diff options
| author | Ingo Molnar <mingo@kernel.org> | 2012-07-31 17:05:27 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2012-07-31 17:05:27 +0200 |
| commit | 1f815faec46e83bc96039797151846b60875bb06 (patch) | |
| tree | 41a874f8090e3f69c8a9f13e3c85dd7a371e569b | |
| parent | b44d50dcacea0d485ca2ff9140f8cc28ee22f28d (diff) | |
| parent | e2b34e311be3a57c9abcb927e37a57e38913714c (diff) | |
| download | olio-linux-3.10-1f815faec46e83bc96039797151846b60875bb06.tar.xz olio-linux-3.10-1f815faec46e83bc96039797151846b60875bb06.zip | |
Merge branch 'linus' into timers/urgent
Merge in Linus's branch which already has timers/core merged.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
396 files changed, 9302 insertions, 4783 deletions
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 5c8d7496809..fc103d7a047 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -162,9 +162,9 @@ over a rather long period of time, but improvements are always welcome! when publicizing a pointer to a structure that can be traversed by an RCU read-side critical section. -5. If call_rcu(), or a related primitive such as call_rcu_bh() or - call_rcu_sched(), is used, the callback function must be - written to be called from softirq context. In particular, +5. If call_rcu(), or a related primitive such as call_rcu_bh(), + call_rcu_sched(), or call_srcu() is used, the callback function + must be written to be called from softirq context. In particular, it cannot block. 6. Since synchronize_rcu() can block, it cannot be called from @@ -202,11 +202,12 @@ over a rather long period of time, but improvements are always welcome! updater uses call_rcu_sched() or synchronize_sched(), then the corresponding readers must disable preemption, possibly by calling rcu_read_lock_sched() and rcu_read_unlock_sched(). - If the updater uses synchronize_srcu(), the the corresponding - readers must use srcu_read_lock() and srcu_read_unlock(), - and with the same srcu_struct. The rules for the expedited - primitives are the same as for their non-expedited counterparts. - Mixing things up will result in confusion and broken kernels. + If the updater uses synchronize_srcu() or call_srcu(), + the the corresponding readers must use srcu_read_lock() and + srcu_read_unlock(), and with the same srcu_struct. The rules for + the expedited primitives are the same as for their non-expedited + counterparts. Mixing things up will result in confusion and + broken kernels. One exception to this rule: rcu_read_lock() and rcu_read_unlock() may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh() @@ -333,14 +334,14 @@ over a rather long period of time, but improvements are always welcome! victim CPU from ever going offline.) 14. SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(), - synchronize_srcu(), and synchronize_srcu_expedited()) may only - be invoked from process context. Unlike other forms of RCU, it - -is- permissible to block in an SRCU read-side critical section - (demarked by srcu_read_lock() and srcu_read_unlock()), hence the - "SRCU": "sleepable RCU". Please note that if you don't need - to sleep in read-side critical sections, you should be using - RCU rather than SRCU, because RCU is almost always faster and - easier to use than is SRCU. + synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu()) + may only be invoked from process context. Unlike other forms of + RCU, it -is- permissible to block in an SRCU read-side critical + section (demarked by srcu_read_lock() and srcu_read_unlock()), + hence the "SRCU": "sleepable RCU". Please note that if you + don't need to sleep in read-side critical sections, you should be + using RCU rather than SRCU, because RCU is almost always faster + and easier to use than is SRCU. If you need to enter your read-side critical section in a hardirq or exception handler, and then exit that same read-side @@ -353,8 +354,8 @@ over a rather long period of time, but improvements are always welcome! cleanup_srcu_struct(). These are passed a "struct srcu_struct" that defines the scope of a given SRCU domain. Once initialized, the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock() - synchronize_srcu(), and synchronize_srcu_expedited(). A given - synchronize_srcu() waits only for SRCU read-side critical + synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu(). + A given synchronize_srcu() waits only for SRCU read-side critical sections governed by srcu_read_lock() and srcu_read_unlock() calls that have been passed the same srcu_struct. This property is what makes sleeping read-side critical sections tolerable -- @@ -374,7 +375,7 @@ over a rather long period of time, but improvements are always welcome! requiring SRCU's read-side deadlock immunity or low read-side realtime latency. - Note that, rcu_assign_pointer() relates to SRCU just as they do + Note that, rcu_assign_pointer() relates to SRCU just as it does to other forms of RCU. 15. The whole point of call_rcu(), synchronize_rcu(), and friends diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt index e439a0edee2..38428c12513 100644 --- a/Documentation/RCU/rcubarrier.txt +++ b/Documentation/RCU/rcubarrier.txt @@ -79,8 +79,6 @@ complete. Pseudo-code using rcu_barrier() is as follows: 2. Execute rcu_barrier(). 3. Allow the module to be unloaded. -Quick Quiz #1: Why is there no srcu_barrier()? - The rcutorture module makes use of rcu_barrier in its exit function as follows: @@ -162,7 +160,7 @@ for any pre-existing callbacks to complete. Then lines 55-62 print status and do operation-specific cleanup, and then return, permitting the module-unload operation to be completed. -Quick Quiz #2: Is there any other situation where rcu_barrier() might +Quick Quiz #1: Is there any other situation where rcu_barrier() might be required? Your module might have additional complications. For example, if your @@ -242,7 +240,7 @@ reaches zero, as follows: 4 complete(&rcu_barrier_completion); 5 } -Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes +Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes immediately (thus incrementing rcu_barrier_cpu_count to the value one), but the other CPU's rcu_barrier_func() invocations are delayed for a full grace period? Couldn't this result in @@ -259,12 +257,7 @@ so that your module may be safely unloaded. Answers to Quick Quizzes -Quick Quiz #1: Why is there no srcu_barrier()? - -Answer: Since there is no call_srcu(), there can be no outstanding SRCU - callbacks. Therefore, there is no need to wait for them. - -Quick Quiz #2: Is there any other situation where rcu_barrier() might +Quick Quiz #1: Is there any other situation where rcu_barrier() might be required? Answer: Interestingly enough, rcu_barrier() was not originally @@ -278,7 +271,7 @@ Answer: Interestingly enough, rcu_barrier() was not originally implementing rcutorture, and found that rcu_barrier() solves this problem as well. -Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes +Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes immediately (thus incrementing rcu_barrier_cpu_count to the value one), but the other CPU's rcu_barrier_func() invocations are delayed for a full grace period? Couldn't this result in diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 4ddf3913fd8..7dce8a17eac 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -174,11 +174,20 @@ torture_type The type of RCU to test, with string values as follows: and synchronize_rcu_bh_expedited(). "srcu": srcu_read_lock(), srcu_read_unlock() and + call_srcu(). + + "srcu_sync": srcu_read_lock(), srcu_read_unlock() and synchronize_srcu(). "srcu_expedited": srcu_read_lock(), srcu_read_unlock() and synchronize_srcu_expedited(). + "srcu_raw": srcu_read_lock_raw(), srcu_read_unlock_raw(), + and call_srcu(). + + "srcu_raw_sync": srcu_read_lock_raw(), srcu_read_unlock_raw(), + and synchronize_srcu(). + "sched": preempt_disable(), preempt_enable(), and call_rcu_sched(). diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 6bbe8dcdc3d..69ee188515e 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -833,9 +833,9 @@ sched: Critical sections Grace period Barrier SRCU: Critical sections Grace period Barrier - srcu_read_lock synchronize_srcu N/A - srcu_read_unlock synchronize_srcu_expedited - srcu_read_lock_raw + srcu_read_lock synchronize_srcu srcu_barrier + srcu_read_unlock call_srcu + srcu_read_lock_raw synchronize_srcu_expedited srcu_read_unlock_raw srcu_dereference diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt index 82b43f91585..a4119f6422d 100644 --- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt @@ -1626,3 +1626,5 @@ MX6Q_PAD_SD2_DAT3__PCIE_CTRL_MUX_11 1587 MX6Q_PAD_SD2_DAT3__GPIO_1_12 1588 MX6Q_PAD_SD2_DAT3__SJC_DONE 1589 MX6Q_PAD_SD2_DAT3__ANATOP_TESTO_3 1590 +MX6Q_PAD_ENET_RX_ER__ANATOP_USBOTG_ID 1591 +MX6Q_PAD_GPIO_1__ANATOP_USBOTG_ID 1592 diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 506c7390c2b..13f1aa09b93 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -86,7 +86,7 @@ There is also a gitweb interface available at http://www.kernel.org/git/?p=utils/kernel/kexec/kexec-tools.git More information about kexec-tools can be found at -http://www.kernel.org/pub/linux/utils/kernel/kexec/README.html +http://horms.net/projects/kexec/ 3) Unpack the tarball with the tar command, as follows: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index a92c5ebf373..12783fa833c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2367,6 +2367,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Set maximum number of finished RCU callbacks to process in one batch. + rcutree.fanout_leaf= [KNL,BOOT] + Increase the number of CPUs assigned to each + leaf rcu_node structure. Useful for very large + systems. + rcutree.qhimark= [KNL,BOOT] Set threshold of queued RCU callbacks over which batch limiting is disabled. diff --git a/MAINTAINERS b/MAINTAINERS index 1b71f6ceae0..fe643e7b9df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3433,13 +3433,14 @@ S: Supported F: drivers/idle/i7300_idle.c IEEE 802.15.4 SUBSYSTEM +M: Alexander Smirnov <alex.bluesman.smirnov@gmail.com> M: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> -M: Sergey Lapin <slapin@ossfans.org> L: linux-zigbee-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://apps.sourceforge.net/trac/linux-zigbee T: git git://git.kernel.org/pub/scm/linux/kernel/git/lowpan/lowpan.git S: Maintained F: net/ieee802154/ +F: net/mac802154/ F: drivers/ieee802154/ IIO SUBSYSTEM AND DRIVERS @@ -5564,7 +5565,7 @@ F: Documentation/networking/LICENSE.qla3xxx F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER -M: Anirban Chakraborty <anirban.chakraborty@qlogic.com> +M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> M: Sony Chacko <sony.chacko@qlogic.com> M: linux-driver@qlogic.com L: netdev@vger.kernel.org @@ -5572,7 +5573,6 @@ S: Supported F: drivers/net/ethernet/qlogic/qlcnic/ QLOGIC QLGE 10Gb ETHERNET DRIVER -M: Anirban Chakraborty <anirban.chakraborty@qlogic.com> M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> M: Ron Mercer <ron.mercer@qlogic.com> M: linux-driver@qlogic.com @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Saber-toothed Squirrel # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi index 10dcec7e732..f7b84aced65 100644 --- a/arch/arm/boot/dts/spear13xx.dtsi +++ b/arch/arm/boot/dts/spear13xx.dtsi @@ -43,8 +43,8 @@ pmu { compatible = "arm,cortex-a9-pmu"; - interrupts = <0 8 0x04 - 0 9 0x04>; + interrupts = <0 6 0x04 + 0 7 0x04>; }; L2: l2-cache { @@ -119,8 +119,8 @@ gmac0: eth@e2000000 { compatible = "st,spear600-gmac"; reg = <0xe2000000 0x8000>; - interrupts = <0 23 0x4 - 0 24 0x4>; + interrupts = <0 33 0x4 + 0 34 0x4>; interrupt-names = "macirq", "eth_wake_irq"; status = "disabled"; }; @@ -202,6 +202,7 @@ kbd@e0300000 { compatible = "st,spear300-kbd"; reg = <0xe0300000 0x1000>; + interrupts = <0 52 0x4>; status = "disabled"; }; @@ -224,7 +225,7 @@ serial@e0000000 { compatible = "arm,pl011", "arm,primecell"; reg = <0xe0000000 0x1000>; - interrupts = <0 36 0x4>; + interrupts = <0 35 0x4>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/spear320-evb.dts b/arch/arm/boot/dts/spear320-evb.dts index c13fd1f3b09..e4e912f9502 100644 --- a/arch/arm/boot/dts/spear320-evb.dts +++ b/arch/arm/boot/dts/spear320-evb.dts @@ -15,8 +15,8 @@ /include/ "spear320.dtsi" / { - model = "ST SPEAr300 Evaluation Board"; - compatible = "st,spear300-evb", "st,spear300"; + model = "ST SPEAr320 Evaluation Board"; + compatible = "st,spear320-evb", "st,spear320"; #address-cells = <1>; #size-cells = <1>; @@ -26,7 +26,7 @@ ahb { pinmux@b3000000 { - st,pinmux-mode = <3>; + st,pinmux-mode = <4>; pinctrl-names = "default"; pinctrl-0 = <&state_default>; diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi index 089f0a42c50..a3c36e47d7e 100644 --- a/arch/arm/boot/dts/spear600.dtsi +++ b/arch/arm/boot/dts/spear600.dtsi @@ -181,6 +181,7 @@ timer@f0000000 { compatible = "st,spear-timer"; reg = <0xf0000000 0x400>; + interrupt-parent = <&vic0>; interrupts = <16>; }; }; diff --git a/arch/arm/mach-spear3xx/spear3xx.c b/arch/arm/mach-spear3xx/spear3xx.c index 0f41bd1c47c..66db5f13af8 100644 --- a/arch/arm/mach-spear3xx/spear3xx.c +++ b/arch/arm/mach-spear3xx/spear3xx.c @@ -87,7 +87,7 @@ void __init spear3xx_map_io(void) static void __init spear3xx_timer_init(void) { - char pclk_name[] = "pll3_48m_clk"; + char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; spear3xx_clk_init(); diff --git a/arch/arm/mach-spear6xx/spear6xx.c b/arch/arm/mach-spear6xx/spear6xx.c index 2e2e3596583..9af67d003c6 100644 --- a/arch/arm/mach-spear6xx/spear6xx.c +++ b/arch/arm/mach-spear6xx/spear6xx.c @@ -423,7 +423,7 @@ void __init spear6xx_map_io(void) static void __init spear6xx_timer_init(void) { - char pclk_name[] = "pll3_48m_clk"; + char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; spear6xx_clk_init(); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4044abcf6f9..655878bcc96 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1091,7 +1091,7 @@ error: while (--i) if (pages[i]) __free_pages(pages[i], 0); - if (array_size < PAGE_SIZE) + if (array_size <= PAGE_SIZE) kfree(pages); else vfree(pages); @@ -1106,7 +1106,7 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t s for (i = 0; i < count; i++) if (pages[i]) __free_pages(pages[i], 0); - if (array_size < PAGE_SIZE) + if (array_size <= PAGE_SIZE) kfree(pages); else vfree(pages); diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index f7264621e58..149fbefc1a4 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -180,9 +180,7 @@ void __cpuinit start_secondary(void) notify_cpu_starting(cpu); - ipi_call_lock(); set_cpu_online(cpu, true); - ipi_call_unlock(); local_irq_enable(); diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 1113b8aba07..963d2db53bf 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -382,7 +382,6 @@ smp_callin (void) set_numa_node(cpu_to_node_map[cpuid]); set_numa_mem(local_memory_node(cpu_to_node_map[cpuid])); - ipi_call_lock_irq(); spin_lock(&vector_lock); /* Setup the per cpu irq handling data structures */ __setup_vector_irq(cpuid); @@ -390,7 +389,6 @@ smp_callin (void) set_cpu_online(cpuid, true); per_cpu(cpu_state, cpuid) = CPU_ONLINE; spin_unlock(&vector_lock); - ipi_call_unlock_irq(); smp_setup_percpu_timer(); diff --git a/arch/m32r/boot/compressed/Makefile b/arch/m32r/boot/compressed/Makefile index 177716b1d61..01729c2979b 100644 --- a/arch/m32r/boot/compressed/Makefile +++ b/arch/m32r/boot/compressed/Makefile @@ -43,9 +43,9 @@ endif OBJCOPYFLAGS += -R .empty_zero_page -suffix_$(CONFIG_KERNEL_GZIP) = gz -suffix_$(CONFIG_KERNEL_BZIP2) = bz2 -suffix_$(CONFIG_KERNEL_LZMA) = lzma +suffix-$(CONFIG_KERNEL_GZIP) = gz +suffix-$(CONFIG_KERNEL_BZIP2) = bz2 +suffix-$(CONFIG_KERNEL_LZMA) = lzma $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE $(call if_changed,ld) diff --git a/arch/m32r/boot/compressed/misc.c b/arch/m32r/boot/compressed/misc.c index 370d6088197..28a09529f20 100644 --- a/arch/m32r/boot/compressed/misc.c +++ b/arch/m32r/boot/compressed/misc.c @@ -28,7 +28,7 @@ static unsigned long free_mem_ptr; static unsigned long free_mem_end_ptr; #ifdef CONFIG_KERNEL_BZIP2 -static void *memset(void *s, int c, size_t n) +void *memset(void *s, int c, size_t n) { char *ss = s; @@ -39,6 +39,16 @@ static void *memset(void *s, int c, size_t n) #endif #ifdef CONFIG_KERNEL_GZIP +void *memcpy(void *dest, const void *src, size_t n) +{ + char *d = dest; + const char *s = src; + while (n--) + *d++ = *s++; + + return dest; +} + #define BOOT_HEAP_SIZE 0x10000 #include "../../../../lib/decompress_inflate.c" #endif diff --git a/arch/m32r/include/asm/ptrace.h b/arch/m32r/include/asm/ptrace.h index 527527584dd..4313aa62b51 100644 --- a/arch/m32r/include/asm/ptrace.h +++ b/arch/m32r/include/asm/ptrace.h @@ -113,9 +113,6 @@ struct pt_regs { #define PTRACE_OLDSETOPTIONS 21 -/* options set using PTRACE_SETOPTIONS */ -#define PTRACE_O_TRACESYSGOOD 0x00000001 - #ifdef __KERNEL__ #include <asm/m32r.h> /* M32R_PSW_BSM, M32R_PSW_BPM */ diff --git a/arch/m32r/include/asm/smp.h b/arch/m32r/include/asm/smp.h index cf7829a6155..c689b828dfe 100644 --- a/arch/m32r/include/asm/smp.h +++ b/arch/m32r/include/asm/smp.h @@ -79,11 +79,6 @@ static __inline__ int cpu_number_map(int cpu) return cpu; } -static __inline__ unsigned int num_booting_cpus(void) -{ - return cpumask_weight(&cpu_callout_map); -} - extern void smp_send_timer(void); extern unsigned long send_IPI_mask_phys(const cpumask_t*, int, int); diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c index 4c03361537a..51f5e9aa490 100644 --- a/arch/m32r/kernel/ptrace.c +++ b/arch/m32r/kernel/ptrace.c @@ -591,17 +591,16 @@ void user_enable_single_step(struct task_struct *child) if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0) != sizeof(insn)) - return -EIO; + return; compute_next_pc(insn, pc, &next_pc, child); if (next_pc & 0x80000000) - return -EIO; + return; if (embed_debug_trap(child, next_pc)) - return -EIO; + return; invalidate_cache(); - return 0; } void user_disable_single_step(struct task_struct *child) diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c index f3fb2c029cf..d0f60b97bbc 100644 --- a/arch/m32r/kernel/signal.c +++ b/arch/m32r/kernel/signal.c @@ -286,7 +286,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, case -ERESTARTNOINTR: regs->r0 = regs->orig_r0; if (prev_insn(regs) < 0) - return -EFAULT; + return; } } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 09ab87ee6fe..b3e10fdd389 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -288,6 +288,7 @@ config MIPS_MALTA select SYS_HAS_CPU_MIPS32_R1 select SYS_HAS_CPU_MIPS32_R2 select SYS_HAS_CPU_MIPS64_R1 + select SYS_HAS_CPU_MIPS64_R2 select SYS_HAS_CPU_NEVADA select SYS_HAS_CPU_RM7000 select SYS_HAS_EARLY_PRINTK @@ -1423,6 +1424,7 @@ config CPU_SB1 config CPU_CAVIUM_OCTEON bool "Cavium Octeon processor" depends on SYS_HAS_CPU_CAVIUM_OCTEON + select ARCH_SPARSEMEM_ENABLE select CPU_HAS_PREFETCH select CPU_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_SMP diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig index 6210b8d8410..b311be45a72 100644 --- a/arch/mips/bcm47xx/Kconfig +++ b/arch/mips/bcm47xx/Kconfig @@ -21,6 +21,7 @@ config BCM47XX_BCMA select BCMA select BCMA_HOST_SOC select BCMA_DRIVER_MIPS + select BCMA_HOST_PCI if PCI select BCMA_DRIVER_PCI_HOSTMODE if PCI default y help diff --git a/arch/mips/bcm63xx/dev-pcmcia.c b/arch/mips/bcm63xx/dev-pcmcia.c index de4d917fd54..a551bab5ecb 100644 --- a/arch/mips/bcm63xx/dev-pcmcia.c +++ b/arch/mips/bcm63xx/dev-pcmcia.c @@ -79,11 +79,11 @@ static int __init config_pcmcia_cs(unsigned int cs, return ret; } -static const __initdata struct { +static const struct { unsigned int cs; unsigned int base; unsigned int size; -} pcmcia_cs[3] = { +} pcmcia_cs[3] __initconst = { { .cs = MPI_CS_PCMCIA_COMMON, .base = BCM_PCMCIA_COMMON_BASE_PA, diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig index f9e275a50d9..2f4f6d5e05b 100644 --- a/arch/mips/cavium-octeon/Kconfig +++ b/arch/mips/cavium-octeon/Kconfig @@ -82,10 +82,6 @@ config CAVIUM_OCTEON_LOCK_L2_MEMCPY help Lock the kernel's implementation of memcpy() into L2. -config ARCH_SPARSEMEM_ENABLE - def_bool y - select SPARSEMEM_STATIC - config IOMMU_HELPER bool diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 4b93048044e..ee1fb9f7f51 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -185,7 +185,6 @@ static void __cpuinit octeon_init_secondary(void) octeon_init_cvmcount(); octeon_irq_setup_secondary(); - raw_local_irq_enable(); } /** @@ -233,6 +232,7 @@ static void octeon_smp_finish(void) /* to generate the first CPU timer interrupt */ write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); + local_irq_enable(); } /** diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index 2e1ad4c652b..82ad35ce2b4 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -17,7 +17,6 @@ #include <linux/irqflags.h> #include <linux/types.h> #include <asm/barrier.h> -#include <asm/bug.h> #include <asm/byteorder.h> /* sigh ... */ #include <asm/cpu-features.h> #include <asm/sgidefs.h> diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 285a41fa0b1..eee10dc07ac 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -8,6 +8,7 @@ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H +#include <linux/bug.h> #include <linux/irqflags.h> #include <asm/war.h> diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index f9fa2a479dd..95e40c1e8ed 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -94,6 +94,7 @@ #define PRID_IMP_24KE 0x9600 #define PRID_IMP_74K 0x9700 #define PRID_IMP_1004K 0x9900 +#define PRID_IMP_M14KC 0x9c00 /* * These are the PRID's for when 23:16 == PRID_COMP_SIBYTE @@ -260,12 +261,12 @@ enum cpu_type_enum { */ CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K, CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350, - CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, + CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, CPU_M14KC, /* * MIPS64 class processors */ - CPU_5KC, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, + CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2, CPU_XLR, CPU_XLP, @@ -288,7 +289,7 @@ enum cpu_type_enum { #define MIPS_CPU_ISA_M64R2 0x00000100 #define MIPS_CPU_ISA_32BIT (MIPS_CPU_ISA_I | MIPS_CPU_ISA_II | \ - MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 ) + MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2) #define MIPS_CPU_ISA_64BIT (MIPS_CPU_ISA_III | MIPS_CPU_ISA_IV | \ MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2) diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h index 86548da650e..991b659e254 100644 --- a/arch/mips/include/asm/gic.h +++ b/arch/mips/include/asm/gic.h @@ -206,7 +206,7 @@ #define GIC_VPE_EIC_SHADOW_SET_BASE 0x0100 #define GIC_VPE_EIC_SS(intr) \ - (GIC_EIC_SHADOW_SET_BASE + (4 * intr)) + (GIC_VPE_EIC_SHADOW_SET_BASE + (4 * intr)) #define GIC_VPE_EIC_VEC_BASE 0x0800 #define GIC_VPE_EIC_VEC(intr) \ @@ -330,6 +330,17 @@ struct gic_intr_map { #define GIC_FLAG_TRANSPARENT 0x02 }; +/* + * This is only used in EIC mode. This helps to figure out which + * shared interrupts we need to process when we get a vector interrupt. + */ +#define GIC_MAX_SHARED_INTR 0x5 +struct gic_shared_intr_map { + unsigned int num_shared_intr; + unsigned int intr_list[GIC_MAX_SHARED_INTR]; + unsigned int local_intr_mask; +}; + extern void gic_init(unsigned long gic_base_addr, unsigned long gic_addrspace_size, struct gic_intr_map *intrmap, unsigned int intrmap_size, unsigned int irqbase); @@ -338,5 +349,7 @@ extern unsigned int gic_get_int(void); extern void gic_send_ipi(unsigned int intr); extern unsigned int plat_ipi_call_int_xlate(unsigned int); extern unsigned int plat_ipi_resched_int_xlate(unsigned int); +extern void gic_bind_eic_interrupt(int irq, int set); +extern unsigned int gic_get_timer_pending(void); #endif /* _ASM_GICREGS_H */ diff --git a/arch/mips/include/asm/inst.h b/arch/mips/include/asm/inst.h index 7ebfc392e58..ab84064283d 100644 --- a/arch/mips/include/asm/inst.h +++ b/arch/mips/include/asm/inst.h @@ -251,7 +251,7 @@ struct f_format { /* FPU register format */ unsigned int func : 6; }; -struct ma_format { /* FPU multipy and add format (MIPS IV) */ +struct ma_format { /* FPU multiply and add format (MIPS IV) */ unsigned int opcode : 6; unsigned int fr : 5; unsigned int ft : 5; @@ -324,7 +324,7 @@ struct f_format { /* FPU register format */ unsigned int opcode : 6; }; -struct ma_format { /* FPU multipy and add format (MIPS IV) */ +struct ma_format { /* FPU multiply and add format (MIPS IV) */ unsigned int fmt : 2; unsigned int func : 4; unsigned int fd : 5; diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index a58f22998a8..29d9c23c20c 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <asm/addrspace.h> +#include <asm/bug.h> #include <asm/byteorder.h> #include <asm/cpu.h> #include <asm/cpu-features.h> diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index fb698dc09bc..78dbb8a86da 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -136,6 +136,7 @@ extern void free_irqno(unsigned int irq); * IE7. Since R2 their number has to be read from the c0_intctl register. */ #define CP0_LEGACY_COMPARE_IRQ 7 +#define CP0_LEGACY_PERFCNT_IRQ 7 extern int cp0_compare_irq; extern int cp0_compare_irq_shift; diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h index 94d4faad29a..fdcd78ca1b0 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h @@ -99,7 +99,7 @@ #define CKCTL_6368_USBH_CLK_EN (1 << 15) #define CKCTL_6368_DISABLE_GLESS_EN (1 << 16) #define CKCTL_6368_NAND_CLK_EN (1 << 17) -#define CKCTL_6368_IPSEC_CLK_EN (1 << 17) +#define CKCTL_6368_IPSEC_CLK_EN (1 << 18) #define CKCTL_6368_ALL_SAFE_EN (CKCTL_6368_SWPKT_USB_EN | \ CKCTL_6368_SWPKT_SAR_EN | \ diff --git a/arch/mips/include/asm/mips-boards/maltaint.h b/arch/mips/include/asm/mips-boards/maltaint.h index d11aa02a956..5447d9fc421 100644 --- a/arch/mips/include/asm/mips-boards/maltaint.h +++ b/arch/mips/include/asm/mips-boards/maltaint.h @@ -86,6 +86,16 @@ #define GIC_CPU_INT4 4 /* . */ #define GIC_CPU_INT5 5 /* Core Interrupt 5 */ +/* MALTA GIC local interrupts */ +#define GIC_INT_TMR (GIC_CPU_INT5) +#define GIC_INT_PERFCTR (GIC_CPU_INT5) + +/* GIC constants */ +/* Add 2 to convert non-eic hw int # to eic vector # */ +#define GIC_CPU_TO_VEC_OFFSET (2) +/* If we map an intr to pin X, GIC will actually generate vector X+1 */ +#define GIC_PIN_TO_VEC_OFFSET (1) + #define GIC_EXT_INTR(x) x /* External Interrupts used for IPI */ diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h index c9420aa97e3..e71ff4c317f 100644 --- a/arch/mips/include/asm/mipsmtregs.h +++ b/arch/mips/include/asm/mipsmtregs.h @@ -48,7 +48,7 @@ #define CP0_VPECONF0 $1, 2 #define CP0_VPECONF1 $1, 3 #define CP0_YQMASK $1, 4 -#define CP0_VPESCHEDULE $1, 5 +#define CP0_VPESCHEDULE $1, 5 #define CP0_VPESCHEFBK $1, 6 #define CP0_TCSTATUS $2, 1 #define CP0_TCBIND $2, 2 diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index 5d33621b565..4f8ddba8c36 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -22,7 +22,7 @@ struct task_struct; * switch_to(n) should switch tasks to task nr n, first * checking that n isn't the current task, in which case it does nothing. */ -extern asmlinkage void *resume(void *last, void *next, void *next_ti); +extern asmlinkage void *resume(void *last, void *next, void *next_ti, u32 __usedfpu); extern unsigned int ll_bit; extern struct task_struct *ll_task; @@ -66,11 +66,13 @@ do { \ #define switch_to(prev, next, last) \ do { \ + u32 __usedfpu; \ __mips_mt_fpaff_switch_to(prev); \ if (cpu_has_dsp) \ __save_dsp(prev); \ __clear_software_ll_bit(); \ - (last) = resume(prev, next, task_thread_info(next)); \ + __usedfpu = test_and_clear_tsk_thread_flag(prev, TIF_USEDFPU); \ + (last) = resume(prev, next, task_thread_info(next), __usedfpu); \ } while (0) #define finish_arch_switch(prev) \ diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index e2eca7d1059..ca97e0ecb64 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -60,6 +60,8 @@ struct thread_info { register struct thread_info *__current_thread_info __asm__("$28"); #define current_thread_info() __current_thread_info +#endif /* !__ASSEMBLY__ */ + /* thread information allocation */ #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT) #define THREAD_SIZE_ORDER (1) @@ -85,8 +87,6 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define STACK_WARN (THREAD_SIZE / 8) -#endif /* !__ASSEMBLY__ */ - #define PREEMPT_ACTIVE 0x10000000 /* diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6ae7ce4ac63..f4630e1082a 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -4,7 +4,7 @@ * Copyright (C) xxxx the Anonymous * Copyright (C) 1994 - 2006 Ralf Baechle * Copyright (C) 2003, 2004 Maciej W. Rozycki - * Copyright (C) 2001, 2004 MIPS Inc. + * Copyright (C) 2001, 2004, 2011, 2012 MIPS Technologies, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -199,6 +199,7 @@ void __init check_wait(void) cpu_wait = rm7k_wait_irqoff; break; + case CPU_M14KC: case CPU_24K: case CPU_34K: case CPU_1004K: @@ -810,6 +811,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_5KC; __cpu_name[cpu] = "MIPS 5Kc"; break; + case PRID_IMP_5KE: + c->cputype = CPU_5KE; + __cpu_name[cpu] = "MIPS 5KE"; + break; case PRID_IMP_20KC: c->cputype = CPU_20KC; __cpu_name[cpu] = "MIPS 20Kc"; @@ -831,6 +836,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_74K; __cpu_name[cpu] = "MIPS 74Kc"; break; + case PRID_IMP_M14KC: + c->cputype = CPU_M14KC; + __cpu_name[cpu] = "MIPS M14Kc"; + break; case PRID_IMP_1004K: c->cputype = CPU_1004K; __cpu_name[cpu] = "MIPS 1004Kc"; diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 57ba13edb03..3fc1691110d 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -5,7 +5,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05 by Ralf Baechle + * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05, 12 by Ralf Baechle * Copyright (C) 1999, 2000, 01 Silicon Graphics, Inc. */ #include <linux/interrupt.h> @@ -35,6 +35,12 @@ EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(kernel_thread); /* + * Functions that operate on entire pages. Mostly used by memory management. + */ +EXPORT_SYMBOL(clear_page); +EXPORT_SYMBOL(copy_page); + +/* * Userspace access stuff. */ EXPORT_SYMBOL(__copy_user); diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index ce89c806170..0441f54b2a6 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -31,7 +31,7 @@ /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, int usedfpu) */ .align 7 LEAF(resume) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index f29099b104c..eb5e394a465 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -162,11 +162,6 @@ static unsigned int counters_total_to_per_cpu(unsigned int counters) return counters >> vpe_shift(); } -static unsigned int counters_per_cpu_to_total(unsigned int counters) -{ - return counters << vpe_shift(); -} - #else /* !CONFIG_MIPS_MT_SMP */ #define vpe_id() 0 diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S index 293898391e6..9c51be5a163 100644 --- a/arch/mips/kernel/r2300_switch.S +++ b/arch/mips/kernel/r2300_switch.S @@ -43,7 +43,7 @@ /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) ) + * struct thread_info *next_ti, int usedfpu) */ LEAF(resume) mfc0 t1, CP0_STATUS @@ -51,18 +51,9 @@ LEAF(resume) cpu_save_nonscratch a0 sw ra, THREAD_REG31(a0) - /* - * check if we need to save FPU registers - */ - lw t3, TASK_THREAD_INFO(a0) - lw t0, TI_FLAGS(t3) - li t1, _TIF_USEDFPU - and t2, t0, t1 - beqz t2, 1f - nor t1, zero, t1 + beqz a3, 1f - and t0, t0, t1 - sw t0, TI_FLAGS(t3) + PTR_L t3, TASK_THREAD_INFO(a0) /* * clear saved user stack CU1 bit diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S index 9414f935446..42d2a393842 100644 --- a/arch/mips/kernel/r4k_switch.S +++ b/arch/mips/kernel/r4k_switch.S @@ -41,7 +41,7 @@ /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, int usedfpu) */ .align 5 LEAF(resume) @@ -53,16 +53,10 @@ /* * check if we need to save FPU registers */ - PTR_L t3, TASK_THREAD_INFO(a0) - LONG_L t0, TI_FLAGS(t3) - li t1, _TIF_USEDFPU - and t2, t0, t1 - beqz t2, 1f - nor t1, zero, t1 - and t0, t0, t1 - LONG_S t0, TI_FLAGS(t3) + beqz a3, 1f + PTR_L t3, TASK_THREAD_INFO(a0) /* * clear saved user stack CU1 bit */ diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 3046e298600..8e393b8443f 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -15,7 +15,6 @@ #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/spinlock.h> -#include <linux/init.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/reboot.h> @@ -197,13 +196,6 @@ static void bmips_init_secondary(void) write_c0_brcm_action(ACTION_CLR_IPI(smp_processor_id(), 0)); #endif - - /* make sure there won't be a timer interrupt for a little while */ - write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); - - irq_enable_hazard(); - set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE); - irq_enable_hazard(); } /* @@ -212,6 +204,13 @@ static void bmips_init_secondary(void) static void bmips_smp_finish(void) { pr_info("SMP: CPU%d is running\n", smp_processor_id()); + + /* make sure there won't be a timer interrupt for a little while */ + write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); + + irq_enable_hazard(); + set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE); + irq_enable_hazard(); } /* diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 48650c81804..1268392f1d2 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -122,13 +122,21 @@ asmlinkage __cpuinit void start_secondary(void) notify_cpu_starting(cpu); - mp_ops->smp_finish(); + set_cpu_online(cpu, true); + set_cpu_sibling_map(cpu); cpu_set(cpu, cpu_callin_map); synchronise_count_slave(); + /* + * irq will be enabled in ->smp_finish(), enabling it too early + * is dangerous. + */ + WARN_ON_ONCE(!irqs_disabled()); + mp_ops->smp_finish(); + cpu_idle(); } @@ -196,8 +204,6 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) while (!cpu_isset(cpu, cpu_callin_map)) udelay(100); - set_cpu_online(cpu, true); - return 0; } diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index f5dd38f1d01..15b5f3cfd20 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -322,7 +322,7 @@ int __init smtc_build_cpu_map(int start_cpu_slot) /* * Common setup before any secondaries are started - * Make sure all CPU's are in a sensible state before we boot any of the + * Make sure all CPUs are in a sensible state before we boot any of the * secondaries. * * For MIPS MT "SMTC" operation, we set up all TCs, spread as evenly @@ -340,12 +340,12 @@ static void smtc_tc_setup(int vpe, int tc, int cpu) /* * TCContext gets an offset from the base of the IPIQ array * to be used in low-level code to detect the presence of - * an active IPI queue + * an active IPI queue. */ write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16); /* Bind tc to vpe */ write_tc_c0_tcbind(vpe); - /* In general, all TCs should have the same cpu_data indications */ + /* In general, all TCs should have the same cpu_data indications. */ memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips)); /* For 34Kf, start with TC/CPU 0 as sole owner of single FPU context */ if (cpu_data[0].cputype == CPU_34K || @@ -358,8 +358,8 @@ static void smtc_tc_setup(int vpe, int tc, int cpu) } /* - * Tweak to get Count registes in as close a sync as possible. - * Value seems good for 34K-class cores. + * Tweak to get Count registes in as close a sync as possible. The + * value seems good for 34K-class cores. */ #define CP0_SKEW 8 @@ -615,7 +615,6 @@ void __cpuinit smtc_boot_secondary(int cpu, struct task_struct *idle) void smtc_init_secondary(void) { - local_irq_enable(); } void smtc_smp_finish(void) @@ -631,6 +630,8 @@ void smtc_smp_finish(void) if (cpu > 0 && (cpu_data[cpu].vpe_id != cpu_data[cpu - 1].vpe_id)) write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ); + local_irq_enable(); + printk("TC %d going on-line as CPU %d\n", cpu_data[smp_processor_id()].tc_id, smp_processor_id()); } diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c index 99f913c8d7a..842d55e411f 100644 --- a/arch/mips/kernel/sync-r4k.c +++ b/arch/mips/kernel/sync-r4k.c @@ -111,7 +111,6 @@ void __cpuinit synchronise_count_master(void) void __cpuinit synchronise_count_slave(void) { int i; - unsigned long flags; unsigned int initcount; int ncpus; @@ -123,8 +122,6 @@ void __cpuinit synchronise_count_slave(void) return; #endif - local_irq_save(flags); - /* * Not every cpu is online at the time this gets called, * so we first wait for the master to say everyone is ready @@ -154,7 +151,5 @@ void __cpuinit synchronise_count_slave(void) } /* Arrange for an interrupt in a short while */ write_c0_compare(read_c0_count() + COUNTON); - - local_irq_restore(flags); } #undef NR_LOOPS diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 2d0c2a277f5..c3c29354370 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -132,6 +132,9 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs) unsigned long ra = regs->regs[31]; unsigned long pc = regs->cp0_epc; + if (!task) + task = current; + if (raw_show_trace || !__kernel_text_address(pc)) { show_raw_backtrace(sp); return; @@ -1249,6 +1252,7 @@ static inline void parity_protection_init(void) break; case CPU_5KC: + case CPU_5KE: write_c0_ecc(0x80000000); back_to_back_c0_hazard(); /* Set the PE bit (bit 31) in the c0_errctl register. */ @@ -1498,6 +1502,7 @@ extern void flush_tlb_handlers(void); * Timer interrupt */ int cp0_compare_irq; +EXPORT_SYMBOL_GPL(cp0_compare_irq); int cp0_compare_irq_shift; /* @@ -1597,7 +1602,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu) cp0_perfcount_irq = -1; } else { cp0_compare_irq = CP0_LEGACY_COMPARE_IRQ; - cp0_compare_irq_shift = cp0_compare_irq; + cp0_compare_irq_shift = CP0_LEGACY_PERFCNT_IRQ; cp0_perfcount_irq = -1; } diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 924da5eb703..df243a64f43 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -1,5 +1,6 @@ #include <asm/asm-offsets.h> #include <asm/page.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> #undef mips @@ -72,7 +73,7 @@ SECTIONS .data : { /* Data */ . = . + DATAOFFSET; /* for CONFIG_MAPPED_KERNEL */ - INIT_TASK_DATA(PAGE_SIZE) + INIT_TASK_DATA(THREAD_SIZE) NOSAVE_DATA CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile index 4aa20280613..fd6203f14f1 100644 --- a/arch/mips/mm/Makefile +++ b/arch/mips/mm/Makefile @@ -3,8 +3,8 @@ # obj-y += cache.o dma-default.o extable.o fault.o \ - gup.o init.o mmap.o page.o tlbex.o \ - tlbex-fault.o uasm.o + gup.o init.o mmap.o page.o page-funcs.o \ + tlbex.o tlbex-fault.o uasm.o obj-$(CONFIG_32BIT) += ioremap.o pgtable-32.o obj-$(CONFIG_64BIT) += pgtable-64.o diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5109be96d98..f092c265dc6 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -977,7 +977,7 @@ static void __cpuinit probe_pcache(void) c->icache.linesz = 2 << lsize; else c->icache.linesz = lsize; - c->icache.sets = 64 << ((config1 >> 22) & 7); + c->icache.sets = 32 << (((config1 >> 22) + 1) & 7); c->icache.ways = 1 + ((config1 >> 16) & 7); icache_size = c->icache.sets * @@ -997,7 +997,7 @@ static void __cpuinit probe_pcache(void) c->dcache.linesz = 2 << lsize; else c->dcache.linesz= lsize; - c->dcache.sets = 64 << ((config1 >> 13) & 7); + c->dcache.sets = 32 << (((config1 >> 13) + 1) & 7); c->dcache.ways = 1 + ((config1 >> 7) & 7); dcache_size = c->dcache.sets * @@ -1051,6 +1051,7 @@ static void __cpuinit probe_pcache(void) case CPU_R14000: break; + case CPU_M14KC: case CPU_24K: case CPU_34K: case CPU_74K: diff --git a/arch/mips/mm/page-funcs.S b/arch/mips/mm/page-funcs.S new file mode 100644 index 00000000000..48a6b38ff13 --- /dev/null +++ b/arch/mips/mm/page-funcs.S @@ -0,0 +1,50 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Micro-assembler generated clear_page/copy_page functions. + * + * Copyright (C) 2012 MIPS Technologies, Inc. + * Copyright (C) 2012 Ralf Baechle <ralf@linux-mips.org> + */ +#include <asm/asm.h> +#include <asm/regdef.h> + +#ifdef CONFIG_SIBYTE_DMA_PAGEOPS +#define cpu_clear_page_function_name clear_page_cpu +#define cpu_copy_page_function_name copy_page_cpu +#else +#define cpu_clear_page_function_name clear_page +#define cpu_copy_page_function_name copy_page +#endif + +/* + * Maximum sizes: + * + * R4000 128 bytes S-cache: 0x058 bytes + * R4600 v1.7: 0x05c bytes + * R4600 v2.0: 0x060 bytes + * With prefetching, 16 word strides 0x120 bytes + */ +EXPORT(__clear_page_start) +LEAF(cpu_clear_page_function_name) +1: j 1b /* Dummy, will be replaced. */ + .space 288 +END(cpu_clear_page_function_name) +EXPORT(__clear_page_end) + +/* + * Maximum sizes: + * + * R4000 128 bytes S-cache: 0x11c bytes + * R4600 v1.7: 0x080 bytes + * R4600 v2.0: 0x07c bytes + * With prefetching, 16 word strides 0x540 bytes + */ +EXPORT(__copy_page_start) +LEAF(cpu_copy_page_function_name) +1: j 1b /* Dummy, will be replaced. */ + .space 1344 +END(cpu_copy_page_function_name) +EXPORT(__copy_page_end) diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index cc0b626858b..98f530e1821 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -6,6 +6,7 @@ * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org) * Copyright (C) 2007 Maciej W. Rozycki * Copyright (C) 2008 Thiemo Seufer + * Copyright (C) 2012 MIPS Technologies, Inc. */ #include <linux/init.h> #include <linux/kernel.h> @@ -71,45 +72,6 @@ static struct uasm_reloc __cpuinitdata relocs[5]; #define cpu_is_r4600_v1_x() ((read_c0_prid() & 0xfffffff0) == 0x00002010) #define cpu_is_r4600_v2_x() ((read_c0_prid() & 0xfffffff0) == 0x00002020) -/* - * Maximum sizes: - * - * R4000 128 bytes S-cache: 0x058 bytes - * R4600 v1.7: 0x05c bytes - * R4600 v2.0: 0x060 bytes - * With prefetching, 16 word strides 0x120 bytes - */ - -static u32 clear_page_array[0x120 / 4]; - -#ifdef CONFIG_SIBYTE_DMA_PAGEOPS -void clear_page_cpu(void *page) __attribute__((alias("clear_page_array"))); -#else -void clear_page(void *page) __attribute__((alias("clear_page_array"))); -#endif - -EXPORT_SYMBOL(clear_page); - -/* - * Maximum sizes: - * - * R4000 128 bytes S-cache: 0x11c bytes - * R4600 v1.7: 0x080 bytes - * R4600 v2.0: 0x07c bytes - * With prefetching, 16 word strides 0x540 bytes - */ -static u32 copy_page_array[0x540 / 4]; - -#ifdef CONFIG_SIBYTE_DMA_PAGEOPS -void -copy_page_cpu(void *to, void *from) __attribute__((alias("copy_page_array"))); -#else -void copy_page(void *to, void *from) __attribute__((alias("copy_page_array"))); -#endif - -EXPORT_SYMBOL(copy_page); - - static int pref_bias_clear_store __cpuinitdata; static int pref_bias_copy_load __cpuinitdata; static int pref_bias_copy_store __cpuinitdata; @@ -282,10 +244,15 @@ static inline void __cpuinit build_clear_pref(u32 **buf, int off) } } +extern u32 __clear_page_start; +extern u32 __clear_page_end; +extern u32 __copy_page_start; +extern u32 __copy_page_end; + void __cpuinit build_clear_page(void) { int off; - u32 *buf = (u32 *)&clear_page_array; + u32 *buf = &__clear_page_start; struct uasm_label *l = labels; struct uasm_reloc *r = relocs; int i; @@ -356,17 +323,17 @@ void __cpuinit build_clear_page(void) uasm_i_jr(&buf, RA); uasm_i_nop(&buf); - BUG_ON(buf > clear_page_array + ARRAY_SIZE(clear_page_array)); + BUG_ON(buf > &__clear_page_end); uasm_resolve_relocs(relocs, labels); pr_debug("Synthesized clear page handler (%u instructions).\n", - (u32)(buf - clear_page_array)); + (u32)(buf - &__clear_page_start)); pr_debug("\t.set push\n"); pr_debug("\t.set noreorder\n"); - for (i = 0; i < (buf - clear_page_array); i++) - pr_debug("\t.word 0x%08x\n", clear_page_array[i]); + for (i = 0; i < (buf - &__clear_page_start); i++) + pr_debug("\t.word 0x%08x\n", (&__clear_page_start)[i]); pr_debug("\t.set pop\n"); } @@ -427,7 +394,7 @@ static inline void build_copy_store_pref(u32 **buf, int off) void __cpuinit build_copy_page(void) { int off; - u32 *buf = (u32 *)©_page_array; + u32 *buf = &__copy_page_start; struct uasm_label *l = labels; struct uasm_reloc *r = relocs; int i; @@ -595,21 +562,23 @@ void __cpuinit build_copy_page(void) uasm_i_jr(&buf, RA); uasm_i_nop(&buf); - BUG_ON(buf > copy_page_array + ARRAY_SIZE(copy_page_array)); + BUG_ON(buf > &__copy_page_end); uasm_resolve_relocs(relocs, labels); pr_debug("Synthesized copy page handler (%u instructions).\n", - (u32)(buf - copy_page_array)); + (u32)(buf - &__copy_page_start)); pr_debug("\t.set push\n"); pr_debug("\t.set noreorder\n"); - for (i = 0; i < (buf - copy_page_array); i++) - pr_debug("\t.word 0x%08x\n", copy_page_array[i]); + for (i = 0; i < (buf - &__copy_page_start); i++) + pr_debug("\t.word 0x%08x\n", (&__copy_page_start)[i]); pr_debug("\t.set pop\n"); } #ifdef CONFIG_SIBYTE_DMA_PAGEOPS +extern void clear_page_cpu(void *page); +extern void copy_page_cpu(void *to, void *from); /* * Pad descriptors to cacheline, since each is exclusively owned by a diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 0bc485b3cd6..03eb0ef9158 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -9,6 +9,7 @@ * Copyright (C) 2005, 2007, 2008, 2009 Maciej W. Rozycki * Copyright (C) 2006 Ralf Baechle (ralf@linux-mips.org) * Copyright (C) 2008, 2009 Cavium Networks, Inc. + * Copyright (C) 2011 MIPS Technologies, Inc. * * ... and the days got worse and worse and now you see * I've gone completly out of my mind. @@ -494,6 +495,7 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l, case CPU_R14000: case CPU_4KC: case CPU_4KEC: + case CPU_M14KC: case CPU_SB1: case CPU_SB1A: case CPU_4KSC: diff --git a/arch/mips/mti-malta/malta-pci.c b/arch/mips/mti-malta/malta-pci.c index bf80921f2f5..284dea54faf 100644 --- a/arch/mips/mti-malta/malta-pci.c +++ b/arch/mips/mti-malta/malta-pci.c @@ -241,8 +241,9 @@ void __init mips_pcibios_init(void) return; } - if (controller->io_resource->start < 0x00001000UL) /* FIXME */ - controller->io_resource->start = 0x00001000UL; + /* Change start address to avoid conflicts with ACPI and SMB devices */ + if (controller->io_resource->start < 0x00002000UL) + controller->io_resource->start = 0x00002000UL; iomem_resource.end &= 0xfffffffffULL; /* 64 GB */ ioport_resource.end = controller->io_resource->end; @@ -253,7 +254,7 @@ void __init mips_pcibios_init(void) } /* Enable PCI 2.1 compatibility in PIIX4 */ -static void __init quirk_dlcsetup(struct pci_dev *dev) +static void __devinit quirk_dlcsetup(struct pci_dev *dev) { u8 odlc, ndlc; (void) pci_read_config_byte(dev, 0x82, &odlc); diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index b7f37d4982f..2e28f653f66 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -111,7 +111,7 @@ static void __init pci_clock_check(void) unsigned int __iomem *jmpr_p = (unsigned int *) ioremap(MALTA_JMPRS_REG, sizeof(unsigned int)); int jmpr = (__raw_readl(jmpr_p) >> 2) & 0x07; - static const int pciclocks[] __initdata = { + static const int pciclocks[] __initconst = { 33, 20, 25, 30, 12, 16, 37, 10 }; int pciclock = pciclocks[jmpr]; diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c index acb677a1227..b3df7c2aad1 100644 --- a/arch/mips/netlogic/xlp/setup.c +++ b/arch/mips/netlogic/xlp/setup.c @@ -82,8 +82,10 @@ void __init prom_free_prom_memory(void) void xlp_mmu_init(void) { + /* enable extended TLB and Large Fixed TLB */ write_c0_config6(read_c0_config6() | 0x24); - current_cpu_data.tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1; + + /* set page mask of Fixed TLB in config7 */ write_c0_config7(PM_DEFAULT_MASK >> (13 + (ffz(PM_DEFAULT_MASK >> 13) / 2))); } @@ -100,6 +102,10 @@ void __init prom_init(void) nlm_common_ebase = read_c0_ebase() & (~((1 << 12) - 1)); #ifdef CONFIG_SMP nlm_wakeup_secondary_cpus(0xffffffff); + + /* update TLB size after waking up threads */ + current_cpu_data.tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1; + register_smp_ops(&nlm_smp_ops); #endif } diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c index d1f2d4c52d4..b6e378211a2 100644 --- a/arch/mips/oprofile/common.c +++ b/arch/mips/oprofile/common.c @@ -78,6 +78,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) switch (current_cpu_type()) { case CPU_5KC: + case CPU_M14KC: case CPU_20KC: case CPU_24K: case CPU_25KF: diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index baba3bcaa3c..4d80a856048 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -322,6 +322,10 @@ static int __init mipsxx_init(void) op_model_mipsxx_ops.num_counters = counters; switch (current_cpu_type()) { + case CPU_M14KC: + op_model_mipsxx_ops.cpu_type = "mips/M14Kc"; + break; + case CPU_20KC: op_model_mipsxx_ops.cpu_type = "mips/20K"; break; diff --git a/arch/mips/pci/fixup-fuloong2e.c b/arch/mips/pci/fixup-fuloong2e.c index d5d4c018fb0..0857ab8c391 100644 --- a/arch/mips/pci/fixup-fuloong2e.c +++ b/arch/mips/pci/fixup-fuloong2e.c @@ -48,7 +48,7 @@ int pcibios_plat_dev_init(struct pci_dev *dev) return 0; } -static void __init loongson2e_nec_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_nec_fixup(struct pci_dev *pdev) { unsigned int val; @@ -60,7 +60,7 @@ static void __init loongson2e_nec_fixup(struct pci_dev *pdev) pci_write_config_dword(pdev, 0xe4, 1 << 5); } -static void __init loongson2e_686b_func0_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func0_fixup(struct pci_dev *pdev) { unsigned char c; @@ -135,7 +135,7 @@ static void __init loongson2e_686b_func0_fixup(struct pci_dev *pdev) printk(KERN_INFO"via686b fix: ISA bridge done\n"); } -static void __init loongson2e_686b_func1_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func1_fixup(struct pci_dev *pdev) { printk(KERN_INFO"via686b fix: IDE\n"); @@ -168,19 +168,19 @@ static void __init loongson2e_686b_func1_fixup(struct pci_dev *pdev) printk(KERN_INFO"via686b fix: IDE done\n"); } -static void __init loongson2e_686b_func2_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func2_fixup(struct pci_dev *pdev) { /* irq routing */ pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, 10); } -static void __init loongson2e_686b_func3_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func3_fixup(struct pci_dev *pdev) { /* irq routing */ pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, 11); } -static void __init loongson2e_686b_func5_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func5_fixup(struct pci_dev *pdev) { unsigned int val; unsigned char c; diff --git a/arch/mips/pci/fixup-lemote2f.c b/arch/mips/pci/fixup-lemote2f.c index 4b9768d5d72..a7b917dcf60 100644 --- a/arch/mips/pci/fixup-lemote2f.c +++ b/arch/mips/pci/fixup-lemote2f.c @@ -96,21 +96,21 @@ int pcibios_plat_dev_init(struct pci_dev *dev) } /* CS5536 SPEC. fixup */ -static void __init loongson_cs5536_isa_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_isa_fixup(struct pci_dev *pdev) { /* the uart1 and uart2 interrupt in PIC is enabled as default */ pci_write_config_dword(pdev, PCI_UART1_INT_REG, 1); pci_write_config_dword(pdev, PCI_UART2_INT_REG, 1); } -static void __init loongson_cs5536_ide_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_ide_fixup(struct pci_dev *pdev) { /* setting the mutex pin as IDE function */ pci_write_config_dword(pdev, PCI_IDE_CFG_REG, CS5536_IDE_FLASH_SIGNATURE); } -static void __init loongson_cs5536_acc_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_acc_fixup(struct pci_dev *pdev) { /* enable the AUDIO interrupt in PIC */ pci_write_config_dword(pdev, PCI_ACC_INT_REG, 1); @@ -118,14 +118,14 @@ static void __init loongson_cs5536_acc_fixup(struct pci_dev *pdev) pci_write_config_byte(pdev, PCI_LATENCY_TIMER, 0xc0); } -static void __init loongson_cs5536_ohci_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_ohci_fixup(struct pci_dev *pdev) { /* enable the OHCI interrupt in PIC */ /* THE OHCI, EHCI, UDC, OTG are shared with interrupt in PIC */ pci_write_config_dword(pdev, PCI_OHCI_INT_REG, 1); } -static void __init loongson_cs5536_ehci_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_ehci_fixup(struct pci_dev *pdev) { u32 hi, lo; @@ -137,7 +137,7 @@ static void __init loongson_cs5536_ehci_fixup(struct pci_dev *pdev) pci_write_config_dword(pdev, PCI_EHCI_FLADJ_REG, 0x2000); } -static void __init loongson_nec_fixup(struct pci_dev *pdev) +static void __devinit loongson_nec_fixup(struct pci_dev *pdev) { unsigned int val; diff --git a/arch/mips/pci/fixup-malta.c b/arch/mips/pci/fixup-malta.c index 0f48498bc23..70073c98ed3 100644 --- a/arch/mips/pci/fixup-malta.c +++ b/arch/mips/pci/fixup-malta.c @@ -49,10 +49,10 @@ int pcibios_plat_dev_init(struct pci_dev *dev) return 0; } -static void __init malta_piix_func0_fixup(struct pci_dev *pdev) +static void __devinit malta_piix_func0_fixup(struct pci_dev *pdev) { unsigned char reg_val; - static int piixirqmap[16] __initdata = { /* PIIX PIRQC[A:D] irq mappings */ + static int piixirqmap[16] __devinitdata = { /* PIIX PIRQC[A:D] irq mappings */ 0, 0, 0, 3, 4, 5, 6, 7, 0, 9, 10, 11, @@ -83,7 +83,7 @@ static void __init malta_piix_func0_fixup(struct pci_dev *pdev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0, malta_piix_func0_fixup); -static void __init malta_piix_func1_fixup(struct pci_dev *pdev) +static void __devinit malta_piix_func1_fixup(struct pci_dev *pdev) { unsigned char reg_val; diff --git a/arch/mips/pci/fixup-mpc30x.c b/arch/mips/pci/fixup-mpc30x.c index e08f49cb687..8e4f8288eca 100644 --- a/arch/mips/pci/fixup-mpc30x.c +++ b/arch/mips/pci/fixup-mpc30x.c @@ -22,13 +22,13 @@ #include <asm/vr41xx/mpc30x.h> -static const int internal_func_irqs[] __initdata = { +static const int internal_func_irqs[] __initconst = { VRC4173_CASCADE_IRQ, VRC4173_AC97_IRQ, VRC4173_USB_IRQ, }; -static const int irq_tab_mpc30x[] __initdata = { +static const int irq_tab_mpc30x[] __initconst = { [12] = VRC4173_PCMCIA1_IRQ, [13] = VRC4173_PCMCIA2_IRQ, [29] = MQ200_IRQ, diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c index f0bb9146e6c..d02900a7291 100644 --- a/arch/mips/pci/fixup-sb1250.c +++ b/arch/mips/pci/fixup-sb1250.c @@ -15,7 +15,7 @@ * Set the BCM1250, etc. PCI host bridge's TRDY timeout * to the finite max. */ -static void __init quirk_sb1250_pci(struct pci_dev *dev) +static void __devinit quirk_sb1250_pci(struct pci_dev *dev) { pci_write_config_byte(dev, 0x40, 0xff); } @@ -25,7 +25,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI, /* * The BCM1250, etc. PCI/HT bridge reports as a host bridge. */ -static void __init quirk_sb1250_ht(struct pci_dev *dev) +static void __devinit quirk_sb1250_ht(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; } @@ -35,7 +35,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_HT, /* * Set the SP1011 HT/PCI bridge's TRDY timeout to the finite max. */ -static void __init quirk_sp1011(struct pci_dev *dev) +static void __devinit quirk_sp1011(struct pci_dev *dev) { pci_write_config_byte(dev, 0x64, 0xff); } diff --git a/arch/mips/pci/ops-tx4927.c b/arch/mips/pci/ops-tx4927.c index a1e7e6d80c8..bc13e29d2bb 100644 --- a/arch/mips/pci/ops-tx4927.c +++ b/arch/mips/pci/ops-tx4927.c @@ -495,7 +495,7 @@ irqreturn_t tx4927_pcierr_interrupt(int irq, void *dev_id) } #ifdef CONFIG_TOSHIBA_FPCIB0 -static void __init tx4927_quirk_slc90e66_bridge(struct pci_dev *dev) +static void __devinit tx4927_quirk_slc90e66_bridge(struct pci_dev *dev) { struct tx4927_pcic_reg __iomem *pcicptr = pci_bus_to_pcicptr(dev->bus); diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c index 0fbe4c0c170..fdc24440294 100644 --- a/arch/mips/pci/pci-ip27.c +++ b/arch/mips/pci/pci-ip27.c @@ -212,7 +212,7 @@ static inline void pci_enable_swapping(struct pci_dev *dev) bridge->b_widget.w_tflush; /* Flush */ } -static void __init pci_fixup_ioc3(struct pci_dev *d) +static void __devinit pci_fixup_ioc3(struct pci_dev *d) { pci_disable_swapping(d); } diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c index 1644805a673..172af1cd586 100644 --- a/arch/mips/pci/pci-xlr.c +++ b/arch/mips/pci/pci-xlr.c @@ -41,6 +41,7 @@ #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/console.h> +#include <linux/pci_regs.h> #include <asm/io.h> @@ -156,35 +157,55 @@ struct pci_controller nlm_pci_controller = { .io_offset = 0x00000000UL, }; +/* + * The top level PCIe links on the XLS PCIe controller appear as + * bridges. Given a device, this function finds which link it is + * on. + */ +static struct pci_dev *xls_get_pcie_link(const struct pci_dev *dev) +{ + struct pci_bus *bus, *p; + + /* Find the bridge on bus 0 */ + bus = dev->bus; + for (p = bus->parent; p && p->number != 0; p = p->parent) + bus = p; + + return p ? bus->self : NULL; +} + static int get_irq_vector(const struct pci_dev *dev) { + struct pci_dev *lnk; + if (!nlm_chip_is_xls()) - return PIC_PCIX_IRQ; /* for XLR just one IRQ*/ + return PIC_PCIX_IRQ; /* for XLR just one IRQ */ /* * For XLS PCIe, there is an IRQ per Link, find out which * link the device is on to assign interrupts - */ - if (dev->bus->self == NULL) + */ + lnk = xls_get_pcie_link(dev); + if (lnk == NULL) return 0; - switch (dev->bus->self->devfn) { - case 0x0: + switch (PCI_SLOT(lnk->devfn)) { + case 0: return PIC_PCIE_LINK0_IRQ; - case 0x8: + case 1: return PIC_PCIE_LINK1_IRQ; - case 0x10: + case 2: if (nlm_chip_is_xls_b()) return PIC_PCIE_XLSB0_LINK2_IRQ; else return PIC_PCIE_LINK2_IRQ; - case 0x18: + case 3: if (nlm_chip_is_xls_b()) return PIC_PCIE_XLSB0_LINK3_IRQ; else return PIC_PCIE_LINK3_IRQ; } - WARN(1, "Unexpected devfn %d\n", dev->bus->self->devfn); + WARN(1, "Unexpected devfn %d\n", lnk->devfn); return 0; } @@ -202,7 +223,27 @@ void arch_teardown_msi_irq(unsigned int irq) int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) { struct msi_msg msg; + struct pci_dev *lnk; int irq, ret; + u16 val; + + /* MSI not supported on XLR */ + if (!nlm_chip_is_xls()) + return 1; + + /* + * Enable MSI on the XLS PCIe controller bridge which was disabled + * at enumeration, the bridge MSI capability is at 0x50 + */ + lnk = xls_get_pcie_link(dev); + if (lnk == NULL) + return 1; + + pci_read_config_word(lnk, 0x50 + PCI_MSI_FLAGS, &val); + if ((val & PCI_MSI_FLAGS_ENABLE) == 0) { + val |= PCI_MSI_FLAGS_ENABLE; + pci_write_config_word(lnk, 0x50 + PCI_MSI_FLAGS, val); + } irq = get_irq_vector(dev); if (irq <= 0) @@ -327,7 +368,7 @@ static int __init pcibios_init(void) } } else { /* XLR PCI controller ACK */ - irq_set_handler_data(PIC_PCIE_XLSB0_LINK3_IRQ, xlr_pci_ack); + irq_set_handler_data(PIC_PCIX_IRQ, xlr_pci_ack); } return 0; diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index b71fae23104..5edab2bc6fc 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -115,11 +115,11 @@ static void yos_send_ipi_mask(const struct cpumask *mask, unsigned int action) */ static void __cpuinit yos_init_secondary(void) { - set_c0_status(ST0_CO | ST0_IE | ST0_IM); } static void __cpuinit yos_smp_finish(void) { + set_c0_status(ST0_CO | ST0_IM | ST0_IE); } /* Hook for after all CPUs are online */ diff --git a/arch/mips/powertv/asic/asic-calliope.c b/arch/mips/powertv/asic/asic-calliope.c index 0a170e0ffea..7773f3d956b 100644 --- a/arch/mips/powertv/asic/asic-calliope.c +++ b/arch/mips/powertv/asic/asic-calliope.c @@ -28,7 +28,7 @@ #define CALLIOPE_ADDR(x) (CALLIOPE_IO_BASE + (x)) -const struct register_map calliope_register_map __initdata = { +const struct register_map calliope_register_map __initconst = { .eic_slow0_strt_add = {.phys = CALLIOPE_ADDR(0x800000)}, .eic_cfg_bits = {.phys = CALLIOPE_ADDR(0x800038)}, .eic_ready_status = {.phys = CALLIOPE_ADDR(0x80004c)}, diff --git a/arch/mips/powertv/asic/asic-cronus.c b/arch/mips/powertv/asic/asic-cronus.c index bbc0c122be5..da076db7b7e 100644 --- a/arch/mips/powertv/asic/asic-cronus.c +++ b/arch/mips/powertv/asic/asic-cronus.c @@ -28,7 +28,7 @@ #define CRONUS_ADDR(x) (CRONUS_IO_BASE + (x)) -const struct register_map cronus_register_map __initdata = { +const struct register_map cronus_register_map __initconst = { .eic_slow0_strt_add = {.phys = CRONUS_ADDR(0x000000)}, .eic_cfg_bits = {.phys = CRONUS_ADDR(0x000038)}, .eic_ready_status = {.phys = CRONUS_ADDR(0x00004C)}, diff --git a/arch/mips/powertv/asic/asic-gaia.c b/arch/mips/powertv/asic/asic-gaia.c index 91dda682752..47683b370e7 100644 --- a/arch/mips/powertv/asic/asic-gaia.c +++ b/arch/mips/powertv/asic/asic-gaia.c @@ -23,7 +23,7 @@ #include <linux/init.h> #include <asm/mach-powertv/asic.h> -const struct register_map gaia_register_map __initdata = { +const struct register_map gaia_register_map __initconst = { .eic_slow0_strt_add = {.phys = GAIA_IO_BASE + 0x000000}, .eic_cfg_bits = {.phys = GAIA_IO_BASE + 0x000038}, .eic_ready_status = {.phys = GAIA_IO_BASE + 0x00004C}, diff --git a/arch/mips/powertv/asic/asic-zeus.c b/arch/mips/powertv/asic/asic-zeus.c index 4a05bb09647..6ff4b10f09d 100644 --- a/arch/mips/powertv/asic/asic-zeus.c +++ b/arch/mips/powertv/asic/asic-zeus.c @@ -28,7 +28,7 @@ #define ZEUS_ADDR(x) (ZEUS_IO_BASE + (x)) -const struct register_map zeus_register_map __initdata = { +const struct register_map zeus_register_map __initconst = { .eic_slow0_strt_add = {.phys = ZEUS_ADDR(0x000000)}, .eic_cfg_bits = {.phys = ZEUS_ADDR(0x000038)}, .eic_ready_status = {.phys = ZEUS_ADDR(0x00004c)}, diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c index 682efb0c108..64eb71b1528 100644 --- a/arch/mips/txx9/generic/pci.c +++ b/arch/mips/txx9/generic/pci.c @@ -269,7 +269,7 @@ txx9_i8259_irq_setup(int irq) return err; } -static void __init quirk_slc90e66_bridge(struct pci_dev *dev) +static void __devinit quirk_slc90e66_bridge(struct pci_dev *dev) { int irq; /* PCI/ISA Bridge interrupt */ u8 reg_64; diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 6ab0bee2a54..4d584ae29ae 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -459,10 +459,11 @@ static int handle_signal(int sig, else ret = setup_frame(sig, ka, oldset, regs); if (ret) - return; + return ret; signal_delivered(sig, info, ka, regs, - test_thread_flag(TIF_SINGLESTEP)); + test_thread_flag(TIF_SINGLESTEP)); + return 0; } /* diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 090d35d3697..e62c223e4c4 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -876,9 +876,7 @@ static void __init smp_online(void) notify_cpu_starting(cpu); - ipi_call_lock(); set_cpu_online(cpu, true); - ipi_call_unlock(); local_irq_enable(); } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index a47828d31fe..6266730efd6 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -300,9 +300,7 @@ smp_cpu_init(int cpunum) notify_cpu_starting(cpunum); - ipi_call_lock(); set_cpu_online(cpunum, true); - ipi_call_unlock(); /* Initialise the idle task for this CPU */ atomic_inc(&init_mm.mm_count); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e4cb34322de..e1417c42155 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -571,7 +571,6 @@ void __devinit start_secondary(void *unused) if (system_state == SYSTEM_RUNNING) vdso_data->processorCount++; #endif - ipi_call_lock(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); /* Update sibling maps */ @@ -601,7 +600,6 @@ void __devinit start_secondary(void *unused) of_node_put(np); } of_node_put(l2_cache); - ipi_call_unlock(); local_irq_enable(); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 15cca26ccb6..8dca9c248ac 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -717,9 +717,7 @@ static void __cpuinit smp_start_secondary(void *cpuvoid) init_cpu_vtimer(); pfault_init(); notify_cpu_starting(smp_processor_id()); - ipi_call_lock(); set_cpu_online(smp_processor_id(), true); - ipi_call_unlock(); local_irq_enable(); /* cpu_idle will call schedule for us */ cpu_idle(); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index f591598d92f..781bcb10b8b 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -103,8 +103,6 @@ void __cpuinit smp_callin(void) if (cheetah_pcache_forced_on) cheetah_enable_pcache(); - local_irq_enable(); - callin_flag = 1; __asm__ __volatile__("membar #Sync\n\t" "flush %%g6" : : : "memory"); @@ -124,9 +122,8 @@ void __cpuinit smp_callin(void) while (!cpumask_test_cpu(cpuid, &smp_commenced_mask)) rmb(); - ipi_call_lock_irq(); set_cpu_online(cpuid, true); - ipi_call_unlock_irq(); + local_irq_enable(); /* idle thread is expected to have preempt disabled */ preempt_disable(); @@ -1308,9 +1305,7 @@ int __cpu_disable(void) mdelay(1); local_irq_disable(); - ipi_call_lock(); set_cpu_online(cpu, false); - ipi_call_unlock(); cpu_map_rebuild(); diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c index 84873fbe8f2..e686c5ac90b 100644 --- a/arch/tile/kernel/smpboot.c +++ b/arch/tile/kernel/smpboot.c @@ -198,17 +198,7 @@ void __cpuinit online_secondary(void) notify_cpu_starting(smp_processor_id()); - /* - * We need to hold call_lock, so there is no inconsistency - * between the time smp_call_function() determines number of - * IPI recipients, and the time when the determination is made - * for which cpus receive the IPI. Holding this - * lock helps us to not include this cpu in a currently in progress - * smp_call_function(). - */ - ipi_call_lock(); set_cpu_online(smp_processor_id(), 1); - ipi_call_unlock(); __get_cpu_var(cpu_state) = CPU_ONLINE; /* Set up tile-specific state for this cpu. */ diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1f252143455..b0c5276861e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -49,6 +49,9 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 + # Use -mpreferred-stack-boundary=3 if supported. + KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3) + # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 49331bedc15..70780689599 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -75,23 +75,54 @@ static inline int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ +#define OLDINSTR(oldinstr) "661:\n\t" oldinstr "\n662:\n" + +#define b_replacement(number) "663"#number +#define e_replacement(number) "664"#number + +#define alt_slen "662b-661b" +#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f" + +#define ALTINSTR_ENTRY(feature, number) \ + " .long 661b - .\n" /* label */ \ + " .long " b_replacement(number)"f - .\n" /* new instruction */ \ + " .word " __stringify(feature) "\n" /* feature bit */ \ + " .byte " alt_slen "\n" /* source len */ \ + " .byte " alt_rlen(number) "\n" /* replacement len */ + +#define DISCARD_ENTRY(number) /* rlen <= slen */ \ + " .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n" + +#define ALTINSTR_REPLACEMENT(newinstr, feature, number) /* replacement */ \ + b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t" + /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, newinstr, feature) \ - \ - "661:\n\t" oldinstr "\n662:\n" \ - ".section .altinstructions,\"a\"\n" \ - " .long 661b - .\n" /* label */ \ - " .long 663f - .\n" /* new instruction */ \ - " .word " __stringify(feature) "\n" /* feature bit */ \ - " .byte 662b-661b\n" /* sourcelen */ \ - " .byte 664f-663f\n" /* replacementlen */ \ - ".previous\n" \ - ".section .discard,\"aw\",@progbits\n" \ - " .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \ - ".previous\n" \ - ".section .altinstr_replacement, \"ax\"\n" \ - "663:\n\t" newinstr "\n664:\n" /* replacement */ \ - ".previous" + OLDINSTR(oldinstr) \ + ".section .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feature, 1) \ + ".previous\n" \ + ".section .discard,\"aw\",@progbits\n" \ + DISCARD_ENTRY(1) \ + ".previous\n" \ + ".section .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ + ".previous" + +#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ + OLDINSTR(oldinstr) \ + ".section .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feature1, 1) \ + ALTINSTR_ENTRY(feature2, 2) \ + ".previous\n" \ + ".section .discard,\"aw\",@progbits\n" \ + DISCARD_ENTRY(1) \ + DISCARD_ENTRY(2) \ + ".previous\n" \ + ".section .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ + ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ + ".previous" /* * This must be included *after* the definition of ALTERNATIVE due to @@ -140,6 +171,19 @@ static inline int alternatives_text_reserved(void *start, void *end) : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* + * Like alternative_call, but there are two features and respective functions. + * If CPU has feature2, function2 is used. + * Otherwise, if CPU has feature1, function1 is used. + * Otherwise, old function is used. + */ +#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ + output, input...) \ + asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ + "call %P[new2]", feature2) \ + : output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ + [new2] "i" (newfunc2), ## input) + +/* * use this macro(s) if you need more than one output parameter * in alternative_io */ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index eaff4790ed9..88093c1d44f 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -306,7 +306,8 @@ struct apic { unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid); unsigned long (*check_apicid_present)(int apicid); - void (*vector_allocation_domain)(int cpu, struct cpumask *retmask); + void (*vector_allocation_domain)(int cpu, struct cpumask *retmask, + const struct cpumask *mask); void (*init_apic_ldr)(void); void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); @@ -331,9 +332,9 @@ struct apic { unsigned long (*set_apic_id)(unsigned int id); unsigned long apic_id_mask; - unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask); - unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, - const struct cpumask *andmask); + int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid); /* ipi */ void (*send_IPI_mask)(const struct cpumask *mask, int vector); @@ -537,6 +538,11 @@ static inline const struct cpumask *default_target_cpus(void) #endif } +static inline const struct cpumask *online_target_cpus(void) +{ + return cpu_online_mask; +} + DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); @@ -586,21 +592,50 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) #endif -static inline unsigned int -default_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) { - return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; + unsigned long cpu_mask = cpumask_bits(cpumask)[0] & + cpumask_bits(andmask)[0] & + cpumask_bits(cpu_online_mask)[0] & + APIC_ALL_CPUS; + + if (likely(cpu_mask)) { + *apicid = (unsigned int)cpu_mask; + return 0; + } else { + return -EINVAL; + } } -static inline unsigned int +extern int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid); + +static inline void +flat_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) { - unsigned long mask1 = cpumask_bits(cpumask)[0]; - unsigned long mask2 = cpumask_bits(andmask)[0]; - unsigned long mask3 = cpumask_bits(cpu_online_mask)[0]; + /* Careful. Some cpus do not strictly honor the set of cpus + * specified in the interrupt destination when using lowest + * priority interrupt delivery mode. + * + * In particular there was a hyperthreading cpu observed to + * deliver interrupts to the wrong hyperthread when only one + * hyperthread was specified in the interrupt desitination. + */ + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; +} - return (unsigned int)(mask1 & mask2 & mask3); +static inline void +default_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) +{ + cpumask_copy(retmask, cpumask_of(cpu)); } static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid) diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h index cc70c1c78ca..75ce3f47d20 100644 --- a/arch/x86/include/asm/emergency-restart.h +++ b/arch/x86/include/asm/emergency-restart.h @@ -4,9 +4,7 @@ enum reboot_type { BOOT_TRIPLE = 't', BOOT_KBD = 'k', -#ifdef CONFIG_X86_32 BOOT_BIOS = 'b', -#endif BOOT_ACPI = 'a', BOOT_EFI = 'e', BOOT_CF9 = 'p', diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h index dbe82a5c5ea..d3d74698dce 100644 --- a/arch/x86/include/asm/floppy.h +++ b/arch/x86/include/asm/floppy.h @@ -99,7 +99,7 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id) virtual_dma_residue += virtual_dma_count; virtual_dma_count = 0; #ifdef TRACE_FLPY_INT - printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", + printk(KERN_DEBUG "count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", virtual_dma_count, virtual_dma_residue, calls, bytes, dma_wait); calls = 0; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index db7c1f2709a..2da88c0cda1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -313,8 +313,8 @@ struct kvm_pmu { u64 counter_bitmask[2]; u64 global_ctrl_mask; u8 version; - struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC]; - struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED]; + struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; + struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED]; struct irq_work irq_work; u64 reprogram_pmi; }; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 084ef95274c..813ed103f45 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -115,8 +115,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr, extern unsigned long long native_read_tsc(void); -extern int native_rdmsr_safe_regs(u32 regs[8]); -extern int native_wrmsr_safe_regs(u32 regs[8]); +extern int rdmsr_safe_regs(u32 regs[8]); +extern int wrmsr_safe_regs(u32 regs[8]); static __always_inline unsigned long long __native_read_tsc(void) { @@ -187,43 +187,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) -{ - u32 gprs[8] = { 0 }; - int err; - - gprs[1] = msr; - gprs[7] = 0x9c5a203a; - - err = native_rdmsr_safe_regs(gprs); - - *p = gprs[0] | ((u64)gprs[2] << 32); - - return err; -} - -static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) -{ - u32 gprs[8] = { 0 }; - - gprs[0] = (u32)val; - gprs[1] = msr; - gprs[2] = val >> 32; - gprs[7] = 0x9c5a203a; - - return native_wrmsr_safe_regs(gprs); -} - -static inline int rdmsr_safe_regs(u32 regs[8]) -{ - return native_rdmsr_safe_regs(regs); -} - -static inline int wrmsr_safe_regs(u32 regs[8]) -{ - return native_wrmsr_safe_regs(regs); -} - #define rdtscl(low) \ ((low) = (u32)__native_read_tsc()) @@ -237,6 +200,8 @@ do { \ (high) = (u32)(_l >> 32); \ } while (0) +#define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) + #define rdtscp(low, high, aux) \ do { \ unsigned long long _val = native_read_tscp(&(aux)); \ @@ -248,8 +213,7 @@ do { \ #endif /* !CONFIG_PARAVIRT */ - -#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val), \ +#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \ (u32)((val) >> 32)) #define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2)) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index dc580c42851..c0fa356e90d 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -44,28 +44,14 @@ struct nmiaction { const char *name; }; -#define register_nmi_handler(t, fn, fg, n) \ +#define register_nmi_handler(t, fn, fg, n, init...) \ ({ \ - static struct nmiaction fn##_na = { \ + static struct nmiaction init fn##_na = { \ .handler = (fn), \ .name = (n), \ .flags = (fg), \ }; \ - __register_nmi_handler((t), &fn##_na); \ -}) - -/* - * For special handlers that register/unregister in the - * init section only. This should be considered rare. - */ -#define register_nmi_handler_initonly(t, fn, fg, n) \ -({ \ - static struct nmiaction fn##_na __initdata = { \ - .handler = (fn), \ - .name = (n), \ - .flags = (fg), \ - }; \ - __register_nmi_handler((t), &fn##_na); \ + __register_nmi_handler((t), &fn##_na); \ }) int __register_nmi_handler(unsigned int, struct nmiaction *); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 6cbbabf5270..0b47ddb6f00 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -128,21 +128,11 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err) return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err); } -static inline int paravirt_rdmsr_regs(u32 *regs) -{ - return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs); -} - static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high); } -static inline int paravirt_wrmsr_regs(u32 *regs) -{ - return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs); -} - /* These should all do BUG_ON(_err), but our headers are too tangled. */ #define rdmsr(msr, val1, val2) \ do { \ @@ -176,9 +166,6 @@ do { \ _err; \ }) -#define rdmsr_safe_regs(regs) paravirt_rdmsr_regs(regs) -#define wrmsr_safe_regs(regs) paravirt_wrmsr_regs(regs) - static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; @@ -186,32 +173,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) *p = paravirt_read_msr(msr, &err); return err; } -static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) -{ - u32 gprs[8] = { 0 }; - int err; - - gprs[1] = msr; - gprs[7] = 0x9c5a203a; - - err = paravirt_rdmsr_regs(gprs); - - *p = gprs[0] | ((u64)gprs[2] << 32); - - return err; -} - -static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) -{ - u32 gprs[8] = { 0 }; - - gprs[0] = (u32)val; - gprs[1] = msr; - gprs[2] = val >> 32; - gprs[7] = 0x9c5a203a; - - return paravirt_wrmsr_regs(gprs); -} static inline u64 paravirt_read_tsc(void) { @@ -252,6 +213,8 @@ do { \ high = _l >> 32; \ } while (0) +#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) + static inline unsigned long long paravirt_rdtscp(unsigned int *aux) { return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8e8b9a4987e..8613cbb7ba4 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -153,9 +153,7 @@ struct pv_cpu_ops { /* MSR, PMC and TSR operations. err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ u64 (*read_msr)(unsigned int msr, int *err); - int (*rdmsr_regs)(u32 *regs); int (*write_msr)(unsigned int msr, unsigned low, unsigned high); - int (*wrmsr_regs)(u32 *regs); u64 (*read_tsc)(void); u64 (*read_pmc)(int counter); diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index b3a53174602..5ad24a89b19 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -7,9 +7,13 @@ #undef DEBUG #ifdef DEBUG -#define DBG(x...) printk(x) +#define DBG(fmt, ...) printk(fmt, ##__VA_ARGS__) #else -#define DBG(x...) +#define DBG(fmt, ...) \ +do { \ + if (0) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) #endif #define PCI_PROBE_BIOS 0x0001 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 588f52ea810..c78f14a0df0 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -5,11 +5,10 @@ * Performance event hw details: */ -#define X86_PMC_MAX_GENERIC 32 -#define X86_PMC_MAX_FIXED 3 +#define INTEL_PMC_MAX_GENERIC 32 +#define INTEL_PMC_MAX_FIXED 3 +#define INTEL_PMC_IDX_FIXED 32 -#define X86_PMC_IDX_GENERIC 0 -#define X86_PMC_IDX_FIXED 32 #define X86_PMC_IDX_MAX 64 #define MSR_ARCH_PERFMON_PERFCTR0 0xc1 @@ -48,8 +47,7 @@ (X86_RAW_EVENT_MASK | \ AMD64_EVENTSEL_EVENT) #define AMD64_NUM_COUNTERS 4 -#define AMD64_NUM_COUNTERS_F15H 6 -#define AMD64_NUM_COUNTERS_MAX AMD64_NUM_COUNTERS_F15H +#define AMD64_NUM_COUNTERS_CORE 6 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) @@ -121,16 +119,16 @@ struct x86_pmu_capability { /* Instr_Retired.Any: */ #define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 -#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0) +#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS (INTEL_PMC_IDX_FIXED + 0) /* CPU_CLK_Unhalted.Core: */ #define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a -#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1) +#define INTEL_PMC_IDX_FIXED_CPU_CYCLES (INTEL_PMC_IDX_FIXED + 1) /* CPU_CLK_Unhalted.Ref: */ #define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b -#define X86_PMC_IDX_FIXED_REF_CYCLES (X86_PMC_IDX_FIXED + 2) -#define X86_PMC_MSK_FIXED_REF_CYCLES (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES) +#define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2) +#define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES) /* * We model BTS tracing as another fixed-mode PMC. @@ -139,7 +137,7 @@ struct x86_pmu_capability { * values are used by actual fixed events and higher values are used * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr. */ -#define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16) +#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16) /* * IBS cpuid feature detection @@ -234,6 +232,7 @@ struct perf_guest_switch_msr { extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); +extern void perf_check_microcode(void); #else static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { @@ -247,6 +246,7 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) } static inline void perf_events_lapic_init(void) { } +static inline void perf_check_microcode(void) { } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 98391db840c..f2b489cf160 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -2,9 +2,9 @@ #define _ASM_X86_PGTABLE_2LEVEL_H #define pte_ERROR(e) \ - printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low) + pr_err("%s:%d: bad pte %08lx\n", __FILE__, __LINE__, (e).pte_low) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + pr_err("%s:%d: bad pgd %08lx\n", __FILE__, __LINE__, pgd_val(e)) /* * Certain architectures need to do special things when PTEs diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index cb00ccc7d57..4cc9f2b7cdc 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -9,13 +9,13 @@ */ #define pte_ERROR(e) \ - printk("%s:%d: bad pte %p(%08lx%08lx).\n", \ + pr_err("%s:%d: bad pte %p(%08lx%08lx)\n", \ __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low) #define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %p(%016Lx).\n", \ + pr_err("%s:%d: bad pmd %p(%016Lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %p(%016Lx).\n", \ + pr_err("%s:%d: bad pgd %p(%016Lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) /* Rules for using set_pte: the pte being assigned *must* be diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 975f709e09a..8251be02301 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -26,16 +26,16 @@ extern pgd_t init_level4_pgt[]; extern void paging_init(void); #define pte_ERROR(e) \ - printk("%s:%d: bad pte %p(%016lx).\n", \ + pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %p(%016lx).\n", \ + pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ - printk("%s:%d: bad pud %p(%016lx).\n", \ + pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %p(%016lx).\n", \ + pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index fce3f4ae5bd..fe1ec5bcd84 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -21,8 +21,9 @@ struct real_mode_header { u32 wakeup_header; #endif /* APM/BIOS reboot */ -#ifdef CONFIG_X86_32 u32 machine_real_restart_asm; +#ifdef CONFIG_X86_64 + u32 machine_real_restart_seg; #endif }; diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 92f297069e8..a82c4f1b4d8 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -18,8 +18,8 @@ extern struct machine_ops machine_ops; void native_machine_crash_shutdown(struct pt_regs *regs); void native_machine_shutdown(void); -void machine_real_restart(unsigned int type); -/* These must match dispatch_table in reboot_32.S */ +void __noreturn machine_real_restart(unsigned int type); +/* These must match dispatch in arch/x86/realmore/rm/reboot.S */ #define MRR_BIOS 0 #define MRR_APM 1 diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index f48394513c3..2ffa95dc233 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -169,11 +169,6 @@ void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_cpu_info(int id); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) -/* We don't mark CPUs online until __cpu_up(), so we need another measure */ -static inline int num_booting_cpus(void) -{ - return cpumask_weight(cpu_callout_mask); -} #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 8e796fbbf9c..d8def8b3dba 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -17,6 +17,8 @@ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long +copy_user_enhanced_fast_string(void *to, const void *from, unsigned len); +__must_check unsigned long copy_user_generic_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_unrolled(void *to, const void *from, unsigned len); @@ -26,9 +28,16 @@ copy_user_generic(void *to, const void *from, unsigned len) { unsigned ret; - alternative_call(copy_user_generic_unrolled, + /* + * If CPU has ERMS feature, use copy_user_enhanced_fast_string. + * Otherwise, if CPU has rep_good feature, use copy_user_generic_string. + * Otherwise, use copy_user_generic_unrolled. + */ + alternative_call_2(copy_user_generic_unrolled, copy_user_generic_string, X86_FEATURE_REP_GOOD, + copy_user_enhanced_fast_string, + X86_FEATURE_ERMS, ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from), "=d" (len)), "1" (to), "2" (from), "3" (len) diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 1e9bed14f7a..f3971bbcd1d 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -48,7 +48,7 @@ struct arch_uprobe_task { #endif }; -extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm); +extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 6149b476d9d..a06983cdc12 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -140,6 +140,9 @@ #define IPI_RESET_LIMIT 1 /* after this # consecutive successes, bump up the throttle if it was lowered */ #define COMPLETE_THRESHOLD 5 +/* after this # of giveups (fall back to kernel IPI's) disable the use of + the BAU for a period of time */ +#define GIVEUP_LIMIT 100 #define UV_LB_SUBNODEID 0x10 @@ -166,7 +169,6 @@ #define FLUSH_RETRY_TIMEOUT 2 #define FLUSH_GIVEUP 3 #define FLUSH_COMPLETE 4 -#define FLUSH_RETRY_BUSYBUG 5 /* * tuning the action when the numalink network is extremely delayed @@ -175,7 +177,7 @@ microseconds */ #define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */ -#define CONGESTED_PERIOD 30 /* time for the bau to be +#define DISABLED_PERIOD 10 /* time for the bau to be disabled, in seconds */ /* see msg_type: */ #define MSG_NOOP 0 @@ -520,6 +522,12 @@ struct ptc_stats { unsigned long s_uv2_wars; /* uv2 workaround, perm. busy */ unsigned long s_uv2_wars_hw; /* uv2 workaround, hiwater */ unsigned long s_uv2_war_waits; /* uv2 workaround, long waits */ + unsigned long s_overipilimit; /* over the ipi reset limit */ + unsigned long s_giveuplimit; /* disables, over giveup limit*/ + unsigned long s_enters; /* entries to the driver */ + unsigned long s_ipifordisabled; /* fall back to IPI; disabled */ + unsigned long s_plugged; /* plugged by h/w bug*/ + unsigned long s_congested; /* giveup on long wait */ /* destination statistics */ unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ @@ -586,8 +594,8 @@ struct bau_control { int timeout_tries; int ipi_attempts; int conseccompletes; - int baudisabled; - int set_bau_off; + short nobau; + short baudisabled; short cpu; short osnode; short uvhub_cpu; @@ -596,14 +604,16 @@ struct bau_control { short cpus_in_socket; short cpus_in_uvhub; short partition_base_pnode; - short using_desc; /* an index, like uvhub_cpu */ - unsigned int inuse_map; + short busy; /* all were busy (war) */ unsigned short message_number; unsigned short uvhub_quiesce; short socket_acknowledge_count[DEST_Q_SIZE]; cycles_t send_message; + cycles_t period_end; + cycles_t period_time; spinlock_t uvhub_lock; spinlock_t queue_lock; + spinlock_t disable_lock; /* tunables */ int max_concurr; int max_concurr_const; @@ -614,9 +624,9 @@ struct bau_control { int complete_threshold; int cong_response_us; int cong_reps; - int cong_period; - unsigned long clocks_per_100_usec; - cycles_t period_time; + cycles_t disabled_period; + int period_giveups; + int giveup_limit; long period_requests; struct hub_and_pnode *thp; }; diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h index 92e54abf89e..f90f0a587c6 100644 --- a/arch/x86/include/asm/x2apic.h +++ b/arch/x86/include/asm/x2apic.h @@ -9,15 +9,6 @@ #include <asm/ipi.h> #include <linux/cpumask.h> -/* - * Need to use more than cpu 0, because we need more vectors - * when MSI-X are used. - */ -static const struct cpumask *x2apic_target_cpus(void) -{ - return cpu_online_mask; -} - static int x2apic_apic_id_valid(int apicid) { return 1; @@ -28,15 +19,6 @@ static int x2apic_apic_id_registered(void) return 1; } -/* - * For now each logical cpu is in its own vector allocation domain. - */ -static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) { diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index c090af10ac7..38155f66714 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -156,7 +156,6 @@ struct x86_cpuinit_ops { /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC - * @wallclock_init: init the wallclock device * @get_wallclock: get time from HW clock like RTC etc. * @set_wallclock: set time back to HW clock * @is_untracked_pat_range exclude from PAT logic @@ -164,10 +163,10 @@ struct x86_cpuinit_ops { * @i8042_detect pre-detect if i8042 controller exists * @save_sched_clock_state: save state for sched_clock() on suspend * @restore_sched_clock_state: restore state for sched_clock() on resume + * @apic_post_init: adjust apic if neeeded */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); - void (*wallclock_init)(void); unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long nowtime); void (*iommu_shutdown)(void); @@ -177,6 +176,7 @@ struct x86_platform_ops { int (*i8042_detect)(void); void (*save_sched_clock_state)(void); void (*restore_sched_clock_state)(void); + void (*apic_post_init)(void); }; struct pci_dev; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1f84794f075..931280ff829 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) "SMP alternatives: " fmt + #include <linux/module.h> #include <linux/sched.h> #include <linux/mutex.h> @@ -63,8 +65,11 @@ static int __init setup_noreplace_paravirt(char *str) __setup("noreplace-paravirt", setup_noreplace_paravirt); #endif -#define DPRINTK(fmt, args...) if (debug_alternative) \ - printk(KERN_DEBUG fmt, args) +#define DPRINTK(fmt, ...) \ +do { \ + if (debug_alternative) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ +} while (0) /* * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes @@ -428,7 +433,7 @@ void alternatives_smp_switch(int smp) * If this still occurs then you should see a hang * or crash shortly after this line: */ - printk("lockdep: fixing up alternatives.\n"); + pr_info("lockdep: fixing up alternatives\n"); #endif if (noreplace_smp || smp_alt_once || skip_smp_alternatives) @@ -444,14 +449,14 @@ void alternatives_smp_switch(int smp) if (smp == smp_mode) { /* nothing */ } else if (smp) { - printk(KERN_INFO "SMP alternatives: switching to SMP code\n"); + pr_info("switching to SMP code\n"); clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_lock(mod->locks, mod->locks_end, mod->text, mod->text_end); } else { - printk(KERN_INFO "SMP alternatives: switching to UP code\n"); + pr_info("switching to UP code\n"); set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) @@ -546,7 +551,7 @@ void __init alternative_instructions(void) #ifdef CONFIG_SMP if (smp_alt_once) { if (1 == num_possible_cpus()) { - printk(KERN_INFO "SMP alternatives: switching to UP code\n"); + pr_info("switching to UP code\n"); set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); @@ -664,7 +669,7 @@ static int __kprobes stop_machine_text_poke(void *data) struct text_poke_param *p; int i; - if (atomic_dec_and_test(&stop_machine_first)) { + if (atomic_xchg(&stop_machine_first, 0)) { for (i = 0; i < tpp->nparams; i++) { p = &tpp->params[i]; text_poke(p->addr, p->opcode, p->len); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index be16854591c..f29f6dd6bc0 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -2,6 +2,9 @@ * Shared support code for AMD K8 northbridges and derivates. * Copyright 2006 Andi Kleen, SUSE Labs. Subject to GPLv2. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/slab.h> #include <linux/init.h> @@ -258,7 +261,7 @@ void amd_flush_garts(void) } spin_unlock_irqrestore(&gart_lock, flags); if (!flushed) - printk("nothing to flush?\n"); + pr_notice("nothing to flush?\n"); } EXPORT_SYMBOL_GPL(amd_flush_garts); @@ -269,11 +272,10 @@ static __init int init_amd_nbs(void) err = amd_cache_northbridges(); if (err < 0) - printk(KERN_NOTICE "AMD NB: Cannot enumerate AMD northbridges.\n"); + pr_notice("Cannot enumerate AMD northbridges\n"); if (amd_cache_gart() < 0) - printk(KERN_NOTICE "AMD NB: Cannot initialize GART flush words, " - "GART support disabled.\n"); + pr_notice("Cannot initialize GART flush words, GART support disabled\n"); return err; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 39a222e094a..c421512ca5e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2123,6 +2123,25 @@ void default_init_apic_ldr(void) apic_write(APIC_LDR, val); } +int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) +{ + unsigned int cpu; + + for_each_cpu_and(cpu, cpumask, andmask) { + if (cpumask_test_cpu(cpu, cpu_online_mask)) + break; + } + + if (likely(cpu < nr_cpu_ids)) { + *apicid = per_cpu(x86_cpu_to_apicid, cpu); + return 0; + } + + return -EINVAL; +} + /* * Power management */ diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 0e881c46e8c..00c77cf78e9 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -36,25 +36,6 @@ static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 1; } -static const struct cpumask *flat_target_cpus(void) -{ - return cpu_online_mask; -} - -static void flat_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - /* * Set up the logical destination ID. * @@ -92,7 +73,7 @@ static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector) } static void - flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) +flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { unsigned long mask = cpumask_bits(cpumask)[0]; int cpu = smp_processor_id(); @@ -186,7 +167,7 @@ static struct apic apic_flat = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = flat_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, @@ -210,8 +191,7 @@ static struct apic apic_flat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, @@ -262,17 +242,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static const struct cpumask *physflat_target_cpus(void) -{ - return cpu_online_mask; -} - -static void physflat_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) { default_send_IPI_mask_sequence_phys(cpumask, vector); @@ -294,38 +263,6 @@ static void physflat_send_IPI_all(int vector) physflat_send_IPI_mask(cpu_online_mask, vector); } -static unsigned int physflat_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - cpu = cpumask_first(cpumask); - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - else - return BAD_APICID; -} - -static unsigned int -physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - return per_cpu(x86_cpu_to_apicid, cpu); -} - static int physflat_probe(void) { if (apic == &apic_physflat || num_possible_cpus() > 8) @@ -345,13 +282,13 @@ static struct apic apic_physflat = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = physflat_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = physflat_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, /* not needed, but shouldn't hurt: */ .init_apic_ldr = flat_init_apic_ldr, @@ -370,8 +307,7 @@ static struct apic apic_physflat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = physflat_send_IPI_mask, .