diff options
326 files changed, 5658 insertions, 2989 deletions
diff --git a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt index 46f5c791ea0d..0f2f920e8734 100644 --- a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt +++ b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt @@ -159,6 +159,8 @@ clock which they consume. mixer 343 hdmi 344 g2d 345 + mdma0 346 + smmu_mdma0 347 [Clock Muxes] diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt index 89490beb3c0b..58e49042fc20 100644 --- a/Documentation/networking/batman-adv.txt +++ b/Documentation/networking/batman-adv.txt @@ -66,11 +66,10 @@ All mesh wide settings can be found in batman's own interface folder: # ls /sys/class/net/bat0/mesh/ -# aggregated_ogms gw_bandwidth log_level -# ap_isolation gw_mode orig_interval -# bonding gw_sel_class routing_algo -# bridge_loop_avoidance hop_penalty fragmentation - +#aggregated_ogms distributed_arp_table gw_sel_class orig_interval +#ap_isolation fragmentation hop_penalty routing_algo +#bonding gw_bandwidth isolation_mark vlan0 +#bridge_loop_avoidance gw_mode log_level There is a special folder for debugging information: diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 7373115407e4..c97932c88ea3 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -26,12 +26,36 @@ ip_no_pmtu_disc - INTEGER discarded. Outgoing frames are handled the same as in mode 1, implicitly setting IP_PMTUDISC_DONT on every created socket. - Possible values: 0-2 + Mode 3 is a hardend pmtu discover mode. The kernel will only + accept fragmentation-needed errors if the underlying protocol + can verify them besides a plain socket lookup. Current + protocols for which pmtu events will be honored are TCP, SCTP + and DCCP as they verify e.g. the sequence number or the + association. This mode should not be enabled globally but is + only intended to secure e.g. name servers in namespaces where + TCP path mtu must still work but path MTU information of other + protocols should be discarded. If enabled globally this mode + could break other protocols. + + Possible values: 0-3 Default: FALSE min_pmtu - INTEGER default 552 - minimum discovered Path MTU +ip_forward_use_pmtu - BOOLEAN + By default we don't trust protocol path MTUs while forwarding + because they could be easily forged and can lead to unwanted + fragmentation by the router. + You only need to enable this if you have user-space software + which tries to discover path mtus by itself and depends on the + kernel honoring this information. This is normally not the + case. + Default: 0 (disabled) + Possible values: + 0 - disabled + 1 - enabled + route/max_size - INTEGER Maximum number of routes allowed in the kernel. Increase this when using large numbers of interfaces and/or routes. diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 723bf3d33a6e..91ffe1d9e8ca 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -98,6 +98,11 @@ by the kernel. The destruction of the socket and all associated resources is done by a simple call to close(fd). +Similarly as without PACKET_MMAP, it is possible to use one socket +for capture and transmission. This can be done by mapping the +allocated RX and TX buffer ring with a single mmap() call. +See "Mapping and use of the circular buffer (ring)". + Next I will describe PACKET_MMAP settings and its constraints, also the mapping of the circular buffer in the user process and the use of this buffer. @@ -414,6 +419,19 @@ tp_block_size/tp_frame_size frames there will be a gap between the frames. This is because a frame cannot be spawn across two blocks. +To use one socket for capture and transmission, the mapping of both the +RX and TX buffer ring has to be done with one call to mmap: + + ... + setsockopt(fd, SOL_PACKET, PACKET_RX_RING, &foo, sizeof(foo)); + setsockopt(fd, SOL_PACKET, PACKET_TX_RING, &bar, sizeof(bar)); + ... + rx_ring = mmap(0, size * 2, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); + tx_ring = rx_ring + size; + +RX must be the first as the kernel maps the TX ring memory right +after the RX one. + At the beginning of each frame there is an status field (see struct tpacket_hdr). If this field is 0 means that the frame is ready to be used for the kernel, If not, there is a frame the user can read diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt index 75e4fd708ccb..5a61a240a652 100644 --- a/Documentation/networking/pktgen.txt +++ b/Documentation/networking/pktgen.txt @@ -108,7 +108,9 @@ Examples: MPLS_RND, VID_RND, SVID_RND QUEUE_MAP_RND # queue map random QUEUE_MAP_CPU # queue map mirrors smp_processor_id() + IPSEC # Make IPsec encapsulation for packet + pgset spi SPI_VALUE Set specific SA used to transform packet. pgset "udp_src_min 9" set UDP source port min, If < udp_src_max, then cycle through the port range. @@ -177,6 +179,18 @@ Note when adding devices to a specific CPU there good idea to also assign /proc/irq/XX/smp_affinity so the TX-interrupts gets bound to the same CPU. as this reduces cache bouncing when freeing skb's. +Enable IPsec +============ +Default IPsec transformation with ESP encapsulation plus Transport mode +could be enabled by simply setting: + +pgset "flag IPSEC" +pgset "flows 1" + +To avoid breaking existing testbed scripts for using AH type and tunnel mode, +user could use "pgset spi SPI_VALUE" to specify which formal of transformation +to employ. + Current commands and configuration options ========================================== @@ -225,6 +239,7 @@ flag UDPDST_RND MACSRC_RND MACDST_RND + IPSEC dst_min dst_max diff --git a/MAINTAINERS b/MAINTAINERS index e11d4952bb26..b358a3f0cacd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1368,6 +1368,9 @@ T: git git://git.xilinx.com/linux-xlnx.git S: Supported F: arch/arm/mach-zynq/ F: drivers/cpuidle/cpuidle-zynq.c +N: zynq +N: xilinx +F: drivers/clocksource/cadence_ttc_timer.c ARM SMMU DRIVER M: Will Deacon <will.deacon@arm.com> @@ -2815,8 +2818,10 @@ F: include/uapi/drm/ INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets) M: Daniel Vetter <daniel.vetter@ffwll.ch> +M: Jani Nikula <jani.nikula@linux.intel.com> L: intel-gfx@lists.freedesktop.org L: dri-devel@lists.freedesktop.org +Q: http://patchwork.freedesktop.org/project/intel-gfx/ T: git git://people.freedesktop.org/~danvet/drm-intel S: Supported F: drivers/gpu/drm/i915/ @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = One Giant Leap for Frogkind # *DOCUMENTATION* diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 93e6ca919620..cf29d84fd9c2 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -11,6 +11,7 @@ generic-y += fcntl.h generic-y += fb.h generic-y += ftrace.h generic-y += hardirq.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -47,4 +48,3 @@ generic-y += user.h generic-y += vga.h generic-y += xor.h generic-y += preempt.h -generic-y += hash.h diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index 9db5047812f3..177becde7a26 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -559,7 +559,7 @@ compatible = "arm,pl330", "arm,primecell"; reg = <0x10800000 0x1000>; interrupts = <0 33 0>; - clocks = <&clock 271>; + clocks = <&clock 346>; clock-names = "apb_pclk"; #dma-cells = <1>; #dma-channels = <8>; diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped index 64205d453260..71e5fc7cfb18 100644 --- a/arch/arm/crypto/aesbs-core.S_shipped +++ b/arch/arm/crypto/aesbs-core.S_shipped @@ -58,7 +58,7 @@ # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_ARCH__ 7 #endif #ifdef __thumb__ diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl index f3d96d932573..be068db960ee 100644 --- a/arch/arm/crypto/bsaes-armv7.pl +++ b/arch/arm/crypto/bsaes-armv7.pl @@ -701,7 +701,7 @@ $code.=<<___; # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_ARCH__ 7 #endif #ifdef __thumb__ diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 3c597c222ef2..fbeb39c869e9 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -329,7 +329,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t); */ #define ioremap(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) #define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) -#define ioremap_cached(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED) +#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED) #define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC) #define iounmap __arm_iounmap diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 6976b03e5213..8756e4bcdba0 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -347,7 +347,8 @@ static inline __deprecated void *bus_to_virt(unsigned long x) #define ARCH_PFN_OFFSET PHYS_PFN_OFFSET #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) +#define virt_addr_valid(kaddr) (((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \ + && pfn_valid(__pa(kaddr) >> PAGE_SHIFT) ) #endif diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 75579a9d6f76..3759cacdd7f8 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -117,6 +117,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) return __set_phys_to_machine(pfn, mfn); } -#define xen_remap(cookie, size) ioremap_cached((cookie), (size)); +#define xen_remap(cookie, size) ioremap_cache((cookie), (size)); #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 7940241f0576..6eda3bf85c52 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -36,7 +36,13 @@ #include <asm/system_misc.h> #include <asm/opcodes.h> -static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" }; +static const char *handler[]= { + "prefetch abort", + "data abort", + "address exception", + "interrupt", + "undefined instruction", +}; void *vectors_page; diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c index 9ee78f7b4990..782f6c71fa0a 100644 --- a/arch/arm/mach-footbridge/dc21285-timer.c +++ b/arch/arm/mach-footbridge/dc21285-timer.c @@ -96,11 +96,12 @@ static struct irqaction footbridge_timer_irq = { void __init footbridge_timer_init(void) { struct clock_event_device *ce = &ckevt_dc21285; + unsigned rate = DIV_ROUND_CLOSEST(mem_fclk_21285, 16); - clocksource_register_hz(&cksrc_dc21285, (mem_fclk_21285 + 8) / 16); + clocksource_register_hz(&cksrc_dc21285, rate); setup_irq(ce->irq, &footbridge_timer_irq); ce->cpumask = cpumask_of(smp_processor_id()); - clockevents_config_and_register(ce, mem_fclk_21285, 0x4, 0xffffff); + clockevents_config_and_register(ce, rate, 0x4, 0xffffff); } diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index c18689123023..8ea87bd45c33 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -483,7 +483,7 @@ static struct platform_device lcdc0_device = { .id = 0, .dev = { .platform_data = &lcdc0_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -580,7 +580,7 @@ static struct platform_device hdmi_lcdc_device = { .id = 1, .dev = { .platform_data = &hdmi_lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index fe689b7fdc9e..bc40b853ffd3 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -334,7 +334,7 @@ static struct platform_device lcdc_device = { .resource = lcdc_resources, .dev = { .platform_data = &lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index af06753eb809..e721d2ccceae 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -409,7 +409,7 @@ static struct platform_device lcdc_device = { .resource = lcdc_resources, .dev = { .platform_data = &lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -499,7 +499,7 @@ static struct platform_device hdmi_lcdc_device = { .id = 1, .dev = { .platform_data = &hdmi_lcdc_info, - .coherent_dma_mask = ~0, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 6d5ba9afb16a..3387e60e4ea3 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -175,16 +175,16 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) unsigned long i; if (cache_is_vipt_nonaliasing()) { for (i = 0; i < (1 << compound_order(page)); i++) { - void *addr = kmap_atomic(page); + void *addr = kmap_atomic(page + i); __cpuc_flush_dcache_area(addr, PAGE_SIZE); kunmap_atomic(addr); } } else { for (i = 0; i < (1 << compound_order(page)); i++) { - void *addr = kmap_high_get(page); + void *addr = kmap_high_get(page + i); if (addr) { __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high(page); + kunmap_high(page + i); } } } diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index c5963b3e4624..406cbd3ebd58 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -5,6 +5,7 @@ header-y += arch-v32/ generic-y += clkdev.h generic-y += exec.h +generic-y += hash.h generic-y += kvm_para.h generic-y += linkage.h generic-y += module.h @@ -12,4 +13,3 @@ generic-y += trace_clock.h generic-y += vga.h generic-y += xor.h generic-y += preempt.h -generic-y += hash.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 469d223950ff..ae45d75a3187 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -15,6 +15,7 @@ generic-y += fb.h generic-y += fcntl.h generic-y += ftrace.h generic-y += hardirq.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -54,4 +55,3 @@ generic-y += ucontext.h generic-y += unaligned.h generic-y += xor.h generic-y += preempt.h -generic-y += hash.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 43eec338ff50..ca60945ddf30 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,7 +1,7 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += hash.h generic-y += trace_clock.h generic-y += syscalls.h generic-y += preempt.h -generic-y += hash.h diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index bc42f14c9c2e..199345207d82 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -1,6 +1,6 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += hash.h generic-y += trace_clock.h generic-y += preempt.h -generic-y += hash.h diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index f0e2784e7cca..2f9b751878ba 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -125,42 +125,38 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma void mark_rodata_ro(void); #endif -#ifdef CONFIG_PA8X00 -/* Only pa8800, pa8900 needs this */ - #include <asm/kmap_types.h> #define ARCH_HAS_KMAP -void kunmap_parisc(void *addr); - static inline void *kmap(struct page *page) { might_sleep(); + flush_dcache_page(page); return page_address(page); } static inline void kunmap(struct page *page) { - kunmap_parisc(page_address(page)); + flush_kernel_dcache_page_addr(page_address(page)); } static inline void *kmap_atomic(struct page *page) { pagefault_disable(); + flush_dcache_page(page); return page_address(page); } static inline void __kunmap_atomic(void *addr) { - kunmap_parisc(addr); + flush_kernel_dcache_page_addr(addr); pagefault_enable(); } #define kmap_atomic_prot(page, prot) kmap_atomic(page) #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) #define kmap_atomic_to_page(ptr) virt_to_page(ptr) -#endif #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index b7adb2ac049c..c53fc63149e8 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -28,9 +28,8 @@ struct page; void clear_page_asm(void *page); void copy_page_asm(void *to, void *from); -void clear_user_page(void *vto, unsigned long vaddr, struct page *pg); -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg); +#define clear_user_page(vto, vaddr, page) clear_page_asm(vto) +#define copy_user_page(vto, vfrom, vaddr, page) copy_page_asm(vto, vfrom) /* #define CONFIG_PARISC_TMPALIAS */ diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index c035673209f7..a72545554a31 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -388,41 +388,6 @@ void flush_kernel_dcache_page_addr(void *addr) } EXPORT_SYMBOL(flush_kernel_dcache_page_addr); -void clear_user_page(void *vto, unsigned long vaddr, struct page *page) -{ - clear_page_asm(vto); - if (!parisc_requires_coherency()) - flush_kernel_dcache_page_asm(vto); -} -EXPORT_SYMBOL(clear_user_page); - -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg) -{ - /* Copy using kernel mapping. No coherency is needed - (all in kmap/kunmap) on machines that don't support - non-equivalent aliasing. However, the `from' page - needs to be flushed before it can be accessed through - the kernel mapping. */ - preempt_disable(); - flush_dcache_page_asm(__pa(vfrom), vaddr); - preempt_enable(); - copy_page_asm(vto, vfrom); - if (!parisc_requires_coherency()) - flush_kernel_dcache_page_asm(vto); -} -EXPORT_SYMBOL(copy_user_page); - -#ifdef CONFIG_PA8X00 - -void kunmap_parisc(void *addr) -{ - if (parisc_requires_coherency()) - flush_kernel_dcache_page_addr(addr); -} -EXPORT_SYMBOL(kunmap_parisc); -#endif - void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) { unsigned long flags; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 1e1a03d2d19f..e9f312532526 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -135,7 +135,6 @@ config S390 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 if 32BIT select HAVE_VIRT_CPU_ACCOUNTING - select INIT_ALL_POSSIBLE select KTIME_SCALAR if 32BIT select MODULES_USE_ELF_RELA select OLD_SIGACTION diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index ac9bed8e103f..160779394096 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -31,6 +31,7 @@ extern void smp_yield(void); extern void smp_stop_cpu(void); extern void smp_cpu_set_polarization(int cpu, int val); extern int smp_cpu_get_polarization(int cpu); +extern void smp_fill_possible_mask(void); #else /* CONFIG_SMP */ @@ -50,6 +51,7 @@ static inline int smp_vcpu_scheduled(int cpu) { return 1; } static inline void smp_yield_cpu(int cpu) { } static inline void smp_yield(void) { } static inline void smp_stop_cpu(void) { } +static inline void smp_fill_possible_mask(void) { } #endif /* CONFIG_SMP */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 4444875266ee..0f3d44ecbfc6 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1023,6 +1023,7 @@ void __init setup_arch(char **cmdline_p) setup_vmcoreinfo(); setup_lowcore(); + smp_fill_possible_mask(); cpu_init(); s390_init_cpu_topology(); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index dc4a53465060..958704798f4a 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -721,18 +721,14 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) return 0; } -static int __init setup_possible_cpus(char *s) -{ - int max, cpu; +static unsigned int setup_possible_cpus __initdata; - if (kstrtoint(s, 0, &max) < 0) - return 0; - init_cpu_possible(cpumask_of(0)); - for (cpu = 1; cpu < max && cpu < nr_cpu_ids; cpu++) - set_cpu_possible(cpu, true); +static int __init _setup_possible_cpus(char *s) +{ + get_option(&s, &setup_possible_cpus); return 0; } -early_param("possible_cpus", setup_possible_cpus); +early_param("possible_cpus", _setup_possible_cpus); #ifdef CONFIG_HOTPLUG_CPU @@ -775,6 +771,17 @@ void __noreturn cpu_die(void) #endif /* CONFIG_HOTPLUG_CPU */ +void __init smp_fill_possible_mask(void) +{ + unsigned int possible, cpu; + + possible = setup_possible_cpus; + if (!possible) + possible = MACHINE_IS_VM ? 64 : nr_cpu_ids; + for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++) + set_cpu_possible(cpu, true); +} + void __init smp_prepare_cpus(unsigned int max_cpus) { /* request the 0x1201 emergency signal external interrupt */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 800f064b0da7..069607209a30 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -75,6 +75,7 @@ void zpci_event_availability(void *data) if (!zdev || zdev->state == ZPCI_FN_STATE_CONFIGURED) break; zdev->state = ZPCI_FN_STATE_CONFIGURED; + zdev->fh = ccdf->fh; ret = zpci_enable_device(zdev); if (ret) break; @@ -101,6 +102,7 @@ void zpci_event_availability(void *data) if (pdev) pci_stop_and_remove_bus_device(pdev); + zdev->fh = ccdf->fh; zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; break; diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index 099e7ba40599..1d35e33ccf86 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -2,8 +2,8 @@ header-y += generic-y += clkdev.h +generic-y += hash.h generic-y += trace_clock.h generic-y += xor.h generic-y += preempt.h -generic-y += hash.h diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c index 2a0a596ebf67..d77f2f6c7ff0 100644 --- a/arch/sh/kernel/sh_ksyms_32.c +++ b/arch/sh/kernel/sh_ksyms_32.c @@ -20,6 +20,11 @@ EXPORT_SYMBOL(csum_partial_copy_generic); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(empty_zero_page); +#ifdef CONFIG_FLATMEM +/* need in pfn_valid macro */ +EXPORT_SYMBOL(min_low_pfn); +EXPORT_SYMBOL(max_low_pfn); +#endif #define DECLARE_EXPORT(name) \ extern void name(void);EXPORT_SYMBOL(name) diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index e562d3caee57..ad7e178337f1 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -262,8 +262,8 @@ extern unsigned long __must_check __clear_user(void __user *, unsigned long); extern __must_check long strlen_user(const char __user *str); extern __must_check long strnlen_user(const char __user *str, long n); -#define __copy_to_user_inatomic ___copy_to_user -#define __copy_from_user_inatomic ___copy_from_user +#define __copy_to_user_inatomic __copy_to_user +#define __copy_from_user_inatomic __copy_from_user struct pt_regs; extern unsigned long compute_effective_address(struct pt_regs *, diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 070ed141aac7..76663b019eb5 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -854,7 +854,7 @@ int dma_supported(struct device *dev, u64 device_mask) return 1; #ifdef CONFIG_PCI - if (dev->bus == &pci_bus_type) + if (dev_is_pci(dev)) return pci64_dma_supported(to_pci_dev(dev), device_mask); #endif diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 2096468de9b2..e7e215dfa866 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -666,10 +666,9 @@ EXPORT_SYMBOL(dma_ops); */ int dma_supported(struct device *dev, u64 mask) { -#ifdef CONFIG_PCI - if (dev->bus == &pci_bus_type) + if (dev_is_pci(dev)) return 1; -#endif + return 0; } EXPORT_SYMBOL(dma_supported); diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index 60b19f50c80a..b45fe3fb4d2c 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -6,6 +6,7 @@ #include <linux/kgdb.h> #include <linux/kdebug.h> #include <linux/ftrace.h> +#include <linux/context_tracking.h> #include <asm/cacheflush.h> #include <asm/kdebug.h> diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b66a5338231e..b085311dcd0e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -123,11 +123,12 @@ void smp_callin(void) rmb(); set_cpu_online(cpuid, true); - local_irq_enable(); /* idle thread is expected to have preempt disabled */ preempt_disable(); + local_irq_enable(); + cpu_startup_entry(CPUHP_ONLINE); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index dec48bfaddb8..1673940cf9c3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1350,6 +1350,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) return; } + if (!kvm_vcpu_is_bsp(apic->vcpu)) + value &= ~MSR_IA32_APICBASE_BSP; + vcpu->arch.apic_base = value; + /* update jump label if enable bit changes */ if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) { if (value & MSR_IA32_APICBASE_ENABLE) @@ -1359,10 +1363,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) recalculate_apic_map(vcpu->kvm); } - if (!kvm_vcpu_is_bsp(apic->vcpu)) - value &= ~MSR_IA32_APICBASE_BSP; - - vcpu->arch.apic_base = value; if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) { u32 id = kvm_apic_id(apic); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index b2fe1c252f35..da7837e1349d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8283,8 +8283,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); kvm_set_cr4(vcpu, vmcs12->host_cr4); - if (nested_cpu_has_ept(vmcs12)) - nested_ept_uninit_mmu_context(vcpu); + nested_ept_uninit_mmu_context(vcpu); kvm_set_cr3(vcpu, vmcs12->host_cr3); kvm_mmu_reset_context(vcpu); diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index 8711e3797165..3c2e4aa529c4 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -207,7 +207,7 @@ static int acpi_ac_probe(struct platform_device *pdev) goto end; result = acpi_install_notify_handler(ACPI_HANDLE(&pdev->dev), - ACPI_DEVICE_NOTIFY, acpi_ac_notify_handler, ac); + ACPI_ALL_NOTIFY, acpi_ac_notify_handler, ac); if (result) { power_supply_unregister(&ac->charger); goto end; @@ -255,7 +255,7 @@ static int acpi_ac_remove(struct platform_device *pdev) return -EINVAL; acpi_remove_notify_handler(ACPI_HANDLE(&pdev->dev), - ACPI_DEVICE_NOTIFY, acpi_ac_notify_handler); + ACPI_ALL_NOTIFY, acpi_ac_notify_handler); ac = platform_get_drvdata(pdev); if (ac->charger.dev) diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index fbf1aceda8b8..5876a49dfd38 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -62,6 +62,7 @@ MODULE_AUTHOR("Alexey Starikovskiy <astarikovskiy@suse.de>"); MODULE_DESCRIPTION("ACPI Battery Driver"); MODULE_LICENSE("GPL"); +static int battery_bix_broken_package; static unsigned int cache_time = 1000; module_param(cache_time, uint, 0644); MODULE_PARM_DESC(cache_time, "cache time in milliseconds"); @@ -416,7 +417,12 @@ static int acpi_battery_get_info(struct acpi_battery *battery) ACPI_EXCEPTION((AE_INFO, status, "Evaluating %s", name)); return -ENODEV; } - if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags)) + + if (battery_bix_broken_package) + result = extract_package(battery, buffer.pointer, + extended_info_offsets + 1, + ARRAY_SIZE(extended_info_offsets) - 1); + else if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags)) result = extract_package(battery, buffer.pointer, extended_info_offsets, ARRAY_SIZE(extended_info_offsets)); @@ -754,6 +760,17 @@ static int battery_notify(struct notifier_block *nb, return 0; } +static struct dmi_system_id bat_dmi_table[] = { + { + .ident = "NEC LZ750/LS", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"), + }, + }, + {}, +}; + static int acpi_battery_add(struct acpi_device *device) { int result = 0; @@ -846,6 +863,9 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie) { if (acpi_disabled) return; + + if (dmi_check_system(bat_dmi_table)) + battery_bix_broken_package = 1; acpi_bus_register_driver(&acpi_battery_driver); } diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index bba9b72e25f8..0710004055c8 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -156,6 +156,16 @@ int acpi_bus_get_private_data(acpi_handle handle, void **data) } EXPORT_SYMBOL(acpi_bus_get_private_data); +void acpi_bus_no_hotplug(acpi_handle handle) +{ + struct acpi_device *adev = NULL; + + acpi_bus_get_device(handle, &adev); + if (adev) + adev->flags.no_hotplug = true; +} +EXPORT_SYMBOL_GPL(acpi_bus_no_hotplug); + static void acpi_print_osc_error(acpi_handle handle, struct acpi_osc_context *context, char *error) { diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index c0ed4f273cf2..e3a92a6da39a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -427,6 +427,9 @@ static const struct pci_device_id ahci_pci_tbl[] = { .driver_data = board_ahci_yes_fbs }, /* 88se9128 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9125), .driver_data = board_ahci_yes_fbs }, /* 88se9125 */ + { PCI_DEVICE_SUB(PCI_VENDOR_ID_MARVELL_EXT, 0x9178, + PCI_VENDOR_ID_MARVELL_EXT, 0x9170), + .driver_data = board_ahci_yes_fbs }, /* 88se9170 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172), diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c index fe3ca0989b14..1ad2f62d34b9 100644 --- a/drivers/ata/sata_sis.c +++ b/drivers/ata/sata_sis.c @@ -83,6 +83,10 @@ static struct pci_driver sis_pci_driver = { .id_table = sis_pci_tbl, .probe = sis_init_one, .remove = ata_pci_remove_one, +#ifdef CONFIG_PM + .suspend = ata_pci_device_suspend, + .resume = ata_pci_device_resume, +#endif }; static struct scsi_host_template sis_sht = { diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c index 8e562dc65601..e1f3337a0cf9 100644 --- a/drivers/char/tpm/tpm_ppi.c +++ b/drivers/char/tpm/tpm_ppi.c @@ -27,15 +27,18 @@ static char *tpm_device_name = "TPM"; static acpi_status ppi_callback(acpi_handle handle, u32 level, void *context, void **return_value) { - acpi_status status; + acpi_status status = AE_OK; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer); - if (strstr(buffer.pointer, context) != NULL) { - *return_value = handle; + + if (ACPI_SUCCESS(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer))) { + if (strstr(buffer.pointer, context) != NULL) { + *return_value = handle; + status = AE_CTRL_TERMINATE; + } kfree(buffer.pointer); - return AE_CTRL_TERMINATE; } - return AE_OK; + + return status; } static inline void ppi_assign_params(union acpi_object params[4], diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index 8d3009e44fba..5543b7df8e16 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -87,7 +87,7 @@ static unsigned int _get_table_val(const struct clk_div_table *table, return 0; } -static unsigned int _get_val(struct clk_divider *divider, u8 div) +static unsigned int _get_val(struct clk_divider *divider, unsigned int div) { if (divider->flags & CLK_DIVIDER_ONE_BASED) return div; diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c index 39b40aaede2b..68e515d093d8 100644 --- a/drivers/clk/samsung/clk-exynos-audss.c +++ b/drivers/clk/samsung/clk-exynos-audss.c @@ -26,17 +26,17 @@ static struct clk_onecell_data clk_data; #define ASS_CLK_DIV 0x4 #define ASS_CLK_GATE 0x8 +/* list of all parent clock list */ +static const char *mout_audss_p[] = { "fin_pll", "fout_epll" }; +static const char *mout_i2s_p[] = { "mout_audss", "cdclk0", "sclk_audio0" }; + +#ifdef CONFIG_PM_SLEEP static unsigned long reg_save[][2] = { {ASS_CLK_SRC, 0}, {ASS_CLK_DIV, 0}, {ASS_CLK_GATE, 0}, }; -/* list of all parent clock list */ -static const char *mout_audss_p[] = { "fin_pll", "fout_epll" }; -static const char *mout_i2s_p[] = { "mout_audss", "cdclk0", "sclk_audio0" }; - -#ifdef CONFIG_PM_SLEEP static int exynos_audss_clk_suspend(void) { int i; diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index ad5ff50c5f28..1a7c1b929c69 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -39,7 +39,7 @@ #define SRC_TOP1 0xc214 #define SRC_CAM 0xc220 #define SRC_TV 0xc224 -#define SRC_MFC 0xcc28 +#define SRC_MFC 0xc228 #define SRC_G3D 0xc22c #define E4210_SRC_IMAGE 0xc230 #define SRC_LCD0 0xc234 diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c index adf32343c9f9..e52359cf9b6f 100644 --- a/drivers/clk/samsung/clk-exynos5250.c +++ b/drivers/clk/samsung/clk-exynos5250.c @@ -25,6 +25,7 @@ #define MPLL_LOCK 0x4000 #define MPLL_CON0 0x4100 #define SRC_CORE1 0x4204 +#define GATE_IP_ACP 0x8800 #define CPLL_LOCK 0x10020 #define EPLL_LOCK 0x10030 #define VPLL_LOCK 0x10040 @@ -75,7 +76,6 @@ #define SRC_CDREX 0x20200 #define PLL_DIV2_SEL 