga_manager_ops altera_cvp_ops = { + .state = altera_cvp_state, + .write_init = altera_cvp_write_init, + .write = altera_cvp_write, + .write_complete = altera_cvp_write_complete, +}; + +static ssize_t show_chkcfg(struct device_driver *dev, char *buf) +{ + return snprintf(buf, 3, "%d\n", altera_cvp_chkcfg); +} + +static ssize_t store_chkcfg(struct device_driver *drv, const char *buf, + size_t count) +{ + int ret; + + ret = kstrtobool(buf, &altera_cvp_chkcfg); + if (ret) + return ret; + + return count; +} + +static DRIVER_ATTR(chkcfg, 0600, show_chkcfg, store_chkcfg); + +static int altera_cvp_probe(struct pci_dev *pdev, + const struct pci_device_id *dev_id); +static void altera_cvp_remove(struct pci_dev *pdev); + +#define PCI_VENDOR_ID_ALTERA 0x1172 + +static struct pci_device_id altera_cvp_id_tbl[] = { + { PCI_VDEVICE(ALTERA, PCI_ANY_ID) }, + { } +}; +MODULE_DEVICE_TABLE(pci, altera_cvp_id_tbl); + +static struct pci_driver altera_cvp_driver = { + .name = DRV_NAME, + .id_table = altera_cvp_id_tbl, + .probe = altera_cvp_probe, + .remove = altera_cvp_remove, +}; + +static int altera_cvp_probe(struct pci_dev *pdev, + const struct pci_device_id *dev_id) +{ + struct altera_cvp_conf *conf; + u16 cmd, val; + int ret; + + /* + * First check if this is the expected FPGA device. PCI config + * space access works without enabling the PCI device, memory + * space access is enabled further down. + */ + pci_read_config_word(pdev, VSE_PCIE_EXT_CAP_ID, &val); + if (val != VSE_PCIE_EXT_CAP_ID_VAL) { + dev_err(&pdev->dev, "Wrong EXT_CAP_ID value 0x%x\n", val); + return -ENODEV; + } + + conf = devm_kzalloc(&pdev->dev, sizeof(*conf), GFP_KERNEL); + if (!conf) + return -ENOMEM; + + /* + * Enable memory BAR access. We cannot use pci_enable_device() here + * because it will make the driver unusable with FPGA devices that + * have additional big IOMEM resources (e.g. 4GiB BARs) on 32-bit + * platform. Such BARs will not have an assigned address range and + * pci_enable_device() will fail, complaining about not claimed BAR, + * even if the concerned BAR is not needed for FPGA configuration + * at all. Thus, enable the device via PCI config space command. + */ + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + if (!(cmd & PCI_COMMAND_MEMORY)) { + cmd |= PCI_COMMAND_MEMORY; + pci_write_config_word(pdev, PCI_COMMAND, cmd); + } + + ret = pci_request_region(pdev, CVP_BAR, "CVP"); + if (ret) { + dev_err(&pdev->dev, "Requesting CVP BAR region failed\n"); + goto err_disable; + } + + conf->pci_dev = pdev; + conf->write_data = altera_cvp_write_data_iomem; + + conf->map = pci_iomap(pdev, CVP_BAR, 0); + if (!conf->map) { + dev_warn(&pdev->dev, "Mapping CVP BAR failed\n"); + conf->write_data = altera_cvp_write_data_config; + } + + snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s @%s", + ALTERA_CVP_MGR_NAME, pci_name(pdev)); + + ret = fpga_mgr_register(&pdev->dev, conf->mgr_name, + &altera_cvp_ops, conf); + if (ret) + goto err_unmap; + + ret = driver_create_file(&altera_cvp_driver.driver, + &driver_attr_chkcfg); + if (ret) { + dev_err(&pdev->dev, "Can't create sysfs chkcfg file\n"); + fpga_mgr_unregister(&pdev->dev); + goto err_unmap; + } + + return 0; + +err_unmap: + pci_iounmap(pdev, conf->map); + pci_release_region(pdev, CVP_BAR); +err_disable: + cmd &= ~PCI_COMMAND_MEMORY; + pci_write_config_word(pdev, PCI_COMMAND, cmd); + return ret; +} + +static void altera_cvp_remove(struct pci_dev *pdev) +{ + struct fpga_manager *mgr = pci_get_drvdata(pdev); + struct altera_cvp_conf *conf = mgr->priv; + u16 cmd; + + driver_remove_file(&altera_cvp_driver.driver, &driver_attr_chkcfg); + fpga_mgr_unregister(&pdev->dev); + pci_iounmap(pdev, conf->map); + pci_release_region(pdev, CVP_BAR); + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + cmd &= ~PCI_COMMAND_MEMORY; + pci_write_config_word(pdev, PCI_COMMAND, cmd); +} + +module_pci_driver(altera_cvp_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Anatolij Gustschin <agust@denx.de>"); +MODULE_DESCRIPTION("Module to load Altera FPGA over CvP"); diff --git a/drivers/fpga/altera-hps2fpga.c b/drivers/fpga/altera-hps2fpga.c index 3066b805f2d0..406d2f10741f 100644 --- a/drivers/fpga/altera-hps2fpga.c +++ b/drivers/fpga/altera-hps2fpga.c @@ -66,7 +66,7 @@ static int alt_hps2fpga_enable_show(struct fpga_bridge *bridge) /* The L3 REMAP register is write only, so keep a cached value. */ static unsigned int l3_remap_shadow; -static spinlock_t l3_remap_lock; +static DEFINE_SPINLOCK(l3_remap_lock); static int _alt_hps2fpga_enable_set(struct altera_hps2fpga_data *priv, bool enable) @@ -143,9 +143,15 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) int ret; of_id = of_match_device(altera_fpga_of_match, dev); + if (!of_id) { + dev_err(dev, "failed to match device\n"); + return -ENODEV; + } + priv = (struct altera_hps2fpga_data *)of_id->data; - priv->bridge_reset = of_reset_control_get_by_index(dev->of_node, 0); + priv->bridge_reset = of_reset_control_get_exclusive_by_index(dev->of_node, + 0); if (IS_ERR(priv->bridge_reset)) { dev_err(dev, "Could not get %s reset control\n", priv->name); return PTR_ERR(priv->bridge_reset); @@ -171,8 +177,6 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) return -EBUSY; } - spin_lock_init(&l3_remap_lock); - if (!of_property_read_u32(dev->of_node, "bridge-enable", &enable)) { if (enable > 1) { dev_warn(dev, "invalid bridge-enable %u > 1\n", enable); diff --git a/drivers/fpga/altera-ps-spi.c b/drivers/fpga/altera-ps-spi.c new file mode 100644 index 000000000000..14f14efdf0d5 --- /dev/null +++ b/drivers/fpga/altera-ps-spi.c @@ -0,0 +1,308 @@ +/* + * Altera Passive Serial SPI Driver + * + * Copyright (c) 2017 United Western Technologies, Corporation + * + * Joshua Clayton <stillcompiling@gmail.com> + * + * 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. + * + * Manage Altera FPGA firmware that is loaded over SPI using the passive + * serial configuration method. + * Firmware must be in binary "rbf" format. + * Works on Arria 10, Cyclone V and Stratix V. Should work on Cyclone series. + * May work on other Altera FPGAs. + */ + +#include <linux/bitrev.h> +#include <linux/delay.h> +#include <linux/fpga/fpga-mgr.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/of_gpio.h> +#include <linux/of_device.h> +#include <linux/spi/spi.h> +#include <linux/sizes.h> + +enum altera_ps_devtype { + CYCLONE5, + ARRIA10, +}; + +struct altera_ps_data { + enum altera_ps_devtype devtype; + int status_wait_min_us; + int status_wait_max_us; + int t_cfg_us; + int t_st2ck_us; +}; + +struct altera_ps_conf { + struct gpio_desc *config; + struct gpio_desc *confd; + struct gpio_desc *status; + struct spi_device *spi; + const struct altera_ps_data *data; + u32 info_flags; + char mgr_name[64]; +}; + +/* | Arria 10 | Cyclone5 | Stratix5 | + * t_CF2ST0 | [; 600] | [; 600] | [; 600] |ns + * t_CFG | [2;] | [2;] | [2;] |µs + * t_STATUS | [268; 3000] | [268; 1506] | [268; 1506] |µs + * t_CF2ST1 | [; 3000] | [; 1506] | [; 1506] |µs + * t_CF2CK | [3010;] | [1506;] | [1506;] |µs + * t_ST2CK | [10;] | [2;] | [2;] |µs + * t_CD2UM | [175; 830] | [175; 437] | [175; 437] |µs + */ +static struct altera_ps_data c5_data = { + /* these values for Cyclone5 are compatible with Stratix5 */ + .devtype = CYCLONE5, + .status_wait_min_us = 268, + .status_wait_max_us = 1506, + .t_cfg_us = 2, + .t_st2ck_us = 2, +}; + +static struct altera_ps_data a10_data = { + .devtype = ARRIA10, + .status_wait_min_us = 268, /* min(t_STATUS) */ + .status_wait_max_us = 3000, /* max(t_CF2ST1) */ + .t_cfg_us = 2, /* max { min(t_CFG), max(tCF2ST0) } */ + .t_st2ck_us = 10, /* min(t_ST2CK) */ +}; + +static const struct of_device_id of_ef_match[] = { + { .compatible = "altr,fpga-passive-serial", .data = &c5_data }, + { .compatible = "altr,fpga-arria10-passive-serial", .data = &a10_data }, + {} +}; +MODULE_DEVICE_TABLE(of, of_ef_match); + +static enum fpga_mgr_states altera_ps_state(struct fpga_manager *mgr) +{ + struct altera_ps_conf *conf = mgr->priv; + + if (gpiod_get_value_cansleep(conf->status)) + return FPGA_MGR_STATE_RESET; + + return FPGA_MGR_STATE_UNKNOWN; +} + +static inline void altera_ps_delay(int delay_us) +{ + if (delay_us > 10) + usleep_range(delay_us, delay_us + 5); + else + udelay(delay_us); +} + +static int altera_ps_write_init(struct fpga_manager *mgr, + struct fpga_image_info *info, + const char *buf, size_t count) +{ + struct altera_ps_conf *conf = mgr->priv; + int min, max, waits; + int i; + + conf->info_flags = info->flags; + + if (info->flags & FPGA_MGR_PARTIAL_RECONFIG) { + dev_err(&mgr->dev, "Partial reconfiguration not supported.