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index a6e4c6e06c0..e145f28b409 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -100,12 +100,12 @@ static unsigned long noop_check_apicid_present(int bit) return physid_isset(bit, phys_cpu_present_map); } -static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask) +static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) { if (cpu != 0) pr_warning("APIC: Vector allocated for non-BSP cpu\n"); - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); + cpumask_copy(retmask, cpumask_of(cpu)); } static u32 noop_apic_read(u32 reg) @@ -159,8 +159,7 @@ struct apic apic_noop = { .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 6ec6d5d297c..bc552cff257 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -72,17 +72,6 @@ static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } -static const struct cpumask *numachip_target_cpus(void) -{ - return cpu_online_mask; -} - -static void numachip_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static int __cpuinit numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) { union numachip_csr_g3_ext_irq_gen int_gen; @@ -157,38 +146,6 @@ static void numachip_send_IPI_self(int vector) __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); } -static unsigned int numachip_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - cpu = cpumask_first(cpumask); - if (likely((unsigned)cpu < nr_cpu_ids)) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; -} - -static unsigned int -numachip_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - return per_cpu(x86_cpu_to_apicid, cpu); -} - static int __init numachip_probe(void) { return apic == &apic_numachip; @@ -253,13 +210,13 @@ static struct apic apic_numachip __refconst = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = numachip_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = numachip_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -277,8 +234,7 @@ static struct apic apic_numachip __refconst = { .set_apic_id = set_apic_id, .apic_id_mask = 0xffU << 24, - .cpu_mask_to_apicid = numachip_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = numachip_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 31fbdbfbf96..d50e3640d5a 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -26,15 +26,6 @@ static int bigsmp_apic_id_registered(void) return 1; } -static const struct cpumask *bigsmp_target_cpus(void) -{ -#ifdef CONFIG_SMP - return cpu_online_mask; -#else - return cpumask_of(0); -#endif -} - static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid) { return 0; @@ -105,32 +96,6 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid) return 1; } -/* As we are using single CPU as destination, pick only one CPU here */ -static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - int cpu = cpumask_first(cpumask); - - if (cpu < nr_cpu_ids) - return cpu_physical_id(cpu); - return BAD_APICID; -} - -static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - return cpu_physical_id(cpu); - } - return BAD_APICID; -} - static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) { return cpuid_apic >> index_msb; @@ -177,12 +142,6 @@ static const struct dmi_system_id bigsmp_dmi_table[] = { { } /* NULL entry stops DMI scanning */ }; -static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static int probe_bigsmp(void) { if (def_to_bigsmp) @@ -205,13 +164,13 @@ static struct apic apic_bigsmp = { /* phys delivery to target CPU: */ .irq_dest_mode = 0, - .target_cpus = bigsmp_target_cpus, + .target_cpus = default_target_cpus, .disable_esr = 1, .dest_logical = 0, .check_apicid_used = bigsmp_check_apicid_used, .check_apicid_present = bigsmp_check_apicid_present, - .vector_allocation_domain = bigsmp_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = bigsmp_init_apic_ldr, .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, @@ -229,8 +188,7 @@ static struct apic apic_bigsmp = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = bigsmp_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = bigsmp_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = bigsmp_send_IPI_mask, .send_IPI_mask_allbutself = NULL, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index db4ab1be3c7..0874799a98c 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -394,21 +394,6 @@ static void es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - - static void es7000_wait_for_init_deassert(atomic_t *deassert) { while (!atomic_read(deassert)) @@ -540,45 +525,49 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +es7000_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id) { unsigned int round = 0; - int cpu, uninitialized_var(apicid); + unsigned int cpu, uninitialized_var(apicid); /* * The cpus in the mask must all be on the apic cluster. */ - for_each_cpu(cpu, cpumask) { + for_each_cpu_and(cpu, cpumask, cpu_online_mask) { int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { WARN(1, "Not a valid mask!"); - return BAD_APICID; + return -EINVAL; } - apicid = new_apicid; + apicid |= new_apicid; round++; } - return apicid; + if (!round) + return -EINVAL; + *dest_id = apicid; + return 0; } -static unsigned int +static int es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; + *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; + return 0; cpumask_and(cpumask, inmask, andmask); - cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = es7000_cpu_mask_to_apicid(cpumask); + es7000_cpu_mask_to_apicid(cpumask, apicid); free_cpumask_var(cpumask); - return apicid; + return 0; } static int es7000_phys_pkg_id(int cpuid_apic, int index_msb) @@ -638,7 +627,7 @@ static struct apic __refdata apic_es7000_cluster = { .check_apicid_used = es7000_check_apicid_used, .check_apicid_present = es7000_check_apicid_present, - .vector_allocation_domain = es7000_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = es7000_init_apic_ldr_cluster, .ioapic_phys_id_map = es7000_ioapic_phys_id_map, @@ -656,7 +645,6 @@ static struct apic __refdata apic_es7000_cluster = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, .send_IPI_mask = es7000_send_IPI_mask, @@ -705,7 +693,7 @@ static struct apic __refdata apic_es7000 = { .check_apicid_used = es7000_check_apicid_used, .check_apicid_present = es7000_check_apicid_present, - .vector_allocation_domain = es7000_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = es7000_init_apic_ldr, .ioapic_phys_id_map = es7000_ioapic_phys_id_map, @@ -723,7 +711,6 @@ static struct apic __refdata apic_es7000 = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, .send_IPI_mask = es7000_send_IPI_mask, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5f0ff597437..406eee78468 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -448,8 +448,8 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi entry = alloc_irq_pin_list(node); if (!entry) { - printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n", - node, apic, pin); + pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", + node, apic, pin); return -ENOMEM; } entry->apic = apic; @@ -661,7 +661,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) ioapic_mask_entry(apic, pin); entry = ioapic_read_entry(apic, pin); if (entry.irr) - printk(KERN_ERR "Unable to reset IRR for apic: %d, pin :%d\n", + pr_err("Unable to reset IRR for apic: %d, pin :%d\n", mpc_ioapic_id(apic), pin); } @@ -895,7 +895,7 @@ static int irq_polarity(int idx) } case 2: /* reserved */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); polarity = 1; break; } @@ -906,7 +906,7 @@ static int irq_polarity(int idx) } default: /* invalid */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); polarity = 1; break; } @@ -948,7 +948,7 @@ static int irq_trigger(int idx) } default: { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 1; break; } @@ -962,7 +962,7 @@ static int irq_trigger(int idx) } case 2: /* reserved */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 1; break; } @@ -973,7 +973,7 @@ static int irq_trigger(int idx) } default: /* invalid */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 0; break; } @@ -991,7 +991,7 @@ static int pin_2_irq(int idx, int apic, int pin) * Debugging check, we are in big trouble if this message pops up! */ if (mp_irqs[idx].dstirq != pin) - printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); + pr_err("broken BIOS or MPTABLE parser, ayiee!!\n"); if (test_bit(bus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; @@ -1112,8 +1112,7 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * 0x80, because int 0x80 is hm, kind of importantish. ;) */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; - static int current_offset = VECTOR_OFFSET_START % 8; - unsigned int old_vector; + static int current_offset = VECTOR_OFFSET_START % 16; int cpu, err; cpumask_var_t tmp_mask; @@ -1123,35 +1122,45 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) return -ENOMEM; - old_vector = cfg->vector; - if (old_vector) { - cpumask_and(tmp_mask, mask, cpu_online_mask); - cpumask_and(tmp_mask, cfg->domain, tmp_mask); - if (!cpumask_empty(tmp_mask)) { - free_cpumask_var(tmp_mask); - return 0; - } - } - /* Only try and allocate irqs on cpus that are present */ err = -ENOSPC; - for_each_cpu_and(cpu, mask, cpu_online_mask) { - int new_cpu; - int vector, offset; + cpumask_clear(cfg->old_domain); + cpu = cpumask_first_and(mask, cpu_online_mask); + while (cpu < nr_cpu_ids) { + int new_cpu, vector, offset; - apic->vector_allocation_domain(cpu, tmp_mask); + apic->vector_allocation_domain(cpu, tmp_mask, mask); + + if (cpumask_subset(tmp_mask, cfg->domain)) { + err = 0; + if (cpumask_equal(tmp_mask, cfg->domain)) + break; + /* + * New cpumask using the vector is a proper subset of + * the current in use mask. So cleanup the vector + * allocation for the members that are not used anymore. + */ + cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); + cfg->move_in_progress = 1; + cpumask_and(cfg->domain, cfg->domain, tmp_mask); + break; + } vector = current_vector; offset = current_offset; next: - vector += 8; + vector += 16; if (vector >= first_system_vector) { - /* If out of vectors on large boxen, must share them. */ - offset = (offset + 1) % 8; + offset = (offset + 1) % 16; vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) + + if (unlikely(current_vector == vector)) { + cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); + cpumask_andnot(tmp_mask, mask, cfg->old_domain); + cpu = cpumask_first_and(tmp_mask, cpu_online_mask); continue; + } if (test_bit(vector, used_vectors)) goto next; @@ -1162,7 +1171,7 @@ next: /* Found one! */ current_vector = vector; current_offset = offset; - if (old_vector) { + if (cfg->vector) { cfg->move_in_progress = 1; cpumask_copy(cfg->old_domain, cfg->domain); } @@ -1346,18 +1355,18 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; - /* - * For legacy irqs, cfg->domain starts with cpu 0 for legacy - * controllers like 8259. Now that IO-APIC can handle this irq, update - * the cfg->domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain)) - apic->vector_allocation_domain(0, cfg->domain); if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), + &dest)) { + pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", + mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); + __clear_irq_vector(irq, cfg); + + return; + } apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " @@ -1366,7 +1375,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, cfg->vector, irq, attr->trigger, attr->polarity, dest); if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", + pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); __clear_irq_vector(irq, cfg); @@ -1469,9 +1478,10 @@ void setup_IO_APIC_irq_extra(u32 gsi) * Set up the timer pin, possibly with the 8259A-master behind. */ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, - unsigned int pin, int vector) + unsigned int pin, int vector) { struct IO_APIC_route_entry entry; + unsigned int dest; if (irq_remapping_enabled) return; @@ -1482,9 +1492,13 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, * We use logical delivery to get the timer IRQ * to the first CPU. */ + if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(), + apic->target_cpus(), &dest))) + dest = BAD_APICID; + entry.dest_mode = apic->irq_dest_mode; entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus()); + entry.dest = dest; entry.delivery_mode = apic->irq_delivery_mode; entry.polarity = 0; entry.trigger = 0; @@ -1521,7 +1535,6 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) reg_03.raw = io_apic_read(ioapic_idx, 3); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - printk("\n"); printk(KERN_DEBUG "IO APIC #%d......\n", mpc_ioapic_id(ioapic_idx)); printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); @@ -1578,7 +1591,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) i, ir_entry->index ); - printk("%1d %1d %1d %1d %1d " + pr_cont("%1d %1d %1d %1d %1d " "%1d %1d %X %02X\n", ir_entry->format, ir_entry->mask, @@ -1598,7 +1611,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) i, entry.dest ); - printk("%1d %1d %1d %1d %1d " + pr_cont("%1d %1d %1d %1d %1d " "%1d %1d %02X\n", entry.mask, entry.trigger, @@ -1651,8 +1664,8 @@ __apicdebuginit(void) print_IO_APICs(void) continue; printk(KERN_DEBUG "IRQ%d ", irq); for_each_irq_pin(entry, cfg->irq_2_pin) - printk("-> %d:%d", entry->apic, entry->pin); - printk("\n"); + pr_cont("-> %d:%d", entry->apic, entry->pin); + pr_cont("\n"); } printk(KERN_INFO ".................................... done.\n"); @@ -1665,9 +1678,9 @@ __apicdebuginit(void) print_APIC_field(int base) printk(KERN_DEBUG); for (i = 0; i < 8; i++) - printk(KERN_CONT "%08x", apic_read(base + i*0x10)); + pr_cont("%08x", apic_read(base + i*0x10)); - printk(KERN_CONT "\n"); + pr_cont("\n"); } __apicdebuginit(void) print_local_APIC(void *dummy) @@ -1769,7 +1782,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy) printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v); } } - printk("\n"); + pr_cont("\n"); } __apicdebuginit(void) print_local_APICs(int maxcpu) @@ -2065,7 +2078,7 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) reg_00.raw = io_apic_read(ioapic_idx, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) - printk("could not set ID!\n"); + pr_cont("could not set ID!\n"); else apic_printk(APIC_VERBOSE, " ok.\n"); } @@ -2210,71 +2223,6 @@ void send_cleanup_vector(struct irq_cfg *cfg) cfg->move_in_progress = 0; } -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - /* - * With interrupt-remapping, destination information comes - * from interrupt-remapping table entry. - */ - if (!irq_remapped(cfg)) - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) -{ - struct irq_cfg *cfg = data->chip_data; - - if (!cpumask_intersects(mask, cpu_online_mask)) - return -1; - - if (assign_irq_vector(data->irq, data->chip_data, mask)) - return -1; - - cpumask_copy(data->affinity, mask); - - *dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain); - return 0; -} - -static int -ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = __ioapic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, data->chip_data); - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return ret; -} - asmlinkage void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; @@ -2362,6 +2310,87 @@ void irq_force_complete_move(int irq) static inline void irq_complete_move(struct irq_cfg *cfg) { } #endif +static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) +{ + int apic, pin; + struct irq_pin_list *entry; + u8 vector = cfg->vector; + + for_each_irq_pin(entry, cfg->irq_2_pin) { + unsigned int reg; + + apic = entry->apic; + pin = entry->pin; + /* + * With interrupt-remapping, destination information comes + * from interrupt-remapping table entry. + */ + if (!irq_remapped(cfg)) + io_apic_write(apic, 0x11 + pin*2, dest); + reg = io_apic_read(apic, 0x10 + pin*2); + reg &= ~IO_APIC_REDIR_VECTOR_MASK; + reg |= vector; + io_apic_modify(apic, 0x10 + pin*2, reg); + } +} + +/* + * Either sets data->affinity to a valid value, and returns + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and + * leaves data->affinity untouched. + */ +int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + unsigned int *dest_id) +{ + struct irq_cfg *cfg = data->chip_data; + unsigned int irq = data->irq; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -1; + + if (!cpumask_intersects(mask, cpu_online_mask)) + return -EINVAL; + + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } + + cpumask_copy(data->affinity, mask); + + return 0; +} + +static int +ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + unsigned int dest, irq = data->irq; + unsigned long flags; + int ret; + + if (!config_enabled(CONFIG_SMP)) + return -1; + + raw_spin_lock_irqsave(&ioapic_lock, flags); + ret = __ioapic_set_affinity(data, mask, &dest); + if (!ret) { + /* Only the high 8 bits are valid. */ + dest = SET_APIC_LOGICAL_ID(dest); + __target_IO_APIC_irq(irq, dest, data->chip_data); + ret = IRQ_SET_MASK_OK_NOCOPY; + } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return ret; +} + static void ack_apic_edge(struct irq_data *data) { irq_complete_move(data->chip_data); @@ -2541,9 +2570,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip) chip->irq_ack = ir_ack_apic_edge; chip->irq_eoi = ir_ack_apic_level; -#ifdef CONFIG_SMP chip->irq_set_affinity = set_remapped_irq_affinity; -#endif } #endif /* CONFIG_IRQ_REMAP */ @@ -2554,9 +2581,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_unmask = unmask_ioapic_irq, .irq_ack = ack_apic_edge, .irq_eoi = ack_apic_level, -#ifdef CONFIG_SMP .irq_set_affinity = ioapic_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3038,7 +3063,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, if (err) return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; if (irq_remapped(cfg)) { compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id); @@ -3072,7 +3100,6 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, return err; } -#ifdef CONFIG_SMP static int msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -3092,9 +3119,8 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) __write_msi_msg(data->msi_desc, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, @@ -3105,9 +3131,7 @@ static struct irq_chip msi_chip = { .irq_unmask = unmask_msi_irq, .irq_mask = mask_msi_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3192,7 +3216,6 @@ void native_teardown_msi_irq(unsigned int irq) } #ifdef CONFIG_DMAR_TABLE -#ifdef CONFIG_SMP static int dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) @@ -3214,19 +3237,15 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, dmar_msi_write(irq, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip dmar_msi_type = { .name = "DMAR_MSI", .irq_unmask = dmar_msi_unmask, .irq_mask = dmar_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = dmar_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3247,7 +3266,6 @@ int arch_setup_dmar_msi(unsigned int irq) #ifdef CONFIG_HPET_TIMER -#ifdef CONFIG_SMP static int hpet_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -3267,19 +3285,15 @@ static int hpet_msi_set_affinity(struct irq_data *data, hpet_msi_write(data->handler_data, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .irq_unmask = hpet_msi_unmask, .irq_mask = hpet_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = hpet_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3314,8 +3328,6 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) */ #ifdef CONFIG_HT_IRQ -#ifdef CONFIG_SMP - static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) { struct ht_irq_msg msg; @@ -3340,25 +3352,23 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) return -1; target_ht_irq(data->irq, dest, cfg->vector); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif - static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = ht_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) { struct irq_cfg *cfg; + struct ht_irq_msg msg; + unsigned dest; int err; if (disable_apic) @@ -3366,36 +3376,37 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) cfg = irq_cfg(irq); err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (!err) { - struct ht_irq_msg msg; - unsigned dest; + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus()); + msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + msg.address_lo = + HT_IRQ_LOW_BASE | + HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_VECTOR(cfg->vector) | + ((apic->irq_dest_mode == 0) ? + HT_IRQ_LOW_DM_PHYSICAL : + HT_IRQ_LOW_DM_LOGICAL) | + HT_IRQ_LOW_RQEOI_EDGE | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + HT_IRQ_LOW_MT_FIXED : + HT_IRQ_LOW_MT_ARBITRATED) | + HT_IRQ_LOW_IRQ_MASKED; - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; + write_ht_irq_msg(irq, &msg); - write_ht_irq_msg(irq, &msg); + irq_set_chip_and_handler_name(irq, &ht_irq_chip, + handle_edge_irq, "edge"); - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - } - return err; + return 0; } #endif /* CONFIG_HT_IRQ */ @@ -3563,7 +3574,8 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id) /* Sanity check */ if (reg_00.bits.ID != apic_id) { - printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic); + pr_err("IOAPIC[%d]: Unable to change apic_id!\n", + ioapic); return -1; } } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index f00a68cca37..d661ee95cab 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -406,16 +406,13 @@ static inline int numaq_check_phys_apicid_present(int phys_apicid) * We use physical apicids here, not logical, so just return the default * physical broadcast to stop people from breaking us */ -static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - return 0x0F; -} - -static inline unsigned int +static int numaq_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - return 0x0F; + *apicid = 0x0F; + return 0; } /* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */ @@ -441,20 +438,6 @@ static int probe_numaq(void) return found_numaq; } -static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - static void numaq_setup_portio_remap(void) { int num_quads = num_online_nodes(); @@ -491,7 +474,7 @@ static struct apic __refdata apic_numaq = { .check_apicid_used = numaq_check_apicid_used, .check_apicid_present = numaq_check_apicid_present, - .vector_allocation_domain = numaq_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = numaq_init_apic_ldr, .ioapic_phys_id_map = numaq_ioapic_phys_id_map, @@ -509,7 +492,6 @@ static struct apic __refdata apic_numaq = { .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, - .cpu_mask_to_apicid = numaq_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = numaq_cpu_mask_to_apicid_and, .send_IPI_mask = numaq_send_IPI_mask, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 1b291da09e6..eb35ef9ee63 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -66,21 +66,6 @@ static void setup_apic_flat_routing(void) #endif } -static void default_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* - * Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - /* should be called last. */ static int probe_default(void) { @@ -105,7 +90,7 @@ static struct apic apic_default = { .check_apicid_used = default_check_apicid_used, .check_apicid_present = default_check_apicid_present, - .vector_allocation_domain = default_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, @@ -123,8 +108,7 @@ static struct apic apic_default = { .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, @@ -208,6 +192,9 @@ void __init default_setup_apic_routing(void) if (apic->setup_apic_routing) apic->setup_apic_routing(); + + if (x86_platform.apic_post_init) + x86_platform.apic_post_init(); } void __init generic_apic_probe(void) diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index 3fe98669892..1793dba7a74 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -23,11 +23,6 @@ #include <asm/ipi.h> #include <asm/setup.h> -static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) -{ - return hard_smp_processor_id() >> index_msb; -} - /* * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. */ @@ -48,10 +43,8 @@ void __init default_setup_apic_routing(void) } } - if (is_vsmp_box()) { - /* need to update phys_pkg_id */ - apic->phys_pkg_id = apicid_phys_pkg_id; - } + if (x86_platform.apic_post_init) + x86_platform.apic_post_init(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 659897c0075..77c95c0e1bf 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) "summit: %s: " fmt, __func__ + #include <linux/mm.h> #include <linux/init.h> #include <asm/io.h> @@ -235,8 +237,8 @@ static int summit_apic_id_registered(void) static void summit_setup_apic_routing(void) { - printk("Enabling APIC mode: Summit. Using %d I/O APICs\n", - nr_ioapics); + pr_info("Enabling APIC mode: Summit. Using %d I/O APICs\n", + nr_ioapics); } static int summit_cpu_present_to_apicid(int mps_cpu) @@ -263,43 +265,48 @@ static int summit_check_phys_apicid_present(int physical_apicid) return 1; } -static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +summit_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id) { unsigned int round = 0; - int cpu, apicid = 0; + unsigned int cpu, apicid = 0; /* * The cpus in the mask must all be on the apic cluster. */ - for_each_cpu(cpu, cpumask) { + for_each_cpu_and(cpu, cpumask, cpu_online_mask) { int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - printk("%s: Not a valid mask!\n", __func__); - return BAD_APICID; + pr_err("Not a valid mask!\n"); + return -EINVAL; } apicid |= new_apicid; round++; } - return apicid; + if (!round) + return -EINVAL; + *dest_id = apicid; + return 0; } -static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) +static int +summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, + const struct cpumask *andmask, + unsigned int *apicid) { - int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; + *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; + return 0; cpumask_and(cpumask, inmask, andmask); - cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = summit_cpu_mask_to_apicid(cpumask); + summit_cpu_mask_to_apicid(cpumask, apicid); free_cpumask_var(cpumask); - return apicid; + return 0; } /* @@ -320,20 +327,6 @@ static int probe_summit(void) return 0; } -static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - #ifdef CONFIG_X86_SUMMIT_NUMA static struct rio_table_hdr *rio_table_hdr; static struct scal_detail *scal_devs[MAX_NUMNODES]; @@ -355,7 +348,7 @@ static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) } } if (i == rio_table_hdr->num_rio_dev) { - printk(KERN_ERR "%s: Couldn't find owner Cyclone for Winnipeg!\n", __func__); + pr_err("Couldn't find owner Cyclone for Winnipeg!\n"); return last_bus; } @@ -366,7 +359,7 @@ static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) } } if (i == rio_table_hdr->num_scal_dev) { - printk(KERN_ERR "%s: Couldn't find owner Twister for Cyclone!\n", __func__); + pr_err("Couldn't find owner Twister for Cyclone!\n"); return last_bus; } @@ -396,7 +389,7 @@ static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) num_buses = 9; break; default: - printk(KERN_INFO "%s: Unsupported Winnipeg type!\n", __func__); + pr_info("Unsupported Winnipeg type!\n"); return last_bus; } @@ -411,13 +404,15 @@ static int build_detail_arrays(void) int i, scal_detail_size, rio_detail_size; if (rio_table_hdr->num_scal_dev > MAX_NUMNODES) { - printk(KERN_WARNING "%s: MAX_NUMNODES too low! Defined as %d, but system has %d nodes.\n", __func__, MAX_NUMNODES, rio_table_hdr->num_scal_dev); + pr_warn("MAX_NUMNODES too low! Defined as %d, but system has %d nodes\n", + MAX_NUMNODES, rio_table_hdr->num_scal_dev); return 0; } switch (rio_table_hdr->version) { default: - printk(KERN_WARNING "%s: Invalid Rio Grande Table Version: %d\n", __func__, rio_table_hdr->version); + pr_warn("Invalid Rio Grande Table Version: %d\n", + rio_table_hdr->version); return 0; case 2: scal_detail_size = 11; @@ -462,7 +457,7 @@ void setup_summit(void) offset = *((unsigned short *)(ptr + offset)); } if (!rio_table_hdr) { - printk(KERN_ERR "%s: Unable to locate Rio Grande Table in EBDA - bailing!\n", __func__); + pr_err("Unable to locate Rio Grande Table in EBDA - bailing!\n"); return; } @@ -509,7 +504,7 @@ static struct apic apic_summit = { .check_apicid_used = summit_check_apicid_used, .check_apicid_present = summit_check_apicid_present, - .vector_allocation_domain = summit_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = summit_init_apic_ldr, .ioapic_phys_id_map = summit_ioapic_phys_id_map, @@ -527,7 +522,6 @@ static struct apic apic_summit = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = summit_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = summit_cpu_mask_to_apicid_and, .send_IPI_mask = summit_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index ff35cff0e1a..c88baa4ff0e 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -81,7 +81,7 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) } static void - x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) +x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) { __x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLBUT); } @@ -96,36 +96,37 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) +static int +x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) { - /* - * We're using fixed IRQ delivery, can only return one logical APIC ID. - * May as well be the first. - */ - int cpu = cpumask_first(cpumask); + u32 dest = 0; + u16 cluster; + int i; - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_logical_apicid, cpu); - else - return BAD_APICID; -} + for_each_cpu_and(i, cpumask, andmask) { + if (!cpumask_test_cpu(i, cpu_online_mask)) + continue; + dest = per_cpu(x86_cpu_to_logical_apicid, i); + cluster = x2apic_cluster(i); + break; + } -static unsigned int -x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; + if (!dest) + return -EINVAL; - /* - * We're using fixed IRQ delivery, can only return one logical APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; + for_each_cpu_and(i, cpumask, andmask) { + if (!cpumask_test_cpu(i, cpu_online_mask)) + continue; + if (cluster != x2apic_cluster(i)) + continue; + dest |= per_cpu(x86_cpu_to_logical_apicid, i); } - return per_cpu(x86_cpu_to_logical_apicid, cpu); + *apicid = dest; + + return 0; } static void init_x2apic_ldr(void) @@ -208,6 +209,32 @@ static int x2apic_cluster_probe(void) return 0; } +static const struct cpumask *x2apic_cluster_target_cpus(void) +{ + return cpu_all_mask; +} + +/* + * Each x2apic cluster is an allocation domain. + */ +static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) +{ + /* + * To minimize vector pressure, default case of boot, device bringup + * etc will use a single cpu for the interrupt destination. + * + * On explicit migration requests coming from irqbalance etc, + * interrupts will be routed to the x2apic cluster (cluster-id + * derived from the first cpu in the mask) members specified + * in the mask. + */ + if (mask == x2apic_cluster_target_cpus()) + cpumask_copy(retmask, cpumask_of(cpu)); + else + cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu)); +} + static struct apic apic_x2apic_cluster = { .name = "cluster x2apic", @@ -219,13 +246,13 @@ static struct apic apic_x2apic_cluster = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = x2apic_target_cpus, + .target_cpus = x2apic_cluster_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = x2apic_vector_allocation_domain, + .vector_allocation_domain = cluster_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -243,7 +270,6 @@ static struct apic apic_x2apic_cluster = { .set_apic_id = x2apic_set_apic_id, .apic_id_mask = 0xFFFFFFFFu, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index c17e982db27..e03a1e180e8 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -76,38 +76,6 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - int cpu = cpumask_first(cpumask); - - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - else - return BAD_APICID; -} - -static unsigned int -x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - - return per_cpu(x86_cpu_to_apicid, cpu); -} - static void init_x2apic_ldr(void) { } @@ -131,13 +99,13 @@ static struct apic apic_x2apic_phys = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = x2apic_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = x2apic_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -155,8 +123,7 @@ static struct apic apic_x2apic_phys = { .set_apic_id = x2apic_set_apic_id, .apic_id_mask = 0xFFFFFFFFu, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index c6d03f7a440..8cfade9510a 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -185,17 +185,6 @@ EXPORT_SYMBOL_GPL(uv_possible_blades); unsigned long sn_rtc_cycles_per_second; EXPORT_SYMBOL(sn_rtc_cycles_per_second); -static const struct cpumask *uv_target_cpus(void) -{ - return cpu_online_mask; -} - -static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { #ifdef CONFIG_SMP @@ -280,25 +269,12 @@ static void uv_init_apic_ldr(void) { } -static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - int cpu = cpumask_first(cpumask); - - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; - else - return BAD_APICID; -} - -static unsigned int +static int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - int cpu; + int unsigned cpu; /* * We're using fixed IRQ delivery, can only return one phys APIC ID. @@ -308,7 +284,13 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; + + if (likely(cpu < nr_cpu_ids)) { + *apicid = per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; + return 0; + } + + return -EINVAL; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -362,13 +344,13 @@ static struct apic __refdata apic_x2apic_uv_x = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = uv_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = uv_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = uv_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -386,7 +368,6 @@ static struct apic __refdata apic_x2apic_uv_x = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFFFFFFFu, - .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, .send_IPI_mask = uv_send_IPI_mask, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 07b0c0db466..d65464e4350 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -201,6 +201,8 @@ * http://www.microsoft.com/whdc/archive/amp_12.mspx] */ +#define pr_fmt(fmt) "apm: " fmt + #include <linux/module.h> #include <linux/poll.h> @@ -485,11 +487,11 @@ static void apm_error(char *str, int err) if (error_table[i].key == err) break; if (i < ERROR_COUNT) - printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg); + pr_notice("%s: %s\n", str, error_table[i].msg); else if (err < 0) - printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err); + pr_notice("%s: linux error code %i\n", str, err); else - printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n", + pr_notice("%s: unknown error code %#2.2x\n", str, err); } @@ -1184,7 +1186,7 @@ static void queue_event(apm_event_t event, struct apm_user *sender) static int notified; if (notified++ == 0) - printk(KERN_ERR "apm: an event queue overflowed\n"); + pr_err("an event queue overflowed\n"); if (++as->event_tail >= APM_MAX_EVENTS) as->event_tail = 0; } @@ -1447,7 +1449,7 @@ static void apm_mainloop(void) static int check_apm_user(struct apm_user *as, const char *func) { if (as == NULL || as->magic != APM_BIOS_MAGIC) { - printk(KERN_ERR "apm: %s passed bad filp\n", func); + pr_err("%s passed bad filp\n", func); return 1; } return 0; @@ -1586,7 +1588,7 @@ static int do_release(struct inode *inode, struct file *filp) as1 = as1->next) ; if (as1 == NULL) - printk(KERN_ERR "apm: filp not in user list\n"); + pr_err("filp not in user list\n"); else as1->next = as->next; } @@ -1600,11 +1602,9 @@ static int do_open(struct inode *inode, struct file *filp) struct apm_user *as; as = kmalloc(sizeof(*as), GFP_KERNEL); - if (as == NULL) { - printk(KERN_ERR "apm: cannot allocate struct of size %d bytes\n", - sizeof(*as)); + if (as == NULL) return -ENOMEM; - } + as->magic = APM_BIOS_MAGIC; as->event_tail = as->event_head = 0; as->suspends_pending = as->standbys_pending = 0; @@ -2313,16 +2313,16 @@ static int __init apm_init(void) } if (apm_info.disabled) { - printk(KERN_NOTICE "apm: disabled on user request.\n"); + pr_notice("disabled on user request.\n"); return -ENODEV; } if ((num_online_cpus() > 1) && !power_off && !smp) { - printk(KERN_NOTICE "apm: disabled - APM is not SMP safe.\n"); + pr_notice("disabled - APM is not SMP safe.\n"); apm_info.disabled = 1; return -ENODEV; } if (!acpi_disabled) { - printk(KERN_NOTICE "apm: overridden by ACPI.\n"); + pr_notice("overridden by ACPI.\n"); apm_info.disabled = 1; return -ENODEV; } @@ -2356,8 +2356,7 @@ static int __init apm_init(void) kapmd_task = kthread_create(apm, NULL, "kapmd"); if (IS_ERR(kapmd_task)) { - printk(KERN_ERR "apm: disabled - Unable to start kernel " - "thread.\n"); + pr_err("disabled - Unable to start kernel thread\n"); err = PTR_ERR(kapmd_task); kapmd_task = NULL; remove_proc_entry("apm", NULL); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 6ab6aa2fdfd..bac4c3804cc 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -32,7 +32,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_PERF_EVENTS obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o endif obj-$(CONFIG_X86_MCE) += mcheck/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 146bb6218ee..9d92e19039f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -19,6 +19,39 @@ #include "cpu.h" +static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) +{ + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + u32 gprs[8] = { 0 }; + int err; + + WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + + gprs[1] = msr; + gprs[7] = 0x9c5a203a; + + err = rdmsr_safe_regs(gprs); + + *p = gprs[0] | ((u64)gprs[2] << 32); + + return err; +} + +static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) +{ + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + u32 gprs[8] = { 0 }; + + WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + + gprs[0] = (u32)val; + gprs[1] = msr; + gprs[2] = val >> 32; + gprs[7] = 0x9c5a203a; + + return wrmsr_safe_regs(gprs); +} + #ifdef CONFIG_X86_32 /* * B step AMD K6 before B 9730xxxx have hardware bugs that can cause @@ -586,9 +619,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_TOPOEXT)) { u64 val; - if (!rdmsrl_amd_safe(0xc0011005, &val)) { + if (!rdmsrl_safe(0xc0011005, &val)) { val |= 1ULL << 54; - wrmsrl_amd_safe(0xc0011005, val); + wrmsrl_safe(0xc0011005, val); rdmsrl(0xc0011005, val); if (val & (1ULL << 54)) { set_cpu_cap(c, X86_FEATURE_TOPOEXT); @@ -679,7 +712,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask); if (err == 0) { mask |= (1 << 10); - checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask); + wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask); } } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 46674fbb62b..c97bb7b5a9f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -55,8 +55,8 @@ static void __init check_fpu(void) if (!boot_cpu_data.hard_math) { #ifndef CONFIG_MATH_EMULATION - printk(KERN_EMERG "No coprocessor found and no math emulation present.\n"); - printk(KERN_EMERG "Giving up.\n"); + pr_emerg("No coprocessor found and no math emulation present\n"); + pr_emerg("Giving up\n"); for (;;) ; #endif return; @@ -86,7 +86,7 @@ static void __init check_fpu(void) boot_cpu_data.fdiv_bug = fdiv_bug; if (boot_cpu_data.fdiv_bug) - printk(KERN_WARNING "Hmm, FPU with FDIV bug.\n"); + pr_warn("Hmm, FPU with FDIV bug\n"); } static void __init check_hlt(void) @@ -94,16 +94,16 @@ static void __init check_hlt(void) if (boot_cpu_data.x86 >= 5 || paravirt_enabled()) return; - printk(KERN_INFO "Checking 'hlt' instruction... "); + pr_info("Checking 'hlt' instruction... "); if (!boot_cpu_data.hlt_works_ok) { - printk("disabled\n"); + pr_cont("disabled\n"); return; } halt(); halt(); halt(); halt(); - printk(KERN_CONT "OK.\n"); + pr_cont("OK\n"); } /* @@ -116,7 +116,7 @@ static void __init check_popad(void) #ifndef CONFIG_X86_POPAD_OK int res, inp = (int) &res; - printk(KERN_INFO "Checking for popad bug... "); + pr_info("Checking for popad bug... "); __asm__ __volatile__( "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " : "=&a" (res) @@ -127,9 +127,9 @@ static void __init check_popad(void) * CPU hard. Too bad. */ if (res != 12345678) - printk(KERN_CONT "Buggy.\n"); + pr_cont("Buggy\n"); else - printk(KERN_CONT "OK.\n"); + pr_cont("OK\n"); #endif } @@ -161,7 +161,7 @@ void __init check_bugs(void) { identify_boot_cpu(); #ifndef CONFIG_SMP - printk(KERN_INFO "CPU: "); + pr_info("CPU: "); print_cpu_info(&boot_cpu_data); #endif check_config(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6b9333b429b..5bbc082c47a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -947,7 +947,7 @@ static void __cpuinit __print_cpu_msr(void) index_max = msr_range_array[i].max; for (index = index_min; index < index_max; index++) { - if (rdmsrl_amd_safe(index, &val)) + if (rdmsrl_safe(index, &val)) continue; printk(KERN_INFO " MSR%08x: %016llx\n", index, val); } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index da27c5d2168..5a5a5dc1ff1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -7,6 +7,9 @@ * Copyright 2008 Intel Corporation * Author: Andi Kleen */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/thread_info.h> #include <linux/capability.h> #include <linux/miscdevice.h> @@ -210,7 +213,7 @@ static void drain_mcelog_buffer(void) cpu_relax(); if (!m->finished && retries >= 4) { - pr_err("MCE: skipping error being logged currently!\n"); + pr_err("skipping error being logged currently!\n"); break; } } @@ -1167,8 +1170,9 @@ int memory_failure(unsigned long pfn, int vector, int flags) { /* mce_severity() should not hand us an ACTION_REQUIRED error */ BUG_ON(flags & MF_ACTION_REQUIRED); - printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n" - "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn); + pr_err("Uncorrected memory error in page 0x%lx ignored\n" + "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", + pfn); return 0; } @@ -1358,11 +1362,10 @@ static int __cpuinit __mcheck_cpu_cap_init(void) b = cap & MCG_BANKCNT_MASK; if (!banks) - printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b); + pr_info("CPU supports %d MCE banks\n", b); if (b > MAX_NR_BANKS) { - printk(KERN_WARNING - "MCE: Using only %u machine check banks out of %u\n", + pr_warn("Using only %u machine check banks out of %u\n", MAX_NR_BANKS, b); b = MAX_NR_BANKS; } @@ -1419,7 +1422,7 @@ static void __mcheck_cpu_init_generic(void) static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { if (c->x86_vendor == X86_VENDOR_UNKNOWN) { - pr_info("MCE: unknown CPU type - not enabling MCE support.\n"); + pr_info("unknown CPU type - not enabling MCE support\n"); return -EOPNOTSUPP; } @@ -1574,7 +1577,7 @@ static void __mcheck_cpu_init_timer(void) /* Handle unconfigured int18 (should never happen) */ static void unexpected_machine_check(struct pt_regs *regs, long error_code) { - printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n", + pr_err("CPU#%d: Unexpected int18 (Machine Check)\n", smp_processor_id()); } @@ -1893,8 +1896,7 @@ static int __init mcheck_enable(char *str) get_option(&str, &monarch_timeout); } } else { - printk(KERN_INFO "mce argument %s ignored. Please use /sys\n", - str); + pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; } return 1; diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index bdda2e6c673..35ffda5d072 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -258,11 +258,11 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk, /* Compute the maximum size with which we can make a range: */ if (range_startk) - max_align = ffs(range_startk) - 1; + max_align = __ffs(range_startk); else - max_align = 32; + max_align = BITS_PER_LONG - 1; - align = fls(range_sizek) - 1; + align = __fls(range_sizek); if (align > max_align) align = max_align; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 75772ae6c65..e9fe907cd24 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -361,11 +361,7 @@ static void __init print_mtrr_state(void) } pr_debug("MTRR variable ranges %sabled:\n", mtrr_state.enabled & 2 ? "en" : "dis"); - if (size_or_mask & 0xffffffffUL) - high_width = ffs(size_or_mask & 0xffffffffUL) - 1; - else - high_width = ffs(size_or_mask>>32) + 32 - 1; - high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4; + high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c4706cf9c01..29557aa06dd 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -35,17 +35,6 @@ #include "perf_event.h" -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\ - (unsigned long)(val)); \ - native_write_msr((msr), (u32)((u64)(val)), \ - (u32)((u64)(val) >> 32)); \ -} while (0) -#endif - struct x86_pmu x86_pmu __read_mostly; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { @@ -74,7 +63,7 @@ u64 x86_perf_event_update(struct perf_event *event) int idx = hwc->idx; s64 delta; - if (idx == X86_PMC_IDX_FIXED_BTS) + if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; /* @@ -86,7 +75,7 @@ u64 x86_perf_event_update(struct perf_event *event) */ again: prev_raw_count = local64_read(&hwc->prev_count); - rdmsrl(hwc->event_base, new_raw_count); + rdpmcl(hwc->event_base_rdpmc, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) @@ -189,7 +178,7 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_new = 0; + u64 val, val_new = ~0; int i, reg, ret = 0; /* @@ -222,8 +211,9 @@ static bool check_hw_exists(void) * that don't trap on the MSR access and always return 0s. */ val = 0xabcdUL; - ret = checking_wrmsrl(x86_pmu_event_addr(0), val); - ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new); + reg = x86_pmu_event_addr(0); + ret = wrmsrl_safe(reg, val); + ret |= rdmsrl_safe(reg, &val_new); if (ret || val != val_new) goto msr_fail; @@ -240,6 +230,7 @@ bios_fail: msr_fail: printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); + printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); return false; } @@ -388,7 +379,7 @@ int x86_pmu_hw_config(struct perf_event *event) int precise = 0; /* Support for constant skid */ - if (x86_pmu.pebs_active) { + if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; /* Support for IP fixup */ @@ -637,8 +628,8 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ - if (x86_pmu.num_counters_fixed) { - idx = X86_PMC_IDX_FIXED; + if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { + idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; @@ -646,7 +637,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; - for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) { + for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } @@ -704,8 +695,8 @@ static bool perf_sched_next_event(struct perf_sched *sched) /* * Assign a counter for each event. */ -static int perf_assign_events(struct event_constraint **constraints, int n, - int wmin, int wmax, int *assign) +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int *assign) { struct perf_sched sched; @@ -824,15 +815,17 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; - if (hwc->idx == X86_PMC_IDX_FIXED_BTS) { + if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) { hwc->config_base = 0; hwc->event_base = 0; - } else if (hwc->idx >= X86_PMC_IDX_FIXED) { + } else if (hwc->idx >= INTEL_PMC_IDX_FIXED) { hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; - hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED); + hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED); + hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30; } else { hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); + hwc->event_base_rdpmc = hwc->idx; } } @@ -930,7 +923,7 @@ int x86_perf_event_set_period(struct perf_event *event) s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; - if (idx == X86_PMC_IDX_FIXED_BTS) + if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; /* @@ -1316,7 +1309,6 @@ static struct attribute_group x86_pmu_format_group = { static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; - struct event_constraint *c; int err; pr_info("Performance Events: "); @@ -1347,21 +1339,8 @@ static int __init init_hw_perf_events(void) for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); - if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) { - WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", - x86_pmu.num_counters, X86_PMC_MAX_GENERIC); - x86_pmu.num_counters = X86_PMC_MAX_GENERIC; - } - x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; - - if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) { - WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", - x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED); - x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED; - } - - x86_pmu.intel_ctrl |= - ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED; + if (!x86_pmu.intel_ctrl) + x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; perf_events_lapic_init(); register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI"); @@ -1370,22 +1349,6 @@ static int __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0); - if (x86_pmu.event_constraints) { - /* - * event on fixed counter2 (REF_CYCLES) only works on this - * counter, so do not extend mask to generic counters - */ - for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != X86_RAW_EVENT_MASK - || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) { - continue; - } - - c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; - c->weight += x86_pmu.num_counters; - } - } - x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; @@ -1620,8 +1583,8 @@ static int x86_pmu_event_idx(struct perf_event *event) if (!x86_pmu.attr_rdpmc) return 0; - if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) { - idx -= X86_PMC_IDX_FIXED; + if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) { + idx -= INTEL_PMC_IDX_FIXED; idx |= 1 << 30; } @@ -1649,7 +1612,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { - unsigned long val = simple_strtoul(buf, NULL, 0); + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; @@ -1682,13 +1650,20 @@ static void x86_pmu_flush_branch_stack(void) x86_pmu.flush_branch_stack(); } +void perf_check_microcode(void) +{ + if (x86_pmu.check_microcode) + x86_pmu.check_microcode(); +} +EXPORT_SYMBOL_GPL(perf_check_microcode); + static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, - .attr_groups = x86_pmu_attr_groups, + .attr_groups = x86_pmu_attr_groups, - .event_init = x86_pmu_event_init, + .event_init = x86_pmu_event_init, .add = x86_pmu_add, .del = x86_pmu_del, @@ -1696,11 +1671,11 @@ static struct pmu pmu = { .stop = x86_pmu_stop, .read = x86_pmu_read, - .start_txn = x86_pmu_start_txn, - .cancel_txn = x86_pmu_cancel_txn, - .commit_txn = x86_pmu_commit_txn, + .start_txn = x86_pmu_start_txn, + .cancel_txn = x86_pmu_cancel_txn, + .commit_txn = x86_pmu_commit_txn, - .event_idx = x86_pmu_event_idx, + .event_idx = x86_pmu_event_idx, .flush_branch_stack = x86_pmu_flush_branch_stack, }; @@ -1863,7 +1838,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { - if (user_mode(regs)) + if (!kernel_ip(regs->ip)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 7241e2fc3c1..a15df4be151 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -14,6 +14,18 @@ #include <linux/perf_event.h> +#if 0 +#undef wrmsrl +#define wrmsrl(msr, val) \ +do { \ + unsigned int _msr = (msr); \ + u64 _val = (val); \ + trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ + (unsigned long long)(_val)); \ + native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ +} while (0) +#endif + /* * | NHM/WSM | SNB | * register ------------------------------- @@ -57,7 +69,7 @@ struct amd_nb { }; /* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +#define MAX_PEBS_EVENTS 8 /* * A debug store configuration. @@ -349,6 +361,8 @@ struct x86_pmu { void (*cpu_starting)(int cpu); void (*cpu_dying)(int cpu); void (*cpu_dead)(int cpu); + + void (*check_microcode)(void); void (*flush_branch_stack)(void); /* @@ -360,12 +374,16 @@ struct x86_pmu { /* * Intel DebugStore bits */ - int bts, pebs; - int bts_active, pebs_active; + int bts :1, + bts_active :1, + pebs :1, + pebs_active :1, + pebs_broken :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); + int max_pebs_events; /* * Intel LBR @@ -468,6 +486,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, void x86_pmu_enable_all(int added); +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int *assign); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); void x86_pmu_stop(struct perf_event *event, int flags); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 11a4eb9131d..4528ae7b6ec 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -366,7 +366,7 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; - if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15) + if (boot_cpu_data.x86_max_cores < 2) return; nb_id = amd_get_nb_id(cpu); @@ -422,35 +422,6 @@ static struct attribute *amd_format_attr[] = { NULL, }; -static __initconst const struct x86_pmu amd_pmu = { - .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, - .hw_config = amd_pmu_hw_config, - .schedule_events = x86_schedule_events, - .eventsel = MSR_K7_EVNTSEL0, - .perfctr = MSR_K7_PERFCTR0, - .event_map = amd_pmu_event_map, - .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_counters = AMD64_NUM_COUNTERS, - .cntval_bits = 48, - .cntval_mask = (1ULL << 48) - 1, - .apic = 1, - /* use highest bit to detect overflow */ - .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints, - .put_event_constraints = amd_put_event_constraints, - - .format_attrs = amd_format_attr, - - .cpu_prepare = amd_pmu_cpu_prepare, - .cpu_starting = amd_pmu_cpu_starting, - .cpu_dead = amd_pmu_cpu_dead, -}; - /* AMD Family 15h */ #define AMD_EVENT_TYPE_MASK 0x000000F0ULL @@ -597,8 +568,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev } } -static __initconst const struct x86_pmu amd_pmu_f15h = { - .name = "AMD Family 15h", +static __initconst const struct x86_pmu amd_pmu = { + .name = "AMD", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, .enable_all = x86_pmu_enable_all, @@ -606,50 +577,68 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { .disable = x86_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, - .eventsel = MSR_F15H_PERF_CTL, - .perfctr = MSR_F15H_PERF_CTR, + .eventsel = MSR_K7_EVNTSEL0, + .perfctr = MSR_K7_PERFCTR0, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_counters = AMD64_NUM_COUNTERS_F15H, + .num_counters = AMD64_NUM_COUNTERS, .cntval_bits = 48, .cntval_mask = (1ULL << 48) - 1, .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints_f15h, - /* nortbridge counters not yet implemented: */ -#if 0 + .get_event_constraints = amd_get_event_constraints, .put_event_constraints = amd_put_event_constraints, + .format_attrs = amd_format_attr, + .cpu_prepare = amd_pmu_cpu_prepare, - .cpu_dead = amd_pmu_cpu_dead, -#endif .cpu_starting = amd_pmu_cpu_starting, - .format_attrs = amd_format_attr, + .cpu_dead = amd_pmu_cpu_dead, }; +static int setup_event_constraints(void) +{ + if (boot_cpu_data.x86 >= 0x15) + x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; + return 0; +} + +static int setup_perfctr_core(void) +{ + if (!cpu_has_perfctr_core) { + WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h, + KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!"); + return -ENODEV; + } + + WARN(x86_pmu.get_event_constraints == amd_get_event_constraints, + KERN_ERR "hw perf events core counters need constraints handler!"); + + /* + * If core performance counter extensions exists, we must use + * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also + * x86_pmu_addr_offset(). + */ + x86_pmu.eventsel = MSR_F15H_PERF_CTL; + x86_pmu.perfctr = MSR_F15H_PERF_CTR; + x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE; + + printk(KERN_INFO "perf: AMD core performance counters detected\n"); + + return 0; +} + __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) return -ENODEV; - /* - * If core performance counter extensions exists, it must be - * family 15h, otherwise fail. See x86_pmu_addr_offset(). - */ - switch (boot_cpu_data.x86) { - case 0x15: - if (!cpu_has_perfctr_core) - return -ENODEV; - x86_pmu = amd_pmu_f15h; - break; - default: - if (cpu_has_perfctr_core) - return -ENODEV; - x86_pmu = amd_pmu; - break; - } + x86_pmu = amd_pmu; + + setup_event_constraints(); + setup_perfctr_core(); /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 187c294bc65..7a8b9d0abca 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -5,6 +5,8 @@ * among events on a single PMU. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/stddef.h> #include <linux/types.h> #include <linux/init.h> @@ -21,14 +23,14 @@ */ static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e, - [PERF_COUNT_HW_CACHE_MISSES] = 0x412e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, - [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, - [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e, + [PERF_COUNT_HW_CACHE_MISSES] = 0x412e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, + [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, + [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */ }; static struct event_constraint intel_core_event_constraints[] __read_mostly = @@ -747,7 +749,7 @@ static void intel_pmu_disable_all(void) wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); - if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); intel_pmu_pebs_disable_all(); @@ -763,9 +765,9 @@ static void intel_pmu_enable_all(int added) wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask); - if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { + if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { struct perf_event *event = - cpuc->events[X86_PMC_IDX_FIXED_BTS]; + cpuc->events[INTEL_PMC_IDX_FIXED_BTS]; if (WARN_ON_ONCE(!event)) return; @@ -871,7 +873,7 @@ static inline void intel_pmu_ack_status(u64 ack) static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) { - int idx = hwc->idx - X86_PMC_IDX_FIXED; + int idx = hwc->idx - INTEL_PMC_IDX_FIXED; u64 ctrl_val, mask; mask = 0xfULL << (idx * 4); @@ -886,7 +888,7 @@ static void intel_pmu_disable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { + if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { intel_pmu_disable_bts(); intel_pmu_drain_bts_buffer(); return; @@ -915,7 +917,7 @@ static void intel_pmu_disable_event(struct perf_event *event) static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) { - int idx = hwc->idx - X86_PMC_IDX_FIXED; + int idx = hwc->idx - INTEL_PMC_IDX_FIXED; u64 ctrl_val, bits, mask; /* @@ -949,7 +951,7 @@ static void intel_pmu_enable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { + if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { if (!__this_cpu_read(cpu_hw_events.enabled)) return; @@ -1000,14 +1002,14 @@ static void intel_pmu_reset(void) local_irq_save(flags); - printk("clearing PMU state on CPU#%d\n", smp_processor_id()); + pr_info("clearing PMU state on CPU#%d\n", smp_processor_id()); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - checking_wrmsrl(x86_pmu_config_addr(idx), 0ull); - checking_wrmsrl(x86_pmu_event_addr(idx), 0ull); + wrmsrl_safe(x86_pmu_config_addr(idx), 0ull); + wrmsrl_safe(x86_pmu_event_addr(idx), 0ull); } for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) - checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); + wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); if (ds) ds->bts_index = ds->bts_buffer_base; @@ -1707,16 +1709,61 @@ static __init void intel_clovertown_quirk(void) * But taken together it might just make sense to not enable PEBS on * these chips. */ - printk(KERN_WARNING "PEBS disabled due to CPU errata.\n"); + pr_warn("PEBS disabled due to CPU errata\n"); x86_pmu.pebs = 0; x86_pmu.pebs_constraints = NULL; } +static int intel_snb_pebs_broken(int cpu) +{ + u32 rev = UINT_MAX; /* default to broken for unknown models */ + + switch (cpu_data(cpu).x86_model) { + case 42: /* SNB */ + rev = 0x28; + break; + + case 45: /* SNB-EP */ + switch (cpu_data(cpu).x86_mask) { + case 6: rev = 0x618; break; + case 7: rev = 0x70c; break; + } + } + + return (cpu_data(cpu).microcode < rev); +} + +static void intel_snb_check_microcode(void) +{ + int pebs_broken = 0; + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + if ((pebs_broken = intel_snb_pebs_broken(cpu))) + break; + } + put_online_cpus(); + + if (pebs_broken == x86_pmu.pebs_broken) + return; + + /* + * Serialized by the microcode lock.. + */ + if (x86_pmu.pebs_broken) { + pr_info("PEBS enabled due to microcode update\n"); + x86_pmu.pebs_broken = 0; + } else { + pr_info("PEBS disabled due to CPU errata, please upgrade microcode\n"); + x86_pmu.pebs_broken = 1; + } +} + static __init void intel_sandybridge_quirk(void) { - printk(KERN_WARNING "PEBS disabled due to CPU errata.\n"); - x86_pmu.pebs = 0; - x86_pmu.pebs_constraints = NULL; + x86_pmu.check_microcode = intel_snb_check_microcode; + intel_snb_check_microcode(); } static const struct { int id; char *name; } intel_arch_events_map[] __initconst = { @@ -1736,8 +1783,8 @@ static __init void intel_arch_events_quirk(void) /* disable event that reported as not presend by cpuid */ for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) { intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0; - printk(KERN_WARNING "CPUID marked event: \'%s\' unavailable\n", - intel_arch_events_map[bit].name); + pr_warn("CPUID marked event: \'%s\' unavailable\n", + intel_arch_events_map[bit].name); } } @@ -1756,7 +1803,7 @@ static __init void intel_nehalem_quirk(void) intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89; ebx.split.no_branch_misses_retired = 0; x86_pmu.events_maskl = ebx.full; - printk(KERN_INFO "CPU erratum AAJ80 worked around\n"); + pr_info("CPU erratum AAJ80 worked around\n"); } } @@ -1765,6 +1812,7 @@ __init int intel_pmu_init(void) union cpuid10_edx edx; union cpuid10_eax eax; union cpuid10_ebx ebx; + struct event_constraint *c; unsigned int unused; int version; @@ -1800,6 +1848,8 @@ __init int intel_pmu_init(void) x86_pmu.events_maskl = ebx.full; x86_pmu.events_mask_len = eax.split.mask_length; + x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events: @@ -1951,5 +2001,37 @@ __init int intel_pmu_init(void) } } + if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) { + WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", + x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC; + } + x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + + if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) { + WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", + x86_pmu.num_counters_fixed, INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED; + } + + x86_pmu.intel_ctrl |= + ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + + if (x86_pmu.event_constraints) { + /* + * event on fixed counter2 (REF_CYCLES) only works on this + * counter, so do not extend mask to generic counters + */ + for_each_event_constraint(c, x86_pmu.event_constraints) { + if (c->cmask != X86_RAW_EVENT_MASK + || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { + continue; + } + + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; + c->weight += x86_pmu.num_counters; + } + } + return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 35e2192df9f..629ae0b7ad9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -248,7 +248,7 @@ void reserve_ds_buffers(void) */ struct event_constraint bts_constraint = - EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); + EVENT_CONSTRAINT(0, 1ULL << INTEL_PMC_IDX_FIXED_BTS, 0); void intel_pmu_enable_bts(u64 config) { @@ -295,7 +295,7 @@ int intel_pmu_drain_bts_buffer(void) u64 to; u64 flags; }; - struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; + struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS]; struct bts_record *at, *top; struct perf_output_handle handle; struct perf_event_header header; @@ -620,7 +620,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) * Should not happen, we program the threshold at 1 and do not * set a reset value. */ - WARN_ON_ONCE(n > 1); + WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); at += n - 1; __intel_pmu_pebs_event(event, iregs, at); @@ -651,10 +651,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * Should not happen, we program the threshold at 1 and do not * set a reset value. */ - WARN_ON_ONCE(n > MAX_PEBS_EVENTS); + WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n); for ( ; at < top; at++) { - for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) { + for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) { event = cpuc->events[bit]; if (!test_bit(bit, cpuc->active_mask)) continue; @@ -670,7 +670,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) break; } - if (!event || bit >= MAX_PEBS_EVENTS) + if (!event || bit >= x86_pmu.max_pebs_events) continue; __intel_pmu_pebs_event(event, iregs, at); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c new file mode 100644 index 00000000000..19faffc6088 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -0,0 +1,1850 @@ +#include "perf_event_intel_uncore.h" + +static struct intel_uncore_type *empty_uncore[] = { NULL, }; +static struct intel_uncore_type **msr_uncores = empty_uncore; +static struct intel_uncore_type **pci_uncores = empty_uncore; +/* pci bus to socket mapping */ +static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; + +static DEFINE_RAW_SPINLOCK(uncore_box_lock); + +/* mask of cpus that collect uncore events */ +static cpumask_t uncore_cpu_mask; + +/* constraint for the fixed counter */ +static struct event_constraint constraint_fixed = + EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); +static struct event_constraint constraint_empty = + EVENT_CONSTRAINT(0, 0, 0); + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); +DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand0, filter_brand0, "config1:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand1, filter_brand1, "config1:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand2, filter_brand2, "config1:16-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand3, filter_brand3, "config1:24-31"); + +/* Sandy Bridge-EP uncore support */ +static struct intel_uncore_type snbep_uncore_cbox; +static struct intel_uncore_type snbep_uncore_pcu; + +static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config; + + pci_read_config_dword(pdev, box_ctl, &config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); +} + +static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config; + + pci_read_config_dword(pdev, box_ctl, &config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); +} + +static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | + SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count; + + pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); + pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); + return count; +} + +static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, + SNBEP_PMON_BOX_CTL_INT); +} + +static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + return; + } +} + +static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + return; + } +} + +static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, reg1->config); + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_msr_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 count; + + rdmsrl(hwc->event_base, count); + return count; +} + +static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); +} + +static struct event_constraint * +snbep_uncore_get_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + unsigned long flags; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || (box->phys_id >= 0 && reg1->alloc)) + return NULL; + + er = &box->shared_regs[reg1->idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || er->config1 == reg1->config) { + atomic_inc(&er->ref); + er->config1 = reg1->config; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (ok) { + if (box->phys_id >= 0) + reg1->alloc = 1; + return NULL; + } + return &constraint_empty; +} + +static void snbep_uncore_put_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + + if (box->phys_id < 0 || !reg1->alloc) + return; + + er = &box->shared_regs[reg1->idx]; + atomic_dec(&er->ref); + reg1->alloc = 0; +} + +static int snbep_uncore_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (box->pmu->type == &snbep_uncore_cbox) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & + SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK; + } else if (box->pmu->type == &snbep_uncore_pcu) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->config = event->attr.config1 & + SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK; + } else { + return 0; + } + reg1->idx = 0; + return 0; +} + +static struct attribute *snbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *snbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *snbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_nid.attr, + &format_attr_filter_state.attr, + &format_attr_filter_opc.attr, + NULL, +}; + +static struct attribute *snbep_uncore_pcu_formats_attr[] = { + &format_attr_event.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_brand0.attr, + &format_attr_filter_brand1.attr, + &format_attr_filter_brand2.attr, + &format_attr_filter_brand3.attr, + NULL, +}; + +static struct uncore_event_desc snbep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc snbep_uncore_qpi_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), + INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"), + { /* end: all zeroes */ }, +}; + +static struct attribute_group snbep_uncore_format_group = { + .name = "format", + .attrs = snbep_uncore_formats_attr, +}; + +static struct attribute_group snbep_uncore_ubox_format_group = { + .name = "format", + .attrs = snbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group snbep_uncore_cbox_format_group = { + .name = "format", + .attrs = snbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group snbep_uncore_pcu_format_group = { + .name = "format", + .attrs = snbep_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_ops snbep_uncore_msr_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = snbep_uncore_msr_enable_event, + .read_counter = snbep_uncore_msr_read_counter, + .get_constraint = snbep_uncore_get_constraint, + .put_constraint = snbep_uncore_put_constraint, + .hw_config = snbep_uncore_hw_config, +}; + +static struct intel_uncore_ops snbep_uncore_pci_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +static struct event_constraint snbep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x04, 0x3), + UNCORE_EVENT_CONSTRAINT(0x05, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), + EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x30, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_ubox_format_group, +}; + +static struct intel_uncore_type snbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_cbox_format_group, +}; + +static struct intel_uncore_type snbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *snbep_msr_uncores[] = { + &snbep_uncore_ubox, + &snbep_uncore_cbox, + &snbep_uncore_pcu, + NULL, +}; + +#define SNBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &snbep_uncore_pci_ops, \ + .format_group = &snbep_uncore_format_group + +static struct intel_uncore_type snbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_descs = snbep_uncore_qpi_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + + +static struct intel_uncore_type snbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type *snbep_pci_uncores[] = { + &snbep_uncore_ha, + &snbep_uncore_imc, + &snbep_uncore_qpi, + &snbep_uncore_r2pcie, + &snbep_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { + { /* Home Agent */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), + .driver_data = (unsigned long)&snbep_uncore_ha, + }, + { /* MC Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* MC Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* MC Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* MC Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* QPI Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), + .driver_data = (unsigned long)&snbep_uncore_qpi, + }, + { /* QPI Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), + .driver_data = (unsigned long)&snbep_uncore_qpi, + }, + { /* P2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), + .driver_data = (unsigned long)&snbep_uncore_r2pcie, + }, + { /* R3QPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), + .driver_data = (unsigned long)&snbep_uncore_r3qpi, + }, + { /* R3QPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), + .driver_data = (unsigned long)&snbep_uncore_r3qpi, + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver snbep_uncore_pci_driver = { + .name = "snbep_uncore", + .id_table = snbep_uncore_pci_ids, +}; + +/* + * build pci bus to socket mapping + */ +static void snbep_pci2phy_map_init(void) +{ + struct pci_dev *ubox_dev = NULL; + int i, bus, nodeid; + u32 config; + + while (1) { + /* find the UBOX device */ + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX, + ubox_dev); + if (!ubox_dev) + break; + bus = ubox_dev->bus->number; + /* get the Node ID of the local register */ + pci_read_config_dword(ubox_dev, 0x40, &config); + nodeid = config; + /* get the Node ID mapping */ + pci_read_config_dword(ubox_dev, 0x54, &config); + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == ((config >> (3 * i)) & 0x7)) { + pcibus_to_physid[bus] = i; + break; + } + } + }; + return; +} +/* end of Sandy Bridge-EP uncore support */ + + +/* Sandy Bridge uncore support */ +static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); +} + +static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static u64 snb_uncore_msr_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + u64 count; + rdmsrl(event->hw.event_base, count); + return count; +} + +static void snb_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) { + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); + } +} + +static struct attribute *snb_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask5.attr, + NULL, +}; + +static struct attribute_group snb_uncore_format_group = { + .name = "format", + .attrs = snb_uncore_formats_attr, +}; + +static struct intel_uncore_ops snb_uncore_msr_ops = { + .init_box = snb_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = snb_uncore_msr_read_counter, +}; + +static struct event_constraint snb_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x80, 0x1), + UNCORE_EVENT_CONSTRAINT(0x83, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snb_uncore_cbox = { + .name = "cbox", + .num_counters = 2, + .num_boxes = 4, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .constraints = snb_uncore_cbox_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + +static struct intel_uncore_type *snb_msr_uncores[] = { + &snb_uncore_cbox, + NULL, +}; +/* end of Sandy Bridge uncore support */ + +/* Nehalem uncore support */ +static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); +} + +static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, + NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); +} + +static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *nhm_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group nhm_uncore_format_group = { + .name = "format", + .attrs = nhm_uncore_formats_attr, +}; + +static struct uncore_event_desc nhm_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhm_uncore_msr_ops = { + .disable_box = nhm_uncore_msr_disable_box, + .enable_box = nhm_uncore_msr_enable_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = nhm_uncore_msr_enable_event, + .read_counter = snb_uncore_msr_read_counter, +}; + +static struct intel_uncore_type nhm_uncore = { + .name = "", + .num_counters = 8, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = NHM_UNC_PERFEVTSEL0, + .perf_ctr = NHM_UNC_UNCORE_PMC0, + .fixed_ctr = NHM_UNC_FIXED_CTR, + .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, + .event_mask = NHM_UNC_RAW_EVENT_MASK, + .event_descs = nhm_uncore_events, + .ops = &nhm_uncore_msr_ops, + .format_group = &nhm_uncore_format_group, +}; + +static struct intel_uncore_type *nhm_msr_uncores[] = { + &nhm_uncore, + NULL, +}; +/* end of Nehalem uncore support */ + +static void uncore_assign_hw_event(struct intel_uncore_box *box, + struct perf_event *event, int idx) +{ + struct hw_perf_event *hwc = &event->hw; + + hwc->idx = idx; + hwc->last_tag = ++box->tags[idx]; + + if (hwc->idx == UNCORE_PMC_IDX_FIXED) { + hwc->event_base = uncore_fixed_ctr(box); + hwc->config_base = uncore_fixed_ctl(box); + return; + } + + hwc->config_base = uncore_event_ctl(box, hwc->idx); + hwc->event_base = uncore_perf_ctr(box, hwc->idx); +} + +static void uncore_perf_event_update(struct intel_uncore_box *box, + struct perf_event *event) +{ + u64 prev_count, new_count, delta; + int shift; + + if (event->hw.idx >= UNCORE_PMC_IDX_FIXED) + shift = 64 - uncore_fixed_ctr_bits(box); + else + shift = 64 - uncore_perf_ctr_bits(box); + + /* the hrtimer might modify the previous event value */ +again: + prev_count = local64_read(&event->hw.prev_count); + new_count = uncore_read_counter(box, event); + if (local64_xchg(&event->hw.prev_count, new_count) != prev_count) + goto again; + + delta = (new_count << shift) - (prev_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); +} + +/* + * The overflow interrupt is unavailable for SandyBridge-EP, is broken + * for SandyBridge. So we use hrtimer to periodically poll the counter + * to avoid overflow. + */ +static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) +{ + struct intel_uncore_box *box; + unsigned long flags; + int bit; + + box = container_of(hrtimer, struct intel_uncore_box, hrtimer); + if (!box->n_active || box->cpu != smp_processor_id()) + return HRTIMER_NORESTART; + /* + * disable local interrupt to prevent uncore_pmu_event_start/stop + * to interrupt the update process + */ + local_irq_save(flags); + + for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX) + uncore_perf_event_update(box, box->events[bit]); + + local_irq_restore(flags); + + hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL)); + return HRTIMER_RESTART; +} + +static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) +{ + __hrtimer_start_range_ns(&box->hrtimer, + ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) +{ + hrtimer_cancel(&box->hrtimer); +} + +static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) +{ + hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + box->hrtimer.function = uncore_pmu_hrtimer; +} + +struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, + int cpu) +{ + struct intel_uncore_box *box; + int i, size; + + size = sizeof(*box) + type->num_shared_regs * + sizeof(struct intel_uncore_extra_reg); + + box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); + if (!box) + return NULL; + + for (i = 0; i < type->num_shared_regs; i++) + raw_spin_lock_init(&box->shared_regs[i].lock); + + uncore_pmu_init_hrtimer(box); + atomic_set(&box->refcnt, 1); + box->cpu = -1; + box->phys_id = -1; + + return box; +} + +static struct intel_uncore_box * +uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) +{ + static struct intel_uncore_box *box; + + box = *per_cpu_ptr(pmu->box, cpu); + if (box) + return box; + + raw_spin_lock(&uncore_box_lock); + list_for_each_entry(box, &pmu->box_list, list) { + if (box->phys_id == topology_physical_package_id(cpu)) { + atomic_inc(&box->refcnt); + *per_cpu_ptr(pmu->box, cpu) = box; + break; + } + } + raw_spin_unlock(&uncore_box_lock); + + return *per_cpu_ptr(pmu->box, cpu); +} + +static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct intel_uncore_pmu, pmu); +} + +static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + /* + * perf core schedules event on the basis of cpu, uncore events are + * collected by one of the cpus inside a physical package. + */ + return uncore_pmu_to_box(uncore_event_to_pmu(event), + smp_processor_id()); +} + +static int uncore_collect_events(struct intel_uncore_box *box, + struct perf_event *leader, bool dogrp) +{ + struct perf_event *event; + int n, max_count; + + max_count = box->pmu->type->num_counters; + if (box->pmu->type->fixed_ctl) + max_count++; + + if (box->n_events >= max_count) + return -EINVAL; + + n = box->n_events; + box->event_list[n] = leader; + n++; + if (!dogrp) + return n; + + list_for_each_entry(event, &leader->sibling_list, group_entry) { + if (event->state <= PERF_EVENT_STATE_OFF) + continue; + + if (n >= max_count) + return -EINVAL; + + box->event_list[n] = event; + n++; + } + return n; +} + +static struct event_constraint * +uncore_get_event_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct intel_uncore_type *type = box->pmu->type; + struct event_constraint *c; + + if (type->ops->get_constraint) { + c = type->ops->get_constraint(box, event); + if (c) + return c; + } + + if (event->hw.config == ~0ULL) + return &constraint_fixed; + + if (type->constraints) { + for_each_event_constraint(c, type->constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &type->unconstrainted; +} + +static void uncore_put_event_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + if (box->pmu->type->ops->put_constraint) + box->pmu->type->ops->put_constraint(box, event); +} + +static int uncore_assign_events(struct intel_uncore_box *box, + int assign[], int n) +{ + unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX]; + int i, wmin, wmax, ret = 0; + struct hw_perf_event *hwc; + + bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); + + for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { + c = uncore_get_event_constraint(box, box->event_list[i]); + constraints[i] = c; + wmin = min(wmin, c->weight); + wmax = max(wmax, c->weight); + } + + /* fastpath, try to reuse previous register */ + for (i = 0; i < n; i++) { + hwc = &box->event_list[i]->hw; + c = constraints[i]; + + /* never assigned */ + if (hwc->idx == -1) + break; + + /* constraint still honored */ + if (!test_bit(hwc->idx, c->idxmsk)) + break; + + /* not already used */ + if (test_bit(hwc->idx, used_mask)) + break; + + __set_bit(hwc->idx, used_mask); + if (assign) + assign[i] = hwc->idx; + } + /* slow path */ + if (i != n) + ret = perf_assign_events(constraints, n, wmin, wmax, assign); + + if (!assign || ret) { + for (i = 0; i < n; i++) + uncore_put_event_constraint(box, box->event_list[i]); + } + return ret ? -EINVAL : 0; +} + +static void uncore_pmu_event_start(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int idx = event->hw.idx; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX)) + return; + + event->hw.state = 0; + box->events[idx] = event; + box->n_active++; + __set_bit(idx, box->active_mask); + + local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); + uncore_enable_event(box, event); + + if (box->n_active == 1) { + uncore_enable_box(box); + uncore_pmu_start_hrtimer(box); + } +} + +static void uncore_pmu_event_stop(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (__test_and_clear_bit(hwc->idx, box->active_mask)) { + uncore_disable_event(box, event); + box->n_active--; + box->events[hwc->idx] = NULL; + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (box->n_active == 0) { + uncore_disable_box(box); + uncore_pmu_cancel_hrtimer(box); + } + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int uncore_pmu_event_add(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + int assign[UNCORE_PMC_IDX_MAX]; + int i, n, ret; + + if (!box) + return -ENODEV; + + ret = n = uncore_collect_events(box, event, false); + if (ret < 0) + return ret; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + ret = uncore_assign_events(box, assign, n); + if (ret) + return ret; + + /* save events moving to new counters */ + for (i = 0; i < box->n_events; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx == assign[i] && + hwc->last_tag == box->tags[assign[i]]) + continue; + /* + * Ensure we don't accidentally enable a stopped + * counter simply because we rescheduled. + */ + if (hwc->state & PERF_HES_STOPPED) + hwc->state |= PERF_HES_ARCH; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + } + + /* reprogram moved events into new counters */ + for (i = 0; i < n; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx != assign[i] || + hwc->last_tag != box->tags[assign[i]]) + uncore_assign_hw_event(box, event, assign[i]); + else if (i < box->n_events) + continue; + + if (hwc->state & PERF_HES_ARCH) + continue; + + uncore_pmu_event_start(event, 0); + } + box->n_events = n; + + return 0; +} + +static void uncore_pmu_event_del(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int i; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + uncore_put_event_constraint(box, event); + + while (++i < box->n_events) + box->event_list[i - 1] = box->event_list[i]; + + --box->n_events; + break; + } + } + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; +} + +static void uncore_pmu_event_read(struct perf_event *event) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + uncore_perf_event_update(box, event); +} + +/* + * validation ensures the group can be loaded onto the + * PMU if it was the only group available. + */ +static int uncore_validate_group(struct intel_uncore_pmu *pmu, + struct perf_event *event) +{ + struct perf_event *leader = event->group_leader; + struct intel_uncore_box *fake_box; + int ret = -EINVAL, n; + + fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + if (!fake_box) + return -ENOMEM; + + fake_box->pmu = pmu; + /* + * the event is not yet connected with its + * siblings therefore we must first collect + * existing siblings, then add the new event + * before we can simulate the scheduling + */ + n = uncore_collect_events(fake_box, leader, true); + if (n < 0) + goto out; + + fake_box->n_events = n; + n = uncore_collect_events(fake_box, event, false); + if (n < 0) + goto out; + + fake_box->n_events = n; + + ret = uncore_assign_events(fake_box, NULL, n); +out: + kfree(fake_box); + return ret; +} + +int uncore_pmu_event_init(struct perf_event *event) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + int ret; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* + * Uncore PMU does measure at all privilege level all the time. + * So it doesn't make sense to specify any exclude bits. + */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_hv || event->attr.exclude_idle) + return -EINVAL; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + event->cpu = box->cpu; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + + if (event->attr.config == UNCORE_FIXED_EVENT) { + /* no fixed counter */ + if (!pmu->type->fixed_ctl) + return -EINVAL; + /* + * if there is only one fixed counter, only the first pmu + * can access the fixed counter + */ + if (pmu->type->single_fixed && pmu->pmu_idx > 0) + return -EINVAL; + hwc->config = ~0ULL; + } else { + hwc->config = event->attr.config & pmu->type->event_mask; + if (pmu->type->ops->hw_config) { + ret = pmu->type->ops->hw_config(box, event); + if (ret) + return ret; + } + } + + if (event->group_leader != event) + ret = uncore_validate_group(pmu, event); + else + ret = 0; + + return ret; +} + +static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) +{ + int ret; + + pmu->pmu = (struct pmu) { + .attr_groups = pmu->type->attr_groups, + .task_ctx_nr = perf_invalid_context, + .event_init = uncore_pmu_event_init, + .add = uncore_pmu_event_add, + .del = uncore_pmu_event_del, + .start = uncore_pmu_event_start, + .stop = uncore_pmu_event_stop, + .read = uncore_pmu_event_read, + }; + + if (pmu->type->num_boxes == 1) { + if (strlen(pmu->type->name) > 0) + sprintf(pmu->name, "uncore_%s", pmu->type->name); + else + sprintf(pmu->name, "uncore"); + } else { + sprintf(pmu->name, "uncore_%s_%d", pmu->type->name, + pmu->pmu_idx); + } + + ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); + return ret; +} + +static void __init uncore_type_exit(struct intel_uncore_type *type) +{ + int i; + + for (i = 0; i < type->num_boxes; i++) + free_percpu(type->pmus[i].box); + kfree(type->pmus); + type->pmus = NULL; + kfree(type->attr_groups[1]); + type->attr_groups[1] = NULL; +} + +static void uncore_types_exit(struct intel_uncore_type **types) +{ + int i; + for (i = 0; types[i]; i++) + uncore_type_exit(types[i]); +} + +static int __init uncore_type_init(struct intel_uncore_type *type) +{ + struct intel_uncore_pmu *pmus; + struct attribute_group *events_group; + struct attribute **attrs; + int i, j; + + pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL); + if (!pmus) + return -ENOMEM; + + type->unconstrainted = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, + 0, type->num_counters, 0); + + for (i = 0; i < type->num_boxes; i++) { + pmus[i].func_id = -1; + pmus[i].pmu_idx = i; + pmus[i].type = type; + INIT_LIST_HEAD(&pmus[i].box_list); + pmus[i].box = alloc_percpu(struct intel_uncore_box *); + if (!pmus[i].box) + goto fail; + } + + if (type->event_descs) { + i = 0; + while (type->event_descs[i].attr.attr.name) + i++; + + events_group = kzalloc(sizeof(struct attribute *) * (i + 1) + + sizeof(*events_group), GFP_KERNEL); + if (!events_group) + goto fail; + + attrs = (struct attribute **)(events_group + 1); + events_group->name = "events"; + events_group->attrs = attrs; + + for (j = 0; j < i; j++) + attrs[j] = &type->event_descs[j].attr.attr; + + type->attr_groups[1] = events_group; + } + + type->pmus = pmus; + return 0; +fail: + uncore_type_exit(type); + return -ENOMEM; +} + +static int __init uncore_types_init(struct intel_uncore_type **types) +{ + int i, ret; + + for (i = 0; types[i]; i++) { + ret = uncore_type_init(types[i]); + if (ret) + goto fail; + } + return 0; +fail: + while (--i >= 0) + uncore_type_exit(types[i]); + return ret; +} + +static struct pci_driver *uncore_pci_driver; +static bool pcidrv_registered; + +/* + * add a pci uncore device + */ +static int __devinit uncore_pci_add(struct intel_uncore_type *type, + struct pci_dev *pdev) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, phys_id; + + phys_id = pcibus_to_physid[pdev->bus->number]; + if (phys_id < 0) + return -ENODEV; + + box = uncore_alloc_box(type, 0); + if (!box) + return -ENOMEM; + + /* + * for performance monitoring unit with multiple boxes, + * each box has a different function id. + */ + for (i = 0; i < type->num_boxes; i++) { + pmu = &type->pmus[i]; + if (pmu->func_id == pdev->devfn) + break; + if (pmu->func_id < 0) { + pmu->func_id = pdev->devfn; + break; + } + pmu = NULL; + } + + if (!pmu) { + kfree(box); + return -EINVAL; + } + + box->phys_id = phys_id; + box->pci_dev = pdev; + box->pmu = pmu; + uncore_box_init(box); + pci_set_drvdata(pdev, box); + + raw_spin_lock(&uncore_box_lock); + list_add_tail(&box->list, &pmu->box_list); + raw_spin_unlock(&uncore_box_lock); + + return 0; +} + +static void uncore_pci_remove(struct pci_dev *pdev) +{ + struct intel_uncore_box *box = pci_get_drvdata(pdev); + struct intel_uncore_pmu *pmu = box->pmu; + int cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + + if (WARN_ON_ONCE(phys_id != box->phys_id)) + return; + + raw_spin_lock(&uncore_box_lock); + list_del(&box->list); + raw_spin_unlock(&uncore_box_lock); + + for_each_possible_cpu(cpu) { + if (*per_cpu_ptr(pmu->box, cpu) == box) { + *per_cpu_ptr(pmu->box, cpu) = NULL; + atomic_dec(&box->refcnt); + } + } + + WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); + kfree(box); +} + +static int __devinit uncore_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct intel_uncore_type *type; + + type = (struct intel_uncore_type *)id->driver_data; + return uncore_pci_add(type, pdev); +} + +static int __init uncore_pci_init(void) +{ + int ret; + + switch (boot_cpu_data.x86_model) { + case 45: /* Sandy Bridge-EP */ + pci_uncores = snbep_pci_uncores; + uncore_pci_driver = &snbep_uncore_pci_driver; + snbep_pci2phy_map_init(); + break; + default: + return 0; + } + + ret = uncore_types_init(pci_uncores); + if (ret) + return ret; + + uncore_pci_driver->probe = uncore_pci_probe; + uncore_pci_driver->remove = uncore_pci_remove; + + ret = pci_register_driver(uncore_pci_driver); + if (ret == 0) + pcidrv_registered = true; + else + uncore_types_exit(pci_uncores); + + return ret; +} + +static void __init uncore_pci_exit(void) +{ + if (pcidrv_registered) { + pcidrv_registered = false; + pci_unregister_driver(uncore_pci_driver); + uncore_types_exit(pci_uncores); + } +} + +static void __cpuinit uncore_cpu_dying(int