0x20a24 #define GATE_IP_DISP1 0x10928 -#define GATE_IP_ACP 0x10000 /* list of PLLs to be registered */ enum exynos5250_plls { @@ -120,7 +120,8 @@ enum exynos5250_clks { spi2, i2s1, i2s2, pcm1, pcm2, pwm, spdif, ac97, hsi2c0, hsi2c1, hsi2c2, hsi2c3, chipid, sysreg, pmu, cmu_top, cmu_core, cmu_mem, tzpc0, tzpc1, tzpc2, tzpc3, tzpc4, tzpc5, tzpc6, tzpc7, tzpc8, tzpc9, hdmi_cec, mct, - wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d, + wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d, mdma0, + smmu_mdma0, /* mux clocks */ mout_hdmi = 1024, @@ -354,8 +355,8 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = { GATE(smmu_gscl2, "smmu_gscl2", "aclk266", GATE_IP_GSCL, 9, 0, 0), GATE(smmu_gscl3, "smmu_gscl3", "aclk266", GATE_IP_GSCL, 10, 0, 0), GATE(mfc, "mfc", "aclk333", GATE_IP_MFC, 0, 0, 0), - GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 1, 0, 0), - GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 2, 0, 0), + GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 2, 0, 0), + GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 1, 0, 0), GATE(rotator, "rotator", "aclk266", GATE_IP_GEN, 1, 0, 0), GATE(jpeg, "jpeg", "aclk166", GATE_IP_GEN, 2, 0, 0), GATE(mdma1, "mdma1", "aclk266", GATE_IP_GEN, 4, 0, 0), @@ -406,7 +407,8 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = { GATE(hsi2c2, "hsi2c2", "aclk66", GATE_IP_PERIC, 30, 0, 0), GATE(hsi2c3, "hsi2c3", "aclk66", GATE_IP_PERIC, 31, 0, 0), GATE(chipid, "chipid", "aclk66", GATE_IP_PERIS, 0, 0, 0), - GATE(sysreg, "sysreg", "aclk66", GATE_IP_PERIS, 1, 0, 0), + GATE(sysreg, "sysreg", "aclk66", + GATE_IP_PERIS, 1, CLK_IGNORE_UNUSED, 0), GATE(pmu, "pmu", "aclk66", GATE_IP_PERIS, 2, CLK_IGNORE_UNUSED, 0), GATE(tzpc0, "tzpc0", "aclk66", GATE_IP_PERIS, 6, 0, 0), GATE(tzpc1, "tzpc1", "aclk66", GATE_IP_PERIS, 7, 0, 0), @@ -492,6 +494,8 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = { GATE(mixer, "mixer", "mout_aclk200_disp1", GATE_IP_DISP1, 5, 0, 0), GATE(hdmi, "hdmi", "mout_aclk200_disp1", GATE_IP_DISP1, 6, 0, 0), GATE(g2d, "g2d", "aclk200", GATE_IP_ACP, 3, 0, 0), + GATE(mdma0, "mdma0", "aclk266", GATE_IP_ACP, 1, 0, 0), + GATE(smmu_mdma0, "smmu_mdma0", "aclk266", GATE_IP_ACP, 5, 0, 0), }; static struct samsung_pll_rate_table vpll_24mhz_tbl[] __initdata = { diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 16d7b4ac94be..8d19f7c06010 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -839,9 +839,6 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy) /* set default policy */ ret = cpufreq_set_policy(policy, &new_policy); - policy->user_policy.policy = policy->policy; - policy->user_policy.governor = policy->governor; - if (ret) { pr_debug("setting policy failed\n"); if (cpufreq_driver->exit) @@ -1016,15 +1013,17 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, read_unlock_irqrestore(&cpufreq_driver_lock, flags); #endif - if (frozen) - /* Restore the saved policy when doing light-weight init */ - policy = cpufreq_policy_restore(cpu); - else + /* + * Restore the saved policy when doing light-weight init and fall back + * to the full init if that fails. + */ + policy = frozen ? cpufreq_policy_restore(cpu) : NULL; + if (!policy) { + frozen = false; policy = cpufreq_policy_alloc(); - - if (!policy) - goto nomem_out; - + if (!policy) + goto nomem_out; + } /* * In the resume path, since we restore a saved policy, the assignment @@ -1069,8 +1068,10 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, */ cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); - policy->user_policy.min = policy->min; - policy->user_policy.max = policy->max; + if (!frozen) { + policy->user_policy.min = policy->min; + policy->user_policy.max = policy->max; + } blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_START, policy); @@ -1101,6 +1102,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, cpufreq_init_policy(policy); + if (!frozen) { + policy->user_policy.policy = policy->policy; + policy->user_policy.governor = policy->governor; + } + kobject_uevent(&policy->kobj, KOBJ_ADD); up_read(&cpufreq_rwsem); @@ -1118,8 +1124,11 @@ err_get_freq: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); err_set_policy_cpu: - if (frozen) + if (frozen) { + /* Do not leave stale fallback data behind. */ + per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL; cpufreq_policy_put_kobj(policy); + } cpufreq_policy_free(policy); nomem_out: diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 5f1cbae36961..d51f17ed691e 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -581,7 +581,8 @@ static void intel_pstate_timer_func(unsigned long __data) } #define ICPU(model, policy) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy } + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\ + (unsigned long)&policy } static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x2a, core_params), @@ -614,6 +615,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu = all_cpu_data[cpunum]; intel_pstate_get_cpu_pstates(cpu); + if (!cpu->pstate.current_pstate) { + all_cpu_data[cpunum] = NULL; + kfree(cpu); + return -ENODATA; + } cpu->cpu = cpunum; diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c index 36795639df0d..6e51114057d0 100644 --- a/drivers/cpuidle/cpuidle-calxeda.c +++ b/drivers/cpuidle/cpuidle-calxeda.c @@ -65,7 +65,7 @@ static struct cpuidle_driver calxeda_idle_driver = { .state_count = 2, }; -static int __init calxeda_cpuidle_probe(struct platform_device *pdev) +static int calxeda_cpuidle_probe(struct platform_device *pdev) { return cpuidle_register(&calxeda_idle_driver, NULL); } diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 9dd6e01eac33..f757a0f428bd 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -1410,14 +1410,12 @@ static const struct platform_device_info ixp_dev_info __initdata = { static int __init ixp_module_init(void) { int num = ARRAY_SIZE(ixp4xx_algos); - int i, err ; + int i, err; pdev = platform_device_register_full(&ixp_dev_info); if (IS_ERR(pdev)) return PTR_ERR(pdev); - dev = &pdev->dev; - spin_lock_init(&desc_lock); spin_lock_init(&emerg_lock); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 1a49c777607c..87529181efcc 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -817,7 +817,15 @@ int ioat_dma_self_test(struct ioatdma_device *device) } dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_src)) { + dev_err(dev, "mapping src buffer failed\n"); + goto free_resources; + } dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma_dest)) { + dev_err(dev, "mapping dest buffer failed\n"); + goto unmap_src; + } flags = DMA_PREP_INTERRUPT; tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src, IOAT_TEST_SIZE, flags); @@ -855,8 +863,9 @@ int ioat_dma_self_test(struct ioatdma_device *device) } unmap_dma: - dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE); dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE); +unmap_src: + dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE); free_resources: dma->device_free_chan_resources(dma_chan); out: diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index c79dd2b1f70e..d3c3b5b15824 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -906,14 +906,12 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, WARN_ON(readq(>t_entries[i-1]) != gen8_pte_encode(addr, level, true)); -#if 0 /* TODO: Still needed on GEN8? */ /* This next bit makes the above posting read even more important. We * want to flush the TLBs only after we're certain all the PTE updates * have finished. */ I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); POSTING_READ(GFX_FLSH_CNTL_GEN6); -#endif } /* diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 54e82a80cf50..769b864465a9 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -10541,11 +10541,20 @@ static struct intel_quirk intel_quirks[] = { /* Sony Vaio Y cannot use SSC on LVDS */ { 0x0046, 0x104d, 0x9076, quirk_ssc_force_disable }, - /* - * All GM45 Acer (and its brands eMachines and Packard Bell) laptops - * seem to use inverted backlight PWM. - */ - { 0x2a42, 0x1025, PCI_ANY_ID, quirk_invert_brightness }, + /* Acer Aspire 5734Z must invert backlight brightness */ + { 0x2a42, 0x1025, 0x0459, quirk_invert_brightness }, + + /* Acer/eMachines G725 */ + { 0x2a42, 0x1025, 0x0210, quirk_invert_brightness }, + + /* Acer/eMachines e725 */ + { 0x2a42, 0x1025, 0x0212, quirk_invert_brightness }, + + /* Acer/Packard Bell NCL20 */ + { 0x2a42, 0x1025, 0x034b, quirk_invert_brightness }, + + /* Acer Aspire 4736Z */ + { 0x2a42, 0x1025, 0x0260, quirk_invert_brightness }, /* Dell XPS13 HD Sandy Bridge */ { 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable }, diff --git a/drivers/gpu/drm/nouveau/core/core/subdev.c b/drivers/gpu/drm/nouveau/core/core/subdev.c index 48f06378d3f9..2ea5568b6cf5 100644 --- a/drivers/gpu/drm/nouveau/core/core/subdev.c +++ b/drivers/gpu/drm/nouveau/core/core/subdev.c @@ -104,11 +104,8 @@ nouveau_subdev_create_(struct nouveau_object *parent, if (parent) { struct nouveau_device *device = nv_device(parent); - int subidx = nv_hclass(subdev) & 0xff; - subdev->debug = nouveau_dbgopt(device->dbgopt, subname); subdev->mmio = nv_subdev(device)->mmio; - device->subdev[subidx] = *pobject; } return 0; diff --git a/drivers/gpu/drm/nouveau/core/engine/device/base.c b/drivers/gpu/drm/nouveau/core/engine/device/base.c index 9135b25a29d0..dd01c6c435d6 100644 --- a/drivers/gpu/drm/nouveau/core/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/core/engine/device/base.c @@ -268,6 +268,8 @@ nouveau_devobj_ctor(struct nouveau_object *parent, if (ret) return ret; + device->subdev[i] = devobj->subdev[i]; + /* note: can't init *any* subdevs until devinit has been run * due to not knowing exactly what the vbios init tables will * mess with. devinit also can't be run until all of its diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c index 8d06eef2b9ee..dbc5e33de94f 100644 --- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c +++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c @@ -161,7 +161,7 @@ nvc0_identify(struct nouveau_device *device) device->oclass[NVDEV_SUBDEV_THERM ] = &nva3_therm_oclass; device->oclass[NVDEV_SUBDEV_MXM ] = &nv50_mxm_oclass; device->oclass[NVDEV_SUBDEV_DEVINIT] = &nvc0_devinit_oclass; - device->oclass[NVDEV_SUBDEV_MC ] = nvc3_mc_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = nvc0_mc_oclass; device->oclass[NVDEV_SUBDEV_BUS ] = nvc0_bus_oclass; device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass; device->oclass[NVDEV_SUBDEV_FB ] = nvc0_fb_oclass; diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c index 434bb4b0fa2e..5c8a63dc506a 100644 --- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c +++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c @@ -334,7 +334,7 @@ nvc0_graph_mthd(struct nvc0_graph_priv *priv, struct nvc0_graph_mthd *mthds) while ((mthd = &mthds[i++]) && (init = mthd->init)) { u32 addr = 0x80000000 | mthd->oclass; for (data = 0; init->count; init++) { - if (data != init->data) { + if (init == mthd->init || data != init->data) { nv_wr32(priv, 0x40448c, init->data); data = init->data; } diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h index 8541aa382ff2..d89dbdf39b0d 100644 --- a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h @@ -75,6 +75,11 @@ struct nouveau_fb { static inline struct nouveau_fb * nouveau_fb(void *obj) { + /* fbram uses this before device subdev pointer is valid */ + if (nv_iclass(obj, NV_SUBDEV_CLASS) && + nv_subidx(obj) == NVDEV_SUBDEV_FB) + return obj; + return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_FB]; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c index 420908cb82b6..df1b1b423093 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c @@ -365,13 +365,13 @@ static u16 init_script(struct nouveau_bios *bios, int index) { struct nvbios_init init = { .bios = bios }; - u16 data; + u16 bmp_ver = bmp_version(bios), data; - if (bmp_version(bios) && bmp_version(bios) < 0x0510) { - if (index > 1) + if (bmp_ver && bmp_ver < 0x0510) { + if (index > 1 || bmp_ver < 0x0100) return 0x0000; - data = bios->bmp_offset + (bios->version.major < 2 ? 14 : 18); + data = bios->bmp_offset + (bmp_ver < 0x0200 ? 14 : 18); return nv_ro16(bios, data + (index * 2)); } @@ -1294,7 +1294,11 @@ init_jump(struct nvbios_init *init) u16 offset = nv_ro16(bios, init->offset + 1); trace("JUMP\t0x%04x\n", offset); - init->offset = offset; + + if (init_exec(init)) + init->offset = offset; + else + init->offset += 3; } /** diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 6828d81ed7b9..900fae01793e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -447,6 +447,8 @@ nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS) if (ret) goto done; + info->offset = ntfy->node->offset; + done: if (ret) nouveau_abi16_ntfy_fini(chan, ntfy); diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 95c740454049..ba0183fb84f3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -51,6 +51,7 @@ static struct nouveau_dsm_priv { bool dsm_detected; bool optimus_detected; acpi_handle dhandle; + acpi_handle other_handle; acpi_handle rom_handle; } nouveau_dsm_priv; @@ -260,9 +261,10 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev) if (!dhandle) return false; - if (!acpi_has_method(dhandle, "_DSM")) + if (!acpi_has_method(dhandle, "_DSM")) { + nouveau_dsm_priv.other_handle = dhandle; return false; - + } if (nouveau_test_dsm(dhandle, nouveau_dsm, NOUVEAU_DSM_POWER)) retval |= NOUVEAU_DSM_HAS_MUX; @@ -338,6 +340,16 @@ static bool nouveau_dsm_detect(void) printk(KERN_INFO "VGA switcheroo: detected DSM switching method %s handle\n", acpi_method_name); nouveau_dsm_priv.dsm_detected = true; + /* + * On some systems hotplug events are generated for the device + * being switched off when _DSM is executed. They cause ACPI + * hotplug to trigger and attempt to remove the device from + * the system, which causes it to break down. Prevent that from + * happening by setting the no_hotplug flag for the involved + * ACPI device objects. + */ + acpi_bus_no_hotplug(nouveau_dsm_priv.dhandle); + acpi_bus_no_hotplug(nouveau_dsm_priv.other_handle); ret = true; } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 29c3efdfc7dd..25ea82f8def3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -610,7 +610,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, ret = nouveau_fence_sync(fence, chan); nouveau_fence_unref(&fence); if (ret) - return ret; + goto fail_free; if (new_bo != old_bo) { ret = nouveau_bo_pin(new_bo, TTM_PL_FLAG_VRAM); diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index b1970596a782..0b9621c9aeea 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1143,31 +1143,53 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, } if (tiling_flags & RADEON_TILING_MACRO) { - if (rdev->family >= CHIP_BONAIRE) - tmp = rdev->config.cik.tile_config; - else if (rdev->family >= CHIP_TAHITI) - tmp = rdev->config.si.tile_config; - else if (rdev->family >= CHIP_CAYMAN) - tmp = rdev->config.cayman.tile_config; - else - tmp = rdev->config.evergreen.tile_config; + evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split); - switch ((tmp & 0xf0) >> 4) { - case 0: /* 4 banks */ - fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK); - break; - case 1: /* 8 banks */ - default: - fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK); - break; - case 2: /* 16 banks */ - fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK); - break; + /* Set NUM_BANKS. */ + if (rdev->family >= CHIP_BONAIRE) { + unsigned tileb, index, num_banks, tile_split_bytes; + + /* Calculate the macrotile mode index. */ + tile_split_bytes = 64 << tile_split; + tileb = 8 * 8 * target_fb->bits_per_pixel / 8; + tileb = min(tile_split_bytes, tileb); + + for (index = 0; tileb > 64; index++) { + tileb >>= 1; + } + + if (index >= 16) { + DRM_ERROR("Wrong screen bpp (%u) or tile split (%u)\n", + target_fb->bits_per_pixel, tile_split); + return -EINVAL; + } + + num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3; + fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks); + } else { + /* SI and older. */ + if (rdev->family >= CHIP_TAHITI) + tmp = rdev->config.si.tile_config; + else if (rdev->family >= CHIP_CAYMAN) + tmp = rdev->config.cayman.tile_config; + else + tmp = rdev->config.evergreen.tile_config; + + switch ((tmp & 0xf0) >> 4) { + case 0: /* 4 banks */ + fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK); + break; + case 1: /* 8 banks */ + default: + fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK); + break; + case 2: /* 16 banks */ + fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK); + break; + } } fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1); - - evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split); fb_format |= EVERGREEN_GRPH_TILE_SPLIT(tile_split); fb_format |= EVERGREEN_GRPH_BANK_WIDTH(bankw); fb_format |= EVERGREEN_GRPH_BANK_HEIGHT(bankh); @@ -1180,19 +1202,12 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1); if (rdev->family >= CHIP_BONAIRE) { - u32 num_pipe_configs = rdev->config.cik.max_tile_pipes; - u32 num_rb = rdev->config.cik.max_backends_per_se; - if (num_pipe_configs > 8) - num_pipe_configs = 8; - if (num_pipe_configs == 8) - fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P8_32x32_16x16); - else if (num_pipe_configs == 4) { - if (num_rb == 4) - fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_16x16); - else if (num_rb < 4) - fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_8x16); - } else if (num_pipe_configs == 2) - fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P2); + /* Read the pipe config from the 2D TILED SCANOUT mode. + * It should be the same for the other modes too, but not all + * modes set the pipe config field. */ + u32 pipe_config = (rdev->config.cik.tile_mode_array[10] >> 6) & 0x1f; + + fb_format |= CIK_GRPH_PIPE_CONFIG(pipe_config); } else if ((rdev->family == CHIP_TAHITI) || (rdev->family == CHIP_PITCAIRN)) fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16); diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index b43a3a3c9067..e950fabd7f5e 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3057,7 +3057,7 @@ static u32 cik_create_bitmask(u32 bit_width) * Returns the disabled RB bitmask. */ static u32 cik_get_rb_disabled(struct radeon_device *rdev, - u32 max_rb_num, u32 se_num, + u32 max_rb_num_per_se, u32 sh_per_se) { u32 data, mask; @@ -3071,7 +3071,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev, data >>= BACKEND_DISABLE_SHIFT; - mask = cik_create_bitmask(max_rb_num / se_num / sh_per_se); + mask = cik_create_bitmask(max_rb_num_per_se / sh_per_se); return data & mask; } @@ -3088,7 +3088,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev, */ static void cik_setup_rb(struct radeon_device *rdev, u32 se_num, u32 sh_per_se, - u32 max_rb_num) + u32 max_rb_num_per_se) { int i, j; u32 data, mask; @@ -3098,7 +3098,7 @@ static void cik_setup_rb(struct radeon_device *rdev, for (i = 0; i < se_num; i++) { for (j = 0; j < sh_per_se; j++) { cik_select_se_sh(rdev, i, j); - data = cik_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se); + data = cik_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se); if (rdev->family == CHIP_HAWAII) disabled_rbs |= data << ((i * sh_per_se + j) * HAWAII_RB_BITMAP_WIDTH_PER_SH); else @@ -3108,12 +3108,14 @@ static void cik_setup_rb(struct radeon_device *rdev, cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); mask = 1; - for (i = 0; i < max_rb_num; i++) { + for (i = 0; i < max_rb_num_per_se * se_num; i++) { if (!(disabled_rbs & mask)) enabled_rbs |= mask; mask <<= 1; } + rdev->config.cik.backend_enable_mask = enabled_rbs; + for (i = 0; i < se_num; i++) { cik_select_se_sh(rdev, i, 0xffffffff); data = 0; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index b1f990d0eaa1..45e1f447bc79 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -1940,7 +1940,7 @@ struct si_asic { unsigned sc_earlyz_tile_fifo_size; unsigned num_tile_pipes; - unsigned num_backends_per_se; + unsigned backend_enable_mask; unsigned backend_disable_mask_per_asic; unsigned backend_map; unsigned num_texture_channel_caches; @@ -1970,7 +1970,7 @@ struct cik_asic { unsigned sc_earlyz_tile_fifo_size; unsigned num_tile_pipes; - unsigned num_backends_per_se; + unsigned backend_enable_mask; unsigned backend_disable_mask_per_asic; unsigned backend_map; unsigned num_texture_channel_caches; diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 9d302eaeea15..485848f889f5 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -33,6 +33,7 @@ static struct radeon_atpx_priv { bool atpx_detected; /* handle for device - and atpx */ acpi_handle dhandle; + acpi_handle other_handle; struct radeon_atpx atpx; } radeon_atpx_priv; @@ -451,9 +452,10 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev) return false; status = acpi_get_handle(dhandle, "ATPX", &atpx_handle); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + radeon_atpx_priv.other_handle = dhandle; return false; - + } radeon_atpx_priv.dhandle = dhandle; radeon_atpx_priv.atpx.handle = atpx_handle; return true; @@ -530,6 +532,16 @@ static bool radeon_atpx_detect(void) printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n", acpi_method_name); radeon_atpx_priv.atpx_detected = true; + /* + * On some systems hotplug events are generated for the device + * being switched off when ATPX is executed. They cause ACPI + * hotplug to trigger and attempt to remove the device from + * the system, which causes it to break down. Prevent that from + * happening by setting the no_hotplug flag for the involved + * ACPI device objects. + */ + acpi_bus_no_hotplug(radeon_atpx_priv.dhandle); + acpi_bus_no_hotplug(radeon_atpx_priv.other_handle); return true; } return false; diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 1958b36ad0e5..db39ea36bf22 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -77,9 +77,10 @@ * 2.33.0 - Add SI tiling mode array query * 2.34.0 - Add CIK tiling mode array query * 2.35.0 - Add CIK macrotile mode array query + * 2.36.0 - Fix CIK DCE tiling setup */ #define KMS_DRIVER_MAJOR 2 -#define KMS_DRIVER_MINOR 35 +#define KMS_DRIVER_MINOR 36 #define KMS_DRIVER_PATCHLEVEL 0 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags); int radeon_driver_unload_kms(struct drm_device *dev); diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 55d0b474bd37..21d593c0ecaf 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -461,6 +461,15 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case RADEON_INFO_SI_CP_DMA_COMPUTE: *value = 1; break; + case RADEON_INFO_SI_BACKEND_ENABLED_MASK: + if (rdev->family >= CHIP_BONAIRE) { + *value = rdev->config.cik.backend_enable_mask; + } else if (rdev->family >= CHIP_TAHITI) { + *value = rdev->config.si.backend_enable_mask; + } else { + DRM_DEBUG_KMS("BACKEND_ENABLED_MASK is si+ only!\n"); + } + break; default: DRM_DEBUG_KMS("Invalid request %d\n", info->request); return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 373d088bac66..b9c0529b4a2e 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -473,7 +473,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, return -EINVAL; } - if ((start >> 28) != (end >> 28)) { + if ((start >> 28) != ((end - 1) >> 28)) { DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n", start, end); return -EINVAL; diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index a36736dab5e0..85e1edfaa3be 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2811,7 +2811,7 @@ static void si_setup_spi(struct radeon_device *rdev, } static u32 si_get_rb_disabled(struct radeon_device *rdev, - u32 max_rb_num, u32 se_num, + u32 max_rb_num_per_se, u32 sh_per_se) { u32 data, mask; @@ -2825,14 +2825,14 @@ static u32 si_get_rb_disabled(struct radeon_device *rdev, data >>= BACKEND_DISABLE_SHIFT; - mask = si_create_bitmask(max_rb_num / se_num / sh_per_se); + mask = si_create_bitmask(max_rb_num_per_se / sh_per_se); return data & mask; } static void si_setup_rb(struct radeon_device *rdev, u32 se_num, u32 sh_per_se, - u32 max_rb_num) + u32 max_rb_num_per_se) { int i, j; u32 data, mask; @@ -2842,19 +2842,21 @@ static void si_setup_rb(struct radeon_device *rdev, for (i = 0; i < se_num; i++) { for (j = 0; j < sh_per_se; j++) { si_select_se_sh(rdev, i, j); - data = si_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se); + data = si_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se); disabled_rbs |= data << ((i * sh_per_se + j) * TAHITI_RB_BITMAP_WIDTH_PER_SH); } } si_select_se_sh(rdev, 0xffffffff, 0xffffffff); mask = 1; - for (i = 0; i < max_rb_num; i++) { + for (i = 0; i < max_rb_num_per_se * se_num; i++) { if (!(disabled_rbs & mask)) enabled_rbs |= mask; mask <<= 1; } + rdev->config.si.backend_enable_mask = enabled_rbs; + for (i = 0; i < se_num; i++) { si_select_se_sh(rdev, i, 0xffffffff); data = 0; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index f80b700f821c..797ed29a36ea 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -123,7 +123,7 @@ static struct cpuidle_state *cpuidle_state_table; * which is also the index into the MWAIT hint array. * Thus C0 is a dummy. */ -static struct cpuidle_state nehalem_cstates[] __initdata = { +static struct cpuidle_state nehalem_cstates[] = { { .name = "C1-NHM", .desc = "MWAIT 0x00", @@ -156,7 +156,7 @@ static struct cpuidle_state nehalem_cstates[] __initdata = { .enter = NULL } }; -static struct cpuidle_state snb_cstates[] __initdata = { +static struct cpuidle_state snb_cstates[] = { { .name = "C1-SNB", .desc = "MWAIT 0x00", @@ -196,7 +196,7 @@ static struct cpuidle_state snb_cstates[] __initdata = { .enter = NULL } }; -static struct cpuidle_state ivb_cstates[] __initdata = { +static struct cpuidle_state ivb_cstates[] = { { .name = "C1-IVB", .desc = "MWAIT 0x00", @@ -236,7 +236,7 @@ static struct cpuidle_state ivb_cstates[] __initdata = { .enter = NULL } }; -static struct cpuidle_state hsw_cstates[] __initdata = { +static struct cpuidle_state hsw_cstates[] = { { .name = "C1-HSW", .desc = "MWAIT 0x00", @@ -297,7 +297,7 @@ static struct cpuidle_state hsw_cstates[] __initdata = { .enter = NULL } }; -static struct cpuidle_state atom_cstates[] __initdata = { +static struct cpuidle_state atom_cstates[] = { { .name = "C1E-ATM", .desc = "MWAIT 0x00", @@ -329,7 +329,7 @@ static struct cpuidle_state atom_cstates[] __initdata = { { .enter = NULL } }; -static struct cpuidle_state avn_cstates[] __initdata = { +static struct cpuidle_state avn_cstates[] = { { .name = "C1-AVN", .desc = "MWAIT 0x00", @@ -344,6 +344,8 @@ static struct cpuidle_state avn_cstates[] __initdata = { .exit_latency = 15, .target_residency = 45, .enter = &intel_idle }, + { + .enter = NULL } }; /** diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 8e49db690f33..6c17f2dc0f09 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2310,7 +2310,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv) inet_get_local_port_range(&init_net, &low, &high); remaining = (high - low) + 1; - rover = net_random() % remaining + low; + rover = prandom_u32() % remaining + low; retry: if (last_used_port != rover && !idr_find(ps, (unsigned short) rover)) { diff --git a/drivers/input/input.c b/drivers/input/input.c index 846ccdd905b1..d2965e4b3224 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1871,6 +1871,10 @@ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int break; case EV_ABS: + input_alloc_absinfo(dev); + if (!dev->absinfo) + return; + __set_bit(code, dev->absbit); break; diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 75762d6ff3ba..aa127ba392a4 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -455,7 +455,18 @@ static void zforce_complete(struct zforce_ts *ts, int cmd, int result) } } -static irqreturn_t zforce_interrupt(int irq, void *dev_id) +static irqreturn_t zforce_irq(int irq, void *dev_id) +{ + struct zforce_ts *ts = dev_id; + struct i2c_client *client = ts->client; + + if (ts->suspended && device_may_wakeup(&client->dev)) + pm_wakeup_event(&client->dev, 500); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t zforce_irq_thread(int irq, void *dev_id) { struct zforce_ts *ts = dev_id; struct i2c_client *client = ts->client; @@ -465,12 +476,10 @@ static irqreturn_t zforce_interrupt(int irq, void *dev_id) u8 *payload; /* - * When suspended, emit a wakeup signal if necessary and return. + * When still suspended, return. * Due to the level-interrupt we will get re-triggered later. */ if (ts->suspended) { - if (device_may_wakeup(&client->dev)) - pm_wakeup_event(&client->dev, 500); msleep(20); return IRQ_HANDLED; } @@ -763,8 +772,8 @@ static int zforce_probe(struct i2c_client *client, * Therefore we can trigger the interrupt anytime it is low and do * not need to limit it to the interrupt edge. */ - ret = devm_request_threaded_irq(&client->dev, client->irq, NULL, - zforce_interrupt, + ret = devm_request_threaded_irq(&client->dev, client->irq, + zforce_irq, zforce_irq_thread, IRQF_TRIGGER_LOW | IRQF_ONESHOT, input_dev->name, ts); if (ret) { diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c index 05188351711d..a97263e902ff 100644 --- a/drivers/leds/leds-lp5521.c +++ b/drivers/leds/leds-lp5521.c @@ -244,18 +244,12 @@ static int lp5521_update_program_memory(struct lp55xx_chip *chip, if (i % 2) goto err; - mutex_lock(&chip->lock); - for (i = 0; i < LP5521_PROGRAM_LENGTH; i++) { ret = lp55xx_write(chip, addr[idx] + i, pattern[i]); - if (ret) { - mutex_unlock(&chip->lock); + if (ret) return -EINVAL; - } } - mutex_unlock(&chip->lock); - return size; err: @@ -427,15 +421,17 @@ static ssize_t store_engine_load(struct device *dev, { struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev)); struct lp55xx_chip *chip = led->chip; + int ret; mutex_lock(&chip->lock); chip->engine_idx = nr; lp5521_load_engine(chip); + ret = lp5521_update_program_memory(chip, buf, len); mutex_unlock(&chip->lock); - return lp5521_update_program_memory(chip, buf, len); + return ret; } store_load(1) store_load(2) diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c index 6b553d9f4266..fd9ab5f61441 100644 --- a/drivers/leds/leds-lp5523.c +++ b/drivers/leds/leds-lp5523.c @@ -337,18 +337,12 @@ static int lp5523_update_program_memory(struct lp55xx_chip *chip, if (i % 2) goto err; - mutex_lock(&chip->lock); - for (i = 0; i < LP5523_PROGRAM_LENGTH; i++) { ret = lp55xx_write(chip, LP5523_REG_PROG_MEM + i, pattern[i]); - if (ret) { - mutex_unlock(&chip->lock); + if (ret) return -EINVAL; - } } - mutex_unlock(&chip->lock); - return size; err: @@ -548,15 +542,17 @@ static ssize_t store_engine_load(struct