\n"); + return -EINVAL; + } + + gpiod_set_value_cansleep(conf->config, 1); + + /* wait min reset pulse time */ + altera_ps_delay(conf->data->t_cfg_us); + + if (!gpiod_get_value_cansleep(conf->status)) { + dev_err(&mgr->dev, "Status pin failed to show a reset\n"); + return -EIO; + } + + gpiod_set_value_cansleep(conf->config, 0); + + min = conf->data->status_wait_min_us; + max = conf->data->status_wait_max_us; + waits = max / min; + if (max % min) + waits++; + + /* wait for max { max(t_STATUS), max(t_CF2ST1) } */ + for (i = 0; i < waits; i++) { + usleep_range(min, min + 10); + if (!gpiod_get_value_cansleep(conf->status)) { + /* wait for min(t_ST2CK)*/ + altera_ps_delay(conf->data->t_st2ck_us); + return 0; + } + } + + dev_err(&mgr->dev, "Status pin not ready.\n"); + return -EIO; +} + +static void rev_buf(char *buf, size_t len) +{ + u32 *fw32 = (u32 *)buf; + size_t extra_bytes = (len & 0x03); + const u32 *fw_end = (u32 *)(buf + len - extra_bytes); + + /* set buffer to lsb first */ + while (fw32 < fw_end) { + *fw32 = bitrev8x4(*fw32); + fw32++; + } + + if (extra_bytes) { + buf = (char *)fw_end; + while (extra_bytes) { + *buf = bitrev8(*buf); + buf++; + extra_bytes--; + } + } +} + +static int altera_ps_write(struct fpga_manager *mgr, const char *buf, + size_t count) +{ + struct altera_ps_conf *conf = mgr->priv; + const char *fw_data = buf; + const char *fw_data_end = fw_data + count; + + while (fw_data < fw_data_end) { + int ret; + size_t stride = min_t(size_t, fw_data_end - fw_data, SZ_4K); + + if (!(conf->info_flags & FPGA_MGR_BITSTREAM_LSB_FIRST)) + rev_buf((char *)fw_data, stride); + + ret = spi_write(conf->spi, fw_data, stride); + if (ret) { + dev_err(&mgr->dev, "spi error in firmware write: %d\n", + ret); + return ret; + } + fw_data += stride; + } + + return 0; +} + +static int altera_ps_write_complete(struct fpga_manager *mgr, + struct fpga_image_info *info) +{ + struct altera_ps_conf *conf = mgr->priv; + const char dummy[] = {0}; + int ret; + + if (gpiod_get_value_cansleep(conf->status)) { + dev_err(&mgr->dev, "Error during configuration.\n"); + return -EIO; + } + + if (!IS_ERR(conf->confd)) { + if (!gpiod_get_raw_value_cansleep(conf->confd)) { + dev_err(&mgr->dev, "CONF_DONE is inactive!\n"); + return -EIO; + } + } + + /* + * After CONF_DONE goes high, send two additional falling edges on DCLK + * to begin initialization and enter user mode + */ + ret = spi_write(conf->spi, dummy, 1); + if (ret) { + dev_err(&mgr->dev, "spi error during end sequence: %d\n", ret); + return ret; + } + + return 0; +} + +static const struct fpga_manager_ops altera_ps_ops = { + .state = altera_ps_state, + .write_init = altera_ps_write_init, + .write = altera_ps_write, + .write_complete = altera_ps_write_complete, +}; + +static int altera_ps_probe(struct spi_device *spi) +{ + struct altera_ps_conf *conf; + const struct of_device_id *of_id; + + conf = devm_kzalloc(&spi->dev, sizeof(*conf), GFP_KERNEL); + if (!conf) + return -ENOMEM; + + of_id = of_match_device(of_ef_match, &spi->dev); + if (!of_id) + return -ENODEV; + + conf->data = of_id->data; + conf->spi = spi; + conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_HIGH); + if (IS_ERR(conf->config)) { + dev_err(&spi->dev, "Failed to get config gpio: %ld\n", + PTR_ERR(conf->config)); + return PTR_ERR(conf->config); + } + + conf->status = devm_gpiod_get(&spi->dev, "nstat", GPIOD_IN); + if (IS_ERR(conf->status)) { + dev_err(&spi->dev, "Failed to get status gpio: %ld\n", + PTR_ERR(conf->status)); + return PTR_ERR(conf->status); + } + + conf->confd = devm_gpiod_get(&spi->dev, "confd", GPIOD_IN); + if (IS_ERR(conf->confd)) { + dev_warn(&spi->dev, "Not using confd gpio: %ld\n", + PTR_ERR(conf->confd)); + } + + /* Register manager with unique name */ + snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s %s", + dev_driver_string(&spi->dev), dev_name(&spi->dev)); + + return fpga_mgr_register(&spi->dev, conf->mgr_name, + &altera_ps_ops, conf); +} + +static int altera_ps_remove(struct spi_device *spi) +{ + fpga_mgr_unregister(&spi->dev); + + return 0; +} + +static const struct spi_device_id altera_ps_spi_ids[] = { + {"cyclone-ps-spi", 0}, + {} +}; +MODULE_DEVICE_TABLE(spi, altera_ps_spi_ids); + +static struct spi_driver altera_ps_driver = { + .driver = { + .name = "altera-ps-spi", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(of_ef_match), + }, + .id_table = altera_ps_spi_ids, + .probe = altera_ps_probe, + .remove = altera_ps_remove, +}; + +module_spi_driver(altera_ps_driver) + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Joshua Clayton <stillcompiling@gmail.com>"); +MODULE_DESCRIPTION("Module to load Altera FPGA firmware over SPI"); diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index 3b6b2f4182a1..d9ab7c75b14f 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -319,8 +319,8 @@ static int child_regions_with_firmware(struct device_node *overlay) of_node_put(child_region); if (ret) - pr_err("firmware-name not allowed in child FPGA region: %s", - child_region->full_name); + pr_err("firmware-name not allowed in child FPGA region: %pOF", + child_region); return ret; } diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index e57cc40cb768..63ac1c6a825f 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -177,6 +177,11 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, &vmbus_connection.chn_msg_list); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); + if (newchannel->rescind) { + err = -ENODEV; + goto error_free_gpadl; + } + ret = vmbus_post_msg(open_msg, sizeof(struct vmbus_channel_open_channel), true); @@ -421,6 +426,11 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); + if (channel->rescind) { + ret = -ENODEV; + goto cleanup; + } + ret = vmbus_post_msg(gpadlmsg, msginfo->msgsize - sizeof(*msginfo), true); if (ret != 0) @@ -494,6 +504,10 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) list_add_tail(&info->msglistentry, &vmbus_connection.chn_msg_list); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); + + if (channel->rescind) + goto post_msg_err; + ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown), true); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 4bbb8dea4727..968af173c4c1 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -451,6 +451,12 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) /* Make sure this is a new offer */ mutex_lock(&vmbus_connection.channel_mutex); + /* + * Now that we have acquired the channel_mutex, + * we can release the potentially racing rescind thread. + */ + atomic_dec(&vmbus_connection.offer_in_progress); + list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { if (!uuid_le_cmp(channel->offermsg.offer.if_type, newchannel->offermsg.offer.if_type) && @@ -481,7 +487,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) channel->num_sc++; spin_unlock_irqrestore(&channel->lock, flags); } else { - atomic_dec(&vmbus_connection.offer_in_progress); goto err_free_chan; } } @@ -510,7 +515,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) if (!fnew) { if (channel->sc_creation_callback != NULL) channel->sc_creation_callback(newchannel); - atomic_dec(&vmbus_connection.offer_in_progress); return; } @@ -541,7 +545,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) goto err_deq_chan; } - atomic_dec(&vmbus_connection.offer_in_progress); + newchannel->probe_done = true; return; err_deq_chan: @@ -882,8 +886,27 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) channel->rescind = true; spin_unlock_irqrestore(&channel->lock, flags); + /* + * Now that we have posted the rescind state, perform + * rescind related cleanup. + */ vmbus_rescind_cleanup(channel); + /* + * Now wait for offer handling to complete. + */ + while (READ_ONCE(channel->probe_done) == false) { + /* + * We wait here until any channel offer is currently + * being processed. + */ + msleep(1); + } + + /* + * At this point, the rescind handling can proceed safely. + */ + if (channel->device_obj) { if (channel->chn_rescind_callback) { channel->chn_rescind_callback(channel); diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index f5728deff893..db0e6652d7ef 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -584,10 +584,6 @@ static int hv_memory_notifier(struct notifier_block *nb, unsigned long val, switch (val) { case MEM_ONLINE: - spin_lock_irqsave(&dm_device.ha_lock, flags); - dm_device.num_pages_onlined += mem->nr_pages; - spin_unlock_irqrestore(&dm_device.ha_lock, flags); - /* Fall through */ case MEM_CANCEL_ONLINE: if (dm_device.ha_waiting) { dm_device.ha_waiting = false; @@ -644,6 +640,9 @@ static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg) __online_page_set_limits(pg); __online_page_increment_counters(pg); __online_page_free(pg); + + WARN_ON_ONCE(!spin_is_locked(&dm_device.ha_lock)); + dm_device.num_pages_onlined++; } static void hv_bring_pgs_online(struct hv_hotadd_state *has, @@ -1036,8 +1035,8 @@ static void process_info(struct hv_dynmem_device *dm, struct dm_info_msg *msg) if (info_hdr->data_size == sizeof(__u64)) { __u64 *max_page_count = (__u64 *)&info_hdr[1]; - pr_info("INFO_TYPE_MAX_PAGE_CNT = %llu\n", - *max_page_count); + pr_info("Max. dynamic memory size: %llu MB\n", + (*max_page_count) >> (20 - PAGE_SHIFT)); } break; @@ -1656,6 +1655,7 @@ static int balloon_probe(struct hv_device *dev, } dm_device.state = DM_INITIALIZED; + last_post_time = jiffies; return 0; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index 9a90b915b5be..5eed1e7da15c 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -304,7 +304,7 @@ static int process_ob_ipinfo(void *in_msg, void *out_msg, int op) strlen((char *)in->body.kvp_ip_val.adapter_id), UTF16_HOST_ENDIAN, (wchar_t *)out->kvp_ip_val.adapter_id, - MAX_IP_ADDR_SIZE); + MAX_ADAPTER_ID_SIZE); if (len < 0) return len; diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 1f450c39a9b0..12eb8caa4263 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -29,6 +29,7 @@ #include <linux/uio.