diff options
480 files changed, 6902 insertions, 3004 deletions
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 3943b5b..00a5ba5 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -39,8 +39,8 @@ up. Although MT wq wasted a lot of resource, the level of concurrency provided was unsatisfactory. The limitation was common to both ST and MT wq albeit less severe on MT. Each wq maintained its own separate -worker pool. A MT wq could provide only one execution context per CPU -while a ST wq one for the whole system. Work items had to compete for +worker pool. An MT wq could provide only one execution context per CPU +while an ST wq one for the whole system. Work items had to compete for those very limited execution contexts leading to various problems including proneness to deadlocks around the single execution context. @@ -151,7 +151,7 @@ Application Programming Interface (API) ``alloc_workqueue()`` allocates a wq. The original ``create_*workqueue()`` functions are deprecated and scheduled for -removal. ``alloc_workqueue()`` takes three arguments - @``name``, +removal. ``alloc_workqueue()`` takes three arguments - ``@name``, ``@flags`` and ``@max_active``. ``@name`` is the name of the wq and also used as the name of the rescuer thread if there is one. @@ -197,7 +197,7 @@ resources, scheduled and executed. served by worker threads with elevated nice level. Note that normal and highpri worker-pools don't interact with - each other. Each maintain its separate pool of workers and + each other. Each maintains its separate pool of workers and implements concurrency management among its workers. ``WQ_CPU_INTENSIVE`` @@ -249,8 +249,8 @@ unbound worker-pools and only one work item could be active at any given time thus achieving the same ordering property as ST wq. In the current implementation the above configuration only guarantees -ST behavior within a given NUMA node. Instead alloc_ordered_queue should -be used to achieve system wide ST behavior. +ST behavior within a given NUMA node. Instead ``alloc_ordered_queue()`` should +be used to achieve system-wide ST behavior. Example Execution Scenarios diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt index 03a7cee..c15e753 100644 --- a/Documentation/cpu-freq/index.txt +++ b/Documentation/cpu-freq/index.txt @@ -32,8 +32,6 @@ cpufreq-stats.txt - General description of sysfs cpufreq stats. index.txt - File index, Mailing list and Links (this document) -intel-pstate.txt - Intel pstate cpufreq driver specific file. - pcc-cpufreq.txt - PCC cpufreq driver specific file. diff --git a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt index a135504..cac24ee 100644 --- a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt +++ b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt @@ -32,7 +32,7 @@ Example: compatible = "st,stm32h743-rcc", "st,stm32-rcc"; reg = <0x58024400 0x400>; #reset-cells = <1>; - #clock-cells = <2>; + #clock-cells = <1>; clocks = <&clk_hse>, <&clk_lse>, <&clk_i2s_ckin>; st,syscfg = <&pwrcfg>; diff --git a/Documentation/devicetree/bindings/leds/ams,as3645a.txt b/Documentation/devicetree/bindings/leds/ams,as3645a.txt index 12c5ef2..fdc40e3 100644 --- a/Documentation/devicetree/bindings/leds/ams,as3645a.txt +++ b/Documentation/devicetree/bindings/leds/ams,as3645a.txt @@ -15,11 +15,14 @@ Required properties compatible : Must be "ams,as3645a". reg : The I2C address of the device. Typically 0x30. +#address-cells : 1 +#size-cells : 0 -Required properties of the "flash" child node -============================================= +Required properties of the flash child node (0) +=============================================== +reg: 0 flash-timeout-us: Flash timeout in microseconds. The value must be in the range [100000, 850000] and divisible by 50000. flash-max-microamp: Maximum flash current in microamperes. Has to be @@ -33,20 +36,21 @@ ams,input-max-microamp: Maximum flash controller input current. The and divisible by 50000. -Optional properties of the "flash" child node -============================================= +Optional properties of the flash child node +=========================================== label : The label of the flash LED. -Required properties of the "indicator" child node -================================================= +Required properties of the indicator child node (1) +=================================================== +reg: 1 led-max-microamp: Maximum indicator current. The allowed values are 2500, 5000, 7500 and 10000. -Optional properties of the "indicator" child node -================================================= +Optional properties of the indicator child node +=============================================== label : The label of the indicator LED. @@ -55,16 +59,20 @@ Example ======= as3645a@30 { + #address-cells: 1 + #size-cells: 0 reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; ams,input-max-microamp = <1750000>; label = "as3645a:flash"; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; label = "as3645a:indicator"; }; diff --git a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt index 3eca6de..a65d7b7 100644 --- a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt +++ b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt @@ -8,6 +8,12 @@ Required properties: the firmware event log - linux,sml-size : size of the memory allocated for the firmware event log +Optional properties: + +- powered-while-suspended: present when the TPM is left powered on between + suspend and resume (makes the suspend/resume + callbacks do nothing). + Example (for OpenPower Systems with Nuvoton TPM 2.0 on I2C) ---------------------------------------------------------- diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt index 4fc9694..cf504d0 100644 --- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt +++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt @@ -41,6 +41,8 @@ Required properties: - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART. - "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART. - "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART. + - "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART. + - "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART. - "renesas,scif-r8a77995" for R8A77995 (R-Car D3) SCIF compatible UART. - "renesas,hscif-r8a77995" for R8A77995 (R-Car D3) HSCIF compatible UART. - "renesas,scifa-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFA compatible UART. diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 1ea1fd4..1afd298 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -3,8 +3,8 @@ Device tree binding vendor prefix registry. Keep list in alphabetical order. This isn't an exhaustive list, but you should add new prefixes to it before using them to avoid name-space collisions. -abcn Abracon Corporation abilis Abilis Systems +abracon Abracon Corporation actions Actions Semiconductor Co., Ltd. active-semi Active-Semi International Inc ad Avionic Design GmbH diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt index 4421135..d661e6f 100644 --- a/Documentation/driver-model/driver.txt +++ b/Documentation/driver-model/driver.txt @@ -196,12 +196,13 @@ struct driver_attribute { }; Device drivers can export attributes via their sysfs directories. -Drivers can declare attributes using a DRIVER_ATTR macro that works -identically to the DEVICE_ATTR macro. +Drivers can declare attributes using a DRIVER_ATTR_RW and DRIVER_ATTR_RO +macro that works identically to the DEVICE_ATTR_RW and DEVICE_ATTR_RO +macros. Example: -DRIVER_ATTR(debug,0644,show_debug,store_debug); +DRIVER_ATTR_RW(debug); This is equivalent to declaring: diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 24da7b3..9a3658c 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -366,7 +366,8 @@ struct driver_attribute { Declaring: -DRIVER_ATTR(_name, _mode, _show, _store) +DRIVER_ATTR_RO(_name) +DRIVER_ATTR_RW(_name) Creation/Removal: diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index b3345d0..77f4de5 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1680,6 +1680,9 @@ accept_dad - INTEGER 2: Enable DAD, and disable IPv6 operation if MAC-based duplicate link-local address has been found. + DAD operation and mode on a given interface will be selected according + to the maximum value of conf/{all,interface}/accept_dad. + force_tllao - BOOLEAN Enable sending the target link-layer address option even when responding to a unicast neighbor solicitation. @@ -1727,16 +1730,23 @@ suppress_frag_ndisc - INTEGER optimistic_dad - BOOLEAN Whether to perform Optimistic Duplicate Address Detection (RFC 4429). - 0: disabled (default) - 1: enabled + 0: disabled (default) + 1: enabled + + Optimistic Duplicate Address Detection for the interface will be enabled + if at least one of conf/{all,interface}/optimistic_dad is set to 1, + it will be disabled otherwise. use_optimistic - BOOLEAN If enabled, do not classify optimistic addresses as deprecated during source address selection. Preferred addresses will still be chosen before optimistic addresses, subject to other ranking in the source address selection algorithm. - 0: disabled (default) - 1: enabled + 0: disabled (default) + 1: enabled + + This will be enabled if at least one of + conf/{all,interface}/use_optimistic is set to 1, disabled otherwise. stable_secret - IPv6 address This IPv6 address will be used as a secret to generate IPv6 diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 5e40e1f..82236a1 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -13,42 +13,42 @@ an example setup using a data-center-class switch ASIC chip. Other setups with SR-IOV or soft switches, such as OVS, are possible. -                             User-space tools - -       user space                   | -      +-------------------------------------------------------------------+ -       kernel                       | Netlink -                                    | -                     +--------------+-------------------------------+ -                     |         Network stack                        | -                     |           (Linux)                            | -                     |                                              | -                     +----------------------------------------------+ + User-space tools + + user space | + +-------------------------------------------------------------------+ + kernel | Netlink + | + +--------------+-------------------------------+ + | Network stack | + | (Linux) | + | | + +----------------------------------------------+ sw1p2 sw1p4 sw1p6 -                      sw1p1  + sw1p3 +  sw1p5 +         eth1 -                        +    |    +    |    +    |            + -                        |    |    |    |    |    |            | -                     +--+----+----+----+-+--+----+---+  +-----+-----+ -                     |         Switch driver         |  |    mgmt   | -                     |        (this document)        |  |   driver  | -                     |                               |  |           | -                     +--------------+----------------+  +-----------+ -                                    | -       kernel                       | HW bus (eg PCI) -      +-------------------------------------------------------------------+ -       hardware                     | -                     +--------------+---+------------+ -                     |         Switch device (sw1)   | -                     |  +----+                       +--------+ -                     |  |    v offloaded data path   | mgmt port -                     |  |    |                       | -                     +--|----|----+----+----+----+---+ -                        |    |    |    |    |    | -                        +    +    +    +    +    + -                       p1   p2   p3   p4   p5   p6 - -                             front-panel ports + sw1p1 + sw1p3 + sw1p5 + eth1 + + | + | + | + + | | | | | | | + +--+----+----+----+----+----+---+ +-----+-----+ + | Switch driver | | mgmt | + | (this document) | | driver | + | | | | + +--------------+----------------+ +-----------+ + | + kernel | HW bus (eg PCI) + +-------------------------------------------------------------------+ + hardware | + +--------------+----------------+ + | Switch device (sw1) | + | +----+ +--------+ + | | v offloaded data path | mgmt port + | | | | + +--|----|----+----+----+----+---+ + | | | | | | + + + + + + + + p1 p2 p3 p4 p5 p6 + + front-panel ports Fig 1. diff --git a/MAINTAINERS b/MAINTAINERS index fa4e916..65b0c88 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2865,7 +2865,6 @@ S: Supported F: drivers/scsi/bnx2i/ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER -M: Yuval Mintz <Yuval.Mintz@cavium.com> M: Ariel Elior <ariel.elior@cavium.com> M: everest-linux-l2@cavium.com L: netdev@vger.kernel.org @@ -6655,8 +6654,8 @@ M: Alexander Aring <alex.aring@gmail.com> M: Stefan Schmidt <stefan@osg.samsung.com> L: linux-wpan@vger.kernel.org W: http://wpan.cakelab.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git S: Maintained F: net/ieee802154/ F: net/mac802154/ @@ -8598,6 +8597,12 @@ M: Sean Wang <sean.wang@mediatek.com> S: Maintained F: drivers/media/rc/mtk-cir.c +MEDIATEK PMIC LED DRIVER +M: Sean Wang <sean.wang@mediatek.com> +S: Maintained +F: drivers/leds/leds-mt6323.c +F: Documentation/devicetree/bindings/leds/leds-mt6323.txt + MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@openwrt.org> M: John Crispin <john@phrozen.org> @@ -11059,7 +11064,6 @@ S: Supported F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER -M: Yuval Mintz <Yuval.Mintz@cavium.com> M: Ariel Elior <Ariel.Elior@cavium.com> M: everest-linux-l2@cavium.com L: netdev@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = Fearless Coyote # *DOCUMENTATION* @@ -933,7 +933,11 @@ ifdef CONFIG_STACK_VALIDATION ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else - $(warning "Cannot use CONFIG_STACK_VALIDATION, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + ifdef CONFIG_ORC_UNWINDER + $(error "Cannot generate ORC metadata for CONFIG_ORC_UNWINDER=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + else + $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + endif SKIP_STACK_VALIDATION := 1 export SKIP_STACK_VALIDATION endif @@ -1172,11 +1176,11 @@ headers_check: headers_install PHONY += kselftest kselftest: - $(Q)$(MAKE) -C tools/testing/selftests run_tests + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests PHONY += kselftest-clean kselftest-clean: - $(Q)$(MAKE) -C tools/testing/selftests clean + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean PHONY += kselftest-merge kselftest-merge: diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index cb47ae7..1b0bd72 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -267,15 +267,19 @@ clock-frequency = <400000>; as3645a@30 { + #address-cells = <1>; + #size-cells = <0>; reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; - peak-current-limit = <1750000>; + ams,input-max-microamp = <1750000>; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; }; }; diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 1d468b5..776757d 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -139,11 +139,10 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_UPROBE 3 /* breakpointed or singlestepping */ -#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */ -#define TIF_SYSCALL_TRACE 5 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */ -#define TIF_SYSCALL_TRACEPOINT 7 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ +#define TIF_SYSCALL_TRACE 4 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ +#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ +#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ #define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 @@ -154,7 +153,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_UPROBE (1 << TIF_UPROBE) -#define _TIF_FSCHECK (1 << TIF_FSCHECK) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) @@ -168,9 +166,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, /* * Change these and you break ASM code in entry-common.S */ -#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_FSCHECK) +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 87936dd..0bf2347 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -70,8 +70,6 @@ static inline void set_fs(mm_segment_t fs) { current_thread_info()->addr_limit = fs; modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER); - /* On user-mode return, check fs is correct */ - set_thread_flag(TIF_FSCHECK); } #define segment_eq(a, b) ((a) == (b)) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index ca3614d..99c9082 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -12,6 +12,7 @@ #include <asm/unistd.h> #include <asm/ftrace.h> #include <asm/unwind.h> +#include <asm/memory.h> #ifdef CONFIG_AEABI #include <asm/unistd-oabi.h> #endif @@ -48,12 +49,14 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts + ldr r2, [tsk, #TI_ADDR_LIMIT] + cmp r2, #TASK_SIZE + blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK - bne fast_work_pending - tst r1, #_TIF_WORK_MASK + tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK bne fast_work_pending + /* perform architecture specific actions before user return */ arch_ret_to_user r1, lr @@ -76,16 +79,16 @@ ret_fast_syscall: UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 disable_irq_notrace @ disable interrupts + ldr r2, [tsk, #TI_ADDR_LIMIT] + cmp r2, #TASK_SIZE + blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK - bne fast_work_pending - tst r1, #_TIF_WORK_MASK + tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK beq no_work_pending UNWIND(.fnend ) ENDPROC(ret_fast_syscall) /* Slower path - fall through to work_pending */ -fast_work_pending: #endif tst r1, #_TIF_SYSCALL_WORK @@ -111,6 +114,9 @@ ENTRY(ret_to_user) ret_slow_syscall: disable_irq_notrace @ disable interrupts ENTRY(ret_to_user_from_irq) + ldr r2, [tsk, #TI_ADDR_LIMIT] + cmp r2, #TASK_SIZE + blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK bne slow_work_pending diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index e2de50b..b67ae12 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -614,10 +614,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) * Update the trace code with the current status. */ trace_hardirqs_off(); - - /* Check valid user FS if needed */ - addr_limit_user_check(); - do { if (likely(thread_flags & _TIF_NEED_RESCHED)) { schedule(); @@ -678,3 +674,9 @@ struct page *get_signal_page(void) return page; } + +/* Defer to generic check */ +asmlinkage void addr_limit_check_failed(void) +{ + addr_limit_user_check(); +} diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bc4e923..b46e54c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -401,7 +401,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) /* Find an entry in the third-level page table. */ #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t)) +#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr)))) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 7434ec0..0b243ec 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -384,6 +384,7 @@ ENTRY(kimage_vaddr) * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) + msr SPsel, #1 // We want to use SP_EL{1,2} mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 b.eq 1f diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index c45214f..0bdc96c 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -751,10 +751,10 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, */ trace_hardirqs_off(); - /* Check valid user FS if needed */ - addr_limit_user_check(); - do { + /* Check valid user FS if needed */ + addr_limit_user_check(); + if (thread_flags & _TIF_NEED_RESCHED) { schedule(); } else { diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 89993c4..2069e9b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -651,7 +651,7 @@ static const struct fault_info fault_info[] = { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_bad, SIGBUS, 0, "unknown 8" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 9d26abd..4f798aa 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -39,7 +39,7 @@ config MICROBLAZE # Endianness selection choice prompt "Endianness selection" - default CPU_BIG_ENDIAN + default CPU_LITTLE_ENDIAN help microblaze architectures can be configured for either little or big endian formats. Be sure to select the appropriate mode. diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index e77a596..06609ca 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ generic-y += fcntl.h generic-y += ioctl.h generic-y += ioctls.h generic-y += ipcbuf.h +generic-y += kvm_para.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index e45ada8..94700c5 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -165,7 +165,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, unsigned long attrs) { #ifdef CONFIG_MMU - unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; unsigned long pfn; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index ba7b7dd..a57dedb 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -257,6 +257,18 @@ config PARISC_PAGE_SIZE_64KB endchoice +config PARISC_SELF_EXTRACT + bool "Build kernel as self-extracting executable" + default y + help + Say Y if you want to build the parisc kernel as a kind of + self-extracting executable. + + If you say N here, the kernel will be compressed with gzip + which can be loaded by the palo bootloader directly too. + + If you don't know what to do here, say Y. + config SMP bool "Symmetric multi-processing support" ---help--- diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 58fae5d..01946eb 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -129,8 +129,13 @@ Image: vmlinux bzImage: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ +ifdef CONFIG_PARISC_SELF_EXTRACT vmlinuz: bzImage $(OBJCOPY) $(boot)/bzImage $@ +else +vmlinuz: vmlinux + @gzip -cf -9 $< > $@ +endif install: $(CONFIG_SHELL) $(src)/arch/parisc/install.sh \ diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile index 5450a11..7d7e594 100644 --- a/arch/parisc/boot/compressed/Makefile +++ b/arch/parisc/boot/compressed/Makefile @@ -15,7 +15,7 @@ targets += misc.o piggy.o sizes.h head.o real2.o firmware.o KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs +KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs -Os ifndef CONFIG_64BIT KBUILD_CFLAGS += -mfast-indirect-calls endif diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 13a4bf9..9345b44 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -24,7 +24,8 @@ /* Symbols defined by linker scripts */ extern char input_data[]; extern int input_len; -extern __le32 output_len; /* at unaligned address, little-endian */ +/* output_len is inserted by the linker possibly at an unaligned address */ +extern __le32 output_len __aligned(1); extern char _text, _end; extern char _bss, _ebss; extern char _startcode_end; diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index 26b4455..510341f 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -280,6 +280,7 @@ void setup_pdc(void); /* in inventory.c */ /* wrapper-functions from pdc.c */ int pdc_add_valid(unsigned long address); +int pdc_instr(unsigned int *instr); int pdc_chassis_info(struct pdc_chassis_info *chassis_info, void *led_info, unsigned long len); int pdc_chassis_disp(unsigned long disp); int pdc_chassis_warn(unsigned long *warn); diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h index a5dc906..ad9c9c3 100644 --- a/arch/parisc/include/asm/smp.h +++ b/arch/parisc/include/asm/smp.h @@ -1,6 +1,7 @@ #ifndef __ASM_SMP_H #define __ASM_SMP_H +extern int init_per_cpu(int cpuid); #if defined(CONFIG_SMP) diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index ab80e5c..6d471c0 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -233,6 +233,26 @@ int pdc_add_valid(unsigned long address) EXPORT_SYMBOL(pdc_add_valid); /** + * pdc_instr - Get instruction that invokes PDCE_CHECK in HPMC handler. + * @instr: Pointer to variable which will get instruction opcode. + * + * The return value is PDC_OK (0) in case call succeeded. + */ +int __init pdc_instr(unsigned int *instr) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_INSTR, 0UL, __pa(pdc_result)); + convert_to_wide(pdc_result); + *instr = pdc_result[0]; + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + +/** * pdc_chassis_info - Return chassis information. * @result: The return buffer. * @chassis_info: The memory buffer address. diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c index 05730a8..00aed08 100644 --- a/arch/parisc/kernel/pdt.c +++ b/arch/parisc/kernel/pdt.c @@ -15,6 +15,7 @@ #include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/kthread.h> +#include <linux/initrd.h> #include <asm/pdc.h> #include <asm/pdcpat.h> @@ -216,8 +217,16 @@ void __init pdc_pdt_init(void) } for (i = 0; i < pdt_status.pdt_entries; i++) { + unsigned long addr; + report_mem_err(pdt_entry[i]); + addr = pdt_entry[i] & PDT_ADDR_PHYS_MASK; + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && + addr >= initrd_start && addr < initrd_end) + pr_crit("CRITICAL: initrd possibly broken " + "due to bad memory!\n"); + /* mark memory page bad */ memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE); } diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index a778bd3..e120d63 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -317,7 +317,7 @@ void __init collect_boot_cpu_data(void) * * o Enable CPU profiling hooks. */ -int init_per_cpu(int cpunum) +int __init init_per_cpu(int cpunum) { int ret; struct pdc_coproc_cfg coproc_cfg; diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index dee6f9d..f7d0c3b3 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -38,6 +38,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/clock.h> +#include <linux/start_kernel.h> #include <asm/processor.h> #include <asm/sections.h> @@ -48,6 +49,7 @@ #include <asm/io.h> #include <asm/setup.h> #include <asm/unwind.h> +#include <asm/smp.h> static char __initdata command_line[COMMAND_LINE_SIZE]; @@ -115,7 +117,6 @@ void __init dma_ops_init(void) } #endif -extern int init_per_cpu(int cpuid); extern void collect_boot_cpu_data(void); void __init setup_arch(char **cmdline_p) @@ -398,9 +399,8 @@ static int __init parisc_init(void) } arch_initcall(parisc_init); -void start_parisc(void) +void __init start_parisc(void) { - extern void start_kernel(void); extern void early_trap_init(void); int ret, cpunum; diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 6336510..30c28ab 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -255,12 +255,11 @@ void arch_send_call_function_single_ipi(int cpu) static void __init smp_cpu_init(int cpunum) { - extern int init_per_cpu(int); /* arch/parisc/kernel/processor.c */ extern void init_IRQ(void); /* arch/parisc/kernel/irq.c */ extern void start_cpu_itimer(void); /* arch/parisc/kernel/time.c */ /* Set modes and Enable floating point coprocessor */ - (void) init_per_cpu(cpunum); + init_per_cpu(cpunum); disable_sr_hashing(); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 991654c..23033315 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -817,7 +817,7 @@ void __init initialize_ivt(const void *iva) u32 check = 0; u32 *ivap; u32 *hpmcp; - u32 length; + u32 length, instr; if (strcmp((const char *)iva, "cows can fly")) panic("IVT invalid"); @@ -827,6 +827,14 @@ void __init initialize_ivt(const void *iva) for (i = 0; i < 8; i++) *ivap++ = 0; + /* + * Use PDC_INSTR firmware function to get instruction that invokes + * PDCE_CHECK in HPMC handler. See programming note at page 1-31 of + * the PA 1.1 Firmware Architecture document. + */ + if (pdc_instr(&instr) == PDC_OK) + ivap[0] = instr; + /* Compute Checksum for HPMC handler */ length = os_hpmc_size; ivap[7] = length; diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 48dc7d4..caab39d 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/kallsyms.h> #include <linux/sort.h> +#include <linux/sched.h> #include <linux/uaccess.h> #include <asm/assembly.h> @@ -279,6 +280,17 @@ static void unwind_frame_regs(struct unwind_frame_info *info) info->prev_sp = sp - 64; info->prev_ip = 0; + + /* The stack is at the end inside the thread_union + * struct. If we reach data, we have reached the + * beginning of the stack and should stop unwinding. */ + if (info->prev_sp >= (unsigned long) task_thread_info(info->t) && + info->prev_sp < ((unsigned long) task_thread_info(info->t) + + THREAD_SZ_ALGN)) { + info->prev_sp = 0; + break; + } + if (get_user(tmp, (unsigned long *)(info->prev_sp - RP_OFFSET))) break; info->prev_ip = tmp; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 5b101f6..e247edb 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/extable.h> #include <linux/uaccess.h> +#include <linux/hugetlb.h> #include <asm/traps.h> @@ -261,7 +262,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, struct task_struct *tsk; struct mm_struct *mm; unsigned long acc_type; - int fault; + int fault = 0; unsigned int flags; if (faulthandler_disabled()) @@ -315,7 +316,8 @@ good_area: goto out_of_memory; else if (fault & VM_FAULT_SIGSEGV) goto bad_area; - else if (fault & VM_FAULT_SIGBUS) + else if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| + VM_FAULT_HWPOISON_LARGE)) goto bad_area; BUG(); } @@ -352,8 +354,7 @@ bad_area: if (user_mode(regs)) { struct siginfo si; - - show_signal_msg(regs, code, address, tsk, vma); + unsigned int lsb = 0; switch (code) { case 15: /* Data TLB miss fault/Data page fault */ @@ -386,6 +387,30 @@ bad_area: si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR; break; } + +#ifdef CONFIG_MEMORY_FAILURE + if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { + printk(KERN_ERR + "MCE: Killing %s:%d due to hardware memory corruption fault at %08lx\n", + tsk->comm, tsk->pid, address); + si.si_signo = SIGBUS; + si.si_code = BUS_MCEERR_AR; + } +#endif + + /* + * Either small page or large page may be poisoned. + * In other words, VM_FAULT_HWPOISON_LARGE and + * VM_FAULT_HWPOISON are mutually exclusive. + */ + if (fault & VM_FAULT_HWPOISON_LARGE) + lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); + else if (fault & VM_FAULT_HWPOISON) + lsb = PAGE_SHIFT; + else + show_signal_msg(regs, code, address, tsk, vma); + si.si_addr_lsb = lsb; + si.si_errno = 0; si.si_addr = (void __user *) address; force_sig_info(si.si_signo, &si, current); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 17936f8..ec69fa4 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1121,6 +1121,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) BEGIN_FTR_SECTION mtspr SPRN_PPR, r0 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + +/* Move canary into DSISR to check for later */ +BEGIN_FTR_SECTION + li r0, 0x7fff + mtspr SPRN_HDSISR, r0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) @@ -1956,9 +1963,14 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) kvmppc_hdsi: ld r3, VCPU_KVM(r9) lbz r0, KVM_RADIX(r3) - cmpwi r0, 0 mfspr r4, SPRN_HDAR mfspr r6, SPRN_HDSISR +BEGIN_FTR_SECTION + /* Look for DSISR canary. If we find it, retry instruction */ + cmpdi r6, 0x7fff + beq 6f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + cmpwi r0, 0 bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */ /* HPTE not found fault or protection fault? */ andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 0b034eb..7f69d17 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -98,7 +98,7 @@ static struct clocksource timer_clocksource = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static void __init timer_setup(void) +static void __init um_timer_setup(void) { int err; @@ -132,5 +132,5 @@ void read_persistent_clock(struct timespec *ts) void __init time_init(void) { timer_set_signal_handler(); - late_time_init = timer_setup; + late_time_init = um_timer_setup; } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4cf100f..72db066 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), @@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 8e2457c..005908e 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index db1fe37..a719681 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3462,7 +3462,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = { static struct intel_uncore_type skx_uncore_iio = { .name = "iio", .num_counters = 4, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IIO0_MSR_PMON_CTL0, .perf_ctr = SKX_IIO0_MSR_PMON_CTR0, @@ -3492,7 +3492,7 @@ static const struct attribute_group skx_uncore_format_group = { static struct intel_uncore_type skx_uncore_irp = { .name = "irp", .num_counters = 2, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IRP0_MSR_PMON_CTL0, .perf_ctr = SKX_IRP0_MSR_PMON_CTR0, diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 4bb3ec6..0672367 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -63,6 +63,14 @@ static bool test_intel(int idx) case INTEL_FAM6_ATOM_SILVERMONT1: case INTEL_FAM6_ATOM_SILVERMONT2: case INTEL_FAM6_ATOM_AIRMONT: + + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_DENVERTON: + + case INTEL_FAM6_ATOM_GEMINI_LAKE: + + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index e0bb46c..0e2a5ed 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (fpu->fpstate_active) { + if (fpu->initialized) { unsigned long fx_aligned, math_size; sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 1b02038..c096624 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -218,10 +218,9 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ { \ - register void *__sp asm(_ASM_SP); \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ - : output, "+r" (__sp) \ + : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input); \ } diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 676ee58..b0dc91f 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -11,10 +11,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif @@ -132,4 +134,15 @@ /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif +#ifndef __ASSEMBLY__ +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) +#endif + #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 554cdb2..e3221ff 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -23,11 +23,9 @@ /* * High level FPU state handling functions: */ -extern void fpu__activate_curr(struct fpu *fpu); -extern void fpu__activate_fpstate_read(struct fpu *fpu); -extern void fpu__activate_fpstate_write(struct fpu *fpu); -extern void fpu__current_fpstate_write_begin(void); -extern void fpu__current_fpstate_write_end(void); +extern void fpu__initialize(struct fpu *fpu); +extern void fpu__prepare_read(struct fpu *fpu); +extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern void fpu__restore(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); @@ -120,20 +118,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); err; \ }) -#define check_insn(insn, output, input...) \ -({ \ - int err; \ +#define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ + : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { @@ -153,20 +142,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - int err; - if (IS_ENABLED(CONFIG_X86_32)) { - err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { /* See comment in copy_fxregs_to_kernel() below. */ - err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); } } - /* Copying from a kernel buffer to FPU registers should never fail: */ - WARN_ON_FPU(err); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) @@ -183,9 +168,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) static inline void copy_kernel_to_fregs(struct fregs_state *fx) { - int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - - WARN_ON_FPU(err); + kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) @@ -281,18 +264,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ -#define XSTATE_XRESTORE(st, lmask, hmask, err) \ +#define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ - "xor %[err], %[err]\n" \ "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ - : [err] "=r" (err) \ + _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ + : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -336,7 +314,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ + /* + * We should never fault when copying from a kernel buffer, and the FPU + * state we set at boot time should be valid. + */ WARN_ON_FPU(err); } @@ -350,7 +331,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u32 hmask = mask >> 32; int err; - WARN_ON(!alternatives_patched); + WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); @@ -365,12 +346,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err; - - XSTATE_XRESTORE(xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ - WARN_ON_FPU(err); + XSTATE_XRESTORE(xstate, lmask, hmask); } /* @@ -526,38 +503,17 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) */ static inline void fpregs_deactivate(struct fpu *fpu) { - WARN_ON_FPU(!fpu->fpregs_active); - - fpu->fpregs_active = 0; this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { - WARN_ON_FPU(fpu->fpregs_active); - - fpu->fpregs_active = 1; this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int fpregs_active(void) -{ - return current->thread.fpu.fpregs_active; -} - -/* * FPU state switching for scheduling. * * This is a two-stage process: @@ -571,14 +527,13 @@ static inline int fpregs_active(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->fpregs_active) { + if (old_fpu->initialized) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ - old_fpu->fpregs_active = 0; trace_x86_fpu_regs_deactivated(old_fpu); } else old_fpu->last_cpu = -1; @@ -595,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu) static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu) { bool preload = static_cpu_has(X86_FEATURE_FPU) && - new_fpu->fpstate_active; + new_fpu->initialized; if (preload) { if (!fpregs_state_valid(new_fpu, cpu)) @@ -617,8 +572,7 @@ static inline void user_fpu_begin(void) struct fpu *fpu = ¤t->thread.fpu; preempt_disable(); - if (!fpregs_active()) - fpregs_activate(fpu); + fpregs_activate(fpu); preempt_enable(); } diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 3c80f5b..a152057 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -68,6 +68,9 @@ struct fxregs_state { /* Default value for fxregs_state.mxcsr: */ #define MXCSR_DEFAULT 0x1f80 +/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */ +#define MXCSR_AND_FLAGS_SIZE sizeof(u64) + /* * Software based FPU emulation state. This is arbitrary really, * it matches the x87 format to make it easier to understand: @@ -290,36 +293,13 @@ struct fpu { unsigned int last_cpu; /* - * @fpstate_active: + * @initialized: * - * This flag indicates whether this context is active: if the task + * This flag indicates whether this context is initialized: if the task * is not running then we can restore from this context, if the task * is running then we should save into this context. */ - unsigned char fpstate_active; - - /* - * @fpregs_active: - * - * This flag determines whether a given context is actively - * loaded into the FPU's registers and that those registers - * represent the task's current FPU state. - * - * Note the interaction with fpstate_active: - * - * # task does not use the FPU: - * fpstate_active == 0 - * - * # task uses the FPU and regs are active: - * fpstate_active == 1 && fpregs_active == 1 - * - * # the regs are inactive but still match fpstate: - * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu - * - * The third state is what we use for the lazy restore optimization - * on lazy-switching CPUs. - */ - unsigned char fpregs_active; + unsigned char initialized; /* * @state: diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 1b2799e..83fee24 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,12 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave); -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave); +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); + +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +extern int validate_xstate_header(const struct xstate_header *hdr); + #endif diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 7ae318c..c120b5d 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -286,6 +286,32 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } +/* + * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID + * bits. This serves two purposes. It prevents a nasty situation in + * which PCID-unaware code saves CR3, loads some other value (with PCID + * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if + * the saved ASID was nonzero. It also means that any bugs involving + * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger + * deterministically. + */ + +static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) +{ + if (static_cpu_has(X86_FEATURE_PCID)) { + VM_WARN_ON_ONCE(asid > 4094); + return __sme_pa(mm->pgd) | (asid + 1); + } else { + VM_WARN_ON_ONCE(asid != 0); + return __sme_pa(mm->pgd); + } +} + +static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) +{ + VM_WARN_ON_ONCE(asid > 4094); + return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH; +} /* * This can be used from process context to figure out what the value of @@ -296,10 +322,8 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, */ static inline unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); - - if (static_cpu_has(X86_FEATURE_PCID)) - cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid); + unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm), + this_cpu_read(cpu_tlbstate.loaded_mm_asid)); /* For now, be very restrictive about when this can be called. */ VM_WARN_ON(in_nmi() || preemptible()); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 63cc96f..738503e 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -179,7 +179,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) u64 input_address = input ? virt_to_phys(input) : 0; u64 output_address = output ? virt_to_phys(output) : 0; u64 hv_status; - register void *__sp asm(_ASM_SP); #ifdef CONFIG_X86_64 if (!hv_hypercall_pg) @@ -187,7 +186,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) __asm__ __volatile__("mov %4, %%r8\n" "call *%5" - : "=a" (hv_status), "+r" (__sp), + : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input_address) : "r" (output_address), "m" (hv_hypercall_pg) : "cc", "memory", "r8", "r9", "r10", "r11"); @@ -202,7 +201,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) __asm__ __volatile__("call *%7" : "=A" (hv_status), - "+c" (input_address_lo), "+r" (__sp) + "+c" (input_address_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input_address_hi), "D"(output_address_hi), "S"(output_address_lo), @@ -224,12 +223,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) { u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; - register void *__sp asm(_ASM_SP); #ifdef CONFIG_X86_64 { __asm__ __volatile__("call *%4" - : "=a" (hv_status), "+r" (__sp), + : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input1) : "m" (hv_hypercall_pg) : "cc", "r8", "r9", "r10", "r11"); @@ -242,7 +240,7 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) __asm__ __volatile__ ("call *%5" : "=A"(hv_status), "+c"(input1_lo), - "+r"(__sp) + ASM_CALL_CONSTRAINT : "A" (control), "b" (input1_hi), "m" (hv_hypercall_pg) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 42873ed..280d94c 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -459,8 +459,8 @@ int paravirt_disable_iospace(void); */ #ifdef CONFIG_X86_32 #define PVOP_VCALL_ARGS \ - unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \ - register void *__sp asm("esp") + unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; + #define PVOP_CALL_ARGS PVOP_VCALL_ARGS #define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) @@ -480,8 +480,8 @@ int paravirt_disable_iospace(void); /* [re]ax isn't an arg, but the return val */ #define PVOP_VCALL_ARGS \ unsigned long __edi = __edi, __esi = __esi, \ - __edx = __edx, __ecx = __ecx, __eax = __eax; \ - register void *__sp asm("rsp") + __edx = __edx, __ecx = __ecx, __eax = __eax; + #define PVOP_CALL_ARGS PVOP_VCALL_ARGS #define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) @@ -532,7 +532,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ @@ -542,7 +542,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ @@ -569,7 +569,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index ec1f3c6..4f44505 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -100,19 +100,14 @@ static __always_inline bool should_resched(int preempt_offset) #ifdef CONFIG_PREEMPT extern asmlinkage void ___preempt_schedule(void); -# define __preempt_schedule() \ -({ \ - register void *__sp asm(_ASM_SP); \ - asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \ -}) +# define __preempt_schedule() \ + asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void ___preempt_schedule_notrace(void); -# define __preempt_schedule_notrace() \ -({ \ - register void *__sp asm(_ASM_SP); \ - asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \ -}) +# define __preempt_schedule_notrace() \ + asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT) + extern asmlinkage void preempt_schedule_notrace(void); #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3fa26a6..b390ff7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -677,8 +677,6 @@ static inline void sync_core(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ - register void *__sp asm(_ASM_SP); - #ifdef CONFIG_X86_32 asm volatile ( "pushfl\n\t" @@ -686,7 +684,7 @@ static inline void sync_core(void) "pushl $1f\n\t" "iret\n\t" "1:" - : "+r" (__sp) : : "memory"); + : ASM_CALL_CONSTRAINT : : "memory"); #else unsigned int tmp; @@ -703,7 +701,7 @@ static inline void sync_core(void) "iretq\n\t" UNWIND_HINT_RESTORE "1:" - : "=&r" (tmp), "+r" (__sp) : : "cc", "memory"); + : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory"); #endif } diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index a34e0d4..7116b79 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -103,7 +103,6 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) ({ \ long tmp; \ struct rw_semaphore* ret; \ - register void *__sp asm(_ASM_SP); \ \ asm volatile("# beginning down_write\n\t" \ LOCK_PREFIX " xadd %1,(%4)\n\t" \ @@ -114,7 +113,8 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) " call " slow_path "\n" \ "1:\n" \ "# ending down_write" \ - : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \ + : "+m" (sem->count), "=d" (tmp), \ + "=a" (ret), ASM_CALL_CONSTRAINT \ : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \ : "memory", "cc"); \ ret; \ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 5161da1a..89e7eeb 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -158,17 +158,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 342e597..39f7a27 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -12,25 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_STRUCT__entry( __field(struct fpu *, fpu) - __field(bool, fpregs_active) - __field(bool, fpstate_active) + __field(bool, initialized) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; - __entry->fpregs_active = fpu->fpregs_active; - __entry->fpstate_active = fpu->fpstate_active; + __entry->initialized = fpu->initialized; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, - __entry->fpregs_active, - __entry->fpstate_active, + __entry->initialized, __entry->xfeatures, __entry->xcomp_bv ) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 184eb98..4b89291 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -166,11 +166,11 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ - register void *__sp asm(_ASM_SP); \ __chk_user_ptr(ptr); \ might_fault(); \ asm volatile("call __get_user_%P4" \ - : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \ + : "=a" (__ret_gu), "=r" (__val_gu), \ + ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ @@ -337,7 +337,7 @@ do { \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ : "=r" (retval), "=&A"(x) \ - : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \ + : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9606688..7cb282e 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -113,10 +113,9 @@ extern struct { char _entry[32]; } hypercall_page[]; register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \ register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \ register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \ - register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \ - register void *__sp asm(_ASM_SP); + register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; -#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp) +#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT #define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1) #define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2) #define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3) @@ -552,13 +551,13 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { - u32 *p = (u32 *) &desc; - mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; mcl->args[1] = *(unsigned long *)&desc; } else { + u32 *p = (u32 *)&desc; + mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; mcl->args[2] = *p++; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index db68488..0af86d9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -21,14 +21,6 @@ void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#endif - identify_boot_cpu(); if (!IS_ENABLED(CONFIG_SMP)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 775f101..c9176ba 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -904,6 +904,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e1114f0..f92a659 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpregs_active) { + if (fpu->initialized) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpregs_active) + if (fpu->initialized) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu) preempt_disable(); trace_x86_fpu_before_save(fpu); - if (fpu->fpregs_active) { + if (fpu->initialized) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { - dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) + if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * - * We have to do all this with preemption disabled, - * mostly because of the FNSAVE case, because in that - * case we must not allow preemption in the window - * between the FNSAVE and us marking the context lazy. - * - * It shouldn't be an issue as even FNSAVE is plenty - * fast in terms of critical section length. + * ( The function 'fails' in the FNSAVE case, which destroys + * register contents so we have to copy them back. ) */ - preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { - memcpy(&src_fpu->state, &dst_fpu->state, - fpu_kernel_xstate_size); - + memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); copy_kernel_to_fpregs(&src_fpu->state); } - preempt_enable(); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Activate the current task's in-memory FPU context, * if it has not been used before: */ -void fpu__activate_curr(struct fpu *fpu) +void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for the current task: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } -EXPORT_SYMBOL_GPL(fpu__activate_curr); +EXPORT_SYMBOL_GPL(fpu__initialize); /* * This function must be called before we read a task's fpstate. * - * If the task has not used the FPU before then initialize its - * fpstate. + * There's two cases where this gets called: + * + * - for the current task (when coredumping), in which case we have + * to save the latest FPU registers into the fpstate, + * + * - or it's called for stopped tasks (ptrace), in which case the + * registers were already saved by the context-switch code when + * the task scheduled out - we only have to initialize the registers + * if they've never been initialized. * * If the task has used the FPU before then save it. */ -void fpu__activate_fpstate_read(struct fpu *fpu) +void fpu__prepare_read(struct fpu *fpu) { - /* - * If fpregs are active (in the current CPU), then - * copy them to the fpstate: - */ - if (fpu->fpregs_active) { + if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for current and for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } } @@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ -void fpu__activate_fpstate_write(struct fpu *fpu) +void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU @@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ WARN_ON_FPU(fpu == ¤t->thread.fpu); - if (fpu->fpstate_active) { - /* Invalidate any lazy state: */ + if (fpu->initialized) { + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); @@ -310,74 +300,11 @@ void fpu__activate_fpstate_write(struct fpu *fpu) trace_x86_fpu_activate_state(fpu); /* Safe to do for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } /* - * This function must be called before we write the current - * task's fpstate. - * - * This call gets the current FPU register state and moves - * it in to the 'fpstate'. Preemption is disabled so that - * no writes to the 'fpstate' can occur from context - * swiches. - * - * Must be followed by a fpu__current_fpstate_write_end(). - */ -void fpu__current_fpstate_write_begin(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * Ensure that the context-switching code does not write - * over the fpstate while we are doing our update. - */ - preempt_disable(); - - /* - * Move the fpregs in to the fpu's 'fpstate'. - */ - fpu__activate_fpstate_read(fpu); - - /* - * The caller is about to write to 'fpu'. Ensure that no - * CPU thinks that its fpregs match the fpstate. This - * ensures we will not be lazy and skip a XRSTOR in the - * future. - */ - __fpu_invalidate_fpregs_state(fpu); -} - -/* - * This function must be paired with fpu__current_fpstate_write_begin() - * - * This will ensure that the modified fpstate gets placed back in - * the fpregs if necessary. - * - * Note: This function may be called whether or not an _actual_ - * write to the fpstate occurred. - */ -void fpu__current_fpstate_write_end(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * 'fpu' now has an updated copy of the state, but the - * registers may still be out of date. Update them with - * an XRSTOR if they are active. - */ - if (fpregs_active()) - copy_kernel_to_fpregs(&fpu->state); - - /* - * Our update is done and the fpregs/fpstate are in sync - * if necessary. Context switches can happen again. - */ - preempt_enable(); -} - -/* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate * access to the hardware registers, so that FPU instructions @@ -389,7 +316,7 @@ void fpu__current_fpstate_write_end(void) */ void fpu__restore(struct fpu *fpu) { - fpu__activate_curr(fpu); + fpu__initialize(fpu); /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ kernel_fpu_disable(); @@ -414,15 +341,17 @@ void fpu__drop(struct fpu *fpu) { preempt_disable(); - if (fpu->fpregs_active) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - fpregs_deactivate(fpu); + if (fpu == ¤t->thread.fpu) { + if (fpu->initialized) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } } - fpu->fpstate_active = 0; + fpu->initialized = 0; trace_x86_fpu_dropped(fpu); @@ -462,9 +391,11 @@ void fpu__clear(struct fpu *fpu) * Make sure fpstate is cleared and initialized. */ if (static_cpu_has(X86_FEATURE_FPU)) { - fpu__activate_curr(fpu); + preempt_disable(); + fpu__initialize(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); + preempt_enable(); } } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d5d44c4..7affb7e 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - WARN_ON_FPU(current->thread.fpu.fpstate_active); + WARN_ON_FPU(current->thread.fpu.initialized); } /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b188b16..3ea1513 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -16,14 +16,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r { struct fpu *target_fpu = &target->thread.fpu; - return target_fpu->fpstate_active ? regset->n : 0; + return target_fpu->initialized ? regset->n : 0; } int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { struct fpu *target_fpu = &target->thread.fpu; - if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized) return regset->n; else return 0; @@ -38,7 +38,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); fpstate_sanitize_xstate(fpu); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -55,7 +55,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -89,10 +89,13 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (using_compacted_format()) { - ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave); + if (kbuf) + ret = copy_xstate_to_kernel(kbuf, xsave, pos, count); + else + ret = copy_xstate_to_user(ubuf, xsave, pos, count); } else { fpstate_sanitize_xstate(fpu); /* @@ -129,28 +132,29 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copyin_to_xsaves(kbuf, ubuf, xsave); - else + if (using_compacted_format()) { + if (kbuf) + ret = copy_kernel_to_xstate(xsave, kbuf); + else + ret = copy_user_to_xstate(xsave, ubuf); + } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); + if (!ret) + ret = validate_xstate_header(&xsave->header); + } /* * mxcsr reserved bits must be masked to zero for security reasons. */ xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->header.xfeatures &= xfeatures_mask; + /* - * These bits must be zero. + * In case of failure, mark all states as init: */ - memset(&xsave->header.reserved, 0, 48); + if (ret) + fpstate_init(&fpu->state); return ret; } @@ -299,7 +303,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); @@ -329,7 +333,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) @@ -369,7 +373,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) struct fpu *fpu = &tsk->thread.fpu; int fpvalid; - fpvalid = fpu->fpstate_active; + fpvalid = fpu->initialized; if (fpvalid) fpvalid = !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct), diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 83c23c2..fb639e7 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -155,7 +155,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) */ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + struct xregs_state *xsave = &fpu->state.xsave; struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); @@ -170,13 +171,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpregs_active() || using_compacted_format()) { + if (fpu->initialized || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; /* Update the thread's fxstate to save the fsave header. */ if (ia32_fxstate) - copy_fxregs_to_kernel(&tsk->thread.fpu); + copy_fxregs_to_kernel(fpu); } else { /* * It is a *bug* if kernel uses compacted-format for xsave @@ -189,7 +190,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return -1; } - fpstate_sanitize_xstate(&tsk->thread.fpu); + fpstate_sanitize_xstate(fpu); if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size)) return -1; } @@ -213,8 +214,11 @@ sanitize_restored_xstate(struct task_struct *tsk, struct xstate_header *header = &xsave->header; if (use_xsave()) { - /* These bits must be zero. */ - memset(header->reserved, 0, 48); + /* + * Note: we don't need to zero the reserved bits in the + * xstate_header here because we either didn't copy them at all, + * or we checked earlier that they aren't set. + */ /* * Init the state that is not present in the memory @@ -223,7 +227,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= (xfeatures_mask & xfeatures); + header->xfeatures &= xfeatures; } if (use_fxsr()) { @@ -279,7 +283,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_READ, buf, size)) return -EACCES; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, @@ -307,28 +311,29 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) /* * For 32-bit frames with fxstate, copy the user state to the * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. + * header. Validate and sanitize the copied state. */ struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; /* - * Drop the current fpu which clears fpu->fpstate_active. This ensures + * Drop the current fpu which clears fpu->initialized. This ensures * that any context-switch during the copy of the new state, * avoids the intermediate state from getting restored/saved. * Thus avoiding the new restored state from getting corrupted. * We will be ready to restore/save the state only after - * fpu->fpstate_active is again set. + * fpu->initialized is again set. */ fpu__drop(fpu); if (using_compacted_format()) { - err = copyin_to_xsaves(NULL, buf_fx, - &fpu->state.xsave); + err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); } else { - err = __copy_from_user(&fpu->state.xsave, - buf_fx, state_size); + err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); + + if (!err && state_size > offsetof(struct xregs_state, header)) + err = validate_xstate_header(&fpu->state.xsave.header); } if (err || __copy_from_user(&env, buf, sizeof(env))) { @@ -339,7 +344,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } - fpu->fpstate_active = 1; + fpu->initialized = 1; preempt_disable(); fpu__restore(fpu); preempt_enable(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c24ac1e..f1d5476 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -483,6 +483,30 @@ int using_compacted_format(void) return boot_cpu_has(X86_FEATURE_XSAVES); } +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +int validate_xstate_header(const struct xstate_header *hdr) +{ + /* No unknown or supervisor features may be set */ + if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + return -EINVAL; + + /* Userspace must use the uncompacted format */ + if (hdr->xcomp_bv) + return -EINVAL; + + /* + * If 'reserved' is shrunken to add a new field, make sure to validate + * that new field here! + */ + BUILD_BUG_ON(sizeof(hdr->reserved) != 48); + + /* No reserved bits may be set */ + if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + return 0; +} + static void __xstate_dump_leaves(void) { int i; @@ -867,7 +891,7 @@ const void *get_xsave_field_ptr(int xsave_state) { struct fpu *fpu = ¤t->thread.fpu; - if (!fpu->fpstate_active) + if (!fpu->initialized) return NULL; /* * fpu__save() takes the CPU's xstate registers @@ -921,38 +945,129 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, #endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* + * Weird legacy quirk: SSE and YMM states store information in the + * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP + * area is marked as unused in the xfeatures header, we need to copy + * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. + */ +static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) +{ + if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) + return false; + + if (xfeatures & XFEATURE_MASK_FP) + return false; + + return true; +} + +/* * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int xstate_copyout(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +static inline void +__copy_xstate_to_kernel(void *kbuf, const void *data, + unsigned int offset, unsigned int size, unsigned int size_total) { - if ((count == 0) || (pos < start_pos)) - return 0; + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + memcpy(kbuf + offset, data, copy); + } +} - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; +/* + * Convert from kernel XSAVES compacted format to standard format and copy + * to a kernel-space ptrace buffer. + * + * It supports partial copy but pos always starts from zero. This is called + * from xstateregs_get() and there we check the CPU has XSAVES. + */ +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) +{ + unsigned int offset, size; + struct xstate_header header; + int i; + + /* + * Currently copy_regset_to_user() starts from pos 0: + */ + if (unlikely(offset_start != 0)) + return -EFAULT; + + /* + * The destination is a ptrace buffer; we put in only user xstates: + */ + memset(&header, 0, sizeof(header)); + header.xfeatures = xsave->header.xfeatures; + header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + + /* + * Copy xregs_state->header: + */ + offset = offsetof(struct xregs_state, header); + size = sizeof(header); + + __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + + for (i = 0; i < XFEATURE_MAX; i++) { + /* + * Copy only in-use xstates: + */ + if ((header.xfeatures >> i) & 1) { + void *src = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + + __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); } + + } + + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); + } + + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + offset = offsetof(struct fxregs_state, sw_reserved); + size = sizeof(xstate_fx_sw_bytes); + + __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + + return 0; +} + +static inline int +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) +{ + if (!size) + return 0; + + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); + + if (__copy_to_user(ubuf + offset, data, copy)) + return -EFAULT; } return 0; } /* * Convert from kernel XSAVES compacted format to standard format and copy - * to a ptrace buffer. It supports partial copy but pos always starts from + * to a user-space buffer. It supports partial copy but pos always starts from * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -961,7 +1076,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -977,8 +1092,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total); if (ret) return ret; @@ -992,25 +1106,30 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count); + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= count) - break; } } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; @@ -1018,55 +1137,98 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, } /* - * Convert from a ptrace standard-format buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * and copy to the target thread. This is called from xstateregs_set(). */ -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 xfeatures; - u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; + memcpy(&hdr, kbuf + offset, size); + + if (validate_xstate_header(&hdr)) + return -EINVAL; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = ((u64)1 << i); + + if (hdr.xfeatures & mask) { + void *dst = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + memcpy(dst, kbuf + offset, size); + } + } + + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + memcpy(&xsave->i387.mxcsr, kbuf + offset, size); } /* - * Reject if the user sets any disabled or supervisor features: + * The state that came in from userspace was user-state only. + * Mask all the user states out of 'xfeatures': + */ + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + + /* + * Add back in the features that came in from userspace: */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures |= hdr.xfeatures; - if (xfeatures & ~allowed_features) + return 0; +} + +/* + * Convert from a ptrace or sigreturn standard-format user-space buffer to + * kernel XSAVES format and copy to the target thread. This is called from + * xstateregs_set(), as well as potentially from the sigreturn() and + * rt_sigreturn() system calls. + */ +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) +{ + unsigned int offset, size; + int i; + struct xstate_header hdr; + + offset = offsetof(struct xregs_state, header); + size = sizeof(hdr); + + if (__copy_from_user(&hdr, ubuf + offset, size)) + return -EFAULT; + + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } } + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + return -EFAULT; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1076,7 +1238,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a..d4eb450 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -64,7 +64,7 @@ static void call_on_stack(void *func, void *stack) static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,7 +88,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -139,7 +139,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4b0592c..8c1cc08 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent) return 0; out_clean_nodes: - for (j = i - 1; j > 0; j--) + for (j = i - 1; j >= 0; j--) cleanup_setup_data_node(*(kobjp + j)); kfree(kobjp); out_setup_data_kobj: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aa60a08..e675704 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -140,7 +140,8 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1 || + rcu_preempt_depth(); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e044423..4e188fd 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -263,7 +263,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = (unsigned long) ka->sa.sa_restorer; } - if (fpu->fpstate_active) { + if (fpu->initialized) { sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; @@ -279,7 +279,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (fpu->fpstate_active && + if (fpu->initialized && copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; @@ -755,7 +755,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (fpu->fpstate_active) + if (fpu->initialized) fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0854ff1..ad59edd 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -232,12 +232,6 @@ static void notrace start_secondary(void *unused) */ if (boot_cpu_has(X86_FEATURE_PCID)) __write_cr4(__read_cr4() | X86_CR4_PCIDE); - cpu_init(); - x86_cpuinit.early_percpu_clock_init(); - preempt_disable(); - smp_callin(); - - enable_start_cpu0 = 0; #ifdef CONFIG_X86_32 /* switch away from the initial page table */ @@ -245,6 +239,13 @@ static void notrace start_secondary(void *unused) __flush_tlb_all(); #endif + cpu_init(); + x86_cpuinit.early_percpu_clock_init(); + preempt_disable(); + smp_callin(); + + enable_start_cpu0 = 0; + /* otherwise gcc will move up smp_processor_id before the cpu_init */ barrier(); /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 34ea365..67db4f4 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -142,7 +142,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_enable_no_resched(); } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 15f527b..a36254c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5298,7 +5298,6 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) @@ -5306,7 +5305,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [fastop]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0726ca7..a2b804e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -200,6 +200,8 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ + unsigned long vmcs_host_cr4; /* May not match real cr4 */ struct list_head loaded_vmcss_on_cpu_link; }; @@ -600,8 +602,6 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) struct pi_desc old, new; unsigned int dest; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + /* + * In case of hot-plug or hot-unplug, we may have to undo + * vmx_vcpu_pi_put even if there is no assigned device. And we + * always keep PI.NDST up to date for simplicity: it makes the + * code easier, and CPU migration is not a fast path. + */ + if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * First handle the simple case where no cmpxchg is necessary; just + * allow posting non-urgent interrupts. + * + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block will do it for us and the wakeup_handler + * expects the VCPU to be on the blocked_vcpu_list that matches + * PI.NDST. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || + vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + return; + } + + /* The full case. */ do { old.control = new.control = pi_desc->control; - /* - * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there - * are two possible cases: - * 1. After running 'pre_block', context switch - * happened. For this case, 'sn' was set in - * vmx_vcpu_put(), so we need to clear it here. - * 2. After running 'pre_block', we were blocked, - * and woken up by some other guy. For this case, - * we don't need to do anything, 'pi_post_block' - * will do everything for us. However, we cannot - * check whether it is case #1 or case #2 here - * (maybe, not needed), so we also clear sn here, - * I think it is not a big deal. - */ - if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { - if (vcpu->cpu != cpu) { - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - } + dest = cpu_physical_id(cpu); - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ new.sn = 0; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); } static void decache_tsc_multiplier(struct vcpu_vmx *vmx) @@ -5178,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 @@ -9045,7 +9043,6 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) { u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - register void *__sp asm(_ASM_SP); if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { @@ -9074,7 +9071,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif - "+r"(__sp) + ASM_CALL_CONSTRAINT : [entry]"r"(entry), [ss]"i"(__KERNEL_DS), @@ -9274,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the @@ -9592,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; + return &vmx->vcpu; free_vmcs: @@ -9840,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && + !to_vmx(vcpu)->nested.nested_run_pending) { vmcs12->vm_exit_intr_error_code = fault->error_code; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | @@ -11705,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +static void __pi_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + do { + old.control = new.control = pi_desc->control; + WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the VCPU is blocked\n"); + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); + + if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + vcpu->pre_pcpu = -1; + } +} + /* * This routine does the following things for vCPU which is going * to be blocked if VT-d PI is enabled. @@ -11720,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, */ static int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned long flags; unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -11730,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) !kvm_vcpu_apicv_active(vcpu)) return 0; - vcpu->pre_pcpu = vcpu->cpu; - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + WARN_ON(irqs_disabled()); + local_irq_disable(); + if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + } do { old.control = new.control = pi_desc->control; - /* - * We should not block the vCPU if - * an interrupt is posted for it. - */ - if (pi_test_on(pi_desc) == 1) { - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - - return 1; - } - WARN((pi_desc->sn == 1), "Warning: SN field of posted-interrupts " "is set before blocking\n"); @@ -11779,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); - return 0; + /* We should not block the vCPU if an interrupt is posted for it. */ + if (pi_test_on(pi_desc) == 1) + __pi_post_block(vcpu); + + local_irq_enable(); + return (vcpu->pre_pcpu == -1); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -11798,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - unsigned long flags; - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (vcpu->pre_pcpu == -1) return; - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* Allow posting non-urgent interrupts */ - new.sn = 0; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); - - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - } + WARN_ON(irqs_disabled()); + local_irq_disable(); + __pi_post_block(vcpu); + local_irq_enable(); } static void vmx_post_block(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd17b7d..03869eb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7225,7 +7225,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index d4a7df2..220638a 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -114,7 +114,7 @@ void math_emulate(struct math_emu_info *info) struct desc_struct code_descriptor; struct fpu *fpu = ¤t->thread.fpu; - fpu__activate_curr(fpu); + fpu__initialize(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index c076f71..c3521e2 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -2,6 +2,7 @@ #include <linux/uaccess.h> #include <linux/sched/debug.h> +#include <asm/fpu/internal.h> #include <asm/traps.h> #include <asm/kdebug.h> @@ -78,6 +79,29 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_refcount); +/* + * Handler for when we fail to restore a task's FPU state. We should never get + * here because the FPU state of a task using the FPU (task->thread.fpu.state) + * should always be valid. However, past bugs have allowed userspace to set + * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). + * These caused XRSTOR to fail when switching to the task, leaking the FPU + * registers of the task previously executing on the CPU. Mitigate this class + * of vulnerability by restoring from the initial state (essentially, zeroing + * out all the FPU registers) if we can't restore from the task's FPU state. + */ +bool ex_handler_fprestore(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + + WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", + (void *)instruction_pointer(regs)); + + __copy_kernel_to_fpregs(&init_fpstate, -1); + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fprestore); + bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b836a72..e2baeaa 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -192,8 +192,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, - struct vm_area_struct *vma) +static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) @@ -209,7 +208,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * valid VMA, so we should never reach this without a * valid VMA. */ - if (!vma) { + if (!pkey) { WARN_ONCE(1, "PKU fault with no VMA passed in"); info->si_pkey = 0; return; @@ -219,13 +218,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * absolutely guranteed to be 100% accurate because of * the race explained above. */ - info->si_pkey = vma_pkey(vma); + info->si_pkey = *pkey; } static void force_sig_info_fault(int si_signo, int si_code, unsigned long address, - struct task_struct *tsk, struct vm_area_struct *vma, - int fault) + struct task_struct *tsk, u32 *pkey, int fault) { unsigned lsb = 0; siginfo_t info; @@ -240,7 +238,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, vma); + fill_sig_info_pkey(si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -762,8 +760,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; unsigned long flags; int sig; - /* No context means no VMA to pass down */ - struct vm_area_struct *vma = NULL; /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF)) { @@ -788,7 +784,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* XXX: hwpoison faults will set the wrong code. */ force_sig_info_fault(signal, si_code, address, - tsk, vma, 0); + tsk, NULL, 0); } /* @@ -806,7 +802,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, if (is_vmalloc_addr((void *)address) && (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { - register void *__sp asm("rsp"); unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *); /* * We're likely to be running with very little stack space @@ -821,7 +816,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, asm volatile ("movq %[stack], %%rsp\n\t" "call handle_stack_overflow\n\t" "1: jmp 1b" - : "+r" (__sp) + : ASM_CALL_CONSTRAINT : "D" ("kernel stack overflow (page fault)"), "S" (regs), "d" (address), [stack] "rm" (stack)); @@ -897,8 +892,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - int si_code) + unsigned long address, u32 *pkey, int si_code) { struct task_struct *tsk = current; @@ -946,7 +940,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_PF; - force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0); + force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0); return; } @@ -959,9 +953,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, u32 *pkey) { - __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR); + __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR); } static void @@ -969,6 +963,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma, int si_code) { struct mm_struct *mm = current->mm; + u32 pkey; + + if (vma) + pkey = vma_pkey(vma); /* * Something tried to access memory that isn't in our memory map.. @@ -976,7 +974,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, */ up_read(&mm->mmap_sem); - __bad_area_nosemaphore(regs, error_code, address, vma, si_code); + __bad_area_nosemaphore(regs, error_code, address, + (vma) ? &pkey : NULL, si_code); } static noinline void @@ -1019,7 +1018,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, - struct vm_area_struct *vma, unsigned int fault) + u32 *pkey, unsigned int fault) { struct task_struct *tsk = current; int code = BUS_ADRERR; @@ -1046,13 +1045,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, code = BUS_MCEERR_AR; } #endif - force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault); + force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault); } static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - unsigned int fault) + unsigned long address, u32 *pkey, unsigned int fault) { if (fatal_signal_pending(current) && !(error_code & PF_USER)) { no_context(regs, error_code, address, 0, 0); @@ -1076,9 +1074,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) - do_sigbus(regs, error_code, address, vma, fault); + do_sigbus(regs, error_code, address, pkey, fault); else if (fault & VM_FAULT_SIGSEGV) - bad_area_nosemaphore(regs, error_code, address, vma); + bad_area_nosemaphore(regs, error_code, address, pkey); else BUG(); } @@ -1268,6 +1266,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, struct mm_struct *mm; int fault, major = 0; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + u32 pkey; tsk = current; mm = tsk->mm; @@ -1468,9 +1467,10 @@ good_area: return; } + pkey = vma_pkey(vma); up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, error_code, address, vma, fault); + mm_fault_error(regs, error_code, address, &pkey, fault); return; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 3fcc8e0..16c5f37 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -10,6 +10,8 @@ * published by the Free Software Foundation. */ +#define DISABLE_BRANCH_PROFILING + #include <linux/linkage.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 2dab69a..d7bc0eea 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -18,7 +18,6 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/mmu_context.h> /* vma_pkey() */ -#include <asm/fpu/internal.h> /* fpregs_active() */ int __execute_only_pkey(struct mm_struct *mm) { @@ -45,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - fpregs_active() && + current->thread.fpu.initialized && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 1ab3821..49d9778 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -126,8 +126,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != - (__sme_pa(real_prev->pgd) | prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -172,7 +171,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, */ this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, next_tlb_gen); - write_cr3(__sme_pa(next->pgd) | prev_asid); + write_cr3(build_cr3(next, prev_asid)); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } @@ -192,7 +191,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer()); + unsigned int index = pgd_index(current_stack_pointer); pgd_t *pgd = next->pgd + index; if (unlikely(pgd_none(*pgd))) @@ -216,12 +215,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - write_cr3(__sme_pa(next->pgd) | new_asid); + write_cr3(build_cr3(next, new_asid)); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH); + write_cr3(build_cr3_noflush(next, new_asid)); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); } @@ -265,7 +264,7 @@ void initialize_tlbstate_and_flush(void) !(cr4_read_shadow() & X86_CR4_PCIDE)); /* Force ASID 0 and force a TLB flush. */ - write_cr3(cr3 & ~CR3_PCID_MASK); + write_cr3(build_cr3(mm, 0)); /* Reinitialize tlbstate. */ this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 7330cb3..71495f1 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1238,21 +1238,16 @@ static void __init xen_pagetable_cleanhighmap(void) * from _brk_limit way up to the max_pfn_mapped (which is the end of * the ramdisk). We continue on, erasing PMD entries that point to page * tables - do note that they are accessible at this stage via __va. - * For good measure we also round up to the PMD - which means that if + * As Xen is aligning the memory end to a 4MB boundary, for good + * measure we also round up to PMD_SIZE * 2 - which means that if * anybody is using __ka address to the initial boot-stack - and try * to use it - they are going to crash. The xen_start_info has been * taken care of already in xen_setup_kernel_pagetable. */ addr = xen_start_info->pt_base; - size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE); + size = xen_start_info->nr_pt_frames * PAGE_SIZE; - xen_cleanhighmap(addr, addr + size); + xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); -#ifdef DEBUG - /* This is superfluous and is not necessary, but you know what - * lets do it. The MODULES_VADDR -> MODULES_END should be clear of - * anything at this stage. */ - xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1); -#endif } #endif diff --git a/block/blk-core.c b/block/blk-core.c index aebe676..048be4a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) kobject_init(&q->kobj, &blk_queue_ktype); +#ifdef CONFIG_BLK_DEV_IO_TRACE + mutex_init(&q->blk_trace_mutex); +#endif mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index c82408c..dbddff8 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -154,7 +154,6 @@ static int bsg_prepare_job(struct device *dev, struct request *req) failjob_rls_rqst_payload: kfree(job->request_payload.sg_list); failjob_rls_job: - kfree(job); return -ENOMEM; } diff --git a/block/partition-generic.c b/block/partition-generic.c index 86e8fe1..88c555d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -112,7 +112,7 @@ ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); - struct request_queue *q = dev_to_disk(dev)->queue; + struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; int cpu; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 077f9ba..3c3a37b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -743,17 +743,19 @@ static int ghes_proc(struct ghes *ghes) } ghes_do_proc(ghes, ghes->estatus); +out: + ghes_clear_estatus(ghes); + + if (rc == -ENOENT) + return rc; + /* * GHESv2 type HEST entries introduce support for error acknowledgment, * so only acknowledge the error if this support is present. */ - if (is_hest_type_generic_v2(ghes)) { - rc = ghes_ack_error(ghes->generic_v2); - if (rc) - return rc; - } -out: - ghes_clear_estatus(ghes); + if (is_hest_type_generic_v2(ghes)) + return ghes_ack_error(ghes->generic_v2); + return rc; } diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d055b3f..ab34239 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2217,7 +2217,7 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, debug_id, (u64)fda->num_fds); continue; } - fd_array = (u32 *)(parent_buffer + fda->parent_offset); + fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); for (fd_index = 0; fd_index < fda->num_fds; fd_index++) task_close_fd(proc, fd_array[fd_index]); } break; @@ -2326,7 +2326,6 @@ static int binder_translate_handle(struct flat_binder_object *fp, (u64)node->ptr); binder_node_unlock(node); } else { - int ret; struct binder_ref_data dest_rdata; binder_node_unlock(node); @@ -2442,7 +2441,7 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, */ parent_buffer = parent->buffer - binder_alloc_get_user_buffer_offset(&target_proc->alloc); - fd_array = (u32 *)(parent_buffer + fda->parent_offset); + fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) { binder_user_error("%d:%d parent offset not aligned correctly.\n", proc->pid, thread->pid); @@ -2508,7 +2507,7 @@ static int binder_fixup_parent(struct binder_transaction *t, proc->pid, thread->pid); return -EINVAL; } - parent_buffer = (u8 *)(parent->buffer - + parent_buffer = (u8 *)((uintptr_t)parent->buffer - binder_alloc_get_user_buffer_offset( &target_proc->alloc)); *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer; @@ -3083,6 +3082,7 @@ static void binder_transaction(struct binder_proc *proc, err_dead_proc_or_thread: return_error = BR_DEAD_REPLY; return_error_line = __LINE__; + binder_dequeue_work(proc, tcomplete); err_translate_failed: err_bad_object_type: err_bad_offset: diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index cb9b0e9..9f78bb0 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -621,8 +621,11 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, static int ahci_pci_reset_controller(struct ata_host *host) { struct pci_dev *pdev = to_pci_dev(host->dev); + int rc; - ahci_reset_controller(host); + rc = ahci_reset_controller(host); + if (rc) + return rc; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { struct ahci_host_priv *hpriv = host->private_data; diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 8401c3b..b702c20 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -492,6 +492,7 @@ static const struct ich_laptop ich_laptop[] = { { 0x27DF, 0x152D, 0x0778 }, /* ICH7 on unknown Intel */ { 0x24CA, 0x1025, 0x0061 }, /* ICH4 on ACER Aspire 2023WLMi */ { 0x24CA, 0x1025, 0x003d }, /* ICH4 on ACER TM290 */ + { 0x24CA, 0x10CF, 0x11AB }, /* ICH4M on Fujitsu-Siemens Lifebook S6120 */ { 0x266F, 0x1025, 0x0066 }, /* ICH6 on ACER Aspire 1694WLMi */ { 0x2653, 0x1043, 0x82D8 }, /* ICH6M on Asus Eee 701 */ { 0x27df, 0x104d, 0x900e }, /* ICH7 on Sony TZ-90 */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 1945a8e..ee4c1ec 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3234,19 +3234,19 @@ static const struct ata_timing ata_timing[] = { }; #define ENOUGH(v, unit) (((v)-1)/(unit)+1) -#define EZ(v, unit) ((v)?ENOUGH(v, unit):0) +#define EZ(v, unit) ((v)?ENOUGH(((v) * 1000), unit):0) static void ata_timing_quantize(const struct ata_timing *t, struct ata_timing *q, int T, int UT) { - q->setup = EZ(t->setup * 1000, T); - q->act8b = EZ(t->act8b * 1000, T); - q->rec8b = EZ(t->rec8b * 1000, T); - q->cyc8b = EZ(t->cyc8b * 1000, T); - q->active = EZ(t->active * 1000, T); - q->recover = EZ(t->recover * 1000, T); - q->dmack_hold = EZ(t->dmack_hold * 1000, T); - q->cycle = EZ(t->cycle * 1000, T); - q->udma = EZ(t->udma * 1000, UT); + q->setup = EZ(t->setup, T); + q->act8b = EZ(t->act8b, T); + q->rec8b = EZ(t->rec8b, T); + q->cyc8b = EZ(t->cyc8b, T); + q->active = EZ(t->active, T); + q->recover = EZ(t->recover, T); + q->dmack_hold = EZ(t->dmack_hold, T); + q->cycle = EZ(t->cycle, T); + q->udma = EZ(t->udma, UT); } void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b, diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index cfeb049..642afd8 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -647,18 +647,25 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf, static int charlcd_open(struct inode *inode, struct file *file) { struct charlcd_priv *priv = to_priv(the_charlcd); + int ret; + ret = -EBUSY; if (!atomic_dec_and_test(&charlcd_available)) - return -EBUSY; /* open only once at a time */ + goto fail; /* open only once at a time */ + ret = -EPERM; if (file->f_mode & FMODE_READ) /* device is write-only */ - return -EPERM; + goto fail; if (priv->must_clear) { charlcd_clear_display(&priv->lcd); priv->must_clear = false; } return nonseekable_open(inode, file); + + fail: + atomic_inc(&charlcd_available); + return ret; } static int charlcd_release(struct inode *inode, struct file *file) diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index df126dc..6911acd 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1105,14 +1105,21 @@ static ssize_t keypad_read(struct file *file, static int keypad_open(struct inode *inode, struct file *file) { + int ret; + + ret = -EBUSY; if (!atomic_dec_and_test(&keypad_available)) - return -EBUSY; /* open only once at a time */ + goto fail; /* open only once at a time */ + ret = -EPERM; if (file->f_mode & FMODE_WRITE) /* device is read-only */ - return -EPERM; + goto fail; keypad_buflen = 0; /* flush the buffer on opening */ return 0; + fail: + atomic_inc(&keypad_available); + return ret; } static int keypad_release(struct inode *inode, struct file *file) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 41be9ff..6df7d66 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -166,11 +166,11 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) } #ifdef CONFIG_CPU_FREQ -static cpumask_var_t cpus_to_visit; -static void parsing_done_workfn(struct work_struct *work); -static DECLARE_WORK(parsing_done_work, parsing_done_workfn); +static cpumask_var_t cpus_to_visit __initdata; +static void __init parsing_done_workfn(struct work_struct *work); +static __initdata DECLARE_WORK(parsing_done_work, parsing_done_workfn); -static int +static int __init init_cpu_capacity_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -206,7 +206,7 @@ init_cpu_capacity_callback(struct notifier_block *nb, return 0; } -static struct notifier_block init_cpu_capacity_notifier = { +static struct notifier_block init_cpu_capacity_notifier __initdata = { .notifier_call = init_cpu_capacity_callback, }; @@ -232,7 +232,7 @@ static int __init register_cpufreq_notifier(void) } core_initcall(register_cpufreq_notifier); -static void parsing_done_workfn(struct work_struct *work) +static void __init parsing_done_workfn(struct work_struct *work) { cpufreq_unregister_notifier(&init_cpu_capacity_notifier, CPUFREQ_POLICY_NOTIFIER); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index d1bd992..9045c5f 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -868,7 +868,8 @@ static ssize_t driver_override_store(struct device *dev, struct platform_device *pdev = to_platform_device(dev); char *driver_override, *old, *cp; - if (count > PATH_MAX) + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) return -EINVAL; driver_override = kstrndup(buf, count, GFP_KERNEL); diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index a8cc14f..a6de325 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -1581,6 +1581,9 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, opp->available = availability_req; + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + /* Notify the change of the OPP availability */ if (availability_req) blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE, @@ -1589,8 +1592,12 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_DISABLE, opp); + dev_pm_opp_put(opp); + goto put_table; + unlock: mutex_unlock(&opp_table->lock); +put_table: dev_pm_opp_put_opp_table(opp_table); return r; } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bbd0d18..2d7178f 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -342,7 +342,7 @@ static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff, if (!brd) return -ENODEV; - page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512); + page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT); if (!page) return -ENOSPC; *kaddr = page_address(page); diff --git a/drivers/block/loop.h b/drivers/block/loop.h index f68c1d5..1f39567 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -67,10 +67,8 @@ struct loop_device { struct loop_cmd { struct kthread_work work; struct request *rq; - union { - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - }; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2aa87cb..3684e21 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1194,6 +1194,12 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* The block layer will pass back some non-nbd ioctls in case we have + * special handling for them, but we don't so just return an error. + */ + if (_IOC_TYPE(cmd) != 0xab) + return -EINVAL; + mutex_lock(&nbd->config_lock); /* Don't allow ioctl operations on a nbd device that was created with diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index fe597e6..1d6729b 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -455,7 +455,7 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, goto out; } - msleep(TPM_TIMEOUT); /* CHECK */ + tpm_msleep(TPM_TIMEOUT); rmb(); } while (time_before(jiffies, stop)); @@ -970,7 +970,7 @@ int tpm_do_selftest(struct tpm_chip *chip) dev_info( &chip->dev, HW_ERR "TPM command timed out during continue self test"); - msleep(delay_msec); + tpm_msleep(delay_msec); continue; } @@ -985,7 +985,7 @@ int tpm_do_selftest(struct tpm_chip *chip) } if (rc != TPM_WARN_DOING_SELFTEST) return rc; - msleep(delay_msec); + tpm_msleep(delay_msec); } while (--loops > 0); return rc; @@ -1085,7 +1085,7 @@ again: } } else { do { - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); status = chip->ops->status(chip); if ((status & mask) == mask) return 0; @@ -1150,7 +1150,7 @@ int tpm_pm_suspend(struct device *dev) */ if (rc != TPM_WARN_RETRY) break; - msleep(TPM_TIMEOUT_RETRY); + tpm_msleep(TPM_TIMEOUT_RETRY); } if (rc) diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 04fbff2..2d5466a 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -50,7 +50,8 @@ enum tpm_const { enum tpm_timeout { TPM_TIMEOUT = 5, /* msecs */ - TPM_TIMEOUT_RETRY = 100 /* msecs */ + TPM_TIMEOUT_RETRY = 100, /* msecs */ + TPM_TIMEOUT_RANGE_US = 300 /* usecs */ }; /* TPM addresses */ @@ -527,6 +528,12 @@ int tpm_pm_resume(struct device *dev); int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout, wait_queue_head_t *queue, bool check_cancel); +static inline void tpm_msleep(unsigned int delay_msec) +{ + usleep_range(delay_msec * 1000, + (delay_msec * 1000) + TPM_TIMEOUT_RANGE_US); +}; + struct tpm_chip *tpm_chip_find_get(int chip_num); __must_check int tpm_try_get_ops(struct tpm_chip *chip); void tpm_put_ops(struct tpm_chip *chip); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index f7f34b2a..e1a41b7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -899,7 +899,7 @@ static int tpm2_do_selftest(struct tpm_chip *chip) if (rc != TPM2_RC_TESTING) break; - msleep(delay_msec); + tpm_msleep(delay_msec); } return rc; diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index a4ac63a..8f0a98d 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -665,7 +665,7 @@ static const struct dev_pm_ops crb_pm = { SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL) }; -static struct acpi_device_id crb_device_ids[] = { +static const struct acpi_device_id crb_device_ids[] = { {"MSFT0101", 0}, {"", 0}, }; diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index f01d083..25f6e26 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -32,26 +32,70 @@ static const char tpm_ibmvtpm_driver_name[] = "tpm_ibmvtpm"; -static struct vio_device_id tpm_ibmvtpm_device_table[] = { +static const struct vio_device_id tpm_ibmvtpm_device_table[] = { { "IBM,vtpm", "IBM,vtpm"}, { "", "" } }; MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table); /** + * + * ibmvtpm_send_crq_word - Send a CRQ request + * @vdev: vio device struct + * @w1: pre-constructed first word of tpm crq (second word is reserved) + * + * Return: + * 0 - Success + * Non-zero - Failure + */ +static int ibmvtpm_send_crq_word(struct vio_dev *vdev, u64 w1) +{ + return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, 0); +} + +/** + * * ibmvtpm_send_crq - Send a CRQ request * * @vdev: vio device struct - * @w1: first word - * @w2: second word + * @valid: Valid field + * @msg: Type field + * @len: Length field + * @data: Data field + * + * The ibmvtpm crq is defined as follows: + * + * Byte | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 + * ----------------------------------------------------------------------- + * Word0 | Valid | Type | Length | Data + * ----------------------------------------------------------------------- + * Word1 | Reserved + * ----------------------------------------------------------------------- + * + * Which matches the following structure (on bigendian host): + * + * struct ibmvtpm_crq { + * u8 valid; + * u8 msg; + * __be16 len; + * __be32 data; + * __be64 reserved; + * } __attribute__((packed, aligned(8))); + * + * However, the value is passed in a register so just compute the numeric value + * to load into the register avoiding byteswap altogether. Endian only affects + * memory loads and stores - registers are internally represented the same. * * Return: - * 0 -Sucess + * 0 (H_SUCCESS) - Success * Non-zero - Failure */ -static int ibmvtpm_send_crq(struct vio_dev *vdev, u64 w1, u64 w2) +static int ibmvtpm_send_crq(struct vio_dev *vdev, + u8 valid, u8 msg, u16 len, u32 data) { - return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, w2); + u64 w1 = ((u64)valid << 56) | ((u64)msg << 48) | ((u64)len << 32) | + (u64)data; + return ibmvtpm_send_crq_word(vdev, w1); } /** @@ -109,8 +153,6 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count) static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) { struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); - struct ibmvtpm_crq crq; - __be64 *word = (__be64 *)&crq; int rc, sig; if (!ibmvtpm->rtce_buf) { @@ -137,10 +179,6 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) spin_lock(&ibmvtpm->rtce_lock); ibmvtpm->res_len = 0; memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count); - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_TPM_COMMAND; - crq.len = cpu_to_be16(count); - crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle); /* * set the processing flag before the Hcall, since we may get the @@ -148,8 +186,9 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) */ ibmvtpm->tpm_processing_cmd = true; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]), - be64_to_cpu(word[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND, + count, ibmvtpm->rtce_dma_handle); if (rc != H_SUCCESS) { dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc); rc = 0; @@ -182,15 +221,10 @@ static u8 tpm_ibmvtpm_status(struct tpm_chip *chip) */ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm) { - struct ibmvtpm_crq crq; - u64 *buf = (u64 *) &crq; int rc; - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE; - - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), - cpu_to_be64(buf[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_GET_RTCE_BUFFER_SIZE, 0, 0); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc); @@ -210,15 +244,10 @@ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm) */ static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm) { - struct ibmvtpm_crq crq; - u64 *buf = (u64 *) &crq; int rc; - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_GET_VERSION; - - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), - cpu_to_be64(buf[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_GET_VERSION, 0, 0); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_version failed rc=%d\n", rc); @@ -238,7 +267,7 @@ static int ibmvtpm_crq_send_init_complete(struct ibmvtpm_dev *ibmvtpm) { int rc; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_COMP_CMD, 0); + rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_COMP_CMD); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_send_init_complete failed rc=%d\n", rc); @@ -258,7 +287,7 @@ static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm) { int rc; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_CMD, 0); + rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_send_init failed rc=%d\n", rc); @@ -340,15 +369,10 @@ static int tpm_ibmvtpm_suspend(struct device *dev) { struct tpm_chip *chip = dev_get_drvdata(dev); struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); - struct ibmvtpm_crq crq; - u64 *buf = (u64 *) &crq; int rc = 0; - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND; - - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), - cpu_to_be64(buf[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_PREPARE_TO_SUSPEND, 0, 0); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "tpm_ibmvtpm_suspend failed rc=%d\n", rc); diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c index 3b1b9f9..d8f1004 100644 --- a/drivers/char/tpm/tpm_infineon.c +++ b/drivers/char/tpm/tpm_infineon.c @@ -191,7 +191,7 @@ static int wait(struct tpm_chip *chip, int wait_for_bit) /* check the status-register if wait_for_bit is set */ if (status & 1 << wait_for_bit) break; - msleep(TPM_MSLEEP_TIME); + tpm_msleep(TPM_MSLEEP_TIME); } if (i == TPM_MAX_TRIES) { /* timeout occurs */ if (wait_for_bit == STAT_XFE) @@ -226,7 +226,7 @@ static void tpm_wtx(struct tpm_chip *chip) wait_and_send(chip, TPM_CTRL_WTX); wait_and_send(chip, 0x00); wait_and_send(chip, 0x00); - msleep(TPM_WTX_MSLEEP_TIME); + tpm_msleep(TPM_WTX_MSLEEP_TIME); } static void tpm_wtx_abort(struct tpm_chip *chip) @@ -237,7 +237,7 @@ static void tpm_wtx_abort(struct tpm_chip *chip) wait_and_send(chip, 0x00); wait_and_send(chip, 0x00); number_of_wtx = 0; - msleep(TPM_WTX_MSLEEP_TIME); + tpm_msleep(TPM_WTX_MSLEEP_TIME); } static int tpm_inf_recv(struct tpm_chip *chip, u8 * buf, size_t count) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index b617b2e..63bc6c3 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -51,7 +51,7 @@ static int wait_startup(struct tpm_chip *chip, int l) if (access & TPM_ACCESS_VALID) return 0; - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); } while (time_before(jiffies, stop)); return -1; } @@ -117,7 +117,7 @@ again: do { if (check_locality(chip, l)) return l; - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); } while (time_before(jiffies, stop)); } return -1; @@ -164,7 +164,7 @@ static int get_burstcount(struct tpm_chip *chip) burstcnt = (value >> 8) & 0xFFFF; if (burstcnt) return burstcnt; - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); } while (time_before(jiffies, stop)); return -EBUSY; } @@ -396,7 +396,7 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) priv->irq = irq; chip->flags |= TPM_CHIP_FLAG_IRQ; if (!priv->irq_tested) - msleep(1); + tpm_msleep(1); if (!priv->irq_tested) disable_interrupts(chip); priv->irq_tested = true; diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c index 6a20dc8..9a7d7f0 100644 --- a/drivers/clocksource/numachip.c +++ b/drivers/clocksource/numachip.c @@ -43,7 +43,7 @@ static int numachip2_set_next_event(unsigned long delta, struct clock_event_devi return 0; } -static struct clock_event_device numachip2_clockevent = { +static const struct clock_event_device numachip2_clockevent __initconst = { .name = "numachip2", .rating = 400, .set_next_event = numachip2_set_next_event, diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c index 2ff64d9..62d2469 100644 --- a/drivers/clocksource/timer-integrator-ap.c +++ b/drivers/clocksource/timer-integrator-ap.c @@ -36,8 +36,8 @@ static u64 notrace integrator_read_sched_clock(void) return -readl(sched_clk_base + TIMER_VALUE); } -static int integrator_clocksource_init(unsigned long inrate, - void __iomem *base) +static int __init integrator_clocksource_init(unsigned long inrate, + void __iomem *base) { u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC; unsigned long rate = inrate; diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 430edad..a753c50 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -118,6 +118,10 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "sigma,tango4", }, + { .compatible = "ti,am33xx", }, + { .compatible = "ti,am43", }, + { .compatible = "ti,dra7", }, + { } }; diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 08629ee..00e73d2 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -361,12 +361,12 @@ static const struct fpga_manager_ops altera_cvp_ops = { .write_complete = altera_cvp_write_complete, }; -static ssize_t show_chkcfg(struct device_driver *dev, char *buf) +static ssize_t chkcfg_show(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, +static ssize_t chkcfg_store(struct device_driver *drv, const char *buf, size_t count) { int ret; @@ -378,7 +378,7 @@ static ssize_t store_chkcfg(struct device_driver *drv, const char *buf, return count; } -static DRIVER_ATTR(chkcfg, 0600, show_chkcfg, store_chkcfg); +static DRIVER_ATTR_RW(chkcfg); static int altera_cvp_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index d228f5a..dbbe986 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -636,7 +636,194 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev) NUM_BANKS(ADDR_SURF_2_BANK); for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); - } else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) { + } else if (adev->asic_type == CHIP_OLAND) { + tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[1] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[2] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[3] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[4] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[5] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[6] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[7] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[8] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[9] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[10] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[11] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[12] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[13] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[14] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[15] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[16] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[17] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[22] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[23] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[24] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[25] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) | + NUM_BANKS(ADDR_SURF_8_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1); + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) + WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); + } else if (adev->asic_type == CHIP_HAINAN) { tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | ARRAY_MODE(ARRAY_2D_TILED_THIN1) | PIPE_CONFIG(ADDR_SURF_P2) | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e4a8c2e..660b3fb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -892,6 +892,8 @@ static int kfd_ioctl_get_tile_config(struct file *filep, int err = 0; dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; dev->kfd2kgd->get_tile_config(dev->kgd, &config); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 5979158..944abfa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -292,7 +292,10 @@ static int create_signal_event(struct file *devkfd, struct kfd_event *ev) { if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) { - pr_warn("Signal event wasn't created because limit was reached\n"); + if (!p->signal_event_limit_reached) { + pr_warn("Signal event wasn't created because limit was reached\n"); + p->signal_event_limit_reached = true; + } return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 0649dd4..ed71ad4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -184,7 +184,7 @@ static void uninitialize(struct kernel_queue *kq) if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ) kq->mqd->destroy_mqd(kq->mqd, kq->queue->mqd, - false, + KFD_PREEMPT_TYPE_WAVEFRONT_RESET, QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, kq->queue->pipe, kq->queue->queue); @@ -210,6 +210,11 @@ static int acquire_packet_buffer(struct kernel_queue *kq, uint32_t wptr, rptr; unsigned int *queue_address; + /* When rptr == wptr, the buffer is empty. + * When rptr == wptr + 1, the buffer is full. + * It is always rptr that advances to the position of wptr, rather than + * the opposite. So we can only use up to queue_size_dwords - 1 dwords. + */ rptr = *kq->rptr_kernel; wptr = *kq->wptr_kernel; queue_address = (unsigned int *)kq->pq_kernel_addr; @@ -219,11 +224,10 @@ static int acquire_packet_buffer(struct kernel_queue *kq, pr_debug("wptr: %d\n", wptr); pr_debug("queue_address 0x%p\n", queue_address); - available_size = (rptr - 1 - wptr + queue_size_dwords) % + available_size = (rptr + queue_size_dwords - 1 - wptr) % queue_size_dwords; - if (packet_size_in_dwords >= queue_size_dwords || - packet_size_in_dwords >= available_size) { + if (packet_size_in_dwords > available_size) { /* * make sure calling functions know * acquire_packet_buffer() failed @@ -233,6 +237,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq, } if (wptr + packet_size_in_dwords >= queue_size_dwords) { + /* make sure after rolling back to position 0, there is + * still enough space. + */ + if (packet_size_in_dwords >= rptr) { + *buffer_ptr = NULL; + return -ENOMEM; + } + /* fill nops, roll back and start at position 0 */ while (wptr > 0) { queue_address[wptr] = kq->nop_packet; wptr = (wptr + 1) % queue_size_dwords; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index b397ec7..b87e96c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -521,6 +521,7 @@ struct kfd_process { struct list_head signal_event_pages; u32 next_nonsignal_event_id; size_t signal_event_count; + bool signal_event_limit_reached; }; /** diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 5a63459..5788116 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -551,12 +551,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { void etnaviv_gem_free_object(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + struct etnaviv_drm_private *priv = obj->dev->dev_private; struct etnaviv_vram_mapping *mapping, *tmp; /* object should not be active */ WARN_ON(is_active(etnaviv_obj)); + mutex_lock(&priv->gem_lock); list_del(&etnaviv_obj->gem_node); + mutex_unlock(&priv->gem_lock); list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list, obj_node) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 026ef4e..46dfe07 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -445,8 +445,10 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, cmdbuf->user_size = ALIGN(args->stream_size, 8); ret = etnaviv_gpu_submit(gpu, submit, cmdbuf); - if (ret == 0) - cmdbuf = NULL; + if (ret) + goto out; + + cmdbuf = NULL; if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) { /* diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 14c5613..afbf50d 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -509,23 +509,25 @@ static void qxl_primary_atomic_update(struct drm_plane *plane, .y2 = qfb->base.height }; - if (!old_state->fb) { - qxl_io_log(qdev, - "create primary fb: %dx%d,%d,%d\n", - bo->surf.width, bo->surf.height, - bo->surf.stride, bo->surf.format); + if (old_state->fb) { + qfb_old = to_qxl_framebuffer(old_state->fb); + bo_old = gem_to_qxl_bo(qfb_old->obj); + } else { + bo_old = NULL; + } - qxl_io_create_primary(qdev, 0, bo); - bo->is_primary = true; + if (bo == bo_old) return; - } else { - qfb_old = to_qxl_framebuffer(old_state->fb); - bo_old = gem_to_qxl_bo(qfb_old->obj); + if (bo_old && bo_old->is_primary) { + qxl_io_destroy_primary(qdev); bo_old->is_primary = false; } - bo->is_primary = true; + if (!bo->is_primary) { + qxl_io_create_primary(qdev, 0, bo); + bo->is_primary = true; + } qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1); } @@ -534,13 +536,15 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane, { struct qxl_device *qdev = plane->dev->dev_private; - if (old_state->fb) - { struct qxl_framebuffer *qfb = + if (old_state->fb) { + struct qxl_framebuffer *qfb = to_qxl_framebuffer(old_state->fb); struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj); - qxl_io_destroy_primary(qdev); - bo->is_primary = false; + if (bo->is_primary) { + qxl_io_destroy_primary(qdev); + bo->is_primary = false; + } } } @@ -698,14 +702,15 @@ static void qxl_plane_cleanup_fb(struct drm_plane *plane, struct drm_gem_object *obj; struct qxl_bo *user_bo; - if (!plane->state->fb) { - /* we never executed prepare_fb, so there's nothing to + if (!old_state->fb) { + /* + * we never executed prepare_fb, so there's nothing to * unpin. */ return; } - obj = to_qxl_framebuffer(plane->state->fb)->obj; + obj = to_qxl_framebuffer(old_state->fb)->obj; user_bo = gem_to_qxl_bo(obj); qxl_bo_unpin(user_bo); } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 997131d..ffc10ca 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1663,7 +1663,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, radeon_agp_suspend(rdev); pci_save_state(dev->pdev); - if (freeze && rdev->family >= CHIP_CEDAR) { + if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) { rdev->asic->asic_reset(rdev, true); pci_restore_state(dev->pdev); } else if (suspend) { diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 06f0530..882d85d 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -26,7 +26,7 @@ config DRM_SUN4I_HDMI_CEC bool "Allwinner A10 HDMI CEC Support" depends on DRM_SUN4I_HDMI select CEC_CORE - depends on CEC_PIN + select CEC_PIN help Choose this option if you have an Allwinner SoC with an HDMI controller and want to use CEC. diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index 1457750..a1f8cba 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -15,7 +15,7 @@ #include <drm/drm_connector.h> #include <drm/drm_encoder.h> -#include <media/cec.h> +#include <media/cec-pin.h> #define SUN4I_HDMI_CTRL_REG 0x004 #define SUN4I_HDMI_CTRL_ENABLE BIT(31) diff --git a/drivers/gpu/drm/tegra/trace.h b/drivers/gpu/drm/tegra/trace.h index e9b7cdad..5a1ab40 100644 --- a/drivers/gpu/drm/tegra/trace.h +++ b/drivers/gpu/drm/tegra/trace.h @@ -63,6 +63,6 @@ DEFINE_EVENT(register_access, sor_readl, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 060df71..bcbb031 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -936,14 +936,10 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) void vmbus_hvsock_device_unregister(struct vmbus_channel *channel) { - mutex_lock(&vmbus_connection.channel_mutex); - BUG_ON(!is_hvsock_channel(channel)); channel->rescind = true; vmbus_device_unregister(channel->device_obj); - - mutex_unlock(&vmbus_connection.channel_mutex); } EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister); diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index daa75bd..2364281 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -170,6 +170,10 @@ static void fcopy_send_data(struct work_struct *dummy) out_src = smsg_out; break; + case WRITE_TO_FILE: + out_src = fcopy_transaction.fcopy_msg; + out_len = sizeof(struct hv_do_fcopy); + break; default: out_src = fcopy_transaction.fcopy_msg; out_len = fcopy_transaction.recv_len; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index bc9cebc..c2a2ce8 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -144,6 +144,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)0, }, { + /* Lewisburg PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa1a6), + .driver_data = (kernel_ulong_t)0, + }, + { /* Gemini Lake */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -158,6 +163,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Cedar Fork PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x18e1), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index 9414900..f129869 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -1119,7 +1119,7 @@ void stm_source_unregister_device(struct stm_source_data *data) stm_source_link_drop(src); - device_destroy(&stm_source_class, src->dev.devt); + device_unregister(&src->dev); } EXPORT_SYMBOL_GPL(stm_source_unregister_device); diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c index e6706a0..47c3d7f 100644 --- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -257,7 +257,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, unsigned int vref_mv) { struct ad7793_state *st = iio_priv(indio_dev); - int i, ret = -1; + int i, ret; unsigned long long scale_uv; u32 id; @@ -266,7 +266,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, return ret; /* reset the serial interface */ - ret = spi_write(st->sd.spi, (u8 *)&ret, sizeof(ret)); + ret = ad_sd_reset(&st->sd, 32); if (ret < 0) goto out; usleep_range(500, 2000); /* Wait for at least 500us */ diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index d10bd0c..22c4c17 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -177,6 +177,34 @@ out: } EXPORT_SYMBOL_GPL(ad_sd_read_reg); +/** + * ad_sd_reset() - Reset the serial interface + * + * @sigma_delta: The sigma delta device + * @reset_length: Number of SCLKs with DIN = 1 + * + * Returns 0 on success, an error code otherwise. + **/ +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length) +{ + uint8_t *buf; + unsigned int size; + int ret; + + size = DIV_ROUND_UP(reset_length, 8); + buf = kcalloc(size, sizeof(*buf), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + memset(buf, 0xff, size); + ret = spi_write(sigma_delta->spi, buf, size); + kfree(buf); + + return ret; +} +EXPORT_SYMBOL_GPL(ad_sd_reset); + static int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, unsigned int mode, unsigned int channel) { diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c index 634717a..071dd23 100644 --- a/drivers/iio/adc/mcp320x.c +++ b/drivers/iio/adc/mcp320x.c @@ -17,6 +17,8 @@ * MCP3204 * MCP3208 * ------------ + * 13 bit converter + * MCP3301 * * Datasheet can be found here: * http://ww1.microchip.com/downloads/en/DeviceDoc/21293C.pdf mcp3001 @@ -96,7 +98,7 @@ static int mcp320x_channel_to_tx_data(int device_index, } static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel, - bool differential, int device_index) + bool differential, int device_index, int *val) { int ret; @@ -117,19 +119,25 @@ static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel, switch (device_index) { case mcp3001: - return (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3); + *val = (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3); + return 0; case mcp3002: case mcp3004: case mcp3008: - return (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6); + *val = (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6); + return 0; case mcp3201: - return (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1); + *val = (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1); + return 0; case mcp3202: case mcp3204: case mcp3208: - return (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4); + *val = (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4); + return 0; case mcp3301: - return sign_extend32((adc->rx_buf[0] & 0x1f) << 8 | adc->rx_buf[1], 12); + *val = sign_extend32((adc->rx_buf[0] & 0x1f) << 8 + | adc->rx_buf[1], 12); + return 0; default: return -EINVAL; } @@ -150,12 +158,10 @@ static int mcp320x_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: ret = mcp320x_adc_conversion(adc, channel->address, - channel->differential, device_index); - + channel->differential, device_index, val); if (ret < 0) goto out; - *val = ret; ret = IIO_VAL_INT; break; @@ -312,6 +318,7 @@ static int mcp320x_probe(struct spi_device *spi) indio_dev->name = spi_get_device_id(spi)->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &mcp320x_info; + spi_set_drvdata(spi, indio_dev); chip_info = &mcp320x_chip_infos[spi_get_device_id(spi)->driver_data]; indio_dev->channels = chip_info->channels; diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index e3c15f8..4df32cf 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -1666,7 +1666,7 @@ static int stm32_adc_chan_of_init(struct iio_dev *indio_dev) num_channels = of_property_count_u32_elems(node, "st,adc-channels"); if (num_channels < 0 || - num_channels >= adc_info->max_channels) { + num_channels > adc_info->max_channels) { dev_err(&indio_dev->dev, "Bad st,adc-channels?\n"); return num_channels < 0 ? num_channels : -EINVAL; } diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c index d121002..e0dc204 100644 --- a/drivers/iio/adc/ti-ads1015.c +++ b/drivers/iio/adc/ti-ads1015.c @@ -52,7 +52,7 @@ #define ADS1015_CFG_COMP_QUE_MASK GENMASK(1, 0) #define ADS1015_CFG_COMP_LAT_MASK BIT(2) -#define ADS1015_CFG_COMP_POL_MASK BIT(2) +#define ADS1015_CFG_COMP_POL_MASK BIT(3) #define ADS1015_CFG_COMP_MODE_MASK BIT(4) #define ADS1015_CFG_DR_MASK GENMASK(7, 5) #define ADS1015_CFG_MOD_MASK BIT(8) @@ -1017,10 +1017,12 @@ static int ads1015_probe(struct i2c_client *client, switch (irq_trig) { case IRQF_TRIGGER_LOW: - cfg_comp |= ADS1015_CFG_COMP_POL_LOW; + cfg_comp |= ADS1015_CFG_COMP_POL_LOW << + ADS1015_CFG_COMP_POL_SHIFT; break; case IRQF_TRIGGER_HIGH: - cfg_comp |= ADS1015_CFG_COMP_POL_HIGH; + cfg_comp |= ADS1015_CFG_COMP_POL_HIGH << + ADS1015_CFG_COMP_POL_SHIFT; break; default: return -EINVAL; diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c index 1edd99f..e3cfb91 100644 --- a/drivers/iio/adc/twl4030-madc.c +++ b/drivers/iio/adc/twl4030-madc.c @@ -887,21 +887,27 @@ static int twl4030_madc_probe(struct platform_device *pdev) /* Enable 3v1 bias regulator for MADC[3:6] */ madc->usb3v1 = devm_regulator_get(madc->dev, "vusb3v1"); - if (IS_ERR(madc->usb3v1)) - return -ENODEV; + if (IS_ERR(madc->usb3v1)) { + ret = -ENODEV; + goto err_i2c; + } ret = regulator_enable(madc->usb3v1); - if (ret) + if (ret) { dev_err(madc->dev, "could not enable 3v1 bias regulator\n"); + goto err_i2c; + } ret = iio_device_register(iio_dev); if (ret) { dev_err(&pdev->dev, "could not register iio device\n"); - goto err_i2c; + goto err_usb3v1; } return 0; +err_usb3v1: + regulator_disable(madc->usb3v1); err_i2c: twl4030_madc_set_current_generator(madc, 0, 0); err_current_generator: diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index d99bb14..02e833b 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -463,8 +463,17 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable) u8 drdy_mask; struct st_sensor_data *sdata = iio_priv(indio_dev); - if (!sdata->sensor_settings->drdy_irq.addr) + if (!sdata->sensor_settings->drdy_irq.addr) { + /* + * there are some devices (e.g. LIS3MDL) where drdy line is + * routed to a given pin and it is not possible to select a + * different one. Take into account irq status register + * to understand if irq trigger can be properly supported + */ + if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) + sdata->hw_irq_trigger = enable; return 0; + } /* Enable/Disable the interrupt generator 1. */ if (sdata->sensor_settings->drdy_irq.ig1.en_addr > 0) { diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 17ec4ce..a47428b 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -310,8 +310,10 @@ static ssize_t iio_debugfs_read_reg(struct file *file, char __user *userbuf, ret = indio_dev->info->debugfs_reg_access(indio_dev, indio_dev->cached_reg_addr, 0, &val); - if (ret) + if (ret) { dev_err(indio_dev->dev.parent, "%s: read failed\n", __func__); + return ret; + } len = snprintf(buf, sizeof(buf), "0x%X\n", val); diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index e68368b..08aafba 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -315,6 +315,10 @@ static const struct st_sensor_settings st_magn_sensors_settings[] = { }, }, }, + .drdy_irq = { + /* drdy line is routed drdy pin */ + .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, + }, .multi_read_bit = true, .bootime = 2, }, diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 0d2ea3e..8f26428 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -573,7 +573,7 @@ static int bmp280_chip_config(struct bmp280_data *data) u8 osrs = BMP280_OSRS_TEMP_X(data->oversampling_temp + 1) | BMP280_OSRS_PRESS_X(data->oversampling_press + 1); - ret = regmap_update_bits(data->regmap, BMP280_REG_CTRL_MEAS, + ret = regmap_write_bits(data->regmap, BMP280_REG_CTRL_MEAS, BMP280_OSRS_TEMP_MASK | BMP280_OSRS_PRESS_MASK | BMP280_MODE_MASK, diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index 9b90534..eb212f8c 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -174,6 +174,7 @@ static void stm32_timer_stop(struct stm32_timer_trigger *priv) clk_disable(priv->clk); /* Stop timer */ + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0); regmap_write(priv->regmap, TIM_PSC, 0); regmap_write(priv->regmap, TIM_ARR, 0); @@ -715,8 +716,9 @@ static ssize_t stm32_count_set_preset(struct iio_dev *indio_dev, if (ret) return ret; + /* TIMx_ARR register shouldn't be buffered (ARPE=0) */ + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_write(priv->regmap, TIM_ARR, preset); - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, TIM_CR1_ARPE); return len; } diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index 70ad19c..88bdafb 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -432,8 +432,10 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) atomic_set(&qp->qp_sec->error_list_count, 0); init_completion(&qp->qp_sec->error_complete); ret = security_ib_alloc_security(&qp->qp_sec->security); - if (ret) + if (ret) { kfree(qp->qp_sec); + qp->qp_sec = NULL; + } return ret; } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 4ab30d8..52a2cf2 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3869,15 +3869,15 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, resp.raw_packet_caps = attr.raw_packet_caps; resp.response_length += sizeof(resp.raw_packet_caps); - if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps)) + if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps)) goto end; - resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size; - resp.xrq_caps.max_num_tags = attr.xrq_caps.max_num_tags; - resp.xrq_caps.max_ops = attr.xrq_caps.max_ops; - resp.xrq_caps.max_sge = attr.xrq_caps.max_sge; - resp.xrq_caps.flags = attr.xrq_caps.flags; - resp.response_length += sizeof(resp.xrq_caps); + resp.tm_caps.max_rndv_hdr_size = attr.tm_caps.max_rndv_hdr_size; + resp.tm_caps.max_num_tags = attr.tm_caps.max_num_tags; + resp.tm_caps.max_ops = attr.tm_caps.max_ops; + resp.tm_caps.max_sge = attr.tm_caps.max_sge; + resp.tm_caps.flags = attr.tm_caps.flags; + resp.response_length += sizeof(resp.tm_caps); end: err = ib_copy_to_udata(ucore, &resp, resp.response_length); return err; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index ee9e27d..de57d6c 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1646,7 +1646,7 @@ static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid) */ if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) { if (attr.qp_state >= IB_QPS_INIT) { - if (qp->device->get_link_layer(qp->device, attr.port_num) != + if (rdma_port_get_link_layer(qp->device, attr.port_num) != IB_LINK_LAYER_INFINIBAND) return true; goto lid_check; @@ -1655,7 +1655,7 @@ static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid) /* Can't get a quick answer, iterate over all ports */ for (port = 0; port < qp->device->phys_port_cnt; port++) - if (qp->device->get_link_layer(qp->device, port) != + if (rdma_port_get_link_layer(qp->device, port) != IB_LINK_LAYER_INFINIBAND) num_eth_ports++; diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index b3ad37f..ecbac91 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -93,11 +93,13 @@ struct bnxt_re_dev { struct ib_device ibdev; struct list_head list; unsigned long flags; -#define BNXT_RE_FLAG_NETDEV_REGISTERED 0 -#define BNXT_RE_FLAG_IBDEV_REGISTERED 1 -#define BNXT_RE_FLAG_GOT_MSIX 2 -#define BNXT_RE_FLAG_RCFW_CHANNEL_EN 8 -#define BNXT_RE_FLAG_QOS_WORK_REG 16 +#define BNXT_RE_FLAG_NETDEV_REGISTERED 0 +#define BNXT_RE_FLAG_IBDEV_REGISTERED 1 +#define BNXT_RE_FLAG_GOT_MSIX 2 +#define BNXT_RE_FLAG_HAVE_L2_REF 3 +#define BNXT_RE_FLAG_RCFW_CHANNEL_EN 4 +#define BNXT_RE_FLAG_QOS_WORK_REG 5 +#define BNXT_RE_FLAG_TASK_IN_PROG 6 struct net_device *netdev; unsigned int version, major, minor; struct bnxt_en_dev *en_dev; @@ -108,6 +110,8 @@ struct bnxt_re_dev { struct delayed_work worker; u8 cur_prio_map; + u8 active_speed; + u8 active_width; /* FP Notification Queue (CQ & SRQ) */ struct tasklet_struct nq_task; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 01eee15..0d89621 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -259,14 +259,9 @@ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num, port_attr->sm_sl = 0; port_attr->subnet_timeout = 0; port_attr->init_type_reply = 0; - /* call the underlying netdev's ethtool hooks to query speed settings - * for which we acquire rtnl_lock _only_ if it's registered with - * IB stack to avoid race in the NETDEV_UNREG path - */ - if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags)) - if (ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed, - &port_attr->active_width)) - return -EINVAL; + port_attr->active_speed = rdev->active_speed; + port_attr->active_width = rdev->active_width; + return 0; } @@ -319,6 +314,7 @@ int bnxt_re_del_gid(struct ib_device *ibdev, u8 port_num, struct bnxt_re_gid_ctx *ctx, **ctx_tbl; struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl; + struct bnxt_qplib_gid *gid_to_del; /* Delete the entry from the hardware */ ctx = *context; @@ -328,11 +324,25 @@ int bnxt_re_del_gid(struct ib_device *ibdev, u8 port_num, if (sgid_tbl && sgid_tbl->active) { if (ctx->idx >= sgid_tbl->max) return -EINVAL; + gid_to_del = &sgid_tbl->tbl[ctx->idx]; + /* DEL_GID is called in WQ context(netdevice_event_work_handler) + * or via the ib_unregister_device path. In the former case QP1 + * may not be destroyed yet, in which case just return as FW + * needs that entry to be present and will fail it's deletion. + * We could get invoked again after QP1 is destroyed OR get an + * ADD_GID call with a different GID value for the same index + * where we issue MODIFY_GID cmd to update the GID entry -- TBD + */ + if (ctx->idx == 0 && + rdma_link_local_addr((struct in6_addr *)gid_to_del) && + ctx->refcnt == 1 && rdev->qp1_sqp) { + dev_dbg(rdev_to_dev(rdev), + "Trying to delete GID0 while QP1 is alive\n"); + return -EFAULT; + } ctx->refcnt--; if (!ctx->refcnt) { - rc = bnxt_qplib_del_sgid(sgid_tbl, - &sgid_tbl->tbl[ctx->idx], - true); + rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to remove GID: %#x", rc); @@ -816,6 +826,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) kfree(rdev->sqp_ah); kfree(rdev->qp1_sqp); + rdev->qp1_sqp = NULL; + rdev->sqp_ah = NULL; } if (!IS_ERR_OR_NULL(qp->rumem)) @@ -1436,11 +1448,14 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu); + qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu); } else if (qp_attr->qp_state == IB_QPS_RTR) { qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; qp->qplib_qp.path_mtu = __from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu)); + qp->qplib_qp.mtu = + ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu)); } if (qp_attr_mask & IB_QP_TIMEOUT) { @@ -1551,43 +1566,46 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, { struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp); struct bnxt_re_dev *rdev = qp->rdev; - struct bnxt_qplib_qp qplib_qp; + struct bnxt_qplib_qp *qplib_qp; int rc; - memset(&qplib_qp, 0, sizeof(struct bnxt_qplib_qp)); - qplib_qp.id = qp->qplib_qp.id; - qplib_qp.ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index; + qplib_qp = kzalloc(sizeof(*qplib_qp), GFP_KERNEL); + if (!qplib_qp) + return -ENOMEM; + + qplib_qp->id = qp->qplib_qp.id; + qplib_qp->ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index; - rc = bnxt_qplib_query_qp(&rdev->qplib_res, &qplib_qp); + rc = bnxt_qplib_query_qp(&rdev->qplib_res, qplib_qp); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to query HW QP"); - return rc; + goto out; } - qp_attr->qp_state = __to_ib_qp_state(qplib_qp.state); - qp_attr->en_sqd_async_notify = qplib_qp.en_sqd_async_notify ? 1 : 0; - qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp.access); - qp_attr->pkey_index = qplib_qp.pkey_index; - qp_attr->qkey = qplib_qp.qkey; + qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state); + qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0; + qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access); + qp_attr->pkey_index = qplib_qp->pkey_index; + qp_attr->qkey = qplib_qp->qkey; qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; - rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp.ah.flow_label, - qplib_qp.ah.host_sgid_index, - qplib_qp.ah.hop_limit, - qplib_qp.ah.traffic_class); - rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp.ah.dgid.data); - rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp.ah.sl); - ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp.ah.dmac); - qp_attr->path_mtu = __to_ib_mtu(qplib_qp.path_mtu); - qp_attr->timeout = qplib_qp.timeout; - qp_attr->retry_cnt = qplib_qp.retry_cnt; - qp_attr->rnr_retry = qplib_qp.rnr_retry; - qp_attr->min_rnr_timer = qplib_qp.min_rnr_timer; - qp_attr->rq_psn = qplib_qp.rq.psn; - qp_attr->max_rd_atomic = qplib_qp.max_rd_atomic; - qp_attr->sq_psn = qplib_qp.sq.psn; - qp_attr->max_dest_rd_atomic = qplib_qp.max_dest_rd_atomic; - qp_init_attr->sq_sig_type = qplib_qp.sig_type ? IB_SIGNAL_ALL_WR : - IB_SIGNAL_REQ_WR; - qp_attr->dest_qp_num = qplib_qp.dest_qpn; + rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp->ah.flow_label, + qplib_qp->ah.host_sgid_index, + qplib_qp->ah.hop_limit, + qplib_qp->ah.traffic_class); + rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp->ah.dgid.data); + rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp->ah.sl); + ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp->ah.dmac); + qp_attr->path_mtu = __to_ib_mtu(qplib_qp->path_mtu); + qp_attr->timeout = qplib_qp->timeout; + qp_attr->retry_cnt = qplib_qp->retry_cnt; + qp_attr->rnr_retry = qplib_qp->rnr_retry; + qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer; + qp_attr->rq_psn = qplib_qp->rq.psn; + qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic; + qp_attr->sq_psn = qplib_qp->sq.psn; + qp_attr->max_dest_rd_atomic = qplib_qp->max_dest_rd_atomic; + qp_init_attr->sq_sig_type = qplib_qp->sig_type ? IB_SIGNAL_ALL_WR : + IB_SIGNAL_REQ_WR; + qp_attr->dest_qp_num = qplib_qp->dest_qpn; qp_attr->cap.max_send_wr = qp->qplib_qp.sq.max_wqe; qp_attr->cap.max_send_sge = qp->qplib_qp.sq.max_sge; @@ -1596,7 +1614,9 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, qp_attr->cap.max_inline_data = qp->qplib_qp.max_inline_data; qp_init_attr->cap = qp_attr->cap; - return 0; +out: + kfree(qplib_qp); + return rc; } /* Routine for sending QP1 packets for RoCE V1 an V2 @@ -1908,6 +1928,7 @@ static int bnxt_re_build_atomic_wqe(struct ib_send_wr *wr, switch (wr->opcode) { case IB_WR_ATOMIC_CMP_AND_SWP: wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP; + wqe->atomic.cmp_data = atomic_wr(wr)->compare_add; wqe->atomic.swap_data = atomic_wr(wr)->swap; break; case IB_WR_ATOMIC_FETCH_AND_ADD: @@ -3062,7 +3083,7 @@ int bnxt_re_dereg_mr(struct ib_mr *ib_mr) return rc; } - if (mr->npages && mr->pages) { + if (mr->pages) { rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res, &mr->qplib_frpl); kfree(mr->pages); diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 82d1cbc..e7450ea 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1161,6 +1161,8 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) } } set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags); + ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, + &rdev->active_width); bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE); bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE); @@ -1255,10 +1257,14 @@ static void bnxt_re_task(struct work_struct *work) else if (netif_carrier_ok(rdev->netdev)) bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE); + ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, + &rdev->active_width); break; default: break; } + smp_mb__before_atomic(); + clear_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags); kfree(re_work); } @@ -1317,6 +1323,11 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, break; case NETDEV_UNREGISTER: + /* netdev notifier will call NETDEV_UNREGISTER again later since + * we are still holding the reference to the netdev + */ + if (test_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags)) + goto exit; bnxt_re_ib_unreg(rdev, false); bnxt_re_remove_one(rdev); bnxt_re_dev_unreg(rdev); @@ -1335,6 +1346,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, re_work->vlan_dev = (real_dev == netdev ? NULL : netdev); INIT_WORK(&re_work->work, bnxt_re_task); + set_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags); queue_work(bnxt_re_wq, &re_work->work); } } @@ -1375,6 +1387,22 @@ err_netdev: static void __exit bnxt_re_mod_exit(void) { + struct bnxt_re_dev *rdev; + LIST_HEAD(to_be_deleted); + + mutex_lock(&bnxt_re_dev_lock); + /* Free all adapter allocated resources */ + if (!list_empty(&bnxt_re_dev_list)) + list_splice_init(&bnxt_re_dev_list, &to_be_deleted); + mutex_unlock(&bnxt_re_dev_lock); + + list_for_each_entry(rdev, &to_be_deleted, list) { + dev_info(rdev_to_dev(rdev), "Unregistering Device"); + bnxt_re_dev_stop(rdev); + bnxt_re_ib_unreg(rdev, true); + bnxt_re_remove_one(rdev); + bnxt_re_dev_unreg(rdev); + } unregister_netdevice_notifier(&bnxt_re_netdev_notifier); if (bnxt_re_wq) destroy_workqueue(bnxt_re_wq); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 391bb70..2bdb156 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -107,6 +107,9 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, return -EINVAL; } + if (test_bit(FIRMWARE_TIMED_OUT, &rcfw->flags)) + return -ETIMEDOUT; + /* Cmdq are in 16-byte units, each request can consume 1 or more * cmdqe */ @@ -226,6 +229,7 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, /* timed out */ dev_err(&rcfw->pdev->dev, "QPLIB: cmdq[%#x]=%#x timedout (%d)msec", cookie, opcode, RCFW_CMD_WAIT_TIME_MS); + set_bit(FIRMWARE_TIMED_OUT, &rcfw->flags); return rc; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 0ed312f..85b16da 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -162,8 +162,9 @@ struct bnxt_qplib_rcfw { unsigned long *cmdq_bitmap; u32 bmap_size; unsigned long flags; -#define FIRMWARE_INITIALIZED_FLAG 1 +#define FIRMWARE_INITIALIZED_FLAG BIT(0) #define FIRMWARE_FIRST_FLAG BIT(31) +#define FIRMWARE_TIMED_OUT BIT(3) wait_queue_head_t waitq; int (*aeq_handler)(struct bnxt_qplib_rcfw *, struct creq_func_event *); diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index ceaa2fa..daf7a56 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -2333,9 +2333,14 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb) unsigned int stid = GET_TID(rpl); struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid); + if (!ep) { + pr_debug("%s stid %d lookup failure!\n", __func__, stid); + goto out; + } pr_debug("%s ep %p\n", __func__, ep); c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status)); c4iw_put_ep(&ep->com); +out: return 0; } @@ -2594,9 +2599,9 @@ fail: c4iw_put_ep(&child_ep->com); reject: reject_cr(dev, hwtid, skb); +out: if (parent_ep) c4iw_put_ep(&parent_ep->com); -out: return 0; } @@ -3457,7 +3462,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog) cm_id->provider_data = ep; goto out; } - + remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid); cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, ep->com.local_addr.ss_family); fail2: diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index b2ed4b9..0be4278 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1066,6 +1066,8 @@ static int read_idle_sma(struct hfi1_devdata *dd, u64 *data); static int thermal_init(struct hfi1_devdata *dd); static void update_statusp(struct hfi1_pportdata *ppd, u32 state); +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs); static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, int msecs); static void log_state_transition(struct hfi1_pportdata *ppd, u32 state); @@ -8238,6 +8240,7 @@ static irqreturn_t general_interrupt(int irq, void *data) u64 regs[CCE_NUM_INT_CSRS]; u32 bit; int i; + irqreturn_t handled = IRQ_NONE; this_cpu_inc(*dd->int_counter); @@ -8258,9 +8261,10 @@ static irqreturn_t general_interrupt(int irq, void *data) for_each_set_bit(bit, (unsigned long *)®s[0], CCE_NUM_INT_CSRS * 64) { is_interrupt(dd, bit); + handled = IRQ_HANDLED; } - return IRQ_HANDLED; + return handled; } static irqreturn_t sdma_interrupt(int irq, void *data) @@ -9413,7 +9417,7 @@ static void set_qsfp_int_n(struct hfi1_pportdata *ppd, u8 enable) write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask); } -void reset_qsfp(struct hfi1_pportdata *ppd) +int reset_qsfp(struct hfi1_pportdata *ppd) { struct hfi1_devdata *dd = ppd->dd; u64 mask, qsfp_mask; @@ -9443,6 +9447,13 @@ void reset_qsfp(struct hfi1_pportdata *ppd) * for alarms and warnings */ set_qsfp_int_n(ppd, 1); + + /* + * After the reset, AOC transmitters are enabled by default. They need + * to be turned off to complete the QSFP setup before they can be + * enabled again. + */ + return set_qsfp_tx(ppd, 0); } static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd, @@ -10305,6 +10316,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) { struct hfi1_devdata *dd = ppd->dd; u32 previous_state; + int offline_state_ret; int ret; update_lcb_cache(dd); @@ -10326,28 +10338,11 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) ppd->offline_disabled_reason = HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT); - /* - * Wait for offline transition. It can take a while for - * the link to go down. - */ - ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000); - if (ret < 0) - return ret; - - /* - * Now in charge of LCB - must be after the physical state is - * offline.quiet and before host_link_state is changed. - */ - set_host_lcb_access(dd); - write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ - - /* make sure the logical state is also down */ - ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); - if (ret) - force_logical_link_state_down(ppd); - - ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + offline_state_ret = wait_phys_link_offline_substates(ppd, 10000); + if (offline_state_ret < 0) + return offline_state_ret; + /* Disabling AOC transmitters */ if (ppd->port_type == PORT_TYPE_QSFP && ppd->qsfp_info.limiting_active && qsfp_mod_present(ppd)) { @@ -10365,6 +10360,30 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) } /* + * Wait for the offline.Quiet transition if it hasn't happened yet. It + * can take a while for the link to go down. + */ + if (offline_state_ret != PLS_OFFLINE_QUIET) { + ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000); + if (ret < 0) + return ret; + } + + /* + * Now in charge of LCB - must be after the physical state is + * offline.quiet and before host_link_state is changed. + */ + set_host_lcb_access(dd); + write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ + + /* make sure the logical state is also down */ + ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); + if (ret) + force_logical_link_state_down(ppd); + + ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + + /* * The LNI has a mandatory wait time after the physical state * moves to Offline.Quiet. The wait time may be different * depending on how the link went down. The 8051 firmware @@ -10396,6 +10415,9 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) & (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) { /* went down while attempting link up */ check_lni_states(ppd); + + /* The QSFP doesn't need to be reset on LNI failure */ + ppd->qsfp_info.reset_needed = 0; } /* the active link width (downgrade) is 0 on link down */ @@ -12804,6 +12826,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state, return 0; } +/* + * wait_phys_link_offline_quiet_substates - wait for any offline substate + * @ppd: port device + * @msecs: the number of milliseconds to wait + * + * Wait up to msecs milliseconds for any offline physical link + * state change to occur. + * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT. + */ +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs) +{ + u32 read_state; + unsigned long timeout; + + timeout = jiffies + msecs_to_jiffies(msecs); + while (1) { + read_state = read_physical_state(ppd->dd); + if ((read_state & 0xF0) == PLS_OFFLINE) + break; + if (time_after(jiffies, timeout)) { + dd_dev_err(ppd->dd, + "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n", + read_state, msecs); + return -ETIMEDOUT; + } + usleep_range(1950, 2050); /* sleep 2ms-ish */ + } + + log_state_transition(ppd, read_state); + return read_state; +} + #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \ (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK) diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index b8345a6..50b8645 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -204,6 +204,7 @@ #define PLS_OFFLINE_READY_TO_QUIET_LT 0x92 #define PLS_OFFLINE_REPORT_FAILURE 0x93 #define PLS_OFFLINE_READY_TO_QUIET_BCC 0x94 +#define PLS_OFFLINE_QUIET_DURATION 0x95 #define PLS_POLLING 0x20 #define PLS_POLLING_QUIET 0x20 #define PLS_POLLING_ACTIVE 0x21 @@ -722,7 +723,7 @@ void handle_link_downgrade(struct work_struct *work); void handle_link_bounce(struct work_struct *work); void handle_start_link(struct work_struct *work); void handle_sma_message(struct work_struct *work); -void reset_qsfp(struct hfi1_pportdata *ppd); +int reset_qsfp(struct hfi1_pportdata *ppd); void qsfp_event(struct work_struct *work); void start_freeze_handling(struct hfi1_pportdata *ppd, int flags); int send_idle_sma(struct hfi1_devdata *dd, u64 message); diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c index d46b171..1613af1 100644 --- a/drivers/infiniband/hw/hfi1/eprom.c +++ b/drivers/infiniband/hw/hfi1/eprom.c @@ -204,7 +204,10 @@ done_asic: return ret; } -/* magic character sequence that trails an image */ +/* magic character sequence that begins an image */ +#define IMAGE_START_MAGIC "APO=" + +/* magic character sequence that might trail an image */ #define IMAGE_TRAIL_MAGIC "egamiAPO" /* EPROM file types */ @@ -250,6 +253,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, { void *buffer; void *p; + u32 length; int ret; buffer = kmalloc(P1_SIZE, GFP_KERNEL); @@ -262,15 +266,21 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, return ret; } - /* scan for image magic that may trail the actual data */ - p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); - if (!p) { + /* config partition is valid only if it starts with IMAGE_START_MAGIC */ + if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) { kfree(buffer); return -ENOENT; } + /* scan for image magic that may trail the actual data */ + p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); + if (p) + length = p - buffer; + else + length = P1_SIZE; + *data = buffer; - *size = p - buffer; + *size = length; return 0; } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 2bc8926..d9a1e98 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -930,15 +930,8 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) switch (ret) { case 0: ret = setup_base_ctxt(fd, uctxt); - if (uctxt->subctxt_cnt) { - /* - * Base context is done (successfully or not), notify - * anybody using a sub-context that is waiting for - * this completion. - */ - clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); - wake_up(&uctxt->wait); - } + if (ret) + deallocate_ctxt(uctxt); break; case 1: ret = complete_subctxt(fd); @@ -1305,25 +1298,25 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, /* Now allocate the RcvHdr queue and eager buffers. */ ret = hfi1_create_rcvhdrq(dd, uctxt); if (ret) - return ret; + goto done; ret = hfi1_setup_eagerbufs(uctxt); if (ret) - goto setup_failed; + goto done; /* If sub-contexts are enabled, do the appropriate setup */ if (uctxt->subctxt_cnt) ret = setup_subctxt(uctxt); if (ret) - goto setup_failed; + goto done; ret = hfi1_alloc_ctxt_rcv_groups(uctxt); if (ret) - goto setup_failed; + goto done; ret = init_user_ctxt(fd, uctxt); if (ret) - goto setup_failed; + goto done; user_init(uctxt); @@ -1331,12 +1324,22 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, fd->uctxt = uctxt; hfi1_rcd_get(uctxt); - return 0; +done: + if (uctxt->subctxt_cnt) { + /* + * On error, set the failed bit so sub-contexts will clean up + * correctly. + */ + if (ret) + set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); -setup_failed: - /* Set the failed bit so sub-context init can do the right thing */ - set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); - deallocate_ctxt(uctxt); + /* + * Base context is done (successfully or not), notify anybody + * using a sub-context that is waiting for this completion. + */ + clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); + wake_up(&uctxt->wait); + } return ret; } diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 82447b7..09e50fd 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -68,7 +68,7 @@ /* * Code to adjust PCIe capabilities. */ -static int tune_pcie_caps(struct hfi1_devdata *); +static void tune_pcie_caps(struct hfi1_devdata *); /* * Do all the common PCIe setup and initialization. @@ -351,7 +351,7 @@ int pcie_speeds(struct hfi1_devdata *dd) */ int request_msix(struct hfi1_devdata *dd, u32 msireq) { - int nvec, ret; + int nvec; nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq, PCI_IRQ_MSIX | PCI_IRQ_LEGACY); @@ -360,12 +360,7 @@ int request_msix(struct hfi1_devdata *dd, u32 msireq) return nvec; } - ret = tune_pcie_caps(dd); - if (ret) { - dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret); - pci_free_irq_vectors(dd->pcidev); - return ret; - } + tune_pcie_caps(dd); /* check for legacy IRQ */ if (nvec == 1 && !dd->pcidev->msix_enabled) @@ -502,7 +497,7 @@ uint aspm_mode = ASPM_MODE_DISABLED; module_param_named(aspm, aspm_mode, uint, S_IRUGO); MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic"); -static int tune_pcie_caps(struct hfi1_devdata *dd) +static void tune_pcie_caps(struct hfi1_devdata *dd) { struct pci_dev *parent; u16 rc_mpss, rc_mps, ep_mpss, ep_mps; @@ -513,22 +508,14 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * Turn on extended tags in DevCtl in case the BIOS has turned it off * to improve WFR SDMA bandwidth */ - ret = pcie_capability_read_word(dd->pcidev, - PCI_EXP_DEVCTL, &ectl); - if (ret) { - dd_dev_err(dd, "Unable to read from PCI config\n"); - return ret; - } - - if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl); + if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { dd_dev_info(dd, "Enabling PCIe extended tags\n"); ectl |= PCI_EXP_DEVCTL_EXT_TAG; ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl); - if (ret) { - dd_dev_err(dd, "Unable to write to PCI config\n"); - return ret; - } + if (ret) + dd_dev_info(dd, "Unable to write to PCI config\n"); } /* Find out supported and configured values for parent (root) */ parent = dd->pcidev->bus->self; @@ -536,15 +523,22 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * The driver cannot perform the tuning if it does not have * access to the upstream component. */ - if (!parent) - return -EINVAL; + if (!parent) { + dd_dev_info(dd, "Parent not found\n"); + return; + } if (!pci_is_root_bus(parent->bus)) { dd_dev_info(dd, "Parent not root\n"); - return -EINVAL; + return; + } + if (!pci_is_pcie(parent)) { + dd_dev_info(dd, "Parent is not PCI Express capable\n"); + return; + } + if (!pci_is_pcie(dd->pcidev)) { + dd_dev_info(dd, "PCI device is not PCI Express capable\n"); + return; } - - if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev)) - return -EINVAL; rc_mpss = parent->pcie_mpss; rc_mps = ffs(pcie_get_mps(parent)) - 8; /* Find out supported and configured values for endpoint (us) */ @@ -590,8 +584,6 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) ep_mrrs = max_mrrs; pcie_set_readrq(dd->pcidev, ep_mrrs); } - - return 0; } /* End of PCIe capability tuning */ diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c index a8af96d..d486355 100644 --- a/drivers/infiniband/hw/hfi1/platform.c +++ b/drivers/infiniband/hw/hfi1/platform.c @@ -790,7 +790,9 @@ static int tune_active_qsfp(struct hfi1_pportdata *ppd, u32 *ptr_tx_preset, * reuse of stale settings established in our previous pass through. */ if (ppd->qsfp_info.reset_needed) { - reset_qsfp(ppd); + ret = reset_qsfp(ppd); + if (ret) + return ret; refresh_qsfp_cache(ppd, &ppd->qsfp_info); } else { ppd->qsfp_info.reset_needed = 1; diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 9b15664..a65e4cbd 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -201,7 +201,6 @@ enum init_completion_state { CEQ_CREATED, ILQ_CREATED, IEQ_CREATED, - INET_NOTIFIER, IP_ADDR_REGISTERED, RDMA_DEV_REGISTERED }; diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 14f36ba..5230dd3 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -1504,23 +1504,40 @@ static void i40iw_add_hte_node(struct i40iw_cm_core *cm_core, } /** - * listen_port_in_use - determine if port is in use - * @port: Listen port number + * i40iw_port_in_use - determine if port is in use + * @port: port number + * @active_side: flag for listener side vs active side */ -static bool i40iw_listen_port_in_use(struct i40iw_cm_core *cm_core, u16 port) +static bool i40iw_port_in_use(struct i40iw_cm_core *cm_core, u16 port, bool active_side) { struct i40iw_cm_listener *listen_node; + struct i40iw_cm_node *cm_node; unsigned long flags; bool ret = false; - spin_lock_irqsave(&cm_core->listen_list_lock, flags); - list_for_each_entry(listen_node, &cm_core->listen_nodes, list) { - if (listen_node->loc_port == port) { - ret = true; - break; + if (active_side) { + /* search connected node list */ + spin_lock_irqsave(&cm_core->ht_lock, flags); + list_for_each_entry(cm_node, &cm_core->connected_nodes, list) { + if (cm_node->loc_port == port) { + ret = true; + break; + } + } + if (!ret) + clear_bit(port, cm_core->active_side_ports); + spin_unlock_irqrestore(&cm_core->ht_lock, flags); + } else { + spin_lock_irqsave(&cm_core->listen_list_lock, flags); + list_for_each_entry(listen_node, &cm_core->listen_nodes, list) { + if (listen_node->loc_port == port) { + ret = true; + break; + } } + spin_unlock_irqrestore(&cm_core->listen_list_lock, flags); } - spin_unlock_irqrestore(&cm_core->listen_list_lock, flags); + return ret; } @@ -1868,7 +1885,7 @@ static int i40iw_dec_refcnt_listen(struct i40iw_cm_core *cm_core, spin_unlock_irqrestore(&cm_core->listen_list_lock, flags); if (listener->iwdev) { - if (apbvt_del && !i40iw_listen_port_in_use(cm_core, listener->loc_port)) + if (apbvt_del && !i40iw_port_in_use(cm_core, listener->loc_port, false)) i40iw_manage_apbvt(listener->iwdev, listener->loc_port, I40IW_MANAGE_APBVT_DEL); @@ -2247,21 +2264,21 @@ static void i40iw_rem_ref_cm_node(struct i40iw_cm_node *cm_node) if (cm_node->listener) { i40iw_dec_refcnt_listen(cm_core, cm_node->listener, 0, true); } else { - if (!i40iw_listen_port_in_use(cm_core, cm_node->loc_port) && - cm_node->apbvt_set) { + if (!i40iw_port_in_use(cm_core, cm_node->loc_port, true) && cm_node->apbvt_set) { i40iw_manage_apbvt(cm_node->iwdev, cm_node->loc_port, I40IW_MANAGE_APBVT_DEL); - i40iw_get_addr_info(cm_node, &nfo); - if (cm_node->qhash_set) { - i40iw_manage_qhash(cm_node->iwdev, - &nfo, - I40IW_QHASH_TYPE_TCP_ESTABLISHED, - I40IW_QHASH_MANAGE_TYPE_DELETE, - NULL, - false); - cm_node->qhash_set = 0; - } + cm_node->apbvt_set = 0; + } + i40iw_get_addr_info(cm_node, &nfo); + if (cm_node->qhash_set) { + i40iw_manage_qhash(cm_node->iwdev, + &nfo, + I40IW_QHASH_TYPE_TCP_ESTABLISHED, + I40IW_QHASH_MANAGE_TYPE_DELETE, + NULL, + false); + cm_node->qhash_set = 0; } } @@ -3255,7 +3272,8 @@ static void i40iw_init_tcp_ctx(struct i40iw_cm_node *cm_node, tcp_info->snd_mss = cpu_to_le32(((u32)cm_node->tcp_cntxt.mss)); if (cm_node->vlan_id < VLAN_TAG_PRESENT) { tcp_info->insert_vlan_tag = true; - tcp_info->vlan_tag = cpu_to_le16(cm_node->vlan_id); + tcp_info->vlan_tag = cpu_to_le16(((u16)cm_node->user_pri << I40IW_VLAN_PRIO_SHIFT) | + cm_node->vlan_id); } if (cm_node->ipv4) { tcp_info->src_port = cpu_to_le16(cm_node->loc_port); @@ -3737,10 +3755,8 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) struct sockaddr_in *raddr; struct sockaddr_in6 *laddr6; struct sockaddr_in6 *raddr6; - bool qhash_set = false; - int apbvt_set = 0; - int err = 0; - enum i40iw_status_code status; + int ret = 0; + unsigned long flags; ibqp = i40iw_get_qp(cm_id->device, conn_param->qpn); if (!ibqp) @@ -3789,32 +3805,6 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) cm_info.user_pri = rt_tos2priority(cm_id->tos); i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB, "%s TOS:[%d] UP:[%d]\n", __func__, cm_id->tos, cm_info.user_pri); - if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) || - (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32, - raddr6->sin6_addr.in6_u.u6_addr32, - sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) { - status = i40iw_manage_qhash(iwdev, - &cm_info, - I40IW_QHASH_TYPE_TCP_ESTABLISHED, - I40IW_QHASH_MANAGE_TYPE_ADD, - NULL, - true); - if (status) - return -EINVAL; - qhash_set = true; - } - status = i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD); - if (status) { - i40iw_manage_qhash(iwdev, - &cm_info, - I40IW_QHASH_TYPE_TCP_ESTABLISHED, - I40IW_QHASH_MANAGE_TYPE_DELETE, - NULL, - false); - return -EINVAL; - } - - apbvt_set = 1; cm_id->add_ref(cm_id); cm_node = i40iw_create_cm_node(&iwdev->cm_core, iwdev, conn_param->private_data_len, @@ -3822,17 +3812,40 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) &cm_info); if (IS_ERR(cm_node)) { - err = PTR_ERR(cm_node); - goto err_out; + ret = PTR_ERR(cm_node); + cm_id->rem_ref(cm_id); + return ret; + } + + if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) || + (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32, + raddr6->sin6_addr.in6_u.u6_addr32, + sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) { + if (i40iw_manage_qhash(iwdev, &cm_info, I40IW_QHASH_TYPE_TCP_ESTABLISHED, + I40IW_QHASH_MANAGE_TYPE_ADD, NULL, true)) { + ret = -EINVAL; + goto err; + } + cm_node->qhash_set = true; } + spin_lock_irqsave(&iwdev->cm_core.ht_lock, flags); + if (!test_and_set_bit(cm_info.loc_port, iwdev->cm_core.active_side_ports)) { + spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags); + if (i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD)) { + ret = -EINVAL; + goto err; + } + } else { + spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags); + } + + cm_node->apbvt_set = true; i40iw_record_ird_ord(cm_node, (u16)conn_param->ird, (u16)conn_param->ord); if (cm_node->send_rdma0_op == SEND_RDMA_READ_ZERO && !cm_node->ord_size) cm_node->ord_size = 1; - cm_node->apbvt_set = apbvt_set; - cm_node->qhash_set = qhash_set; iwqp->cm_node = cm_node; cm_node->iwqp = iwqp; iwqp->cm_id = cm_id; @@ -3840,11 +3853,9 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (cm_node->state != I40IW_CM_STATE_OFFLOADED) { cm_node->state = I40IW_CM_STATE_SYN_SENT; - err = i40iw_send_syn(cm_node, 0); - if (err) { - i40iw_rem_ref_cm_node(cm_node); - goto err_out; - } + ret = i40iw_send_syn(cm_node, 0); + if (ret) + goto err; } i40iw_debug(cm_node->dev, @@ -3853,9 +3864,10 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) cm_node->rem_port, cm_node, cm_node->cm_id); + return 0; -err_out: +err: if (cm_info.ipv4) i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_CM, @@ -3867,22 +3879,10 @@ err_out: "Api - connect() FAILED: dest addr=%pI6", cm_info.rem_addr); - if (qhash_set) - i40iw_manage_qhash(iwdev, - &cm_info, - I40IW_QHASH_TYPE_TCP_ESTABLISHED, - I40IW_QHASH_MANAGE_TYPE_DELETE, - NULL, - false); - - if (apbvt_set && !i40iw_listen_port_in_use(&iwdev->cm_core, - cm_info.loc_port)) - i40iw_manage_apbvt(iwdev, - cm_info.loc_port, - I40IW_MANAGE_APBVT_DEL); + i40iw_rem_ref_cm_node(cm_node); cm_id->rem_ref(cm_id); iwdev->cm_core.stats_connect_errs++; - return err; + return ret; } /** diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.h b/drivers/infiniband/hw/i40iw/i40iw_cm.h index 2e52e38..45abef7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.h +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.h @@ -71,6 +71,9 @@ #define I40IW_HW_IRD_SETTING_32 32 #define I40IW_HW_IRD_SETTING_64 64 +#define MAX_PORTS 65536 +#define I40IW_VLAN_PRIO_SHIFT 13 + enum ietf_mpa_flags { IETF_MPA_FLAGS_MARKERS = 0x80, /* receive Markers */ IETF_MPA_FLAGS_CRC = 0x40, /* receive Markers */ @@ -411,6 +414,8 @@ struct i40iw_cm_core { spinlock_t ht_lock; /* manage hash table */ spinlock_t listen_list_lock; /* listen list */ + unsigned long active_side_ports[BITS_TO_LONGS(MAX_PORTS)]; + u64 stats_nodes_created; u64 stats_nodes_destroyed; u64 stats_listen_created; diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index cc742c3..27590ae 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -99,8 +99,6 @@ static struct notifier_block i40iw_net_notifier = { .notifier_call = i40iw_net_event }; -static atomic_t i40iw_notifiers_registered; - /** * i40iw_find_i40e_handler - find a handler given a client info * @ldev: pointer to a client info @@ -1376,11 +1374,20 @@ error: */ static void i40iw_register_notifiers(void) { - if (atomic_inc_return(&i40iw_notifiers_registered) == 1) { - register_inetaddr_notifier(&i40iw_inetaddr_notifier); - register_inet6addr_notifier(&i40iw_inetaddr6_notifier); - register_netevent_notifier(&i40iw_net_notifier); - } + register_inetaddr_notifier(&i40iw_inetaddr_notifier); + register_inet6addr_notifier(&i40iw_inetaddr6_notifier); + register_netevent_notifier(&i40iw_net_notifier); +} + +/** + * i40iw_unregister_notifiers - unregister tcp ip notifiers + */ + +static void i40iw_unregister_notifiers(void) +{ + unregister_netevent_notifier(&i40iw_net_notifier); + unregister_inetaddr_notifier(&i40iw_inetaddr_notifier); + unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier); } /** @@ -1400,6 +1407,11 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev, u32 i; u32 size; + if (!ldev->msix_count) { + i40iw_pr_err("No MSI-X vectors\n"); + return I40IW_ERR_CONFIG; + } + iwdev->msix_count = ldev->msix_count; size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count; @@ -1462,12 +1474,6 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev) if (!iwdev->reset) i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx); /* fallthrough */ - case INET_NOTIFIER: - if (!atomic_dec_return(&i40iw_notifiers_registered)) { - unregister_netevent_notifier(&i40iw_net_notifier); - unregister_inetaddr_notifier(&i40iw_inetaddr_notifier); - unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier); - } /* fallthrough */ case PBLE_CHUNK_MEM: i40iw_destroy_pble_pool(dev, iwdev->pble_rsrc); @@ -1550,7 +1556,7 @@ static enum i40iw_status_code i40iw_setup_init_state(struct i40iw_handler *hdl, status = i40iw_save_msix_info(iwdev, ldev); if (status) - goto exit; + return status; iwdev->hw.dev_context = (void *)ldev->pcidev; iwdev->hw.hw_addr = ldev->hw_addr; status = i40iw_allocate_dma_mem(&iwdev->hw, @@ -1667,8 +1673,6 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client) break; iwdev->init_state = PBLE_CHUNK_MEM; iwdev->virtchnl_wq = alloc_ordered_workqueue("iwvch", WQ_MEM_RECLAIM); - i40iw_register_notifiers(); - iwdev->init_state = INET_NOTIFIER; status = i40iw_add_mac_ip(iwdev); if (status) break; @@ -2018,6 +2022,8 @@ static int __init i40iw_init_module(void) i40iw_client.type = I40E_CLIENT_IWARP; spin_lock_init(&i40iw_handler_lock); ret = i40e_register_client(&i40iw_client); + i40iw_register_notifiers(); + return ret; } @@ -2029,6 +2035,7 @@ static int __init i40iw_init_module(void) */ static void __exit i40iw_exit_module(void) { + i40iw_unregister_notifiers(); i40e_unregister_client(&i40iw_client); } diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 62f1f45..e52dbbb 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -160,7 +160,7 @@ int i40iw_inetaddr_event(struct notifier_block *notifier, return NOTIFY_DONE; iwdev = &hdl->device; - if (iwdev->init_state < INET_NOTIFIER) + if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing) return NOTIFY_DONE; netdev = iwdev->ldev->netdev; @@ -217,7 +217,7 @@ int i40iw_inet6addr_event(struct notifier_block *notifier, return NOTIFY_DONE; iwdev = &hdl->device; - if (iwdev->init_state < INET_NOTIFIER) + if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing) return NOTIFY_DONE; netdev = iwdev->ldev->netdev; @@ -266,7 +266,7 @@ int i40iw_net_event(struct notifier_block *notifier, unsigned long event, void * if (!iwhdl) return NOTIFY_DONE; iwdev = &iwhdl->device; - if (iwdev->init_state < INET_NOTIFIER) + if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing) return NOTIFY_DONE; p = (__be32 *)neigh->primary_key; i40iw_copy_ip_ntohl(local_ipaddr, p); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 1aa4110..28b3d02 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -1027,7 +1027,19 @@ int i40iw_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, iwqp->hw_tcp_state = I40IW_TCP_STATE_CLOSED; iwqp->last_aeq = I40IW_AE_RESET_SENT; spin_unlock_irqrestore(&iwqp->lock, flags); + i40iw_cm_disconn(iwqp); } + } else { + spin_lock_irqsave(&iwqp->lock, flags); + if (iwqp->cm_id) { + if (atomic_inc_return(&iwqp->close_timer_started) == 1) { + iwqp->cm_id->add_ref(iwqp->cm_id); + i40iw_schedule_cm_timer(iwqp->cm_node, + (struct i40iw_puda_buf *)iwqp, + I40IW_TIMER_TYPE_CLOSE, 1, 0); + } + } + spin_unlock_irqrestore(&iwqp->lock, flags); } } return 0; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index ab3c562..d6fbad8 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -778,13 +778,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, } if (MLX5_CAP_GEN(mdev, tag_matching)) { - props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; - props->xrq_caps.max_num_tags = + props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; + props->tm_caps.max_num_tags = (1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1; - props->xrq_caps.flags = IB_TM_CAP_RC; - props->xrq_caps.max_ops = + props->tm_caps.flags = IB_TM_CAP_RC; + props->tm_caps.max_ops = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz); - props->xrq_caps.max_sge = MLX5_TM_MAX_SGE; + props->tm_caps.max_sge = MLX5_TM_MAX_SGE; } if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) { @@ -3837,11 +3837,13 @@ static int delay_drop_debugfs_init(struct mlx5_ib_dev *dev) if (!dbg) return -ENOMEM; + dev->delay_drop.dbg = dbg; + dbg->dir_debugfs = debugfs_create_dir("delay_drop", dev->mdev->priv.dbg_root); if (!dbg->dir_debugfs) - return -ENOMEM; + goto out_debugfs; dbg->events_cnt_debugfs = debugfs_create_atomic_t("num_timeout_events", 0400, @@ -3865,8 +3867,6 @@ static int delay_drop_debugfs_init(struct mlx5_ib_dev *dev) if (!dbg->timeout_debugfs) goto out_debugfs; - dev->delay_drop.dbg = dbg; - return 0; out_debugfs: diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c index 914f212..f3dbd75 100644 --- a/drivers/infiniband/hw/mlx5/mem.c +++ b/drivers/infiniband/hw/mlx5/mem.c @@ -50,13 +50,9 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, { unsigned long tmp; unsigned long m; - int i, k; - u64 base = 0; - int p = 0; - int skip; - int mask; - u64 len; - u64 pfn; + u64 base = ~0, p = 0; + u64 len, pfn; + int i = 0; struct scatterlist *sg; int entry; unsigned long page_shift = umem->page_shift; @@ -76,33 +72,24 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, m = find_first_bit(&tmp, BITS_PER_LONG); if (max_page_shift) m = min_t(unsigned long, max_page_shift - page_shift, m); - skip = 1 << m; - mask = skip - 1; - i = 0; + for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { len = sg_dma_len(sg) >> page_shift; pfn = sg_dma_address(sg) >> page_shift; - for (k = 0; k < len; k++) { - if (!(i & mask)) { - tmp = (unsigned long)pfn; - m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG)); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } else { - if (base + p != pfn) { - tmp = (unsigned long)p; - m = find_first_bit(&tmp, BITS_PER_LONG); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } - } - p++; - i++; + if (base + p != pfn) { + /* If either the offset or the new + * base are unaligned update m + */ + tmp = (unsigned long)(pfn | p); + if (!IS_ALIGNED(tmp, 1 << m)) + m = find_first_bit(&tmp, BITS_PER_LONG); + + base = pfn; + p = 0; } + + p += len; + i += len; } if (i) { diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 0e2789d..37bbc54 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -47,7 +47,8 @@ enum { #define MLX5_UMR_ALIGN 2048 -static int clean_mr(struct mlx5_ib_mr *mr); +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static int mr_cache_max_order(struct mlx5_ib_dev *dev); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); @@ -1270,8 +1271,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift, update_xlt_flags); + if (err) { - mlx5_ib_dereg_mr(&mr->ibmr); + dereg_mr(dev, mr); return ERR_PTR(err); } } @@ -1356,7 +1358,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, err = mr_umem_get(pd, addr, len, access_flags, &mr->umem, &npages, &page_shift, &ncont, &order); if (err < 0) { - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1410,7 +1412,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (err) { mlx5_ib_warn(dev, "Failed to rereg UMR\n"); ib_umem_release(mr->umem); - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1469,9 +1471,8 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr) } } -static int clean_mr(struct mlx5_ib_mr *mr) +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); int allocated_from_cache = mr->allocated_from_cache; int err; @@ -1507,10 +1508,8 @@ static int clean_mr(struct mlx5_ib_mr *mr) return 0; } -int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(ibmr->device); - struct mlx5_ib_mr *mr = to_mmr(ibmr); int npages = mr->npages; struct ib_umem *umem = mr->umem; @@ -1539,7 +1538,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) } #endif - clean_mr(mr); + clean_mr(dev, mr); if (umem) { ib_umem_release(umem); @@ -1549,6 +1548,14 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) return 0; } +int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +{ + struct mlx5_ib_dev *dev = to_mdev(ibmr->device); + struct mlx5_ib_mr *mr = to_mmr(ibmr); + + return dereg_mr(dev, mr); +} + struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg) diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index f0dc5f4..442b9bd 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3232,7 +3232,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->ibmr.iova); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX, - mr->ibmr.length); + lower_32_bits(mr->ibmr.length)); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0); set_wqe_32bit_value(wqe->wqe_words, @@ -3274,7 +3274,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->npages * 8); nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, " - "length: %d, rkey: %0x, pgl_paddr: %llx, " + "length: %lld, rkey: %0x, pgl_paddr: %llx, " "page_list_len: %u, wqe_misc: %x\n", (unsigned long long) mr->ibmr.iova, mr->ibmr.length, diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index dcb5942..65b166c 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -252,7 +252,10 @@ static int ocrdma_get_mbx_errno(u32 status) case OCRDMA_MBX_ADDI_STATUS_INSUFFICIENT_RESOURCES: err_num = -EAGAIN; break; + default: + err_num = -EFAULT; } + break; default: err_num = -EFAULT; } diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h index 663a0c3..984aa34 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h @@ -416,9 +416,34 @@ static inline enum ib_wc_status pvrdma_wc_status_to_ib( return (enum ib_wc_status)status; } -static inline int pvrdma_wc_opcode_to_ib(int opcode) -{ - return opcode; +static inline int pvrdma_wc_opcode_to_ib(unsigned int opcode) +{ + switch (opcode) { + case PVRDMA_WC_SEND: + return IB_WC_SEND; + case PVRDMA_WC_RDMA_WRITE: + return IB_WC_RDMA_WRITE; + case PVRDMA_WC_RDMA_READ: + return IB_WC_RDMA_READ; + case PVRDMA_WC_COMP_SWAP: + return IB_WC_COMP_SWAP; + case PVRDMA_WC_FETCH_ADD: + return IB_WC_FETCH_ADD; + case PVRDMA_WC_LOCAL_INV: + return IB_WC_LOCAL_INV; + case PVRDMA_WC_FAST_REG_MR: + return IB_WC_REG_MR; + case PVRDMA_WC_MASKED_COMP_SWAP: + return IB_WC_MASKED_COMP_SWAP; + case PVRDMA_WC_MASKED_FETCH_ADD: + return IB_WC_MASKED_FETCH_ADD; + case PVRDMA_WC_RECV: + return IB_WC_RECV; + case PVRDMA_WC_RECV_RDMA_WITH_IMM: + return IB_WC_RECV_RDMA_WITH_IMM; + default: + return IB_WC_SEND; + } } static inline int pvrdma_wc_flags_to_ib(int flags) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 14b62f7..7774654 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -823,12 +823,18 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) wc->status != IB_WC_WR_FLUSH_ERR) { struct ipoib_neigh *neigh; - if (wc->status != IB_WC_RNR_RETRY_EXC_ERR) - ipoib_warn(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n", - wc->status, wr_id, wc->vendor_err); + /* IB_WC[_RNR]_RETRY_EXC_ERR error is part of the life cycle, + * so don't make waves. + */ + if (wc->status == IB_WC_RNR_RETRY_EXC_ERR || + wc->status == IB_WC_RETRY_EXC_ERR) + ipoib_dbg(priv, + "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n", + __func__, wc->status, wr_id, wc->vendor_err); else - ipoib_dbg(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n", - wc->status, wr_id, wc->vendor_err); + ipoib_warn(priv, + "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n", + __func__, wc->status, wr_id, wc->vendor_err); spin_lock_irqsave(&priv->lock, flags); neigh = tx->neigh; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 2e07537..6cd6163 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1000,19 +1000,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv) */ priv->dev->broadcast[8] = priv->pkey >> 8; priv->dev->broadcast[9] = priv->pkey & 0xff; - - /* - * Update the broadcast address in the priv->broadcast object, - * in case it already exists, otherwise no one will do that. - */ - if (priv->broadcast) { - spin_lock_irq(&priv->lock); - memcpy(priv->broadcast->mcmember.mgid.raw, - priv->dev->broadcast + 4, - sizeof(union ib_gid)); - spin_unlock_irq(&priv->lock); - } - return 0; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index bac95b5..dcc77014 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2180,6 +2180,7 @@ static struct net_device *ipoib_add_port(const char *format, { struct ipoib_dev_priv *priv; struct ib_port_attr attr; + struct rdma_netdev *rn; int result = -ENOMEM; priv = ipoib_intf_alloc(hca, port, format); @@ -2279,7 +2280,8 @@ register_failed: ipoib_dev_cleanup(priv->dev); device_init_failed: - free_netdev(priv->dev); + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); alloc_mem_failed: @@ -2328,7 +2330,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) return; list_for_each_entry_safe(priv, tmp, dev_list, list) { - struct rdma_netdev *rn = netdev_priv(priv->dev); + struct rdma_netdev *parent_rn = netdev_priv(priv->dev); ib_unregister_event_handler(&priv->event_handler); flush_workqueue(ipoib_workqueue); @@ -2350,10 +2352,15 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) unregister_netdev(priv->dev); mutex_unlock(&priv->sysfs_mutex); - rn->free_rdma_netdev(priv->dev); + parent_rn->free_rdma_netdev(priv->dev); + + list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) { + struct rdma_netdev *child_rn; - list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) + child_rn = netdev_priv(cpriv->dev); + child_rn->free_rdma_netdev(cpriv->dev); kfree(cpriv); + } kfree(priv); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 9927cd6..55a9b71 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -141,14 +141,17 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); - if (!priv) { + if (!down_write_trylock(&ppriv->vlan_rwsem)) { rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - return -ENOMEM; + return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); + if (!priv) { + result = -ENOMEM; + goto out; + } /* * First ensure this isn't a duplicate. We check the parent device and @@ -175,8 +178,11 @@ out: rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - if (result) { - free_netdev(priv->dev); + if (result && priv) { + struct rdma_netdev *rn; + + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); } @@ -204,7 +210,12 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + if (!down_write_trylock(&ppriv->vlan_rwsem)) { + rtnl_unlock(); + mutex_unlock(&ppriv->sysfs_mutex); + return restart_syscall(); + } + list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) { if (priv->pkey == pkey && priv->child_type == IPOIB_LEGACY_CHILD) { @@ -224,7 +235,10 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) mutex_unlock(&ppriv->sysfs_mutex); if (dev) { - free_netdev(dev); + struct rdma_netdev *rn; + + rn = netdev_priv(dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); return 0; } diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 9c3e9ab..322209d 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -154,7 +154,7 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec) { int i; - iser_err("page vec npages %d data length %d\n", + iser_err("page vec npages %d data length %lld\n", page_vec->npages, page_vec->fake_mr.length); for (i = 0; i < page_vec->npages; i++) iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 382de42..6fe2d03 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -874,7 +874,7 @@ static bool copy_device_table(void) hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4); entry = (((u64) hi) << 32) + lo; if (last_entry && last_entry != entry) { - pr_err("IOMMU:%d should use the same dev table as others!/n", + pr_err("IOMMU:%d should use the same dev table as others!\n", iommu->index); return false; } @@ -882,7 +882,7 @@ static bool copy_device_table(void) old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12; if (old_devtb_size != dev_table_size) { - pr_err("The device table size of IOMMU:%d is not expected!/n", + pr_err("The device table size of IOMMU:%d is not expected!\n", iommu->index); return false; } @@ -890,7 +890,7 @@ static bool copy_device_table(void) old_devtb_phys = entry & PAGE_MASK; if (old_devtb_phys >= 0x100000000ULL) { - pr_err("The address of old device table is above 4G, not trustworthy!/n"); + pr_err("The address of old device table is above 4G, not trustworthy!\n"); return false; } old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB); @@ -901,7 +901,7 @@ static bool copy_device_table(void) old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag, get_order(dev_table_size)); if (old_dev_tbl_cpy == NULL) { - pr_err("Failed to allocate memory for copying old device table!/n"); + pr_err("Failed to allocate memory for copying old device table!\n"); return false; } diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index d665d0d..6961fc3 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -245,7 +245,7 @@ static void __arm_v7s_free_table(void *table, int lvl, static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries, struct io_pgtable_cfg *cfg) { - if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) + if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA) return; dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep), diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index bd515be..16d33ac 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, int ret; spin_lock_irqsave(&dom->pgtlock, flags); - ret = dom->iop->map(dom->iop, iova, paddr, size, prot); + ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32), + size, prot); spin_unlock_irqrestore(&dom->pgtlock, flags); return ret; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 519149e..b5df99c 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1042,7 +1042,7 @@ static int get_cpu_number(struct device_node *dn) { const __be32 *cell; u64 hwid; - int i; + int cpu; cell = of_get_property(dn, "reg", NULL); if (!cell) @@ -1056,9 +1056,9 @@ static int get_cpu_number(struct device_node *dn) if (hwid & ~MPIDR_HWID_BITMASK) return -1; - for (i = 0; i < num_possible_cpus(); i++) - if (cpu_logical_map(i) == hwid) - return i; + for_each_possible_cpu(cpu) + if (cpu_logical_map(cpu) == hwid) + return cpu; return -1; } diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index 2370e6d..cd0bcc3 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -173,7 +173,9 @@ int its_map_vlpi(int irq, struct its_vlpi_map *map) { struct its_cmd_info info = { .cmd_type = MAP_VLPI, - .map = map, + { + .map = map, + }, }; /* @@ -189,7 +191,9 @@ int its_get_vlpi(int irq, struct its_vlpi_map *map) { struct its_cmd_info info = { .cmd_type = GET_VLPI, - .map = map, + { + .map = map, + }, }; return irq_set_vcpu_affinity(irq, &info); @@ -205,7 +209,9 @@ int its_prop_update_vlpi(int irq, u8 config, bool inv) { struct its_cmd_info info = { .cmd_type = inv ? PROP_UPDATE_AND_INV_VLPI : PROP_UPDATE_VLPI, - .config = config, + { + .config = config, + }, }; return irq_set_vcpu_affinity(irq, &info); diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 6e52a88..c90976d 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -169,20 +169,19 @@ static void gic_mask_irq(struct irq_data *d) { unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); - write_gic_rmask(BIT(intr)); + write_gic_rmask(intr); gic_clear_pcpu_masks(intr); } static void gic_unmask_irq(struct irq_data *d) { - struct cpumask *affinity = irq_data_get_affinity_mask(d); unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); unsigned int cpu; - write_gic_smask(BIT(intr)); + write_gic_smask(intr); gic_clear_pcpu_masks(intr); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(d)); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); } @@ -420,13 +419,17 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw, unsigned int cpu) { int intr = GIC_HWIRQ_TO_SHARED(hw); + struct irq_data *data; unsigned long flags; + data = irq_get_irq_data(virq); + spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); gic_clear_pcpu_masks(intr); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); + irq_data_update_effective_affinity(data, cpumask_of(cpu)); spin_unlock_irqrestore(&gic_lock, flags); return 0; @@ -645,7 +648,7 @@ static int __init gic_of_init(struct device_node *node, /* Find the first available CPU vector. */ i = 0; - reserved = (C_SW0 | C_SW1) >> __fls(C_SW0); + reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0); while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors", i++, &cpu_vec)) reserved |= BIT(cpu_vec); @@ -684,11 +687,11 @@ static int __init gic_of_init(struct device_node *node, gicconfig = read_gic_config(); gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS; - gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS); + gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS); gic_shared_intrs = (gic_shared_intrs + 1) * 8; gic_vpes = gicconfig & GIC_CONFIG_PVPS; - gic_vpes >>= __fls(GIC_CONFIG_PVPS); + gic_vpes >>= __ffs(GIC_CONFIG_PVPS); gic_vpes = gic_vpes + 1; if (cpu_has_veic) { @@ -767,7 +770,7 @@ static int __init gic_of_init(struct device_node *node, for (i = 0; i < gic_shared_intrs; i++) { change_gic_pol(i, GIC_POL_ACTIVE_HIGH); change_gic_trig(i, GIC_TRIG_LEVEL); - write_gic_rmask(BIT(i)); + write_gic_rmask(i); } for (i = 0; i < gic_vpes; i++) { diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c index 6c44609..cd2b3c6 100644 --- a/drivers/isdn/i4l/isdn_ppp.c +++ b/drivers/isdn/i4l/isdn_ppp.c @@ -825,7 +825,6 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count) isdn_net_local *lp; struct ippp_struct *is; int proto; - unsigned char protobuf[4]; is = file->private_data; @@ -839,24 +838,28 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count) if (!lp) printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n"); else { - /* - * Don't reset huptimer for - * LCP packets. (Echo requests). - */ - if (copy_from_user(protobuf, buf, 4)) - return -EFAULT; - proto = PPP_PROTOCOL(protobuf); - if (proto != PPP_LCP) - lp->huptimer = 0; + if (lp->isdn_device < 0 || lp->isdn_channel < 0) { + unsigned char protobuf[4]; + /* + * Don't reset huptimer for + * LCP packets. (Echo requests). + */ + if (copy_from_user(protobuf, buf, 4)) + return -EFAULT; + + proto = PPP_PROTOCOL(protobuf); + if (proto != PPP_LCP) + lp->huptimer = 0; - if (lp->isdn_device < 0 || lp->isdn_channel < 0) return 0; + } if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) && lp->dialstate == 0 && (lp->flags & ISDN_NET_CONNECTED)) { unsigned short hl; struct sk_buff *skb; + unsigned char *cpy_buf; /* * we need to reserve enough space in front of * sk_buff. old call to dev_alloc_skb only reserved @@ -869,11 +872,21 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count) return count; } skb_reserve(skb, hl); - if (copy_from_user(skb_put(skb, count), buf, count)) + cpy_buf = skb_put(skb, count); + if (copy_from_user(cpy_buf, buf, count)) { kfree_skb(skb); return -EFAULT; } + + /* + * Don't reset huptimer for + * LCP packets. (Echo requests). + */ + proto = PPP_PROTOCOL(cpy_buf); + if (proto != PPP_LCP) + lp->huptimer = 0; + if (is->debug & 0x40) { printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len); isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot); diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index bbbbe08..9a257f9 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -112,6 +112,10 @@ #define AS_PEAK_mA_TO_REG(a) \ ((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250) +/* LED numbers for Devicetree */ +#define AS_LED_FLASH 0 +#define AS_LED_INDICATOR 1 + enum as_mode { AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT, AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT, @@ -491,10 +495,29 @@ static int as3645a_parse_node(struct as3645a *flash, struct device_node *node) { struct as3645a_config *cfg = &flash->cfg; + struct device_node *child; const char *name; int rval; - flash->flash_node = of_get_child_by_name(node, "flash"); + for_each_child_of_node(node, child) { + u32 id = 0; + + of_property_read_u32(child, "reg", &id); + + switch (id) { + case AS_LED_FLASH: + flash->flash_node = of_node_get(child); + break; + case AS_LED_INDICATOR: + flash->indicator_node = of_node_get(child); + break; + default: + dev_warn(&flash->client->dev, + "unknown LED %u encountered, ignoring\n", id); + break; + } + } + if (!flash->flash_node) { dev_err(&flash->client->dev, "can't find flash node\n"); return -ENODEV; @@ -534,11 +557,10 @@ static int as3645a_parse_node(struct as3645a *flash, of_property_read_u32(flash->flash_node, "voltage-reference", &cfg->voltage_reference); - of_property_read_u32(flash->flash_node, "peak-current-limit", + of_property_read_u32(flash->flash_node, "ams,input-max-microamp", &cfg->peak); cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak); - flash->indicator_node = of_get_child_by_name(node, "indicator"); if (!flash->indicator_node) { dev_warn(&flash->client->dev, "can't find indicator node\n"); @@ -721,6 +743,7 @@ static int as3645a_remove(struct i2c_client *client) as3645a_set_control(flash, AS_MODE_EXT_TORCH, false); v4l2_flash_release(flash->vf); + v4l2_flash_release(flash->vfind); led_classdev_flash_unregister(&flash->fled); led_classdev_unregister(&flash->iled_cdev); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285..1ac58c5 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio) if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); return DM_MAPIO_SUBMITTED; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 08fcaeb..0ff1bbf 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ +void md_handle_request(struct mddev *mddev, struct bio *bio) +{ +check_suspended: + rcu_read_lock(); + if (mddev->suspended) { + DEFINE_WAIT(__wait); + for (;;) { + prepare_to_wait(&mddev->sb_wait, &__wait, + TASK_UNINTERRUPTIBLE); + if (!mddev->suspended) + break; + rcu_read_unlock(); + schedule(); + rcu_read_lock(); + } + finish_wait(&mddev->sb_wait, &__wait); + } + atomic_inc(&mddev->active_io); + rcu_read_unlock(); + + if (!mddev->pers->make_request(mddev, bio)) { + atomic_dec(&mddev->active_io); + wake_up(&mddev->sb_wait); + goto check_suspended; + } + + if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) + wake_up(&mddev->sb_wait); +} +EXPORT_SYMBOL(md_handle_request); + static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); @@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) bio_endio(bio); return BLK_QC_T_NONE; } -check_suspended: - rcu_read_lock(); - if (mddev->suspended) { - DEFINE_WAIT(__wait); - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!mddev->suspended) - break; - rcu_read_unlock(); - schedule(); - rcu_read_lock(); - } - finish_wait(&mddev->sb_wait, &__wait); - } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); /* * save the sectors now since our bio can @@ -310,20 +324,14 @@ check_suspended: sectors = bio_sectors(bio); /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; - if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); - goto check_suspended; - } + + md_handle_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); - return BLK_QC_T_NONE; } @@ -439,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws) struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct bio *bio = mddev->flush_bio; + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); } - - mddev->flush_bio = NULL; - wake_up(&mddev->sb_wait); } void md_flush_request(struct mddev *mddev, struct bio *bio) diff --git a/drivers/md/md.h b/drivers/md/md.h index 561d22b..d8287d3 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); +extern void md_handle_request(struct mddev *mddev, struct bio *bio); extern void mddev_suspend(struct mddev *mddev); extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 0764094..928e24a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6575,14 +6575,17 @@ static ssize_t raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - unsigned long new; + unsigned int new; int err; struct r5worker_group *new_groups, *old_groups; int group_cnt, worker_cnt_per_group; if (len >= PAGE_SIZE) return -EINVAL; - if (kstrtoul(page, 10, &new)) + if (kstrtouint(page, 10, &new)) + return -EINVAL; + /* 8192 should be big enough */ + if (new > 8192) return -EINVAL; err = mddev_lock(mddev); diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index bbaddf1..d0ccc67 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -392,6 +392,7 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = { enum { INTEL_DSM_FNS = 0, + INTEL_DSM_V18_SWITCH = 3, INTEL_DSM_DRV_STRENGTH = 9, INTEL_DSM_D3_RETUNE = 10, }; @@ -557,6 +558,19 @@ static void intel_hs400_enhanced_strobe(struct mmc_host *mmc, sdhci_writel(host, val, INTEL_HS400_ES_REG); } +static void sdhci_intel_voltage_switch(struct sdhci_host *host) +{ + struct sdhci_pci_slot *slot = sdhci_priv(host); + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct device *dev = &slot->chip->pdev->dev; + u32 result = 0; + int err; + + err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result); + pr_debug("%s: %s DSM error %d result %u\n", + mmc_hostname(host->mmc), __func__, err, result); +} + static const struct sdhci_ops sdhci_intel_byt_ops = { .set_clock = sdhci_set_clock, .set_power = sdhci_intel_set_power, @@ -565,6 +579,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, + .voltage_switch = sdhci_intel_voltage_switch, }; static void byt_read_dsm(struct sdhci_pci_slot *slot) diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 12cf828..a7293e1 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -129,50 +129,6 @@ static int tmio_mmc_next_sg(struct tmio_mmc_host *host) #define CMDREQ_TIMEOUT 5000 -#ifdef CONFIG_MMC_DEBUG - -#define STATUS_TO_TEXT(a, status, i) \ - do { \ - if ((status) & TMIO_STAT_##a) { \ - if ((i)++) \ - printk(KERN_DEBUG " | "); \ - printk(KERN_DEBUG #a); \ - } \ - } while (0) - -static void pr_debug_status(u32 status) -{ - int i = 0; - - pr_debug("status: %08x = ", status); - STATUS_TO_TEXT(CARD_REMOVE, status, i); - STATUS_TO_TEXT(CARD_INSERT, status, i); - STATUS_TO_TEXT(SIGSTATE, status, i); - STATUS_TO_TEXT(WRPROTECT, status, i); - STATUS_TO_TEXT(CARD_REMOVE_A, status, i); - STATUS_TO_TEXT(CARD_INSERT_A, status, i); - STATUS_TO_TEXT(SIGSTATE_A, status, i); - STATUS_TO_TEXT(CMD_IDX_ERR, status, i); - STATUS_TO_TEXT(STOPBIT_ERR, status, i); - STATUS_TO_TEXT(ILL_FUNC, status, i); - STATUS_TO_TEXT(CMD_BUSY, status, i); - STATUS_TO_TEXT(CMDRESPEND, status, i); - STATUS_TO_TEXT(DATAEND, status, i); - STATUS_TO_TEXT(CRCFAIL, status, i); - STATUS_TO_TEXT(DATATIMEOUT, status, i); - STATUS_TO_TEXT(CMDTIMEOUT, status, i); - STATUS_TO_TEXT(RXOVERFLOW, status, i); - STATUS_TO_TEXT(TXUNDERRUN, status, i); - STATUS_TO_TEXT(RXRDY, status, i); - STATUS_TO_TEXT(TXRQ, status, i); - STATUS_TO_TEXT(ILL_ACCESS, status, i); - printk("\n"); -} - -#else -#define pr_debug_status(s) do { } while (0) -#endif - static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable) { struct tmio_mmc_host *host = mmc_priv(mmc); @@ -762,9 +718,6 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS); ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask; - pr_debug_status(status); - pr_debug_status(ireg); - /* Clear the status except the interrupt status */ sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 5736b0c..a308e70 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -581,6 +581,14 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, slave->mtd.erasesize = parent->erasesize; } + /* + * Slave erasesize might differ from the master one if the master + * exposes several regions with different erasesize. Adjust + * wr_alignment accordingly. + */ + if (!(slave->mtd.flags & MTD_NO_ERASE)) + wr_alignment = slave->mtd.erasesize; + tmp = slave->offset; remainder = do_div(tmp, wr_alignment); if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) { diff --git a/drivers/mtd/nand/atmel/pmecc.c b/drivers/mtd/nand/atmel/pmecc.c index 146af821..8268636 100644 --- a/drivers/mtd/nand/atmel/pmecc.c +++ b/drivers/mtd/nand/atmel/pmecc.c @@ -363,7 +363,7 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, size += (req->ecc.strength + 1) * sizeof(u16); /* Reserve space for mu, dmu and delta. */ size = ALIGN(size, sizeof(s32)); - size += (req->ecc.strength + 1) * sizeof(s32); + size += (req->ecc.strength + 1) * sizeof(s32) * 3; user = kzalloc(size, GFP_KERNEL); if (!user) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c3c53f6..83eec9a 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -432,6 +432,27 @@ static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv) netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n"); } +static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv, + u64 *tx_bytes, u64 *tx_packets) +{ + struct bcm_sysport_tx_ring *ring; + u64 bytes = 0, packets = 0; + unsigned int start; + unsigned int q; + + for (q = 0; q < priv->netdev->num_tx_queues; q++) { + ring = &priv->tx_rings[q]; + do { + start = u64_stats_fetch_begin_irq(&priv->syncp); + bytes = ring->bytes; + packets = ring->packets; + } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); + + *tx_bytes += bytes; + *tx_packets += packets; + } +} + static void bcm_sysport_get_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { @@ -439,11 +460,16 @@ static void bcm_sysport_get_stats(struct net_device *dev, struct bcm_sysport_stats64 *stats64 = &priv->stats64; struct u64_stats_sync *syncp = &priv->syncp; struct bcm_sysport_tx_ring *ring; + u64 tx_bytes = 0, tx_packets = 0; unsigned int start; int i, j; - if (netif_running(dev)) + if (netif_running(dev)) { bcm_sysport_update_mib_counters(priv); + bcm_sysport_update_tx_stats(priv, &tx_bytes, &tx_packets); + stats64->tx_bytes = tx_bytes; + stats64->tx_packets = tx_packets; + } for (i = 0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) { const struct bcm_sysport_stats *s; @@ -461,12 +487,13 @@ static void bcm_sysport_get_stats(struct net_device *dev, continue; p += s->stat_offset; - if (s->stat_sizeof == sizeof(u64)) + if (s->stat_sizeof == sizeof(u64) && + s->type == BCM_SYSPORT_STAT_NETDEV64) { do { start = u64_stats_fetch_begin_irq(syncp); data[i] = *(u64 *)p; } while (u64_stats_fetch_retry_irq(syncp, start)); - else + } else data[i] = *(u32 *)p; j++; } @@ -1716,27 +1743,12 @@ static void bcm_sysport_get_stats64(struct net_device *dev, { struct bcm_sysport_priv *priv = netdev_priv(dev); struct bcm_sysport_stats64 *stats64 = &priv->stats64; - struct bcm_sysport_tx_ring *ring; - u64 tx_packets = 0, tx_bytes = 0; unsigned int start; - unsigned int q; netdev_stats_to_stats64(stats, &dev->stats); - for (q = 0; q < dev->num_tx_queues; q++) { - ring = &priv->tx_rings[q]; - do { - start = u64_stats_fetch_begin_irq(&priv->syncp); - tx_bytes = ring->bytes; - tx_packets = ring->packets; - } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); - - stats->tx_bytes += tx_bytes; - stats->tx_packets += tx_packets; - } - - stats64->tx_bytes = stats->tx_bytes; - stats64->tx_packets = stats->tx_packets; + bcm_sysport_update_tx_stats(priv, &stats->tx_bytes, + &stats->tx_packets); do { start = u64_stats_fetch_begin_irq(&priv->syncp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index ccd699f..7dd3d13 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -750,6 +750,10 @@ int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid, { int rc = 0; + if (!is_classid_clsact_ingress(cls_flower->common.classid) || + cls_flower->common.chain_index) + return -EOPNOTSUPP; + switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: rc = bnxt_tc_add_flow(bp, src_fid, cls_flower); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 38c7b21..ede1876 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -374,8 +374,8 @@ struct bufdesc_ex { #define FEC_ENET_TS_AVAIL ((uint)0x00010000) #define FEC_ENET_TS_TIMER ((uint)0x00008000) -#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII | FEC_ENET_TS_TIMER) -#define FEC_NAPI_IMASK (FEC_ENET_MII | FEC_ENET_TS_TIMER) +#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII) +#define FEC_NAPI_IMASK FEC_ENET_MII #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF)) /* ENET interrupt coalescing macro define */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 56f56d6..3dc2d77 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1559,14 +1559,14 @@ fec_enet_collect_events(struct fec_enet_private *fep, uint int_events) if (int_events == 0) return false; - if (int_events & FEC_ENET_RXF) + if (int_events & FEC_ENET_RXF_0) fep->work_rx |= (1 << 2); if (int_events & FEC_ENET_RXF_1) fep->work_rx |= (1 << 0); if (int_events & FEC_ENET_RXF_2) fep->work_rx |= (1 << 1); - if (int_events & FEC_ENET_TXF) + if (int_events & FEC_ENET_TXF_0) fep->work_tx |= (1 << 2); if (int_events & FEC_ENET_TXF_1) fep->work_tx |= (1 << 0); @@ -1604,8 +1604,8 @@ fec_enet_interrupt(int irq, void *dev_id) } if (fep->ptp_clock) - fec_ptp_check_pps_event(fep); - + if (fec_ptp_check_pps_event(fep)) + ret = IRQ_HANDLED; return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 59efbd6..5bcb223 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -37,20 +37,15 @@ static bool hnae3_client_match(enum hnae3_client_type client_type, } static int hnae3_match_n_instantiate(struct hnae3_client *client, - struct hnae3_ae_dev *ae_dev, - bool is_reg, bool *matched) + struct hnae3_ae_dev *ae_dev, bool is_reg) { int ret; - *matched = false; - /* check if this client matches the type of ae_dev */ if (!