device *dev, { struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev)); struct lp55xx_chip *chip = led->chip; + int ret; mutex_lock(&chip->lock); chip->engine_idx = nr; lp5523_load_engine_and_select_page(chip); + ret = lp5523_update_program_memory(chip, buf, len); mutex_unlock(&chip->lock); - return lp5523_update_program_memory(chip, buf, len); + return ret; } store_load(1) store_load(2) diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index 11e20afbdcac..705698fd2c7e 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -1228,8 +1228,14 @@ static void rtsx_pci_remove(struct pci_dev *pcidev) pcr->remove_pci = true; - cancel_delayed_work(&pcr->carddet_work); - cancel_delayed_work(&pcr->idle_work); + /* Disable interrupts at the pcr level */ + spin_lock_irq(&pcr->lock); + rtsx_pci_writel(pcr, RTSX_BIER, 0); + pcr->bier = 0; + spin_unlock_irq(&pcr->lock); + + cancel_delayed_work_sync(&pcr->carddet_work); + cancel_delayed_work_sync(&pcr->idle_work); mfd_remove_devices(&pcidev->dev); diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c index d210d131fef2..0f55589a56b8 100644 --- a/drivers/mtd/maps/pxa2xx-flash.c +++ b/drivers/mtd/maps/pxa2xx-flash.c @@ -73,7 +73,7 @@ static int pxa2xx_flash_probe(struct platform_device *pdev) return -ENOMEM; } info->map.cached = - ioremap_cached(info->map.phys, info->map.size); + ioremap_cache(info->map.phys, info->map.size); if (!info->map.cached) printk(KERN_WARNING "Failed to ioremap cached %s\n", info->map.name); diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 539e24a1c86c..cce1f1bf90b4 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -34,14 +34,14 @@ #include "bonding.h" #include "bond_3ad.h" -// General definitions +/* General definitions */ #define AD_SHORT_TIMEOUT 1 #define AD_LONG_TIMEOUT 0 #define AD_STANDBY 0x2 #define AD_MAX_TX_IN_SECOND 3 #define AD_COLLECTOR_MAX_DELAY 0 -// Timer definitions(43.4.4 in the 802.3ad standard) +/* Timer definitions (43.4.4 in the 802.3ad standard) */ #define AD_FAST_PERIODIC_TIME 1 #define AD_SLOW_PERIODIC_TIME 30 #define AD_SHORT_TIMEOUT_TIME (3*AD_FAST_PERIODIC_TIME) @@ -49,7 +49,7 @@ #define AD_CHURN_DETECTION_TIME 60 #define AD_AGGREGATE_WAIT_TIME 2 -// Port state definitions(43.4.2.2 in the 802.3ad standard) +/* Port state definitions (43.4.2.2 in the 802.3ad standard) */ #define AD_STATE_LACP_ACTIVITY 0x1 #define AD_STATE_LACP_TIMEOUT 0x2 #define AD_STATE_AGGREGATION 0x4 @@ -59,7 +59,9 @@ #define AD_STATE_DEFAULTED 0x40 #define AD_STATE_EXPIRED 0x80 -// Port Variables definitions used by the State Machines(43.4.7 in the 802.3ad standard) +/* Port Variables definitions used by the State Machines (43.4.7 in the + * 802.3ad standard) + */ #define AD_PORT_BEGIN 0x1 #define AD_PORT_LACP_ENABLED 0x2 #define AD_PORT_ACTOR_CHURN 0x4 @@ -71,24 +73,23 @@ #define AD_PORT_SELECTED 0x100 #define AD_PORT_MOVED 0x200 -// Port Key definitions -// key is determined according to the link speed, duplex and -// user key(which is yet not supported) -// ------------------------------------------------------------ -// Port key : | User key | Speed |Duplex| -// ------------------------------------------------------------ -// 16 6 1 0 +/* Port Key definitions + * key is determined according to the link speed, duplex and + * user key (which is yet not supported) + * -------------------------------------------------------------- + * Port key : | User key | Speed | Duplex | + * -------------------------------------------------------------- + * 16 6 1 0 + */ #define AD_DUPLEX_KEY_BITS 0x1 #define AD_SPEED_KEY_BITS 0x3E #define AD_USER_KEY_BITS 0xFFC0 -//dalloun #define AD_LINK_SPEED_BITMASK_1MBPS 0x1 #define AD_LINK_SPEED_BITMASK_10MBPS 0x2 #define AD_LINK_SPEED_BITMASK_100MBPS 0x4 #define AD_LINK_SPEED_BITMASK_1000MBPS 0x8 #define AD_LINK_SPEED_BITMASK_10000MBPS 0x10 -//endalloun /* compare MAC addresses */ #define MAC_ADDRESS_EQUAL(A, B) \ @@ -100,7 +101,7 @@ static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR; -// ================= main 802.3ad protocol functions ================== +/* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); static int ad_marker_send(struct port *port, struct bond_marker *marker); static void ad_mux_machine(struct port *port); @@ -114,13 +115,13 @@ static void ad_initialize_agg(struct aggregator *aggregator); static void ad_initialize_port(struct port *port, int lacp_fast); static void ad_enable_collecting_distributing(struct port *port); static void ad_disable_collecting_distributing(struct port *port); -static void ad_marker_info_received(struct bond_marker *marker_info, struct port *port); -static void ad_marker_response_received(struct bond_marker *marker, struct port *port); +static void ad_marker_info_received(struct bond_marker *marker_info, + struct port *port); +static void ad_marker_response_received(struct bond_marker *marker, + struct port *port); -///////////////////////////////////////////////////////////////////////////////// -// ================= api to bonding and kernel code ================== -///////////////////////////////////////////////////////////////////////////////// +/* ================= api to bonding and kernel code ================== */ /** * __get_bond_by_port - get the port's bonding struct @@ -142,26 +143,32 @@ static inline struct bonding *__get_bond_by_port(struct port *port) * * Return the aggregator of the first slave in @bond, or %NULL if it can't be * found. + * The caller must hold RCU or RTNL lock. */ static inline struct aggregator *__get_first_agg(struct port *port) { struct bonding *bond = __get_bond_by_port(port); struct slave *first_slave; + struct aggregator *agg; /* If there's no bond for this port, or bond has no slaves */ if (bond == NULL) return NULL; + rcu_read_lock(); first_slave = bond_first_slave_rcu(bond); + agg = first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL; rcu_read_unlock(); - return first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL; + + return agg; } -/* - * __agg_has_partner +/** + * __agg_has_partner - see if we have a partner + * @agg: the agregator we're looking at * * Return nonzero if aggregator has a partner (denoted by a non-zero ether - * address for the partner). Return 0 if not. + * address for the partner). Return 0 if not. */ static inline int __agg_has_partner(struct aggregator *agg) { @@ -171,7 +178,6 @@ static inline int __agg_has_partner(struct aggregator *agg) /** * __disable_port - disable the port's slave * @port: the port we're looking at - * */ static inline void __disable_port(struct port *port) { @@ -181,7 +187,6 @@ static inline void __disable_port(struct port *port) /** * __enable_port - enable the port's slave, if it's up * @port: the port we're looking at - * */ static inline void __enable_port(struct port *port) { @@ -194,7 +199,6 @@ static inline void __enable_port(struct port *port) /** * __port_is_enabled - check if the port's slave is in active state * @port: the port we're looking at - * */ static inline int __port_is_enabled(struct port *port) { @@ -220,7 +224,6 @@ static inline u32 __get_agg_selection_mode(struct port *port) /** * __check_agg_selection_timer - check if the selection timer has expired * @port: the port we're looking at - * */ static inline int __check_agg_selection_timer(struct port *port) { @@ -235,7 +238,6 @@ static inline int __check_agg_selection_timer(struct port *port) /** * __get_state_machine_lock - lock the port's state machines * @port: the port we're looking at - * */ static inline void __get_state_machine_lock(struct port *port) { @@ -245,7 +247,6 @@ static inline void __get_state_machine_lock(struct port *port) /** * __release_state_machine_lock - unlock the port's state machines * @port: the port we're looking at - * */ static inline void __release_state_machine_lock(struct port *port) { @@ -268,10 +269,11 @@ static u16 __get_link_speed(struct port *port) struct slave *slave = port->slave; u16 speed; - /* this if covers only a special case: when the configuration starts with - * link down, it sets the speed to 0. - * This is done in spite of the fact that the e100 driver reports 0 to be - * compatible with MVT in the future.*/ + /* this if covers only a special case: when the configuration starts + * with link down, it sets the speed to 0. + * This is done in spite of the fact that the e100 driver reports 0 + * to be compatible with MVT in the future. + */ if (slave->link != BOND_LINK_UP) speed = 0; else { @@ -293,7 +295,8 @@ static u16 __get_link_speed(struct port *port) break; default: - speed = 0; // unknown speed value from ethtool. shouldn't happen + /* unknown speed value from ethtool. shouldn't happen */ + speed = 0; break; } } @@ -317,8 +320,9 @@ static u8 __get_duplex(struct port *port) u8 retval; - // handling a special case: when the configuration starts with - // link down, it sets the duplex to 0. + /* handling a special case: when the configuration starts with + * link down, it sets the duplex to 0. + */ if (slave->link != BOND_LINK_UP) retval = 0x0; else { @@ -342,15 +346,14 @@ static u8 __get_duplex(struct port *port) /** * __initialize_port_locks - initialize a port's STATE machine spinlock * @port: the slave of the port we're looking at - * */ static inline void __initialize_port_locks(struct slave *slave) { - // make sure it isn't called twice + /* make sure it isn't called twice */ spin_lock_init(&(SLAVE_AD_INFO(slave).state_machine_lock)); } -//conversions +/* Conversions */ /** * __ad_timer_to_ticks - convert a given timer type to AD module ticks @@ -359,39 +362,38 @@ static inline void __initialize_port_locks(struct slave *slave) * * If @timer_type is %current_while_timer, @par indicates long/short timer. * If @timer_type is %periodic_timer, @par is one of %FAST_PERIODIC_TIME, - * %SLOW_PERIODIC_TIME. + * %SLOW_PERIODIC_TIME. */ static u16 __ad_timer_to_ticks(u16 timer_type, u16 par) { u16 retval = 0; /* to silence the compiler */ switch (timer_type) { - case AD_CURRENT_WHILE_TIMER: // for rx machine usage + case AD_CURRENT_WHILE_TIMER: /* for rx machine usage */ if (par) - retval = (AD_SHORT_TIMEOUT_TIME*ad_ticks_per_sec); // short timeout + retval = (AD_SHORT_TIMEOUT_TIME*ad_ticks_per_sec); else - retval = (AD_LONG_TIMEOUT_TIME*ad_ticks_per_sec); // long timeout + retval = (AD_LONG_TIMEOUT_TIME*ad_ticks_per_sec); break; - case AD_ACTOR_CHURN_TIMER: // for local churn machine + case AD_ACTOR_CHURN_TIMER: /* for local churn machine */ retval = (AD_CHURN_DETECTION_TIME*ad_ticks_per_sec); break; - case AD_PERIODIC_TIMER: // for periodic machine - retval = (par*ad_ticks_per_sec); // long timeout + case AD_PERIODIC_TIMER: /* for periodic machine */ + retval = (par*ad_ticks_per_sec); /* long timeout */ break; - case AD_PARTNER_CHURN_TIMER: // for remote churn machine + case AD_PARTNER_CHURN_TIMER: /* for remote churn machine */ retval = (AD_CHURN_DETECTION_TIME*ad_ticks_per_sec); break; - case AD_WAIT_WHILE_TIMER: // for selection machine + case AD_WAIT_WHILE_TIMER: /* for selection machine */ retval = (AD_AGGREGATE_WAIT_TIME*ad_ticks_per_sec); break; } + return retval; } -///////////////////////////////////////////////////////////////////////////////// -// ================= ad_rx_machine helper functions ================== -///////////////////////////////////////////////////////////////////////////////// +/* ================= ad_rx_machine helper functions ================== */ /** * __choose_matched - update a port's matched variable from a received lacpdu @@ -451,7 +453,9 @@ static void __record_pdu(struct lacpdu *lacpdu, struct port *port) struct port_params *partner = &port->partner_oper; __choose_matched(lacpdu, port); - // record the new parameter values for the partner operational + /* record the new parameter values for the partner + * operational + */ partner->port_number = ntohs(lacpdu->actor_port); partner->port_priority = ntohs(lacpdu->actor_port_priority); partner->system = lacpdu->actor_system; @@ -459,10 +463,12 @@ static void __record_pdu(struct lacpdu *lacpdu, struct port *port) partner->key = ntohs(lacpdu->actor_key); partner->port_state = lacpdu->actor_state; - // set actor_oper_port_state.defaulted to FALSE + /* set actor_oper_port_state.defaulted to FALSE */ port->actor_oper_port_state &= ~AD_STATE_DEFAULTED; - // set the partner sync. to on if the partner is sync. and the port is matched + /* set the partner sync. to on if the partner is sync, + * and the port is matched + */ if ((port->sm_vars & AD_PORT_MATCHED) && (lacpdu->actor_state & AD_STATE_SYNCHRONIZATION)) partner->port_state |= AD_STATE_SYNCHRONIZATION; @@ -482,11 +488,11 @@ static void __record_pdu(struct lacpdu *lacpdu, struct port *port) static void __record_default(struct port *port) { if (port) { - // record the partner admin parameters + /* record the partner admin parameters */ memcpy(&port->partner_oper, &port->partner_admin, sizeof(struct port_params)); - // set actor_oper_port_state.defaulted to true + /* set actor_oper_port_state.defaulted to true */ port->actor_oper_port_state |= AD_STATE_DEFAULTED; } } @@ -591,36 +597,6 @@ static void __update_ntt(struct lacpdu *lacpdu, struct port *port) } /** - * __attach_bond_to_agg - * @port: the port we're looking at - * - * Handle the attaching of the port's control parser/multiplexer and the - * aggregator. This function does nothing since the parser/multiplexer of the - * receive and the parser/multiplexer of the aggregator are already combined. - */ -static void __attach_bond_to_agg(struct port *port) -{ - port = NULL; /* just to satisfy the compiler */ - // This function does nothing since the parser/multiplexer of the receive - // and the parser/multiplexer of the aggregator are already combined -} - -/** - * __detach_bond_from_agg - * @port: the port we're looking at - * - * Handle the detaching of the port's control parser/multiplexer from the - * aggregator. This function does nothing since the parser/multiplexer of the - * receive and the parser/multiplexer of the aggregator are already combined. - */ -static void __detach_bond_from_agg(struct port *port) -{ - port = NULL; /* just to satisfy the compiler */ - // This function does nothing since the parser/multiplexer of the receive - // and the parser/multiplexer of the aggregator are already combined -} - -/** * __agg_ports_are_ready - check if all ports in an aggregator are ready * @aggregator: the aggregator we're looking at * @@ -631,7 +607,9 @@ static int __agg_ports_are_ready(struct aggregator *aggregator) int retval = 1; if (aggregator) { - // scan all ports in this aggregator to verfy if they are all ready + /* scan all ports in this aggregator to verfy if they are + * all ready. + */ for (port = aggregator->lag_ports; port; port = port->next_port_in_aggregator) { @@ -691,7 +669,7 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) bandwidth = aggregator->num_of_ports * 10000; break; default: - bandwidth = 0; /*to silence the compiler ....*/ + bandwidth = 0; /* to silence the compiler */ } } return bandwidth; @@ -701,6 +679,7 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) * __get_active_agg - get the current active aggregator * @aggregator: the aggregator we're looking at * + * Caller must hold RCU lock. */ static struct aggregator *__get_active_agg(struct aggregator *aggregator) { @@ -708,13 +687,9 @@ static struct aggregator *__get_active_agg(struct aggregator *aggregator) struct list_head *iter; struct slave *slave; - rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) - if (SLAVE_AD_INFO(slave).aggregator.is_active) { - rcu_read_unlock(); + if (SLAVE_AD_INFO(slave).aggregator.is_active) return &(SLAVE_AD_INFO(slave).aggregator); - } - rcu_read_unlock(); return NULL; } @@ -722,15 +697,14 @@ static struct aggregator *__get_active_agg(struct aggregator *aggregator) /** * __update_lacpdu_from_port - update a port's lacpdu fields * @port: the port we're looking at - * */ static inline void __update_lacpdu_from_port(struct port *port) { struct lacpdu *lacpdu = &port->lacpdu; const struct port_params *partner = &port->partner_oper; - /* update current actual Actor parameters */ - /* lacpdu->subtype initialized + /* update current actual Actor parameters + * lacpdu->subtype initialized * lacpdu->version_number initialized * lacpdu->tlv_type_actor_info initialized * lacpdu->actor_information_length initialized @@ -766,9 +740,7 @@ static inline void __update_lacpdu_from_port(struct port *port) */ } -////////////////////////////////////////////////////////////////////////////////////// -// ================= main 802.3ad protocol code ====================================== -////////////////////////////////////////////////////////////////////////////////////// +/* ================= main 802.3ad protocol code ========================= */ /** * ad_lacpdu_send - send out a lacpdu packet on a given port @@ -798,11 +770,12 @@ static int ad_lacpdu_send(struct port *port) memcpy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); /* Note: source address is set to be the member's PERMANENT address, - because we use it to identify loopback lacpdus in receive. */ + * because we use it to identify loopback lacpdus in receive. + */ memcpy(lacpdu_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU; - lacpdu_header->lacpdu = port->lacpdu; // struct copy + lacpdu_header->lacpdu = port->lacpdu; dev_queue_xmit(skb); @@ -839,11 +812,12 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) memcpy(marker_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); /* Note: source address is set to be the member's PERMANENT address, - because we use it to identify loopback MARKERs in receive. */ + * because we use it to identify loopback MARKERs in receive. + */ memcpy(marker_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); marker_header->hdr.h_proto = PKT_TYPE_LACPDU; - marker_header->marker = *marker; // struct copy + marker_header->marker = *marker; dev_queue_xmit(skb); @@ -853,72 +827,90 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) /** * ad_mux_machine - handle a port's mux state machine * @port: the port we're looking at - * */ static void ad_mux_machine(struct port *port) { mux_states_t last_state; - // keep current State Machine state to compare later if it was changed + /* keep current State Machine state to compare later if it was + * changed + */ last_state = port->sm_mux_state; if (port->sm_vars & AD_PORT_BEGIN) { - port->sm_mux_state = AD_MUX_DETACHED; // next state + port->sm_mux_state = AD_MUX_DETACHED; } else { switch (port->sm_mux_state) { case AD_MUX_DETACHED: if ((port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY)) /* if SELECTED or STANDBY */ - port->sm_mux_state = AD_MUX_WAITING; // next state + port->sm_mux_state = AD_MUX_WAITING; break; case AD_MUX_WAITING: - // if SELECTED == FALSE return to DETACH state - if (!(port->sm_vars & AD_PORT_SELECTED)) { // if UNSELECTED + /* if SELECTED == FALSE return to DETACH state */ + if (!(port->sm_vars & AD_PORT_SELECTED)) { port->sm_vars &= ~AD_PORT_READY_N; - // in order to withhold the Selection Logic to check all ports READY_N value - // every callback cycle to update ready variable, we check READY_N and update READY here + /* in order to withhold the Selection Logic to + * check all ports READY_N value every callback + * cycle to update ready variable, we check + * READY_N and update READY here + */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); - port->sm_mux_state = AD_MUX_DETACHED; // next state + port->sm_mux_state = AD_MUX_DETACHED; break; } - // check if the wait_while_timer expired + /* check if the wait_while_timer expired */ if (port->sm_mux_timer_counter && !(--port->sm_mux_timer_counter)) port->sm_vars |= AD_PORT_READY_N; - // in order to withhold the selection logic to check all ports READY_N value - // every callback cycle to update ready variable, we check READY_N and update READY here + /* in order to withhold the selection logic to check + * all ports READY_N value every callback cycle to + * update ready variable, we check READY_N and update + * READY here + */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); - // if the wait_while_timer expired, and the port is in READY state, move to ATTACHED state + /* if the wait_while_timer expired, and the port is + * in READY state, move to ATTACHED state + */ if ((port->sm_vars & AD_PORT_READY) && !port->sm_mux_timer_counter) - port->sm_mux_state = AD_MUX_ATTACHED; // next state + port->sm_mux_state = AD_MUX_ATTACHED; break; case AD_MUX_ATTACHED: - // check also if agg_select_timer expired(so the edable port will take place only after this timer) - if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & AD_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { - port->sm_mux_state = AD_MUX_COLLECTING_DISTRIBUTING;// next state - } else if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY)) { // if UNSELECTED or STANDBY + /* check also if agg_select_timer expired (so the + * edable port will take place only after this timer) + */ + if ((port->sm_vars & AD_PORT_SELECTED) && + (port->partner_oper.port_state & AD_STATE_SYNCHRONIZATION) && + !__check_agg_selection_timer(port)) { + port->sm_mux_state = AD_MUX_COLLECTING_DISTRIBUTING; + } else if (!(port->sm_vars & AD_PORT_SELECTED) || + (port->sm_vars & AD_PORT_STANDBY)) { + /* if UNSELECTED or STANDBY */ port->sm_vars &= ~AD_PORT_READY_N; - // in order to withhold the selection logic to check all ports READY_N value - // every callback cycle to update ready variable, we check READY_N and update READY here + /* in order to withhold the selection logic to + * check all ports READY_N value every callback + * cycle to update ready variable, we check + * READY_N and update READY here + */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); - port->sm_mux_state = AD_MUX_DETACHED;// next state + port->sm_mux_state = AD_MUX_DETACHED; } break; case AD_MUX_COLLECTING_DISTRIBUTING: - if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY) || - !(port->partner_oper.port_state & AD_STATE_SYNCHRONIZATION) - ) { - port->sm_mux_state = AD_MUX_ATTACHED;// next state - + if (!(port->sm_vars & AD_PORT_SELECTED) || + (port->sm_vars & AD_PORT_STANDBY) || + !(port->partner_oper.port_state & AD_STATE_SYNCHRONIZATION)) { + port->sm_mux_state = AD_MUX_ATTACHED; } else { - // if port state hasn't changed make - // sure that a collecting distributing - // port in an active aggregator is enabled + /* if port state hasn't changed make + * sure that a collecting distributing + * port in an active aggregator is enabled + */ if (port->aggregator && port->aggregator->is_active && !__port_is_enabled(port)) { @@ -927,19 +919,18 @@ static void ad_mux_machine(struct port *port) } } break; - default: //to silence the compiler + default: break; } } - // check if the state machine was changed + /* check if the state machine was changed */ if (port->sm_mux_state != last_state) { pr_debug("Mux Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_mux_state); switch (port->sm_mux_state) { case AD_MUX_DETACHED: - __detach_bond_from_agg(port); port->actor_oper_port_state &= ~AD_STATE_SYNCHRONIZATION; ad_disable_collecting_distributing(port); port->actor_oper_port_state &= ~AD_STATE_COLLECTING; @@ -950,7 +941,6 @@ static void ad_mux_machine(struct port *port) port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); break; case AD_MUX_ATTACHED: - __attach_bond_to_agg(port); port->actor_oper_port_state |= AD_STATE_SYNCHRONIZATION; port->actor_oper_port_state &= ~AD_STATE_COLLECTING; port->actor_oper_port_state &= ~AD_STATE_DISTRIBUTING; @@ -963,7 +953,7 @@ static void ad_mux_machine(struct port *port) ad_enable_collecting_distributing(port); port->ntt = true; break; - default: //to silence the compiler + default: break; } } @@ -982,59 +972,63 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) { rx_states_t last_state; - // keep current State Machine state to compare later if it was changed + /* keep current State Machine state to compare later if it was + * changed + */ last_state = port->sm_rx_state; - // check if state machine should change state - // first, check if port was reinitialized + /* check if state machine should change state */ + + /* first, check if port was reinitialized */ if (port->sm_vars & AD_PORT_BEGIN) - /* next state */ port->sm_rx_state = AD_RX_INITIALIZE; - // check if port is not enabled + /* check if port is not enabled */ else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED)) - /* next state */ port->sm_rx_state = AD_RX_PORT_DISABLED; - // check if new lacpdu arrived - else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) || (port->sm_rx_state == AD_RX_DEFAULTED) || (port->sm_rx_state == AD_RX_CURRENT))) { - port->sm_rx_timer_counter = 0; // zero timer + /* check if new lacpdu arrived */ + else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) || + (port->sm_rx_state == AD_RX_DEFAULTED) || + (port->sm_rx_state == AD_RX_CURRENT))) { + port->sm_rx_timer_counter = 0; port->sm_rx_state = AD_RX_CURRENT; } else { - // if timer is on, and if it is expired - if (port->sm_rx_timer_counter && !(--port->sm_rx_timer_counter)) { + /* if timer is on, and if it is expired */ + if (port->sm_rx_timer_counter && + !(--port->sm_rx_timer_counter)) { switch (port->sm_rx_state) { case AD_RX_EXPIRED: - port->sm_rx_state = AD_RX_DEFAULTED; // next state + port->sm_rx_state = AD_RX_DEFAULTED; break; case AD_RX_CURRENT: - port->sm_rx_state = AD_RX_EXPIRED; // next state + port->sm_rx_state = AD_RX_EXPIRED; break; - default: //to silence the compiler + default: break; } } else { - // if no lacpdu arrived and no timer is on + /* if no lacpdu arrived and no timer is on */ switch (port->sm_rx_state) { case AD_RX_PORT_DISABLED: if (port->sm_vars & AD_PORT_MOVED) - port->sm_rx_state = AD_RX_INITIALIZE; // next state + port->sm_rx_state = AD_RX_INITIALIZE; else if (port->is_enabled && (port->sm_vars & AD_PORT_LACP_ENABLED)) - port->sm_rx_state = AD_RX_EXPIRED; // next state + port->sm_rx_state = AD_RX_EXPIRED; else if (port->is_enabled && ((port->sm_vars & AD_PORT_LACP_ENABLED) == 0)) - port->sm_rx_state = AD_RX_LACP_DISABLED; // next state + port->sm_rx_state = AD_RX_LACP_DISABLED; break; - default: //to silence the compiler + default: break; } } } - // check if the State machine was changed or new lacpdu arrived + /* check if the State machine was changed or new lacpdu arrived */ if ((port->sm_rx_state != last_state) || (lacpdu)) { pr_debug("Rx Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, @@ -1049,10 +1043,9 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) __record_default(port); port->actor_oper_port_state &= ~AD_STATE_EXPIRED; port->sm_vars &= ~AD_PORT_MOVED; - port->sm_rx_state = AD_RX_PORT_DISABLED; // next state - - /*- Fall Through -*/ + port->sm_rx_state = AD_RX_PORT_DISABLED; + /* Fall Through */ case AD_RX_PORT_DISABLED: port->sm_vars &= ~AD_PORT_MATCHED; break; @@ -1064,13 +1057,15 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->actor_oper_port_state &= ~AD_STATE_EXPIRED; break; case AD_RX_EXPIRED: - //Reset of the Synchronization flag. (Standard 43.4.12) - //This reset cause to disable this port in the COLLECTING_DISTRIBUTING state of the - //mux machine in case of EXPIRED even if LINK_DOWN didn't arrive for the port. + /* Reset of the Synchronization flag (Standard 43.4.12) + * This reset cause to disable this port in the + * COLLECTING_DISTRIBUTING state of the mux machine in + * case of EXPIRED even if LINK_DOWN didn't arrive for + * the port. + */ port->partner_oper.port_state &= ~AD_STATE_SYNCHRONIZATION; port->sm_vars &= ~AD_PORT_MATCHED; - port->partner_oper.port_state |= - AD_STATE_LACP_ACTIVITY; + port->partner_oper.port_state |= AD_STATE_LACP_ACTIVITY; port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT)); port->actor_oper_port_state |= AD_STATE_EXPIRED; break; @@ -1082,10 +1077,11 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) break; case AD_RX_CURRENT: /* detect loopback situation */ - if (MAC_ADDRESS_EQUAL(&(lacpdu->actor_system), &(port->actor_system))) { - pr_err("%s: An illegal loopback occurred on adapter (%s).\n" - "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", - port->slave->bond->dev->name, port->slave->dev->name); + if (MAC_ADDRESS_EQUAL(&(lacpdu->actor_system), + &(port->actor_system))) { + pr_err("%s: An illegal loopback occurred on adapter (%s).\nCheck the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", + port->slave->bond->dev->name, + port->slave->dev->name); return; } __update_selected(lacpdu, port); @@ -1094,7 +1090,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(port->actor_oper_port_state & AD_STATE_LACP_TIMEOUT)); port->actor_oper_port_state &= ~AD_STATE_EXPIRED; break; - default: /* to silence the compiler */ + default: break; } } @@ -1103,13 +1099,14 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) /** * ad_tx_machine - handle a port's tx state machine * @port: the port we're looking at - * */ static void ad_tx_machine(struct port *port) { - // check if tx timer expired, to verify that we do not send more than 3 packets per second + /* check if tx timer expired, to verify that we do not send more than + * 3 packets per second + */ if (port->sm_tx_timer_counter && !(--port->sm_tx_timer_counter)) { - // check if there is something to send + /* check if there is something to send */ if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) { __update_lacpdu_from_port(port); @@ -1117,14 +1114,16 @@ static void ad_tx_machine(struct port *port) pr_debug("Sent LACPDU on port %d\n", port->actor_port_number); - /* mark ntt as false, so it will not be sent again until - demanded */ + /* mark ntt as false, so it will not be sent + * again until demanded + */ port->ntt = false; } } - // restart tx timer(to verify that we will not exceed AD_MAX_TX_IN_SECOND - port->sm_tx_timer_counter = - ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; + /* restart tx timer(to verify that we will not exceed + * AD_MAX_TX_IN_SECOND + */ + port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; } } @@ -1138,76 +1137,79 @@ static void ad_periodic_machine(struct port *port) { periodic_states_t last_state; - // keep current state machine state to compare later if it was changed + /* keep current state machine state to compare later if it was changed */ last_state = port->sm_periodic_state; - // check if port was reinitialized + /* check if port was reinitialized */ if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || (!(port->actor_oper_port_state & AD_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & AD_STATE_LACP_ACTIVITY)) ) { - port->sm_periodic_state = AD_NO_PERIODIC; // next state + port->sm_periodic_state = AD_NO_PERIODIC; } - // check if state machine should change state + /* check if state machine should change state */ else if (port->sm_periodic_timer_counter) { - // check if periodic state machine expired + /* check if periodic state machine expired */ if (!(--port->sm_periodic_timer_counter)) { - // if expired then do tx - port->sm_periodic_state = AD_PERIODIC_TX; // next state + /* if expired then do tx */ + port->sm_periodic_state = AD_PERIODIC_TX; } else { - // If not expired, check if there is some new timeout parameter from the partner state + /* If not expired, check if there is some new timeout + * parameter from the partner state + */ switch (port->sm_periodic_state) { case AD_FAST_PERIODIC: if (!(port->partner_oper.port_state & AD_STATE_LACP_TIMEOUT)) - port->sm_periodic_state = AD_SLOW_PERIODIC; // next state + port->sm_periodic_state = AD_SLOW_PERIODIC; break; case AD_SLOW_PERIODIC: if ((port->partner_oper.port_state & AD_STATE_LACP_TIMEOUT)) { - // stop current timer port->sm_periodic_timer_counter = 0; - port->sm_periodic_state = AD_PERIODIC_TX; // next state + port->sm_periodic_state = AD_PERIODIC_TX; } break; - default: //to silence the compiler + default: break; } } } else { switch (port->sm_periodic_state) { case AD_NO_PERIODIC: - port->sm_periodic_state = AD_FAST_PERIODIC; // next state + port->sm_periodic_state = AD_FAST_PERIODIC; break; case AD_PERIODIC_TX: - if (!(port->partner_oper.port_state - & AD_STATE_LACP_TIMEOUT)) - port->sm_periodic_state = AD_SLOW_PERIODIC; // next state + if (!(port->partner_oper.port_state & + AD_STATE_LACP_TIMEOUT)) + port->sm_periodic_state = AD_SLOW_PERIODIC; else - port->sm_periodic_state = AD_FAST_PERIODIC; // next state + port->sm_periodic_state = AD_FAST_PERIODIC; break; - default: //to silence the compiler + default: break; } } - // check if the state machine was changed + /* check if the state machine was changed */ if (port->sm_periodic_state != last_state) { pr_debug("Periodic Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_periodic_state); switch (port->sm_periodic_state) { case AD_NO_PERIODIC: - port->sm_periodic_timer_counter = 0; // zero timer + port->sm_periodic_timer_counter = 0; break; case AD_FAST_PERIODIC: - port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_FAST_PERIODIC_TIME))-1; // decrement 1 tick we lost in the PERIODIC_TX cycle + /* decrement 1 tick we lost in the PERIODIC_TX cycle */ + port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_FAST_PERIODIC_TIME))-1; break; case AD_SLOW_PERIODIC: - port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_SLOW_PERIODIC_TIME))-1; // decrement 1 tick we lost in the PERIODIC_TX cycle + /* decrement 1 tick we lost in the PERIODIC_TX cycle */ + port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_SLOW_PERIODIC_TIME))-1; break; case AD_PERIODIC_TX: port->ntt = true; break; - default: //to silence the compiler + default: break; } } @@ -1230,30 +1232,38 @@ static void ad_port_selection_logic(struct port *port) struct slave *slave; int found = 0; - // if the port is already Selected, do nothing + /* if the port is already Selected, do nothing */ if (port->sm_vars & AD_PORT_SELECTED) return; bond = __get_bond_by_port(port); - // if the port is connected to other aggregator, detach it + /* if the port is connected to other aggregator, detach it */ if (port->aggregator) { - // detach the port from its former aggregator + /* detach the port from its former aggregator */ temp_aggregator = port->aggregator; for (curr_port = temp_aggregator->lag_ports; curr_port; last_port = curr_port, - curr_port = curr_port->next_port_in_aggregator) { + curr_port = curr_port->next_port_in_aggregator) { if (curr_port == port) { temp_aggregator->num_of_ports--; - if (!last_port) {// if it is the first port attached to the aggregator + /* if it is the first port attached to the + * aggregator + */ + if (!last_port) { temp_aggregator->lag_ports = port->next_port_in_aggregator; - } else {// not the first port attached to the aggregator + } else { + /* not the first port attached to the + * aggregator + */ last_port->next_port_in_aggregator = port->next_port_in_aggregator; } - // clear the port's relations to this aggregator + /* clear the port's relations to this + * aggregator + */ port->aggregator = NULL; port->next_port_in_aggregator = NULL; port->actor_port_aggregator_identifier = 0; @@ -1261,25 +1271,30 @@ static void ad_port_selection_logic(struct port *port) pr_debug("Port %d left LAG %d\n", port->actor_port_number, temp_aggregator->aggregator_identifier); - // if the aggregator is empty, clear its parameters, and set it ready to be attached + /* if the aggregator is empty, clear its + * parameters, and set it ready to be attached + */ if (!temp_aggregator->lag_ports) ad_clear_agg(temp_aggregator); break; } } - if (!curr_port) { // meaning: the port was related to an aggregator but was not on the aggregator port list - pr_warning("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n", - port->slave->bond->dev->name, - port->actor_port_number, - port->slave->dev->name, - port->aggregator->aggregator_identifier); + if (!curr_port) { + /* meaning: the port was related to an aggregator + * but was not on the aggregator port list + */ + pr_warn("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n", + port->slave->bond->dev->name, + port->actor_port_number, + port->slave->dev->name, + port->aggregator->aggregator_identifier); } } - // search on all aggregators for a suitable aggregator for this port + /* search on all aggregators for a suitable aggregator for this port */ bond_for_each_slave(bond, slave, iter) { aggregator = &(SLAVE_AD_INFO(slave).aggregator); - // keep a free aggregator for later use(if needed) + /* keep a free aggregator for later use(if needed) */ if (!aggregator->lag_ports) { if (!free_aggregator) free_aggregator = aggregator; @@ -1306,23 +1321,26 @@ static void ad_port_selection_logic(struct port *port) port->actor_port_number, port->aggregator->aggregator_identifier); - // mark this port as selected + /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; found = 1; break; } } - // the port couldn't find an aggregator - attach it to a new aggregator + /* the port couldn't find an aggregator - attach it to a new + * aggregator + */ if (!found) { if (free_aggregator) { - // assign port a new aggregator + /* assign port a new aggregator */ port->aggregator = free_aggregator; port->actor_port_aggregator_identifier = port->aggregator->aggregator_identifier; - // update the new aggregator's parameters - // if port was responsed from the end-user + /* update the new aggregator's parameters + * if port was responsed from the end-user + */ if (port->actor_oper_port_key & AD_DUPLEX_KEY_BITS) /* if port is full duplex */ port->aggregator->is_individual = false; @@ -1341,7 +1359,7 @@ static void ad_port_selection_logic(struct port *port) port->aggregator->lag_ports = port; port->aggregator->num_of_ports++; - // mark this port as selected + /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; pr_debug("Port %d joined LAG %d(new LAG)\n", @@ -1353,23 +1371,24 @@ static void ad_port_selection_logic(struct port *port) port->actor_port_number, port->slave->dev->name); } } - // if all aggregator's ports are READY_N == TRUE, set ready=TRUE in all aggregator's ports - // else set ready=FALSE in all aggregator's ports - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + /* if all aggregator's ports are READY_N == TRUE, set ready=TRUE + * in all aggregator's ports, else set ready=FALSE in all + * aggregator's ports + */ + __set_agg_ports_ready(port->aggregator, + __agg_ports_are_ready(port->aggregator)); aggregator = __get_first_agg(port); ad_agg_selection_logic(aggregator); } -/* - * Decide if "agg" is a better choice for the new active aggregator that +/* Decide if "agg" is a better choice for the new active aggregator that * the current best, according to the ad_select policy. */ static struct aggregator *ad_agg_selection_test(struct aggregator *best, struct aggregator *curr) { - /* - * 0. If no best, select current. + /* 0. If no best, select current. * * 1. If the current agg is not individual, and the best is * individual, select current. @@ -1425,9 +1444,9 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, break; default: - pr_warning("%s: Impossible agg select mode %d\n", - curr->slave->bond->dev->name, - __get_agg_selection_mode(curr->lag_ports)); + pr_warn("%s: Impossible agg select mode %d\n", + curr->slave->bond->dev->name, + __get_agg_selection_mode(curr->lag_ports)); break; } @@ -1437,10 +1456,12 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, static int agg_device_up(const struct aggregator *agg) { struct port *port = agg->lag_ports; + if (!port) return 0; - return (netif_running(port->slave->dev) && - netif_carrier_ok(port->slave->dev)); + + return netif_running(port->slave->dev) && + netif_carrier_ok(port->slave->dev); } /** @@ -1476,11 +1497,11 @@ static void ad_agg_selection_logic(struct aggregator *agg) struct slave *slave; struct port *port; + rcu_read_lock(); origin = agg; active = __get_active_agg(agg); best = (active && agg_device_up(active)) ? active : NULL; - rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { agg = &(SLAVE_AD_INFO(slave).aggregator); @@ -1492,8 +1513,7 @@ static void ad_agg_selection_logic(struct aggregator *agg) if (best && __get_agg_selection_mode(best->lag_ports) == BOND_AD_STABLE) { - /* - * For the STABLE policy, don't replace the old active + /* For the STABLE policy, don't replace the old active * aggregator if it's still active (it has an answering * partner) or if both the best and active don't have an * answering partner. @@ -1501,7 +1521,8 @@ static void ad_agg_selection_logic(struct aggregator *agg) if (active && active->lag_ports && active->lag_ports->is_enabled && (__agg_has_partner(active) || - (!__agg_has_partner(active) && !__agg_has_partner(best)))) { + (!__agg_has_partner(active) && + !__agg_has_partner(best)))) { if (!(!active->actor_oper_aggregator_key && best->actor_oper_aggregator_key)) { best = NULL; @@ -1538,7 +1559,7 @@ static void ad_agg_selection_logic(struct aggregator *agg) /* check if any partner replys */ if (best->is_individual) { - pr_warning("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n", + pr_warn("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n", best->slave ? best->slave->bond->dev->name : "NULL"); } @@ -1552,7 +1573,9 @@ static void ad_agg_selection_logic(struct aggregator *agg) best->partner_oper_aggregator_key, best->is_individual, best->is_active); - /* disable the ports that were related to the former active_aggregator */ + /* disable the ports that were related to the former + * active_aggregator + */ if (active) { for (port = active->lag_ports; port; port = port->next_port_in_aggregator) { @@ -1561,8 +1584,7 @@ static void ad_agg_selection_logic(struct aggregator *agg) } } - /* - * if the selected aggregator is of join individuals + /* if the selected aggregator is of join individuals * (partner_system is NULL), enable their ports */ active = __get_active_agg(origin); @@ -1584,7 +1606,6 @@ static void ad_agg_selection_logic(struct aggregator *agg) /** * ad_clear_agg - clear a given aggregator's parameters * @aggregator: the aggregator we're looking at - * */ static void ad_clear_agg(struct aggregator *aggregator) { @@ -1608,7 +1629,6 @@ static void ad_clear_agg(struct aggregator *aggregator) /** * ad_initialize_agg - initialize a given aggregator's parameters * @aggregator: the aggregator we're looking at - * */ static void ad_initialize_agg(struct aggregator *aggregator) { @@ -1625,7 +1645,6 @@ static void ad_initialize_agg(struct aggregator *aggregator) * ad_initialize_port - initialize a given port's parameters * @aggregator: the aggregator we're looking at * @lacp_fast: boolean. whether fast periodic should be used - * */ static void ad_initialize_port(struct port *port, int lacp_fast) { @@ -1657,8 +1676,10 @@ static void ad_initialize_port(struct port *port, int lacp_fast) port->ntt = false; port->actor_admin_port_key = 1; port->actor_oper_port_key = 1; - port->actor_admin_port_state = AD_STATE_AGGREGATION | AD_STATE_LACP_ACTIVITY; - port->actor_oper_port_state = AD_STATE_AGGREGATION | AD_STATE_LACP_ACTIVITY; + port->actor_admin_port_state = AD_STATE_AGGREGATION | + AD_STATE_LACP_ACTIVITY; + port->actor_oper_port_state = AD_STATE_AGGREGATION | + AD_STATE_LACP_ACTIVITY; if (lacp_fast) port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT; @@ -1667,7 +1688,7 @@ static void ad_initialize_port(struct port *port, int lacp_fast) memcpy(&port->partner_oper, &tmpl, sizeof(tmpl)); port->is_enabled = true; - // ****** private parameters ****** + /* private parameters */ port->sm_vars = 0x3; port->sm_rx_state = 0; port->sm_rx_timer_counter = 0; @@ -1705,11 +1726,12 @@ static void ad_enable_collecting_distributing(struct port *port) /** * ad_disable_collecting_distributing - disable a port's transmit/receive * @port: the port we're looking at - * */ static void ad_disable_collecting_distributing(struct port *port) { - if (port->aggregator && !MAC_ADDRESS_EQUAL(&(port->aggregator->partner_system), &(null_mac_addr))) { + if (port->aggregator && + !MAC_ADDRESS_EQUAL(&(port->aggregator->partner_system), + &(null_mac_addr))) { pr_debug("Disabling port %d(LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); @@ -1717,66 +1739,22 @@ static void ad_disable_collecting_distributing(struct port *port) } } -#if 0 -/** - * ad_marker_info_send - send a marker information frame - * @port: the port we're looking at - * - * This function does nothing since we decided not to implement send and handle - * response for marker PDU's, in this stage, but only to respond to marker - * information. - */ -static void ad_marker_info_send(struct port *port) -{ - struct bond_marker marker; - u16 index; - - // fill the marker PDU with the appropriate values - marker.subtype = 0x02; - marker.version_number = 0x01; - marker.tlv_type = AD_MARKER_INFORMATION_SUBTYPE; - marker.marker_length = 0x16; - // convert requester_port to Big Endian - marker.requester_port = (((port->actor_port_number & 0xFF) << 8) |((u16)(port->actor_port_number & 0xFF00) >> 8)); - marker.requester_system = port->actor_system; - // convert requester_port(u32) to Big Endian - marker.requester_transaction_id = - (((++port->transaction_id & 0xFF) << 24) - | ((port->transaction_id & 0xFF00) << 8) - | ((port->transaction_id & 0xFF0000) >> 8) - | ((port->transaction_id & 0xFF000000) >> 24)); - marker.pad = 0; - marker.tlv_type_terminator = 0x00; - marker.terminator_length = 0x00; - for (index = 0; index < 90; index++) - marker.reserved_90[index] = 0; - - // send the marker information - if (ad_marker_send(port, &marker) >= 0) { - pr_debug("Sent Marker Information on port %d\n", - port->actor_port_number); - } -} -#endif - /** * ad_marker_info_received - handle receive of a Marker information frame * @marker_info: Marker info received * @port: the port we're looking at - * */ static void ad_marker_info_received(struct bond_marker *marker_info, struct port *port) { struct bond_marker marker; - // copy the received marker data to the response marker - //marker = *marker_info; + /* copy the received marker data to the response marker */ memcpy(&marker, marker_info, sizeof(struct bond_marker)); - // change the marker subtype to marker response + /* change the marker subtype to marker response */ marker.tlv_type = AD_MARKER_RESPONSE_SUBTYPE; - // send the marker response + /* send the marker response */ if (ad_marker_send(port, &marker) >= 0) { pr_debug("Sent Marker Response on port %d\n", port->actor_port_number); @@ -1793,22 +1771,21 @@ static void ad_marker_info_received(struct bond_marker *marker_info, * information. */ static void ad_marker_response_received(struct bond_marker *marker, - struct port *port) + struct port *port) { - marker = NULL; /* just to satisfy the compiler */ - port = NULL; /* just to satisfy the compiler */ - // DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW + marker = NULL; + port = NULL; + /* DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW */ } -////////////////////////////////////////////////////////////////////////////////////// -// ================= AD exported functions to the main bonding code ================== -////////////////////////////////////////////////////////////////////////////////////// +/* ========= AD exported functions to the main bonding code ========= */ -// Check aggregators status in team every T seconds +/* Check aggregators status in team every T seconds */ #define AD_AGGREGATOR_SELECTION_TIMER 8 -/* - * bond_3ad_initiate_agg_selection(struct bonding *bond) +/** + * bond_3ad_initiate_agg_selection - initate aggregator selection + * @bond: bonding struct * * Set the aggregation selection timer, to initiate an agg selection in * the very near future. Called during first initialization, and during @@ -1839,7 +1816,9 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) BOND_AD_INFO(bond).system.sys_priority = 0xFFFF; BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); - // initialize how many times this module is called in one second(should be about every 100ms) + /* initialize how many times this module is called in one + * second (should be about every 100ms) + */ ad_ticks_per_sec = tick_resolution; bond_3ad_initiate_agg_selection(bond, @@ -1874,21 +1853,21 @@ void bond_3ad_bind_slave(struct slave *slave) port->actor_port_number = SLAVE_AD_INFO(slave).id; /* key is determined according to the link speed, duplex and user key(which * is yet not supported) - * ------------------------------------------------------------ - * Port key : | User key | Speed |Duplex| - * ------------------------------------------------------------ - * 16 6 1 0 */ - port->actor_admin_port_key = 0; /* initialize this parameter */ + port->actor_admin_port_key = 0; port->actor_admin_port_key |= __get_duplex(port); port->actor_admin_port_key |= (__get_link_speed(port) << 1); port->actor_oper_port_key = port->actor_admin_port_key; - /* if the port is not full duplex, then the port should be not lacp Enabled */ + /* if the port is not full duplex, then the port should be not + * lacp Enabled + */ if (!(port->actor_oper_port_key & AD_DUPLEX_KEY_BITS)) port->sm_vars &= ~AD_PORT_LACP_ENABLED; /* actor system is the bond's system */ port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr; - /* tx timer(to verify that no more than MAX_TX_IN_SECOND lacpdu's are sent in one second) */ + /* tx timer(to verify that no more than MAX_TX_IN_SECOND + * lacpdu's are sent in one second) + */ port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; port->aggregator = NULL; port->next_port_in_aggregator = NULL; @@ -1925,16 +1904,13 @@ void bond_3ad_unbind_slave(struct slave *slave) struct slave *slave_iter; struct list_head *iter; - // find the aggregator related to this slave aggregator = &(SLAVE_AD_INFO(slave).aggregator); - - // find the port related to this slave port = &(SLAVE_AD_INFO(slave).port); - // if slave is null, the whole port is not initialized + /* if slave is null, the whole port is not initialized */ if (!port->slave) { - pr_warning("Warning: %s: Trying to unbind an uninitialized port on %s\n", - slave->bond->dev->name, slave->dev->name); + pr_warn("Warning: %s: Trying to unbind an uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } @@ -1946,34 +1922,42 @@ void bond_3ad_unbind_slave(struct slave *slave) __update_lacpdu_from_port(port); ad_lacpdu_send(port); - // check if this aggregator is occupied + /* check if this aggregator is occupied */ if (aggregator->lag_ports) { - // check if there are other ports related to this aggregator except - // the port related to this slave(thats ensure us that there is a - // reason to search for new aggregator, and that we will find one - if ((aggregator->lag_ports != port) || (aggregator->lag_ports->next_port_in_aggregator)) { - // find new aggregator for the related port(s) + /* check if there are other ports related to this aggregator + * except the port related to this slave(thats ensure us that + * there is a reason to search for new aggregator, and that we + * will find one + */ + if ((aggregator->lag_ports != port) || + (aggregator->lag_ports->next_port_in_aggregator)) { + /* find new aggregator for the related port(s) */ bond_for_each_slave(bond, slave_iter, iter) { new_aggregator = &(SLAVE_AD_INFO(slave_iter).aggregator); - // if the new aggregator is empty, or it is connected to our port only - if (!new_aggregator->lag_ports - || ((new_aggregator->lag_ports == port) - && !new_aggregator->lag_ports->next_port_in_aggregator)) + /* if the new aggregator is empty, or it is + * connected to our port only + */ + if (!new_aggregator->lag_ports || + ((new_aggregator->lag_ports == port) && + !new_aggregator->lag_ports->next_port_in_aggregator)) break; } if (!slave_iter) new_aggregator = NULL; - // if new aggregator found, copy the aggregator's parameters - // and connect the related lag_ports to the new aggregator + + /* if new aggregator found, copy the aggregator's + * parameters and connect the related lag_ports to the + * new aggregator + */ if ((new_aggregator) && ((!new_aggregator->lag_ports) || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator))) { pr_debug("Some port(s) related to LAG %d - replaceing with LAG %d\n", aggregator->aggregator_identifier, new_aggregator->aggregator_identifier); - if ((new_aggregator->lag_ports == port) && new_aggregator->is_active) { + if ((new_aggregator->lag_ports == port) && + new_aggregator->is_active) { pr_info("%s: Removing an active aggregator\n", aggregator->slave->bond->dev->name); - // select new active aggregator select_new_active_agg = 1; } @@ -1989,30 +1973,33 @@ void bond_3ad_unbind_slave(struct slave *slave) new_aggregator->is_active = aggregator->is_active; new_aggregator->num_of_ports = aggregator->num_of_ports; - // update the information that is written on the ports about the aggregator + /* update the information that is written on + * the ports about the aggregator + */ for (temp_port = aggregator->lag_ports; temp_port; temp_port = temp_port->next_port_in_aggregator) { temp_port->aggregator = new_aggregator; temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; } - // clear the aggregator ad_clear_agg(aggregator); if (select_new_active_agg) ad_agg_selection_logic(__get_first_agg(port)); } else { - pr_warning("%s: Warning: unbinding aggregator, and could not find a new aggregator for its ports\n", - slave->bond->dev->name); + pr_warn("%s: Warning: unbinding aggregator, and could not find a new aggregator for its ports\n", + slave->bond->dev->name); } - } else { // in case that the only port related to this aggregator is the one we want to remove + } else { + /* in case that the only port related to this + * aggregator is the one we want to remove + */ select_new_active_agg = aggregator->is_active; - // clear the aggregator ad_clear_agg(aggregator); if (select_new_active_agg) { pr_info("%s: Removing an active aggregator\n", slave->bond->dev->name); - // select new active aggregator + /* select new active aggregator */ temp_aggregator = __get_first_agg(port); if (temp_aggregator) ad_agg_selection_logic(temp_aggregator); @@ -2021,15 +2008,19 @@ void bond_3ad_unbind_slave(struct slave *slave) } pr_debug("Unbinding port %d\n", port->actor_port_number); - // find the aggregator that this port is connected to + + /* find the aggregator that this port is connected to */ bond_for_each_slave(bond, slave_iter, iter) { temp_aggregator = &(SLAVE_AD_INFO(slave_iter).aggregator); prev_port = NULL; - // search the port in the aggregator's related ports + /* search the port in the aggregator's related ports */ for (temp_port = temp_aggregator->lag_ports; temp_port; prev_port = temp_port, - temp_port = temp_port->next_port_in_aggregator) { - if (temp_port == port) { // the aggregator found - detach the port from this aggregator + temp_port = temp_port->next_port_in_aggregator) { + if (temp_port == port) { + /* the aggregator found - detach the port from + * this aggregator + */ if (prev_port) prev_port->next_port_in_aggregator = temp_port->next_port_in_aggregator; else @@ -2037,12 +2028,11 @@ void bond_3ad_unbind_slave(struct slave *slave) temp_aggregator->num_of_ports--; if (temp_aggregator->num_of_ports == 0) { select_new_active_agg = temp_aggregator->is_active; - // clear the aggregator ad_clear_agg(temp_aggregator); if (select_new_active_agg) { pr_info("%s: Removing an active aggregator\n", slave->bond->dev->name); - // select new active aggregator + /* select new active aggregator */ ad_agg_selection_logic(__get_first_agg(port)); } } @@ -2083,15 +2073,16 @@ void bond_3ad_state_machine_handler(struct work_struct *work) goto re_arm; /* check if agg_select_timer timer after initialize is timed out */ - if (BOND_AD_INFO(bond).agg_select_timer && !(--BOND_AD_INFO(bond).agg_select_timer)) { + if (BOND_AD_INFO(bond).agg_select_timer && + !(--BOND_AD_INFO(bond).agg_select_timer)) { slave = bond_first_slave_rcu(bond); port = slave ? &(SLAVE_AD_INFO(slave).port) : NULL; /* select the active aggregator for the bond */ if (port) { if (!port->slave) { - pr_warning("%s: Warning: bond's first port is uninitialized\n", - bond->dev->name); + pr_warn("%s: Warning: bond's first port is uninitialized\n", + bond->dev->name); goto re_arm; } @@ -2105,8 +2096,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work) bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave).port); if (!port->slave) { - pr_warning("%s: Warning: Found an uninitialized port\n", - bond->dev->name); + pr_warn("%s: Warning: Found an uninitialized port\n", + bond->dev->name); goto re_arm; } @@ -2145,7 +2136,8 @@ re_arm: * received frames (loopback). Since only the payload is given to this * function, it check for loopback. */ -static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u16 length) +static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, + u16 length) { struct port *port; int ret = RX_HANDLER_ANOTHER; @@ -2155,8 +2147,8 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u1 port = &(SLAVE_AD_INFO(slave).port); if (!port->slave) { - pr_warning("%s: Warning: port of slave %s is uninitialized\n", - slave->dev->name, slave->bond->dev->name); + pr_warn("%s: Warning: port of slave %s is uninitialized\n", + slave->dev->name, slave->bond->dev->name); return ret; } @@ -2173,7 +2165,9 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u1 case AD_TYPE_MARKER: ret = RX_HANDLER_CONSUMED; - // No need to convert fields to Little Endian since we don't use the marker's fields. + /* No need to convert fields to Little Endian since we + * don't use the marker's fields. + */ switch (((struct bond_marker *)lacpdu)->tlv_type) { case AD_MARKER_INFORMATION_SUBTYPE: @@ -2211,8 +2205,8 @@ void bond_3ad_adapter_speed_changed(struct slave *slave) /* if slave is null, the whole port is not initialized */ if (!port->slave) { - pr_warning("Warning: %s: speed changed for uninitialized port on %s\n", - slave->bond->dev->name, slave->dev->name); + pr_warn("Warning: %s: speed changed for uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } @@ -2244,8 +2238,8 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave) /* if slave is null, the whole port is not initialized */ if (!port->slave) { - pr_warning("%s: Warning: duplex changed for uninitialized port on %s\n", - slave->bond->dev->name, slave->dev->name); + pr_warn("%s: Warning: duplex changed for uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } @@ -2278,8 +2272,8 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) /* if slave is null, the whole port is not initialized */ if (!port->slave) { - pr_warning("Warning: %s: link status changed for uninitialized port on %s\n", - slave->bond->dev->name, slave->dev->name); + pr_warn("Warning: %s: link status changed for uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } @@ -2317,10 +2311,13 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) __release_state_machine_lock(port); } -/* - * set link state for bonding master: if we have an active - * aggregator, we're up, if not, we're down. Presumes that we cannot - * have an active aggregator if there are no slaves with link up. +/** + * bond_3ad_set_carrier - set link state for bonding master + * @bond - bonding structure + * + * if we have an active aggregator, we're up, if not, we're down. + * Presumes that we cannot have an active aggregator if there are + * no slaves with link up. * * This behavior complies with IEEE 802.3 section 43.3.9. * @@ -2331,32 +2328,32 @@ int bond_3ad_set_carrier(struct bonding *bond) { struct aggregator *active; struct slave *first_slave; + int ret = 1; rcu_read_lock(); first_slave = bond_first_slave_rcu(bond); - rcu_read_unlock(); - if (!first_slave) - return 0; + if (!first_slave) { + ret = 0; + goto out; + } active = __get_active_agg(&(SLAVE_AD_INFO(first_slave).aggregator)); if (active) { /* are enough slaves available to consider link up? */ if (active->num_of_ports < bond->params.min_links) { if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); - return 1; + goto out; } } else if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); - return 1; + goto out; } - return 0; - } - - if (netif_carrier_ok(bond->dev)) { + } else if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); - return 1; } - return 0; +out: + rcu_read_unlock(); + return ret; } /** @@ -2388,7 +2385,8 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond, ad_info->ports = aggregator->num_of_ports; ad_info->actor_key = aggregator->actor_oper_aggregator_key; ad_info->partner_key = aggregator->partner_oper_aggregator_key; - memcpy(ad_info->partner_system, aggregator->partner_system.mac_addr_value, ETH_ALEN); + memcpy(ad_info->partner_system, + aggregator->partner_system.mac_addr_value, ETH_ALEN); return 0; } @@ -2460,7 +2458,8 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) } /* we couldn't find any suitable slave after the agg_no, so use the - * first suitable found, if found. */ + * first suitable found, if found. + */ if (first_ok_slave) bond_dev_queue_xmit(bond, skb, first_ok_slave->dev); else @@ -2493,7 +2492,10 