cpu) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, j; + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + box = *per_cpu_ptr(pmu->box, cpu); + *per_cpu_ptr(pmu->box, cpu) = NULL; + if (box && atomic_dec_and_test(&box->refcnt)) + kfree(box); + } + } +} + +static int __cpuinit uncore_cpu_starting(int cpu) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box, *exist; + int i, j, k, phys_id; + + phys_id = topology_physical_package_id(cpu); + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + box = *per_cpu_ptr(pmu->box, cpu); + /* called by uncore_cpu_init? */ + if (box && box->phys_id >= 0) { + uncore_box_init(box); + continue; + } + + for_each_online_cpu(k) { + exist = *per_cpu_ptr(pmu->box, k); + if (exist && exist->phys_id == phys_id) { + atomic_inc(&exist->refcnt); + *per_cpu_ptr(pmu->box, cpu) = exist; + kfree(box); + box = NULL; + break; + } + } + + if (box) { + box->phys_id = phys_id; + uncore_box_init(box); + } + } + } + return 0; +} + +static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, j; + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + if (pmu->func_id < 0) + pmu->func_id = j; + + box = uncore_alloc_box(type, cpu); + if (!box) + return -ENOMEM; + + box->pmu = pmu; + box->phys_id = phys_id; + *per_cpu_ptr(pmu->box, cpu) = box; + } + } + return 0; +} + +static void __cpuinit uncore_change_context(struct intel_uncore_type **uncores, + int old_cpu, int new_cpu) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, j; + + for (i = 0; uncores[i]; i++) { + type = uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + if (old_cpu < 0) + box = uncore_pmu_to_box(pmu, new_cpu); + else + box = uncore_pmu_to_box(pmu, old_cpu); + if (!box) + continue; + + if (old_cpu < 0) { + WARN_ON_ONCE(box->cpu != -1); + box->cpu = new_cpu; + continue; + } + + WARN_ON_ONCE(box->cpu != old_cpu); + if (new_cpu >= 0) { + uncore_pmu_cancel_hrtimer(box); + perf_pmu_migrate_context(&pmu->pmu, + old_cpu, new_cpu); + box->cpu = new_cpu; + } else { + box->cpu = -1; + } + } + } +} + +static void __cpuinit uncore_event_exit_cpu(int cpu) +{ + int i, phys_id, target; + + /* if exiting cpu is used for collecting uncore events */ + if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) + return; + + /* find a new cpu to collect uncore events */ + phys_id = topology_physical_package_id(cpu); + target = -1; + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (phys_id == topology_physical_package_id(i)) { + target = i; + break; + } + } + + /* migrate uncore events to the new cpu */ + if (target >= 0) + cpumask_set_cpu(target, &uncore_cpu_mask); + + uncore_change_context(msr_uncores, cpu, target); + uncore_change_context(pci_uncores, cpu, target); +} + +static void __cpuinit uncore_event_init_cpu(int cpu) +{ + int i, phys_id; + + phys_id = topology_physical_package_id(cpu); + for_each_cpu(i, &uncore_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) + return; + } + + cpumask_set_cpu(cpu, &uncore_cpu_mask); + + uncore_change_context(msr_uncores, -1, cpu); + uncore_change_context(pci_uncores, -1, cpu); +} + +static int __cpuinit uncore_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + /* allocate/free data structure for uncore box */ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + uncore_cpu_prepare(cpu, -1); + break; + case CPU_STARTING: + uncore_cpu_starting(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + uncore_cpu_dying(cpu); + break; + default: + break; + } + + /* select the cpu that collects uncore events */ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_FAILED: + case CPU_STARTING: + uncore_event_init_cpu(cpu); + break; + case CPU_DOWN_PREPARE: + uncore_event_exit_cpu(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block uncore_cpu_nb __cpuinitdata = { + .notifier_call = uncore_cpu_notifier, + /* + * to migrate uncore events, our notifier should be executed + * before perf core's notifier. + */ + .priority = CPU_PRI_PERF + 1, +}; + +static void __init uncore_cpu_setup(void *dummy) +{ + uncore_cpu_starting(smp_processor_id()); +} + +static int __init uncore_cpu_init(void) +{ + int ret, cpu, max_cores; + + max_cores = boot_cpu_data.x86_max_cores; + switch (boot_cpu_data.x86_model) { + case 26: /* Nehalem */ + case 30: + case 37: /* Westmere */ + case 44: + msr_uncores = nhm_msr_uncores; + break; + case 42: /* Sandy Bridge */ + if (snb_uncore_cbox.num_boxes > max_cores) + snb_uncore_cbox.num_boxes = max_cores; + msr_uncores = snb_msr_uncores; + break; + case 45: /* Sandy Birdge-EP */ + if (snbep_uncore_cbox.num_boxes > max_cores) + snbep_uncore_cbox.num_boxes = max_cores; + msr_uncores = snbep_msr_uncores; + break; + default: + return 0; + } + + ret = uncore_types_init(msr_uncores); + if (ret) + return ret; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + int i, phys_id = topology_physical_package_id(cpu); + + for_each_cpu(i, &uncore_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) { + phys_id = -1; + break; + } + } + if (phys_id < 0) + continue; + + uncore_cpu_prepare(cpu, phys_id); + uncore_event_init_cpu(cpu); + } + on_each_cpu(uncore_cpu_setup, NULL, 1); + + register_cpu_notifier(&uncore_cpu_nb); + + put_online_cpus(); + + return 0; +} + +static int __init uncore_pmus_register(void) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_type *type; + int i, j; + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + uncore_pmu_register(pmu); + } + } + + for (i = 0; pci_uncores[i]; i++) { + type = pci_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + uncore_pmu_register(pmu); + } + } + + return 0; +} + +static int __init intel_uncore_init(void) +{ + int ret; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -ENODEV; + + ret = uncore_pci_init(); + if (ret) + goto fail; + ret = uncore_cpu_init(); + if (ret) { + uncore_pci_exit(); + goto fail; + } + + uncore_pmus_register(); + return 0; +fail: + return ret; +} +device_initcall(intel_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h new file mode 100644 index 00000000000..b13e9ea81de --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -0,0 +1,424 @@ +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/perf_event.h> +#include "perf_event.h" + +#define UNCORE_PMU_NAME_LEN 32 +#define UNCORE_BOX_HASH_SIZE 8 + +#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC) + +#define UNCORE_FIXED_EVENT 0xff +#define UNCORE_PMC_IDX_MAX_GENERIC 8 +#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC +#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) + +#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) + +/* SNB event control */ +#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff +#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 +#define SNB_UNC_CTL_EDGE_DET (1 << 18) +#define SNB_UNC_CTL_EN (1 << 22) +#define SNB_UNC_CTL_INVERT (1 << 23) +#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 +#define NHM_UNC_CTL_CMASK_MASK 0xff000000 +#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + SNB_UNC_CTL_CMASK_MASK) + +#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + NHM_UNC_CTL_CMASK_MASK) + +/* SNB global control register */ +#define SNB_UNC_PERF_GLOBAL_CTL 0x391 +#define SNB_UNC_FIXED_CTR_CTRL 0x394 +#define SNB_UNC_FIXED_CTR 0x395 + +/* SNB uncore global control */ +#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) +#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) + +/* SNB Cbo register */ +#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 +#define SNB_UNC_CBO_0_PER_CTR0 0x706 +#define SNB_UNC_CBO_MSR_OFFSET 0x10 + +/* NHM global control register */ +#define NHM_UNC_PERF_GLOBAL_CTL 0x391 +#define NHM_UNC_FIXED_CTR 0x394 +#define NHM_UNC_FIXED_CTR_CTRL 0x395 + +/* NHM uncore global control */ +#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) +#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* NHM uncore register */ +#define NHM_UNC_PERFEVTSEL0 0x3c0 +#define NHM_UNC_UNCORE_PMC0 0x3b0 + +/* SNB-EP Box level control */ +#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) +#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) +#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) +#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) +#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS | \ + SNBEP_PMON_BOX_CTL_FRZ_EN) +/* SNB-EP event control */ +#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff +#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 +#define SNBEP_PMON_CTL_RST (1 << 17) +#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) /* only for QPI */ +#define SNBEP_PMON_CTL_EN (1 << 22) +#define SNBEP_PMON_CTL_INVERT (1 << 23) +#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 +#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PMON_CTL_TRESH_MASK) + +/* SNB-EP Ubox event control */ +#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) + +#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) +#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* SNB-EP PCU event control */ +#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 +#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) +#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) +#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) + +/* SNB-EP pci control register */ +#define SNBEP_PCI_PMON_BOX_CTL 0xf4 +#define SNBEP_PCI_PMON_CTL0 0xd8 +/* SNB-EP pci counter register */ +#define SNBEP_PCI_PMON_CTR0 0xa0 + +/* SNB-EP home agent register */ +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 +#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 +/* SNB-EP memory controller register */ +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 +/* SNB-EP QPI register */ +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c + +/* SNB-EP Ubox register */ +#define SNBEP_U_MSR_PMON_CTR0 0xc16 +#define SNBEP_U_MSR_PMON_CTL0 0xc10 + +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 + +/* SNB-EP Cbo register */ +#define SNBEP_C0_MSR_PMON_CTR0 0xd16 +#define SNBEP_C0_MSR_PMON_CTL0 0xd10 +#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 +#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK 0xfffffc1f +#define SNBEP_CBO_MSR_OFFSET 0x20 + +/* SNB-EP PCU register */ +#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 +#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 +#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff +#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc +#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd + +struct intel_uncore_ops; +struct intel_uncore_pmu; +struct intel_uncore_box; +struct uncore_event_desc; + +struct intel_uncore_type { + const char *name; + int num_counters; + int num_boxes; + int perf_ctr_bits; + int fixed_ctr_bits; + unsigned perf_ctr; + unsigned event_ctl; + unsigned event_mask; + unsigned fixed_ctr; + unsigned fixed_ctl; + unsigned box_ctl; + unsigned msr_offset; + unsigned num_shared_regs:8; + unsigned single_fixed:1; + struct event_constraint unconstrainted; + struct event_constraint *constraints; + struct intel_uncore_pmu *pmus; + struct intel_uncore_ops *ops; + struct uncore_event_desc *event_descs; + const struct attribute_group *attr_groups[3]; +}; + +#define format_group attr_groups[0] + +struct intel_uncore_ops { + void (*init_box)(struct intel_uncore_box *); + void (*disable_box)(struct intel_uncore_box *); + void (*enable_box)(struct intel_uncore_box *); + void (*disable_event)(struct intel_uncore_box *, struct perf_event *); + void (*enable_event)(struct intel_uncore_box *, struct perf_event *); + u64 (*read_counter)(struct intel_uncore_box *, struct perf_event *); + int (*hw_config)(struct intel_uncore_box *, struct perf_event *); + struct event_constraint *(*get_constraint)(struct intel_uncore_box *, + struct perf_event *); + void (*put_constraint)(struct intel_uncore_box *, struct perf_event *); +}; + +struct intel_uncore_pmu { + struct pmu pmu; + char name[UNCORE_PMU_NAME_LEN]; + int pmu_idx; + int func_id; + struct intel_uncore_type *type; + struct intel_uncore_box ** __percpu box; + struct list_head box_list; +}; + +struct intel_uncore_extra_reg { + raw_spinlock_t lock; + u64 config1; + atomic_t ref; +}; + +struct intel_uncore_box { + int phys_id; + int n_active; /* number of active events */ + int n_events; + int cpu; /* cpu to collect events */ + unsigned long flags; + atomic_t refcnt; + struct perf_event *events[UNCORE_PMC_IDX_MAX]; + struct perf_event *event_list[UNCORE_PMC_IDX_MAX]; + unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + u64 tags[UNCORE_PMC_IDX_MAX]; + struct pci_dev *pci_dev; + struct intel_uncore_pmu *pmu; + struct hrtimer hrtimer; + struct list_head list; + struct intel_uncore_extra_reg shared_regs[0]; +}; + +#define UNCORE_BOX_FLAG_INITIATED 0 + +struct uncore_event_desc { + struct kobj_attribute attr; + const char *config; +}; + +#define INTEL_UNCORE_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \ + .config = _config, \ +} + +#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __uncore_##_var##_show, NULL) + + +static ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box) +{ + return box->pmu->type->box_ctl; +} + +static inline unsigned uncore_pci_fixed_ctl(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctl; +} + +static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctr; +} + +static inline +unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx) +{ + return idx * 4 + box->pmu->type->event_ctl; +} + +static inline +unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx) +{ + return idx * 8 + box->pmu->type->perf_ctr; +} + +static inline +unsigned uncore_msr_box_ctl(struct intel_uncore_box *box) +{ + if (!box->pmu->type->box_ctl) + return 0; + return box->pmu->type->box_ctl + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box) +{ + if (!box->pmu->type->fixed_ctl) + return 0; + return box->pmu->type->fixed_ctl + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctr + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) +{ + return idx + box->pmu->type->event_ctl + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) +{ + return idx + box->pmu->type->perf_ctr + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_fixed_ctl(struct intel_uncore_box *box) +{ + if (box->pci_dev) + return uncore_pci_fixed_ctl(box); + else + return uncore_msr_fixed_ctl(box); +} + +static inline +unsigned uncore_fixed_ctr(struct intel_uncore_box *box) +{ + if (box->pci_dev) + return uncore_pci_fixed_ctr(box); + else + return uncore_msr_fixed_ctr(box); +} + +static inline +unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx) +{ + if (box->pci_dev) + return uncore_pci_event_ctl(box, idx); + else + return uncore_msr_event_ctl(box, idx); +} + +static inline +unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx) +{ + if (box->pci_dev) + return uncore_pci_perf_ctr(box, idx); + else + return uncore_msr_perf_ctr(box, idx); +} + +static inline int uncore_perf_ctr_bits(struct intel_uncore_box *box) +{ + return box->pmu->type->perf_ctr_bits; +} + +static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctr_bits; +} + +static inline int uncore_num_counters(struct intel_uncore_box *box) +{ + return box->pmu->type->num_counters; +} + +static inline void uncore_disable_box(struct intel_uncore_box *box) +{ + if (box->pmu->type->ops->disable_box) + box->pmu->type->ops->disable_box(box); +} + +static inline void uncore_enable_box(struct intel_uncore_box *box) +{ + if (box->pmu->type->ops->enable_box) + box->pmu->type->ops->enable_box(box); +} + +static inline void uncore_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->disable_event(box, event); +} + +static inline void uncore_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->enable_event(box, event); +} + +static inline u64 uncore_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + return box->pmu->type->ops->read_counter(box, event); +} + +static inline void uncore_box_init(struct intel_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 47124a73dd7..92c7e39a079 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void) * So at moment let leave metrics turned on forever -- it's * ok for now but need to be revisited! * - * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0); - * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0); + * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0); */ } @@ -909,7 +909,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) * state we need to clear P4_CCCR_OVF, otherwise interrupt get * asserted again and again */ - (void)checking_wrmsrl(hwc->config_base, + (void)wrmsrl_safe(hwc->config_base, (u64)(p4_config_unpack_cccr(hwc->config)) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); } @@ -943,8 +943,8 @@ static void p4_pmu_enable_pebs(u64 config) bind = &p4_pebs_bind_map[idx]; - (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); - (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); + (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); + (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); } static void p4_pmu_enable_event(struct perf_event *event) @@ -978,8 +978,8 @@ static void p4_pmu_enable_event(struct perf_event *event) */ p4_pmu_enable_pebs(hwc->config); - (void)checking_wrmsrl(escr_addr, escr_conf); - (void)checking_wrmsrl(hwc->config_base, + (void)wrmsrl_safe(escr_addr, escr_conf); + (void)wrmsrl_safe(hwc->config_base, (cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE); } @@ -1325,7 +1325,7 @@ __init int p4_pmu_init(void) unsigned int low, high; /* If we get stripped -- indexing fails */ - BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC); + BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC); rdmsr(MSR_IA32_MISC_ENABLE, low, high); if (!(low & (1 << 7))) { diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 32bcfc7dd23..e4dd0f7a045 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -71,7 +71,7 @@ p6_pmu_disable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base, val); + (void)wrmsrl_safe(hwc->config_base, val); } static void p6_pmu_enable_event(struct perf_event *event) @@ -84,7 +84,7 @@ static void p6_pmu_enable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base, val); + (void)wrmsrl_safe(hwc->config_base, val); } PMU_FORMAT_ATTR(event, "config:0-7" ); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 571246d81ed..ae42418bc50 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -27,8 +27,8 @@ static int die_counter; void printk_address(unsigned long address, int reliable) { - printk(" [<%p>] %s%pB\n", (void *) address, - reliable ? "" : "? ", (void *) address); + pr_cont(" [<%p>] %s%pB\n", + (void *)address, reliable ? "" : "? ", (void *)address); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -271,6 +271,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; + print_modules(); show_regs(regs); #ifdef CONFIG_X86_32 if (user_mode_vm(regs)) { diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index e0b1d783daa..1038a417ea5 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -73,11 +73,11 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, if (kstack_end(stack)) break; if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - printk(KERN_CONT "\n"); - printk(KERN_CONT " %08lx", *stack++); + pr_cont("\n"); + pr_cont(" %08lx", *stack++); touch_nmi_watchdog(); } - printk(KERN_CONT "\n"); + pr_cont("\n"); show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -86,12 +86,11 @@ void show_regs(struct pt_regs *regs) { int i; - print_modules(); __show_regs(regs, !user_mode_vm(regs)); - printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", - TASK_COMM_LEN, current->comm, task_pid_nr(current), - current_thread_info(), current, task_thread_info(current)); + pr_emerg("Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", + TASK_COMM_LEN, current->comm, task_pid_nr(current), + current_thread_info(), current, task_thread_info(current)); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. @@ -102,10 +101,10 @@ void show_regs(struct pt_regs *regs) unsigned char c; u8 *ip; - printk(KERN_EMERG "Stack:\n"); + pr_emerg("Stack:\n"); show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); - printk(KERN_EMERG "Code: "); + pr_emerg("Code:"); ip = (u8 *)regs->ip - code_prologue; if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { @@ -116,16 +115,16 @@ void show_regs(struct pt_regs *regs) for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - printk(KERN_CONT " Bad EIP value."); + pr_cont(" Bad EIP value."); break; } if (ip == (u8 *)regs->ip) - printk(KERN_CONT "<%02x> ", c); + pr_cont(" <%02x>", c); else - printk(KERN_CONT "%02x ", c); + pr_cont(" %02x", c); } } - printk(KERN_CONT "\n"); + pr_cont("\n"); } int is_valid_bugaddr(unsigned long ip) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 791b76122aa..b653675d528 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -228,20 +228,20 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, if (stack >= irq_stack && stack <= irq_stack_end) { if (stack == irq_stack_end) { stack = (unsigned long *) (irq_stack_end[-1]); - printk(KERN_CONT " <EOI> "); + pr_cont(" <EOI> "); } } else { if (((long) stack & (THREAD_SIZE-1)) == 0) break; } if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - printk(KERN_CONT "\n"); - printk(KERN_CONT " %016lx", *stack++); + pr_cont("\n"); + pr_cont(" %016lx", *stack++); touch_nmi_watchdog(); } preempt_enable(); - printk(KERN_CONT "\n"); + pr_cont("\n"); show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -254,10 +254,9 @@ void show_regs(struct pt_regs *regs) sp = regs->sp; printk("CPU %d ", cpu); - print_modules(); __show_regs(regs, 1); - printk("Process %s (pid: %d, threadinfo %p, task %p)\n", - cur->comm, cur->pid, task_thread_info(cur), cur); + printk(KERN_DEFAULT "Process %s (pid: %d, threadinfo %p, task %p)\n", + cur->comm, cur->pid, task_thread_info(cur), cur); /* * When in-kernel, we also print out the stack and code at the @@ -284,16 +283,16 @@ void show_regs(struct pt_regs *regs) for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - printk(KERN_CONT " Bad RIP value."); + pr_cont(" Bad RIP value."); break; } if (ip == (u8 *)regs->ip) - printk(KERN_CONT "<%02x> ", c); + pr_cont("<%02x> ", c); else - printk(KERN_CONT "%02x ", c); + pr_cont("%02x ", c); } } - printk(KERN_CONT "\n"); + pr_cont("\n"); } int is_valid_bugaddr(unsigned long ip) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 7d65133b51b..111f6bbd8b3 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1758,10 +1758,30 @@ end_repeat_nmi: */ call save_paranoid DEFAULT_FRAME 0 + + /* + * Save off the CR2 register. If we take a page fault in the NMI then + * it could corrupt the CR2 value. If the NMI preempts a page fault + * handler before it was able to read the CR2 register, and then the + * NMI itself takes a page fault, the page fault that was preempted + * will read the information from the NMI page fault and not the + * origin fault. Save it off and restore it if it changes. + * Use the r12 callee-saved register. + */ + movq %cr2, %r12 + /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi + + /* Did the NMI take a page fault? Restore cr2 if it did */ + movq %cr2, %rcx + cmpq %rcx, %r12 + je 1f + movq %r12, %cr2 +1: + testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 3dafc6003b7..1f5f1d5d2a0 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -294,9 +294,9 @@ void fixup_irqs(void) raw_spin_unlock(&desc->lock); if (break_affinity && set_affinity) - printk("Broke affinity for irq %i\n", irq); + pr_notice("Broke affinity for irq %i\n", irq); else if (!set_affinity) - printk("Cannot set affinity for irq %i\n", irq); + pr_notice("Cannot set affinity for irq %i\n", irq); } /* diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index fbdfc691718..4873e62db6a 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -87,6 +87,7 @@ #include <asm/microcode.h> #include <asm/processor.h> #include <asm/cpu_device_id.h> +#include <asm/perf_event.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -277,7 +278,6 @@ static int reload_for_cpu(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; int err = 0; - mutex_lock(µcode_mutex); if (uci->valid) { enum ucode_state ustate; @@ -288,7 +288,6 @@ static int reload_for_cpu(int cpu) if (ustate == UCODE_ERROR) err = -EINVAL; } - mutex_unlock(µcode_mutex); return err; } @@ -298,19 +297,31 @@ static ssize_t reload_store(struct device *dev, const char *buf, size_t size) { unsigned long val; - int cpu = dev->id; - ssize_t ret = 0; + int cpu; + ssize_t ret = 0, tmp_ret; ret = kstrtoul(buf, 0, &val); if (ret) return ret; - if (val == 1) { - get_online_cpus(); - if (cpu_online(cpu)) - ret = reload_for_cpu(cpu); - put_online_cpus(); + if (val != 1) + return size; + + get_online_cpus(); + mutex_lock(µcode_mutex); + for_each_online_cpu(cpu) { + tmp_ret = reload_for_cpu(cpu); + if (tmp_ret != 0) + pr_warn("Error reloading microcode on CPU %d\n", cpu); + + /* save retval of the first encountered reload error */ + if (!ret) + ret = tmp_ret; } + if (!ret) + perf_check_microcode(); + mutex_unlock(µcode_mutex); + put_online_cpus(); if (!ret) ret = size; @@ -339,7 +350,6 @@ static DEVICE_ATTR(version, 0400, version_show, NULL); static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL); static struct attribute *mc_default_attrs[] = { - &dev_attr_reload.attr, &dev_attr_version.attr, &dev_attr_processor_flags.attr, NULL @@ -504,7 +514,7 @@ static struct notifier_block __refdata mc_cpu_notifier = { #ifdef MODULE /* Autoload on Intel and AMD systems */ -static const struct x86_cpu_id microcode_id[] = { +static const struct x86_cpu_id __initconst microcode_id[] = { #ifdef CONFIG_MICROCODE_INTEL { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, }, #endif @@ -516,6 +526,16 @@ static const struct x86_cpu_id microcode_id[] = { MODULE_DEVICE_TABLE(x86cpu, microcode_id); #endif +static struct attribute *cpu_root_microcode_attrs[] = { + &dev_attr_reload.attr, + NULL +}; + +static struct attribute_group cpu_root_microcode_group = { + .name = "microcode", + .attrs = cpu_root_microcode_attrs, +}; + static int __init microcode_init(void) { struct cpuinfo_x86 *c = &cpu_data(0); @@ -540,16 +560,25 @@ static int __init microcode_init(void) mutex_lock(µcode_mutex); error = subsys_interface_register(&mc_cpu_interface); - + if (!error) + perf_check_microcode(); mutex_unlock(µcode_mutex); put_online_cpus(); if (error) goto out_pdev; + error = sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpu_root_microcode_group); + + if (error) { + pr_err("Error creating microcode group!\n"); + goto out_driver; + } + error = microcode_dev_init(); if (error) - goto out_driver; + goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); register_hotcpu_notifier(&mc_cpu_notifier); @@ -559,7 +588,11 @@ static int __init microcode_init(void) return 0; -out_driver: + out_ucode_group: + sysfs_remove_group(&cpu_subsys.dev_root->kobj, + &cpu_root_microcode_group); + + out_driver: get_online_cpus(); mutex_lock(µcode_mutex); @@ -568,7 +601,7 @@ out_driver: mutex_unlock(µcode_mutex); put_online_cpus(); -out_pdev: + out_pdev: platform_device_unregister(microcode_pdev); return error; @@ -584,6 +617,9 @@ static void __exit microcode_exit(void) unregister_hotcpu_notifier(&mc_cpu_notifier); unregister_syscore_ops(&mc_syscore_ops); + sysfs_remove_group(&cpu_subsys.dev_root->kobj, + &cpu_root_microcode_group); + get_online_cpus(); mutex_lock(µcode_mutex); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f21fd94ac89..202494d2ec6 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -15,6 +15,9 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/moduleloader.h> #include <linux/elf.h> #include <linux/vmalloc.h> @@ -30,9 +33,14 @@ #include <asm/pgtable.h> #if 0 -#define DEBUGP printk +#define DEBUGP(fmt, ...) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__) #else -#define DEBUGP(fmt...) +#define DEBUGP(fmt, ...) \ +do { \ + if (0) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ +} while (0) #endif void *module_alloc(unsigned long size) @@ -56,8 +64,8 @@ int apply_relocate(Elf32_Shdr *sechdrs, Elf32_Sym *sym; uint32_t *location; - DEBUGP("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); + DEBUGP("Applying relocate section %u to %u\n", + relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -77,7 +85,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value - (uint32_t)location; break; default: - printk(KERN_ERR "module %s: Unknown relocation: %u\n", + pr_err("%s: Unknown relocation: %u\n", me->name, ELF32_R_TYPE(rel[i].r_info)); return -ENOEXEC; } @@ -97,8 +105,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, void *loc; u64 val; - DEBUGP("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); + DEBUGP("Applying relocate section %u to %u\n", + relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { /* This is where to make the change */ loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -110,8 +118,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, + ELF64_R_SYM(rel[i].r_info); DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n", - (int)ELF64_R_TYPE(rel[i].r_info), - sym->st_value, rel[i].r_addend, (u64)loc); + (int)ELF64_R_TYPE(rel[i].r_info), + sym->st_value, rel[i].r_addend, (u64)loc); val = sym->st_value + rel[i].r_addend; @@ -140,7 +148,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, #endif break; default: - printk(KERN_ERR "module %s: Unknown rela relocation: %llu\n", + pr_err("%s: Unknown rela relocation: %llu\n", me->name, ELF64_R_TYPE(rel[i].r_info)); return -ENOEXEC; } @@ -148,9 +156,9 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return 0; overflow: - printk(KERN_ERR "overflow in relocation type %d val %Lx\n", + pr_err("overflow in relocation type %d val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), val); - printk(KERN_ERR "`%s' likely not compiled with -mcmodel=kernel\n", + pr_err("`%s' likely not compiled with -mcmodel=kernel\n", me->name); return -ENOEXEC; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a0b2f84457b..f84f5c57de3 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -365,8 +365,9 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) #ifdef CONFIG_X86_32 /* * For i386, NMIs use the same stack as the kernel, and we can - * add a workaround to the iret problem in C. Simply have 3 states - * the NMI can be in. + * add a workaround to the iret problem in C (preventing nested + * NMIs if an NMI takes a trap). Simply have 3 states the NMI + * can be in: * * 1) not running * 2) executing @@ -383,32 +384,50 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) * If an NMI hits a breakpoint that executes an iret, another * NMI can preempt it. We do not want to allow this new NMI * to run, but we want to execute it when the first one finishes. - * We set the state to "latched", and the first NMI will perform - * an cmpxchg on the state, and if it doesn't successfully - * reset the state to "not running" it will restart the next - * NMI. + * We set the state to "latched", and the exit of the first NMI will + * perform a dec_return, if the result is zero (NOT_RUNNING), then + * it will simply exit the NMI handler. If not, the dec_return + * would have set the state to NMI_EXECUTING (what we want it to + * be when we are running). In this case, we simply jump back + * to rerun the NMI handler again, and restart the 'latched' NMI. + * + * No trap (breakpoint or page fault) should be hit before nmi_restart, + * thus there is no race between the first check of state for NOT_RUNNING + * and setting it to NMI_EXECUTING. The HW will prevent nested NMIs + * at this point. + * + * In case the NMI takes a page fault, we need to save off the CR2 + * because the NMI could have preempted another page fault and corrupt + * the CR2 that is about to be read. As nested NMIs must be restarted + * and they can not take breakpoints or page faults, the update of the + * CR2 must be done before converting the nmi state back to NOT_RUNNING. + * Otherwise, there would be a race of another nested NMI coming in + * after setting state to NOT_RUNNING but before updating the nmi_cr2. */ enum nmi_states { - NMI_NOT_RUNNING, + NMI_NOT_RUNNING = 0, NMI_EXECUTING, NMI_LATCHED, }; static DEFINE_PER_CPU(enum nmi_states, nmi_state); +static DEFINE_PER_CPU(unsigned long, nmi_cr2); #define nmi_nesting_preprocess(regs) \ do { \ - if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \ - __get_cpu_var(nmi_state) = NMI_LATCHED; \ + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \ + this_cpu_write(nmi_state, NMI_LATCHED); \ return; \ } \ - nmi_restart: \ - __get_cpu_var(nmi_state) = NMI_EXECUTING; \ - } while (0) + this_cpu_write(nmi_state, NMI_EXECUTING); \ + this_cpu_write(nmi_cr2, read_cr2()); \ + } while (0); \ + nmi_restart: #define nmi_nesting_postprocess() \ do { \ - if (cmpxchg(&__get_cpu_var(nmi_state), \ - NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \ + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \ + write_cr2(this_cpu_read(nmi_cr2)); \ + if (this_cpu_dec_return(nmi_state)) \ goto nmi_restart; \ } while (0) #else /* x86_64 */ diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index 149b8d9c6ad..6d9582ec032 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -42,7 +42,8 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs) static void __init init_nmi_testsuite(void) { /* trap all the unknown NMIs we may generate */ - register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk"); + register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk", + __initdata); } static void __init cleanup_nmi_testsuite(void) @@ -64,8 +65,8 @@ static void __init test_nmi_ipi(struct cpumask *mask) { unsigned long timeout; - if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback, - NMI_FLAG_FIRST, "nmi_selftest")) { + if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback, + NMI_FLAG_FIRST, "nmi_selftest", __initdata)) { nmi_fail = FAILURE; return; } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 9ce885996fd..17fff18a103 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -352,9 +352,7 @@ struct pv_cpu_ops pv_cpu_ops = { #endif .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, - .rdmsr_regs = native_rdmsr_safe_regs, .write_msr = native_write_msr_safe, - .wrmsr_regs = native_wrmsr_safe_regs, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, .read_tscp = native_read_tscp, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index b72838bae64..299d49302e7 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -22,6 +22,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "Calgary: " fmt + #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -245,7 +247,7 @@ static unsigned long iommu_range_alloc(struct device *dev, offset = iommu_area_alloc(tbl->it_map, tbl->it_size, 0, npages, 0, boundary_size, 0); if (offset == ~0UL) { - printk(KERN_WARNING "Calgary: IOMMU full.\n"); + pr_warn("IOMMU full\n"); spin_unlock_irqrestore(&tbl->it_lock, flags); if (panic_on_overflow) panic("Calgary: fix the allocator.\n"); @@ -271,8 +273,8 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, entry = iommu_range_alloc(dev, tbl, npages); if (unlikely(entry == DMA_ERROR_CODE)) { - printk(KERN_WARNING "Calgary: failed to allocate %u pages in " - "iommu %p\n", npages, tbl); + pr_warn("failed to allocate %u pages in iommu %p\n", + npages, tbl); return DMA_ERROR_CODE; } @@ -561,8 +563,7 @@ static void calgary_tce_cache_blast(struct iommu_table *tbl) i++; } while ((val & 0xff) != 0xff && i < 100); if (i == 100) - printk(KERN_WARNING "Calgary: PCI bus not quiesced, " - "continuing anyway\n"); + pr_warn("PCI bus not quiesced, continuing anyway\n"); /* invalidate TCE cache */ target = calgary_reg(bbar, tar_offset(tbl->it_busno)); @@ -604,8 +605,7 @@ begin: i++; } while ((val64 & 0xff) != 0xff && i < 100); if (i == 100) - printk(KERN_WARNING "CalIOC2: PCI bus not quiesced, " - "continuing anyway\n"); + pr_warn("CalIOC2: PCI bus not quiesced, continuing anyway\n"); /* 3. poll Page Migration DEBUG for SoftStopFault */ target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG); @@ -617,8 +617,7 @@ begin: if (++count < 100) goto begin; else { - printk(KERN_WARNING "CalIOC2: too many SoftStopFaults, " - "aborting TCE cache flush sequence!\n"); + pr_warn("CalIOC2: too many SoftStopFaults, aborting TCE cache flush sequence!\n"); return; /* pray for the best */ } } @@ -840,8 +839,8 @@ static void calgary_dump_error_regs(struct iommu_table *tbl) plssr = be32_to_cpu(readl(target)); /* If no error, the agent ID in the CSR is not valid */ - printk(KERN_EMERG "Calgary: DMA error on Calgary PHB 0x%x, " - "0x%08x@CSR 0x%08x@PLSSR\n", tbl->it_busno, csr, plssr); + pr_emerg("DMA error on Calgary PHB 0x%x, 0x%08x@CSR 0x%08x@PLSSR\n", + tbl->it_busno, csr, plssr); } static void calioc2_dump_error_regs(struct iommu_table *tbl) @@ -867,22 +866,21 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl) target = calgary_reg(bbar, phboff | 0x800); mck = be32_to_cpu(readl(target)); - printk(KERN_EMERG "Calgary: DMA error on CalIOC2 PHB 0x%x\n", - tbl->it_busno); + pr_emerg("DMA error on CalIOC2 PHB 0x%x\n", tbl->it_busno); - printk(KERN_EMERG "Calgary: 0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n", - csr, plssr, csmr, mck); + pr_emerg("0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n", + csr, plssr, csmr, mck); /* dump rest of error regs */ - printk(KERN_EMERG "Calgary: "); + pr_emerg(""); for (i = 0; i < ARRAY_SIZE(errregs); i++) { /* err regs are at 0x810 - 0x870 */ erroff = (0x810 + (i * 0x10)); target = calgary_reg(bbar, phboff | erroff); errregs[i] = be32_to_cpu(readl(target)); - printk("0x%08x@0x%lx ", errregs[i], erroff); + pr_cont("0x%08x@0x%lx ", errregs[i], erroff); } - printk("\n"); + pr_cont("\n"); /* root complex status */ target = calgary_reg(bbar, phboff | PHB_ROOT_COMPLEX_STATUS); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 735279e54e5..ef6a8456f71 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -145,16 +147,14 @@ void show_regs_common(void) /* Board Name is optional */ board = dmi_get_system_info(DMI_BOARD_NAME); - printk(KERN_CONT "\n"); - printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk(KERN_CONT " %s %s", vendor, product); - if (board) - printk(KERN_CONT "/%s", board); - printk(KERN_CONT "\n"); + printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s %s%s%s\n", + current->pid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version, + vendor, product, + board ? "/" : "", + board ? board : ""); } void flush_thread(void) @@ -645,7 +645,7 @@ static void amd_e400_idle(void) amd_e400_c1e_detected = true; if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); - printk(KERN_INFO "System has AMD C1E enabled\n"); + pr_info("System has AMD C1E enabled\n"); } } @@ -659,8 +659,7 @@ static void amd_e400_idle(void) */ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &cpu); - printk(KERN_INFO "Switch to broadcast mode on CPU%d\n", - cpu); + pr_info("Switch to broadcast mode on CPU%d\n", cpu); } clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); @@ -681,8 +680,7 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP if (pm_idle == poll_idle && smp_num_siblings > 1) { - printk_once(KERN_WARNING "WARNING: polling idle and HT enabled," - " performance may degrade.\n"); + pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); } #endif if (pm_idle) @@ -692,11 +690,11 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) /* * One CPU supports mwait => All CPUs supports mwait */ - printk(KERN_INFO "using mwait in idle threads.\n"); + pr_info("using mwait in idle threads\n"); pm_idle = mwait_idle; } else if (cpu_has_amd_erratum(amd_erratum_400)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ - printk(KERN_INFO "using AMD E400 aware idle routine\n"); + pr_info("using AMD E400 aware idle routine\n"); pm_idle = amd_e400_idle; } else pm_idle = default_idle; @@ -715,7 +713,7 @@ static int __init idle_setup(char *str) return -EINVAL; if (!strcmp(str, "poll")) { - printk("using polling idle threads.\n"); + pr_info("using polling idle threads\n"); pm_idle = poll_idle; boot_option_idle_override = IDLE_POLL; } else if (!strcmp(str, "mwait")) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 61cdf7fdf09..0a980c9d7cb 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -117,10 +117,10 @@ void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { if (dead_task->mm->context.size) { - printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", - dead_task->comm, - dead_task->mm->context.ldt, - dead_task->mm->context.size); + pr_warn("WARNING: dead process %8s still has LDT? <%p/%d>\n", + dead_task->comm, + dead_task->mm->context.ldt, + dead_task->mm->context.size); BUG(); } } @@ -466,7 +466,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) task->thread.gs = addr; if (doit) { load_gs_index(0); - ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); } } put_cpu(); @@ -494,7 +494,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) /* set the selector to 0 to not confuse __switch_to */ loadsegment(fs, 0); - ret = checking_wrmsrl(MSR_FS_BASE, addr); + ret = wrmsrl_safe(MSR_FS_BASE, addr); } } put_cpu(); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 5de92f1abd7..52190a938b4 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/reboot.h> #include <linux/init.h> @@ -20,14 +22,12 @@ #include <asm/virtext.h> #include <asm/cpu.h> #include <asm/nmi.h> +#include <asm/smp.h> -#ifdef CONFIG_X86_32 -# include <linux/ctype.h> -# include <linux/mc146818rtc.h> -# include <asm/realmode.h> -#else -# include <asm/x86_init.h> -#endif +#include <linux/ctype.h> +#include <linux/mc146818rtc.h> +#include <asm/realmode.h> +#include <asm/x86_init.h> /* * Power off function, if any @@ -49,7 +49,7 @@ int reboot_force; */ static int reboot_default = 1; -#if defined(CONFIG_X86_32) && defined(CONFIG_SMP) +#ifdef CONFIG_SMP static int reboot_cpu = -1; #endif @@ -67,8 +67,8 @@ bool port_cf9_safe = false; * reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci] * warm Don't set the cold reboot flag * cold Set the cold reboot flag - * bios Reboot by jumping through the BIOS (only for X86_32) - * smp Reboot by executing reset on BSP or other CPU (only for X86_32) + * bios Reboot by jumping through the BIOS + * smp Reboot by executing reset on BSP or other CPU * triple Force a triple fault (init) * kbd Use the keyboard controller. cold reset (default) * acpi Use the RESET_REG in the FADT @@ -95,7 +95,6 @@ static int __init reboot_setup(char *str) reboot_mode = 0; break; -#ifdef CONFIG_X86_32 #ifdef CONFIG_SMP case 's': if (isdigit(*(str+1))) { @@ -112,7 +111,6 @@ static int __init reboot_setup(char *str) #endif /* CONFIG_SMP */ case 'b': -#endif case 'a': case 'k': case 't': @@ -138,7 +136,6 @@ static int __init reboot_setup(char *str) __setup("reboot=", reboot_setup); -#ifdef CONFIG_X86_32 /* * Reboot options and system auto-detection code provided by * Dell Inc. so their systems "just work". :-) @@ -152,16 +149,14 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) { if (reboot_type != BOOT_BIOS) { reboot_type = BOOT_BIOS; - printk(KERN_INFO "%s series board detected. Selecting BIOS-method for reboots.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboots.\n", + "BIOS", d->ident); } return 0; } -void machine_real_restart(unsigned int type) +void __noreturn machine_real_restart(unsigned int type) { - void (*restart_lowmem)(unsigned int) = (void (*)(unsigned int)) - real_mode_header->machine_real_restart_asm; - local_irq_disable(); /* @@ -181,25 +176,28 @@ void machine_real_restart(unsigned int type) /* * Switch back to the initial page table. */ +#ifdef CONFIG_X86_32 load_cr3(initial_page_table); - - /* - * Write 0x1234 to absolute memory location 0x472. The BIOS reads - * this on booting to tell it to "Bypass memory test (also warm - * boot)". This seems like a fairly standard thing that gets set by - * REBOOT.COM programs, and the previous reset routine did this - * too. */ - *((unsigned short *)0x472) = reboot_mode; +#else + write_cr3(real_mode_header->trampoline_pgd); +#endif /* Jump to the identity-mapped low memory code */ - restart_lowmem(type); +#ifdef CONFIG_X86_32 + asm volatile("jmpl *%0" : : + "rm" (real_mode_header->machine_real_restart_asm), + "a" (type)); +#else + asm volatile("ljmpl *%0" : : + "m" (real_mode_header->machine_real_restart_asm), + "D" (type)); +#endif + unreachable(); } #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(machine_real_restart); #endif -#endif /* CONFIG_X86_32 */ - /* * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot */ @@ -207,8 +205,8 @@ static int __init set_pci_reboot(const struct dmi_system_id *d) { if (reboot_type != BOOT_CF9) { reboot_type = BOOT_CF9; - printk(KERN_INFO "%s series board detected. " - "Selecting PCI-method for reboots.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboots.\n", + "PCI", d->ident); } return 0; } @@ -217,17 +215,16 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d) { if (reboot_type != BOOT_KBD) { reboot_type = BOOT_KBD; - printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboot.\n", + "KBD", d->ident); } return 0; } /* - * This is a single dmi_table handling all reboot quirks. Note that - * REBOOT_BIOS is only available for 32bit + * This is a single dmi_table handling all reboot quirks. */ static struct dmi_system_id __initdata reboot_dmi_table[] = { -#ifdef CONFIG_X86_32 { /* Handle problems with rebooting on Dell E520's */ .callback = set_bios_reboot, .ident = "Dell E520", @@ -377,7 +374,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, -#endif /* CONFIG_X86_32 */ { /* Handle reboot issue on Acer Aspire one */ .callback = set_kbd_reboot, @@ -584,13 +580,11 @@ static void native_machine_emergency_restart(void) reboot_type = BOOT_KBD; break; -#ifdef CONFIG_X86_32 case BOOT_BIOS: machine_real_restart(MRR_BIOS); reboot_type = BOOT_KBD; break; -#endif case BOOT_ACPI: acpi_reboot(); @@ -632,12 +626,10 @@ void native_machine_shutdown(void) /* The boot cpu is always logical cpu 0 */ int reboot_cpu_id = 0; -#ifdef CONFIG_X86_32 /* See if there has been given a command line override */ if ((reboot_cpu != -1) && (reboot_cpu < nr_cpu_ids) && cpu_online(reboot_cpu)) reboot_cpu_id = reboot_cpu; -#endif /* Make certain the cpu I'm about to reboot on is online */ if (!cpu_online(reboot_cpu_id)) @@ -678,7 +670,7 @@ static void __machine_emergency_restart(int emergency) static void native_machine_restart(char *__unused) { - printk("machine restart\n"); + pr_notice("machine restart\n"); if (!reboot_force) machine_shutdown(); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 16be6dc14db..f4b9b80e1b9 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1031,8 +1031,6 @@ void __init setup_arch(char **cmdline_p) x86_init.timers.wallclock_init(); - x86_platform.wallclock_init(); - mcheck_init(); arch_init_ideal_nops(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 21af737053a..b280908a376 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -6,6 +6,9 @@ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes * 2000-2002 x86-64 support by Andi Kleen */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> @@ -814,7 +817,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); print_vma_addr(" in ", regs->ip); - printk(KERN_CONT "\n"); + pr_cont("\n"); } force_sig(SIGSEGV, me); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7bd8a082365..c1a310fb830 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1,4 +1,4 @@ -/* + /* * x86 SMP booting functions * * (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk> @@ -39,6 +39,8 @@ * Glauber Costa : i386 and x86_64 integration */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/init.h> #include <linux/smp.h> #include <linux/module.h> @@ -184,7 +186,7 @@ static void __cpuinit smp_callin(void) * boards) */ - pr_debug("CALLIN, before setup_local_APIC().\n"); + pr_debug("CALLIN, before setup_local_APIC()\n"); if (apic->smp_callin_clear_local_apic) apic->smp_callin_clear_local_apic(); setup_local_APIC(); @@ -255,22 +257,13 @@ notrace static void __cpuinit start_secondary(void *unused) check_tsc_sync_target(); /* - * We need to hold call_lock, so there is no inconsistency - * between the time smp_call_function() determines number of - * IPI recipients, and the time when the determination is made - * for which cpus receive the IPI. Holding this - * lock helps us to not include this cpu in a currently in progress - * smp_call_function(). - * * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. */ - ipi_call_lock(); lock_vector_lock(); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); - ipi_call_unlock(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); @@ -432,17 +425,16 @@ static void impress_friends(void) /* * Allow the user to impress friends. */ - pr_debug("Before bogomips.\n"); + pr_debug("Before bogomips\n"); for_each_possible_cpu(cpu) if (cpumask_test_cpu(cpu, cpu_callout_mask)) bogosum += cpu_data(cpu).loops_per_jiffy; - printk(KERN_INFO - "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", + pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n", num_online_cpus(), bogosum/(500000/HZ), (bogosum/(5000/HZ))%100); - pr_debug("Before bogocount - setting activated=1.\n"); + pr_debug("Before bogocount - setting activated=1\n"); } void __inquire_remote_apic(int apicid) @@ -452,18 +444,17 @@ void __inquire_remote_apic(int apicid) int timeout; u32 status; - printk(KERN_INFO "Inquiring remote APIC 0x%x...\n", apicid); + pr_info("Inquiring remote APIC 0x%x...\n", apicid); for (i = 0; i < ARRAY_SIZE(regs); i++) { - printk(KERN_INFO "... APIC 0x%x %s: ", apicid, names[i]); + pr_info("... APIC 0x%x %s: ", apicid, names[i]); /* * Wait for idle. */ status = safe_apic_wait_icr_idle(); if (status) - printk(KERN_CONT - "a previous APIC delivery may have failed\n"); + pr_cont("a previous APIC delivery may have failed\n"); apic_icr_write(APIC_DM_REMRD | regs[i], apicid); @@ -476,10 +467,10 @@ void __inquire_remote_apic(int apicid) switch (status) { case APIC_ICR_RR_VALID: status = apic_read(APIC_RRR); - printk(KERN_CONT "%08x\n", status); + pr_cont("%08x\n", status); break; default: - printk(KERN_CONT "failed\n"); + pr_cont("failed\n"); } } } @@ -513,12 +504,12 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) apic_write(APIC_ESR, 0); accept_status = (apic_read(APIC_ESR) & 0xEF); } - pr_debug("NMI sent.\n"); + pr_debug("NMI sent\n"); if (send_status) - printk(KERN_ERR "APIC never delivered???\n"); + pr_err("APIC never delivered???\n"); if (accept_status) - printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); + pr_err("APIC delivery error (%lx)\n", accept_status); return (send_status | accept_status); } @@ -540,7 +531,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) apic_read(APIC_ESR); } - pr_debug("Asserting INIT.\n"); + pr_debug("Asserting INIT\n"); /* * Turn INIT on target chip @@ -556,7 +547,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) mdelay(10); - pr_debug("Deasserting INIT.\n"); + pr_debug("Deasserting INIT\n"); /* Target chip */ /* Send IPI */ @@ -589,14 +580,14 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Run STARTUP IPI loop. */ - pr_debug("#startup loops: %d.\n", num_starts); + pr_debug("#startup loops: %d\n", num_starts); for (j = 1; j <= num_starts; j++) { - pr_debug("Sending STARTUP #%d.\n", j); + pr_debug("Sending STARTUP #%d\n", j); if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); apic_read(APIC_ESR); - pr_debug("After apic_write.\n"); + pr_debug("After apic_write\n"); /* * STARTUP IPI @@ -613,7 +604,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) */ udelay(300); - pr_debug("Startup point 1.\n"); + pr_debug("Startup point 1\n"); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -628,12 +619,12 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) if (send_status || accept_status) break; } - pr_debug("After Startup.\n"); + pr_debug("After Startup\n"); if (send_status) - printk(KERN_ERR "APIC never delivered???\n"); + pr_err("APIC never delivered???\n"); if (accept_status) - printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); + pr_err("APIC delivery error (%lx)\n", accept_status); return (send_status | accept_status); } @@ -647,11 +638,11 @@ static void __cpuinit announce_cpu(int cpu, int apicid) if (system_state == SYSTEM_BOOTING) { if (node != current_node) { if (current_node > (-1)) - pr_cont(" Ok.\n"); + pr_cont(" OK\n"); current_node = node; pr_info("Booting Node %3d, Processors ", node); } - pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : ""); + pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : ""); return; } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", @@ -731,9 +722,9 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) /* * allow APs to start initializing. */ - pr_debug("Before Callout %d.\n", cpu); + pr_debug("Before Callout %d\n", cpu); cpumask_set_cpu(cpu, cpu_callout_mask); - pr_debug("After Callout %d.\n", cpu); + pr_debug("After Callout %d\n", cpu); /* * Wait 5s total for a response @@ -761,7 +752,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) pr_err("CPU%d: Stuck ??\n", cpu); else /* trampoline code not run */ - pr_err("CPU%d: Not responding.\n", cpu); + pr_err("CPU%d: Not responding\n", cpu); if (apic->inquire_remote_apic) apic->inquire_remote_apic(apicid); } @@ -806,7 +797,7 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || !physid_isset(apicid, phys_cpu_present_map) || !apic->apic_id_valid(apicid)) { - printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); + pr_err("%s: bad cpu %d\n", __func__, cpu); return -EINVAL; } @@ -887,9 +878,8 @@ static int __init smp_sanity_check(unsigned max_cpus) unsigned int cpu; unsigned nr; - printk(KERN_WARNING - "More than 8 CPUs detected - skipping them.\n" - "Use CONFIG_X86_BIGSMP.\n"); + pr_warn("More than 8 CPUs detected - skipping them\n" + "Use CONFIG_X86_BIGSMP\n"); nr = 0; for_each_present_cpu(cpu) { @@ -910,8 +900,7 @@ static int __init smp_sanity_check(unsigned max_cpus) #endif if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) { - printk(KERN_WARNING - "weird, boot CPU (#%d) not listed by the BIOS.\n", + pr_warn("weird, boot CPU (#%d) not listed by the BIOS\n", hard_smp_processor_id()); physid_set(hard_smp_processor_id(), phys_cpu_present_map); @@ -923,11 +912,10 @@ static int __init smp_sanity_check(unsigned max_cpus) */ if (!smp_found_config && !acpi_lapic) { preempt_enable(); - printk(KERN_NOTICE "SMP motherboard not detected.\n"); + pr_notice("SMP motherboard not detected\n"); disable_smp(); if (APIC_init_uniprocessor()) - printk(KERN_NOTICE "Local APIC not detected." - " Using dummy APIC emulation.\n"); + pr_notice("Local APIC not detected. Using dummy APIC emulation.\n"); return -1; } @@ -936,9 +924,8 @@ static int __init smp_sanity_check(unsigned max_cpus) * CPU too, but we do it for the sake of robustness anyway. */ if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) { - printk(KERN_NOTICE - "weird, boot CPU (#%d) not listed by the BIOS.\n", - boot_cpu_physical_apicid); + pr_notice("weird, boot CPU (#%d) not listed by the BIOS\n", + boot_cpu_physical_apicid); physid_set(hard_smp_processor_id(), phys_cpu_present_map); } preempt_enable(); @@ -951,8 +938,7 @@ static int __init smp_sanity_check(unsigned max_cpus) if (!disable_apic) { pr_err("BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); - pr_err("... forcing use of dummy APIC emulation." - "(tell your hw vendor)\n"); + pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n"); } smpboot_clear_io_apic(); disable_ioapic_support(); @@ -965,7 +951,7 @@ static int __init smp_sanity_check(unsigned max_cpus) * If SMP should be disabled, then really disable it! */ if (!max_cpus) { - printk(KERN_INFO "SMP mode deactivated.\n"); + pr_info("SMP mode deactivated\n"); smpboot_clear_io_apic(); connect_bsp_APIC(); @@ -1017,7 +1003,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) if (smp_sanity_check(max_cpus) < 0) { - printk(KERN_INFO "SMP disabled\n"); + pr_info("SMP disabled\n"); disable_smp(); goto out; } @@ -1055,7 +1041,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) * Set up local APIC timer on boot CPU. */ - printk(KERN_INFO "CPU%d: ", 0); + pr_info("CPU%d: ", 0); print_cpu_info(&cpu_data(0)); x86_init.timers.setup_percpu_clockev(); @@ -1105,7 +1091,7 @@ void __init native_smp_prepare_boot_cpu(void) void __init native_smp_cpus_done(unsigned int max_cpus) { - pr_debug("Boot done.\n"); + pr_debug("Boot done\n"); nmi_selftest(); impress_friends(); @@ -1166,8 +1152,7 @@ __init void prefill_possible_map(void) /* nr_cpu_ids could be reduced via nr_cpus= */ if (possible > nr_cpu_ids) { - printk(KERN_WARNING - "%d Processors exceeds NR_CPUS limit of %d\n", + pr_warn("%d Processors exceeds NR_CPUS limit of %d\n", possible, nr_cpu_ids); possible = nr_cpu_ids; } @@ -1176,13 +1161,12 @@ __init void prefill_possible_map(void) if (!setup_max_cpus) #endif if (possible > i) { - printk(KERN_WARNING - "%d Processors exceeds max_cpus limit of %u\n", + pr_warn("%d Processors exceeds max_cpus limit of %u\n", possible, setup_max_cpus); possible = i; } - printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", + pr_info("Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); for (i = 0; i < possible; i++) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 05b31d92f69..b481341c936 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -9,6 +9,9 @@ /* * Handle hardware traps and faults. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/spinlock.h> @@ -143,12 +146,11 @@ trap_signal: #ifdef CONFIG_X86_64 if (show_unhandled_signals && unhandled_signal(tsk, signr) && printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] trap %s ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, str, - regs->ip, regs->sp, error_code); + pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", + tsk->comm, tsk->pid, str, + regs->ip, regs->sp, error_code); print_vma_addr(" in ", regs->ip); - printk("\n"); + pr_cont("\n"); } #endif @@ -269,12 +271,11 @@ do_general_protection(struct pt_regs *regs, long error_code) if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] general protection ip:%lx sp:%lx error:%lx", + pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx", tsk->comm, task_pid_nr(tsk), regs->ip, regs->sp, error_code); print_vma_addr(" in ", regs->ip); - printk("\n"); + pr_cont("\n"); } force_sig(SIGSEGV, tsk); @@ -570,7 +571,7 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) conditional_sti(regs); #if 0 /* No need to warn about this any longer. */ - printk(KERN_INFO "Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); + pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); #endif } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index fc0a147e372..cfa5d4f7ca5 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> @@ -84,8 +86,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable); #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { - printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC completely.\n"); + pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n"); tsc_disabled = 1; return 1; } @@ -373,7 +374,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - printk("Fast TSC calibration failed\n"); + pr_err("Fast TSC calibration failed\n"); return 0; success: @@ -392,7 +393,7 @@ success: */ delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); - printk("Fast TSC calibration using PIT\n"); + pr_info("Fast TSC calibration using PIT\n"); return delta; } @@ -487,9 +488,8 @@ unsigned long native_calibrate_tsc(void) * use the reference value, as it is more precise. */ if (delta >= 90 && delta <= 110) { - printk(KERN_INFO - "TSC: PIT calibration matches %s. %d loops\n", - hpet ? "HPET" : "PMTIMER", i + 1); + pr_info("PIT calibration matches %s. %d loops\n", + hpet ? "HPET" : "PMTIMER", i + 1); return tsc_ref_min; } @@ -511,38 +511,36 @@ unsigned long native_calibrate_tsc(void) */ if (tsc_pit_min == ULONG_MAX) { /* PIT gave no useful value */ - printk(KERN_WARNING "TSC: Unable to calibrate against PIT\n"); + pr_warn("Unable to calibrate against PIT\n"); /* We don't have an alternative source, disable TSC */ if (!hpet && !ref1 && !ref2) { - printk("TSC: No reference (HPET/PMTIMER) available\n"); + pr_notice("No reference (HPET/PMTIMER) available\n"); return 0; } /* The alternative source failed as well, disable TSC */ if (tsc_ref_min == ULONG_MAX) { - printk(KERN_WARNING "TSC: HPET/PMTIMER calibration " - "failed.\n"); + pr_warn("HPET/PMTIMER calibration failed\n"); return 0; } /* Use the alternative source */ - printk(KERN_INFO "TSC: using %s reference calibration\n", - hpet ? "HPET" : "PMTIMER"); + pr_info("using %s reference calibration\n", + hpet ? "HPET" : "PMTIMER"); return tsc_ref_min; } /* We don't have an alternative source, use the PIT calibration value */ if (!hpet && !ref1 && !ref2) { - printk(KERN_INFO "TSC: Using PIT calibration value\n"); + pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /* The alternative source failed, use the PIT calibration value */ if (tsc_ref_min == ULONG_MAX) { - printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed. " - "Using PIT calibration\n"); + pr_warn("HPET/PMTIMER calibration failed. Using PIT calibration.\n"); return tsc_pit_min; } @@ -551,9 +549,9 @@ unsigned long native_calibrate_tsc(void) * the PIT value as we know that there are PMTIMERs around * running at double speed. At least we let the user know: */ - printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n", - hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); - printk(KERN_INFO "TSC: Using PIT calibration value\n"); + pr_warn("PIT calibration deviates from %s: %lu %lu\n", + hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); + pr_info("Using PIT calibration value\n"); return tsc_pit_min; } @@ -785,7 +783,7 @@ void mark_tsc_unstable(char *reason) tsc_unstable = 1; sched_clock_stable = 0; disable_sched_clock_irqtime(); - printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); + pr_info("Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) clocksource_mark_unstable(&clocksource_tsc); @@ -912,9 +910,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) goto out; tsc_khz = freq; - printk(KERN_INFO "Refined TSC clocksource calibration: " - "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000, - (unsigned long)tsc_khz % 1000); + pr_info("Refined TSC clocksource calibration: %lu.%03lu MHz\n", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); out: clocksource_register_khz(&clocksource_tsc, tsc_khz); @@ -970,9 +968,9 @@ void __init tsc_init(void) return; } - printk("Detected %lu.%03lu MHz processor.\n", - (unsigned long)cpu_khz / 1000, - (unsigned long)cpu_khz % 1000); + pr_info("Detected %lu.%03lu MHz processor\n", + (unsigned long)cpu_khz / 1000, + (unsigned long)cpu_khz % 1000); /* * Secondary CPUs do not run through tsc_init(), so set up diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index dc4e910a7d9..36fd42091fa 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -409,9 +409,10 @@ static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. * @mm: the probed address space. * @arch_uprobe: the probepoint information. + * @addr: virtual address at which to install the probepoint * Return 0 on success or a -ve number on error. */ -int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm) +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) { int ret; struct insn insn; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 255f58ae71e..54abcc0baf2 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -28,6 +28,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/errno.h> #include <linux/interrupt.h> @@ -137,14 +139,14 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) local_irq_enable(); if (!current->thread.vm86_info) { - printk("no vm86_info: BAD\n"); + pr_alert("no vm86_info: BAD\n"); do_exit(SIGSEGV); } set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask); tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs, regs); tmp += put_user(current->thread.screen_bitmap, ¤t->thread.vm86_info->screen_bitmap); if (tmp) { - printk("vm86: could not access userspace vm86_info\n"); + pr_alert("could not access userspace vm86_info\n"); do_exit(SIGSEGV); } diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 8eeb55a551b..992f890283e 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -16,6 +16,7 @@ #include <linux/pci_ids.h> #include <linux/pci_regs.h> #include <linux/smp.h> +#include <linux/irq.h> #include <asm/apic.h> #include <asm/pci-direct.h> @@ -95,6 +96,18 @@ static void __init set_vsmp_pv_ops(void) ctl = readl(address + 4); printk(KERN_INFO "vSMP CTL: capabilities:0x%08x control:0x%08x\n", cap, ctl); + + /* If possible, let the vSMP foundation route the interrupt optimally */ +#ifdef CONFIG_SMP + if (cap & ctl & BIT(8)) { + ctl &= ~BIT(8); +#ifdef CONFIG_PROC_FS + /* Don't let users change irq affinity via procfs */ + no_irq_affinity = 1; +#endif + } +#endif + if (cap & ctl & (1 << 4)) { /* Setup irq ops and turn on vSMP IRQ fastpath handling */ pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); @@ -102,12 +115,11 @@ static void __init set_vsmp_pv_ops(void) pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); pv_init_ops.patch = vsmp_patch; - ctl &= ~(1 << 4); - writel(ctl, address + 4); - ctl = readl(address + 4); - printk(KERN_INFO "vSMP CTL: control set to:0x%08x\n", ctl); } + writel(ctl, address + 4); + ctl = readl(address + 4); + pr_info("vSMP CTL: control set to:0x%08x\n", ctl); early_iounmap(address, 8); } @@ -187,12 +199,36 @@ static void __init vsmp_cap_cpus(void) #endif } +static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return hard_smp_processor_id() >> index_msb; +} + +/* + * In vSMP, all cpus should be capable of handling interrupts, regardless of + * the APIC used. + */ +static void fill_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) +{ + cpumask_setall(retmask); +} + +static void vsmp_apic_post_init(void) +{ + /* need to update phys_pkg_id */ + apic->phys_pkg_id = apicid_phys_pkg_id; + apic->vector_allocation_domain = fill_vector_allocation_domain; +} + void __init vsmp_init(void) { detect_vsmp_box(); if (!is_vsmp_box()) return; + x86_platform.apic_post_init = vsmp_apic_post_init; + vsmp_cap_cpus(); set_vsmp_pv_ops(); diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 5db36caf428..8d141b30904 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -18,6 +18,8 @@ * use the vDSO. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/time.h> #include <linux/init.h> #include <linux/kernel.h> @@ -111,18 +113,13 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { - static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - struct task_struct *tsk; - - if (!show_unhandled_signals || !__ratelimit(&rs)) + if (!show_unhandled_signals) return; - tsk = current; - - printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, tsk->comm, task_pid_nr(tsk), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 9796c2f3d07..6020f6f5927 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -28,6 +28,7 @@ EXPORT_SYMBOL(__put_user_8); EXPORT_SYMBOL(copy_user_generic_string); EXPORT_SYMBOL(copy_user_generic_unrolled); +EXPORT_SYMBOL(copy_user_enhanced_fast_string); EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 35c5e543f55..9f3167e891e 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -29,7 +29,6 @@ void __init x86_init_uint_noop(unsigned int unused) { } void __init x86_init_pgd_noop(pgd_t *unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } -void wallclock_init_noop(void) { } /* * The platform setup functions are preset with the default functions @@ -101,7 +100,6 @@ static int default_i8042_detect(void) { return 1; }; struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, - .wallclock_init = wallclock_init_noop, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index bd18149b2b0..3d3e2070911 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -3,6 +3,9 @@ * * Author: Suresh Siddha <suresh.b.siddha@intel.com> */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/bootmem.h> #include <linux/compat.h> #include <asm/i387.h> @@ -162,7 +165,7 @@ int save_i387_xstate(void __user *buf) BUG_ON(sig_xstate_size < xstate_size); if ((unsigned long)buf % 64) - printk("save_i387_xstate: bad fpstate %p\n", buf); + pr_err("%s: bad fpstate %p\n", __func__, buf); if (!used_math()) return 0; @@ -422,7 +425,7 @@ static void __init xstate_enable_boot_cpu(void) pcntxt_mask = eax + ((u64)edx << 32); if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { - printk(KERN_ERR "FP/SSE not shown under xsave features 0x%llx\n", + pr_err("FP/SSE not shown under xsave features 0x%llx\n", pcntxt_mask); BUG(); } @@ -445,9 +448,8 @@ static void __init xstate_enable_boot_cpu(void) setup_xstate_init(); - printk(KERN_INFO "xsave/xrstor: enabled xstate_bv 0x%llx, " - "cntxt size 0x%x\n", - pcntxt_mask, xstate_size); + pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", + pcntxt_mask, xstate_size); } /* diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 2e88438ffd8..9b7ec1150ab 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -80,10 +80,10 @@ static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) { - if (idx < X86_PMC_IDX_FIXED) + if (idx < INTEL_PMC_IDX_FIXED) return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); else - return get_fixed_pmc_idx(pmu, idx - X86_PMC_IDX_FIXED); + return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); } void kvm_deliver_pmi(struct kvm_vcpu *vcpu) @@ -291,7 +291,7 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx) if (pmc_is_gp(pmc)) reprogram_gp_counter(pmc, pmc->eventsel); else { - int fidx = idx - X86_PMC_IDX_FIXED; + int fidx = idx - INTEL_PMC_IDX_FIXED; reprogram_fixed_counter(pmc, fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); } @@ -452,7 +452,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) return; pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff, - X86_PMC_MAX_GENERIC); + INTEL_PMC_MAX_GENERIC); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << ((entry->eax >> 16) & 0xff)) - 1; bitmap_len = (entry->eax >> 24) & 0xff; @@ -462,13 +462,13 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) pmu->nr_arch_fixed_counters = 0; } else { pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f), - X86_PMC_MAX_FIXED); + INTEL_PMC_MAX_FIXED); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1; } pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED); + (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; } @@ -478,15 +478,15 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = &vcpu->arch.pmu; memset(pmu, 0, sizeof(*pmu)); - for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; } - for (i = 0; i < X86_PMC_MAX_FIXED; i++) { + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + X86_PMC_IDX_FIXED; + pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; } init_irq_work(&pmu->irq_work, trigger_pmi); kvm_pmu_cpuid_update(vcpu); @@ -498,13 +498,13 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) int i; irq_work_sync(&pmu->irq_work); - for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { struct kvm_pmc *pmc = &pmu->gp_counters[i]; stop_counter(pmc); pmc->counter = pmc->eventsel = 0; } - for (i = 0; i < X86_PMC_MAX_FIXED; i++) + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) stop_counter(&pmu->fixed_counters[i]); pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 911d2641f14..62d02e3c3ed 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -710,16 +710,6 @@ TRACE_EVENT(kvm_skinit, __entry->rip, __entry->slb) ); -#define __print_insn(insn, ilen) ({ \ - int i; \ - const char *ret = p->buffer + p->len; \ - \ - for (i = 0; i < ilen; ++i) \ - trace_seq_printf(p, " %02x", insn[i]); \ - trace_seq_printf(p, "%c", 0); \ - ret; \ - }) - #define KVM_EMUL_INSN_F_CR0_PE (1 << 0) #define KVM_EMUL_INSN_F_EFL_VM (1 << 1) #define KVM_EMUL_INSN_F_CS_D (1 << 2) @@ -786,7 +776,7 @@ TRACE_EVENT(kvm_emulate_insn, TP_printk("%x:%llx:%s (%s)%s", __entry->csbase, __entry->rip, - __print_insn(__entry->insn, __entry->len), + __print_hex(__entry->insn, __entry->len), __print_symbolic(__entry->flags, kvm_trace_symbol_emul_flags), __entry->failed ? " failed" : "" diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c index a311cc59b65..8d6ef78b5d0 100644 --- a/arch/x86/lib/msr-reg-export.c +++ b/arch/x86/lib/msr-reg-export.c @@ -1,5 +1,5 @@ #include <linux/module.h> #include <asm/msr.h> -EXPORT_SYMBOL(native_rdmsr_safe_regs); -EXPORT_SYMBOL(native_wrmsr_safe_regs); +EXPORT_SYMBOL(rdmsr_safe_regs); +EXPORT_SYMBOL(wrmsr_safe_regs); diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index 69fa10623f2..f6d13eefad1 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -6,13 +6,13 @@ #ifdef CONFIG_X86_64 /* - * int native_{rdmsr,wrmsr}_safe_regs(u32 gprs[8]); + * int {rdmsr,wrmsr}_safe_regs(u32 gprs[8]); * * reg layout: u32 gprs[eax, ecx, edx, ebx, esp, ebp, esi, edi] * */ .macro op_safe_regs op -ENTRY(native_\op\()_safe_regs) +ENTRY(\op\()_safe_regs) CFI_STARTPROC pushq_cfi %rbx pushq_cfi %rbp @@ -45,13 +45,13 @@ ENTRY(native_\op\()_safe_regs) _ASM_EXTABLE(1b, 3b) CFI_ENDPROC -ENDPROC(native_\op\()_safe_regs) +ENDPROC(\op\()_safe_regs) .endm #else /* X86_32 */ .macro op_safe_regs op -ENTRY(native_\op\()_safe_regs) +ENTRY(\op\()_safe_regs) CFI_STARTPROC pushl_cfi %ebx pushl_cfi %ebp @@ -92,7 +92,7 @@ ENTRY(native_\op\()_safe_regs) _ASM_EXTABLE(1b, 3b) CFI_ENDPROC -ENDPROC(native_\op\()_safe_regs) +ENDPROC(\op\()_safe_regs) .endm #endif diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index bc4e9d84157..e0e6990723e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -385,7 +385,7 @@ void free_initmem(void) } #ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) +void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 303f0863782..b2b94438ff0 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -312,7 +312,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) goto fail; } /* both registers must be reserved */ - if (num_counters == AMD64_NUM_COUNTERS_F15H) { + if (num_counters == AMD64_NUM_COUNTERS_CORE) { msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1); msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1); } else { @@ -514,7 +514,7 @@ static int op_amd_init(struct oprofile_operations *ops) ops->create_files = setup_ibs_files; if (boot_cpu_data.x86 == 0x15) { - num_counters = AMD64_NUM_COUNTERS_F15H; + num_counters = AMD64_NUM_COUNTERS_CORE; } else { num_counters = AMD64_NUM_COUNTERS; } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 59880afa851..71b5d5a07d7 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1,7 +1,7 @@ /* * SGI UltraViolet TLB flush routines. * - * (c) 2008-2011 Cliff Wickman <cpw@sgi.com>, SGI. + * (c) 2008-2012 Cliff Wickman <cpw@sgi.com>, SGI. * * This code is released under the GNU General Public License version 2 or * later. @@ -38,8 +38,7 @@ static int timeout_base_ns[] = { static int timeout_us; static int nobau; -static int baudisabled; -static spinlock_t disable_lock; +static int nobau_perm; static cycles_t congested_cycles; /* tunables: */ @@ -47,12 +46,13 @@ static int max_concurr = MAX_BAU_CONCURRENT; static int max_concurr_const = MAX_BAU_CONCURRENT; static int plugged_delay = PLUGGED_DELAY; static int plugsb4reset = PLUGSB4RESET; +static int giveup_limit = GIVEUP_LIMIT; static int timeoutsb4reset = TIMEOUTSB4RESET; static int ipi_reset_limit = IPI_RESET_LIMIT; static int complete_threshold = COMPLETE_THRESHOLD; static int congested_respns_us = CONGESTED_RESPONSE_US; static int congested_reps = CONGESTED_REPS; -static int congested_period = CONGESTED_PERIOD; +static int disabled_period = DISABLED_PERIOD; static struct tunables tunables[] = { {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */ @@ -63,7 +63,8 @@ static struct tunables tunables[] = { {&complete_threshold, COMPLETE_THRESHOLD}, {&congested_respns_us, CONGESTED_RESPONSE_US}, {&congested_reps, CONGESTED_REPS}, - {&congested_period, CONGESTED_PERIOD} + {&disabled_period, DISABLED_PERIOD}, + {&giveup_limit, GIVEUP_LIMIT} }; static struct dentry *tunables_dir; @@ -120,6 +121,40 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); +static void +set_bau_on(void) +{ + int cpu; + struct bau_control *bcp; + + if (nobau_perm) { + pr_info("BAU not initialized; cannot be turned on\n"); + return; + } + nobau = 0; + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->nobau = 0; + } + pr_info("BAU turned on\n"); + return; +} + +static void +set_bau_off(void) +{ + int cpu; + struct bau_control *bcp; + + nobau = 1; + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->nobau = 1; + } + pr_info("BAU turned off\n"); + return; +} + /* * Determine the first node on a uvhub. 'Nodes' are used for kernel * memory allocation. @@ -278,7 +313,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, * Both sockets dump their completed count total into * the message's count. */ - smaster->socket_acknowledge_count[mdp->msg_slot] = 0; + *sp = 0; asp = (struct atomic_short *)&msg->acknowledge_count; msg_ack_count = atom_asr(socket_ack_count, asp); @@ -491,16 +526,15 @@ static int uv1_wait_completion(struct bau_desc *bau_desc, } /* - * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register. + * UV2 could have an extra bit of status in the ACTIVATION_STATUS_2 register. + * But not currently used. */ static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc) { unsigned long descriptor_status; - unsigned long descriptor_status2; - descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK); - descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL; - descriptor_status = (descriptor_status << 1) | descriptor_status2; + descriptor_status = + ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1; return descriptor_status; } @@ -531,87 +565,11 @@ int normal_busy(struct bau_control *bcp) */ int handle_uv2_busy(struct bau_control *bcp) { - int busy_one = bcp->using_desc; - int normal = bcp->uvhub_cpu; - int selected = -1; - int i; - unsigned long descriptor_status; - unsigned long status; - int mmr_offset; - struct bau_desc *bau_desc_old; - struct bau_desc *bau_desc_new; - struct bau_control *hmaster = bcp->uvhub_master; struct ptc_stats *stat = bcp->statp; - cycles_t ttm; stat->s_uv2_wars++; - spin_lock(&hmaster->uvhub_lock); - /* try for the original first */ - if (busy_one != normal) { - if (!normal_busy(bcp)) - selected = normal; - } - if (selected < 0) { - /* can't use the normal, select an alternate */ - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; - descriptor_status = read_lmmr(mmr_offset); - - /* scan available descriptors 32-63 */ - for (i = 0; i < UV_CPUS_PER_AS; i++) { - if ((hmaster->inuse_map & (1 << i)) == 0) { - status = ((descriptor_status >> - (i * UV_ACT_STATUS_SIZE)) & - UV_ACT_STATUS_MASK) << 1; - if (status != UV2H_DESC_BUSY) { - selected = i + UV_CPUS_PER_AS; - break; - } - } - } - } - - if (busy_one != normal) - /* mark the busy alternate as not in-use */ - hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS)); - - if (selected >= 0) { - /* switch to the selected descriptor */ - if (selected != normal) { - /* set the selected alternate as in-use */ - hmaster->inuse_map |= - (1 << (selected - UV_CPUS_PER_AS)); - if (selected > stat->s_uv2_wars_hw) - stat->s_uv2_wars_hw = selected; - } - bau_desc_old = bcp->descriptor_base; - bau_desc_old += (ITEMS_PER_DESC * busy_one); - bcp->using_desc = selected; - bau_desc_new = bcp->descriptor_base; - bau_desc_new += (ITEMS_PER_DESC * selected); - *bau_desc_new = *bau_desc_old; - } else { - /* - * All are busy. Wait for the normal one for this cpu to - * free up. - */ - stat->s_uv2_war_waits++; - spin_unlock(&hmaster->uvhub_lock); - ttm = get_cycles(); - do { - cpu_relax(); - } while (normal_busy(bcp)); - spin_lock(&hmaster->uvhub_lock); - /* switch to the original descriptor */ - bcp->using_desc = normal; - bau_desc_old = bcp->descriptor_base; - bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc); - bcp->using_desc = (ITEMS_PER_DESC * normal); - bau_desc_new = bcp->descriptor_base; - bau_desc_new += (ITEMS_PER_DESC * normal); - *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */ - } - spin_unlock(&hmaster->uvhub_lock); - return FLUSH_RETRY_BUSYBUG; + bcp->busy = 1; + return FLUSH_GIVEUP; } static int uv2_wait_completion(struct bau_desc *bau_desc, @@ -620,7 +578,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, { unsigned long descriptor_stat; cycles_t ttm; - int desc = bcp->using_desc; + int desc = bcp->uvhub_cpu; long busy_reps = 0; struct ptc_stats *stat = bcp->statp; @@ -628,24 +586,38 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, /* spin on the status MMR, waiting for it to go idle */ while (descriptor_stat != UV2H_DESC_IDLE) { - /* - * Our software ack messages may be blocked because - * there are no swack resources available. As long - * as none of them has timed out hardware will NACK - * our message and its state will stay IDLE. - */ - if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) || - (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) { + if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT)) { + /* + * A h/w bug on the destination side may + * have prevented the message being marked + * pending, thus it doesn't get replied to + * and gets continually nacked until it times + * out with a SOURCE_TIMEOUT. + */ stat->s_stimeout++; return FLUSH_GIVEUP; - } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) { - stat->s_strongnacks++; - bcp->conseccompletes = 0; - return FLUSH_GIVEUP; } else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) { + ttm = get_cycles(); + + /* + * Our retries may be blocked by all destination + * swack resources being consumed, and a timeout + * pending. In that case hardware returns the + * ERROR that looks like a destination timeout. + * Without using the extended status we have to + * deduce from the short time that this was a + * strong nack. + */ + if (cycles_2_us(ttm - bcp->send_message) < timeout_us) { + bcp->conseccompletes = 0; + stat->s_plugged++; + /* FLUSH_RETRY_PLUGGED causes hang on boot */ + return FLUSH_GIVEUP; + } stat->s_dtimeout++; bcp->conseccompletes = 0; - return FLUSH_RETRY_TIMEOUT; + /* FLUSH_RETRY_TIMEOUT causes hang on boot */ + return FLUSH_GIVEUP; } else { busy_reps++; if (busy_reps > 1000000) { @@ -653,9 +625,8 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, busy_reps = 0; ttm = get_cycles(); if ((ttm - bcp->send_message) > - (bcp->clocks_per_100_usec)) { + bcp->timeout_interval) return handle_uv2_busy(bcp); - } } /* * descriptor_stat is still BUSY @@ -679,7 +650,7 @@ static int wait_completion(struct bau_desc *bau_desc, { int right_shift; unsigned long mmr_offset; - int desc = bcp->using_desc; + int desc = bcp->uvhub_cpu; if (desc < UV_CPUS_PER_AS) { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; @@ -758,33 +729,31 @@ static void destination_timeout(struct bau_desc *bau_desc, } /* - * Completions are taking a very long time due to a congested numalink - * network. + * Stop all cpus on a uvhub from using the BAU for a period of time. + * This is reversed by check_enable. */ -static void disable_for_congestion(struct bau_control *bcp, - struct ptc_stats *stat) +static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat) { - /* let only one cpu do this disabling */ - spin_lock(&disable_lock); + int tcpu; + struct bau_control *tbcp; + struct bau_control *hmaster; + cycles_t tm1; - if (!baudisabled && bcp->period_requests && - ((bcp->period_time / bcp->period_requests) > congested_cycles)) { - int tcpu; - struct bau_control *tbcp; - /* it becomes this cpu's job to turn on the use of the - BAU again */ - baudisabled = 1; - bcp->set_bau_off = 1; - bcp->set_bau_on_time = get_cycles(); - bcp->set_bau_on_time += sec_2_cycles(bcp->cong_period); + hmaster = bcp->uvhub_master; + spin_lock(&hmaster->disable_lock); + if (!bcp->baudisabled) { stat->s_bau_disabled++; + tm1 = get_cycles(); for_each_present_cpu(tcpu) { tbcp = &per_cpu(bau_control, tcpu); - tbcp->baudisabled = 1; + if (tbcp->uvhub_master == hmaster) { + tbcp->baudisabled = 1; + tbcp->set_bau_on_time = + tm1 + bcp->disabled_period; + } } } - - spin_unlock(&disable_lock); + spin_unlock(&hmaster->disable_lock); } static void count_max_concurr(int stat, struct bau_control *bcp, @@ -815,16 +784,30 @@ static void record_send_stats(cycles_t time1, cycles_t time2, bcp->period_requests++; bcp->period_time += elapsed; if ((elapsed > congested_cycles) && - (bcp->period_requests > bcp->cong_reps)) - disable_for_congestion(bcp, stat); + (bcp->period_requests > bcp->cong_reps) && + ((bcp->period_time / bcp->period_requests) > + congested_cycles)) { + stat->s_congested++; + disable_for_period(bcp, stat); + } } } else stat->s_requestor--; if (completion_status == FLUSH_COMPLETE && try > 1) stat->s_retriesok++; - else if (completion_status == FLUSH_GIVEUP) + else if (completion_status == FLUSH_GIVEUP) { stat->s_giveup++; + if (get_cycles() > bcp->period_end) + bcp->period_giveups = 0; + bcp->period_giveups++; + if (bcp->period_giveups == 1) + bcp->period_end = get_cycles() + bcp->disabled_period; + if (bcp->period_giveups > bcp->giveup_limit) { + disable_for_period(bcp, stat); + stat->s_giveuplimit++; + } + } } /* @@ -868,7 +851,8 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc, * Returns 1 if it gives up entirely and the original cpu mask is to be * returned to the kernel. */ -int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) +int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, + struct bau_desc *bau_desc) { int seq_number = 0; int completion_stat = 0; @@ -881,24 +865,23 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) struct bau_control *hmaster = bcp->uvhub_master; struct uv1_bau_msg_header *uv1_hdr = NULL; struct uv2_bau_msg_header *uv2_hdr = NULL; - struct bau_desc *bau_desc; - if (bcp->uvhub_version == 1) + if (bcp->uvhub_version == 1) { + uv1 = 1; uv1_throttle(hmaster, stat); + } while (hmaster->uvhub_quiesce) cpu_relax(); time1 = get_cycles(); + if (uv1) + uv1_hdr = &bau_desc->header.uv1_hdr; + else + uv2_hdr = &bau_desc->header.uv2_hdr; + do { - bau_desc = bcp->descriptor_base; - bau_desc += (ITEMS_PER_DESC * bcp->using_desc); - if (bcp->uvhub_version == 1) { - uv1 = 1; - uv1_hdr = &bau_desc->header.uv1_hdr; - } else - uv2_hdr = &bau_desc->header.uv2_hdr; - if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) { + if (try == 0) { if (uv1) uv1_hdr->msg_type = MSG_REGULAR; else @@ -916,25 +899,24 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) uv1_hdr->sequence = seq_number; else uv2_hdr->sequence = seq_number; - index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc; + index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu; bcp->send_message = get_cycles(); write_mmr_activation(index); try++; completion_stat = wait_completion(bau_desc, bcp, try); - /* UV2: wait_completion() may change the bcp->using_desc */ handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat); if (bcp->ipi_attempts >= bcp->ipi_reset_limit) { bcp->ipi_attempts = 0; + stat->s_overipilimit++; completion_stat = FLUSH_GIVEUP; break; } cpu_relax(); } while ((completion_stat == FLUSH_RETRY_PLUGGED) || - (completion_stat == FLUSH_RETRY_BUSYBUG) || (completion_stat == FLUSH_RETRY_TIMEOUT)); time2 = get_cycles(); @@ -955,28 +937,33 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) } /* - * The BAU is disabled. When the disabled time period has expired, the cpu - * that disabled it must re-enable it. - * Return 0 if it is re-enabled for all cpus. + * The BAU is disabled for this uvhub. When the disabled time period has + * expired re-enable it. + * Return 0 if it is re-enabled for all cpus on this uvhub. */ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat) { int tcpu; struct bau_control *tbcp; + struct bau_control *hmaster; - if (bcp->set_bau_off) { - if (get_cycles() >= bcp->set_bau_on_time) { - stat->s_bau_reenabled++; - baudisabled = 0; - for_each_present_cpu(tcpu) { - tbcp = &per_cpu(bau_control, tcpu); + hmaster = bcp->uvhub_master; + spin_lock(&hmaster->disable_lock); + if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) { + stat->s_bau_reenabled++; + for_each_present_cpu(tcpu) { + tbcp = &per_cpu(bau_control, tcpu); + if (tbcp->uvhub_master == hmaster) { tbcp->baudisabled = 0; tbcp->period_requests = 0; tbcp->period_time = 0; + tbcp->period_giveups = 0; } - return 0; } + spin_unlock(&hmaster->disable_lock); + return 0; } + spin_unlock(&hmaster->disable_lock); return -1; } @@ -1078,18 +1065,32 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct cpumask *flush_mask; struct ptc_stats *stat; struct bau_control *bcp; - - /* kernel was booted 'nobau' */ - if (nobau) - return cpumask; + unsigned long descriptor_status; + unsigned long status; bcp = &per_cpu(bau_control, cpu); stat = bcp->statp; + stat->s_enters++; + + if (bcp->nobau) + return cpumask; + + if (bcp->busy) { + descriptor_status = + read_lmmr(UVH_LB_BAU_SB_ACTIVATION_STATUS_0); + status = ((descriptor_status >> (bcp->uvhub_cpu * + UV_ACT_STATUS_SIZE)) & UV_ACT_STATUS_MASK) << 1; + if (status == UV2H_DESC_BUSY) + return cpumask; + bcp->busy = 0; + } /* bau was disabled due to slow response */ if (bcp->baudisabled) { - if (check_enable(bcp, stat)) + if (check_enable(bcp, stat)) { + stat->s_ipifordisabled++; return cpumask; + } } /* @@ -1105,7 +1106,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, stat->s_ntargself++; bau_desc = bcp->descriptor_base; - bau_desc += (ITEMS_PER_DESC * bcp->using_desc); + bau_desc += (ITEMS_PER_DESC * bcp->uvhub_cpu); bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes)) return NULL; @@ -1118,25 +1119,27 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, * uv_flush_send_and_wait returns 0 if all cpu's were messaged, * or 1 if it gave up and the original cpumask should be returned. */ - if (!uv_flush_send_and_wait(flush_mask, bcp)) + if (!uv_flush_send_and_wait(flush_mask, bcp, bau_desc)) return NULL; else return cpumask; } /* - * Search the message queue for any 'other' message with the same software - * acknowledge resource bit vector. + * Search the message queue for any 'other' unprocessed message with the + * same software acknowledge resource bit vector as the 'msg' message. */ struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, - struct bau_control *bcp, unsigned char swack_vec) + struct bau_control *bcp) { struct bau_pq_entry *msg_next = msg + 1; + unsigned char swack_vec = msg->swack_vec; if (msg_next > bcp->queue_last) msg_next = bcp->queue_first; - while ((msg_next->swack_vec != 0) && (msg_next != msg)) { - if (msg_next->swack_vec == swack_vec) + while (msg_next != msg) { + if ((msg_next->canceled == 0) && (msg_next->replied_to == 0) && + (msg_next->swack_vec == swack_vec)) return msg_next; msg_next++; if (msg_next > bcp->queue_last) @@ -1165,32 +1168,30 @@ void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) * This message was assigned a swack resource, but no * reserved acknowlegment is pending. * The bug has prevented this message from setting the MMR. - * And no other message has used the same sw_ack resource. - * Do the requested shootdown but do not reply to the msg. - * (the 0 means make no acknowledge) */ - bau_process_message(mdp, bcp, 0); - return; - } - - /* - * Some message has set the MMR 'pending' bit; it might have been - * another message. Look for that message. - */ - other_msg = find_another_by_swack(msg, bcp, msg->swack_vec); - if (other_msg) { - /* There is another. Do not ack the current one. */ - bau_process_message(mdp, bcp, 0); /* - * Let the natural processing of that message acknowledge - * it. Don't get the processing of sw_ack's out of order. + * Some message has set the MMR 'pending' bit; it might have + * been another message. Look for that message. */ - return; + other_msg = find_another_by_swack(msg, bcp); + if (other_msg) { + /* + * There is another. Process this one but do not + * ack it. + */ + bau_process_message(mdp, bcp, 0); + /* + * Let the natural processing of that other message + * acknowledge it. Don't get the processing of sw_ack's + * out of order. + */ + return; + } } /* - * There is no other message using this sw_ack, so it is safe to - * acknowledge it. + * Either the MMR shows this one pending a reply or there is no + * other message using this sw_ack, so it is safe to acknowledge it. */ bau_process_message(mdp, bcp, 1); @@ -1295,7 +1296,8 @@ static void __init enable_timeouts(void) */ mmr_image |= (1L << SOFTACK_MSHIFT); if (is_uv2_hub()) { - mmr_image |= (1L << UV2_EXT_SHFT); + /* hw bug workaround; do not use extended status */ + mmr_image &= ~(1L << UV2_EXT_SHFT); } write_mmr_misc_control(pnode, mmr_image); } @@ -1338,29 +1340,34 @@ static inline unsigned long long usec_2_cycles(unsigned long microsec) static int ptc_seq_show(struct seq_file *file, void *data) { struct ptc_stats *stat; + struct bau_control *bcp; int cpu; cpu = *(loff_t *)data; if (!cpu) { seq_printf(file, - "# cpu sent stime self locals remotes ncpus localhub "); + "# cpu bauoff sent stime self locals remotes ncpus localhub "); seq_printf(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok "); + "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries "); + seq_printf(file, + "rok resetp resett giveup sto bz throt disable "); seq_printf(file, - "resetp resett giveup sto bz throt swack recv rtime "); + "enable wars warshw warwaits enters ipidis plugged "); seq_printf(file, - "all one mult none retry canc nocan reset rcan "); + "ipiover glim cong swack recv rtime all one mult "); seq_printf(file, - "disable enable wars warshw warwaits\n"); + "none retry canc nocan reset rcan\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { - stat = &per_cpu(ptcstats, cpu); + bcp = &per_cpu(bau_control, cpu); + stat = bcp->statp; /* source side statistics */ seq_printf(file, - "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", - cpu, stat->s_requestor, cycles_2_us(stat->s_time), + "cpu %d %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + cpu, bcp->nobau, stat->s_requestor, + cycles_2_us(stat->s_time), stat->s_ntargself, stat->s_ntarglocals, stat->s_ntargremotes, stat->s_ntargcpu, stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub, @@ -1374,20 +1381,23 @@ static int ptc_seq_show(struct seq_file *file, void *data) stat->s_resets_plug, stat->s_resets_timeout, stat->s_giveup, stat->s_stimeout, stat->s_busy, stat->s_throttles); + seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + stat->s_bau_disabled, stat->s_bau_reenabled, + stat->s_uv2_wars, stat->s_uv2_wars_hw, + stat->s_uv2_war_waits, stat->s_enters, + stat->s_ipifordisabled, stat->s_plugged, + stat->s_overipilimit, stat->s_giveuplimit, + stat->s_congested); /* destination side statistics */ seq_printf(file, - "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)), stat->d_requestee, cycles_2_us(stat->d_time), stat->d_alltlb, stat->d_onetlb, stat->d_multmsg, stat->d_nomsg, stat->d_retries, stat->d_canceled, stat->d_nocanceled, stat->d_resets, stat->d_rcanceled); - seq_printf(file, "%ld %ld %ld %ld %ld\n", - stat->s_bau_disabled, stat->s_bau_reenabled, - stat->s_uv2_wars, stat->s_uv2_wars_hw, - stat->s_uv2_war_waits); } return 0; } @@ -1401,13 +1411,14 @@ static ssize_t tunables_read(struct file *file, char __user *userbuf, char *buf; int ret; - buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n", - "max_concur plugged_delay plugsb4reset", - "timeoutsb4reset ipi_reset_limit complete_threshold", - "congested_response_us congested_reps congested_period", + buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d %d\n", + "max_concur plugged_delay plugsb4reset timeoutsb4reset", + "ipi_reset_limit complete_threshold congested_response_us", + "congested_reps disabled_period giveup_limit", max_concurr, plugged_delay, plugsb4reset, timeoutsb4reset, ipi_reset_limit, complete_threshold, - congested_respns_us, congested_reps, congested_period); + congested_respns_us, congested_reps, disabled_period, + giveup_limit); if (!buf) return -ENOMEM; @@ -1438,6 +1449,14 @@ static ssize_t ptc_proc_write(struct file *file, const char __user *user, return -EFAULT; optstr[count - 1] = '\0'; + if (!strcmp(optstr, "on")) { + set_bau_on(); + return count; + } else if (!strcmp(optstr, "off")) { + set_bau_off(); + return count; + } + if (strict_strtol(optstr, 10, &input_arg) < 0) { printk(KERN_DEBUG "%s is invalid\n", optstr); return -EINVAL; @@ -1570,7 +1589,8 @@ static ssize_t tunables_write(struct file *file, const char __user *user, bcp->complete_threshold = complete_threshold; bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; - bcp->cong_period = congested_period; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; } return count; } @@ -1699,6 +1719,10 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) * fairness chaining multilevel count replied_to */ } else { + /* + * BIOS uses legacy mode, but UV2 hardware always + * uses native mode for selective broadcasts. + */ uv2_hdr = &bd2->header.uv2_hdr; uv2_hdr->swack_flag = 1; uv2_hdr->base_dest_nasid = @@ -1811,8 +1835,8 @@ static int calculate_destination_timeout(void) index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK; mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT); mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK; - base = timeout_base_ns[index]; - ts_ns = base * mult1 * mult2; + ts_ns = timeout_base_ns[index]; + ts_ns *= (mult1 * mult2); ret = ts_ns / 1000; } else { /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */ @@ -1836,6 +1860,8 @@ static void __init init_per_cpu_tunables(void) for_each_present_cpu(cpu) { bcp = &per_cpu(bau_control, cpu); bcp->baudisabled = 0; + if (nobau) + bcp->nobau = 1; bcp->statp = &per_cpu(ptcstats, cpu); /* time interval to catch a hardware stay-busy bug */ bcp->timeout_interval = usec_2_cycles(2*timeout_us); @@ -1848,10 +1874,11 @@ static void __init init_per_cpu_tunables(void) bcp->complete_threshold = complete_threshold; bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; - bcp->cong_period = congested_period; - bcp->clocks_per_100_usec = usec_2_cycles(100); + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; spin_lock_init(&bcp->queue_lock); spin_lock_init(&bcp->uvhub_lock); + spin_lock_init(&bcp->disable_lock); } } @@ -1972,7 +1999,6 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, } bcp->uvhub_master = *hmasterp; bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id; - bcp->using_desc = bcp->uvhub_cpu; if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { printk(KERN_EMERG "%d cpus per uvhub invalid\n", bcp->uvhub_cpu); @@ -2069,16 +2095,12 @@ static int __init uv_bau_init(void) if (!is_uv_system()) return 0; - if (nobau) - return 0; - for_each_possible_cpu(cur_cpu) { mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); } nuvhubs = uv_num_possible_blades(); - spin_lock_init(&disable_lock); congested_cycles = usec_2_cycles(congested_respns_us); uv_base_pnode = 0x7fffffff; @@ -2091,7 +2113,8 @@ static int __init uv_bau_init(void) enable_timeouts(); if (init_per_cpu(nuvhubs, uv_base_pnode)) { - nobau = 1; + set_bau_off(); + nobau_perm = 1; return 0; } diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index f25c2765a5c..acf7752da95 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -135,6 +135,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; int mmr_pnode, err; + unsigned int dest; BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long)); @@ -143,6 +144,10 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, if (err != 0) return err; + err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest); + if (err != 0) + return err; + if (limit == UV_AFFINITY_CPU) irq_set_status_flags(irq, IRQ_NO_BALANCING); else @@ -159,7 +164,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, entry->polarity = 0; entry->trigger = 0; entry->mask = 0; - entry->dest = apic->cpu_mask_to_apicid(eligible_cpu); + entry->dest = dest; mmr_pnode = uv_blade_to_pnode(mmr_blade); uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); @@ -222,7 +227,7 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, if (cfg->move_in_progress) send_cleanup_vector(cfg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } /* diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 5b84a2d3088..b2d534cab25 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -22,7 +22,7 @@ wakeup-objs += video-bios.o realmode-y += header.o realmode-y += trampoline_$(BITS).o realmode-y += stack.o -realmode-$(CONFIG_X86_32) += reboot_32.o +realmode-y += reboot.o realmode-$(CONFIG_ACPI_SLEEP) += $(wakeup-objs) targets += $(realmode-y) diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index fadf48378ad..a28221d94e6 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -6,6 +6,7 @@ #include <linux/linkage.h> #include <asm/page_types.h> +#include <asm/segment.h> #include "realmode.h" @@ -28,8 +29,9 @@ GLOBAL(real_mode_header) .long pa_wakeup_header #endif /* APM/BIOS reboot */ -#ifdef CONFIG_X86_32 .long pa_machine_real_restart_asm +#ifdef CONFIG_X86_64 + .long __KERNEL32_CS #endif END(real_mode_header) diff --git a/arch/x86/realmode/rm/reboot_32.S b/arch/x86/realmode/rm/reboot.S index 114044876b3..f932ea61d1c 100644 --- a/arch/x86/realmode/rm/reboot_32.S +++ b/arch/x86/realmode/rm/reboot.S @@ -2,6 +2,8 @@ #include <linux/init.h> #include <asm/segment.h> #include <asm/page_types.h> +#include <asm/processor-flags.h> +#include <asm/msr-index.h> #include "realmode.h" /* @@ -12,13 +14,35 @@ * doesn't work with at least one type of 486 motherboard. It is easy * to stop this code working; hence the copious comments. * - * This code is called with the restart type (0 = BIOS, 1 = APM) in %eax. + * This code is called with the restart type (0 = BIOS, 1 = APM) in + * the primary argument register (%eax for 32 bit, %edi for 64 bit). */ .section ".text32", "ax" .code32 - - .balign 16 ENTRY(machine_real_restart_asm) + +#ifdef CONFIG_X86_64 + /* Switch to trampoline GDT as it is guaranteed < 4 GiB */ + movl $__KERNEL_DS, %eax + movl %eax, %ds + lgdtl pa_tr_gdt + + /* Disable paging to drop us out of long mode */ + movl %cr0, %eax + andl $~X86_CR0_PG, %eax + movl %eax, %cr0 + ljmpl $__KERNEL32_CS, $pa_machine_real_restart_paging_off + +GLOBAL(machine_real_restart_paging_off) + xorl %eax, %eax + xorl %edx, %edx + movl $MSR_EFER, %ecx + wrmsr + + movl %edi, %eax + +#endif /* CONFIG_X86_64 */ + /* Set up the IDT for real mode. */ lidtl pa_machine_real_restart_idt diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 66e6d935982..0faad646f5f 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -205,9 +205,9 @@ void syscall32_cpu_init(void) { /* Load these always in case some future AMD CPU supports SYSENTER from compat mode too. */ - checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); - checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); wrmsrl(MSR_CSTAR, ia32_cstar_target); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ff962d4b821..ed7d54985d0 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1124,9 +1124,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, - .rdmsr_regs = native_rdmsr_safe_regs, .write_msr = xen_write_msr_safe, - .wrmsr_regs = native_wrmsr_safe_regs, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index afb250d22a6..f58dca7a6e5 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -80,9 +80,7 @@ static void __cpuinit cpu_bringup(void) notify_cpu_starting(cpu); - ipi_call_lock(); set_cpu_online(cpu, true); - ipi_call_unlock(); this_cpu_write(cpu_state, CPU_ONLINE); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index dcb8a6e4869..4b01ab3d2c2 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -24,6 +24,7 @@ #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> +#include <scsi/scsi_scan.h> #include "base.h" #include "power/power.h" @@ -332,6 +333,7 @@ void wait_for_device_probe(void) /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); + scsi_complete_async_scans(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 65665c9c42c..8f428a8ab00 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -499,7 +499,7 @@ static int rbd_header_from_disk(struct rbd_image_header *header, / sizeof (*ondisk)) return -EINVAL; header->snapc = kmalloc(sizeof(struct ceph_snap_context) + - snap_count * sizeof (*ondisk), + snap_count * sizeof(u64), gfp_flags); if (!header->snapc) return -ENOMEM; @@ -977,7 +977,7 @@ static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg) op = (void *)(replyhead + 1); rc = le32_to_cpu(replyhead->result); bytes = le64_to_cpu(op->extent.length); - read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ); + read_op = (le16_to_cpu(op->op) == CEPH_OSD_OP_READ); dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc); diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c index 8f05652d53e..0fcec2aae19 100644 --- a/drivers/clk/spear/spear1310_clock.c +++ b/drivers/clk/spear/spear1310_clock.c @@ -345,31 +345,30 @@ static struct frac_rate_tbl gen_rtbl[] = { /* clock parents */ static const char *vco_parents[] = { "osc_24m_clk", "osc_25m_clk", }; static const char *gpt_parents[] = { "osc_24m_clk", "apb_clk", }; -static const char *uart0_parents[] = { "pll5_clk", "uart_synth_gate_clk", }; -static const char *c3_parents[] = { "pll5_clk", "c3_synth_gate_clk", }; -static const char *gmac_phy_input_parents[] = { "gmii_125m_pad_clk", "pll2_clk", +static const char *uart0_parents[] = { "pll5_clk", "uart_syn_gclk", }; +static const char *c3_parents[] = { "pll5_clk", "c3_syn_gclk", }; +static const char *gmac_phy_input_parents[] = { "gmii_pad_clk", "pll2_clk", "osc_25m_clk", }; -static const char *gmac_phy_parents[] = { "gmac_phy_input_mux_clk", - "gmac_phy_synth_gate_clk", }; +static const char *gmac_phy_parents[] = { "phy_input_mclk", "phy_syn_gclk", }; static const char *clcd_synth_parents[] = { "vco1div4_clk", "pll2_clk", }; -static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_synth_clk", }; +static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_syn_clk", }; static const char *i2s_src_parents[] = { "vco1div2_clk", "none", "pll3_clk", "i2s_src_pad_clk", }; -static const char *i2s_ref_parents[] = { "i2s_src_mux_clk", "i2s_prs1_clk", }; +static const char *i2s_ref_parents[] = { "i2s_src_mclk", "i2s_prs1_clk", }; static const char *gen_synth0_1_parents[] = { "vco1div4_clk", "vco3div2_clk", "pll3_clk", }; static const char *gen_synth2_3_parents[] = { "vco1div4_clk", "vco3div2_clk", "pll2_clk", }; static const char *rmii_phy_parents[] = { "ras_tx50_clk", "none", - "ras_pll2_clk", "ras_synth0_clk", }; + "ras_pll2_clk", "ras_syn0_clk", }; static const char *smii_rgmii_phy_parents[] = { "none", "ras_tx125_clk", - "ras_pll2_clk", "ras_synth0_clk", }; -static const char *uart_parents[] = { "ras_apb_clk", "gen_synth3_clk", }; -static const char *i2c_parents[] = { "ras_apb_clk", "gen_synth1_clk", }; -static const char *ssp1_parents[] = { "ras_apb_clk", "gen_synth1_clk", + "ras_pll2_clk", "ras_syn0_clk", }; +static const char *uart_parents[] = { "ras_apb_clk", "gen_syn3_clk", }; +static const char *i2c_parents[] = { "ras_apb_clk", "gen_syn1_clk", }; +static const char *ssp1_parents[] = { "ras_apb_clk", "gen_syn1_clk", "ras_plclk0_clk", }; -static const char *pci_parents[] = { "ras_pll3_clk", "gen_synth2_clk", }; -static const char *tdm_parents[] = { "ras_pll3_clk", "gen_synth1_clk", }; +static const char *pci_parents[] = { "ras_pll3_clk", "gen_syn2_clk", }; +static const char *tdm_parents[] = { "ras_pll3_clk", "gen_syn1_clk", }; void __init spear1310_clk_init(void) { @@ -390,9 +389,9 @@ void __init spear1310_clk_init(void) 25000000); clk_register_clkdev(clk, "osc_25m_clk", NULL); - clk = clk_register_fixed_rate(NULL, "gmii_125m_pad_clk", NULL, - CLK_IS_ROOT, 125000000); - clk_register_clkdev(clk, "gmii_125m_pad_clk", NULL); + clk = clk_register_fixed_rate(NULL, "gmii_pad_clk", NULL, CLK_IS_ROOT, + 125000000); + clk_register_clkdev(clk, "gmii_pad_clk", NULL); clk = clk_register_fixed_rate(NULL, "i2s_src_pad_clk", NULL, CLK_IS_ROOT, 12288000); @@ -406,34 +405,34 @@ void __init spear1310_clk_init(void) /* clock derived from 24 or 25 MHz osc clk */ /* vco-pll */ - clk = clk_register_mux(NULL, "vco1_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco1_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG, SPEAR1310_PLL1_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco1_mux_clk", NULL); - clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mux_clk", + clk_register_clkdev(clk, "vco1_mclk", NULL); + clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mclk", 0, SPEAR1310_PLL1_CTR, SPEAR1310_PLL1_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco1_clk", NULL); clk_register_clkdev(clk1, "pll1_clk", NULL); - clk = clk_register_mux(NULL, "vco2_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco2_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG, SPEAR1310_PLL2_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco2_mux_clk", NULL); - clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mux_clk", + clk_register_clkdev(clk, "vco2_mclk", NULL); + clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mclk", 0, SPEAR1310_PLL2_CTR, SPEAR1310_PLL2_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco2_clk", NULL); clk_register_clkdev(clk1, "pll2_clk", NULL); - clk = clk_register_mux(NULL, "vco3_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco3_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG, SPEAR1310_PLL3_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco3_mux_clk", NULL); - clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mux_clk", + clk_register_clkdev(clk, "vco3_mclk", NULL); + clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mclk", 0, SPEAR1310_PLL3_CTR, SPEAR1310_PLL3_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco3_clk", NULL); @@ -473,7 +472,7 @@ void __init spear1310_clk_init(void) /* peripherals */ clk_register_fixed_factor(NULL, "thermal_clk", "osc_24m_clk", 0, 1, 128); - clk = clk_register_gate(NULL, "thermal_gate_clk", "thermal_clk", 0, + clk = clk_register_gate(NULL, "thermal_gclk", "thermal_clk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_THSENS_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_thermal"); @@ -500,177 +499,176 @@ void __init spear1310_clk_init(void) clk_register_clkdev(clk, "apb_clk", NULL); /* gpt clocks */ - clk = clk_register_mux(NULL, "gpt0_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt0_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT0_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt0_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mux_clk", 0, + clk_register_clkdev(clk, "gpt0_mclk", NULL); + clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_GPT0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt1_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT1_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk_register_clkdev(clk, "gpt1_mclk", NULL); + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt2_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT2_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk_register_clkdev(clk, "gpt2_mclk", NULL); + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); - clk = clk_register_mux(NULL, "gpt3_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt3_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT3_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt3_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mux_clk", 0, + clk_register_clkdev(clk, "gpt3_mclk", NULL); + clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_GPT3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt3"); /* others */ - clk = clk_register_aux("uart_synth_clk", "uart_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1310_UART_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart_synth_clk", NULL); - clk_register_clkdev(clk1, "uart_synth_gate_clk", NULL); + clk = clk_register_aux("uart_syn_clk", "uart_syn_gclk", "vco1div2_clk", + 0, SPEAR1310_UART_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "uart_syn_clk", NULL); + clk_register_clkdev(clk1, "uart_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart0_mux_clk", uart0_parents, + clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents, ARRAY_SIZE(uart0_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_UART_CLK_SHIFT, SPEAR1310_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart0_mux_clk", NULL); + clk_register_clkdev(clk, "uart0_mclk", NULL); - clk = clk_register_gate(NULL, "uart0_clk", "uart0_mux_clk", 0, + clk = clk_register_gate(NULL, "uart0_clk", "uart0_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_UART_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "e0000000.serial"); - clk = clk_register_aux("sdhci_synth_clk", "sdhci_synth_gate_clk", + clk = clk_register_aux("sdhci_syn_clk", "sdhci_syn_gclk", "vco1div2_clk", 0, SPEAR1310_SDHCI_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "sdhci_synth_clk", NULL); - clk_register_clkdev(clk1, "sdhci_synth_gate_clk", NULL); + clk_register_clkdev(clk, "sdhci_syn_clk", NULL); + clk_register_clkdev(clk1, "sdhci_syn_gclk", NULL); - clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_syn_gclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_SDHCI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b3000000.sdhci"); - clk = clk_register_aux("cfxd_synth_clk", "cfxd_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1310_CFXD_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "cfxd_synth_clk", NULL); - clk_register_clkdev(clk1, "cfxd_synth_gate_clk", NULL); + clk = clk_register_aux("cfxd_syn_clk", "cfxd_syn_gclk", "vco1div2_clk", + 0, SPEAR1310_CFXD_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "cfxd_syn_clk", NULL); + clk_register_clkdev(clk1, "cfxd_syn_gclk", NULL); - clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_syn_gclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_CFXD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b2800000.cf"); clk_register_clkdev(clk, NULL, "arasan_xd"); - clk = clk_register_aux("c3_synth_clk", "c3_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1310_C3_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "c3_synth_clk", NULL); - clk_register_clkdev(clk1, "c3_synth_gate_clk", NULL); + clk = clk_register_aux("c3_syn_clk", "c3_syn_gclk", "vco1div2_clk", + 0, SPEAR1310_C3_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "c3_syn_clk", NULL); + clk_register_clkdev(clk1, "c3_syn_gclk", NULL); - clk = clk_register_mux(NULL, "c3_mux_clk", c3_parents, + clk = clk_register_mux(NULL, "c3_mclk", c3_parents, ARRAY_SIZE(c3_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_C3_CLK_SHIFT, SPEAR1310_C3_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "c3_mux_clk", NULL); + clk_register_clkdev(clk, "c3_mclk", NULL); - clk = clk_register_gate(NULL, "c3_clk", "c3_mux_clk", 0, + clk = clk_register_gate(NULL, "c3_clk", "c3_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_C3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "c3"); /* gmac */ - clk = clk_register_mux(NULL, "gmac_phy_input_mux_clk", - gmac_phy_input_parents, + clk = clk_register_mux(NULL, "phy_input_mclk", gmac_phy_input_parents, ARRAY_SIZE(gmac_phy_input_parents), 0, SPEAR1310_GMAC_CLK_CFG, SPEAR1310_GMAC_PHY_INPUT_CLK_SHIFT, SPEAR1310_GMAC_PHY_INPUT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gmac_phy_input_mux_clk", NULL); + clk_register_clkdev(clk, "phy_input_mclk", NULL); - clk = clk_register_aux("gmac_phy_synth_clk", "gmac_phy_synth_gate_clk", - "gmac_phy_input_mux_clk", 0, SPEAR1310_GMAC_CLK_SYNT, - NULL, gmac_rtbl, ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gmac_phy_synth_clk", NULL); - clk_register_clkdev(clk1, "gmac_phy_synth_gate_clk", NULL); + clk = clk_register_aux("phy_syn_clk", "phy_syn_gclk", "phy_input_mclk", + 0, SPEAR1310_GMAC_CLK_SYNT, NULL, gmac_rtbl, + ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "phy_syn_clk", NULL); + clk_register_clkdev(clk1, "phy_syn_gclk", NULL); - clk = clk_register_mux(NULL, "gmac_phy_mux_clk", gmac_phy_parents, + clk = clk_register_mux(NULL, "phy_mclk", gmac_phy_parents, ARRAY_SIZE(gmac_phy_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GMAC_PHY_CLK_SHIFT, SPEAR1310_GMAC_PHY_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "stmmacphy.0"); /* clcd */ - clk = clk_register_mux(NULL, "clcd_synth_mux_clk", clcd_synth_parents, + clk = clk_register_mux(NULL, "clcd_syn_mclk", clcd_synth_parents, ARRAY_SIZE(clcd_synth_parents), 0, SPEAR1310_CLCD_CLK_SYNT, SPEAR1310_CLCD_SYNT_CLK_SHIFT, SPEAR1310_CLCD_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "clcd_synth_mux_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_mclk", NULL); - clk = clk_register_frac("clcd_synth_clk", "clcd_synth_mux_clk", 0, + clk = clk_register_frac("clcd_syn_clk", "clcd_syn_mclk", 0, SPEAR1310_CLCD_CLK_SYNT, clcd_rtbl, ARRAY_SIZE(clcd_rtbl), &_lock); - clk_register_clkdev(clk, "clcd_synth_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_clk", NULL); - clk = clk_register_mux(NULL, "clcd_pixel_mux_clk", clcd_pixel_parents, + clk = clk_register_mux(NULL, "clcd_pixel_mclk", clcd_pixel_parents, ARRAY_SIZE(clcd_pixel_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_CLCD_CLK_SHIFT, SPEAR1310_CLCD_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "clcd_pixel_clk", NULL); - clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mux_clk", 0, + clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_CLCD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "clcd_clk", NULL); /* i2s */ - clk = clk_register_mux(NULL, "i2s_src_mux_clk", i2s_src_parents, + clk = clk_register_mux(NULL, "i2s_src_mclk", i2s_src_parents, ARRAY_SIZE(i2s_src_parents), 0, SPEAR1310_I2S_CLK_CFG, SPEAR1310_I2S_SRC_CLK_SHIFT, SPEAR1310_I2S_SRC_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_src_clk", NULL); - clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mux_clk", 0, + clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mclk", 0, SPEAR1310_I2S_CLK_CFG, &i2s_prs1_masks, i2s_prs1_rtbl, ARRAY_SIZE(i2s_prs1_rtbl), &_lock, NULL); clk_register_clkdev(clk, "i2s_prs1_clk", NULL); - clk = clk_register_mux(NULL, "i2s_ref_mux_clk", i2s_ref_parents, + clk = clk_register_mux(NULL, "i2s_ref_mclk", i2s_ref_parents, ARRAY_SIZE(i2s_ref_parents), 0, SPEAR1310_I2S_CLK_CFG, SPEAR1310_I2S_REF_SHIFT, SPEAR1310_I2S_REF_SEL_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_clk", NULL); - clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mux_clk", 0, + clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mclk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_I2S_REF_PAD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_pad_clk", NULL); - clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gate_clk", + clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gclk", "i2s_ref_pad_clk", 0, SPEAR1310_I2S_CLK_CFG, &i2s_sclk_masks, i2s_sclk_rtbl, ARRAY_SIZE(i2s_sclk_rtbl), &_lock, &clk1); clk_register_clkdev(clk, "i2s_sclk_clk", NULL); - clk_register_clkdev(clk1, "i2s_sclk_gate_clk", NULL); + clk_register_clkdev(clk1, "i2s_sclk_gclk", NULL); /* clock derived from ahb clk */ clk = clk_register_gate(NULL, "i2c0_clk", "ahb_clk", 0, @@ -747,13 +745,13 @@ void __init spear1310_clk_init(void) &_lock); clk_register_clkdev(clk, "sysram1_clk", NULL); - clk = clk_register_aux("adc_synth_clk", "adc_synth_gate_clk", "ahb_clk", + clk = clk_register_aux("adc_syn_clk", "adc_syn_gclk", "ahb_clk", 0, SPEAR1310_ADC_CLK_SYNT, NULL, adc_rtbl, ARRAY_SIZE(adc_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "adc_synth_clk", NULL); - clk_register_clkdev(clk1, "adc_synth_gate_clk", NULL); + clk_register_clkdev(clk, "adc_syn_clk", NULL); + clk_register_clkdev(clk1, "adc_syn_gclk", NULL); - clk = clk_register_gate(NULL, "adc_clk", "adc_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "adc_clk", "adc_syn_gclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_ADC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "adc_clk"); @@ -790,37 +788,37 @@ void __init spear1310_clk_init(void) clk_register_clkdev(clk, NULL, "e0300000.kbd"); /* RAS clks */ - clk = clk_register_mux(NULL, "gen_synth0_1_mux_clk", - gen_synth0_1_parents, ARRAY_SIZE(gen_synth0_1_parents), - 0, SPEAR1310_PLL_CFG, SPEAR1310_RAS_SYNT0_1_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn0_1_mclk", gen_synth0_1_parents, + ARRAY_SIZE(gen_synth0_1_parents), 0, SPEAR1310_PLL_CFG, + SPEAR1310_RAS_SYNT0_1_CLK_SHIFT, SPEAR1310_RAS_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth0_1_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_1_clk", NULL); - clk = clk_register_mux(NULL, "gen_synth2_3_mux_clk", - gen_synth2_3_parents, ARRAY_SIZE(gen_synth2_3_parents), - 0, SPEAR1310_PLL_CFG, SPEAR1310_RAS_SYNT2_3_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn2_3_mclk", gen_synth2_3_parents, + ARRAY_SIZE(gen_synth2_3_parents), 0, SPEAR1310_PLL_CFG, + SPEAR1310_RAS_SYNT2_3_CLK_SHIFT, SPEAR1310_RAS_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth2_3_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_3_clk", NULL); - clk = clk_register_frac("gen_synth0_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn0_clk", "gen_syn0_1_clk", 0, SPEAR1310_RAS_CLK_SYNT0, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth0_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_clk", NULL); - clk = clk_register_frac("gen_synth1_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn1_clk", "gen_syn0_1_clk", 0, SPEAR1310_RAS_CLK_SYNT1, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth1_clk", NULL); + clk_register_clkdev(clk, "gen_syn1_clk", NULL); - clk = clk_register_frac("gen_synth2_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn2_clk", "gen_syn2_3_clk", 0, SPEAR1310_RAS_CLK_SYNT2, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth2_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_clk", NULL); - clk = clk_register_frac("gen_synth3_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn3_clk", "gen_syn2_3_clk", 0, SPEAR1310_RAS_CLK_SYNT3, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth3_clk", NULL); + clk_register_clkdev(clk, "gen_syn3_clk", NULL); clk = clk_register_gate(NULL, "ras_osc_24m_clk", "osc_24m_clk", 0, SPEAR1310_RAS_CLK_ENB, SPEAR1310_OSC_24M_CLK_ENB, 0, @@ -847,7 +845,7 @@ void __init spear1310_clk_init(void) &_lock); clk_register_clkdev(clk, "ras_pll3_clk", NULL); - clk = clk_register_gate(NULL, "ras_tx125_clk", "gmii_125m_pad_clk", 0, + clk = clk_register_gate(NULL, "ras_tx125_clk", "gmii_pad_clk", 0, SPEAR1310_RAS_CLK_ENB, SPEAR1310_C125M_PAD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "ras_tx125_clk", NULL); @@ -912,7 +910,7 @@ void __init spear1310_clk_init(void) &_lock); clk_register_clkdev(clk, NULL, "5c700000.eth"); - clk = clk_register_mux(NULL, "smii_rgmii_phy_mux_clk", + clk = clk_register_mux(NULL, "smii_rgmii_phy_mclk", smii_rgmii_phy_parents, ARRAY_SIZE(smii_rgmii_phy_parents), 0, SPEAR1310_RAS_CTRL_REG1, @@ -922,184 +920,184 @@ void __init spear1310_clk_init(void) clk_register_clkdev(clk, NULL, "stmmacphy.2"); clk_register_clkdev(clk, NULL, "stmmacphy.4"); - clk = clk_register_mux(NULL, "rmii_phy_mux_clk", rmii_phy_parents, + clk = clk_register_mux(NULL, "rmii_phy_mclk", rmii_phy_parents, ARRAY_SIZE(rmii_phy_parents), 0, SPEAR1310_RAS_CTRL_REG1, SPEAR1310_RMII_PHY_CLK_SHIFT, SPEAR1310_PHY_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "stmmacphy.3"); - clk = clk_register_mux(NULL, "uart1_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart1_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART1_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart1_mux_clk", NULL); + clk_register_clkdev(clk, "uart1_mclk", NULL); - clk = clk_register_gate(NULL, "uart1_clk", "uart1_mux_clk", 0, + clk = clk_register_gate(NULL, "uart1_clk", "uart1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5c800000.serial"); - clk = clk_register_mux(NULL, "uart2_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart2_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART2_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart2_mux_clk", NULL); + clk_register_clkdev(clk, "uart2_mclk", NULL); - clk = clk_register_gate(NULL, "uart2_clk", "uart2_mux_clk", 0, + clk = clk_register_gate(NULL, "uart2_clk", "uart2_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5c900000.serial"); - clk = clk_register_mux(NULL, "uart3_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart3_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART3_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart3_mux_clk", NULL); + clk_register_clkdev(clk, "uart3_mclk", NULL); - clk = clk_register_gate(NULL, "uart3_clk", "uart3_mux_clk", 0, + clk = clk_register_gate(NULL, "uart3_clk", "uart3_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5ca00000.serial"); - clk = clk_register_mux(NULL, "uart4_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart4_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART4_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart4_mux_clk", NULL); + clk_register_clkdev(clk, "uart4_mclk", NULL); - clk = clk_register_gate(NULL, "uart4_clk", "uart4_mux_clk", 0, + clk = clk_register_gate(NULL, "uart4_clk", "uart4_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART4_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cb00000.serial"); - clk = clk_register_mux(NULL, "uart5_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart5_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART5_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart5_mux_clk", NULL); + clk_register_clkdev(clk, "uart5_mclk", NULL); - clk = clk_register_gate(NULL, "uart5_clk", "uart5_mux_clk", 0, + clk = clk_register_gate(NULL, "uart5_clk", "uart5_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART5_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cc00000.serial"); - clk = clk_register_mux(NULL, "i2c1_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c1_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C1_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c1_mux_clk", NULL); + clk_register_clkdev(clk, "i2c1_mclk", NULL); - clk = clk_register_gate(NULL, "i2c1_clk", "i2c1_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c1_clk", "i2c1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cd00000.i2c"); - clk = clk_register_mux(NULL, "i2c2_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c2_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C2_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c2_mux_clk", NULL); + clk_register_clkdev(clk, "i2c2_mclk", NULL); - clk = clk_register_gate(NULL, "i2c2_clk", "i2c2_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c2_clk", "i2c2_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5ce00000.i2c"); - clk = clk_register_mux(NULL, "i2c3_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c3_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C3_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c3_mux_clk", NULL); + clk_register_clkdev(clk, "i2c3_mclk", NULL); - clk = clk_register_gate(NULL, "i2c3_clk", "i2c3_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c3_clk", "i2c3_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cf00000.i2c"); - clk = clk_register_mux(NULL, "i2c4_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c4_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C4_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c4_mux_clk", NULL); + clk_register_clkdev(clk, "i2c4_mclk", NULL); - clk = clk_register_gate(NULL, "i2c4_clk", "i2c4_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c4_clk", "i2c4_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C4_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d000000.i2c"); - clk = clk_register_mux(NULL, "i2c5_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c5_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C5_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c5_mux_clk", NULL); + clk_register_clkdev(clk, "i2c5_mclk", NULL); - clk = clk_register_gate(NULL, "i2c5_clk", "i2c5_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c5_clk", "i2c5_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C5_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d100000.i2c"); - clk = clk_register_mux(NULL, "i2c6_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c6_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C6_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c6_mux_clk", NULL); + clk_register_clkdev(clk, "i2c6_mclk", NULL); - clk = clk_register_gate(NULL, "i2c6_clk", "i2c6_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c6_clk", "i2c6_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C6_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d200000.i2c"); - clk = clk_register_mux(NULL, "i2c7_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c7_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C7_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c7_mux_clk", NULL); + clk_register_clkdev(clk, "i2c7_mclk", NULL); - clk = clk_register_gate(NULL, "i2c7_clk", "i2c7_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c7_clk", "i2c7_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C7_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d300000.i2c"); - clk = clk_register_mux(NULL, "ssp1_mux_clk", ssp1_parents, + clk = clk_register_mux(NULL, "ssp1_mclk", ssp1_parents, ARRAY_SIZE(ssp1_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_SSP1_CLK_SHIFT, SPEAR1310_SSP1_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "ssp1_mux_clk", NULL); + clk_register_clkdev(clk, "ssp1_mclk", NULL); - clk = clk_register_gate(NULL, "ssp1_clk", "ssp1_mux_clk", 0, + clk = clk_register_gate(NULL, "ssp1_clk", "ssp1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_SSP1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d400000.spi"); - clk = clk_register_mux(NULL, "pci_mux_clk", pci_parents, + clk = clk_register_mux(NULL, "pci_mclk", pci_parents, ARRAY_SIZE(pci_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_PCI_CLK_SHIFT, SPEAR1310_PCI_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "pci_mux_clk", NULL); + clk_register_clkdev(clk, "pci_mclk", NULL); - clk = clk_register_gate(NULL, "pci_clk", "pci_mux_clk", 0, + clk = clk_register_gate(NULL, "pci_clk", "pci_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_PCI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "pci"); - clk = clk_register_mux(NULL, "tdm1_mux_clk", tdm_parents, + clk = clk_register_mux(NULL, "tdm1_mclk", tdm_parents, ARRAY_SIZE(tdm_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_TDM1_CLK_SHIFT, SPEAR1310_TDM_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "tdm1_mux_clk", NULL); + clk_register_clkdev(clk, "tdm1_mclk", NULL); - clk = clk_register_gate(NULL, "tdm1_clk", "tdm1_mux_clk", 0, + clk = clk_register_gate(NULL, "tdm1_clk", "tdm1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_TDM1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "tdm_hdlc.0"); - clk = clk_register_mux(NULL, "tdm2_mux_clk", tdm_parents, + clk = clk_register_mux(NULL, "tdm2_mclk", tdm_parents, ARRAY_SIZE(tdm_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_TDM2_CLK_SHIFT, SPEAR1310_TDM_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "tdm2_mux_clk", NULL); + clk_register_clkdev(clk, "tdm2_mclk", NULL); - clk = clk_register_gate(NULL, "tdm2_clk", "tdm2_mux_clk", 0, + clk = clk_register_gate(NULL, "tdm2_clk", "tdm2_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_TDM2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "tdm_hdlc.1"); diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c index e3ea7216223..2352cee7f64 100644 --- a/drivers/clk/spear/spear1340_clock.c +++ b/drivers/clk/spear/spear1340_clock.c @@ -369,27 +369,25 @@ static struct frac_rate_tbl gen_rtbl[] = { /* clock parents */ static const char *vco_parents[] = { "osc_24m_clk", "osc_25m_clk", }; -static const char *sys_parents[] = { "none", "pll1_clk", "none", "none", - "sys_synth_clk", "none", "pll2_clk", "pll3_clk", }; -static const char *ahb_parents[] = { "cpu_div3_clk", "amba_synth_clk", }; +static const char *sys_parents[] = { "pll1_clk", "pll1_clk", "pll1_clk", + "pll1_clk", "sys_synth_clk", "sys_synth_clk", "pll2_clk", "pll3_clk", }; +static const char *ahb_parents[] = { "cpu_div3_clk", "amba_syn_clk", }; static const char *gpt_parents[] = { "osc_24m_clk", "apb_clk", }; static const char *uart0_parents[] = { "pll5_clk", "osc_24m_clk", - "uart0_synth_gate_clk", }; + "uart0_syn_gclk", }; static const char *uart1_parents[] = { "pll5_clk", "osc_24m_clk", - "uart1_synth_gate_clk", }; -static const char *c3_parents[] = { "pll5_clk", "c3_synth_gate_clk", }; -static const char *gmac_phy_input_parents[] = { "gmii_125m_pad_clk", "pll2_clk", + "uart1_syn_gclk", }; +static const char *c3_parents[] = { "pll5_clk", "c3_syn_gclk", }; +static const char *gmac_phy_input_parents[] = { "gmii_pad_clk", "pll2_clk", "osc_25m_clk", }; -static const char *gmac_phy_parents[] = { "gmac_phy_input_mux_clk", - "gmac_phy_synth_gate_clk", }; +static const char *gmac_phy_parents[] = { "phy_input_mclk", "phy_syn_gclk", }; static const char *clcd_synth_parents[] = { "vco1div4_clk", "pll2_clk", }; -static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_synth_clk", }; +static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_syn_clk", }; static const char *i2s_src_parents[] = { "vco1div2_clk", "pll2_clk", "pll3_clk", "i2s_src_pad_clk", }; -static const char *i2s_ref_parents[] = { "i2s_src_mux_clk", "i2s_prs1_clk", }; -static const char *spdif_out_parents[] = { "i2s_src_pad_clk", "gen_synth2_clk", -}; -static const char *spdif_in_parents[] = { "pll2_clk", "gen_synth3_clk", }; +static const char *i2s_ref_parents[] = { "i2s_src_mclk", "i2s_prs1_clk", }; +static const char *spdif_out_parents[] = { "i2s_src_pad_clk", "gen_syn2_clk", }; +static const char *spdif_in_parents[] = { "pll2_clk", "gen_syn3_clk", }; static const char *gen_synth0_1_parents[] = { "vco1div4_clk", "vco3div2_clk", "pll3_clk", }; @@ -415,9 +413,9 @@ void __init spear1340_clk_init(void) 25000000); clk_register_clkdev(clk, "osc_25m_clk", NULL); - clk = clk_register_fixed_rate(NULL, "gmii_125m_pad_clk", NULL, - CLK_IS_ROOT, 125000000); - clk_register_clkdev(clk, "gmii_125m_pad_clk", NULL); + clk = clk_register_fixed_rate(NULL, "gmii_pad_clk", NULL, CLK_IS_ROOT, + 125000000); + clk_register_clkdev(clk, "gmii_pad_clk", NULL); clk = clk_register_fixed_rate(NULL, "i2s_src_pad_clk", NULL, CLK_IS_ROOT, 12288000); @@ -431,35 +429,35 @@ void __init spear1340_clk_init(void) /* clock derived from 24 or 25 MHz osc clk */ /* vco-pll */ - clk = clk_register_mux(NULL, "vco1_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco1_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG, SPEAR1340_PLL1_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco1_mux_clk", NULL); - clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mux_clk", - 0, SPEAR1340_PLL1_CTR, SPEAR1340_PLL1_FRQ, pll_rtbl, + clk_register_clkdev(clk, "vco1_mclk", NULL); + clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mclk", 0, + SPEAR1340_PLL1_CTR, SPEAR1340_PLL1_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco1_clk", NULL); clk_register_clkdev(clk1, "pll1_clk", NULL); - clk = clk_register_mux(NULL, "vco2_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco2_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG, SPEAR1340_PLL2_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco2_mux_clk", NULL); - clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mux_clk", - 0, SPEAR1340_PLL2_CTR, SPEAR1340_PLL2_FRQ, pll_rtbl, + clk_register_clkdev(clk, "vco2_mclk", NULL); + clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mclk", 0, + SPEAR1340_PLL2_CTR, SPEAR1340_PLL2_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco2_clk", NULL); clk_register_clkdev(clk1, "pll2_clk", NULL); - clk = clk_register_mux(NULL, "vco3_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco3_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG, SPEAR1340_PLL3_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco3_mux_clk", NULL); - clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mux_clk", - 0, SPEAR1340_PLL3_CTR, SPEAR1340_PLL3_FRQ, pll_rtbl, + clk_register_clkdev(clk, "vco3_mclk", NULL); + clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mclk", 0, + SPEAR1340_PLL3_CTR, SPEAR1340_PLL3_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco3_clk", NULL); clk_register_clkdev(clk1, "pll3_clk", NULL); @@ -498,7 +496,7 @@ void __init spear1340_clk_init(void) /* peripherals */ clk_register_fixed_factor(NULL, "thermal_clk", "osc_24m_clk", 0, 1, 128); - clk = clk_register_gate(NULL, "thermal_gate_clk", "thermal_clk", 0, + clk = clk_register_gate(NULL, "thermal_gclk", "thermal_clk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_THSENS_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_thermal"); @@ -509,23 +507,23 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, "ddr_clk", NULL); /* clock derived from pll1 clk */ - clk = clk_register_frac("sys_synth_clk", "vco1div2_clk", 0, + clk = clk_register_frac("sys_syn_clk", "vco1div2_clk", 0, SPEAR1340_SYS_CLK_SYNT, sys_synth_rtbl, ARRAY_SIZE(sys_synth_rtbl), &_lock); - clk_register_clkdev(clk, "sys_synth_clk", NULL); + clk_register_clkdev(clk, "sys_syn_clk", NULL); - clk = clk_register_frac("amba_synth_clk", "vco1div2_clk", 0, + clk = clk_register_frac("amba_syn_clk", "vco1div2_clk", 0, SPEAR1340_AMBA_CLK_SYNT, amba_synth_rtbl, ARRAY_SIZE(amba_synth_rtbl), &_lock); - clk_register_clkdev(clk, "amba_synth_clk", NULL); + clk_register_clkdev(clk, "amba_syn_clk", NULL); - clk = clk_register_mux(NULL, "sys_mux_clk", sys_parents, + clk = clk_register_mux(NULL, "sys_mclk", sys_parents, ARRAY_SIZE(sys_parents), 0, SPEAR1340_SYS_CLK_CTRL, SPEAR1340_SCLK_SRC_SEL_SHIFT, SPEAR1340_SCLK_SRC_SEL_MASK, 0, &_lock); clk_register_clkdev(clk, "sys_clk", NULL); - clk = clk_register_fixed_factor(NULL, "cpu_clk", "sys_mux_clk", 0, 1, + clk = clk_register_fixed_factor(NULL, "cpu_clk", "sys_mclk", 0, 1, 2); clk_register_clkdev(clk, "cpu_clk", NULL); @@ -548,194 +546,193 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, "apb_clk", NULL); /* gpt clocks */ - clk = clk_register_mux(NULL, "gpt0_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt0_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT0_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt0_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mux_clk", 0, + clk_register_clkdev(clk, "gpt0_mclk", NULL); + clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_GPT0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt1_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT1_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk_register_clkdev(clk, "gpt1_mclk", NULL); + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt2_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT2_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk_register_clkdev(clk, "gpt2_mclk", NULL); + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); - clk = clk_register_mux(NULL, "gpt3_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt3_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT3_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt3_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mux_clk", 0, + clk_register_clkdev(clk, "gpt3_mclk", NULL); + clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_GPT3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt3"); /* others */ - clk = clk_register_aux("uart0_synth_clk", "uart0_synth_gate_clk", + clk = clk_register_aux("uart0_syn_clk", "uart0_syn_gclk", "vco1div2_clk", 0, SPEAR1340_UART0_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart0_synth_clk", NULL); - clk_register_clkdev(clk1, "uart0_synth_gate_clk", NULL); + clk_register_clkdev(clk, "uart0_syn_clk", NULL); + clk_register_clkdev(clk1, "uart0_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart0_mux_clk", uart0_parents, + clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents, ARRAY_SIZE(uart0_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_UART0_CLK_SHIFT, SPEAR1340_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart0_mux_clk", NULL); + clk_register_clkdev(clk, "uart0_mclk", NULL); - clk = clk_register_gate(NULL, "uart0_clk", "uart0_mux_clk", 0, + clk = clk_register_gate(NULL, "uart0_clk", "uart0_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_UART0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "e0000000.serial"); - clk = clk_register_aux("uart1_synth_clk", "uart1_synth_gate_clk", + clk = clk_register_aux("uart1_syn_clk", "uart1_syn_gclk", "vco1div2_clk", 0, SPEAR1340_UART1_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart1_synth_clk", NULL); - clk_register_clkdev(clk1, "uart1_synth_gate_clk", NULL); + clk_register_clkdev(clk, "uart1_syn_clk", NULL); + clk_register_clkdev(clk1, "uart1_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart1_mux_clk", uart1_parents, + clk = clk_register_mux(NULL, "uart1_mclk", uart1_parents, ARRAY_SIZE(uart1_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_UART1_CLK_SHIFT, SPEAR1340_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart1_mux_clk", NULL); + clk_register_clkdev(clk, "uart1_mclk", NULL); - clk = clk_register_gate(NULL, "uart1_clk", "uart1_mux_clk", 0, - SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_UART1_CLK_ENB, 0, + clk = clk_register_gate(NULL, "uart1_clk", "uart1_mclk", 0, + SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_UART1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b4100000.serial"); - clk = clk_register_aux("sdhci_synth_clk", "sdhci_synth_gate_clk", + clk = clk_register_aux("sdhci_syn_clk", "sdhci_syn_gclk", "vco1div2_clk", 0, SPEAR1340_SDHCI_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "sdhci_synth_clk", NULL); - clk_register_clkdev(clk1, "sdhci_synth_gate_clk", NULL); + clk_register_clkdev(clk, "sdhci_syn_clk", NULL); + clk_register_clkdev(clk1, "sdhci_syn_gclk", NULL); - clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_syn_gclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_SDHCI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b3000000.sdhci"); - clk = clk_register_aux("cfxd_synth_clk", "cfxd_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1340_CFXD_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "cfxd_synth_clk", NULL); - clk_register_clkdev(clk1, "cfxd_synth_gate_clk", NULL); + clk = clk_register_aux("cfxd_syn_clk", "cfxd_syn_gclk", "vco1div2_clk", + 0, SPEAR1340_CFXD_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "cfxd_syn_clk", NULL); + clk_register_clkdev(clk1, "cfxd_syn_gclk", NULL); - clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_syn_gclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_CFXD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b2800000.cf"); clk_register_clkdev(clk, NULL, "arasan_xd"); - clk = clk_register_aux("c3_synth_clk", "c3_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1340_C3_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "c3_synth_clk", NULL); - clk_register_clkdev(clk1, "c3_synth_gate_clk", NULL); + clk = clk_register_aux("c3_syn_clk", "c3_syn_gclk", "vco1div2_clk", 0, + SPEAR1340_C3_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "c3_syn_clk", NULL); + clk_register_clkdev(clk1, "c3_syn_gclk", NULL); - clk = clk_register_mux(NULL, "c3_mux_clk", c3_parents, + clk = clk_register_mux(NULL, "c3_mclk", c3_parents, ARRAY_SIZE(c3_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_C3_CLK_SHIFT, SPEAR1340_C3_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "c3_mux_clk", NULL); + clk_register_clkdev(clk, "c3_mclk", NULL); - clk = clk_register_gate(NULL, "c3_clk", "c3_mux_clk", 0, + clk = clk_register_gate(NULL, "c3_clk", "c3_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_C3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "c3"); /* gmac */ - clk = clk_register_mux(NULL, "gmac_phy_input_mux_clk", - gmac_phy_input_parents, + clk = clk_register_mux(NULL, "phy_input_mclk", gmac_phy_input_parents, ARRAY_SIZE(gmac_phy_input_parents), 0, SPEAR1340_GMAC_CLK_CFG, SPEAR1340_GMAC_PHY_INPUT_CLK_SHIFT, SPEAR1340_GMAC_PHY_INPUT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gmac_phy_input_mux_clk", NULL); + clk_register_clkdev(clk, "phy_input_mclk", NULL); - clk = clk_register_aux("gmac_phy_synth_clk", "gmac_phy_synth_gate_clk", - "gmac_phy_input_mux_clk", 0, SPEAR1340_GMAC_CLK_SYNT, - NULL, gmac_rtbl, ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gmac_phy_synth_clk", NULL); - clk_register_clkdev(clk1, "gmac_phy_synth_gate_clk", NULL); + clk = clk_register_aux("phy_syn_clk", "phy_syn_gclk", "phy_input_mclk", + 0, SPEAR1340_GMAC_CLK_SYNT, NULL, gmac_rtbl, + ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "phy_syn_clk", NULL); + clk_register_clkdev(clk1, "phy_syn_gclk", NULL); - clk = clk_register_mux(NULL, "gmac_phy_mux_clk", gmac_phy_parents, + clk = clk_register_mux(NULL, "phy_mclk", gmac_phy_parents, ARRAY_SIZE(gmac_phy_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GMAC_PHY_CLK_SHIFT, SPEAR1340_GMAC_PHY_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "stmmacphy.0"); /* clcd */ - clk = clk_register_mux(NULL, "clcd_synth_mux_clk", clcd_synth_parents, + clk = clk_register_mux(NULL, "clcd_syn_mclk", clcd_synth_parents, ARRAY_SIZE(clcd_synth_parents), 0, SPEAR1340_CLCD_CLK_SYNT, SPEAR1340_CLCD_SYNT_CLK_SHIFT, SPEAR1340_CLCD_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "clcd_synth_mux_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_mclk", NULL); - clk = clk_register_frac("clcd_synth_clk", "clcd_synth_mux_clk", 0, + clk = clk_register_frac("clcd_syn_clk", "clcd_syn_mclk", 0, SPEAR1340_CLCD_CLK_SYNT, clcd_rtbl, ARRAY_SIZE(clcd_rtbl), &_lock); - clk_register_clkdev(clk, "clcd_synth_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_clk", NULL); - clk = clk_register_mux(NULL, "clcd_pixel_mux_clk", clcd_pixel_parents, + clk = clk_register_mux(NULL, "clcd_pixel_mclk", clcd_pixel_parents, ARRAY_SIZE(clcd_pixel_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_CLCD_CLK_SHIFT, SPEAR1340_CLCD_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "clcd_pixel_clk", NULL); - clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mux_clk", 0, + clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_CLCD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "clcd_clk", NULL); /* i2s */ - clk = clk_register_mux(NULL, "i2s_src_mux_clk", i2s_src_parents, + clk = clk_register_mux(NULL, "i2s_src_mclk", i2s_src_parents, ARRAY_SIZE(i2s_src_parents), 0, SPEAR1340_I2S_CLK_CFG, SPEAR1340_I2S_SRC_CLK_SHIFT, SPEAR1340_I2S_SRC_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_src_clk", NULL); - clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mux_clk", 0, + clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mclk", 0, SPEAR1340_I2S_CLK_CFG, &i2s_prs1_masks, i2s_prs1_rtbl, ARRAY_SIZE(i2s_prs1_rtbl), &_lock, NULL); clk_register_clkdev(clk, "i2s_prs1_clk", NULL); - clk = clk_register_mux(NULL, "i2s_ref_mux_clk", i2s_ref_parents, + clk = clk_register_mux(NULL, "i2s_ref_mclk", i2s_ref_parents, ARRAY_SIZE(i2s_ref_parents), 0, SPEAR1340_I2S_CLK_CFG, SPEAR1340_I2S_REF_SHIFT, SPEAR1340_I2S_REF_SEL_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_clk", NULL); - clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mux_clk", 0, + clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_I2S_REF_PAD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_pad_clk", NULL); - clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gate_clk", - "i2s_ref_mux_clk", 0, SPEAR1340_I2S_CLK_CFG, - &i2s_sclk_masks, i2s_sclk_rtbl, - ARRAY_SIZE(i2s_sclk_rtbl), &_lock, &clk1); + clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gclk", "i2s_ref_mclk", + 0, SPEAR1340_I2S_CLK_CFG, &i2s_sclk_masks, + i2s_sclk_rtbl, ARRAY_SIZE(i2s_sclk_rtbl), &_lock, + &clk1); clk_register_clkdev(clk, "i2s_sclk_clk", NULL); - clk_register_clkdev(clk1, "i2s_sclk_gate_clk", NULL); + clk_register_clkdev(clk1, "i2s_sclk_gclk", NULL); /* clock derived from ahb clk */ clk = clk_register_gate(NULL, "i2c0_clk", "ahb_clk", 0, @@ -744,7 +741,7 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, NULL, "e0280000.i2c"); clk = clk_register_gate(NULL, "i2c1_clk", "ahb_clk", 0, - SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_I2C1_CLK_ENB, 0, + SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_I2C1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b4000000.i2c"); @@ -800,13 +797,13 @@ void __init spear1340_clk_init(void) &_lock); clk_register_clkdev(clk, "sysram1_clk", NULL); - clk = clk_register_aux("adc_synth_clk", "adc_synth_gate_clk", "ahb_clk", + clk = clk_register_aux("adc_syn_clk", "adc_syn_gclk", "ahb_clk", 0, SPEAR1340_ADC_CLK_SYNT, NULL, adc_rtbl, ARRAY_SIZE(adc_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "adc_synth_clk", NULL); - clk_register_clkdev(clk1, "adc_synth_gate_clk", NULL); + clk_register_clkdev(clk, "adc_syn_clk", NULL); + clk_register_clkdev(clk1, "adc_syn_gclk", NULL); - clk = clk_register_gate(NULL, "adc_clk", "adc_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "adc_clk", "adc_syn_gclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_ADC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "adc_clk"); @@ -843,39 +840,39 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, NULL, "e0300000.kbd"); /* RAS clks */ - clk = clk_register_mux(NULL, "gen_synth0_1_mux_clk", - gen_synth0_1_parents, ARRAY_SIZE(gen_synth0_1_parents), - 0, SPEAR1340_PLL_CFG, SPEAR1340_GEN_SYNT0_1_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn0_1_mclk", gen_synth0_1_parents, + ARRAY_SIZE(gen_synth0_1_parents), 0, SPEAR1340_PLL_CFG, + SPEAR1340_GEN_SYNT0_1_CLK_SHIFT, SPEAR1340_GEN_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth0_1_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_1_clk", NULL); - clk = clk_register_mux(NULL, "gen_synth2_3_mux_clk", - gen_synth2_3_parents, ARRAY_SIZE(gen_synth2_3_parents), - 0, SPEAR1340_PLL_CFG, SPEAR1340_GEN_SYNT2_3_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn2_3_mclk", gen_synth2_3_parents, + ARRAY_SIZE(gen_synth2_3_parents), 0, SPEAR1340_PLL_CFG, + SPEAR1340_GEN_SYNT2_3_CLK_SHIFT, SPEAR1340_GEN_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth2_3_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_3_clk", NULL); - clk = clk_register_frac("gen_synth0_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn0_clk", "gen_syn0_1_clk", 0, SPEAR1340_GEN_CLK_SYNT0, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth0_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_clk", NULL); - clk = clk_register_frac("gen_synth1_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn1_clk", "gen_syn0_1_clk", 0, SPEAR1340_GEN_CLK_SYNT1, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth1_clk", NULL); + clk_register_clkdev(clk, "gen_syn1_clk", NULL); - clk = clk_register_frac("gen_synth2_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn2_clk", "gen_syn2_3_clk", 0, SPEAR1340_GEN_CLK_SYNT2, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth2_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_clk", NULL); - clk = clk_register_frac("gen_synth3_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn3_clk", "gen_syn2_3_clk", 0, SPEAR1340_GEN_CLK_SYNT3, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth3_clk", NULL); + clk_register_clkdev(clk, "gen_syn3_clk", NULL); - clk = clk_register_gate(NULL, "mali_clk", "gen_synth3_clk", 0, + clk = clk_register_gate(NULL, "mali_clk", "gen_syn3_clk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_MALI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "mali"); @@ -890,74 +887,74 @@ void __init spear1340_clk_init(void) &_lock); clk_register_clkdev(clk, NULL, "spear_cec.1"); - clk = clk_register_mux(NULL, "spdif_out_mux_clk", spdif_out_parents, + clk = clk_register_mux(NULL, "spdif_out_mclk", spdif_out_parents, ARRAY_SIZE(spdif_out_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_SPDIF_OUT_CLK_SHIFT, SPEAR1340_SPDIF_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "spdif_out_mux_clk", NULL); + clk_register_clkdev(clk, "spdif_out_mclk", NULL); - clk = clk_register_gate(NULL, "spdif_out_clk", "spdif_out_mux_clk", 0, + clk = clk_register_gate(NULL, "spdif_out_clk", "spdif_out_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_SPDIF_OUT_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spdif-out"); - clk = clk_register_mux(NULL, "spdif_in_mux_clk", spdif_in_parents, + clk = clk_register_mux(NULL, "spdif_in_mclk", spdif_in_parents, ARRAY_SIZE(spdif_in_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_SPDIF_IN_CLK_SHIFT, SPEAR1340_SPDIF_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "spdif_in_mux_clk", NULL); + clk_register_clkdev(clk, "spdif_in_mclk", NULL); - clk = clk_register_gate(NULL, "spdif_in_clk", "spdif_in_mux_clk", 0, + clk = clk_register_gate(NULL, "spdif_in_clk", "spdif_in_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_SPDIF_IN_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spdif-in"); - clk = clk_register_gate(NULL, "acp_clk", "acp_mux_clk", 0, + clk = clk_register_gate(NULL, "acp_clk", "acp_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_ACP_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "acp_clk"); - clk = clk_register_gate(NULL, "plgpio_clk", "plgpio_mux_clk", 0, + clk = clk_register_gate(NULL, "plgpio_clk", "plgpio_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_PLGPIO_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "plgpio"); - clk = clk_register_gate(NULL, "video_dec_clk", "video_dec_mux_clk", 0, + clk = clk_register_gate(NULL, "video_dec_clk", "video_dec_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_VIDEO_DEC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "video_dec"); - clk = clk_register_gate(NULL, "video_enc_clk", "video_enc_mux_clk", 0, + clk = clk_register_gate(NULL, "video_enc_clk", "video_enc_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_VIDEO_ENC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "video_enc"); - clk = clk_register_gate(NULL, "video_in_clk", "video_in_mux_clk", 0, + clk = clk_register_gate(NULL, "video_in_clk", "video_in_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_VIDEO_IN_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_vip"); - clk = clk_register_gate(NULL, "cam0_clk", "cam0_mux_clk", 0, + clk = clk_register_gate(NULL, "cam0_clk", "cam0_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.0"); - clk = clk_register_gate(NULL, "cam1_clk", "cam1_mux_clk", 0, + clk = clk_register_gate(NULL, "cam1_clk", "cam1_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.1"); - clk = clk_register_gate(NULL, "cam2_clk", "cam2_mux_clk", 0, + clk = clk_register_gate(NULL, "cam2_clk", "cam2_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.2"); - clk = clk_register_gate(NULL, "cam3_clk", "cam3_mux_clk", 0, + clk = clk_register_gate(NULL, "cam3_clk", "cam3_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.3"); - clk = clk_register_gate(NULL, "pwm_clk", "pwm_mux_clk", 0, + clk = clk_register_gate(NULL, "pwm_clk", "pwm_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_PWM_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "pwm"); diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index 01dd6daff2a..c3157454bb3 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -122,12 +122,12 @@ static struct gpt_rate_tbl gpt_rtbl[] = { }; /* clock parents */ -static const char *uart0_parents[] = { "pll3_48m_clk", "uart_synth_gate_clk", }; -static const char *firda_parents[] = { "pll3_48m_clk", "firda_synth_gate_clk", +static const char *uart0_parents[] = { "pll3_clk", "uart_syn_gclk", }; +static const char *firda_parents[] = { "pll3_clk", "firda_syn_gclk", }; -static const char *gpt0_parents[] = { "pll3_48m_clk", "gpt0_synth_clk", }; -static const char *gpt1_parents[] = { "pll3_48m_clk", "gpt1_synth_clk", }; -static const char *gpt2_parents[] = { "pll3_48m_clk", "gpt2_synth_clk", }; +static const char *gpt0_parents[] = { "pll3_clk", "gpt0_syn_clk", }; +static const char *gpt1_parents[] = { "pll3_clk", "gpt1_syn_clk", }; +static const char *gpt2_parents[] = { "pll3_clk", "gpt2_syn_clk", }; static const char *gen2_3_parents[] = { "pll1_clk", "pll2_clk", }; static const char *ddr_parents[] = { "ahb_clk", "ahbmult2_clk", "none", "pll2_clk", }; @@ -137,7 +137,7 @@ static void __init spear300_clk_init(void) { struct clk *clk; - clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_48m_clk", 0, + clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_clk", 0, 1, 1); clk_register_clkdev(clk, NULL, "60000000.clcd"); @@ -219,15 +219,11 @@ static void __init spear310_clk_init(void) #define SPEAR320_UARTX_PCLK_VAL_SYNTH1 0x0 #define SPEAR320_UARTX_PCLK_VAL_APB 0x1 -static const char *i2s_ref_parents[] = { "ras_pll2_clk", - "ras_gen2_synth_gate_clk", }; -static const char *sdhci_parents[] = { "ras_pll3_48m_clk", - "ras_gen3_synth_gate_clk", -}; +static const char *i2s_ref_parents[] = { "ras_pll2_clk", "ras_syn2_gclk", }; +static const char *sdhci_parents[] = { "ras_pll3_clk", "ras_syn3_gclk", }; static const char *smii0_parents[] = { "smii_125m_pad", "ras_pll2_clk", - "ras_gen0_synth_gate_clk", }; -static const char *uartx_parents[] = { "ras_gen1_synth_gate_clk", "ras_apb_clk", -}; + "ras_syn0_gclk", }; +static const char *uartx_parents[] = { "ras_syn1_gclk", "ras_apb_clk", }; static void __init spear320_clk_init(void) { @@ -237,7 +233,7 @@ static void __init spear320_clk_init(void) CLK_IS_ROOT, 125000000); clk_register_clkdev(clk, "smii_125m_pad", NULL); - clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_48m_clk", 0, + clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_clk", 0, 1, 1); clk_register_clkdev(clk, NULL, "90000000.clcd"); @@ -363,9 +359,9 @@ void __init spear3xx_clk_init(void) clk_register_clkdev(clk, NULL, "fc900000.rtc"); /* clock derived from 24 MHz osc clk */ - clk = clk_register_fixed_rate(NULL, "pll3_48m_clk", "osc_24m_clk", 0, + clk = clk_register_fixed_rate(NULL, "pll3_clk", "osc_24m_clk", 0, 48000000); - clk_register_clkdev(clk, "pll3_48m_clk", NULL); + clk_register_clkdev(clk, "pll3_clk", NULL); clk = clk_register_fixed_factor(NULL, "wdt_clk", "osc_24m_clk", 0, 1, 1); @@ -392,98 +388,98 @@ void __init spear3xx_clk_init(void) HCLK_RATIO_MASK, 0, &_lock); clk_register_clkdev(clk, "ahb_clk", NULL); - clk = clk_register_aux("uart_synth_clk", "uart_synth_gate_clk", - "pll1_clk", 0, UART_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart_synth_clk", NULL); - clk_register_clkdev(clk1, "uart_synth_gate_clk", NULL); + clk = clk_register_aux("uart_syn_clk", "uart_syn_gclk", "pll1_clk", 0, + UART_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "uart_syn_clk", NULL); + clk_register_clkdev(clk1, "uart_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart0_mux_clk", uart0_parents, + clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents, ARRAY_SIZE(uart0_parents), 0, PERIP_CLK_CFG, UART_CLK_SHIFT, UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart0_mux_clk", NULL); + clk_register_clkdev(clk, "uart0_mclk", NULL); - clk = clk_register_gate(NULL, "uart0", "uart0_mux_clk", 0, - PERIP1_CLK_ENB, UART_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "uart0", "uart0_mclk", 0, PERIP1_CLK_ENB, + UART_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "d0000000.serial"); - clk = clk_register_aux("firda_synth_clk", "firda_synth_gate_clk", - "pll1_clk", 0, FIRDA_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "firda_synth_clk", NULL); - clk_register_clkdev(clk1, "firda_synth_gate_clk", NULL); + clk = clk_register_aux("firda_syn_clk", "firda_syn_gclk", "pll1_clk", 0, + FIRDA_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "firda_syn_clk", NULL); + clk_register_clkdev(clk1, "firda_syn_gclk", NULL); - clk = clk_register_mux(NULL, "firda_mux_clk", firda_parents, + clk = clk_register_mux(NULL, "firda_mclk", firda_parents, ARRAY_SIZE(firda_parents), 0, PERIP_CLK_CFG, FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "firda_mux_clk", NULL); + clk_register_clkdev(clk, "firda_mclk", NULL); - clk = clk_register_gate(NULL, "firda_clk", "firda_mux_clk", 0, + clk = clk_register_gate(NULL, "firda_clk", "firda_mclk", 0, PERIP1_CLK_ENB, FIRDA_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "firda"); /* gpt clocks */ - clk_register_gpt("gpt0_synth_clk", "pll1_clk", 0, PRSC0_CLK_CFG, - gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); + clk_register_gpt("gpt0_syn_clk", "pll1_clk", 0, PRSC0_CLK_CFG, gpt_rtbl, + ARRAY_SIZE(gpt_rtbl), &_lock); clk = clk_register_mux(NULL, "gpt0_clk", gpt0_parents, ARRAY_SIZE(gpt0_parents), 0, PERIP_CLK_CFG, GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk_register_gpt("gpt1_synth_clk", "pll1_clk", 0, PRSC1_CLK_CFG, - gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt1_parents, + clk_register_gpt("gpt1_syn_clk", "pll1_clk", 0, PRSC1_CLK_CFG, gpt_rtbl, + ARRAY_SIZE(gpt_rtbl), &_lock); + clk = clk_register_mux(NULL, "gpt1_mclk", gpt1_parents, ARRAY_SIZE(gpt1_parents), 0, PERIP_CLK_CFG, GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk_register_clkdev(clk, "gpt1_mclk", NULL); + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, PERIP1_CLK_ENB, GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk_register_gpt("gpt2_synth_clk", "pll1_clk", 0, PRSC2_CLK_CFG, - gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt2_parents, + clk_register_gpt("gpt2_syn_clk", "pll1_clk", 0, PRSC2_CLK_CFG, gpt_rtbl, + ARRAY_SIZE(gpt_rtbl), &_lock); + clk = clk_register_mux(NULL, "gpt2_mclk", gpt2_parents, ARRAY_SIZE(gpt2_parents), 0, PERIP_CLK_CFG, GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk_register_clkdev(clk, "gpt2_mclk", NULL); + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, PERIP1_CLK_ENB, GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); /* general synths clocks */ - clk = clk_register_aux("gen0_synth_clk", "gen0_synth_gate_clk", - "pll1_clk", 0, GEN0_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen0_synth_clk", NULL); - clk_register_clkdev(clk1, "gen0_synth_gate_clk", NULL); + clk = clk_register_aux("gen0_syn_clk", "gen0_syn_gclk", "pll1_clk", + 0, GEN0_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "gen0_syn_clk", NULL); + clk_register_clkdev(clk1, "gen0_syn_gclk", NULL); - clk = clk_register_aux("gen1_synth_clk", "gen1_synth_gate_clk", - "pll1_clk", 0, GEN1_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen1_synth_clk", NULL); - clk_register_clkdev(clk1, "gen1_synth_gate_clk", NULL); + clk = clk_register_aux("gen1_syn_clk", "gen1_syn_gclk", "pll1_clk", + 0, GEN1_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "gen1_syn_clk", NULL); + clk_register_clkdev(clk1, "gen1_syn_gclk", NULL); - clk = clk_register_mux(NULL, "gen2_3_parent_clk", gen2_3_parents, + clk = clk_register_mux(NULL, "gen2_3_par_clk", gen2_3_parents, ARRAY_SIZE(gen2_3_parents), 0, CORE_CLK_CFG, GEN_SYNTH2_3_CLK_SHIFT, GEN_SYNTH2_3_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen2_3_parent_clk", NULL); + clk_register_clkdev(clk, "gen2_3_par_clk", NULL); - clk = clk_register_aux("gen2_synth_clk", "gen2_synth_gate_clk", - "gen2_3_parent_clk", 0, GEN2_CLK_SYNT, NULL, aux_rtbl, + clk = clk_register_aux("gen2_syn_clk", "gen2_syn_gclk", + "gen2_3_par_clk", 0, GEN2_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen2_synth_clk", NULL); - clk_register_clkdev(clk1, "gen2_synth_gate_clk", NULL); + clk_register_clkdev(clk, "gen2_syn_clk", NULL); + clk_register_clkdev(clk1, "gen2_syn_gclk", NULL); - clk = clk_register_aux("gen3_synth_clk", "gen3_synth_gate_clk", - "gen2_3_parent_clk", 0, GEN3_CLK_SYNT, NULL, aux_rtbl, + clk = clk_register_aux("gen3_syn_clk", "gen3_syn_gclk", + "gen2_3_par_clk", 0, GEN3_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen3_synth_clk", NULL); - clk_register_clkdev(clk1, "gen3_synth_gate_clk", NULL); + clk_register_clkdev(clk, "gen3_syn_clk", NULL); + clk_register_clkdev(clk1, "gen3_syn_gclk", NULL); /* clock derived from pll3 clk */ - clk = clk_register_gate(NULL, "usbh_clk", "pll3_48m_clk", 0, - PERIP1_CLK_ENB, USBH_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "usbh_clk", "pll3_clk", 0, PERIP1_CLK_ENB, + USBH_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "usbh_clk", NULL); clk = clk_register_fixed_factor(NULL, "usbh.0_clk", "usbh_clk", 0, 1, @@ -494,8 +490,8 @@ void __init spear3xx_clk_init(void) 1); clk_register_clkdev(clk, "usbh.1_clk", NULL); - clk = clk_register_gate(NULL, "usbd_clk", "pll3_48m_clk", 0, - PERIP1_CLK_ENB, USBD_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "usbd_clk", "pll3_clk", 0, PERIP1_CLK_ENB, + USBD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "designware_udc"); /* clock derived from ahb clk */ @@ -579,29 +575,25 @@ void __init spear3xx_clk_init(void) RAS_CLK_ENB, RAS_PLL2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "ras_pll2_clk", NULL); - clk = clk_register_gate(NULL, "ras_pll3_48m_clk", "pll3_48m_clk", 0, + clk = clk_register_gate(NULL, "ras_pll3_clk", "pll3_clk", 0, RAS_CLK_ENB, RAS_48M_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_pll3_48m_clk", NULL); + clk_register_clkdev(clk, "ras_pll3_clk", NULL); - clk = clk_register_gate(NULL, "ras_gen0_synth_gate_clk", - "gen0_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT0_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen0_synth_gate_clk", NULL); + clk = clk_register_gate(NULL, "ras_syn0_gclk", "gen0_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT0_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn0_gclk", NULL); - clk = clk_register_gate(NULL, "ras_gen1_synth_gate_clk", - "gen1_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT1_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen1_synth_gate_clk", NULL); + clk = clk_register_gate(NULL, "ras_syn1_gclk", "gen1_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT1_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn1_gclk", NULL); - clk = clk_register_gate(NULL, "ras_gen2_synth_gate_clk", - "gen2_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT2_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen2_synth_gate_clk", NULL); + clk = clk_register_gate(NULL, "ras_syn2_gclk", "gen2_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT2_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn2_gclk", NULL); - clk = clk_register_gate(NULL, "ras_gen3_synth_gate_clk", - "gen3_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT3_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen3_synth_gate_clk", NULL); + clk = clk_register_gate(NULL, "ras_syn3_gclk", "gen3_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT3_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn3_gclk", NULL); if (of_machine_is_compatible("st,spear300")) spear300_clk_init(); diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c index 61026ae564a..a98d0866f54 100644 --- a/drivers/clk/spear/spear6xx_clock.c +++ b/drivers/clk/spear/spear6xx_clock.c @@ -97,13 +97,12 @@ static struct aux_rate_tbl aux_rtbl[] = { {.xscale = 1, .yscale = 2, .eq = 1}, /* 166 MHz */ }; -static const char *clcd_parents[] = { "pll3_48m_clk", "clcd_synth_gate_clk", }; -static const char *firda_parents[] = { "pll3_48m_clk", "firda_synth_gate_clk", -}; -static const char *uart_parents[] = { "pll3_48m_clk", "uart_synth_gate_clk", }; -static const char *gpt0_1_parents[] = { "pll3_48m_clk", "gpt0_1_synth_clk", }; -static const char *gpt2_parents[] = { "pll3_48m_clk", "gpt2_synth_clk", }; -static const char *gpt3_parents[] = { "pll3_48m_clk", "gpt3_synth_clk", }; +static const char *clcd_parents[] = { "pll3_clk", "clcd_syn_gclk", }; +static const char *firda_parents[] = { "pll3_clk", "firda_syn_gclk", }; +static const char *uart_parents[] = { "pll3_clk", "uart_syn_gclk", }; +static const char *gpt0_1_parents[] = { "pll3_clk", "gpt0_1_syn_clk", }; +static const char *gpt2_parents[] = { "pll3_clk", "gpt2_syn_clk", }; +static const char *gpt3_parents[] = { "pll3_clk", "gpt3_syn_clk", }; static const char *ddr_parents[] = { "ahb_clk", "ahbmult2_clk", "none", "pll2_clk", }; @@ -136,9 +135,9 @@ void __init spear6xx_clk_init(void) clk_register_clkdev(clk, NULL, "rtc-spear"); /* clock derived from 30 MHz osc clk */ - clk = clk_register_fixed_rate(NULL, "pll3_48m_clk", "osc_24m_clk", 0, + clk = clk_register_fixed_rate(NULL, "pll3_clk", "osc_24m_clk", 0, 48000000); - clk_register_clkdev(clk, "pll3_48m_clk", NULL); + clk_register_clkdev(clk, "pll3_clk", NULL); clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "osc_30m_clk", 0, PLL1_CTR, PLL1_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), @@ -146,9 +145,9 @@ void __init spear6xx_clk_init(void) clk_register_clkdev(clk, "vco1_clk", NULL); clk_register_clkdev(clk1, "pll1_clk", NULL); - clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, - "osc_30m_clk", 0, PLL2_CTR, PLL2_FRQ, pll_rtbl, - ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); + clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "osc_30m_clk", + 0, PLL2_CTR, PLL2_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), + &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco2_clk", NULL); clk_register_clkdev(clk1, "pll2_clk", NULL); @@ -165,111 +164,111 @@ void __init spear6xx_clk_init(void) HCLK_RATIO_MASK, 0, &_lock); clk_register_clkdev(clk, "ahb_clk", NULL); - clk = clk_register_aux("uart_synth_clk", "uart_synth_gate_clk", - "pll1_clk", 0, UART_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart_synth_clk", NULL); - clk_register_clkdev(clk1, "uart_synth_gate_clk", NULL); + clk = clk_register_aux("uart_syn_clk", "uart_syn_gclk", "pll1_clk", 0, + UART_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "uart_syn_clk", NULL); + clk_register_clkdev(clk1, "uart_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, PERIP_CLK_CFG, UART_CLK_SHIFT, UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart_mux_clk", NULL); + clk_register_clkdev(clk, "uart_mclk", NULL); - clk = clk_register_gate(NULL, "uart0", "uart_mux_clk", 0, - PERIP1_CLK_ENB, UART0_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "uart0", "uart_mclk", 0, PERIP1_CLK_ENB, + UART0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "d0000000.serial"); - clk = clk_register_gate(NULL, "uart1", "uart_mux_clk", 0, - PERIP1_CLK_ENB, UART1_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "uart1", "uart_mclk", 0, PERIP1_CLK_ENB, + UART1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "d0080000.serial"); - clk = clk_register_aux("firda_synth_clk", "firda_synth_gate_clk", - "pll1_clk", 0, FIRDA_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "firda_synth_clk", NULL); - clk_register_clkdev(clk1, "firda_synth_gate_clk", NULL); + clk = clk_register_aux("firda_syn_clk", "firda_syn_gclk", "pll1_clk", + 0, FIRDA_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "firda_syn_clk", NULL); + clk_register_clkdev(clk1, "firda_syn_gclk", NULL); - clk = clk_register_mux(NULL, "firda_mux_clk", firda_parents, + clk = clk_register_mux(NULL, "firda_mclk", firda_parents, ARRAY_SIZE(firda_parents), 0, PERIP_CLK_CFG, FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "firda_mux_clk", NULL); + clk_register_clkdev(clk, "firda_mclk", NULL); - clk = clk_register_gate(NULL, "firda_clk", "firda_mux_clk", 0, + clk = clk_register_gate(NULL, "firda_clk", "firda_mclk", 0, PERIP1_CLK_ENB, FIRDA_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "firda"); - clk = clk_register_aux("clcd_synth_clk", "clcd_synth_gate_clk", - "pll1_clk", 0, CLCD_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "clcd_synth_clk", NULL); - clk_register_clkdev(clk1, "clcd_synth_gate_clk", NULL); + clk = clk_register_aux("clcd_syn_clk", "clcd_syn_gclk", "pll1_clk", + 0, CLCD_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "clcd_syn_clk", NULL); + clk_register_clkdev(clk1, "clcd_syn_gclk", NULL); - clk = clk_register_mux(NULL, "clcd_mux_clk", clcd_parents, + clk = clk_register_mux(NULL, "clcd_mclk", clcd_parents, ARRAY_SIZE(clcd_parents), 0, PERIP_CLK_CFG, CLCD_CLK_SHIFT, CLCD_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "clcd_mux_clk", NULL); + clk_register_clkdev(clk, "clcd_mclk", NULL); - clk = clk_register_gate(NULL, "clcd_clk", "clcd_mux_clk", 0, + clk = clk_register_gate(NULL, "clcd_clk", "clcd_mclk", 0, PERIP1_CLK_ENB, CLCD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "clcd"); /* gpt clocks */ - clk = clk_register_gpt("gpt0_1_synth_clk", "pll1_clk", 0, PRSC0_CLK_CFG, + clk = clk_register_gpt("gpt0_1_syn_clk", "pll1_clk", 0, PRSC0_CLK_CFG, gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk_register_clkdev(clk, "gpt0_1_synth_clk", NULL); + clk_register_clkdev(clk, "gpt0_1_syn_clk", NULL); - clk = clk_register_mux(NULL, "gpt0_mux_clk", gpt0_1_parents, + clk = clk_register_mux(NULL, "gpt0_mclk", gpt0_1_parents, ARRAY_SIZE(gpt0_1_parents), 0, PERIP_CLK_CFG, GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt0_1_parents, + clk = clk_register_mux(NULL, "gpt1_mclk", gpt0_1_parents, ARRAY_SIZE(gpt0_1_parents), 0, PERIP_CLK_CFG, GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); + clk_register_clkdev(clk, "gpt1_mclk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, PERIP1_CLK_ENB, GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk = clk_register_gpt("gpt2_synth_clk", "pll1_clk", 0, PRSC1_CLK_CFG, + clk = clk_register_gpt("gpt2_syn_clk", "pll1_clk", 0, PRSC1_CLK_CFG, gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk_register_clkdev(clk, "gpt2_synth_clk", NULL); + clk_register_clkdev(clk, "gpt2_syn_clk", NULL); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt2_parents, + clk = clk_register_mux(NULL, "gpt2_mclk", gpt2_parents, ARRAY_SIZE(gpt2_parents), 0, PERIP_CLK_CFG, GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); + clk_register_clkdev(clk, "gpt2_mclk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, PERIP1_CLK_ENB, GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); - clk = clk_register_gpt("gpt3_synth_clk", "pll1_clk", 0, PRSC2_CLK_CFG, + clk = clk_register_gpt("gpt3_syn_clk", "pll1_clk", 0, PRSC2_CLK_CFG, gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk_register_clkdev(clk, "gpt3_synth_clk", NULL); + clk_register_clkdev(clk, "gpt3_syn_clk", NULL); - clk = clk_register_mux(NULL, "gpt3_mux_clk", gpt3_parents, + clk = clk_register_mux(NULL, "gpt3_mclk", gpt3_parents, ARRAY_SIZE(gpt3_parents), 0, PERIP_CLK_CFG, GPT3_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt3_mux_clk", NULL); + clk_register_clkdev(clk, "gpt3_mclk", NULL); - clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mux_clk", 0, + clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0, PERIP1_CLK_ENB, GPT3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt3"); /* clock derived from pll3 clk */ - clk = clk_register_gate(NULL, "usbh0_clk", "pll3_48m_clk", 0, + clk = clk_register_gate(NULL, "usbh0_clk", "pll3_clk", 0, PERIP1_CLK_ENB, USBH0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "usbh.0_clk"); - clk = clk_register_gate(NULL, "usbh1_clk", "pll3_48m_clk", 0, + clk = clk_register_gate(NULL, "usbh1_clk", "pll3_clk", 0, PERIP1_CLK_ENB, USBH1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "usbh.1_clk"); - clk = clk_register_gate(NULL, "usbd_clk", "pll3_48m_clk", 0, - PERIP1_CLK_ENB, USBD_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "usbd_clk", "pll3_clk", 0, PERIP1_CLK_ENB, + USBD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "designware_udc"); /* clock derived from ahb clk */ @@ -278,9 +277,8 @@ void __init spear6xx_clk_init(void) clk_register_clkdev(clk, "ahbmult2_clk", NULL); clk = clk_register_mux(NULL, "ddr_clk", ddr_parents, - ARRAY_SIZE(ddr_parents), - 0, PLL_CLK_CFG, MCTR_CLK_SHIFT, MCTR_CLK_MASK, 0, - &_lock); + ARRAY_SIZE(ddr_parents), 0, PLL_CLK_CFG, MCTR_CLK_SHIFT, + MCTR_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "ddr_clk", NULL); clk = clk_register_divider(NULL, "apb_clk", "ahb_clk", diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c index 9764045428c..b7e7b49d8f6 100644 --- a/drivers/gpu/drm/gma500/cdv_device.c +++ b/drivers/gpu/drm/gma500/cdv_device.c @@ -78,21 +78,6 @@ static int cdv_backlight_combination_mode(struct drm_device *dev) return REG_READ(BLC_PWM_CTL2) & PWM_LEGACY_MODE; } -static int cdv_get_brightness(struct backlight_device *bd) -{ - struct drm_device *dev = bl_get_data(bd); - u32 val = REG_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK; - - if (cdv_backlight_combination_mode(dev)) { - u8 lbpc; - - val &= ~1; - pci_read_config_byte(dev->pdev, 0xF4, &lbpc); - val *= lbpc; - } - return val; -} - static u32 cdv_get_max_backlight(struct drm_device *dev) { u32 max = REG_READ(BLC_PWM_CTL); @@ -110,6 +95,22 @@ static u32 cdv_get_max_backlight(struct drm_device *dev) return max; } +static int cdv_get_brightness(struct backlight_device *bd) +{ + struct drm_device *dev = bl_get_data(bd); + u32 val = REG_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK; + + if (cdv_backlight_combination_mode(dev)) { + u8 lbpc; + + val &= ~1; + pci_read_config_byte(dev->pdev, 0xF4, &lbpc); + val *= lbpc; + } + return (val * 100)/cdv_get_max_backlight(dev); + +} + static int cdv_set_brightness(struct backlight_device *bd) { struct drm_device *dev = bl_get_data(bd); @@ -120,6 +121,9 @@ static int cdv_set_brightness(struct backlight_device *bd) if (level < 1) level = 1; + level *= cdv_get_max_backlight(dev); + level /= 100; + if (cdv_backlight_combination_mode(dev)) { u32 max = cdv_get_max_backlight(dev); u8 lbpc; @@ -157,7 +161,6 @@ static int cdv_backlight_init(struct drm_device *dev) cdv_backlight_device->props.brightness = cdv_get_brightness(cdv_backlight_device); - cdv_backlight_device->props.max_brightness = cdv_get_max_backlight(dev); backlight_update_status(cdv_backlight_device); dev_priv->backlight_device = cdv_backlight_device; return 0; diff --git a/drivers/gpu/drm/gma500/opregion.c b/drivers/gpu/drm/gma500/opregion.c index 4f186eca3a3..c430bd42468 100644 --- a/drivers/gpu/drm/gma500/opregion.c +++ b/drivers/gpu/drm/gma500/opregion.c @@ -144,6 +144,8 @@ struct opregion_asle { #define ASLE_CBLV_VALID (1<<31) +static struct psb_intel_opregion *system_opregion; + static u32 asle_set_backlight(struct drm_device *dev, u32 bclp) { struct drm_psb_private *dev_priv = dev->dev_private; @@ -205,7 +207,7 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev) struct drm_psb_private *dev_priv = dev->dev_private; struct opregion_asle *asle = dev_priv->opregion.asle; - if (asle) { + if (asle && system_opregion ) { /* Don't do this on Medfield or other non PC like devices, they use the bit for something different altogether */ psb_enable_pipestat(dev_priv, 0, PIPE_LEGACY_BLC_EVENT_ENABLE); @@ -221,7 +223,6 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev) #define ACPI_EV_LID (1<<1) #define ACPI_EV_DOCK (1<<2) -static struct psb_intel_opregion *system_opregion; static int psb_intel_opregion_video_event(struct notifier_block *nb, unsigned long val, void *data) @@ -266,9 +267,6 @@ void psb_intel_opregion_init(struct drm_device *dev) system_opregion = opregion; register_acpi_notifier(&psb_intel_opregion_notifier); } - - if (opregion->asle) - psb_intel_opregion_enable_asle(dev); } void psb_intel_opregion_fini(struct drm_device *dev) diff --git a/drivers/gpu/drm/gma500/opregion.h b/drivers/gpu/drm/gma500/opregion.h index 72dc6b92126..4a90f8b0e16 100644 --- a/drivers/gpu/drm/gma500/opregion.h +++ b/drivers/gpu/drm/gma500/opregion.h @@ -27,6 +27,7 @@ extern void psb_intel_opregion_asle_intr(struct drm_device *dev); extern void psb_intel_opregion_init(struct drm_device *dev); extern void psb_intel_opregion_fini(struct drm_device *dev); extern int psb_intel_opregion_setup(struct drm_device *dev); +extern void psb_intel_opregion_enable_asle(struct drm_device *dev); #else @@ -46,4 +47,8 @@ extern inline int psb_intel_opregion_setup(struct drm_device *dev) { return 0; } + +extern inline void psb_intel_opregion_enable_asle(struct drm_device *dev) +{ +} #endif diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c index eff039bf92d..5971bc82b76 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -144,6 +144,10 @@ static int psb_backlight_init(struct drm_device *dev) psb_backlight_device->props.max_brightness = 100; backlight_update_status(psb_backlight_device); dev_priv->backlight_device = psb_backlight_device; + + /* This must occur after the backlight is properly initialised */ + psb_lid_timer_init(dev_priv); + return 0; } @@ -354,13 +358,6 @@ static int psb_chip_setup(struct drm_device *dev) return 0; } -/* Not exactly an erratum more an irritation */ -static void psb_chip_errata(struct drm_device *dev) -{ - struct drm_psb_private *dev_priv = dev->dev_private; - psb_lid_timer_init(dev_priv); -} - static void psb_chip_teardown(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; @@ -379,7 +376,6 @@ const struct psb_ops psb_chip_ops = { .sgx_offset = PSB_SGX_OFFSET, .chip_setup = psb_chip_setup, .chip_teardown = psb_chip_teardown, - .errata = psb_chip_errata, .crtc_helper = &psb_intel_helper_funcs, .crtc_funcs = &psb_intel_crtc_funcs, diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index caba6e08693..a8858a907f4 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -374,6 +374,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset) if (ret) return ret; + psb_intel_opregion_enable_asle(dev); #if 0 /*enable runtime pm at last*/ pm_runtime_enable(&dev->pdev->dev); diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index bef04c19276..3fda8c87f02 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -386,6 +386,7 @@ config HID_MULTITOUCH - Unitec Panels - XAT optical touch panels - Xiroku optical touch panels + - Zytronic touch panels If unsure, say N. diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 875ff451842..32039235cfe 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -659,6 +659,9 @@ #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 #define USB_DEVICE_ID_SAMSUNG_WIRELESS_KBD_MOUSE 0x0600 +#define USB_VENDOR_ID_SENNHEISER 0x1395 +#define USB_DEVICE_ID_SENNHEISER_BTD500USB 0x002c + #define USB_VENDOR_ID_SIGMA_MICRO 0x1c4f #define USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD 0x0002 @@ -808,6 +811,9 @@ #define USB_VENDOR_ID_ZYDACRON 0x13EC #define USB_DEVICE_ID_ZYDACRON_REMOTE_CONTROL 0x0006 +#define USB_VENDOR_ID_ZYTRONIC 0x14c8 +#define USB_DEVICE_ID_ZYTRONIC_ZXY100 0x0005 + #define USB_VENDOR_ID_PRIMAX 0x0461 #define USB_DEVICE_ID_PRIMAX_KEYBOARD 0x4e05 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 132b0019365..5301006f6c1 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -301,6 +301,9 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI), + HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, {} }; diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 6e3332a9997..76479246d4e 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1048,6 +1048,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR2) }, + /* Zytronic panels */ + { .driver_data = MT_CLS_SERIAL, + MT_USB_DEVICE(USB_VENDOR_ID_ZYTRONIC, + USB_DEVICE_ID_ZYTRONIC_ZXY100) }, + /* Generic MT device */ { HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) }, { } diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 0597ee604f6..903eef3d3e1 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -76,6 +76,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_PRODIGE, USB_DEVICE_ID_PRODIGE_CORDLESS, HID_QUIRK_NOGET }, { USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NOGET }, { USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB, HID_QUIRK_NOGET }, { USB_VENDOR_ID_SUN, USB_DEVICE_ID_RARITAN_KVM_DONGLE, HID_QUIRK_NOGET }, { USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_1, HID_QUIRK_NOGET }, { USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_2, HID_QUIRK_NOGET }, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 5c1bc995e56..f10221f4080 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -123,7 +123,7 @@ static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv, skb_frag_size_set(frag, size); skb->data_len += size; - skb->truesize += size; + skb->truesize += PAGE_SIZE; } else skb_put(skb, length); @@ -156,14 +156,18 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) struct ipoib_dev_priv *priv = netdev_priv(dev); struct sk_buff *skb; int buf_size; + int tailroom; u64 *mapping; - if (ipoib_ud_need_sg(priv->max_ib_mtu)) + if (ipoib_ud_need_sg(priv->max_ib_mtu)) { buf_size = IPOIB_UD_HEAD_SIZE; - else + tailroom = 128; /* reserve some tailroom for IP/TCP headers */ + } else { buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); + tailroom = 0; + } - skb = dev_alloc_skb(buf_size + 4); + skb = dev_alloc_skb(buf_size + tailroom + 4); if (unlikely(!skb)) return NULL; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 3a74e4410fc..86e2f4a62b9 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -26,6 +26,8 @@ * These routines are used by both DMA-remapping and Interrupt-remapping */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* has to precede printk.h */ + #include <linux/pci.h> #include <linux/dmar.h> #include <linux/iova.h> @@ -39,8 +41,6 @@ #include <asm/irq_remapping.h> #include <asm/iommu_table.h> -#define PREFIX "DMAR: " - /* No locks are needed as DMA remapping hardware unit * list is constructed at boot time and hotplug of * these units are not supported by the architecture. @@ -83,16 +83,12 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, * ignore it */ if (!bus) { - printk(KERN_WARNING - PREFIX "Device scope bus [%d] not found\n", - scope->bus); + pr_warn("Device scope bus [%d] not found\n", scope->bus); break; } pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn)); if (!pdev) { - printk(KERN_WARNING PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", - segment, bus->number, path->dev, path->fn); + /* warning will be printed below */ break; } path ++; @@ -100,9 +96,8 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, bus = pdev->subordinate; } if (!pdev) { - printk(KERN_WARNING PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", - segment, scope->bus, path->dev, path->fn); + pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n", + segment, scope->bus, path->dev, path->fn); *dev = NULL; return 0; } @@ -110,9 +105,8 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, pdev->subordinate) || (scope->entry_type == \ ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) { pci_dev_put(pdev); - printk(KERN_WARNING PREFIX - "Device scope type does not match for %s\n", - pci_name(pdev)); + pr_warn("Device scope type does not match for %s\n", + pci_name(pdev)); return -EINVAL; } *dev = pdev; @@ -134,8 +128,7 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt, scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) (*cnt)++; else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) { - printk(KERN_WARNING PREFIX - "Unsupported device scope\n"); + pr_warn("Unsupported device scope\n"); } start += scope->length; } @@ -261,25 +254,23 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header) case ACPI_DMAR_TYPE_HARDWARE_UNIT: drhd = container_of(header, struct acpi_dmar_hardware_unit, header); - printk (KERN_INFO PREFIX - "DRHD base: %#016Lx flags: %#x\n", + pr_info("DRHD base: %#016Lx flags: %#x\n", (unsigned long long)drhd->address, drhd->flags); break; case ACPI_DMAR_TYPE_RESERVED_MEMORY: rmrr = container_of(header, struct acpi_dmar_reserved_memory, header); - printk (KERN_INFO PREFIX - "RMRR base: %#016Lx end: %#016Lx\n", + pr_info("RMRR base: %#016Lx end: %#016Lx\n", (unsigned long long)rmrr->base_address, (unsigned long long)rmrr->end_address); break; case ACPI_DMAR_TYPE_ATSR: atsr = container_of(header, struct acpi_dmar_atsr, header); - printk(KERN_INFO PREFIX "ATSR flags: %#x\n", atsr->flags); + pr_info("ATSR flags: %#x\n", atsr->flags); break; case ACPI_DMAR_HARDWARE_AFFINITY: rhsa = container_of(header, struct acpi_dmar_rhsa, header); - printk(KERN_INFO PREFIX "RHSA base: %#016Lx proximity domain: %#x\n", + pr_info("RHSA base: %#016Lx proximity domain: %#x\n", (unsigned long long)rhsa->base_address, rhsa->proximity_domain); break; @@ -299,7 +290,7 @@ static int __init dmar_table_detect(void) &dmar_tbl_size); if (ACPI_SUCCESS(status) && !dmar_tbl) { - printk (KERN_WARNING PREFIX "Unable to map DMAR\n"); + pr_warn("Unable to map DMAR\n"); status = AE_NOT_FOUND; } @@ -333,20 +324,18 @@ parse_dmar_table(void) return -ENODEV; if (dmar->width < PAGE_SHIFT - 1) { - printk(KERN_WARNING PREFIX "Invalid DMAR haw\n"); + pr_warn("Invalid DMAR haw\n"); return -EINVAL; } - printk (KERN_INFO PREFIX "Host address width %d\n", - dmar->width + 1); + pr_info("Host address width %d\n", dmar->width + 1); entry_header = (struct acpi_dmar_header *)(dmar + 1); while (((unsigned long)entry_header) < (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - printk(KERN_WARNING PREFIX - "Invalid 0-length structure\n"); + pr_warn("Invalid 0-length structure\n"); ret = -EINVAL; break; } @@ -369,8 +358,7 @@ parse_dmar_table(void) #endif break; default: - printk(KERN_WARNING PREFIX - "Unknown DMAR structure type %d\n", + pr_warn("Unknown DMAR structure type %d\n", entry_header->type); ret = 0; /* for forward compatibility */ break; @@ -469,12 +457,12 @@ int __init dmar_table_init(void) ret = parse_dmar_table(); if (ret) { if (ret != -ENODEV) - printk(KERN_INFO PREFIX "parse DMAR table failure.