(hnae3_client_match(client->type, ae_dev->dev_type) && hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) { return 0; } - /* there is a match of client and dev */ - *matched = true; /* now, (un-)instantiate client by calling lower layer */ if (is_reg) { @@ -69,7 +64,6 @@ int hnae3_register_client(struct hnae3_client *client) { struct hnae3_client *client_tmp; struct hnae3_ae_dev *ae_dev; - bool matched; int ret = 0; mutex_lock(&hnae3_common_lock); @@ -86,7 +80,7 @@ int hnae3_register_client(struct hnae3_client *client) /* if the client could not be initialized on current port, for * any error reasons, move on to next available port */ - ret = hnae3_match_n_instantiate(client, ae_dev, true, &matched); + ret = hnae3_match_n_instantiate(client, ae_dev, true); if (ret) dev_err(&ae_dev->pdev->dev, "match and instantiation failed for port\n"); @@ -102,12 +96,11 @@ EXPORT_SYMBOL(hnae3_register_client); void hnae3_unregister_client(struct hnae3_client *client) { struct hnae3_ae_dev *ae_dev; - bool matched; mutex_lock(&hnae3_common_lock); /* un-initialize the client on every matched port */ list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { - hnae3_match_n_instantiate(client, ae_dev, false, &matched); + hnae3_match_n_instantiate(client, ae_dev, false); } list_del(&client->node); @@ -124,7 +117,6 @@ int hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) const struct pci_device_id *id; struct hnae3_ae_dev *ae_dev; struct hnae3_client *client; - bool matched; int ret = 0; mutex_lock(&hnae3_common_lock); @@ -151,13 +143,10 @@ int hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) * initialize the figure out client instance */ list_for_each_entry(client, &hnae3_client_list, node) { - ret = hnae3_match_n_instantiate(client, ae_dev, true, - &matched); + ret = hnae3_match_n_instantiate(client, ae_dev, true); if (ret) dev_err(&ae_dev->pdev->dev, "match and instantiation failed\n"); - if (matched) - break; } } @@ -175,7 +164,6 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo) const struct pci_device_id *id; struct hnae3_ae_dev *ae_dev; struct hnae3_client *client; - bool matched; mutex_lock(&hnae3_common_lock); /* Check if there are matched ae_dev */ @@ -187,12 +175,8 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo) /* check the client list for the match with this ae_dev type and * un-initialize the figure out client instance */ - list_for_each_entry(client, &hnae3_client_list, node) { - hnae3_match_n_instantiate(client, ae_dev, false, - &matched); - if (matched) - break; - } + list_for_each_entry(client, &hnae3_client_list, node) + hnae3_match_n_instantiate(client, ae_dev, false); ae_algo->ops->uninit_ae_dev(ae_dev); hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); @@ -212,7 +196,6 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) const struct pci_device_id *id; struct hnae3_ae_algo *ae_algo; struct hnae3_client *client; - bool matched; int ret = 0; mutex_lock(&hnae3_common_lock); @@ -246,13 +229,10 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) * initialize the figure out client instance */ list_for_each_entry(client, &hnae3_client_list, node) { - ret = hnae3_match_n_instantiate(client, ae_dev, true, - &matched); + ret = hnae3_match_n_instantiate(client, ae_dev, true); if (ret) dev_err(&ae_dev->pdev->dev, "match and instantiation failed\n"); - if (matched) - break; } out_err: @@ -270,7 +250,6 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev) const struct pci_device_id *id; struct hnae3_ae_algo *ae_algo; struct hnae3_client *client; - bool matched; mutex_lock(&hnae3_common_lock); /* Check if there are matched ae_algo */ @@ -279,12 +258,8 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev) if (!id) continue; - list_for_each_entry(client, &hnae3_client_list, node) { - hnae3_match_n_instantiate(client, ae_dev, false, - &matched); - if (matched) - break; - } + list_for_each_entry(client, &hnae3_client_list, node) + hnae3_match_n_instantiate(client, ae_dev, false); ae_algo->ops->uninit_ae_dev(ae_dev); hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index b2f28ae..1a01cad 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -49,7 +49,17 @@ #define HNAE3_CLASS_NAME_SIZE 16 #define HNAE3_DEV_INITED_B 0x0 -#define HNAE_DEV_SUPPORT_ROCE_B 0x1 +#define HNAE3_DEV_SUPPORT_ROCE_B 0x1 +#define HNAE3_DEV_SUPPORT_DCB_B 0x2 + +#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\ + BIT(HNAE3_DEV_SUPPORT_ROCE_B)) + +#define hnae3_dev_roce_supported(hdev) \ + hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) + +#define hnae3_dev_dcb_supported(hdev) \ + hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) #define ring_ptr_move_fw(ring, p) \ ((ring)->p = ((ring)->p + 1) % (ring)->desc_num) @@ -366,12 +376,12 @@ struct hnae3_ae_algo { struct hnae3_tc_info { u16 tqp_offset; /* TQP offset from base TQP */ u16 tqp_count; /* Total TQPs */ - u8 up; /* user priority */ u8 tc; /* TC index */ bool enable; /* If this TC is enable or not */ }; #define HNAE3_MAX_TC 8 +#define HNAE3_MAX_USER_PRIO 8 struct hnae3_knic_private_info { struct net_device *netdev; /* Set by KNIC client when init instance */ u16 rss_size; /* Allocated RSS queues */ @@ -379,6 +389,7 @@ struct hnae3_knic_private_info { u16 num_desc; u8 num_tc; /* Total number of enabled TCs */ + u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */ struct hnae3_tc_info tc_info[HNAE3_MAX_TC]; /* Idx of array is HW TC */ u16 num_tqps; /* total number of TQPs in this handle */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 91ae013..758cf39 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -238,7 +238,7 @@ struct hclge_tqp_map { u8 rsv[18]; }; -#define HCLGE_VECTOR_ELEMENTS_PER_CMD 11 +#define HCLGE_VECTOR_ELEMENTS_PER_CMD 10 enum hclge_int_type { HCLGE_INT_TX, @@ -252,8 +252,12 @@ struct hclge_ctrl_vector_chain { #define HCLGE_INT_TYPE_S 0 #define HCLGE_INT_TYPE_M 0x3 #define HCLGE_TQP_ID_S 2 -#define HCLGE_TQP_ID_M (0x3fff << HCLGE_TQP_ID_S) +#define HCLGE_TQP_ID_M (0x7ff << HCLGE_TQP_ID_S) +#define HCLGE_INT_GL_IDX_S 13 +#define HCLGE_INT_GL_IDX_M (0x3 << HCLGE_INT_GL_IDX_S) __le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD]; + u8 vfid; + u8 rsv; }; #define HCLGE_TC_NUM 8 @@ -266,7 +270,8 @@ struct hclge_tx_buff_alloc { struct hclge_rx_priv_buff { __le16 buf_num[HCLGE_TC_NUM]; - u8 rsv[8]; + __le16 shared_buf; + u8 rsv[6]; }; struct hclge_query_version { @@ -684,6 +689,7 @@ struct hclge_reset_tqp_queue { #define HCLGE_DEFAULT_TX_BUF 0x4000 /* 16k bytes */ #define HCLGE_TOTAL_PKT_BUF 0x108000 /* 1.03125M bytes */ #define HCLGE_DEFAULT_DV 0xA000 /* 40k byte */ +#define HCLGE_DEFAULT_NON_DCB_DV 0x7800 /* 30K byte */ #define HCLGE_TYPE_CRQ 0 #define HCLGE_TYPE_CSQ 1 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bb45365..e0685e6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -46,17 +46,7 @@ static const struct pci_device_id ae_algo_pci_tbl[] = { {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, - /* Required last entry */ - {0, } -}; - -static const struct pci_device_id roce_pci_tbl[] = { - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, - /* Required last entry */ + /* required last entry */ {0, } }; @@ -894,7 +884,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) hdev->num_tqps = __le16_to_cpu(req->tqp_num); hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S; - if (hnae_get_bit(hdev->ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B)) { + if (hnae3_dev_roce_supported(hdev)) { hdev->num_roce_msix = hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number), HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); @@ -1063,9 +1053,9 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->base_tqp_pid = 0; hdev->rss_size_max = 1; hdev->rx_buf_len = cfg.rx_buf_len; - for (i = 0; i < ETH_ALEN; i++) - hdev->hw.mac.mac_addr[i] = cfg.mac_addr[i]; + ether_addr_copy(hdev->hw.mac.mac_addr, cfg.mac_addr); hdev->hw.mac.media_type = cfg.media_type; + hdev->hw.mac.phy_addr = cfg.phy_addr; hdev->num_desc = cfg.tqp_desc_num; hdev->tm_info.num_pg = 1; hdev->tm_info.num_tc = cfg.tc_num; @@ -1454,7 +1444,11 @@ static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all) tc_num = hclge_get_tc_num(hdev); pfc_enable_num = hclge_get_pfc_enalbe_num(hdev); - shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV; + if (hnae3_dev_dcb_supported(hdev)) + shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV; + else + shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_NON_DCB_DV; + shared_buf_tc = pfc_enable_num * hdev->mps + (tc_num - pfc_enable_num) * hdev->mps / 2 + hdev->mps; @@ -1495,6 +1489,16 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size) struct hclge_priv_buf *priv; int i; + /* When DCB is not supported, rx private + * buffer is not allocated. + */ + if (!hnae3_dev_dcb_supported(hdev)) { + if (!hclge_is_rx_buf_ok(hdev, rx_all)) + return -ENOMEM; + + return 0; + } + /* step 1, try to alloc private buffer for all enabled tc */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { priv = &hdev->priv_buf[i]; @@ -1510,6 +1514,11 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size) priv->wl.high = 2 * hdev->mps; priv->buf_size = priv->wl.high; } + } else { + priv->enable = 0; + priv->wl.low = 0; + priv->wl.high = 0; + priv->buf_size = 0; } } @@ -1522,8 +1531,15 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size) for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { priv = &hdev->priv_buf[i]; - if (hdev->hw_tc_map & BIT(i)) - priv->enable = 1; + priv->enable = 0; + priv->wl.low = 0; + priv->wl.high = 0; + priv->buf_size = 0; + + if (!(hdev->hw_tc_map & BIT(i))) + continue; + + priv->enable = 1; if (hdev->tm_info.hw_pfc_map & BIT(i)) { priv->wl.low = 128; @@ -1616,6 +1632,10 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev) cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B); } + req->shared_buf = + cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) | + (1 << HCLGE_TC0_PRI_BUF_EN_B)); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, @@ -1782,18 +1802,22 @@ int hclge_buffer_alloc(struct hclge_dev *hdev) return ret; } - ret = hclge_rx_priv_wl_config(hdev); - if (ret) { - dev_err(&hdev->pdev->dev, - "could not configure rx private waterline %d\n", ret); - return ret; - } + if (hnae3_dev_dcb_supported(hdev)) { + ret = hclge_rx_priv_wl_config(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not configure rx private waterline %d\n", + ret); + return ret; + } - ret = hclge_common_thrd_config(hdev); - if (ret) { - dev_err(&hdev->pdev->dev, - "could not configure common threshold %d\n", ret); - return ret; + ret = hclge_common_thrd_config(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not configure common threshold %d\n", + ret); + return ret; + } } ret = hclge_common_wl_config(hdev); @@ -2582,6 +2606,7 @@ static int hclge_rss_init_hw(struct hclge_dev *hdev) u16 tc_valid[HCLGE_MAX_TC_NUM]; u16 tc_size[HCLGE_MAX_TC_NUM]; u32 *rss_indir = NULL; + u16 rss_size = 0, roundup_size; const u8 *key; int i, ret, j; @@ -2596,7 +2621,13 @@ static int hclge_rss_init_hw(struct hclge_dev *hdev) for (j = 0; j < hdev->num_vmdq_vport + 1; j++) { for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) { vport[j].rss_indirection_tbl[i] = - i % hdev->rss_size_max; + i % vport[j].alloc_rss_size; + + /* vport 0 is for PF */ + if (j != 0) + continue; + + rss_size = vport[j].alloc_rss_size; rss_indir[i] = vport[j].rss_indirection_tbl[i]; } } @@ -2613,42 +2644,31 @@ static int hclge_rss_init_hw(struct hclge_dev *hdev) if (ret) goto err; + /* Each TC have the same queue size, and tc_size set to hardware is + * the log2 of roundup power of two of rss_size, the acutal queue + * size is limited by indirection table. + */ + if (rss_size > HCLGE_RSS_TC_SIZE_7 || rss_size == 0) { + dev_err(&hdev->pdev->dev, + "Configure rss tc size failed, invalid TC_SIZE = %d\n", + rss_size); + return -EINVAL; + } + + roundup_size = roundup_pow_of_two(rss_size); + roundup_size = ilog2(roundup_size); + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - if (hdev->hw_tc_map & BIT(i)) - tc_valid[i] = 1; - else - tc_valid[i] = 0; + tc_valid[i] = 0; - switch (hdev->rss_size_max) { - case HCLGE_RSS_TC_SIZE_0: - tc_size[i] = 0; - break; - case HCLGE_RSS_TC_SIZE_1: - tc_size[i] = 1; - break; - case HCLGE_RSS_TC_SIZE_2: - tc_size[i] = 2; - break; - case HCLGE_RSS_TC_SIZE_3: - tc_size[i] = 3; - break; - case HCLGE_RSS_TC_SIZE_4: - tc_size[i] = 4; - break; - case HCLGE_RSS_TC_SIZE_5: - tc_size[i] = 5; - break; - case HCLGE_RSS_TC_SIZE_6: - tc_size[i] = 6; - break; - case HCLGE_RSS_TC_SIZE_7: - tc_size[i] = 7; - break; - default: - break; - } - tc_offset[i] = hdev->rss_size_max * i; + if (!(hdev->hw_tc_map & BIT(i))) + continue; + + tc_valid[i] = 1; + tc_size[i] = roundup_size; + tc_offset[i] = rss_size * i; } + ret = hclge_set_rss_tc_mode(hdev, tc_valid, tc_size, tc_offset); err: @@ -2679,7 +2699,11 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, node->tqp_index); + hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + req->vfid = vport->vport_id; if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD; @@ -2763,8 +2787,12 @@ static int hclge_unmap_ring_from_vector( hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, node->tqp_index); + hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + req->vfid = vport->vport_id; if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD; @@ -2778,7 +2806,7 @@ static int hclge_unmap_ring_from_vector( } i = 0; hclge_cmd_setup_basic_desc(&desc, - HCLGE_OPC_ADD_RING_TO_VECTOR, + HCLGE_OPC_DEL_RING_TO_VECTOR, false); req->int_vector_id = vector_id; } @@ -3665,6 +3693,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) { #define HCLGE_VLAN_TYPE_VF_TABLE 0 #define HCLGE_VLAN_TYPE_PORT_TABLE 1 + struct hnae3_handle *handle; int ret; ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_VF_TABLE, @@ -3674,8 +3703,11 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_PORT_TABLE, true); + if (ret) + return ret; - return ret; + handle = &hdev->vport[0].nic; + return hclge_set_port_vlan_filter(handle, htons(ETH_P_8021Q), 0, false); } static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) @@ -3920,8 +3952,7 @@ static int hclge_init_client_instance(struct hnae3_client *client, goto err; if (hdev->roce_client && - hnae_get_bit(hdev->ae_dev->flag, - HNAE_DEV_SUPPORT_ROCE_B)) { + hnae3_dev_roce_supported(hdev)) { struct hnae3_client *rc = hdev->roce_client; ret = hclge_init_roce_base_info(vport); @@ -3944,8 +3975,7 @@ static int hclge_init_client_instance(struct hnae3_client *client, break; case HNAE3_CLIENT_ROCE: - if (hnae_get_bit(hdev->ae_dev->flag, - HNAE_DEV_SUPPORT_ROCE_B)) { + if (hnae3_dev_roce_supported(hdev)) { hdev->roce_client = client; vport->roce.client = client; } @@ -4057,7 +4087,6 @@ static void hclge_pci_uninit(struct hclge_dev *hdev) static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) { struct pci_dev *pdev = ae_dev->pdev; - const struct pci_device_id *id; struct hclge_dev *hdev; int ret; @@ -4072,10 +4101,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hdev->ae_dev = ae_dev; ae_dev->priv = hdev; - id = pci_match_id(roce_pci_tbl, ae_dev->pdev); - if (id) - hnae_set_bit(ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B, 1); - ret = hclge_pci_init(hdev); if (ret) { dev_err(&pdev->dev, "PCI init failed\n"); @@ -4138,12 +4163,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } - ret = hclge_rss_init_hw(hdev); - if (ret) { - dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret); - return ret; - } - ret = hclge_init_vlan_config(hdev); if (ret) { dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret); @@ -4156,6 +4175,12 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = hclge_rss_init_hw(hdev); + if (ret) { + dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret); + return ret; + } + setup_timer(&hdev->service_timer, hclge_service_timer, (unsigned long)hdev); INIT_WORK(&hdev->service_task, hclge_service_task); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index edb10ad..9fcfd93 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -176,7 +176,6 @@ struct hclge_pg_info { struct hclge_tc_info { u8 tc_id; u8 tc_sch_mode; /* 0: sp; 1: dwrr */ - u8 up; u8 pgid; u32 bw_limit; }; @@ -197,6 +196,7 @@ struct hclge_tm_info { u8 num_tc; u8 num_pg; /* It must be 1 if vNET-Base schd */ u8 pg_dwrr[HCLGE_PG_NUM]; + u8 prio_tc[HNAE3_MAX_USER_PRIO]; struct hclge_pg_info pg_info[HCLGE_PG_NUM]; struct hclge_tc_info tc_info[HNAE3_MAX_TC]; enum hclge_fc_mode fc_mode; @@ -477,6 +477,7 @@ struct hclge_vport { u8 rss_hash_key[HCLGE_RSS_KEY_SIZE]; /* User configured hash keys */ /* User configured lookup table entries */ u8 rss_indirection_tbl[HCLGE_RSS_IND_TBL_SIZE]; + u16 alloc_rss_size; u16 qs_offset; u16 bw_limit; /* VSI BW Limit (0 = disabled) */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 1c577d2..73a75d7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -128,9 +128,7 @@ static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id) { u8 tc; - for (tc = 0; tc < hdev->tm_info.num_tc; tc++) - if (hdev->tm_info.tc_info[tc].up == pri_id) - break; + tc = hdev->tm_info.prio_tc[pri_id]; if (tc >= hdev->tm_info.num_tc) return -EINVAL; @@ -158,7 +156,7 @@ static int hclge_up_to_tc_map(struct hclge_dev *hdev) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, false); - for (pri_id = 0; pri_id < hdev->tm_info.num_tc; pri_id++) { + for (pri_id = 0; pri_id < HNAE3_MAX_USER_PRIO; pri_id++) { ret = hclge_fill_pri_array(hdev, pri, pri_id); if (ret) return ret; @@ -280,11 +278,11 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, shap_cfg_cmd->pg_id = pg_id; - hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b); - hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u); - hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s); - hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b); - hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s); + hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b); + hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u); + hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s); + hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b); + hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s); return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -307,11 +305,11 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, shap_cfg_cmd->pri_id = pri_id; - hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b); - hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u); - hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s); - hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b); - hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s); + hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b); + hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u); + hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s); + hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b); + hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s); return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -397,6 +395,7 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) kinfo->num_tqps / kinfo->num_tc); vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id; vport->dwrr = 100; /* 100 percent as init */ + vport->alloc_rss_size = kinfo->rss_size; for (i = 0; i < kinfo->num_tc; i++) { if (hdev->hw_tc_map & BIT(i)) { @@ -404,16 +403,17 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size; kinfo->tc_info[i].tqp_count = kinfo->rss_size; kinfo->tc_info[i].tc = i; - kinfo->tc_info[i].up = hdev->tm_info.tc_info[i].up; } else { /* Set to default queue if TC is disable */ kinfo->tc_info[i].enable = false; kinfo->tc_info[i].tqp_offset = 0; kinfo->tc_info[i].tqp_count = 1; kinfo->tc_info[i].tc = 0; - kinfo->tc_info[i].up = 0; } } + + memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc, + FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc)); } static void hclge_tm_vport_info_update(struct hclge_dev *hdev) @@ -435,12 +435,15 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev) for (i = 0; i < hdev->tm_info.num_tc; i++) { hdev->tm_info.tc_info[i].tc_id = i; hdev->tm_info.tc_info[i].tc_sch_mode = HCLGE_SCH_MODE_DWRR; - hdev->tm_info.tc_info[i].up = i; hdev->tm_info.tc_info[i].pgid = 0; hdev->tm_info.tc_info[i].bw_limit = hdev->tm_info.pg_info[0].bw_limit; } + for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) + hdev->tm_info.prio_tc[i] = + (i >= hdev->tm_info.num_tc) ? 0 : i; + hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; } @@ -976,6 +979,10 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev) if (ret) return ret; + /* Only DCB-supported dev supports qset back pressure setting */ + if (!hnae3_dev_dcb_supported(hdev)) + return 0; + for (i = 0; i < hdev->tm_info.num_tc; i++) { ret = hclge_tm_qs_bp_cfg(hdev, i); if (ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 7e67337..85158b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -94,10 +94,10 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; -#define hclge_tm_set_feild(dest, string, val) \ +#define hclge_tm_set_field(dest, string, val) \ hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \ (HCLGE_TM_SHAP_##string##_LSH), val) -#define hclge_tm_get_feild(src, string) \ +#define hclge_tm_get_field(src, string) \ hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \ (HCLGE_TM_SHAP_##string##_LSH)) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index 1c3e294..35369e1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -41,11 +41,16 @@ static struct hnae3_client client; static const struct pci_device_id hns3_pci_tbl[] = { {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0}, {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), + HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), + HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), + HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), + HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), + HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, /* required last entry */ {0, } }; @@ -1348,6 +1353,7 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } ae_dev->pdev = pdev; + ae_dev->flag = ent->driver_data; ae_dev->dev_type = HNAE3_DEV_KNIC; pci_set_drvdata(pdev, ae_dev); @@ -2705,10 +2711,11 @@ static void hns3_init_mac_addr(struct net_device *netdev) eth_hw_addr_random(netdev); dev_warn(priv->dev, "using random MAC address %pM\n", netdev->dev_addr); - /* Also copy this new MAC address into hdev */ - if (h->ae_algo->ops->set_mac_addr) - h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr); } + + if (h->ae_algo->ops->set_mac_addr) + h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr); + } static void hns3_nic_set_priv_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index 2c74baa..fff09dc 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -402,7 +402,7 @@ static int mal_poll(struct napi_struct *napi, int budget) unsigned long flags; MAL_DBG2(mal, "poll(%d)" NL, budget); - again: + /* Process TX skbs */ list_for_each(l, &mal->poll_list) { struct mal_commac *mc = @@ -451,7 +451,6 @@ static int mal_poll(struct napi_struct *napi, int budget) spin_lock_irqsave(&mal->lock, flags); mal_disable_eob_irq(mal); spin_unlock_irqrestore(&mal->lock, flags); - goto again; } mc->ops->poll_tx(mc->dev); } diff --git a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c index bbe2463..c8c6231 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c @@ -88,6 +88,8 @@ static void emac_set_msglevel(struct net_device *netdev, u32 data) static int emac_get_sset_count(struct net_device *netdev, int sset) { switch (sset) { + case ETH_SS_PRIV_FLAGS: + return 1; case ETH_SS_STATS: return EMAC_STATS_LEN; default: @@ -100,6 +102,10 @@ static void emac_get_strings(struct net_device *netdev, u32 stringset, u8 *data) unsigned int i; switch (stringset) { + case ETH_SS_PRIV_FLAGS: + strcpy(data, "single-pause-mode"); + break; + case ETH_SS_STATS: for (i = 0; i < EMAC_STATS_LEN; i++) { strlcpy(data, emac_ethtool_stat_strings[i], @@ -230,6 +236,27 @@ static int emac_get_regs_len(struct net_device *netdev) return EMAC_MAX_REG_SIZE * sizeof(u32); } +#define EMAC_PRIV_ENABLE_SINGLE_PAUSE BIT(0) + +static int emac_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct emac_adapter *adpt = netdev_priv(netdev); + + adpt->single_pause_mode = !!(flags & EMAC_PRIV_ENABLE_SINGLE_PAUSE); + + if (netif_running(netdev)) + return emac_reinit_locked(adpt); + + return 0; +} + +static u32 emac_get_priv_flags(struct net_device *netdev) +{ + struct emac_adapter *adpt = netdev_priv(netdev); + + return adpt->single_pause_mode ? EMAC_PRIV_ENABLE_SINGLE_PAUSE : 0; +} + static const struct ethtool_ops emac_ethtool_ops = { .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, @@ -253,6 +280,9 @@ static const struct ethtool_ops emac_ethtool_ops = { .get_regs_len = emac_get_regs_len, .get_regs = emac_get_regs, + + .set_priv_flags = emac_set_priv_flags, + .get_priv_flags = emac_get_priv_flags, }; void emac_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index bcd4708..0ea3ca0 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -551,6 +551,28 @@ static void emac_mac_start(struct emac_adapter *adpt) mac &= ~(HUGEN | VLAN_STRIP | TPAUSE | SIMR | HUGE | MULTI_ALL | DEBUG_MODE | SINGLE_PAUSE_MODE); + /* Enable single-pause-frame mode if requested. + * + * If enabled, the EMAC will send a single pause frame when the RX + * queue is full. This normally leads to packet loss because + * the pause frame disables the remote MAC only for 33ms (the quanta), + * and then the remote MAC continues sending packets even though + * the RX queue is still full. + * + * If disabled, the EMAC sends a pause frame every 31ms until the RX + * queue is no longer full. Normally, this is the preferred + * method of operation. However, when the system is hung (e.g. + * cores are halted), the EMAC interrupt handler is never called + * and so the RX queue fills up quickly and stays full. The resuling + * non-stop "flood" of pause frames sometimes has the effect of + * disabling nearby switches. In some cases, other nearby switches + * are also affected, shutting down the entire network. + * + * The user can enable or disable single-pause-frame mode + * via ethtool. + */ + mac |= adpt->single_pause_mode ? SINGLE_PAUSE_MODE : 0; + writel_relaxed(csr1, adpt->csr + EMAC_EMAC_WRAPPER_CSR1); writel_relaxed(mac, adpt->base + EMAC_MAC_CTRL); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 60850bf..7595435 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -443,6 +443,9 @@ static void emac_init_adapter(struct emac_adapter *adpt) /* default to automatic flow control */ adpt->automatic = true; + + /* Disable single-pause-frame mode by default */ + adpt->single_pause_mode = false; } /* Get the clock */ diff --git a/drivers/net/ethernet/qualcomm/emac/emac.h b/drivers/net/ethernet/qualcomm/emac/emac.h index 8ee4ec6..d7c9f44 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.h +++ b/drivers/net/ethernet/qualcomm/emac/emac.h @@ -363,6 +363,9 @@ struct emac_adapter { bool tx_flow_control; bool rx_flow_control; + /* True == use single-pause-frame mode. */ + bool single_pause_mode; + /* Ring parameter */ u8 tpd_burst; u8 rfd_burst; diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index ca22f28..d24b47b 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2135,11 +2135,12 @@ static int rtl8139_poll(struct napi_struct *napi, int budget) if (likely(RTL_R16(IntrStatus) & RxAckBits)) work_done += rtl8139_rx(dev, tp, budget); - if (work_done < budget && napi_complete_done(napi, work_done)) { + if (work_done < budget) { unsigned long flags; spin_lock_irqsave(&tp->lock, flags); - RTL_W16_F(IntrMask, rtl8139_intr_mask); + if (napi_complete_done(napi, work_done)) + RTL_W16_F(IntrMask, rtl8139_intr_mask); spin_unlock_irqrestore(&tp->lock, flags); } spin_unlock(&tp->rx_lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index a366b37..8a280b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -315,6 +315,7 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, { .compatible = "allwinner,sun8i-h3-emac" }, { .compatible = "allwinner,sun8i-v3s-emac" }, { .compatible = "allwinner,sun50i-a64-emac" }, + {}, }; /* If phy-handle property is passed from DT, use it as the PHY */ diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index d98cdfb..5176be7 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -150,6 +150,8 @@ struct netvsc_device_info { u32 num_chn; u32 send_sections; u32 recv_sections; + u32 send_section_size; + u32 recv_section_size; }; enum rndis_device_state { diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index a5511b7..8d5077f 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -76,9 +76,6 @@ static struct netvsc_device *alloc_net_device(void) net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; - net_device->recv_section_size = NETVSC_RECV_SECTION_SIZE; - net_device->send_section_size = NETVSC_SEND_SECTION_SIZE; - init_completion(&net_device->channel_init_wait); init_waitqueue_head(&net_device->subchan_open); INIT_WORK(&net_device->subchan_work, rndis_set_subchannel); @@ -262,7 +259,7 @@ static int netvsc_init_buf(struct hv_device *device, int ret = 0; /* Get receive buffer area. */ - buf_size = device_info->recv_sections * net_device->recv_section_size; + buf_size = device_info->recv_sections * device_info->recv_section_size; buf_size = roundup(buf_size, PAGE_SIZE); net_device->recv_buf = vzalloc(buf_size); @@ -344,7 +341,7 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; /* Now setup the send buffer. */ - buf_size = device_info->send_sections * net_device->send_section_size; + buf_size = device_info->send_sections * device_info->send_section_size; buf_size = round_up(buf_size, PAGE_SIZE); net_device->send_buf = vzalloc(buf_size); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d4902ee5f..a32ae02 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -848,7 +848,9 @@ static int netvsc_set_channels(struct net_device *net, device_info.num_chn = count; device_info.ring_size = ring_size; device_info.send_sections = nvdev->send_section_cnt; + device_info.send_section_size = nvdev->send_section_size; device_info.recv_sections = nvdev->recv_section_cnt; + device_info.recv_section_size = nvdev->recv_section_size; rndis_filter_device_remove(dev, nvdev); @@ -963,7 +965,9 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) device_info.ring_size = ring_size; device_info.num_chn = nvdev->num_chn; device_info.send_sections = nvdev->send_section_cnt; + device_info.send_section_size = nvdev->send_section_size; device_info.recv_sections = nvdev->recv_section_cnt; + device_info.recv_section_size = nvdev->recv_section_size; rndis_filter_device_remove(hdev, nvdev); @@ -1485,7 +1489,9 @@ static int netvsc_set_ringparam(struct net_device *ndev, device_info.num_chn = nvdev->num_chn; device_info.ring_size = ring_size; device_info.send_sections = new_tx; + device_info.send_section_size = nvdev->send_section_size; device_info.recv_sections = new_rx; + device_info.recv_section_size = nvdev->recv_section_size; netif_device_detach(ndev); was_opened = rndis_filter_opened(nvdev); @@ -1934,7 +1940,9 @@ static int netvsc_probe(struct hv_device *dev, device_info.ring_size = ring_size; device_info.num_chn = VRSS_CHANNEL_DEFAULT; device_info.send_sections = NETVSC_DEFAULT_TX; + device_info.send_section_size = NETVSC_SEND_SECTION_SIZE; device_info.recv_sections = NETVSC_DEFAULT_RX; + device_info.recv_section_size = NETVSC_RECV_SECTION_SIZE; nvdev = rndis_filter_device_add(dev, &device_info); if (IS_ERR(nvdev)) { diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index a9d16a3..cd931cf 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -160,15 +160,6 @@ config MDIO_XGENE endif -menuconfig PHYLIB - tristate "PHY Device support and infrastructure" - depends on NETDEVICES - select MDIO_DEVICE - help - Ethernet controllers are usually attached to PHY - devices. This option provides infrastructure for - managing PHY devices. - config PHYLINK tristate depends on NETDEVICES @@ -179,6 +170,15 @@ config PHYLINK configuration links, PHYs, and Serdes links with MAC level autonegotiation modes. +menuconfig PHYLIB + tristate "PHY Device support and infrastructure" + depends on NETDEVICES + select MDIO_DEVICE + help + Ethernet controllers are usually attached to PHY + devices. This option provides infrastructure for + managing PHY devices. + if PHYLIB config SWPHY diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e842d2c..2b1e67b 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -373,7 +373,8 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, cmd->base.port = PORT_BNC; else cmd->base.port = PORT_MII; - + cmd->base.transceiver = phy_is_internal(phydev) ? + XCVR_INTERNAL : XCVR_EXTERNAL; cmd->base.phy_address = phydev->mdio.addr; cmd->base.autoneg = phydev->autoneg; cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8cf0c59..67f25ac 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -879,7 +879,7 @@ void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) { const char *drv_name = phydev->drv ? phydev->drv->name : "unbound"; char *irq_str; - char irq_num[4]; + char irq_num[8]; switch(phydev->irq) { case PHY_POLL: diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index d15dd39..2e5150b 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -44,7 +44,7 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev) priv->phy_drv->read_status(phydev); val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG); - val &= XILINX_GMII2RGMII_SPEED_MASK; + val &= ~XILINX_GMII2RGMII_SPEED_MASK; if (phydev->speed == SPEED_1000) val |= BMCR_SPEED1000; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index b99a7fb..0161f77 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1265,30 +1265,45 @@ static int lan78xx_ethtool_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { struct lan78xx_net *dev = netdev_priv(netdev); + int ret; + + ret = usb_autopm_get_interface(dev->intf); + if (ret) + return ret; ee->magic = LAN78XX_EEPROM_MAGIC; - return lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data); + ret = lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data); + + usb_autopm_put_interface(dev->intf); + + return ret; } static int lan78xx_ethtool_set_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { struct lan78xx_net *dev = netdev_priv(netdev); + int ret; + + ret = usb_autopm_get_interface(dev->intf); + if (ret) + return ret; - /* Allow entire eeprom update only */ - if ((ee->magic == LAN78XX_EEPROM_MAGIC) && - (ee->offset == 0) && - (ee->len == 512) && - (data[0] == EEPROM_INDICATOR)) - return lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data); + /* Invalid EEPROM_INDICATOR at offset zero will result in a failure + * to load data from EEPROM + */ + if (ee->magic == LAN78XX_EEPROM_MAGIC) + ret = lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data); else if ((ee->magic == LAN78XX_OTP_MAGIC) && (ee->offset == 0) && (ee->len == 512) && (data[0] == OTP_INDICATOR_1)) - return lan78xx_write_raw_otp(dev, ee->offset, ee->len, data); + ret = lan78xx_write_raw_otp(dev, ee->offset, ee->len, data); + + usb_autopm_put_interface(dev->intf); - return -EINVAL; + return ret; } static void lan78xx_get_strings(struct net_device *netdev, u32 stringset, @@ -2434,7 +2449,6 @@ static int lan78xx_reset(struct lan78xx_net *dev) /* LAN7801 only has RGMII mode */ if (dev->chipid == ID_REV_CHIP_ID_7801_) buf &= ~MAC_CR_GMII_EN_; - buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_; ret = lan78xx_write_reg(dev, MAC_CR, buf); ret = lan78xx_read_reg(dev, MAC_TX, &buf); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index acc816b..bb2aad0 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -134,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req) return false; if (nvme_req(req)->status & NVME_SC_DNR) return false; - if (jiffies - req->start_time >= req->timeout) - return false; if (nvme_req(req)->retries >= nvme_max_retries) return false; return true; @@ -2590,7 +2588,7 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work); spin_lock_irq(&ctrl->lock); - while (ctrl->event_limit > 0) { + while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) { int aer_idx = --ctrl->event_limit; spin_unlock_irq(&ctrl->lock); @@ -2677,7 +2675,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, /*FALLTHRU*/ case NVME_SC_ABORT_REQ: ++ctrl->event_limit; - queue_work(nvme_wq, &ctrl->async_event_work); + if (ctrl->state == NVME_CTRL_LIVE) + queue_work(nvme_wq, &ctrl->async_event_work); break; default: break; @@ -2692,7 +2691,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, nvme_queue_scan(ctrl); break; case NVME_AER_NOTICE_FW_ACT_STARTING: - schedule_work(&ctrl->fw_act_work); + queue_work(nvme_wq, &ctrl->fw_act_work); break; default: dev_warn(ctrl->device, "async event result %08x\n", result); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 4730775..555c976 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -565,6 +565,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->queue_size = NVMF_DEF_QUEUE_SIZE; opts->nr_io_queues = num_online_cpus(); opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; + opts->kato = NVME_DEFAULT_KATO; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -655,21 +656,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, goto out; } - if (opts->discovery_nqn) { - pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n"); - ret = -EINVAL; - goto out; - } - if (token < 0) { pr_err("Invalid keep_alive_tmo %d\n", token); ret = -EINVAL; goto out; - } else if (token == 0) { + } else if (token == 0 && !opts->discovery_nqn) { /* Allowed for debug */ pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n"); } opts->kato = token; + + if (opts->discovery_nqn && opts->kato) { + pr_err("Discovery controllers cannot accept KATO != 0\n"); + ret = -EINVAL; + goto out; + } + break; case NVMF_OPT_CTRL_LOSS_TMO: if (match_int(args, &token)) { @@ -762,8 +764,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, uuid_copy(&opts->host->id, &hostid); out: - if (!opts->discovery_nqn && !opts->kato) - opts->kato = NVME_DEFAULT_KATO; kfree(options); return ret; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d2e882c..af075e9 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1376,7 +1376,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) if (atomic_read(&op->state) == FCPOP_STATE_ABORTED) status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1); else if (freq->status) - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); /* * For the linux implementation, if we have an unsuccesful @@ -1404,7 +1404,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) */ if (freq->transferred_length != be32_to_cpu(op->cmd_iu.data_len)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result.u64 = 0; @@ -1421,7 +1421,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) freq->transferred_length || op->rsp_iu.status_code || sqe->common.command_id != cqe->command_id)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result = cqe->result; @@ -1429,7 +1429,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) break; default: - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } @@ -1989,16 +1989,17 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, * as well as those by FC-NVME spec. */ WARN_ON_ONCE(sqe->common.metadata); - WARN_ON_ONCE(sqe->common.dptr.prp1); - WARN_ON_ONCE(sqe->common.dptr.prp2); sqe->common.flags |= NVME_CMD_SGL_METABUF; /* - * format SQE DPTR field per FC-NVME rules - * type=data block descr; subtype=offset; - * offset is currently 0. + * format SQE DPTR field per FC-NVME rules: + * type=0x5 Transport SGL Data Block Descriptor + * subtype=0xA Transport-specific value + * address=0 + * length=length of the data series */ - sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET; + sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) | + NVME_SGL_FMT_TRANSPORT_A; sqe->rw.dptr.sgl.length = cpu_to_le32(data_len); sqe->rw.dptr.sgl.addr = 0; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4a21213..cb73bc8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -24,6 +24,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/once.h> #include <linux/pci.h> #include <linux/poison.h> #include <linux/t10-pi.h> @@ -540,6 +541,20 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) } #endif +static void nvme_print_sgl(struct scatterlist *sgl, int nents) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + dma_addr_t phys = sg_phys(sg); + pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " + "dma_address:%pad dma_length:%d\n", + i, &phys, sg->offset, sg->length, &sg_dma_address(sg), + sg_dma_len(sg)); + } +} + static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -622,19 +637,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) return BLK_STS_OK; bad_sgl: - if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n", - blk_rq_payload_bytes(req), iod->nents)) { - for_each_sg(iod->sg, sg, iod->nents, i) { - dma_addr_t phys = sg_phys(sg); - pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " - "dma_address:%pad dma_length:%d\n", i, &phys, - sg->offset, sg->length, - &sg_dma_address(sg), - sg_dma_len(sg)); - } - } + WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents), + "Invalid SGL for payload:%d nents:%d\n", + blk_rq_payload_bytes(req), iod->nents); return BLK_STS_IOERR; - } static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, @@ -1313,11 +1319,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) if (result < 0) goto release_cq; + nvme_init_queue(nvmeq, qid); result = queue_request_irq(nvmeq); if (result < 0) goto release_sq; - nvme_init_queue(nvmeq, qid); return result; release_sq: @@ -1464,6 +1470,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) return result; nvmeq->cq_vector = 0; + nvme_init_queue(nvmeq, 0); result = queue_request_irq(nvmeq); if (result) { nvmeq->cq_vector = -1; @@ -2156,7 +2163,6 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out; - nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) goto out; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 5898300..92a03ff 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -942,7 +942,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - WARN_ON_ONCE(!changed); + if (!changed) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING); + return; + } + ctrl->ctrl.nr_reconnects = 0; nvme_start_ctrl(&ctrl->ctrl); @@ -962,7 +967,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, err_work); - nvme_stop_ctrl(&ctrl->ctrl); + nvme_stop_keep_alive(&ctrl->ctrl); if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 7c23eaf..1b208be 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -390,10 +390,10 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) if (status) nvmet_set_status(req, status); - /* XXX: need to fill in something useful for sq_head */ - req->rsp->sq_head = 0; - if (likely(req->sq)) /* may happen during early failure */ - req->rsp->sq_id = cpu_to_le16(req->sq->qid); + if (req->sq->size) + req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; + req->rsp->sq_head = cpu_to_le16(req->sq->sqhd); + req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; if (req->ns) @@ -420,6 +420,7 @@ void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid, u16 size) { + sq->sqhd = 0; sq->qid = qid; sq->size = size; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 859a667..db3bf6b 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -109,9 +109,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) pr_warn("queue already connected!\n"); return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; } + if (!sqsize) { + pr_warn("queue size zero!\n"); + return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + } - nvmet_cq_setup(ctrl, req->cq, qid, sqsize); - nvmet_sq_setup(ctrl, req->sq, qid, sqsize); + /* note: convert queue size from 0's-based value to 1's-based value */ + nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1); + nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1); return 0; } diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 421e43b..58e010b 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -148,7 +148,7 @@ struct nvmet_fc_tgt_assoc { u32 a_id; struct nvmet_fc_tgtport *tgtport; struct list_head a_list; - struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; }; @@ -608,7 +608,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, unsigned long flags; int ret; - if (qid >= NVMET_NR_QUEUES) + if (qid > NVMET_NR_QUEUES) return NULL; queue = kzalloc((sizeof(*queue) + @@ -783,6 +783,9 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, u16 qid = nvmet_fc_getqueueid(connection_id); unsigned long flags; + if (qid > NVMET_NR_QUEUES) + return NULL; + spin_lock_irqsave(&tgtport->lock, flags); list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { @@ -888,7 +891,7 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) int i; spin_lock_irqsave(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) { + for (i = NVMET_NR_QUEUES; i >= 0; i--) { queue = assoc->queues[i]; if (queue) { if (!nvmet_fc_tgt_q_get(queue)) @@ -1910,8 +1913,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, spin_lock_irqsave(&fod->flock, flags); fod->writedataactive = false; spin_unlock_irqrestore(&fod->flock, flags); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); } else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ { fcpreq->fcp_error = ret; fcpreq->transferred_length = 0; @@ -1929,8 +1931,7 @@ __nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort) /* if in the middle of an io and we need to tear down */ if (abort) { if (fcpreq->op == NVMET_FCOP_WRITEDATA) { - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return true; } @@ -1968,8 +1969,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) fod->abort = true; spin_unlock(&fod->flock); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return; } @@ -2533,13 +2533,17 @@ nvmet_fc_remove_port(struct nvmet_port *port) { struct nvmet_fc_tgtport *tgtport = port->priv; unsigned long flags; + bool matched = false; spin_lock_irqsave(&nvmet_fc_tgtlock, flags); if (tgtport->port == port) { - nvmet_fc_tgtport_put(tgtport); + matched = true; tgtport->port = NULL; } spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags); + + if (matched) + nvmet_fc_tgtport_put(tgtport); } static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1cb9847..7b75d9d 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -224,8 +224,6 @@ struct fcloop_nport { struct fcloop_lport *lport; struct list_head nport_list; struct kref ref; - struct completion rport_unreg_done; - struct completion tport_unreg_done; u64 node_name; u64 port_name; u32 port_role; @@ -576,7 +574,7 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, tfcp_req->aborted = true; spin_unlock(&tfcp_req->reqlock); - tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED; + tfcp_req->status = NVME_SC_INTERNAL; /* * nothing more to do. If io wasn't active, the transport should @@ -631,6 +629,32 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, } static void +fcloop_nport_free(struct kref *ref) +{ + struct fcloop_nport *nport = + container_of(ref, struct fcloop_nport, ref); + unsigned long flags; + + spin_lock_irqsave(&fcloop_lock, flags); + list_del(&nport->nport_list); + spin_unlock_irqrestore(&fcloop_lock, flags); + + kfree(nport); +} + +static void +fcloop_nport_put(struct fcloop_nport *nport) +{ + kref_put(&nport->ref, fcloop_nport_free); +} + +static int +fcloop_nport_get(struct fcloop_nport *nport) +{ + return kref_get_unless_zero(&nport->ref); +} + +static void fcloop_localport_delete(struct nvme_fc_local_port *localport) { struct fcloop_lport *lport = localport->private; @@ -644,8 +668,7 @@ fcloop_remoteport_delete(struct nvme_fc_remote_port *remoteport) { struct fcloop_rport *rport = remoteport->private; - /* release any threads waiting for the unreg to complete */ - complete(&rport->nport->rport_unreg_done); + fcloop_nport_put(rport->nport); } static void @@ -653,8 +676,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) { struct fcloop_tport *tport = targetport->private; - /* release any threads waiting for the unreg to complete */ - complete(&tport->nport->tport_unreg_done); + fcloop_nport_put(tport->nport); } #define FCLOOP_HW_QUEUES 4 @@ -722,6 +744,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr, goto out_free_opts; } + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = opts->wwnn; pinfo.port_name = opts->wwpn; pinfo.port_role = opts->roles; @@ -804,32 +827,6 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr, return ret ? ret : count; } -static void -fcloop_nport_free(struct kref *ref) -{ - struct fcloop_nport *nport = - container_of(ref, struct fcloop_nport, ref); - unsigned long flags; - - spin_lock_irqsave(&fcloop_lock, flags); - list_del(&nport->nport_list); - spin_unlock_irqrestore(&fcloop_lock, flags); - - kfree(nport); -} - -static void -fcloop_nport_put(struct fcloop_nport *nport) -{ - kref_put(&nport->ref, fcloop_nport_free); -} - -static int -fcloop_nport_get(struct fcloop_nport *nport) -{ - return kref_get_unless_zero(&nport->ref); -} - static struct fcloop_nport * fcloop_alloc_nport(const char *buf, size_t count, bool remoteport) { @@ -938,6 +935,7 @@ fcloop_create_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -EIO; + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = nport->node_name; pinfo.port_name = nport->port_name; pinfo.port_role = nport->port_role; @@ -979,24 +977,12 @@ __unlink_remote_port(struct fcloop_nport *nport) } static int -__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) +__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) { - int ret; - if (!rport) return -EALREADY; - init_completion(&nport->rport_unreg_done); - - ret = nvme_fc_unregister_remoteport(rport->remoteport); - if (ret) - return ret; - - wait_for_completion(&nport->rport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvme_fc_unregister_remoteport(rport->remoteport); } static ssize_t @@ -1029,7 +1015,7 @@ fcloop_delete_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); return ret ? ret : count; } @@ -1086,24 +1072,12 @@ __unlink_target_port(struct fcloop_nport *nport) } static int -__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) +__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) { - int ret; - if (!tport) return -EALREADY; - init_completion(&nport->tport_unreg_done); - - ret = nvmet_fc_unregister_targetport(tport->targetport); - if (ret) - return ret; - - wait_for_completion(&nport->tport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvmet_fc_unregister_targetport(tport->targetport); } static ssize_t @@ -1136,7 +1110,7 @@ fcloop_delete_target_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); return ret ? ret : count; } @@ -1223,11 +1197,11 @@ static void __exit fcloop_exit(void) spin_unlock_irqrestore(&fcloop_lock, flags); - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); if (ret) pr_warn("%s: Failed deleting target port\n", __func__); - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); if (ret) pr_warn("%s: Failed deleting remote port\n", __func__); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7d261ab..7b8e20a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -74,6 +74,7 @@ struct nvmet_sq { struct percpu_ref ref; u16 qid; u16 size; + u16 sqhd; struct completion free_done; struct completion confirm_done; }; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index de54c7f..d12e5de 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -135,7 +135,7 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, /* Stop the user from writing */ if (pos >= nvmem->size) - return 0; + return -EFBIG; if (count < nvmem->word_size) return -EINVAL; @@ -789,6 +789,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, return ERR_PTR(-EINVAL); nvmem = __nvmem_device_get(nvmem_np, NULL, NULL); + of_node_put(nvmem_np); if (IS_ERR(nvmem)) return ERR_CAST(nvmem); diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 1eecfa3..8e075ea 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -686,7 +686,7 @@ static ssize_t driver_override_store(struct device *dev, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - char *driver_override, *old = pdev->driver_override, *cp; + char *driver_override, *old, *cp; /* We need to keep extra room for a newline */ if (count >= (PAGE_SIZE - 1)) @@ -700,12 +700,15 @@ static ssize_t driver_override_store(struct device *dev, if (cp) *cp = '\0'; + device_lock(dev); + old = pdev->driver_override; if (strlen(driver_override)) { pdev->driver_override = driver_override; } else { kfree(driver_override); pdev->driver_override = NULL; } + device_unlock(dev); kfree(old); @@ -716,8 +719,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); + ssize_t len; - return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index 85de30f..56a8195 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -254,10 +254,12 @@ static int bl_update_status(struct backlight_device *b) { struct acpi_device *device = bl_get_data(b); - if (b->props.power == FB_BLANK_POWERDOWN) - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); - else - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + if (fext) { + if (b->props.power == FB_BLANK_POWERDOWN) + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); + else + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + } return set_lcd_level(device, b->props.brightness); } diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index a64285a..af3e4d3 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -699,13 +699,13 @@ static void _aac_probe_container1(void * context, struct fib * fibptr) int status; dresp = (struct aac_mount *) fib_data(fibptr); - if (!(fibptr->dev->supplement_adapter_info.supported_options2 & - AAC_OPTION_VARIABLE_BLOCK_SIZE)) + if (!aac_supports_2T(fibptr->dev)) { dresp->mnt[0].capacityhigh = 0; - if ((le32_to_cpu(dresp->status) != ST_OK) || - (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { - _aac_probe_container2(context, fibptr); - return; + if ((le32_to_cpu(dresp->status) == ST_OK) && + (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { + _aac_probe_container2(context, fibptr); + return; + } } scsicmd = (struct scsi_cmnd *) context; diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 92fabf2..403a639 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2701,6 +2701,11 @@ static inline int aac_is_src(struct aac_dev *dev) return 0; } +static inline int aac_supports_2T(struct aac_dev *dev) +{ + return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64); +} + char * get_container_type(unsigned type); extern int numacb; extern char aac_driver_version[]; diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 87cc4a9..62beb25 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -906,12 +906,14 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", @@ -962,12 +964,14 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 48c2b2b..0c9361c 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -740,6 +740,8 @@ static void aac_send_iop_reset(struct aac_dev *dev) aac_set_intx_mode(dev); src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK); + + msleep(5000); } static void aac_send_hardware_soft_reset(struct aac_dev *dev) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 7e7ae78..100bc4c 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -6131,6 +6131,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) "Extents and RPI headers enabled.\n"); } mempool_free(mboxq, phba->mbox_mem_pool); + rc = -EIO; goto out_free_bsmbx; } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 79ba3ce..23bdb1c 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -884,7 +884,7 @@ out_err: wcqe->total_data_placed); nCmd->transferred_length = 0; nCmd->rcv_rsplen = 0; - nCmd->status = NVME_SC_FC_TRANSPORT_ERROR; + nCmd->status = NVME_SC_INTERNAL; } } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 1f59e7a..6b33a1f 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -180,7 +180,7 @@ static void qla_nvme_sp_done(void *ptr, int res) goto rel; if (unlikely(res == QLA_FUNCTION_FAILED)) - fd->status = NVME_SC_FC_TRANSPORT_ERROR; + fd->status = NVME_SC_INTERNAL; else fd->status = 0; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 3894205..dab876c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -580,7 +580,8 @@ int scsi_check_sense(struct scsi_cmnd *scmd) if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x24 || /* Invalid field in cdb */ - sshdr.asc == 0x26) { /* Parameter value invalid */ + sshdr.asc == 0x26 || /* Parameter value invalid */ + sshdr.asc == 0x27) { /* Write protected */ set_host_byte(scmd, DID_TARGET_FAILURE); } return SUCCESS; diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index ba9d70f..cbd4495 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2739,7 +2739,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, list_for_each_entry(rport, &fc_host->rports, peers) { - if ((rport->port_state == FC_PORTSTATE_BLOCKED) && + if ((rport->port_state == FC_PORTSTATE_BLOCKED || + rport->port_state == FC_PORTSTATE_NOTPRESENT) && (rport->channel == channel)) { switch (fc_host->tgtid_bind_type) { @@ -2876,7 +2877,6 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, memcpy(&rport->port_name, &ids->port_name, sizeof(rport->port_name)); rport->port_id = ids->port_id; - rport->roles = ids->roles; rport->port_state = FC_PORTSTATE_ONLINE; rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT; @@ -2885,15 +2885,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, fci->f->dd_fcrport_size); spin_unlock_irqrestore(shost->host_lock, flags); - if (ids->roles & FC_PORT_ROLE_FCP_TARGET) { - scsi_target_unblock(&rport->dev, SDEV_RUNNING); - - /* initiate a scan of the target */ - spin_lock_irqsave(shost->host_lock, flags); - rport->flags |= FC_RPORT_SCAN_PENDING; - scsi_queue_work(shost, &rport->scan_work); - spin_unlock_irqrestore(shost->host_lock, flags); - } + fc_remote_port_rolechg(rport, ids->roles); return rport; } } diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 8934f19..0190aef 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3689,7 +3689,7 @@ iscsi_if_rx(struct sk_buff *skb) uint32_t group; nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || + if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || skb->len < nlh->nlmsg_len) { break; } diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index d11c6de..6150d27 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -223,11 +223,9 @@ static int ad7192_setup(struct ad7192_state *st, struct iio_dev *indio_dev = spi_get_drvdata(st->sd.spi); unsigned long long scale_uv; int i, ret, id; - u8 ones[6]; /* reset the serial interface */ - memset(&ones, 0xFF, 6); - ret = spi_write(st->sd.spi, &ones, 6); + ret = ad_sd_reset(&st->sd, 48); if (ret < 0) goto out; usleep_range(500, 1000); /* Wait for at least 500us */ diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c index 13eaf16..87595c5 100644 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.c +++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c @@ -496,8 +496,12 @@ static int spinand_program_page(struct spi_device *spi_nand, if (!wbuf) return -ENOMEM; - enable_read_hw_ecc = 0; - spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); + enable_read_hw_ecc = 1; + retval = spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); + if (retval < 0) { + dev_err(&spi_nand->dev, "ecc error on read page!!!\n"); + return retval; + } for (i = offset, j = 0; i < len; i++, j++) wbuf[i] &= buf[j]; diff --git a/drivers/staging/pi433/rf69.c b/drivers/staging/pi433/rf69.c index c4b1b21..290b419 100644 --- a/drivers/staging/pi433/rf69.c +++ b/drivers/staging/pi433/rf69.c @@ -570,12 +570,6 @@ int rf69_set_dio_mapping(struct spi_device *spi, u8 DIONumber, u8 value) dev_dbg(&spi->dev, "set: DIO mapping"); #endif - // check DIO number - if (DIONumber > 5) { - dev_dbg(&spi->dev, "set: illegal input param"); - return -EINVAL; - } - switch (DIONumber) { case 0: mask=MASK_DIO0; shift=SHIFT_DIO0; regaddr=REG_DIOMAPPING1; break; case 1: mask=MASK_DIO1; shift=SHIFT_DIO1; regaddr=REG_DIOMAPPING1; break; @@ -583,6 +577,9 @@ int rf69_set_dio_mapping(struct spi_device *spi, u8 DIONumber, u8 value) case 3: mask=MASK_DIO3; shift=SHIFT_DIO3; regaddr=REG_DIOMAPPING1; break; case 4: mask=MASK_DIO4; shift=SHIFT_DIO4; regaddr=REG_DIOMAPPING2; break; case 5: mask=MASK_DIO5; shift=SHIFT_DIO5; regaddr=REG_DIOMAPPING2; break; + default: + dev_dbg(&spi->dev, "set: illegal input param"); + return -EINVAL; } // read reg diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index 6b77820..cb8a95a 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -119,9 +119,8 @@ void rtw_free_mlme_priv_ie_data(struct mlme_priv *pmlmepriv) void _rtw_free_mlme_priv(struct mlme_priv *pmlmepriv) { - rtw_free_mlme_priv_ie_data(pmlmepriv); - if (pmlmepriv) { + rtw_free_mlme_priv_ie_data(pmlmepriv); if (pmlmepriv->free_bss_buf) { vfree(pmlmepriv->free_bss_buf); } diff --git a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c index 9227745..ce1dd6f 100644 --- a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c +++ b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c @@ -311,6 +311,8 @@ static ssize_t proc_set_cam(struct file *file, const char __user *buffer, size_t if (num < 2) return count; + if (id >= TOTAL_CAM_ENTRY) + return -EINVAL; if (strcmp("c", cmd) == 0) { _clear_cam_entry(adapter, id); diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c index 5f84526..edbf6af 100644 --- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c +++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c @@ -2901,11 +2901,11 @@ halmac_update_datapack_88xx(struct halmac_adapter *halmac_adapter, if (halmac_adapter->fw_version.h2c_version < 4) return HALMAC_RET_FW_NO_SUPPORT; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "[TRACE]%s ==========>\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; - HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "[TRACE]%s <==========\n", __func__); diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c index f33024e..544f638 100644 --- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c +++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c @@ -1618,10 +1618,11 @@ halmac_send_h2c_set_pwr_mode_88xx(struct halmac_adapter *halmac_adapter, void *driver_adapter = NULL; enum halmac_ret_status status = HALMAC_RET_SUCCESS; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "%s!!\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; h2c_header = h2c_buff; h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX; @@ -1713,10 +1714,11 @@ halmac_media_status_rpt_88xx(struct halmac_adapter *halmac_adapter, u8 op_mode, void *driver_adapter = NULL; enum halmac_ret_status status = HALMAC_RET_SUCCESS; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "halmac_send_h2c_set_pwr_mode_88xx!!\n"); - driver_adapter = halmac_adapter->driver_adapter; h2c_header = H2c_buff; h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX; @@ -2143,10 +2145,11 @@ halmac_func_ctrl_ch_switch_88xx(struct halmac_adapter *halmac_adapter, enum halmac_cmd_process_status *process_status = &halmac_adapter->halmac_state.scan_state_set.process_status; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "halmac_ctrl_ch_switch!!\n"); - driver_adapter = halmac_adapter->driver_adapter; halmac_api = (struct halmac_api *)halmac_adapter->halmac_api; if (halmac_transition_scan_state_88xx( @@ -2276,15 +2279,13 @@ enum halmac_ret_status halmac_send_h2c_update_bcn_parse_info_88xx( { u8 h2c_buff[HALMAC_H2C_CMD_SIZE_88XX] = {0}; u16 h2c_seq_mum = 0; - void *driver_adapter = NULL; + void *driver_adapter = halmac_adapter->driver_adapter; struct halmac_h2c_header_info h2c_header_info; enum halmac_ret_status status = HALMAC_RET_SUCCESS; HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "%s!!