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, return ret; } -/* +/** + * bond_3ad_update_lacp_rate - change the lacp rate + * @bond - bonding struct + * * When modify lacp_rate parameter via sysfs, * update actor_oper_port_state of each port. * diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e06c4453eabb..7069b846a6ce 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3692,7 +3692,8 @@ static inline int bond_slave_override(struct bonding *bond, } -static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index 9142b473175c..c53384d41c96 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -252,7 +252,7 @@ static int el3_isa_id_sequence(__be16 *phys_addr) for (i = 0; i < el3_cards; i++) { struct el3_private *lp = netdev_priv(el3_devs[i]); if (lp->type == EL3_PNP && - ether_addr_equal(phys_addr, el3_devs[i]->dev_addr)) { + ether_addr_equal((u8 *)phys_addr, el3_devs[i]->dev_addr)) { if (el3_debug > 3) pr_debug("3c509 with address %02x %02x %02x %02x %02x %02x was found by ISAPnP\n", phys_addr[0] & 0xff, phys_addr[0] >> 8, diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index d71103dbf2cd..8fc93c5f6abc 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -106,6 +106,9 @@ struct alx_priv { u16 msg_enable; bool msi; + + /* protects hw.stats */ + spinlock_t stats_lock; }; extern const struct ethtool_ops alx_ethtool_ops; diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c index 45b36507abc1..08e22df2a300 100644 --- a/drivers/net/ethernet/atheros/alx/ethtool.c +++ b/drivers/net/ethernet/atheros/alx/ethtool.c @@ -46,6 +46,66 @@ #include "reg.h" #include "hw.h" +/* The order of these strings must match the order of the fields in + * struct alx_hw_stats + * See hw.h + */ +static const char alx_gstrings_stats[][ETH_GSTRING_LEN] = { + "rx_packets", + "rx_bcast_packets", + "rx_mcast_packets", + "rx_pause_packets", + "rx_ctrl_packets", + "rx_fcs_errors", + "rx_length_errors", + "rx_bytes", + "rx_runt_packets", + "rx_fragments", + "rx_64B_or_less_packets", + "rx_65B_to_127B_packets", + "rx_128B_to_255B_packets", + "rx_256B_to_511B_packets", + "rx_512B_to_1023B_packets", + "rx_1024B_to_1518B_packets", + "rx_1519B_to_mtu_packets", + "rx_oversize_packets", + "rx_rxf_ov_drop_packets", + "rx_rrd_ov_drop_packets", + "rx_align_errors", + "rx_bcast_bytes", + "rx_mcast_bytes", + "rx_address_errors", + "tx_packets", + "tx_bcast_packets", + "tx_mcast_packets", + "tx_pause_packets", + "tx_exc_defer_packets", + "tx_ctrl_packets", + "tx_defer_packets", + "tx_bytes", + "tx_64B_or_less_packets", + "tx_65B_to_127B_packets", + "tx_128B_to_255B_packets", + "tx_256B_to_511B_packets", + "tx_512B_to_1023B_packets", + "tx_1024B_to_1518B_packets", + "tx_1519B_to_mtu_packets", + "tx_single_collision", + "tx_multiple_collisions", + "tx_late_collision", + "tx_abort_collision", + "tx_underrun", + "tx_trd_eop", + "tx_length_errors", + "tx_trunc_packets", + "tx_bcast_bytes", + "tx_mcast_bytes", + "tx_update", +}; + +#define ALX_NUM_STATS ARRAY_SIZE(alx_gstrings_stats) + + static u32 alx_get_supported_speeds(struct alx_hw *hw) { u32 supported = SUPPORTED_10baseT_Half | @@ -201,6 +261,44 @@ static void alx_set_msglevel(struct net_device *netdev, u32 data) alx->msg_enable = data; } +static void alx_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *estats, u64 *data) +{ + struct alx_priv *alx = netdev_priv(netdev); + struct alx_hw *hw = &alx->hw; + + spin_lock(&alx->stats_lock); + + alx_update_hw_stats(hw); + BUILD_BUG_ON(sizeof(hw->stats) - offsetof(struct alx_hw_stats, rx_ok) < + ALX_NUM_STATS * sizeof(u64)); + memcpy(data, &hw->stats.rx_ok, ALX_NUM_STATS * sizeof(u64)); + + spin_unlock(&alx->stats_lock); +} + +static void alx_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) +{ + switch (stringset) { + case ETH_SS_STATS: + memcpy(buf, &alx_gstrings_stats, sizeof(alx_gstrings_stats)); + break; + default: + WARN_ON(1); + break; + } +} + +static int alx_get_sset_count(struct net_device *netdev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ALX_NUM_STATS; + default: + return -EINVAL; + } +} + const struct ethtool_ops alx_ethtool_ops = { .get_settings = alx_get_settings, .set_settings = alx_set_settings, @@ -209,4 +307,7 @@ const struct ethtool_ops alx_ethtool_ops = { .get_msglevel = alx_get_msglevel, .set_msglevel = alx_set_msglevel, .get_link = ethtool_op_get_link, + .get_strings = alx_get_strings, + .get_sset_count = alx_get_sset_count, + .get_ethtool_stats = alx_get_ethtool_stats, }; diff --git a/drivers/net/ethernet/atheros/alx/hw.c b/drivers/net/ethernet/atheros/alx/hw.c index 1e8c24a3cb4e..7712f068f6d4 100644 --- a/drivers/net/ethernet/atheros/alx/hw.c +++ b/drivers/net/ethernet/atheros/alx/hw.c @@ -1050,3 +1050,61 @@ bool alx_get_phy_info(struct alx_hw *hw) return true; } + +void alx_update_hw_stats(struct alx_hw *hw) +{ + /* RX stats */ + hw->stats.rx_ok += alx_read_mem32(hw, ALX_MIB_RX_OK); + hw->stats.rx_bcast += alx_read_mem32(hw, ALX_MIB_RX_BCAST); + hw->stats.rx_mcast += alx_read_mem32(hw, ALX_MIB_RX_MCAST); + hw->stats.rx_pause += alx_read_mem32(hw, ALX_MIB_RX_PAUSE); + hw->stats.rx_ctrl += alx_read_mem32(hw, ALX_MIB_RX_CTRL); + hw->stats.rx_fcs_err += alx_read_mem32(hw, ALX_MIB_RX_FCS_ERR); + hw->stats.rx_len_err += alx_read_mem32(hw, ALX_MIB_RX_LEN_ERR); + hw->stats.rx_byte_cnt += alx_read_mem32(hw, ALX_MIB_RX_BYTE_CNT); + hw->stats.rx_runt += alx_read_mem32(hw, ALX_MIB_RX_RUNT); + hw->stats.rx_frag += alx_read_mem32(hw, ALX_MIB_RX_FRAG); + hw->stats.rx_sz_64B += alx_read_mem32(hw, ALX_MIB_RX_SZ_64B); + hw->stats.rx_sz_127B += alx_read_mem32(hw, ALX_MIB_RX_SZ_127B); + hw->stats.rx_sz_255B += alx_read_mem32(hw, ALX_MIB_RX_SZ_255B); + hw->stats.rx_sz_511B += alx_read_mem32(hw, ALX_MIB_RX_SZ_511B); + hw->stats.rx_sz_1023B += alx_read_mem32(hw, ALX_MIB_RX_SZ_1023B); + hw->stats.rx_sz_1518B += alx_read_mem32(hw, ALX_MIB_RX_SZ_1518B); + hw->stats.rx_sz_max += alx_read_mem32(hw, ALX_MIB_RX_SZ_MAX); + hw->stats.rx_ov_sz += alx_read_mem32(hw, ALX_MIB_RX_OV_SZ); + hw->stats.rx_ov_rxf += alx_read_mem32(hw, ALX_MIB_RX_OV_RXF); + hw->stats.rx_ov_rrd += alx_read_mem32(hw, ALX_MIB_RX_OV_RRD); + hw->stats.rx_align_err += alx_read_mem32(hw, ALX_MIB_RX_ALIGN_ERR); + hw->stats.rx_bc_byte_cnt += alx_read_mem32(hw, ALX_MIB_RX_BCCNT); + hw->stats.rx_mc_byte_cnt += alx_read_mem32(hw, ALX_MIB_RX_MCCNT); + hw->stats.rx_err_addr += alx_read_mem32(hw, ALX_MIB_RX_ERRADDR); + + /* TX stats */ + hw->stats.tx_ok += alx_read_mem32(hw, ALX_MIB_TX_OK); + hw->stats.tx_bcast += alx_read_mem32(hw, ALX_MIB_TX_BCAST); + hw->stats.tx_mcast += alx_read_mem32(hw, ALX_MIB_TX_MCAST); + hw->stats.tx_pause += alx_read_mem32(hw, ALX_MIB_TX_PAUSE); + hw->stats.tx_exc_defer += alx_read_mem32(hw, ALX_MIB_TX_EXC_DEFER); + hw->stats.tx_ctrl += alx_read_mem32(hw, ALX_MIB_TX_CTRL); + hw->stats.tx_defer += alx_read_mem32(hw, ALX_MIB_TX_DEFER); + hw->stats.tx_byte_cnt += alx_read_mem32(hw, ALX_MIB_TX_BYTE_CNT); + hw->stats.tx_sz_64B += alx_read_mem32(hw, ALX_MIB_TX_SZ_64B); + hw->stats.tx_sz_127B += alx_read_mem32(hw, ALX_MIB_TX_SZ_127B); + hw->stats.tx_sz_255B += alx_read_mem32(hw, ALX_MIB_TX_SZ_255B); + hw->stats.tx_sz_511B += alx_read_mem32(hw, ALX_MIB_TX_SZ_511B); + hw->stats.tx_sz_1023B += alx_read_mem32(hw, ALX_MIB_TX_SZ_1023B); + hw->stats.tx_sz_1518B += alx_read_mem32(hw, ALX_MIB_TX_SZ_1518B); + hw->stats.tx_sz_max += alx_read_mem32(hw, ALX_MIB_TX_SZ_MAX); + hw->stats.tx_single_col += alx_read_mem32(hw, ALX_MIB_TX_SINGLE_COL); + hw->stats.tx_multi_col += alx_read_mem32(hw, ALX_MIB_TX_MULTI_COL); + hw->stats.tx_late_col += alx_read_mem32(hw, ALX_MIB_TX_LATE_COL); + hw->stats.tx_abort_col += alx_read_mem32(hw, ALX_MIB_TX_ABORT_COL); + hw->stats.tx_underrun += alx_read_mem32(hw, ALX_MIB_TX_UNDERRUN); + hw->stats.tx_trd_eop += alx_read_mem32(hw, ALX_MIB_TX_TRD_EOP); + hw->stats.tx_len_err += alx_read_mem32(hw, ALX_MIB_TX_LEN_ERR); + hw->stats.tx_trunc += alx_read_mem32(hw, ALX_MIB_TX_TRUNC); + hw->stats.tx_bc_byte_cnt += alx_read_mem32(hw, ALX_MIB_TX_BCCNT); + hw->stats.tx_mc_byte_cnt += alx_read_mem32(hw, ALX_MIB_TX_MCCNT); + + hw->stats.update += alx_read_mem32(hw, ALX_MIB_UPDATE); +} diff --git a/drivers/net/ethernet/atheros/alx/hw.h b/drivers/net/ethernet/atheros/alx/hw.h index 96f3b4381e17..15548802d6f8 100644 --- a/drivers/net/ethernet/atheros/alx/hw.h +++ b/drivers/net/ethernet/atheros/alx/hw.h @@ -381,6 +381,73 @@ struct alx_rrd { ALX_ISR_RX_Q6 | \ ALX_ISR_RX_Q7) +/* Statistics counters collected by the MAC + * + * The order of the fields must match the strings in alx_gstrings_stats + * All stats fields should be u64 + * See ethtool.c + */ +struct alx_hw_stats { + /* rx */ + u64 rx_ok; /* good RX packets */ + u64 rx_bcast; /* good RX broadcast packets */ + u64 rx_mcast; /* good RX multicast packets */ + u64 rx_pause; /* RX pause frames */ + u64 rx_ctrl; /* RX control packets other than pause frames */ + u64 rx_fcs_err; /* RX packets with bad FCS */ + u64 rx_len_err; /* RX packets with length != actual size */ + u64 rx_byte_cnt; /* good bytes received. FCS is NOT included */ + u64 rx_runt; /* RX packets < 64 bytes with good FCS */ + u64 rx_frag; /* RX packets < 64 bytes with bad FCS */ + u64 rx_sz_64B; /* 64 byte RX packets */ + u64 rx_sz_127B; /* 65-127 byte RX packets */ + u64 rx_sz_255B; /* 128-255 byte RX packets */ + u64 rx_sz_511B; /* 256-511 byte RX packets */ + u64 rx_sz_1023B; /* 512-1023 byte RX packets */ + u64 rx_sz_1518B; /* 1024-1518 byte RX packets */ + u64 rx_sz_max; /* 1519 byte to MTU RX packets */ + u64 rx_ov_sz; /* truncated RX packets, size > MTU */ + u64 rx_ov_rxf; /* frames dropped due to RX FIFO overflow */ + u64 rx_ov_rrd; /* frames dropped due to RRD overflow */ + u64 rx_align_err; /* alignment errors */ + u64 rx_bc_byte_cnt; /* RX broadcast bytes, excluding FCS */ + u64 rx_mc_byte_cnt; /* RX multicast bytes, excluding FCS */ + u64 rx_err_addr; /* packets dropped due to address filtering */ + + /* tx */ + u64 tx_ok; /* good TX packets */ + u64 tx_bcast; /* good TX broadcast packets */ + u64 tx_mcast; /* good TX multicast packets */ + u64 tx_pause; /* TX pause frames */ + u64 tx_exc_defer; /* TX packets deferred excessively */ + u64 tx_ctrl; /* TX control frames, excluding pause frames */ + u64 tx_defer; /* TX packets deferred */ + u64 tx_byte_cnt; /* bytes transmitted, FCS is NOT included */ + u64 tx_sz_64B; /* 64 byte TX packets */ + u64 tx_sz_127B; /* 65-127 byte TX packets */ + u64 tx_sz_255B; /* 128-255 byte TX packets */ + u64 tx_sz_511B; /* 256-511 byte TX packets */ + u64 tx_sz_1023B; /* 512-1023 byte TX packets */ + u64 tx_sz_1518B; /* 1024-1518 byte TX packets */ + u64 tx_sz_max; /* 1519 byte to MTU TX packets */ + u64 tx_single_col; /* packets TX after a single collision */ + u64 tx_multi_col; /* packets TX after multiple collisions */ + u64 tx_late_col; /* TX packets with late collisions */ + u64 tx_abort_col; /* TX packets aborted w/excessive collisions */ + u64 tx_underrun; /* TX packets aborted due to TX FIFO underrun + * or TRD FIFO underrun + */ + u64 tx_trd_eop; /* reads beyond the EOP into the next frame + * when TRD was not written timely + */ + u64 tx_len_err; /* TX packets where length != actual size */ + u64 tx_trunc; /* TX packets truncated due to size > MTU */ + u64 tx_bc_byte_cnt; /* broadcast bytes transmitted, excluding FCS */ + u64 tx_mc_byte_cnt; /* multicast bytes transmitted, excluding FCS */ + u64 update; +}; + + /* maximum interrupt vectors for msix */ #define ALX_MAX_MSIX_INTRS 16 @@ -424,6 +491,9 @@ struct alx_hw { /* PHY link patch flag */ bool lnk_patch; + + /* cumulated stats from the hardware (registers are cleared on read) */ + struct alx_hw_stats stats; }; static inline int alx_hw_revision(struct alx_hw *hw) @@ -491,6 +561,7 @@ bool alx_phy_configured(struct alx_hw *hw); void alx_configure_basic(struct alx_hw *hw); void alx_disable_rss(struct alx_hw *hw); bool alx_get_phy_info(struct alx_hw *hw); +void alx_update_hw_stats(struct alx_hw *hw); static inline u32 alx_speed_to_ethadv(int speed, u8 duplex) { diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index c3c4c266b846..e92ffd6e1c15 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1166,10 +1166,60 @@ static void alx_poll_controller(struct net_device *netdev) } #endif +static struct rtnl_link_stats64 *alx_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *net_stats) +{ + struct alx_priv *alx = netdev_priv(dev); + struct alx_hw_stats *hw_stats = &alx->hw.stats; + + spin_lock(&alx->stats_lock); + + alx_update_hw_stats(&alx->hw); + + net_stats->tx_bytes = hw_stats->tx_byte_cnt; + net_stats->rx_bytes = hw_stats->rx_byte_cnt; + net_stats->multicast = hw_stats->rx_mcast; + net_stats->collisions = hw_stats->tx_single_col + + hw_stats->tx_multi_col + + hw_stats->tx_late_col + + hw_stats->tx_abort_col; + + net_stats->rx_errors = hw_stats->rx_frag + + hw_stats->rx_fcs_err + + hw_stats->rx_len_err + + hw_stats->rx_ov_sz + + hw_stats->rx_ov_rrd + + hw_stats->rx_align_err + + hw_stats->rx_ov_rxf; + + net_stats->rx_fifo_errors = hw_stats->rx_ov_rxf; + net_stats->rx_length_errors = hw_stats->rx_len_err; + net_stats->rx_crc_errors = hw_stats->rx_fcs_err; + net_stats->rx_frame_errors = hw_stats->rx_align_err; + net_stats->rx_dropped = hw_stats->rx_ov_rrd; + + net_stats->tx_errors = hw_stats->tx_late_col + + hw_stats->tx_abort_col + + hw_stats->tx_underrun + + hw_stats->tx_trunc; + + net_stats->tx_aborted_errors = hw_stats->tx_abort_col; + net_stats->tx_fifo_errors = hw_stats->tx_underrun; + net_stats->tx_window_errors = hw_stats->tx_late_col; + + net_stats->tx_packets = hw_stats->tx_ok + net_stats->tx_errors; + net_stats->rx_packets = hw_stats->rx_ok + net_stats->rx_errors; + + spin_unlock(&alx->stats_lock); + + return net_stats; +} + static const struct net_device_ops alx_netdev_ops = { .ndo_open = alx_open, .ndo_stop = alx_stop, .ndo_start_xmit = alx_start_xmit, + .ndo_get_stats64 = alx_get_stats64, .ndo_set_rx_mode = alx_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = alx_set_mac_address, diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h index e4358c98bc4e..af006b44b2a6 100644 --- a/drivers/net/ethernet/atheros/alx/reg.h +++ b/drivers/net/ethernet/atheros/alx/reg.h @@ -404,15 +404,59 @@ /* MIB */ #define ALX_MIB_BASE 0x1700 + #define ALX_MIB_RX_OK (ALX_MIB_BASE + 0) +#define ALX_MIB_RX_BCAST (ALX_MIB_BASE + 4) +#define ALX_MIB_RX_MCAST (ALX_MIB_BASE + 8) +#define ALX_MIB_RX_PAUSE (ALX_MIB_BASE + 12) +#define ALX_MIB_RX_CTRL (ALX_MIB_BASE + 16) +#define ALX_MIB_RX_FCS_ERR (ALX_MIB_BASE + 20) +#define ALX_MIB_RX_LEN_ERR (ALX_MIB_BASE + 24) +#define ALX_MIB_RX_BYTE_CNT (ALX_MIB_BASE + 28) +#define ALX_MIB_RX_RUNT (ALX_MIB_BASE + 32) +#define ALX_MIB_RX_FRAG (ALX_MIB_BASE + 36) +#define ALX_MIB_RX_SZ_64B (ALX_MIB_BASE + 40) +#define ALX_MIB_RX_SZ_127B (ALX_MIB_BASE + 44) +#define ALX_MIB_RX_SZ_255B (ALX_MIB_BASE + 48) +#define ALX_MIB_RX_SZ_511B (ALX_MIB_BASE + 52) +#define ALX_MIB_RX_SZ_1023B (ALX_MIB_BASE + 56) +#define ALX_MIB_RX_SZ_1518B (ALX_MIB_BASE + 60) +#define ALX_MIB_RX_SZ_MAX (ALX_MIB_BASE + 64) +#define ALX_MIB_RX_OV_SZ (ALX_MIB_BASE + 68) +#define ALX_MIB_RX_OV_RXF (ALX_MIB_BASE + 72) +#define ALX_MIB_RX_OV_RRD (ALX_MIB_BASE + 76) +#define ALX_MIB_RX_ALIGN_ERR (ALX_MIB_BASE + 80) +#define ALX_MIB_RX_BCCNT (ALX_MIB_BASE + 84) +#define ALX_MIB_RX_MCCNT (ALX_MIB_BASE + 88) #define ALX_MIB_RX_ERRADDR (ALX_MIB_BASE + 92) + #define ALX_MIB_TX_OK (ALX_MIB_BASE + 96) +#define ALX_MIB_TX_BCAST (ALX_MIB_BASE + 100) +#define ALX_MIB_TX_MCAST (ALX_MIB_BASE + 104) +#define ALX_MIB_TX_PAUSE (ALX_MIB_BASE + 108) +#define ALX_MIB_TX_EXC_DEFER (ALX_MIB_BASE + 112) +#define ALX_MIB_TX_CTRL (ALX_MIB_BASE + 116) +#define ALX_MIB_TX_DEFER (ALX_MIB_BASE + 120) +#define ALX_MIB_TX_BYTE_CNT (ALX_MIB_BASE + 124) +#define ALX_MIB_TX_SZ_64B (ALX_MIB_BASE + 128) +#define ALX_MIB_TX_SZ_127B (ALX_MIB_BASE + 132) +#define ALX_MIB_TX_SZ_255B (ALX_MIB_BASE + 136) +#define ALX_MIB_TX_SZ_511B (ALX_MIB_BASE + 140) +#define ALX_MIB_TX_SZ_1023B (ALX_MIB_BASE + 144) +#define ALX_MIB_TX_SZ_1518B (ALX_MIB_BASE + 148) +#define ALX_MIB_TX_SZ_MAX (ALX_MIB_BASE + 152) +#define ALX_MIB_TX_SINGLE_COL (ALX_MIB_BASE + 156) +#define ALX_MIB_TX_MULTI_COL (ALX_MIB_BASE + 160) +#define ALX_MIB_TX_LATE_COL (ALX_MIB_BASE + 164) +#define ALX_MIB_TX_ABORT_COL (ALX_MIB_BASE + 168) +#define ALX_MIB_TX_UNDERRUN (ALX_MIB_BASE + 172) +#define ALX_MIB_TX_TRD_EOP (ALX_MIB_BASE + 176) +#define ALX_MIB_TX_LEN_ERR (ALX_MIB_BASE + 180) +#define ALX_MIB_TX_TRUNC (ALX_MIB_BASE + 184) +#define ALX_MIB_TX_BCCNT (ALX_MIB_BASE + 188) #define ALX_MIB_TX_MCCNT (ALX_MIB_BASE + 192) +#define ALX_MIB_UPDATE (ALX_MIB_BASE + 196) -#define ALX_RX_STATS_BIN ALX_MIB_RX_OK -#define ALX_RX_STATS_END ALX_MIB_RX_ERRADDR -#define ALX_TX_STATS_BIN ALX_MIB_TX_OK -#define ALX_TX_STATS_END ALX_MIB_TX_MCCNT #define ALX_ISR 0x1600 #define ALX_ISR_DIS BIT(31) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index eb105abcf0e7..9819a548e3b9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -520,10 +520,12 @@ struct bnx2x_fastpath { #define BNX2X_FP_STATE_IDLE 0 #define BNX2X_FP_STATE_NAPI (1 << 0) /* NAPI owns this FP */ #define BNX2X_FP_STATE_POLL (1 << 1) /* poll owns this FP */ -#define BNX2X_FP_STATE_NAPI_YIELD (1 << 2) /* NAPI yielded this FP */ -#define BNX2X_FP_STATE_POLL_YIELD (1 << 3) /* poll yielded this FP */ +#define BNX2X_FP_STATE_DISABLED (1 << 2) +#define BNX2X_FP_STATE_NAPI_YIELD (1 << 3) /* NAPI yielded this FP */ +#define BNX2X_FP_STATE_POLL_YIELD (1 << 4) /* poll yielded this FP */ +#define BNX2X_FP_OWNED (BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL) #define BNX2X_FP_YIELD (BNX2X_FP_STATE_NAPI_YIELD | BNX2X_FP_STATE_POLL_YIELD) -#define BNX2X_FP_LOCKED (BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL) +#define BNX2X_FP_LOCKED (BNX2X_FP_OWNED | BNX2X_FP_STATE_DISABLED) #define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD) /* protect state */ spinlock_t lock; @@ -613,7 +615,7 @@ static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp) { bool rc = true; - spin_lock(&fp->lock); + spin_lock_bh(&fp->lock); if (fp->state & BNX2X_FP_LOCKED) { WARN_ON(fp->state & BNX2X_FP_STATE_NAPI); fp->state |= BNX2X_FP_STATE_NAPI_YIELD; @@ -622,7 +624,7 @@ static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp) /* we don't care if someone yielded */ fp->state = BNX2X_FP_STATE_NAPI; } - spin_unlock(&fp->lock); + spin_unlock_bh(&fp->lock); return rc; } @@ -631,14 +633,16 @@ static inline bool bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp) { bool rc = false; - spin_lock(&fp->lock); + spin_lock_bh(&fp->lock); WARN_ON(fp->state & (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_NAPI_YIELD)); if (fp->state & BNX2X_FP_STATE_POLL_YIELD) rc = true; - fp->state = BNX2X_FP_STATE_IDLE; - spin_unlock(&fp->lock); + + /* state ==> idle, unless currently disabled */ + fp->state &= BNX2X_FP_STATE_DISABLED; + spin_unlock_bh(&fp->lock); return rc; } @@ -669,7 +673,9 @@ static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp) if (fp->state & BNX2X_FP_STATE_POLL_YIELD) rc = true; - fp->state = BNX2X_FP_STATE_IDLE; + + /* state ==> idle, unless currently disabled */ + fp->state &= BNX2X_FP_STATE_DISABLED; spin_unlock_bh(&fp->lock); return rc; } @@ -677,9 +683,23 @@ static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp) /* true if a socket is polling, even if it did not get the lock */ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp) { - WARN_ON(!(fp->state & BNX2X_FP_LOCKED)); + WARN_ON(!(fp->state & BNX2X_FP_OWNED)); return fp->state & BNX2X_FP_USER_PEND; } + +/* false if fp is currently owned */ +static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp) +{ + int rc = true; + + spin_lock_bh(&fp->lock); + if (fp->state & BNX2X_FP_OWNED) + rc = false; + fp->state |= BNX2X_FP_STATE_DISABLED; + spin_unlock_bh(&fp->lock); + + return rc; +} #else static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp) { @@ -709,6 +729,10 @@ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp) { return false; } +static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp) +{ + return true; +} #endif /* CONFIG_NET_RX_BUSY_POLL */ /* Use 2500 as a mini-jumbo MTU for FCoE */ @@ -2057,7 +2081,6 @@ int bnx2x_del_all_macs(struct bnx2x *bp, void bnx2x_func_init(struct bnx2x *bp, struct bnx2x_func_init_params *p); void bnx2x_init_sb(struct bnx2x *bp, dma_addr_t mapping, int vfid, u8 vf_valid, int fw_sb_id, int igu_sb_id); -u32 bnx2x_get_pretend_reg(struct bnx2x *bp); int bnx2x_get_gpio(struct bnx2x *bp, int gpio_num, u8 port); int bnx2x_set_gpio(struct bnx2x *bp, int gpio_num, u32 mode, u8 port); int bnx2x_set_mult_gpio(struct bnx2x *bp, u8 pins, u32 mode); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 282ebf61f530..9d7419e0390b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -30,6 +30,43 @@ #include "bnx2x_init.h" #include "bnx2x_sp.h" +static void bnx2x_free_fp_mem_cnic(struct bnx2x *bp); +static int bnx2x_alloc_fp_mem_cnic(struct bnx2x *bp); +static int bnx2x_alloc_fp_mem(struct bnx2x *bp); +static int bnx2x_poll(struct napi_struct *napi, int budget); + +static void bnx2x_add_all_napi_cnic(struct bnx2x *bp) +{ + int i; + + /* Add NAPI objects */ + for_each_rx_queue_cnic(bp, i) { + netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi), + bnx2x_poll, NAPI_POLL_WEIGHT); + napi_hash_add(&bnx2x_fp(bp, i, napi)); + } +} + +static void bnx2x_add_all_napi(struct bnx2x *bp) +{ + int i; + + /* Add NAPI objects */ + for_each_eth_queue(bp, i) { + netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi), + bnx2x_poll, NAPI_POLL_WEIGHT); + napi_hash_add(&bnx2x_fp(bp, i, napi)); + } +} + +static int bnx2x_calc_num_queues(struct bnx2x *bp) +{ + return bnx2x_num_queues ? + min_t(int, bnx2x_num_queues, BNX2X_MAX_QUEUES(bp)) : + min_t(int, netif_get_num_default_rss_queues(), + BNX2X_MAX_QUEUES(bp)); +} + /** * bnx2x_move_fp - move content of the fastpath structure. * @@ -145,7 +182,7 @@ static void bnx2x_shrink_eth_fp(struct bnx2x *bp, int delta) } } -int load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */ +int bnx2x_load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */ /* free skb in the packet ring at pos idx * return idx of last bd freed @@ -160,6 +197,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, struct sk_buff *skb = tx_buf->skb; u16 bd_idx = TX_BD(tx_buf->first_bd), new_cons; int nbd; + u16 split_bd_len = 0; /* prefetch skb end pointer to speedup dev_kfree_skb() */ prefetch(&skb->end); @@ -167,10 +205,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, DP(NETIF_MSG_TX_DONE, "fp[%d]: pkt_idx %d buff @(%p)->skb %p\n", txdata->txq_index, idx, tx_buf, skb); - /* unmap first bd */ tx_start_bd = &txdata->tx_desc_ring[bd_idx].start_bd; - dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd), - BD_UNMAP_LEN(tx_start_bd), DMA_TO_DEVICE); nbd = le16_to_cpu(tx_start_bd->nbd) - 1; #ifdef BNX2X_STOP_ON_ERROR @@ -188,12 +223,19 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, --nbd; bd_idx = TX_BD(NEXT_TX_IDX(bd_idx)); - /* ...and the TSO split header bd since they have no mapping */ + /* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */ if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) { + tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd; + split_bd_len = BD_UNMAP_LEN(tx_data_bd); --nbd; bd_idx = TX_BD(NEXT_TX_IDX(bd_idx)); } + /* unmap first bd */ + dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd), + BD_UNMAP_LEN(tx_start_bd) + split_bd_len, + DMA_TO_DEVICE); + /* now free frags */ while (nbd > 0) { @@ -813,7 +855,7 @@ void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe, skb->ip_summed = CHECKSUM_UNNECESSARY; } -int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget) +static int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget) { struct bnx2x *bp = fp->bp; u16 bd_cons, bd_prod, bd_prod_fw, comp_ring_cons; @@ -1483,7 +1525,7 @@ static void bnx2x_free_rx_skbs(struct bnx2x *bp) } } -void bnx2x_free_skbs_cnic(struct bnx2x *bp) +static void bnx2x_free_skbs_cnic(struct bnx2x *bp) { bnx2x_free_tx_skbs_cnic(bp); bnx2x_free_rx_skbs_cnic(bp); @@ -1792,26 +1834,22 @@ static void bnx2x_napi_disable_cnic(struct bnx2x *bp) { int i; - local_bh_disable(); for_each_rx_queue_cnic(bp, i) { napi_disable(&bnx2x_fp(bp, i, napi)); - while (!bnx2x_fp_lock_napi(&bp->fp[i])) - mdelay(1); + while (!bnx2x_fp_ll_disable(&bp->fp[i])) + usleep_range(1000, 2000); } - local_bh_enable(); } static void bnx2x_napi_disable(struct bnx2x *bp) { int i; - local_bh_disable(); for_each_eth_queue(bp, i) { napi_disable(&bnx2x_fp(bp, i, napi)); - while (!bnx2x_fp_lock_napi(&bp->fp[i])) - mdelay(1); + while (!bnx2x_fp_ll_disable(&bp->fp[i])) + usleep_range(1000, 2000); } - local_bh_enable(); } void bnx2x_netif_start(struct bnx2x *bp) @@ -1834,7 +1872,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) bnx2x_napi_disable_cnic(bp); } -u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb) +u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { struct bnx2x *bp = netdev_priv(dev); @@ -2302,16 +2341,16 @@ static int bnx2x_nic_load_no_mcp(struct bnx2x *bp, int port) int path = BP_PATH(bp); DP(NETIF_MSG_IFUP, "NO MCP - load counts[%d] %d, %d, %d\n", - path, load_count[path][0], load_count[path][1], - load_count[path][2]); - load_count[path][0]++; - load_count[path][1 + port]++; + path, bnx2x_load_count[path][0], bnx2x_load_count[path][1], + bnx2x_load_count[path][2]); + bnx2x_load_count[path][0]++; + bnx2x_load_count[path][1 + port]++; DP(NETIF_MSG_IFUP, "NO MCP - new load counts[%d] %d, %d, %d\n", - path, load_count[path][0], load_count[path][1], - load_count[path][2]); - if (load_count[path][0] == 1) + path, bnx2x_load_count[path][0], bnx2x_load_count[path][1], + bnx2x_load_count[path][2]); + if (bnx2x_load_count[path][0] == 1) return FW_MSG_CODE_DRV_LOAD_COMMON; - else if (load_count[path][1 + port] == 1) + else if (bnx2x_load_count[path][1 + port] == 1) return FW_MSG_CODE_DRV_LOAD_PORT; else return FW_MSG_CODE_DRV_LOAD_FUNCTION; @@ -3069,7 +3108,7 @@ int bnx2x_set_power_state(struct bnx2x *bp, pci_power_t state) /* * net_device service functions */ -int bnx2x_poll(struct napi_struct *napi, int budget) +static int bnx2x_poll(struct napi_struct *napi, int budget) { int work_done = 0; u8 cos; @@ -4196,7 +4235,7 @@ static void bnx2x_free_fp_mem_at(struct bnx2x *bp, int fp_index) /* end of fastpath */ } -void bnx2x_free_fp_mem_cnic(struct bnx2x *bp) +static void bnx2x_free_fp_mem_cnic(struct bnx2x *bp) { int i; for_each_cnic_queue(bp, i) @@ -4410,7 +4449,7 @@ alloc_mem_err: return 0; } -int bnx2x_alloc_fp_mem_cnic(struct bnx2x *bp) +static int bnx2x_alloc_fp_mem_cnic(struct bnx2x *bp) { if (!NO_FCOE(bp)) /* FCoE */ @@ -4423,7 +4462,7 @@ int bnx2x_alloc_fp_mem_cnic(struct bnx2x *bp) return 0; } -int bnx2x_alloc_fp_mem(struct bnx2x *bp) +static int bnx2x_alloc_fp_mem(struct bnx2x *bp) { int i; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index da8fcaa74495..17d1689aec6b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -26,10 +26,8 @@ #include "bnx2x_sriov.h" /* This is used as a replacement for an MCP if it's not present */ -extern int load_count[2][3]; /* per-path: 0-common, 1-port0, 2-port1 */ - -extern int num_queues; -extern int int_mode; +extern int bnx2x_load_count[2][3]; /* per-path: 0-common, 1-port0, 2-port1 */ +extern int bnx2x_num_queues; /************************ Macros ********************************/ #define BNX2X_PCI_FREE(x, y, size) \ @@ -417,35 +415,8 @@ int bnx2x_set_eth_mac(struct bnx2x *bp, bool set); * If bp->state is OPEN, should be called with * netif_addr_lock_bh() */ -void bnx2x_set_rx_mode(struct net_device *dev); void bnx2x_set_rx_mode_inner(struct bnx2x *bp); -/** - * bnx2x_set_storm_rx_mode - configure MAC filtering rules in a FW. - * - * @bp: driver handle - * - * If bp->state is OPEN, should be called with - * netif_addr_lock_bh(). - */ -int bnx2x_set_storm_rx_mode(struct bnx2x *bp); - -/** - * bnx2x_set_q_rx_mode - configures rx_mode for a single queue. - * - * @bp: driver handle - * @cl_id: client id - * @rx_mode_flags: rx mode configuration - * @rx_accept_flags: rx accept configuration - * @tx_accept_flags: tx accept configuration (tx switch) - * @ramrod_flags: ramrod configuration - */ -int bnx2x_set_q_rx_mode(struct bnx2x *bp, u8 cl_id, - unsigned long rx_mode_flags, - unsigned long rx_accept_flags, - unsigned long tx_accept_flags, - unsigned long ramrod_flags); - /* Parity errors related */ void bnx2x_set_pf_load(struct bnx2x *bp); bool bnx2x_clear_pf_load(struct bnx2x *bp); @@ -524,7 +495,8 @@ int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac); int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); /* select_queue callback */ -u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb); +u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, @@ -564,9 +536,6 @@ int bnx2x_reload_if_running(struct net_device *dev); int bnx2x_change_mac_addr(struct net_device *dev, void *p); -/* NAPI poll Rx part */ -int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget); - /* NAPI poll Tx part */ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata); @@ -577,13 +546,9 @@ int bnx2x_resume(struct pci_dev *pdev); /* Release IRQ vectors */ void bnx2x_free_irq(struct bnx2x *bp); -void bnx2x_free_fp_mem_cnic(struct bnx2x *bp); void bnx2x_free_fp_mem(struct bnx2x *bp); -int bnx2x_alloc_fp_mem_cnic(struct bnx2x *bp); -int bnx2x_alloc_fp_mem(struct bnx2x *bp); void bnx2x_init_rx_rings(struct bnx2x *bp); void bnx2x_init_rx_rings_cnic(struct bnx2x *bp); -void bnx2x_free_skbs_cnic(struct bnx2x *bp); void bnx2x_free_skbs(struct bnx2x *bp); void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw); void bnx2x_netif_start(struct bnx2x *bp); @@ -607,15 +572,6 @@ int bnx2x_enable_msix(struct bnx2x *bp); int bnx2x_enable_msi(struct bnx2x *bp); /** - * bnx2x_poll - NAPI callback - * - * @napi: napi structure - * @budget: - * - */ -int bnx2x_poll(struct napi_struct *napi, int budget); - -/** * bnx2x_low_latency_recv - LL callback * * @napi: napi structure @@ -861,30 +817,6 @@ static inline void bnx2x_free_rx_sge(struct bnx2x *bp, sge->addr_lo = 0; } -static inline void bnx2x_add_all_napi_cnic(struct bnx2x *bp) -{ - int i; - - /* Add NAPI objects */ - for_each_rx_queue_cnic(bp, i) { - netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi), - bnx2x_poll, NAPI_POLL_WEIGHT); - napi_hash_add(&bnx2x_fp(bp, i, napi)); - } -} - -static inline void bnx2x_add_all_napi(struct bnx2x *bp) -{ - int i; - - /* Add NAPI objects */ - for_each_eth_queue(bp, i) { - netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi), - bnx2x_poll, NAPI_POLL_WEIGHT); - napi_hash_add(&bnx2x_fp(bp, i, napi)); - } -} - static inline void bnx2x_del_all_napi_cnic(struct bnx2x *bp) { int i; @@ -918,14 +850,6 @@ static inline void bnx2x_disable_msi(struct bnx2x *bp) } } -static inline int bnx2x_calc_num_queues(struct bnx2x *bp) -{ - return num_queues ? - min_t(int, num_queues, BNX2X_MAX_QUEUES(bp)) : - min_t(int, netif_get_num_default_rss_queues(), - BNX2X_MAX_QUEUES(bp)); -} - static inline void bnx2x_clear_sge_mask_next_elems(struct bnx2x_fastpath *fp) { int i, j; @@ -1172,8 +1096,6 @@ static inline u8 bnx2x_fp_qzone_id(struct bnx2x_fastpath *fp) return fp->cl_id; } -u32 bnx2x_rx_ustorm_prods_offset(struct bnx2x_fastpath *fp); - static inline void bnx2x_init_txdata(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, u32 cid, int txq_index, __le16 *tx_cons_sb, @@ -1206,47 +1128,6 @@ static inline u8 bnx2x_cnic_igu_sb_id(struct bnx2x *bp) return bp->igu_base_sb; } -static inline void bnx2x_init_fcoe_fp(struct bnx2x *bp) -{ - struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp); - unsigned long q_type = 0; - - bnx2x_fcoe(bp, rx_queue) = BNX2X_NUM_ETH_QUEUES(bp); - bnx2x_fcoe(bp, cl_id) = bnx2x_cnic_eth_cl_id(bp, - BNX2X_FCOE_ETH_CL_ID_IDX); - bnx2x_fcoe(bp, cid) = BNX2X_FCOE_ETH_CID(bp); - bnx2x_fcoe(bp, fw_sb_id) = DEF_SB_ID; - bnx2x_fcoe(bp, igu_sb_id) = bp->igu_dsb_id; - bnx2x_fcoe(bp, rx_cons_sb) = BNX2X_FCOE_L2_RX_INDEX; - bnx2x_init_txdata(bp, bnx2x_fcoe(bp, txdata_ptr[0]), - fp->cid, FCOE_TXQ_IDX(bp), BNX2X_FCOE_L2_TX_INDEX, - fp); - - DP(NETIF_MSG_IFUP, "created fcoe tx data (fp index %d)\n", fp->index); - - /* qZone id equals to FW (per path) client id */ - bnx2x_fcoe(bp, cl_qzone_id) = bnx2x_fp_qzone_id(fp); - /* init shortcut */ - bnx2x_fcoe(bp, ustorm_rx_prods_offset) = - bnx2x_rx_ustorm_prods_offset(fp); - - /* Configure Queue State object */ - __set_bit(BNX2X_Q_TYPE_HAS_RX, &q_type); - __set_bit(BNX2X_Q_TYPE_HAS_TX, &q_type); - - /* No multi-CoS for FCoE L2 client */ - BUG_ON(fp->max_cos != 1); - - bnx2x_init_queue_obj(bp, &bnx2x_sp_obj(bp, fp).q_obj, fp->cl_id, - &fp->cid, 1, BP_FUNC(bp), bnx2x_sp(bp, q_rdata), - bnx2x_sp_mapping(bp, q_rdata), q_type); - - DP(NETIF_MSG_IFUP, - "queue[%d]: bnx2x_init_sb(%p,%p) cl_id %d fw_sb %d igu_sb %d\n", - fp->index, bp, fp->status_blk.e2_sb, fp->cl_id, fp->fw_sb_id, - fp->igu_sb_id); -} - static inline int bnx2x_clean_tx_queue(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 11fc79585491..c5ce99be4d90 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -205,6 +205,11 @@ typedef int (*read_sfp_module_eeprom_func_p)(struct bnx2x_phy *phy, (_bank + (_addr & 0xf)), \ _val) +static int bnx2x_check_half_open_conn(struct link_params *params, + struct link_vars *vars, u8 notify); +static int bnx2x_sfp_module_detection(struct bnx2x_phy *phy, + struct link_params *params); + static u32 bnx2x_bits_en(struct bnx2x *bp, u32 reg, u32 bits) { u32 val = REG_RD(bp, reg); @@ -1399,57 +1404,6 @@ static void bnx2x_update_pfc_xmac(struct link_params *params, udelay(30); } - -static void bnx2x_emac_get_pfc_stat(struct link_params *params, - u32 pfc_frames_sent[2], - u32 pfc_frames_received[2]) -{ - /* Read pfc statistic */ - struct bnx2x *bp = params->bp; - u32 emac_base = params->port ? GRCBASE_EMAC1 : GRCBASE_EMAC0; - u32 val_xon = 0; - u32 val_xoff = 0; - - DP(NETIF_MSG_LINK, "pfc statistic read from EMAC\n"); - - /* PFC received frames */ - val_xoff = REG_RD(bp, emac_base + - EMAC_REG_RX_PFC_STATS_XOFF_RCVD); - val_xoff &= EMAC_REG_RX_PFC_STATS_XOFF_RCVD_COUNT; - val_xon = REG_RD(bp, emac_base + EMAC_REG_RX_PFC_STATS_XON_RCVD); - val_xon &= EMAC_REG_RX_PFC_STATS_XON_RCVD_COUNT; - - pfc_frames_received[0] = val_xon + val_xoff; - - /* PFC received sent */ - val_xoff = REG_RD(bp, emac_base + - EMAC_REG_RX_PFC_STATS_XOFF_SENT); - val_xoff &= EMAC_REG_RX_PFC_STATS_XOFF_SENT_COUNT; - val_xon = REG_RD(bp, emac_base + EMAC_REG_RX_PFC_STATS_XON_SENT); - val_xon &= EMAC_REG_RX_PFC_STATS_XON_SENT_COUNT; - - pfc_frames_sent[0] = val_xon + val_xoff; -} - -/* Read pfc statistic*/ -void bnx2x_pfc_statistic(struct link_params *params, struct link_vars *vars, - u32 pfc_frames_sent[2], - u32 pfc_frames_received[2]) -{ - /* Read pfc statistic */ - struct bnx2x *bp = params->bp; - - DP(NETIF_MSG_LINK, "pfc statistic\n"); - - if (!vars->link_up) - return; - - if (vars->mac_type == MAC_TYPE_EMAC) { - DP(NETIF_MSG_LINK, "About to read PFC stats from EMAC\n"); - bnx2x_emac_get_pfc_stat(params, pfc_frames_sent, - pfc_frames_received); - } -} /******************************************************************/ /* MAC/PBF section */ /******************************************************************/ @@ -13413,9 +13367,9 @@ static u8 bnx2x_analyze_link_error(struct link_params *params, * a fault, for example, due to break in the TX side of fiber. * ******************************************************************************/ -int bnx2x_check_half_open_conn(struct link_params *params, - struct link_vars *vars, - u8 notify) +static int bnx2x_check_half_open_conn(struct link_params *params, + struct link_vars *vars, + u8 notify) { struct bnx2x *bp = params->bp; u32 lss_status = 0; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index 4df45234fdc0..389f5f8cb0a3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -533,19 +533,11 @@ int bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos); int bnx2x_ets_e3b0_config(const struct link_params *params, const struct link_vars *vars, struct bnx2x_ets_params *ets_params); -/* Read pfc statistic*/ -void bnx2x_pfc_statistic(struct link_params *params, struct link_vars *vars, - u32 pfc_frames_sent[2], - u32 pfc_frames_received[2]); + void bnx2x_init_mod_abs_int(struct bnx2x *bp, struct link_vars *vars, u32 chip_id, u32 shmem_base, u32 shmem2_base, u8 port); -int bnx2x_sfp_module_detection(struct bnx2x_phy *phy, - struct link_params *params); - void bnx2x_period_func(struct link_params *params, struct link_vars *vars); -int bnx2x_check_half_open_conn(struct link_params *params, - struct link_vars *vars, u8 notify); #endif /* BNX2X_LINK_H */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 18498fed520b..f90079acb58c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -94,8 +94,8 @@ MODULE_FIRMWARE(FW_FILE_NAME_E1); MODULE_FIRMWARE(FW_FILE_NAME_E1H); MODULE_FIRMWARE(FW_FILE_NAME_E2); -int num_queues; -module_param(num_queues, int, 0); +int bnx2x_num_queues; +module_param_named(num_queues, bnx2x_num_queues, int, 0); MODULE_PARM_DESC(num_queues, " Set number of queues (default is as a number of CPUs)"); @@ -103,7 +103,7 @@ static int disable_tpa; module_param(disable_tpa, int, 0); MODULE_PARM_DESC(disable_tpa, " Disable the TPA (LRO) feature"); -int int_mode; +static int int_mode; module_param(int_mode, int, 0); MODULE_PARM_DESC(int_mode, " Force interrupt mode other than MSI-X " "(1 INT#x; 2 MSI)"); @@ -279,6 +279,12 @@ MODULE_DEVICE_TABLE(pci, bnx2x_pci_tbl); #define BNX2X_PREV_WAIT_NEEDED 1 static DEFINE_SEMAPHORE(bnx2x_prev_sem); static LIST_HEAD(bnx2x_prev_list); + +/* Forward declaration */ +static struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev); +static u32 bnx2x_rx_ustorm_prods_offset(struct bnx2x_fastpath *fp); +static int bnx2x_set_storm_rx_mode(struct bnx2x *bp); + /**************************************************************************** * General service functions ****************************************************************************/ @@ -5857,11 +5863,11 @@ static void bnx2x_init_eq_ring(struct bnx2x *bp) } /* called with netif_addr_lock_bh() */ -int bnx2x_set_q_rx_mode(struct bnx2x *bp, u8 cl_id, - unsigned long rx_mode_flags, - unsigned long rx_accept_flags, - unsigned long tx_accept_flags, - unsigned long ramrod_flags) +static int bnx2x_set_q_rx_mode(struct bnx2x *bp, u8 cl_id, + unsigned long rx_mode_flags, + unsigned long rx_accept_flags, + unsigned long tx_accept_flags, + unsigned long ramrod_flags) { struct bnx2x_rx_mode_ramrod_params ramrod_param; int rc; @@ -5969,7 +5975,7 @@ static int bnx2x_fill_accept_flags(struct bnx2x *bp, u32 rx_mode, } /* called with netif_addr_lock_bh() */ -int bnx2x_set_storm_rx_mode(struct bnx2x *bp) +static int bnx2x_set_storm_rx_mode(struct bnx2x *bp) { unsigned long rx_mode_flags = 0, ramrod_flags = 0; unsigned long rx_accept_flags = 0, tx_accept_flags = 0; @@ -6165,6 +6171,47 @@ static void bnx2x_init_tx_rings(struct bnx2x *bp) bnx2x_init_tx_ring_one(bp->fp[i].txdata_ptr[cos]); } +static void bnx2x_init_fcoe_fp(struct bnx2x *bp) +{ + struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp); + unsigned long q_type = 0; + + bnx2x_fcoe(bp, rx_queue) = BNX2X_NUM_ETH_QUEUES(bp); + bnx2x_fcoe(bp, cl_id) = bnx2x_cnic_eth_cl_id(bp, + BNX2X_FCOE_ETH_CL_ID_IDX); + bnx2x_fcoe(bp, cid) = BNX2X_FCOE_ETH_CID(bp); + bnx2x_fcoe(bp, fw_sb_id) = DEF_SB_ID; + bnx2x_fcoe(bp, igu_sb_id) = bp->igu_dsb_id; + bnx2x_fcoe(bp, rx_cons_sb) = BNX2X_FCOE_L2_RX_INDEX; + bnx2x_init_txdata(bp, bnx2x_fcoe(bp, txdata_ptr[0]), + fp->cid, FCOE_TXQ_IDX(bp), BNX2X_FCOE_L2_TX_INDEX, + fp); + + DP(NETIF_MSG_IFUP, "created fcoe tx data (fp index %d)\n", fp->index); + + /* qZone id equals to FW (per path) client id */ + bnx2x_fcoe(bp, cl_qzone_id) = bnx2x_fp_qzone_id(fp); + /* init shortcut */ + bnx2x_fcoe(bp, ustorm_rx_prods_offset) = + bnx2x_rx_ustorm_prods_offset(fp); + + /* Configure Queue State object */ + __set_bit(BNX2X_Q_TYPE_HAS_RX, &q_type); + __set_bit(BNX2X_Q_TYPE_HAS_TX, &q_type); + + /* No multi-CoS for FCoE L2 client */ + BUG_ON(fp->max_cos != 1); + + bnx2x_init_queue_obj(bp, &bnx2x_sp_obj(bp, fp).q_obj, fp->cl_id, + &fp->cid, 1, BP_FUNC(bp), bnx2x_sp(bp, q_rdata), + bnx2x_sp_mapping(bp, q_rdata), q_type); + + DP(NETIF_MSG_IFUP, + "queue[%d]: bnx2x_init_sb(%p,%p) cl_id %d fw_sb %d igu_sb %d\n", + fp->index, bp, fp->status_blk.e2_sb, fp->cl_id, fp->fw_sb_id, + fp->igu_sb_id); +} + void bnx2x_nic_init_cnic(struct bnx2x *bp) { if (!NO_FCOE(bp)) @@ -8737,16 +8784,16 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode) int path = BP_PATH(bp); DP(NETIF_MSG_IFDOWN, "NO MCP - load counts[%d] %d, %d, %d\n", - path, load_count[path][0], load_count[path][1], - load_count[path][2]); - load_count[path][0]--; - load_count[path][1 + port]--; + path, bnx2x_load_count[path][0], bnx2x_load_count[path][1], + bnx2x_load_count[path][2]); + bnx2x_load_count[path][0]--; + bnx2x_load_count[path][1 + port]--; DP(NETIF_MSG_IFDOWN, "NO MCP - new load counts[%d] %d, %d, %d\n", - path, load_count[path][0], load_count[path][1], - load_count[path][2]); - if (load_count[path][0] == 0) + path, bnx2x_load_count[path][0], bnx2x_load_count[path][1], + bnx2x_load_count[path][2]); + if (bnx2x_load_count[path][0] == 0) reset_code = FW_MSG_CODE_DRV_UNLOAD_COMMON; - else if (load_count[path][1 + port] == 0) + else if (bnx2x_load_count[path][1 + port] == 0) reset_code = FW_MSG_CODE_DRV_UNLOAD_PORT; else reset_code = FW_MSG_CODE_DRV_UNLOAD_FUNCTION; @@ -9772,7 +9819,7 @@ period_task_exit: * Init service functions */ -u32 bnx2x_get_pretend_reg(struct bnx2x *bp) +static u32 bnx2x_get_pretend_reg(struct bnx2x *bp) { u32 base = PXP2_REG_PGL_PRETEND_FUNC_F0; u32 stride = PXP2_REG_PGL_PRETEND_FUNC_F1 - base; @@ -12005,7 +12052,7 @@ static int bnx2x_set_mc_list(struct bnx2x *bp) } /* If bp->state is OPEN, should be called with netif_addr_lock_bh() */ -void bnx2x_set_rx_mode(struct net_device *dev) +static void bnx2x_set_rx_mode(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); @@ -12783,8 +12830,6 @@ static int set_is_vf(int chip_id) } } -struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev); - static int bnx2x_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -13859,7 +13904,7 @@ static int bnx2x_unregister_cnic(struct net_device *dev) return 0; } -struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev) +static struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); struct cnic_eth_dev *cp = &bp->cnic_eth_dev; @@ -13909,7 +13954,7 @@ struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev) return cp; } -u32 bnx2x_rx_ustorm_prods_offset(struct bnx2x_fastpath *fp) +static u32 bnx2x_rx_ustorm_prods_offset(struct bnx2x_fastpath *fp) { struct bnx2x *bp = fp->bp; u32 offset = BAR_USTRORM_INTMEM; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 98cccd487fc2..9373584e400f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -355,23 +355,6 @@ static bool bnx2x_get_credit_vlan(struct bnx2x_vlan_mac_obj *o) return vp->get(vp, 1); } - -static bool bnx2x_get_credit_vlan_mac(struct bnx2x_vlan_mac_obj *o) -{ - struct bnx2x_credit_pool_obj *mp = o->macs_pool; - struct bnx2x_credit_pool_obj *vp = o->vlans_pool; - - if (!mp->get(mp, 1)) - return false; - - if (!vp->get(vp, 1)) { - mp->put(mp, 1); - return false; - } - - return true; -} - static bool bnx2x_put_cam_offset_mac(struct bnx2x_vlan_mac_obj *o, int offset) { struct bnx2x_credit_pool_obj *mp = o->macs_pool; @@ -400,22 +383,6 @@ static bool bnx2x_put_credit_vlan(struct bnx2x_vlan_mac_obj *o) return vp->put(vp, 1); } -static bool bnx2x_put_credit_vlan_mac(struct bnx2x_vlan_mac_obj *o) -{ - struct bnx2x_credit_pool_obj *mp = o->macs_pool; - struct bnx2x_credit_pool_obj *vp = o->vlans_pool; - - if (!mp->put(mp, 1)) - return false; - - if (!vp->put(vp, 1)) { - mp->get(mp, 1); - return false; - } - - return true; -} - /** * __bnx2x_vlan_mac_h_write_trylock - try getting the vlan mac writer lock * @@ -507,22 +474,6 @@ static void __bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp, } } -/** - * bnx2x_vlan_mac_h_write_unlock - unlock the vlan mac head list writer lock - * - * @bp: device handle - * @o: vlan_mac object - * - * @details Notice if a pending execution exists, it would perform it - - * possibly releasing and reclaiming the execution queue lock. - */ -void bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *o) -{ - spin_lock_bh(&o->exe_queue.lock); - __bnx2x_vlan_mac_h_write_unlock(bp, o); - spin_unlock_bh(&o->exe_queue.lock); -} /** * __bnx2x_vlan_mac_h_read_lock - lock the vlan mac head list reader lock @@ -685,25 +636,6 @@ static int bnx2x_check_vlan_add(struct bnx2x *bp, return 0; } -static int bnx2x_check_vlan_mac_add(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *o, - union bnx2x_classification_ramrod_data *data) -{ - struct bnx2x_vlan_mac_registry_elem *pos; - - DP(BNX2X_MSG_SP, "Checking VLAN_MAC (%pM, %d) for ADD command\n", - data->vlan_mac.mac, data->vlan_mac.vlan); - - list_for_each_entry(pos, &o->head, link) - if ((data->vlan_mac.vlan == pos->u.vlan_mac.vlan) && - ether_addr_equal_unaligned(data->vlan_mac.mac, pos->u.vlan_mac.mac) && - (data->vlan_mac.is_inner_mac == - pos->u.vlan_mac.is_inner_mac)) - return -EEXIST; - - return 0; -} - /* check_del() callbacks */ static struct bnx2x_vlan_mac_registry_elem * bnx2x_check_mac_del(struct bnx2x *bp, @@ -738,26 +670,6 @@ static struct bnx2x_vlan_mac_registry_elem * return NULL; } -static struct bnx2x_vlan_mac_registry_elem * - bnx2x_check_vlan_mac_del(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *o, - union bnx2x_classification_ramrod_data *data) -{ - struct bnx2x_vlan_mac_registry_elem *pos; - - DP(BNX2X_MSG_SP, "Checking VLAN_MAC (%pM, %d) for DEL command\n", - data->vlan_mac.mac, data->vlan_mac.vlan); - - list_for_each_entry(pos, &o->head, link) - if ((data->vlan_mac.vlan == pos->u.vlan_mac.vlan) && - ether_addr_equal_unaligned(data->vlan_mac.mac, pos->u.vlan_mac.mac) && - (data->vlan_mac.is_inner_mac == - pos->u.vlan_mac.is_inner_mac)) - return pos; - - return NULL; -} - /* check_move() callback */ static bool bnx2x_check_move(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *src_o, @@ -809,8 +721,8 @@ static inline u8 bnx2x_vlan_mac_get_rx_tx_flag(struct bnx2x_vlan_mac_obj *o) return rx_tx_flag; } -void bnx2x_set_mac_in_nig(struct bnx2x *bp, - bool add, unsigned char *dev_addr, int index) +static void bnx2x_set_mac_in_nig(struct bnx2x *bp, + bool add, unsigned char *dev_addr, int index) { u32 wb_data[2]; u32 reg_offset = BP_PORT(bp) ? NIG_REG_LLH1_FUNC_MEM : @@ -1124,97 +1036,6 @@ static void bnx2x_set_one_vlan_e2(struct bnx2x *bp, rule_cnt); } -static void bnx2x_set_one_vlan_mac_e2(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *o, - struct bnx2x_exeq_elem *elem, - int rule_idx, int cam_offset) -{ - struct bnx2x_raw_obj *raw = &o->raw; - struct eth_classify_rules_ramrod_data *data = - (struct eth_classify_rules_ramrod_data *)(raw->rdata); - int rule_cnt = rule_idx + 1; - union eth_classify_rule_cmd *rule_entry = &data->rules[rule_idx]; - enum bnx2x_vlan_mac_cmd cmd = elem->cmd_data.vlan_mac.cmd; - bool add = (cmd == BNX2X_VLAN_MAC_ADD) ? true : false; - u16 vlan = elem->cmd_data.vlan_mac.u.vlan_mac.vlan; - u8 *mac = elem->cmd_data.vlan_mac.u.vlan_mac.mac; - - /* Reset the ramrod data buffer for the first rule */ - if (rule_idx == 0) - memset(data, 0, sizeof(*data)); - - /* Set a rule header */ - bnx2x_vlan_mac_set_cmd_hdr_e2(bp, o, add, CLASSIFY_RULE_OPCODE_PAIR, - &rule_entry->pair.header); - - /* Set VLAN and MAC themselves */ - rule_entry->pair.vlan = cpu_to_le16(vlan); - bnx2x_set_fw_mac_addr(&rule_entry->pair.mac_msb, - &rule_entry->pair.mac_mid, - &rule_entry->pair.mac_lsb, mac); - rule_entry->pair.inner_mac = - cpu_to_le16(elem->cmd_data.vlan_mac.u.vlan_mac.is_inner_mac); - /* MOVE: Add a rule that will add this MAC to the target Queue */ - if (cmd == BNX2X_VLAN_MAC_MOVE) { - rule_entry++; - rule_cnt++; - - /* Setup ramrod data */ - bnx2x_vlan_mac_set_cmd_hdr_e2(bp, - elem->cmd_data.vlan_mac.target_obj, - true, CLASSIFY_RULE_OPCODE_PAIR, - &rule_entry->pair.header); - - /* Set a VLAN itself */ - rule_entry->pair.vlan = cpu_to_le16(vlan); - bnx2x_set_fw_mac_addr(&rule_entry->pair.mac_msb, - &rule_entry->pair.mac_mid, - &rule_entry->pair.mac_lsb, mac); - rule_entry->pair.inner_mac = - cpu_to_le16(elem->cmd_data.vlan_mac.u. - vlan_mac.is_inner_mac); - } - - /* Set the ramrod data header */ - /* TODO: take this to the higher level in order to prevent multiple - writing */ - bnx2x_vlan_mac_set_rdata_hdr_e2(raw->cid, raw->state, &data->header, - rule_cnt); -} - -/** - * bnx2x_set_one_vlan_mac_e1h - - * - * @bp: device handle - * @o: bnx2x_vlan_mac_obj - * @elem: bnx2x_exeq_elem - * @rule_idx: rule_idx - * @cam_offset: cam_offset - */ -static void bnx2x_set_one_vlan_mac_e1h(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *o, - struct bnx2x_exeq_elem *elem, - int rule_idx, int cam_offset) -{ - struct bnx2x_raw_obj *raw = &o->raw; - struct mac_configuration_cmd *config = - (struct mac_configuration_cmd *)(raw->rdata); - /* 57710 and 57711 do not support MOVE command, - * so it's either ADD or DEL - */ - bool add = (elem->cmd_data.vlan_mac.cmd == BNX2X_VLAN_MAC_ADD) ? - true : false; - - /* Reset the ramrod data buffer */ - memset(config, 0, sizeof(*config)); - - bnx2x_vlan_mac_set_rdata_e1x(bp, o, BNX2X_FILTER_VLAN_MAC_PENDING, - cam_offset, add, - elem->cmd_data.vlan_mac.u.vlan_mac.mac, - elem->cmd_data.vlan_mac.u.vlan_mac.vlan, - ETH_VLAN_FILTER_CLASSIFY, config); -} - /** * bnx2x_vlan_mac_restore - reconfigure next MAC/VLAN/VLAN-MAC element * @@ -1314,24 +1135,6 @@ static struct bnx2x_exeq_elem *bnx2x_exeq_get_vlan( return NULL; } -static struct bnx2x_exeq_elem *bnx2x_exeq_get_vlan_mac( - struct bnx2x_exe_queue_obj *o, - struct bnx2x_exeq_elem *elem) -{ - struct bnx2x_exeq_elem *pos; - struct bnx2x_vlan_mac_ramrod_data *data = - &elem->cmd_data.vlan_mac.u.vlan_mac; - - /* Check pending for execution commands */ - list_for_each_entry(pos, &o->exe_queue, link) - if (!memcmp(&pos->cmd_data.vlan_mac.u.vlan_mac, data, - sizeof(*data)) && - (pos->cmd_data.vlan_mac.cmd == elem->cmd_data.vlan_mac.cmd)) - return pos; - - return NULL; -} - /** * bnx2x_validate_vlan_mac_add - check if an ADD command can be executed * @@ -2239,69 +2042,6 @@ void bnx2x_init_vlan_obj(struct bnx2x *bp, } } -void bnx2x_init_vlan_mac_obj(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *vlan_mac_obj, - u8 cl_id, u32 cid, u8 func_id, void *rdata, - dma_addr_t rdata_mapping, int state, - unsigned long *pstate, bnx2x_obj_type type, - struct bnx2x_credit_pool_obj *macs_pool, - struct bnx2x_credit_pool_obj *vlans_pool) -{ - union bnx2x_qable_obj *qable_obj = - (union bnx2x_qable_obj *)vlan_mac_obj; - - bnx2x_init_vlan_mac_common(vlan_mac_obj, cl_id, cid, func_id, rdata, - rdata_mapping, state, pstate, type, - macs_pool, vlans_pool); - - /* CAM pool handling */ - vlan_mac_obj->get_credit = bnx2x_get_credit_vlan_mac; - vlan_mac_obj->put_credit = bnx2x_put_credit_vlan_mac; - /* CAM offset is relevant for 57710 and 57711 chips only which have a - * single CAM for both MACs and VLAN-MAC pairs. So the offset - * will be taken from MACs' pool object only. - */ - vlan_mac_obj->get_cam_offset = bnx2x_get_cam_offset_mac; - vlan_mac_obj->put_cam_offset = bnx2x_put_cam_offset_mac; - - if (CHIP_IS_E1(bp)) { - BNX2X_ERR("Do not support chips others than E2\n"); - BUG(); - } else if (CHIP_IS_E1H(bp)) { - vlan_mac_obj->set_one_rule = bnx2x_set_one_vlan_mac_e1h; - vlan_mac_obj->check_del = bnx2x_check_vlan_mac_del; - vlan_mac_obj->check_add = bnx2x_check_vlan_mac_add; - vlan_mac_obj->check_move = bnx2x_check_move_always_err; - vlan_mac_obj->ramrod_cmd = RAMROD_CMD_ID_ETH_SET_MAC; - - /* Exe Queue */ - bnx2x_exe_queue_init(bp, - &vlan_mac_obj->exe_queue, 1, qable_obj, - bnx2x_validate_vlan_mac, - bnx2x_remove_vlan_mac, - bnx2x_optimize_vlan_mac, - bnx2x_execute_vlan_mac, - bnx2x_exeq_get_vlan_mac); - } else { - vlan_mac_obj->set_one_rule = bnx2x_set_one_vlan_mac_e2; - vlan_mac_obj->check_del = bnx2x_check_vlan_mac_del; - vlan_mac_obj->check_add = bnx2x_check_vlan_mac_add; - vlan_mac_obj->check_move = bnx2x_check_move; - vlan_mac_obj->ramrod_cmd = - RAMROD_CMD_ID_ETH_CLASSIFICATION_RULES; - - /* Exe Queue */ - bnx2x_exe_queue_init(bp, - &vlan_mac_obj->exe_queue, - CLASSIFY_RULES_COUNT, - qable_obj, bnx2x_validate_vlan_mac, - bnx2x_remove_vlan_mac, - bnx2x_optimize_vlan_mac, - bnx2x_execute_vlan_mac, - bnx2x_exeq_get_vlan_mac); - } -} - /* RX_MODE verbs: DROP_ALL/ACCEPT_ALL/ACCEPT_ALL_MULTI/ACCEPT_ALL_VLAN/NORMAL */ static inline void __storm_memset_mac_filters(struct bnx2x *bp, struct tstorm_eth_mac_filter_config *mac_filters, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 6a53c15c85a3..c8b939b141de 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -448,9 +448,6 @@ enum { BNX2X_LLH_CAM_MAX_PF_LINE = NIG_REG_LLH1_FUNC_MEM_SIZE / 2 }; -void bnx2x_set_mac_in_nig(struct bnx2x *bp, - bool add, unsigned char *dev_addr, int index); - /** RX_MODE verbs:DROP_ALL/ACCEPT_ALL/ACCEPT_ALL_MULTI/ACCEPT_ALL_VLAN/NORMAL */ /* RX_MODE ramrod special flags: set in rx_mode_flags field in @@ -1307,22 +1304,12 @@ void bnx2x_init_vlan_obj(struct bnx2x *bp, unsigned long *pstate, bnx2x_obj_type type, struct bnx2x_credit_pool_obj *vlans_pool); -void bnx2x_init_vlan_mac_obj(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *vlan_mac_obj, - u8 cl_id, u32 cid, u8 func_id, void *rdata, - dma_addr_t rdata_mapping, int state, - unsigned long *pstate, bnx2x_obj_type type, - struct bnx2x_credit_pool_obj *macs_pool, - struct bnx2x_credit_pool_obj *vlans_pool); - int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o); void bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o); int bnx2x_vlan_mac_h_write_lock(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o); -void bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *o); int bnx2x_config_vlan_mac(struct bnx2x *bp, struct bnx2x_vlan_mac_ramrod_params *p); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 31ab924600c1..208636d05cc0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -799,10 +799,10 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp, return -ENOMEM; } -int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp, - struct bnx2x_virtf *vf, - struct bnx2x_vfop_cmd *cmd, - int qid, u16 vid, bool add) +static int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp, + struct bnx2x_virtf *vf, + struct bnx2x_vfop_cmd *cmd, + int qid, u16 vid, bool add) { struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); int rc; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index d72ab7e24de0..d9fcca1b5a9d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -665,11 +665,6 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp, struct bnx2x_vfop_filters *macs, int qid, bool drv_only); -int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp, - struct bnx2x_virtf *vf, - struct bnx2x_vfop_cmd *cmd, - int qid, u16 vid, bool add); - int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp, struct bnx2x_virtf *vf, struct bnx2x_vfop_cmd *cmd, @@ -727,13 +722,6 @@ void bnx2x_vf_enable_access(struct bnx2x *bp, u8 abs_vfid); /* Handles an FLR (or VF_DISABLE) notification form the MCP */ void bnx2x_vf_handle_flr_event(struct bnx2x *bp); -void bnx2x_add_tlv(struct bnx2x *bp, void *tlvs_list, u16 offset, u16 type, - u16 length); -void bnx2x_vfpf_prep(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv, - u16 type, u16 length); -void bnx2x_vfpf_finalize(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv); -void bnx2x_dp_tlv_list(struct bnx2x *bp, void *tlvs_list); - bool bnx2x_tlv_supported(u16 tlvtype); u32 bnx2x_crc_vf_bulletin(struct bnx2x *bp, @@ -750,7 +738,6 @@ int bnx2x_vfpf_init(struct bnx2x *bp); void bnx2x_vfpf_close_vf(struct bnx2x *bp); int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bool is_leading); -int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx); int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set); int bnx2x_vfpf_config_rss(struct bnx2x *bp, struct bnx2x_config_rss_params *params); @@ -814,7 +801,6 @@ static inline int bnx2x_vfpf_release(struct bnx2x *bp) {return 0; } static inline int bnx2x_vfpf_init(struct bnx2x *bp) {return 0; } static inline void bnx2x_vfpf_close_vf(struct bnx2x *bp) {} static inline int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bool is_leading) {return 0; } -static inline int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx) {return 0; } static inline int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set) {return 0; } static inline int bnx2x_vfpf_config_rss(struct bnx2x *bp, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 1b1ad31b4553..3fa6c2a2a5a9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -21,9 +21,11 @@ #include "bnx2x_cmn.h" #include <linux/crc32.h> +static int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx); + /* place a given tlv on the tlv buffer at a given offset */ -void bnx2x_add_tlv(struct bnx2x *bp, void *tlvs_list, u16 offset, u16 type, - u16 length) +static void bnx2x_add_tlv(struct bnx2x *bp, void *tlvs_list, + u16 offset, u16 type, u16 length) { struct channel_tlv *tl = (struct channel_tlv *)(tlvs_list + offset); @@ -33,8 +35,8 @@ void bnx2x_add_tlv(struct bnx2x *bp, void *tlvs_list, u16 offset, u16 type, } /* Clear the mailbox and init the header of the first tlv */ -void bnx2x_vfpf_prep(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv, - u16 type, u16 length) +static void bnx2x_vfpf_prep(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv, + u16 type, u16 length) { mutex_lock(&bp->vf2pf_mutex); @@ -52,7 +54,8 @@ void bnx2x_vfpf_prep(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv, } /* releases the mailbox */ -void bnx2x_vfpf_finalize(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv) +static void bnx2x_vfpf_finalize(struct bnx2x *bp, + struct vfpf_first_tlv *first_tlv) { DP(BNX2X_MSG_IOV, "done sending [%d] tlv over vf pf channel\n", first_tlv->tl.type); @@ -85,7 +88,7 @@ static void *bnx2x_search_tlv_list(struct bnx2x *bp, void *tlvs_list, } /* list the types and lengths of the tlvs on the buffer */ -void bnx2x_dp_tlv_list(struct bnx2x *bp, void *tlvs_list) +static void bnx2x_dp_tlv_list(struct bnx2x *bp, void *tlvs_list) { int i = 1; struct channel_tlv *tlv = (struct channel_tlv *)tlvs_list; @@ -633,7 +636,7 @@ int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, return rc; } -int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx) +static int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx) { struct vfpf_q_op_tlv *req = &bp->vf2pf_mbox->req.q_op; struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp; diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index cb05be905def..81e8402a74b4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -423,7 +423,7 @@ u64 cxgb4_select_ntuple(struct net_device *dev, * in the Compressed Filter Tuple. */ if (tp->vlan_shift >= 0 && l2t->vlan != VLAN_NONE) - ntuple |= (F_FT_VLAN_VLD | l2t->vlan) << tp->vlan_shift; + ntuple |= (u64)(F_FT_VLAN_VLD | l2t->vlan) << tp->vlan_shift; if (tp->port_shift >= 0) ntuple |= (u64)l2t->lport << tp->port_shift; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 9fb2eb8cf152..333bb54d0bdf 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -243,6 +243,7 @@ config IXGBEVF config I40E tristate "Intel(R) Ethernet Controller XL710 Family support" + select PTP_1588_CLOCK depends on PCI ---help--- This driver supports Intel(R) Ethernet Controller XL710 Family of diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 6ec1a795f184..e4d2e27078a7 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -40,4 +40,5 @@ i40e-objs := i40e_main.o \ i40e_debugfs.o \ i40e_diag.o \ i40e_txrx.o \ + i40e_ptp.o \ i40e_virtchnl_pf.o diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 4d4cdbf6fad7..c05984d72cfb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -50,6 +50,9 @@ #include <net/ip6_checksum.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> +#include <linux/clocksource.