\n"); + pr_info("parse DMAR table failure.\n"); return ret; } if (list_empty(&dmar_drhd_units)) { - printk(KERN_INFO PREFIX "No DMAR devices found\n"); + pr_info("No DMAR devices found\n"); return -ENODEV; } @@ -506,8 +494,7 @@ int __init check_zero_address(void) (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - printk(KERN_WARNING PREFIX - "Invalid 0-length structure\n"); + pr_warn("Invalid 0-length structure\n"); return 0; } @@ -558,8 +545,7 @@ int __init detect_intel_iommu(void) if (ret && irq_remapping_enabled && cpu_has_x2apic && dmar->flags & 0x1) - printk(KERN_INFO - "Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); + pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); if (ret && !no_iommu && !iommu_detected && !dmar_disabled) { iommu_detected = 1; @@ -579,14 +565,89 @@ int __init detect_intel_iommu(void) } +static void unmap_iommu(struct intel_iommu *iommu) +{ + iounmap(iommu->reg); + release_mem_region(iommu->reg_phys, iommu->reg_size); +} + +/** + * map_iommu: map the iommu's registers + * @iommu: the iommu to map + * @phys_addr: the physical address of the base resgister + * + * Memory map the iommu's registers. Start w/ a single page, and + * possibly expand if that turns out to be insufficent. + */ +static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) +{ + int map_size, err=0; + + iommu->reg_phys = phys_addr; + iommu->reg_size = VTD_PAGE_SIZE; + + if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) { + pr_err("IOMMU: can't reserve memory\n"); + err = -EBUSY; + goto out; + } + + iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size); + if (!iommu->reg) { + pr_err("IOMMU: can't map the region\n"); + err = -ENOMEM; + goto release; + } + + iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); + iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); + + if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { + err = -EINVAL; + warn_invalid_dmar(phys_addr, " returns all ones"); + goto unmap; + } + + /* the registers might be more than one page */ + map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), + cap_max_fault_reg_offset(iommu->cap)); + map_size = VTD_PAGE_ALIGN(map_size); + if (map_size > iommu->reg_size) { + iounmap(iommu->reg); + release_mem_region(iommu->reg_phys, iommu->reg_size); + iommu->reg_size = map_size; + if (!request_mem_region(iommu->reg_phys, iommu->reg_size, + iommu->name)) { + pr_err("IOMMU: can't reserve memory\n"); + err = -EBUSY; + goto out; + } + iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size); + if (!iommu->reg) { + pr_err("IOMMU: can't map the region\n"); + err = -ENOMEM; + goto release; + } + } + err = 0; + goto out; + +unmap: + iounmap(iommu->reg); +release: + release_mem_region(iommu->reg_phys, iommu->reg_size); +out: + return err; +} + int alloc_iommu(struct dmar_drhd_unit *drhd) { struct intel_iommu *iommu; - int map_size; u32 ver; static int iommu_allocated = 0; int agaw = 0; int msagaw = 0; + int err; if (!drhd->reg_base_addr) { warn_invalid_dmar(0, ""); @@ -600,30 +661,22 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->seq_id = iommu_allocated++; sprintf (iommu->name, "dmar%d", iommu->seq_id); - iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE); - if (!iommu->reg) { - printk(KERN_ERR "IOMMU: can't map the region\n"); + err = map_iommu(iommu, drhd->reg_base_addr); + if (err) { + pr_err("IOMMU: failed to map %s\n", iommu->name); goto error; } - iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); - iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); - - if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { - warn_invalid_dmar(drhd->reg_base_addr, " returns all ones"); - goto err_unmap; - } + err = -EINVAL; agaw = iommu_calculate_agaw(iommu); if (agaw < 0) { - printk(KERN_ERR - "Cannot get a valid agaw for iommu (seq_id = %d)\n", - iommu->seq_id); + pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", + iommu->seq_id); goto err_unmap; } msagaw = iommu_calculate_max_sagaw(iommu); if (msagaw < 0) { - printk(KERN_ERR - "Cannot get a valid max agaw for iommu (seq_id = %d)\n", + pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", iommu->seq_id); goto err_unmap; } @@ -632,19 +685,6 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->node = -1; - /* the registers might be more than one page */ - map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), - cap_max_fault_reg_offset(iommu->cap)); - map_size = VTD_PAGE_ALIGN(map_size); - if (map_size > VTD_PAGE_SIZE) { - iounmap(iommu->reg); - iommu->reg = ioremap(drhd->reg_base_addr, map_size); - if (!iommu->reg) { - printk(KERN_ERR "IOMMU: can't map the region\n"); - goto error; - } - } - ver = readl(iommu->reg + DMAR_VER_REG); pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n", iommu->seq_id, @@ -659,10 +699,10 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) return 0; err_unmap: - iounmap(iommu->reg); + unmap_iommu(iommu); error: kfree(iommu); - return -1; + return err; } void free_iommu(struct intel_iommu *iommu) @@ -673,7 +713,8 @@ void free_iommu(struct intel_iommu *iommu) free_dmar_iommu(iommu); if (iommu->reg) - iounmap(iommu->reg); + unmap_iommu(iommu); + kfree(iommu); } @@ -710,7 +751,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index) if (fault & DMA_FSTS_IQE) { head = readl(iommu->reg + DMAR_IQH_REG); if ((head >> DMAR_IQ_SHIFT) == index) { - printk(KERN_ERR "VT-d detected invalid descriptor: " + pr_err("VT-d detected invalid descriptor: " "low=%llx, high=%llx\n", (unsigned long long)qi->desc[index].low, (unsigned long long)qi->desc[index].high); @@ -1129,15 +1170,14 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); if (fault_type == INTR_REMAP) - printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] " + pr_err("INTR-REMAP: Request device [[%02x:%02x.%d] " "fault index %llx\n" "INTR-REMAP:[fault reason %02d] %s\n", (source_id >> 8), PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else - printk(KERN_ERR - "DMAR:[%s] Request device [%02x:%02x.%d] " + pr_err("DMAR:[%s] Request device [%02x:%02x.%d] " "fault addr %llx \n" "DMAR:[fault reason %02d] %s\n", (type ? "DMA Read" : "DMA Write"), @@ -1157,8 +1197,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) raw_spin_lock_irqsave(&iommu->register_lock, flag); fault_status = readl(iommu->reg + DMAR_FSTS_REG); if (fault_status) - printk(KERN_ERR "DRHD: handling fault status reg %x\n", - fault_status); + pr_err("DRHD: handling fault status reg %x\n", fault_status); /* TBD: ignore advanced fault log currently */ if (!(fault_status & DMA_FSTS_PPF)) @@ -1224,7 +1263,7 @@ int dmar_set_interrupt(struct intel_iommu *iommu) irq = create_irq(); if (!irq) { - printk(KERN_ERR "IOMMU: no free vectors\n"); + pr_err("IOMMU: no free vectors\n"); return -EINVAL; } @@ -1241,7 +1280,7 @@ int dmar_set_interrupt(struct intel_iommu *iommu) ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu); if (ret) - printk(KERN_ERR "IOMMU: can't request irq\n"); + pr_err("IOMMU: can't request irq\n"); return ret; } @@ -1258,8 +1297,7 @@ int __init enable_drhd_fault_handling(void) ret = dmar_set_interrupt(iommu); if (ret) { - printk(KERN_ERR "DRHD %Lx: failed to enable fault, " - " interrupt, ret %d\n", + pr_err("DRHD %Lx: failed to enable fault, interrupt, ret %d\n", (unsigned long long)drhd->reg_base_addr, ret); return -1; } diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 6d347064b8b..e0b18f3ae9a 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -902,7 +902,6 @@ static int intel_setup_ioapic_entry(int irq, return 0; } -#ifdef CONFIG_SMP /* * Migrate the IO-APIC irq in the presence of intr-remapping. * @@ -924,6 +923,10 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_cfg *cfg = data->chip_data; unsigned int dest, irq = data->irq; struct irte irte; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -EINVAL; if (!cpumask_intersects(mask, cpu_online_mask)) return -EINVAL; @@ -931,10 +934,16 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, if (get_irte(irq, &irte)) return -EBUSY; - if (assign_irq_vector(irq, cfg, mask)) - return -EBUSY; + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); + err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); @@ -956,7 +965,6 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, cpumask_copy(data->affinity, mask); return 0; } -#endif static void intel_compose_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, @@ -1058,9 +1066,7 @@ struct irq_remap_ops intel_irq_remap_ops = { .reenable = reenable_irq_remapping, .enable_faulting = enable_drhd_fault_handling, .setup_ioapic_entry = intel_setup_ioapic_entry, -#ifdef CONFIG_SMP .set_affinity = intel_ioapic_set_affinity, -#endif .free_irq = free_irte, .compose_msi_msg = intel_compose_msi_msg, .msi_alloc_irq = intel_msi_alloc_irq, diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 40cda8e98d8..1d29b1c66e7 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -111,16 +111,15 @@ int setup_ioapic_remapped_entry(int irq, vector, attr); } -#ifdef CONFIG_SMP int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - if (!remap_ops || !remap_ops->set_affinity) + if (!config_enabled(CONFIG_SMP) || !remap_ops || + !remap_ops->set_affinity) return 0; return remap_ops->set_affinity(data, mask, force); } -#endif void free_remapped_irq(int irq) { diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index be9d72950c5..b12974cc1df 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -59,11 +59,9 @@ struct irq_remap_ops { unsigned int, int, struct io_apic_irq_attr *); -#ifdef CONFIG_SMP /* Set the CPU affinity of a remapped interrupt */ int (*set_affinity)(struct irq_data *data, const struct cpumask *mask, bool force); -#endif /* Free an IRQ */ int (*free_irq)(int); diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index 1a0ae4445ff..5f21f629b7a 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -135,8 +135,8 @@ send_layer2(struct mISDNstack *st, struct sk_buff *skb) skb = NULL; else if (*debug & DEBUG_SEND_ERR) printk(KERN_DEBUG - "%s ch%d mgr prim(%x) addr(%x) err %d\n", - __func__, ch->nr, hh->prim, ch->addr, ret); + "%s mgr prim(%x) err %d\n", + __func__, hh->prim, ret); } out: mutex_unlock(&st->lmutex); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index d039de8322f..b58b7a33914 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1084,6 +1084,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->split_io = dm_rh_get_region_size(ms->rh); ti->num_flush_requests = 1; ti->num_discard_requests = 1; + ti->discard_zeroes_data_unsupported = 1; ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); @@ -1214,7 +1215,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, * We need to dec pending if this was a write. */ if (rw == WRITE) { - if (!(bio->bi_rw & REQ_FLUSH)) + if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) dm_rh_dec(ms->rh, map_context->ll); return error; } diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 7771ed21218..69732e03eb3 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -404,6 +404,9 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio) return; } + if (bio->bi_rw & REQ_DISCARD) + return; + /* We must inform the log that the sync count has changed. */ log->type->set_region_sync(log, region, 0); @@ -524,7 +527,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios) struct bio *bio; for (bio = bios->head; bio; bio = bio->bi_next) { - if (bio->bi_rw & REQ_FLUSH) + if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)) continue; rh_inc(rh, dm_rh_bio_to_region(rh, bio)); } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ce59824fb41..68694da0d21 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1245,7 +1245,10 @@ static void process_discard(struct thin_c *tc, struct bio *bio) cell_release_singleton(cell, bio); cell_release_singleton(cell2, bio); - remap_and_issue(tc, bio, lookup_result.block); + if ((!lookup_result.shared) && pool->pf.discard_passdown) + remap_and_issue(tc, bio, lookup_result.block); + else + bio_endio(bio, 0); } break; @@ -2628,6 +2631,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) if (tc->pool->pf.discard_enabled) { ti->discards_supported = 1; ti->num_discard_requests = 1; + ti->discard_zeroes_data_unsupported = 1; } dm_put(pool_md); diff --git a/drivers/md/md.c b/drivers/md/md.c index a4c219e3c85..d5ab4493c8b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2931,6 +2931,7 @@ offset_store(struct md_rdev *rdev, const char *buf, size_t len) * can be sane */ return -EBUSY; rdev->data_offset = offset; + rdev->new_data_offset = offset; return len; } @@ -3926,8 +3927,8 @@ array_state_show(struct mddev *mddev, char *page) return sprintf(page, "%s\n", array_states[st]); } -static int do_md_stop(struct mddev * mddev, int ro, int is_open); -static int md_set_readonly(struct mddev * mddev, int is_open); +static int do_md_stop(struct mddev * mddev, int ro, struct block_device *bdev); +static int md_set_readonly(struct mddev * mddev, struct block_device *bdev); static int do_md_run(struct mddev * mddev); static int restart_array(struct mddev *mddev); @@ -3943,14 +3944,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) /* stopping an active array */ if (atomic_read(&mddev->openers) > 0) return -EBUSY; - err = do_md_stop(mddev, 0, 0); + err = do_md_stop(mddev, 0, NULL); break; case inactive: /* stopping an active array */ if (mddev->pers) { if (atomic_read(&mddev->openers) > 0) return -EBUSY; - err = do_md_stop(mddev, 2, 0); + err = do_md_stop(mddev, 2, NULL); } else err = 0; /* already inactive */ break; @@ -3958,7 +3959,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) break; /* not supported yet */ case readonly: if (mddev->pers) - err = md_set_readonly(mddev, 0); + err = md_set_readonly(mddev, NULL); else { mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); @@ -3968,7 +3969,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) case read_auto: if (mddev->pers) { if (mddev->ro == 0) - err = md_set_readonly(mddev, 0); + err = md_set_readonly(mddev, NULL); else if (mddev->ro == 1) err = restart_array(mddev); if (err == 0) { @@ -5351,15 +5352,17 @@ void md_stop(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_stop); -static int md_set_readonly(struct mddev *mddev, int is_open) +static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) { int err = 0; mutex_lock(&mddev->open_mutex); - if (atomic_read(&mddev->openers) > is_open) { + if (atomic_read(&mddev->openers) > !!bdev) { printk("md: %s still in use.\n",mdname(mddev)); err = -EBUSY; goto out; } + if (bdev) + sync_blockdev(bdev); if (mddev->pers) { __md_stop_writes(mddev); @@ -5381,18 +5384,26 @@ out: * 0 - completely stop and dis-assemble array * 2 - stop but do not disassemble array */ -static int do_md_stop(struct mddev * mddev, int mode, int is_open) +static int do_md_stop(struct mddev * mddev, int mode, + struct block_device *bdev) { struct gendisk *disk = mddev->gendisk; struct md_rdev *rdev; mutex_lock(&mddev->open_mutex); - if (atomic_read(&mddev->openers) > is_open || + if (atomic_read(&mddev->openers) > !!bdev || mddev->sysfs_active) { printk("md: %s still in use.\n",mdname(mddev)); mutex_unlock(&mddev->open_mutex); return -EBUSY; } + if (bdev) + /* It is possible IO was issued on some other + * open file which was closed before we took ->open_mutex. + * As that was not the last close __blkdev_put will not + * have called sync_blockdev, so we must. + */ + sync_blockdev(bdev); if (mddev->pers) { if (mddev->ro) @@ -5466,7 +5477,7 @@ static void autorun_array(struct mddev *mddev) err = do_md_run(mddev); if (err) { printk(KERN_WARNING "md: do_md_run() returned %d\n", err); - do_md_stop(mddev, 0, 0); + do_md_stop(mddev, 0, NULL); } } @@ -6481,11 +6492,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto done_unlock; case STOP_ARRAY: - err = do_md_stop(mddev, 0, 1); + err = do_md_stop(mddev, 0, bdev); goto done_unlock; case STOP_ARRAY_RO: - err = md_set_readonly(mddev, 1); + err = md_set_readonly(mddev, bdev); goto done_unlock; case BLKROSET: diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 240ff312504..cacd008d686 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1818,8 +1818,14 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) if (atomic_dec_and_test(&r1_bio->remaining)) { /* if we're here, all write(s) have completed, so clean up */ - md_done_sync(mddev, r1_bio->sectors, 1); - put_buf(r1_bio); + int s = r1_bio->sectors; + if (test_bit(R1BIO_MadeGood, &r1_bio->state) || + test_bit(R1BIO_WriteError, &r1_bio->state)) + reschedule_retry(r1_bio); + else { + put_buf(r1_bio); + md_done_sync(mddev, s, 1); + } } } diff --git a/drivers/media/video/cx25821/cx25821-core.c b/drivers/media/video/cx25821/cx25821-core.c index 83c1aa6b2e6..f11f6f07e91 100644 --- a/drivers/media/video/cx25821/cx25821-core.c +++ b/drivers/media/video/cx25821/cx25821-core.c @@ -904,9 +904,6 @@ static int cx25821_dev_setup(struct cx25821_dev *dev) list_add_tail(&dev->devlist, &cx25821_devlist); mutex_unlock(&cx25821_devlist_mutex); - strcpy(cx25821_boards[UNKNOWN_BOARD].name, "unknown"); - strcpy(cx25821_boards[CX25821_BOARD].name, "cx25821"); - if (dev->pci->device != 0x8210) { pr_info("%s(): Exiting. Incorrect Hardware device = 0x%02x\n", __func__, dev->pci->device); diff --git a/drivers/media/video/cx25821/cx25821.h b/drivers/media/video/cx25821/cx25821.h index b9aa801b00a..029f2934a6d 100644 --- a/drivers/media/video/cx25821/cx25821.h +++ b/drivers/media/video/cx25821/cx25821.h @@ -187,7 +187,7 @@ enum port { }; struct cx25821_board { - char *name; + const char *name; enum port porta; enum port portb; enum port portc; diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c index 83dbb2ddff1..0cbada18f6f 100644 --- a/drivers/media/video/v4l2-dev.c +++ b/drivers/media/video/v4l2-dev.c @@ -681,6 +681,7 @@ static void determine_valid_ioctls(struct video_device *vdev) SET_VALID_IOCTL(ops, VIDIOC_G_DV_TIMINGS, vidioc_g_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_ENUM_DV_TIMINGS, vidioc_enum_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_QUERY_DV_TIMINGS, vidioc_query_dv_timings); + SET_VALID_IOCTL(ops, VIDIOC_DV_TIMINGS_CAP, vidioc_dv_timings_cap); /* yes, really vidioc_subscribe_event */ SET_VALID_IOCTL(ops, VIDIOC_DQEVENT, vidioc_subscribe_event); SET_VALID_IOCTL(ops, VIDIOC_SUBSCRIBE_EVENT, vidioc_subscribe_event); diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 3680aa251de..2cf084eb9d5 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -6,7 +6,7 @@ #include "bonding.h" #include "bond_alb.h" -#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS) #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b9c2ae62166..2ee76993f05 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3227,6 +3227,12 @@ static int bond_master_netdev_event(unsigned long event, switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); + case NETDEV_UNREGISTER: + bond_remove_proc_entry(event_bond); + break; + case NETDEV_REGISTER: + bond_create_proc_entry(event_bond); + break; default: break; } @@ -4411,8 +4417,6 @@ static void bond_uninit(struct net_device *bond_dev) bond_work_cancel_all(bond); - bond_remove_proc_entry(bond); - bond_debug_unregister(bond); __hw_addr_flush(&bond->mc_list); @@ -4814,7 +4818,6 @@ static int bond_init(struct net_device *bond_dev) bond_set_lockdep_class(bond_dev); - bond_create_proc_entry(bond); list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 9cc15701101..1f78b63d5ef 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -261,7 +261,6 @@ static void atl1c_check_link_status(struct atl1c_adapter *adapter) if ((phy_data & BMSR_LSTATUS) == 0) { /* link down */ netif_carrier_off(netdev); - netif_stop_queue(netdev); hw->hibernate = true; if (atl1c_reset_mac(hw) != 0) if (netif_msg_hw(adapter)) diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 46b8b7d8163..d09c6b583d1 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -656,7 +656,7 @@ static int b44_alloc_rx_skb(struct b44 *bp, int src_idx, u32 dest_idx_unmasked) dma_unmap_single(bp->sdev->dma_dev, mapping, RX_PKT_BUF_SZ, DMA_FROM_DEVICE); dev_kfree_skb_any(skb); - skb = __netdev_alloc_skb(bp->dev, RX_PKT_BUF_SZ, GFP_ATOMIC|GFP_DMA); + skb = alloc_skb(RX_PKT_BUF_SZ, GFP_ATOMIC | GFP_DMA); if (skb == NULL) return -ENOMEM; mapping = dma_map_single(bp->sdev->dma_dev, skb->data, @@ -967,7 +967,7 @@ static netdev_tx_t b44_start_xmit(struct sk_buff *skb, struct net_device *dev) dma_unmap_single(bp->sdev->dma_dev, mapping, len, DMA_TO_DEVICE); - bounce_skb = __netdev_alloc_skb(dev, len, GFP_ATOMIC | GFP_DMA); + bounce_skb = alloc_skb(len, GFP_ATOMIC | GFP_DMA); if (!bounce_skb) goto err_out; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index ac7b7448853..1fa4927a45b 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -5372,7 +5372,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp) int k, last; if (skb == NULL) { - j++; + j = NEXT_TX_BD(j); continue; } @@ -5384,8 +5384,8 @@ bnx2_free_tx_skbs(struct bnx2 *bp) tx_buf->skb = NULL; last = tx_buf->nr_frags; - j++; - for (k = 0; k < last; k++, j++) { + j = NEXT_TX_BD(j); + for (k = 0; k < last; k++, j = NEXT_TX_BD(j)) { tx_buf = &txr->tx_buf_ring[TX_RING_IDX(j)]; dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(tx_buf, mapping), diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index c95e7b5e2b8..2c89d17cbb2 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -534,7 +534,8 @@ int cnic_unregister_driver(int ulp_type) } if (atomic_read(&ulp_ops->ref_count) != 0) - netdev_warn(dev->netdev, "Failed waiting for ref count to go to zero\n"); + pr_warn("%s: Failed waiting for ref count to go to zero\n", + __func__); return 0; out_unlock: @@ -1053,12 +1054,13 @@ static int cnic_init_uio(struct cnic_dev *dev) uinfo = &udev->cnic_uinfo; - uinfo->mem[0].addr = dev->netdev->base_addr; + uinfo->mem[0].addr = pci_resource_start(dev->pcidev, 0); uinfo->mem[0].internal_addr = dev->regview; - uinfo->mem[0].size = dev->netdev->mem_end - dev->netdev->mem_start; uinfo->mem[0].memtype = UIO_MEM_PHYS; if (test_bit(CNIC_F_BNX2_CLASS, &dev->flags)) { + uinfo->mem[0].size = MB_GET_CID_ADDR(TX_TSS_CID + + TX_MAX_TSS_RINGS + 1); uinfo->mem[1].addr = (unsigned long) cp->status_blk.gen & PAGE_MASK; if (cp->ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) @@ -1068,6 +1070,8 @@ static int cnic_init_uio(struct cnic_dev *dev) uinfo->name = "bnx2_cnic"; } else if (test_bit(CNIC_F_BNX2X_CLASS, &dev->flags)) { + uinfo->mem[0].size = pci_resource_len(dev->pcidev, 0); + uinfo->mem[1].addr = (unsigned long) cp->bnx2x_def_status_blk & PAGE_MASK; uinfo->mem[1].size = sizeof(*cp->bnx2x_def_status_blk); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f2db8fca46a..ab1d80ff079 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2063,10 +2063,9 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - /* Steal sock reference for processing TX time stamps */ - swap(skb_new->sk, skb->sk); - swap(skb_new->destructor, skb->destructor); - kfree_skb(skb); + if (skb->sk) + skb_set_owner_w(skb_new, skb->sk); + consume_skb(skb); skb = skb_new; } diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 36db4df09ae..1f063dcd8f8 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1572,6 +1572,9 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) ctrl = er32(CTRL); status = er32(STATUS); rxcw = er32(RXCW); + /* SYNCH bit and IV bit are sticky */ + udelay(10); + rxcw = er32(RXCW); if ((rxcw & E1000_RXCW_SYNCH) && !(rxcw & E1000_RXCW_IV)) { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 238ab2f8a5e..e3a7b07df62 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -325,24 +325,46 @@ static inline void __ew32flash(struct e1000_hw *hw, unsigned long reg, u32 val) **/ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) { - u16 phy_reg; - u32 phy_id; + u16 phy_reg = 0; + u32 phy_id = 0; + s32 ret_val; + u16 retry_count; + + for (retry_count = 0; retry_count < 2; retry_count++) { + ret_val = e1e_rphy_locked(hw, PHY_ID1, &phy_reg); + if (ret_val || (phy_reg == 0xFFFF)) + continue; + phy_id = (u32)(phy_reg << 16); - e1e_rphy_locked(hw, PHY_ID1, &phy_reg); - phy_id = (u32)(phy_reg << 16); - e1e_rphy_locked(hw, PHY_ID2, &phy_reg); - phy_id |= (u32)(phy_reg & PHY_REVISION_MASK); + ret_val = e1e_rphy_locked(hw, PHY_ID2, &phy_reg); + if (ret_val || (phy_reg == 0xFFFF)) { + phy_id = 0; + continue; + } + phy_id |= (u32)(phy_reg & PHY_REVISION_MASK); + break; + } if (hw->phy.id) { if (hw->phy.id == phy_id) return true; - } else { - if ((phy_id != 0) && (phy_id != PHY_REVISION_MASK)) - hw->phy.id = phy_id; + } else if (phy_id) { + hw->phy.id = phy_id; + hw->phy.revision = (u32)(phy_reg & ~PHY_REVISION_MASK); return true; } - return false; + /* + * In case the PHY needs to be in mdio slow mode, + * set slow mode and try to get the PHY id again. + */ + hw->phy.ops.release(hw); + ret_val = e1000_set_mdio_slow_mode_hv(hw); + if (!ret_val) + ret_val = e1000e_get_phy_id(hw); + hw->phy.ops.acquire(hw); + + return !ret_val; } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 18ca3bcadf0..e242104ab47 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6647,6 +6647,11 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) return -EINVAL; } + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + e_err(drv, "Enable failed, SR-IOV enabled\n"); + return -EINVAL; + } + /* Hardware supports up to 8 traffic classes */ if (tc > adapter->dcb_cfg.num_tcs.pg_tcs || (hw->mac.type == ixgbe_mac_82598EB && diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index f69ec4288b1..41e32257a4e 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -201,6 +201,9 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, unsigned int i, eop, count = 0; unsigned int total_bytes = 0, total_packets = 0; + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return true; + i = tx_ring->next_to_clean; eop = tx_ring->tx_buffer_info[i].next_to_watch; eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop); @@ -969,8 +972,6 @@ static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data) r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues); for (i = 0; i < q_vector->txr_count; i++) { tx_ring = &(adapter->tx_ring[r_idx]); - tx_ring->total_bytes = 0; - tx_ring->total_packets = 0; ixgbevf_clean_tx_irq(adapter, tx_ring); r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues, r_idx + 1); @@ -994,16 +995,6 @@ static irqreturn_t ixgbevf_msix_clean_rx(int irq, void *data) struct ixgbe_hw *hw = &adapter->hw; struct ixgbevf_ring *rx_ring; int r_idx; - int i; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - rx_ring->total_bytes = 0; - rx_ring->total_packets = 0; - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } if (!q_vector->rxr_count) return IRQ_HANDLED; diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index fb8377da168..4b785e10f2e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -51,7 +51,7 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum); - + wmb(); entry = (++priv->cur_tx) % txsize; desc = priv->dma_tx + entry; @@ -59,6 +59,7 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) len, DMA_TO_DEVICE); desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 0, len, csum); + wmb(); priv->hw->desc->set_tx_owner(desc); priv->tx_skbuff[entry] = NULL; } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 51b3b68528e..ea3003edde1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1212,6 +1212,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion); wmb(); priv->hw->desc->set_tx_owner(desc); + wmb(); } /* Interrupt on completition only for the latest segment */ @@ -1227,6 +1228,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* To avoid raise condition */ priv->hw->desc->set_tx_owner(first); + wmb(); priv->cur_tx++; @@ -1290,6 +1292,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) } wmb(); priv->hw->desc->set_rx_owner(p + entry); + wmb(); } } diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 39ea0674dcd..5c120189ec8 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -46,7 +46,13 @@ static int mdio_mux_read(struct mii_bus *bus, int phy_id, int regnum) struct mdio_mux_parent_bus *pb = cb->parent; int r; - mutex_lock(&pb->mii_bus->mdio_lock); + /* In theory multiple mdio_mux could be stacked, thus creating + * more than a single level of nesting. But in practice, + * SINGLE_DEPTH_NESTING will cover the vast majority of use + * cases. We use it, instead of trying to handle the general + * case. + */ + mutex_lock_nested(&pb->mii_bus->mdio_lock, SINGLE_DEPTH_NESTING); r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data); if (r) goto out; @@ -71,7 +77,7 @@ static int mdio_mux_write(struct mii_bus *bus, int phy_id, int r; - mutex_lock(&pb->mii_bus->mdio_lock); + mutex_lock_nested(&pb->mii_bus->mdio_lock, SINGLE_DEPTH_NESTING); r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data); if (r) goto out; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index b01960fcfbc..a051cedd64b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -346,6 +346,15 @@ static const struct driver_info qmi_wwan_force_int1 = { .data = BIT(1), /* interface whitelist bitmap */ }; +static const struct driver_info qmi_wwan_force_int2 = { + .description = "Qualcomm WWAN/QMI device", + .flags = FLAG_WWAN, + .bind = qmi_wwan_bind_shared, + .unbind = qmi_wwan_unbind_shared, + .manage_power = qmi_wwan_manage_power, + .data = BIT(2), /* interface whitelist bitmap */ +}; + static const struct driver_info qmi_wwan_force_int3 = { .description = "Qualcomm WWAN/QMI device", .flags = FLAG_WWAN, @@ -498,6 +507,15 @@ static const struct usb_device_id products[] = { .bInterfaceProtocol = 0xff, .driver_info = (unsigned long)&qmi_wwan_force_int4, }, + { /* ZTE MF60 */ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x19d2, + .idProduct = 0x1402, + .bInterfaceClass = 0xff, + .bInterfaceSubClass = 0xff, + .bInterfaceProtocol = 0xff, + .driver_info = (unsigned long)&qmi_wwan_force_int2, + }, { /* Sierra Wireless MC77xx in QMI mode */ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, .idVendor = 0x1199, diff --git a/drivers/net/wireless/b43legacy/dma.c b/drivers/net/wireless/b43legacy/dma.c index f1f8bd09bd8..c8baf020c20 100644 --- a/drivers/net/wireless/b43legacy/dma.c +++ b/drivers/net/wireless/b43legacy/dma.c @@ -1072,7 +1072,7 @@ static int dma_tx_fragment(struct b43legacy_dmaring *ring, meta->dmaaddr = map_descbuffer(ring, skb->data, skb->len, 1); /* create a bounce buffer in zone_dma on mapping failure. */ if (b43legacy_dma_mapping_error(ring, meta->dmaaddr, skb->len, 1)) { - bounce_skb = __dev_alloc_skb(skb->len, GFP_ATOMIC | GFP_DMA); + bounce_skb = alloc_skb(skb->len, GFP_ATOMIC | GFP_DMA); if (!bounce_skb) { ring->current_slot = old_top_slot; ring->used_slots = old_used_slots; diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c index 509301a5e7e..ff5d689e13f 100644 --- a/drivers/net/wireless/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/iwlegacy/4965-mac.c @@ -3405,7 +3405,7 @@ il4965_remove_dynamic_key(struct il_priv *il, return 0; } - if (il->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET) { + if (il->stations[sta_id].sta.key.key_flags & STA_KEY_FLG_INVALID) { IL_WARN("Removing wrong key %d 0x%x\n", keyconf->keyidx, key_flags); spin_unlock_irqrestore(&il->sta_lock, flags); @@ -3420,7 +3420,7 @@ il4965_remove_dynamic_key(struct il_priv *il, memset(&il->stations[sta_id].sta.key, 0, sizeof(struct il4965_keyinfo)); il->stations[sta_id].sta.key.key_flags = STA_KEY_FLG_NO_ENC | STA_KEY_FLG_INVALID; - il->stations[sta_id].sta.key.key_offset = WEP_INVALID_OFFSET; + il->stations[sta_id].sta.key.key_offset = keyconf->hw_key_idx; il->stations[sta_id].sta.sta.modify_mask = STA_MODIFY_KEY_MASK; il->stations[sta_id].sta.mode = STA_CONTROL_MODIFY_MSK; diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c index cbf2dc18341..5d4807c2b56 100644 --- a/drivers/net/wireless/iwlegacy/common.c +++ b/drivers/net/wireless/iwlegacy/common.c @@ -4767,14 +4767,12 @@ il_bg_watchdog(unsigned long data) return; /* monitor and check for other stuck queues */ - if (il_is_any_associated(il)) { - for (cnt = 0; cnt < il->hw_params.max_txq_num; cnt++) { - /* skip as we already checked the command queue */ - if (cnt == il->cmd_queue) - continue; - if (il_check_stuck_queue(il, cnt)) - return; - } + for (cnt = 0; cnt < il->hw_params.max_txq_num; cnt++) { + /* skip as we already checked the command queue */ + if (cnt == il->cmd_queue) + continue; + if (il_check_stuck_queue(il, cnt)) + return; } mod_timer(&il->watchdog, diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index ce61b6fae1c..5c7fd185373 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -958,6 +958,7 @@ static int mwifiex_cfg80211_start_ap(struct wiphy *wiphy, case NL80211_HIDDEN_SSID_ZERO_CONTENTS: /* firmware doesn't support this type of hidden SSID */ default: + kfree(bss_cfg); return -EINVAL; } diff --git a/drivers/net/wireless/rt2x00/rt2x00usb.c b/drivers/net/wireless/rt2x00/rt2x00usb.c index d357d1ed92f..74ecc33fdd9 100644 --- a/drivers/net/wireless/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/rt2x00/rt2x00usb.c @@ -436,8 +436,8 @@ void rt2x00usb_kick_queue(struct data_queue *queue) case QID_RX: if (!rt2x00queue_full(queue)) rt2x00queue_for_each_entry(queue, - Q_INDEX_DONE, Q_INDEX, + Q_INDEX_DONE, NULL, rt2x00usb_kick_rx_entry); break; diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c index efc4b7f308c..f3cfa0b9adf 100644 --- a/drivers/oprofile/oprofile_perf.c +++ b/drivers/oprofile/oprofile_perf.c @@ -1,5 +1,6 @@ /* * Copyright 2010 ARM Ltd. + * Copyright 2012 Advanced Micro Devices, Inc., Robert Richter * * Perf-events backend for OProfile. */ @@ -25,7 +26,7 @@ static int oprofile_perf_enabled; static DEFINE_MUTEX(oprofile_perf_mutex); static struct op_counter_config *counter_config; -static struct perf_event **perf_events[NR_CPUS]; +static DEFINE_PER_CPU(struct perf_event **, perf_events); static int num_counters; /* @@ -38,7 +39,7 @@ static void op_overflow_handler(struct perf_event *event, u32 cpu = smp_processor_id(); for (id = 0; id < num_counters; ++id) - if (perf_events[cpu][id] == event) + if (per_cpu(perf_events, cpu)[id] == event) break; if (id != num_counters) @@ -74,7 +75,7 @@ static int op_create_counter(int cpu, int event) { struct perf_event *pevent; - if (!counter_config[event].enabled || perf_events[cpu][event]) + if (!counter_config[event].enabled || per_cpu(perf_events, cpu)[event]) return 0; pevent = perf_event_create_kernel_counter(&counter_config[event].attr, @@ -91,18 +92,18 @@ static int op_create_counter(int cpu, int event) return -EBUSY; } - perf_events[cpu][event] = pevent; + per_cpu(perf_events, cpu)[event] = pevent; return 0; } static void op_destroy_counter(int cpu, int event) { - struct perf_event *pevent = perf_events[cpu][event]; + struct perf_event *pevent = per_cpu(perf_events, cpu)[event]; if (pevent) { perf_event_release_kernel(pevent); - perf_events[cpu][event] = NULL; + per_cpu(perf_events, cpu)[event] = NULL; } } @@ -257,12 +258,12 @@ void oprofile_perf_exit(void) for_each_possible_cpu(cpu) { for (id = 0; id < num_counters; ++id) { - event = perf_events[cpu][id]; + event = per_cpu(perf_events, cpu)[id]; if (event) perf_event_release_kernel(event); } - kfree(perf_events[cpu]); + kfree(per_cpu(perf_events, cpu)); } kfree(counter_config); @@ -277,8 +278,6 @@ int __init oprofile_perf_init(struct oprofile_operations *ops) if (ret) return ret; - memset(&perf_events, 0, sizeof(perf_events)); - num_counters = perf_num_counters(); if (num_counters <= 0) { pr_info("oprofile: no performance counters\n"); @@ -298,9 +297,9 @@ int __init oprofile_perf_init(struct oprofile_operations *ops) } for_each_possible_cpu(cpu) { - perf_events[cpu] = kcalloc(num_counters, + per_cpu(perf_events, cpu) = kcalloc(num_counters, sizeof(struct perf_event *), GFP_KERNEL); - if (!perf_events[cpu]) { + if (!per_cpu(perf_events, cpu)) { pr_info("oprofile: failed to allocate %d perf events " "for cpu %d\n", num_counters, cpu); ret = -ENOMEM; diff --git a/drivers/pinctrl/pinctrl-imx.c b/drivers/pinctrl/pinctrl-imx.c index dd6d93aa533..90c837f469a 100644 --- a/drivers/pinctrl/pinctrl-imx.c +++ b/drivers/pinctrl/pinctrl-imx.c @@ -474,7 +474,9 @@ static int __devinit imx_pinctrl_parse_groups(struct device_node *np, grp->configs[j] = config & ~IMX_PAD_SION; } +#ifdef DEBUG IMX_PMX_DUMP(info, grp->pins, grp->mux_mode, grp->configs, grp->npins); +#endif return 0; } diff --git a/drivers/pinctrl/pinctrl-imx6q.c b/drivers/pinctrl/pinctrl-imx6q.c index 7737d4d71a3..e9bf71fbedc 100644 --- a/drivers/pinctrl/pinctrl-imx6q.c +++ b/drivers/pinctrl/pinctrl-imx6q.c @@ -1950,6 +1950,8 @@ static struct imx_pin_reg imx6q_pin_regs[] = { IMX_PIN_REG(MX6Q_PAD_SD2_DAT3, 0x0744, 0x035C, 5, 0x0000, 0), /* MX6Q_PAD_SD2_DAT3__GPIO_1_12 */ IMX_PIN_REG(MX6Q_PAD_SD2_DAT3, 0x0744, 0x035C, 6, 0x0000, 0), /* MX6Q_PAD_SD2_DAT3__SJC_DONE */ IMX_PIN_REG(MX6Q_PAD_SD2_DAT3, 0x0744, 0x035C, 7, 0x0000, 0), /* MX6Q_PAD_SD2_DAT3__ANATOP_TESTO_3 */ + IMX_PIN_REG(MX6Q_PAD_ENET_RX_ER, 0x04EC, 0x01D8, 0, 0x0000, 0), /* MX6Q_PAD_ENET_RX_ER__ANATOP_USBOTG_ID */ + IMX_PIN_REG(MX6Q_PAD_GPIO_1, 0x05F4, 0x0224, 3, 0x0000, 0), /* MX6Q_PAD_GPIO_1__ANATOP_USBOTG_ID */ }; /* Pad names for the pinmux subsystem */ diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 4f20f8dd3d7..17f6dfd8dbf 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -694,10 +694,10 @@ MODULE_DEVICE_TABLE(acpi, ideapad_device_ids); static int __devinit ideapad_acpi_add(struct acpi_device *adevice) { int ret, i; - unsigned long cfg; + int cfg; struct ideapad_private *priv; - if (read_method_int(adevice->handle, "_CFG", (int *)&cfg)) + if (read_method_int(adevice->handle, "_CFG", &cfg)) return -ENODEV; priv = kzalloc(sizeof(*priv), GFP_KERNEL); @@ -721,7 +721,7 @@ static int __devinit ideapad_acpi_add(struct acpi_device *adevice) goto input_failed; for (i = 0; i < IDEAPAD_RFKILL_DEV_NUM; i++) { - if (test_bit(ideapad_rfk_data[i].cfgbit, &cfg)) + if (test_bit(ideapad_rfk_data[i].cfgbit, &priv->cfg)) ideapad_register_rfkill(adevice, i); else priv->rfk[i] = NULL; diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index 0ffdb3cde2b..9af4257d490 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -72,6 +72,7 @@ #include <linux/string.h> #include <linux/tick.h> #include <linux/timer.h> +#include <linux/dmi.h> #include <drm/i915_drm.h> #include <asm/msr.h> #include <asm/processor.h> @@ -1485,6 +1486,24 @@ static DEFINE_PCI_DEVICE_TABLE(ips_id_table) = { MODULE_DEVICE_TABLE(pci, ips_id_table); +static int ips_blacklist_callback(const struct dmi_system_id *id) +{ + pr_info("Blacklisted intel_ips for %s\n", id->ident); + return 1; +} + +static const struct dmi_system_id ips_blacklist[] = { + { + .callback = ips_blacklist_callback, + .ident = "HP ProBook", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook"), + }, + }, + { } /* terminating entry */ +}; + static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id) { u64 platform_info; @@ -1494,6 +1513,9 @@ static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id) u16 htshi, trc, trc_required_mask; u8 tse; + if (dmi_check_system(ips_blacklist)) + return -ENODEV; + ips = kzalloc(sizeof(struct ips_driver), GFP_KERNEL); if (!ips) return -ENOMEM; diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 210d4ae547c..d456ff0c73b 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -973,7 +973,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, struct device_attribute *attr, const char *buffer, size_t count) { - unsigned long value = 0; + int value; int ret = 0; struct sony_nc_value *item = container_of(attr, struct sony_nc_value, devattr); @@ -984,7 +984,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, if (count > 31) return -EINVAL; - if (kstrtoul(buffer, 10, &value)) + if (kstrtoint(buffer, 10, &value)) return -EINVAL; if (item->validate) @@ -994,7 +994,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, return value; ret = sony_nc_int_call(sony_nc_acpi_handle, *item->acpiset, - (int *)&value, NULL); + &value, NULL); if (ret < 0) return -EIO; @@ -1010,6 +1010,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, struct sony_backlight_props { struct backlight_device *dev; int handle; + int cmd_base; u8 offset; u8 maxlvl; }; @@ -1037,7 +1038,7 @@ static int sony_nc_get_brightness_ng(struct backlight_device *bd) struct sony_backlight_props *sdev = (struct sony_backlight_props *)bl_get_data(bd); - sony_call_snc_handle(sdev->handle, 0x0200, &result); + sony_call_snc_handle(sdev->handle, sdev->cmd_base + 0x100, &result); return (result & 0xff) - sdev->offset; } @@ -1049,7 +1050,8 @@ static int sony_nc_update_status_ng(struct backlight_device *bd) (struct sony_backlight_props *)bl_get_data(bd); value = bd->props.brightness + sdev->offset; - if (sony_call_snc_handle(sdev->handle, 0x0100 | (value << 16), &result)) + if (sony_call_snc_handle(sdev->handle, sdev->cmd_base | (value << 0x10), + &result)) return -EIO; return value; @@ -1172,6 +1174,11 @@ static int sony_nc_hotkeys_decode(u32 event, unsigned int handle) /* * ACPI callbacks */ +enum event_types { + HOTKEY = 1, + KILLSWITCH, + GFX_SWITCH +}; static void sony_nc_notify(struct acpi_device *device, u32 event) { u32 real_ev = event; @@ -1196,7 +1203,7 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) /* hotkey event */ case 0x0100: case 0x0127: - ev_type = 1; + ev_type = HOTKEY; real_ev = sony_nc_hotkeys_decode(event, handle); if (real_ev > 0) @@ -1216,7 +1223,7 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) * update the rfkill device status when the * switch is moved. */ - ev_type = 2; + ev_type = KILLSWITCH; sony_call_snc_handle(handle, 0x0100, &result); real_ev = result & 0x03; @@ -1226,6 +1233,24 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) break; + case 0x0128: + case 0x0146: + /* Hybrid GFX switching */ + sony_call_snc_handle(handle, 0x0000, &result); + dprintk("GFX switch event received (reason: %s)\n", + (result & 0x01) ? + "switch change" : "unknown"); + + /* verify the switch state + * 1: discrete GFX + * 0: integrated GFX + */ + sony_call_snc_handle(handle, 0x0100, &result); + + ev_type = GFX_SWITCH; + real_ev = result & 0xff; + break; + default: dprintk("Unknown event 0x%x for handle 0x%x\n", event, handle); @@ -1238,7 +1263,7 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) } else { /* old style event */ - ev_type = 1; + ev_type = HOTKEY; sony_laptop_report_input_event(real_ev); } @@ -1893,32 +1918,33 @@ static ssize_t sony_nc_battery_care_limit_store(struct device *dev, * bits 4,5: store the limit into the EC * bits 6,7: store the limit into the battery */ + cmd = 0; - /* - * handle 0x0115 should allow storing on battery too; - * handle 0x0136 same as 0x0115 + health status; - * handle 0x013f, same as 0x0136 but no storing on the battery - * - * Store only inside the EC for now, regardless the handle number - */ - if (value == 0) - /* disable limits */ - cmd = 0x0; + if (value > 0) { + if (value <= 50) + cmd = 0x20; - else if (value <= 50) - cmd = 0x21; + else if (value <= 80) + cmd = 0x10; - else if (value <= 80) - cmd = 0x11; + else if (value <= 100) + cmd = 0x30; - else if (value <= 100) - cmd = 0x31; + else + return -EINVAL; - else - return -EINVAL; + /* + * handle 0x0115 should allow storing on battery too; + * handle 0x0136 same as 0x0115 + health status; + * handle 0x013f, same as 0x0136 but no storing on the battery + */ + if (bcare_ctl->handle != 0x013f) + cmd = cmd | (cmd << 2); - if (sony_call_snc_handle(bcare_ctl->handle, (cmd << 0x10) | 0x0100, - &result)) + cmd = (cmd | 0x1) << 0x10; + } + + if (sony_call_snc_handle(bcare_ctl->handle, cmd | 0x0100, &result)) return -EIO; return count; @@ -2113,7 +2139,7 @@ static ssize_t sony_nc_thermal_mode_show(struct device *dev, struct device_attribute *attr, char *buffer) { ssize_t count = 0; - unsigned int mode = sony_nc_thermal_mode_get(); + int mode = sony_nc_thermal_mode_get(); if (mode < 0) return mode; @@ -2472,6 +2498,7 @@ static void sony_nc_backlight_ng_read_limits(int handle, { u64 offset; int i; + int lvl_table_len = 0; u8 min = 0xff, max = 0x00; unsigned char buffer[32] = { 0 }; @@ -2480,8 +2507,6 @@ static void sony_nc_backlight_ng_read_limits(int handle, props->maxlvl = 0xff; offset = sony_find_snc_handle(handle); - if (offset < 0) - return; /* try to read the boundaries from ACPI tables, if we fail the above * defaults should be reasonable @@ -2491,11 +2516,21 @@ static void sony_nc_backlight_ng_read_limits(int handle, if (i < 0) return; + switch (handle) { + case 0x012f: + case 0x0137: + lvl_table_len = 9; + break; + case 0x143: + lvl_table_len = 16; + break; + } + /* the buffer lists brightness levels available, brightness levels are * from position 0 to 8 in the array, other values are used by ALS * control. */ - for (i = 0; i < 9 && i < ARRAY_SIZE(buffer); i++) { + for (i = 0; i < lvl_table_len && i < ARRAY_SIZE(buffer); i++) { dprintk("Brightness level: %d\n", buffer[i]); @@ -2520,16 +2555,24 @@ static void sony_nc_backlight_setup(void) const struct backlight_ops *ops = NULL; struct backlight_properties props; - if (sony_find_snc_handle(0x12f) != -1) { + if (sony_find_snc_handle(0x12f) >= 0) { ops = &sony_backlight_ng_ops; + sony_bl_props.cmd_base = 0x0100; sony_nc_backlight_ng_read_limits(0x12f, &sony_bl_props); max_brightness = sony_bl_props.maxlvl - sony_bl_props.offset; - } else if (sony_find_snc_handle(0x137) != -1) { + } else if (sony_find_snc_handle(0x137) >= 0) { ops = &sony_backlight_ng_ops; + sony_bl_props.cmd_base = 0x0100; sony_nc_backlight_ng_read_limits(0x137, &sony_bl_props); max_brightness = sony_bl_props.maxlvl - sony_bl_props.offset; + } else if (sony_find_snc_handle(0x143) >= 0) { + ops = &sony_backlight_ng_ops; + sony_bl_props.cmd_base = 0x3000; + sony_nc_backlight_ng_read_limits(0x143, &sony_bl_props); + max_brightness = sony_bl_props.maxlvl - sony_bl_props.offset; + } else if (ACPI_SUCCESS(acpi_get_handle(sony_nc_acpi_handle, "GBRT", &unused))) { ops = &sony_backlight_ops; @@ -2597,6 +2640,12 @@ static int sony_nc_add(struct acpi_device *device) } } + result = sony_laptop_setup_input(device); + if (result) { + pr_err("Unable to create input devices\n"); + goto outplatform; + } + if (ACPI_SUCCESS(acpi_get_handle(sony_nc_acpi_handle, "ECON", &handle))) { int arg = 1; @@ -2614,12 +2663,6 @@ static int sony_nc_add(struct acpi_device *device) } /* setup input devices and helper fifo */ - result = sony_laptop_setup_input(device); - if (result) { - pr_err("Unable to create input devices\n"); - goto outsnc; - } - if (acpi_video_backlight_support()) { pr_info("brightness ignored, must be controlled by ACPI video driver\n"); } else { @@ -2667,22 +2710,21 @@ static int sony_nc_add(struct acpi_device *device) return 0; - out_sysfs: +out_sysfs: for (item = sony_nc_values; item->name; ++item) { device_remove_file(&sony_pf_device->dev, &item->devattr); } sony_nc_backlight_cleanup(); - - sony_laptop_remove_input(); - - outsnc: sony_nc_function_cleanup(sony_pf_device); sony_nc_handles_cleanup(sony_pf_device); - outpresent: +outplatform: + sony_laptop_remove_input(); + +outpresent: sony_pf_remove(); - outwalk: +outwalk: sony_nc_rfkill_cleanup(); return result; } diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 39d3aa41add..f56c8ba3a86 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -1085,7 +1085,7 @@ static int __init rpmsg_init(void) return ret; } -module_init(rpmsg_init); +subsys_initcall(rpmsg_init); static void __exit rpmsg_fini(void) { diff --git a/drivers/scsi/scsi_wait_scan.c b/drivers/scsi/scsi_wait_scan.c index ae781487461..07273453887 100644 --- a/drivers/scsi/scsi_wait_scan.c +++ b/drivers/scsi/scsi_wait_scan.c @@ -22,11 +22,6 @@ static int __init wait_scan_init(void) * and might not yet have reached the scsi async scanning */ wait_for_device_probe(); - /* - * and then we wait for the actual asynchronous scsi scan - * to finish. - */ - scsi_complete_async_scans(); return 0; } diff --git a/drivers/target/target_core_cdb.c b/drivers/target/target_core_cdb.c index 9888693a18f..664f6e775d0 100644 --- a/drivers/target/target_core_cdb.c +++ b/drivers/target/target_core_cdb.c @@ -1095,7 +1095,7 @@ int target_emulate_write_same(struct se_cmd *cmd) if (num_blocks != 0) range = num_blocks; else - range = (dev->transport->get_blocks(dev) - lba); + range = (dev->transport->get_blocks(dev) - lba) + 1; pr_debug("WRITE_SAME UNMAP: LBA: %llu Range: %llu\n", (unsigned long long)lba, (unsigned long long)range); diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 85564998500..a1bcd927a9e 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -2031,7 +2031,7 @@ static int __core_scsi3_write_aptpl_to_file( if (IS_ERR(file) || !file || !file->f_dentry) { pr_err("filp_open(%s) for APTPL metadata" " failed\n", path); - return (PTR_ERR(file) < 0 ? PTR_ERR(file) : -ENOENT); + return IS_ERR(file) ? PTR_ERR(file) : -ENOENT; } iov[0].iov_base = &buf[0]; @@ -3818,7 +3818,7 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd) " SPC-2 reservation is held, returning" " RESERVATION_CONFLICT\n"); cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; - ret = EINVAL; + ret = -EINVAL; goto out; } @@ -3828,7 +3828,8 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd) */ if (!cmd->se_sess) { cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - return -EINVAL; + ret = -EINVAL; + goto out; } if (cmd->data_length < 24) { diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index f03fb9730f5..5b65f33939a 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -230,6 +230,8 @@ u32 ft_get_task_tag(struct se_cmd *se_cmd) { struct ft_cmd *cmd = container_of(se_cmd, struct ft_cmd, se_cmd); + if (cmd->aborted) + return ~0; return fc_seq_exch(cmd->seq)->rxid; } diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 5b400730c21..4ee522b3f66 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -86,7 +86,31 @@ static struct { #endif /* CONFIG_CIFS_WEAK_PW_HASH */ #endif /* CIFS_POSIX */ -/* Forward declarations */ +#ifdef CONFIG_HIGHMEM +/* + * On arches that have high memory, kmap address space is limited. By + * serializing the kmap operations on those arches, we ensure that we don't + * end up with a bunch of threads in writeback with partially mapped page + * arrays, stuck waiting for kmap to come back. That situation prevents + * progress and can deadlock. + */ +static DEFINE_MUTEX(cifs_kmap_mutex); + +static inline void +cifs_kmap_lock(void) +{ + mutex_lock(&cifs_kmap_mutex); +} + +static inline void +cifs_kmap_unlock(void) +{ + mutex_unlock(&cifs_kmap_mutex); +} +#else /* !CONFIG_HIGHMEM */ +#define cifs_kmap_lock() do { ; } while(0) +#define cifs_kmap_unlock() do { ; } while(0) +#endif /* CONFIG_HIGHMEM */ /* Mark as invalid, all open files on tree connections since they were closed when session to server was lost */ @@ -1503,7 +1527,9 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* marshal up the page array */ + cifs_kmap_lock(); len = rdata->marshal_iov(rdata, data_len); + cifs_kmap_unlock(); data_len -= len; /* issue the read if we have any iovecs left to fill */ @@ -2069,7 +2095,9 @@ cifs_async_writev(struct cifs_writedata *wdata) * and set the iov_len properly for each one. It may also set * wdata->bytes too. */ + cifs_kmap_lock(); wdata->marshal_iov(iov, wdata); + cifs_kmap_unlock(); cFYI(1, "async write at %llu %u bytes", wdata->offset, wdata->bytes); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0ae86ddf221..94b7788c318 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3445,6 +3445,18 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, #define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024) #define CIFS_DEFAULT_NON_POSIX_WSIZE (65536) +/* + * On hosts with high memory, we can't currently support wsize/rsize that are + * larger than we can kmap at once. Cap the rsize/wsize at + * LAST_PKMAP * PAGE_SIZE. We'll never be able to fill a read or write request + * larger than that anyway. + */ +#ifdef CONFIG_HIGHMEM +#define CIFS_KMAP_SIZE_LIMIT (LAST_PKMAP * PAGE_CACHE_SIZE) +#else /* CONFIG_HIGHMEM */ +#define CIFS_KMAP_SIZE_LIMIT (1<<24) +#endif /* CONFIG_HIGHMEM */ + static unsigned int cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) { @@ -3475,6 +3487,9 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) wsize = min_t(unsigned int, wsize, server->maxBuf - sizeof(WRITE_REQ) + 4); + /* limit to the amount that we can kmap at once */ + wsize = min_t(unsigned int, wsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_WSIZE */ wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE); @@ -3516,6 +3531,9 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) if (!(server->capabilities & CAP_LARGE_READ_X)) rsize = min_t(unsigned int, CIFSMaxBufSize, rsize); + /* limit to the amount that we can kmap at once */ + rsize = min_t(unsigned int, rsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_RSIZE */ rsize = min_t(unsigned int, rsize, CIFS_MAX_RSIZE); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 0a8224d1c4c..a4217f02fab 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -86,9 +86,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, dentry = d_lookup(parent, name); if (dentry) { - /* FIXME: check for inode number changes? */ - if (dentry->d_inode != NULL) + inode = dentry->d_inode; + /* update inode in place if i_ino didn't change */ + if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + cifs_fattr_to_inode(inode, fattr); return dentry; + } d_drop(dentry); dput(dentry); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 3097ee58fd7..f25d4ea14be 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -365,16 +365,14 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct kvec *iov, if (mid == NULL) return -ENOMEM; - /* put it on the pending_mid_q */ - spin_lock(&GlobalMid_Lock); - list_add_tail(&mid->qhead, &server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); - rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number); - if (rc) - delete_mid(mid); + if (rc) { + DeleteMidQEntry(mid); + return rc; + } + *ret_mid = mid; - return rc; + return 0; } /* @@ -407,17 +405,21 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov, mid->callback_data = cbdata; mid->mid_state = MID_REQUEST_SUBMITTED; + /* put it on the pending_mid_q */ + spin_lock(&GlobalMid_Lock); + list_add_tail(&mid->qhead, &server->pending_mid_q); + spin_unlock(&GlobalMid_Lock); + + cifs_in_send_inc(server); rc = smb_sendv(server, iov, nvec); cifs_in_send_dec(server); cifs_save_when_sent(mid); mutex_unlock(&server->srv_mutex); - if (rc) - goto out_err; + if (rc == 0) + return 0; - return rc; -out_err: delete_mid(mid); add_credits(server, 1); wake_up(&server->request_q); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 74598f67efe..1c8b5567080 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1710,7 +1710,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP)) + if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epds.events &= ~EPOLLWAKEUP; /* diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 49cf230554a..24a49d47e93 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -735,13 +735,7 @@ static int _prepare_for_striping(struct ore_io_state *ios) out: ios->numdevs = devs_in_group; ios->pages_consumed = cur_pg; - if (unlikely(ret)) { - if (length == ios->length) - return ret; - else - ios->length -= length; - } - return 0; + return ret; } int ore_create(struct ore_io_state *ios) diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index d222c77cfa1..5f376d14fdc 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -144,26 +144,26 @@ static void _sp2d_reset(struct __stripe_pages_2d *sp2d, { unsigned data_devs = sp2d->data_devs; unsigned group_width = data_devs + sp2d->parity; - unsigned p; + int p, c; if (!sp2d->needed) return; - for (p = 0; p < sp2d->pages_in_unit; p++) { - struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; - - if (_1ps->write_count < group_width) { - unsigned c; + for (c = data_devs - 1; c >= 0; --c) + for (p = sp2d->pages_in_unit - 1; p >= 0; --p) { + struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; - for (c = 0; c < data_devs; c++) - if (_1ps->page_is_read[c]) { - struct page *page = _1ps->pages[c]; + if (_1ps->page_is_read[c]) { + struct page *page = _1ps->pages[c]; - r4w->put_page(priv, page); - _1ps->page_is_read[c] = false; - } + r4w->put_page(priv, page); + _1ps->page_is_read[c] = false; + } } + for (p = 0; p < sp2d->pages_in_unit; p++) { + struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; + memset(_1ps->pages, 0, group_width * sizeof(*_1ps->pages)); _1ps->write_count = 0; _1ps->tx = NULL; @@ -461,16 +461,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret) * ios->sp2d[p][*], xor is calculated the same way. These pages are * allocated/freed and don't go through cache */ -static int _read_4_write(struct ore_io_state *ios) +static int _read_4_write_first_stripe(struct ore_io_state *ios) { - struct ore_io_state *ios_read; struct ore_striping_info read_si; struct __stripe_pages_2d *sp2d = ios->sp2d; u64 offset = ios->si.first_stripe_start; - u64 last_stripe_end; - unsigned bytes_in_stripe = ios->si.bytes_in_stripe; - unsigned i, c, p, min_p = sp2d->pages_in_unit, max_p = -1; - int ret; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; if (offset == ios->offset) /* Go to start collect $200 */ goto read_last_stripe; @@ -478,6 +474,9 @@ static int _read_4_write(struct ore_io_state *ios) min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); + ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n", + offset, ios->offset, min_p, max_p); + for (c = 0; ; c++) { ore_calc_stripe_info(ios->layout, offset, 0, &read_si); read_si.obj_offset += min_p * PAGE_SIZE; @@ -512,6 +511,18 @@ static int _read_4_write(struct ore_io_state *ios) } read_last_stripe: + return 0; +} + +static int _read_4_write_last_stripe(struct ore_io_state *ios) +{ + struct ore_striping_info read_si; + struct __stripe_pages_2d *sp2d = ios->sp2d; + u64 offset; + u64 last_stripe_end; + unsigned bytes_in_stripe = ios->si.bytes_in_stripe; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; + offset = ios->offset + ios->length; if (offset % PAGE_SIZE) _add_to_r4w_last_page(ios, &offset); @@ -527,15 +538,15 @@ read_last_stripe: c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1, ios->layout->mirrors_p1, read_si.par_dev, read_si.dev); - BUG_ON(ios->si.first_stripe_start + bytes_in_stripe != last_stripe_end); - /* unaligned IO must be within a single stripe */ - if (min_p == sp2d->pages_in_unit) { /* Didn't do it yet */ min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); } + ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n", + offset, last_stripe_end, min_p, max_p); + while (offset < last_stripe_end) { struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; @@ -568,6 +579,15 @@ read_last_stripe: } read_it: + return 0; +} + +static int _read_4_write_execute(struct ore_io_state *ios) +{ + struct ore_io_state *ios_read; + unsigned i; + int ret; + ios_read = ios->ios_read_4_write; if (!ios_read) return 0; @@ -591,6 +611,8 @@ read_it: } _mark_read4write_pages_uptodate(ios_read, ret); + ore_put_io_state(ios_read); + ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */ return 0; } @@ -626,8 +648,11 @@ int _ore_add_parity_unit(struct ore_io_state *ios, /* If first stripe, Read in all read4write pages * (if needed) before we calculate the first parity. */ - _read_4_write(ios); + _read_4_write_first_stripe(ios); } + if (!cur_len) /* If last stripe r4w pages of last stripe */ + _read_4_write_last_stripe(ios); + _read_4_write_execute(ios); for (i = 0; i < num_pages; i++) { pages[i] = _raid_page_alloc(); @@ -654,34 +679,14 @@ int _ore_add_parity_unit(struct ore_io_state *ios, int _ore_post_alloc_raid_stuff(struct ore_io_state *ios) { - struct ore_layout *layout = ios->layout; - if (ios->parity_pages) { + struct ore_layout *layout = ios->layout; unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE; - unsigned stripe_size = ios->si.bytes_in_stripe; - u64 last_stripe, first_stripe; if (_sp2d_alloc(pages_in_unit, layout->group_width, layout->parity, &ios->sp2d)) { return -ENOMEM; } - - /* Round io down to last full strip */ - first_stripe = div_u64(ios->offset, stripe_size); - last_stripe = div_u64(ios->offset + ios->length, stripe_size); - - /* If an IO spans more then a single stripe it must end at - * a stripe boundary. The reminder at the end is pushed into the - * next IO. - */ - if (last_stripe != first_stripe) { - ios->length = last_stripe * stripe_size - ios->offset; - - BUG_ON(!ios->length); - ios->nr_pages = (ios->length + PAGE_SIZE - 1) / - PAGE_SIZE; - ios->si.length = ios->length; /*make it consistent */ - } } return 0; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index e34deac3f36..6ec6f9ee2fe 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -268,7 +268,6 @@ group_extend_out: err = ext4_move_extents(filp, donor_filp, me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); - mnt_drop_write(filp->f_path.mnt); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) diff --git a/fs/fifo.c b/fs/fifo.c index b1a524d798e..cf6f4345ceb 100644 --- a/fs/fifo.c +++ b/fs/fifo.c @@ -14,7 +14,7 @@ #include <linux/sched.h> #include <linux/pipe_fs_i.h> -static void wait_for_partner(struct inode* inode, unsigned int *cnt) +static int wait_for_partner(struct inode* inode, unsigned int *cnt) { int cur = *cnt; @@ -23,6 +23,7 @@ static void wait_for_partner(struct inode* inode, unsigned int *cnt) if (signal_pending(current)) break; } + return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct inode* inode) @@ -67,8 +68,7 @@ static int fifo_open(struct inode *inode, struct file *filp) * seen a writer */ filp->f_version = pipe->w_counter; } else { - wait_for_partner(inode, &pipe->w_counter); - if(signal_pending(current)) + if (wait_for_partner(inode, &pipe->w_counter)) goto err_rd; } } @@ -90,8 +90,7 @@ static int fifo_open(struct inode *inode, struct file *filp) wake_up_partner(inode); if (!pipe->readers) { - wait_for_partner(inode, &pipe->r_counter); - if (signal_pending(current)) + if (wait_for_partner(inode, &pipe->r_counter)) goto err_wr; } break; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index b47277baeba..f50d3e8d6f2 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -454,7 +454,10 @@ int objio_read_pagelist(struct nfs_read_data *rdata) objios->ios->done = _read_done; dprintk("%s: offset=0x%llx length=0x%x\n", __func__, rdata->args.offset, rdata->args.count); - return ore_read(objios->ios); + ret = ore_read(objios->ios); + if (unlikely(ret)) + objio_free_result(&objios->oir); + return ret; } /* @@ -486,8 +489,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) struct nfs_write_data *wdata = objios->oir.rpcdata; struct address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(mapping, index); + struct page *page; + loff_t i_size = i_size_read(wdata->header->inode); + + if (offset >= i_size) { + *uptodate = true; + dprintk("%s: g_zero_page index=0x%lx\n", __func__, index); + return ZERO_PAGE(0); + } + page = find_get_page(mapping, index); if (!page) { page = find_or_create_page(mapping, index, GFP_NOFS); if (unlikely(!page)) { @@ -507,8 +518,10 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) static void __r4w_put_page(void *priv, struct page *page) { - dprintk("%s: index=0x%lx\n", __func__, page->index); - page_cache_release(page); + dprintk("%s: index=0x%lx\n", __func__, + (page == ZERO_PAGE(0)) ? -1UL : page->index); + if (ZERO_PAGE(0) != page) + page_cache_release(page); return; } @@ -539,8 +552,10 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how) dprintk("%s: offset=0x%llx length=0x%x\n", __func__, wdata->args.offset, wdata->args.count); ret = ore_write(objios->ios); - if (unlikely(ret)) + if (unlikely(ret)) { + objio_free_result(&objios->oir); return ret; + } if (objios->sync) _write_done(objios->ios, objios); diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index ef3d1ba6d99..15e2fc5aa60 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -718,8 +718,12 @@ static int fixup_free_space(struct ubifs_info *c) lnum = ubifs_next_log_lnum(c, lnum); } - /* Fixup the current log head */ - err = fixup_leb(c, c->lhead_lnum, c->lhead_offs); + /* + * Fixup the log head which contains the only a CS node at the + * beginning. + */ + err = fixup_leb(c, c->lhead_lnum, + ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size)); if (err) goto out; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 9d1aeb7e273..4f33c32affe 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1074,13 +1074,13 @@ restart: * If we couldn't get anything, give up. */ if (bno_cur_lt == NULL && bno_cur_gt == NULL) { + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + if (!forced++) { trace_xfs_alloc_near_busy(args); xfs_log_force(args->mp, XFS_LOG_SYNC); goto restart; } - - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_neither(args); args->agbno = NULLAGBLOCK; return 0; @@ -2434,13 +2434,22 @@ xfs_alloc_vextent_worker( current_restore_flags_nested(&pflags, PF_FSTRANS); } - -int /* error */ +/* + * Data allocation requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. Metadata + * requests, OTOH, are generally from low stack usage paths, so avoid the + * context switch overhead here. + */ +int xfs_alloc_vextent( - xfs_alloc_arg_t *args) /* allocation argument structure */ + struct xfs_alloc_arg *args) { DECLARE_COMPLETION_ONSTACK(done); + if (!args->userdata) + return __xfs_alloc_vextent(args); + + args->done = &done; INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); queue_work(xfs_alloc_wq, &args->work); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index a4beb421018..269b35c084d 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -989,27 +989,6 @@ xfs_buf_ioerror_alert( (__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length); } -int -xfs_bwrite( - struct xfs_buf *bp) -{ - int error; - - ASSERT(xfs_buf_islocked(bp)); - - bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); - - xfs_bdstrat_cb(bp); - - error = xfs_buf_iowait(bp); - if (error) { - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); - } - return error; -} - /* * Called when we want to stop a buffer from getting written or read. * We attach the EIO error, muck with its flags, and call xfs_buf_ioend @@ -1079,14 +1058,7 @@ xfs_bioerror_relse( return EIO; } - -/* - * All xfs metadata buffers except log state machine buffers - * get this attached as their b_bdstrat callback function. - * This is so that we can catch a buffer - * after prematurely unpinning it to forcibly shutdown the filesystem. - */ -int +STATIC int xfs_bdstrat_cb( struct xfs_buf *bp) { @@ -1107,6 +1079,27 @@ xfs_bdstrat_cb( return 0; } +int +xfs_bwrite( + struct xfs_buf *bp) +{ + int error; + + ASSERT(xfs_buf_islocked(bp)); + + bp->b_flags |= XBF_WRITE; + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); + + xfs_bdstrat_cb(bp); + + error = xfs_buf_iowait(bp); + if (error) { + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_META_IO_ERROR); + } + return error; +} + /* * Wrapper around bdstrat so that we can stop data from going to disk in case * we are shutting down the filesystem. Typically user data goes thru this @@ -1243,7 +1236,7 @@ xfs_buf_iorequest( */ atomic_set(&bp->b_io_remaining, 1); _xfs_buf_ioapply(bp); - _xfs_buf_ioend(bp, 0); + _xfs_buf_ioend(bp, 1); xfs_buf_rele(bp); } diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 7f1d1392ce3..79344c48008 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -180,7 +180,6 @@ extern void xfs_buf_unlock(xfs_buf_t *); extern int xfs_bwrite(struct xfs_buf *bp); extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *); -extern int xfs_bdstrat_cb(struct xfs_buf *); extern void xfs_buf_ioend(xfs_buf_t *, int); extern void xfs_buf_ioerror(xfs_buf_t *, int); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 45df2b857d4..d9e451115f9 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -954,7 +954,7 @@ xfs_buf_iodone_callbacks( if (!XFS_BUF_ISSTALE(bp)) { bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE; - xfs_bdstrat_cb(bp); + xfs_buf_iorequest(bp); } else { xfs_buf_relse(bp); } diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h index c544356b374..294b1e755ab 100644 --- a/include/asm-generic/dma-contiguous.h +++ b/include/asm-generic/dma-contiguous.h @@ -18,7 +18,7 @@ static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { if (dev) dev->cma_area = cma; - if (!dev || !dma_contiguous_default_area) + if (!dev && !dma_contiguous_default_area) dma_contiguous_default_area = cma; } diff --git a/include/linux/capability.h b/include/linux/capability.h index 68d56effc32..d10b7ed595b 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -360,11 +360,11 @@ struct cpu_vfs_cap_data { #define CAP_WAKE_ALARM 35 -/* Allow preventing system suspends while epoll events are pending */ +/* Allow preventing system suspends */ -#define CAP_EPOLLWAKEUP 36 +#define CAP_BLOCK_SUSPEND 36 -#define CAP_LAST_CAP CAP_EPOLLWAKEUP +#define CAP_LAST_CAP CAP_BLOCK_SUSPEND #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 2521a95fa6d..44c87e731e9 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -163,16 +163,8 @@ struct ceph_connection { /* connection negotiation temps */ char in_banner[CEPH_BANNER_MAX_LEN]; - union { - struct { /* outgoing connection */ - struct ceph_msg_connect out_connect; - struct ceph_msg_connect_reply in_reply; - }; - struct { /* incoming */ - struct ceph_msg_connect in_connect; - struct ceph_msg_connect_reply out_reply; - }; - }; + struct ceph_msg_connect out_connect; + struct ceph_msg_connect_reply in_reply; struct ceph_entity_addr actual_peer_addr; /* message out temps */ diff --git a/include/linux/device.h b/include/linux/device.h index 161d96241b1..6de94151ff6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -865,8 +865,6 @@ extern int (*platform_notify_remove)(struct device *dev); extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); -extern void wait_for_device_probe(void); - #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev); extern int devtmpfs_delete_node(struct device *dev); diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6f8be328770..f4bb378ccf6 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -34,7 +34,7 @@ * re-allowed until epoll_wait is called again after consuming the wakeup * event(s). * - * Requires CAP_EPOLLWAKEUP + * Requires CAP_BLOCK_SUSPEND */ #define EPOLLWAKEUP (1 << 29) diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 176a939d154..af961d6f7ab 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -65,7 +65,7 @@ struct trace_iterator { void *private; int cpu_file; struct mutex mutex; - struct ring_buffer_iter *buffer_iter[NR_CPUS]; + struct ring_buffer_iter **buffer_iter; unsigned long iter_flags; /* trace_seq for __print_flags() and __print_symbolic() etc. */ @@ -207,6 +207,9 @@ struct ftrace_event_call { * bit 1: enabled * bit 2: filter_active * bit 3: enabled cmd record + * bit 4: allow trace by non root (cap any) + * bit 5: failed to apply filter + * bit 6: ftrace internal event (do not enable) * * Changes to flags must hold the event_mutex. * diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9e65eff6af3..8a747618699 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -168,8 +168,8 @@ extern struct cred init_cred; .children = LIST_HEAD_INIT(tsk.children), \ .sibling = LIST_HEAD_INIT(tsk.sibling), \ .group_leader = &tsk, \ - RCU_INIT_POINTER(.real_cred, &init_cred), \ - RCU_INIT_POINTER(.cred, &init_cred), \ + RCU_POINTER_INITIALIZER(real_cred, &init_cred), \ + RCU_POINTER_INITIALIZER(cred, &init_cred), \ .comm = INIT_TASK_COMM, \ .thread = INIT_THREAD, \ .fs = &init_fs, \ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e6ca56de993..78e2ada50cd 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -308,6 +308,8 @@ enum { struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ + u64 reg_phys; /* physical address of hw register set */ + u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ diff --git a/include/linux/irq.h b/include/linux/irq.h index a5261e3d2e3..553fb66da13 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -150,9 +150,7 @@ struct irq_data { void *handler_data; void *chip_data; struct msi_desc *msi_desc; -#ifdef CONFIG_SMP cpumask_var_t affinity; -#endif }; /* diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index c513a40510f..0976fc46d1e 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -42,8 +42,7 @@ * allowed. * * Not initializing the key (static data is initialized to 0s anyway) is the - * same as using STATIC_KEY_INIT_FALSE and static_key_false() is - * equivalent with static_branch(). + * same as using STATIC_KEY_INIT_FALSE. * */ @@ -107,12 +106,6 @@ static __always_inline bool static_key_true(struct static_key *key) return !static_key_false(key); } -/* Deprecated. Please use 'static_key_false() instead. */ -static __always_inline bool static_branch(struct static_key *key) -{ - return arch_static_branch(key); -} - extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; @@ -166,14 +159,6 @@ static __always_inline bool static_key_true(struct static_key *key) return false; } -/* Deprecated. Please use 'static_key_false() instead. */ -static __always_inline bool static_branch(struct static_key *key) -{ - if (unlikely(atomic_read(&key->enabled)) > 0) - return true; - return false; -} - static inline void static_key_slow_inc(struct static_key *key) { atomic_inc(&key->enabled); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e07f5e0c5df..604382143bc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -377,7 +377,6 @@ extern enum system_states { SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, - SYSTEM_SUSPEND_DISK, } system_state; #define TAINT_PROPRIETARY_MODULE 0 diff --git a/include/linux/key.h b/include/linux/key.h index 4cd22ed627e..cef3b315ba7 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -303,7 +303,9 @@ static inline bool key_is_instantiated(const struct key *key) rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ - (rcu_assign_pointer((KEY)->payload.rcudata, PAYLOAD)) +do { \ + rcu_assign_pointer((KEY)->payload.rcudata, (PAYLOAD)); \ +} while (0) #ifdef CONFIG_SYSCTL extern ctl_table key_sysctls[]; diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index d6bd50110ec..2e7a1e032c7 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -55,12 +55,17 @@ struct kmsg_dumper { #ifdef CONFIG_PRINTK void kmsg_dump(enum kmsg_dump_reason reason); +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len); + bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len); bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, char *buf, size_t size, size_t *len); +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper); + void kmsg_dump_rewind(struct kmsg_dumper *dumper); int kmsg_dump_register(struct kmsg_dumper *dumper); @@ -71,6 +76,13 @@ static inline void kmsg_dump(enum kmsg_dump_reason reason) { } +static inline bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, + bool syslog, const char *line, + size_t size, size_t *len) +{ + return false; +} + static inline bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, const char *line, size_t size, size_t *len) { @@ -83,6 +95,10 @@ static inline bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, return false; } +static inline void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ +} + static inline void kmsg_dump_rewind(struct kmsg_dumper *dumper) { } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ab741b0d007..5f187026b81 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2755,6 +2755,17 @@ #define PCI_DEVICE_ID_INTEL_IOAT_SNB7 0x3c27 #define PCI_DEVICE_ID_INTEL_IOAT_SNB8 0x3c2e #define PCI_DEVICE_ID_INTEL_IOAT_SNB9 0x3c2f +#define PCI_DEVICE_ID_INTEL_UNC_HA 0x3c46 +#define PCI_DEVICE_ID_INTEL_UNC_IMC0 0x3cb0 +#define PCI_DEVICE_ID_INTEL_UNC_IMC1 0x3cb1 +#define PCI_DEVICE_ID_INTEL_UNC_IMC2 0x3cb4 +#define PCI_DEVICE_ID_INTEL_UNC_IMC3 0x3cb5 +#define PCI_DEVICE_ID_INTEL_UNC_QPI0 0x3c41 +#define PCI_DEVICE_ID_INTEL_UNC_QPI1 0x3c42 +#define PCI_DEVICE_ID_INTEL_UNC_R2PCIE 0x3c43 +#define PCI_DEVICE_ID_INTEL_UNC_R3QPI0 0x3c44 +#define PCI_DEVICE_ID_INTEL_UNC_R3QPI1 0x3c45 +#define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX 0x3ce0 #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f #define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 #define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 45db49f64bb..76c5c8b724a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -677,6 +677,7 @@ struct hw_perf_event { u64 last_tag; unsigned long config_base; unsigned long event_base; + int event_base_rdpmc; int idx; int last_cpu; @@ -1106,6 +1107,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, struct task_struct *task, perf_overflow_handler_t callback, void *context); +extern void perf_pmu_migrate_context(struct pmu *pmu, + int src_cpu, int dst_cpu); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9cac722b169..115ead2b515 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -147,6 +147,7 @@ extern void synchronize_sched(void); extern void __rcu_read_lock(void); extern void __rcu_read_unlock(void); +extern void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* @@ -255,6 +256,10 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) +extern int rcu_is_cpu_idle(void); +#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */ + #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ @@ -266,15 +271,6 @@ static inline bool rcu_lockdep_current_cpu_online(void) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#ifdef CONFIG_PROVE_RCU -extern int rcu_is_cpu_idle(void); -#else /* !CONFIG_PROVE_RCU */ -static inline int rcu_is_cpu_idle(void) -{ - return 0; -} -#endif /* else !CONFIG_PROVE_RCU */ - static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); @@ -431,8 +427,7 @@ extern int rcu_my_thread_group_empty(void); static inline void rcu_preempt_sleep_check(void) { rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), - "Illegal context switch in RCU read-side " - "critical section"); + "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) @@ -513,10 +508,10 @@ static inline void rcu_preempt_sleep_check(void) (_________p1); \ }) #define __rcu_assign_pointer(p, v, space) \ - ({ \ + do { \ smp_wmb(); \ (p) = (typeof(*v) __force space *)(v); \ - }) + } while (0) /** @@ -851,7 +846,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see - * any prior initialization. Returns the value assigned. + * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from @@ -903,25 +898,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * the reader-accessible portions of the linked structure. */ #define RCU_INIT_POINTER(p, v) \ - p = (typeof(*v) __force __rcu *)(v) - -static __always_inline bool __is_kfree_rcu_offset(unsigned long offset) -{ - return offset < 4096; -} - -static __always_inline -void __kfree_rcu(struct rcu_head *head, unsigned long offset) -{ - typedef void (*rcu_callback)(struct rcu_head *); - - BUILD_BUG_ON(!__builtin_constant_p(offset)); - - /* See the kfree_rcu() header comment. */ - BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); + do { \ + p = (typeof(*v) __force __rcu *)(v); \ + } while (0) - kfree_call_rcu(head, (rcu_callback)offset); -} +/** + * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer + * + * GCC-style initialization for an RCU-protected pointer in a structure field. + */ +#define RCU_POINTER_INITIALIZER(p, v) \ + .p = (typeof(*v) __force __rcu *)(v) /* * Does the specified offset indicate that the corresponding rcu_head @@ -935,7 +922,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) #define __kfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ + kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ } while (0) /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a1f493e0fe..64d9df5c3a4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1581,7 +1581,6 @@ struct task_struct { #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; - int uprobe_srcu_id; #endif }; diff --git a/include/linux/smp.h b/include/linux/smp.h index 717fb746c9a..dd6f06be3c9 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -90,10 +90,6 @@ void kick_all_cpus_sync(void); void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); -void ipi_call_lock(void); -void ipi_call_unlock(void); -void ipi_call_lock_irq(void); -void ipi_call_unlock_irq(void); #else static inline void call_function_init(void) { } #endif @@ -181,7 +177,6 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info) } while (0) static inline void smp_send_reschedule(int cpu) { } -#define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index bd96ecd0e05..802de56c41e 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -153,7 +153,7 @@ static inline void tracepoint_synchronize_unregister(void) } \ static inline void trace_##name##_rcuidle(proto) \ { \ - if (static_branch(&__tracepoint_##name.key)) \ + if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d6146b4811c..95374d1696a 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1425,7 +1425,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb) struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (!ct || !nf_ct_is_untracked(ct)) { - nf_reset(skb); + nf_conntrack_put(skb->nfct); skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index a88fb693938..e1ce1048fe5 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -78,7 +78,7 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; - if (net->ct.nf_conntrack_event_cb == NULL) + if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) return; e = nf_ct_ecache_find(ct); diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index d274734b2aa..5bde94d8585 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -541,6 +541,50 @@ TRACE_EVENT(rcu_torture_read, __entry->rcutorturename, __entry->rhp) ); +/* + * Tracepoint for _rcu_barrier() execution. The string "s" describes + * the _rcu_barrier phase: + * "Begin": rcu_barrier_callback() started. + * "Check": rcu_barrier_callback() checking for piggybacking. + * "EarlyExit": rcu_barrier_callback() piggybacked, thus early exit. + * "Inc1": rcu_barrier_callback() piggyback check counter incremented. + * "Offline": rcu_barrier_callback() found offline CPU + * "OnlineQ": rcu_barrier_callback() found online CPU with callbacks. + * "OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks. + * "IRQ": An rcu_barrier_callback() callback posted on remote CPU. + * "CB": An rcu_barrier_callback() invoked a callback, not the last. + * "LastCB": An rcu_barrier_callback() invoked the last callback. + * "Inc2": rcu_barrier_callback() piggyback check counter incremented. + * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument + * is the count of remaining callbacks, and "done" is the piggybacking count. + */ +TRACE_EVENT(rcu_barrier, + + TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done), + + TP_ARGS(rcuname, s, cpu, cnt, done), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(char *, s) + __field(int, cpu) + __field(int, cnt) + __field(unsigned long, done) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->s = s; + __entry->cpu = cpu; + __entry->cnt = cnt; + __entry->done = done; + ), + + TP_printk("%s %s cpu %d remaining %d # %lu", + __entry->rcuname, __entry->s, __entry->cpu, __entry->cnt, + __entry->done) +); + #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) @@ -564,6 +608,7 @@ TRACE_EVENT(rcu_torture_read, #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ do { } while (0) #define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0) #endif /* #else #ifdef CONFIG_RCU_TRACE */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 769724944fc..c6bc2faaf26 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -571,6 +571,7 @@ static inline void ftrace_test_probe_##call(void) \ #undef __print_flags #undef __print_symbolic +#undef __print_hex #undef __get_dynamic_array #undef __get_str diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 67b847dfa2b..1f91413edb8 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/kmsg_dump.h> #include <linux/reboot.h> #include <linux/sched.h> #include <linux/sysrq.h> @@ -2040,8 +2041,15 @@ static int kdb_env(int argc, const char **argv) */ static int kdb_dmesg(int argc, const char **argv) { - char *syslog_data[4], *start, *end, c = '\0', *p; - int diag, logging, logsize, lines = 0, adjust = 0, n; + int diag; + int logging; + int lines = 0; + int adjust = 0; + int n = 0; + int skip = 0; + struct kmsg_dumper dumper = { .active = 1 }; + size_t len; + char buf[201]; if (argc > 2) return KDB_ARGCOUNT; @@ -2064,22 +2072,10 @@ static int kdb_dmesg(int argc, const char **argv) kdb_set(2, setargs); } - /* syslog_data[0,1] physical start, end+1. syslog_data[2,3] - * logical start, end+1. */ - kdb_syslog_data(syslog_data); - if (syslog_data[2] == syslog_data[3]) - return 0; - logsize = syslog_data[1] - syslog_data[0]; - start = syslog_data[2]; - end = syslog_data[3]; -#define KDB_WRAP(p) (((p - syslog_data[0]) % logsize) + syslog_data[0]) - for (n = 0, p = start; p < end; ++p) { - c = *KDB_WRAP(p); - if (c == '\n') - ++n; - } - if (c != '\n') - ++n; + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, NULL, 0, NULL)) + n++; + if (lines < 0) { if (adjust >= n) kdb_printf("buffer only contains %d lines, nothing " @@ -2087,21 +2083,11 @@ static int kdb_dmesg(int argc, const char **argv) else if (adjust - lines >= n) kdb_printf("buffer only contains %d lines, last %d " "lines printed\n", n, n - adjust); - if (adjust) { - for (; start < end && adjust; ++start) { - if (*KDB_WRAP(start) == '\n') - --adjust; - } - if (start < end) - ++start; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - ++lines; - } - end = p; + skip = adjust; + lines = abs(lines); } else if (lines > 0) { - int skip = n - (adjust + lines); + skip = n - lines - adjust; + lines = abs(lines); if (adjust >= n) { kdb_printf("buffer only contains %d lines, " "nothing printed\n", n); @@ -2112,35 +2098,24 @@ static int kdb_dmesg(int argc, const char **argv) kdb_printf("buffer only contains %d lines, first " "%d lines printed\n", n, lines); } - for (; start < end && skip; ++start) { - if (*KDB_WRAP(start) == '\n') - --skip; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - --lines; - } - end = p; + } else { + lines = n; } - /* Do a line at a time (max 200 chars) to reduce protocol overhead */ - c = '\n'; - while (start != end) { - char buf[201]; - p = buf; - if (KDB_FLAG(CMD_INTERRUPT)) - return 0; - while (start < end && (c = *KDB_WRAP(start)) && - (p - buf) < sizeof(buf)-1) { - ++start; - *p++ = c; - if (c == '\n') - break; + + if (skip >= n || skip < 0) + return 0; + + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, buf, sizeof(buf), &len)) { + if (skip) { + skip--; + continue; } - *p = '\0'; - kdb_printf("%s", buf); + if (!lines--) + break; + + kdb_printf("%.*s\n", (int)len - 1, buf); } - if (c != '\n') - kdb_printf("\n"); return 0; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 47c4e56e513..392ec6a2584 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -205,7 +205,6 @@ extern char kdb_grep_string[]; extern int kdb_grep_leading; extern int kdb_grep_trailing; extern char *kdb_cmds[]; -extern void kdb_syslog_data(char *syslog_data[]); extern unsigned long kdb_task_state_string(const char *); extern char kdb_task_state_char (const struct task_struct *); extern unsigned long kdb_task_state(const struct task_struct *p, diff --git a/kernel/events/core.c b/kernel/events/core.c index d7d71d6ec97..f1cf0edeb39 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1645,6 +1645,8 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); event->ctx = ctx; + if (event->cpu != -1) + event->cpu = cpu; if (!task) { /* @@ -6252,6 +6254,8 @@ SYSCALL_DEFINE5(perf_event_open, } } + get_online_cpus(); + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL, NULL); if (IS_ERR(event)) { @@ -6304,7 +6308,7 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, cpu); + ctx = find_get_context(pmu, task, event->cpu); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; @@ -6377,20 +6381,23 @@ SYSCALL_DEFINE5(perf_event_open, mutex_lock(&ctx->mutex); if (move_group) { - perf_install_in_context(ctx, group_leader, cpu); + synchronize_rcu(); + perf_install_in_context(ctx, group_leader, event->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_install_in_context(ctx, sibling, cpu); + perf_install_in_context(ctx, sibling, event->cpu); get_ctx(ctx); } } - perf_install_in_context(ctx, event, cpu); + perf_install_in_context(ctx, event, event->cpu); ++ctx->generation; perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); + put_online_cpus(); + event->owner = current; mutex_lock(¤t->perf_event_mutex); @@ -6419,6 +6426,7 @@ err_context: err_alloc: free_event(event); err_task: + put_online_cpus(); if (task) put_task_struct(task); err_group_fd: @@ -6479,6 +6487,39 @@ err: } EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) +{ + struct perf_event_context *src_ctx; + struct perf_event_context *dst_ctx; + struct perf_event *event, *tmp; + LIST_HEAD(events); + + src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx; + dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx; + + mutex_lock(&src_ctx->mutex); + list_for_each_entry_safe(event, tmp, &src_ctx->event_list, + event_entry) { + perf_remove_from_context(event); + put_ctx(src_ctx); + list_add(&event->event_entry, &events); + } + mutex_unlock(&src_ctx->mutex); + + synchronize_rcu(); + + mutex_lock(&dst_ctx->mutex); + list_for_each_entry_safe(event, tmp, &events, event_entry) { + list_del(&event->event_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + mutex_unlock(&dst_ctx->mutex); +} +EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); + static void sync_child_event(struct perf_event *child_event, struct task_struct *child) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 985be4d80fe..f93532748bc 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -38,13 +38,29 @@ #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE -static struct srcu_struct uprobes_srcu; static struct rb_root uprobes_tree = RB_ROOT; static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 +/* + * We need separate register/unregister and mmap/munmap lock hashes because + * of mmap_sem nesting. + * + * uprobe_register() needs to install probes on (potentially) all processes + * and thus needs to acquire multiple mmap_sems (consequtively, not + * concurrently), whereas uprobe_mmap() is called while holding mmap_sem + * for the particular process doing the mmap. + * + * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem + * because of lock order against i_mmap_mutex. This means there's a hole in + * the register vma iteration where a mmap() can happen. + * + * Thus uprobe_register() can race with uprobe_mmap() and we can try and + * install a probe where one is already installed. + */ + /* serialize (un)register */ static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; @@ -61,17 +77,6 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; */ static atomic_t uprobe_events = ATOMIC_INIT(0); -/* - * Maintain a temporary per vma info that can be used to search if a vma - * has already been handled. This structure is introduced since extending - * vm_area_struct wasnt recommended. - */ -struct vma_info { - struct list_head probe_list; - struct mm_struct *mm; - loff_t vaddr; -}; - struct uprobe { struct rb_node rb_node; /* node in the rb tree */ atomic_t ref; @@ -100,7 +105,8 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register) if (!is_register) return true; - if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) + if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) + == (VM_READ|VM_EXEC)) return true; return false; @@ -129,33 +135,17 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; - spinlock_t *ptl; unsigned long addr; - int err = -EFAULT; + spinlock_t *ptl; + pte_t *ptep; addr = page_address_in_vma(page, vma); if (addr == -EFAULT) - goto out; - - pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) - goto out; - - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) - goto out; - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - goto out; + return -EFAULT; - ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); + ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) - goto out; + return -EAGAIN; get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr); @@ -174,10 +164,8 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct try_to_free_swap(page); put_page(page); pte_unmap_unlock(ptep, ptl); - err = 0; -out: - return err; + return 0; } /** @@ -222,9 +210,8 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, void *vaddr_old, *vaddr_new; struct vm_area_struct *vma; struct uprobe *uprobe; - loff_t addr; int ret; - +retry: /* Read the page with vaddr into memory */ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); if (ret <= 0) @@ -246,10 +233,6 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, if (mapping != vma->vm_file->f_mapping) goto put_out; - addr = vma_address(vma, uprobe->offset); - if (vaddr != (unsigned long)addr) - goto put_out; - ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) @@ -267,11 +250,7 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, vaddr_new = kmap_atomic(new_page); memcpy(vaddr_new, vaddr_old, PAGE_SIZE); - - /* poke the new insn in, ASSUMES we don't cross page boundary */ - vaddr &= ~PAGE_MASK; - BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); kunmap_atomic(vaddr_old); @@ -291,6 +270,8 @@ unlock_out: put_out: put_page(old_page); + if (unlikely(ret == -EAGAIN)) + goto retry; return ret; } @@ -312,7 +293,7 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_ void *vaddr_new; int ret; - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL); + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (ret <= 0) return ret; @@ -333,10 +314,20 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) uprobe_opcode_t opcode; int result; + if (current->mm == mm) { + pagefault_disable(); + result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, + sizeof(opcode)); + pagefault_enable(); + + if (likely(result == 0)) + goto out; + } + result = read_opcode(mm, vaddr, &opcode); if (result) return result; - +out: if (is_swbp_insn(&opcode)) return 1; @@ -355,7 +346,9 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { int result; - + /* + * See the comment near uprobes_hash(). + */ result = is_swbp_at_addr(mm, vaddr); if (result == 1) return -EEXIST; @@ -520,7 +513,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = igrab(inode); uprobe->offset = offset; init_rwsem(&uprobe->consumer_rwsem); - INIT_LIST_HEAD(&uprobe->pending_list); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); @@ -588,20 +580,22 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) } static int -__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn, - unsigned long nbytes, unsigned long offset) +__copy_insn(struct address_space *mapping, struct file *filp, char *insn, + unsigned long nbytes, loff_t offset) { - struct file *filp = vma->vm_file; struct page *page; void *vaddr; - unsigned long off1; - unsigned long idx; + unsigned long off; + pgoff_t idx; if (!filp) return -EINVAL; - idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); - off1 = offset &= ~PAGE_MASK; + if (!mapping->a_ops->readpage) + return -EIO; + + idx = offset >> PAGE_CACHE_SHIFT; + off = offset & ~PAGE_MASK; /* * Ensure that the page that has the original instruction is @@ -612,22 +606,20 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins return PTR_ERR(page); vaddr = kmap_atomic(page); - memcpy(insn, vaddr + off1, nbytes); + memcpy(insn, vaddr + off, nbytes); kunmap_atomic(vaddr); page_cache_release(page); return 0; } -static int -copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) +static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping; unsigned long nbytes; int bytes; - addr &= ~PAGE_MASK; - nbytes = PAGE_SIZE - addr; + nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK); mapping = uprobe->inode->i_mapping; /* Instruction at end of binary; copy only available bytes */ @@ -638,13 +630,13 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) /* Instruction at the page-boundary; copy bytes in second page */ if (nbytes < bytes) { - if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes, - bytes - nbytes, uprobe->offset + nbytes)) - return -ENOMEM; - + int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes, + bytes - nbytes, uprobe->offset + nbytes); + if (err) + return err; bytes = nbytes; } - return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset); + return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset); } /* @@ -672,9 +664,8 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) */ static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, - struct vm_area_struct *vma, loff_t vaddr) + struct vm_area_struct *vma, unsigned long vaddr) { - unsigned long addr; int ret; /* @@ -687,20 +678,22 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (!uprobe->consumers) return -EEXIST; - addr = (unsigned long)vaddr; - if (!