\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; - UPDATE_BEACON_PARSING_INFO_SET_FUNC_EN(h2c_buff, bcn_ie_info->func_en); UPDATE_BEACON_PARSING_INFO_SET_SIZE_TH(h2c_buff, bcn_ie_info->size_th); UPDATE_BEACON_PARSING_INFO_SET_TIMEOUT(h2c_buff, bcn_ie_info->timeout); diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 67956e2..56f7be6 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -1376,6 +1376,8 @@ static void reset_highlight_buffers(struct vc_data *); static int read_all_key; +static int in_keyboard_notifier; + static void start_read_all_timer(struct vc_data *vc, int command); enum { @@ -1408,7 +1410,10 @@ static void read_all_doc(struct vc_data *vc) cursor_track = read_all_mode; spk_reset_index_count(0); if (get_sentence_buf(vc, 0) == -1) { - kbd_fakekey2(vc, RA_DOWN_ARROW); + del_timer(&cursor_timer); + if (!in_keyboard_notifier) + speakup_fake_down_arrow(); + start_read_all_timer(vc, RA_DOWN_ARROW); } else { say_sentence_num(0, 0); synth_insert_next_index(0); @@ -2212,8 +2217,10 @@ static int keyboard_notifier_call(struct notifier_block *nb, int ret = NOTIFY_OK; static int keycode; /* to hold the current keycode */ + in_keyboard_notifier = 1; + if (vc->vc_mode == KD_GRAPHICS) - return ret; + goto out; /* * First, determine whether we are handling a fake keypress on @@ -2225,7 +2232,7 @@ static int keyboard_notifier_call(struct notifier_block *nb, */ if (speakup_fake_key_pressed()) - return ret; + goto out; switch (code) { case KBD_KEYCODE: @@ -2266,6 +2273,8 @@ static int keyboard_notifier_call(struct notifier_block *nb, break; } } +out: + in_keyboard_notifier = 0; return ret; } diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c index 74cce4f..27ecf6f 100644 --- a/drivers/staging/unisys/visorbus/visorchipset.c +++ b/drivers/staging/unisys/visorbus/visorchipset.c @@ -1826,7 +1826,7 @@ static __init int visorutil_spar_detect(void) return 0; } -static int init_unisys(void) +static int __init init_unisys(void) { int result; @@ -1841,7 +1841,7 @@ static int init_unisys(void) return 0; }; -static void exit_unisys(void) +static void __exit exit_unisys(void) { acpi_bus_unregister_driver(&unisys_acpi_driver); } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c index 0159ca4..be08849 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c @@ -612,18 +612,20 @@ free_pagelist(struct vchiq_pagelist_info *pagelistinfo, if (head_bytes > actual) head_bytes = actual; - memcpy((char *)page_address(pages[0]) + + memcpy((char *)kmap(pages[0]) + pagelist->offset, fragments, head_bytes); + kunmap(pages[0]); } if ((actual >= 0) && (head_bytes < actual) && (tail_bytes != 0)) { - memcpy((char *)page_address(pages[num_pages - 1]) + + memcpy((char *)kmap(pages[num_pages - 1]) + ((pagelist->offset + actual) & (PAGE_SIZE - 1) & ~(g_cache_line_size - 1)), fragments + g_cache_line_size, tail_bytes); + kunmap(pages[num_pages - 1]); } down(&g_free_fragments_mutex); diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 1c0c955..7dd3804 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -246,11 +246,11 @@ struct mxser_port { unsigned char err_shadow; struct async_icount icount; /* kernel counters for 4 input interrupts */ - int timeout; + unsigned int timeout; int read_status_mask; int ignore_status_mask; - int xmit_fifo_size; + unsigned int xmit_fifo_size; int xmit_head; int xmit_tail; int xmit_cnt; @@ -572,8 +572,9 @@ static void mxser_dtr_rts(struct tty_port *port, int on) static int mxser_set_baud(struct tty_struct *tty, long newspd) { struct mxser_port *info = tty->driver_data; - int quot = 0, baud; + unsigned int quot = 0, baud; unsigned char cval; + u64 timeout; if (!info->ioaddr) return -1; @@ -594,8 +595,13 @@ static int mxser_set_baud(struct tty_struct *tty, long newspd) quot = 0; } - info->timeout = ((info->xmit_fifo_size * HZ * 10 * quot) / info->baud_base); - info->timeout += HZ / 50; /* Add .02 seconds of slop */ + /* + * worst case (128 * 1000 * 10 * 18432) needs 35 bits, so divide in the + * u64 domain + */ + timeout = (u64)info->xmit_fifo_size * HZ * 10 * quot; + do_div(timeout, info->baud_base); + info->timeout = timeout + HZ / 50; /* Add .02 seconds of slop */ if (quot) { info->MCR |= UART_MCR_DTR; diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index 583c9a0..8c48c37 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -507,9 +507,14 @@ static void bcm_uart_set_termios(struct uart_port *port, { unsigned int ctl, baud, quot, ier; unsigned long flags; + int tries; spin_lock_irqsave(&port->lock, flags); + /* Drain the hot tub fully before we power it off for the winter. */ + for (tries = 3; !bcm_uart_tx_empty(port) && tries; tries--) + mdelay(10); + /* disable uart while changing speed */ bcm_uart_disable(port); bcm_uart_flush(port); diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 849c1f9..f025218 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1276,7 +1276,6 @@ static void rx_dma_timer_init(struct lpuart_port *sport) static int lpuart_startup(struct uart_port *port) { struct lpuart_port *sport = container_of(port, struct lpuart_port, port); - int ret; unsigned long flags; unsigned char temp; @@ -1291,11 +1290,6 @@ static int lpuart_startup(struct uart_port *port) sport->rxfifo_size = 0x1 << (((temp >> UARTPFIFO_RXSIZE_OFF) & UARTPFIFO_FIFOSIZE_MASK) + 1); - ret = devm_request_irq(port->dev, port->irq, lpuart_int, 0, - DRIVER_NAME, sport); - if (ret) - return ret; - spin_lock_irqsave(&sport->port.lock, flags); lpuart_setup_watermark(sport); @@ -1333,7 +1327,6 @@ static int lpuart_startup(struct uart_port *port) static int lpuart32_startup(struct uart_port *port) { struct lpuart_port *sport = container_of(port, struct lpuart_port, port); - int ret; unsigned long flags; unsigned long temp; @@ -1346,11 +1339,6 @@ static int lpuart32_startup(struct uart_port *port) sport->rxfifo_size = 0x1 << (((temp >> UARTFIFO_RXSIZE_OFF) & UARTFIFO_FIFOSIZE_MASK) - 1); - ret = devm_request_irq(port->dev, port->irq, lpuart32_int, 0, - DRIVER_NAME, sport); - if (ret) - return ret; - spin_lock_irqsave(&sport->port.lock, flags); lpuart32_setup_watermark(sport); @@ -1380,8 +1368,6 @@ static void lpuart_shutdown(struct uart_port *port) spin_unlock_irqrestore(&port->lock, flags); - devm_free_irq(port->dev, port->irq, sport); - if (sport->lpuart_dma_rx_use) { del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); @@ -1400,7 +1386,6 @@ static void lpuart_shutdown(struct uart_port *port) static void lpuart32_shutdown(struct uart_port *port) { - struct lpuart_port *sport = container_of(port, struct lpuart_port, port); unsigned long temp; unsigned long flags; @@ -1413,8 +1398,6 @@ static void lpuart32_shutdown(struct uart_port *port) lpuart32_write(port, temp, UARTCTRL); spin_unlock_irqrestore(&port->lock, flags); - - devm_free_irq(port->dev, port->irq, sport); } static void @@ -2212,16 +2195,22 @@ static int lpuart_probe(struct platform_device *pdev) platform_set_drvdata(pdev, &sport->port); - if (lpuart_is_32(sport)) + if (lpuart_is_32(sport)) { lpuart_reg.cons = LPUART32_CONSOLE; - else + ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0, + DRIVER_NAME, sport); + } else { lpuart_reg.cons = LPUART_CONSOLE; + ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0, + DRIVER_NAME, sport); + } + + if (ret) + goto failed_irq_request; ret = uart_add_one_port(&lpuart_reg, &sport->port); - if (ret) { - clk_disable_unprepare(sport->clk); - return ret; - } + if (ret) + goto failed_attach_port; sport->dma_tx_chan = dma_request_slave_channel(sport->port.dev, "tx"); if (!sport->dma_tx_chan) @@ -2240,6 +2229,11 @@ static int lpuart_probe(struct platform_device *pdev) } return 0; + +failed_attach_port: +failed_irq_request: + clk_disable_unprepare(sport->clk); + return ret; } static int lpuart_remove(struct platform_device *pdev) diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index cdd2f94..b9c7a90 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -889,7 +889,16 @@ static int sccnxp_probe(struct platform_device *pdev) goto err_out; uartclk = 0; } else { - clk_prepare_enable(clk); + ret = clk_prepare_enable(clk); + if (ret) + goto err_out; + + ret = devm_add_action_or_reset(&pdev->dev, + (void(*)(void *))clk_disable_unprepare, + clk); + if (ret) + goto err_out; + uartclk = clk_get_rate(clk); } @@ -988,7 +997,7 @@ static int sccnxp_probe(struct platform_device *pdev) uart_unregister_driver(&s->uart); err_out: if (!IS_ERR(s->regulator)) - return regulator_disable(s->regulator); + regulator_disable(s->regulator); return ret; } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 5aacea1..3e865db 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -190,8 +190,10 @@ static void wdm_in_callback(struct urb *urb) /* * only set a new error if there is no previous error. * Errors are only cleared during read/open + * Avoid propagating -EPIPE (stall) to userspace since it is + * better handled as an empty read */ - if (desc->rerr == 0) + if (desc->rerr == 0 && status != -EPIPE) desc->rerr = status; if (length + desc->length > desc->wMaxCommand) { diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 4be52c6..68b54bd 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -643,15 +643,23 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, } else if (header->bDescriptorType == USB_DT_INTERFACE_ASSOCIATION) { + struct usb_interface_assoc_descriptor *d; + + d = (struct usb_interface_assoc_descriptor *)header; + if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) { + dev_warn(ddev, + "config %d has an invalid interface association descriptor of length %d, skipping\n", + cfgno, d->bLength); + continue; + } + if (iad_num == USB_MAXIADS) { dev_warn(ddev, "found more Interface " "Association Descriptors " "than allocated for in " "configuration %d\n", cfgno); } else { - config->intf_assoc[iad_num] = - (struct usb_interface_assoc_descriptor - *)header; + config->intf_assoc[iad_num] = d; iad_num++; } @@ -852,7 +860,7 @@ int usb_get_configuration(struct usb_device *dev) } if (dev->quirks & USB_QUIRK_DELAY_INIT) - msleep(100); + msleep(200); result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 318bb3b..4664e54 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -140,6 +140,9 @@ module_param(usbfs_memory_mb, uint, 0644); MODULE_PARM_DESC(usbfs_memory_mb, "maximum MB allowed for usbfs buffers (0 = no limit)"); +/* Hard limit, necessary to avoid arithmetic overflow */ +#define USBFS_XFER_MAX (UINT_MAX / 2 - 1000000) + static atomic64_t usbfs_memory_usage; /* Total memory currently allocated */ /* Check whether it's okay to allocate more memory for a transfer */ @@ -1460,6 +1463,8 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb USBDEVFS_URB_ZERO_PACKET | USBDEVFS_URB_NO_INTERRUPT)) return -EINVAL; + if ((unsigned int)uurb->buffer_length >= USBFS_XFER_MAX) + return -EINVAL; if (uurb->buffer_length > 0 && !uurb->buffer) return -EINVAL; if (!(uurb->type == USBDEVFS_URB_TYPE_CONTROL && @@ -1571,7 +1576,11 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb totlen += isopkt[u].length; } u *= sizeof(struct usb_iso_packet_descriptor); - uurb->buffer_length = totlen; + if (totlen <= uurb->buffer_length) + uurb->buffer_length = totlen; + else + WARN_ONCE(1, "uurb->buffer_length is too short %d vs %d", + totlen, uurb->buffer_length); break; default: diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 41eaf0b..b5c7336 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4838,7 +4838,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, goto loop; if (udev->quirks & USB_QUIRK_DELAY_INIT) - msleep(1000); + msleep(2000); /* consecutive bus-powered hubs aren't reliable; they can * violate the voltage drop budget. if the new child has diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 4c38ea4..371a07d8 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -2069,6 +2069,10 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, elength = 1; goto next_desc; } + if ((buflen < elength) || (elength < 3)) { + dev_err(&intf->dev, "invalid descriptor buffer length\n"); + break; + } if (buffer[1] != USB_DT_CS_INTERFACE) { dev_err(&intf->dev, "skipping garbage\n"); goto next_desc; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 4cef7d4..a26d1fd 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -177,6 +177,7 @@ static const struct of_device_id of_dwc3_simple_match[] = { { .compatible = "rockchip,rk3399-dwc3" }, { .compatible = "xlnx,zynqmp-dwc3" }, { .compatible = "cavium,octeon-7130-usb-uctl" }, + { .compatible = "sprd,sc9860-dwc3" }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, of_dwc3_simple_match); diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 827e376..75e6cb0 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -990,6 +990,8 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, DWC3_TRBCTL_CONTROL_DATA, true); + req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, maxpacket - rem, @@ -1015,6 +1017,8 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, DWC3_TRBCTL_CONTROL_DATA, true); + req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, 0, DWC3_TRBCTL_CONTROL_DATA, @@ -1029,6 +1033,9 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, DWC3_TRBCTL_CONTROL_DATA, false); + + req->trb = &dwc->ep0_trb[dep->trb_enqueue]; + ret = dwc3_ep0_start_trans(dep); } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 9990944..8b34258 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -46,7 +46,8 @@ static void ffs_data_get(struct ffs_data *ffs); static void ffs_data_put(struct ffs_data *ffs); /* Creates new ffs_data object. */ -static struct ffs_data *__must_check ffs_data_new(void) __attribute__((malloc)); +static struct ffs_data *__must_check ffs_data_new(const char *dev_name) + __attribute__((malloc)); /* Opened counter handling. */ static void ffs_data_opened(struct ffs_data *ffs); @@ -780,11 +781,12 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, struct usb_request *req) { struct ffs_io_data *io_data = req->context; + struct ffs_data *ffs = io_data->ffs; ENTER(); INIT_WORK(&io_data->work, ffs_user_copy_worker); - schedule_work(&io_data->work); + queue_work(ffs->io_completion_wq, &io_data->work); } static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile) @@ -1500,7 +1502,7 @@ ffs_fs_mount(struct file_system_type *t, int flags, if (unlikely(ret < 0)) return ERR_PTR(ret); - ffs = ffs_data_new(); + ffs = ffs_data_new(dev_name); if (unlikely(!ffs)) return ERR_PTR(-ENOMEM); ffs->file_perms = data.perms; @@ -1610,6 +1612,7 @@ static void ffs_data_put(struct ffs_data *ffs) BUG_ON(waitqueue_active(&ffs->ev.waitq) || waitqueue_active(&ffs->ep0req_completion.wait) || waitqueue_active(&ffs->wait)); + destroy_workqueue(ffs->io_completion_wq); kfree(ffs->dev_name); kfree(ffs); } @@ -1642,7 +1645,7 @@ static void ffs_data_closed(struct ffs_data *ffs) ffs_data_put(ffs); } -static struct ffs_data *ffs_data_new(void) +static struct ffs_data *ffs_data_new(const char *dev_name) { struct ffs_data *ffs = kzalloc(sizeof *ffs, GFP_KERNEL); if (unlikely(!ffs)) @@ -1650,6 +1653,12 @@ static struct ffs_data *ffs_data_new(void) ENTER(); + ffs->io_completion_wq = alloc_ordered_workqueue("%s", 0, dev_name); + if (!ffs->io_completion_wq) { + kfree(ffs); + return NULL; + } + refcount_set(&ffs->ref, 1); atomic_set(&ffs->opened, 0); ffs->state = FFS_READ_DESCRIPTORS; diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index d6bd024..5153e29 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -307,8 +307,6 @@ struct fsg_common { struct completion thread_notifier; struct task_struct *thread_task; - /* Callback functions. */ - const struct fsg_operations *ops; /* Gadget's private data. */ void *private_data; @@ -2438,6 +2436,7 @@ static void handle_exception(struct fsg_common *common) static int fsg_main_thread(void *common_) { struct fsg_common *common = common_; + int i; /* * Allow the thread to be killed by a signal, but set the signal mask @@ -2476,21 +2475,16 @@ static int fsg_main_thread(void *common_) common->thread_task = NULL; spin_unlock_irq(&common->lock); - if (!common->ops || !common->ops->thread_exits - || common->ops->thread_exits(common) < 0) { - int i; + /* Eject media from all LUNs */ - down_write(&common->filesem); - for (i = 0; i < ARRAY_SIZE(common->luns); i++) { - struct fsg_lun *curlun = common->luns[i]; - if (!curlun || !fsg_lun_is_open(curlun)) - continue; + down_write(&common->filesem); + for (i = 0; i < ARRAY_SIZE(common->luns); i++) { + struct fsg_lun *curlun = common->luns[i]; + if (curlun && fsg_lun_is_open(curlun)) fsg_lun_close(curlun); - curlun->unit_attention_data = SS_MEDIUM_NOT_PRESENT; - } - up_write(&common->filesem); } + up_write(&common->filesem); /* Let fsg_unbind() know the thread has exited */ complete_and_exit(&common->thread_notifier, 0); @@ -2681,13 +2675,6 @@ void fsg_common_remove_luns(struct fsg_common *common) } EXPORT_SYMBOL_GPL(fsg_common_remove_luns); -void fsg_common_set_ops(struct fsg_common *common, - const struct fsg_operations *ops) -{ - common->ops = ops; -} -EXPORT_SYMBOL_GPL(fsg_common_set_ops); - void fsg_common_free_buffers(struct fsg_common *common) { _fsg_common_free_buffers(common->buffhds, common->fsg_num_buffers); diff --git a/drivers/usb/gadget/function/f_mass_storage.h b/drivers/usb/gadget/function/f_mass_storage.h index d390231..dc05ca0 100644 --- a/drivers/usb/gadget/function/f_mass_storage.h +++ b/drivers/usb/gadget/function/f_mass_storage.h @@ -60,17 +60,6 @@ struct fsg_module_parameters { struct fsg_common; /* FSF callback functions */ -struct fsg_operations { - /* - * Callback function to call when thread exits. If no - * callback is set or it returns value lower then zero MSF - * will force eject all LUNs it operates on (including those - * marked as non-removable or with prevent_medium_removal flag - * set). - */ - int (*thread_exits)(struct fsg_common *common); -}; - struct fsg_lun_opts { struct config_group group; struct fsg_lun *lun; @@ -142,9 +131,6 @@ void fsg_common_remove_lun(struct fsg_lun *lun); void fsg_common_remove_luns(struct fsg_common *common); -void fsg_common_set_ops(struct fsg_common *common, - const struct fsg_operations *ops); - int fsg_common_create_lun(struct fsg_common *common, struct fsg_lun_config *cfg, unsigned int id, const char *name, const char **name_pfx); diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 8df244f..ea0da35a 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -555,6 +555,7 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) size_t size; /* Amount of data in a TX request. */ size_t bytes_copied = 0; struct usb_request *req; + int value; DBG(dev, "printer_write trying to send %d bytes\n", (int)len); @@ -634,7 +635,11 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) return -EAGAIN; } - if (usb_ep_queue(dev->in_ep, req, GFP_ATOMIC)) { + /* here, we unlock, and only unlock, to avoid deadlock. */ + spin_unlock(&dev->lock); + value = usb_ep_queue(dev->in_ep, req, GFP_ATOMIC); + spin_lock(&dev->lock); + if (value) { list_add(&req->list, &dev->tx_reqs); spin_unlock_irqrestore(&dev->lock, flags); mutex_unlock(&dev->lock_printer_io); diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h index 540f1c4..79f70eb 100644 --- a/drivers/usb/gadget/function/u_fs.h +++ b/drivers/usb/gadget/function/u_fs.h @@ -279,6 +279,7 @@ struct ffs_data { } file_perms; struct eventfd_ctx *ffs_eventfd; + struct workqueue_struct *io_completion_wq; bool no_disconnect; struct work_struct reset_work; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 684900f..5c28bee 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -28,7 +28,7 @@ #include <linux/aio.h> #include <linux/uio.h> #include <linux/refcount.h> - +#include <linux/delay.h> #include <linux/device.h> #include <linux/moduleparam.h> @@ -116,6 +116,7 @@ enum ep0_state { struct dev_data { spinlock_t lock; refcount_t count; + int udc_usage; enum ep0_state state; /* P: lock */ struct usb_gadgetfs_event event [N_EVENT]; unsigned ev_next; @@ -513,9 +514,9 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } - spin_unlock(&epdata->dev->lock); usb_ep_free_request(ep, req); + spin_unlock(&epdata->dev->lock); put_ep(epdata); } @@ -939,9 +940,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) struct usb_request *req = dev->req; if ((retval = setup_req (ep, req, 0)) == 0) { + ++dev->udc_usage; spin_unlock_irq (&dev->lock); retval = usb_ep_queue (ep, req, GFP_KERNEL); spin_lock_irq (&dev->lock); + --dev->udc_usage; } dev->state = STATE_DEV_CONNECTED; @@ -983,11 +986,14 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) retval = -EIO; else { len = min (len, (size_t)dev->req->actual); -// FIXME don't call this with the spinlock held ... + ++dev->udc_usage; + spin_unlock_irq(&dev->lock); if (copy_to_user (buf, dev->req->buf, len)) retval = -EFAULT; else retval = len; + spin_lock_irq(&dev->lock); + --dev->udc_usage; clean_req (dev->gadget->ep0, dev->req); /* NOTE userspace can't yet choose to stall */ } @@ -1131,6 +1137,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) retval = setup_req (dev->gadget->ep0, dev->req, len); if (retval == 0) { dev->state = STATE_DEV_CONNECTED; + ++dev->udc_usage; spin_unlock_irq (&dev->lock); if (copy_from_user (dev->req->buf, buf, len)) retval = -EFAULT; @@ -1142,6 +1149,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) GFP_KERNEL); } spin_lock_irq(&dev->lock); + --dev->udc_usage; if (retval < 0) { clean_req (dev->gadget->ep0, dev->req); } else @@ -1243,9 +1251,21 @@ static long dev_ioctl (struct file *fd, unsigned code, unsigned long value) struct usb_gadget *gadget = dev->gadget; long ret = -ENOTTY; - if (gadget->ops->ioctl) + spin_lock_irq(&dev->lock); + if (dev->state == STATE_DEV_OPENED || + dev->state == STATE_DEV_UNBOUND) { + /* Not bound to a UDC */ + } else if (gadget->ops->ioctl) { + ++dev->udc_usage; + spin_unlock_irq(&dev->lock); + ret = gadget->ops->ioctl (gadget, code, value); + spin_lock_irq(&dev->lock); + --dev->udc_usage; + } + spin_unlock_irq(&dev->lock); + return ret; } @@ -1463,10 +1483,12 @@ delegate: if (value < 0) break; + ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, GFP_KERNEL); spin_lock (&dev->lock); + --dev->udc_usage; if (value < 0) { clean_req (gadget->ep0, dev->req); break; @@ -1490,8 +1512,12 @@ delegate: req->length = value; req->zero = value < w_length; + ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); + spin_lock(&dev->lock); + --dev->udc_usage; + spin_unlock(&dev->lock); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; @@ -1518,21 +1544,24 @@ static void destroy_ep_files (struct dev_data *dev) /* break link to FS */ ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles); list_del_init (&ep->epfiles); + spin_unlock_irq (&dev->lock); + dentry = ep->dentry; ep->dentry = NULL; parent = d_inode(dentry->d_parent); /* break link to controller */ + mutex_lock(&ep->lock); if (ep->state == STATE_EP_ENABLED) (void) usb_ep_disable (ep->ep); ep->state = STATE_EP_UNBOUND; usb_ep_free_request (ep->ep, ep->req); ep->ep = NULL; + mutex_unlock(&ep->lock); + wake_up (&ep->wait); put_ep (ep); - spin_unlock_irq (&dev->lock); - /* break link to dcache */ inode_lock(parent); d_delete (dentry); @@ -1603,6 +1632,11 @@ gadgetfs_unbind (struct usb_gadget *gadget) spin_lock_irq (&dev->lock); dev->state = STATE_DEV_UNBOUND; + while (dev->udc_usage > 0) { + spin_unlock_irq(&dev->lock); + usleep_range(1000, 2000); + spin_lock_irq(&dev->lock); + } spin_unlock_irq (&dev->lock); destroy_ep_files (dev); diff --git a/drivers/usb/gadget/legacy/mass_storage.c b/drivers/usb/gadget/legacy/mass_storage.c index e99ab57..fcba597 100644 --- a/drivers/usb/gadget/legacy/mass_storage.c +++ b/drivers/usb/gadget/legacy/mass_storage.c @@ -107,15 +107,6 @@ static unsigned int fsg_num_buffers = CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS; FSG_MODULE_PARAMETERS(/* no prefix */, mod_data); -static unsigned long msg_registered; -static void msg_cleanup(void); - -static int msg_thread_exits(struct fsg_common *common) -{ - msg_cleanup(); - return 0; -} - static int msg_do_config(struct usb_configuration *c) { struct fsg_opts *opts; @@ -154,9 +145,6 @@ static struct usb_configuration msg_config_driver = { static int msg_bind(struct usb_composite_dev *cdev) { - static const struct fsg_operations ops = { - .thread_exits = msg_thread_exits, - }; struct fsg_opts *opts; struct fsg_config config; int status; @@ -173,8 +161,6 @@ static int msg_bind(struct usb_composite_dev *cdev) if (status) goto fail; - fsg_common_set_ops(opts->common, &ops); - status = fsg_common_set_cdev(opts->common, cdev, config.can_stall); if (status) goto fail_set_cdev; @@ -256,18 +242,12 @@ MODULE_LICENSE("GPL"); static int __init msg_init(void) { - int ret; - - ret = usb_composite_probe(&msg_driver); - set_bit(0, &msg_registered); - - return ret; + return usb_composite_probe(&msg_driver); } module_init(msg_init); -static void msg_cleanup(void) +static void __exit msg_cleanup(void) { - if (test_and_clear_bit(0, &msg_registered)) - usb_composite_unregister(&msg_driver); + usb_composite_unregister(&msg_driver); } module_exit(msg_cleanup); diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig index 7cd5c96..1e95670 100644 --- a/drivers/usb/gadget/udc/Kconfig +++ b/drivers/usb/gadget/udc/Kconfig @@ -273,6 +273,7 @@ config USB_SNP_CORE config USB_SNP_UDC_PLAT tristate "Synopsys USB 2.0 Device controller" depends on USB_GADGET && OF && HAS_DMA + depends on EXTCON || EXTCON=n select USB_GADGET_DUALSPEED select USB_SNP_CORE default ARCH_BCM_IPROC diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 98d7140..a884c02 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -29,6 +29,8 @@ #include <linux/of_gpio.h> #include "atmel_usba_udc.h" +#define USBA_VBUS_IRQFLAGS (IRQF_ONESHOT \ + | IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING) #ifdef CONFIG_USB_GADGET_DEBUG_FS #include <linux/debugfs.h> @@ -2361,7 +2363,7 @@ static int usba_udc_probe(struct platform_device *pdev) IRQ_NOAUTOEN); ret = devm_request_threaded_irq(&pdev->dev, gpio_to_irq(udc->vbus_pin), NULL, - usba_vbus_irq_thread, IRQF_ONESHOT, + usba_vbus_irq_thread, USBA_VBUS_IRQFLAGS, "atmel_usba_udc", udc); if (ret) { udc->vbus_pin = -ENODEV; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 75c51ca..d41d07a 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1320,8 +1320,7 @@ static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *dri udc->dev.driver = &driver->driver; udc->gadget->dev.driver = &driver->driver; - if (driver->max_speed < udc->gadget->max_speed) - usb_gadget_udc_set_speed(udc, driver->max_speed); + usb_gadget_udc_set_speed(udc, driver->max_speed); ret = driver->bind(udc->gadget, driver); if (ret) diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index a030d79..b17618a 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -237,6 +237,8 @@ struct dummy_hcd { struct usb_device *udev; struct list_head urbp_list; + struct urbp *next_frame_urbp; + u32 stream_en_ep; u8 num_stream[30 / 2]; @@ -253,11 +255,13 @@ struct dummy { */ struct dummy_ep ep[DUMMY_ENDPOINTS]; int address; + int callback_usage; struct usb_gadget gadget; struct usb_gadget_driver *driver; struct dummy_request fifo_req; u8 fifo_buf[FIFO_SIZE]; u16 devstatus; + unsigned ints_enabled:1; unsigned udc_suspended:1; unsigned pullup:1; @@ -375,11 +379,10 @@ static void set_link_state_by_speed(struct dummy_hcd *dum_hcd) USB_PORT_STAT_CONNECTION) == 0) dum_hcd->port_status |= (USB_PORT_STAT_C_CONNECTION << 16); - if ((dum_hcd->port_status & - USB_PORT_STAT_ENABLE) == 1 && - (dum_hcd->port_status & - USB_SS_PORT_LS_U0) == 1 && - dum_hcd->rh_state != DUMMY_RH_SUSPENDED) + if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) && + (dum_hcd->port_status & + USB_PORT_STAT_LINK_STATE) == USB_SS_PORT_LS_U0 && + dum_hcd->rh_state != DUMMY_RH_SUSPENDED) dum_hcd->active = 1; } } else { @@ -440,18 +443,27 @@ static void set_link_state(struct dummy_hcd *dum_hcd) (~dum_hcd->old_status) & dum_hcd->port_status; /* Report reset and disconnect events to the driver */ - if (dum->driver && (disconnect || reset)) { + if (dum->ints_enabled && (disconnect || reset)) { stop_activity(dum); + ++dum->callback_usage; + spin_unlock(&dum->lock); if (reset) usb_gadget_udc_reset(&dum->gadget, dum->driver); else dum->driver->disconnect(&dum->gadget); + spin_lock(&dum->lock); + --dum->callback_usage; } - } else if (dum_hcd->active != dum_hcd->old_active) { + } else if (dum_hcd->active != dum_hcd->old_active && + dum->ints_enabled) { + ++dum->callback_usage; + spin_unlock(&dum->lock); if (dum_hcd->old_active && dum->driver->suspend) dum->driver->suspend(&dum->gadget); else if (!dum_hcd->old_active && dum->driver->resume) dum->driver->resume(&dum->gadget); + spin_lock(&dum->lock); + --dum->callback_usage; } dum_hcd->old_status = dum_hcd->port_status; @@ -972,8 +984,11 @@ static int dummy_udc_start(struct usb_gadget *g, * can't enumerate without help from the driver we're binding. */ + spin_lock_irq(&dum->lock); dum->devstatus = 0; dum->driver = driver; + dum->ints_enabled = 1; + spin_unlock_irq(&dum->lock); return 0; } @@ -984,6 +999,16 @@ static int dummy_udc_stop(struct usb_gadget *g) struct dummy *dum = dum_hcd->dum; spin_lock_irq(&dum->lock); + dum->ints_enabled = 0; + stop_activity(dum); + + /* emulate synchronize_irq(): wait for callbacks to finish */ + while (dum->callback_usage > 0) { + spin_unlock_irq(&dum->lock); + usleep_range(1000, 2000); + spin_lock_irq(&dum->lock); + } + dum->driver = NULL; spin_unlock_irq(&dum->lock); @@ -1037,7 +1062,12 @@ static int dummy_udc_probe(struct platform_device *pdev) memzero_explicit(&dum->gadget, sizeof(struct usb_gadget)); dum->gadget.name = gadget_name; dum->gadget.ops = &dummy_ops; - dum->gadget.max_speed = USB_SPEED_SUPER; + if (mod_data.is_super_speed) + dum->gadget.max_speed = USB_SPEED_SUPER; + else if (mod_data.is_high_speed) + dum->gadget.max_speed = USB_SPEED_HIGH; + else + dum->gadget.max_speed = USB_SPEED_FULL; dum->gadget.dev.parent = &pdev->dev; init_dummy_udc_hw(dum); @@ -1246,6 +1276,8 @@ static int dummy_urb_enqueue( list_add_tail(&urbp->urbp_list, &dum_hcd->urbp_list); urb->hcpriv = urbp; + if (!dum_hcd->next_frame_urbp) + dum_hcd->next_frame_urbp = urbp; if (usb_pipetype(urb->pipe) == PIPE_CONTROL) urb->error_count = 1; /* mark as a new urb */ @@ -1521,6 +1553,8 @@ static struct dummy_ep *find_endpoint(struct dummy *dum, u8 address) if (!is_active((dum->gadget.speed == USB_SPEED_SUPER ? dum->ss_hcd : dum->hs_hcd))) return NULL; + if (!dum->ints_enabled) + return NULL; if ((address & ~USB_DIR_IN) == 0) return &dum->ep[0]; for (i = 1; i < DUMMY_ENDPOINTS; i++) { @@ -1762,6 +1796,7 @@ static void dummy_timer(unsigned long _dum_hcd) spin_unlock_irqrestore(&dum->lock, flags); return; } + dum_hcd->next_frame_urbp = NULL; for (i = 0; i < DUMMY_ENDPOINTS; i++) { if (!ep_info[i].name) @@ -1778,6 +1813,10 @@ restart: int type; int status = -EINPROGRESS; + /* stop when we reach URBs queued after the timer interrupt */ + if (urbp == dum_hcd->next_frame_urbp) + break; + urb = urbp->urb; if (urb->unlinked) goto return_urb; @@ -1857,10 +1896,12 @@ restart: * until setup() returns; no reentrancy issues etc. */ if (value > 0) { + ++dum->callback_usage; spin_unlock(&dum->lock); value = dum->driver->setup(&dum->gadget, &setup); spin_lock(&dum->lock); + --dum->callback_usage; if (value >= 0) { /* no delays (max 64KB data stage) */ @@ -2561,8 +2602,6 @@ static struct hc_driver dummy_hcd = { .product_desc = "Dummy host controller", .hcd_priv_size = sizeof(struct dummy_hcd), - .flags = HCD_USB3 | HCD_SHARED, - .reset = dummy_setup, .start = dummy_start, .stop = dummy_stop, @@ -2591,8 +2630,12 @@ static int dummy_hcd_probe(struct platform_device *pdev) dev_info(&pdev->dev, "%s, driver " DRIVER_VERSION "\n", driver_desc); dum = *((void **)dev_get_platdata(&pdev->dev)); - if (!mod_data.is_super_speed) + if (mod_data.is_super_speed) + dummy_hcd.flags = HCD_USB3 | HCD_SHARED; + else if (mod_data.is_high_speed) dummy_hcd.flags = HCD_USB2; + else + dummy_hcd.flags = HCD_USB11; hs_hcd = usb_create_hcd(&dummy_hcd, &pdev->dev, dev_name(&pdev->dev)); if (!hs_hcd) return -ENOMEM; diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index df37c1e..63a2061 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1038,7 +1038,7 @@ static int usb3_write_pipe(struct renesas_usb3_ep *usb3_ep, usb3_ep->ep.maxpacket); u8 *buf = usb3_req->req.buf + usb3_req->req.actual; u32 tmp = 0; - bool is_last; + bool is_last = !len ? true : false; if (usb3_wait_pipe_status(usb3_ep, PX_STA_BUFSTS) < 0) return -EBUSY; @@ -1059,7 +1059,8 @@ static int usb3_write_pipe(struct renesas_usb3_ep *usb3_ep, usb3_write(usb3, tmp, fifo_reg); } - is_last = usb3_is_transfer_complete(usb3_ep, usb3_req); + if (!is_last) + is_last = usb3_is_transfer_complete(usb3_ep, usb3_req); /* Send the data */ usb3_set_px_con_send(usb3_ep, len, is_last); @@ -1150,7 +1151,8 @@ static void usb3_start_pipe0(struct renesas_usb3_ep *usb3_ep, usb3_set_p0_con_for_ctrl_read_data(usb3); } else { usb3_clear_bit(usb3, P0_MOD_DIR, USB3_P0_MOD); - usb3_set_p0_con_for_ctrl_write_data(usb3); + if (usb3_req->req.length) + usb3_set_p0_con_for_ctrl_write_data(usb3); } usb3_p0_xfer(usb3_ep, usb3_req); @@ -2053,7 +2055,16 @@ static u32 usb3_calc_ramarea(int ram_size) static u32 usb3_calc_rammap_val(struct renesas_usb3_ep *usb3_ep, const struct usb_endpoint_descriptor *desc) { - return usb3_ep->rammap_val | PN_RAMMAP_MPKT(usb_endpoint_maxp(desc)); + int i; + const u32 max_packet_array[] = {8, 16, 32, 64, 512}; + u32 mpkt = PN_RAMMAP_MPKT(1024); + + for (i = 0; i < ARRAY_SIZE(max_packet_array); i++) { + if (usb_endpoint_maxp(desc) <= max_packet_array[i]) + mpkt = PN_RAMMAP_MPKT(max_packet_array[i]); + } + + return usb3_ep->rammap_val | mpkt; } static int usb3_enable_pipe_n(struct renesas_usb3_ep *usb3_ep, diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 658d9d1..6dda362 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -447,7 +447,7 @@ static int usb_asmedia_wait_write(struct pci_dev *pdev) if ((value & ASMT_CONTROL_WRITE_BIT) == 0) return 0; - usleep_range(40, 60); + udelay(50); } dev_warn(&pdev->dev, "%s: check_write_ready timeout", __func__); @@ -1022,7 +1022,7 @@ EXPORT_SYMBOL_GPL(usb_disable_xhci_ports); * * Takes care of the handoff between the Pre-OS (i.e. BIOS) and the OS. * It signals to the BIOS that the OS wants control of the host controller, - * and then waits 5 seconds for the BIOS to hand over control. + * and then waits 1 second for the BIOS to hand over control. * If we timeout, assume the BIOS is broken and take control anyway. */ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) @@ -1069,9 +1069,9 @@ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) if (val & XHCI_HC_BIOS_OWNED) { writel(val | XHCI_HC_OS_OWNED, base + ext_cap_offset); - /* Wait for 5 seconds with 10 microsecond polling interval */ + /* Wait for 1 second with 10 microsecond polling interval */ timeout = handshake(base + ext_cap_offset, XHCI_HC_BIOS_OWNED, - 0, 5000, 10); + 0, 1000000, 10); /* Assume a buggy BIOS and take HC ownership anyway */ if (timeout) { @@ -1100,7 +1100,7 @@ hc_init: * operational or runtime registers. Wait 5 seconds and no more. */ timeout = handshake(op_reg_base + XHCI_STS_OFFSET, XHCI_STS_CNR, 0, - 5000, 10); + 5000000, 10); /* Assume a buggy HC and start HC initialization anyway */ if (timeout) { val = readl(op_reg_base + XHCI_STS_OFFSET); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index ad89a6d..da9158f 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -112,7 +112,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, /* If PSI table exists, add the custom speed attributes from it */ if (usb3_1 && xhci->usb3_rhub.psi_count) { - u32 ssp_cap_base, bm_attrib, psi; + u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp; int offset; ssp_cap_base = USB_DT_BOS_SIZE + USB_DT_USB_SS_CAP_SIZE; @@ -139,6 +139,15 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, for (i = 0; i < xhci->usb3_rhub.psi_count; i++) { psi = xhci->usb3_rhub.psi[i]; psi &= ~USB_SSP_SUBLINK_SPEED_RSVD; + psi_exp = XHCI_EXT_PORT_PSIE(psi); + psi_mant = XHCI_EXT_PORT_PSIM(psi); + + /* Shift to Gbps and set SSP Link BIT(14) if 10Gpbs */ + for (; psi_exp < 3; psi_exp++) + psi_mant /= 1000; + if (psi_mant >= 10) + psi |= BIT(14); + if ((psi & PLT_MASK) == PLT_SYM) { /* Symmetric, create SSA RX and TX from one PSI entry */ put_unaligned_le32(psi, &buf[offset]); @@ -1506,9 +1515,6 @@ int xhci_bus_suspend(struct usb_hcd *hcd) t2 |= PORT_WKOC_E | PORT_WKCONN_E; t2 &= ~PORT_WKDISC_E; } - if ((xhci->quirks & XHCI_U2_DISABLE_WAKE) && - (hcd->speed < HCD_USB3)) - t2 &= ~PORT_WAKE_BITS; } else t2 &= ~PORT_WAKE_BITS; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 8071c8f..76f3929 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -54,11 +54,6 @@ #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 #define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 -#define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 -#define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba -#define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb -#define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc - #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 static const char hcd_name[] = "xhci_hcd"; @@ -142,13 +137,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; - if ((pdev->vendor == PCI_VENDOR_ID_AMD) && - ((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1))) - xhci->quirks |= XHCI_U2_DISABLE_WAKE; - if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 163bafd..1cb6eae 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -178,14 +178,18 @@ static int xhci_plat_probe(struct platform_device *pdev) * 2. xhci_plat is child of a device from firmware (dwc3-plat) * 3. xhci_plat is grandchild of a pci device (dwc3-pci) */ - sysdev = &pdev->dev; - if (sysdev->parent && !sysdev->of_node && sysdev->parent->of_node) - sysdev = sysdev->parent; + for (sysdev = &pdev->dev; sysdev; sysdev = sysdev->parent) { + if (is_of_node(sysdev->fwnode) || + is_acpi_device_node(sysdev->fwnode)) + break; #ifdef CONFIG_PCI - else if (sysdev->parent && sysdev->parent->parent && - sysdev->parent->parent->bus == &pci_bus_type) - sysdev = sysdev->parent->parent; + else if (sysdev->bus == &pci_bus_type) + break; #endif + } + + if (!sysdev) + sysdev = &pdev->dev; /* Try to set 64-bit DMA first */ if (WARN_ON(!sysdev->dma_mask)) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b2ff1ff..ee198ea 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1703,7 +1703,8 @@ static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, if (xhci->quirks & XHCI_MTK_HOST) { ret = xhci_mtk_add_ep_quirk(hcd, udev, ep); if (ret < 0) { - xhci_free_endpoint_ring(xhci, virt_dev, ep_index); + xhci_ring_free(xhci, virt_dev->eps[ep_index].new_ring); + virt_dev->eps[ep_index].new_ring = NULL; return ret; } } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 2abaa4d..2b48aa4 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -735,6 +735,8 @@ struct xhci_ep_ctx { #define EP_MAXPSTREAMS(p) (((p) << 10) & EP_MAXPSTREAMS_MASK) /* Endpoint is set up with a Linear Stream Array (vs. Secondary Stream Array) */ #define EP_HAS_LSA (1 << 15) +/* hosts with LEC=1 use bits 31:24 as ESIT high bits. */ +#define CTX_TO_MAX_ESIT_PAYLOAD_HI(p) (((p) >> 24) & 0xff) /* ep_info2 bitmasks */ /* @@ -1681,7 +1683,7 @@ struct xhci_bus_state { static inline unsigned int hcd_index(struct usb_hcd *hcd) { - if (hcd->speed == HCD_USB3) + if (hcd->speed >= HCD_USB3) return 0; else return 1; @@ -1826,7 +1828,7 @@ struct xhci_hcd { /* For controller with a broken Port Disable implementation */ #define XHCI_BROKEN_PORT_PED (1 << 25) #define XHCI_LIMIT_ENDPOINT_INTERVAL_7 (1 << 26) -#define XHCI_U2_DISABLE_WAKE (1 << 27) +/* Reserved. It was XHCI_U2_DISABLE_WAKE */ #define XHCI_ASMEDIA_MODIFY_FLOWCONTROL (1 << 28) unsigned int num_active_eps; @@ -2540,8 +2542,8 @@ static inline const char *xhci_decode_ep_context(u32 info, u32 info2, u64 deq, u8 lsa; u8 hid; - esit = EP_MAX_ESIT_PAYLOAD_HI(info) << 16 | - EP_MAX_ESIT_PAYLOAD_LO(tx_info); + esit = CTX_TO_MAX_ESIT_PAYLOAD_HI(info) << 16 | + CTX_TO_MAX_ESIT_PAYLOAD(tx_info); ep_state = info & EP_STATE_MASK; max_pstr = info & EP_MAXPSTREAMS_MASK; diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index d1af831..68f2690 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -282,11 +282,26 @@ static void usbhsf_fifo_clear(struct usbhs_pipe *pipe, struct usbhs_fifo *fifo) { struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); + int ret = 0; - if (!usbhs_pipe_is_dcp(pipe)) - usbhsf_fifo_barrier(priv, fifo); + if (!usbhs_pipe_is_dcp(pipe)) { + /* + * This driver checks the pipe condition first to avoid -EBUSY + * from usbhsf_fifo_barrier() with about 10 msec delay in + * the interrupt handler if the pipe is RX direction and empty. + */ + if (usbhs_pipe_is_dir_in(pipe)) + ret = usbhs_pipe_is_accessible(pipe); + if (!ret) + ret = usbhsf_fifo_barrier(priv, fifo); + } - usbhs_write(priv, fifo->ctr, BCLR); + /* + * if non-DCP pipe, this driver should set BCLR when + * usbhsf_fifo_barrier() returns 0. + */ + if (!ret) + usbhs_write(priv, fifo->ctr, BCLR); } static int usbhsf_fifo_rcv_len(struct usbhs_priv *priv, diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 1a59f33..a3ccb89 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -834,13 +834,25 @@ Retry_Sense: if (result == USB_STOR_TRANSPORT_GOOD) { srb->result = SAM_STAT_GOOD; srb->sense_buffer[0] = 0x0; + } + + /* + * ATA-passthru commands use sense data to report + * the command completion status, and often devices + * return Check Condition status when nothing is + * wrong. + */ + else if (srb->cmnd[0] == ATA_16 || + srb->cmnd[0] == ATA_12) { + /* leave the data alone */ + } /* * If there was a problem, report an unspecified * hardware error to prevent the higher layers from * entering an infinite retry loop. */ - } else { + else { srb->result = DID_ERROR << 16; if ((sshdr.response_code & 0x72) == 0x72) srb->sense_buffer[1] = HARDWARE_ERROR; diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h index f58caa9..a155cd0 100644 --- a/drivers/usb/storage/uas-detect.h +++ b/drivers/usb/storage/uas-detect.h @@ -9,7 +9,8 @@ static int uas_is_interface(struct usb_host_interface *intf) intf->desc.bInterfaceProtocol == USB_PR_UAS); } -static int uas_find_uas_alt_setting(struct usb_interface *intf) +static struct usb_host_interface *uas_find_uas_alt_setting( + struct usb_interface *intf) { int i; @@ -17,10 +18,10 @@ static int uas_find_uas_alt_setting(struct usb_interface *intf) struct usb_host_interface *alt = &intf->altsetting[i]; if (uas_is_interface(alt)) - return alt->desc.bAlternateSetting; + return alt; } - return -ENODEV; + return NULL; } static int uas_find_endpoints(struct usb_host_interface *alt, @@ -58,14 +59,14 @@ static int uas_use_uas_driver(struct usb_interface *intf, struct usb_device *udev = interface_to_usbdev(intf); struct usb_hcd *hcd = bus_to_hcd(udev->bus); unsigned long flags = id->driver_info; - int r, alt; - + struct usb_host_interface *alt; + int r; alt = uas_find_uas_alt_setting(intf); - if (alt < 0) + if (!alt) return 0; - r = uas_find_endpoints(&intf->altsetting[alt], eps); + r = uas_find_endpoints(alt, eps); if (r < 0) return 0; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index cfb1e3b..63cf981 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -873,14 +873,14 @@ MODULE_DEVICE_TABLE(usb, uas_usb_ids); static int uas_switch_interface(struct usb_device *udev, struct usb_interface *intf) { - int alt; + struct usb_host_interface *alt; alt = uas_find_uas_alt_setting(intf); - if (alt < 0) - return alt; + if (!alt) + return -ENODEV; - return usb_set_interface(udev, - intf->altsetting[0].desc.bInterfaceNumber, alt); + return usb_set_interface(udev, alt->desc.bInterfaceNumber, + alt->desc.bAlternateSetting); } static int uas_configure_endpoints(struct uas_dev_info *devinfo) diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 5a70c33..eb06d88 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1459,6 +1459,13 @@ UNUSUAL_DEV( 0x0bc2, 0x3010, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SANE_SENSE ), +/* Reported by Kris Lindgren <kris.lindgren@gmail.com> */ +UNUSUAL_DEV( 0x0bc2, 0x3332, 0x0000, 0x9999, + "Seagate", + "External", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT ), + UNUSUAL_DEV( 0x0d49, 0x7310, 0x0000, 0x9999, "Maxtor", "USB to SATA", diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c index 35a1e77..9a53912 100644 --- a/drivers/uwb/hwa-rc.c +++ b/drivers/uwb/hwa-rc.c @@ -825,6 +825,8 @@ static int hwarc_probe(struct usb_interface *iface, if (iface->cur_altsetting->desc.bNumEndpoints < 1) return -ENODEV; + if (!usb_endpoint_xfer_int(&iface->cur_altsetting->endpoint[0].desc)) + return -ENODEV; result = -ENOMEM; uwb_rc = uwb_rc_alloc(); diff --git a/drivers/uwb/uwbd.c b/drivers/uwb/uwbd.c index 01c20a2..39dd4ef 100644 --- a/drivers/uwb/uwbd.c +++ b/drivers/uwb/uwbd.c @@ -302,18 +302,22 @@ static int uwbd(void *param) /** Start the UWB daemon */ void uwbd_start(struct uwb_rc *rc) { - rc->uwbd.task = kthread_run(uwbd, rc, "uwbd"); - if (rc->uwbd.task == NULL) + struct task_struct *task = kthread_run(uwbd, rc, "uwbd"); + if (IS_ERR(task)) { + rc->uwbd.task = NULL; printk(KERN_ERR "UWB: Cannot start management daemon; " "UWB won't work\n"); - else + } else { + rc->uwbd.task = task; rc->uwbd.pid = rc->uwbd.task->pid; + } } /* Stop the UWB daemon and free any unprocessed events */ void uwbd_stop(struct uwb_rc *rc) { - kthread_stop(rc->uwbd.task); + if (rc->uwbd.task) + kthread_stop(rc->uwbd.task); uwbd_flush(rc); } diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index 5fbfd9c..5b3d57f 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -169,6 +169,9 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data) static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) { struct pci_bar_info *bar = data; + unsigned int pos = (offset - PCI_BASE_ADDRESS_0) / 4; + const struct resource *res = dev->resource; + u32 mask; if (unlikely(!bar)) { pr_warn(DRV_NAME ": driver data not found for %s\n", @@ -179,7 +182,13 @@ static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) /* A write to obtain the length must happen as a 32-bit write. * This does not (yet) support writing individual bytes */ - if (value == ~0) + if (res[pos].flags & IORESOURCE_IO) + mask = ~PCI_BASE_ADDRESS_IO_MASK; + else if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64)) + mask = 0; + else + mask = ~PCI_BASE_ADDRESS_MEM_MASK; + if ((value | mask) == ~0U) bar->which = 1; else { u32 tmpval; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b51d23f..280384b 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -107,7 +107,8 @@ static void end_compressed_bio_read(struct bio *bio) struct inode *inode; struct page *page; unsigned long index; - int ret; + unsigned int mirror = btrfs_io_bio(bio)->mirror_num; + int ret = 0; if (bio->bi_status) cb->errors = 1; @@ -118,6 +119,21 @@ static void end_compressed_bio_read(struct bio *bio) if (!refcount_dec_and_test(&cb->pending_bios)) goto out; + /* + * Record the correct mirror_num in cb->orig_bio so that + * read-repair can work properly. + */ + ASSERT(btrfs_io_bio(cb->orig_bio)); + btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; + cb->mirror_num = mirror; + + /* + * Some IO in this cb have failed, just skip checksum as there + * is no way it could be correct. + */ + if (cb->errors == 1) + goto csum_failed; + inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5a8933d..899ddae 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -709,7 +709,6 @@ struct btrfs_delayed_root; #define BTRFS_FS_OPEN 5 #define BTRFS_FS_QUOTA_ENABLED 6 #define BTRFS_FS_QUOTA_ENABLING 7 -#define BTRFS_FS_QUOTA_DISABLING 8 #define BTRFS_FS_UPDATE_UUID_TREE_GEN 9 #define BTRFS_FS_CREATING_FREE_SPACE_TREE 10 #define BTRFS_FS_BTREE_ERR 11 diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 487bbe4..dfdab84 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3643,7 +3643,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) u64 flags; do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); - backup_super_roots(fs_info); + + /* + * max_mirrors == 0 indicates we're from commit_transaction, + * not from fsync where the tree roots in fs_info have not + * been consistent on disk. + */ + if (max_mirrors == 0) + backup_super_roots(fs_info); sb = fs_info->super_for_commit; dev_item = &sb->dev_item; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3e5bb0c..12ab19a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3471,8 +3471,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, unsigned int write_flags = 0; unsigned long nr_written = 0; - if (wbc->sync_mode == WB_SYNC_ALL) - write_flags = REQ_SYNC; + write_flags = wbc_to_write_flags(wbc); trace___extent_writepage(page, inode, wbc); @@ -3718,7 +3717,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, unsigned long i, num_pages; unsigned long bio_flags = 0; unsigned long start, end; - unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META; + unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META; int ret = 0; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); @@ -4063,9 +4062,6 @@ static void flush_epd_write_bio(struct extent_page_data *epd) if (epd->bio) { int ret; - bio_set_op_attrs(epd->bio, REQ_OP_WRITE, - epd->sync_io ? REQ_SYNC : 0); - ret = submit_one_bio(epd->bio, 0, epd->bio_flags); BUG_ON(ret < 0); /* -ENOMEM */ epd->bio = NULL; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 128f3e5..d94e3f6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -135,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, const u64 offset, const u64 bytes) { + unsigned long index = offset >> PAGE_SHIFT; + unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + index++; + if (!page) + continue; + ClearPagePrivate2(page); + put_page(page); + } return __endio_write_update_ordered(inode, offset + PAGE_SIZE, bytes - PAGE_SIZE, false); } @@ -8357,11 +8369,8 @@ static void btrfs_endio_direct_read(struct bio *bio) struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); - if (!err) - bio->bi_status = 0; - } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@ -8369,7 +8378,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_status = bio->bi_status; + dio_bio->bi_status = err; dio_end_io(dio_bio); if (io_bio->end_io) @@ -8387,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; + u64 last_offset; int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { @@ -8398,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode, } again: + last_offset = ordered_offset; ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, ordered_bytes, @@ -8409,6 +8420,12 @@ again: btrfs_queue_work(wq, &ordered->work); out_test: /* + * If btrfs_dec_test_ordered_pending does not find any ordered extent + * in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; + /* * our bio might span multiple ordered extents. If we haven't * completed the accounting for the whole dio, go back and try again */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d6715c2..6c7a49f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2773,9 +2773,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, } mutex_unlock(&fs_devices->device_list_mutex); - fi_args->nodesize = fs_info->super_copy->nodesize; - fi_args->sectorsize = fs_info->super_copy->sectorsize; - fi_args->clone_alignment = fs_info->super_copy->sectorsize; + fi_args->nodesize = fs_info->nodesize; + fi_args->sectorsize = fs_info->sectorsize; + fi_args->clone_alignment = fs_info->sectorsize; if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; @@ -3032,7 +3032,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, out: if (ret) btrfs_cmp_data_free(cmp); - return 0; + return ret; } static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp) @@ -4061,6 +4061,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } + if (!is_fstree(new_root->objectid)) { + ret = -ENOENT; + goto out; + } path = btrfs_alloc_path(); if (!path) { diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5c8b61c..e172d48 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -807,7 +807,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, } ret = 0; out: - set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags); btrfs_free_path(path); return ret; } @@ -953,7 +952,6 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, if (!fs_info->quota_root) goto out; clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -1307,6 +1305,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, } } ret = del_qgroup_item(trans, quota_root, qgroupid); + if (ret && ret != -ENOENT) + goto out; while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -2086,8 +2086,6 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags)) set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags)) - clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); spin_lock(&fs_info->qgroup_lock); while (!list_empty(&fs_info->dirty_qgroups)) { diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3a49a3c..9841fae 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2400,11 +2400,11 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->node = NULL; reloc_root->commit_root = NULL; - __del_reloc_root(reloc_root); } } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 32b043e..8fd195c 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2630,7 +2630,7 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino) } else { btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ad7f4ba..c800d06 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4181,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct extent_map *em, *n; struct list_head extents; struct extent_map_tree *tree = &inode->extent_tree; + u64 logged_start, logged_end; u64 test_gen; int ret = 0; int num = 0; @@ -4190,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, down_write(&inode->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; + logged_start = start; + logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); - /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we @@ -4208,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, if (em->generation <= test_gen) continue; + + if (em->start < logged_start) + logged_start = em->start; + if ((em->start + em->len - 1) > logged_end) + logged_end = em->start + em->len - 1; + /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); set_bit(EXTENT_FLAG_LOGGING, &em->flags); @@ -4216,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - btrfs_get_logged_extents(inode, logged_list, start, end); + btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end); /* * Some ordered extents started by fsync might have completed * before we could collect them into the list logged_list, which diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0e8f16c..b397375 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6166,7 +6166,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, map_length = length; btrfs_bio_counter_inc_blocked(fs_info); - ret = __btrfs_map_block(fs_info, bio_op(bio), logical, + ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, &bbio, mirror_num, 1); if (ret) { btrfs_bio_counter_dec(fs_info); diff --git a/fs/direct-io.c b/fs/direct-io.c index 5fa2211..62cf812 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -229,6 +229,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) { loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; + int err; /* * AIO submission can race with bio completion to get here while @@ -258,8 +259,22 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) if (ret == 0) ret = transferred; + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (ret > 0 && dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages) { + err = invalidate_inode_pages2_range(dio->inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + ret - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + if (dio->end_io) { - int err; // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); @@ -304,6 +319,7 @@ static void dio_bio_end_aio(struct bio *bio) struct dio *dio = bio->bi_private; unsigned long remaining; unsigned long flags; + bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); @@ -315,7 +331,19 @@ static void dio_bio_end_aio(struct bio *bio) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - if (dio->result && dio->defer_completion) { + /* + * Defer completion when defer_completion is set or + * when the inode has pages mapped and this is AIO write. + * We need to invalidate those pages because there is a + * chance they contain stale data in the case buffered IO + * went in between AIO submission and completion into the + * same region. + */ + if (dio->result) + defer_completion = dio->defer_completion || + (dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages); + if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); @@ -1210,10 +1238,19 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ - if (dio->is_async && iov_iter_rw(iter) == WRITE && - ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host))) { - retval = dio_set_defer_completion(dio); + if (dio->is_async && iov_iter_rw(iter) == WRITE) { + retval = 0; + if ((iocb->ki_filp->f_flags & O_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host)) + retval = dio_set_defer_completion(dio); + else if (!dio->inode->i_sb->s_dio_done_wq) { + /* + * In case of AIO write racing with buffered read we + * need to defer completion. We can't decide this now, + * however the workqueue needs to be initialized here. + */ + retval = sb_init_dio_done_wq(dio->inode->i_sb); + } if (retval) { /* * We grab i_mutex only for reads so we don't have diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 98e845b..11066d8 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1945,13 +1945,9 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) { struct gfs2_glock_iter *gi = seq->private; loff_t n = *pos; - int ret; - - if (gi->last_pos <= *pos) - n = (*pos - gi->last_pos); - ret = rhashtable_walk_start(&gi->hti); - if (ret) + rhashtable_walk_enter(&gl_hash_table, &gi->hti); + if (rhashtable_walk_start(&gi->hti) != 0) return NULL; do { @@ -1959,6 +1955,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) } while (gi->gl && n--); gi->last_pos = *pos; + return gi->gl; } @@ -1970,6 +1967,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr, (*pos)++; gi->last_pos = *pos; gfs2_glock_iter_next(gi); + return gi->gl; } @@ -1980,6 +1978,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) gi->gl = NULL; rhashtable_walk_stop(&gi->hti); + rhashtable_walk_exit(&gi->hti); } static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) @@ -2042,12 +2041,10 @@ static int __gfs2_glocks_open(struct inode *inode, struct file *file, struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - rhashtable_walk_enter(&gl_hash_table, &gi->hti); } return ret; } @@ -2063,7 +2060,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; - rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } @@ -713,8 +713,24 @@ struct iomap_dio { static ssize_t iomap_dio_complete(struct iomap_dio *dio) { struct kiocb *iocb = dio->iocb; + struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (!dio->error && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + ret = invalidate_inode_pages2_range(inode->i_mapping, + iocb->ki_pos >> PAGE_SHIFT, + (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + } + if (dio->end_io) { ret = dio->end_io(iocb, dio->error ? dio->error : dio->size, @@ -993,6 +1009,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, WARN_ON_ONCE(ret); ret = 0; + if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; + } + inode_dio_begin(inode); blk_start_plug(&plug); @@ -1015,13 +1038,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret < 0) iomap_dio_set_error(dio, ret); - if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && - !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - iomap_dio_set_error(dio, ret); - } - if (!atomic_dec_and_test(&dio->ref)) { if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; @@ -1042,19 +1058,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, ret = iomap_dio_complete(dio); - /* - * Try again to invalidate clean pages which might have been cached by - * non-direct readahead, or faulted in by get_user_pages() if the source - * of the write was an mmap'ed region of the file we're writing. Either - * one is a pretty crazy thing to do, so we don't support it 100%. If - * this invalidation fails, tough, the write still worked... - */ - if (iov_iter_rw(iter) == WRITE) { - int err = invalidate_inode_pages2_range(mapping, - start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(err); - } - return ret; out_free_dio: diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index db692f5..447a24d 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -514,9 +514,11 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) if (sbi->s_fmode != ISOFS_INVALID_MODE) seq_printf(m, ",fmode=%o", sbi->s_fmode); +#ifdef CONFIG_JOLIET if (sbi->s_nls_iocharset && strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); +#endif return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 525157c..77a8eac 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -119,30 +119,25 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) * simple bit tests. */ static const char * const task_state_array[] = { - "R (running)", /* 0 */ - "S (sleeping)", /* 1 */ - "D (disk sleep)", /* 2 */ - "T (stopped)", /* 4 */ - "t (tracing stop)", /* 8 */ - "X (dead)", /* 16 */ - "Z (zombie)", /* 32 */ + + /* states in TASK_REPORT: */ + "R (running)", /* 0x00 */ + "S (sleeping)", /* 0x01 */ + "D (disk sleep)", /* 0x02 */ + "T (stopped)", /* 0x04 */ + "t (tracing stop)", /* 0x08 */ + "X (dead)", /* 0x10 */ + "Z (zombie)", /* 0x20 */ + "P (parked)", /* 0x40 */ + + /* states beyond TASK_REPORT: */ + "I (idle)", /* 0x80 */ }; static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; - - /* - * Parked tasks do not run; they sit in __kthread_parkme(). - * Without this check, we would report them as running, which is - * clearly wrong, so we report them as sleeping instead. - */ - if (tsk->state == TASK_PARKED) - state = TASK_INTERRUPTIBLE; - - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); - - return task_state_array[fls(state)]; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); + return task_state_array[__get_task_state(tsk)]; } static inline int get_task_umask(struct task_struct *tsk) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8381db9..50b0556 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1980,7 +1980,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0, &warn_to[cnt]); if (ret) { + spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); + spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; } } diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index c0187cd..a73e5b3 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -328,12 +328,16 @@ static int v2_write_dquot(struct dquot *dquot) if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); + } else { + down_read(&dqopt->dqio_sem); } ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); if (alloc) up_write(&dqopt->dqio_sem); + else + up_read(&dqopt->dqio_sem); return ret; } diff --git a/fs/read_write.c b/fs/read_write.c index a2b9a47..f0d4b16 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -112,7 +112,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -120,7 +120,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index b008ff3..df3e600 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -156,7 +156,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -216,7 +217,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * counter, we only make the adjustment for AG 0. This assumes that + * there aren't any AGs hungrier for per-AG reservation than AG 0. + */ + if (pag->pag_agno == 0) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 459f4b4f0..044a363 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -49,7 +49,6 @@ #include "xfs_rmap.