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> #include "i40e_type.h" #include "i40e_prototype.h" #include "i40e_virtchnl.h" @@ -88,7 +91,7 @@ /* The values in here are decimal coded as hex as is the case in the NVM map*/ #define I40E_CURRENT_NVM_VERSION_HI 0x2 -#define I40E_CURRENT_NVM_VERSION_LO 0x1 +#define I40E_CURRENT_NVM_VERSION_LO 0x30 /* magic for getting defines into strings */ @@ -242,6 +245,7 @@ struct i40e_pf { #define I40E_FLAG_DCB_ENABLED (u64)(1 << 20) #define I40E_FLAG_FDIR_ENABLED (u64)(1 << 21) #define I40E_FLAG_FDIR_ATR_ENABLED (u64)(1 << 22) +#define I40E_FLAG_PTP (u64)(1 << 25) #define I40E_FLAG_MFP_ENABLED (u64)(1 << 26) #ifdef CONFIG_I40E_VXLAN #define I40E_FLAG_VXLAN_FILTER_SYNC (u64)(1 << 27) @@ -302,6 +306,20 @@ struct i40e_pf { u32 fcoe_hmc_filt_num; u32 fcoe_hmc_cntx_num; struct i40e_filter_control_settings filter_settings; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_caps; + struct sk_buff *ptp_tx_skb; + struct work_struct ptp_tx_work; + struct hwtstamp_config tstamp_config; + unsigned long ptp_tx_start; + unsigned long last_rx_ptp_check; + spinlock_t tmreg_lock; /* Used to protect the device time registers. */ + u64 ptp_base_adj; + u32 tx_hwtstamp_timeouts; + u32 rx_hwtstamp_cleared; + bool ptp_tx; + bool ptp_rx; }; struct i40e_mac_filter { @@ -566,4 +584,12 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, bool is_vf, bool is_netdev); void i40e_vlan_stripping_enable(struct i40e_vsi *vsi); +void i40e_ptp_rx_hang(struct i40e_vsi *vsi); +void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf); +void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index); +void i40e_ptp_set_increment(struct i40e_pf *pf); +int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr); +int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr); +void i40e_ptp_init(struct i40e_pf *pf); +void i40e_ptp_stop(struct i40e_pf *pf); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index c75aa2d07491..a50e6b3479ae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -128,7 +128,7 @@ static void i40e_free_adminq_arq(struct i40e_hw *hw) /** * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure **/ static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw) { @@ -195,7 +195,7 @@ unwind_alloc_arq_bufs: /** * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure **/ static i40e_status i40e_alloc_asq_bufs(struct i40e_hw *hw) { @@ -235,7 +235,7 @@ unwind_alloc_asq_bufs: /** * i40e_free_arq_bufs - Free receive queue buffer info elements - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure **/ static void i40e_free_arq_bufs(struct i40e_hw *hw) { @@ -254,7 +254,7 @@ static void i40e_free_arq_bufs(struct i40e_hw *hw) /** * i40e_free_asq_bufs - Free send queue buffer info elements - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure **/ static void i40e_free_asq_bufs(struct i40e_hw *hw) { @@ -277,7 +277,7 @@ static void i40e_free_asq_bufs(struct i40e_hw *hw) /** * i40e_config_asq_regs - configure ASQ registers - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * Configure base address and length registers for the transmit queue **/ @@ -304,7 +304,7 @@ static void i40e_config_asq_regs(struct i40e_hw *hw) /** * i40e_config_arq_regs - ARQ register configuration - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * Configure base address and length registers for the receive (event queue) **/ @@ -334,7 +334,7 @@ static void i40e_config_arq_regs(struct i40e_hw *hw) /** * i40e_init_asq - main initialization routine for ASQ - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * This is the main initialization routine for the Admin Send Queue * Prior to calling this function, drivers *MUST* set the following fields @@ -391,7 +391,7 @@ init_adminq_exit: /** * i40e_init_arq - initialize ARQ - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * The main initialization routine for the Admin Receive (Event) Queue. * Prior to calling this function, drivers *MUST* set the following fields @@ -448,7 +448,7 @@ init_adminq_exit: /** * i40e_shutdown_asq - shutdown the ASQ - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * The main shutdown routine for the Admin Send Queue **/ @@ -479,7 +479,7 @@ static i40e_status i40e_shutdown_asq(struct i40e_hw *hw) /** * i40e_shutdown_arq - shutdown ARQ - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * The main shutdown routine for the Admin Receive Queue **/ @@ -510,7 +510,7 @@ static i40e_status i40e_shutdown_arq(struct i40e_hw *hw) /** * i40e_init_adminq - main initialization routine for Admin Queue - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure * * Prior to calling this function, drivers *MUST* set the following fields * in the hw->aq structure: @@ -607,7 +607,7 @@ init_adminq_exit: /** * i40e_shutdown_adminq - shutdown routine for the Admin Queue - * @hw: pointer to the hardware structure + * @hw: pointer to the hardware structure **/ i40e_status i40e_shutdown_adminq(struct i40e_hw *hw) { @@ -626,7 +626,7 @@ i40e_status i40e_shutdown_adminq(struct i40e_hw *hw) /** * i40e_clean_asq - cleans Admin send queue - * @asq: pointer to the adminq send ring + * @hw: pointer to the hardware structure * * returns the number of free desc **/ @@ -922,7 +922,7 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw, "AQRX: Event received with error 0x%X.\n", hw->aq.arq_last_status); } else { - memcpy(&e->desc, desc, sizeof(struct i40e_aq_desc)); + e->desc = *desc; datalen = le16_to_cpu(desc->datalen); e->msg_size = min(datalen, e->msg_size); if (e->msg_buf != NULL && (e->msg_size != 0)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 807312bb62a2..0b5a75c40978 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -74,7 +74,8 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw) /** * i40e_debug_aq * @hw: debug mask related to admin queue - * @cap: pointer to adminq command descriptor + * @mask: debug mask + * @desc: pointer to admin queue descriptor * @buffer: pointer to command buffer * * Dumps debug log about adminq command with descriptor contents. @@ -599,8 +600,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, goto aq_get_link_info_exit; /* save off old link status information */ - memcpy(&hw->phy.link_info_old, hw_link_info, - sizeof(struct i40e_link_status)); + hw->phy.link_info_old = *hw_link_info; /* update link status */ hw_link_info->phy_type = (enum i40e_aq_phy_type)resp->phy_type; @@ -630,7 +630,7 @@ aq_get_link_info_exit: /** * i40e_aq_add_vsi * @hw: pointer to the hw struct - * @vsi: pointer to a vsi context struct + * @vsi_ctx: pointer to a vsi context struct * @cmd_details: pointer to command details structure or NULL * * Add a VSI context to the hardware. @@ -682,7 +682,8 @@ aq_add_vsi_exit: * @cmd_details: pointer to command details structure or NULL **/ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, - u16 seid, bool set, struct i40e_asq_cmd_details *cmd_details) + u16 seid, bool set, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = @@ -776,7 +777,7 @@ i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, /** * i40e_get_vsi_params - get VSI configuration info * @hw: pointer to the hw struct - * @vsi: pointer to a vsi context struct + * @vsi_ctx: pointer to a vsi context struct * @cmd_details: pointer to command details structure or NULL **/ i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw, @@ -818,7 +819,7 @@ aq_get_vsi_params_exit: /** * i40e_aq_update_vsi_params * @hw: pointer to the hw struct - * @vsi: pointer to a vsi context struct + * @vsi_ctx: pointer to a vsi context struct * @cmd_details: pointer to command details structure or NULL * * Update a VSI context. @@ -921,7 +922,6 @@ i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw, /** * i40e_aq_send_driver_version * @hw: pointer to the hw struct - * @event: driver event: driver ok, start or stop * @dv: driver's major, minor version * @cmd_details: pointer to command details structure or NULL * @@ -1039,10 +1039,10 @@ i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, * @hw: pointer to the hw struct * @veb_seid: the SEID of the VEB to query * @switch_id: the uplink switch id - * @floating_veb: set to true if the VEB is floating + * @floating: set to true if the VEB is floating * @statistic_index: index of the stats counter block for this VEB * @vebs_used: number of VEB's used by function - * @vebs_unallocated: total VEB's not reserved by any function + * @vebs_free: total VEB's not reserved by any function * @cmd_details: pointer to command details structure or NULL * * This retrieves the parameters for a particular VEB, specified by @@ -1179,6 +1179,8 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, * i40e_aq_send_msg_to_vf * @hw: pointer to the hardware structure * @vfid: vf id to send msg + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code * @msg: pointer to the msg buffer * @msglen: msg length * @cmd_details: pointer to command details @@ -1723,6 +1725,7 @@ i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, * @udp_port: the UDP port to add * @header_len: length of the tunneling header length in DWords * @protocol_index: protocol index type + * @filter_index: pointer to filter index * @cmd_details: pointer to command details structure or NULL **/ i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw, diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 0220b18b2b18..36a5cc89bf0b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1083,7 +1083,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, vsi = i40e_dbg_find_vsi(pf, vsi_seid); if (!vsi) { dev_info(&pf->pdev->dev, - "add relay: vsi VSI %d not found\n", vsi_seid); + "add relay: VSI %d not found\n", vsi_seid); goto command_write_done; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index b886ee5bd99d..7b87d5115816 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -108,6 +108,8 @@ static struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("rx_oversize", stats.rx_oversize), I40E_PF_STAT("rx_jabber", stats.rx_jabber), I40E_PF_STAT("VF_admin_queue_requests", vf_aq_requests), + I40E_PF_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts), + I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared), }; #define I40E_QUEUE_STATS_LEN(n) \ @@ -748,7 +750,36 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, static int i40e_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { - return ethtool_op_get_ts_info(dev, info); + struct i40e_pf *pf = i40e_netdev_to_pf(dev); + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (pf->ptp_clock) + info->phc_index = ptp_clock_index(pf->ptp_clock); + else + info->phc_index = -1; + + info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); + + info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); + + return 0; } static int i40e_link_test(struct net_device *netdev, u64 *data) @@ -1634,7 +1665,7 @@ static int i40e_set_channels(struct net_device *dev, * class queue mapping */ new_count = i40e_reconfig_rss_queues(pf, count); - if (new_count > 1) + if (new_count > 0) return 0; else return -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c index 76dfef3e0104..bf2d4cc5b569 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c @@ -89,11 +89,9 @@ i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, sd_entry->u.pd_table.pd_entry = (struct i40e_hmc_pd_entry *) sd_entry->u.pd_table.pd_entry_virt_mem.va; - memcpy(&sd_entry->u.pd_table.pd_page_addr, &mem, - sizeof(struct i40e_dma_mem)); + sd_entry->u.pd_table.pd_page_addr = mem; } else { - memcpy(&sd_entry->u.bp.addr, &mem, - sizeof(struct i40e_dma_mem)); + sd_entry->u.bp.addr = mem; sd_entry->u.bp.sd_pd_index = sd_index; } /* initialize the sd entry */ @@ -164,7 +162,7 @@ i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, if (ret_code) goto exit; - memcpy(&pd_entry->bp.addr, &mem, sizeof(struct i40e_dma_mem)); + pd_entry->bp.addr = mem; pd_entry->bp.sd_pd_index = pd_index; pd_entry->bp.entry_type = I40E_SD_TYPE_PAGED; /* Set page address and valid bit */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h index 72bf30aba150..0cd4701234f8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h @@ -116,7 +116,6 @@ struct i40e_hmc_info { * @hw: pointer to our hw struct * @pa: pointer to physical address * @sd_index: segment descriptor index - * @hmc_fn_id: hmc function id * @type: if sd entry is direct or paged **/ #define I40E_SET_PF_SD_ENTRY(hw, pa, sd_index, type) \ @@ -138,7 +137,6 @@ struct i40e_hmc_info { * I40E_CLEAR_PF_SD_ENTRY - marks the sd entry as invalid in the hardware * @hw: pointer to our hw struct * @sd_index: segment descriptor index - * @hmc_fn_id: hmc function id * @type: if sd entry is direct or paged **/ #define I40E_CLEAR_PF_SD_ENTRY(hw, sd_index, type) \ @@ -159,7 +157,6 @@ struct i40e_hmc_info { * @hw: pointer to our hw struct * @sd_idx: segment descriptor index * @pd_idx: page descriptor index - * @hmc_fn_id: hmc function id **/ #define I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, pd_idx) \ wr32((hw), I40E_PFHMC_PDINV, \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1b792ee592d0..ad04da288f5d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -38,7 +38,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 0 #define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 25 +#define DRV_VERSION_BUILD 28 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -1698,6 +1698,27 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) } /** + * i40e_ioctl - Access the hwtstamp interface + * @netdev: network interface device structure + * @ifr: interface request data + * @cmd: ioctl command + **/ +int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_pf *pf = np->vsi->back; + + switch (cmd) { + case SIOCGHWTSTAMP: + return i40e_ptp_get_ts_config(pf, ifr); + case SIOCSHWTSTAMP: + return i40e_ptp_set_ts_config(pf, ifr); + default: + return -EOPNOTSUPP; + } +} + +/** * i40e_vlan_stripping_enable - Turn on vlan stripping for the VSI * @vsi: the vsi being adjusted **/ @@ -2150,7 +2171,8 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) tx_ctx.base = (ring->dma / 128); tx_ctx.qlen = ring->count; tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FDIR_ENABLED | - I40E_FLAG_FDIR_ATR_ENABLED)); + I40E_FLAG_FDIR_ATR_ENABLED)); + tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP); /* As part of VSI creation/update, FW allocates certain * Tx arbitration queue sets for each TC enabled for @@ -2488,6 +2510,7 @@ static void i40e_enable_misc_int_causes(struct i40e_hw *hw) I40E_PFINT_ICR0_ENA_GRST_MASK | I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_MASK | I40E_PFINT_ICR0_ENA_GPIO_MASK | + I40E_PFINT_ICR0_ENA_TIMESYNC_MASK | I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK | I40E_PFINT_ICR0_ENA_HMC_ERR_MASK | I40E_PFINT_ICR0_ENA_VFLR_MASK | @@ -2831,6 +2854,18 @@ static irqreturn_t i40e_intr(int irq, void *data) dev_info(&pf->pdev->dev, "HMC error interrupt\n"); } + if (icr0 & I40E_PFINT_ICR0_TIMESYNC_MASK) { + u32 prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_0); + + if (prttsyn_stat & I40E_PRTTSYN_STAT_0_TXTIME_MASK) { + ena_mask &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; + i40e_ptp_tx_hwtstamp(pf); + prttsyn_stat &= ~I40E_PRTTSYN_STAT_0_TXTIME_MASK; + } + + wr32(hw, I40E_PRTTSYN_STAT_0, prttsyn_stat); + } + /* If a critical error is pending we have no choice but to reset the * device. * Report and mask out any remaining unexpected interrupts. @@ -3008,11 +3043,13 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) continue; /* turn on/off the queue */ - if (enable) + if (enable) { + wr32(hw, I40E_QTX_HEAD(pf_q), 0); tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK | I40E_QTX_ENA_QENA_STAT_MASK; - else + } else { tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK; + } wr32(hw, I40E_QTX_ENA(pf_q), tx_reg); @@ -3113,7 +3150,7 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) **/ int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool request) { - int ret; + int ret = 0; /* do rx first for enable and last for disable */ if (request) { @@ -3122,10 +3159,9 @@ int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool request) return ret; ret = i40e_vsi_control_tx(vsi, request); } else { - ret = i40e_vsi_control_tx(vsi, request); - if (ret) - return ret; - ret = i40e_vsi_control_rx(vsi, request); + /* Ignore return value, we need to shutdown whatever we can */ + i40e_vsi_control_tx(vsi, request); + i40e_vsi_control_rx(vsi, request); } return ret; @@ -4303,6 +4339,9 @@ static void i40e_link_event(struct i40e_pf *pf) if (pf->vf) i40e_vc_notify_link_state(pf); + + if (pf->flags & I40E_FLAG_PTP) + i40e_ptp_set_increment(pf); } /** @@ -4384,6 +4423,8 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf) for (i = 0; i < I40E_MAX_VEB; i++) if (pf->veb[i]) i40e_update_veb_stats(pf->veb[i]); + + i40e_ptp_rx_hang(pf->vsi[pf->lan_vsi]); } /** @@ -6032,6 +6073,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = i40e_set_mac, .ndo_change_mtu = i40e_change_mtu, + .ndo_do_ioctl = i40e_ioctl, .ndo_tx_timeout = i40e_tx_timeout, .ndo_vlan_rx_add_vid = i40e_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = i40e_vlan_rx_kill_vid, @@ -7298,6 +7340,8 @@ no_autoneg: ~I40E_PRTDCB_MFLCN_RFCE_MASK); fc_complete: + i40e_ptp_init(pf); + return ret; } @@ -7611,6 +7655,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pf_reset; } + i40e_clear_pxe_mode(hw); err = i40e_get_capabilities(pf); if (err) goto err_adminq_setup; @@ -7801,6 +7846,8 @@ static void i40e_remove(struct pci_dev *pdev) i40e_dbg_pf_exit(pf); + i40e_ptp_stop(pf); + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { i40e_free_vfs(pf); pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 37d66c87abc9..e12bf07fd23d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -244,6 +244,7 @@ i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, /** * i40e_calc_nvm_checksum - Calculates and returns the checksum * @hw: pointer to hardware structure + * @checksum: pointer to the checksum * * This function calculate SW Checksum that covers the whole 64kB shadow RAM * except the VPD and PCIe ALT Auto-load modules. The structure and size of VPD diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index c7c3d8231b36..f8c53a6ec580 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -93,9 +93,9 @@ i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, u16 vsi_id, bool set_filter, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, - u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details); + u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw, - u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details); + u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw, struct i40e_vsi_context *vsi_ctx, struct i40e_asq_cmd_details *cmd_details); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c new file mode 100644 index 000000000000..e33ec6c842b7 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -0,0 +1,662 @@ +/******************************************************************************* + * + * Intel Ethernet Controller XL710 Family Linux Driver + * Copyright(c) 2013 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along + * with this program. If not, see <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +#include "i40e.h" +#include <linux/export.h> +#include <linux/ptp_classify.h> + +/* The XL710 timesync is very much like Intel's 82599 design when it comes to + * the fundamental clock design. However, the clock operations are much simpler + * in the XL710 because the device supports a full 64 bits of nanoseconds. + * Because the field is so wide, we can forgo the cycle counter and just + * operate with the nanosecond field directly without fear of overflow. + * + * Much like the 82599, the update period is dependent upon the link speed: + * At 40Gb link or no link, the period is 1.6ns. + * At 10Gb link, the period is multiplied by 2. (3.2ns) + * At 1Gb link, the period is multiplied by 20. (32ns) + * 1588 functionality is not supported at 100Mbps. + */ +#define I40E_PTP_40GB_INCVAL 0x0199999999ULL +#define I40E_PTP_10GB_INCVAL 0x0333333333ULL +#define I40E_PTP_1GB_INCVAL 0x2000000000ULL + +#define I40E_PRTTSYN_CTL1_TSYNTYPE_V1 (0x1 << \ + I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT) +#define I40E_PRTTSYN_CTL1_TSYNTYPE_V2 (0x2 << \ + I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT) +#define I40E_PTP_TX_TIMEOUT (HZ * 15) + +/** + * i40e_ptp_read - Read the PHC time from the device + * @pf: Board private structure + * @ts: timespec structure to hold the current time value + * + * This function reads the PRTTSYN_TIME registers and stores them in a + * timespec. However, since the registers are 64 bits of nanoseconds, we must + * convert the result to a timespec before we can return. + **/ +static void i40e_ptp_read(struct i40e_pf *pf, struct timespec *ts) +{ + struct i40e_hw *hw = &pf->hw; + u32 hi, lo; + u64 ns; + + /* The timer latches on the lowest register read. */ + lo = rd32(hw, I40E_PRTTSYN_TIME_L); + hi = rd32(hw, I40E_PRTTSYN_TIME_H); + + ns = (((u64)hi) << 32) | lo; + + *ts = ns_to_timespec(ns); +} + +/** + * i40e_ptp_write - Write the PHC time to the device + * @pf: Board private structure + * @ts: timespec structure that holds the new time value + * + * This function writes the PRTTSYN_TIME registers with the user value. Since + * we receive a timespec from the stack, we must convert that timespec into + * nanoseconds before programming the registers. + **/ +static void i40e_ptp_write(struct i40e_pf *pf, const struct timespec *ts) +{ + struct i40e_hw *hw = &pf->hw; + u64 ns = timespec_to_ns(ts); + + /* The timer will not update until the high register is written, so + * write the low register first. + */ + wr32(hw, I40E_PRTTSYN_TIME_L, ns & 0xFFFFFFFF); + wr32(hw, I40E_PRTTSYN_TIME_H, ns >> 32); +} + +/** + * i40e_ptp_convert_to_hwtstamp - Convert device clock to system time + * @hwtstamps: Timestamp structure to update + * @timestamp: Timestamp from the hardware + * + * We need to convert the NIC clock value into a hwtstamp which can be used by + * the upper level timestamping functions. Since the timestamp is simply a 64- + * bit nanosecond value, we can call ns_to_ktime directly to handle this. + **/ +static void i40e_ptp_convert_to_hwtstamp(struct skb_shared_hwtstamps *hwtstamps, + u64 timestamp) +{ + memset(hwtstamps, 0, sizeof(*hwtstamps)); + + hwtstamps->hwtstamp = ns_to_ktime(timestamp); +} + +/** + * i40e_ptp_adjfreq - Adjust the PHC frequency + * @ptp: The PTP clock structure + * @ppb: Parts per billion adjustment from the base + * + * Adjust the frequency of the PHC by the indicated parts per billion from the + * base frequency. + **/ +static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +{ + struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); + struct i40e_hw *hw = &pf->hw; + u64 adj, freq, diff; + int neg_adj = 0; + + if (ppb < 0) { + neg_adj = 1; + ppb = -ppb; + } + + smp_mb(); /* Force any pending update before accessing. */ + adj = ACCESS_ONCE(pf->ptp_base_adj); + + freq = adj; + freq *= ppb; + diff = div_u64(freq, 1000000000ULL); + + if (neg_adj) + adj -= diff; + else + adj += diff; + + wr32(hw, I40E_PRTTSYN_INC_L, adj & 0xFFFFFFFF); + wr32(hw, I40E_PRTTSYN_INC_H, adj >> 32); + + return 0; +} + +/** + * i40e_ptp_adjtime - Adjust the PHC time + * @ptp: The PTP clock structure + * @delta: Offset in nanoseconds to adjust the PHC time by + * + * Adjust the frequency of the PHC by the indicated parts per billion from the + * base frequency. + **/ +static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); + struct timespec now, then = ns_to_timespec(delta); + unsigned long flags; + + spin_lock_irqsave(&pf->tmreg_lock, flags); + + i40e_ptp_read(pf, &now); + now = timespec_add(now, then); + i40e_ptp_write(pf, (const struct timespec *)&now); + + spin_unlock_irqrestore(&pf->tmreg_lock, flags); + + return 0; +} + +/** + * i40e_ptp_gettime - Get the time of the PHC + * @ptp: The PTP clock structure + * @ts: timespec structure to hold the current time value + * + * Read the device clock and return the correct value on ns, after converting it + * into a timespec struct. + **/ +static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +{ + struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&pf->tmreg_lock, flags); + i40e_ptp_read(pf, ts); + spin_unlock_irqrestore(&pf->tmreg_lock, flags); + + return 0; +} + +/** + * i40e_ptp_settime - Set the time of the PHC + * @ptp: The PTP clock structure + * @ts: timespec structure that holds the new time value + * + * Set the device clock to the user input value. The conversion from timespec + * to ns happens in the write function. + **/ +static int i40e_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec *ts) +{ + struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&pf->tmreg_lock, flags); + i40e_ptp_write(pf, ts); + spin_unlock_irqrestore(&pf->tmreg_lock, flags); + + return 0; +} + +/** + * i40e_ptp_tx_work + * @work: pointer to work struct + * + * This work function polls the PRTTSYN_STAT_0.TXTIME bit to determine when a + * Tx timestamp event has occurred, in order to pass the Tx timestamp value up + * the stack in the skb. + */ +static void i40e_ptp_tx_work(struct work_struct *work) +{ + struct i40e_pf *pf = container_of(work, struct i40e_pf, + ptp_tx_work); + struct i40e_hw *hw = &pf->hw; + u32 prttsyn_stat_0; + + if (!pf->ptp_tx_skb) + return; + + if (time_is_before_jiffies(pf->ptp_tx_start + + I40E_PTP_TX_TIMEOUT)) { + dev_kfree_skb_any(pf->ptp_tx_skb); + pf->ptp_tx_skb = NULL; + pf->tx_hwtstamp_timeouts++; + dev_warn(&pf->pdev->dev, "clearing Tx timestamp hang"); + return; + } + + prttsyn_stat_0 = rd32(hw, I40E_PRTTSYN_STAT_0); + if (prttsyn_stat_0 & I40E_PRTTSYN_STAT_0_TXTIME_MASK) + i40e_ptp_tx_hwtstamp(pf); + else + schedule_work(&pf->ptp_tx_work); +} + +/** + * i40e_ptp_enable - Enable/disable ancillary features of the PHC subsystem + * @ptp: The PTP clock structure + * @rq: The requested feature to change + * @on: Enable/disable flag + * + * The XL710 does not support any of the ancillary features of the PHC + * subsystem, so this function may just return. + **/ +static int i40e_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +/** + * i40e_ptp_rx_hang - Detect error case when Rx timestamp registers are hung + * @vsi: The VSI with the rings relevant to 1588 + * + * This watchdog task is scheduled to detect error case where hardware has + * dropped an Rx packet that was timestamped when the ring is full. The + * particular error is rare but leaves the device in a state unable to timestamp + * any future packets. + **/ +void i40e_ptp_rx_hang(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + struct i40e_ring *rx_ring; + unsigned long rx_event; + u32 prttsyn_stat; + int n; + + if (pf->flags & I40E_FLAG_PTP) + return; + + prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1); + + /* Unless all four receive timestamp registers are latched, we are not + * concerned about a possible PTP Rx hang, so just update the timeout + * counter and exit. + */ + if (!(prttsyn_stat & ((I40E_PRTTSYN_STAT_1_RXT0_MASK << + I40E_PRTTSYN_STAT_1_RXT0_SHIFT) | + (I40E_PRTTSYN_STAT_1_RXT1_MASK << + I40E_PRTTSYN_STAT_1_RXT1_SHIFT) | + (I40E_PRTTSYN_STAT_1_RXT2_MASK << + I40E_PRTTSYN_STAT_1_RXT2_SHIFT) | + (I40E_PRTTSYN_STAT_1_RXT3_MASK << + I40E_PRTTSYN_STAT_1_RXT3_SHIFT)))) { + pf->last_rx_ptp_check = jiffies; + return; + } + + /* Determine the most recent watchdog or rx_timestamp event. */ + rx_event = pf->last_rx_ptp_check; + for (n = 0; n < vsi->num_queue_pairs; n++) { + rx_ring = vsi->rx_rings[n]; + if (time_after(rx_ring->last_rx_timestamp, rx_event)) + rx_event = rx_ring->last_rx_timestamp; + } + + /* Only need to read the high RXSTMP register to clear the lock */ + if (time_is_before_jiffies(rx_event + 5 * HZ)) { + rd32(hw, I40E_PRTTSYN_RXTIME_H(0)); + rd32(hw, I40E_PRTTSYN_RXTIME_H(1)); + rd32(hw, I40E_PRTTSYN_RXTIME_H(2)); + rd32(hw, I40E_PRTTSYN_RXTIME_H(3)); + pf->last_rx_ptp_check = jiffies; + pf->rx_hwtstamp_cleared++; + dev_warn(&vsi->back->pdev->dev, + "%s: clearing Rx timestamp hang", + __func__); + } +} + +/** + * i40e_ptp_tx_hwtstamp - Utility function which returns the Tx timestamp + * @pf: Board private structure + * + * Read the value of the Tx timestamp from the registers, convert it into a + * value consumable by the stack, and store that result into the shhwtstamps + * struct before returning it up the stack. + **/ +void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf) +{ + struct skb_shared_hwtstamps shhwtstamps; + struct i40e_hw *hw = &pf->hw; + u32 hi, lo; + u64 ns; + + lo = rd32(hw, I40E_PRTTSYN_TXTIME_L); + hi = rd32(hw, I40E_PRTTSYN_TXTIME_H); + + ns = (((u64)hi) << 32) | lo; + + i40e_ptp_convert_to_hwtstamp(&shhwtstamps, ns); + skb_tstamp_tx(pf->ptp_tx_skb, &shhwtstamps); + dev_kfree_skb_any(pf->ptp_tx_skb); + pf->ptp_tx_skb = NULL; +} + +/** + * i40e_ptp_rx_hwtstamp - Utility function which checks for an Rx timestamp + * @pf: Board private structure + * @skb: Particular skb to send timestamp with + * @index: Index into the receive timestamp registers for the timestamp + * + * The XL710 receives a notification in the receive descriptor with an offset + * into the set of RXTIME registers where the timestamp is for that skb. This + * function goes and fetches the receive timestamp from that offset, if a valid + * one exists. The RXTIME registers are in ns, so we must convert the result + * first. + **/ +void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index) +{ + u32 prttsyn_stat, hi, lo; + struct i40e_hw *hw; + u64 ns; + + /* Since we cannot turn off the Rx timestamp logic if the device is + * doing Tx timestamping, check if Rx timestamping is configured. + */ + if (!pf->ptp_rx) + return; + + hw = &pf->hw; + + prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1); + + if (!(prttsyn_stat & (1 << index))) + return; + + lo = rd32(hw, I40E_PRTTSYN_RXTIME_L(index)); + hi = rd32(hw, I40E_PRTTSYN_RXTIME_H(index)); + + ns = (((u64)hi) << 32) | lo; + + i40e_ptp_convert_to_hwtstamp(skb_hwtstamps(skb), ns); +} + +/** + * i40e_ptp_set_increment - Utility function to update clock increment rate + * @pf: Board private structure + * + * During a link change, the DMA frequency that drives the 1588 logic will + * change. In order to keep the PRTTSYN_TIME registers in units of nanoseconds, + * we must update the increment value per clock tick. + **/ +void i40e_ptp_set_increment(struct i40e_pf *pf) +{ + struct i40e_link_status *hw_link_info; + struct i40e_hw *hw = &pf->hw; + u64 incval; + + hw_link_info = &hw->phy.link_info; + + i40e_aq_get_link_info(&pf->hw, true, NULL, NULL); + + switch (hw_link_info->link_speed) { + case I40E_LINK_SPEED_10GB: + incval = I40E_PTP_10GB_INCVAL; + break; + case I40E_LINK_SPEED_1GB: + incval = I40E_PTP_1GB_INCVAL; + break; + case I40E_LINK_SPEED_100MB: + dev_warn(&pf->pdev->dev, + "%s: 1588 functionality is not supported at 100 Mbps. Stopping the PHC.