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/prefetch.h> #include "hyperv_vmbus.h" @@ -94,30 +95,6 @@ hv_set_next_write_location(struct hv_ring_buffer_info *ring_info, ring_info->ring_buffer->write_index = next_write_location; } -/* Get the next read location for the specified ring buffer. */ -static inline u32 -hv_get_next_read_location(const struct hv_ring_buffer_info *ring_info) -{ - return ring_info->ring_buffer->read_index; -} - -/* - * Get the next read location + offset for the specified ring buffer. - * This allows the caller to skip. - */ -static inline u32 -hv_get_next_readlocation_withoffset(const struct hv_ring_buffer_info *ring_info, - u32 offset) -{ - u32 next = ring_info->ring_buffer->read_index; - - next += offset; - if (next >= ring_info->ring_datasize) - next -= ring_info->ring_datasize; - - return next; -} - /* Set the next read location for the specified ring buffer. */ static inline void hv_set_next_read_location(struct hv_ring_buffer_info *ring_info, @@ -142,29 +119,6 @@ hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info) } /* - * Helper routine to copy to source from ring buffer. - * Assume there is enough room. Handles wrap-around in src case only!! - */ -static u32 hv_copyfrom_ringbuffer( - const struct hv_ring_buffer_info *ring_info, - void *dest, - u32 destlen, - u32 start_read_offset) -{ - void *ring_buffer = hv_get_ring_buffer(ring_info); - u32 ring_buffer_size = hv_get_ring_buffersize(ring_info); - - memcpy(dest, ring_buffer + start_read_offset, destlen); - - start_read_offset += destlen; - if (start_read_offset >= ring_buffer_size) - start_read_offset -= ring_buffer_size; - - return start_read_offset; -} - - -/* * Helper routine to copy from source to ring buffer. * Assume there is enough room. Handles wrap-around in dest case only!! */ @@ -334,33 +288,22 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, return 0; } -static inline void -init_cached_read_index(struct hv_ring_buffer_info *rbi) -{ - rbi->cached_read_index = rbi->ring_buffer->read_index; -} - int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, u64 *requestid, bool raw) { - u32 bytes_avail_toread; - u32 next_read_location; - u64 prev_indices = 0; - struct vmpacket_descriptor desc; - u32 offset; - u32 packetlen; - struct hv_ring_buffer_info *inring_info = &channel->inbound; - - if (buflen <= 0) + struct vmpacket_descriptor *desc; + u32 packetlen, offset; + + if (unlikely(buflen == 0)) return -EINVAL; *buffer_actual_len = 0; *requestid = 0; - bytes_avail_toread = hv_get_bytes_to_read(inring_info); /* Make sure there is something to read */ - if (bytes_avail_toread < sizeof(desc)) { + desc = hv_pkt_iter_first(channel); + if (desc == NULL) { /* * No error is set when there is even no header, drivers are * supposed to analyze buffer_actual_len. @@ -368,48 +311,22 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, return 0; } - init_cached_read_index(inring_info); - - next_read_location = hv_get_next_read_location(inring_info); - next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc, - sizeof(desc), - next_read_location); - - offset = raw ? 0 : (desc.offset8 << 3); - packetlen = (desc.len8 << 3) - offset; + offset = raw ? 0 : (desc->offset8 << 3); + packetlen = (desc->len8 << 3) - offset; *buffer_actual_len = packetlen; - *requestid = desc.trans_id; - - if (bytes_avail_toread < packetlen + offset) - return -EAGAIN; + *requestid = desc->trans_id; - if (packetlen > buflen) + if (unlikely(packetlen > buflen)) return -ENOBUFS; - next_read_location = - hv_get_next_readlocation_withoffset(inring_info, offset); + /* since ring is double mapped, only one copy is necessary */ + memcpy(buffer, (const char *)desc + offset, packetlen); - next_read_location = hv_copyfrom_ringbuffer(inring_info, - buffer, - packetlen, - next_read_location); + /* Advance ring index to next packet descriptor */ + __hv_pkt_iter_next(channel, desc); - next_read_location = hv_copyfrom_ringbuffer(inring_info, - &prev_indices, - sizeof(u64), - next_read_location); - - /* - * Make sure all reads are done before we update the read index since - * the writer may start writing to the read area once the read index - * is updated. - */ - virt_mb(); - - /* Update the read index */ - hv_set_next_read_location(inring_info, next_read_location); - - hv_signal_on_read(channel); + /* Notify host of update */ + hv_pkt_iter_close(channel); return 0; } @@ -440,14 +357,16 @@ static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->inbound; - - /* set state for later hv_signal_on_read() */ - init_cached_read_index(rbi); + struct vmpacket_descriptor *desc; if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) return NULL; - return hv_get_ring_buffer(rbi) + rbi->priv_read_index; + desc = hv_get_ring_buffer(rbi) + rbi->priv_read_index; + if (desc) + prefetch((char *)desc + (desc->len8 << 3)); + + return desc; } EXPORT_SYMBOL_GPL(hv_pkt_iter_first); @@ -471,10 +390,7 @@ __hv_pkt_iter_next(struct vmbus_channel *channel, rbi->priv_read_index -= dsize; /* more data? */ - if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) - return NULL; - else - return hv_get_ring_buffer(rbi) + rbi->priv_read_index; + return hv_pkt_iter_first(channel); } EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); @@ -484,6 +400,7 @@ EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); void hv_pkt_iter_close(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->inbound; + u32 orig_write_sz = hv_get_bytes_to_write(rbi); /* * Make sure all reads are done before we update the read index since @@ -493,6 +410,40 @@ void hv_pkt_iter_close(struct vmbus_channel *channel) virt_rmb(); rbi->ring_buffer->read_index = rbi->priv_read_index; - hv_signal_on_read(channel); + /* + * Issue a full memory barrier before making the signaling decision. + * Here is the reason for having this barrier: + * If the reading of the pend_sz (in this function) + * were to be reordered and read before we commit the new read + * index (in the calling function) we could + * have a problem. If the host were to set the pending_sz after we + * have sampled pending_sz and go to sleep before we commit the + * read index, we could miss sending the interrupt. Issue a full + * memory barrier to address this. + */ + virt_mb(); + + /* If host has disabled notifications then skip */ + if (rbi->ring_buffer->interrupt_mask) + return; + + if (rbi->ring_buffer->feature_bits.feat_pending_send_sz) { + u32 pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); + + /* + * If there was space before we began iteration, + * then host was not blocked. Also handles case where + * pending_sz is zero then host has nothing pending + * and does not need to be signaled. + */ + if (orig_write_sz > pending_sz) + return; + + /* If pending write will not fit, don't give false hope. */ + if (hv_get_bytes_to_write(rbi) < pending_sz) + return; + } + + vmbus_setevent(channel); } EXPORT_SYMBOL_GPL(hv_pkt_iter_close); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index ed84e96715a0..43160a2eafe0 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -940,6 +940,9 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu) if (channel->offermsg.child_relid != relid) continue; + if (channel->rescind) + continue; + switch (channel->callback_mode) { case HV_CALL_ISR: vmbus_channel_isr(channel); diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index b0b766416306..d84819dc2468 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -60,6 +60,7 @@ lkdtm-$(CONFIG_LKDTM) += lkdtm_core.o lkdtm-$(CONFIG_LKDTM) += lkdtm_bugs.o lkdtm-$(CONFIG_LKDTM) += lkdtm_heap.o lkdtm-$(CONFIG_LKDTM) += lkdtm_perms.o +lkdtm-$(CONFIG_LKDTM) += lkdtm_refcount.o lkdtm-$(CONFIG_LKDTM) += lkdtm_rodata_objcopy.o lkdtm-$(CONFIG_LKDTM) += lkdtm_usercopy.o diff --git a/drivers/misc/aspeed-lpc-snoop.c b/drivers/misc/aspeed-lpc-snoop.c index 593905565b74..cb78c98bc78d 100644 --- a/drivers/misc/aspeed-lpc-snoop.c +++ b/drivers/misc/aspeed-lpc-snoop.c @@ -20,6 +20,7 @@ #include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/regmap.h> @@ -51,6 +52,13 @@ #define HICRB_ENSNP0D BIT(14) #define HICRB_ENSNP1D BIT(15) +struct aspeed_lpc_snoop_model_data { + /* The ast2400 has bits 14 and 15 as reserved, whereas the ast2500 + * can use them. + */ + unsigned int has_hicrb_ensnp; +}; + struct aspeed_lpc_snoop { struct regmap *regmap; int irq; @@ -123,10 +131,13 @@ static int aspeed_lpc_snoop_config_irq(struct aspeed_lpc_snoop *lpc_snoop, } static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop, - int channel, u16 lpc_port) + struct device *dev, + int channel, u16 lpc_port) { int rc = 0; u32 hicr5_en, snpwadr_mask, snpwadr_shift, hicrb_en; + const struct aspeed_lpc_snoop_model_data *model_data = + of_device_get_match_data(dev); /* Create FIFO datastructure */ rc = kfifo_alloc(&lpc_snoop->snoop_fifo[channel], @@ -155,7 +166,9 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop, regmap_update_bits(lpc_snoop->regmap, HICR5, hicr5_en, hicr5_en); regmap_update_bits(lpc_snoop->regmap, SNPWADR, snpwadr_mask, lpc_port << snpwadr_shift); - regmap_update_bits(lpc_snoop->regmap, HICRB, hicrb_en, hicrb_en); + if (model_data->has_hicrb_ensnp) + regmap_update_bits(lpc_snoop->regmap, HICRB, + hicrb_en, hicrb_en); return rc; } @@ -213,14 +226,14 @@ static int aspeed_lpc_snoop_probe(struct platform_device *pdev) if (rc) return rc; - rc = aspeed_lpc_enable_snoop(lpc_snoop, 0, port); + rc = aspeed_lpc_enable_snoop(lpc_snoop, dev, 0, port); if (rc) return rc; /* Configuration of 2nd snoop channel port is optional */ if (of_property_read_u32_index(dev->of_node, "snoop-ports", 1, &port) == 0) { - rc = aspeed_lpc_enable_snoop(lpc_snoop, 1, port); + rc = aspeed_lpc_enable_snoop(lpc_snoop, dev, 1, port); if (rc) aspeed_lpc_disable_snoop(lpc_snoop, 0); } @@ -239,8 +252,19 @@ static int aspeed_lpc_snoop_remove(struct platform_device *pdev) return 0; } +static const struct aspeed_lpc_snoop_model_data ast2400_model_data = { + .has_hicrb_ensnp = 0, +}; + +static const struct aspeed_lpc_snoop_model_data ast2500_model_data = { + .has_hicrb_ensnp = 1, +}; + static const struct of_device_id aspeed_lpc_snoop_match[] = { - { .compatible = "aspeed,ast2500-lpc-snoop" }, + { .compatible = "aspeed,ast2400-lpc-snoop", + .data = &ast2400_model_data }, + { .compatible = "aspeed,ast2500-lpc-snoop", + .data = &ast2500_model_data }, { }, }; diff --git a/drivers/misc/lkdtm.h b/drivers/misc/lkdtm.h index 3b4976396ec4..bfb6c45b6130 100644 --- a/drivers/misc/lkdtm.h +++ b/drivers/misc/lkdtm.h @@ -14,20 +14,17 @@ void lkdtm_EXCEPTION(void); void lkdtm_LOOP(void); void lkdtm_OVERFLOW(void); void lkdtm_CORRUPT_STACK(void); +void lkdtm_CORRUPT_STACK_STRONG(void); void lkdtm_UNALIGNED_LOAD_STORE_WRITE(void); void lkdtm_SOFTLOCKUP(void); void lkdtm_HARDLOCKUP(void); void lkdtm_SPINLOCKUP(void); void lkdtm_HUNG_TASK(void); -void lkdtm_REFCOUNT_SATURATE_INC(void); -void lkdtm_REFCOUNT_SATURATE_ADD(void); -void lkdtm_REFCOUNT_ZERO_DEC(void); -void lkdtm_REFCOUNT_ZERO_INC(void); -void lkdtm_REFCOUNT_ZERO_SUB(void); -void lkdtm_REFCOUNT_ZERO_ADD(void); void lkdtm_CORRUPT_LIST_ADD(void); void lkdtm_CORRUPT_LIST_DEL(void); void lkdtm_CORRUPT_USER_DS(void); +void lkdtm_STACK_GUARD_PAGE_LEADING(void); +void lkdtm_STACK_GUARD_PAGE_TRAILING(void); /* lkdtm_heap.c */ void lkdtm_OVERWRITE_ALLOCATION(void); @@ -49,6 +46,27 @@ void lkdtm_EXEC_RODATA(void); void lkdtm_EXEC_USERSPACE(void); void lkdtm_ACCESS_USERSPACE(void); +/* lkdtm_refcount.c */ +void lkdtm_REFCOUNT_INC_OVERFLOW(void); +void lkdtm_REFCOUNT_ADD_OVERFLOW(void); +void lkdtm_REFCOUNT_INC_NOT_ZERO_OVERFLOW(void); +void lkdtm_REFCOUNT_ADD_NOT_ZERO_OVERFLOW(void); +void lkdtm_REFCOUNT_DEC_ZERO(void); +void lkdtm_REFCOUNT_DEC_NEGATIVE(void); +void lkdtm_REFCOUNT_DEC_AND_TEST_NEGATIVE(void); +void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void); +void lkdtm_REFCOUNT_INC_ZERO(void); +void lkdtm_REFCOUNT_ADD_ZERO(void); +void lkdtm_REFCOUNT_INC_SATURATED(void); +void lkdtm_REFCOUNT_DEC_SATURATED(void); +void lkdtm_REFCOUNT_ADD_SATURATED(void); +void lkdtm_REFCOUNT_INC_NOT_ZERO_SATURATED(void); +void lkdtm_REFCOUNT_ADD_NOT_ZERO_SATURATED(void); +void lkdtm_REFCOUNT_DEC_AND_TEST_SATURATED(void); +void lkdtm_REFCOUNT_SUB_AND_TEST_SATURATED(void); +void lkdtm_REFCOUNT_TIMING(void); +void lkdtm_ATOMIC_TIMING(void); + /* lkdtm_rodata.c */ void lkdtm_rodata_do_nothing(void); diff --git a/drivers/misc/lkdtm_bugs.c b/drivers/misc/lkdtm_bugs.c index d9028ef50fbe..9e0b4f959987 100644 --- a/drivers/misc/lkdtm_bugs.c +++ b/drivers/misc/lkdtm_bugs.c @@ -6,9 +6,9 @@ */ #include "lkdtm.h" #include <linux/list.h> -#include <linux/refcount.h> #include <linux/sched.h> #include <linux/sched/signal.h> +#include <linux/sched/task_stack.h> #include <linux/uaccess.h> struct lkdtm_list { @@ -85,16 +85,31 @@ void lkdtm_OVERFLOW(void) static noinline void __lkdtm_CORRUPT_STACK(void *stack) { - memset(stack, 'a', 64); + memset(stack, '\xff', 64); } +/* This should trip the stack canary, not corrupt the return address. */ noinline void lkdtm_CORRUPT_STACK(void) { /* Use default char array length that triggers stack protection. */ - char data[8]; + char data[8] __aligned(sizeof(void *)); + + __lkdtm_CORRUPT_STACK(&data); + + pr_info("Corrupted stack containing char array ...\n"); +} + +/* Same as above but will only get a canary with -fstack-protector-strong */ +noinline void lkdtm_CORRUPT_STACK_STRONG(void) +{ + union { + unsigned short shorts[4]; + unsigned long *ptr; + } data __aligned(sizeof(void *)); + __lkdtm_CORRUPT_STACK(&data); - pr_info("Corrupted stack with '%16s'...\n", data); + pr_info("Corrupted stack containing union ...\n"); } void lkdtm_UNALIGNED_LOAD_STORE_WRITE(void) @@ -137,88 +152,6 @@ void lkdtm_HUNG_TASK(void) schedule(); } -void lkdtm_REFCOUNT_SATURATE_INC(void) -{ - refcount_t over = REFCOUNT_INIT(UINT_MAX - 1); - - pr_info("attempting good refcount decrement\n"); - refcount_dec(&over); - refcount_inc(&over); - - pr_info("attempting bad refcount inc overflow\n"); - refcount_inc(&over); - refcount_inc(&over); - if (refcount_read(&over) == UINT_MAX) - pr_err("Correctly stayed saturated, but no BUG?!\n"); - else - pr_err("Fail: refcount wrapped\n"); -} - -void lkdtm_REFCOUNT_SATURATE_ADD(void) -{ - refcount_t over = REFCOUNT_INIT(UINT_MAX - 1); - - pr_info("attempting good refcount decrement\n"); - refcount_dec(&over); - refcount_inc(&over); - - pr_info("attempting bad refcount add overflow\n"); - refcount_add(2, &over); - if (refcount_read(&over) == UINT_MAX) - pr_err("Correctly stayed saturated, but no BUG?!\n"); - else - pr_err("Fail: refcount wrapped\n"); -} - -void lkdtm_REFCOUNT_ZERO_DEC(void) -{ - refcount_t zero = REFCOUNT_INIT(1); - - pr_info("attempting bad refcount decrement to zero\n"); - refcount_dec(&zero); - if (refcount_read(&zero) == 0) - pr_err("Stayed at zero, but no BUG?!\n"); - else - pr_err("Fail: refcount went crazy\n"); -} - -void lkdtm_REFCOUNT_ZERO_SUB(void) -{ - refcount_t zero = REFCOUNT_INIT(1); - - pr_info("attempting bad refcount subtract past zero\n"); - if (!refcount_sub_and_test(2, &zero)) - pr_info("wrap attempt was noticed\n"); - if (refcount_read(&zero) == 1) - pr_err("Correctly stayed above 0, but no BUG?!\n"); - else - pr_err("Fail: refcount wrapped\n"); -} - -void lkdtm_REFCOUNT_ZERO_INC(void) -{ - refcount_t zero = REFCOUNT_INIT(0); - - pr_info("attempting bad refcount increment from zero\n"); - refcount_inc(&zero); - if (refcount_read(&zero) == 0) - pr_err("Stayed at zero, but no BUG?!\n"); - else - pr_err("Fail: refcount went past zero\n"); -} - -void lkdtm_REFCOUNT_ZERO_ADD(void) -{ - refcount_t zero = REFCOUNT_INIT(0); - - pr_info("attempting bad refcount addition from zero\n"); - refcount_add(2, &zero); - if (refcount_read(&zero) == 0) - pr_err("Stayed at zero, but no BUG?!\n"); - else - pr_err("Fail: refcount went past zero\n"); -} - void lkdtm_CORRUPT_LIST_ADD(void) { /* @@ -282,6 +215,7 @@ void lkdtm_CORRUPT_LIST_DEL(void) pr_err("list_del() corruption not detected!\n"); } +/* Test if unbalanced set_fs(KERNEL_DS)/set_fs(USER_DS) check exists. */ void lkdtm_CORRUPT_USER_DS(void) { pr_info("setting bad task size limit\n"); @@ -290,3 +224,31 @@ void lkdtm_CORRUPT_USER_DS(void) /* Make sure we do not keep running with a KERNEL_DS! */ force_sig(SIGKILL, current); } + +/* Test that VMAP_STACK is actually allocating with a leading guard page */ +void lkdtm_STACK_GUARD_PAGE_LEADING(void) +{ + const unsigned char *stack = task_stack_page(current); + const unsigned char *ptr = stack - 1; + volatile unsigned char byte; + + pr_info("attempting bad read from page below current stack\n"); + + byte = *ptr; + + pr_err("FAIL: accessed page before stack!