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_rmap_btree.h" #include "xfs_icache.h" @@ -192,12 +191,8 @@ xfs_bmap_worst_indlen( int maxrecs; /* maximum record count at this level */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t rval; /* return value */ - xfs_filblks_t orig_len; mp = ip->i_mount; - - /* Calculate the worst-case size of the bmbt. */ - orig_len = len; maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); @@ -205,20 +200,12 @@ xfs_bmap_worst_indlen( len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) { - rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) + return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; - break; - } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } - - /* Calculate the worst-case size of the rmapbt. */ - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + - mp->m_rmap_maxlevels; - return rval; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2917260..f18e593 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -343,7 +343,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index cd9a540..bc6c6e1 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1459,7 +1459,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index da14658..2f97c12 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1258,8 +1258,6 @@ xfs_buf_ioapply_map( int size; int offset; - total_nr_pages = bp->b_page_count; - /* skip the pages in the buffer before the start offset */ page_index = 0; offset = *buf_offset; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index bd786a9..eaf86f5 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -347,7 +347,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ebdd0bd..309e26c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -58,7 +58,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int @@ -377,8 +377,6 @@ restart: */ spin_lock(&ip->i_flags_lock); if (iocb->ki_pos > i_size_read(inode)) { - bool zero = false; - spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { @@ -399,7 +397,7 @@ restart: drained_dio = true; goto restart; } - error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); + error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL); if (error) return error; } else @@ -436,7 +434,6 @@ xfs_dio_write_end_io( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); loff_t offset = iocb->ki_pos; - bool update_size = false; int error = 0; trace_xfs_end_io_direct_write(ip, offset, size); @@ -447,6 +444,21 @@ xfs_dio_write_end_io( if (size <= 0) return size; + if (flags & IOMAP_DIO_COW) { + error = xfs_reflink_end_cow(ip, offset, size); + if (error) + return error; + } + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & IOMAP_DIO_UNWRITTEN) + return xfs_iomap_write_unwritten(ip, offset, size, true); + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -461,20 +473,11 @@ xfs_dio_write_end_io( spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) { i_size_write(inode, offset + size); - update_size = true; - } - spin_unlock(&ip->i_flags_lock); - - if (flags & IOMAP_DIO_COW) { - error = xfs_reflink_end_cow(ip, offset, size); - if (error) - return error; - } - - if (flags & IOMAP_DIO_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size); - else if (update_size) + spin_unlock(&ip->i_flags_lock); error = xfs_setfilesize(ip, offset, size); + } else { + spin_unlock(&ip->i_flags_lock); + } return error; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 5599dda..4ec5b7f 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1624,10 +1624,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 6d0f74e..a705f34 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -745,7 +745,7 @@ xfs_iflush_done( */ iip = INODE_ITEM(blip); if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || - lip->li_flags & XFS_LI_FAILED) + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 5049e8a..aa75389 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1088,6 +1088,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1100,7 +1101,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a1909bc..f179bdf 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -829,7 +829,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -840,6 +841,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -899,7 +901,8 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 00db3ec..ee53506 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 2f2dc3c..4246876 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -274,7 +274,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c996f4a..584cf2d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1654,6 +1654,16 @@ xfs_fs_fill_super( "DAX and reflink have not been tested together!"); } + if (mp->m_flags & XFS_MOUNT_DISCARD) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + + if (!blk_queue_discard(q)) { + xfs_warn(mp, "mounting with \"discard\" option, but " + "the device does not support discard"); + mp->m_flags &= ~XFS_MOUNT_DISCARD; + } + } + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp, diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 0504ef8..976f8ac 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -115,15 +115,35 @@ do { \ (__ret); \ }) -#define this_cpu_generic_read(pcp) \ +#define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ typeof(pcp) __ret; \ preempt_disable_notrace(); \ - __ret = raw_cpu_generic_read(pcp); \ + __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ __ret; \ }) +#define __this_cpu_generic_read_noirq(pcp) \ +({ \ + typeof(pcp) __ret; \ + unsigned long __flags; \ + raw_local_irq_save(__flags); \ + __ret = raw_cpu_generic_read(pcp); \ + raw_local_irq_restore(__flags); \ + __ret; \ +}) + +#define this_cpu_generic_read(pcp) \ +({ \ + typeof(pcp) __ret; \ + if (__native_word(pcp)) \ + __ret = __this_cpu_generic_read_nopreempt(pcp); \ + else \ + __ret = __this_cpu_generic_read_noirq(pcp); \ + __ret; \ +}) + #define this_cpu_generic_to_op(pcp, val, op) \ do { \ unsigned long __flags; \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 460294b..02fa42d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -551,6 +551,7 @@ struct request_queue { int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace *blk_trace; + struct mutex blk_trace_mutex; #endif /* * for flush operations diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f24bfb2..6d50876 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -3,8 +3,27 @@ #include <linux/types.h> +/* + * CPU-up CPU-down + * + * BP AP BP AP + * + * OFFLINE OFFLINE + * | ^ + * v | + * BRINGUP_CPU->AP_OFFLINE BRINGUP_CPU <- AP_IDLE_DEAD (idle thread/play_dead) + * | AP_OFFLINE + * v (IRQ-off) ,---------------^ + * AP_ONLNE | (stop_machine) + * | TEARDOWN_CPU <- AP_ONLINE_IDLE + * | ^ + * v | + * AP_ACTIVE AP_ACTIVE + */ + enum cpuhp_state { - CPUHP_OFFLINE, + CPUHP_INVALID = -1, + CPUHP_OFFLINE = 0, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, diff --git a/include/linux/device.h b/include/linux/device.h index 1d26079..66fe271 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -307,8 +307,6 @@ struct driver_attribute { size_t count); }; -#define DRIVER_ATTR(_name, _mode, _show, _store) \ - struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store) #define DRIVER_ATTR_RW(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 5ba430c..1fc7abd 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -111,6 +111,9 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length); + int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a7f2ac6..41b8c57 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,11 +167,11 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue - * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping diff --git a/include/linux/irq.h b/include/linux/irq.h index b99a784..d4728bf 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -783,10 +783,7 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) static inline struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { - if (!cpumask_empty(d->common->effective_affinity)) - return d->common->effective_affinity; - - return d->common->affinity; + return d->common->effective_affinity; } static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) diff --git a/include/linux/key.h b/include/linux/key.h index 0441141..e315e16 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -187,6 +187,7 @@ struct key { #define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 10 /* set if key should not be removed */ +#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -243,6 +244,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ +#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 9c5cb44..a726f96 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,11 +346,6 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * - * @defer_rcv: Called by the transport to signal the LLLD that it has - * begun processing of a previously received NVME CMD IU. The LLDD - * is now free to re-use the rcv buffer associated with the - * nvmefc_tgt_fcp_req. - * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -806,11 +801,19 @@ struct nvmet_fc_target_port { * outstanding operation (if there was one) to complete, then will * call the fcp_req_release() callback to return the command's * exchange context back to the LLDD. + * Entrypoint is Mandatory. * * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req * to the LLDD after all operations on the fcp operation are complete. * This may be due to the command completing or upon completion of * abort cleanup. + * Entrypoint is Mandatory. + * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * Entrypoint is Optional. * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 87723c8..9310ce77 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -471,12 +471,14 @@ enum nvme_opcode { * * @NVME_SGL_FMT_ADDRESS: absolute address of the data block * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation * request subtype */ enum { NVME_SGL_FMT_ADDRESS = 0x00, NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_TRANSPORT_A = 0x0A, NVME_SGL_FMT_INVALIDATE = 0x0f, }; @@ -490,12 +492,16 @@ enum { * * For struct nvme_keyed_sgl_desc: * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + * + * Transport-specific SGL types: + * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor */ enum { NVME_SGL_FMT_DATA_DESC = 0x00, NVME_SGL_FMT_SEG_DESC = 0x02, NVME_SGL_FMT_LAST_SEG_DESC = 0x03, NVME_KEY_SGL_FMT_DATA_DESC = 0x04, + NVME_TRANSPORT_SGL_DATA_DESC = 0x05, }; struct nvme_sgl_desc { @@ -1127,19 +1133,6 @@ enum { NVME_SC_UNWRITTEN_BLOCK = 0x287, NVME_SC_DNR = 0x4000, - - - /* - * FC Transport-specific error status values for NVME commands - * - * Transport-specific status code values must be in the range 0xB0..0xBF - */ - - /* Generic FC failure - catchall */ - NVME_SC_FC_TRANSPORT_ERROR = 0x00B0, - - /* I/O failure due to FC ABTS'd */ - NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1, }; struct nvme_completion { diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index e0d1946..fb908e5 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -57,7 +57,14 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); +#ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); +#else +static inline struct platform_device *of_find_device_by_node(struct device_node *np) +{ + return NULL; +} +#endif /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, diff --git a/include/linux/pci.h b/include/linux/pci.h index f68c58a..f4f8ee5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1685,6 +1685,8 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) +static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) +{ return false; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 92fb8dd..26a7df4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,25 +65,23 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0 -#define TASK_INTERRUPTIBLE 1 -#define TASK_UNINTERRUPTIBLE 2 -#define __TASK_STOPPED 4 -#define __TASK_TRACED 8 +#define TASK_RUNNING 0x0000 +#define TASK_INTERRUPTIBLE 0x0001 +#define TASK_UNINTERRUPTIBLE 0x0002 +#define __TASK_STOPPED 0x0004 +#define __TASK_TRACED 0x0008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 16 -#define EXIT_ZOMBIE 32 +#define EXIT_DEAD 0x0010 +#define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_DEAD 64 -#define TASK_WAKEKILL 128 -#define TASK_WAKING 256 -#define TASK_PARKED 512 -#define TASK_NOLOAD 1024 -#define TASK_NEW 2048 -#define TASK_STATE_MAX 4096 - -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" +#define TASK_PARKED 0x0040 +#define TASK_DEAD 0x0080 +#define TASK_WAKEKILL 0x0100 +#define TASK_WAKING 0x0200 +#define TASK_NOLOAD 0x0400 +#define TASK_NEW 0x0800 +#define TASK_STATE_MAX 0x1000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -99,7 +97,8 @@ struct task_group; /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) @@ -1243,17 +1242,34 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } -static inline char task_state_to_char(struct task_struct *task) +#define TASK_REPORT_IDLE (TASK_REPORT + 1) +#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) + +static inline unsigned int __get_task_state(struct task_struct *tsk) +{ + unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + + BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); + + if (tsk_state == TASK_IDLE) + state = TASK_REPORT_IDLE; + + return fls(state); +} + +static inline char __task_state_to_char(unsigned int state) { - const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - unsigned long state = task->state; + static const char state_char[] = "RSDTtXZPI"; - state = state ? __ffs(state) + 1 : 0; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); - /* Make sure the string lines up properly with the number of task states: */ - BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + return state_char[state]; +} - return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; +static inline char task_state_to_char(struct task_struct *tsk) +{ + return __task_state_to_char(__get_task_state(tsk)); } /** diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 95606a2..a78186d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -221,21 +221,25 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifdef TIF_FSCHECK /* * Called before coming back to user-mode. Returning to user-mode with an * address limit different than USER_DS can allow to overwrite kernel memory. */ static inline void addr_limit_user_check(void) { - +#ifdef TIF_FSCHECK if (!test_thread_flag(TIF_FSCHECK)) return; +#endif - BUG_ON(!segment_eq(get_fs(), USER_DS)); + if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS), + "Invalid address limit on user-mode return")) + force_sig(SIGKILL, current); + +#ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); -} #endif +} asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); diff --git a/include/linux/timer.h b/include/linux/timer.h index e6789b8..6383c52 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -168,6 +168,20 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) +#define TIMER_DATA_TYPE unsigned long +#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) + +static inline void timer_setup(struct timer_list *timer, + void (*callback)(struct timer_list *), + unsigned int flags) +{ + __setup_timer(timer, (TIMER_FUNC_TYPE)callback, + (TIMER_DATA_TYPE)timer, flags); +} + +#define from_timer(var, callback_timer, timer_fieldname) \ + container_of(callback_timer, typeof(*var), timer_fieldname) + /** * timer_pending - is a timer pending? * @timer: the timer in question diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 7f11050..2e0f222 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -272,6 +272,7 @@ struct trace_event_call { int perf_refcount; struct hlist_head __percpu *perf_events; struct bpf_prog *prog; + struct perf_event *bpf_prog_owner; int (*perf_perm)(struct trace_event_call *, struct perf_event *); diff --git a/include/net/dst.h b/include/net/dst.h index 93568bd..06a6765 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -271,7 +271,7 @@ static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) - atomic_inc(&dst->__refcnt); + dst_hold(dst); return dst; } @@ -312,21 +312,6 @@ static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb } /** - * skb_dst_force - makes sure skb dst is refcounted - * @skb: buffer - * - * If dst is not yet refcounted, let's do it - */ -static inline void skb_dst_force(struct sk_buff *skb) -{ - if (skb_dst_is_noref(skb)) { - WARN_ON(!rcu_read_lock_held()); - skb->_skb_refdst &= ~SKB_DST_NOREF; - dst_clone(skb_dst(skb)); - } -} - -/** * dst_hold_safe - Take a reference on a dst if possible * @dst: pointer to dst entry * @@ -339,16 +324,17 @@ static inline bool dst_hold_safe(struct dst_entry *dst) } /** - * skb_dst_force_safe - makes sure skb dst is refcounted + * skb_dst_force - makes sure skb dst is refcounted * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. */ -static inline void skb_dst_force_safe(struct sk_buff *skb) +static inline void skb_dst_force(struct sk_buff *skb) { if (skb_dst_is_noref(skb)) { struct dst_entry *dst = skb_dst(skb); + WARN_ON(!rcu_read_lock_held()); if (!dst_hold_safe(dst)) dst = NULL; diff --git a/include/net/route.h b/include/net/route.h index 1b09a93..57dfc68 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -190,7 +190,7 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, rcu_read_lock(); err = ip_route_input_noref(skb, dst, src, tos, devin); if (!err) { - skb_dst_force_safe(skb); + skb_dst_force(skb); if (!skb_dst(skb)) err = -EINVAL; } diff --git a/include/net/sock.h b/include/net/sock.h index 03a3625..a6b9a8d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -856,7 +856,7 @@ void sk_stream_write_space(struct sock *sk); static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ - skb_dst_force_safe(skb); + skb_dst_force(skb); if (!sk->sk_backlog.tail) sk->sk_backlog.head = skb; diff --git a/include/net/tcp.h b/include/net/tcp.h index b510f28..3bc910a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -544,7 +544,6 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); -bool tcp_may_send_now(struct sock *sk); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bdb1279..e8608b2 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -285,7 +285,7 @@ enum ib_tm_cap_flags { IB_TM_CAP_RC = 1 << 0, }; -struct ib_xrq_caps { +struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ @@ -358,7 +358,7 @@ struct ib_device_attr { struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ - struct ib_xrq_caps xrq_caps; + struct ib_tm_caps tm_caps; }; enum ib_mtu { @@ -1739,7 +1739,7 @@ struct ib_mr { u32 lkey; u32 rkey; u64 iova; - u32 length; + u64 length; unsigned int page_size; bool need_inval; union { diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index ae1409f..3c8b7f6 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -114,7 +114,10 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ - return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state; + if (preempt) + return TASK_STATE_MAX; + + return __get_task_state(p); } #endif /* CREATE_TRACE_POINTS */ @@ -152,12 +155,14 @@ TRACE_EVENT(sched_switch, TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - __entry->prev_state & (TASK_STATE_MAX-1) ? - __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", - { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, - { 16, "Z" }, { 32, "X" }, { 64, "x" }, - { 128, "K" }, { 256, "W" }, { 512, "P" }, - { 1024, "N" }) : "R", + + (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? + __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", + { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" }, + { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }, + { 0x40, "P" }, { 0x80, "I" }) : + "R", + __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 9c041da..5bd1b1d 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1753,6 +1753,8 @@ enum ethtool_reset_flags { * %ethtool_link_mode_bit_indices for the link modes, and other * link features that the link partner advertised through * autonegotiation; 0 if unknown or not applicable. Read-only. + * @transceiver: Used to distinguish different possible PHY types, + * reported consistently by PHYLIB. Read-only. * * If autonegotiation is disabled, the speed and @duplex represent the * fixed link mode and are writable if the driver supports multiple @@ -1804,7 +1806,9 @@ struct ethtool_link_settings { __u8 eth_tp_mdix; __u8 eth_tp_mdix_ctrl; __s8 link_mode_masks_nwords; - __u32 reserved[8]; + __u8 transceiver; + __u8 reserved1[3]; + __u32 reserved[7]; __u32 link_mode_masks[0]; /* layout of link_mode_masks fields: * __u32 map_supported[link_mode_masks_nwords]; diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index ce1169a..2a5d630 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -780,6 +780,7 @@ struct usb_interface_assoc_descriptor { __u8 iFunction; } __attribute__ ((packed)); +#define USB_DT_INTERFACE_ASSOCIATION_SIZE 8 /*-------------------------------------------------------------------------*/ diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 9a0b647..d4e0b53 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -261,7 +261,7 @@ struct ib_uverbs_ex_query_device_resp { struct ib_uverbs_rss_caps rss_caps; __u32 max_wq_type_rq; __u32 raw_packet_caps; - struct ib_uverbs_tm_caps xrq_caps; + struct ib_uverbs_tm_caps tm_caps; }; struct ib_uverbs_query_port { @@ -1154,7 +1154,7 @@ static int put_compat_shm_info(struct shm_info *ip, info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; - return copy_to_user(up, &info, sizeof(info)); + return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 959c9a0..e093d9a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -75,8 +75,8 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr) static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; + int err = -EINVAL; u64 cost; - int err; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -108,6 +108,8 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (err) goto free_dtab; + err = -ENOMEM; + /* A per cpu bitfield with a bit per possible net device */ dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), __alignof__(unsigned long)); @@ -128,7 +130,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) free_dtab: free_percpu(dtab->flush_needed); kfree(dtab); - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); } static void dev_map_free(struct bpf_map *map) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb17e1c..25d0749 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -186,15 +186,17 @@ static int bpf_map_alloc_id(struct bpf_map *map) static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { + unsigned long flags; + if (do_idr_lock) - spin_lock_bh(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); if (do_idr_lock) - spin_unlock_bh(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 799b245..b914fbe 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4205,7 +4205,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } if (insn->imm == BPF_FUNC_redirect_map) { - u64 addr = (unsigned long)prog; + /* Note, we cannot use prog directly as imm as subsequent + * rewrites would still change the prog pointer. The only + * stable address we can use is aux, which also works with + * prog clones during blinding. + */ + u64 addr = (unsigned long)prog->aux; struct bpf_insn r4_ld[] = { BPF_LD_IMM64(BPF_REG_4, addr), *insn, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd..4485727 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2311,6 +2311,14 @@ out_release_tset: list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308..8de11a2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -46,11 +46,13 @@ * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation - * @done: Signal completion to the issuer of the task + * @done_up: Signal completion to the issuer of the task for cpu-up + * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; + enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; @@ -58,18 +60,39 @@ struct cpuhp_cpu_state { bool single; bool bringup; struct hlist_node *node; + struct hlist_node *last; enum cpuhp_state cb_state; int result; - struct completion done; + struct completion done_up; + struct completion done_down; #endif }; -static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, +}; #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) -static struct lock_class_key cpuhp_state_key; -static struct lockdep_map cpuhp_state_lock_map = - STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +static struct lockdep_map cpuhp_state_down_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); + + +static void inline cpuhp_lock_acquire(bool bringup) +{ + lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} + +static void inline cpuhp_lock_release(bool bringup) +{ + lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} +#else + +static void inline cpuhp_lock_acquire(bool bringup) { } +static void inline cpuhp_lock_release(bool bringup) { } + #endif /** @@ -123,13 +146,16 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked - * @step: The step in the state machine + * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked + * @node: For multi-instance, do a single entry callback for install/remove + * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, - bool bringup, struct hlist_node *node) + bool bringup, struct hlist_node *node, + struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); @@ -137,7 +163,17 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int (*cb)(unsigned int cpu); int ret, cnt; + if (st->fail == state) { + st->fail = CPUHP_INVALID; + + if (!(bringup ? step->startup.single : step->teardown.single)) + return 0; + + return -EAGAIN; + } + if (!step->multi_instance) { + WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; @@ -152,6 +188,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* Single invocation for instance add/remove */ if (node) { + WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); @@ -161,13 +198,23 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { + if (lastp && node == *lastp) + break; + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); - if (ret) - goto err; + if (ret) { + if (!lastp) + goto err; + + *lastp = node; + return ret; + } cnt++; } + if (lastp) + *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ @@ -178,12 +225,39 @@ err: hlist_for_each(node, &step->list) { if (!cnt--) break; - cbm(cpu, node); + + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); + ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, ret); + /* + * Rollback must not fail, + */ + WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP +static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + wait_for_completion(done); +} + +static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + complete(done); +} + +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -271,14 +345,79 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); +static inline enum cpuhp_state +cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + + st->rollback = false; + st->last = NULL; + + st->target = target; + st->single = false; + st->bringup = st->state < target; + + return prev_state; +} + +static inline void +cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +{ + st->rollback = true; + + /* + * If we have st->last we need to undo partial multi_instance of this + * state first. Otherwise start undo at the previous state. + */ + if (!st->last) { + if (st->bringup) + st->state--; + else + st->state++; + } + + st->target = prev_state; + st->bringup = !st->bringup; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) +{ + if (!st->single && st->state == st->target) + return; + + st->result = 0; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_ap_thread(st, st->bringup); +} + +static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state; + int ret; + + prev_state = cpuhp_set_state(st, target); + __cpuhp_kick_ap(st); + if ((ret = st->result)) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } + + return ret; +} static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; @@ -286,12 +425,10 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) { - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - } - return st->result; + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -317,32 +454,6 @@ static int bringup_cpu(unsigned int cpu) /* * Hotplug state machine related functions */ -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL); - } -} - -static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, - enum cpuhp_state target) -{ - enum cpuhp_state prev_state = st->state; - int ret = 0; - - for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } - return ret; -} static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { @@ -350,7 +461,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } } @@ -362,7 +473,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, while (st->state < target) { st->state++; - ret = cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_up(cpu, st); @@ -379,7 +490,8 @@ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - init_completion(&st->done); + init_completion(&st->done_up); + init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) @@ -389,69 +501,90 @@ static int cpuhp_should_run(unsigned int cpu) return st->should_run; } -/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ -static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); - - return cpuhp_down_callbacks(cpu, st, target); -} - -/* Execute the online startup callbacks. Used to be CPU_ONLINE */ -static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - return cpuhp_up_callbacks(cpu, st, st->target); -} - /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. + * + * Each invocation of this function by the smpboot thread does a single AP + * state callback. + * + * It has 3 modes of operation: + * - single: runs st->cb_state + * - up: runs ++st->state, while st->state < st->target + * - down: runs st->state--, while st->state > st->target + * + * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - int ret = 0; + bool bringup = st->bringup; + enum cpuhp_state state; /* - * Paired with the mb() in cpuhp_kick_ap_work and - * cpuhp_invoke_ap_callback, so the work set is consistent visible. + * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures + * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (!st->should_run) + + if (WARN_ON_ONCE(!st->should_run)) return; - st->should_run = false; + cpuhp_lock_acquire(bringup); - lock_map_acquire(&cpuhp_state_lock_map); - /* Single callback invocation for [un]install ? */ if (st->single) { - if (st->cb_state < CPUHP_AP_ONLINE) { - local_irq_disable(); - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); - local_irq_enable(); + state = st->cb_state; + st->should_run = false; + } else { + if (bringup) { + st->state++; + state = st->state; + st->should_run = (st->state < st->target); + WARN_ON_ONCE(st->state > st->target); } else { - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + state = st->state; + st->state--; + st->should_run = (st->state > st->target); + WARN_ON_ONCE(st->state < st->target); } - } else if (st->rollback) { - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + } + + WARN_ON_ONCE(!cpuhp_is_ap_state(state)); - undo_cpu_down(cpu, st); - st->rollback = false; + if (st->rollback) { + struct cpuhp_step *step = cpuhp_get_step(state); + if (step->skip_onerr) + goto next; + } + + if (cpuhp_is_atomic_state(state)) { + local_irq_disable(); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + local_irq_enable(); + + /* + * STARTING/DYING must not fail! + */ + WARN_ON_ONCE(st->result); } else { - /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); - - /* Regular hotplug work */ - if (st->state < st->target) - ret = cpuhp_ap_online(cpu, st); - else if (st->state > st->target) - ret = cpuhp_ap_offline(cpu, st); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + } + + if (st->result) { + /* + * If we fail on a rollback, we're up a creek without no + * paddle, no way forward, no way back. We loose, thanks for + * playing. + */ + WARN_ON_ONCE(st->rollback); + st->should_run = false; } - lock_map_release(&cpuhp_state_lock_map); - st->result = ret; - complete(&st->done); + +next: + cpuhp_lock_release(bringup); + + if (!st->should_run) + complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ @@ -460,62 +593,64 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; if (!cpu_online(cpu)) return 0; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) - return cpuhp_invoke_callback(cpu, state, bringup, node); + return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + st->rollback = false; + st->last = NULL; + + st->node = node; + st->bringup = bringup; st->cb_state = state; st->single = true; - st->bringup = bringup; - st->node = node; - /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() - */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); - wait_for_completion(&st->done); - return st->result; -} + __cpuhp_kick_ap(st); -/* Regular hotplug invocation of the AP hotplug thread */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) -{ - st->result = 0; - st->single = false; /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() + * If we failed and did a partial, do a rollback. */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); + if ((ret = st->result) && st->last) { + st->rollback = true; + st->bringup = !bringup; + + __cpuhp_kick_ap(st); + } + + return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; + enum cpuhp_state prev_state = st->state; + int ret; + + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); + + trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); + ret = cpuhp_kick_ap(st, st->target); + trace_cpuhp_exit(cpu, st->state, prev_state, ret); - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - trace_cpuhp_exit(cpu, st->state, state, st->result); - return st->result; + return ret; } static struct smp_hotplug_thread cpuhp_threads = { @@ -581,6 +716,7 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); + int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -594,8 +730,13 @@ static int take_cpu_down(void *_param) WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ - for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + /* + * DYING must not fail! + */ + WARN_ON_ONCE(ret); + } /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -639,7 +780,7 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ @@ -658,7 +799,7 @@ static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; - complete(&st->done); + complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) @@ -676,11 +817,32 @@ void cpuhp_report_idle_dead(void) cpuhp_complete_idle_dead, st, 0); } -#else -#define takedown_cpu NULL -#endif +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_get_step(st->state); -#ifdef CONFIG_HOTPLUG_CPU + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + return ret; +} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -699,13 +861,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; - st->target = target; + prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { + st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -720,6 +882,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; + + st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need @@ -727,9 +891,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { - st->target = prev_state; - st->rollback = true; - cpuhp_kick_ap_work(cpu); + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); } out: @@ -754,11 +917,15 @@ out: cpu_maps_update_done(); return err; } + int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); + +#else +#define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** @@ -772,11 +939,16 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + /* + * STARTING must not fail! + */ + WARN_ON_ONCE(ret); } } @@ -794,7 +966,7 @@ void cpuhp_online_idle(enum cpuhp_state state) return; st->state = CPUHP_AP_ONLINE_IDLE; - complete(&st->done); + complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ @@ -829,7 +1001,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - st->target = target; + cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1296,6 +1468,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct cpuhp_step *sp = cpuhp_get_step(state); int ret; + /* + * If there's nothing to do, we done. + * Relies on the union for multi_instance. + */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; @@ -1307,9 +1483,9 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; @@ -1641,9 +1817,55 @@ static ssize_t show_cpuhp_target(struct device *dev, } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static ssize_t write_cpuhp_fail(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int fail, ret; + + ret = kstrtoint(buf, 10, &fail); + if (ret) + return ret; + + /* + * Cannot fail STARTING/DYING callbacks. + */ + if (cpuhp_is_atomic_state(fail)) + return -EINVAL; + + /* + * Cannot fail anything that doesn't have callbacks. + */ + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(fail); + if (!sp->startup.single && !sp->teardown.single) + ret = -EINVAL; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + st->fail = fail; + + return count; +} + +static ssize_t show_cpuhp_fail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->fail); +} + +static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); + static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, + &dev_attr_fail.attr, NULL }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 3e691b7..6bc21e2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8171,6 +8171,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) } } event->tp_event->prog = prog; + event->tp_event->bpf_prog_owner = event; return 0; } @@ -8185,7 +8186,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) return; prog = event->tp_event->prog; - if (prog) { + if (prog && event->tp_event->bpf_prog_owner == event) { event->tp_event->prog = NULL; bpf_prog_put(prog); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index af71a84e..f684d8e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -412,6 +412,19 @@ err: return NULL; } +static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +{ + if (rb->aux_overwrite) + return false; + + if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); + return true; + } + + return false; +} + /* * Commit the data written by hardware into the ring buffer by adjusting * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the @@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) } rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) wakeup = true; - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); - } if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) @@ -484,9 +495,8 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; } diff --git a/kernel/exit.c b/kernel/exit.c index 3481aba..f2cd53e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1600,12 +1600,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; + if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } @@ -1723,16 +1721,15 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err && uru) { - /* kernel_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - err = copy_to_user(uru, &ru, sizeof(ru)); - else - err = put_compat_rusage(&ru, uru); - if (err) - return -EFAULT; + if (uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } } if (!infop) diff --git a/kernel/extable.c b/kernel/extable.c index 38c2412..9aa1cc4 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -102,15 +102,7 @@ int core_kernel_data(unsigned long addr) int __kernel_text_address(unsigned long addr) { - if (core_kernel_text(addr)) - return 1; - if (is_module_text_address(addr)) - return 1; - if (is_ftrace_trampoline(addr)) - return 1; - if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; - if (is_bpf_text_address(addr)) + if (kernel_text_address(addr)) return 1; /* * There might be init symbols in saved stacktraces. @@ -127,17 +119,42 @@ int __kernel_text_address(unsigned long addr) int kernel_text_address(unsigned long addr) { + bool no_rcu; + int ret = 1; + if (core_kernel_text(addr)) return 1; + + /* + * If a stack dump happens while RCU is not watching, then + * RCU needs to be notified that it requires to start + * watching again. This can happen either by tracing that + * triggers a stack trace, or a WARN() that happens during + * coming back from idle, or cpu on or offlining. + * + * is_module_text_address() as well as the kprobe slots + * and is_bpf_text_address() require RCU to be watching. + */ + no_rcu = !rcu_is_watching(); + + /* Treat this like an NMI as it can happen anywhere */ + if (no_rcu) + rcu_nmi_enter(); + if (is_module_text_address(addr)) - return 1; + goto out; if (is_ftrace_trampoline(addr)) - return 1; + goto out; if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; + goto out; if (is_bpf_text_address(addr)) - return 1; - return 0; + goto out; + ret = 0; +out: + if (no_rcu) + rcu_nmi_exit(); + + return ret; } /* diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf..0518a0b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ retry: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index f7086b7..5270a54 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -322,7 +322,6 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } - d->name = name; return 0; } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b705..ac4644e 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void **slot; + void __rcu **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -1453,7 +1453,7 @@ out_free_desc: /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) { - void **slot; + void __rcu **slot; if (d->hwirq < d->domain->revmap_size) return; /* Not using radix tree. */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 573dc52..d00132b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,6 +1643,10 @@ const void *free_irq(unsigned int irq, void *dev_id) #endif action = __free_irq(irq, dev_id); + + if (!action) + return NULL; + devname = action->name; kfree(action); return devname; diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 02f6606..1fefe6d 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -613,6 +613,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) DEFINE_WAKE_Q(wake_q); /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1250e4b..0c44c7b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -882,6 +882,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -1015,6 +1020,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966..d17c5da 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb..2f93e4a 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index c24579d..bb3a380 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -473,14 +473,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + refcount_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - refcount_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -491,10 +496,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -503,6 +506,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) { memset(info, 0, sizeof(*info)); @@ -1025,13 +1034,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbb..423554a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2a685b4..45a3928 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629a..c738e76 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b..0c33197 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a4df67c..49cb414 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; - /* - * There's a slight chance that we are tracing inside the - * RCU infrastructure, and rcu_irq_enter() will not work - * as expected. - */ - if (unlikely(rcu_irq_enter_disabled())) - return; - local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b19c491..2689b7c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -219,7 +219,8 @@ config FRAME_WARN range 0 8192 default 0 if KASAN default 2048 if GCC_PLUGIN_LATENT_ENTROPY - default 1024 if !64BIT + default 1280 if (!64BIT && PARISC) + default 1024 if (!64BIT && !PARISC) default 2048 if 64BIT help Tell gcc to warn at build time for stack frames larger than this. diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index e590523..f237a09 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -294,6 +294,26 @@ static void cleanup_uevent_env(struct subprocess_info *info) } #endif +static void zap_modalias_env(struct kobj_uevent_env *env) +{ + static const char modalias_prefix[] = "MODALIAS="; + int i; + + for (i = 0; i < env->envp_idx;) { + if (strncmp(env->envp[i], modalias_prefix, + sizeof(modalias_prefix) - 1)) { + i++; + continue; + } + + if (i != env->envp_idx - 1) + memmove(&env->envp[i], &env->envp[i + 1], + sizeof(env->envp[i]) * env->envp_idx - 1); + + env->envp_idx--; + } +} + /** * kobject_uevent_env - send an uevent with environmental data * @@ -409,16 +429,29 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, } } - /* - * Mark "add" and "remove" events in the object to ensure proper - * events to userspace during automatic cleanup. If the object did - * send an "add" event, "remove" will automatically generated by - * the core, if not already done by the caller. - */ - if (action == KOBJ_ADD) + switch (action) { + case KOBJ_ADD: + /* + * Mark "add" event so we can make sure we deliver "remove" + * event to userspace during automatic cleanup. If + * the object did send an "add" event, "remove" will + * automatically generated by the core, if not already done + * by the caller. + */ kobj->state_add_uevent_sent = 1; - else if (action == KOBJ_REMOVE) + break; + + case KOBJ_REMOVE: kobj->state_remove_uevent_sent = 1; + break; + + case KOBJ_UNBIND: + zap_modalias_env(env); + break; + + default: + break; + } mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 707ca5d..ddd7dde 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -735,9 +735,9 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_exit); * rhashtable_walk_start - Start a hash table walk * @iter: Hash table iterator * - * Start a hash table walk. Note that we take the RCU lock in all - * cases including when we return an error. So you must always call - * rhashtable_walk_stop to clean up. + * Start a hash table walk at the current iterator position. Note that we take + * the RCU lock in all cases including when we return an error. So you must + * always call rhashtable_walk_stop to clean up. * * Returns zero if successful. * @@ -846,7 +846,8 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_next); * rhashtable_walk_stop - Finish a hash table walk * @iter: Hash table iterator * - * Finish a hash table walk. + * Finish a hash table walk. Does not reset the iterator to the start of the + * hash table. */ void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU) diff --git a/mm/filemap.c b/mm/filemap.c index 870971e..db250d0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2926,9 +2926,15 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... + * + * Most of the time we do not need this since dio_complete() will do + * the invalidation for us. However there are some file systems that + * do not end up with dio_complete() being called, so let's not break + * them by removing it completely */ - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); + if (mapping->nrpages) + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c index 6142484..7a58460 100644 --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -73,7 +73,7 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk, last_alloc + 1 : 0; as_len = 0; - start = chunk->start_offset; + start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; /* * If a bit is set in the allocation map, the bound_map identifies diff --git a/mm/percpu.c b/mm/percpu.c index 59d44d6..aa121ce 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -353,6 +353,8 @@ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, block->contig_hint_start); return; } + /* reset to satisfy the second predicate above */ + block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; @@ -407,6 +409,8 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, *bit_off = pcpu_block_off_to_off(i, block->first_free); return; } + /* reset to satisfy the second predicate above */ + block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index c18115d..db82a40 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -126,14 +126,4 @@ config BT_DEBUGFS Provide extensive information about internal Bluetooth states in debugfs. -config BT_LEGACY_IOCTL - bool "Enable legacy ioctl interfaces" - depends on BT && BT_BREDR - default y - help - Enable support for legacy ioctl interfaces. This is only needed - for old and deprecated applications using direct ioctl calls for - controller management. Since Linux 3.4 all configuration and - setup is done via mgmt interface and this is no longer needed. - source "drivers/bluetooth/Kconfig" diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 0bad296..65d734c 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -878,7 +878,6 @@ static int hci_sock_release(struct socket *sock) return 0; } -#ifdef CONFIG_BT_LEGACY_IOCTL static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; @@ -1050,7 +1049,6 @@ done: release_sock(sk); return err; } -#endif static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) @@ -1971,11 +1969,7 @@ static const struct proto_ops hci_sock_ops = { .getname = hci_sock_getname, .sendmsg = hci_sock_sendmsg, .recvmsg = hci_sock_recvmsg, -#ifdef CONFIG_BT_LEGACY_IOCTL .ioctl = hci_sock_ioctl, -#else - .ioctl = sock_no_ioctl, -#endif .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/compat.c b/net/compat.c index 6ded6c8..2238171 100644 --- a/net/compat.c +++ b/net/compat.c @@ -185,6 +185,13 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); } + /* + * check the length of messages copied in is the same as the + * what we get from the first loop + */ + if ((char *)kcmsg - (char *)kcmsg_base != kcmlen) + goto Einval; + /* Ok, looks like we made it. Hook it up and return success. */ kmsg->msg_control = kcmsg_base; kmsg->msg_controllen = kcmlen; diff --git a/net/core/dev.c b/net/core/dev.c index fb766d9..588b473 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1948,8 +1948,12 @@ again: goto again; } out_unlock: - if (pt_prev) - pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); + if (pt_prev) { + if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) + pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); + else + kfree_skb(skb2); + } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); @@ -3892,6 +3896,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); + skb->mac_header += off; switch (act) { case XDP_REDIRECT: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6a582ae..3228411 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -525,6 +525,8 @@ convert_link_ksettings_to_legacy_settings( = link_ksettings->base.eth_tp_mdix; legacy_settings->eth_tp_mdix_ctrl = link_ksettings->base.eth_tp_mdix_ctrl; + legacy_settings->transceiver + = link_ksettings->base.transceiver; return retval; } diff --git a/net/core/filter.c b/net/core/filter.c index 24dd33d..82edad5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1794,7 +1794,7 @@ struct redirect_info { u32 flags; struct bpf_map *map; struct bpf_map *map_to_flush; - const struct bpf_prog *map_owner; + unsigned long map_owner; }; static DEFINE_PER_CPU(struct redirect_info, redirect_info); @@ -2500,11 +2500,17 @@ void xdp_do_flush_map(void) } EXPORT_SYMBOL_GPL(xdp_do_flush_map); +static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, + unsigned long aux) +{ + return (unsigned long)xdp_prog->aux != aux; +} + static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); - const struct bpf_prog *map_owner = ri->map_owner; + unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; struct net_device *fwd = NULL; u32 index = ri->ifindex; @@ -2512,9 +2518,9 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, ri->ifindex = 0; ri->map = NULL; - ri->map_owner = NULL; + ri->map_owner = 0; - if (unlikely(map_owner != xdp_prog)) { + if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { err = -EFAULT; map = NULL; goto err; @@ -2574,7 +2580,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); - const struct bpf_prog *map_owner = ri->map_owner; + unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; struct net_device *fwd = NULL; u32 index = ri->ifindex; @@ -2583,10 +2589,10 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, ri->ifindex = 0; ri->map = NULL; - ri->map_owner = NULL; + ri->map_owner = 0; if (map) { - if (unlikely(map_owner != xdp_prog)) { + if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { err = -EFAULT; map = NULL; goto err; @@ -2632,7 +2638,7 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) ri->ifindex = ifindex; ri->flags = flags; ri->map = NULL; - ri->map_owner = NULL; + ri->map_owner = 0; return XDP_REDIRECT; } @@ -2646,7 +2652,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { }; BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags, - const struct bpf_prog *, map_owner) + unsigned long, map_owner) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b9c64b4..c039c93 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -266,7 +266,7 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, #if IS_ENABLED(CONFIG_IPV6) if (tb->fast_sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr, - &sk->sk_v6_rcv_saddr, + inet6_rcv_saddr(sk), tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, @@ -321,13 +321,14 @@ tb_found: goto fail_unlock; } success: - if (!hlist_empty(&tb->owners)) { + if (hlist_empty(&tb->owners)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif @@ -354,6 +355,7 @@ success: tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1c839c9..0bc9e46 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1806,40 +1806,6 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, return !after(end_seq, tcp_wnd_end(tp)); } -/* This checks if the data bearing packet SKB (usually tcp_send_head(sk)) - * should be put on the wire right now. If so, it returns the number of - * packets allowed by the congestion window. - */ -static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb, - unsigned int cur_mss, int nonagle) -{ - const struct tcp_sock *tp = tcp_sk(sk); - unsigned int cwnd_quota; - - tcp_init_tso_segs(skb, cur_mss); - - if (!tcp_nagle_test(tp, skb, cur_mss, nonagle)) - return 0; - - cwnd_quota = tcp_cwnd_test(tp, skb); - if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss)) - cwnd_quota = 0; - - return cwnd_quota; -} - -/* Test if sending is allowed right now. */ -bool tcp_may_send_now(struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_send_head(sk); - - return skb && - tcp_snd_test(sk, skb, tcp_current_mss(sk), - (tcp_skb_is_last(sk, skb) ? - tp->nonagle : TCP_NAGLE_PUSH)); -} - /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions @@ -3423,6 +3389,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto done; } + /* data was not sent, this is our new send_head */ + sk->sk_send_head = syn_data; + tp->packets_out -= tcp_skb_pcount(syn_data); + fallback: /* Send a regular SYN with Fast Open cookie request option */ if (fo->cookie.len > 0) @@ -3475,6 +3445,11 @@ int tcp_connect(struct sock *sk) */ tp->snd_nxt = tp->write_seq; tp->pushed_seq = tp->write_seq; + buff = tcp_send_head(sk); + if (unlikely(buff)) { + tp->snd_nxt = TCP_SKB_CB(buff)->seq; + tp->pushed_seq = TCP_SKB_CB(buff)->seq; + } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c2e2a78..96861c7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1399,10 +1399,18 @@ static inline int ipv6_saddr_preferred(int type) return 0; } -static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev) +static bool ipv6_use_optimistic_addr(struct net *net, + struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic; + if (!idev) + return false; + if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + return false; + if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic) + return false; + + return true; #else return false; #endif @@ -1472,7 +1480,7 @@ static int ipv6_get_saddr_eval(struct net *net, /* Rule 3: Avoid deprecated and optimistic addresses */ u8 avoid = IFA_F_DEPRECATED; - if (!ipv6_use_optimistic_addr(score->ifa->idev)) + if (!ipv6_use_optimistic_addr(net, score->ifa->idev)) avoid |= IFA_F_OPTIMISTIC; ret = ipv6_saddr_preferred(score->addr_type) || !(score->ifa->flags & avoid); @@ -2460,7 +2468,8 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, int max_addresses = in6_dev->cnf.max_addresses; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - if (in6_dev->cnf.optimistic_dad && + if ((net->ipv6.devconf_all->optimistic_dad || + in6_dev->cnf.optimistic_dad) && !net->ipv6.devconf_all->forwarding && sllao) addr_flags |= IFA_F_OPTIMISTIC; #endif @@ -3051,7 +3060,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev, u32 addr_flags = flags | IFA_F_PERMANENT; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - if (idev->cnf.optimistic_dad && + if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad || + idev->cnf.optimistic_dad) && !dev_net(idev->dev)->ipv6.devconf_all->forwarding) addr_flags |= IFA_F_OPTIMISTIC; #endif @@ -3810,6 +3820,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) goto out; if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || + dev_net(dev)->ipv6.devconf_all->accept_dad < 1 || idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { @@ -3841,7 +3852,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) */ if (ifp->flags & IFA_F_OPTIMISTIC) { ip6_ins_rt(ifp->rt); - if (ipv6_use_optimistic_addr(idev)) { + if (ipv6_use_optimistic_addr(dev_net(dev), idev)) { /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ @@ -3897,7 +3908,9 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; - if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 && + if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 || + idev->cnf.accept_dad > 1) && + !idev->cnf.disable_ipv6 && !(ifp->flags & IFA_F_STABLE_PRIVACY)) { struct in6_addr addr; @@ -4940,9 +4953,10 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) /* Don't send DELADDR notification for TENTATIVE address, * since NEWADDR notification is sent only after removing - * TENTATIVE flag. + * TENTATIVE flag, if DAD has not failed. */ - if (ifa->flags & IFA_F_TENTATIVE && event == RTM_DELADDR) + if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) && + event == RTM_DELADDR) return; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b7a72d4..20f66f4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -940,24 +940,25 @@ done: } static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, - const void *daddr, const void *saddr, unsigned int len) + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) { struct ip6_tnl *t = netdev_priv(dev); - struct ipv6hdr *ipv6h = skb_push(skb, t->hlen); - __be16 *p = (__be16 *)(ipv6h+1); + struct ipv6hdr *ipv6h; + __be16 *p; - ip6_flow_hdr(ipv6h, 0, - ip6_make_flowlabel(dev_net(dev), skb, - t->fl.u.ip6.flowlabel, true, - &t->fl.u.ip6)); + ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h)); + ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb, + t->fl.u.ip6.flowlabel, + true, &t->fl.u.ip6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; ipv6h->daddr = t->parms.raddr; - p[0] = t->parms.o_flags; - p[1] = htons(type); + p = (__be16 *)(ipv6h + 1); + p[0] = t->parms.o_flags; + p[1] = htons(type); /* * Set the source hardware address. diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index ae73164..f2f21c2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -2259,6 +2259,9 @@ static int __init ip6_tunnel_init(void) { int err; + if (!ipv6_mod_enabled()) + return -EOPNOTSUPP; + err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto out_pernet; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e2ecfb1..40d7234 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1015,6 +1015,7 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, */ offset = skb_transport_offset(skb); skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + csum = skb->csum; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index f236c0b..51063d9 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1041,12 +1041,24 @@ out: static int mtype_head(struct ip_set *set, struct sk_buff *skb) { - const struct htype *h = set->data; + struct htype *h = set->data; const struct htable *t; struct nlattr *nested; size_t memsize; u8 htable_bits; + /* If any members have expired, set->elements will be wrong + * mytype_expire function will update it with the right count. + * we do not hold set->lock here, so grab it first. + * set->elements can still be incorrect in the case of a huge set, + * because elements might time out during the listing. + */ + if (SET_WITH_TIMEOUT(set)) { + spin_lock_bh(&set->lock); + mtype_expire(set, h); + spin_unlock_bh(&set->lock); + } + rcu_read_lock_bh(); t = rcu_dereference_bh_nfnl(h->table); memsize = mtype_ahash_memsize(h, t) + set->ext_size; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index f393a70..af8345f 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -429,7 +429,7 @@ nf_nat_setup_info(struct nf_conn *ct, srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - lock = &nf_nat_locks[srchash % ARRAY_SIZE(nf_nat_locks)]; + lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS]; spin_lock_bh(lock); hlist_add_head_rcu(&ct->nat_bysource, &nf_nat_bysource[srchash]); @@ -532,9 +532,9 @@ static void __nf_nat_cleanup_conntrack(struct nf_conn *ct) unsigned int h; h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - spin_lock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]); + spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); hlist_del_rcu(&ct->nat_bysource); - spin_unlock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]); + spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); } static int nf_nat_proto_clean(struct nf_conn *ct, void *data) @@ -807,8 +807,8 @@ static int __init nf_nat_init(void) /* Leave them the same for the moment. */ nf_nat_htable_size = nf_conntrack_htable_size; - if (nf_nat_htable_size < ARRAY_SIZE(nf_nat_locks)) - nf_nat_htable_size = ARRAY_SIZE(nf_nat_locks); + if (nf_nat_htable_size < CONNTRACK_LOCKS) + nf_nat_htable_size = CONNTRACK_LOCKS; nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0); if (!nf_nat_bysource) @@ -821,7 +821,7 @@ static int __init nf_nat_init(void) return ret; } - for (i = 0; i < ARRAY_SIZE(nf_nat_locks); i++) + for (i = 0; i < CONNTRACK_LOCKS; i++) spin_lock_init(&nf_nat_locks[i]); nf_ct_helper_expectfn_register(&follow_master_nat); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c261729..d288f52 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1684,10 +1684,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) mutex_lock(&fanout_mutex); - err = -EINVAL; - if (!po->running) - goto out; - err = -EALREADY; if (po->fanout) goto out; @@ -1749,7 +1745,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) list_add(&match->list, &fanout_list); } err = -EINVAL; - if (match->type == type && + + spin_lock(&po->bind_lock); + if (po->running && + match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; @@ -1761,6 +1760,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) err = 0; } } + spin_unlock(&po->bind_lock); + + if (err && !refcount_read(&match->sk_ref)) { + list_del(&match->list); + kfree(match); + } + out: if (err && rollover) { kfree(rollover); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 1a267e7..d230cb4 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -922,28 +922,28 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_flags_valid(fnew->flags)) { err = -EINVAL; - goto errout; + goto errout_idr; } } err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); if (err) - goto errout; + goto errout_idr; err = fl_check_assign_mask(head, &mask); if (err) - goto errout; + goto errout_idr; if (!tc_skip_sw(fnew->flags)) { if (!fold && fl_lookup(head, &fnew->mkey)) { err = -EEXIST; - goto errout; + goto errout_idr; } err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, head->ht_params); if (err) - goto errout; + goto errout_idr; } if (!tc_skip_hw(fnew->flags)) { @@ -952,7 +952,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, &mask.key, fnew); if (err) - goto errout; + goto errout_idr; } if (!tc_in_hw(fnew->flags)) @@ -981,6 +981,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(tb); return 0; +errout_idr: + if (fnew->handle) + idr_remove_ext(&head->handle_idr, fnew->handle); errout: tcf_exts_destroy(&fnew->exts); kfree(fnew); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 21cc45ca..eeac606 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -32,6 +32,7 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, if (tc_skip_sw(head->flags)) return -1; + *res = head->res; return tcf_exts_exec(skb, &head->exts, res); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 92237e7..bf8c81e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -685,6 +685,7 @@ void qdisc_reset(struct Qdisc *qdisc) qdisc->gso_skb = NULL; } qdisc->q.qlen = 0; + qdisc->qstats.backlog = 0; } EXPORT_SYMBOL(qdisc_reset); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index daaf214..3f88b75 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -958,6 +958,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } if (cl != NULL) { + int old_flags; + if (parentid) { if (cl->cl_parent && cl->cl_parent->cl_common.classid != parentid) @@ -978,6 +980,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } sch_tree_lock(sch); + old_flags = cl->cl_flags; + if (rsc != NULL) hfsc_change_rsc(cl, rsc, cur_time); if (fsc != NULL) @@ -986,10 +990,21 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, hfsc_change_usc(cl, usc, cur_time); if (cl->qdisc->q.qlen != 0) { - if (cl->cl_flags & HFSC_RSC) - update_ed(cl, qdisc_peek_len(cl->qdisc)); - if (cl->cl_flags & HFSC_FSC) - update_vf(cl, 0, cur_time); + int len = qdisc_peek_len(cl->qdisc); + + if (cl->cl_flags & HFSC_RSC) { + if (old_flags & HFSC_RSC) + update_ed(cl, len); + else + init_ed(cl, len); + } + + if (cl->cl_flags & HFSC_FSC) { + if (old_flags & HFSC_FSC) + update_vf(cl, 0, cur_time); + else + init_vf(cl, len); + } } sch_tree_unlock(sch); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 8c6d24b..745f145 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -282,6 +282,7 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock, __be32 *subnet, u8 *prefix_len) { struct dst_entry *dst = sk_dst_get(clcsock->sk); + struct in_device *in_dev; struct sockaddr_in addr; int rc = -ENOENT; int len; @@ -298,14 +299,17 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock, /* get address to which the internal TCP socket is bound */ kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len); /* analyze IPv4 specific data of net_device belonging to TCP socket */ - for_ifa(dst->dev->ip_ptr) { - if (ifa->ifa_address != addr.sin_addr.s_addr) + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dst->dev); + for_ifa(in_dev) { + if (!inet_ifa_match(addr.sin_addr.s_addr, ifa)) continue; *prefix_len = inet_mask_len(ifa->ifa_mask); *subnet = ifa->ifa_address & ifa->ifa_mask; rc = 0; break; - } endfor_ifa(dst->dev->ip_ptr); + } endfor_ifa(in_dev); + rcu_read_unlock(); out_rel: dst_release(dst); @@ -509,7 +513,7 @@ decline_rdma: /* RDMA setup failed, switch back to TCP */ smc->use_fallback = true; if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) { - rc = smc_clc_send_decline(smc, reason_code, 0); + rc = smc_clc_send_decline(smc, reason_code); if (rc < sizeof(struct smc_clc_msg_decline)) goto out_err; } @@ -804,8 +808,6 @@ static void smc_listen_work(struct work_struct *work) rc = local_contact; if (rc == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ - else if (rc == -ENOLINK) - reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */ goto decline_rdma; } link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; @@ -899,7 +901,7 @@ decline_rdma: smc_conn_free(&new_smc->conn); new_smc->use_fallback = true; if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) { - rc = smc_clc_send_decline(new_smc, reason_code, 0); + rc = smc_clc_send_decline(new_smc, reason_code); if (rc < sizeof(struct smc_clc_msg_decline)) goto out_err; } diff --git a/net/smc/smc.h b/net/smc/smc.h index 6e44313e..0ccd6fa 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -149,7 +149,7 @@ struct smc_connection { atomic_t sndbuf_space; /* remaining space in sndbuf */ u16 tx_cdc_seq; /* sequence # for CDC send */ spinlock_t send_lock; /* protect wr_sends */ - struct work_struct tx_work; /* retry of smc_cdc_msg_send */ + struct delayed_work tx_work; /* retry of smc_cdc_msg_send */ struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl. * .prod cf. TCP rcv_nxt diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 3934913..b7dd274 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -95,9 +95,10 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } if (clcm->type == SMC_CLC_DECLINE) { reason_code = SMC_CLC_DECL_REPLY; - if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis) - == SMC_CLC_DECL_SYNCERR) + if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { smc->conn.lgr->sync_err = true; + smc_lgr_terminate(smc->conn.lgr); + } } out: @@ -105,8 +106,7 @@ out: } /* send CLC DECLINE message across internal TCP socket */ -int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, - u8 out_of_sync) +int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) { struct smc_clc_msg_decline dclc; struct msghdr msg; @@ -118,7 +118,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, dclc.hdr.type = SMC_CLC_DECLINE; dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; - dclc.hdr.flag = out_of_sync ? 1 : 0; + dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 13db8ce..1c55414 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -106,8 +106,7 @@ struct smc_ib_device; int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type); -int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, - u8 out_of_sync); +int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info); int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev, u8 ibport); int smc_clc_send_confirm(struct smc_sock *smc); diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 3c2e166..f0d16fb 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -174,15 +174,15 @@ int smc_close_active(struct smc_sock *smc) { struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; - long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT; struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int old_state; + long timeout; int rc = 0; - if (sock_flag(sk, SOCK_LINGER) && - !