(uprobe->flags & UPROBE_COPY_INSN)) { - ret = copy_insn(uprobe, vma, addr); + ret = copy_insn(uprobe, vma->vm_file); if (ret) return ret; if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) - return -EEXIST; + return -ENOTSUPP; - ret = arch_uprobe_analyze_insn(&uprobe->arch, mm); + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) return ret; + /* write_opcode() assumes we don't cross page boundary */ + BUG_ON((uprobe->offset & ~PAGE_MASK) + + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + uprobe->flags |= UPROBE_COPY_INSN; } @@ -713,7 +706,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, * Hence increment before and decrement on failure. */ atomic_inc(&mm->uprobes_state.count); - ret = set_swbp(&uprobe->arch, mm, addr); + ret = set_swbp(&uprobe->arch, mm, vaddr); if (ret) atomic_dec(&mm->uprobes_state.count); @@ -721,27 +714,21 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, } static void -remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr) +remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true)) + if (!set_orig_insn(&uprobe->arch, mm, vaddr, true)) atomic_dec(&mm->uprobes_state.count); } /* - * There could be threads that have hit the breakpoint and are entering the - * notifier code and trying to acquire the uprobes_treelock. The thread - * calling delete_uprobe() that is removing the uprobe from the rb_tree can - * race with these threads and might acquire the uprobes_treelock compared - * to some of the breakpoint hit threads. In such a case, the breakpoint - * hit threads will not find the uprobe. The current unregistering thread - * waits till all other threads have hit a breakpoint, to acquire the - * uprobes_treelock before the uprobe is removed from the rbtree. + * There could be threads that have already hit the breakpoint. They + * will recheck the current insn and restart if find_uprobe() fails. + * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { unsigned long flags; - synchronize_srcu(&uprobes_srcu); spin_lock_irqsave(&uprobes_treelock, flags); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock_irqrestore(&uprobes_treelock, flags); @@ -750,139 +737,135 @@ static void delete_uprobe(struct uprobe *uprobe) atomic_dec(&uprobe_events); } -static struct vma_info * -__find_next_vma_info(struct address_space *mapping, struct list_head *head, - struct vma_info *vi, loff_t offset, bool is_register) +struct map_info { + struct map_info *next; + struct mm_struct *mm; + unsigned long vaddr; +}; + +static inline struct map_info *free_map_info(struct map_info *info) +{ + struct map_info *next = info->next; + kfree(info); + return next; +} + +static struct map_info * +build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { + unsigned long pgoff = offset >> PAGE_SHIFT; struct prio_tree_iter iter; struct vm_area_struct *vma; - struct vma_info *tmpvi; - unsigned long pgoff; - int existing_vma; - loff_t vaddr; - - pgoff = offset >> PAGE_SHIFT; + struct map_info *curr = NULL; + struct map_info *prev = NULL; + struct map_info *info; + int more = 0; + again: + mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; - existing_vma = 0; - vaddr = vma_address(vma, offset); - - list_for_each_entry(tmpvi, head, probe_list) { - if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { - existing_vma = 1; - break; - } + if (!prev && !more) { + /* + * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through + * reclaim. This is optimistic, no harm done if it fails. + */ + prev = kmalloc(sizeof(struct map_info), + GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (prev) + prev->next = NULL; } - - /* - * Another vma needs a probe to be installed. However skip - * installing the probe if the vma is about to be unlinked. - */ - if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { - vi->mm = vma->vm_mm; - vi->vaddr = vaddr; - list_add(&vi->probe_list, head); - - return vi; + if (!prev) { + more++; + continue; } - } - - return NULL; -} -/* - * Iterate in the rmap prio tree and find a vma where a probe has not - * yet been inserted. - */ -static struct vma_info * -find_next_vma_info(struct address_space *mapping, struct list_head *head, - loff_t offset, bool is_register) -{ - struct vma_info *vi, *retvi; + if (!atomic_inc_not_zero(&vma->vm_mm->mm_users)) + continue; - vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); - if (!vi) - return ERR_PTR(-ENOMEM); + info = prev; + prev = prev->next; + info->next = curr; + curr = info; - mutex_lock(&mapping->i_mmap_mutex); - retvi = __find_next_vma_info(mapping, head, vi, offset, is_register); + info->mm = vma->vm_mm; + info->vaddr = vma_address(vma, offset); + } mutex_unlock(&mapping->i_mmap_mutex); - if (!retvi) - kfree(vi); + if (!more) + goto out; - return retvi; + prev = curr; + while (curr) { + mmput(curr->mm); + curr = curr->next; + } + + do { + info = kmalloc(sizeof(struct map_info), GFP_KERNEL); + if (!info) { + curr = ERR_PTR(-ENOMEM); + goto out; + } + info->next = prev; + prev = info; + } while (--more); + + goto again; + out: + while (prev) + prev = free_map_info(prev); + return curr; } static int register_for_each_vma(struct uprobe *uprobe, bool is_register) { - struct list_head try_list; - struct vm_area_struct *vma; - struct address_space *mapping; - struct vma_info *vi, *tmpvi; - struct mm_struct *mm; - loff_t vaddr; - int ret; + struct map_info *info; + int err = 0; - mapping = uprobe->inode->i_mapping; - INIT_LIST_HEAD(&try_list); + info = build_map_info(uprobe->inode->i_mapping, + uprobe->offset, is_register); + if (IS_ERR(info)) + return PTR_ERR(info); - ret = 0; + while (info) { + struct mm_struct *mm = info->mm; + struct vm_area_struct *vma; - for (;;) { - vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register); - if (!vi) - break; + if (err) + goto free; - if (IS_ERR(vi)) { - ret = PTR_ERR(vi); - break; - } + down_write(&mm->mmap_sem); + vma = find_vma(mm, (unsigned long)info->vaddr); + if (!vma || !valid_vma(vma, is_register)) + goto unlock; - mm = vi->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, (unsigned long)vi->vaddr); - if (!vma || !valid_vma(vma, is_register)) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - vaddr = vma_address(vma, uprobe->offset); if (vma->vm_file->f_mapping->host != uprobe->inode || - vaddr != vi->vaddr) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - - if (is_register) - ret = install_breakpoint(uprobe, mm, vma, vi->vaddr); - else - remove_breakpoint(uprobe, mm, vi->vaddr); + vma_address(vma, uprobe->offset) != info->vaddr) + goto unlock; - up_read(&mm->mmap_sem); - mmput(mm); if (is_register) { - if (ret && ret == -EEXIST) - ret = 0; - if (ret) - break; + err = install_breakpoint(uprobe, mm, vma, info->vaddr); + /* + * We can race against uprobe_mmap(), see the + * comment near uprobe_hash(). + */ + if (err == -EEXIST) + err = 0; + } else { + remove_breakpoint(uprobe, mm, info->vaddr); } + unlock: + up_write(&mm->mmap_sem); + free: + mmput(mm); + info = free_map_info(info); } - list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { - list_del(&vi->probe_list); - kfree(vi); - } - - return ret; + return err; } static int __uprobe_register(struct uprobe *uprobe) @@ -1048,7 +1031,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head) int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; - struct uprobe *uprobe, *u; + struct uprobe *uprobe; struct inode *inode; int ret, count; @@ -1066,12 +1049,9 @@ int uprobe_mmap(struct vm_area_struct *vma) ret = 0; count = 0; - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); + list_for_each_entry(uprobe, &tmp_list, pending_list) { if (!ret) { - vaddr = vma_address(vma, uprobe->offset); + loff_t vaddr = vma_address(vma, uprobe->offset); if (vaddr < vma->vm_start || vaddr >= vma->vm_end) { put_uprobe(uprobe); @@ -1079,8 +1059,10 @@ int uprobe_mmap(struct vm_area_struct *vma) } ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); - - /* Ignore double add: */ + /* + * We can race against uprobe_register(), see the + * comment near uprobe_hash(). + */ if (ret == -EEXIST) { ret = 0; @@ -1115,7 +1097,7 @@ int uprobe_mmap(struct vm_area_struct *vma) void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct list_head tmp_list; - struct uprobe *uprobe, *u; + struct uprobe *uprobe; struct inode *inode; if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) @@ -1132,11 +1114,8 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, &tmp_list); - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); - vaddr = vma_address(vma, uprobe->offset); + list_for_each_entry(uprobe, &tmp_list, pending_list) { + loff_t vaddr = vma_address(vma, uprobe->offset); if (vaddr >= start && vaddr < end) { /* @@ -1378,9 +1357,6 @@ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; - if (t->uprobe_srcu_id != -1) - srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id); - if (!utask) return; @@ -1398,7 +1374,6 @@ void uprobe_free_utask(struct task_struct *t) void uprobe_copy_process(struct task_struct *t) { t->utask = NULL; - t->uprobe_srcu_id = -1; } /* @@ -1417,7 +1392,6 @@ static struct uprobe_task *add_utask(void) if (unlikely(!utask)) return NULL; - utask->active_uprobe = NULL; current->utask = utask; return utask; } @@ -1479,41 +1453,64 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) return false; } +static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) +{ + struct mm_struct *mm = current->mm; + struct uprobe *uprobe = NULL; + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, bp_vaddr); + if (vma && vma->vm_start <= bp_vaddr) { + if (valid_vma(vma, false)) { + struct inode *inode; + loff_t offset; + + inode = vma->vm_file->f_mapping->host; + offset = bp_vaddr - vma->vm_start; + offset += (vma->vm_pgoff << PAGE_SHIFT); + uprobe = find_uprobe(inode, offset); + } + + if (!uprobe) + *is_swbp = is_swbp_at_addr(mm, bp_vaddr); + } else { + *is_swbp = -EFAULT; + } + up_read(&mm->mmap_sem); + + return uprobe; +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { - struct vm_area_struct *vma; struct uprobe_task *utask; struct uprobe *uprobe; - struct mm_struct *mm; unsigned long bp_vaddr; + int uninitialized_var(is_swbp); - uprobe = NULL; bp_vaddr = uprobe_get_swbp_addr(regs); - mm = current->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, bp_vaddr); - - if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) { - struct inode *inode; - loff_t offset; - - inode = vma->vm_file->f_mapping->host; - offset = bp_vaddr - vma->vm_start; - offset += (vma->vm_pgoff << PAGE_SHIFT); - uprobe = find_uprobe(inode, offset); - } - - srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id); - current->uprobe_srcu_id = -1; - up_read(&mm->mmap_sem); + uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { - /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + if (is_swbp > 0) { + /* No matching uprobe; signal SIGTRAP. */ + send_sig(SIGTRAP, current, 0); + } else { + /* + * Either we raced with uprobe_unregister() or we can't + * access this memory. The latter is only possible if + * another thread plays with our ->mm. In both cases + * we can simply restart. If this vma was unmapped we + * can pretend this insn was not executed yet and get + * the (correct) SIGSEGV after restart. + */ + instruction_pointer_set(regs, bp_vaddr); + } return; } @@ -1620,7 +1617,6 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs) utask->state = UTASK_BP_HIT; set_thread_flag(TIF_UPROBE); - current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu); return 1; } @@ -1655,7 +1651,6 @@ static int __init init_uprobes(void) mutex_init(&uprobes_mutex[i]); mutex_init(&uprobes_mmap_mutex[i]); } - init_srcu_struct(&uprobes_srcu); return register_die_notifier(&uprobe_exception_nb); } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 8b53db38a27..238025f5472 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -27,7 +27,6 @@ #include <linux/syscore_ops.h> #include <linux/ctype.h> #include <linux/genhd.h> -#include <scsi/scsi_scan.h> #include "power.h" @@ -748,13 +747,6 @@ static int software_resume(void) async_synchronize_full(); } - /* - * We can't depend on SCSI devices being available after loading - * one of their modules until scsi_complete_async_scans() is - * called and the resume device usually is a SCSI one. - */ - scsi_complete_async_scans(); - swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { error = -ENODEV; diff --git a/kernel/power/user.c b/kernel/power/user.c index 91b0fd021a9..4ed81e74f86 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -24,7 +24,6 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> -#include <scsi/scsi_scan.h> #include <asm/uaccess.h> @@ -84,7 +83,6 @@ static int snapshot_open(struct inode *inode, struct file *filp) * appear. */ wait_for_device_probe(); - scsi_complete_async_scans(); data->swap = -1; data->mode = O_WRONLY; diff --git a/kernel/printk.c b/kernel/printk.c index 177fa49357a..ac4bc9e7946 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1192,21 +1192,6 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } -#ifdef CONFIG_KGDB_KDB -/* kdb dmesg command needs access to the syslog buffer. do_syslog() - * uses locks so it cannot be used during debugging. Just tell kdb - * where the start and end of the physical and logical logs are. This - * is equivalent to do_syslog(3). - */ -void kdb_syslog_data(char *syslog_data[4]) -{ - syslog_data[0] = log_buf; - syslog_data[1] = log_buf + log_buf_len; - syslog_data[2] = log_buf + log_first_idx; - syslog_data[3] = log_buf + log_next_idx; -} -#endif /* CONFIG_KGDB_KDB */ - static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) @@ -2525,7 +2510,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) } /** - * kmsg_dump_get_line - retrieve one kmsg log line + * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to @@ -2540,11 +2525,12 @@ void kmsg_dump(enum kmsg_dump_reason reason) * * A return value of FALSE indicates that there are no more records to * read. + * + * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ -bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len) +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) { - unsigned long flags; struct log *msg; size_t l = 0; bool ret = false; @@ -2552,7 +2538,6 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, if (!dumper->active) goto out; - raw_spin_lock_irqsave(&logbuf_lock, flags); if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; @@ -2560,10 +2545,8 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, } /* last entry */ - if (dumper->cur_seq >= log_next_seq) { - raw_spin_unlock_irqrestore(&logbuf_lock, flags); + if (dumper->cur_seq >= log_next_seq) goto out; - } msg = log_from_idx(dumper->cur_idx); l = msg_print_text(msg, 0, syslog, line, size); @@ -2571,12 +2554,41 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, dumper->cur_idx = log_next(dumper->cur_idx); dumper->cur_seq++; ret = true; - raw_spin_unlock_irqrestore(&logbuf_lock, flags); out: if (len) *len = l; return ret; } + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + return ret; +} EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** @@ -2679,6 +2691,24 @@ out: EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** + * kmsg_dump_rewind_nolock - reset the interator (unlocked version) + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + * + * The function is similar to kmsg_dump_rewind(), but grabs no locks. + */ +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; +} + +/** * kmsg_dump_rewind - reset the interator * @dumper: registered kmsg dumper * @@ -2691,10 +2721,7 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper) unsigned long flags; raw_spin_lock_irqsave(&logbuf_lock, flags); - dumper->cur_seq = clear_seq; - dumper->cur_idx = clear_idx; - dumper->next_seq = log_next_seq; - dumper->next_idx = log_next_idx; + kmsg_dump_rewind_nolock(dumper); raw_spin_unlock_irqrestore(&logbuf_lock, flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 95cba41ce1e..4e6a61b15e8 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -54,6 +54,50 @@ #ifdef CONFIG_PREEMPT_RCU /* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + barrier(); /* critical section before exit code. */ + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + +/* * Check for a task exiting while in a preemptible-RCU read-side * critical section, clean up if so. No need to issue warnings, * as debug_check_no_locks_held() already does this if lockdep diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 37a5444204d..547b1fe5b05 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -172,7 +172,7 @@ void rcu_irq_enter(void) local_irq_restore(flags); } -#ifdef CONFIG_PROVE_RCU +#ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Test whether RCU thinks that the current CPU is idle. @@ -183,7 +183,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* * Test whether the current CPU was interrupted from idle. Nested diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index fc31a2d6510..918fd1e8509 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,7 +132,6 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -351,8 +350,9 @@ static int rcu_initiate_boost(void) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); - } else + } else { RCU_TRACE(rcu_initiate_boost_trace()); + } return 1; } @@ -527,23 +527,11 @@ void rcu_preempt_note_context_switch(void) } /* - * Tiny-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutiny.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -627,38 +615,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } /* - * Tiny-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the rcu_preempt_ctrlblk structure, which is * checked elsewhere. This is called from the scheduling-clock interrupt. @@ -823,9 +779,9 @@ void synchronize_rcu_expedited(void) rpcp->exp_tasks = NULL; /* Wait for tail of ->blkd_tasks list to drain. */ - if (!rcu_preempted_readers_exp()) + if (!rcu_preempted_readers_exp()) { local_irq_restore(flags); - else { + } else { rcu_initiate_boost(); local_irq_restore(flags); wait_event(sync_rcu_preempt_exp_wq, @@ -846,8 +802,6 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); */ int rcu_preempt_needs_cpu(void) { - if (!rcu_preempt_running_reader()) - rcu_preempt_cpu_qs(); return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index e66b34ab755..25b15033c61 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -49,8 +49,7 @@ #include <asm/byteorder.h> MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and " - "Josh Triplett <josh@freedesktop.org>"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>"); static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ @@ -206,6 +205,7 @@ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ +static bool barrier_phase; /* Test phase. */ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); @@ -407,8 +407,9 @@ rcu_torture_cb(struct rcu_head *p) if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { rp->rtort_mbtest = 0; rcu_torture_free(rp); - } else + } else { cur_ops->deferred_free(rp); + } } static int rcu_no_completed(void) @@ -635,6 +636,17 @@ static void srcu_torture_synchronize(void) synchronize_srcu(&srcu_ctl); } +static void srcu_torture_call(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + call_srcu(&srcu_ctl, head, func); +} + +static void srcu_torture_barrier(void) +{ + srcu_barrier(&srcu_ctl); +} + static int srcu_torture_stats(char *page) { int cnt = 0; @@ -661,8 +673,8 @@ static struct rcu_torture_ops srcu_ops = { .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, - .call = NULL, - .cb_barrier = NULL, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, .name = "srcu" }; @@ -1013,7 +1025,11 @@ rcu_torture_fakewriter(void *arg) do { schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); udelay(rcu_random(&rand) & 0x3ff); - cur_ops->sync(); + if (cur_ops->cb_barrier != NULL && + rcu_random(&rand) % (nfakewriters * 8) == 0) + cur_ops->cb_barrier(); + else + cur_ops->sync(); rcu_stutter_wait("rcu_torture_fakewriter"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); @@ -1183,27 +1199,27 @@ rcu_torture_printk(char *page) } cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " - "rtmbe: %d rtbke: %ld rtbre: %ld " - "rtbf: %ld rtb: %ld nt: %ld " - "onoff: %ld/%ld:%ld/%ld " - "barrier: %ld/%ld:%ld", + "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), atomic_read(&n_rcu_torture_alloc), atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free), + atomic_read(&n_rcu_torture_free)); + cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ", atomic_read(&n_rcu_torture_mberror), n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror, + n_rcu_torture_boost_rterror); + cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers, + n_rcu_torture_timers); + cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ", n_online_successes, n_online_attempts, n_offline_successes, - n_offline_attempts, + n_offline_attempts); + cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld", n_barrier_successes, n_barrier_attempts, n_rcu_torture_barrier_error); @@ -1445,8 +1461,7 @@ rcu_torture_shutdown(void *arg) delta = shutdown_time - jiffies_snap; if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_shutdown task: %lu " - "jiffies remaining\n", + "rcu_torture_shutdown task: %lu jiffies remaining\n", torture_type, delta); schedule_timeout_interruptible(delta); jiffies_snap = ACCESS_ONCE(jiffies); @@ -1498,8 +1513,7 @@ rcu_torture_onoff(void *arg) if (cpu_down(cpu) == 0) { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "offlined %d\n", + "rcu_torture_onoff task: offlined %d\n", torture_type, cpu); n_offline_successes++; } @@ -1512,8 +1526,7 @@ rcu_torture_onoff(void *arg) if (cpu_up(cpu) == 0) { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "onlined %d\n", + "rcu_torture_onoff task: onlined %d\n", torture_type, cpu); n_online_successes++; } @@ -1631,6 +1644,7 @@ void rcu_torture_barrier_cbf(struct rcu_head *rcu) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; + bool lastphase = 0; struct rcu_head rcu; init_rcu_head_on_stack(&rcu); @@ -1638,9 +1652,11 @@ static int rcu_torture_barrier_cbs(void *arg) set_user_nice(current, 19); do { wait_event(barrier_cbs_wq[myid], - atomic_read(&barrier_cbs_count) == n_barrier_cbs || + barrier_phase != lastphase || kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP); + lastphase = barrier_phase; + smp_mb(); /* ensure barrier_phase load before ->call(). */ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) break; cur_ops->call(&rcu, rcu_torture_barrier_cbf); @@ -1665,7 +1681,8 @@ static int rcu_torture_barrier(void *arg) do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); - /* wake_up() path contains the required barriers. */ + smp_mb(); /* Ensure barrier_phase after prior assignments. */ + barrier_phase = !barrier_phase; for (i = 0; i < n_barrier_cbs; i++) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, @@ -1684,7 +1701,7 @@ static int rcu_torture_barrier(void *arg) schedule_timeout_interruptible(HZ / 10); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping"); - rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); + rcutorture_shutdown_absorb("rcu_torture_barrier"); while (!kthread_should_stop()) schedule_timeout_interruptible(1); return 0; @@ -1908,8 +1925,8 @@ rcu_torture_init(void) static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, - &srcu_ops, &srcu_sync_ops, &srcu_raw_ops, - &srcu_raw_sync_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops, + &srcu_raw_ops, &srcu_raw_sync_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); @@ -1931,8 +1948,7 @@ rcu_torture_init(void) return -EINVAL; } if (cur_ops->fqs == NULL && fqs_duration != 0) { - printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero " - "fqs_duration, fqs disabled.\n"); + printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); fqs_duration = 0; } if (cur_ops->init) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4b97bba7396..f280e542e3e 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -60,36 +60,44 @@ /* Data structures. */ -static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; +static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; -#define RCU_STATE_INITIALIZER(structname) { \ - .level = { &structname##_state.node[0] }, \ - .levelcnt = { \ - NUM_RCU_LVL_0, /* root of hierarchy. */ \ - NUM_RCU_LVL_1, \ - NUM_RCU_LVL_2, \ - NUM_RCU_LVL_3, \ - NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ - }, \ +#define RCU_STATE_INITIALIZER(sname, cr) { \ + .level = { &sname##_state.node[0] }, \ + .call = cr, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ - .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \ - .orphan_nxttail = &structname##_state.orphan_nxtlist, \ - .orphan_donetail = &structname##_state.orphan_donelist, \ - .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.fqslock), \ - .n_force_qs = 0, \ - .n_force_qs_ngp = 0, \ - .name = #structname, \ + .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.onofflock), \ + .orphan_nxttail = &sname##_state.orphan_nxtlist, \ + .orphan_donetail = &sname##_state.orphan_donelist, \ + .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ + .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \ + .name = #sname, \ } -struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched); +struct rcu_state rcu_sched_state = + RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched); DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); -struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh); +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; +LIST_HEAD(rcu_struct_flavors); + +/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ +static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; +module_param(rcu_fanout_leaf, int, 0); +int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; +static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ + NUM_RCU_LVL_0, + NUM_RCU_LVL_1, + NUM_RCU_LVL_2, + NUM_RCU_LVL_3, + NUM_RCU_LVL_4, +}; +int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ /* * The rcu_scheduler_active variable transitions from zero to one just @@ -147,13 +155,6 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); unsigned long rcutorture_testseq; unsigned long rcutorture_vernum; -/* State information for rcu_barrier() and friends. */ - -static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; -static atomic_t rcu_barrier_cpu_count; -static DEFINE_MUTEX(rcu_barrier_mutex); -static struct completion rcu_barrier_completion; - /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node @@ -358,7 +359,7 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -468,7 +469,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) trace_rcu_dyntick("Error on exit: not idle task", oldval, rdtp->dynticks_nesting); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -585,8 +586,6 @@ void rcu_nmi_exit(void) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } -#ifdef CONFIG_PROVE_RCU - /** * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle * @@ -604,7 +603,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* * Is the current CPU online? Disable preemption to avoid false positives @@ -645,9 +644,7 @@ bool rcu_lockdep_current_cpu_online(void) } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ /** * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle @@ -733,7 +730,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) int cpu; long delta; unsigned long flags; - int ndetected; + int ndetected = 0; struct rcu_node *rnp = rcu_get_root(rsp); /* Only let one CPU complain about others per time interval. */ @@ -774,7 +771,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) */ rnp = rcu_get_root(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); - ndetected = rcu_print_task_stall(rnp); + ndetected += rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); print_cpu_stall_info_end(); @@ -860,9 +857,10 @@ static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) */ void rcu_cpu_stall_reset(void) { - rcu_sched_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_bh_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_preempt_stall_reset(); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rsp->jiffies_stall = jiffies + ULONG_MAX / 2; } static struct notifier_block rcu_panic_block = { @@ -894,8 +892,9 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct if (rnp->qsmask & rdp->grpmask) { rdp->qs_pending = 1; rdp->passed_quiesce = 0; - } else + } else { rdp->qs_pending = 0; + } zero_cpu_stall_ticks(rdp); } } @@ -937,6 +936,18 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) } /* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + int i; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; +} + +/* * Advance this CPU's callbacks, but only if the current grace period * has ended. This may be called only from the CPU to whom the rdp * belongs. In addition, the corresponding leaf rcu_node structure's @@ -1328,8 +1339,6 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - int i; - /* * Orphan the callbacks. First adjust the counts. This is safe * because ->onofflock excludes _rcu_barrier()'s adoption of @@ -1340,7 +1349,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->qlen += rdp->qlen; rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; } /* @@ -1369,9 +1378,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, } /* Finally, initialize the rcu_data structure's list to empty. */ - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); } /* @@ -1505,6 +1512,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); + WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", + cpu, rdp->qlen, rdp->nxtlist); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -1592,7 +1602,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - rdp->qlen -= count; + ACCESS_ONCE(rdp->qlen) -= count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -1605,6 +1615,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rdp->n_force_qs_snap = rsp->n_force_qs; } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = rdp->qlen; + WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0)); local_irq_restore(flags); @@ -1745,8 +1756,6 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) break; /* grace period idle or initializing, ignore. */ case RCU_SAVE_DYNTICK: - if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK) - break; /* So gcc recognizes the dead code. */ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ @@ -1788,9 +1797,10 @@ unlock_fqs_ret: * whom the rdp belongs. */ static void -__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +__rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); WARN_ON_ONCE(rdp->beenonline == 0); @@ -1826,11 +1836,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_process_callbacks(struct softirq_action *unused) { + struct rcu_state *rsp; + trace_rcu_utilization("Start RCU core"); - __rcu_process_callbacks(&rcu_sched_state, - &__get_cpu_var(rcu_sched_data)); - __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); - rcu_preempt_process_callbacks(); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); trace_rcu_utilization("End RCU core"); } @@ -1857,6 +1867,56 @@ static void invoke_rcu_core(void) raise_softirq(RCU_SOFTIRQ); } +/* + * Handle any core-RCU processing required by a call_rcu() invocation. + */ +static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, + struct rcu_head *head, unsigned long flags) +{ + /* + * If called from an extended quiescent state, invoke the RCU + * core in order to force a re-evaluation of RCU's idleness. + */ + if (rcu_is_cpu_idle() && cpu_online(smp_processor_id())) + invoke_rcu_core(); + + /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) + return; + + /* + * Force the grace period if too many callbacks or too long waiting. + * Enforce hysteresis, and don't invoke force_quiescent_state() + * if some other CPU has recently done so. Also, don't bother + * invoking force_quiescent_state() if the newly enqueued callback + * is the only one waiting for a grace period to complete. + */ + if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { + + /* Are we ignoring a completed grace period? */ + rcu_process_gp_end(rsp, rdp); + check_for_new_grace_period(rsp, rdp); + + /* Start a new grace period if one not already started. */ + if (!rcu_gp_in_progress(rsp)) { + unsigned long nestflag; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + raw_spin_lock_irqsave(&rnp_root->lock, nestflag); + rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ + } else { + /* Give the grace period a kick. */ + rdp->blimit = LONG_MAX; + if (rsp->n_force_qs == rdp->n_force_qs_snap && + *rdp->nxttail[RCU_DONE_TAIL] != head) + force_quiescent_state(rsp, 0); + rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->qlen_last_fqs_check = rdp->qlen; + } + } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) + force_quiescent_state(rsp, 1); +} + static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp, bool lazy) @@ -1881,7 +1941,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ - rdp->qlen++; + ACCESS_ONCE(rdp->qlen)++; if (lazy) rdp->qlen_lazy++; else @@ -1896,43 +1956,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), else trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); - /* If interrupts were disabled, don't dive into RCU core. */ - if (irqs_disabled_flags(flags)) { - local_irq_restore(flags); - return; - } - - /* - * Force the grace period if too many callbacks or too long waiting. - * Enforce hysteresis, and don't invoke force_quiescent_state() - * if some other CPU has recently done so. Also, don't bother - * invoking force_quiescent_state() if the newly enqueued callback - * is the only one waiting for a grace period to complete. - */ - if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { - - /* Are we ignoring a completed grace period? */ - rcu_process_gp_end(rsp, rdp); - check_for_new_grace_period(rsp, rdp); - - /* Start a new grace period if one not already started. */ - if (!rcu_gp_in_progress(rsp)) { - unsigned long nestflag; - struct rcu_node *rnp_root = rcu_get_root(rsp); - - raw_spin_lock_irqsave(&rnp_root->lock, nestflag); - rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ - } else { - /* Give the grace period a kick. */ - rdp->blimit = LONG_MAX; - if (rsp->n_force_qs == rdp->n_force_qs_snap && - *rdp->nxttail[RCU_DONE_TAIL] != head) - force_quiescent_state(rsp, 0); - rdp->n_force_qs_snap = rsp->n_force_qs; - rdp->qlen_last_fqs_check = rdp->qlen; - } - } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); + /* Go handle any RCU core processing required. */ + __call_rcu_core(rsp, rdp, head, flags); local_irq_restore(flags); } @@ -1962,28 +1987,16 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * occasionally incorrectly indicate that there are multiple CPUs online * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. - * - * Of course, sampling num_online_cpus() with preemption enabled can - * give erroneous results if there are concurrent CPU-hotplug operations. - * For example, given a demonic sequence of preemptions in num_online_cpus() - * and CPU-hotplug operations, there could be two or more CPUs online at - * all times, but num_online_cpus() might well return one (or even zero). - * - * However, all such demonic sequences require at least one CPU-offline - * operation. Furthermore, rcu_blocking_is_gp() giving the wrong answer - * is only a problem if there is an RCU read-side critical section executing - * throughout. But RCU-sched and RCU-bh read-side critical sections - * disable either preemption or bh, which prevents a CPU from going offline. - * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return - * that there is only one CPU when in fact there was more than one throughout - * is when there were no RCU readers in the system. If there are no - * RCU readers, the grace period by definition can be of zero length, - * regardless of the number of online CPUs. */ static inline int rcu_blocking_is_gp(void) { + int ret; + might_sleep(); /* Check for RCU read-side critical section. */ - return num_online_cpus() <= 1; + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; } /** @@ -2118,9 +2131,9 @@ void synchronize_sched_expedited(void) put_online_cpus(); /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_sched(); return; } @@ -2241,9 +2254,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) */ static int rcu_pending(int cpu) { - return __rcu_pending(&rcu_sched_state, &per_cpu(rcu_sched_data, cpu)) || - __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)) || - rcu_preempt_pending(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + if (__rcu_pending(rsp, per_cpu_ptr(rsp->rda, cpu))) + return 1; + return 0; } /* @@ -2253,20 +2269,41 @@ static int rcu_pending(int cpu) */ static int rcu_cpu_has_callbacks(int cpu) { + struct rcu_state *rsp; + /* RCU callbacks either ready or pending? */ - return per_cpu(rcu_sched_data, cpu).nxtlist || - per_cpu(rcu_bh_data, cpu).nxtlist || - rcu_preempt_cpu_has_callbacks(cpu); + for_each_rcu_flavor(rsp) + if (per_cpu_ptr(rsp->rda, cpu)->nxtlist) + return 1; + return 0; +} + +/* + * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * the compiler is expected to optimize this away. + */ +static void _rcu_barrier_trace(struct rcu_state *rsp, char *s, + int cpu, unsigned long done) +{ + trace_rcu_barrier(rsp->name, s, cpu, + atomic_read(&rsp->barrier_cpu_count), done); } /* * RCU callback function for _rcu_barrier(). If we are last, wake * up the task executing _rcu_barrier(). */ -static void rcu_barrier_callback(struct rcu_head *notused) +static void rcu_barrier_callback(struct rcu_head *rhp) { - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) - complete(&rcu_barrier_completion); + struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); + struct rcu_state *rsp = rdp->rsp; + + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { + _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done); + complete(&rsp->barrier_completion); + } else { + _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done); + } } /* @@ -2274,35 +2311,63 @@ static void rcu_barrier_callback(struct rcu_head *notused) */ static void rcu_barrier_func(void *type) { - int cpu = smp_processor_id(); - struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu); - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head)); + struct rcu_state *rsp = type; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); - atomic_inc(&rcu_barrier_cpu_count); - call_rcu_func = type; - call_rcu_func(head, rcu_barrier_callback); + _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); + atomic_inc(&rsp->barrier_cpu_count); + rsp->call(&rdp->barrier_head, rcu_barrier_callback); } /* * Orchestrate the specified type of RCU barrier, waiting for all * RCU callbacks of the specified type to complete. */ -static void _rcu_barrier(struct rcu_state *rsp, - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head))) +static void _rcu_barrier(struct rcu_state *rsp) { int cpu; unsigned long flags; struct rcu_data *rdp; - struct rcu_head rh; + struct rcu_data rd; + unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); + unsigned long snap_done; - init_rcu_head_on_stack(&rh); + init_rcu_head_on_stack(&rd.barrier_head); + _rcu_barrier_trace(rsp, "Begin", -1, snap); /* Take mutex to serialize concurrent rcu_barrier() requests. */ - mutex_lock(&rcu_barrier_mutex); + mutex_lock(&rsp->barrier_mutex); + + /* + * Ensure that all prior references, including to ->n_barrier_done, + * are ordered before the _rcu_barrier() machinery. + */ + smp_mb(); /* See above block comment. */ + + /* + * Recheck ->n_barrier_done to see if others did our work for us. + * This means checking ->n_barrier_done for an even-to-odd-to-even + * transition. The "if" expression below therefore rounds the old + * value up to the next even number and adds two before comparing. + */ + snap_done = ACCESS_ONCE(rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "Check", -1, snap_done); + if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) { + _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done); + smp_mb(); /* caller's subsequent code after above check. */ + mutex_unlock(&rsp->barrier_mutex); + return; + } - smp_mb(); /* Prevent any prior operations from leaking in. */ + /* + * Increment ->n_barrier_done to avoid duplicate work. Use + * ACCESS_ONCE() to prevent the compiler from speculating + * the increment to precede the early-exit check. + */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); + _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); + smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ /* * Initialize the count to one rather than to zero in order to @@ -2321,8 +2386,8 @@ static void _rcu_barrier(struct rcu_state *rsp, * 6. Both rcu_barrier_callback() callbacks are invoked, awakening * us -- but before CPU 1's orphaned callbacks are invoked!!! */ - init_completion(&rcu_barrier_completion); - atomic_set(&rcu_barrier_cpu_count, 1); + init_completion(&rsp->barrier_completion); + atomic_set(&rsp->barrier_cpu_count, 1); raw_spin_lock_irqsave(&rsp->onofflock, flags); rsp->rcu_barrier_in_progress = current; raw_spin_unlock_irqrestore(&rsp->onofflock, flags); @@ -2338,14 +2403,19 @@ static void _rcu_barrier(struct rcu_state *rsp, preempt_disable(); rdp = per_cpu_ptr(rsp->rda, cpu); if (cpu_is_offline(cpu)) { + _rcu_barrier_trace(rsp, "Offline", cpu, + rsp->n_barrier_done); preempt_enable(); while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen)) schedule_timeout_interruptible(1); } else if (ACCESS_ONCE(rdp->qlen)) { - smp_call_function_single(cpu, rcu_barrier_func, - (void *)call_rcu_func, 1); + _rcu_barrier_trace(rsp, "OnlineQ", cpu, + rsp->n_barrier_done); + smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); preempt_enable(); } else { + _rcu_barrier_trace(rsp, "OnlineNQ", cpu, + rsp->n_barrier_done); preempt_enable(); } } @@ -2362,24 +2432,32 @@ static void _rcu_barrier(struct rcu_state *rsp, rcu_adopt_orphan_cbs(rsp); rsp->rcu_barrier_in_progress = NULL; raw_spin_unlock_irqrestore(&rsp->onofflock, flags); - atomic_inc(&rcu_barrier_cpu_count); + atomic_inc(&rsp->barrier_cpu_count); smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */ - call_rcu_func(&rh, rcu_barrier_callback); + rd.rsp = rsp; + rsp->call(&rd.barrier_head, rcu_barrier_callback); /* * Now that we have an rcu_barrier_callback() callback on each * CPU, and thus each counted, remove the initial count. */ - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) - complete(&rcu_barrier_completion); + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) + complete(&rsp->barrier_completion); + + /* Increment ->n_barrier_done to prevent duplicate work. */ + smp_mb(); /* Keep increment after above mechanism. */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); + _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); + smp_mb(); /* Keep increment before caller's subsequent code. */ /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ - wait_for_completion(&rcu_barrier_completion); + wait_for_completion(&rsp->barrier_completion); /* Other rcu_barrier() invocations can now safely proceed. */ - mutex_unlock(&rcu_barrier_mutex); + mutex_unlock(&rsp->barrier_mutex); - destroy_rcu_head_on_stack(&rh); + destroy_rcu_head_on_stack(&rd.barrier_head); } /** @@ -2387,7 +2465,7 @@ static void _rcu_barrier(struct rcu_state *rsp, */ void rcu_barrier_bh(void) { - _rcu_barrier(&rcu_bh_state, call_rcu_bh); + _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); @@ -2396,7 +2474,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_bh); */ void rcu_barrier_sched(void) { - _rcu_barrier(&rcu_sched_state, call_rcu_sched); + _rcu_barrier(&rcu_sched_state); } EXPORT_SYMBOL_GPL(rcu_barrier_sched); @@ -2407,18 +2485,15 @@ static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; - int i; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); @@ -2492,9 +2567,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) static void __cpuinit rcu_prepare_cpu(int cpu) { - rcu_init_percpu_data(cpu, &rcu_sched_state, 0); - rcu_init_percpu_data(cpu, &rcu_bh_state, 0); - rcu_preempt_init_percpu_data(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_init_percpu_data(cpu, rsp, + strcmp(rsp->name, "rcu_preempt") == 0); } /* @@ -2506,6 +2583,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, long cpu = (long)hcpu; struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); struct rcu_node *rnp = rdp->mynode; + struct rcu_state *rsp; trace_rcu_utilization("Start CPU hotplug"); switch (action) { @@ -2530,18 +2608,16 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, * touch any data without introducing corruption. We send the * dying CPU's callbacks to an arbitrarily chosen online CPU. */ - rcu_cleanup_dying_cpu(&rcu_bh_state); - rcu_cleanup_dying_cpu(&rcu_sched_state); - rcu_preempt_cleanup_dying_cpu(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - rcu_cleanup_dead_cpu(cpu, &rcu_bh_state); - rcu_cleanup_dead_cpu(cpu, &rcu_sched_state); - rcu_preempt_cleanup_dead_cpu(cpu); + for_each_rcu_flavor(rsp) + rcu_cleanup_dead_cpu(cpu, rsp); break; default: break; @@ -2574,9 +2650,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) { int i; - for (i = NUM_RCU_LVLS - 1; i > 0; i--) + for (i = rcu_num_lvls - 1; i > 0; i--) rsp->levelspread[i] = CONFIG_RCU_FANOUT; - rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF; + rsp->levelspread[0] = rcu_fanout_leaf; } #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ static void __init rcu_init_levelspread(struct rcu_state *rsp) @@ -2586,7 +2662,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) int i; cprv = NR_CPUS; - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { ccur = rsp->levelcnt[i]; rsp->levelspread[i] = (cprv + ccur - 1) / ccur; cprv = ccur; @@ -2613,13 +2689,15 @@ static void __init rcu_init_one(struct rcu_state *rsp, /* Initialize the level-tracking arrays. */ - for (i = 1; i < NUM_RCU_LVLS; i++) + for (i = 0; i < rcu_num_lvls; i++) + rsp->levelcnt[i] = num_rcu_lvl[i]; + for (i = 1; i < rcu_num_lvls; i++) rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; rcu_init_levelspread(rsp); /* Initialize the elements themselves, starting from the leaves. */ - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { cpustride *= rsp->levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { @@ -2649,13 +2727,74 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; - rnp = rsp->level[NUM_RCU_LVLS - 1]; + rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; per_cpu_ptr(rsp->rda, i)->mynode = rnp; rcu_boot_init_percpu_data(i, rsp); } + list_add(&rsp->flavors, &rcu_struct_flavors); +} + +/* + * Compute the rcu_node tree geometry from kernel parameters. This cannot + * replace the definitions in rcutree.h because those are needed to size + * the ->node array in the rcu_state structure. + */ +static void __init rcu_init_geometry(void) +{ + int i; + int j; + int n = nr_cpu_ids; + int rcu_capacity[MAX_RCU_LVLS + 1]; + + /* If the compile-time values are accurate, just leave. */ + if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF) + return; + + /* + * Compute number of nodes that can be handled an rcu_node tree + * with the given number of levels. Setting rcu_capacity[0] makes + * some of the arithmetic easier. + */ + rcu_capacity[0] = 1; + rcu_capacity[1] = rcu_fanout_leaf; + for (i = 2; i <= MAX_RCU_LVLS; i++) + rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT; + + /* + * The boot-time rcu_fanout_leaf parameter is only permitted + * to increase the leaf-level fanout, not decrease it. Of course, + * the leaf-level fanout cannot exceed the number of bits in + * the rcu_node masks. Finally, the tree must be able to accommodate + * the configured number of CPUs. Complain and fall back to the + * compile-time values if these limits are exceeded. + */ + if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF || + rcu_fanout_leaf > sizeof(unsigned long) * 8 || + n > rcu_capacity[MAX_RCU_LVLS]) { + WARN_ON(1); + return; + } + + /* Calculate the number of rcu_nodes at each level of the tree. */ + for (i = 1; i <= MAX_RCU_LVLS; i++) + if (n <= rcu_capacity[i]) { + for (j = 0; j <= i; j++) + num_rcu_lvl[j] = + DIV_ROUND_UP(n, rcu_capacity[i - j]); + rcu_num_lvls = i; + for (j = i + 1; j <= MAX_RCU_LVLS; j++) + num_rcu_lvl[j] = 0; + break; + } + + /* Calculate the total number of rcu_node structures. */ + rcu_num_nodes = 0; + for (i = 0; i <= MAX_RCU_LVLS; i++) + rcu_num_nodes += num_rcu_lvl[i]; + rcu_num_nodes -= n; } void __init rcu_init(void) @@ -2663,6 +2802,7 @@ void __init rcu_init(void) int cpu; rcu_bootup_announce(); + rcu_init_geometry(); rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 19b61ac1079..4d29169f212 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -42,28 +42,28 @@ #define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) #if NR_CPUS <= RCU_FANOUT_1 -# define NUM_RCU_LVLS 1 +# define RCU_NUM_LVLS 1 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 (NR_CPUS) # define NUM_RCU_LVL_2 0 # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_2 -# define NUM_RCU_LVLS 2 +# define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_3 -# define NUM_RCU_LVLS 3 +# define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_3 (NR_CPUS) # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_4 -# define NUM_RCU_LVLS 4 +# define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) @@ -76,6 +76,9 @@ #define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) +extern int rcu_num_lvls; +extern int rcu_num_nodes; + /* * Dynticks per-CPU state. */ @@ -97,6 +100,7 @@ struct rcu_dynticks { /* # times non-lazy CBs posted to CPU. */ unsigned long nonlazy_posted_snap; /* idle-period nonlazy_posted snapshot. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ }; @@ -206,7 +210,7 @@ struct rcu_node { */ #define rcu_for_each_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* * Do a breadth-first scan of the non-leaf rcu_node structures for the @@ -215,7 +219,7 @@ struct rcu_node { */ #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++) /* * Scan the leaves of the rcu_node hierarchy for the specified rcu_state @@ -224,8 +228,8 @@ struct rcu_node { * It is still a leaf node, even if it is also the root node. */ #define rcu_for_each_leaf_node(rsp, rnp) \ - for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ @@ -311,6 +315,9 @@ struct rcu_data { unsigned long n_rp_need_fqs; unsigned long n_rp_need_nothing; + /* 6) _rcu_barrier() callback. */ + struct rcu_head barrier_head; + int cpu; struct rcu_state *rsp; }; @@ -357,10 +364,12 @@ do { \ */ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ - struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */ + struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ - u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */ + u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ + void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ + void (*func)(struct rcu_head *head)); /* The following fields are guarded by the root rcu_node's lock. */ @@ -392,6 +401,11 @@ struct rcu_state { struct task_struct *rcu_barrier_in_progress; /* Task doing rcu_barrier(), */ /* or NULL if no barrier. */ + struct mutex barrier_mutex; /* Guards barrier fields. */ + atomic_t barrier_cpu_count; /* # CPUs waiting on. */ + struct completion barrier_completion; /* Wake at barrier end. */ + unsigned long n_barrier_done; /* ++ at start and end of */ + /* _rcu_barrier(). */ raw_spinlock_t fqslock; /* Only one task forcing */ /* quiescent states. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ @@ -409,8 +423,13 @@ struct rcu_state { unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ char *name; /* Name of structure. */ + struct list_head flavors; /* List of RCU flavors. */ }; +extern struct list_head rcu_struct_flavors; +#define for_each_rcu_flavor(rsp) \ + list_for_each_entry((rsp), &rcu_struct_flavors, flavors) + /* Return values for rcu_preempt_offline_tasks(). */ #define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ @@ -453,25 +472,18 @@ static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); -static void rcu_preempt_stall_reset(void); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_preempt_cleanup_dead_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); -static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ -static int rcu_preempt_pending(int cpu); -static int rcu_preempt_cpu_has_callbacks(int cpu); -static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void rcu_preempt_cleanup_dying_cpu(void); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3e4899459f3..7f3244c0df0 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -68,17 +68,21 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n"); #endif #if NUM_RCU_LVL_4 != 0 - printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); + printk(KERN_INFO "\tFour-level hierarchy is enabled.\n"); #endif + if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) + printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + if (nr_cpu_ids != NR_CPUS) + printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); } #ifdef CONFIG_TREE_PREEMPT_RCU -struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt); +struct rcu_state rcu_preempt_state = + RCU_STATE_INITIALIZER(rcu_preempt, call_rcu); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -233,18 +237,6 @@ static void rcu_preempt_note_context_switch(int cpu) } /* - * Tree-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutree.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. @@ -310,7 +302,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -398,8 +390,9 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) rnp->grphi, !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rnp, flags); - } else + } else { raw_spin_unlock_irqrestore(&rnp->lock, flags); + } #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ @@ -418,38 +411,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } } -/* - * Tree-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* @@ -540,16 +501,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* - * Suppress preemptible RCU's CPU stall warnings by pushing the - * time of the next stall-warning message comfortably far into the - * future. - */ -static void rcu_preempt_stall_reset(void) -{ - rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2; -} - -/* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be @@ -650,14 +601,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Do CPU-offline processing for preemptible RCU. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ - rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state); -} - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, * which is checked elsewhere. @@ -677,15 +620,6 @@ static void rcu_preempt_check_callbacks(int cpu) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } -/* - * Process callbacks for preemptible RCU. - */ -static void rcu_preempt_process_callbacks(void) -{ - __rcu_process_callbacks(&rcu_preempt_state, - &__get_cpu_var(rcu_preempt_data)); -} - #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void) @@ -824,9 +758,9 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) int must_wait = 0; raw_spin_lock_irqsave(&rnp->lock, flags); - if (list_empty(&rnp->blkd_tasks)) + if (list_empty(&rnp->blkd_tasks)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - else { + } else { rnp->exp_tasks = rnp->blkd_tasks.next; rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ must_wait = 1; @@ -870,9 +804,9 @@ void synchronize_rcu_expedited(void) * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_rcu(); return; } @@ -917,51 +851,16 @@ mb_ret: } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -/* - * Check to see if there is any immediate preemptible-RCU-related work - * to be done. - */ -static int rcu_preempt_pending(int cpu) -{ - return __rcu_pending(&rcu_preempt_state, - &per_cpu(rcu_preempt_data, cpu)); -} - -/* - * Does preemptible RCU have callbacks on this CPU? - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return !!per_cpu(rcu_preempt_data, cpu).nxtlist; -} - /** * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. */ void rcu_barrier(void) { - _rcu_barrier(&rcu_preempt_state, call_rcu); + _rcu_barrier(&rcu_preempt_state); } EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Initialize preemptible RCU's per-CPU data. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ - rcu_init_percpu_data(cpu, &rcu_preempt_state, 1); -} - -/* - * Move preemptible RCU's callbacks from dying CPU to other online CPU - * and record a quiescent state. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ - rcu_cleanup_dying_cpu(&rcu_preempt_state); -} - -/* * Initialize preemptible RCU's state structures. */ static void __init __rcu_init_preempt(void) @@ -1046,14 +945,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* - * Because preemptible RCU does not exist, there is no need to suppress - * its CPU stall warnings. - */ -static void rcu_preempt_stall_reset(void) -{ -} - -/* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. @@ -1081,14 +972,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptible RCU does not exist, it never needs CPU-offline - * processing. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ -} - -/* * Because preemptible RCU does not exist, it never has any callbacks * to check. */ @@ -1097,14 +980,6 @@ static void rcu_preempt_check_callbacks(int cpu) } /* - * Because preemptible RCU does not exist, it never has any callbacks - * to process. - */ -static void rcu_preempt_process_callbacks(void) -{ -} - -/* * Queue an RCU callback for lazy invocation after a grace period. * This will likely be later named something like "call_rcu_lazy()", * but this change will require some way of tagging the lazy RCU @@ -1145,22 +1020,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptible RCU does not exist, it never has any work to do. - */ -static int rcu_preempt_pending(int cpu) -{ - return 0; -} - -/* - * Because preemptible RCU does not exist, it never has callbacks - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return 0; -} - -/* * Because preemptible RCU does not exist, rcu_barrier() is just * another name for rcu_barrier_sched(). */ @@ -1171,21 +1030,6 @@ void rcu_barrier(void) EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Because preemptible RCU does not exist, there is no per-CPU - * data to initialize. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ -} - -/* - * Because there is no preemptible RCU, there is no cleanup to do. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ -} - -/* * Because preemptible RCU does not exist, it need not be initialized. */ static void __init __rcu_init_preempt(void) @@ -1968,9 +1812,11 @@ static void rcu_idle_count_callbacks_posted(void) */ #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ -#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ +extern int tick_nohz_enabled; + /* * Does the specified flavor of RCU have non-lazy callbacks pending on * the specified CPU? Both RCU flavor and CPU are specified by the @@ -2047,10 +1893,13 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) return 1; } /* Set up for the possibility that RCU will post a timer. */ - if (rcu_cpu_has_nonlazy_callbacks(cpu)) - *delta_jiffies = RCU_IDLE_GP_DELAY; - else - *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + *delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies, + RCU_IDLE_GP_DELAY) - jiffies; + } else { + *delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY; + *delta_jiffies = round_jiffies(*delta_jiffies) - jiffies; + } return 0; } @@ -2109,6 +1958,7 @@ static void rcu_cleanup_after_idle(int cpu) del_timer(&rdtp->idle_gp_timer); trace_rcu_prep_idle("Cleanup after idle"); + rdtp->tick_nohz_enabled_snap = ACCESS_ONCE(tick_nohz_enabled); } /* @@ -2134,6 +1984,18 @@ static void rcu_prepare_for_idle(int cpu) { struct timer_list *tp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + int tne; + + /* Handle nohz enablement switches conservatively. */ + tne = ACCESS_ONCE(tick_nohz_enabled); + if (tne != rdtp->tick_nohz_enabled_snap) { + if (rcu_cpu_has_callbacks(cpu)) + invoke_rcu_core(); /* force nohz to see update. */ + rdtp->tick_nohz_enabled_snap = tne; + return; + } + if (!tne) + return; /* * If this is an idle re-entry, for example, due to use of @@ -2187,10 +2049,11 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_nonlazy_callbacks(cpu)) { trace_rcu_prep_idle("Dyntick with callbacks"); rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_GP_DELAY; + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); } else { rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_LAZY_GP_DELAY; + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); trace_rcu_prep_idle("Dyntick with lazy callbacks"); } tp = &rdtp->idle_gp_timer; @@ -2231,8 +2094,9 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_callbacks(cpu)) { trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - } else + } else { trace_rcu_prep_idle("Callbacks drained"); + } } /* @@ -2269,6 +2133,7 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { + *cp = '\0'; } #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index d4bc16ddd1d..abffb486e94 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,6 +46,31 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +static int show_rcubarrier(struct seq_file *m, void *unused) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + seq_printf(m, "%s: %c bcc: %d nbd: %lu\n", + rsp->name, rsp->rcu_barrier_in_progress ? 'B' : '.', + atomic_read(&rsp->barrier_cpu_count), + rsp->n_barrier_done); + return 0; +} + +static int rcubarrier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcubarrier, NULL); +} + +static const struct file_operations rcubarrier_fops = { + .owner = THIS_MODULE, + .open = rcubarrier_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + #ifdef CONFIG_RCU_BOOST static char convert_kthread_status(unsigned int kthread_status) @@ -95,24 +120,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } -#define PRINT_RCU_DATA(name, func, m) \ - do { \ - int _p_r_d_i; \ - \ - for_each_possible_cpu(_p_r_d_i) \ - func(m, &per_cpu(name, _p_r_d_i)); \ - } while (0) - static int show_rcudata(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data, m); - seq_puts(m, "rcu_bh:\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m); + int cpu; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -166,6 +183,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { + int cpu; + struct rcu_state *rsp; + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); @@ -173,14 +193,11 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) seq_puts(m, "\"kt\",\"ktl\""); #endif /* #ifdef CONFIG_RCU_BOOST */ seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "\"rcu_preempt:\"\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "\"rcu_sched:\"\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data_csv, m); - seq_puts(m, "\"rcu_bh:\"\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m); + for_each_rcu_flavor(rsp) { + seq_printf(m, "\"%s:\"\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data_csv(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -201,8 +218,7 @@ static const struct file_operations rcudata_csv_fops = { static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) { - seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu " - "j=%04x bt=%04x\n", + seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", rnp->grplo, rnp->grphi, "T."[list_empty(&rnp->blkd_tasks)], "N."[!rnp->gp_tasks], @@ -210,11 +226,11 @@ static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) "B."[!rnp->boost_tasks], convert_kthread_status(rnp->boost_kthread_status), rnp->n_tasks_boosted, rnp->n_exp_boosts, - rnp->n_normal_boosts, + rnp->n_normal_boosts); + seq_printf(m, "j=%04x bt=%04x\n", (int)(jiffies & 0xffff), (int)(rnp->boost_time & 0xffff)); - seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", - " balk", + seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", rnp->n_balk_blkd_tasks, rnp->n_balk_exp_gp_tasks, rnp->n_balk_boost_tasks, @@ -270,15 +286,15 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp; gpnum = rsp->gpnum; - seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x " - "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", - rsp->completed, gpnum, rsp->fqs_state, + seq_printf(m, "%s: c=%lu g=%lu s=%d jfq=%ld j=%x ", + rsp->name, rsp->completed, gpnum, rsp->fqs_state, (long)(rsp->jiffies_force_qs - jiffies), - (int)(jiffies & 0xffff), + (int)(jiffies & 0xffff)); + seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen); - for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) { + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { if (rnp->level != level) { seq_puts(m, "\n"); level = rnp->level; @@ -295,14 +311,10 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) static int show_rcuhier(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_one_rcu_state(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_one_rcu_state(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_one_rcu_state(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + print_one_rcu_state(m, rsp); return 0; } @@ -343,11 +355,10 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) static int show_rcugp(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - show_one_rcugp(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - show_one_rcugp(m, &rcu_sched_state); - show_one_rcugp(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + show_one_rcugp(m, rsp); return 0; } @@ -366,44 +377,36 @@ static const struct file_operations rcugp_fops = { static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) { - seq_printf(m, "%3d%cnp=%ld " - "qsp=%ld rpq=%ld cbr=%ld cng=%ld " - "gpc=%ld gps=%ld nf=%ld nn=%ld\n", + seq_printf(m, "%3d%cnp=%ld ", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', - rdp->n_rcu_pending, + rdp->n_rcu_pending); + seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", rdp->n_rp_qs_pending, rdp->n_rp_report_qs, rdp->n_rp_cb_ready, - rdp->n_rp_cpu_needs_gp, + rdp->n_rp_cpu_needs_gp); + seq_printf(m, "gpc=%ld gps=%ld nf=%ld nn=%ld\n", rdp->n_rp_gp_completed, rdp->n_rp_gp_started, rdp->n_rp_need_fqs, rdp->n_rp_need_nothing); } -static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp) +static int show_rcu_pending(struct seq_file *m, void *unused) { int cpu; struct rcu_data *rdp; + struct rcu_state *rsp; - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - if (rdp->beenonline) - print_one_rcu_pending(m, rdp); + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->beenonline) + print_one_rcu_pending(m, rdp); + } } -} - -static int show_rcu_pending(struct seq_file *m, void *unused) -{ -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_rcu_pendings(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_rcu_pendings(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_rcu_pendings(m, &rcu_bh_state); return 0; } @@ -453,6 +456,11 @@ static int __init rcutree_trace_init(void) if (!rcudir) goto free_out; + retval = debugfs_create_file("rcubarrier", 0444, rcudir, + NULL, &rcubarrier_fops); + if (!retval) + goto free_out; + retval = debugfs_create_file("rcudata", 0444, rcudir, NULL, &rcudata_fops); if (!retval) diff --git a/kernel/smp.c b/kernel/smp.c index d0ae5b24875..29dd40a9f2f 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -581,26 +581,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait) return 0; } EXPORT_SYMBOL(smp_call_function); - -void ipi_call_lock(void) -{ - raw_spin_lock(&call_function.lock); -} - -void ipi_call_unlock(void) -{ - raw_spin_unlock(&call_function.lock); -} - -void ipi_call_lock_irq(void) -{ - raw_spin_lock_irq(&call_function.lock); -} - -void ipi_call_unlock_irq(void) -{ - raw_spin_unlock_irq(&call_function.lock); -} #endif /* USE_GENERIC_SMP_HELPERS */ /* Setup configured maximum number of CPUs to activate */ diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 80c0acfb847..6ef9433e1c7 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -3,8 +3,6 @@ struct task_struct; -int smpboot_prepare(unsigned int cpu); - #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD struct task_struct *idle_thread_get(unsigned int cpu); void idle_thread_set_boot_cpu(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 41be02250e0..024540f97f7 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -105,7 +105,7 @@ static ktime_t tick_init_jiffy_update(void) /* * NO HZ enabled ? */ -static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_enabled __read_mostly = 1; /* * Enable / Disable tickless mode diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 8f2aba1246f..cf364db5589 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -745,6 +745,7 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; + timekeeping_update(&timekeeper, false); write_sequnlock_irqrestore(&timekeeper.lock, flags); touch_softlockup_watchdog(); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a008663d86c..b4f20fba09f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -312,7 +312,7 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { - if (ftrace_disabled) + if (unlikely(ftrace_disabled)) return -ENODEV; if (FTRACE_WARN_ON(ops == &global_ops)) @@ -4299,16 +4299,12 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); - if (unlikely(ftrace_disabled)) - goto out_unlock; - ret = __register_ftrace_function(ops); if (!ret) ret = ftrace_startup(ops, 0); - - out_unlock: mutex_unlock(&ftrace_lock); + return ret; } EXPORT_SYMBOL_GPL(register_ftrace_function); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f765465bffe..49491fa7daa 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3239,6 +3239,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) if (cpu_buffer->commit_page == cpu_buffer->reader_page) goto out; + /* Don't bother swapping if the ring buffer is empty */ + if (rb_num_of_entries(cpu_buffer) == 0) + goto out; + /* * Reset the reader page to size zero. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a7fa0702be1..a120f98c411 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -830,6 +830,8 @@ int register_tracer(struct tracer *type) current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ @@ -1708,9 +1710,11 @@ EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); + iter->idx++; - if (iter->buffer_iter[iter->cpu]) - ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); + if (buf_iter) + ring_buffer_read(buf_iter, NULL); } static struct trace_entry * @@ -1718,7 +1722,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; - struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu]; + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); @@ -1856,10 +1860,10 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) tr->data[cpu]->skipped_entries = 0; - if (!iter->buffer_iter[cpu]) + buf_iter = trace_buffer_iter(iter, cpu); + if (!buf_iter) return; - buf_iter = iter->buffer_iter[cpu]; ring_buffer_iter_reset(buf_iter); /* @@ -2205,13 +2209,15 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) int trace_empty(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { cpu = iter->cpu_file; - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2221,8 +2227,9 @@ int trace_empty(struct trace_iterator *iter) } for_each_tracing_cpu(cpu) { - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2381,6 +2388,11 @@ __tracing_open(struct inode *inode, struct file *file) if (!iter) return ERR_PTR(-ENOMEM); + iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), + GFP_KERNEL); + if (!iter->buffer_iter) + goto release; + /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. @@ -2441,6 +2453,8 @@ __tracing_open(struct inode *inode, struct file *file) fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); + kfree(iter->buffer_iter); +release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } @@ -2481,6 +2495,7 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); kfree(iter->trace); + kfree(iter->buffer_iter); seq_release_private(inode, file); return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5aec220d2de..55e1f7f0db1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -317,6 +317,14 @@ struct tracer { #define TRACE_PIPE_ALL_CPU -1 +static inline struct ring_buffer_iter * +trace_buffer_iter(struct trace_iterator *iter, int cpu) +{ + if (iter->buffer_iter && iter->buffer_iter[cpu]) + return iter->buffer_iter[cpu]; + return NULL; +} + int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void trace_wake_up(void); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index a7d2a4c653d..ce27c8ba8d3 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -538,7 +538,7 @@ get_return_for_leaf(struct trace_iterator *iter, next = &data->ret; } else { - ring_iter = iter->buffer_iter[iter->cpu]; + ring_iter = trace_buffer_iter(iter, iter->cpu); /* First peek to compare current entry and the next one */ if (ring_iter) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index df611a0e76c..123b189c732 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1325,4 +1325,4 @@ __init static int init_events(void) return 0; } -device_initcall(init_events); +early_initcall(init_events); diff --git a/lib/list_debug.c b/lib/list_debug.c index 23a5e031cd8..c24c2f7e296 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -87,12 +87,10 @@ void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { WARN(next->prev != prev, - "list_add_rcu corruption. next->prev should be " - "prev (%p), but was %p. (next=%p).\n", + "list_add_rcu corruption. next->prev should be prev (%p), but was %p. (next=%p).\n", prev, next->prev, next); WARN(prev->next != next, - "list_add_rcu corruption. prev->next should be " - "next (%p), but was %p. (prev=%p).\n", + "list_add_rcu corruption. prev->next should be next (%p), but was %p. (prev=%p).\n", next, prev->next, prev); new->next = next; new->prev = prev; diff --git a/mm/bootmem.c b/mm/bootmem.c index 73096630cb3..bcb63ac48cc 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -710,6 +710,10 @@ again: if (ptr) return ptr; + /* do not panic in alloc_bootmem_bdata() */ + if (limit && goal + size > limit) + limit = 0; + ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit); if (ptr) return ptr; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 44030096da6..4a4f9219683 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5635,7 +5635,12 @@ static struct page * __alloc_contig_migrate_alloc(struct page *page, unsigned long private, int **resultp) { - return alloc_page(GFP_HIGHUSER_MOVABLE); + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + + return alloc_page(gfp_mask); } /* [start, end) must belong to a single zone. */ diff --git a/mm/vmscan.c b/mm/vmscan.c index 661576324c7..66e431060c0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2688,7 +2688,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - schedule(); + + if (!kthread_should_stop()) + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 6089f0cf23b..9096bcb0813 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -403,6 +403,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_DOWN: + if (dev->features & NETIF_F_HW_VLAN_FILTER) + vlan_vid_del(dev, 0); + /* Put all VLANs for this dev in the down state too. */ for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 051f7abae66..779095ded68 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -842,6 +842,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, case AX25_P_NETROM: if (ax25_protocol_is_registered(AX25_P_NETROM)) return -ESOCKTNOSUPPORT; + break; #endif #ifdef CONFIG_ROSE_MODULE case AX25_P_ROSE: diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 8bf97515a77..c5863f49913 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1351,6 +1351,7 @@ void bla_free(struct bat_priv *bat_priv) * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame + * @is_bcast: the packet came in a broadcast packet type. * * bla_rx avoidance checks if: * * we have to race for a claim @@ -1361,7 +1362,8 @@ void bla_free(struct bat_priv *bat_priv) * process the skb. * */ -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast) { struct ethhdr *ethhdr; struct claim search_claim, *claim = NULL; @@ -1380,7 +1382,7 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) if (unlikely(atomic_read(&bat_priv->bla_num_requests))) /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest)) + if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) goto handled; memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); @@ -1406,8 +1408,13 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) } /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest)) { - /* ... drop it. the responsible gateway is in charge. */ + if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* ... drop it. the responsible gateway is in charge. + * + * We need to check is_bcast because with the gateway + * feature, broadcasts (like DHCP requests) may be sent + * using a unicast packet type. + */ goto handled; } else { /* seems the client considers us as its best gateway. diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index e39f93acc28..dc5227b398d 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -23,7 +23,8 @@ #define _NET_BATMAN_ADV_BLA_H_ #ifdef CONFIG_BATMAN_ADV_BLA -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast); int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); int bla_is_backbone_gw(struct sk_buff *skb, struct orig_node *orig_node, int hdr_size); @@ -41,7 +42,7 @@ void bla_free(struct bat_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_BLA */ static inline int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, - short vid) + short vid, bool is_bcast) { return 0; } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6e2530b0204..a0ec0e4ada4 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -256,7 +256,11 @@ void interface_rx(struct net_device *soft_iface, struct bat_priv *bat_priv = netdev_priv(soft_iface); struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; + struct batman_header *batadv_header = (struct batman_header *)skb->data; short vid __maybe_unused = -1; + bool is_bcast; + + is_bcast = (batadv_header->packet_type == BAT_BCAST); /* check if enough space is available for pulling, and pull */ if (!pskb_may_pull(skb, hdr_size)) @@ -302,7 +306,7 @@ void interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (bla_rx(bat_priv, skb, vid)) + if (bla_rx(bat_priv, skb, vid, is_bcast)) goto out; netif_rx(skb); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 554b3128960..8c83c175b03 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -561,9 +561,9 @@ static int __init caif_device_init(void) static void __exit caif_device_exit(void) { - unregister_pernet_subsys(&caif_net_ops); unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); + unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b332c3d7605..10255e81be7 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1423,7 +1423,7 @@ static int process_connect(struct ceph_connection *con) * dropped messages. */ dout("process_connect got RESET peer seq %u\n", - le32_to_cpu(con->in_connect.connect_seq)); + le32_to_cpu(con->in_reply.connect_seq)); pr_err("%s%lld %s connection reset\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr)); @@ -1450,10 +1450,10 @@ static int process_connect(struct ceph_connection *con) * If we sent a smaller connect_seq than the peer has, try * again with a larger value. */ - dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", + dout("process_connect got RETRY_SESSION my seq %u, peer %u\n", le32_to_cpu(con->out_connect.connect_seq), - le32_to_cpu(con->in_connect.connect_seq)); - con->connect_seq = le32_to_cpu(con->in_connect.connect_seq); + le32_to_cpu(con->in_reply.connect_seq)); + con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) @@ -1468,9 +1468,9 @@ static int process_connect(struct ceph_connection *con) */ dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", con->peer_global_seq, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) diff --git a/net/core/dev.c b/net/core/dev.c index 84f01ba81a3..1cb0d8a6aa6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2444,8 +2444,12 @@ static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); - if ((!skb->priority) && (skb->sk) && map) - skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } } #else #define skb_update_prio(skb) @@ -6279,7 +6283,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index dddbacb8f28..42f1e1c7514 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,7 +27,9 @@ static DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); -struct net init_net; +struct net init_net = { + .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), +}; EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 5b8aa2fae48..b2e9caa1ad1 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -49,8 +49,9 @@ static int get_prioidx(u32 *prio) return -ENOSPC; } set_bit(prioidx, prioidx_map); + if (atomic_read(&max_prioidx) < prioidx) + atomic_set(&max_prioidx, prioidx); spin_unlock_irqrestore(&prioidx_map_lock, flags); - atomic_set(&max_prioidx, prioidx); *prio = prioidx; return 0; } @@ -64,7 +65,7 @@ static void put_prioidx(u32 idx) spin_unlock_irqrestore(&prioidx_map_lock, flags); } -static void extend_netdev_table(struct net_device *dev, u32 new_len) +static int extend_netdev_table(struct net_device *dev, u32 new_len) { size_t new_size = sizeof(struct netprio_map) + ((sizeof(u32) * new_len)); @@ -76,7 +77,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) if (!new_priomap) { pr_warn("Unable to alloc new priomap!\n"); - return; + return -ENOMEM; } for (i = 0; @@ -89,46 +90,79 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) rcu_assign_pointer(dev->priomap, new_priomap); if (old_priomap) kfree_rcu(old_priomap, rcu); + return 0; } -static void update_netdev_tables(void) +static int write_update_netdev_table(struct net_device *dev) { + int ret = 0; + u32 max_len; + struct netprio_map *map; + + rtnl_lock(); + max_len = atomic_read(&max_prioidx) + 1; + map = rtnl_dereference(dev->priomap); + if (!map || map->priomap_len < max_len) + ret = extend_netdev_table(dev, max_len); + rtnl_unlock(); + + return ret; +} + +static int update_netdev_tables(void) +{ + int ret = 0; struct net_device *dev; - u32 max_len = atomic_read(&max_prioidx) + 1; + u32 max_len; struct netprio_map *map; rtnl_lock(); + max_len = atomic_read(&max_prioidx) + 1; for_each_netdev(&init_net, dev) { map = rtnl_dereference(dev->priomap); - if ((!map) || - (map->priomap_len < max_len)) - extend_netdev_table(dev, max_len); + /* + * don't allocate priomap if we didn't + * change net_prio.ifpriomap (map == NULL), + * this will speed up skb_update_prio. + */ + if (map && map->priomap_len < max_len) { + ret = extend_netdev_table(dev, max_len); + if (ret < 0) + break; + } } rtnl_unlock(); + return ret; } static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) { struct cgroup_netprio_state *cs; - int ret; + int ret = -EINVAL; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); - if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { - kfree(cs); - return ERR_PTR(-EINVAL); - } + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) + goto out; ret = get_prioidx(&cs->prioidx); - if (ret != 0) { + if (ret < 0) { pr_warn("No space in priority index array\n"); - kfree(cs); - return ERR_PTR(ret); + goto out; + } + + ret = update_netdev_tables(); + if (ret < 0) { + put_prioidx(cs->prioidx); + goto out; } return &cs->css; +out: + kfree(cs); + return ERR_PTR(ret); } static void cgrp_destroy(struct cgroup *cgrp) @@ -141,7 +175,7 @@ static void cgrp_destroy(struct cgroup *cgrp) rtnl_lock(); for_each_netdev(&init_net, dev) { map = rtnl_dereference(dev->priomap); - if (map) + if (map && cs->prioidx < map->priomap_len) map->priomap[cs->prioidx] = 0; } rtnl_unlock(); @@ -165,7 +199,7 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft, rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { map = rcu_dereference(dev->priomap); - priority = map ? map->priomap[prioidx] : 0; + priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0; cb->fill(cb, dev->name, priority); } rcu_read_unlock(); @@ -220,13 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, if (!dev) goto out_free_devname; - update_netdev_tables(); - ret = 0; + ret = write_update_netdev_table(dev); + if (ret < 0) + goto out_put_dev; + rcu_read_lock(); map = rcu_dereference(dev->priomap); if (map) map->priomap[prioidx] = priority; rcu_read_unlock(); + +out_put_dev: dev_put(dev); out_free_devname: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 46a3d23d259..d124306b81f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -353,7 +353,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - if (fragsz <= PAGE_SIZE && !(gfp_mask & __GFP_WAIT)) { + if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { void *data = netdev_alloc_frag(fragsz); if (likely(data)) { diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 6fbb2ad7bb6..16705611589 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -230,6 +230,12 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, mtu = dev->mtu; pr_debug("name = %s, mtu = %u\n", dev->name, mtu); + if (size > mtu) { + pr_debug("size = %Zu, mtu = %u\n", size, mtu); + err = -EINVAL; + goto out_dev; + } + hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(sk, hlen + tlen + size, @@ -258,12 +264,6 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, if (err < 0) goto out_skb; - if (size > mtu) { - pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; - goto out_skb; - } - skb->dev = dev; skb->sk = sk; skb->protocol = htons(ETH_P_IEEE802154); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c48adc565e9..667c1d4ca98 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1725,8 +1725,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) case CIPSO_V4_TAG_LOCAL: /* This is a non-standard tag that we only allow for * local connections, so if the incoming interface is - * not the loopback device drop the packet. */ - if (!