\n"); +} + +/* Test that VMAP_STACK is actually allocating with a trailing guard page */ +void lkdtm_STACK_GUARD_PAGE_TRAILING(void) +{ + const unsigned char *stack = task_stack_page(current); + const unsigned char *ptr = stack + THREAD_SIZE; + volatile unsigned char byte; + + pr_info("attempting bad read from page above current stack\n"); + + byte = *ptr; + + pr_err("FAIL: accessed page after stack!\n"); +} diff --git a/drivers/misc/lkdtm_core.c b/drivers/misc/lkdtm_core.c index 42d2b8e31e6b..981b3ef71e47 100644 --- a/drivers/misc/lkdtm_core.c +++ b/drivers/misc/lkdtm_core.c @@ -201,6 +201,9 @@ struct crashtype crashtypes[] = { CRASHTYPE(CORRUPT_LIST_DEL), CRASHTYPE(CORRUPT_USER_DS), CRASHTYPE(CORRUPT_STACK), + CRASHTYPE(CORRUPT_STACK_STRONG), + CRASHTYPE(STACK_GUARD_PAGE_LEADING), + CRASHTYPE(STACK_GUARD_PAGE_TRAILING), CRASHTYPE(UNALIGNED_LOAD_STORE_WRITE), CRASHTYPE(OVERWRITE_ALLOCATION), CRASHTYPE(WRITE_AFTER_FREE), @@ -221,12 +224,25 @@ struct crashtype crashtypes[] = { CRASHTYPE(WRITE_RO), CRASHTYPE(WRITE_RO_AFTER_INIT), CRASHTYPE(WRITE_KERN), - CRASHTYPE(REFCOUNT_SATURATE_INC), - CRASHTYPE(REFCOUNT_SATURATE_ADD), - CRASHTYPE(REFCOUNT_ZERO_DEC), - CRASHTYPE(REFCOUNT_ZERO_INC), - CRASHTYPE(REFCOUNT_ZERO_SUB), - CRASHTYPE(REFCOUNT_ZERO_ADD), + CRASHTYPE(REFCOUNT_INC_OVERFLOW), + CRASHTYPE(REFCOUNT_ADD_OVERFLOW), + CRASHTYPE(REFCOUNT_INC_NOT_ZERO_OVERFLOW), + CRASHTYPE(REFCOUNT_ADD_NOT_ZERO_OVERFLOW), + CRASHTYPE(REFCOUNT_DEC_ZERO), + CRASHTYPE(REFCOUNT_DEC_NEGATIVE), + CRASHTYPE(REFCOUNT_DEC_AND_TEST_NEGATIVE), + CRASHTYPE(REFCOUNT_SUB_AND_TEST_NEGATIVE), + CRASHTYPE(REFCOUNT_INC_ZERO), + CRASHTYPE(REFCOUNT_ADD_ZERO), + CRASHTYPE(REFCOUNT_INC_SATURATED), + CRASHTYPE(REFCOUNT_DEC_SATURATED), + CRASHTYPE(REFCOUNT_ADD_SATURATED), + CRASHTYPE(REFCOUNT_INC_NOT_ZERO_SATURATED), + CRASHTYPE(REFCOUNT_ADD_NOT_ZERO_SATURATED), + CRASHTYPE(REFCOUNT_DEC_AND_TEST_SATURATED), + CRASHTYPE(REFCOUNT_SUB_AND_TEST_SATURATED), + CRASHTYPE(REFCOUNT_TIMING), + CRASHTYPE(ATOMIC_TIMING), CRASHTYPE(USERCOPY_HEAP_SIZE_TO), CRASHTYPE(USERCOPY_HEAP_SIZE_FROM), CRASHTYPE(USERCOPY_HEAP_FLAG_TO), diff --git a/drivers/misc/lkdtm_refcount.c b/drivers/misc/lkdtm_refcount.c new file mode 100644 index 000000000000..29af0152a337 --- /dev/null +++ b/drivers/misc/lkdtm_refcount.c @@ -0,0 +1,400 @@ +/* + * This is for all the tests related to refcount bugs (e.g. overflow, + * underflow, reaching zero untested, etc). + */ +#include "lkdtm.h" +#include <linux/refcount.h> + +#ifdef CONFIG_REFCOUNT_FULL +#define REFCOUNT_MAX (UINT_MAX - 1) +#define REFCOUNT_SATURATED UINT_MAX +#else +#define REFCOUNT_MAX INT_MAX +#define REFCOUNT_SATURATED (INT_MIN / 2) +#endif + +static void overflow_check(refcount_t *ref) +{ + switch (refcount_read(ref)) { + case REFCOUNT_SATURATED: + pr_info("Overflow detected: saturated\n"); + break; + case REFCOUNT_MAX: + pr_warn("Overflow detected: unsafely reset to max\n"); + break; + default: + pr_err("Fail: refcount wrapped to %d\n", refcount_read(ref)); + } +} + +/* + * A refcount_inc() above the maximum value of the refcount implementation, + * should at least saturate, and at most also WARN. + */ +void lkdtm_REFCOUNT_INC_OVERFLOW(void) +{ + refcount_t over = REFCOUNT_INIT(REFCOUNT_MAX - 1); + + pr_info("attempting good refcount_inc() without overflow\n"); + refcount_dec(&over); + refcount_inc(&over); + + pr_info("attempting bad refcount_inc() overflow\n"); + refcount_inc(&over); + refcount_inc(&over); + + overflow_check(&over); +} + +/* refcount_add() should behave just like refcount_inc() above. */ +void lkdtm_REFCOUNT_ADD_OVERFLOW(void) +{ + refcount_t over = REFCOUNT_INIT(REFCOUNT_MAX - 1); + + pr_info("attempting good refcount_add() without overflow\n"); + refcount_dec(&over); + refcount_dec(&over); + refcount_dec(&over); + refcount_dec(&over); + refcount_add(4, &over); + + pr_info("attempting bad refcount_add() overflow\n"); + refcount_add(4, &over); + + overflow_check(&over); +} + +/* refcount_inc_not_zero() should behave just like refcount_inc() above. */ +void lkdtm_REFCOUNT_INC_NOT_ZERO_OVERFLOW(void) +{ + refcount_t over = REFCOUNT_INIT(REFCOUNT_MAX); + + pr_info("attempting bad refcount_inc_not_zero() overflow\n"); + if (!refcount_inc_not_zero(&over)) + pr_warn("Weird: refcount_inc_not_zero() reported zero\n"); + + overflow_check(&over); +} + +/* refcount_add_not_zero() should behave just like refcount_inc() above. */ +void lkdtm_REFCOUNT_ADD_NOT_ZERO_OVERFLOW(void) +{ + refcount_t over = REFCOUNT_INIT(REFCOUNT_MAX); + + pr_info("attempting bad refcount_add_not_zero() overflow\n"); + if (!refcount_add_not_zero(6, &over)) + pr_warn("Weird: refcount_add_not_zero() reported zero\n"); + + overflow_check(&over); +} + +static void check_zero(refcount_t *ref) +{ + switch (refcount_read(ref)) { + case REFCOUNT_SATURATED: + pr_info("Zero detected: saturated\n"); + break; + case REFCOUNT_MAX: + pr_warn("Zero detected: unsafely reset to max\n"); + break; + case 0: + pr_warn("Still at zero: refcount_inc/add() must not inc-from-0\n"); + break; + default: + pr_err("Fail: refcount went crazy: %d\n", refcount_read(ref)); + } +} + +/* + * A refcount_dec(), as opposed to a refcount_dec_and_test(), when it hits + * zero it should either saturate (when inc-from-zero isn't protected) + * or stay at zero (when inc-from-zero is protected) and should WARN for both. + */ +void lkdtm_REFCOUNT_DEC_ZERO(void) +{ + refcount_t zero = REFCOUNT_INIT(2); + + pr_info("attempting good refcount_dec()\n"); + refcount_dec(&zero); + + pr_info("attempting bad refcount_dec() to zero\n"); + refcount_dec(&zero); + + check_zero(&zero); +} + +static void check_negative(refcount_t *ref, int start) +{ + /* + * CONFIG_REFCOUNT_FULL refuses to move a refcount at all on an + * over-sub, so we have to track our starting position instead of + * looking only at zero-pinning. + */ + if (refcount_read(ref) == start) { + pr_warn("Still at %d: refcount_inc/add() must not inc-from-0\n", + start); + return; + } + + switch (refcount_read(ref)) { + case REFCOUNT_SATURATED: + pr_info("Negative detected: saturated\n"); + break; + case REFCOUNT_MAX: + pr_warn("Negative detected: unsafely reset to max\n"); + break; + default: + pr_err("Fail: refcount went crazy: %d\n", refcount_read(ref)); + } +} + +/* A refcount_dec() going negative should saturate and may WARN. */ +void lkdtm_REFCOUNT_DEC_NEGATIVE(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_dec() below zero\n"); + refcount_dec(&neg); + + check_negative(&neg, 0); +} + +/* + * A refcount_dec_and_test() should act like refcount_dec() above when + * going negative. + */ +void lkdtm_REFCOUNT_DEC_AND_TEST_NEGATIVE(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_dec_and_test() below zero\n"); + if (refcount_dec_and_test(&neg)) + pr_warn("Weird: refcount_dec_and_test() reported zero\n"); + + check_negative(&neg, 0); +} + +/* + * A refcount_sub_and_test() should act like refcount_dec_and_test() + * above when going negative. + */ +void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void) +{ + refcount_t neg = REFCOUNT_INIT(3); + + pr_info("attempting bad refcount_sub_and_test() below zero\n"); + if (refcount_sub_and_test(5, &neg)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_negative(&neg, 3); +} + +static void check_from_zero(refcount_t *ref) +{ + switch (refcount_read(ref)) { + case 0: + pr_info("Zero detected: stayed at zero\n"); + break; + case REFCOUNT_SATURATED: + pr_info("Zero detected: saturated\n"); + break; + case REFCOUNT_MAX: + pr_warn("Zero detected: unsafely reset to max\n"); + break; + default: + pr_info("Fail: zero not detected, incremeted to %d\n", + refcount_read(ref)); + } +} + +/* + * A refcount_inc() from zero should pin to zero or saturate and may WARN. + * Only CONFIG_REFCOUNT_FULL provides this protection currently. + */ +void lkdtm_REFCOUNT_INC_ZERO(void) +{ + refcount_t zero = REFCOUNT_INIT(0); + + pr_info("attempting safe refcount_inc_not_zero() from zero\n"); + if (!refcount_inc_not_zero(&zero)) { + pr_info("Good: zero detected\n"); + if (refcount_read(&zero) == 0) + pr_info("Correctly stayed at zero\n"); + else + pr_err("Fail: refcount went past zero!\n"); + } else { + pr_err("Fail: Zero not detected!?\n"); + } + + pr_info("attempting bad refcount_inc() from zero\n"); + refcount_inc(&zero); + + check_from_zero(&zero); +} + +/* + * A refcount_add() should act like refcount_inc() above when starting + * at zero. + */ +void lkdtm_REFCOUNT_ADD_ZERO(void) +{ + refcount_t zero = REFCOUNT_INIT(0); + + pr_info("attempting safe refcount_add_not_zero() from zero\n"); + if (!refcount_add_not_zero(3, &zero)) { + pr_info("Good: zero detected\n"); + if (refcount_read(&zero) == 0) + pr_info("Correctly stayed at zero\n"); + else + pr_err("Fail: refcount went past zero\n"); + } else { + pr_err("Fail: Zero not detected!?