(current->flags & PF_EXITING)) - timeout = sk->sk_lingertime; + timeout = current->flags & PF_EXITING ? + 0 : sock_flag(sk, SOCK_LINGER) ? + sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT; again: old_state = sk->sk_state; @@ -208,7 +208,7 @@ again: case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); release_sock(sk); - cancel_work_sync(&conn->tx_work); + cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state == SMC_ACTIVE) { /* send close request */ @@ -234,7 +234,7 @@ again: if (!smc_cdc_rxed_any_close(conn)) smc_close_stream_wait(smc, timeout); release_sock(sk); - cancel_work_sync(&conn->tx_work); + cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_err != ECONNABORTED) { /* confirm close from peer */ @@ -263,7 +263,9 @@ again: /* peer sending PeerConnectionClosed will cause transition */ break; case SMC_PROCESSABORT: - cancel_work_sync(&conn->tx_work); + release_sock(sk); + cancel_delayed_work_sync(&conn->tx_work); + lock_sock(sk); smc_close_abort(conn); sk->sk_state = SMC_CLOSED; smc_close_wait_tx_pends(smc); @@ -411,13 +413,14 @@ void smc_close_sock_put_work(struct work_struct *work) int smc_close_shutdown_write(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; - long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT; struct sock *sk = &smc->sk; int old_state; + long timeout; int rc = 0; - if (sock_flag(sk, SOCK_LINGER)) - timeout = sk->sk_lingertime; + timeout = current->flags & PF_EXITING ? + 0 : sock_flag(sk, SOCK_LINGER) ? + sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT; again: old_state = sk->sk_state; @@ -425,7 +428,7 @@ again: case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); release_sock(sk); - cancel_work_sync(&conn->tx_work); + cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); /* send close wr request */ rc = smc_close_wr(conn); @@ -439,7 +442,7 @@ again: if (!smc_cdc_rxed_any_close(conn)) smc_close_stream_wait(smc, timeout); release_sock(sk); - cancel_work_sync(&conn->tx_work); + cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); /* confirm close from peer */ rc = smc_close_wr(conn); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 1a16d51..20b66e7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -25,8 +25,9 @@ #include "smc_cdc.h" #include "smc_close.h" -#define SMC_LGR_NUM_INCR 256 -#define SMC_LGR_FREE_DELAY (600 * HZ) +#define SMC_LGR_NUM_INCR 256 +#define SMC_LGR_FREE_DELAY_SERV (600 * HZ) +#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10) static u32 smc_lgr_num; /* unique link group number */ @@ -107,8 +108,15 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) __smc_lgr_unregister_conn(conn); } write_unlock_bh(&lgr->conns_lock); - if (reduced && !lgr->conns_num) - schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY); + if (!reduced || lgr->conns_num) + return; + /* client link group creation always follows the server link group + * creation. For client use a somewhat higher removal delay time, + * otherwise there is a risk of out-of-sync link groups. + */ + mod_delayed_work(system_wq, &lgr->free_work, + lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT : + SMC_LGR_FREE_DELAY_SERV); } static void smc_lgr_free_work(struct work_struct *work) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 547e0e1..0b58522 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -380,6 +380,7 @@ static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport); if (ndev) { memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN); + dev_put(ndev); } else if (!rc) { memcpy(&smcibdev->mac[ibport - 1][0], &smcibdev->gid[ibport - 1].raw[8], 3); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 78f7af2..31f8453 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -181,8 +181,10 @@ static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem) sizeof(new_pnetelem->ndev->name)) || smc_pnet_same_ibname(pnetelem, new_pnetelem->smcibdev->ibdev->name, - new_pnetelem->ib_port)) + new_pnetelem->ib_port)) { + dev_put(pnetelem->ndev); goto found; + } } list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist); rc = 0; diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index b17a333..3e631ae 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -148,6 +148,8 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, read_done = sock_intr_errno(timeo); break; } + if (!timeo) + return -EAGAIN; } if (!atomic_read(&conn->bytes_to_rcv)) { diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 3c656be..38665732 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -24,6 +24,8 @@ #include "smc_cdc.h" #include "smc_tx.h" +#define SMC_TX_WORK_DELAY HZ + /***************************** sndbuf producer *******************************/ /* callback implementation for sk.sk_write_space() @@ -406,7 +408,8 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) goto out_unlock; } rc = 0; - schedule_work(&conn->tx_work); + schedule_delayed_work(&conn->tx_work, + SMC_TX_WORK_DELAY); } goto out_unlock; } @@ -430,7 +433,7 @@ out_unlock: */ static void smc_tx_work(struct work_struct *work) { - struct smc_connection *conn = container_of(work, + struct smc_connection *conn = container_of(to_delayed_work(work), struct smc_connection, tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); @@ -468,7 +471,8 @@ void smc_tx_consumer_update(struct smc_connection *conn) if (!rc) rc = smc_cdc_msg_send(conn, wr_buf, pend); if (rc < 0) { - schedule_work(&conn->tx_work); + schedule_delayed_work(&conn->tx_work, + SMC_TX_WORK_DELAY); return; } smc_curs_write(&conn->rx_curs_confirmed, @@ -487,6 +491,6 @@ void smc_tx_consumer_update(struct smc_connection *conn) void smc_tx_init(struct smc_sock *smc) { smc->sk.sk_write_space = smc_tx_write_space; - INIT_WORK(&smc->conn.tx_work, smc_tx_work); + INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); spin_lock_init(&smc->conn.send_lock); } diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index ab56bda..525d91e 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -244,7 +244,7 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv) int rc; ib_req_notify_cq(link->smcibdev->roce_cq_send, - IB_CQ_SOLICITED_MASK | IB_CQ_REPORT_MISSED_EVENTS); + IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS); pend = container_of(priv, struct smc_wr_tx_pend, priv); rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx], &failed_wr); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 5a936a6..df062e0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -401,7 +401,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (unlikely(n != mw->mw_nents)) goto out_mapmr_err; - dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n", + dprintk("RPC: %s: Using frmr %p to map %u segments (%llu bytes)\n", __func__, frmr, mw->mw_nents, mr->length); key = (u8)(mr->rkey & 0x000000FF); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0df8023..6908742 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9987,6 +9987,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) if (err) return err; + if (!setup.chandef.chan) + return -EINVAL; + err = validate_beacon_tx_rate(rdev, setup.chandef.chan->band, &setup.beacon_rate); if (err) @@ -10903,6 +10906,9 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) if (err) return err; + if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] || + !tb[NL80211_REKEY_DATA_KCK]) + return -EINVAL; if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN) return -ERANGE; if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2e3a10e7..061d0c3 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -265,6 +265,8 @@ objtool_args += --no-fp endif ifdef CONFIG_GCOV_KERNEL objtool_args += --no-unreachable +else +objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory diff --git a/scripts/dtc/dtx_diff b/scripts/dtc/dtx_diff index f9a3d8d..8c4fbad 100755 --- a/scripts/dtc/dtx_diff +++ b/scripts/dtc/dtx_diff @@ -86,6 +86,7 @@ eod compile_to_dts() { dtx="$1" + dtc_include="$2" if [ -d "${dtx}" ] ; then @@ -113,7 +114,7 @@ compile_to_dts() { # ----- input is DTS (source) if ( cpp ${cpp_flags} -x assembler-with-cpp ${dtx} \ - | ${DTC} -I dts ) ; then + | ${DTC} ${dtc_include} -I dts ) ; then return fi @@ -320,18 +321,13 @@ fi cpp_flags="\ -nostdinc \ - -I${srctree}/arch/${ARCH}/boot/dts \ -I${srctree}/scripts/dtc/include-prefixes \ - -I${srctree}/drivers/of/testcase-data \ -undef -D__DTS__" -dtc_flags="\ - -i ${srctree}/arch/${ARCH}/boot/dts/ \ - -i ${srctree}/kernel/dts \ - ${dtx_path_1_dtc_include} \ - ${dtx_path_2_dtc_include}" - -DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -" +DTC="\ + ${DTC} \ + -i ${srctree}/scripts/dtc/include-prefixes \ + -O dts -qq -f ${dtc_sort} -o -" # ----- do the diff or decompile @@ -339,11 +335,11 @@ DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -" if (( ${cmd_diff} )) ; then diff ${diff_flags} --label "${dtx_file_1}" --label "${dtx_file_2}" \ - <(compile_to_dts "${dtx_file_1}") \ - <(compile_to_dts "${dtx_file_2}") + <(compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}") \ + <(compile_to_dts "${dtx_file_2}" "${dtx_path_2_dtc_include}") else - compile_to_dts "${dtx_file_1}" + compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}" fi diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore index 9cdec70..d5b291e 100644 --- a/security/apparmor/.gitignore +++ b/security/apparmor/.gitignore @@ -1,5 +1,6 @@ # # Generated include files # +net_names.h capability_names.h rlim_names.h diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile index a16b195..dafdd38 100644 --- a/security/apparmor/Makefile +++ b/security/apparmor/Makefile @@ -4,11 +4,44 @@ obj-$(CONFIG_SECURITY_APPARMOR) += apparmor.o apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \ path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \ - resource.o secid.o file.o policy_ns.o label.o + resource.o secid.o file.o policy_ns.o label.o mount.o net.o apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o -clean-files := capability_names.h rlim_names.h +clean-files := capability_names.h rlim_names.h net_names.h +# Build a lower case string table of address family names +# Transform lines from +# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ +# #define AF_INET 2 /* Internet IP Protocol */ +# to +# [1] = "local", +# [2] = "inet", +# +# and build the securityfs entries for the mapping. +# Transforms lines from +# #define AF_INET 2 /* Internet IP Protocol */ +# to +# #define AA_SFS_AF_MASK "local inet" +quiet_cmd_make-af = GEN $@ +cmd_make-af = echo "static const char *address_family_names[] = {" > $@ ;\ + sed $< >>$@ -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \ + 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\ + echo "};" >> $@ ;\ + printf '%s' '\#define AA_SFS_AF_MASK "' >> $@ ;\ + sed -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \ + 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/\L\1/p'\ + $< | tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@ + +# Build a lower case string table of sock type names +# Transform lines from +# SOCK_STREAM = 1, +# to +# [1] = "stream", +quiet_cmd_make-sock = GEN $@ +cmd_make-sock = echo "static const char *sock_type_names[] = {" >> $@ ;\ + sed $^ >>$@ -r -n \ + -e 's/^\tSOCK_([A-Z0-9_]+)[\t]+=[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\ + echo "};" >> $@ # Build a lower case string table of capability names # Transforms lines from @@ -61,6 +94,7 @@ cmd_make-rlim = echo "static const char *const rlim_names[RLIM_NLIMITS] = {" \ tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@ $(obj)/capability.o : $(obj)/capability_names.h +$(obj)/net.o : $(obj)/net_names.h $(obj)/resource.o : $(obj)/rlim_names.h $(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \ $(src)/Makefile @@ -68,3 +102,8 @@ $(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \ $(obj)/rlim_names.h : $(srctree)/include/uapi/asm-generic/resource.h \ $(src)/Makefile $(call cmd,make-rlim) +$(obj)/net_names.h : $(srctree)/include/linux/socket.h \ + $(srctree)/include/linux/net.h \ + $(src)/Makefile + $(call cmd,make-af) + $(call cmd,make-sock) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 853c2ec..518d592 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -32,6 +32,7 @@ #include "include/audit.h" #include "include/context.h" #include "include/crypto.h" +#include "include/ipc.h" #include "include/policy_ns.h" #include "include/label.h" #include "include/policy.h" @@ -248,8 +249,10 @@ static struct dentry *aafs_create(const char *name, umode_t mode, inode_lock(dir); dentry = lookup_one_len(name, parent, strlen(name)); - if (IS_ERR(dentry)) + if (IS_ERR(dentry)) { + error = PTR_ERR(dentry); goto fail_lock; + } if (d_really_is_positive(dentry)) { error = -EEXIST; @@ -1443,6 +1446,10 @@ void __aafs_profile_migrate_dents(struct aa_profile *old, { int i; + AA_BUG(!old); + AA_BUG(!new); + AA_BUG(!mutex_is_locked(&profiles_ns(old)->lock)); + for (i = 0; i < AAFS_PROF_SIZEOF; i++) { new->dents[i] = old->dents[i]; if (new->dents[i]) @@ -1506,6 +1513,9 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent) struct dentry *dent = NULL, *dir; int error; + AA_BUG(!profile); + AA_BUG(!mutex_is_locked(&profiles_ns(profile)->lock)); + if (!parent) { struct aa_profile *p; p = aa_deref_parent(profile); @@ -1731,6 +1741,7 @@ void __aafs_ns_rmdir(struct aa_ns *ns) if (!ns) return; + AA_BUG(!mutex_is_locked(&ns->lock)); list_for_each_entry(child, &ns->base.profiles, base.list) __aafs_profile_rmdir(child); @@ -1903,6 +1914,10 @@ static struct aa_ns *__next_ns(struct aa_ns *root, struct aa_ns *ns) { struct aa_ns *parent, *next; + AA_BUG(!root); + AA_BUG(!ns); + AA_BUG(ns != root && !mutex_is_locked(&ns->parent->lock)); + /* is next namespace a child */ if (!list_empty(&ns->sub_ns)) { next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list); @@ -1937,6 +1952,9 @@ static struct aa_ns *__next_ns(struct aa_ns *root, struct aa_ns *ns) static struct aa_profile *__first_profile(struct aa_ns *root, struct aa_ns *ns) { + AA_BUG(!root); + AA_BUG(ns && !mutex_is_locked(&ns->lock)); + for (; ns; ns = __next_ns(root, ns)) { if (!list_empty(&ns->base.profiles)) return list_first_entry(&ns->base.profiles, @@ -1959,6 +1977,8 @@ static struct aa_profile *__next_profile(struct aa_profile *p) struct aa_profile *parent; struct aa_ns *ns = p->ns; + AA_BUG(!mutex_is_locked(&profiles_ns(p)->lock)); + /* is next profile a child */ if (!list_empty(&p->base.profiles)) return list_first_entry(&p->base.profiles, typeof(*p), @@ -2127,6 +2147,11 @@ static struct aa_sfs_entry aa_sfs_entry_ptrace[] = { { } }; +static struct aa_sfs_entry aa_sfs_entry_signal[] = { + AA_SFS_FILE_STRING("mask", AA_SFS_SIG_MASK), + { } +}; + static struct aa_sfs_entry aa_sfs_entry_domain[] = { AA_SFS_FILE_BOOLEAN("change_hat", 1), AA_SFS_FILE_BOOLEAN("change_hatv", 1), @@ -2151,9 +2176,14 @@ static struct aa_sfs_entry aa_sfs_entry_policy[] = { { } }; +static struct aa_sfs_entry aa_sfs_entry_mount[] = { + AA_SFS_FILE_STRING("mask", "mount umount pivot_root"), + { } +}; + static struct aa_sfs_entry aa_sfs_entry_ns[] = { AA_SFS_FILE_BOOLEAN("profile", 1), - AA_SFS_FILE_BOOLEAN("pivot_root", 1), + AA_SFS_FILE_BOOLEAN("pivot_root", 0), { } }; @@ -2172,22 +2202,25 @@ static struct aa_sfs_entry aa_sfs_entry_features[] = { AA_SFS_DIR("policy", aa_sfs_entry_policy), AA_SFS_DIR("domain", aa_sfs_entry_domain), AA_SFS_DIR("file", aa_sfs_entry_file), + AA_SFS_DIR("network", aa_sfs_entry_network), + AA_SFS_DIR("mount", aa_sfs_entry_mount), AA_SFS_DIR("namespaces", aa_sfs_entry_ns), AA_SFS_FILE_U64("capability", VFS_CAP_FLAGS_MASK), AA_SFS_DIR("rlimit", aa_sfs_entry_rlimit), AA_SFS_DIR("caps", aa_sfs_entry_caps), AA_SFS_DIR("ptrace", aa_sfs_entry_ptrace), + AA_SFS_DIR("signal", aa_sfs_entry_signal), AA_SFS_DIR("query", aa_sfs_entry_query), { } }; static struct aa_sfs_entry aa_sfs_entry_apparmor[] = { - AA_SFS_FILE_FOPS(".access", 0640, &aa_sfs_access), + AA_SFS_FILE_FOPS(".access", 0666, &aa_sfs_access), AA_SFS_FILE_FOPS(".stacked", 0444, &seq_ns_stacked_fops), AA_SFS_FILE_FOPS(".ns_stacked", 0444, &seq_ns_nsstacked_fops), - AA_SFS_FILE_FOPS(".ns_level", 0666, &seq_ns_level_fops), - AA_SFS_FILE_FOPS(".ns_name", 0640, &seq_ns_name_fops), - AA_SFS_FILE_FOPS("profiles", 0440, &aa_sfs_profiles_fops), + AA_SFS_FILE_FOPS(".ns_level", 0444, &seq_ns_level_fops), + AA_SFS_FILE_FOPS(".ns_name", 0444, &seq_ns_name_fops), + AA_SFS_FILE_FOPS("profiles", 0444, &aa_sfs_profiles_fops), AA_SFS_DIR("features", aa_sfs_entry_features), { } }; diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 17a601c..dd754b7 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -374,8 +374,8 @@ static const char *next_name(int xtype, const char *name) * * Returns: refcounted label, or NULL on failure (MAYBE NULL) */ -static struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex, - const char **name) +struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex, + const char **name) { struct aa_label *label = NULL; u32 xtype = xindex & AA_X_TYPE_MASK; diff --git a/security/apparmor/file.c b/security/apparmor/file.c index 3382518..db80221 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -21,6 +21,7 @@ #include "include/context.h" #include "include/file.h" #include "include/match.h" +#include "include/net.h" #include "include/path.h" #include "include/policy.h" #include "include/label.h" @@ -566,6 +567,32 @@ static int __file_path_perm(const char *op, struct aa_label *label, return error; } +static int __file_sock_perm(const char *op, struct aa_label *label, + struct aa_label *flabel, struct file *file, + u32 request, u32 denied) +{ + struct socket *sock = (struct socket *) file->private_data; + int error; + + AA_BUG(!sock); + + /* revalidation due to label out of date. No revocation at this time */ + if (!denied && aa_label_is_subset(flabel, label)) + return 0; + + /* TODO: improve to skip profiles cached in flabel */ + error = aa_sock_file_perm(label, op, request, sock); + if (denied) { + /* TODO: improve to skip profiles checked above */ + /* check every profile in file label to is cached */ + last_error(error, aa_sock_file_perm(flabel, op, request, sock)); + } + if (!error) + update_file_ctx(file_ctx(file), label, request); + + return error; +} + /** * aa_file_perm - do permission revalidation check & audit for @file * @op: operation being checked @@ -610,6 +637,9 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file, error = __file_path_perm(op, label, flabel, file, request, denied); + else if (S_ISSOCK(file_inode(file)->i_mode)) + error = __file_sock_perm(op, label, flabel, file, request, + denied); done: rcu_read_unlock(); diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h index aaf893f..829082c 100644 --- a/security/apparmor/include/apparmor.h +++ b/security/apparmor/include/apparmor.h @@ -27,7 +27,9 @@ #define AA_CLASS_NET 4 #define AA_CLASS_RLIMITS 5 #define AA_CLASS_DOMAIN 6 +#define AA_CLASS_MOUNT 7 #define AA_CLASS_PTRACE 9 +#define AA_CLASS_SIGNAL 10 #define AA_CLASS_LABEL 16 #define AA_CLASS_LAST AA_CLASS_LABEL diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index c68839a..ff4316e 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -71,6 +71,10 @@ enum audit_type { #define OP_FMPROT "file_mprotect" #define OP_INHERIT "file_inherit" +#define OP_PIVOTROOT "pivotroot" +#define OP_MOUNT "mount" +#define OP_UMOUNT "umount" + #define OP_CREATE "create" #define OP_POST_CREATE "post_create" #define OP_BIND "bind" @@ -86,6 +90,7 @@ enum audit_type { #define OP_SHUTDOWN "socket_shutdown" #define OP_PTRACE "ptrace" +#define OP_SIGNAL "signal" #define OP_EXEC "exec" @@ -116,20 +121,36 @@ struct apparmor_audit_data { /* these entries require a custom callback fn */ struct { struct aa_label *peer; - struct { - const char *target; - kuid_t ouid; - } fs; + union { + struct { + kuid_t ouid; + const char *target; + } fs; + struct { + int type, protocol; + struct sock *peer_sk; + void *addr; + int addrlen; + } net; + int signal; + struct { + int rlim; + unsigned long max; + } rlim; + }; }; struct { - const char *name; - long pos; + struct aa_profile *profile; const char *ns; + long pos; } iface; struct { - int rlim; - unsigned long max; - } rlim; + const char *src_name; + const char *type; + const char *trans; + const char *data; + unsigned long flags; + } mnt; }; }; diff --git a/security/apparmor/include/domain.h b/security/apparmor/include/domain.h index 24c5976..ac9862f 100644 --- a/security/apparmor/include/domain.h +++ b/security/apparmor/include/domain.h @@ -15,6 +15,8 @@ #include <linux/binfmts.h> #include <linux/types.h> +#include "label.h" + #ifndef __AA_DOMAIN_H #define __AA_DOMAIN_H @@ -29,6 +31,9 @@ struct aa_domain { #define AA_CHANGE_ONEXEC 4 #define AA_CHANGE_STACK 8 +struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex, + const char **name); + int apparmor_bprm_set_creds(struct linux_binprm *bprm); void aa_free_domain_entries(struct aa_domain *domain); diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h index 656fdb8..5ffc218 100644 --- a/security/apparmor/include/ipc.h +++ b/security/apparmor/include/ipc.h @@ -27,8 +27,14 @@ struct aa_profile; #define AA_PTRACE_PERM_MASK (AA_PTRACE_READ | AA_PTRACE_TRACE | \ AA_MAY_BE_READ | AA_MAY_BE_TRACED) +#define AA_SIGNAL_PERM_MASK (MAY_READ | MAY_WRITE) + +#define AA_SFS_SIG_MASK "hup int quit ill trap abrt bus fpe kill usr1 " \ + "segv usr2 pipe alrm term stkflt chld cont stop stp ttin ttou urg " \ + "xcpu xfsz vtalrm prof winch io pwr sys emt lost" int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee, u32 request); +int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig); #endif /* __AA_IPC_H */ diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h index 9a283b7..af22dcb 100644 --- a/security/apparmor/include/label.h +++ b/security/apparmor/include/label.h @@ -310,6 +310,7 @@ bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp); #define FLAG_SHOW_MODE 1 #define FLAG_VIEW_SUBNS 2 #define FLAG_HIDDEN_UNCONFINED 4 +#define FLAG_ABS_ROOT 8 int aa_label_snxprint(char *str, size_t size, struct aa_ns *view, struct aa_label *label, int flags); int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, diff --git a/security/apparmor/include/mount.h b/security/apparmor/include/mount.h new file mode 100644 index 0000000..25d6067 --- /dev/null +++ b/security/apparmor/include/mount.h @@ -0,0 +1,54 @@ +/* + * AppArmor security module + * + * This file contains AppArmor file mediation function definitions. + * + * Copyright 2017 Canonical Ltd. + * + * 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. + */ + +#ifndef __AA_MOUNT_H +#define __AA_MOUNT_H + +#include <linux/fs.h> +#include <linux/path.h> + +#include "domain.h" +#include "policy.h" + +/* mount perms */ +#define AA_MAY_PIVOTROOT 0x01 +#define AA_MAY_MOUNT 0x02 +#define AA_MAY_UMOUNT 0x04 +#define AA_AUDIT_DATA 0x40 +#define AA_MNT_CONT_MATCH 0x40 + +#define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN) + +int aa_remount(struct aa_label *label, const struct path *path, + unsigned long flags, void *data); + +int aa_bind_mount(struct aa_label *label, const struct path *path, + const char *old_name, unsigned long flags); + + +int aa_mount_change_type(struct aa_label *label, const struct path *path, + unsigned long flags); + +int aa_move_mount(struct aa_label *label, const struct path *path, + const char *old_name); + +int aa_new_mount(struct aa_label *label, const char *dev_name, + const struct path *path, const char *type, unsigned long flags, + void *data); + +int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags); + +int aa_pivotroot(struct aa_label *label, const struct path *old_path, + const struct path *new_path); + +#endif /* __AA_MOUNT_H */ diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h new file mode 100644 index 0000000..140c8efc --- /dev/null +++ b/security/apparmor/include/net.h @@ -0,0 +1,114 @@ +/* + * AppArmor security module + * + * This file contains AppArmor network mediation definitions. + * + * Copyright (C) 1998-2008 Novell/SUSE + * Copyright 2009-2017 Canonical Ltd. + * + * 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. + */ + +#ifndef __AA_NET_H +#define __AA_NET_H + +#include <net/sock.h> +#include <linux/path.h> + +#include "apparmorfs.h" +#include "label.h" +#include "perms.h" +#include "policy.h" + +#define AA_MAY_SEND AA_MAY_WRITE +#define AA_MAY_RECEIVE AA_MAY_READ + +#define AA_MAY_SHUTDOWN AA_MAY_DELETE + +#define AA_MAY_CONNECT AA_MAY_OPEN +#define AA_MAY_ACCEPT 0x00100000 + +#define AA_MAY_BIND 0x00200000 +#define AA_MAY_LISTEN 0x00400000 + +#define AA_MAY_SETOPT 0x01000000 +#define AA_MAY_GETOPT 0x02000000 + +#define NET_PERMS_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \ + AA_MAY_SHUTDOWN | AA_MAY_BIND | AA_MAY_LISTEN | \ + AA_MAY_CONNECT | AA_MAY_ACCEPT | AA_MAY_SETATTR | \ + AA_MAY_GETATTR | AA_MAY_SETOPT | AA_MAY_GETOPT) + +#define NET_FS_PERMS (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \ + AA_MAY_SHUTDOWN | AA_MAY_CONNECT | AA_MAY_RENAME |\ + AA_MAY_SETATTR | AA_MAY_GETATTR | AA_MAY_CHMOD | \ + AA_MAY_CHOWN | AA_MAY_CHGRP | AA_MAY_LOCK | \ + AA_MAY_MPROT) + +#define NET_PEER_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CONNECT | \ + AA_MAY_ACCEPT) +struct aa_sk_ctx { + struct aa_label *label; + struct aa_label *peer; + struct path path; +}; + +#define SK_CTX(X) ((X)->sk_security) +#define SOCK_ctx(X) SOCK_INODE(X)->i_security +#define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \ + struct lsm_network_audit NAME ## _net = { .sk = (SK), \ + .family = (F)}; \ + DEFINE_AUDIT_DATA(NAME, \ + ((SK) && (F) != AF_UNIX) ? LSM_AUDIT_DATA_NET : \ + LSM_AUDIT_DATA_NONE, \ + OP); \ + NAME.u.net = &(NAME ## _net); \ + aad(&NAME)->net.type = (T); \ + aad(&NAME)->net.protocol = (P) + +#define DEFINE_AUDIT_SK(NAME, OP, SK) \ + DEFINE_AUDIT_NET(NAME, OP, SK, (SK)->sk_family, (SK)->sk_type, \ + (SK)->sk_protocol) + +/* struct aa_net - network confinement data + * @allow: basic network families permissions + * @audit: which network permissions to force audit + * @quiet: which network permissions to quiet rejects + */ +struct aa_net { + u16 allow[AF_MAX]; + u16 audit[AF_MAX]; + u16 quiet[AF_MAX]; +}; + + +extern struct aa_sfs_entry aa_sfs_entry_network[]; + +void audit_net_cb(struct audit_buffer *ab, void *va); +int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, + u32 request, u16 family, int type); +int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, + int type, int protocol); +static inline int aa_profile_af_sk_perm(struct aa_profile *profile, + struct common_audit_data *sa, + u32 request, + struct sock *sk) +{ + return aa_profile_af_perm(profile, sa, request, sk->sk_family, + sk->sk_type); +} +int aa_sk_perm(const char *op, u32 request, struct sock *sk); + +int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, + struct socket *sock); + + +static inline void aa_free_net_rules(struct aa_net *new) +{ + /* NOP */ +} + +#endif /* __AA_NET_H */ diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h index 2b27bb7..af04d5a 100644 --- a/security/apparmor/include/perms.h +++ b/security/apparmor/include/perms.h @@ -135,9 +135,10 @@ extern struct aa_perms allperms; void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask); -void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask); +void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names, + u32 mask); void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, - u32 chrsmask, const char **names, u32 namesmask); + u32 chrsmask, const char * const *names, u32 namesmask); void aa_apply_modes_to_perms(struct aa_profile *profile, struct aa_perms *perms); void aa_compute_perms(struct aa_dfa *dfa, unsigned int state, diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index 17fe41a..4364088 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -30,6 +30,7 @@ #include "file.h" #include "lib.h" #include "label.h" +#include "net.h" #include "perms.h" #include "resource.h" @@ -111,6 +112,7 @@ struct aa_data { * @policy: general match rules governing policy * @file: The set of rules governing basic file access and domain transitions * @caps: capabilities for the profile + * @net: network controls for the profile * @rlimits: rlimits for the profile * * @dents: dentries for the profiles file entries in apparmorfs @@ -148,6 +150,7 @@ struct aa_profile { struct aa_policydb policy; struct aa_file_rules file; struct aa_caps caps; + struct aa_net net; struct aa_rlimit rlimits; struct aa_loaddata *rawdata; @@ -220,6 +223,16 @@ static inline unsigned int PROFILE_MEDIATES_SAFE(struct aa_profile *profile, return 0; } +static inline unsigned int PROFILE_MEDIATES_AF(struct aa_profile *profile, + u16 AF) { + unsigned int state = PROFILE_MEDIATES(profile, AA_CLASS_NET); + u16 be_af = cpu_to_be16(AF); + + if (!state) + return 0; + return aa_dfa_match_len(profile->policy.dfa, state, (char *) &be_af, 2); +} + /** * aa_get_profile - increment refcount on profile @p * @p: profile (MAYBE NULL) diff --git a/security/apparmor/include/sig_names.h b/security/apparmor/include/sig_names.h new file mode 100644 index 0000000..92e62fe --- /dev/null +++ b/security/apparmor/include/sig_names.h @@ -0,0 +1,98 @@ +#include <linux/signal.h> + +#define SIGUNKNOWN 0 +#define MAXMAPPED_SIG 35 +/* provide a mapping of arch signal to internal signal # for mediation + * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO + * map to the same entry those that may/or may not get a separate entry + */ +static const int sig_map[MAXMAPPED_SIG] = { + [0] = MAXMAPPED_SIG, /* existence test */ + [SIGHUP] = 1, + [SIGINT] = 2, + [SIGQUIT] = 3, + [SIGILL] = 4, + [SIGTRAP] = 5, /* -, 5, - */ + [SIGABRT] = 6, /* SIGIOT: -, 6, - */ + [SIGBUS] = 7, /* 10, 7, 10 */ + [SIGFPE] = 8, + [SIGKILL] = 9, + [SIGUSR1] = 10, /* 30, 10, 16 */ + [SIGSEGV] = 11, + [SIGUSR2] = 12, /* 31, 12, 17 */ + [SIGPIPE] = 13, + [SIGALRM] = 14, + [SIGTERM] = 15, +#ifdef SIGSTKFLT + [SIGSTKFLT] = 16, /* -, 16, - */ +#endif + [SIGCHLD] = 17, /* 20, 17, 18. SIGCHLD -, -, 18 */ + [SIGCONT] = 18, /* 19, 18, 25 */ + [SIGSTOP] = 19, /* 17, 19, 23 */ + [SIGTSTP] = 20, /* 18, 20, 24 */ + [SIGTTIN] = 21, /* 21, 21, 26 */ + [SIGTTOU] = 22, /* 22, 22, 27 */ + [SIGURG] = 23, /* 16, 23, 21 */ + [SIGXCPU] = 24, /* 24, 24, 30 */ + [SIGXFSZ] = 25, /* 25, 25, 31 */ + [SIGVTALRM] = 26, /* 26, 26, 28 */ + [SIGPROF] = 27, /* 27, 27, 29 */ + [SIGWINCH] = 28, /* 28, 28, 20 */ + [SIGIO] = 29, /* SIGPOLL: 23, 29, 22 */ + [SIGPWR] = 30, /* 29, 30, 19. SIGINFO 29, -, - */ +#ifdef SIGSYS + [SIGSYS] = 31, /* 12, 31, 12. often SIG LOST/UNUSED */ +#endif +#ifdef SIGEMT + [SIGEMT] = 32, /* 7, - , 7 */ +#endif +#if defined(SIGLOST) && SIGPWR != SIGLOST /* sparc */ + [SIGLOST] = 33, /* unused on Linux */ +#endif +#if defined(SIGUNUSED) && \ + defined(SIGLOST) && defined(SIGSYS) && SIGLOST != SIGSYS + [SIGUNUSED] = 34, /* -, 31, - */ +#endif +}; + +/* this table is ordered post sig_map[sig] mapping */ +static const char *const sig_names[MAXMAPPED_SIG + 1] = { + "unknown", + "hup", + "int", + "quit", + "ill", + "trap", + "abrt", + "bus", + "fpe", + "kill", + "usr1", + "segv", + "usr2", + "pipe", + "alrm", + "term", + "stkflt", + "chld", + "cont", + "stop", + "stp", + "ttin", + "ttou", + "urg", + "xcpu", + "xfsz", + "vtalrm", + "prof", + "winch", + "io", + "pwr", + "sys", + "emt", + "lost", + "unused", + + "exists", /* always last existence test mapped to MAXMAPPED_SIG */ +}; + diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c index 11e66b5..66fb9ed 100644 --- a/security/apparmor/ipc.c +++ b/security/apparmor/ipc.c @@ -20,6 +20,7 @@ #include "include/context.h" #include "include/policy.h" #include "include/ipc.h" +#include "include/sig_names.h" /** * audit_ptrace_mask - convert mask to permission string @@ -121,3 +122,101 @@ int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee, } +static inline int map_signal_num(int sig) +{ + if (sig > SIGRTMAX) + return SIGUNKNOWN; + else if (sig >= SIGRTMIN) + return sig - SIGRTMIN + 128; /* rt sigs mapped to 128 */ + else if (sig <= MAXMAPPED_SIG) + return sig_map[sig]; + return SIGUNKNOWN; +} + +/** + * audit_file_mask - convert mask to permission string + * @buffer: buffer to write string to (NOT NULL) + * @mask: permission mask to convert + */ +static void audit_signal_mask(struct audit_buffer *ab, u32 mask) +{ + if (mask & MAY_READ) + audit_log_string(ab, "receive"); + if (mask & MAY_WRITE) + audit_log_string(ab, "send"); +} + +/** + * audit_cb - call back for signal specific audit fields + * @ab: audit_buffer (NOT NULL) + * @va: audit struct to audit values of (NOT NULL) + */ +static void audit_signal_cb(struct audit_buffer *ab, void *va) +{ + struct common_audit_data *sa = va; + + if (aad(sa)->request & AA_SIGNAL_PERM_MASK) { + audit_log_format(ab, " requested_mask="); + audit_signal_mask(ab, aad(sa)->request); + if (aad(sa)->denied & AA_SIGNAL_PERM_MASK) { + audit_log_format(ab, " denied_mask="); + audit_signal_mask(ab, aad(sa)->denied); + } + } + if (aad(sa)->signal <= MAXMAPPED_SIG) + audit_log_format(ab, " signal=%s", sig_names[aad(sa)->signal]); + else + audit_log_format(ab, " signal=rtmin+%d", + aad(sa)->signal - 128); + audit_log_format(ab, " peer="); + aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + FLAGS_NONE, GFP_ATOMIC); +} + +/* TODO: update to handle compound name&name2, conditionals */ +static void profile_match_signal(struct aa_profile *profile, const char *label, + int signal, struct aa_perms *perms) +{ + unsigned int state; + + /* TODO: secondary cache check <profile, profile, perm> */ + state = aa_dfa_next(profile->policy.dfa, + profile->policy.start[AA_CLASS_SIGNAL], + signal); + state = aa_dfa_match(profile->policy.dfa, state, label); + aa_compute_perms(profile->policy.dfa, state, perms); +} + +static int profile_signal_perm(struct aa_profile *profile, + struct aa_profile *peer, u32 request, + struct common_audit_data *sa) +{ + struct aa_perms perms; + + if (profile_unconfined(profile) || + !PROFILE_MEDIATES(profile, AA_CLASS_SIGNAL)) + return 0; + + aad(sa)->peer = &peer->label; + profile_match_signal(profile, peer->base.hname, aad(sa)->signal, + &perms); + aa_apply_modes_to_perms(profile, &perms); + return aa_check_perms(profile, &perms, request, sa, audit_signal_cb); +} + +static int aa_signal_cross_perm(struct aa_profile *sender, + struct aa_profile *target, + struct common_audit_data *sa) +{ + return xcheck(profile_signal_perm(sender, target, MAY_WRITE, sa), + profile_signal_perm(target, sender, MAY_READ, sa)); +} + +int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig) +{ + DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, OP_SIGNAL); + + aad(&sa)->signal = map_signal_num(sig); + return xcheck_labels_profiles(sender, target, aa_signal_cross_perm, + &sa); +} diff --git a/security/apparmor/label.c b/security/apparmor/label.c index e052eab..c5b99b9 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -49,7 +49,7 @@ static void free_proxy(struct aa_proxy *proxy) /* p->label will not updated any more as p is dead */ aa_put_label(rcu_dereference_protected(proxy->label, true)); memset(proxy, 0, sizeof(*proxy)); - proxy->label = (struct aa_label *) PROXY_POISON; + RCU_INIT_POINTER(proxy->label, (struct aa_label *)PROXY_POISON); kfree(proxy); } } @@ -1450,9 +1450,11 @@ bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp) * cached label name is present and visible * @label->hname only exists if label is namespace hierachical */ -static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label) +static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label, + int flags) { - if (label->hname && labels_ns(label) == ns) + if (label->hname && (!ns || labels_ns(label) == ns) && + !(flags & ~FLAG_SHOW_MODE)) return true; return false; @@ -1495,7 +1497,7 @@ static int aa_profile_snxprint(char *str, size_t size, struct aa_ns *view, view = profiles_ns(profile); if (view != profile->ns && - (!prev_ns || (prev_ns && *prev_ns != profile->ns))) { + (!prev_ns || (*prev_ns != profile->ns))) { if (prev_ns) *prev_ns = profile->ns; ns_name = aa_ns_name(view, profile->ns, @@ -1605,8 +1607,13 @@ int aa_label_snxprint(char *str, size_t size, struct aa_ns *ns, AA_BUG(!str && size != 0); AA_BUG(!label); - if (!ns) + if (flags & FLAG_ABS_ROOT) { + ns = root_ns; + len = snprintf(str, size, "="); + update_for_len(total, len, size, str); + } else if (!ns) { ns = labels_ns(label); + } label_for_each(i, label, profile) { if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) { @@ -1710,10 +1717,8 @@ void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, AA_BUG(!ab); AA_BUG(!label); - if (!ns) - ns = labels_ns(label); - - if (!use_label_hname(ns, label) || display_mode(ns, label, flags)) { + if (!use_label_hname(ns, label, flags) || + display_mode(ns, label, flags)) { len = aa_label_asxprint(&name, ns, label, flags, gfp); if (len == -1) { AA_DEBUG("label print error"); @@ -1738,10 +1743,7 @@ void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, AA_BUG(!f); AA_BUG(!label); - if (!ns) - ns = labels_ns(label); - - if (!use_label_hname(ns, label)) { + if (!use_label_hname(ns, label, flags)) { char *str; int len; @@ -1764,10 +1766,7 @@ void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, { AA_BUG(!label); - if (!ns) - ns = labels_ns(label); - - if (!use_label_hname(ns, label)) { + if (!use_label_hname(ns, label, flags)) { char *str; int len; @@ -1874,6 +1873,9 @@ struct aa_label *aa_label_parse(struct aa_label *base, const char *str, if (*str == '&') str++; } + if (*str == '=') + base = &root_ns->unconfined->label; + error = vec_setup(profile, vec, len, gfp); if (error) return ERR_PTR(error); diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index 08ca26b..8818621 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -211,7 +211,8 @@ void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask) *str = '\0'; } -void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask) +void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names, + u32 mask) { const char *fmt = "%s"; unsigned int i, perm = 1; @@ -229,7 +230,7 @@ void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask) } void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, - u32 chrsmask, const char **names, u32 namesmask) + u32 chrsmask, const char * const *names, u32 namesmask) { char str[33]; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 7a82c0f..72b915d 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -33,11 +33,13 @@ #include "include/context.h" #include "include/file.h" #include "include/ipc.h" +#include "include/net.h" #include "include/path.h" #include "include/label.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/procattr.h" +#include "include/mount.h" /* Flag indicating whether initialization completed */ int apparmor_initialized; @@ -511,6 +513,65 @@ static int apparmor_file_mprotect(struct vm_area_struct *vma, !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0); } +static int apparmor_sb_mount(const char *dev_name, const struct path *path, + const char *type, unsigned long flags, void *data) +{ + struct aa_label *label; + int error = 0; + + /* Discard magic */ + if ((flags & MS_MGC_MSK) == MS_MGC_VAL) + flags &= ~MS_MGC_MSK; + + flags &= ~AA_MS_IGNORE_MASK; + + label = __begin_current_label_crit_section(); + if (!unconfined(label)) { + if (flags & MS_REMOUNT) + error = aa_remount(label, path, flags, data); + else if (flags & MS_BIND) + error = aa_bind_mount(label, path, dev_name, flags); + else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | + MS_UNBINDABLE)) + error = aa_mount_change_type(label, path, flags); + else if (flags & MS_MOVE) + error = aa_move_mount(label, path, dev_name); + else + error = aa_new_mount(label, dev_name, path, type, + flags, data); + } + __end_current_label_crit_section(label); + + return error; +} + +static int apparmor_sb_umount(struct vfsmount *mnt, int flags) +{ + struct aa_label *label; + int error = 0; + + label = __begin_current_label_crit_section(); + if (!unconfined(label)) + error = aa_umount(label, mnt, flags); + __end_current_label_crit_section(label); + + return error; +} + +static int apparmor_sb_pivotroot(const struct path *old_path, + const struct path *new_path) +{ + struct aa_label *label; + int error = 0; + + label = aa_get_current_label(); + if (!unconfined(label)) + error = aa_pivotroot(label, old_path, new_path); + aa_put_label(label); + + return error; +} + static int apparmor_getprocattr(struct task_struct *task, char *name, char **value) { @@ -656,12 +717,398 @@ static int apparmor_task_setrlimit(struct task_struct *task, return error; } +static int apparmor_task_kill(struct task_struct *target, struct siginfo *info, + int sig, u32 secid) +{ + struct aa_label *cl, *tl; + int error; + + if (secid) + /* TODO: after secid to label mapping is done. + * Dealing with USB IO specific behavior + */ + return 0; + cl = __begin_current_label_crit_section(); + tl = aa_get_task_label(target); + error = aa_may_signal(cl, tl, sig); + aa_put_label(tl); + __end_current_label_crit_section(cl); + + return error; +} + +/** + * apparmor_sk_alloc_security - allocate and attach the sk_security field + */ +static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) +{ + struct aa_sk_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), flags); + if (!ctx) + return -ENOMEM; + + SK_CTX(sk) = ctx; + + return 0; +} + +/** + * apparmor_sk_free_security - free the sk_security field + */ +static void apparmor_sk_free_security(struct sock *sk) +{ + struct aa_sk_ctx *ctx = SK_CTX(sk); + + SK_CTX(sk) = NULL; + aa_put_label(ctx->label); + aa_put_label(ctx->peer); + path_put(&ctx->path); + kfree(ctx); +} + +/** + * apparmor_clone_security - clone the sk_security field + */ +static void apparmor_sk_clone_security(const struct sock *sk, + struct sock *newsk) +{ + struct aa_sk_ctx *ctx = SK_CTX(sk); + struct aa_sk_ctx *new = SK_CTX(newsk); + + new->label = aa_get_label(ctx->label); + new->peer = aa_get_label(ctx->peer); + new->path = ctx->path; + path_get(&new->path); +} + +static int aa_sock_create_perm(struct aa_label *label, int family, int type, + int protocol) +{ + AA_BUG(!label); + AA_BUG(in_interrupt()); + + return aa_af_perm(label, OP_CREATE, AA_MAY_CREATE, family, type, + protocol); +} + + +/** + * apparmor_socket_create - check perms before creating a new socket + */ +static int apparmor_socket_create(int family, int type, int protocol, int kern) +{ + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + if (!(kern || unconfined(label))) + error = aa_sock_create_perm(label, family, type, protocol); + end_current_label_crit_section(label); + + return error; +} + +/** + * apparmor_socket_post_create - setup the per-socket security struct + * + * Note: + * - kernel sockets currently labeled unconfined but we may want to + * move to a special kernel label + * - socket may not have sk here if created with sock_create_lite or + * sock_alloc. These should be accept cases which will be handled in + * sock_graft. + */ +static int apparmor_socket_post_create(struct socket *sock, int family, + int type, int protocol, int kern) +{ + struct aa_label *label; + + if (kern) { + struct aa_ns *ns = aa_get_current_ns(); + + label = aa_get_label(ns_unconfined(ns)); + aa_put_ns(ns); + } else + label = aa_get_current_label(); + + if (sock->sk) { + struct aa_sk_ctx *ctx = SK_CTX(sock->sk); + + aa_put_label(ctx->label); + ctx->label = aa_get_label(label); + } + aa_put_label(label); + + return 0; +} + +/** + * apparmor_socket_bind - check perms before bind addr to socket + */ +static int apparmor_socket_bind(struct socket *sock, + struct sockaddr *address, int addrlen) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(!address); + AA_BUG(in_interrupt()); + + return aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk); +} + +/** + * apparmor_socket_connect - check perms before connecting @sock to @address + */ +static int apparmor_socket_connect(struct socket *sock, + struct sockaddr *address, int addrlen) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(!address); + AA_BUG(in_interrupt()); + + return aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk); +} + +/** + * apparmor_socket_list - check perms before allowing listen + */ +static int apparmor_socket_listen(struct socket *sock, int backlog) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(in_interrupt()); + + return aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk); +} + +/** + * apparmor_socket_accept - check perms before accepting a new connection. + * + * Note: while @newsock is created and has some information, the accept + * has not been done. + */ +static int apparmor_socket_accept(struct socket *sock, struct socket *newsock) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(!newsock); + AA_BUG(in_interrupt()); + + return aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk); +} + +static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock, + struct msghdr *msg, int size) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(!msg); + AA_BUG(in_interrupt()); + + return aa_sk_perm(op, request, sock->sk); +} + +/** + * apparmor_socket_sendmsg - check perms before sending msg to another socket + */ +static int apparmor_socket_sendmsg(struct socket *sock, + struct msghdr *msg, int size) +{ + return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); +} + +/** + * apparmor_socket_recvmsg - check perms before receiving a message + */ +static int apparmor_socket_recvmsg(struct socket *sock, + struct msghdr *msg, int size, int flags) +{ + return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size); +} + +/* revaliation, get/set attr, shutdown */ +static int aa_sock_perm(const char *op, u32 request, struct socket *sock) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(in_interrupt()); + + return aa_sk_perm(op, request, sock->sk); +} + +/** + * apparmor_socket_getsockname - check perms before getting the local address + */ +static int apparmor_socket_getsockname(struct socket *sock) +{ + return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock); +} + +/** + * apparmor_socket_getpeername - check perms before getting remote address + */ +static int apparmor_socket_getpeername(struct socket *sock) +{ + return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock); +} + +/* revaliation, get/set attr, opt */ +static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock, + int level, int optname) +{ + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(in_interrupt()); + + return aa_sk_perm(op, request, sock->sk); +} + +/** + * apparmor_getsockopt - check perms before getting socket options + */ +static int apparmor_socket_getsockopt(struct socket *sock, int level, + int optname) +{ + return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock, + level, optname); +} + +/** + * apparmor_setsockopt - check perms before setting socket options + */ +static int apparmor_socket_setsockopt(struct socket *sock, int level, + int optname) +{ + return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock, + level, optname); +} + +/** + * apparmor_socket_shutdown - check perms before shutting down @sock conn + */ +static int apparmor_socket_shutdown(struct socket *sock, int how) +{ + return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock); +} + +/** + * apparmor_socket_sock_recv_skb - check perms before associating skb to sk + * + * Note: can not sleep may be called with locks held + * + * dont want protocol specific in __skb_recv_datagram() + * to deny an incoming connection socket_sock_rcv_skb() + */ +static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + return 0; +} + + +static struct aa_label *sk_peer_label(struct sock *sk) +{ + struct aa_sk_ctx *ctx = SK_CTX(sk); + + if (ctx->peer) + return ctx->peer; + + return ERR_PTR(-ENOPROTOOPT); +} + +/** + * apparmor_socket_getpeersec_stream - get security context of peer + * + * Note: for tcp only valid if using ipsec or cipso on lan + */ +static int apparmor_socket_getpeersec_stream(struct socket *sock, + char __user *optval, + int __user *optlen, + unsigned int len) +{ + char *name; + int slen, error = 0; + struct aa_label *label; + struct aa_label *peer; + + label = begin_current_label_crit_section(); + peer = sk_peer_label(sock->sk); + if (IS_ERR(peer)) { + error = PTR_ERR(peer); + goto done; + } + slen = aa_label_asxprint(&name, labels_ns(label), peer, + FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | + FLAG_HIDDEN_UNCONFINED, GFP_KERNEL); + /* don't include terminating \0 in slen, it breaks some apps */ + if (slen < 0) { + error = -ENOMEM; + } else { + if (slen > len) { + error = -ERANGE; + } else if (copy_to_user(optval, name, slen)) { + error = -EFAULT; + goto out; + } + if (put_user(slen, optlen)) + error = -EFAULT; +out: + kfree(name); + + } + +done: + end_current_label_crit_section(label); + + return error; +} + +/** + * apparmor_socket_getpeersec_dgram - get security label of packet + * @sock: the peer socket + * @skb: packet data + * @secid: pointer to where to put the secid of the packet + * + * Sets the netlabel socket state on sk from parent + */ +static int apparmor_socket_getpeersec_dgram(struct socket *sock, + struct sk_buff *skb, u32 *secid) + +{ + /* TODO: requires secid support */ + return -ENOPROTOOPT; +} + +/** + * apparmor_sock_graft - Initialize newly created socket + * @sk: child sock + * @parent: parent socket + * + * Note: could set off of SOCK_CTX(parent) but need to track inode and we can + * just set sk security information off of current creating process label + * Labeling of sk for accept case - probably should be sock based + * instead of task, because of the case where an implicitly labeled + * socket is shared by different tasks. + */ +static void apparmor_sock_graft(struct sock *sk, struct socket *parent) +{ + struct aa_sk_ctx *ctx = SK_CTX(sk); + + if (!ctx->label) + ctx->label = aa_get_current_label(); +} + static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), LSM_HOOK_INIT(capget, apparmor_capget), LSM_HOOK_INIT(capable, apparmor_capable), + LSM_HOOK_INIT(sb_mount, apparmor_sb_mount), + LSM_HOOK_INIT(sb_umount, apparmor_sb_umount), + LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot), + LSM_HOOK_INIT(path_link, apparmor_path_link), LSM_HOOK_INIT(path_unlink, apparmor_path_unlink), LSM_HOOK_INIT(path_symlink, apparmor_path_symlink), @@ -686,6 +1133,30 @@ static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(getprocattr, apparmor_getprocattr), LSM_HOOK_INIT(setprocattr, apparmor_setprocattr), + LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security), + LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security), + LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security), + + LSM_HOOK_INIT(socket_create, apparmor_socket_create), + LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create), + LSM_HOOK_INIT(socket_bind, apparmor_socket_bind), + LSM_HOOK_INIT(socket_connect, apparmor_socket_connect), + LSM_HOOK_INIT(socket_listen, apparmor_socket_listen), + LSM_HOOK_INIT(socket_accept, apparmor_socket_accept), + LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg), + LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg), + LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname), + LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername), + LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt), + LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt), + LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown), + LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb), + LSM_HOOK_INIT(socket_getpeersec_stream, + apparmor_socket_getpeersec_stream), + LSM_HOOK_INIT(socket_getpeersec_dgram, + apparmor_socket_getpeersec_dgram), + LSM_HOOK_INIT(sock_graft, apparmor_sock_graft), + LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank), LSM_HOOK_INIT(cred_free, apparmor_cred_free), LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare), @@ -696,6 +1167,7 @@ static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds), LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit), + LSM_HOOK_INIT(task_kill, apparmor_task_kill), }; /* diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c new file mode 100644 index 0000000..82a64b5 --- /dev/null +++ b/security/apparmor/mount.c @@ -0,0 +1,696 @@ +/* + * AppArmor security module + * + * This file contains AppArmor mediation of files + * + * Copyright (C) 1998-2008 Novell/SUSE + * Copyright 2009-2017 Canonical Ltd. + * + * 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. + */ + +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/namei.h> + +#include "include/apparmor.h" +#include "include/audit.h" +#include "include/context.h" +#include "include/domain.h" +#include "include/file.h" +#include "include/match.h" +#include "include/mount.h" +#include "include/path.h" +#include "include/policy.h" + + +static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags) +{ + if (flags & MS_RDONLY) + audit_log_format(ab, "ro"); + else + audit_log_format(ab, "rw"); + if (flags & MS_NOSUID) + audit_log_format(ab, ", nosuid"); + if (flags & MS_NODEV) + audit_log_format(ab, ", nodev"); + if (flags & MS_NOEXEC) + audit_log_format(ab, ", noexec"); + if (flags & MS_SYNCHRONOUS) + audit_log_format(ab, ", sync"); + if (flags & MS_REMOUNT) + audit_log_format(ab, ", remount"); + if (flags & MS_MANDLOCK) + audit_log_format(ab, ", mand"); + if (flags & MS_DIRSYNC) + audit_log_format(ab, ", dirsync"); + if (flags & MS_NOATIME) + audit_log_format(ab, ", noatime"); + if (flags & MS_NODIRATIME) + audit_log_format(ab, ", nodiratime"); + if (flags & MS_BIND) + audit_log_format(ab, flags & MS_REC ? ", rbind" : ", bind"); + if (flags & MS_MOVE) + audit_log_format(ab, ", move"); + if (flags & MS_SILENT) + audit_log_format(ab, ", silent"); + if (flags & MS_POSIXACL) + audit_log_format(ab, ", acl"); + if (flags & MS_UNBINDABLE) + audit_log_format(ab, flags & MS_REC ? ", runbindable" : + ", unbindable"); + if (flags & MS_PRIVATE) + audit_log_format(ab, flags & MS_REC ? ", rprivate" : + ", private"); + if (flags & MS_SLAVE) + audit_log_format(ab, flags & MS_REC ? ", rslave" : + ", slave"); + if (flags & MS_SHARED) + audit_log_format(ab, flags & MS_REC ? ", rshared" : + ", shared"); + if (flags & MS_RELATIME) + audit_log_format(ab, ", relatime"); + if (flags & MS_I_VERSION) + audit_log_format(ab, ", iversion"); + if (flags & MS_STRICTATIME) + audit_log_format(ab, ", strictatime"); + if (flags & MS_NOUSER) + audit_log_format(ab, ", nouser"); +} + +/** + * audit_cb - call back for mount specific audit fields + * @ab: audit_buffer (NOT NULL) + * @va: audit struct to audit values of (NOT NULL) + */ +static void audit_cb(struct audit_buffer *ab, void *va) +{ + struct common_audit_data *sa = va; + + if (aad(sa)->mnt.type) { + audit_log_format(ab, " fstype="); + audit_log_untrustedstring(ab, aad(sa)->mnt.type); + } + if (aad(sa)->mnt.src_name) { + audit_log_format(ab, " srcname="); + audit_log_untrustedstring(ab, aad(sa)->mnt.src_name); + } + if (aad(sa)->mnt.trans) { + audit_log_format(ab, " trans="); + audit_log_untrustedstring(ab, aad(sa)->mnt.trans); + } + if (aad(sa)->mnt.flags) { + audit_log_format(ab, " flags=\""); + audit_mnt_flags(ab, aad(sa)->mnt.flags); + audit_log_format(ab, "\""); + } + if (aad(sa)->mnt.data) { + audit_log_format(ab, " options="); + audit_log_untrustedstring(ab, aad(sa)->mnt.data); + } +} + +/** + * audit_mount - handle the auditing of mount operations + * @profile: the profile being enforced (NOT NULL) + * @op: operation being mediated (NOT NULL) + * @name: name of object being mediated (MAYBE NULL) + * @src_name: src_name of object being mediated (MAYBE_NULL) + * @type: type of filesystem (MAYBE_NULL) + * @trans: name of trans (MAYBE NULL) + * @flags: filesystem idependent mount flags + * @data: filesystem mount flags + * @request: permissions requested + * @perms: the permissions computed for the request (NOT NULL) + * @info: extra information message (MAYBE NULL) + * @error: 0 if operation allowed else failure error code + * + * Returns: %0 or error on failure + */ +static int audit_mount(struct aa_profile *profile, const char *op, + const char *name, const char *src_name, + const char *type, const char *trans, + unsigned long flags, const void *data, u32 request, + struct aa_perms *perms, const char *info, int error) +{ + int audit_type = AUDIT_APPARMOR_AUTO; + DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, op); + + if (likely(!error)) { + u32 mask = perms->audit; + + if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL)) + mask = 0xffff; + + /* mask off perms that are not being force audited */ + request &= mask; + + if (likely(!request)) + return 0; + audit_type = AUDIT_APPARMOR_AUDIT; + } else { + /* only report permissions that were denied */ + request = request & ~perms->allow; + + if (request & perms->kill) + audit_type = AUDIT_APPARMOR_KILL; + + /* quiet known rejects, assumes quiet and kill do not overlap */ + if ((request & perms->quiet) && + AUDIT_MODE(profile) != AUDIT_NOQUIET && + AUDIT_MODE(profile) != AUDIT_ALL) + request &= ~perms->quiet; + + if (!request) + return error; + } + + aad(&sa)->name = name; + aad(&sa)->mnt.src_name = src_name; + aad(&sa)->mnt.type = type; + aad(&sa)->mnt.trans = trans; + aad(&sa)->mnt.flags = flags; + if (data && (perms->audit & AA_AUDIT_DATA)) + aad(&sa)->mnt.data = data; + aad(&sa)->info = info; + aad(&sa)->error = error; + + return aa_audit(audit_type, profile, &sa, audit_cb); +} + +/** + * match_mnt_flags - Do an ordered match on mount flags + * @dfa: dfa to match against + * @state: state to start in + * @flags: mount flags to match against + * + * Mount flags are encoded as an ordered match. This is done instead of + * checking against a simple bitmask, to allow for logical operations + * on the flags. + * + * Returns: next state after flags match + */ +static unsigned int match_mnt_flags(struct aa_dfa *dfa, unsigned int state, + unsigned long flags) +{ + unsigned int i; + + for (i = 0; i <= 31 ; ++i) { + if ((1 << i) & flags) + state = aa_dfa_next(dfa, state, i + 1); + } + + return state; +} + +/** + * compute_mnt_perms - compute mount permission associated with @state + * @dfa: dfa to match against (NOT NULL) + * @state: state match finished in + * + * Returns: mount permissions + */ +static struct aa_perms compute_mnt_perms(struct aa_dfa *dfa, + unsigned int state) +{ + struct aa_perms perms; + + perms.kill = 0; + perms.allow = dfa_user_allow(dfa, state); + perms.audit = dfa_user_audit(dfa, state); + perms.quiet = dfa_user_quiet(dfa, state); + perms.xindex = dfa_user_xindex(dfa, state); + + return perms; +} + +static const char * const mnt_info_table[] = { + "match succeeded", + "failed mntpnt match", + "failed srcname match", + "failed type match", + "failed flags match", + "failed data match" +}; + +/* + * Returns 0 on success else element that match failed in, this is the + * index into the mnt_info_table above + */ +static int do_match_mnt(struct aa_dfa *dfa, unsigned int start, + const char *mntpnt, const char *devname, + const char *type, unsigned long flags, + void *data, bool binary, struct aa_perms *perms) +{ + unsigned int state; + + AA_BUG(!dfa); + AA_BUG(!perms); + + state = aa_dfa_match(dfa, start, mntpnt); + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 1; + + if (devname) + state = aa_dfa_match(dfa, state, devname); + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 2; + + if (type) + state = aa_dfa_match(dfa, state, type); + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 3; + + state = match_mnt_flags(dfa, state, flags); + if (!state) + return 4; + *perms = compute_mnt_perms(dfa, state); + if (perms->allow & AA_MAY_MOUNT) + return 0; + + /* only match data if not binary and the DFA flags data is expected */ + if (data && !binary && (perms->allow & AA_MNT_CONT_MATCH)) { + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 4; + + state = aa_dfa_match(dfa, state, data); + if (!state) + return 5; + *perms = compute_mnt_perms(dfa, state); + if (perms->allow & AA_MAY_MOUNT) + return 0; + } + + /* failed at end of flags match */ + return 4; +} + + +static int path_flags(struct aa_profile *profile, const struct path *path) +{ + AA_BUG(!profile); + AA_BUG(!path); + + return profile->path_flags | + (S_ISDIR(path->dentry->d_inode->i_mode) ? PATH_IS_DIR : 0); +} + +/** + * match_mnt_path_str - handle path matching for mount + * @profile: the confining profile + * @mntpath: for the mntpnt (NOT NULL) + * @buffer: buffer to be used to lookup mntpath + * @devnme: string for the devname/src_name (MAY BE NULL OR ERRPTR) + * @type: string for the dev type (MAYBE NULL) + * @flags: mount flags to match + * @data: fs mount data (MAYBE NULL) + * @binary: whether @data is binary + * @devinfo: error str if (IS_ERR(@devname)) + * + * Returns: 0 on success else error + */ +static int match_mnt_path_str(struct aa_profile *profile, + const struct path *mntpath, char *buffer, + const char *devname, const char *type, + unsigned long flags, void *data, bool binary, + const char *devinfo) +{ + struct aa_perms perms = { }; + const char *mntpnt = NULL, *info = NULL; + int pos, error; + + AA_BUG(!profile); + AA_BUG(!mntpath); + AA_BUG(!buffer); + + error = aa_path_name(mntpath, path_flags(profile, mntpath), buffer, + &mntpnt, &info, profile->disconnected); + if (error) + goto audit; + if (IS_ERR(devname)) { + error = PTR_ERR(devname); + devname = NULL; + info = devinfo; + goto audit; + } + + error = -EACCES; + pos = do_match_mnt(profile->policy.dfa, + profile->policy.start[AA_CLASS_MOUNT], + mntpnt, devname, type, flags, data, binary, &perms); + if (pos) { + info = mnt_info_table[pos]; + goto audit; + } + error = 0; + +audit: + return audit_mount(profile, OP_MOUNT, mntpnt, devname, type, NULL, + flags, data, AA_MAY_MOUNT, &perms, info, error); +} + +/** + * match_mnt - handle path matching for mount + * @profile: the confining profile + * @mntpath: for the mntpnt (NOT NULL) + * @buffer: buffer to be used to lookup mntpath + * @devpath: path devname/src_name (MAYBE NULL) + * @devbuffer: buffer to be used to lookup devname/src_name + * @type: string for the dev type (MAYBE NULL) + * @flags: mount flags to match + * @data: fs mount data (MAYBE NULL) + * @binary: whether @data is binary + * + * Returns: 0 on success else error + */ +static int match_mnt(struct aa_profile *profile, const struct path *path, + char *buffer, struct path *devpath, char *devbuffer, + const char *type, unsigned long flags, void *data, + bool binary) +{ + const char *devname = NULL, *info = NULL; + int error = -EACCES; + + AA_BUG(!profile); + AA_BUG(devpath && !devbuffer); + + if (devpath) { + error = aa_path_name(devpath, path_flags(profile, devpath), + devbuffer, &devname, &info, + profile->disconnected); + if (error) + devname = ERR_PTR(error); + } + + return match_mnt_path_str(profile, path, buffer, devname, type, flags, + data, binary, info); +} + +int aa_remount(struct aa_label *label, const struct path *path, + unsigned long flags, void *data) +{ + struct aa_profile *profile; + char *buffer = NULL; + bool binary; + int error; + + AA_BUG(!label); + AA_BUG(!path); + + binary = path->dentry->d_sb->s_type->fs_flags & FS_BINARY_MOUNTDATA; + + get_buffers(buffer); + error = fn_for_each_confined(label, profile, + match_mnt(profile, path, buffer, NULL, NULL, NULL, + flags, data, binary)); + put_buffers(buffer); + + return error; +} + +int aa_bind_mount(struct aa_label *label, const struct path *path, + const char *dev_name, unsigned long flags) +{ + struct aa_profile *profile; + char *buffer = NULL, *old_buffer = NULL; + struct path old_path; + int error; + + AA_BUG(!label); + AA_BUG(!path); + + if (!dev_name || !*dev_name) + return -EINVAL; + + flags &= MS_REC | MS_BIND; + + error = kern_path(dev_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); + if (error) + return error; + + get_buffers(buffer, old_buffer); + error = fn_for_each_confined(label, profile, + match_mnt(profile, path, buffer, &old_path, old_buffer, + NULL, flags, NULL, false)); + put_buffers(buffer, old_buffer); + path_put(&old_path); + + return error; +} + +int aa_mount_change_type(struct aa_label *label, const struct path *path, + unsigned long flags) +{ + struct aa_profile *profile; + char *buffer = NULL; + int error; + + AA_BUG(!label); + AA_BUG(!path); + + /* These are the flags allowed by do_change_type() */ + flags &= (MS_REC | MS_SILENT | MS_SHARED | MS_PRIVATE | MS_SLAVE | + MS_UNBINDABLE); + + get_buffers(buffer); + error = fn_for_each_confined(label, profile, + match_mnt(profile, path, buffer, NULL, NULL, NULL, + flags, NULL, false)); + put_buffers(buffer); + + return error; +} + +int aa_move_mount(struct aa_label *label, const struct path *path, + const char *orig_name) +{ + struct aa_profile *profile; + char *buffer = NULL, *old_buffer = NULL; + struct path old_path; + int error; + + AA_BUG(!label); + AA_BUG(!path); + + if (!orig_name || !*orig_name) + return -EINVAL; + + error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path); + if (error) + return error; + + get_buffers(buffer, old_buffer); + error = fn_for_each_confined(label, profile, + match_mnt(profile, path, buffer, &old_path, old_buffer, + NULL, MS_MOVE, NULL, false)); + put_buffers(buffer, old_buffer); + path_put(&old_path); + + return error; +} + +int aa_new_mount(struct aa_label *label, const char *dev_name, + const struct path *path, const char *type, unsigned long flags, + void *data) +{ + struct aa_profile *profile; + char *buffer = NULL, *dev_buffer = NULL; + bool binary = true; + int error; + int requires_dev = 0; + struct path tmp_path, *dev_path = NULL; + + AA_BUG(!label); + AA_BUG(!path); + + if (type) { + struct file_system_type *fstype; + + fstype = get_fs_type(type); + if (!fstype) + return -ENODEV; + binary = fstype->fs_flags & FS_BINARY_MOUNTDATA; + requires_dev = fstype->fs_flags & FS_REQUIRES_DEV; + put_filesystem(fstype); + + if (requires_dev) { + if (!dev_name || !