(skb->dev->flags & IFF_LOOPBACK)) { + * not the loopback device drop the packet. Further, + * there is no legitimate reason for setting this from + * userspace so reject it if skb is NULL. */ + if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a4bb856de08..0db5d34a06b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2174,15 +2174,13 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, sdata->name, mgmt->sa, status_code); ieee80211_destroy_assoc_data(sdata, false); } else { - printk(KERN_DEBUG "%s: associated\n", sdata->name); - if (!ieee80211_assoc_success(sdata, *bss, mgmt, len)) { /* oops -- internal error -- send timeout for now */ - ieee80211_destroy_assoc_data(sdata, true); - sta_info_destroy_addr(sdata, mgmt->bssid); + ieee80211_destroy_assoc_data(sdata, false); cfg80211_put_bss(*bss); return RX_MGMT_CFG80211_ASSOC_TIMEOUT; } + printk(KERN_DEBUG "%s: associated\n", sdata->name); /* * destroy assoc_data afterwards, as otherwise an idle diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 2d1acc6c544..f9e51ef8dfa 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -809,7 +809,7 @@ minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) max_rates = sband->n_bitrates; } - msp = kzalloc(sizeof(struct minstrel_ht_sta), gfp); + msp = kzalloc(sizeof(*msp), gfp); if (!msp) return NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index d43e3c122f7..84444dda194 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1521,11 +1521,12 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_service *svc; struct ip_vs_dest *dest; unsigned int idx; - if (event != NETDEV_UNREGISTER) + if (event != NETDEV_UNREGISTER || !ipvs) return NOTIFY_DONE; IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); EnterFunction(2); @@ -1551,7 +1552,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } } - list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + list_for_each_entry(dest, &ipvs->dest_trash, n_list) { __ip_vs_dev_reset(dest, dev); } mutex_unlock(&__ip_vs_mutex); diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 035960ec5cb..c6f7db720d8 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -16,6 +16,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); @@ -310,7 +311,8 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) info->del_set.flags, 0, UINT_MAX); /* Normalize to fit into jiffies */ - if (add_opt.timeout > UINT_MAX/MSEC_PER_SEC) + if (add_opt.timeout != IPSET_NO_TIMEOUT && + add_opt.timeout > UINT_MAX/MSEC_PER_SEC) add_opt.timeout = UINT_MAX/MSEC_PER_SEC; if (info->add_set.index != IPSET_INVALID_ID) ip_set_add(info->add_set.index, skb, par, &add_opt); diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index 17a707db40e..e06d458fc71 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -292,7 +292,7 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *addr, pr_debug("%p\n", sk); - if (llcp_sock == NULL) + if (llcp_sock == NULL || llcp_sock->dev == NULL) return -EBADFD; addr->sa_family = AF_NFC; diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c index 2754f098d43..bebaa43484b 100644 --- a/net/rxrpc/ar-peer.c +++ b/net/rxrpc/ar-peer.c @@ -229,7 +229,7 @@ found_UDP_peer: return peer; new_UDP_peer: - _net("Rx UDP DGRAM from NEW peer %d", peer->debug_id); + _net("Rx UDP DGRAM from NEW peer"); read_unlock_bh(&rxrpc_peer_lock); _leave(" = -EBUSY [new]"); return ERR_PTR(-EBUSY); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a2a95aabf9c..c412ad0d030 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -331,29 +331,22 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } -static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) +static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct sk_buff_head *list = &sch->q; psched_time_t tnext = netem_skb_cb(nskb)->time_to_send; - struct sk_buff *skb; - - if (likely(skb_queue_len(list) < sch->limit)) { - skb = skb_peek_tail(list); - /* Optimize for add at tail */ - if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send)) - return qdisc_enqueue_tail(nskb, sch); + struct sk_buff *skb = skb_peek_tail(list); - skb_queue_reverse_walk(list, skb) { - if (tnext >= netem_skb_cb(skb)->time_to_send) - break; - } + /* Optimize for add at tail */ + if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send)) + return __skb_queue_tail(list, nskb); - __skb_queue_after(list, skb, nskb); - sch->qstats.backlog += qdisc_pkt_len(nskb); - return NET_XMIT_SUCCESS; + skb_queue_reverse_walk(list, skb) { + if (tnext >= netem_skb_cb(skb)->time_to_send) + break; } - return qdisc_reshape_fail(nskb, sch); + __skb_queue_after(list, skb, nskb); } /* @@ -368,7 +361,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2; - int ret; int count = 1; /* Random duplication */ @@ -419,6 +411,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); } + if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) + return qdisc_reshape_fail(skb, sch); + + sch->qstats.backlog += qdisc_pkt_len(skb); + cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ @@ -450,7 +447,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) cb->time_to_send = now + delay; ++q->counter; - ret = tfifo_enqueue(skb, sch); + tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front @@ -460,16 +457,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) q->counter = 0; __skb_queue_head(&sch->q, skb); - sch->qstats.backlog += qdisc_pkt_len(skb); sch->qstats.requeues++; - ret = NET_XMIT_SUCCESS; - } - - if (ret != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(ret)) { - sch->qstats.drops++; - return ret; - } } return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 74305c883bd..30ea4674cab 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -570,6 +570,8 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) sch->qstats.backlog = q->qdisc->qstats.backlog; opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sctp/input.c b/net/sctp/input.c index 80564fe0302..8b9b6790a3d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -736,15 +736,12 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) epb = &ep->base; - if (hlist_unhashed(&epb->node)) - return; - epb->hashent = sctp_ep_hashfn(epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } @@ -825,7 +822,7 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b3b8a8d813e..31c7bfcd9b5 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1231,8 +1231,14 @@ out_free: SCTP_DEBUG_PRINTK("About to exit __sctp_connect() free asoc: %p" " kaddrs: %p err: %d\n", asoc, kaddrs, err); - if (asoc) + if (asoc) { + /* sctp_primitive_ASSOCIATE may have added this association + * To the hash table, try to unhash it, just in case, its a noop + * if it wasn't hashed so we're safe + */ + sctp_unhash_established(asoc); sctp_association_free(asoc); + } return err; } @@ -1942,8 +1948,10 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_unlock; out_free: - if (new_asoc) + if (new_asoc) { + sctp_unhash_established(asoc); sctp_association_free(asoc); + } out_unlock: sctp_release_sock(sk); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 372ec6502aa..ffd8900a38e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2717,7 +2717,7 @@ static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); - if (ia_valid & ATTR_SIZE) + if (selinux_policycap_openperm && (ia_valid & ATTR_SIZE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index b8c53723e09..df2de54a958 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -145,7 +145,9 @@ struct security_class_mapping secclass_map[] = { "node_bind", "name_connect", NULL } }, { "memprotect", { "mmap_zero", NULL } }, { "peer", { "recv", NULL } }, - { "capability2", { "mac_override", "mac_admin", "syslog", NULL } }, + { "capability2", + { "mac_override", "mac_admin", "syslog", "wake_alarm", "block_suspend", + NULL } }, { "kernel_service", { "use_as_override", "create_files_as", NULL } }, { "tun_socket", { COMMON_SOCK_PERMS, NULL } }, diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 3d69aa9ff51..46c2f6b7b12 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -250,8 +250,12 @@ endef all_objs := $(sort $(ALL_OBJS)) all_deps := $(all_objs:%.o=.%.d) +# let .d file also depends on the source and header files define check_deps - $(CC) -M $(CFLAGS) $< > $@; + @set -e; $(RM) $@; \ + $(CC) -M $(CFLAGS) $< > $@.$$$$; \ + sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \ + $(RM) $@.$$$$ endef $(gui_deps): ks_version.h @@ -270,11 +274,13 @@ endif tags: force $(RM) tags - find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px + find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \ + --regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/' TAGS: force $(RM) TAGS - find . -name '*.[ch]' | xargs etags + find . -name '*.[ch]' | xargs etags \ + --regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/' define do_install $(print_install) \ @@ -290,7 +296,7 @@ install_lib: all_cmd install_plugins install_python install: install_lib clean: - $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES).*.d + $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d $(RM) tags TAGS endif # skip-makefile diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 554828219c3..5f34aa371b5 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -467,8 +467,10 @@ int pevent_register_function(struct pevent *pevent, char *func, item->mod = NULL; item->addr = addr; - pevent->funclist = item; + if (!item->func || (mod && !item->mod)) + die("malloc func"); + pevent->funclist = item; pevent->func_count++; return 0; @@ -511,12 +513,12 @@ struct printk_list { static int printk_cmp(const void *a, const void *b) { - const struct func_map *fa = a; - const struct func_map *fb = b; + const struct printk_map *pa = a; + const struct printk_map *pb = b; - if (fa->addr < fb->addr) + if (pa->addr < pb->addr) return -1; - if (fa->addr > fb->addr) + if (pa->addr > pb->addr) return 1; return 0; @@ -583,10 +585,13 @@ int pevent_register_print_string(struct pevent *pevent, char *fmt, item = malloc_or_die(sizeof(*item)); item->next = pevent->printklist; - pevent->printklist = item; item->printk = strdup(fmt); item->addr = addr; + if (!item->printk) + die("malloc fmt"); + + pevent->printklist = item; pevent->printk_count++; return 0; @@ -616,7 +621,9 @@ static struct event_format *alloc_event(void) { struct event_format *event; - event = malloc_or_die(sizeof(*event)); + event = malloc(sizeof(*event)); + if (!event) + return NULL; memset(event, 0, sizeof(*event)); return event; @@ -626,12 +633,8 @@ static void add_event(struct pevent *pevent, struct event_format *event) { int i; - if (!pevent->events) - pevent->events = malloc_or_die(sizeof(event)); - else - pevent->events = - realloc(pevent->events, sizeof(event) * - (pevent->nr_events + 1)); + pevent->events = realloc(pevent->events, sizeof(event) * + (pevent->nr_events + 1)); if (!pevent->events) die("Can not allocate events"); @@ -697,6 +700,10 @@ static void free_arg(struct print_arg *arg) free_arg(arg->symbol.field); free_flag_sym(arg->symbol.symbols); break; + case PRINT_HEX: + free_arg(arg->hex.field); + free_arg(arg->hex.size); + break; case PRINT_TYPE: free(arg->typecast.type); free_arg(arg->typecast.item); @@ -775,6 +782,25 @@ int pevent_peek_char(void) return __peek_char(); } +static int extend_token(char **tok, char *buf, int size) +{ + char *newtok = realloc(*tok, size); + + if (!newtok) { + free(*tok); + *tok = NULL; + return -1; + } + + if (!*tok) + strcpy(newtok, buf); + else + strcat(newtok, buf); + *tok = newtok; + + return 0; +} + static enum event_type force_token(const char *str, char **tok); static enum event_type __read_token(char **tok) @@ -859,17 +885,10 @@ static enum event_type __read_token(char **tok) do { if (i == (BUFSIZ - 1)) { buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + BUFSIZ); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); + tok_size += BUFSIZ; - if (!*tok) + if (extend_token(tok, buf, tok_size) < 0) return EVENT_NONE; - tok_size += BUFSIZ; i = 0; } last_ch = ch; @@ -908,17 +927,10 @@ static enum event_type __read_token(char **tok) while (get_type(__peek_char()) == type) { if (i == (BUFSIZ - 1)) { buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + BUFSIZ); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); + tok_size += BUFSIZ; - if (!*tok) + if (extend_token(tok, buf, tok_size) < 0) return EVENT_NONE; - tok_size += BUFSIZ; i = 0; } ch = __read_char(); @@ -927,14 +939,7 @@ static enum event_type __read_token(char **tok) out: buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + i); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); - if (!*tok) + if (extend_token(tok, buf, tok_size + i + 1) < 0) return EVENT_NONE; if (type == EVENT_ITEM) { @@ -1255,9 +1260,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f field->flags |= FIELD_IS_POINTER; if (field->type) { - field->type = realloc(field->type, - strlen(field->type) + - strlen(last_token) + 2); + char *new_type; + new_type = realloc(field->type, + strlen(field->type) + + strlen(last_token) + 2); + if (!new_type) { + free(last_token); + goto fail; + } + field->type = new_type; strcat(field->type, " "); strcat(field->type, last_token); free(last_token); @@ -1282,6 +1293,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f if (strcmp(token, "[") == 0) { enum event_type last_type = type; char *brackets = token; + char *new_brackets; int len; field->flags |= FIELD_IS_ARRAY; @@ -1301,9 +1313,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f len = 1; last_type = type; - brackets = realloc(brackets, - strlen(brackets) + - strlen(token) + len); + new_brackets = realloc(brackets, + strlen(brackets) + + strlen(token) + len); + if (!new_brackets) { + free(brackets); + goto fail; + } + brackets = new_brackets; if (len == 2) strcat(brackets, " "); strcat(brackets, token); @@ -1319,7 +1336,12 @@ static int event_read_fields(struct event_format *event, struct format_field **f free_token(token); - brackets = realloc(brackets, strlen(brackets) + 2); + new_brackets = realloc(brackets, strlen(brackets) + 2); + if (!new_brackets) { + free(brackets); + goto fail; + } + brackets = new_brackets; strcat(brackets, "]"); /* add brackets to type */ @@ -1330,10 +1352,16 @@ static int event_read_fields(struct event_format *event, struct format_field **f * the format: type [] item; */ if (type == EVENT_ITEM) { - field->type = realloc(field->type, - strlen(field->type) + - strlen(field->name) + - strlen(brackets) + 2); + char *new_type; + new_type = realloc(field->type, + strlen(field->type) + + strlen(field->name) + + strlen(brackets) + 2); + if (!new_type) { + free(brackets); + goto fail; + } + field->type = new_type; strcat(field->type, " "); strcat(field->type, field->name); free_token(field->name); @@ -1341,9 +1369,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f field->name = token; type = read_token(&token); } else { - field->type = realloc(field->type, - strlen(field->type) + - strlen(brackets) + 1); + char *new_type; + new_type = realloc(field->type, + strlen(field->type) + + strlen(brackets) + 1); + if (!new_type) { + free(brackets); + goto fail; + } + field->type = new_type; strcat(field->type, brackets); } free(brackets); @@ -1726,10 +1760,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) /* could just be a type pointer */ if ((strcmp(arg->op.op, "*") == 0) && type == EVENT_DELIM && (strcmp(token, ")") == 0)) { + char *new_atom; + if (left->type != PRINT_ATOM) die("bad pointer type"); - left->atom.atom = realloc(left->atom.atom, + new_atom = realloc(left->atom.atom, strlen(left->atom.atom) + 3); + if (!new_atom) + goto out_free; + + left->atom.atom = new_atom; strcat(left->atom.atom, " *"); free(arg->op.op); *arg = *left; @@ -2146,6 +2186,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** if (value == NULL) goto out_free; field->value = strdup(value); + if (field->value == NULL) + goto out_free; free_arg(arg); arg = alloc_arg(); @@ -2159,6 +2201,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** if (value == NULL) goto out_free; field->str = strdup(value); + if (field->str == NULL) + goto out_free; free_arg(arg); arg = NULL; @@ -2260,6 +2304,45 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok) } static enum event_type +process_hex(struct event_format *event, struct print_arg *arg, char **tok) +{ + struct print_arg *field; + enum event_type type; + char *token; + + memset(arg, 0, sizeof(*arg)); + arg->type = PRINT_HEX; + + field = alloc_arg(); + type = process_arg(event, field, &token); + + if (test_type_token(type, token, EVENT_DELIM, ",")) + goto out_free; + + arg->hex.field = field; + + free_token(token); + + field = alloc_arg(); + type = process_arg(event, field, &token); + + if (test_type_token(type, token, EVENT_DELIM, ")")) + goto out_free; + + arg->hex.size = field; + + free_token(token); + type = read_token_item(tok); + return type; + + out_free: + free_arg(field); + free_token(token); + *tok = NULL; + return EVENT_ERROR; +} + +static enum event_type process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok) { struct format_field *field; @@ -2488,6 +2571,10 @@ process_function(struct event_format *event, struct print_arg *arg, is_symbolic_field = 1; return process_symbols(event, arg, tok); } + if (strcmp(token, "__print_hex") == 0) { + free_token(token); + return process_hex(event, arg, tok); + } if (strcmp(token, "__get_str") == 0) { free_token(token); return process_str(event, arg, tok); @@ -2541,7 +2628,16 @@ process_arg_token(struct event_format *event, struct print_arg *arg, } /* atoms can be more than one token long */ while (type == EVENT_ITEM) { - atom = realloc(atom, strlen(atom) + strlen(token) + 2); + char *new_atom; + new_atom = realloc(atom, + strlen(atom) + strlen(token) + 2); + if (!new_atom) { + free(atom); + *tok = NULL; + free_token(token); + return EVENT_ERROR; + } + atom = new_atom; strcat(atom, " "); strcat(atom, token); free_token(token); @@ -2835,7 +2931,7 @@ static int get_common_info(struct pevent *pevent, event = pevent->events[0]; field = pevent_find_common_field(event, type); if (!field) - die("field '%s' not found", type); + return -1; *offset = field->offset; *size = field->size; @@ -2886,15 +2982,16 @@ static int parse_common_flags(struct pevent *pevent, void *data) static int parse_common_lock_depth(struct pevent *pevent, void *data) { - int ret; - - ret = __parse_common(pevent, data, - &pevent->ld_size, &pevent->ld_offset, - "common_lock_depth"); - if (ret < 0) - return -1; + return __parse_common(pevent, data, + &pevent->ld_size, &pevent->ld_offset, + "common_lock_depth"); +} - return ret; +static int parse_common_migrate_disable(struct pevent *pevent, void *data) +{ + return __parse_common(pevent, data, + &pevent->ld_size, &pevent->ld_offset, + "common_migrate_disable"); } static int events_id_cmp(const void *a, const void *b); @@ -2995,6 +3092,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg break; case PRINT_FLAGS: case PRINT_SYMBOL: + case PRINT_HEX: break; case PRINT_TYPE: val = eval_num_arg(data, size, event, arg->typecast.item); @@ -3214,11 +3312,13 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, { struct pevent *pevent = event->pevent; struct print_flag_sym *flag; + struct format_field *field; unsigned long long val, fval; unsigned long addr; char *str; + unsigned char *hex; int print; - int len; + int i, len; switch (arg->type) { case PRINT_NULL: @@ -3228,27 +3328,29 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, print_str_to_seq(s, format, len_arg, arg->atom.atom); return; case PRINT_FIELD: - if (!arg->field.field) { - arg->field.field = pevent_find_any_field(event, arg->field.name); - if (!arg->field.field) + field = arg->field.field; + if (!field) { + field = pevent_find_any_field(event, arg->field.name); + if (!field) die("field %s not found", arg->field.name); + arg->field.field = field; } /* Zero sized fields, mean the rest of the data */ - len = arg->field.field->size ? : size - arg->field.field->offset; + len = field->size ? : size - field->offset; /* * Some events pass in pointers. If this is not an array * and the size is the same as long_size, assume that it * is a pointer. */ - if (!(arg->field.field->flags & FIELD_IS_ARRAY) && - arg->field.field->size == pevent->long_size) { - addr = *(unsigned long *)(data + arg->field.field->offset); + if (!(field->flags & FIELD_IS_ARRAY) && + field->size == pevent->long_size) { + addr = *(unsigned long *)(data + field->offset); trace_seq_printf(s, "%lx", addr); break; } str = malloc_or_die(len + 1); - memcpy(str, data + arg->field.field->offset, len); + memcpy(str, data + field->offset, len); str[len] = 0; print_str_to_seq(s, format, len_arg, str); free(str); @@ -3281,6 +3383,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, } } break; + case PRINT_HEX: + field = arg->hex.field->field.field; + if (!field) { + str = arg->hex.field->field.name; + field = pevent_find_any_field(event, str); + if (!field) + die("field %s not found", str); + arg->hex.field->field.field = field; + } + hex = data + field->offset; + len = eval_num_arg(data, size, event, arg->hex.size); + for (i = 0; i < len; i++) { + if (i) + trace_seq_putc(s, ' '); + trace_seq_printf(s, "%02x", hex[i]); + } + break; case PRINT_TYPE: break; @@ -3299,7 +3418,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, break; } case PRINT_BSTRING: - trace_seq_printf(s, format, arg->string.string); + print_str_to_seq(s, format, len_arg, arg->string.string); break; case PRINT_OP: /* @@ -3363,6 +3482,10 @@ process_defined_func(struct trace_seq *s, void *data, int size, string = malloc_or_die(sizeof(*string)); string->next = strings; string->str = strdup(str.buffer); + if (!string->str) + die("malloc str"); + + args[i] = (unsigned long long)string->str; strings = string; trace_seq_destroy(&str); break; @@ -3400,6 +3523,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc unsigned long long ip, val; char *ptr; void *bptr; + int vsize; field = pevent->bprint_buf_field; ip_field = pevent->bprint_ip_field; @@ -3448,6 +3572,8 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc goto process_again; case '0' ... '9': goto process_again; + case '.': + goto process_again; case 'p': ls = 1; /* fall through */ @@ -3455,23 +3581,30 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc case 'u': case 'x': case 'i': - /* the pointers are always 4 bytes aligned */ - bptr = (void *)(((unsigned long)bptr + 3) & - ~3); switch (ls) { case 0: - ls = 4; + vsize = 4; break; case 1: - ls = pevent->long_size; + vsize = pevent->long_size; break; case 2: - ls = 8; + vsize = 8; + break; default: + vsize = ls; /* ? */ break; } - val = pevent_read_number(pevent, bptr, ls); - bptr += ls; + /* fall through */ + case '*': + if (*ptr == '*') + vsize = 4; + + /* the pointers are always 4 bytes aligned */ + bptr = (void *)(((unsigned long)bptr + 3) & + ~3); + val = pevent_read_number(pevent, bptr, vsize); + bptr += vsize; arg = alloc_arg(); arg->next = NULL; arg->type = PRINT_ATOM; @@ -3479,12 +3612,21 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc sprintf(arg->atom.atom, "%lld", val); *next = arg; next = &arg->next; + /* + * The '*' case means that an arg is used as the length. + * We need to continue to figure out for what. + */ + if (*ptr == '*') + goto process_again; + break; case 's': arg = alloc_arg(); arg->next = NULL; arg->type = PRINT_BSTRING; arg->string.string = strdup(bptr); + if (!arg->string.string) + break; bptr += strlen(bptr) + 1; *next = arg; next = &arg->next; @@ -3589,6 +3731,16 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size, trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]); } +static int is_printable_array(char *p, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len && p[i]; i++) + if (!isprint(p[i])) + return 0; + return 1; +} + static void print_event_fields(struct trace_seq *s, void *data, int size, struct event_format *event) { @@ -3608,7 +3760,8 @@ static void print_event_fields(struct trace_seq *s, void *data, int size, len = offset >> 16; offset &= 0xffff; } - if (field->flags & FIELD_IS_STRING) { + if (field->flags & FIELD_IS_STRING && + is_printable_array(data + offset, len)) { trace_seq_printf(s, "%s", (char *)data + offset); } else { trace_seq_puts(s, "ARRAY["); @@ -3619,6 +3772,7 @@ static void print_event_fields(struct trace_seq *s, void *data, int size, *((unsigned char *)data + offset + i)); } trace_seq_putc(s, ']'); + field->flags &= ~FIELD_IS_STRING; } } else { val = pevent_read_number(event->pevent, data + field->offset, @@ -3758,6 +3912,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event } else if (*(ptr+1) == 'M' || *(ptr+1) == 'm') { print_mac_arg(s, *(ptr+1), data, size, event, arg); ptr++; + arg = arg->next; break; } @@ -3794,14 +3949,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event break; } } - if (pevent->long_size == 8 && ls) { + if (pevent->long_size == 8 && ls && + sizeof(long) != 8) { char *p; ls = 2; /* make %l into %ll */ p = strchr(format, 'l'); if (p) - memmove(p, p+1, strlen(p)+1); + memmove(p+1, p, strlen(p)+1); else if (strcmp(format, "%p") == 0) strcpy(format, "0x%llx"); } @@ -3878,8 +4034,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event * pevent_data_lat_fmt - parse the data for the latency format * @pevent: a handle to the pevent * @s: the trace_seq to write to - * @data: the raw data to read from - * @size: currently unused. + * @record: the record to read from * * This parses out the Latency format (interrupts disabled, * need rescheduling, in hard/soft interrupt, preempt count @@ -3889,10 +4044,13 @@ void pevent_data_lat_fmt(struct pevent *pevent, struct trace_seq *s, struct pevent_record *record) { static int check_lock_depth = 1; + static int check_migrate_disable = 1; static int lock_depth_exists; + static int migrate_disable_exists; unsigned int lat_flags; unsigned int pc; int lock_depth; + int migrate_disable; int hardirq; int softirq; void *data = record->data; @@ -3900,18 +4058,26 @@ void pevent_data_lat_fmt(struct pevent *pevent, lat_flags = parse_common_flags(pevent, data); pc = parse_common_pc(pevent, data); /* lock_depth may not always exist */ - if (check_lock_depth) { - struct format_field *field; - struct event_format *event; - - check_lock_depth = 0; - event = pevent->events[0]; - field = pevent_find_common_field(event, "common_lock_depth"); - if (field) - lock_depth_exists = 1; - } if (lock_depth_exists) lock_depth = parse_common_lock_depth(pevent, data); + else if (check_lock_depth) { + lock_depth = parse_common_lock_depth(pevent, data); + if (lock_depth < 0) + check_lock_depth = 0; + else + lock_depth_exists = 1; + } + + /* migrate_disable may not always exist */ + if (migrate_disable_exists) + migrate_disable = parse_common_migrate_disable(pevent, data); + else if (check_migrate_disable) { + migrate_disable = parse_common_migrate_disable(pevent, data); + if (migrate_disable < 0) + check_migrate_disable = 0; + else + migrate_disable_exists = 1; + } hardirq = lat_flags & TRACE_FLAG_HARDIRQ; softirq = lat_flags & TRACE_FLAG_SOFTIRQ; @@ -3930,6 +4096,13 @@ void pevent_data_lat_fmt(struct pevent *pevent, else trace_seq_putc(s, '.'); + if (migrate_disable_exists) { + if (migrate_disable < 0) + trace_seq_putc(s, '.'); + else + trace_seq_printf(s, "%d", migrate_disable); + } + if (lock_depth_exists) { if (lock_depth < 0) trace_seq_putc(s, '.'); @@ -3996,10 +4169,7 @@ const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid) * pevent_data_comm_from_pid - parse the data into the print format * @s: the trace_seq to write to * @event: the handle to the event - * @cpu: the cpu the event was recorded on - * @data: the raw data - * @size: the size of the raw data - * @nsecs: the timestamp of the event + * @record: the record to read from * * This parses the raw @data using the given @event information and * writes the print format into the trace_seq. @@ -4279,6 +4449,13 @@ static void print_args(struct print_arg *args) trace_seq_destroy(&s); printf(")"); break; + case PRINT_HEX: + printf("__print_hex("); + print_args(args->hex.field); + printf(", "); + print_args(args->hex.size); + printf(")"); + break; case PRINT_STRING: case PRINT_BSTRING: printf("__get_str(%s)", args->string.string); @@ -4541,6 +4718,8 @@ int pevent_parse_event(struct pevent *pevent, die("failed to read event id"); event->system = strdup(sys); + if (!event->system) + die("failed to allocate system"); /* Add pevent to event so that it can be referenced */ event->pevent = pevent; @@ -4582,6 +4761,11 @@ int pevent_parse_event(struct pevent *pevent, list = &arg->next; arg->type = PRINT_FIELD; arg->field.name = strdup(field->name); + if (!arg->field.name) { + do_warning("failed to allocate field name"); + event->flags |= EVENT_FL_FAILED; + return -1; + } arg->field.field = field; } return 0; @@ -4753,7 +4937,7 @@ int pevent_get_any_field_val(struct trace_seq *s, struct event_format *event, * @record: The record with the field name. * @err: print default error if failed. * - * Returns: 0 on success, -1 field not fould, or 1 if buffer is full. + * Returns: 0 on success, -1 field not found, or 1 if buffer is full. */ int pevent_print_num_field(struct trace_seq *s, const char *fmt, struct event_format *event, const char *name, @@ -4795,11 +4979,12 @@ static void free_func_handle(struct pevent_function_handler *func) * pevent_register_print_function - register a helper function * @pevent: the handle to the pevent * @func: the function to process the helper function + * @ret_type: the return type of the helper function * @name: the name of the helper function * @parameters: A list of enum pevent_func_arg_type * * Some events may have helper functions in the print format arguments. - * This allows a plugin to dynmically create a way to process one + * This allows a plugin to dynamically create a way to process one * of these functions. * * The @parameters is a variable list of pevent_func_arg_type enums that @@ -4870,12 +5055,13 @@ int pevent_register_print_function(struct pevent *pevent, } /** - * pevent_register_event_handle - register a way to parse an event + * pevent_register_event_handler - register a way to parse an event * @pevent: the handle to the pevent * @id: the id of the event to register * @sys_name: the system name the event belongs to * @event_name: the name of the event * @func: the function to call to parse the event information + * @context: the data to be passed to @func * * This function allows a developer to override the parsing of * a given event. If for some reason the default print format @@ -4925,6 +5111,11 @@ int pevent_register_event_handler(struct pevent *pevent, if (sys_name) handle->sys_name = strdup(sys_name); + if ((event_name && !handle->event_name) || + (sys_name && !handle->sys_name)) { + die("Failed to allocate event/sys name"); + } + handle->func = func; handle->next = pevent->handlers; pevent->handlers = handle; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index ac997bc7b59..5772ad8cb38 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -226,6 +226,11 @@ struct print_arg_symbol { struct print_flag_sym *symbols; }; +struct print_arg_hex { + struct print_arg *field; + struct print_arg *size; +}; + struct print_arg_dynarray { struct format_field *field; struct print_arg *index; @@ -253,6 +258,7 @@ enum print_arg_type { PRINT_FIELD, PRINT_FLAGS, PRINT_SYMBOL, + PRINT_HEX, PRINT_TYPE, PRINT_STRING, PRINT_BSTRING, @@ -270,6 +276,7 @@ struct print_arg { struct print_arg_typecast typecast; struct print_arg_flags flags; struct print_arg_symbol symbol; + struct print_arg_hex hex; struct print_arg_func func; struct print_arg_string string; struct print_arg_op op; diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index dfcfe2c131d..ad17855528f 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -96,7 +96,7 @@ static enum event_type read_token(char **tok) (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) && pevent_peek_char() == '~') { /* append it */ - *tok = malloc(3); + *tok = malloc_or_die(3); sprintf(*tok, "%c%c", *token, '~'); free_token(token); /* Now remove the '~' from the buffer */ @@ -148,17 +148,11 @@ add_filter_type(struct event_filter *filter, int id) if (filter_type) return filter_type; - if (!filter->filters) - filter->event_filters = - malloc_or_die(sizeof(*filter->event_filters)); - else { - filter->event_filters = - realloc(filter->event_filters, - sizeof(*filter->event_filters) * - (filter->filters + 1)); - if (!filter->event_filters) - die("Could not allocate filter"); - } + filter->event_filters = realloc(filter->event_filters, + sizeof(*filter->event_filters) * + (filter->filters + 1)); + if (!filter->event_filters) + die("Could not allocate filter"); for (i = 0; i < filter->filters; i++) { if (filter->event_filters[i].event_id > id) @@ -1480,7 +1474,7 @@ void pevent_filter_clear_trivial(struct event_filter *filter, { struct filter_type *filter_type; int count = 0; - int *ids; + int *ids = NULL; int i; if (!filter->filters) @@ -1504,10 +1498,8 @@ void pevent_filter_clear_trivial(struct event_filter *filter, default: break; } - if (count) - ids = realloc(ids, sizeof(*ids) * (count + 1)); - else - ids = malloc(sizeof(*ids)); + + ids = realloc(ids, sizeof(*ids) * (count + 1)); if (!ids) die("Can't allocate ids"); ids[count++] = filter_type->event_id; @@ -1710,18 +1702,43 @@ static int test_num(struct event_format *event, static const char *get_field_str(struct filter_arg *arg, struct pevent_record *record) { - const char *val = record->data + arg->str.field->offset; + struct event_format *event; + struct pevent *pevent; + unsigned long long addr; + const char *val = NULL; + char hex[64]; - /* - * We need to copy the data since we can't be sure the field - * is null terminated. - */ - if (*(val + arg->str.field->size - 1)) { - /* copy it */ - memcpy(arg->str.buffer, val, arg->str.field->size); - /* the buffer is already NULL terminated */ - val = arg->str.buffer; + /* If the field is not a string convert it */ + if (arg->str.field->flags & FIELD_IS_STRING) { + val = record->data + arg->str.field->offset; + + /* + * We need to copy the data since we can't be sure the field + * is null terminated. + */ + if (*(val + arg->str.field->size - 1)) { + /* copy it */ + memcpy(arg->str.buffer, val, arg->str.field->size); + /* the buffer is already NULL terminated */ + val = arg->str.buffer; + } + + } else { + event = arg->str.field->event; + pevent = event->pevent; + addr = get_value(event, arg->str.field, record); + + if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG)) + /* convert to a kernel symbol */ + val = pevent_find_function(pevent, addr); + + if (val == NULL) { + /* just use the hex of the string name */ + snprintf(hex, 64, "0x%llx", addr); + val = hex; + } } + return val; } @@ -2001,11 +2018,13 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg) char *lstr; char *rstr; char *op; - char *str; + char *str = NULL; int len; lstr = arg_to_str(filter, arg->exp.left); rstr = arg_to_str(filter, arg->exp.right); + if (!lstr || !rstr) + goto out; switch (arg->exp.type) { case FILTER_EXP_ADD: @@ -2045,6 +2064,7 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg) len = strlen(op) + strlen(lstr) + strlen(rstr) + 4; str = malloc_or_die(len); snprintf(str, len, "%s %s %s", lstr, op, rstr); +out: free(lstr); free(rstr); @@ -2061,6 +2081,8 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg) lstr = arg_to_str(filter, arg->num.left); rstr = arg_to_str(filter, arg->num.right); + if (!lstr || !rstr) + goto out; switch (arg->num.type) { case FILTER_CMP_EQ: @@ -2097,6 +2119,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg) break; } +out: free(lstr); free(rstr); return str; @@ -2247,7 +2270,12 @@ int pevent_filter_compare(struct event_filter *filter1, struct event_filter *fil /* The best way to compare complex filters is with strings */ str1 = arg_to_str(filter1, filter_type1->filter); str2 = arg_to_str(filter2, filter_type2->filter); - result = strcmp(str1, str2) != 0; + if (str1 && str2) + result = strcmp(str1, str2) != 0; + else + /* bail out if allocation fails */ + result = 1; + free(str1); free(str2); if (result) diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index a3dbadb26ef..7065cd6fbdf 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -12,7 +12,7 @@ SYNOPSIS DESCRIPTION ----------- -This 'perf bench' command is general framework for benchmark suites. +This 'perf bench' command is a general framework for benchmark suites. COMMON OPTIONS -------------- @@ -45,14 +45,20 @@ SUBSYSTEM 'sched':: Scheduler and IPC mechanisms. +'mem':: + Memory access performance. + +'all':: + All benchmark subsystems. + SUITES FOR 'sched' ~~~~~~~~~~~~~~~~~~ *messaging*:: Suite for evaluating performance of scheduler and IPC mechanisms. Based on hackbench by Rusty Russell. -Options of *pipe* -^^^^^^^^^^^^^^^^^ +Options of *messaging* +^^^^^^^^^^^^^^^^^^^^^^ -p:: --pipe:: Use pipe() instead of socketpair() @@ -115,6 +121,72 @@ Example of *pipe* 59004 ops/sec --------------------- +SUITES FOR 'mem' +~~~~~~~~~~~~~~~~ +*memcpy*:: +Suite for evaluating performance of simple memory copy in various ways. + +Options of *memcpy* +^^^^^^^^^^^^^^^^^^^ +-l:: +--length:: +Specify length of memory to copy (default: 1MB). +Available units are B, KB, MB, GB and TB (case insensitive). + +-r:: +--routine:: +Specify routine to copy (default: default). +Available routines are depend on the architecture. +On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported. + +-i:: +--iterations:: +Repeat memcpy invocation this number of times. + +-c:: +--cycle:: +Use perf's cpu-cycles event instead of gettimeofday syscall. + +-o:: +--only-prefault:: +Show only the result with page faults before memcpy. + +-n:: +--no-prefault:: +Show only the result without page faults before memcpy. + +*memset*:: +Suite for evaluating performance of simple memory set in various ways. + +Options of *memset* +^^^^^^^^^^^^^^^^^^^ +-l:: +--length:: +Specify length of memory to set (default: 1MB). +Available units are B, KB, MB, GB and TB (case insensitive). + +-r:: +--routine:: +Specify routine to set (default: default). +Available routines are depend on the architecture. +On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported. + +-i:: +--iterations:: +Repeat memset invocation this number of times. + +-c:: +--cycle:: +Use perf's cpu-cycles event instead of gettimeofday syscall. + +-o:: +--only-prefault:: +Show only the result with page faults before memset. + +-n:: +--no-prefault:: +Show only the result without page faults before memset. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 2d89f02719b..495210a612c 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -57,7 +57,7 @@ OPTIONS -s:: --sort=:: - Sort by key(s): pid, comm, dso, symbol, parent. + Sort by key(s): pid, comm, dso, symbol, parent, srcline. -p:: --parent=<regex>:: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 4a5680cb242..5b80d84d6b4 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -112,7 +112,7 @@ Default is to monitor all CPUS. -s:: --sort:: - Sort by key(s): pid, comm, dso, symbol, parent + Sort by key(s): pid, comm, dso, symbol, parent, srcline. -n:: --show-nr-samples:: diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 0eee64cfe9a..75d74e5db8d 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -155,7 +155,7 @@ endif ### --- END CONFIGURATION SECTION --- -BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE +BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = # Guard against environment variables @@ -503,6 +503,7 @@ else LIB_OBJS += $(OUTPUT)ui/progress.o LIB_OBJS += $(OUTPUT)ui/util.o LIB_OBJS += $(OUTPUT)ui/tui/setup.o + LIB_OBJS += $(OUTPUT)ui/tui/util.o LIB_H += ui/browser.h LIB_H += ui/browsers/map.h LIB_H += ui/helpline.h @@ -522,13 +523,18 @@ else msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); BASIC_CFLAGS += -DNO_GTK2_SUPPORT else + ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y) + BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR + endif BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0) EXTLIBS += $(shell pkg-config --libs gtk+-2.0) LIB_OBJS += $(OUTPUT)ui/gtk/browser.o LIB_OBJS += $(OUTPUT)ui/gtk/setup.o + LIB_OBJS += $(OUTPUT)ui/gtk/util.o # Make sure that it'd be included only once. ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),) LIB_OBJS += $(OUTPUT)ui/setup.o + LIB_OBJS += $(OUTPUT)ui/util.o endif endif endif diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 71557225bf9..02dad5d3359 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -24,21 +24,21 @@ static const char *length_str = "1MB"; static const char *routine = "default"; static int iterations = 1; -static bool use_clock; -static int clock_fd; +static bool use_cycle; +static int cycle_fd; static bool only_prefault; static bool no_prefault; static const struct option options[] = { OPT_STRING('l', "length", &length_str, "1MB", "Specify length of memory to copy. " - "available unit: B, MB, GB (upper and lower)"), + "Available units: B, KB, MB, GB and TB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", "Specify routine to copy"), OPT_INTEGER('i', "iterations", &iterations, "repeat memcpy() invocation this number of times"), - OPT_BOOLEAN('c', "clock", &use_clock, - "Use CPU clock for measuring"), + OPT_BOOLEAN('c', "cycle", &use_cycle, + "Use cycles event instead of gettimeofday() for measuring"), OPT_BOOLEAN('o', "only-prefault", &only_prefault, "Show only the result with page faults before memcpy()"), OPT_BOOLEAN('n', "no-prefault", &no_prefault, @@ -76,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = { NULL }; -static struct perf_event_attr clock_attr = { +static struct perf_event_attr cycle_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }; -static void init_clock(void) +static void init_cycle(void) { - clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0); + cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); - if (clock_fd < 0 && errno == ENOSYS) + if (cycle_fd < 0 && errno == ENOSYS) die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); else - BUG_ON(clock_fd < 0); + BUG_ON(cycle_fd < 0); } -static u64 get_clock(void) +static u64 get_cycle(void) { int ret; u64 clk; - ret = read(clock_fd, &clk, sizeof(u64)); + ret = read(cycle_fd, &clk, sizeof(u64)); BUG_ON(ret != sizeof(u64)); return clk; @@ -119,9 +119,9 @@ static void alloc_mem(void **dst, void **src, size_t length) die("memory allocation failed - maybe length is too large?\n"); } -static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault) +static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault) { - u64 clock_start = 0ULL, clock_end = 0ULL; + u64 cycle_start = 0ULL, cycle_end = 0ULL; void *src = NULL, *dst = NULL; int i; @@ -130,14 +130,14 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault) if (prefault) fn(dst, src, len); - clock_start = get_clock(); + cycle_start = get_cycle(); for (i = 0; i < iterations; ++i) fn(dst, src, len); - clock_end = get_clock(); + cycle_end = get_cycle(); free(src); free(dst); - return clock_end - clock_start; + return cycle_end - cycle_start; } static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) @@ -182,17 +182,17 @@ int bench_mem_memcpy(int argc, const char **argv, int i; size_t len; double result_bps[2]; - u64 result_clock[2]; + u64 result_cycle[2]; argc = parse_options(argc, argv, options, bench_mem_memcpy_usage, 0); - if (use_clock) - init_clock(); + if (use_cycle) + init_cycle(); len = (size_t)perf_atoll((char *)length_str); - result_clock[0] = result_clock[1] = 0ULL; + result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; if ((s64)len <= 0) { @@ -223,11 +223,11 @@ int bench_mem_memcpy(int argc, const char **argv, if (!only_prefault && !no_prefault) { /* show both of results */ - if (use_clock) { - result_clock[0] = - do_memcpy_clock(routines[i].fn, len, false); - result_clock[1] = - do_memcpy_clock(routines[i].fn, len, true); + if (use_cycle) { + result_cycle[0] = + do_memcpy_cycle(routines[i].fn, len, false); + result_cycle[1] = + do_memcpy_cycle(routines[i].fn, len, true); } else { result_bps[0] = do_memcpy_gettimeofday(routines[i].fn, @@ -237,9 +237,9 @@ int bench_mem_memcpy(int argc, const char **argv, len, true); } } else { - if (use_clock) { - result_clock[pf] = - do_memcpy_clock(routines[i].fn, + if (use_cycle) { + result_cycle[pf] = + do_memcpy_cycle(routines[i].fn, len, only_prefault); } else { result_bps[pf] = @@ -251,12 +251,12 @@ int bench_mem_memcpy(int argc, const char **argv, switch (bench_format) { case BENCH_FORMAT_DEFAULT: if (!only_prefault && !no_prefault) { - if (use_clock) { - printf(" %14lf Clock/Byte\n", - (double)result_clock[0] + if (use_cycle) { + printf(" %14lf Cycle/Byte\n", + (double)result_cycle[0] / (double)len); - printf(" %14lf Clock/Byte (with prefault)\n", - (double)result_clock[1] + printf(" %14lf Cycle/Byte (with prefault)\n", + (double)result_cycle[1] / (double)len); } else { print_bps(result_bps[0]); @@ -265,9 +265,9 @@ int bench_mem_memcpy(int argc, const char **argv, printf(" (with prefault)\n"); } } else { - if (use_clock) { - printf(" %14lf Clock/Byte", - (double)result_clock[pf] + if (use_cycle) { + printf(" %14lf Cycle/Byte", + (double)result_cycle[pf] / (double)len); } else print_bps(result_bps[pf]); @@ -277,17 +277,17 @@ int bench_mem_memcpy(int argc, const char **argv, break; case BENCH_FORMAT_SIMPLE: if (!only_prefault && !no_prefault) { - if (use_clock) { + if (use_cycle) { printf("%lf %lf\n", - (double)result_clock[0] / (double)len, - (double)result_clock[1] / (double)len); + (double)result_cycle[0] / (double)len, + (double)result_cycle[1] / (double)len); } else { printf("%lf %lf\n", result_bps[0], result_bps[1]); } } else { - if (use_clock) { - printf("%lf\n", (double)result_clock[pf] + if (use_cycle) { + printf("%lf\n", (double)result_cycle[pf] / (double)len); } else printf("%lf\n", result_bps[pf]); diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index e9079185bd7..350cc955726 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -24,21 +24,21 @@ static const char *length_str = "1MB"; static const char *routine = "default"; static int iterations = 1; -static bool use_clock; -static int clock_fd; +static bool use_cycle; +static int cycle_fd; static bool only_prefault; static bool no_prefault; static const struct option options[] = { OPT_STRING('l', "length", &length_str, "1MB", - "Specify length of memory to copy. " - "available unit: B, MB, GB (upper and lower)"), + "Specify length of memory to set. " + "Available units: B, KB, MB, GB and TB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", - "Specify routine to copy"), + "Specify routine to set"), OPT_INTEGER('i', "iterations", &iterations, "repeat memset() invocation this number of times"), - OPT_BOOLEAN('c', "clock", &use_clock, - "Use CPU clock for measuring"), + OPT_BOOLEAN('c', "cycle", &use_cycle, + "Use cycles event instead of gettimeofday() for measuring"), OPT_BOOLEAN('o', "only-prefault", &only_prefault, "Show only the result with page faults before memset()"), OPT_BOOLEAN('n', "no-prefault", &no_prefault, @@ -76,27 +76,27 @@ static const char * const bench_mem_memset_usage[] = { NULL }; -static struct perf_event_attr clock_attr = { +static struct perf_event_attr cycle_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }; -static void init_clock(void) +static void init_cycle(void) { - clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0); + cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); - if (clock_fd < 0 && errno == ENOSYS) + if (cycle_fd < 0 && errno == ENOSYS) die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); else - BUG_ON(clock_fd < 0); + BUG_ON(cycle_fd < 0); } -static u64 get_clock(void) +static u64 get_cycle(void) { int ret; u64 clk; - ret = read(clock_fd, &clk, sizeof(u64)); + ret = read(cycle_fd, &clk, sizeof(u64)); BUG_ON(ret != sizeof(u64)); return clk; @@ -115,9 +115,9 @@ static void alloc_mem(void **dst, size_t length) die("memory allocation failed - maybe length is too large?\n"); } -static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) +static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault) { - u64 clock_start = 0ULL, clock_end = 0ULL; + u64 cycle_start = 0ULL, cycle_end = 0ULL; void *dst = NULL; int i; @@ -126,13 +126,13 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) if (prefault) fn(dst, -1, len); - clock_start = get_clock(); + cycle_start = get_cycle(); for (i = 0; i < iterations; ++i) fn(dst, i, len); - clock_end = get_clock(); + cycle_end = get_cycle(); free(dst); - return clock_end - clock_start; + return cycle_end - cycle_start; } static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) @@ -176,17 +176,17 @@ int bench_mem_memset(int argc, const char **argv, int i; size_t len; double result_bps[2]; - u64 result_clock[2]; + u64 result_cycle[2]; argc = parse_options(argc, argv, options, bench_mem_memset_usage, 0); - if (use_clock) - init_clock(); + if (use_cycle) + init_cycle(); len = (size_t)perf_atoll((char *)length_str); - result_clock[0] = result_clock[1] = 0ULL; + result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; if ((s64)len <= 0) { @@ -217,11 +217,11 @@ int bench_mem_memset(int argc, const char **argv, if (!only_prefault && !no_prefault) { /* show both of results */ - if (use_clock) { - result_clock[0] = - do_memset_clock(routines[i].fn, len, false); - result_clock[1] = - do_memset_clock(routines[i].fn, len, true); + if (use_cycle) { + result_cycle[0] = + do_memset_cycle(routines[i].fn, len, false); + result_cycle[1] = + do_memset_cycle(routines[i].fn, len, true); } else { result_bps[0] = do_memset_gettimeofday(routines[i].fn, @@ -231,9 +231,9 @@ int bench_mem_memset(int argc, const char **argv, len, true); } } else { - if (use_clock) { - result_clock[pf] = - do_memset_clock(routines[i].fn, + if (use_cycle) { + result_cycle[pf] = + do_memset_cycle(routines[i].fn, len, only_prefault); } else { result_bps[pf] = @@ -245,12 +245,12 @@ int bench_mem_memset(int argc, const char **argv, switch (bench_format) { case BENCH_FORMAT_DEFAULT: if (!only_prefault && !no_prefault) { - if (use_clock) { - printf(" %14lf Clock/Byte\n", - (double)result_clock[0] + if (use_cycle) { + printf(" %14lf Cycle/Byte\n", + (double)result_cycle[0] / (double)len); - printf(" %14lf Clock/Byte (with prefault)\n ", - (double)result_clock[1] + printf(" %14lf Cycle/Byte (with prefault)\n ", + (double)result_cycle[1] / (double)len); } else { print_bps(result_bps[0]); @@ -259,9 +259,9 @@ int bench_mem_memset(int argc, const char **argv, printf(" (with prefault)\n"); } } else { - if (use_clock) { - printf(" %14lf Clock/Byte", - (double)result_clock[pf] + if (use_cycle) { + printf(" %14lf Cycle/Byte", + (double)result_cycle[pf] / (double)len); } else print_bps(result_bps[pf]); @@ -271,17 +271,17 @@ int bench_mem_memset(int argc, const char **argv, break; case BENCH_FORMAT_SIMPLE: if (!only_prefault && !no_prefault) { - if (use_clock) { + if (use_cycle) { printf("%lf %lf\n", - (double)result_clock[0] / (double)len, - (double)result_clock[1] / (double)len); + (double)result_cycle[0] / (double)len, + (double)result_cycle[1] / (double)len); } else { printf("%lf %lf\n", result_bps[0], result_bps[1]); } } else { - if (use_clock) { - printf("%lf\n", (double)result_clock[pf] + if (use_cycle) { + printf("%lf\n", (double)result_cycle[pf] / (double)len); } else printf("%lf\n", result_bps[pf]); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index b0e74ab2d7a..1f310021644 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -33,7 +33,7 @@ struct bench_suite { }; \ /* sentinel: easy for help */ -#define suite_all { "all", "test all suite (pseudo suite)", NULL } +#define suite_all { "all", "Test all benchmark suites", NULL } static struct bench_suite sched_suites[] = { { "messaging", @@ -75,7 +75,7 @@ static struct bench_subsys subsystems[] = { "memory access performance", mem_suites }, { "all", /* sentinel: easy for help */ - "test all subsystem (pseudo subsystem)", + "all benchmark subsystem", NULL }, { NULL, NULL, diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index acd78dc2834..0dd5a058f76 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -60,7 +60,7 @@ static int __cmd_evlist(const char *input_name, struct perf_attr_details *detail list_for_each_entry(pos, &session->evlist->entries, node) { bool first = true; - printf("%s", event_name(pos)); + printf("%s", perf_evsel__name(pos)); if (details->verbose || details->freq) { comma_printf(&first, " sample_freq=%" PRIu64, diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 547af48deb4..ce35015f2dc 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -57,6 +57,11 @@ static unsigned long nr_allocs, nr_cross_allocs; #define PATH_SYS_NODE "/sys/devices/system/node" +struct perf_kmem { + struct perf_tool tool; + struct perf_session *session; +}; + static void init_cpunode_map(void) { FILE *fp; @@ -278,14 +283,16 @@ static void process_free_event(void *data, s_alloc->alloc_cpu = -1; } -static void process_raw_event(union perf_event *raw_event __used, void *data, +static void process_raw_event(struct perf_tool *tool, + union perf_event *raw_event __used, void *data, int cpu, u64 timestamp, struct thread *thread) { + struct perf_kmem *kmem = container_of(tool, struct perf_kmem, tool); struct event_format *event; int type; - type = trace_parse_common_type(data); - event = trace_find_event(type); + type = trace_parse_common_type(kmem->session->pevent, data); + event = pevent_find_event(kmem->session->pevent, type); if (!strcmp(event->name, "kmalloc") || !strcmp(event->name, "kmem_cache_alloc")) { @@ -306,7 +313,7 @@ static void process_raw_event(union perf_event *raw_event __used, void *data, } } -static int process_sample_event(struct perf_tool *tool __used, +static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel __used, @@ -322,16 +329,18 @@ static int process_sample_event(struct perf_tool *tool __used, dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - process_raw_event(event, sample->raw_data, sample->cpu, + process_raw_event(tool, event, sample->raw_data, sample->cpu, sample->time, thread); return 0; } -static struct perf_tool perf_kmem = { - .sample = process_sample_event, - .comm = perf_event__process_comm, - .ordered_samples = true, +static struct perf_kmem perf_kmem = { + .tool = { + .sample = process_sample_event, + .comm = perf_event__process_comm, + .ordered_samples = true, + }, }; static double fragmentation(unsigned long n_req, unsigned long n_alloc) @@ -486,11 +495,15 @@ static void sort_result(void) static int __cmd_kmem(void) { int err = -EINVAL; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, - 0, false, &perf_kmem); + struct perf_session *session; + + session = perf_session__new(input_name, O_RDONLY, 0, false, + &perf_kmem.tool); if (session == NULL) return -ENOMEM; + perf_kmem.session = session; + if (perf_session__create_kernel_maps(session) < 0) goto out_delete; @@ -498,7 +511,7 @@ static int __cmd_kmem(void) goto out_delete; setup_pager(); - err = perf_session__process_events(session, &perf_kmem); + err = perf_session__process_events(session, &perf_kmem.tool); if (err != 0) goto out_delete; sort_result(); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index fd53319de20..b3c42854886 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -724,8 +724,8 @@ process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread) struct event_format *event; int type; - type = trace_parse_common_type(data); - event = trace_find_event(type); + type = trace_parse_common_type(session->pevent, data); + event = pevent_find_event(session->pevent, type); if (!strcmp(event->name, "lock_acquire")) process_lock_acquire_event(data, event, cpu, timestamp, thread); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f95840d04e4..f5a6452931e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -265,7 +265,7 @@ try_again: if (err == ENOENT) { ui__error("The %s event is not supported.\n", - event_name(pos)); + perf_evsel__name(pos)); exit(EXIT_FAILURE); } @@ -916,7 +916,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) usage_with_options(record_usage, record_options); list_for_each_entry(pos, &evsel_list->entries, node) { - if (perf_header__push_event(pos->attr.config, event_name(pos))) + if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos))) goto out_free_fd; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 25249f76329..69b1c118515 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -69,7 +69,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, evsel, al->thread, + err = machine__resolve_callchain(machine, al->thread, sample->callchain, &parent); if (err) return err; @@ -140,7 +140,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, struct hist_entry *he; if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, evsel, al->thread, + err = machine__resolve_callchain(machine, al->thread, sample->callchain, &parent); if (err) return err; @@ -230,7 +230,7 @@ static int process_read_event(struct perf_tool *tool, struct perf_report *rep = container_of(tool, struct perf_report, tool); if (rep->show_threads) { - const char *name = evsel ? event_name(evsel) : "unknown"; + const char *name = evsel ? perf_evsel__name(evsel) : "unknown"; perf_read_values_add_value(&rep->show_threads_values, event->read.pid, event->read.tid, event->read.id, @@ -239,17 +239,18 @@ static int process_read_event(struct perf_tool *tool, } dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, - evsel ? event_name(evsel) : "FAIL", + evsel ? perf_evsel__name(evsel) : "FAIL", event->read.value); return 0; } +/* For pipe mode, sample_type is not currently set */ static int perf_report__setup_sample_type(struct perf_report *rep) { struct perf_session *self = rep->session; - if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) { + if (!self->fd_pipe && !(self->sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { ui__error("Selected --sort parent, but no " "callchain data. Did you call " @@ -272,7 +273,8 @@ static int perf_report__setup_sample_type(struct perf_report *rep) } if (sort__branch_mode == 1) { - if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) { + if (!self->fd_pipe && + !(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) { ui__error("Selected -b but no branch data. " "Did you call perf record without -b?\n"); return -1; @@ -314,7 +316,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, list_for_each_entry(pos, &evlist->entries, node) { struct hists *hists = &pos->hists; - const char *evname = event_name(pos); + const char *evname = perf_evsel__name(pos); hists__fprintf_nr_sample_events(hists, evname, stdout); hists__fprintf(hists, NULL, false, true, 0, 0, stdout); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index b125e07eb39..7a9ad2b1ee7 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -43,6 +43,11 @@ static u64 sleep_measurement_overhead; static unsigned long nr_tasks; +struct perf_sched { + struct perf_tool tool; + struct perf_session *session; +}; + struct sched_atom; struct task_desc { @@ -1597,11 +1602,13 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, struct perf_evsel *evsel, struct machine *machine) { + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + struct pevent *pevent = sched->session->pevent; struct thread *thread = machine__findnew_thread(machine, sample->pid); if (thread == NULL) { pr_debug("problem processing %s event, skipping it.\n", - evsel->name); + perf_evsel__name(evsel)); return -1; } @@ -1612,7 +1619,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, tracepoint_handler f = evsel->handler.func; if (evsel->handler.data == NULL) - evsel->handler.data = trace_find_event(evsel->attr.config); + evsel->handler.data = pevent_find_event(pevent, + evsel->attr.config); f(tool, evsel->handler.data, sample, machine, thread); } @@ -1620,12 +1628,14 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, return 0; } -static struct perf_tool perf_sched = { - .sample = perf_sched__process_tracepoint_sample, - .comm = perf_event__process_comm, - .lost = perf_event__process_lost, - .fork = perf_event__process_task, - .ordered_samples = true, +static struct perf_sched perf_sched = { + .tool = { + .sample = perf_sched__process_tracepoint_sample, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_task, + .ordered_samples = true, + }, }; static void read_events(bool destroy, struct perf_session **psession) @@ -1640,16 +1650,20 @@ static void read_events(bool destroy, struct perf_session **psession) { "sched:sched_process_exit", process_sched_exit_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, - 0, false, &perf_sched); + struct perf_session *session; + + session = perf_session__new(input_name, O_RDONLY, 0, false, + &perf_sched.tool); if (session == NULL) die("No Memory"); - err = perf_evlist__set_tracepoints_handlers_array(session->evlist, handlers); + perf_sched.session = session; + + err = perf_session__set_tracepoints_handlers(session, handlers); assert(err == 0); if (perf_session__has_traces(session, "record -R")) { - err = perf_session__process_events(session, &perf_sched); + err = perf_session__process_events(session, &perf_sched.tool); if (err) die("Failed to process events, error %d", err); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8e395a538eb..1e60ab70b2b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -28,6 +28,11 @@ static bool system_wide; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +struct perf_script { + struct perf_tool tool; + struct perf_session *session; +}; + enum perf_output_field { PERF_OUTPUT_COMM = 1U << 0, PERF_OUTPUT_TID = 1U << 1, @@ -137,10 +142,11 @@ static const char *output_field2str(enum perf_output_field field) #define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x) -static int perf_event_attr__check_stype(struct perf_event_attr *attr, - u64 sample_type, const char *sample_msg, - enum perf_output_field field) +static int perf_evsel__check_stype(struct perf_evsel *evsel, + u64 sample_type, const char *sample_msg, + enum perf_output_field field) { + struct perf_event_attr *attr = &evsel->attr; int type = attr->type; const char *evname; @@ -148,7 +154,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr, return 0; if (output[type].user_set) { - evname = __event_name(attr->type, attr->config); + evname = perf_evsel__name(evsel); pr_err("Samples for '%s' event do not have %s attribute set. " "Cannot print '%s' field.\n", evname, sample_msg, output_field2str(field)); @@ -157,7 +163,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr, /* user did not ask for it explicitly so remove from the default list */ output[type].fields &= ~field; - evname = __event_name(attr->type, attr->config); + evname = perf_evsel__name(evsel); pr_debug("Samples for '%s' event do not have %s attribute set. " "Skipping '%s' field.\n", evname, sample_msg, output_field2str(field)); @@ -175,8 +181,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, return -EINVAL; if (PRINT_FIELD(IP)) { - if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP", - PERF_OUTPUT_IP)) + if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP", + PERF_OUTPUT_IP)) return -EINVAL; if (!no_callchain && @@ -185,8 +191,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, } if (PRINT_FIELD(ADDR) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_ADDR, "ADDR", - PERF_OUTPUT_ADDR)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", + PERF_OUTPUT_ADDR)) return -EINVAL; if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { @@ -208,18 +214,18 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, } if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID", - PERF_OUTPUT_TID|PERF_OUTPUT_PID)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", + PERF_OUTPUT_TID|PERF_OUTPUT_PID)) return -EINVAL; if (PRINT_FIELD(TIME) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME", - PERF_OUTPUT_TIME)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME", + PERF_OUTPUT_TIME)) return -EINVAL; if (PRINT_FIELD(CPU) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU", - PERF_OUTPUT_CPU)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU", + PERF_OUTPUT_CPU)) return -EINVAL; return 0; @@ -256,11 +262,13 @@ static int perf_session__check_output_opt(struct perf_session *session) return 0; } -static void print_sample_start(struct perf_sample *sample, +static void print_sample_start(struct pevent *pevent, + struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr) + struct perf_evsel *evsel) { int type; + struct perf_event_attr *attr = &evsel->attr; struct event_format *event; const char *evname = NULL; unsigned long secs; @@ -300,12 +308,18 @@ static void print_sample_start(struct perf_sample *sample, if (PRINT_FIELD(EVNAME)) { if (attr->type == PERF_TYPE_TRACEPOINT) { - type = trace_parse_common_type(sample->raw_data); - event = trace_find_event(type); + /* + * XXX Do we really need this here? + * perf_evlist__set_tracepoint_names should have done + * this already + */ + type = trace_parse_common_type(pevent, + sample->raw_data); + event = pevent_find_event(pevent, type); if (event) evname = event->name; } else - evname = __event_name(attr->type, attr->config); + evname = perf_evsel__name(evsel); printf("%s: ", evname ? evname : "[unknown]"); } @@ -387,7 +401,7 @@ static void print_sample_bts(union perf_event *event, printf(" "); else printf("\n"); - perf_event__print_ip(event, sample, machine, evsel, + perf_event__print_ip(event, sample, machine, PRINT_FIELD(SYM), PRINT_FIELD(DSO), PRINT_FIELD(SYMOFFSET)); } @@ -402,6 +416,7 @@ static void print_sample_bts(union perf_event *event, } static void process_event(union perf_event *event __unused, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, @@ -412,7 +427,7 @@ static void process_event(union perf_event *event __unused, if (output[attr->type].fields == 0) return; - print_sample_start(sample, thread, attr); + print_sample_start(pevent, sample, thread, evsel); if (is_bts_event(attr)) { print_sample_bts(event, sample, evsel, machine, thread); @@ -420,7 +435,7 @@ static void process_event(union perf_event *event __unused, } if (PRINT_FIELD(TRACE)) - print_trace_event(sample->cpu, sample->raw_data, + print_trace_event(pevent, sample->cpu, sample->raw_data, sample->raw_size); if (PRINT_FIELD(ADDR)) @@ -431,7 +446,7 @@ static void process_event(union perf_event *event __unused, printf(" "); else printf("\n"); - perf_event__print_ip(event, sample, machine, evsel, + perf_event__print_ip(event, sample, machine, PRINT_FIELD(SYM), PRINT_FIELD(DSO), PRINT_FIELD(SYMOFFSET)); } @@ -451,7 +466,8 @@ static int default_stop_script(void) return 0; } -static int default_generate_script(const char *outfile __unused) +static int default_generate_script(struct pevent *pevent __unused, + const char *outfile __unused) { return 0; } @@ -489,6 +505,7 @@ static int process_sample_event(struct perf_tool *tool __used, struct machine *machine) { struct addr_location al; + struct perf_script *scr = container_of(tool, struct perf_script, tool); struct thread *thread = machine__findnew_thread(machine, event->ip.tid); if (thread == NULL) { @@ -520,24 +537,27 @@ static int process_sample_event(struct perf_tool *tool __used, if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) return 0; - scripting_ops->process_event(event, sample, evsel, machine, thread); + scripting_ops->process_event(event, scr->session->pevent, + sample, evsel, machine, thread); evsel->hists.stats.total_period += sample->period; return 0; } -static struct perf_tool perf_script = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, - .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, - .tracing_data = perf_event__process_tracing_data, - .build_id = perf_event__process_build_id, - .ordered_samples = true, - .ordering_requires_timestamps = true, +static struct perf_script perf_script = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .exit = perf_event__process_task, + .fork = perf_event__process_task, + .attr = perf_event__process_attr, + .event_type = perf_event__process_event_type, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_samples = true, + .ordering_requires_timestamps = true, + }, }; extern volatile int session_done; @@ -553,7 +573,7 @@ static int __cmd_script(struct perf_session *session) signal(SIGINT, sig_handler); - ret = perf_session__process_events(session, &perf_script); + ret = perf_session__process_events(session, &perf_script.tool); if (debug_mode) pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); @@ -1335,10 +1355,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) if (!script_name) setup_pager(); - session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_script); + session = perf_session__new(input_name, O_RDONLY, 0, false, + &perf_script.tool); if (session == NULL) return -ENOMEM; + perf_script.session = session; + if (cpu_list) { if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap)) return -1; @@ -1384,7 +1407,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) return -1; } - err = scripting_ops->generate_script("perf-script"); + err = scripting_ops->generate_script(session->pevent, + "perf-script"); goto out; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 07b5c7703dd..861f0aec77a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -391,7 +391,7 @@ static int read_counter_aggr(struct perf_evsel *counter) if (verbose) { fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", - event_name(counter), count[0], count[1], count[2]); + perf_evsel__name(counter), count[0], count[1], count[2]); } /* @@ -496,7 +496,7 @@ static int run_perf_stat(int argc __used, const char **argv) errno == ENXIO) { if (verbose) ui__warning("%s event is not supported by the kernel.\n", - event_name(counter)); + perf_evsel__name(counter)); counter->supported = false; continue; } @@ -594,7 +594,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) csv_output ? 0 : -4, evsel_list->cpus->map[cpu], csv_sep); - fprintf(output, fmt, cpustr, msecs, csv_sep, event_name(evsel)); + fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel)); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -792,7 +792,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) else cpu = 0; - fprintf(output, fmt, cpustr, avg, csv_sep, event_name(evsel)); + fprintf(output, fmt, cpustr, avg, csv_sep, perf_evsel__name(evsel)); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -908,7 +908,7 @@ static void print_counter_aggr(struct perf_evsel *counter) counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, csv_output ? 0 : -24, - event_name(counter)); + perf_evsel__name(counter)); if (counter->cgrp) fprintf(output, "%s%s", csv_sep, counter->cgrp->name); @@ -961,7 +961,7 @@ static void print_counter(struct perf_evsel *counter) counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, csv_output ? 0 : -24, - event_name(counter)); + perf_evsel__name(counter)); if (counter->cgrp) fprintf(output, "%s%s", diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 5a8727c0875..5ce30305462 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -583,7 +583,7 @@ static int test__basic_mmap(void) if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { pr_debug("expected %d %s events, got %d\n", expected_nr_events[evsel->idx], - event_name(evsel), nr_events[evsel->idx]); + perf_evsel__name(evsel), nr_events[evsel->idx]); goto out_munmap; } } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 6bb0277b7df..e3cab5f088f 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -245,7 +245,7 @@ static void perf_top__show_details(struct perf_top *top) if (notes->src == NULL) goto out_unlock; - printf("Showing %s for %s\n", event_name(top->sym_evsel), symbol->name); + printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name); printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter); more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx, @@ -408,7 +408,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top->print_entries); if (top->evlist->nr_entries > 1) - fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top->sym_evsel)); + fprintf(stdout, "\t[E] active event counter. \t(%s)\n", perf_evsel__name(top->sym_evsel)); fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); @@ -503,13 +503,13 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) fprintf(stderr, "\nAvailable events:"); list_for_each_entry(top->sym_evsel, &top->evlist->entries, node) - fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, event_name(top->sym_evsel)); + fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel)); prompt_integer(&counter, "Enter details event counter"); if (counter >= top->evlist->nr_entries) { top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node); - fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top->sym_evsel)); + fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel)); sleep(1); break; } @@ -774,7 +774,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, evsel, al.thread, + err = machine__resolve_callchain(machine, al.thread, sample->callchain, &parent); if (err) return; @@ -960,7 +960,7 @@ try_again: if (err == ENOENT) { ui__error("The %s event is not supported.\n", - event_name(counter)); + perf_evsel__name(counter)); goto out_err; } else if (err == EMFILE) { ui__error("Too many events are opened.\n" diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index d9084e03ce5..6c18785a641 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -78,6 +78,19 @@ int main(int argc, char *argv[]) return 0; } endef + +define SOURCE_GTK2_INFOBAR +#pragma GCC diagnostic ignored \"-Wstrict-prototypes\" +#include <gtk/gtk.h> +#pragma GCC diagnostic error \"-Wstrict-prototypes\" + +int main(void) +{ + gtk_info_bar_new(); + + return 0; +} +endef endif ifndef NO_LIBPERL diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 34b1c46eaf4..67a2703e666 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -814,7 +814,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, { struct disasm_line *pos, *n; struct annotation *notes; - const size_t size = symbol__size(sym); + size_t size; struct map_symbol ms = { .map = map, .sym = sym, @@ -834,6 +834,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, if (sym == NULL) return -1; + size = symbol__size(sym); + if (map->dso->annotate_warned) return -1; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 53f6697d014..482f0517b61 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -23,6 +23,7 @@ struct hist_browser { struct hists *hists; struct hist_entry *he_selection; struct map_symbol *selection; + int print_seq; bool has_symbols; }; @@ -800,6 +801,196 @@ do_offset: } } +static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser, + struct callchain_node *chain_node, + u64 total, int level, + FILE *fp) +{ + struct rb_node *node; + int offset = level * LEVEL_OFFSET_STEP; + u64 new_total, remaining; + int printed = 0; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + new_total = chain_node->children_hit; + else + new_total = total; + + remaining = new_total; + node = rb_first(&chain_node->rb_root); + while (node) { + struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); + struct rb_node *next = rb_next(node); + u64 cumul = callchain_cumul_hits(child); + struct callchain_list *chain; + char folded_sign = ' '; + int first = true; + int extra_offset = 0; + + remaining -= cumul; + + list_for_each_entry(chain, &child->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str; + const char *str; + bool was_first = first; + + if (first) + first = false; + else + extra_offset = LEVEL_OFFSET_STEP; + + folded_sign = callchain_list__folded(chain); + + alloc_str = NULL; + str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + if (was_first) { + double percent = cumul * 100.0 / new_total; + + if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) + str = "Not enough memory!"; + else + str = alloc_str; + } + + printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str); + free(alloc_str); + if (folded_sign == '+') + break; + } + + if (folded_sign == '-') { + const int new_level = level + (extra_offset ? 2 : 1); + printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total, + new_level, fp); + } + + node = next; + } + + return printed; +} + +static int hist_browser__fprintf_callchain_node(struct hist_browser *browser, + struct callchain_node *node, + int level, FILE *fp) +{ + struct callchain_list *chain; + int offset = level * LEVEL_OFFSET_STEP; + char folded_sign = ' '; + int printed = 0; + + list_for_each_entry(chain, &node->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *s; + + folded_sign = callchain_list__folded(chain); + s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s); + } + + if (folded_sign == '-') + printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node, + browser->hists->stats.total_period, + level + 1, fp); + return printed; +} + +static int hist_browser__fprintf_callchain(struct hist_browser *browser, + struct rb_root *chain, int level, FILE *fp) +{ + struct rb_node *nd; + int printed = 0; + + for (nd = rb_first(chain); nd; nd = rb_next(nd)) { + struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); + + printed += hist_browser__fprintf_callchain_node(browser, node, level, fp); + } + + return printed; +} + +static int hist_browser__fprintf_entry(struct hist_browser *browser, + struct hist_entry *he, FILE *fp) +{ + char s[8192]; + double percent; + int printed = 0; + char folded_sign = ' '; + + if (symbol_conf.use_callchain) + folded_sign = hist_entry__folded(he); + + hist_entry__snprintf(he, s, sizeof(s), browser->hists); + percent = (he->period * 100.0) / browser->hists->stats.total_period; + + if (symbol_conf.use_callchain) + printed += fprintf(fp, "%c ", folded_sign); + + printed += fprintf(fp, " %5.2f%%", percent); + + if (symbol_conf.show_nr_samples) + printed += fprintf(fp, " %11u", he->nr_events); + + if (symbol_conf.show_total_period) + printed += fprintf(fp, " %12" PRIu64, he->period); + + printed += fprintf(fp, "%s\n", rtrim(s)); + + if (folded_sign == '-') + printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp); + + return printed; +} + +static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp) +{ + struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries)); + int printed = 0; + + while (nd) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + printed += hist_browser__fprintf_entry(browser, h, fp); + nd = hists__filter_entries(rb_next(nd)); + } + + return printed; +} + +static int hist_browser__dump(struct hist_browser *browser) +{ + char filename[64]; + FILE *fp; + + while (1) { + scnprintf(filename, sizeof(filename), "perf.hist.%d", browser->print_seq); + if (access(filename, F_OK)) + break; + /* + * XXX: Just an arbitrary lazy upper limit + */ + if (++browser->print_seq == 8192) { + ui_helpline__fpush("Too many perf.hist.N files, nothing written!"); + return -1; + } + } + + fp = fopen(filename, "w"); + if (fp == NULL) { + char bf[64]; + strerror_r(errno, bf, sizeof(bf)); + ui_helpline__fpush("Couldn't write to %s: %s", filename, bf); + return -1; + } + + ++browser->print_seq; + hist_browser__fprintf(browser, fp); + fclose(fp); + ui_helpline__fpush("%s written!", filename); + + return 0; +} + static struct hist_browser *hist_browser__new(struct hists *hists) { struct hist_browser *browser = zalloc(sizeof(*browser)); @@ -937,6 +1128,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, browser->selection->map->dso->annotate_warned) continue; goto do_annotate; + case 'P': + hist_browser__dump(browser); + continue; case 'd': goto zoom_dso; case 't': @@ -969,6 +1163,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "E Expand all callchains\n" "d Zoom into current DSO\n" "t Zoom into current Thread\n" + "P Print histograms to perf.hist.N\n" "/ Filter symbol by name"); continue; case K_ENTER: @@ -1172,7 +1367,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser, struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); bool current_entry = ui_browser__is_current_entry(browser, row); unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE]; - const char *ev_name = event_name(evsel); + const char *ev_name = perf_evsel__name(evsel); char bf[256], unit; const char *warn = " "; size_t printed; @@ -1240,7 +1435,7 @@ browse_hists: */ if (timer) timer(arg); - ev_name = event_name(pos); + ev_name = perf_evsel__name(pos); key = perf_evsel__hists_browse(pos, nr_events, help, ev_name, true, timer, arg, delay_secs); @@ -1309,17 +1504,11 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, ui_helpline__push("Press ESC to exit"); list_for_each_entry(pos, &evlist->entries, node) { - const char *ev_name = event_name(pos); + const char *ev_name = perf_evsel__name(pos); size_t line_len = strlen(ev_name) + 7; if (menu.b.width < line_len) menu.b.width = line_len; - /* - * Cache the evsel name, tracepoints have a _high_ cost per - * event_name() call. - */ - if (pos->name == NULL) - pos->name = strdup(ev_name); } return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer, @@ -1330,11 +1519,10 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, void(*timer)(void *arg), void *arg, int delay_secs) { - if (evlist->nr_entries == 1) { struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); - const char *ev_name = event_name(first); + const char *ev_name = perf_evsel__name(first); return perf_evsel__hists_browse(first, evlist->nr_entries, help, ev_name, false, timer, arg, delay_secs); diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 0656c381a89..ec12e0b4ded 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -11,8 +11,8 @@ static void perf_gtk__signal(int sig) { + perf_gtk__exit(false); psignal(sig, "perf"); - gtk_main_quit(); } static void perf_gtk__resize_window(GtkWidget *window) @@ -122,13 +122,59 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) gtk_container_add(GTK_CONTAINER(window), view); } +#ifdef HAVE_GTK_INFO_BAR +static GtkWidget *perf_gtk__setup_info_bar(void) +{ + GtkWidget *info_bar; + GtkWidget *label; + GtkWidget *content_area; + + info_bar = gtk_info_bar_new(); + gtk_widget_set_no_show_all(info_bar, TRUE); + + label = gtk_label_new(""); + gtk_widget_show(label); + + content_area = gtk_info_bar_get_content_area(GTK_INFO_BAR(info_bar)); + gtk_container_add(GTK_CONTAINER(content_area), label); + + gtk_info_bar_add_button(GTK_INFO_BAR(info_bar), GTK_STOCK_OK, + GTK_RESPONSE_OK); + g_signal_connect(info_bar, "response", + G_CALLBACK(gtk_widget_hide), NULL); + + pgctx->info_bar = info_bar; + pgctx->message_label = label; + + return info_bar; +} +#endif + +static GtkWidget *perf_gtk__setup_statusbar(void) +{ + GtkWidget *stbar; + unsigned ctxid; + + stbar = gtk_statusbar_new(); + + ctxid = gtk_statusbar_get_context_id(GTK_STATUSBAR(stbar), + "perf report"); + pgctx->statbar = stbar; + pgctx->statbar_ctx_id = ctxid; + + return stbar; +} + int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help __used, void (*timer) (void *arg)__used, void *arg __used, int delay_secs __used) { struct perf_evsel *pos; + GtkWidget *vbox; GtkWidget *notebook; + GtkWidget *info_bar; + GtkWidget *statbar; GtkWidget *window; signal(SIGSEGV, perf_gtk__signal); @@ -143,11 +189,17 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, g_signal_connect(window, "delete_event", gtk_main_quit, NULL); + pgctx = perf_gtk__activate_context(window); + if (!pgctx) + return -1; + + vbox = gtk_vbox_new(FALSE, 0); + notebook = gtk_notebook_new(); list_for_each_entry(pos, &evlist->entries, node) { struct hists *hists = &pos->hists; - const char *evname = event_name(pos); + const char *evname = perf_evsel__name(pos); GtkWidget *scrolled_window; GtkWidget *tab_label; @@ -164,7 +216,16 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); } - gtk_container_add(GTK_CONTAINER(window), notebook); + gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); + + info_bar = perf_gtk__setup_info_bar(); + if (info_bar) + gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0); + + statbar = perf_gtk__setup_statusbar(); + gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); + + gtk_container_add(GTK_CONTAINER(window), vbox); gtk_widget_show_all(window); @@ -174,5 +235,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_main(); + perf_gtk__deactivate_context(&pgctx); + return 0; } diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 75177ee0403..a4d0f2b4a2d 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -1,8 +1,39 @@ #ifndef _PERF_GTK_H_ #define _PERF_GTK_H_ 1 +#include <stdbool.h> + #pragma GCC diagnostic ignored "-Wstrict-prototypes" #include <gtk/gtk.h> #pragma GCC diagnostic error "-Wstrict-prototypes" + +struct perf_gtk_context { + GtkWidget *main_window; + +#ifdef HAVE_GTK_INFO_BAR + GtkWidget *info_bar; + GtkWidget *message_label; +#endif + GtkWidget *statbar; + guint statbar_ctx_id; +}; + +extern struct perf_gtk_context *pgctx; + +static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx) +{ + return ctx && ctx->main_window; +} + +struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window); +int perf_gtk__deactivate_context(struct perf_gtk_context **ctx); + +#ifndef HAVE_GTK_INFO_BAR +static inline GtkWidget *perf_gtk__setup_info_bar(void) +{ + return NULL; +} +#endif + #endif /* _PERF_GTK_H_ */ diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c index 82952995776..92879ce61e2 100644 --- a/tools/perf/ui/gtk/setup.c +++ b/tools/perf/ui/gtk/setup.c @@ -1,12 +1,17 @@ #include "gtk.h" #include "../../util/cache.h" +#include "../../util/debug.h" + +extern struct perf_error_ops perf_gtk_eops; int perf_gtk__init(void) { + perf_error__register(&perf_gtk_eops); return gtk_init_check(NULL, NULL) ? 0 : -1; } void perf_gtk__exit(bool wait_for_ok __used) { + perf_error__unregister(&perf_gtk_eops); gtk_main_quit(); } diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c new file mode 100644 index 00000000000..0ead373c0df --- /dev/null +++ b/tools/perf/ui/gtk/util.c @@ -0,0 +1,129 @@ +#include "../util.h" +#include "../../util/debug.h" +#include "gtk.h" + +#include <string.h> + + +struct perf_gtk_context *pgctx; + +struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window) +{ + struct perf_gtk_context *ctx; + + ctx = malloc(sizeof(*pgctx)); + if (ctx) + ctx->main_window = window; + + return ctx; +} + +int perf_gtk__deactivate_context(struct perf_gtk_context **ctx) +{ + if (!perf_gtk__is_active_context(*ctx)) + return -1; + + free(*ctx); + *ctx = NULL; + return 0; +} + +static int perf_gtk__error(const char *format, va_list args) +{ + char *msg; + GtkWidget *dialog; + + if (!perf_gtk__is_active_context(pgctx) || + vasprintf(&msg, format, args) < 0) { + fprintf(stderr, "Error:\n"); + vfprintf(stderr, format, args); + fprintf(stderr, "\n"); + return -1; + } + + dialog = gtk_message_dialog_new_with_markup(GTK_WINDOW(pgctx->main_window), + GTK_DIALOG_DESTROY_WITH_PARENT, + GTK_MESSAGE_ERROR, + GTK_BUTTONS_CLOSE, + "<b>Error</b>\n\n%s", msg); + gtk_dialog_run(GTK_DIALOG(dialog)); + + gtk_widget_destroy(dialog); + free(msg); + return 0; +} + +#ifdef HAVE_GTK_INFO_BAR +static int perf_gtk__warning_info_bar(const char *format, va_list args) +{ + char *msg; + + if (!perf_gtk__is_active_context(pgctx) || + vasprintf(&msg, format, args) < 0) { + fprintf(stderr, "Warning:\n"); + vfprintf(stderr, format, args); + fprintf(stderr, "\n"); + return -1; + } + + gtk_label_set_text(GTK_LABEL(pgctx->message_label), msg); + gtk_info_bar_set_message_type(GTK_INFO_BAR(pgctx->info_bar), + GTK_MESSAGE_WARNING); + gtk_widget_show(pgctx->info_bar); + + free(msg); + return 0; +} +#else +static int perf_gtk__warning_statusbar(const char *format, va_list args) +{ + char *msg, *p; + + if (!perf_gtk__is_active_context(pgctx) || + vasprintf(&msg, format, args) < 0) { + fprintf(stderr, "Warning:\n"); + vfprintf(stderr, format, args); + fprintf(stderr, "\n"); + return -1; + } + + gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar), + pgctx->statbar_ctx_id); + + /* Only first line can be displayed */ + p = strchr(msg, '\n'); + if (p) + *p = '\0'; + + gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar), + pgctx->statbar_ctx_id, msg); + + free(msg); + return 0; +} +#endif + +struct perf_error_ops perf_gtk_eops = { + .error = perf_gtk__error, +#ifdef HAVE_GTK_INFO_BAR + .warning = perf_gtk__warning_info_bar, +#else + .warning = perf_gtk__warning_statusbar, +#endif +}; + +/* + * FIXME: Functions below should be implemented properly. + * For now, just add stubs for NO_NEWT=1 build. + */ +#ifdef NO_NEWT_SUPPORT +int ui_helpline__show_help(const char *format __used, va_list ap __used) +{ + return 0; +} + +void ui_progress__update(u64 curr __used, u64 total __used, + const char *title __used) +{ +} +#endif diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index d33e943ac43..e813c1d1734 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -15,6 +15,8 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; static volatile int ui__need_resize; +extern struct perf_error_ops perf_tui_eops; + void ui__refresh_dimensions(bool force) { if (force || ui__need_resize) { @@ -122,6 +124,8 @@ int ui__init(void) signal(SIGINT, ui__signal); signal(SIGQUIT, ui__signal); signal(SIGTERM, ui__signal); + + perf_error__register(&perf_tui_eops); out: return err; } @@ -137,4 +141,6 @@ void ui__exit(bool wait_for_ok) SLsmg_refresh(); SLsmg_reset_smg(); SLang_reset_tty(); + + perf_error__unregister(&perf_tui_eops); } diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c new file mode 100644 index 00000000000..092902e30ce --- /dev/null +++ b/tools/perf/ui/tui/util.c @@ -0,0 +1,243 @@ +#include "../../util/util.h" +#include <signal.h> +#include <stdbool.h> +#include <string.h> +#include <sys/ttydefaults.h> + +#include "../../util/cache.h" +#include "../../util/debug.h" +#include "../browser.h" +#include "../keysyms.h" +#include "../helpline.h" +#include "../ui.h" +#include "../util.h" +#include "../libslang.h" + +static void ui_browser__argv_write(struct ui_browser *browser, + void *entry, int row) +{ + char **arg = entry; + bool current_entry = ui_browser__is_current_entry(browser, row); + + ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : + HE_COLORSET_NORMAL); + slsmg_write_nstring(*arg, browser->width); +} + +static int popup_menu__run(struct ui_browser *menu) +{ + int key; + + if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0) + return -1; + + while (1) { + key = ui_browser__run(menu, 0); + + switch (key) { + case K_RIGHT: + case K_ENTER: + key = menu->index; + break; + case K_LEFT: + case K_ESC: + case 'q': + case CTRL('c'): + key = -1; + break; + default: + continue; + } + + break; + } + + ui_browser__hide(menu); + return key; +} + +int ui__popup_menu(int argc, char * const argv[]) +{ + struct ui_browser menu = { + .entries = (void *)argv, + .refresh = ui_browser__argv_refresh, + .seek = ui_browser__argv_seek, + .write = ui_browser__argv_write, + .nr_entries = argc, + }; + + return popup_menu__run(&menu); +} + +int ui_browser__input_window(const char *title, const char *text, char *input, + const char *exit_msg, int delay_secs) +{ + int x, y, len, key; + int max_len = 60, nr_lines = 0; + static char buf[50]; + const char *t; + + t = text; + while (1) { + const char *sep = strchr(t, '\n'); + + if (sep == NULL) + sep = strchr(t, '\0'); + len = sep - t; + if (max_len < len) + max_len = len; + ++nr_lines; + if (*sep == '\0') + break; + t = sep + 1; + } + + max_len += 2; + nr_lines += 8; + y = SLtt_Screen_Rows / 2 - nr_lines / 2; + x = SLtt_Screen_Cols / 2 - max_len / 2; + + SLsmg_set_color(0); + SLsmg_draw_box(y, x++, nr_lines, max_len); + if (title) { + SLsmg_gotorc(y, x + 1); + SLsmg_write_string((char *)title); + } + SLsmg_gotorc(++y, x); + nr_lines -= 7; + max_len -= 2; + SLsmg_write_wrapped_string((unsigned char *)text, y, x, + nr_lines, max_len, 1); + y += nr_lines; + len = 5; + while (len--) { + SLsmg_gotorc(y + len - 1, x); + SLsmg_write_nstring((char *)" ", max_len); + } + SLsmg_draw_box(y++, x + 1, 3, max_len - 2); + + SLsmg_gotorc(y + 3, x); + SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_refresh(); + + x += 2; + len = 0; + key = ui__getch(delay_secs); + while (key != K_TIMER && key != K_ENTER && key != K_ESC) { + if (key == K_BKSPC) { + if (len == 0) + goto next_key; + SLsmg_gotorc(y, x + --len); + SLsmg_write_char(' '); + } else { + buf[len] = key; + SLsmg_gotorc(y, x + len++); + SLsmg_write_char(key); + } + SLsmg_refresh(); + + /* XXX more graceful overflow handling needed */ + if (len == sizeof(buf) - 1) { + ui_helpline__push("maximum size of symbol name reached!"); + key = K_ENTER; + break; + } +next_key: + key = ui__getch(delay_secs); + } + + buf[len] = '\0'; + strncpy(input, buf, len+1); + return key; +} + +int ui__question_window(const char *title, const char *text, + const char *exit_msg, int delay_secs) +{ + int x, y; + int max_len = 0, nr_lines = 0; + const char *t; + + t = text; + while (1) { + const char *sep = strchr(t, '\n'); + int len; + + if (sep == NULL) + sep = strchr(t, '\0'); + len = sep - t; + if (max_len < len) + max_len = len; + ++nr_lines; + if (*sep == '\0') + break; + t = sep + 1; + } + + max_len += 2; + nr_lines += 4; + y = SLtt_Screen_Rows / 2 - nr_lines / 2, + x = SLtt_Screen_Cols / 2 - max_len / 2; + + SLsmg_set_color(0); + SLsmg_draw_box(y, x++, nr_lines, max_len); + if (title) { + SLsmg_gotorc(y, x + 1); + SLsmg_write_string((char *)title); + } + SLsmg_gotorc(++y, x); + nr_lines -= 2; + max_len -= 2; + SLsmg_write_wrapped_string((unsigned char *)text, y, x, + nr_lines, max_len, 1); + SLsmg_gotorc(y + nr_lines - 2, x); + SLsmg_write_nstring((char *)" ", max_len); + SLsmg_gotorc(y + nr_lines - 1, x); + SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_refresh(); + return ui__getch(delay_secs); +} + +int ui__help_window(const char *text) +{ + return ui__question_window("Help", text, "Press any key...", 0); +} + +int ui__dialog_yesno(const char *msg) +{ + return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0); +} + +static int __ui__warning(const char *title, const char *format, va_list args) +{ + char *s; + + if (vasprintf(&s, format, args) > 0) { + int key; + + pthread_mutex_lock(&ui__lock); + key = ui__question_window(title, s, "Press any key...", 0); + pthread_mutex_unlock(&ui__lock); + free(s); + return key; + } + + fprintf(stderr, "%s\n", title); + vfprintf(stderr, format, args); + return K_ESC; +} + +static int perf_tui__error(const char *format, va_list args) +{ + return __ui__warning("Error:", format, args); +} + +static int perf_tui__warning(const char *format, va_list args) +{ + return __ui__warning("Warning:", format, args); +} + +struct perf_error_ops perf_tui_eops = { + .error = perf_tui__error, + .warning = perf_tui__warning, +}; diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c index ad4374a16bb..4f989774c8c 100644 --- a/tools/perf/ui/util.c +++ b/tools/perf/ui/util.c @@ -1,250 +1,85 @@ -#include "../util.h" -#include <signal.h> -#include <stdbool.h> -#include <string.h> -#include <sys/ttydefaults.h> - -#include "../cache.h" -#include "../debug.h" -#include "browser.h" -#include "keysyms.h" -#include "helpline.h" -#include "ui.h" #include "util.h" -#include "libslang.h" - -static void ui_browser__argv_write(struct ui_browser *browser, - void *entry, int row) -{ - char **arg = entry; - bool current_entry = ui_browser__is_current_entry(browser, row); +#include "../debug.h" - ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : - HE_COLORSET_NORMAL); - slsmg_write_nstring(*arg, browser->width); -} -static int popup_menu__run(struct ui_browser *menu) +/* + * Default error logging functions + */ +static int perf_stdio__error(const char *format, va_list args) { - int key; - - if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0) - return -1; - - while (1) { - key = ui_browser__run(menu, 0); - - switch (key) { - case K_RIGHT: - case K_ENTER: - key = menu->index; - break; - case K_LEFT: - case K_ESC: - case 'q': - case CTRL('c'): - key = -1; - break; - default: - continue; - } - - break; - } - - ui_browser__hide(menu); - return key; + fprintf(stderr, "Error:\n"); + vfprintf(stderr, format, args); + return 0; } -int ui__popup_menu(int argc, char * const argv[]) +static int perf_stdio__warning(const char *format, va_list args) { - struct ui_browser menu = { - .entries = (void *)argv, - .refresh = ui_browser__argv_refresh, - .seek = ui_browser__argv_seek, - .write = ui_browser__argv_write, - .nr_entries = argc, - }; - - return popup_menu__run(&menu); + fprintf(stderr, "Warning:\n"); + vfprintf(stderr, format, args); + return 0; } -int ui_browser__input_window(const char *title, const char *text, char *input, - const char *exit_msg, int delay_secs) +static struct perf_error_ops default_eops = { - int x, y, len, key; - int max_len = 60, nr_lines = 0; - static char buf[50]; - const char *t; - - t = text; - while (1) { - const char *sep = strchr(t, '\n'); - - if (sep == NULL) - sep = strchr(t, '\0'); - len = sep - t; - if (max_len < len) - max_len = len; - ++nr_lines; - if (*sep == '\0') - break; - t = sep + 1; - } - - max_len += 2; - nr_lines += 8; - y = SLtt_Screen_Rows / 2 - nr_lines / 2; - x = SLtt_Screen_Cols / 2 - max_len / 2; - - SLsmg_set_color(0); - SLsmg_draw_box(y, x++, nr_lines, max_len); - if (title) { - SLsmg_gotorc(y, x + 1); - SLsmg_write_string((char *)title); - } - SLsmg_gotorc(++y, x); - nr_lines -= 7; - max_len -= 2; - SLsmg_write_wrapped_string((unsigned char *)text, y, x, - nr_lines, max_len, 1); - y += nr_lines; - len = 5; - while (len--) { - SLsmg_gotorc(y + len - 1, x); - SLsmg_write_nstring((char *)" ", max_len); - } - SLsmg_draw_box(y++, x + 1, 3, max_len - 2); - - SLsmg_gotorc(y + 3, x); - SLsmg_write_nstring((char *)exit_msg, max_len); - SLsmg_refresh(); + .error = perf_stdio__error, + .warning = perf_stdio__warning, +}; - x += 2; - len = 0; - key = ui__getch(delay_secs); - while (key != K_TIMER && key != K_ENTER && key != K_ESC) { - if (key == K_BKSPC) { - if (len == 0) - goto next_key; - SLsmg_gotorc(y, x + --len); - SLsmg_write_char(' '); - } else { - buf[len] = key; - SLsmg_gotorc(y, x + len++); - SLsmg_write_char(key); - } - SLsmg_refresh(); +static struct perf_error_ops *perf_eops = &default_eops; - /* XXX more graceful overflow handling needed */ - if (len == sizeof(buf) - 1) { - ui_helpline__push("maximum size of symbol name reached!"); - key = K_ENTER; - break; - } -next_key: - key = ui__getch(delay_secs); - } - buf[len] = '\0'; - strncpy(input, buf, len+1); - return key; -} - -int ui__question_window(const char *title, const char *text, - const char *exit_msg, int delay_secs) +int ui__error(const char *format, ...) { - int x, y; - int max_len = 0, nr_lines = 0; - const char *t; - - t = text; - while (1) { - const char *sep = strchr(t, '\n'); - int len; - - if (sep == NULL) - sep = strchr(t, '\0'); - len = sep - t; - if (max_len < len) - max_len = len; - ++nr_lines; - if (*sep == '\0') - break; - t = sep + 1; - } - - max_len += 2; - nr_lines += 4; - y = SLtt_Screen_Rows / 2 - nr_lines / 2, - x = SLtt_Screen_Cols / 2 - max_len / 2; + int ret; + va_list args; - SLsmg_set_color(0); - SLsmg_draw_box(y, x++, nr_lines, max_len); - if (title) { - SLsmg_gotorc(y, x + 1); - SLsmg_write_string((char *)title); - } - SLsmg_gotorc(++y, x); - nr_lines -= 2; - max_len -= 2; - SLsmg_write_wrapped_string((unsigned char *)text, y, x, - nr_lines, max_len, 1); - SLsmg_gotorc(y + nr_lines - 2, x); - SLsmg_write_nstring((char *)" ", max_len); - SLsmg_gotorc(y + nr_lines - 1, x); - SLsmg_write_nstring((char *)exit_msg, max_len); - SLsmg_refresh(); - return ui__getch(delay_secs); -} + va_start(args, format); + ret = perf_eops->error(format, args); + va_end(args); -int ui__help_window(const char *text) -{ - return ui__question_window("Help", text, "Press any key...", 0); + return ret; } -int ui__dialog_yesno(const char *msg) -{ - return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0); -} - -int __ui__warning(const char *title, const char *format, va_list args) +int ui__warning(const char *format, ...) { - char *s; - - if (use_browser > 0 && vasprintf(&s, format, args) > 0) { - int key; + int ret; + va_list args; - pthread_mutex_lock(&ui__lock); - key = ui__question_window(title, s, "Press any key...", 0); - pthread_mutex_unlock(&ui__lock); - free(s); - return key; - } + va_start(args, format); + ret = perf_eops->warning(format, args); + va_end(args); - fprintf(stderr, "%s:\n", title); - vfprintf(stderr, format, args); - return K_ESC; + return ret; } -int ui__warning(const char *format, ...) + +/** + * perf_error__register - Register error logging functions + * @eops: The pointer to error logging function struct + * + * Register UI-specific error logging functions. Before calling this, + * other logging functions should be unregistered, if any. + */ +int perf_error__register(struct perf_error_ops *eops) { - int key; - va_list args; + if (perf_eops != &default_eops) + return -1; - va_start(args, format); - key = __ui__warning("Warning", format, args); - va_end(args); - return key; + perf_eops = eops; + return 0; } -int ui__error(const char *format, ...) +/** + * perf_error__unregister - Unregister error logging functions + * @eops: The pointer to error logging function struct + * + * Unregister already registered error logging functions. + */ +int perf_error__unregister(struct perf_error_ops *eops) { - int key; - va_list args; + if (perf_eops != eops) + return -1; - va_start(args, format); - key = __ui__warning("Error", format, args); - va_end(args); - return key; + perf_eops = &default_eops; + return 0; } diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h index 2d1738bd71c..361f08c52d3 100644 --- a/tools/perf/ui/util.h +++ b/tools/perf/ui/util.h @@ -9,6 +9,13 @@ int ui__help_window(const char *text); int ui__dialog_yesno(const char *msg); int ui__question_window(const char *title, const char *text, const char *exit_msg, int delay_secs); -int __ui__warning(const char *title, const char *format, va_list args); + +struct perf_error_ops { + int (*error)(const char *format, va_list args); + int (*warning)(const char *format, va_list args); +}; + +int perf_error__register(struct perf_error_ops *eops); +int perf_error__unregister(struct perf_error_ops *eops); #endif /* _PERF_UI_UTIL_H_ */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index efb1fce259a..4dfe0bb3c32 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -47,7 +47,7 @@ int dump_printf(const char *fmt, ...) return ret; } -#ifdef NO_NEWT_SUPPORT +#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) int ui__warning(const char *format, ...) { va_list args; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 6bebe7f0a20..015c91dbc09 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -12,8 +12,9 @@ int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); struct ui_progress; +struct perf_error_ops; -#ifdef NO_NEWT_SUPPORT +#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) static inline int ui_helpline__show_help(const char *format __used, va_list ap __used) { return 0; @@ -23,12 +24,28 @@ static inline void ui_progress__update(u64 curr __used, u64 total __used, const char *title __used) {} #define ui__error(format, arg...) ui__warning(format, ##arg) -#else + +static inline int +perf_error__register(struct perf_error_ops *eops __used) +{ + return 0; +} + +static inline int +perf_error__unregister(struct perf_error_ops *eops __used) +{ + return 0; +} + +#else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ + extern char ui_helpline__last_msg[]; int ui_helpline__show_help(const char *format, va_list ap); #include "../ui/progress.h" int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -#endif +#include "../ui/util.h" + +#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); int ui__error_paranoid(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 7400fb3fc50..f74e9560350 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -224,8 +224,8 @@ out_free_attrs: return err; } -static struct perf_evsel * - perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +struct perf_evsel * +perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) { struct perf_evsel *evsel; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 989bee9624c..40d4d3cdced 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -73,6 +73,9 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, #define perf_evlist__set_tracepoints_handlers_array(evlist, array) \ perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) +struct perf_evsel * +perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); + void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9f6cebd798e..e8177136486 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -15,7 +15,7 @@ #include "cpumap.h" #include "thread_map.h" #include "target.h" -#include "../../include/linux/perf_event.h" +#include "../../../include/linux/hw_breakpoint.