\n"); + } + + pr_info("attempting bad refcount_add() from zero\n"); + refcount_add(3, &zero); + + check_from_zero(&zero); +} + +static void check_saturated(refcount_t *ref) +{ + switch (refcount_read(ref)) { + case REFCOUNT_SATURATED: + pr_info("Saturation detected: still saturated\n"); + break; + case REFCOUNT_MAX: + pr_warn("Saturation detected: unsafely reset to max\n"); + break; + default: + pr_err("Fail: refcount went crazy: %d\n", refcount_read(ref)); + } +} + +/* + * A refcount_inc() from a saturated value should at most warn about + * being saturated already. + */ +void lkdtm_REFCOUNT_INC_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_inc() from saturated\n"); + refcount_inc(&sat); + + check_saturated(&sat); +} + +/* Should act like refcount_inc() above from saturated. */ +void lkdtm_REFCOUNT_DEC_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_dec() from saturated\n"); + refcount_dec(&sat); + + check_saturated(&sat); +} + +/* Should act like refcount_inc() above from saturated. */ +void lkdtm_REFCOUNT_ADD_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_dec() from saturated\n"); + refcount_add(8, &sat); + + check_saturated(&sat); +} + +/* Should act like refcount_inc() above from saturated. */ +void lkdtm_REFCOUNT_INC_NOT_ZERO_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_inc_not_zero() from saturated\n"); + if (!refcount_inc_not_zero(&sat)) + pr_warn("Weird: refcount_inc_not_zero() reported zero\n"); + + check_saturated(&sat); +} + +/* Should act like refcount_inc() above from saturated. */ +void lkdtm_REFCOUNT_ADD_NOT_ZERO_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_add_not_zero() from saturated\n"); + if (!refcount_add_not_zero(7, &sat)) + pr_warn("Weird: refcount_add_not_zero() reported zero\n"); + + check_saturated(&sat); +} + +/* Should act like refcount_inc() above from saturated. */ +void lkdtm_REFCOUNT_DEC_AND_TEST_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_dec_and_test() from saturated\n"); + if (refcount_dec_and_test(&sat)) + pr_warn("Weird: refcount_dec_and_test() reported zero\n"); + + check_saturated(&sat); +} + +/* Should act like refcount_inc() above from saturated. */ +void lkdtm_REFCOUNT_SUB_AND_TEST_SATURATED(void) +{ + refcount_t sat = REFCOUNT_INIT(REFCOUNT_SATURATED); + + pr_info("attempting bad refcount_sub_and_test() from saturated\n"); + if (refcount_sub_and_test(8, &sat)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_saturated(&sat); +} + +/* Used to time the existing atomic_t when used for reference counting */ +void lkdtm_ATOMIC_TIMING(void) +{ + unsigned int i; + atomic_t count = ATOMIC_INIT(1); + + for (i = 0; i < INT_MAX - 1; i++) + atomic_inc(&count); + + for (i = INT_MAX; i > 0; i--) + if (atomic_dec_and_test(&count)) + break; + + if (i != 1) + pr_err("atomic timing: out of sync up/down cycle: %u\n", i - 1); + else + pr_info("atomic timing: done\n"); +} + +/* + * This can be compared to ATOMIC_TIMING when implementing fast refcount + * protections. Looking at the number of CPU cycles tells the real story + * about performance. For example: + * cd /sys/kernel/debug/provoke-crash + * perf stat -B -- cat <(echo REFCOUNT_TIMING) > DIRECT + */ +void lkdtm_REFCOUNT_TIMING(void) +{ + unsigned int i; + refcount_t count = REFCOUNT_INIT(1); + + for (i = 0; i < INT_MAX - 1; i++) + refcount_inc(&count); + + for (i = INT_MAX; i > 0; i--) + if (refcount_dec_and_test(&count)) + break; + + if (i != 1) + pr_err("refcount: out of sync up/down cycle: %u\n", i - 1); + else + pr_info("refcount timing: done\n"); +} diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 71216affcab1..10dcf4ff99a5 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1354,10 +1354,10 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev) .quirk_probe = mei_me_fw_type_sps -#define MEI_CFG_LEGACY_HFS \ +#define MEI_CFG_ICH_HFS \ .fw_status.count = 0 -#define MEI_CFG_ICH_HFS \ +#define MEI_CFG_ICH10_HFS \ .fw_status.count = 1, \ .fw_status.status[0] = PCI_CFG_HFS_1 @@ -1376,38 +1376,61 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev) .fw_status.status[5] = PCI_CFG_HFS_6 /* ICH Legacy devices */ -const struct mei_cfg mei_me_legacy_cfg = { - MEI_CFG_LEGACY_HFS, +static const struct mei_cfg mei_me_ich_cfg = { + MEI_CFG_ICH_HFS, }; /* ICH devices */ -const struct mei_cfg mei_me_ich_cfg = { - MEI_CFG_ICH_HFS, +static const struct mei_cfg mei_me_ich10_cfg = { + MEI_CFG_ICH10_HFS, }; /* PCH devices */ -const struct mei_cfg mei_me_pch_cfg = { +static const struct mei_cfg mei_me_pch_cfg = { MEI_CFG_PCH_HFS, }; - /* PCH Cougar Point and Patsburg with quirk for Node Manager exclusion */ -const struct mei_cfg mei_me_pch_cpt_pbg_cfg = { +static const struct mei_cfg mei_me_pch_cpt_pbg_cfg = { MEI_CFG_PCH_HFS, MEI_CFG_FW_NM, }; /* PCH8 Lynx Point and newer devices */ -const struct mei_cfg mei_me_pch8_cfg = { +static const struct mei_cfg mei_me_pch8_cfg = { MEI_CFG_PCH8_HFS, }; /* PCH8 Lynx Point with quirk for SPS Firmware exclusion */ -const struct mei_cfg mei_me_pch8_sps_cfg = { +static const struct mei_cfg mei_me_pch8_sps_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_SPS, }; +/* + * mei_cfg_list - A list of platform platform specific configurations. + * Note: has to be synchronized with enum mei_cfg_idx. + */ +static const struct mei_cfg *const mei_cfg_list[] = { + [MEI_ME_UNDEF_CFG] = NULL, + [MEI_ME_ICH_CFG] = &mei_me_ich_cfg, + [MEI_ME_ICH10_CFG] = &mei_me_ich10_cfg, + [MEI_ME_PCH_CFG] = &mei_me_pch_cfg, + [MEI_ME_PCH_CPT_PBG_CFG] = &mei_me_pch_cpt_pbg_cfg, + [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, + [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, +}; + +const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx) +{ + BUILD_BUG_ON(ARRAY_SIZE(mei_cfg_list) != MEI_ME_NUM_CFG); + + if (idx >= MEI_ME_NUM_CFG) + return NULL; + + return mei_cfg_list[idx]; +}; + /** * mei_me_dev_init - allocates and initializes the mei device structure * diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index cf64847a35b9..67892533576e 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -41,8 +41,7 @@ struct mei_cfg { #define MEI_PCI_DEVICE(dev, cfg) \ .vendor = PCI_VENDOR_ID_INTEL, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, \ - .driver_data = (kernel_ulong_t)&(cfg) - + .driver_data = (kernel_ulong_t)(cfg), #define MEI_ME_RPM_TIMEOUT 500 /* ms */ @@ -63,12 +62,36 @@ struct mei_me_hw { #define to_me_hw(dev) (struct mei_me_hw *)((dev)->hw) -extern const struct mei_cfg mei_me_legacy_cfg; -extern const struct mei_cfg mei_me_ich_cfg; -extern const struct mei_cfg mei_me_pch_cfg; -extern const struct mei_cfg mei_me_pch_cpt_pbg_cfg; -extern const struct mei_cfg mei_me_pch8_cfg; -extern const struct mei_cfg mei_me_pch8_sps_cfg; +/** + * enum mei_cfg_idx - indices to platform specific configurations. + * + * Note: has to be synchronized with mei_cfg_list[] + * + * @MEI_ME_UNDEF_CFG: Lower sentinel. + * @MEI_ME_ICH_CFG: I/O Controller Hub legacy devices. + * @MEI_ME_ICH10_CFG: I/O Controller Hub platforms Gen10 + * @MEI_ME_PCH_CFG: Platform Controller Hub platforms (Up to Gen8). + * @MEI_ME_PCH_CPT_PBG_CFG:Platform Controller Hub workstations + * with quirk for Node Manager exclusion. + * @MEI_ME_PCH8_CFG: Platform Controller Hub Gen8 and newer + * client platforms. + * @MEI_ME_PCH8_SPS_CFG: Platform Controller Hub Gen8 and newer + * servers platforms with quirk for + * SPS firmware exclusion. + * @MEI_ME_NUM_CFG: Upper Sentinel. + */ +enum mei_cfg_idx { + MEI_ME_UNDEF_CFG, + MEI_ME_ICH_CFG, + MEI_ME_ICH10_CFG, + MEI_ME_PCH_CFG, + MEI_ME_PCH_CPT_PBG_CFG, + MEI_ME_PCH8_CFG, + MEI_ME_PCH8_SPS_CFG, + MEI_ME_NUM_CFG, +}; + +const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx); struct mei_device *mei_me_dev_init(struct pci_dev *pdev, const struct mei_cfg *cfg); diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index bac33311f55a..4ff40d319676 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -43,57 +43,58 @@ /* mei_pci_tbl - PCI Device ID Table */ static const struct pci_device_id