*dev_name) + return -ENOENT; + + error = kern_path(dev_name, LOOKUP_FOLLOW, &tmp_path); + if (error) + return error; + dev_path = &tmp_path; + } + } + + get_buffers(buffer, dev_buffer); + if (dev_path) { + error = fn_for_each_confined(label, profile, + match_mnt(profile, path, buffer, dev_path, dev_buffer, + type, flags, data, binary)); + } else { + error = fn_for_each_confined(label, profile, + match_mnt_path_str(profile, path, buffer, dev_name, + type, flags, data, binary, NULL)); + } + put_buffers(buffer, dev_buffer); + if (dev_path) + path_put(dev_path); + + return error; +} + +static int profile_umount(struct aa_profile *profile, struct path *path, + char *buffer) +{ + struct aa_perms perms = { }; + const char *name = NULL, *info = NULL; + unsigned int state; + int error; + + AA_BUG(!profile); + AA_BUG(!path); + + error = aa_path_name(path, path_flags(profile, path), buffer, &name, + &info, profile->disconnected); + if (error) + goto audit; + + state = aa_dfa_match(profile->policy.dfa, + profile->policy.start[AA_CLASS_MOUNT], + name); + perms = compute_mnt_perms(profile->policy.dfa, state); + if (AA_MAY_UMOUNT & ~perms.allow) + error = -EACCES; + +audit: + return audit_mount(profile, OP_UMOUNT, name, NULL, NULL, NULL, 0, NULL, + AA_MAY_UMOUNT, &perms, info, error); +} + +int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags) +{ + struct aa_profile *profile; + char *buffer = NULL; + int error; + struct path path = { .mnt = mnt, .dentry = mnt->mnt_root }; + + AA_BUG(!label); + AA_BUG(!mnt); + + get_buffers(buffer); + error = fn_for_each_confined(label, profile, + profile_umount(profile, &path, buffer)); + put_buffers(buffer); + + return error; +} + +/* helper fn for transition on pivotroot + * + * Returns: label for transition or ERR_PTR. Does not return NULL + */ +static struct aa_label *build_pivotroot(struct aa_profile *profile, + const struct path *new_path, + char *new_buffer, + const struct path *old_path, + char *old_buffer) +{ + const char *old_name, *new_name = NULL, *info = NULL; + const char *trans_name = NULL; + struct aa_perms perms = { }; + unsigned int state; + int error; + + AA_BUG(!profile); + AA_BUG(!new_path); + AA_BUG(!old_path); + + if (profile_unconfined(profile)) + return aa_get_newest_label(&profile->label); + + error = aa_path_name(old_path, path_flags(profile, old_path), + old_buffer, &old_name, &info, + profile->disconnected); + if (error) + goto audit; + error = aa_path_name(new_path, path_flags(profile, new_path), + new_buffer, &new_name, &info, + profile->disconnected); + if (error) + goto audit; + + error = -EACCES; + state = aa_dfa_match(profile->policy.dfa, + profile->policy.start[AA_CLASS_MOUNT], + new_name); + state = aa_dfa_null_transition(profile->policy.dfa, state); + state = aa_dfa_match(profile->policy.dfa, state, old_name); + perms = compute_mnt_perms(profile->policy.dfa, state); + + if (AA_MAY_PIVOTROOT & perms.allow) + error = 0; + +audit: + error = audit_mount(profile, OP_PIVOTROOT, new_name, old_name, + NULL, trans_name, 0, NULL, AA_MAY_PIVOTROOT, + &perms, info, error); + if (error) + return ERR_PTR(error); + + return aa_get_newest_label(&profile->label); +} + +int aa_pivotroot(struct aa_label *label, const struct path *old_path, + const struct path *new_path) +{ + struct aa_profile *profile; + struct aa_label *target = NULL; + char *old_buffer = NULL, *new_buffer = NULL, *info = NULL; + int error; + + AA_BUG(!label); + AA_BUG(!old_path); + AA_BUG(!new_path); + + get_buffers(old_buffer, new_buffer); + target = fn_label_build(label, profile, GFP_ATOMIC, + build_pivotroot(profile, new_path, new_buffer, + old_path, old_buffer)); + if (!target) { + info = "label build failed"; + error = -ENOMEM; + goto fail; + } else if (!IS_ERR(target)) { + error = aa_replace_current_label(target); + if (error) { + /* TODO: audit target */ + aa_put_label(target); + goto out; + } + } else + /* already audited error */ + error = PTR_ERR(target); +out: + put_buffers(old_buffer, new_buffer); + + return error; + +fail: + /* TODO: add back in auditing of new_name and old_name */ + error = fn_for_each(label, profile, + audit_mount(profile, OP_PIVOTROOT, NULL /*new_name */, + NULL /* old_name */, + NULL, NULL, + 0, NULL, AA_MAY_PIVOTROOT, &nullperms, info, + error)); + goto out; +} diff --git a/security/apparmor/net.c b/security/apparmor/net.c new file mode 100644 index 0000000..33d5443 --- /dev/null +++ b/security/apparmor/net.c @@ -0,0 +1,184 @@ +/* + * AppArmor security module + * + * This file contains AppArmor network mediation + * + * Copyright (C) 1998-2008 Novell/SUSE + * Copyright 2009-2017 Canonical Ltd. + * + * 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. + */ + +#include "include/apparmor.h" +#include "include/audit.h" +#include "include/context.h" +#include "include/label.h" +#include "include/net.h" +#include "include/policy.h" + +#include "net_names.h" + + +struct aa_sfs_entry aa_sfs_entry_network[] = { + AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), + { } +}; + +static const char * const net_mask_names[] = { + "unknown", + "send", + "receive", + "unknown", + + "create", + "shutdown", + "connect", + "unknown", + + "setattr", + "getattr", + "setcred", + "getcred", + + "chmod", + "chown", + "chgrp", + "lock", + + "mmap", + "mprot", + "unknown", + "unknown", + + "accept", + "bind", + "listen", + "unknown", + + "setopt", + "getopt", + "unknown", + "unknown", + + "unknown", + "unknown", + "unknown", + "unknown", +}; + + +/* audit callback for net specific fields */ +void audit_net_cb(struct audit_buffer *ab, void *va) +{ + struct common_audit_data *sa = va; + + audit_log_format(ab, " family="); + if (address_family_names[sa->u.net->family]) + audit_log_string(ab, address_family_names[sa->u.net->family]); + else + audit_log_format(ab, "\"unknown(%d)\"", sa->u.net->family); + audit_log_format(ab, " sock_type="); + if (sock_type_names[aad(sa)->net.type]) + audit_log_string(ab, sock_type_names[aad(sa)->net.type]); + else + audit_log_format(ab, "\"unknown(%d)\"", aad(sa)->net.type); + audit_log_format(ab, " protocol=%d", aad(sa)->net.protocol); + + if (aad(sa)->request & NET_PERMS_MASK) { + audit_log_format(ab, " requested_mask="); + aa_audit_perm_mask(ab, aad(sa)->request, NULL, 0, + net_mask_names, NET_PERMS_MASK); + + if (aad(sa)->denied & NET_PERMS_MASK) { + audit_log_format(ab, " denied_mask="); + aa_audit_perm_mask(ab, aad(sa)->denied, NULL, 0, + net_mask_names, NET_PERMS_MASK); + } + } + if (aad(sa)->peer) { + audit_log_format(ab, " peer="); + aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + FLAGS_NONE, GFP_ATOMIC); + } +} + + +/* Generic af perm */ +int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, + u32 request, u16 family, int type) +{ + struct aa_perms perms = { }; + + AA_BUG(family >= AF_MAX); + AA_BUG(type < 0 || type >= SOCK_MAX); + + if (profile_unconfined(profile)) + return 0; + + perms.allow = (profile->net.allow[family] & (1 << type)) ? + ALL_PERMS_MASK : 0; + perms.audit = (profile->net.audit[family] & (1 << type)) ? + ALL_PERMS_MASK : 0; + perms.quiet = (profile->net.quiet[family] & (1 << type)) ? + ALL_PERMS_MASK : 0; + aa_apply_modes_to_perms(profile, &perms); + + return aa_check_perms(profile, &perms, request, sa, audit_net_cb); +} + +int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, + int type, int protocol) +{ + struct aa_profile *profile; + DEFINE_AUDIT_NET(sa, op, NULL, family, type, protocol); + + return fn_for_each_confined(label, profile, + aa_profile_af_perm(profile, &sa, request, family, + type)); +} + +static int aa_label_sk_perm(struct aa_label *label, const char *op, u32 request, + struct sock *sk) +{ + struct aa_profile *profile; + DEFINE_AUDIT_SK(sa, op, sk); + + AA_BUG(!label); + AA_BUG(!sk); + + if (unconfined(label)) + return 0; + + return fn_for_each_confined(label, profile, + aa_profile_af_sk_perm(profile, &sa, request, sk)); +} + +int aa_sk_perm(const char *op, u32 request, struct sock *sk) +{ + struct aa_label *label; + int error; + + AA_BUG(!sk); + AA_BUG(in_interrupt()); + + /* TODO: switch to begin_current_label ???? */ + label = begin_current_label_crit_section(); + error = aa_label_sk_perm(label, op, request, sk); + end_current_label_crit_section(label); + + return error; +} + + +int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, + struct socket *sock) +{ + AA_BUG(!label); + AA_BUG(!sock); + AA_BUG(!sock->sk); + + return aa_label_sk_perm(label, op, request, sock->sk); +} diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 244ea4a..4243b0c 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -289,85 +289,6 @@ fail: return NULL; } -/** - * aa_new_null_profile - create or find a null-X learning profile - * @parent: profile that caused this profile to be created (NOT NULL) - * @hat: true if the null- learning profile is a hat - * @base: name to base the null profile off of - * @gfp: type of allocation - * - * Find/Create a null- complain mode profile used in learning mode. The - * name of the profile is unique and follows the format of parent//null-XXX. - * where XXX is based on the @name or if that fails or is not supplied - * a unique number - * - * null profiles are added to the profile list but the list does not - * hold a count on them so that they are automatically released when - * not in use. - * - * Returns: new refcounted profile else NULL on failure - */ -struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat, - const char *base, gfp_t gfp) -{ - struct aa_profile *profile; - char *name; - - AA_BUG(!parent); - - if (base) { - name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base), - gfp); - if (name) { - sprintf(name, "%s//null-%s", parent->base.hname, base); - goto name; - } - /* fall through to try shorter uniq */ - } - - name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp); - if (!name) - return NULL; - sprintf(name, "%s//null-%x", parent->base.hname, - atomic_inc_return(&parent->ns->uniq_null)); - -name: - /* lookup to see if this is a dup creation */ - profile = aa_find_child(parent, basename(name)); - if (profile) - goto out; - - profile = aa_alloc_profile(name, NULL, gfp); - if (!profile) - goto fail; - - profile->mode = APPARMOR_COMPLAIN; - profile->label.flags |= FLAG_NULL; - if (hat) - profile->label.flags |= FLAG_HAT; - profile->path_flags = parent->path_flags; - - /* released on free_profile */ - rcu_assign_pointer(profile->parent, aa_get_profile(parent)); - profile->ns = aa_get_ns(parent->ns); - profile->file.dfa = aa_get_dfa(nulldfa); - profile->policy.dfa = aa_get_dfa(nulldfa); - - mutex_lock(&profile->ns->lock); - __add_profile(&parent->base.profiles, profile); - mutex_unlock(&profile->ns->lock); - - /* refcount released by caller */ -out: - kfree(name); - - return profile; - -fail: - aa_free_profile(profile); - return NULL; -} - /* TODO: profile accounting - setup in remove */ /** @@ -559,6 +480,93 @@ struct aa_profile *aa_fqlookupn_profile(struct aa_label *base, } /** + * aa_new_null_profile - create or find a null-X learning profile + * @parent: profile that caused this profile to be created (NOT NULL) + * @hat: true if the null- learning profile is a hat + * @base: name to base the null profile off of + * @gfp: type of allocation + * + * Find/Create a null- complain mode profile used in learning mode. The + * name of the profile is unique and follows the format of parent//null-XXX. + * where XXX is based on the @name or if that fails or is not supplied + * a unique number + * + * null profiles are added to the profile list but the list does not + * hold a count on them so that they are automatically released when + * not in use. + * + * Returns: new refcounted profile else NULL on failure + */ +struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat, + const char *base, gfp_t gfp) +{ + struct aa_profile *p, *profile; + const char *bname; + char *name; + + AA_BUG(!parent); + + if (base) { + name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base), + gfp); + if (name) { + sprintf(name, "%s//null-%s", parent->base.hname, base); + goto name; + } + /* fall through to try shorter uniq */ + } + + name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp); + if (!name) + return NULL; + sprintf(name, "%s//null-%x", parent->base.hname, + atomic_inc_return(&parent->ns->uniq_null)); + +name: + /* lookup to see if this is a dup creation */ + bname = basename(name); + profile = aa_find_child(parent, bname); + if (profile) + goto out; + + profile = aa_alloc_profile(name, NULL, gfp); + if (!profile) + goto fail; + + profile->mode = APPARMOR_COMPLAIN; + profile->label.flags |= FLAG_NULL; + if (hat) + profile->label.flags |= FLAG_HAT; + profile->path_flags = parent->path_flags; + + /* released on free_profile */ + rcu_assign_pointer(profile->parent, aa_get_profile(parent)); + profile->ns = aa_get_ns(parent->ns); + profile->file.dfa = aa_get_dfa(nulldfa); + profile->policy.dfa = aa_get_dfa(nulldfa); + + mutex_lock(&profile->ns->lock); + p = __find_child(&parent->base.profiles, bname); + if (p) { + aa_free_profile(profile); + profile = aa_get_profile(p); + } else { + __add_profile(&parent->base.profiles, profile); + } + mutex_unlock(&profile->ns->lock); + + /* refcount released by caller */ +out: + kfree(name); + + return profile; + +fail: + aa_free_profile(profile); + return NULL; +} + +/** * replacement_allowed - test to see if replacement is allowed * @profile: profile to test if it can be replaced (MAYBE NULL) * @noreplace: true if replacement shouldn't be allowed but addition is okay diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c index 351d3ba..62a3589 100644 --- a/security/apparmor/policy_ns.c +++ b/security/apparmor/policy_ns.c @@ -112,6 +112,8 @@ static struct aa_ns *alloc_ns(const char *prefix, const char *name) ns->unconfined->label.flags |= FLAG_IX_ON_NAME_ERROR | FLAG_IMMUTIBLE | FLAG_NS_COUNT | FLAG_UNCONFINED; ns->unconfined->mode = APPARMOR_UNCONFINED; + ns->unconfined->file.dfa = aa_get_dfa(nulldfa); + ns->unconfined->policy.dfa = aa_get_dfa(nulldfa); /* ns and ns->unconfined share ns->unconfined refcount */ ns->unconfined->ns = ns; diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index c600f4d..5a2aec3 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -85,9 +85,9 @@ static void audit_cb(struct audit_buffer *ab, void *va) audit_log_format(ab, " ns="); audit_log_untrustedstring(ab, aad(sa)->iface.ns); } - if (aad(sa)->iface.name) { + if (aad(sa)->name) { audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, aad(sa)->iface.name); + audit_log_untrustedstring(ab, aad(sa)->name); } if (aad(sa)->iface.pos) audit_log_format(ab, " offset=%ld", aad(sa)->iface.pos); @@ -114,9 +114,9 @@ static int audit_iface(struct aa_profile *new, const char *ns_name, aad(&sa)->iface.pos = e->pos - e->start; aad(&sa)->iface.ns = ns_name; if (new) - aad(&sa)->iface.name = new->base.hname; + aad(&sa)->name = new->base.hname; else - aad(&sa)->iface.name = name; + aad(&sa)->name = name; aad(&sa)->info = info; aad(&sa)->error = error; @@ -275,6 +275,19 @@ fail: return 0; } +static bool unpack_u16(struct aa_ext *e, u16 *data, const char *name) +{ + if (unpack_nameX(e, AA_U16, name)) { + if (!inbounds(e, sizeof(u16))) + return 0; + if (data) + *data = le16_to_cpu(get_unaligned((__le16 *) e->pos)); + e->pos += sizeof(u16); + return 1; + } + return 0; +} + static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name) { if (unpack_nameX(e, AA_U32, name)) { @@ -448,7 +461,7 @@ fail: */ static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile) { - void *pos = e->pos; + void *saved_pos = e->pos; /* exec table is optional */ if (unpack_nameX(e, AA_STRUCT, "xtable")) { @@ -511,7 +524,7 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile) fail: aa_free_domain_entries(&profile->file.trans); - e->pos = pos; + e->pos = saved_pos; return 0; } @@ -583,7 +596,8 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) { struct aa_profile *profile = NULL; const char *tmpname, *tmpns = NULL, *name = NULL; - size_t ns_len; + const char *info = "failed to unpack profile"; + size_t size = 0, ns_len; struct rhashtable_params params = { 0 }; char *key = NULL; struct aa_data *data; @@ -604,8 +618,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len); if (tmpns) { *ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL); - if (!*ns_name) + if (!*ns_name) { + info = "out of memory"; goto fail; + } name = tmpname; } @@ -624,12 +640,15 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) if (IS_ERR(profile->xmatch)) { error = PTR_ERR(profile->xmatch); profile->xmatch = NULL; + info = "bad xmatch"; goto fail; } /* xmatch_len is not optional if xmatch is set */ if (profile->xmatch) { - if (!unpack_u32(e, &tmp, NULL)) + if (!unpack_u32(e, &tmp, NULL)) { + info = "missing xmatch len"; goto fail; + } profile->xmatch_len = tmp; } @@ -637,8 +656,11 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) (void) unpack_str(e, &profile->disconnected, "disconnected"); /* per profile debug flags (complain, audit) */ - if (!unpack_nameX(e, AA_STRUCT, "flags")) + if (!unpack_nameX(e, AA_STRUCT, "flags")) { + info = "profile missing flags"; goto fail; + } + info = "failed to unpack profile flags"; if (!unpack_u32(e, &tmp, NULL)) goto fail; if (tmp & PACKED_FLAG_HAT) @@ -667,6 +689,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) /* set a default value if path_flags field is not present */ profile->path_flags = PATH_MEDIATE_DELETED; + info = "failed to unpack profile capabilities"; if (!unpack_u32(e, &(profile->caps.allow.cap[0]), NULL)) goto fail; if (!unpack_u32(e, &(profile->caps.audit.cap[0]), NULL)) @@ -676,6 +699,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) if (!unpack_u32(e, &tmpcap.cap[0], NULL)) goto fail; + info = "failed to unpack upper profile capabilities"; if (unpack_nameX(e, AA_STRUCT, "caps64")) { /* optional upper half of 64 bit caps */ if (!unpack_u32(e, &(profile->caps.allow.cap[1]), NULL)) @@ -690,6 +714,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } + info = "failed to unpack extended profile capabilities"; if (unpack_nameX(e, AA_STRUCT, "capsx")) { /* optional extended caps mediation mask */ if (!unpack_u32(e, &(profile->caps.extended.cap[0]), NULL)) @@ -700,11 +725,46 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } - if (!unpack_rlimits(e, profile)) + if (!unpack_rlimits(e, profile)) { + info = "failed to unpack profile rlimits"; goto fail; + } + + size = unpack_array(e, "net_allowed_af"); + if (size) { + + for (i = 0; i < size; i++) { + /* discard extraneous rules that this kernel will + * never request + */ + if (i >= AF_MAX) { + u16 tmp; + + if (!unpack_u16(e, &tmp, NULL) || + !unpack_u16(e, &tmp, NULL) || + !unpack_u16(e, &tmp, NULL)) + goto fail; + continue; + } + if (!unpack_u16(e, &profile->net.allow[i], NULL)) + goto fail; + if (!unpack_u16(e, &profile->net.audit[i], NULL)) + goto fail; + if (!unpack_u16(e, &profile->net.quiet[i], NULL)) + goto fail; + } + if (!unpack_nameX(e, AA_ARRAYEND, NULL)) + goto fail; + } + if (VERSION_LT(e->version, v7)) { + /* pre v7 policy always allowed these */ + profile->net.allow[AF_UNIX] = 0xffff; + profile->net.allow[AF_NETLINK] = 0xffff; + } if (unpack_nameX(e, AA_STRUCT, "policydb")) { /* generic policy dfa - optional and may be NULL */ + info = "failed to unpack policydb"; profile->policy.dfa = unpack_dfa(e); if (IS_ERR(profile->policy.dfa)) { error = PTR_ERR(profile->policy.dfa); @@ -734,6 +794,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) if (IS_ERR(profile->file.dfa)) { error = PTR_ERR(profile->file.dfa); profile->file.dfa = NULL; + info = "failed to unpack profile file rules"; goto fail; } else if (profile->file.dfa) { if (!unpack_u32(e, &profile->file.start, "dfa_start")) @@ -746,10 +807,13 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) } else profile->file.dfa = aa_get_dfa(nulldfa); - if (!unpack_trans_table(e, profile)) + if (!unpack_trans_table(e, profile)) { + info = "failed to unpack profile transition table"; goto fail; + } if (unpack_nameX(e, AA_STRUCT, "data")) { + info = "out of memory"; profile->data = kzalloc(sizeof(*profile->data), GFP_KERNEL); if (!profile->data) goto fail; @@ -761,8 +825,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) params.hashfn = strhash; params.obj_cmpfn = datacmp; - if (rhashtable_init(profile->data, ¶ms)) + if (rhashtable_init(profile->data, ¶ms)) { + info = "failed to init key, value hash table"; goto fail; + } while (unpack_strdup(e, &key, NULL)) { data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -784,12 +850,16 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) profile->data->p); } - if (!unpack_nameX(e, AA_STRUCTEND, NULL)) + if (!unpack_nameX(e, AA_STRUCTEND, NULL)) { + info = "failed to unpack end of key, value data table"; goto fail; + } } - if (!unpack_nameX(e, AA_STRUCTEND, NULL)) + if (!unpack_nameX(e, AA_STRUCTEND, NULL)) { + info = "failed to unpack end of profile"; goto fail; + } return profile; @@ -798,8 +868,7 @@ fail: name = NULL; else if (!name) name = "unknown"; - audit_iface(profile, NULL, name, "failed to unpack profile", e, - error); + audit_iface(profile, NULL, name, info, e, error); aa_free_profile(profile); return ERR_PTR(error); @@ -832,7 +901,7 @@ static int verify_header(struct aa_ext *e, int required, const char **ns) * if not specified use previous version * Mask off everything that is not kernel abi version */ - if (VERSION_LT(e->version, v5) && VERSION_GT(e->version, v7)) { + if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v7)) { audit_iface(NULL, NULL, NULL, "unsupported interface version", e, error); return error; diff --git a/security/commoncap.c b/security/commoncap.c index 6bf72b1..c25e0d2 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -294,10 +294,10 @@ int cap_capset(struct cred *new, * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should - * inode_killpriv() be invoked or the change rejected? + * inode_killpriv() be invoked or the change rejected. * - * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and - * -ve to deny the change. + * Returns 1 if security.capability has a value, meaning inode_killpriv() + * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { diff --git a/security/keys/Kconfig b/security/keys/Kconfig index a7a23b5..91eafad 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -45,10 +45,8 @@ config BIG_KEYS bool "Large payload keys" depends on KEYS depends on TMPFS - depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y) select CRYPTO_AES - select CRYPTO_ECB - select CRYPTO_RNG + select CRYPTO_GCM help This option provides support for holding large keys within the kernel (for example Kerberos ticket caches). The data may be stored out to diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 6acb00f..e607830 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -1,5 +1,6 @@ /* Large capacity key type * + * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * @@ -16,10 +17,10 @@ #include <linux/shmem_fs.h> #include <linux/err.h> #include <linux/scatterlist.h> +#include <linux/random.h> #include <keys/user-type.h> #include <keys/big_key-type.h> -#include <crypto/rng.h> -#include <crypto/skcipher.h> +#include <crypto/aead.h> /* * Layout of key payload words. @@ -49,7 +50,12 @@ enum big_key_op { /* * Key size for big_key data encryption */ -#define ENC_KEY_SIZE 16 +#define ENC_KEY_SIZE 32 + +/* + * Authentication tag length + */ +#define ENC_AUTHTAG_SIZE 16 /* * big_key defined keys take an arbitrary string as the description and an @@ -64,57 +70,62 @@ struct key_type key_type_big_key = { .destroy = big_key_destroy, .describe = big_key_describe, .read = big_key_read, + /* no ->update(); don't add it without changing big_key_crypt() nonce */ }; /* - * Crypto names for big_key data encryption + * Crypto names for big_key data authenticated encryption */ -static const char big_key_rng_name[] = "stdrng"; -static const char big_key_alg_name[] = "ecb(aes)"; +static const char big_key_alg_name[] = "gcm(aes)"; /* - * Crypto algorithms for big_key data encryption + * Crypto algorithms for big_key data authenticated encryption */ -static struct crypto_rng *big_key_rng; -static struct crypto_skcipher *big_key_skcipher; +static struct crypto_aead *big_key_aead; /* - * Generate random key to encrypt big_key data + * Since changing the key affects the entire object, we need a mutex. */ -static inline int big_key_gen_enckey(u8 *key) -{ - return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE); -} +static DEFINE_MUTEX(big_key_aead_lock); /* * Encrypt/decrypt big_key data */ static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key) { - int ret = -EINVAL; + int ret; struct scatterlist sgio; - SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher); - - if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) { + struct aead_request *aead_req; + /* We always use a zero nonce. The reason we can get away with this is + * because we're using a different randomly generated key for every + * different encryption. Notably, too, key_type_big_key doesn't define + * an .update function, so there's no chance we'll wind up reusing the + * key to encrypt updated data. Simply put: one key, one encryption. + */ + u8 zero_nonce[crypto_aead_ivsize(big_key_aead)]; + + aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL); + if (!aead_req) + return -ENOMEM; + + memset(zero_nonce, 0, sizeof(zero_nonce)); + sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0)); + aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce); + aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + aead_request_set_ad(aead_req, 0); + + mutex_lock(&big_key_aead_lock); + if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) { ret = -EAGAIN; goto error; } - - skcipher_request_set_tfm(req, big_key_skcipher); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, - NULL, NULL); - - sg_init_one(&sgio, data, datalen); - skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL); - if (op == BIG_KEY_ENC) - ret = crypto_skcipher_encrypt(req); + ret = crypto_aead_encrypt(aead_req); else - ret = crypto_skcipher_decrypt(req); - - skcipher_request_zero(req); - + ret = crypto_aead_decrypt(aead_req); error: + mutex_unlock(&big_key_aead_lock); + aead_request_free(aead_req); return ret; } @@ -146,16 +157,13 @@ int big_key_preparse(struct key_preparsed_payload *prep) * * File content is stored encrypted with randomly generated key. */ - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; - /* prepare aligned data to encrypt */ data = kmalloc(enclen, GFP_KERNEL); if (!data) return -ENOMEM; - memcpy(data, prep->data, datalen); - memset(data + datalen, 0x00, enclen - datalen); /* generate random key */ enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL); @@ -163,13 +171,12 @@ int big_key_preparse(struct key_preparsed_payload *prep) ret = -ENOMEM; goto error; } - - ret = big_key_gen_enckey(enckey); - if (ret) + ret = get_random_bytes_wait(enckey, ENC_KEY_SIZE); + if (unlikely(ret)) goto err_enckey; /* encrypt aligned data */ - ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey); + ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey); if (ret) goto err_enckey; @@ -195,7 +202,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) *path = file->f_path; path_get(path); fput(file); - kfree(data); + kzfree(data); } else { /* Just store the data in a buffer */ void *data = kmalloc(datalen, GFP_KERNEL); @@ -211,9 +218,9 @@ int big_key_preparse(struct key_preparsed_payload *prep) err_fput: fput(file); err_enckey: - kfree(enckey); + kzfree(enckey); error: - kfree(data); + kzfree(data); return ret; } @@ -227,7 +234,7 @@ void big_key_free_preparse(struct key_preparsed_payload *prep) path_put(path); } - kfree(prep->payload.data[big_key_data]); + kzfree(prep->payload.data[big_key_data]); } /* @@ -259,7 +266,7 @@ void big_key_destroy(struct key *key) path->mnt = NULL; path->dentry = NULL; } - kfree(key->payload.data[big_key_data]); + kzfree(key->payload.data[big_key_data]); key->payload.data[big_key_data] = NULL; } @@ -295,7 +302,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) struct file *file; u8 *data; u8 *enckey = (u8 *)key->payload.data[big_key_data]; - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; data = kmalloc(enclen, GFP_KERNEL); @@ -328,7 +335,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) err_fput: fput(file); error: - kfree(data); + kzfree(data); } else { ret = datalen; if (copy_to_user(buffer, key->payload.data[big_key_data], @@ -344,47 +351,31 @@ error: */ static int __init big_key_init(void) { - struct crypto_skcipher *cipher; - struct crypto_rng *rng; int ret; - rng = crypto_alloc_rng(big_key_rng_name, 0, 0); - if (IS_ERR(rng)) { - pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng)); - return PTR_ERR(rng); - } - - big_key_rng = rng; - - /* seed RNG */ - ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng)); - if (ret) { - pr_err("Can't reset rng: %d\n", ret); - goto error_rng; - } - /* init block cipher */ - cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(cipher)) { - ret = PTR_ERR(cipher); + big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(big_key_aead)) { + ret = PTR_ERR(big_key_aead); pr_err("Can't alloc crypto: %d\n", ret); - goto error_rng; + return ret; + } + ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE); + if (ret < 0) { + pr_err("Can't set crypto auth tag len: %d\n", ret); + goto free_aead; } - - big_key_skcipher = cipher; ret = register_key_type(&key_type_big_key); if (ret < 0) { pr_err("Can't register type: %d\n", ret); - goto error_cipher; + goto free_aead; } return 0; -error_cipher: - crypto_free_skcipher(big_key_skcipher); -error_rng: - crypto_free_rng(big_key_rng); +free_aead: + crypto_free_aead(big_key_aead); return ret; } diff --git a/security/keys/internal.h b/security/keys/internal.h index 1c02c65..503adba 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -141,7 +141,7 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref, extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx); extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx); -extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check); +extern struct key *find_keyring_by_name(const char *name, bool uid_keyring); extern int install_user_keyrings(void); extern int install_thread_keyring_to_cred(struct cred *); diff --git a/security/keys/key.c b/security/keys/key.c index 83da68d..eb914a8 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -54,10 +54,10 @@ void __key_check(const struct key *key) struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; - struct rb_node *parent = NULL; - struct rb_node **p; + struct rb_node *parent, **p; try_again: + parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); @@ -302,6 +302,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; + if (flags & KEY_ALLOC_UID_KEYRING) + key->flags |= 1 << KEY_FLAG_UID_KEYRING; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ab0b337..365ff85 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -766,12 +766,17 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) key = key_ref_to_ptr(key_ref); + if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { + ret = -ENOKEY; + goto error2; + } + /* see if we can read it directly */ ret = key_permission(key_ref, KEY_NEED_READ); if (ret == 0) goto can_read_key; if (ret != -EACCES) - goto error; + goto error2; /* we can't; see if it's searchable from this process's keyrings * - we automatically take account of the fact that it may be @@ -1406,11 +1411,9 @@ long keyctl_assume_authority(key_serial_t id) } ret = keyctl_change_reqkey_auth(authkey); - if (ret < 0) - goto error; + if (ret == 0) + ret = authkey->serial; key_put(authkey); - - ret = authkey->serial; error: return ret; } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index de81793..4fa82a8 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -423,7 +423,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m) } struct keyring_read_iterator_context { - size_t qty; + size_t buflen; size_t count; key_serial_t __user *buffer; }; @@ -435,9 +435,9 @@ static int keyring_read_iterator(const void *object, void *data) int ret; kenter("{%s,%d},,{%zu/%zu}", - key->type->name, key->serial, ctx->count, ctx->qty); + key->type->name, key->serial, ctx->count, ctx->buflen); - if (ctx->count >= ctx->qty) + if (ctx->count >= ctx->buflen) return 1; ret = put_user(key->serial, ctx->buffer); @@ -472,16 +472,12 @@ static long keyring_read(const struct key *keyring, return 0; /* Calculate how much data we could return */ - ctx.qty = nr_keys * sizeof(key_serial_t); - if (!buffer || !buflen) - return ctx.qty; - - if (buflen > ctx.qty) - ctx.qty = buflen; + return nr_keys * sizeof(key_serial_t); /* Copy the IDs of the subscribed keys into the buffer */ ctx.buffer = (key_serial_t __user *)buffer; + ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { @@ -1101,15 +1097,15 @@ found: /* * Find a keyring with the specified name. * - * All named keyrings in the current user namespace are searched, provided they - * grant Search permission directly to the caller (unless this check is - * skipped). Keyrings whose usage points have reached zero or who have been - * revoked are skipped. + * Only keyrings that have nonzero refcount, are not revoked, and are owned by a + * user in the current user namespace are considered. If @uid_keyring is %true, + * the keyring additionally must have been allocated as a user or user session + * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ -struct key *find_keyring_by_name(const char *name, bool skip_perm_check) +struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct key *keyring; int bucket; @@ -1137,10 +1133,15 @@ struct key *find_keyring_by_name(const char *name, bool skip_perm_check) if (strcmp(keyring->description, name) != 0) continue; - if (!skip_perm_check && - key_permission(make_key_ref(keyring, 0), - KEY_NEED_SEARCH) < 0) - continue; + if (uid_keyring) { + if (!test_bit(KEY_FLAG_UID_KEYRING, + &keyring->flags)) + continue; + } else { + if (key_permission(make_key_ref(keyring, 0), + KEY_NEED_SEARCH) < 0) + continue; + } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' diff --git a/security/keys/proc.c b/security/keys/proc.c index bf08d02..de83430 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -187,7 +187,7 @@ static int proc_keys_show(struct seq_file *m, void *v) struct keyring_search_context ctx = { .index_key.type = key->type, .index_key.description = key->description, - .cred = current_cred(), + .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, @@ -207,11 +207,7 @@ static int proc_keys_show(struct seq_file *m, void *v) } } - /* check whether the current task is allowed to view the key (assuming - * non-possession) - * - the caller holds a spinlock, and thus the RCU read lock, making our - * access to __current_cred() safe - */ + /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 86bced9..293d359 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -77,7 +77,8 @@ int install_user_keyrings(void) if (IS_ERR(uid_keyring)) { uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(uid_keyring)) { ret = PTR_ERR(uid_keyring); @@ -94,7 +95,8 @@ int install_user_keyrings(void) session_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(session_keyring)) { ret = PTR_ERR(session_keyring); diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index afe9d22..6ebf1af 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -120,6 +120,18 @@ static void request_key_auth_revoke(struct key *key) } } +static void free_request_key_auth(struct request_key_auth *rka) +{ + if (!rka) + return; + key_put(rka->target_key); + key_put(rka->dest_keyring); + if (rka->cred) + put_cred(rka->cred); + kfree(rka->callout_info); + kfree(rka); +} + /* * Destroy an instantiation authorisation token key. */ @@ -129,15 +141,7 @@ static void request_key_auth_destroy(struct key *key) kenter("{%d}", key->serial); - if (rka->cred) { - put_cred(rka->cred); - rka->cred = NULL; - } - - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); + free_request_key_auth(rka); } /* @@ -151,22 +155,18 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, const struct cred *cred = current->cred; struct key *authkey = NULL; char desc[20]; - int ret; + int ret = -ENOMEM; kenter("%d,", target->serial); /* allocate a auth record */ - rka = kmalloc(sizeof(*rka), GFP_KERNEL); - if (!rka) { - kleave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } - rka->callout_info = kmalloc(callout_len, GFP_KERNEL); - if (!rka->callout_info) { - kleave(" = -ENOMEM"); - kfree(rka); - return ERR_PTR(-ENOMEM); - } + rka = kzalloc(sizeof(*rka), GFP_KERNEL); + if (!rka) + goto error; + rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL); + if (!rka->callout_info) + goto error_free_rka; + rka->callout_len = callout_len; /* see if the calling process is already servicing the key request of * another process */ @@ -176,8 +176,12 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, /* if the auth key has been revoked, then the key we're * servicing is already instantiated */ - if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags)) - goto auth_key_revoked; + if (test_bit(KEY_FLAG_REVOKED, + &cred->request_key_auth->flags)) { + up_read(&cred->request_key_auth->sem); + ret = -EKEYREVOKED; + goto error_free_rka; + } irka = cred->request_key_auth->payload.data[0]; rka->cred = get_cred(irka->cred); @@ -193,8 +197,6 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, rka->target_key = key_get(target); rka->dest_keyring = key_get(dest_keyring); - memcpy(rka->callout_info, callout_info, callout_len); - rka->callout_len = callout_len; /* allocate the auth key */ sprintf(desc, "%x", target->serial); @@ -205,32 +207,22 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(authkey)) { ret = PTR_ERR(authkey); - goto error_alloc; + goto error_free_rka; } /* construct the auth key */ ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL); if (ret < 0) - goto error_inst; + goto error_put_authkey; kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage)); return authkey; -auth_key_revoked: - up_read(&cred->request_key_auth->sem); - kfree(rka->callout_info); - kfree(rka); - kleave("= -EKEYREVOKED"); - return ERR_PTR(-EKEYREVOKED); - -error_inst: - key_revoke(authkey); +error_put_authkey: key_put(authkey); -error_alloc: - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); +error_free_rka: + free_request_key_auth(rka); +error: kleave("= %d", ret); return ERR_PTR(ret); } diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 69d09c3..cd7359e 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req { /* kvm attributes for KVM_S390_VM_TOD */ #define KVM_S390_VM_TOD_LOW 0 #define KVM_S390_VM_TOD_HIGH 1 +#define KVM_S390_VM_TOD_EXT 2 + +struct kvm_s390_vm_tod_clock { + __u8 epoch_idx; + __u64 tod; +}; /* kvm attributes for KVM_S390_VM_CPU_MODEL */ /* processor related attributes are r/w */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 8ea315a1..2519c6c 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ @@ -287,6 +288,7 @@ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dff775..c10c912 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h new file mode 100644 index 0000000..e4732d3 --- /dev/null +++ b/tools/include/asm-generic/hugetlb_encode.h @@ -0,0 +1,34 @@ +#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_ +#define _ASM_GENERIC_HUGETLB_ENCODE_H_ + +/* + * Several system calls take a flag to request "hugetlb" huge pages. + * Without further specification, these system calls will use the + * system's default huge page size. If a system supports multiple + * huge page sizes, the desired huge page size can be specified in + * bits [26:31] of the flag arguments. The value in these 6 bits + * will encode the log2 of the huge page size. + * + * The following definitions are associated with this huge page size + * encoding in flag arguments. System call specific header files + * that use this encoding should include this file. They can then + * provide definitions based on these with their own specific prefix. + * for example: + * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT + */ + +#define HUGETLB_FLAG_ENCODE_SHIFT 26 +#define HUGETLB_FLAG_ENCODE_MASK 0x3f + +#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) + +#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 8c27db0..203268f 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -58,20 +58,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 101593a..97677cd 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -700,6 +700,7 @@ struct drm_prime_handle { struct drm_syncobj_create { __u32 handle; +#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) __u32 flags; }; @@ -718,6 +719,24 @@ struct drm_syncobj_handle { __u32 pad; }; +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +struct drm_syncobj_wait { + __u64 handles; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +struct drm_syncobj_array { + __u64 handles; + __u32 count_handles; + __u32 pad; +}; + #if defined(__cplusplus) } #endif @@ -840,6 +859,9 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait) +#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) +#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) /** * Device specific ioctls should only be in their respective headers diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 7ccbd6a..6598fb7 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 #define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 #define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY. + */ +#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 + typedef struct drm_i915_getparam { __s32 param; /* @@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +struct drm_i915_gem_exec_fence { + /** + * User's handle for a drm_syncobj to wait on or signal. + */ + __u32 handle; + +#define I915_EXEC_FENCE_WAIT (1<<0) +#define I915_EXEC_FENCE_SIGNAL (1<<1) + __u32 flags; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 { __u32 DR1; __u32 DR4; __u32 num_cliprects; - /** This is a struct drm_clip_rect *cliprects */ + /** + * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY + * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a + * struct drm_i915_gem_exec_fence *fences. + */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (7<<0) #define I915_EXEC_DEFAULT (0<<0) @@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 { * element). */ #define I915_EXEC_BATCH_FIRST (1<<18) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1)) + +/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr + * define an array of i915_gem_exec_fence structures which specify a set of + * dma fences to wait upon or signal. + */ +#define I915_EXEC_FENCE_ARRAY (1<<19) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; +/** + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + char uuid[36]; + + __u32 n_mux_regs; + __u32 n_boolean_regs; + __u32 n_flex_regs; + + __u64 __user mux_regs_ptr; + __u64 __user boolean_regs_ptr; + __u64 __user flex_regs_ptr; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 461811e..43ab5c4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -143,12 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -enum bpf_sockmap_flags { - BPF_SOCKMAP_UNSPEC, - BPF_SOCKMAP_STRPARSER, - __MAX_BPF_SOCKMAP_FLAG -}; - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -368,9 +362,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -632,7 +637,7 @@ union bpf_attr { FN(skb_adjust_room), \ FN(redirect_map), \ FN(sk_redirect_map), \ - FN(sock_map_update), + FN(sock_map_update), \ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -753,20 +758,23 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6cd63c1..8388875 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size { struct kvm_ppc_smmu_info { __u64 flags; __u32 slb_size; - __u32 pad; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index 81d8edf..a937480 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -1,7 +1,8 @@ #ifndef _UAPI_LINUX_MMAN_H #define _UAPI_LINUX_MMAN_H -#include <uapi/asm/mman.h> +#include <asm/mman.h> +#include <asm-generic/hugetlb_encode.h> #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt index 6a1af43..3995735 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/stack-validation.txt @@ -194,10 +194,10 @@ they mean, and suggestions for how to fix them. If it's a GCC-compiled .c file, the error may be because the function uses an inline asm() statement which has a "call" instruction. An asm() statement with a call instruction must declare the use of the - stack pointer in its output operand. For example, on x86_64: + stack pointer in its output operand. On x86_64, this means adding + the ASM_CALL_CONSTRAINT as an output constraint: - register void *__sp asm("rsp"); - asm volatile("call func" : "+r" (__sp)); + asm volatile("call func" : ASM_CALL_CONSTRAINT); Otherwise the stack frame may not get created before the call. diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0e8c8ec..34a579f 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -208,14 +208,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0x89: - if (rex == 0x48 && modrm == 0xe5) { + if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) { - /* mov %rsp, %rbp */ + /* mov %rsp, reg */ *type = INSN_STACK; op->src.type = OP_SRC_REG; op->src.reg = CFI_SP; op->dest.type = OP_DEST_REG; - op->dest.reg = CFI_BP; + op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b]; break; } @@ -284,11 +284,16 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, case 0x8d: if (sib == 0x24 && rex_w && !rex_b && !rex_x) { - /* lea disp(%rsp), reg */ *type = INSN_STACK; - op->src.type = OP_SRC_ADD; + if (!insn.displacement.value) { + /* lea (%rsp), reg */ + op->src.type = OP_SRC_REG; + } else { + /* lea disp(%rsp), reg */ + op->src.type = OP_SRC_ADD; + op->src.offset = insn.displacement.value; + } op->src.reg = CFI_SP; - op->src.offset = insn.displacement.value; op->dest.type = OP_DEST_REG; op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f744617..a0c518e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1203,24 +1203,39 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state) switch (op->src.type) { case OP_SRC_REG: - if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) { + if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP && + cfa->base == CFI_SP && + regs[CFI_BP].base == CFI_CFA && + regs[CFI_BP].offset == -cfa->offset) { + + /* mov %rsp, %rbp */ + cfa->base = op->dest.reg; + state->bp_scratch = false; + } - if (cfa->base == CFI_SP && - regs[CFI_BP].base == CFI_CFA && - regs[CFI_BP].offset == -cfa->offset) { + else if (op->src.reg == CFI_SP && + op->dest.reg == CFI_BP && state->drap) { - /* mov %rsp, %rbp */ - cfa->base = op->dest.reg; - state->bp_scratch = false; - } + /* drap: mov %rsp, %rbp */ + regs[CFI_BP].base = CFI_BP; + regs[CFI_BP].offset = -state->stack_size; + state->bp_scratch = false; + } - else if (state->drap) { + else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) { - /* drap: mov %rsp, %rbp */ - regs[CFI_BP].base = CFI_BP; - regs[CFI_BP].offset = -state->stack_size; - state->bp_scratch = false; - } + /* + * mov %rsp, %reg + * + * This is needed for the rare case where GCC + * does: + * + * mov %rsp, %rax + * ... + * mov %rax, %rsp + */ + state->vals[op->dest.reg].base = CFI_CFA; + state->vals[op->dest.reg].offset = -state->stack_size; } else if (op->dest.reg == cfa->base) { diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 6207282..627b7ca 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,34 +1,8 @@ tools/perf -tools/arch/alpha/include/asm/barrier.h -tools/arch/arm/include/asm/barrier.h -tools/arch/arm64/include/asm/barrier.h -tools/arch/ia64/include/asm/barrier.h -tools/arch/mips/include/asm/barrier.h -tools/arch/powerpc/include/asm/barrier.h -tools/arch/s390/include/asm/barrier.h -tools/arch/sh/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier_32.h -tools/arch/sparc/include/asm/barrier_64.h -tools/arch/tile/include/asm/barrier.h -tools/arch/x86/include/asm/barrier.h -tools/arch/x86/include/asm/cmpxchg.h -tools/arch/x86/include/asm/cpufeatures.h -tools/arch/x86/include/asm/disabled-features.h -tools/arch/x86/include/asm/required-features.h -tools/arch/x86/include/uapi/asm/svm.h -tools/arch/x86/include/uapi/asm/vmx.h -tools/arch/x86/include/uapi/asm/kvm.h -tools/arch/x86/include/uapi/asm/kvm_perf.h -tools/arch/x86/lib/memcpy_64.S -tools/arch/x86/lib/memset_64.S -tools/arch/s390/include/uapi/asm/kvm_perf.h -tools/arch/s390/include/uapi/asm/sie.h -tools/arch/xtensa/include/asm/barrier.h +tools/arch tools/scripts tools/build -tools/arch/x86/include/asm/atomic.h -tools/arch/x86/include/asm/rmwcc.h +tools/include tools/lib/traceevent tools/lib/api tools/lib/bpf @@ -42,60 +16,3 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c -tools/include/asm/alternative-asm.h -tools/include/asm/atomic.h -tools/include/asm/barrier.h -tools/include/asm/bug.h -tools/include/asm-generic/atomic-gcc.h -tools/include/asm-generic/barrier.h -tools/include/asm-generic/bitops/arch_hweight.h -tools/include/asm-generic/bitops/atomic.h -tools/include/asm-generic/bitops/const_hweight.h -tools/include/asm-generic/bitops/__ffs.h -tools/include/asm-generic/bitops/__ffz.h -tools/include/asm-generic/bitops/__fls.h -tools/include/asm-generic/bitops/find.h -tools/include/asm-generic/bitops/fls64.h -tools/include/asm-generic/bitops/fls.h -tools/include/asm-generic/bitops/hweight.h -tools/include/asm-generic/bitops.h -tools/include/linux/atomic.h -tools/include/linux/bitops.h -tools/include/linux/compiler.h -tools/include/linux/compiler-gcc.h -tools/include/linux/coresight-pmu.h -tools/include/linux/bug.h -tools/include/linux/filter.h -tools/include/linux/hash.h -tools/include/linux/kernel.h -tools/include/linux/list.h -tools/include/linux/log2.h -tools/include/uapi/asm-generic/fcntl.h -tools/include/uapi/asm-generic/ioctls.h -tools/include/uapi/asm-generic/mman-common.h -tools/include/uapi/asm-generic/mman.h -tools/include/uapi/drm/drm.h -tools/include/uapi/drm/i915_drm.h -tools/include/uapi/linux/bpf.h -tools/include/uapi/linux/bpf_common.h -tools/include/uapi/linux/fcntl.h -tools/include/uapi/linux/hw_breakpoint.h -tools/include/uapi/linux/kvm.h -tools/include/uapi/linux/mman.h -tools/include/uapi/linux/perf_event.h -tools/include/uapi/linux/sched.h -tools/include/uapi/linux/stat.h -tools/include/uapi/linux/vhost.h -tools/include/uapi/sound/asound.h -tools/include/linux/poison.h -tools/include/linux/rbtree.h -tools/include/linux/rbtree_augmented.h -tools/include/linux/refcount.h -tools/include/linux/string.h -tools/include/linux/stringify.h -tools/include/linux/types.h -tools/include/linux/err.h -tools/include/linux/bitmap.h -tools/include/linux/time64.h -tools/arch/*/include/uapi/asm/mman.h -tools/arch/*/include/uapi/asm/perf_regs.h diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index bd518b6..5bd7b92 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,5 +1,4 @@ libperf-y += header.o -libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c deleted file mode 100644 index e103f6e..0000000 --- a/tools/perf/arch/s390/util/sym-handling.c +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Architecture specific ELF symbol handling and relocation mapping. - * - * Copyright 2017 IBM Corp. - * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - */ - -#include "symbol.h" - -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - if (ehdr.e_type == ET_EXEC) - return false; - return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; -} - -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map) -{ - if (map->type == MAP__FUNCTION) - sym->st_value += map->start; -} -#endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 510b513..be09d77 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4bb8937..0dccdb8 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; struct perf_evsel *evsel; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5c39f42..9cf781f 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, - struct map *map __maybe_unused) -{ - sym->st_value -= shdr->sh_addr - shdr->sh_offset; -} - int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - arch__adjust_sym_map_offset(&sym, &shdr, map); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; if (strcmp(section_name, (curr_dso->short_name + diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2bd6a1f..aad99e7 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map __maybe_unused); #endif #define SYMBOL_A 0 diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 19e5db9..6eea7cf 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,9 +15,9 @@ #include "syscalltbl.h" #include <stdlib.h> +#include <linux/compiler.h> #ifdef HAVE_SYSCALL_TABLE -#include <linux/compiler.h> #include <string.h> #include "string2.h" #include "util.h" diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 26ce4f7..ff80564 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -52,6 +52,10 @@ override LDFLAGS = override MAKEFLAGS = endif +ifneq ($(KBUILD_SRC),) +override LDFLAGS = +endif + BUILD := $(O) ifndef BUILD BUILD := $(KBUILD_OUTPUT) @@ -62,32 +66,32 @@ endif export BUILD all: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_tests: all - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_hotplug: hotplug - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ done; clean_hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; @@ -103,7 +107,7 @@ install: ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH) - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; @@ -128,7 +132,7 @@ else endif clean: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 20ecbaa..6c53a89 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -12,6 +12,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; + int n; fp = fopen(fcpu, "r"); if (!fp) { @@ -20,17 +21,17 @@ static inline unsigned int bpf_num_possible_cpus(void) } while (fgets(buff, sizeof(buff), fp)) { - if (sscanf(buff, "%u-%u", &start, &end) == 2) { - possible_cpus = start == 0 ? end + 1 : 0; - break; + n = sscanf(buff, "%u-%u", &start, &end); + if (n == 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; } + possible_cpus = start == 0 ? end + 1 : 0; + break; } - fclose(fp); - if (!possible_cpus) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } return possible_cpus; } diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 6b214b7..247b0a1 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -2,14 +2,14 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +TEST_GEN_PROGS := step_after_suspend_test + ifeq ($(ARCH),x86) -TEST_GEN_PROGS := breakpoint_test +TEST_GEN_PROGS += breakpoint_test endif ifneq (,$(filter $(ARCH),aarch64 arm64)) -TEST_GEN_PROGS := breakpoint_test_arm64 +TEST_GEN_PROGS += breakpoint_test_arm64 endif -TEST_GEN_PROGS += step_after_suspend_test - include ../lib.mk diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 2a1cb99..a4fd4c8 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -1,6 +1,8 @@ #!/bin/sh # description: Register/unregister many kprobe events +[ -f kprobe_events ] || exit_unsupported # this is configurable + # ftrace fentry skip size depends on the machine architecture. # Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le case `uname -m` in diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 7c647f6..f0c0369 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -7,14 +7,17 @@ TEST_PROGS := run.sh include ../lib.mk all: - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + if [ -e $$DIR/$(TEST_PROGS) ]; then + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; + fi done override define RUN_TESTS - $(OUTPUT)/run.sh + @cd $(OUTPUT); ./run.sh endef override define INSTALL_RULE @@ -33,7 +36,7 @@ override define EMIT_TESTS endef override define CLEAN - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 849a90f..a97e24e 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,7 +1,9 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDLIBS := $(LDLIBS) -lm +ifeq (,$(filter $(ARCH),x86)) TEST_GEN_FILES := msr aperf +endif TEST_PROGS := run.sh diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index 7868c10..d3ab48f 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -29,13 +29,12 @@ EVALUATE_ONLY=0 -max_cpus=$(($(nproc)-1)) +if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then + echo "$0 # Skipped: Test can only run on x86 architectures." + exit 0 +fi -# compile programs -gcc aperf.c -Wall -D_GNU_SOURCE -o aperf -lm -[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1 -gcc -o msr msr.c -lm -[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1 +max_cpus=$(($(nproc)-1)) function run_test () { diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 6936166..f65886a 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -6,7 +6,14 @@ ifeq (0,$(MAKELEVEL)) OUTPUT := $(shell pwd) endif +# The following are built by lib.mk common compile rules. +# TEST_CUSTOM_PROGS should be used by tests that require +# custom build rule and prevent common build rule use. +# TEST_PROGS are for test shell scripts. +# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests +# and install targets. Common clean doesn't touch them. TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) +TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) @@ -20,17 +27,28 @@ define RUN_TESTS test_num=`echo $$test_num+1 | bc`; \ echo "selftests: $$BASENAME_TEST"; \ echo "========================================"; \ - if [ ! -x $$BASENAME_TEST ]; then \ + if [ ! -x $$TEST ]; then \ echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\ echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \ else \ - cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ + cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ fi; \ done; endef run_tests: all - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS)) +ifneq ($(KBUILD_SRC),) + @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then + @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + fi + @if [ "X$(TEST_PROGS)" != "X" ]; then + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) + else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + fi +else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) +endif define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ @@ -38,10 +56,10 @@ define INSTALL_RULE echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ + @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ + echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ fi endef @@ -53,15 +71,20 @@ else endif define EMIT_TESTS - @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \ BASENAME_TEST=`basename $$TEST`; \ - echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ + echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ done; endef emit_tests: $(EMIT_TESTS) +# define if isn't already. It is undefined in make O= case. +ifeq ($(RM),) +RM := rm -f +endif + define CLEAN $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) endef @@ -69,6 +92,15 @@ endef clean: $(CLEAN) +# When make O= with kselftest target from main level +# the following aren't defined. +# +ifneq ($(KBUILD_SRC),) +LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c +LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +endif + $(OUTPUT)/%:%.c $(LINK.c) $^ $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh index daabb35..daabb35 100644..100755 --- a/tools/testing/selftests/memfd/run_tests.sh +++ b/tools/testing/selftests/memfd/run_tests.sh diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 79a664a..0f5e347 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk override define RUN_TESTS - @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" - @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" + $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef override define EMIT_TESTS diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 9801253..c612d6e 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -6,3 +6,4 @@ reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack +reuseaddr_conflict diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index de1f577..d86bca9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,9 +5,9 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_GEN_FILES = socket -TEST_GEN_FILES += psock_fanout psock_tpacket -TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack msg_zerocopy +TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa +TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 40232af..3ab6ec4 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -55,7 +55,7 @@ #include <unistd.h> #ifndef SO_EE_ORIGIN_ZEROCOPY -#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE +#define SO_EE_ORIGIN_ZEROCOPY 5 #endif #ifndef SO_ZEROCOPY diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index 4e00568..90cb903 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -178,7 +178,7 @@ if [ "$(id -u)" -ne 0 ];then exit 0 fi -ip -Version 2>/dev/null >/dev/null +ip link show 2>/dev/null >/dev/null if [ $? -ne 0 ];then echo "SKIP: Could not run test without the ip tool" exit 0 diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c new file mode 100644 index 0000000..7c5b126 --- /dev/null +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -0,0 +1,114 @@ +/* + * Test for the regression introduced by + * + * b9470c27607b ("inet: kill smallest_size and smallest_port") + * + * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb + * when we open the ipv6 conterpart, which is what was happening previously. + */ +#include <errno.h> +#include <error.h> +#include <arpa/inet.h> +#include <netinet/in.h> +#include <stdbool.h> +#include <stdio.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <unistd.h> + +#define PORT 9999 + +int open_port(int ipv6, int any) +{ + int fd = -1; + int reuseaddr = 1; + int v6only = 1; + int addrlen; + int ret = -1; + struct sockaddr *addr; + int family = ipv6 ? AF_INET6 : AF_INET; + + struct sockaddr_in6 addr6 = { + .sin6_family = AF_INET6, + .sin6_port = htons(PORT), + .sin6_addr = in6addr_any + }; + struct sockaddr_in addr4 = { + .sin_family = AF_INET, + .sin_port = htons(PORT), + .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"), + }; + + + if (ipv6) { + addr = (struct sockaddr*)&addr6; + addrlen = sizeof(addr6); + } else { + addr = (struct sockaddr*)&addr4; + addrlen = sizeof(addr4); + } + + if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) { + perror("socket"); + goto out; + } + + if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only, + sizeof(v6only)) < 0) { + perror("setsockopt IPV6_V6ONLY"); + goto out; + } + + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr, + sizeof(reuseaddr)) < 0) { + perror("setsockopt SO_REUSEADDR"); + goto out; + } + + if (bind(fd, addr, addrlen) < 0) { + perror("bind"); + goto out; + } + + if (any) + return fd; + + if (listen(fd, 1) < 0) { + perror("listen"); + goto out; + } + return fd; +out: + close(fd); + return ret; +} + +int main(void) +{ + int listenfd; + int fd1, fd2; + + fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT); + listenfd = open_port(0, 0); + if (listenfd < 0) + error(1, errno, "Couldn't open listen socket"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + fprintf(stderr, "Opening in6addr_any:%d\n", PORT); + fd1 = open_port(1, 1); + if (fd1 < 0) + error(1, errno, "Couldn't open ipv6 reuseport"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd2 = open_port(0, 1); + if (fd2 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + close(fd1); + fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); + fprintf(stderr, "Success"); + return 0; +} diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 67c3e27..24dbf63 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -6,10 +6,18 @@ */ #include <sys/types.h> -#include <asm/siginfo.h> -#define __have_siginfo_t 1 -#define __have_sigval_t 1 -#define __have_sigevent_t 1 + +/* + * glibc 2.26 and later have SIGSYS in siginfo_t. Before that, + * we need to use the kernel's siginfo.h file and trick glibc + * into accepting it. + */ +#if !__GLIBC_PREREQ(2, 26) +# include <asm/siginfo.h> +# define __have_siginfo_t 1 +# define __have_sigval_t 1 +# define __have_sigevent_t 1 +#endif #include <errno.h> #include <linux/filter.h> @@ -884,7 +892,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS) syscall(__NR_getpid); } -static struct siginfo TRAP_info; +static siginfo_t TRAP_info; static volatile int TRAP_nr; static void TRAP_action(int nr, siginfo_t *info, void *void_context) { diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 7d406c3..97bb150 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -39,7 +39,11 @@ void my_usr1(int sig, siginfo_t *si, void *u) stack_t stk; struct stk_data *p; +#if __s390x__ + register unsigned long sp asm("%15"); +#else register unsigned long sp asm("sp"); +#endif if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + SIGSTKSZ) { diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index 4981c6b..8e04d0a 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -2,12 +2,16 @@ CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra CFLAGS += -I../../../../usr/include/ LDFLAGS += -pthread -TEST_PROGS = sync_test - -all: $(TEST_PROGS) +.PHONY: all clean include ../lib.mk +# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special +# build rules. lib.mk will run and install them. + +TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test +all: $(TEST_CUSTOM_PROGS) + OBJS = sync_test.o sync.o TESTS += sync_alloc.o @@ -18,6 +22,16 @@ TESTS += sync_stress_parallelism.o TESTS += sync_stress_consumer.o TESTS += sync_stress_merge.o -sync_test: $(OBJS) $(TESTS) +OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS)) +TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS)) + +$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) + $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) + +$(OBJS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ + +$(TESTS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ -EXTRA_CLEAN := sync_test $(OBJS) $(TESTS) +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9c92b7b..50da454 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -143,7 +143,8 @@ int setup_timer(int clock_id, int flags, int interval, timer_t *tm1) printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n", clockstring(clock_id), flags ? "ABSTIME":"RELTIME"); - return 0; + /* Indicate timer isn't set, so caller doesn't wait */ + return 1; } printf("%s - timer_create() failed\n", clockstring(clock_id)); return -1; @@ -213,8 +214,9 @@ int do_timer(int clock_id, int flags) int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; while (alarmcount < 5) sleep(1); @@ -228,18 +230,17 @@ int do_timer_oneshot(int clock_id, int flags) timer_t tm1; const int interval = 0; struct timeval timeout; - fd_set fds; int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; memset(&timeout, 0, sizeof(timeout)); timeout.tv_sec = 5; - FD_ZERO(&fds); do { - err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout); + err = select(0, NULL, NULL, NULL, &timeout); } while (err == -1 && errno == EINTR); timer_delete(tm1); diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile index f863c66..ee06851 100644 --- a/tools/testing/selftests/watchdog/Makefile +++ b/tools/testing/selftests/watchdog/Makefile @@ -1,8 +1,3 @@ -TEST_PROGS := watchdog-test - -all: $(TEST_PROGS) +TEST_GEN_PROGS := watchdog-test include ../lib.mk - -clean: - rm -fr $(TEST_PROGS) |