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0)) @@ -78,7 +78,7 @@ static const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = { "ref-cycles", }; -const char *__perf_evsel__hw_name(u64 config) +static const char *__perf_evsel__hw_name(u64 config) { if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config]) return perf_evsel__hw_names[config]; @@ -86,16 +86,15 @@ const char *__perf_evsel__hw_name(u64 config) return "unknown-hardware"; } -static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size) { - int colon = 0; + int colon = 0, r = 0; struct perf_event_attr *attr = &evsel->attr; - int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(attr->config)); bool exclude_guest_default = false; #define MOD_PRINT(context, mod) do { \ if (!attr->exclude_##context) { \ - if (!colon) colon = r++; \ + if (!colon) colon = ++r; \ r += scnprintf(bf + r, size - r, "%c", mod); \ } } while(0) @@ -108,7 +107,7 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) if (attr->precise_ip) { if (!colon) - colon = r++; + colon = ++r; r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp"); exclude_guest_default = true; } @@ -119,39 +118,211 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) } #undef MOD_PRINT if (colon) - bf[colon] = ':'; + bf[colon - 1] = ':'; + return r; +} + +static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config)); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +static const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { + "cpu-clock", + "task-clock", + "page-faults", + "context-switches", + "CPU-migrations", + "minor-faults", + "major-faults", + "alignment-faults", + "emulation-faults", +}; + +static const char *__perf_evsel__sw_name(u64 config) +{ + if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config]) + return perf_evsel__sw_names[config]; + return "unknown-software"; +} + +static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config)); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) +{ + int r; + + r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr); + + if (type & HW_BREAKPOINT_R) + r += scnprintf(bf + r, size - r, "r"); + + if (type & HW_BREAKPOINT_W) + r += scnprintf(bf + r, size - r, "w"); + + if (type & HW_BREAKPOINT_X) + r += scnprintf(bf + r, size - r, "x"); + return r; } -int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size) { - int ret; + struct perf_event_attr *attr = &evsel->attr; + int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "L1-dcache", "l1-d", "l1d", "L1-data", }, + { "L1-icache", "l1-i", "l1i", "L1-instruction", }, + { "LLC", "L2", }, + { "dTLB", "d-tlb", "Data-TLB", }, + { "iTLB", "i-tlb", "Instruction-TLB", }, + { "branch", "branches", "bpu", "btb", "bpc", }, + { "node", }, +}; + +const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "load", "loads", "read", }, + { "store", "stores", "write", }, + { "prefetch", "prefetches", "speculative-read", "speculative-load", }, +}; + +const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "refs", "Reference", "ops", "access", }, + { "misses", "miss", }, +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x +#define CACHE_READ (1 << C(OP_READ)) +#define CACHE_WRITE (1 << C(OP_WRITE)) +#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) +#define COP(x) (1 << x) + +/* + * cache operartion stat + * L1I : Read and prefetch only + * ITLB and BPU : Read-only + */ +static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = { + [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), + [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(ITLB)] = (CACHE_READ), + [C(BPU)] = (CACHE_READ), + [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), +}; + +bool perf_evsel__is_cache_op_valid(u8 type, u8 op) +{ + if (perf_evsel__hw_cache_stat[type] & COP(op)) + return true; /* valid */ + else + return false; /* invalid */ +} + +int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, + char *bf, size_t size) +{ + if (result) { + return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0], + perf_evsel__hw_cache_op[op][0], + perf_evsel__hw_cache_result[result][0]); + } + + return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0], + perf_evsel__hw_cache_op[op][1]); +} + +static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) +{ + u8 op, result, type = (config >> 0) & 0xff; + const char *err = "unknown-ext-hardware-cache-type"; + + if (type > PERF_COUNT_HW_CACHE_MAX) + goto out_err; + + op = (config >> 8) & 0xff; + err = "unknown-ext-hardware-cache-op"; + if (op > PERF_COUNT_HW_CACHE_OP_MAX) + goto out_err; + + result = (config >> 16) & 0xff; + err = "unknown-ext-hardware-cache-result"; + if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + goto out_err; + + err = "invalid-cache"; + if (!perf_evsel__is_cache_op_valid(type, op)) + goto out_err; + + return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size); +out_err: + return scnprintf(bf, size, "%s", err); +} + +static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size); + return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); +} + +static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); +} + +const char *perf_evsel__name(struct perf_evsel *evsel) +{ + char bf[128]; + + if (evsel->name) + return evsel->name; switch (evsel->attr.type) { case PERF_TYPE_RAW: - ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + perf_evsel__raw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_HARDWARE: - ret = perf_evsel__hw_name(evsel, bf, size); + perf_evsel__hw_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_HW_CACHE: + perf_evsel__hw_cache_name(evsel, bf, sizeof(bf)); break; + + case PERF_TYPE_SOFTWARE: + perf_evsel__sw_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_TRACEPOINT: + scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint"); + break; + + case PERF_TYPE_BREAKPOINT: + perf_evsel__bp_name(evsel, bf, sizeof(bf)); + break; + default: - /* - * FIXME - * - * This is the minimal perf_evsel__name so that we can - * reconstruct event names taking into account event modifiers. - * - * The old event_name uses it now for raw anr hw events, so that - * we don't drag all the parsing stuff into the python binding. - * - * On the next devel cycle the rest of the event naming will be - * brought here. - */ - return 0; + scnprintf(bf, sizeof(bf), "%s", "unknown attr type"); + break; } - return ret; + evsel->name = strdup(bf); + + return evsel->name ?: "unknown"; } void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 4ba8b564e6f..67cc5033d19 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -83,8 +83,19 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, struct perf_evsel *first); -const char* __perf_evsel__hw_name(u64 config); -int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size); +bool perf_evsel__is_cache_op_valid(u8 type, u8 op); + +#define PERF_EVSEL__MAX_ALIASES 8 + +extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] + [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_EVSEL__MAX_ALIASES]; +const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES]; +int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, + char *bf, size_t size); +const char *perf_evsel__name(struct perf_evsel *evsel); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index e909d43cf54..5a47aba4675 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -641,7 +641,7 @@ static int write_event_desc(int fd, struct perf_header *h __used, /* * write event string as passed on cmdline */ - ret = do_write_string(fd, event_name(attr)); + ret = do_write_string(fd, perf_evsel__name(attr)); if (ret < 0) return ret; /* @@ -1474,15 +1474,15 @@ out: static int process_tracing_data(struct perf_file_section *section __unused, struct perf_header *ph __unused, - int feat __unused, int fd) + int feat __unused, int fd, void *data) { - trace_report(fd, false); + trace_report(fd, data, false); return 0; } static int process_build_id(struct perf_file_section *section, struct perf_header *ph, - int feat __unused, int fd) + int feat __unused, int fd, void *data __used) { if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) pr_debug("Failed to read buildids, continuing...\n"); @@ -1493,7 +1493,7 @@ struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); int (*process)(struct perf_file_section *section, - struct perf_header *h, int feat, int fd); + struct perf_header *h, int feat, int fd, void *data); const char *name; bool full_only; }; @@ -1988,7 +1988,7 @@ int perf_file_header__read(struct perf_file_header *header, static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, - int feat, int fd, void *data __used) + int feat, int fd, void *data) { if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " @@ -2004,7 +2004,7 @@ static int perf_file_section__process(struct perf_file_section *section, if (!feat_ops[feat].process) return 0; - return feat_ops[feat].process(section, ph, feat, fd); + return feat_ops[feat].process(section, ph, feat, fd, data); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, @@ -2093,9 +2093,11 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel) +static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel, + struct pevent *pevent) { - struct event_format *event = trace_find_event(evsel->attr.config); + struct event_format *event = pevent_find_event(pevent, + evsel->attr.config); char bf[128]; if (event == NULL) @@ -2109,13 +2111,14 @@ static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel) return 0; } -static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist) +static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist, + struct pevent *pevent) { struct perf_evsel *pos; list_for_each_entry(pos, &evlist->entries, node) { if (pos->attr.type == PERF_TYPE_TRACEPOINT && - perf_evsel__set_tracepoint_name(pos)) + perf_evsel__set_tracepoint_name(pos, pevent)) return -1; } @@ -2198,12 +2201,12 @@ int perf_session__read_header(struct perf_session *session, int fd) event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); } - perf_header__process_sections(header, fd, NULL, + perf_header__process_sections(header, fd, &session->pevent, perf_file_section__process); lseek(fd, header->data_offset, SEEK_SET); - if (perf_evlist__set_tracepoint_names(session->evlist)) + if (perf_evlist__set_tracepoint_names(session->evlist, session->pevent)) goto out_delete_evlist; header->frozen = 1; @@ -2419,8 +2422,8 @@ int perf_event__process_tracing_data(union perf_event *event, lseek(session->fd, offset + sizeof(struct tracing_data_event), SEEK_SET); - size_read = trace_report(session->fd, session->repipe); - + size_read = trace_report(session->fd, &session->pevent, + session->repipe); padding = ALIGN(size_read, sizeof(u64)) - size_read; if (read(session->fd, buf, padding) < 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 34bb556d621..0b096c27a41 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -47,6 +47,7 @@ enum hist_column { HISTC_SYMBOL_TO, HISTC_DSO_FROM, HISTC_DSO_TO, + HISTC_SRCLINE, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index 1eb804fd3fb..b6842c1d02a 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -108,4 +108,14 @@ int eprintf(int level, #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + #endif diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 81371bad4ef..c14c665d9a2 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -157,7 +157,7 @@ void machine__exit(struct machine *self); void machine__delete(struct machine *self); int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, struct thread *thread, + struct thread *thread, struct ip_callchain *chain, struct symbol **parent); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c index 76b98e2a587..1b997d2b89c 100644 --- a/tools/perf/util/parse-events-test.c +++ b/tools/perf/util/parse-events-test.c @@ -181,6 +181,22 @@ static int test__checkevent_breakpoint_w(struct perf_evlist *evlist) return 0; } +static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = list_entry(evlist->entries.next, + struct perf_evsel, node); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", + PERF_TYPE_BREAKPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong bp_type", + (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", + HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len); + return 0; +} + static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist) { struct perf_evsel *evsel = list_entry(evlist->entries.next, @@ -309,6 +325,8 @@ static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u")); return test__checkevent_breakpoint(evlist); } @@ -322,6 +340,8 @@ static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:x:k")); return test__checkevent_breakpoint_x(evlist); } @@ -335,6 +355,8 @@ static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp")); return test__checkevent_breakpoint_r(evlist); } @@ -348,10 +370,27 @@ static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:w:up")); return test__checkevent_breakpoint_w(evlist); } +static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = list_entry(evlist->entries.next, + struct perf_evsel, node); + + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp")); + + return test__checkevent_breakpoint_rw(evlist); +} + static int test__checkevent_pmu(struct perf_evlist *evlist) { @@ -413,19 +452,63 @@ static int test__checkevent_pmu_name(struct perf_evlist *evlist) { struct perf_evsel *evsel; - /* cpu/config=1,name=krava1/u */ + /* cpu/config=1,name=krava/u */ evsel = list_entry(evlist->entries.next, struct perf_evsel, node); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); - TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "krava")); + TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava")); - /* cpu/config=2/" */ + /* cpu/config=2/u" */ evsel = list_entry(evsel->node.next, struct perf_evsel, node); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config); - TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "raw 0x2")); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "raw 0x2:u")); + + return 0; +} + +static int test__checkterms_simple(struct list_head *terms) +{ + struct parse_events__term *term; + + /* config=10 */ + term = list_entry(terms->next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 10); + TEST_ASSERT_VAL("wrong config", !term->config); + + /* config1 */ + term = list_entry(term->list.next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 1); + TEST_ASSERT_VAL("wrong config", !term->config); + + /* config2=3 */ + term = list_entry(term->list.next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 3); + TEST_ASSERT_VAL("wrong config", !term->config); + + /* umask=1*/ + term = list_entry(term->list.next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_USER); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 1); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "umask")); return 0; } @@ -541,10 +624,16 @@ static struct test__event_st test__events[] = { .name = "instructions:H", .check = test__checkevent_exclude_guest_modifier, }, + [26] = { + .name = "mem:0:rw", + .check = test__checkevent_breakpoint_rw, + }, + [27] = { + .name = "mem:0:rw:kp", + .check = test__checkevent_breakpoint_rw_modifier, + }, }; -#define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st)) - static struct test__event_st test__events_pmu[] = { [0] = { .name = "cpu/config=10,config1,config2=3,period=1000/u", @@ -556,10 +645,23 @@ static struct test__event_st test__events_pmu[] = { }, }; -#define TEST__EVENTS_PMU_CNT (sizeof(test__events_pmu) / \ - sizeof(struct test__event_st)) +struct test__term { + const char *str; + __u32 type; + int (*check)(struct list_head *terms); +}; + +static struct test__term test__terms[] = { + [0] = { + .str = "config=10,config1,config2=3,umask=1", + .check = test__checkterms_simple, + }, +}; -static int test(struct test__event_st *e) +#define TEST__TERMS_CNT (sizeof(test__terms) / \ + sizeof(struct test__term)) + +static int test_event(struct test__event_st *e) { struct perf_evlist *evlist; int ret; @@ -590,7 +692,48 @@ static int test_events(struct test__event_st *events, unsigned cnt) struct test__event_st *e = &events[i]; pr_debug("running test %d '%s'\n", i, e->name); - ret = test(e); + ret = test_event(e); + if (ret) + break; + } + + return ret; +} + +static int test_term(struct test__term *t) +{ + struct list_head *terms; + int ret; + + terms = malloc(sizeof(*terms)); + if (!terms) + return -ENOMEM; + + INIT_LIST_HEAD(terms); + + ret = parse_events_terms(terms, t->str); + if (ret) { + pr_debug("failed to parse terms '%s', err %d\n", + t->str , ret); + return ret; + } + + ret = t->check(terms); + parse_events__free_terms(terms); + + return ret; +} + +static int test_terms(struct test__term *terms, unsigned cnt) +{ + int ret = 0; + unsigned i; + + for (i = 0; i < cnt; i++) { + struct test__term *t = &terms[i]; + + pr_debug("running test %d '%s'\n", i, t->str); + ret = test_term(t); if (ret) break; } @@ -617,9 +760,17 @@ int parse_events__test(void) { int ret; - ret = test_events(test__events, TEST__EVENTS_CNT); - if (!ret && test_pmu()) - ret = test_events(test__events_pmu, TEST__EVENTS_PMU_CNT); +#define TEST_EVENTS(tests) \ +do { \ + ret = test_events(tests, ARRAY_SIZE(tests)); \ + if (ret) \ + return ret; \ +} while (0) - return ret; + TEST_EVENTS(test__events); + + if (test_pmu()) + TEST_EVENTS(test__events_pmu); + + return test_terms(test__terms, ARRAY_SIZE(test__terms)); } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 05dbc8b3c76..1aa721d7c10 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -11,14 +11,14 @@ #include "cache.h" #include "header.h" #include "debugfs.h" +#include "parse-events-bison.h" +#define YY_EXTRA_TYPE int #include "parse-events-flex.h" #include "pmu.h" #define MAX_NAME_LEN 100 struct event_symbol { - u8 type; - u64 config; const char *symbol; const char *alias; }; @@ -26,32 +26,88 @@ struct event_symbol { #ifdef PARSER_DEBUG extern int parse_events_debug; #endif -int parse_events_parse(struct list_head *list, int *idx); +int parse_events_parse(void *data, void *scanner); -#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x -#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x - -static struct event_symbol event_symbols[] = { - { CHW(CPU_CYCLES), "cpu-cycles", "cycles" }, - { CHW(STALLED_CYCLES_FRONTEND), "stalled-cycles-frontend", "idle-cycles-frontend" }, - { CHW(STALLED_CYCLES_BACKEND), "stalled-cycles-backend", "idle-cycles-backend" }, - { CHW(INSTRUCTIONS), "instructions", "" }, - { CHW(CACHE_REFERENCES), "cache-references", "" }, - { CHW(CACHE_MISSES), "cache-misses", "" }, - { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, - { CHW(BRANCH_MISSES), "branch-misses", "" }, - { CHW(BUS_CYCLES), "bus-cycles", "" }, - { CHW(REF_CPU_CYCLES), "ref-cycles", "" }, +static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = { + .symbol = "cpu-cycles", + .alias = "cycles", + }, + [PERF_COUNT_HW_INSTRUCTIONS] = { + .symbol = "instructions", + .alias = "", + }, + [PERF_COUNT_HW_CACHE_REFERENCES] = { + .symbol = "cache-references", + .alias = "", + }, + [PERF_COUNT_HW_CACHE_MISSES] = { + .symbol = "cache-misses", + .alias = "", + }, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { + .symbol = "branch-instructions", + .alias = "branches", + }, + [PERF_COUNT_HW_BRANCH_MISSES] = { + .symbol = "branch-misses", + .alias = "", + }, + [PERF_COUNT_HW_BUS_CYCLES] = { + .symbol = "bus-cycles", + .alias = "", + }, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = { + .symbol = "stalled-cycles-frontend", + .alias = "idle-cycles-frontend", + }, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = { + .symbol = "stalled-cycles-backend", + .alias = "idle-cycles-backend", + }, + [PERF_COUNT_HW_REF_CPU_CYCLES] = { + .symbol = "ref-cycles", + .alias = "", + }, +}; - { CSW(CPU_CLOCK), "cpu-clock", "" }, - { CSW(TASK_CLOCK), "task-clock", "" }, - { CSW(PAGE_FAULTS), "page-faults", "faults" }, - { CSW(PAGE_FAULTS_MIN), "minor-faults", "" }, - { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, - { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, - { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, - { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" }, - { CSW(EMULATION_FAULTS), "emulation-faults", "" }, +static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { + [PERF_COUNT_SW_CPU_CLOCK] = { + .symbol = "cpu-clock", + .alias = "", + }, + [PERF_COUNT_SW_TASK_CLOCK] = { + .symbol = "task-clock", + .alias = "", + }, + [PERF_COUNT_SW_PAGE_FAULTS] = { + .symbol = "page-faults", + .alias = "faults", + }, + [PERF_COUNT_SW_CONTEXT_SWITCHES] = { + .symbol = "context-switches", + .alias = "cs", + }, + [PERF_COUNT_SW_CPU_MIGRATIONS] = { + .symbol = "cpu-migrations", + .alias = "migrations", + }, + [PERF_COUNT_SW_PAGE_FAULTS_MIN] = { + .symbol = "minor-faults", + .alias = "", + }, + [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = { + .symbol = "major-faults", + .alias = "", + }, + [PERF_COUNT_SW_ALIGNMENT_FAULTS] = { + .symbol = "alignment-faults", + .alias = "", + }, + [PERF_COUNT_SW_EMULATION_FAULTS] = { + .symbol = "emulation-faults", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -62,63 +118,6 @@ static struct event_symbol event_symbols[] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) -static const char *sw_event_names[PERF_COUNT_SW_MAX] = { - "cpu-clock", - "task-clock", - "page-faults", - "context-switches", - "CPU-migrations", - "minor-faults", - "major-faults", - "alignment-faults", - "emulation-faults", -}; - -#define MAX_ALIASES 8 - -static const char *hw_cache[PERF_COUNT_HW_CACHE_MAX][MAX_ALIASES] = { - { "L1-dcache", "l1-d", "l1d", "L1-data", }, - { "L1-icache", "l1-i", "l1i", "L1-instruction", }, - { "LLC", "L2", }, - { "dTLB", "d-tlb", "Data-TLB", }, - { "iTLB", "i-tlb", "Instruction-TLB", }, - { "branch", "branches", "bpu", "btb", "bpc", }, - { "node", }, -}; - -static const char *hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][MAX_ALIASES] = { - { "load", "loads", "read", }, - { "store", "stores", "write", }, - { "prefetch", "prefetches", "speculative-read", "speculative-load", }, -}; - -static const char *hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] - [MAX_ALIASES] = { - { "refs", "Reference", "ops", "access", }, - { "misses", "miss", }, -}; - -#define C(x) PERF_COUNT_HW_CACHE_##x -#define CACHE_READ (1 << C(OP_READ)) -#define CACHE_WRITE (1 << C(OP_WRITE)) -#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) -#define COP(x) (1 << x) - -/* - * cache operartion stat - * L1I : Read and prefetch only - * ITLB and BPU : Read-only - */ -static unsigned long hw_cache_stat[C(MAX)] = { - [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), - [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(ITLB)] = (CACHE_READ), - [C(BPU)] = (CACHE_READ), - [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), -}; - #define for_each_subsystem(sys_dir, sys_dirent, sys_next) \ while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \ if (sys_dirent.d_type == DT_DIR && \ @@ -218,48 +217,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) return NULL; } -#define TP_PATH_LEN (MAX_EVENT_LENGTH * 2 + 1) -static const char *tracepoint_id_to_name(u64 config) -{ - static char buf[TP_PATH_LEN]; - struct tracepoint_path *path; - - path = tracepoint_id_to_path(config); - if (path) { - snprintf(buf, TP_PATH_LEN, "%s:%s", path->system, path->name); - free(path->name); - free(path->system); - free(path); - } else - snprintf(buf, TP_PATH_LEN, "%s:%s", "unknown", "unknown"); - - return buf; -} - -static int is_cache_op_valid(u8 cache_type, u8 cache_op) -{ - if (hw_cache_stat[cache_type] & COP(cache_op)) - return 1; /* valid */ - else - return 0; /* invalid */ -} - -static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result) -{ - static char name[50]; - - if (cache_result) { - sprintf(name, "%s-%s-%s", hw_cache[cache_type][0], - hw_cache_op[cache_op][0], - hw_cache_result[cache_result][0]); - } else { - sprintf(name, "%s-%s", hw_cache[cache_type][0], - hw_cache_op[cache_op][1]); - } - - return name; -} - const char *event_type(int type) { switch (type) { @@ -282,76 +239,6 @@ const char *event_type(int type) return "unknown"; } -const char *event_name(struct perf_evsel *evsel) -{ - u64 config = evsel->attr.config; - int type = evsel->attr.type; - - if (type == PERF_TYPE_RAW || type == PERF_TYPE_HARDWARE) { - /* - * XXX minimal fix, see comment on perf_evsen__name, this static buffer - * will go away together with event_name in the next devel cycle. - */ - static char bf[128]; - perf_evsel__name(evsel, bf, sizeof(bf)); - return bf; - } - - if (evsel->name) - return evsel->name; - - return __event_name(type, config); -} - -const char *__event_name(int type, u64 config) -{ - static char buf[32]; - - if (type == PERF_TYPE_RAW) { - sprintf(buf, "raw 0x%" PRIx64, config); - return buf; - } - - switch (type) { - case PERF_TYPE_HARDWARE: - return __perf_evsel__hw_name(config); - - case PERF_TYPE_HW_CACHE: { - u8 cache_type, cache_op, cache_result; - - cache_type = (config >> 0) & 0xff; - if (cache_type > PERF_COUNT_HW_CACHE_MAX) - return "unknown-ext-hardware-cache-type"; - - cache_op = (config >> 8) & 0xff; - if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX) - return "unknown-ext-hardware-cache-op"; - - cache_result = (config >> 16) & 0xff; - if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX) - return "unknown-ext-hardware-cache-result"; - - if (!is_cache_op_valid(cache_type, cache_op)) - return "invalid-cache"; - - return event_cache_name(cache_type, cache_op, cache_result); - } - - case PERF_TYPE_SOFTWARE: - if (config < PERF_COUNT_SW_MAX && sw_event_names[config]) - return sw_event_names[config]; - return "unknown-software"; - - case PERF_TYPE_TRACEPOINT: - return tracepoint_id_to_name(config); - - default: - break; - } - - return "unknown"; -} - static int add_event(struct list_head **_list, int *idx, struct perf_event_attr *attr, char *name) { @@ -373,19 +260,20 @@ static int add_event(struct list_head **_list, int *idx, return -ENOMEM; } - evsel->name = strdup(name); + if (name) + evsel->name = strdup(name); list_add_tail(&evsel->node, list); *_list = list; return 0; } -static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size) +static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) { int i, j; int n, longest = -1; for (i = 0; i < size; i++) { - for (j = 0; j < MAX_ALIASES && names[i][j]; j++) { + for (j = 0; j < PERF_EVSEL__MAX_ALIASES && names[i][j]; j++) { n = strlen(names[i][j]); if (n > longest && !strncasecmp(str, names[i][j], n)) longest = n; @@ -410,7 +298,7 @@ int parse_events_add_cache(struct list_head **list, int *idx, * No fallback - if we cannot get a clear cache type * then bail out: */ - cache_type = parse_aliases(type, hw_cache, + cache_type = parse_aliases(type, perf_evsel__hw_cache, PERF_COUNT_HW_CACHE_MAX); if (cache_type == -1) return -EINVAL; @@ -423,18 +311,18 @@ int parse_events_add_cache(struct list_head **list, int *idx, snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str); if (cache_op == -1) { - cache_op = parse_aliases(str, hw_cache_op, + cache_op = parse_aliases(str, perf_evsel__hw_cache_op, PERF_COUNT_HW_CACHE_OP_MAX); if (cache_op >= 0) { - if (!is_cache_op_valid(cache_type, cache_op)) + if (!perf_evsel__is_cache_op_valid(cache_type, cache_op)) return -EINVAL; continue; } } if (cache_result == -1) { - cache_result = parse_aliases(str, hw_cache_result, - PERF_COUNT_HW_CACHE_RESULT_MAX); + cache_result = parse_aliases(str, perf_evsel__hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX); if (cache_result >= 0) continue; } @@ -549,21 +437,31 @@ parse_breakpoint_type(const char *type, struct perf_event_attr *attr) if (!type || !type[i]) break; +#define CHECK_SET_TYPE(bit) \ +do { \ + if (attr->bp_type & bit) \ + return -EINVAL; \ + else \ + attr->bp_type |= bit; \ +} while (0) + switch (type[i]) { case 'r': - attr->bp_type |= HW_BREAKPOINT_R; + CHECK_SET_TYPE(HW_BREAKPOINT_R); break; case 'w': - attr->bp_type |= HW_BREAKPOINT_W; + CHECK_SET_TYPE(HW_BREAKPOINT_W); break; case 'x': - attr->bp_type |= HW_BREAKPOINT_X; + CHECK_SET_TYPE(HW_BREAKPOINT_X); break; default: return -EINVAL; } } +#undef CHECK_SET_TYPE + if (!attr->bp_type) /* Default */ attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W; @@ -574,7 +472,6 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, void *ptr, char *type) { struct perf_event_attr attr; - char name[MAX_NAME_LEN]; memset(&attr, 0, sizeof(attr)); attr.bp_addr = (unsigned long) ptr; @@ -593,8 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, attr.type = PERF_TYPE_BREAKPOINT; - snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw"); - return add_event(list, idx, &attr, name); + return add_event(list, idx, &attr, NULL); } static int config_term(struct perf_event_attr *attr, @@ -666,8 +562,7 @@ int parse_events_add_numeric(struct list_head **list, int *idx, config_attr(&attr, head_config, 1)) return -EINVAL; - return add_event(list, idx, &attr, - (char *) __event_name(type, config)); + return add_event(list, idx, &attr, NULL); } static int parse_events__is_name_term(struct parse_events__term *term) @@ -675,8 +570,7 @@ static int parse_events__is_name_term(struct parse_events__term *term) return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; } -static char *pmu_event_name(struct perf_event_attr *attr, - struct list_head *head_terms) +static char *pmu_event_name(struct list_head *head_terms) { struct parse_events__term *term; @@ -684,7 +578,7 @@ static char *pmu_event_name(struct perf_event_attr *attr, if (parse_events__is_name_term(term)) return term->val.str; - return (char *) __event_name(PERF_TYPE_RAW, attr->config); + return NULL; } int parse_events_add_pmu(struct list_head **list, int *idx, @@ -699,6 +593,9 @@ int parse_events_add_pmu(struct list_head **list, int *idx, memset(&attr, 0, sizeof(attr)); + if (perf_pmu__check_alias(pmu, head_config)) + return -EINVAL; + /* * Configure hardcoded terms first, no need to check * return value when called with fail == 0 ;) @@ -709,7 +606,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx, return -EINVAL; return add_event(list, idx, &attr, - pmu_event_name(&attr, head_config)); + pmu_event_name(head_config)); } void parse_events_update_lists(struct list_head *list_event, @@ -787,27 +684,62 @@ int parse_events_modifier(struct list_head *list, char *str) return 0; } -int parse_events(struct perf_evlist *evlist, const char *str, int unset __used) +static int parse_events__scanner(const char *str, void *data, int start_token) { - LIST_HEAD(list); - LIST_HEAD(list_tmp); YY_BUFFER_STATE buffer; - int ret, idx = evlist->nr_entries; + void *scanner; + int ret; - buffer = parse_events__scan_string(str); + ret = parse_events_lex_init_extra(start_token, &scanner); + if (ret) + return ret; + + buffer = parse_events__scan_string(str, scanner); #ifdef PARSER_DEBUG parse_events_debug = 1; #endif - ret = parse_events_parse(&list, &idx); + ret = parse_events_parse(data, scanner); + + parse_events__flush_buffer(buffer, scanner); + parse_events__delete_buffer(buffer, scanner); + parse_events_lex_destroy(scanner); + return ret; +} + +/* + * parse event config string, return a list of event terms. + */ +int parse_events_terms(struct list_head *terms, const char *str) +{ + struct parse_events_data__terms data = { + .terms = NULL, + }; + int ret; - parse_events__flush_buffer(buffer); - parse_events__delete_buffer(buffer); - parse_events_lex_destroy(); + ret = parse_events__scanner(str, &data, PE_START_TERMS); + if (!ret) { + list_splice(data.terms, terms); + free(data.terms); + return 0; + } + parse_events__free_terms(data.terms); + return ret; +} + +int parse_events(struct perf_evlist *evlist, const char *str, int unset __used) +{ + struct parse_events_data__events data = { + .list = LIST_HEAD_INIT(data.list), + .idx = evlist->nr_entries, + }; + int ret; + + ret = parse_events__scanner(str, &data, PE_START_EVENTS); if (!ret) { - int entries = idx - evlist->nr_entries; - perf_evlist__splice_list_tail(evlist, &list, entries); + int entries = data.idx - evlist->nr_entries; + perf_evlist__splice_list_tail(evlist, &data.list, entries); return 0; } @@ -946,16 +878,13 @@ int is_valid_tracepoint(const char *event_string) return 0; } -void print_events_type(u8 type) +static void __print_events_type(u8 type, struct event_symbol *syms, + unsigned max) { - struct event_symbol *syms = event_symbols; - unsigned int i; char name[64]; + unsigned i; - for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { - if (type != syms->type) - continue; - + for (i = 0; i < max ; i++, syms++) { if (strlen(syms->alias)) snprintf(name, sizeof(name), "%s OR %s", syms->symbol, syms->alias); @@ -967,19 +896,28 @@ void print_events_type(u8 type) } } +void print_events_type(u8 type) +{ + if (type == PERF_TYPE_SOFTWARE) + __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX); + else + __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); +} + int print_hwcache_events(const char *event_glob) { unsigned int type, op, i, printed = 0; + char name[64]; for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { /* skip invalid cache type */ - if (!is_cache_op_valid(type, op)) + if (!perf_evsel__is_cache_op_valid(type, op)) continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - char *name = event_cache_name(type, op, i); - + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; @@ -993,26 +931,13 @@ int print_hwcache_events(const char *event_glob) return printed; } -/* - * Print the help text for the event symbols: - */ -void print_events(const char *event_glob) +static void print_symbol_events(const char *event_glob, unsigned type, + struct event_symbol *syms, unsigned max) { - unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0; - struct event_symbol *syms = event_symbols; + unsigned i, printed = 0; char name[MAX_NAME_LEN]; - printf("\n"); - printf("List of pre-defined events (to be used in -e):\n"); - - for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { - type = syms->type; - - if (type != prev_type && printed) { - printf("\n"); - printed = 0; - ntypes_printed++; - } + for (i = 0; i < max; i++, syms++) { if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || @@ -1023,17 +948,31 @@ void print_events(const char *event_glob) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else strncpy(name, syms->symbol, MAX_NAME_LEN); - printf(" %-50s [%s]\n", name, - event_type_descriptors[type]); - prev_type = type; - ++printed; + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); + + printed++; } - if (ntypes_printed) { - printed = 0; + if (printed) printf("\n"); - } +} + +/* + * Print the help text for the event symbols: + */ +void print_events(const char *event_glob) +{ + + printf("\n"); + printf("List of pre-defined events (to be used in -e):\n"); + + print_symbol_events(event_glob, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX); + + print_symbol_events(event_glob, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX); + print_hwcache_events(event_glob); if (event_glob != NULL) @@ -1106,6 +1045,13 @@ int parse_events__term_str(struct parse_events__term **term, config, str, 0); } +int parse_events__term_clone(struct parse_events__term **new, + struct parse_events__term *term) +{ + return new_term(new, term->type_val, term->type_term, term->config, + term->val.str, term->val.num); +} + void parse_events__free_terms(struct list_head *terms) { struct parse_events__term *term, *h; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 8cac57ab4ee..ee9c218a193 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -26,13 +26,12 @@ extern struct tracepoint_path *tracepoint_id_to_path(u64 config); extern bool have_tracepoints(struct list_head *evlist); const char *event_type(int type); -const char *event_name(struct perf_evsel *event); -extern const char *__event_name(int type, u64 config); extern int parse_events_option(const struct option *opt, const char *str, int unset); extern int parse_events(struct perf_evlist *evlist, const char *str, int unset); +extern int parse_events_terms(struct list_head *terms, const char *str); extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) @@ -63,11 +62,22 @@ struct parse_events__term { struct list_head list; }; +struct parse_events_data__events { + struct list_head list; + int idx; +}; + +struct parse_events_data__terms { + struct list_head *terms; +}; + int parse_events__is_hardcoded_term(struct parse_events__term *term); int parse_events__term_num(struct parse_events__term **_term, int type_term, char *config, long num); int parse_events__term_str(struct parse_events__term **_term, int type_term, char *config, char *str); +int parse_events__term_clone(struct parse_events__term **new, + struct parse_events__term *term); void parse_events__free_terms(struct list_head *terms); int parse_events_modifier(struct list_head *list, char *str); int parse_events_add_tracepoint(struct list_head **list, int *idx, @@ -83,8 +93,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx, char *pmu , struct list_head *head_config); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); -void parse_events_error(struct list_head *list_all, - int *idx, char const *msg); +void parse_events_error(void *data, void *scanner, char const *msg); int parse_events__test(void); void print_events(const char *event_glob); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 618a8e78839..384ca74c6b2 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -1,4 +1,6 @@ +%option reentrant +%option bison-bridge %option prefix="parse_events_" %option stack @@ -8,7 +10,10 @@ #include "parse-events-bison.h" #include "parse-events.h" -static int __value(char *str, int base, int token) +char *parse_events_get_text(yyscan_t yyscanner); +YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); + +static int __value(YYSTYPE *yylval, char *str, int base, int token) { long num; @@ -17,35 +22,48 @@ static int __value(char *str, int base, int token) if (errno) return PE_ERROR; - parse_events_lval.num = num; + yylval->num = num; return token; } -static int value(int base) +static int value(yyscan_t scanner, int base) { - return __value(parse_events_text, base, PE_VALUE); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + return __value(yylval, text, base, PE_VALUE); } -static int raw(void) +static int raw(yyscan_t scanner) { - return __value(parse_events_text + 1, 16, PE_RAW); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + return __value(yylval, text + 1, 16, PE_RAW); } -static int str(int token) +static int str(yyscan_t scanner, int token) { - parse_events_lval.str = strdup(parse_events_text); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + yylval->str = strdup(text); return token; } -static int sym(int type, int config) +static int sym(yyscan_t scanner, int type, int config) { - parse_events_lval.num = (type << 16) + config; - return PE_VALUE_SYM; + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = (type << 16) + config; + return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; } -static int term(int type) +static int term(yyscan_t scanner, int type) { - parse_events_lval.num = type; + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = type; return PE_TERM; } @@ -58,28 +76,41 @@ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* modifier_event [ukhpGH]{1,8} -modifier_bp [rwx] +modifier_bp [rwx]{1,3} %% -cpu-cycles|cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } -stalled-cycles-frontend|idle-cycles-frontend { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } -stalled-cycles-backend|idle-cycles-backend { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } -instructions { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } -cache-references { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } -cache-misses { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } -branch-instructions|branches { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } -branch-misses { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } -bus-cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } -ref-cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } -cpu-clock { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } -task-clock { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } -page-faults|faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } -minor-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } -major-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } -context-switches|cs { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } -cpu-migrations|migrations { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } -alignment-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } -emulation-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } + +%{ + { + int start_token; + + start_token = (int) parse_events_get_extra(yyscanner); + if (start_token) { + parse_events_set_extra(NULL, yyscanner); + return start_token; + } + } +%} + +cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } +stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } +stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } +instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } +cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } +cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } +branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } +branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } +bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } +ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } +cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } +task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } +page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } +minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } +major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } +context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } +cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } +alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } +emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | @@ -87,14 +118,14 @@ LLC|L2 | dTLB|d-tlb|Data-TLB | iTLB|i-tlb|Instruction-TLB | branch|branches|bpu|btb|bpc | -node { return str(PE_NAME_CACHE_TYPE); } +node { return str(yyscanner, PE_NAME_CACHE_TYPE); } load|loads|read | store|stores|write | prefetch|prefetches | speculative-read|speculative-load | refs|Reference|ops|access | -misses|miss { return str(PE_NAME_CACHE_OP_RESULT); } +misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } /* * These are event config hardcoded term names to be specified @@ -102,38 +133,39 @@ misses|miss { return str(PE_NAME_CACHE_OP_RESULT); } * so we can put them here directly. In case the we have a conflict * in future, this needs to go into '//' condition block. */ -config { return term(PARSE_EVENTS__TERM_TYPE_CONFIG); } -config1 { return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); } -config2 { return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); } -name { return term(PARSE_EVENTS__TERM_TYPE_NAME); } -period { return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } -branch_type { return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } +config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } +config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } +config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } +name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } +period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } +branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } mem: { BEGIN(mem); return PE_PREFIX_MEM; } -r{num_raw_hex} { return raw(); } -{num_dec} { return value(10); } -{num_hex} { return value(16); } +r{num_raw_hex} { return raw(yyscanner); } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } -{modifier_event} { return str(PE_MODIFIER_EVENT); } -{name} { return str(PE_NAME); } +{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } +{name} { return str(yyscanner, PE_NAME); } "/" { return '/'; } - { return '-'; } , { return ','; } : { return ':'; } = { return '='; } +\n { } <mem>{ -{modifier_bp} { return str(PE_MODIFIER_BP); } +{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } : { return ':'; } -{num_dec} { return value(10); } -{num_hex} { return value(16); } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } /* * We need to separate 'mem:' scanner part, in order to get specific * modifier bits parsed out. Otherwise we would need to handle PE_NAME * and we'd need to parse it manually. During the escape from <mem> * state we need to put the escaping char back, so we dont miss it. */ -. { unput(*parse_events_text); BEGIN(INITIAL); } +. { unput(*yytext); BEGIN(INITIAL); } /* * We destroy the scanner after reaching EOF, * but anyway just to be sure get back to INIT state. @@ -143,7 +175,7 @@ r{num_raw_hex} { return raw(); } %% -int parse_events_wrap(void) +int parse_events_wrap(void *scanner __used) { return 1; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 362cc59332a..2bc5fbff2b5 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,7 +1,8 @@ - +%pure-parser %name-prefix "parse_events_" -%parse-param {struct list_head *list_all} -%parse-param {int *idx} +%parse-param {void *_data} +%parse-param {void *scanner} +%lex-param {void* scanner} %{ @@ -12,8 +13,9 @@ #include "types.h" #include "util.h" #include "parse-events.h" +#include "parse-events-bison.h" -extern int parse_events_lex (void); +extern int parse_events_lex (YYSTYPE* lvalp, void* scanner); #define ABORT_ON(val) \ do { \ @@ -23,14 +25,16 @@ do { \ %} -%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM +%token PE_START_EVENTS PE_START_TERMS +%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM %token PE_NAME %token PE_MODIFIER_EVENT PE_MODIFIER_BP %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW %token PE_ERROR %type <num> PE_VALUE -%type <num> PE_VALUE_SYM +%type <num> PE_VALUE_SYM_HW +%type <num> PE_VALUE_SYM_SW %type <num> PE_RAW %type <num> PE_TERM %type <str> PE_NAME @@ -38,6 +42,7 @@ do { \ %type <str> PE_NAME_CACHE_OP_RESULT %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP +%type <num> value_sym %type <head> event_config %type <term> event_term %type <head> event_pmu @@ -58,24 +63,33 @@ do { \ } %% +start: +PE_START_EVENTS events +| +PE_START_TERMS terms + events: events ',' event | event event: event_def PE_MODIFIER_EVENT { + struct parse_events_data__events *data = _data; + /* * Apply modifier on all events added by single event definition * (there could be more events added for multiple tracepoint * definitions via '*?'. */ ABORT_ON(parse_events_modifier($1, $2)); - parse_events_update_lists($1, list_all); + parse_events_update_lists($1, &data->list); } | event_def { - parse_events_update_lists($1, list_all); + struct parse_events_data__events *data = _data; + + parse_events_update_lists($1, &data->list); } event_def: event_pmu | @@ -89,104 +103,131 @@ event_def: event_pmu | event_pmu: PE_NAME '/' event_config '/' { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_pmu(&list, idx, $1, $3)); + ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3)); parse_events__free_terms($3); $$ = list; } +value_sym: +PE_VALUE_SYM_HW +| +PE_VALUE_SYM_SW + event_legacy_symbol: -PE_VALUE_SYM '/' event_config '/' +value_sym '/' event_config '/' { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, idx, type, config, $3)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, + type, config, $3)); parse_events__free_terms($3); $$ = list; } | -PE_VALUE_SYM sep_slash_dc +value_sym sep_slash_dc { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, idx, type, config, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, + type, config, NULL)); $$ = list; } event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, $5)); + ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5)); $$ = list; } | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, NULL)); + ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL)); $$ = list; } | PE_NAME_CACHE_TYPE { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_cache(&list, idx, $1, NULL, NULL)); + ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL)); $$ = list; } event_legacy_mem: PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, $4)); + ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + (void *) $2, $4)); $$ = list; } | PE_PREFIX_MEM PE_VALUE sep_dc { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, NULL)); + ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + (void *) $2, NULL)); $$ = list; } event_legacy_tracepoint: PE_NAME ':' PE_NAME { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_tracepoint(&list, idx, $1, $3)); + ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3)); $$ = list; } event_legacy_numeric: PE_VALUE ':' PE_VALUE { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_numeric(&list, idx, $1, $3, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, $1, $3, NULL)); $$ = list; } event_legacy_raw: PE_RAW { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_numeric(&list, idx, PERF_TYPE_RAW, $1, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, + PERF_TYPE_RAW, $1, NULL)); $$ = list; } +terms: event_config +{ + struct parse_events_data__terms *data = _data; + data->terms = $1; +} + event_config: event_config ',' event_term { @@ -267,8 +308,7 @@ sep_slash_dc: '/' | ':' | %% -void parse_events_error(struct list_head *list_all __used, - int *idx __used, +void parse_events_error(void *data __used, void *scanner __used, char const *msg __used) { } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index a119a537169..67715a42cd6 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -72,7 +72,7 @@ static int pmu_format(char *name, struct list_head *format) "%s/bus/event_source/devices/%s/format", sysfs, name); if (stat(path, &st) < 0) - return -1; + return 0; /* no error if format does not exist */ if (pmu_format_parse(path, format)) return -1; @@ -80,6 +80,114 @@ static int pmu_format(char *name, struct list_head *format) return 0; } +static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file) +{ + struct perf_pmu__alias *alias; + char buf[256]; + int ret; + + ret = fread(buf, 1, sizeof(buf), file); + if (ret == 0) + return -EINVAL; + buf[ret] = 0; + + alias = malloc(sizeof(*alias)); + if (!alias) + return -ENOMEM; + + INIT_LIST_HEAD(&alias->terms); + ret = parse_events_terms(&alias->terms, buf); + if (ret) { + free(alias); + return ret; + } + + alias->name = strdup(name); + list_add_tail(&alias->list, list); + return 0; +} + +/* + * Process all the sysfs attributes located under the directory + * specified in 'dir' parameter. + */ +static int pmu_aliases_parse(char *dir, struct list_head *head) +{ + struct dirent *evt_ent; + DIR *event_dir; + int ret = 0; + + event_dir = opendir(dir); + if (!event_dir) + return -EINVAL; + + while (!ret && (evt_ent = readdir(event_dir))) { + char path[PATH_MAX]; + char *name = evt_ent->d_name; + FILE *file; + + if (!strcmp(name, ".") || !strcmp(name, "..")) + continue; + + snprintf(path, PATH_MAX, "%s/%s", dir, name); + + ret = -EINVAL; + file = fopen(path, "r"); + if (!file) + break; + ret = perf_pmu__new_alias(head, name, file); + fclose(file); + } + + closedir(event_dir); + return ret; +} + +/* + * Reading the pmu event aliases definition, which should be located at: + * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes. + */ +static int pmu_aliases(char *name, struct list_head *head) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs; + + sysfs = sysfs_find_mountpoint(); + if (!sysfs) + return -1; + + snprintf(path, PATH_MAX, + "%s/bus/event_source/devices/%s/events", sysfs, name); + + if (stat(path, &st) < 0) + return -1; + + if (pmu_aliases_parse(path, head)) + return -1; + + return 0; +} + +static int pmu_alias_terms(struct perf_pmu__alias *alias, + struct list_head *terms) +{ + struct parse_events__term *term, *clone; + LIST_HEAD(list); + int ret; + + list_for_each_entry(term, &alias->terms, list) { + ret = parse_events__term_clone(&clone, term); + if (ret) { + parse_events__free_terms(&list); + return ret; + } + list_add_tail(&clone->list, &list); + } + list_splice(&list, terms); + return 0; +} + /* * Reading/parsing the default pmu type value, which should be * located at: @@ -118,6 +226,7 @@ static struct perf_pmu *pmu_lookup(char *name) { struct perf_pmu *pmu; LIST_HEAD(format); + LIST_HEAD(aliases); __u32 type; /* @@ -135,10 +244,15 @@ static struct perf_pmu *pmu_lookup(char *name) if (!pmu) return NULL; + pmu_aliases(name, &aliases); + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->aliases); list_splice(&format, &pmu->format); + list_splice(&aliases, &pmu->aliases); pmu->name = strdup(name); pmu->type = type; + list_add_tail(&pmu->list, &pmus); return pmu; } @@ -279,6 +393,59 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, return pmu_config(&pmu->format, attr, head_terms); } +static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu, + struct parse_events__term *term) +{ + struct perf_pmu__alias *alias; + char *name; + + if (parse_events__is_hardcoded_term(term)) + return NULL; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (term->val.num != 1) + return NULL; + if (pmu_find_format(&pmu->format, term->config)) + return NULL; + name = term->config; + } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + if (strcasecmp(term->config, "event")) + return NULL; + name = term->val.str; + } else { + return NULL; + } + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, name)) + return alias; + } + return NULL; +} + +/* + * Find alias in the terms list and replace it with the terms + * defined for the alias + */ +int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms) +{ + struct parse_events__term *term, *h; + struct perf_pmu__alias *alias; + int ret; + + list_for_each_entry_safe(term, h, head_terms, list) { + alias = pmu_find_alias(pmu, term); + if (!alias) + continue; + ret = pmu_alias_terms(alias, &term->list); + if (ret) + return ret; + list_del(&term->list); + free(term); + } + return 0; +} + int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits) { diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 68c0db965e1..535f2c5258a 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -19,17 +19,26 @@ struct perf_pmu__format { struct list_head list; }; +struct perf_pmu__alias { + char *name; + struct list_head terms; + struct list_head list; +}; + struct perf_pmu { char *name; __u32 type; struct list_head format; + struct list_head aliases; struct list_head list; }; struct perf_pmu *perf_pmu__find(char *name); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); - +int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms); +struct list_head *perf_pmu__alias(struct perf_pmu *pmu, + struct list_head *head_terms); int perf_pmu_wrap(void); void perf_pmu_error(struct list_head *list, char *name, char const *msg); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 4c1b3d72a1d..02dfa19a467 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -209,6 +209,10 @@ static void define_event_symbols(struct event_format *event, define_symbolic_values(args->symbol.symbols, ev_name, cur_field_name); break; + case PRINT_HEX: + define_event_symbols(event, ev_name, args->hex.field); + define_event_symbols(event, ev_name, args->hex.size); + break; case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: @@ -233,7 +237,8 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event_format *find_cache_event(int type) +static inline +struct event_format *find_cache_event(struct pevent *pevent, int type) { static char ev_name[256]; struct event_format *event; @@ -241,7 +246,7 @@ static inline struct event_format *find_cache_event(int type) if (events[type]) return events[type]; - events[type] = event = trace_find_event(type); + events[type] = event = pevent_find_event(pevent, type); if (!event) return NULL; @@ -252,7 +257,8 @@ static inline struct event_format *find_cache_event(int type) return event; } -static void perl_process_tracepoint(union perf_event *pevent __unused, +static void perl_process_tracepoint(union perf_event *perf_event __unused, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __unused, @@ -275,13 +281,13 @@ static void perl_process_tracepoint(union perf_event *pevent __unused, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - type = trace_parse_common_type(data); + type = trace_parse_common_type(pevent, data); - event = find_cache_event(type); + event = find_cache_event(pevent, type); if (!event) die("ug! no event found for type %d", type); - pid = trace_parse_common_pid(data); + pid = trace_parse_common_pid(pevent, data); sprintf(handler, "%s::%s", event->system, event->name); @@ -314,7 +320,8 @@ static void perl_process_tracepoint(union perf_event *pevent __unused, offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); } else { /* FIELD_IS_NUMERIC */ - val = read_size(data + field->offset, field->size); + val = read_size(pevent, data + field->offset, + field->size); if (field->flags & FIELD_IS_SIGNED) { XPUSHs(sv_2mortal(newSViv(val))); } else { @@ -368,14 +375,15 @@ static void perl_process_event_generic(union perf_event *pevent __unused, LEAVE; } -static void perl_process_event(union perf_event *pevent, +static void perl_process_event(union perf_event *event, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, struct thread *thread) { - perl_process_tracepoint(pevent, sample, evsel, machine, thread); - perl_process_event_generic(pevent, sample, evsel, machine, thread); + perl_process_tracepoint(event, pevent, sample, evsel, machine, thread); + perl_process_event_generic(event, sample, evsel, machine, thread); } static void run_start_sub(void) @@ -448,7 +456,7 @@ static int perl_stop_script(void) return 0; } -static int perl_generate_script(const char *outfile) +static int perl_generate_script(struct pevent *pevent, const char *outfile) { struct event_format *event = NULL; struct format_field *f; @@ -495,7 +503,7 @@ static int perl_generate_script(const char *outfile) fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); - while ((event = trace_find_next_event(event))) { + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index acb9795286c..ce4d1b0c386 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -166,6 +166,10 @@ static void define_event_symbols(struct event_format *event, define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name, cur_field_name); break; + case PRINT_HEX: + define_event_symbols(event, ev_name, args->hex.field); + define_event_symbols(event, ev_name, args->hex.size); + break; case PRINT_STRING: break; case PRINT_TYPE: @@ -190,7 +194,8 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event_format *find_cache_event(int type) +static inline +struct event_format *find_cache_event(struct pevent *pevent, int type) { static char ev_name[256]; struct event_format *event; @@ -198,7 +203,7 @@ static inline struct event_format *find_cache_event(int type) if (events[type]) return events[type]; - events[type] = event = trace_find_event(type); + events[type] = event = pevent_find_event(pevent, type); if (!event) return NULL; @@ -209,7 +214,8 @@ static inline struct event_format *find_cache_event(int type) return event; } -static void python_process_event(union perf_event *pevent __unused, +static void python_process_event(union perf_event *perf_event __unused, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel __unused, struct machine *machine __unused, @@ -233,13 +239,13 @@ static void python_process_event(union perf_event *pevent __unused, if (!t) Py_FatalError("couldn't create Python tuple"); - type = trace_parse_common_type(data); + type = trace_parse_common_type(pevent, data); - event = find_cache_event(type); + event = find_cache_event(pevent, type); if (!event) die("ug! no event found for type %d", type); - pid = trace_parse_common_pid(data); + pid = trace_parse_common_pid(pevent, data); sprintf(handler_name, "%s__%s", event->system, event->name); @@ -284,7 +290,8 @@ static void python_process_event(union perf_event *pevent __unused, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(data + field->offset, field->size); + val = read_size(pevent, data + field->offset, + field->size); if (field->flags & FIELD_IS_SIGNED) { if ((long long)val >= LONG_MIN && (long long)val <= LONG_MAX) @@ -438,7 +445,7 @@ out: return err; } -static int python_generate_script(const char *outfile) +static int python_generate_script(struct pevent *pevent, const char *outfile) { struct event_format *event = NULL; struct format_field *f; @@ -487,7 +494,7 @@ static int python_generate_script(const char *outfile) fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint \"in trace_end\"\n\n"); - while ((event = trace_find_next_event(event))) { + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 56142d0fb8d..8e485592ca2 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,6 +14,7 @@ #include "sort.h" #include "util.h" #include "cpumap.h" +#include "event-parse.h" static int perf_session__open(struct perf_session *self, bool force) { @@ -289,7 +290,6 @@ struct branch_info *machine__resolve_bstack(struct machine *self, } int machine__resolve_callchain(struct machine *self, - struct perf_evsel *evsel __used, struct thread *thread, struct ip_callchain *chain, struct symbol **parent) @@ -1449,7 +1449,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) ret += hists__fprintf_nr_events(&session->hists, fp); list_for_each_entry(pos, &session->evlist->entries, node) { - ret += fprintf(fp, "%s stats:\n", event_name(pos)); + ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); ret += hists__fprintf_nr_events(&pos->hists, fp); } @@ -1490,8 +1490,8 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, } void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct perf_evsel *evsel, - int print_sym, int print_dso, int print_symoffset) + struct machine *machine, int print_sym, + int print_dso, int print_symoffset) { struct addr_location al; struct callchain_cursor_node *node; @@ -1505,7 +1505,7 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, if (symbol_conf.use_callchain && sample->callchain) { - if (machine__resolve_callchain(machine, evsel, al.thread, + if (machine__resolve_callchain(machine, al.thread, sample->callchain, NULL) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); @@ -1611,3 +1611,58 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp, perf_header__fprintf_info(session, fp, full); fprintf(fp, "# ========\n#\n"); } + + +int __perf_session__set_tracepoints_handlers(struct perf_session *session, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs) +{ + struct perf_evlist *evlist = session->evlist; + struct event_format *format; + struct perf_evsel *evsel; + char *tracepoint, *name; + size_t i; + int err; + + for (i = 0; i < nr_assocs; i++) { + err = -ENOMEM; + tracepoint = strdup(assocs[i].name); + if (tracepoint == NULL) + goto out; + + err = -ENOENT; + name = strchr(tracepoint, ':'); + if (name == NULL) + goto out_free; + + *name++ = '\0'; + format = pevent_find_event_by_name(session->pevent, + tracepoint, name); + if (format == NULL) { + /* + * Adding a handler for an event not in the session, + * just ignore it. + */ + goto next; + } + + evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id); + if (evsel == NULL) + goto next; + + err = -EEXIST; + if (evsel->handler.func != NULL) + goto out_free; + evsel->handler.func = assocs[i].handler; +next: + free(tracepoint); + } + + err = 0; +out: + return err; + +out_free: + free(tracepoint); + goto out; +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 0c702e3f0a3..7c435bde6eb 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -33,6 +33,7 @@ struct perf_session { struct machine host_machine; struct rb_root machines; struct perf_evlist *evlist; + struct pevent *pevent; /* * FIXME: Need to split this up further, we need global * stats + per event stats. 'perf diff' also needs @@ -151,11 +152,20 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct perf_evsel *evsel, - int print_sym, int print_dso, int print_symoffset); + struct machine *machine, int print_sym, + int print_dso, int print_symoffset); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); + +struct perf_evsel_str_handler; + +int __perf_session__set_tracepoints_handlers(struct perf_session *session, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs); + +#define perf_session__set_tracepoints_handlers(session, array) \ + __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index a27237430c5..0f5a0a496bc 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -241,6 +241,54 @@ struct sort_entry sort_sym = { .se_width_idx = HISTC_SYMBOL, }; +/* --sort srcline */ + +static int64_t +sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return (int64_t)(right->ip - left->ip); +} + +static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width __used) +{ + FILE *fp; + char cmd[PATH_MAX + 2], *path = self->srcline, *nl; + size_t line_len; + + if (path != NULL) + goto out_path; + + snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64, + self->ms.map->dso->long_name, self->ip); + fp = popen(cmd, "r"); + if (!fp) + goto out_ip; + + if (getline(&path, &line_len, fp) < 0 || !line_len) + goto out_ip; + fclose(fp); + self->srcline = strdup(path); + if (self->srcline == NULL) + goto out_ip; + + nl = strchr(self->srcline, '\n'); + if (nl != NULL) + *nl = '\0'; + path = self->srcline; +out_path: + return repsep_snprintf(bf, size, "%s", path); +out_ip: + return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip); +} + +struct sort_entry sort_srcline = { + .se_header = "Source:Line", + .se_cmp = sort__srcline_cmp, + .se_snprintf = hist_entry__srcline_snprintf, + .se_width_idx = HISTC_SRCLINE, +}; + /* --sort parent */ static int64_t @@ -439,6 +487,7 @@ static struct sort_dimension sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), + DIM(SORT_SRCLINE, "srcline", sort_srcline), }; int sort_dimension__add(const char *tok) diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 472aa5a63a5..e724b26acd5 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -71,6 +71,7 @@ struct hist_entry { char level; bool used; u8 filtered; + char *srcline; struct symbol *parent; union { unsigned long position; @@ -93,6 +94,7 @@ enum sort_type { SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, + SORT_SRCLINE, }; /* diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index d5836382ff2..199bc4d8905 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -313,3 +313,25 @@ int strtailcmp(const char *s1, const char *s2) return 0; } +/** + * rtrim - Removes trailing whitespace from @s. + * @s: The string to be stripped. + * + * Note that the first trailing whitespace is replaced with a %NUL-terminator + * in the given string @s. Returns @s. + */ +char *rtrim(char *s) +{ + size_t size = strlen(s); + char *end; + + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return s; +} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3e2e5ea0f03..50958bbeb26 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1478,14 +1478,31 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) goto out; } - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".note.gnu.build-id", NULL); - if (sec == NULL) { + /* + * Check following sections for notes: + * '.note.gnu.build-id' + * '.notes' + * '.note' (VDSO specific) + */ + do { + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note.gnu.build-id", NULL); + if (sec) + break; + sec = elf_section_by_name(elf, &ehdr, &shdr, ".notes", NULL); - if (sec == NULL) - goto out; - } + if (sec) + break; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note", NULL); + if (sec) + break; + + return err; + + } while (0); data = elf_getdata(sec, NULL); if (data == NULL) @@ -1590,11 +1607,62 @@ out: return err; } +static int filename__read_debuglink(const char *filename, + char *debuglink, size_t size) +{ + int fd, err = -1; + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + Elf_Kind ek; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_close; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_err("%s: cannot get elf header.\n", __func__); + goto out_close; + } + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".gnu_debuglink", NULL); + if (sec == NULL) + goto out_close; + + data = elf_getdata(sec, NULL); + if (data == NULL) + goto out_close; + + /* the start of this section is a zero-terminated string */ + strncpy(debuglink, data->d_buf, size); + + elf_end(elf); + +out_close: + close(fd); +out: + return err; +} + char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { [SYMTAB__KALLSYMS] = 'k', [SYMTAB__JAVA_JIT] = 'j', + [SYMTAB__DEBUGLINK] = 'l', [SYMTAB__BUILD_ID_CACHE] = 'B', [SYMTAB__FEDORA_DEBUGINFO] = 'f', [SYMTAB__UBUNTU_DEBUGINFO] = 'u', @@ -1662,10 +1730,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) */ want_symtab = 1; restart: - for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE; + for (dso->symtab_type = SYMTAB__DEBUGLINK; dso->symtab_type != SYMTAB__NOT_FOUND; dso->symtab_type++) { switch (dso->symtab_type) { + case SYMTAB__DEBUGLINK: { + char *debuglink; + strncpy(name, dso->long_name, size); + debuglink = name + dso->long_name_len; + while (debuglink != name && *debuglink != '/') + debuglink--; + if (*debuglink == '/') + debuglink++; + filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - name)); + } + break; case SYMTAB__BUILD_ID_CACHE: /* skip the locally configured cache if a symfs is given */ if (symbol_conf.symfs[0] || diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index af0752b1aca..a884b99017f 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -257,6 +257,7 @@ enum symtab_type { SYMTAB__KALLSYMS = 0, SYMTAB__GUEST_KALLSYMS, SYMTAB__JAVA_JIT, + SYMTAB__DEBUGLINK, SYMTAB__BUILD_ID_CACHE, SYMTAB__FEDORA_DEBUGINFO, SYMTAB__UBUNTU_DEBUGINFO, diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index abe0e8e9506..7eeebcee291 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -65,7 +65,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) top->freq ? "Hz" : ""); } - ret += SNPRINTF(bf + ret, size - ret, "%s", event_name(top->sym_evsel)); + ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel)); ret += SNPRINTF(bf + ret, size - ret, "], "); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 5dd3b5ec841..0715c843c2e 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -32,29 +32,25 @@ int header_page_size_size; int header_page_ts_size; int header_page_data_offset; -struct pevent *perf_pevent; -static struct pevent *pevent; - bool latency_format; -int read_trace_init(int file_bigendian, int host_bigendian) +struct pevent *read_trace_init(int file_bigendian, int host_bigendian) { - if (pevent) - return 0; - - perf_pevent = pevent_alloc(); - pevent = perf_pevent; + struct pevent *pevent = pevent_alloc(); - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, file_bigendian); - pevent_set_host_bigendian(pevent, host_bigendian); + if (pevent != NULL) { + pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); + pevent_set_file_bigendian(pevent, file_bigendian); + pevent_set_host_bigendian(pevent, host_bigendian); + } - return 0; + return pevent; } static int get_common_field(struct scripting_context *context, int *offset, int *size, const char *type) { + struct pevent *pevent = context->pevent; struct event_format *event; struct format_field *field; @@ -150,7 +146,7 @@ void *raw_field_ptr(struct event_format *event, const char *name, void *data) return data + field->offset; } -int trace_parse_common_type(void *data) +int trace_parse_common_type(struct pevent *pevent, void *data) { struct pevent_record record; @@ -158,7 +154,7 @@ int trace_parse_common_type(void *data) return pevent_data_type(pevent, &record); } -int trace_parse_common_pid(void *data) +int trace_parse_common_pid(struct pevent *pevent, void *data) { struct pevent_record record; @@ -166,27 +162,21 @@ int trace_parse_common_pid(void *data) return pevent_data_pid(pevent, &record); } -unsigned long long read_size(void *ptr, int size) +unsigned long long read_size(struct pevent *pevent, void *ptr, int size) { return pevent_read_number(pevent, ptr, size); } -struct event_format *trace_find_event(int type) -{ - return pevent_find_event(pevent, type); -} - - -void print_trace_event(int cpu, void *data, int size) +void print_trace_event(struct pevent *pevent, int cpu, void *data, int size) { struct event_format *event; struct pevent_record record; struct trace_seq s; int type; - type = trace_parse_common_type(data); + type = trace_parse_common_type(pevent, data); - event = trace_find_event(type); + event = pevent_find_event(pevent, type); if (!event) { warning("ug! no event found for type %d", type); return; @@ -202,8 +192,8 @@ void print_trace_event(int cpu, void *data, int size) trace_seq_do_printf(&s); } -void print_event(int cpu, void *data, int size, unsigned long long nsecs, - char *comm) +void print_event(struct pevent *pevent, int cpu, void *data, int size, + unsigned long long nsecs, char *comm) { struct pevent_record record; struct trace_seq s; @@ -226,7 +216,8 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs, printf("\n"); } -void parse_proc_kallsyms(char *file, unsigned int size __unused) +void parse_proc_kallsyms(struct pevent *pevent, + char *file, unsigned int size __unused) { unsigned long long addr; char *func; @@ -257,7 +248,8 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused) } } -void parse_ftrace_printk(char *file, unsigned int size __unused) +void parse_ftrace_printk(struct pevent *pevent, + char *file, unsigned int size __unused) { unsigned long long addr; char *printk; @@ -281,17 +273,19 @@ void parse_ftrace_printk(char *file, unsigned int size __unused) } } -int parse_ftrace_file(char *buf, unsigned long size) +int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) { return pevent_parse_event(pevent, buf, size, "ftrace"); } -int parse_event_file(char *buf, unsigned long size, char *sys) +int parse_event_file(struct pevent *pevent, + char *buf, unsigned long size, char *sys) { return pevent_parse_event(pevent, buf, size, sys); } -struct event_format *trace_find_next_event(struct event_format *event) +struct event_format *trace_find_next_event(struct pevent *pevent, + struct event_format *event) { static int idx; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index f097e0dd6c5..719ed74a856 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -114,20 +114,20 @@ static void skip(int size) }; } -static unsigned int read4(void) +static unsigned int read4(struct pevent *pevent) { unsigned int data; read_or_die(&data, 4); - return __data2host4(perf_pevent, data); + return __data2host4(pevent, data); } -static unsigned long long read8(void) +static unsigned long long read8(struct pevent *pevent) { unsigned long long data; read_or_die(&data, 8); - return __data2host8(perf_pevent, data); + return __data2host8(pevent, data); } static char *read_string(void) @@ -168,12 +168,12 @@ static char *read_string(void) return str; } -static void read_proc_kallsyms(void) +static void read_proc_kallsyms(struct pevent *pevent) { unsigned int size; char *buf; - size = read4(); + size = read4(pevent); if (!size) return; @@ -181,29 +181,29 @@ static void read_proc_kallsyms(void) read_or_die(buf, size); buf[size] = '\0'; - parse_proc_kallsyms(buf, size); + parse_proc_kallsyms(pevent, buf, size); free(buf); } -static void read_ftrace_printk(void) +static void read_ftrace_printk(struct pevent *pevent) { unsigned int size; char *buf; - size = read4(); + size = read4(pevent); if (!size) return; buf = malloc_or_die(size); read_or_die(buf, size); - parse_ftrace_printk(buf, size); + parse_ftrace_printk(pevent, buf, size); free(buf); } -static void read_header_files(void) +static void read_header_files(struct pevent *pevent) { unsigned long long size; char *header_event; @@ -214,7 +214,7 @@ static void read_header_files(void) if (memcmp(buf, "header_page", 12) != 0) die("did not read header page"); - size = read8(); + size = read8(pevent); skip(size); /* @@ -227,47 +227,48 @@ static void read_header_files(void) if (memcmp(buf, "header_event", 13) != 0) die("did not read header event"); - size = read8(); + size = read8(pevent); header_event = malloc_or_die(size); read_or_die(header_event, size); free(header_event); } -static void read_ftrace_file(unsigned long long size) +static void read_ftrace_file(struct pevent *pevent, unsigned long long size) { char *buf; buf = malloc_or_die(size); read_or_die(buf, size); - parse_ftrace_file(buf, size); + parse_ftrace_file(pevent, buf, size); free(buf); } -static void read_event_file(char *sys, unsigned long long size) +static void read_event_file(struct pevent *pevent, char *sys, + unsigned long long size) { char *buf; buf = malloc_or_die(size); read_or_die(buf, size); - parse_event_file(buf, size, sys); + parse_event_file(pevent, buf, size, sys); free(buf); } -static void read_ftrace_files(void) +static void read_ftrace_files(struct pevent *pevent) { unsigned long long size; int count; int i; - count = read4(); + count = read4(pevent); for (i = 0; i < count; i++) { - size = read8(); - read_ftrace_file(size); + size = read8(pevent); + read_ftrace_file(pevent, size); } } -static void read_event_files(void) +static void read_event_files(struct pevent *pevent) { unsigned long long size; char *sys; @@ -275,15 +276,15 @@ static void read_event_files(void) int count; int i,x; - systems = read4(); + systems = read4(pevent); for (i = 0; i < systems; i++) { sys = read_string(); - count = read4(); + count = read4(pevent); for (x=0; x < count; x++) { - size = read8(); - read_event_file(sys, size); + size = read8(pevent); + read_event_file(pevent, sys, size); } } } @@ -377,7 +378,7 @@ static int calc_index(void *ptr, int cpu) return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page; } -struct pevent_record *trace_peek_data(int cpu) +struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu) { struct pevent_record *data; void *page = cpu_data[cpu].page; @@ -399,15 +400,15 @@ struct pevent_record *trace_peek_data(int cpu) /* FIXME: handle header page */ if (header_page_ts_size != 8) die("expected a long long type for timestamp"); - cpu_data[cpu].timestamp = data2host8(perf_pevent, ptr); + cpu_data[cpu].timestamp = data2host8(pevent, ptr); ptr += 8; switch (header_page_size_size) { case 4: - cpu_data[cpu].page_size = data2host4(perf_pevent, ptr); + cpu_data[cpu].page_size = data2host4(pevent, ptr); ptr += 4; break; case 8: - cpu_data[cpu].page_size = data2host8(perf_pevent, ptr); + cpu_data[cpu].page_size = data2host8(pevent, ptr); ptr += 8; break; default: @@ -421,10 +422,10 @@ read_again: if (idx >= cpu_data[cpu].page_size) { get_next_page(cpu); - return trace_peek_data(cpu); + return trace_peek_data(pevent, cpu); } - type_len_ts = data2host4(perf_pevent, ptr); + type_len_ts = data2host4(pevent, ptr); ptr += 4; type_len = type_len4host(type_len_ts); @@ -434,14 +435,14 @@ read_again: case RINGBUF_TYPE_PADDING: if (!delta) die("error, hit unexpected end of page"); - length = data2host4(perf_pevent, ptr); + length = data2host4(pevent, ptr); ptr += 4; length *= 4; ptr += length; goto read_again; case RINGBUF_TYPE_TIME_EXTEND: - extend = data2host4(perf_pevent, ptr); + extend = data2host4(pevent, ptr); ptr += 4; extend <<= TS_SHIFT; extend += delta; @@ -452,7 +453,7 @@ read_again: ptr += 12; break; case 0: - length = data2host4(perf_pevent, ptr); + length = data2host4(pevent, ptr); ptr += 4; die("here! length=%d", length); break; @@ -477,17 +478,17 @@ read_again: return data; } -struct pevent_record *trace_read_data(int cpu) +struct pevent_record *trace_read_data(struct pevent *pevent, int cpu) { struct pevent_record *data; - data = trace_peek_data(cpu); + data = trace_peek_data(pevent, cpu); cpu_data[cpu].next = NULL; return data; } -ssize_t trace_report(int fd, bool __repipe) +ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) { char buf[BUFSIZ]; char test[] = { 23, 8, 68 }; @@ -519,30 +520,32 @@ ssize_t trace_report(int fd, bool __repipe) file_bigendian = buf[0]; host_bigendian = bigendian(); - read_trace_init(file_bigendian, host_bigendian); + *ppevent = read_trace_init(file_bigendian, host_bigendian); + if (*ppevent == NULL) + die("read_trace_init failed"); read_or_die(buf, 1); long_size = buf[0]; - page_size = read4(); + page_size = read4(*ppevent); - read_header_files(); + read_header_files(*ppevent); - read_ftrace_files(); - read_event_files(); - read_proc_kallsyms(); - read_ftrace_printk(); + read_ftrace_files(*ppevent); + read_event_files(*ppevent); + read_proc_kallsyms(*ppevent); + read_ftrace_printk(*ppevent); size = calc_data_size - 1; calc_data_size = 0; repipe = false; if (show_funcs) { - pevent_print_funcs(perf_pevent); + pevent_print_funcs(*ppevent); return size; } if (show_printk) { - pevent_print_printk(perf_pevent); + pevent_print_printk(*ppevent); return size; } diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 18ae6c1831d..474aa7a7df4 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -36,6 +36,7 @@ static int stop_script_unsupported(void) } static void process_event_unsupported(union perf_event *event __unused, + struct pevent *pevent __unused, struct perf_sample *sample __unused, struct perf_evsel *evsel __unused, struct machine *machine __unused, @@ -61,7 +62,8 @@ static int python_start_script_unsupported(const char *script __unused, return -1; } -static int python_generate_script_unsupported(const char *outfile __unused) +static int python_generate_script_unsupported(struct pevent *pevent __unused, + const char *outfile __unused) { print_python_unsupported_msg(); @@ -122,7 +124,8 @@ static int perl_start_script_unsupported(const char *script __unused, return -1; } -static int perl_generate_script_unsupported(const char *outfile __unused) +static int perl_generate_script_unsupported(struct pevent *pevent __unused, + const char *outfile __unused) { print_perl_unsupported_msg(); diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 639852ac111..8fef1d6687b 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -8,6 +8,7 @@ struct machine; struct perf_sample; union perf_event; +struct perf_tool; struct thread; extern int header_page_size_size; @@ -29,35 +30,36 @@ enum { int bigendian(void); -int read_trace_init(int file_bigendian, int host_bigendian); -void print_trace_event(int cpu, void *data, int size); +struct pevent *read_trace_init(int file_bigendian, int host_bigendian); +void print_trace_event(struct pevent *pevent, int cpu, void *data, int size); -void print_event(int cpu, void *data, int size, unsigned long long nsecs, - char *comm); +void print_event(struct pevent *pevent, int cpu, void *data, int size, + unsigned long long nsecs, char *comm); -int parse_ftrace_file(char *buf, unsigned long size); -int parse_event_file(char *buf, unsigned long size, char *sys); +int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); +int parse_event_file(struct pevent *pevent, + char *buf, unsigned long size, char *sys); -struct pevent_record *trace_peek_data(int cpu); -struct event_format *trace_find_event(int type); +struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu); unsigned long long raw_field_value(struct event_format *event, const char *name, void *data); void *raw_field_ptr(struct event_format *event, const char *name, void *data); -void parse_proc_kallsyms(char *file, unsigned int size __unused); -void parse_ftrace_printk(char *file, unsigned int size __unused); +void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); +void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); -ssize_t trace_report(int fd, bool repipe); +ssize_t trace_report(int fd, struct pevent **pevent, bool repipe); -int trace_parse_common_type(void *data); -int trace_parse_common_pid(void *data); +int trace_parse_common_type(struct pevent *pevent, void *data); +int trace_parse_common_pid(struct pevent *pevent, void *data); -struct event_format *trace_find_next_event(struct event_format *event); -unsigned long long read_size(void *ptr, int size); +struct event_format *trace_find_next_event(struct pevent *pevent, + struct event_format *event); +unsigned long long read_size(struct pevent *pevent, void *ptr, int size); unsigned long long eval_flag(const char *flag); -struct pevent_record *trace_read_data(int cpu); +struct pevent_record *trace_read_data(struct pevent *pevent, int cpu); int read_tracing_data(int fd, struct list_head *pattrs); struct tracing_data { @@ -77,11 +79,12 @@ struct scripting_ops { int (*start_script) (const char *script, int argc, const char **argv); int (*stop_script) (void); void (*process_event) (union perf_event *event, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, struct thread *thread); - int (*generate_script) (const char *outfile); + int (*generate_script) (struct pevent *pevent, const char *outfile); }; int script_spec_register(const char *spec, struct scripting_ops *ops); @@ -90,6 +93,7 @@ void setup_perl_scripting(void); void setup_python_scripting(void); struct scripting_context { + struct pevent *pevent; void *event_data; }; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 2daaedb83d8..b13c7331eaf 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -264,4 +264,6 @@ bool is_power_of_2(unsigned long n) size_t hex_width(u64 v); +char *rtrim(char *s); + #endif |