mei_me_pci_tbl[] = { - {MEI_PCI_DEVICE(MEI_DEV_ID_82946GZ, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_82G35, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_82Q965, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_82G965, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_82GM965, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_82GME965, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82Q35, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82G33, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82Q33, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82X38, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_3200, mei_me_legacy_cfg)}, - - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_6, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_7, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_8, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_9, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_10, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_1, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_2, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_3, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_4, mei_me_legacy_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_1, mei_me_ich_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_2, mei_me_ich_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_3, mei_me_ich_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_4, mei_me_ich_cfg)}, - - {MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_1, mei_me_pch_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_2, mei_me_pch_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CPT_1, mei_me_pch_cpt_pbg_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_PBG_1, mei_me_pch_cpt_pbg_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, mei_me_pch_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, mei_me_pch_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, mei_me_pch_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, mei_me_pch8_sps_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, mei_me_pch8_sps_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_LP, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, mei_me_pch8_sps_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP_2, mei_me_pch8_cfg)}, - - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_sps_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_sps_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, mei_me_pch8_cfg)}, - - {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, mei_me_pch8_cfg)}, - - {MEI_PCI_DEVICE(MEI_DEV_ID_KBP, mei_me_pch8_cfg)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, mei_me_pch8_cfg)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_82946GZ, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_82G35, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_82Q965, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_82G965, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_82GM965, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_82GME965, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82Q35, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82G33, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82Q33, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_82X38, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_3200, MEI_ME_ICH_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_6, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_7, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_8, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_9, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9_10, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_1, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_2, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_3, MEI_ME_ICH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH9M_4, MEI_ME_ICH_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_1, MEI_ME_ICH10_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_2, MEI_ME_ICH10_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_3, MEI_ME_ICH10_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_4, MEI_ME_ICH10_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_1, MEI_ME_PCH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_2, MEI_ME_PCH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CPT_1, MEI_ME_PCH_CPT_PBG_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_PBG_1, MEI_ME_PCH_CPT_PBG_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, MEI_ME_PCH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, MEI_ME_PCH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, MEI_ME_PCH_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_LP, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP_2, MEI_ME_PCH8_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH8_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_KBP, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, MEI_ME_PCH8_CFG)}, /* required last entry */ {0, } @@ -138,12 +139,15 @@ static bool mei_me_quirk_probe(struct pci_dev *pdev, */ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - const struct mei_cfg *cfg = (struct mei_cfg *)(ent->driver_data); + const struct mei_cfg *cfg; struct mei_device *dev; struct mei_me_hw *hw; unsigned int irqflags; int err; + cfg = mei_me_get_cfg(ent->driver_data); + if (!cfg) + return -ENODEV; if (!mei_me_quirk_probe(pdev, cfg)) return -ENODEV; @@ -491,6 +495,7 @@ static struct pci_driver mei_me_driver = { .remove = mei_me_remove, .shutdown = mei_me_shutdown, .driver.pm = MEI_ME_PM_OPS, + .driver.probe_type = PROBE_PREFER_ASYNCHRONOUS, }; module_pci_driver(mei_me_driver); diff --git a/fs/char_dev.c b/fs/char_dev.c index fb8507f521b2..ebcc8fb3fa66 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -28,6 +28,8 @@ static struct kobj_map *cdev_map; static DEFINE_MUTEX(chrdevs_lock); +#define CHRDEV_MAJOR_HASH_SIZE 255 + static struct char_device_struct { struct char_device_struct *next; unsigned int major; @@ -49,16 +51,39 @@ void chrdev_show(struct seq_file *f, off_t offset) { struct char_device_struct *cd; - if (offset < CHRDEV_MAJOR_HASH_SIZE) { - mutex_lock(&chrdevs_lock); - for (cd = chrdevs[offset]; cd; cd = cd->next) + mutex_lock(&chrdevs_lock); + for (cd = chrdevs[major_to_index(offset)]; cd; cd = cd->next) { + if (cd->major == offset) seq_printf(f, "%3d %s\n", cd->major, cd->name); - mutex_unlock(&chrdevs_lock); } + mutex_unlock(&chrdevs_lock); } #endif /* CONFIG_PROC_FS */ +static int find_dynamic_major(void) +{ + int i; + struct char_device_struct *cd; + + for (i = ARRAY_SIZE(chrdevs)-1; i > CHRDEV_MAJOR_DYN_END; i--) { + if (chrdevs[i] == NULL) + return i; + } + + for (i = CHRDEV_MAJOR_DYN_EXT_START; + i > CHRDEV_MAJOR_DYN_EXT_END; i--) { + for (cd = chrdevs[major_to_index(i)]; cd; cd = cd->next) + if (cd->major == i) + break; + + if (cd == NULL || cd->major != i) + return i; + } + + return -EBUSY; +} + /* * Register a single major with a specified minor range. * @@ -84,22 +109,21 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, mutex_lock(&chrdevs_lock); - /* temporary */ if (major == 0) { - for (i = ARRAY_SIZE(chrdevs)-1; i > 0; i--) { - if (chrdevs[i] == NULL) - break; - } - - if (i < CHRDEV_MAJOR_DYN_END) - pr_warn("CHRDEV \"%s\" major number %d goes below the dynamic allocation range\n", - name, i); - - if (i == 0) { - ret = -EBUSY; + ret = find_dynamic_major(); + if (ret < 0) { + pr_err("CHRDEV \"%s\" dynamic allocation region is full\n", + name); goto out; } - major = i; + major = ret; + } + + if (major >= CHRDEV_MAJOR_MAX) { + pr_err("CHRDEV \"%s\" major requested (%d) is greater than the maximum (%d)\n", + name, major, CHRDEV_MAJOR_MAX); + ret = -EINVAL; + goto out; } cd->major = major; diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 50493edc30e5..e5709343feb7 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -7,14 +7,14 @@ static int devinfo_show(struct seq_file *f, void *v) { int i = *(loff_t *) v; - if (i < CHRDEV_MAJOR_HASH_SIZE) { + if (i < CHRDEV_MAJOR_MAX) { if (i == 0) seq_puts(f, "Character devices:\n"); chrdev_show(f, i); } #ifdef CONFIG_BLOCK else { - i -= CHRDEV_MAJOR_HASH_SIZE; + i -= CHRDEV_MAJOR_MAX; if (i == 0) seq_puts(f, "\nBlock devices:\n"); blkdev_show(f, i); @@ -25,7 +25,7 @@ static int devinfo_show(struct seq_file *f, void *v) static void *devinfo_start(struct seq_file *f, loff_t *pos) { - if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + if (*pos < (BLKDEV_MAJOR_MAX + CHRDEV_MAJOR_MAX)) return pos; return NULL; } @@ -33,7 +33,7 @@ static void *devinfo_start(struct seq_file *f, loff_t *pos) static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos) { (*pos)++; - if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + if (*pos >= (BLKDEV_MAJOR_MAX + CHRDEV_MAJOR_MAX)) return NULL; return pos; } diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index fb790b8449c1..b97be27e5a85 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -29,6 +29,8 @@ static inline u32 __bitrev32(u32 x) #endif /* CONFIG_HAVE_ARCH_BITREVERSE */ +#define __bitrev8x4(x) (__bitrev32(swab32(x))) + #define __constant_bitrev32(x) \ ({ \ u32 __x = x; \ @@ -50,6 +52,15 @@ static inline u32 __bitrev32(u32 x) __x; \ }) +#define __constant_bitrev8x4(x) \ +({ \ + u32 __x = x; \ + __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ + __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ + __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ + __x; \ +}) + #define __constant_bitrev8(x) \ ({ \ u8 __x = x; \ @@ -75,6 +86,14 @@ static inline u32 __bitrev32(u32 x) __bitrev16(__x); \ }) +#define bitrev8x4(x) \ +({ \ + u32 __x = x; \ + __builtin_constant_p(__x) ? \ + __constant_bitrev8x4(__x) : \ + __bitrev8x4(__x); \ + }) + #define bitrev8(x) \ ({ \ u8 __x = x; \ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index b4ac24c4411d..bfa14bc023fb 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -67,10 +67,14 @@ enum fpga_mgr_states { * FPGA Manager flags * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting + * FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first + * FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) #define FPGA_MGR_ENCRYPTED_BITSTREAM BIT(2) +#define FPGA_MGR_BITSTREAM_LSB_FIRST BIT(3) +#define FPGA_MGR_COMPRESSED_BITSTREAM BIT(4) /** * struct fpga_image_info - information specific to a FPGA image diff --git a/include/linux/fs.h b/include/linux/fs.h index cbfe127bccf8..cdb18f358aee 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2471,9 +2471,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, #endif /* fs/char_dev.c */ -#define CHRDEV_MAJOR_HASH_SIZE 255 +#define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 +/* Marks the top and bottom of the second segment of free char majors */ +#define CHRDEV_MAJOR_DYN_EXT_START 511 +#define CHRDEV_MAJOR_DYN_EXT_END 384 + extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, @@ -2500,14 +2504,14 @@ static inline void unregister_chrdev(unsigned int major, const char *name) #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_HASH_SIZE 255 +#define BLKDEV_MAJOR_MAX 512 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern void blkdev_show(struct seq_file *,off_t); #else -#define BLKDEV_MAJOR_HASH_SIZE 0 +#define BLKDEV_MAJOR_MAX 0 #endif extern void init_special_inode(struct inode *, umode_t, dev_t); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b7d7bbec74e0..07650d0232cc 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -124,10 +124,7 @@ struct hv_ring_buffer_info { spinlock_t ring_lock; u32 ring_datasize; /* < ring_size */ - u32 ring_data_startoffset; - u32 priv_write_index; u32 priv_read_index; - u32 cached_read_index; }; /* @@ -180,19 +177,6 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) return write; } -static inline u32 hv_get_cached_bytes_to_write( - const struct hv_ring_buffer_info *rbi) -{ - u32 read_loc, write_loc, dsize, write; - - dsize = rbi->ring_datasize; - read_loc = rbi->cached_read_index; - write_loc = rbi->ring_buffer->write_index; - - write = write_loc >= read_loc ? dsize - (write_loc - read_loc) : - read_loc - write_loc; - return write; -} /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. @@ -895,6 +879,8 @@ struct vmbus_channel { */ enum hv_numa_policy affinity_policy; + bool probe_done; + }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) @@ -1474,55 +1460,6 @@ hv_get_ring_buffer(const struct hv_ring_buffer_info *ring_info) } /* - * To optimize the flow management on the send-side, - * when the sender is blocked because of lack of - * sufficient space in the ring buffer, potential the - * consumer of the ring buffer can signal the producer. - * This is controlled by the following parameters: - * - * 1. pending_send_sz: This is the size in bytes that the - * producer is trying to send. - * 2. The feature bit feat_pending_send_sz set to indicate if - * the consumer of the ring will signal when the ring - * state transitions from being full to a state where - * there is room for the producer to send the pending packet. - */ - -static inline void hv_signal_on_read(struct vmbus_channel *channel) -{ - u32 cur_write_sz, cached_write_sz; - u32 pending_sz; - struct hv_ring_buffer_info *rbi = &channel->inbound; - - /* - * Issue a full memory barrier before making the signaling decision. - * Here is the reason for having this barrier: - * If the reading of the pend_sz (in this function) - * were to be reordered and read before we commit the new read - * index (in the calling function) we could - * have a problem. If the host were to set the pending_sz after we - * have sampled pending_sz and go to sleep before we commit the - * read index, we could miss sending the interrupt. Issue a full - * memory barrier to address this. - */ - virt_mb(); - - pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); - /* If the other end is not blocked on write don't bother. */ - if (pending_sz == 0) - return; - - cur_write_sz = hv_get_bytes_to_write(rbi); - - if (cur_write_sz < pending_sz) - return; - - cached_write_sz = hv_get_cached_bytes_to_write(rbi); - if (cached_write_sz < pending_sz) - vmbus_setevent(channel); -} - -/* * Mask off host interrupt callback notifications */ static inline void hv_begin_read(struct hv_ring_buffer_info *rbi) diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 51f891fb1b18..7668b5791c91 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -132,6 +132,7 @@ enum { /* struct binder_fd_array_object - object describing an array of fds in a buffer * @hdr: common header structure + * @pad: padding to ensure correct alignment * @num_fds: number of file descriptors in the buffer * @parent: index in offset array to buffer holding the fd array * @parent_offset: start offset of fd array in the buffer @@ -152,6 +153,7 @@ enum { */ struct binder_fd_array_object { struct binder_object_header hdr; + __u32 pad; binder_size_t num_fds; binder_size_t parent; binder_size_t parent_offset; diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config index d70829033bb7..d3fd428f4b92 100644 --- a/kernel/configs/android-base.config +++ b/kernel/configs/android-base.config @@ -10,6 +10,7 @@ # CONFIG_USELIB is not set CONFIG_ANDROID=y CONFIG_ANDROID_BINDER_IPC=y +CONFIG_ANDROID_BINDER_DEVICES=binder,hwbinder,vndbinder CONFIG_ANDROID_LOW_MEMORY_KILLER=y CONFIG_ARMV8_DEPRECATED=y CONFIG_ASHMEM=y diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c index 26ae609a9448..457a1521f32f 100644 --- a/tools/hv/hv_fcopy_daemon.c +++ b/tools/hv/hv_fcopy_daemon.c @@ -138,14 +138,17 @@ void print_usage(char *argv[]) int main(int argc, char *argv[]) { - int fcopy_fd, len; + int fcopy_fd; int error; int daemonize = 1, long_index = 0, opt; int version = FCOPY_CURRENT_VERSION; - char *buffer[4096 * 2]; - struct hv_fcopy_hdr *in_msg; + union { + struct hv_fcopy_hdr hdr; + struct hv_start_fcopy start; + struct hv_do_fcopy copy; + __u32 kernel_modver; + } buffer = { }; int in_handshake = 1; - __u32 kernel_modver; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -195,32 +198,31 @@ int main(int argc, char *argv[]) * In this loop we process fcopy messages after the * handshake is complete. */ - len = pread(fcopy_fd, buffer, (4096 * 2), 0); + ssize_t len; + + len = pread(fcopy_fd, &buffer, sizeof(buffer), 0); if (len < 0) { syslog(LOG_ERR, "pread failed: %s", strerror(errno)); exit(EXIT_FAILURE); } if (in_handshake) { - if (len != sizeof(kernel_modver)) { + if (len != sizeof(buffer.kernel_modver)) { syslog(LOG_ERR, "invalid version negotiation"); exit(EXIT_FAILURE); } - kernel_modver = *(__u32 *)buffer; in_handshake = 0; - syslog(LOG_INFO, "kernel module version: %d", - kernel_modver); + syslog(LOG_INFO, "kernel module version: %u", + buffer.kernel_modver); continue; } - in_msg = (struct hv_fcopy_hdr *)buffer; - - switch (in_msg->operation) { + switch (buffer.hdr.operation) { case START_FILE_COPY: - error = hv_start_fcopy((struct hv_start_fcopy *)in_msg); + error = hv_start_fcopy(&buffer.start); break; case WRITE_TO_FILE: - error = hv_copy_data((struct hv_do_fcopy *)in_msg); + error = hv_copy_data(&buffer.copy); break; case COMPLETE_FCOPY: error = hv_copy_finished(); @@ -231,7 +233,7 @@ int main(int argc, char *argv[]) default: syslog(LOG_ERR, "Unknown operation: %d", - in_msg->operation); + buffer.hdr.operation); } diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 88b20e007c05..eaa3bec273c8 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -1136,7 +1136,7 @@ static int process_ip_string(FILE *f, char *ip_string, int type) int i = 0; int j = 0; char str[256]; - char sub_str[10]; + char sub_str[13]; int offset = 0; memset(addr, 0, sizeof(addr)); diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index 7ba54195934c..b2b4ebffab8c 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -21,6 +21,7 @@ #include <sys/types.h> #include <sys/poll.h> #include <sys/ioctl.h> +#include <sys/stat.h> #include <fcntl.h> #include <stdio.h> #include <mntent.h> @@ -30,6 +31,7 @@ #include <ctype.h> #include <errno.h> #include <linux/fs.h> +#include <linux/major.h> #include <linux/hyperv.h> #include <syslog.h> #include <getopt.h> @@ -70,6 +72,7 @@ static int vss_operate(int operation) char match[] = "/dev/"; FILE *mounts; struct mntent *ent; + struct stat sb; char errdir[1024] = {0}; unsigned int cmd; int error = 0, root_seen = 0, save_errno = 0; @@ -92,6 +95,10 @@ static int vss_operate(int operation) while ((ent = getmntent(mounts))) { if (strncmp(ent->mnt_fsname, match, strlen(match))) continue; + if (stat(ent->mnt_fsname, &sb) == -1) + continue; + if (S_ISBLK(sb.st_mode) && major(sb.st_rdev) == LOOP_MAJOR) + continue; if (hasmntopt(ent, MNTOPT_RO) != NULL) continue; if (strcmp(ent->mnt_type, "vfat") == 0) |