\n", + __func__); + incval = 0; + break; + case I40E_LINK_SPEED_40GB: + default: + incval = I40E_PTP_40GB_INCVAL; + break; + } + + /* Write the new increment value into the increment register. The + * hardware will not update the clock until both registers have been + * written. + */ + wr32(hw, I40E_PRTTSYN_INC_L, incval & 0xFFFFFFFF); + wr32(hw, I40E_PRTTSYN_INC_H, incval >> 32); + + /* Update the base adjustement value. */ + ACCESS_ONCE(pf->ptp_base_adj) = incval; + smp_mb(); /* Force the above update. */ +} + +/** + * i40e_ptp_get_ts_config - ioctl interface to read the HW timestamping + * @pf: Board private structure + * @ifreq: ioctl data + * + * Obtain the current hardware timestamping settigs as requested. To do this, + * keep a shadow copy of the timestamp settings rather than attempting to + * deconstruct it from the registers. + **/ +int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr) +{ + struct hwtstamp_config *config = &pf->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/** + * i40e_ptp_set_ts_config - ioctl interface to control the HW timestamping + * @pf: Board private structure + * @ifreq: ioctl data + * + * Respond to the user filter requests and make the appropriate hardware + * changes here. The XL710 cannot support splitting of the Tx/Rx timestamping + * logic, so keep track in software of whether to indicate these timestamps + * or not. + * + * It is permissible to "upgrade" the user request to a broader filter, as long + * as the user receives the timestamps they care about and the user is notified + * the filter has been broadened. + **/ +int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr) +{ + struct i40e_hw *hw = &pf->hw; + struct hwtstamp_config *config = &pf->tstamp_config; + u32 pf_id, tsyntype, regval; + + if (copy_from_user(config, ifr->ifr_data, sizeof(*config))) + return -EFAULT; + + /* Reserved for future extensions. */ + if (config->flags) + return -EINVAL; + + /* Confirm that 1588 is supported on this PF. */ + pf_id = (rd32(hw, I40E_PRTTSYN_CTL0) & I40E_PRTTSYN_CTL0_PF_ID_MASK) >> + I40E_PRTTSYN_CTL0_PF_ID_SHIFT; + if (hw->pf_id != pf_id) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + pf->ptp_tx = false; + break; + case HWTSTAMP_TX_ON: + pf->ptp_tx = true; + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + pf->ptp_rx = false; + tsyntype = 0; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + pf->ptp_rx = true; + tsyntype = I40E_PRTTSYN_CTL1_V1MESSTYPE0_MASK | + I40E_PRTTSYN_CTL1_TSYNTYPE_V1 | + I40E_PRTTSYN_CTL1_UDP_ENA_MASK; + config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + pf->ptp_rx = true; + tsyntype = I40E_PRTTSYN_CTL1_V2MESSTYPE0_MASK | + I40E_PRTTSYN_CTL1_TSYNTYPE_V2 | + I40E_PRTTSYN_CTL1_UDP_ENA_MASK; + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_ALL: + default: + return -ERANGE; + } + + /* Clear out all 1588-related registers to clear and unlatch them. */ + rd32(hw, I40E_PRTTSYN_STAT_0); + rd32(hw, I40E_PRTTSYN_TXTIME_H); + rd32(hw, I40E_PRTTSYN_RXTIME_H(0)); + rd32(hw, I40E_PRTTSYN_RXTIME_H(1)); + rd32(hw, I40E_PRTTSYN_RXTIME_H(2)); + rd32(hw, I40E_PRTTSYN_RXTIME_H(3)); + + /* Enable/disable the Tx timestamp interrupt based on user input. */ + regval = rd32(hw, I40E_PRTTSYN_CTL0); + if (pf->ptp_tx) + regval |= I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_MASK; + else + regval &= ~I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_MASK; + wr32(hw, I40E_PRTTSYN_CTL0, regval); + + regval = rd32(hw, I40E_PFINT_ICR0_ENA); + if (pf->ptp_tx) + regval |= I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; + else + regval &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; + wr32(hw, I40E_PFINT_ICR0_ENA, regval); + + /* There is no simple on/off switch for Rx. To "disable" Rx support, + * ignore any received timestamps, rather than turn off the clock. + */ + if (pf->ptp_rx) { + regval = rd32(hw, I40E_PRTTSYN_CTL1); + /* clear everything but the enable bit */ + regval &= I40E_PRTTSYN_CTL1_TSYNENA_MASK; + /* now enable bits for desired Rx timestamps */ + regval |= tsyntype; + wr32(hw, I40E_PRTTSYN_CTL1, regval); + } + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/** + * i40e_ptp_init - Initialize the 1588 support and register the PHC + * @pf: Board private structure + * + * This function registers the device clock as a PHC. If it is successful, it + * starts the clock in the hardware. + **/ +void i40e_ptp_init(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev; + + strncpy(pf->ptp_caps.name, "i40e", sizeof(pf->ptp_caps.name)); + pf->ptp_caps.owner = THIS_MODULE; + pf->ptp_caps.max_adj = 999999999; + pf->ptp_caps.n_ext_ts = 0; + pf->ptp_caps.pps = 0; + pf->ptp_caps.adjfreq = i40e_ptp_adjfreq; + pf->ptp_caps.adjtime = i40e_ptp_adjtime; + pf->ptp_caps.gettime = i40e_ptp_gettime; + pf->ptp_caps.settime = i40e_ptp_settime; + pf->ptp_caps.enable = i40e_ptp_enable; + + /* Attempt to register the clock before enabling the hardware. */ + pf->ptp_clock = ptp_clock_register(&pf->ptp_caps, &pf->pdev->dev); + if (IS_ERR(pf->ptp_clock)) { + pf->ptp_clock = NULL; + dev_err(&pf->pdev->dev, "%s: ptp_clock_register failed\n", + __func__); + } else { + struct timespec ts; + u32 regval; + + spin_lock_init(&pf->tmreg_lock); + INIT_WORK(&pf->ptp_tx_work, i40e_ptp_tx_work); + + dev_info(&pf->pdev->dev, "%s: added PHC on %s\n", __func__, + netdev->name); + pf->flags |= I40E_FLAG_PTP; + + /* Ensure the clocks are running. */ + regval = rd32(hw, I40E_PRTTSYN_CTL0); + regval |= I40E_PRTTSYN_CTL0_TSYNENA_MASK; + wr32(hw, I40E_PRTTSYN_CTL0, regval); + regval = rd32(hw, I40E_PRTTSYN_CTL1); + regval |= I40E_PRTTSYN_CTL1_TSYNENA_MASK; + wr32(hw, I40E_PRTTSYN_CTL1, regval); + + /* Set the increment value per clock tick. */ + i40e_ptp_set_increment(pf); + + /* reset the tstamp_config */ + memset(&pf->tstamp_config, 0, sizeof(pf->tstamp_config)); + + /* Set the clock value. */ + ts = ktime_to_timespec(ktime_get_real()); + i40e_ptp_settime(&pf->ptp_caps, &ts); + } +} + +/** + * i40e_ptp_stop - Disable the driver/hardware support and unregister the PHC + * @pf: Board private structure + * + * This function handles the cleanup work required from the initialization by + * clearing out the important information and unregistering the PHC. + **/ +void i40e_ptp_stop(struct i40e_pf *pf) +{ + pf->flags &= ~I40E_FLAG_PTP; + pf->ptp_tx = false; + pf->ptp_rx = false; + + cancel_work_sync(&pf->ptp_tx_work); + if (pf->ptp_tx_skb) { + dev_kfree_skb_any(pf->ptp_tx_skb); + pf->ptp_tx_skb = NULL; + } + + if (pf->ptp_clock) { + ptp_clock_unregister(pf->ptp_clock); + pf->ptp_clock = NULL; + dev_info(&pf->pdev->dev, "%s: removed PHC on %s\n", __func__, + pf->vsi[pf->lan_vsi]->netdev->name); + } +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 43d88dd66ed4..a089ac19cfe9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -892,6 +892,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT))) return; + /* likely incorrect csum if alternate IP extention headers found */ + if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT)) + return; + /* IP or L4 or outmost IP checksum error */ if (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) | (1 << I40E_RX_DESC_ERROR_L4E_SHIFT) | @@ -1084,6 +1088,13 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) } skb->rxhash = i40e_rx_hash(rx_ring, rx_desc); + if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) { + i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status & + I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >> + I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT); + rx_ring->last_rx_timestamp = jiffies; + } + /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; total_rx_packets++; @@ -1422,6 +1433,46 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, } /** + * i40e_tsyn - set up the tsyn context descriptor + * @tx_ring: ptr to the ring to send + * @skb: ptr to the skb we're sending + * @tx_flags: the collected send information + * + * Returns 0 if no Tx timestamp can happen and 1 if the timestamp will happen + **/ +static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb, + u32 tx_flags, u64 *cd_type_cmd_tso_mss) +{ + struct i40e_pf *pf; + + if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) + return 0; + + /* Tx timestamps cannot be sampled when doing TSO */ + if (tx_flags & I40E_TX_FLAGS_TSO) + return 0; + + /* only timestamp the outbound packet if the user has requested it and + * we are not already transmitting a packet to be timestamped + */ + pf = i40e_netdev_to_pf(tx_ring->netdev); + if (pf->ptp_tx && !pf->ptp_tx_skb) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + pf->ptp_tx_skb = skb_get(skb); + } else { + return 0; + } + + *cd_type_cmd_tso_mss |= (u64)I40E_TX_CTX_DESC_TSYN << + I40E_TXD_CTX_QW1_CMD_SHIFT; + + pf->ptp_tx_start = jiffies; + schedule_work(&pf->ptp_tx_work); + + return 1; +} + +/** * i40e_tx_enable_csum - Enable Tx checksum offloads * @skb: send buffer * @tx_flags: Tx flags currently set @@ -1797,6 +1848,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, __be16 protocol; u32 td_cmd = 0; u8 hdr_len = 0; + int tsyn; int tso; if (0 == i40e_xmit_descriptor_count(skb, tx_ring)) return NETDEV_TX_BUSY; @@ -1827,6 +1879,11 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, skb_tx_timestamp(skb); + tsyn = i40e_tsyn(tx_ring, skb, tx_flags, &cd_type_cmd_tso_mss); + + if (tsyn) + tx_flags |= I40E_TX_FLAGS_TSYN; + /* always enable CRC insertion offload */ td_cmd |= I40E_TX_DESC_CMD_ICRC; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 6f8506c181d9..d5349698e513 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -29,9 +29,8 @@ /* Interrupt Throttling and Rate Limiting (storm control) Goodies */ -#define I40E_MAX_ITR 0x07FF -#define I40E_MIN_ITR 0x0001 -#define I40E_ITR_USEC_RESOLUTION 2 +#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ +#define I40E_MIN_ITR 0x0004 /* reg uses 2 usec resolution */ #define I40E_MAX_IRATE 0x03F #define I40E_MIN_IRATE 0x001 #define I40E_IRATE_USEC_RESOLUTION 4 @@ -137,6 +136,7 @@ enum i40e_dyn_idx_t { #define I40E_TX_FLAGS_IPV6 (u32)(1 << 5) #define I40E_TX_FLAGS_FCCRC (u32)(1 << 6) #define I40E_TX_FLAGS_FSO (u32)(1 << 7) +#define I40E_TX_FLAGS_TSYN (u32)(1 << 8) #define I40E_TX_FLAGS_VLAN_MASK 0xffff0000 #define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29 @@ -249,6 +249,8 @@ struct i40e_ring { u8 atr_sample_rate; u8 atr_count; + unsigned long last_rx_timestamp; + bool ring_active; /* is ring online or not */ /* stats structs */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 12473ad5c8e6..80cf24020f17 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -60,15 +60,6 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 -/* Check whether address is multicast. This is little-endian specific check.*/ -#define I40E_IS_MULTICAST(address) \ - (bool)(((u8 *)(address))[0] & ((u8)0x01)) - -/* Check whether an address is broadcast. */ -#define I40E_IS_BROADCAST(address) \ - ((((u8 *)(address))[0] == ((u8)0xff)) && \ - (((u8 *)(address))[1] == ((u8)0xff))) - /* Switch from mc to the 2usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) (((time) * 1000) / 2) @@ -508,7 +499,9 @@ enum i40e_rx_desc_status_bits { I40E_RX_DESC_STATUS_FLM_SHIFT = 11, I40E_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ I40E_RX_DESC_STATUS_LPBK_SHIFT = 14, - I40E_RX_DESC_STATUS_UDP_0_SHIFT = 16 + I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, + I40E_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ + I40E_RX_DESC_STATUS_UDP_0_SHIFT = 18 }; #define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT I40E_RX_DESC_STATUS_TSYNINDX_SHIFT diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 51a4f6125437..d04a7766be30 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1525,9 +1525,13 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } for (i = 0; i < al->num_elements; i++) { - ret = i40e_check_vf_permission(vf, al->list[i].addr); - if (ret) + if (is_broadcast_ether_addr(al->list[i].addr) || + is_zero_ether_addr(al->list[i].addr)) { + dev_err(&pf->pdev->dev, "invalid VF MAC addr %pM\n", + al->list[i].addr); + ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; + } } vsi = pf->vsi[vsi_id]; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 8f2b3b2a2a90..ffdb01d853db 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -21,6 +21,8 @@ * ******************************************************************************/ +#include <linux/prefetch.h> + #include "i40evf.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index cc06854296a3..5bcc870f8367 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6827,12 +6827,20 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) return __ixgbe_maybe_stop_tx(tx_ring, size); } -#ifdef IXGBE_FCOE -static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { + struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; +#ifdef IXGBE_FCOE struct ixgbe_adapter *adapter; struct ixgbe_ring_feature *f; int txq; +#endif + + if (fwd_adapter) + return skb->queue_mapping + fwd_adapter->tx_base_queue; + +#ifdef IXGBE_FCOE /* * only execute the code below if protocol is FCoE @@ -6858,9 +6866,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) txq -= f->indices; return txq + f->offset; +#else + return __netdev_pick_tx(dev, skb); +#endif } -#endif netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring) @@ -7629,27 +7639,11 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv) kfree(fwd_adapter); } -static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb, - struct net_device *dev, - void *priv) -{ - struct ixgbe_fwd_adapter *fwd_adapter = priv; - unsigned int queue; - struct ixgbe_ring *tx_ring; - - queue = skb->queue_mapping + fwd_adapter->tx_base_queue; - tx_ring = fwd_adapter->real_adapter->tx_ring[queue]; - - return __ixgbe_xmit_frame(skb, dev, tx_ring); -} - static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbe_open, .ndo_stop = ixgbe_close, .ndo_start_xmit = ixgbe_xmit_frame, -#ifdef IXGBE_FCOE .ndo_select_queue = ixgbe_select_queue, -#endif .ndo_set_rx_mode = ixgbe_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ixgbe_set_mac, @@ -7689,7 +7683,6 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, .ndo_dfwd_add_station = ixgbe_fwd_add, .ndo_dfwd_del_station = ixgbe_fwd_del, - .ndo_dfwd_start_xmit = ixgbe_fwd_xmit, }; /** diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 974a007c4277..8f9266c64c75 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -618,7 +618,8 @@ ltq_etop_set_multicast_list(struct net_device *dev) } static u16 -ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb) +ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { /* we are currently only using the first queue */ return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 3b66f26ba049..890922c1c8ee 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -724,7 +724,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud * - not an IP fragment * - no LLS polling in progress */ - if (!mlx4_en_cq_ll_polling(cq) && + if (!mlx4_en_cq_busy_polling(cq) && (dev->features & NETIF_F_GRO)) { struct sk_buff *gro_skb = napi_get_frags(&cq->napi); if (!gro_skb) @@ -816,8 +816,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud skb_mark_napi_id(skb, &cq->napi); - /* Push it up the stack */ - netif_receive_skb(skb); + if (!mlx4_en_cq_busy_polling(cq)) + napi_gro_receive(&cq->napi, skb); + else + netif_receive_skb(skb); next: for (nr = 0; nr < priv->num_frags; nr++) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 160e86d21607..8e8a7eb43a2c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -628,7 +628,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk } } -u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb) +u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 2f1e200f2e4c..3af04c3f42ea 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -661,7 +661,7 @@ static inline bool mlx4_en_cq_unlock_poll(struct mlx4_en_cq *cq) } /* true if a socket is polling, even if it did not get the lock */ -static inline bool mlx4_en_cq_ll_polling(struct mlx4_en_cq *cq) +static inline bool mlx4_en_cq_busy_polling(struct mlx4_en_cq *cq) { WARN_ON(!(cq->state & MLX4_CQ_LOCKED)); return cq->state & CQ_USER_PEND; @@ -691,7 +691,7 @@ static inline bool mlx4_en_cq_unlock_poll(struct mlx4_en_cq *cq) return false; } -static inline bool mlx4_en_cq_ll_polling(struct mlx4_en_cq *cq) +static inline bool mlx4_en_cq_busy_polling(struct mlx4_en_cq *cq) { return false; } @@ -722,7 +722,8 @@ int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); -u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb); +u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 35d48766d842..1accd9531224 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -38,8 +38,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 53 -#define QLCNIC_LINUX_VERSIONID "5.3.53" +#define _QLCNIC_LINUX_SUBVERSION 54 +#define QLCNIC_LINUX_VERSIONID "5.3.54" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) @@ -970,6 +970,9 @@ struct qlcnic_ipaddr { #define QLCNIC_BEACON_EANBLE 0xC #define QLCNIC_BEACON_DISABLE 0xD +#define QLCNIC_BEACON_ON 2 +#define QLCNIC_BEACON_OFF 0 + #define QLCNIC_MSIX_TBL_SPACE 8192 #define QLCNIC_PCI_REG_MSIX_TBL 0x44 #define QLCNIC_MSIX_TBL_PGSIZE 4096 @@ -1079,6 +1082,7 @@ struct qlcnic_adapter { u64 dev_rst_time; bool drv_mac_learn; bool fdb_mac_learn; + u8 rx_mac_learn; unsigned long vlans[BITS_TO_LONGS(VLAN_N_VID)]; u8 flash_mfg_id; struct qlcnic_npar_info *npars; @@ -1267,7 +1271,7 @@ struct qlcnic_pci_func_cfg { u16 port_num; u8 pci_func; u8 func_state; - u8 def_mac_addr[6]; + u8 def_mac_addr[ETH_ALEN]; }; struct qlcnic_npar_func_cfg { @@ -1640,7 +1644,6 @@ int qlcnic_set_default_offload_settings(struct qlcnic_adapter *); int qlcnic_reset_npar_config(struct qlcnic_adapter *); int qlcnic_set_eswitch_port_config(struct qlcnic_adapter *); void qlcnic_add_lb_filter(struct qlcnic_adapter *, struct sk_buff *, int, u16); -int qlcnic_get_beacon_state(struct qlcnic_adapter *, u8 *); int qlcnic_83xx_configure_opmode(struct qlcnic_adapter *adapter); int qlcnic_read_mac_addr(struct qlcnic_adapter *); int qlcnic_setup_netdev(struct qlcnic_adapter *, struct net_device *, int); @@ -1720,6 +1723,7 @@ int qlcnic_83xx_init_mailbox_work(struct qlcnic_adapter *); void qlcnic_83xx_detach_mailbox_work(struct qlcnic_adapter *); void qlcnic_83xx_reinit_mbx_work(struct qlcnic_mailbox *mbx); void qlcnic_83xx_free_mailbox(struct qlcnic_mailbox *mbx); +void qlcnic_update_stats(struct qlcnic_adapter *); /* Adapter hardware abstraction */ struct qlcnic_hardware_ops { @@ -1767,6 +1771,7 @@ struct qlcnic_hardware_ops { pci_channel_state_t); pci_ers_result_t (*io_slot_reset) (struct pci_dev *); void (*io_resume) (struct pci_dev *); + void (*get_beacon_state)(struct qlcnic_adapter *); }; extern struct qlcnic_nic_template qlcnic_vf_ops; @@ -1993,6 +1998,11 @@ static inline void qlcnic_set_mac_filter_count(struct qlcnic_adapter *adapter) adapter->ahw->hw_ops->set_mac_filter_count(adapter); } +static inline void qlcnic_get_beacon_state(struct qlcnic_adapter *adapter) +{ + adapter->ahw->hw_ops->get_beacon_state(adapter); +} + static inline void qlcnic_read_phys_port_id(struct qlcnic_adapter *adapter) { if (adapter->ahw->hw_ops->read_phys_port_id) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 03eb2ad9611a..a684d28e37af 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -181,7 +181,7 @@ static struct qlcnic_hardware_ops qlcnic_83xx_hw_ops = { .io_error_detected = qlcnic_83xx_io_error_detected, .io_slot_reset = qlcnic_83xx_io_slot_reset, .io_resume = qlcnic_83xx_io_resume, - + .get_beacon_state = qlcnic_83xx_get_beacon_state, }; static struct qlcnic_nic_template qlcnic_83xx_ops = { @@ -1388,6 +1388,33 @@ out: netif_device_attach(netdev); } +void qlcnic_83xx_get_beacon_state(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_cmd_args cmd; + u8 beacon_state; + int err = 0; + + err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_LED_CONFIG); + if (!err) { + err = qlcnic_issue_cmd(adapter, &cmd); + if (!err) { + beacon_state = cmd.rsp.arg[4]; + if (beacon_state == QLCNIC_BEACON_DISABLE) + ahw->beacon_state = QLC_83XX_BEACON_OFF; + else if (beacon_state == QLC_83XX_ENABLE_BEACON) + ahw->beacon_state = QLC_83XX_BEACON_ON; + } + } else { + netdev_err(adapter->netdev, "Get beacon state failed, err=%d\n", + err); + } + + qlcnic_free_mbx_args(&cmd); + + return; +} + int qlcnic_83xx_config_led(struct qlcnic_adapter *adapter, u32 state, u32 beacon) { @@ -1591,7 +1618,9 @@ static void qlcnic_83xx_set_interface_id_promisc(struct qlcnic_adapter *adapter, u32 *interface_id) { if (qlcnic_sriov_pf_check(adapter)) { + qlcnic_alloc_lb_filters_mem(adapter); qlcnic_pf_set_interface_id_promisc(adapter, interface_id); + adapter->rx_mac_learn = 1; } else { if (!qlcnic_sriov_vf_check(adapter)) *interface_id = adapter->recv_ctx->context_id << 16; @@ -1618,6 +1647,10 @@ int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *adapter, u32 mode) cmd->type = QLC_83XX_MBX_CMD_NO_WAIT; qlcnic_83xx_set_interface_id_promisc(adapter, &temp); + + if (qlcnic_84xx_check(adapter) && qlcnic_sriov_pf_check(adapter)) + mode = VPORT_MISS_MODE_ACCEPT_ALL; + cmd->req.arg[1] = mode | temp; err = qlcnic_issue_cmd(adapter, cmd); if (!err) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index 34d291168b79..4643b159df86 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -381,6 +381,8 @@ enum qlcnic_83xx_states { /* LED configuration settings */ #define QLC_83XX_ENABLE_BEACON 0xe +#define QLC_83XX_BEACON_ON 1 +#define QLC_83XX_BEACON_OFF 0 #define QLC_83XX_LED_RATE 0xff #define QLC_83XX_LED_ACT (1 << 10) #define QLC_83XX_LED_MOD (0 << 13) @@ -559,6 +561,7 @@ void qlcnic_83xx_napi_del(struct qlcnic_adapter *); void qlcnic_83xx_napi_enable(struct qlcnic_adapter *); void qlcnic_83xx_napi_disable(struct qlcnic_adapter *); int qlcnic_83xx_config_led(struct qlcnic_adapter *, u32, u32); +void qlcnic_83xx_get_beacon_state(struct qlcnic_adapter *); void qlcnic_ind_wr(struct qlcnic_adapter *, u32, u32); int qlcnic_ind_rd(struct qlcnic_adapter *, u32); int qlcnic_83xx_create_rx_ctx(struct qlcnic_adapter *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 22ae884728b8..abe3924c61c5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -2214,6 +2214,7 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac) struct qlcnic_hardware_context *ahw = adapter->ahw; int err = 0; + adapter->rx_mac_learn = 0; ahw->msix_supported = !!qlcnic_use_msi_x; qlcnic_83xx_init_rings(adapter); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c index 474320a5f0c1..23c4fd10e505 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c @@ -224,10 +224,14 @@ int qlcnic_83xx_config_vnic_opmode(struct qlcnic_adapter *adapter) return -EIO; } - if (ahw->capabilities & QLC_83XX_ESWITCH_CAPABILITY) + if (ahw->capabilities & QLC_83XX_ESWITCH_CAPABILITY) { adapter->flags |= QLCNIC_ESWITCH_ENABLED; - else + if (adapter->drv_mac_learn) + adapter->rx_mac_learn = 1; + } else { adapter->flags &= ~QLCNIC_ESWITCH_ENABLED; + adapter->rx_mac_learn = 0; + } ahw->idc.vnic_state = QLCNIC_DEV_NPAR_NON_OPER; ahw->idc.vnic_wait_limit = QLCNIC_DEV_NPAR_OPER_TIMEO; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 45fa6eff56c9..18ced0fb6cf0 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -167,27 +167,35 @@ static const char qlcnic_gstrings_test[][ETH_GSTRING_LEN] = { #define QLCNIC_TEST_LEN ARRAY_SIZE(qlcnic_gstrings_test) -static inline int qlcnic_82xx_statistics(void) +static inline int qlcnic_82xx_statistics(struct qlcnic_adapter *adapter) { - return ARRAY_SIZE(qlcnic_device_gstrings_stats) + - ARRAY_SIZE(qlcnic_83xx_mac_stats_strings); + return ARRAY_SIZE(qlcnic_gstrings_stats) + + ARRAY_SIZE(qlcnic_83xx_mac_stats_strings) + + QLCNIC_TX_STATS_LEN * adapter->drv_tx_rings; } -static inline int qlcnic_83xx_statistics(void) +static inline int qlcnic_83xx_statistics(struct qlcnic_adapter *adapter) { - return ARRAY_SIZE(qlcnic_83xx_tx_stats_strings) + + return ARRAY_SIZE(qlcnic_gstrings_stats) + + ARRAY_SIZE(qlcnic_83xx_tx_stats_strings) + ARRAY_SIZE(qlcnic_83xx_mac_stats_strings) + - ARRAY_SIZE(qlcnic_83xx_rx_stats_strings); + ARRAY_SIZE(qlcnic_83xx_rx_stats_strings) + + QLCNIC_TX_STATS_LEN * adapter->drv_tx_rings; } static int qlcnic_dev_statistics_len(struct qlcnic_adapter *adapter) { - if (qlcnic_82xx_check(adapter)) - return qlcnic_82xx_statistics(); - else if (qlcnic_83xx_check(adapter)) - return qlcnic_83xx_statistics(); - else - return -1; + int len = -1; + + if (qlcnic_82xx_check(adapter)) { + len = qlcnic_82xx_statistics(adapter); + if (adapter->flags & QLCNIC_ESWITCH_ENABLED) + len += ARRAY_SIZE(qlcnic_device_gstrings_stats); + } else if (qlcnic_83xx_check(adapter)) { + len = qlcnic_83xx_statistics(adapter); + } + + return len; } #define QLCNIC_TX_INTR_NOT_CONFIGURED 0X78563412 @@ -923,18 +931,13 @@ static int qlcnic_eeprom_test(struct net_device *dev) static int qlcnic_get_sset_count(struct net_device *dev, int sset) { - int len; struct qlcnic_adapter *adapter = netdev_priv(dev); switch (sset) { case ETH_SS_TEST: return QLCNIC_TEST_LEN; case ETH_SS_STATS: - len = qlcnic_dev_statistics_len(adapter) + QLCNIC_STATS_LEN; - if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) || - qlcnic_83xx_check(adapter)) - return len; - return qlcnic_82xx_statistics(); + return qlcnic_dev_statistics_len(adapter); default: return -EOPNOTSUPP; } @@ -1270,7 +1273,7 @@ static u64 *qlcnic_fill_stats(u64 *data, void *stats, int type) return data; } -static void qlcnic_update_stats(struct qlcnic_adapter *adapter) +void qlcnic_update_stats(struct qlcnic_adapter *adapter) { struct qlcnic_host_tx_ring *tx_ring; int ring; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index a9a149b82375..6ca5e57da3da 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -546,8 +546,11 @@ void __qlcnic_set_multi(struct net_device *netdev, u16 vlan) !adapter->fdb_mac_learn) { qlcnic_alloc_lb_filters_mem(adapter); adapter->drv_mac_learn = 1; + if (adapter->flags & QLCNIC_ESWITCH_ENABLED) + adapter->rx_mac_learn = 1; } else { adapter->drv_mac_learn = 0; + adapter->rx_mac_learn = 0; } qlcnic_nic_set_promisc(adapter, mode); @@ -779,8 +782,8 @@ void qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *adapter) "Could not send interrupt coalescing parameters\n"); } -#define QLCNIC_ENABLE_IPV4_LRO 1 -#define QLCNIC_ENABLE_IPV6_LRO 2 +#define QLCNIC_ENABLE_IPV4_LRO BIT_0 +#define QLCNIC_ENABLE_IPV6_LRO (BIT_1 | BIT_9) int qlcnic_82xx_config_hw_lro(struct qlcnic_adapter *adapter, int enable) { @@ -1530,19 +1533,34 @@ int qlcnic_82xx_config_led(struct qlcnic_adapter *adapter, u32 state, u32 rate) return rv; } -int qlcnic_get_beacon_state(struct qlcnic_adapter *adapter, u8 *h_state) +void qlcnic_82xx_get_beacon_state(struct qlcnic_adapter *adapter) { + struct qlcnic_hardware_context *ahw = adapter->ahw; struct qlcnic_cmd_args cmd; - int err; + u8 beacon_state; + int err = 0; - err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_LED_STATUS); - if (!err) { - err = qlcnic_issue_cmd(adapter, &cmd); - if (!err) - *h_state = cmd.rsp.arg[1]; + if (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_2_BEACON) { + err = qlcnic_alloc_mbx_args(&cmd, adapter, + QLCNIC_CMD_GET_LED_STATUS); + if (!err) { + err = qlcnic_issue_cmd(adapter, &cmd); + if (err) { + netdev_err(adapter->netdev, + "Failed to get current beacon state, err=%d\n", + err); + } else { + beacon_state = cmd.rsp.arg[1]; + if (beacon_state == QLCNIC_BEACON_DISABLE) + ahw->beacon_state = QLCNIC_BEACON_OFF; + else if (beacon_state == QLCNIC_BEACON_EANBLE) + ahw->beacon_state = QLCNIC_BEACON_ON; + } + } + qlcnic_free_mbx_args(&cmd); } - qlcnic_free_mbx_args(&cmd); - return err; + + return; } void qlcnic_82xx_get_func_no(struct qlcnic_adapter *adapter) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 13303e7d1ed7..0e739aed1bc6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -169,6 +169,7 @@ int qlcnic_82xx_config_hw_lro(struct qlcnic_adapter *adapter, int); int qlcnic_82xx_nic_set_promisc(struct qlcnic_adapter *adapter, u32); int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, struct net_device *netdev); +void qlcnic_82xx_get_beacon_state(struct qlcnic_adapter *); void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, u16 vlan_id); void qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *adapter); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 6373f6022486..2f967441e1a8 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -156,9 +156,9 @@ static inline void qlcnic_83xx_disable_tx_intr(struct qlcnic_adapter *adapter, writel(1, tx_ring->crb_intr_mask); } -static inline u8 qlcnic_mac_hash(u64 mac) +static inline u8 qlcnic_mac_hash(u64 mac, u16 vlan) { - return (u8)((mac & 0xff) ^ ((mac >> 40) & 0xff)); + return (u8)((mac & 0xff) ^ ((mac >> 40) & 0xff) ^ (vlan & 0xff)); } static inline u32 qlcnic_get_ref_handle(struct qlcnic_adapter *adapter, @@ -221,8 +221,11 @@ void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, struct sk_buff *skb, u8 hindex, op; int ret; + if (!qlcnic_sriov_pf_check(adapter) || (vlan_id == 0xffff)) + vlan_id = 0; + memcpy(&src_addr, phdr->h_source, ETH_ALEN); - hindex = qlcnic_mac_hash(src_addr) & + hindex = qlcnic_mac_hash(src_addr, vlan_id) & (adapter->fhash.fbucket_size - 1); if (loopback_pkt) { @@ -322,31 +325,47 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, struct sk_buff *skb) { + struct vlan_ethhdr *vh = (struct vlan_ethhdr *)(skb->data); + struct ethhdr *phdr = (struct ethhdr *)(skb->data); + struct net_device *netdev = adapter->netdev; + u16 protocol = ntohs(skb->protocol); struct qlcnic_filter *fil, *tmp_fil; - struct hlist_node *n; struct hlist_head *head; - struct net_device *netdev = adapter->netdev; - struct ethhdr *phdr = (struct ethhdr *)(skb->data); + struct hlist_node *n; u64 src_addr = 0; u16 vlan_id = 0; - u8 hindex; + u8 hindex, hval; - if (ether_addr_equal(phdr->h_source, adapter->mac_addr)) - return; + if (!qlcnic_sriov_pf_check(adapter)) { + if (ether_addr_equal(phdr->h_source, adapter->mac_addr)) + return; + } else { + if (protocol == ETH_P_8021Q) { + vh = (struct vlan_ethhdr *)skb->data; + vlan_id = ntohs(vh->h_vlan_TCI); + } else if (vlan_tx_tag_present(skb)) { + vlan_id = vlan_tx_tag_get(skb); + } + + if (ether_addr_equal(phdr->h_source, adapter->mac_addr) && + !vlan_id) + return; + } if (adapter->fhash.fnum >= adapter->fhash.fmax) { adapter->stats.mac_filter_limit_overrun++; - netdev_info(netdev, "Can not add more than %d mac addresses\n", - adapter->fhash.fmax); + netdev_info(netdev, "Can not add more than %d mac-vlan filters, configured %d\n", + adapter->fhash.fmax, adapter->fhash.fnum); return; } memcpy(&src_addr, phdr->h_source, ETH_ALEN); - hindex = qlcnic_mac_hash(src_addr) & (adapter->fhash.fbucket_size - 1); + hval = qlcnic_mac_hash(src_addr, vlan_id); + hindex = hval & (adapter->fhash.fbucket_size - 1); head = &(adapter->fhash.fhead[hindex]); hlist_for_each_entry_safe(tmp_fil, n, head, fnode) { - if (ether_addr_equal(tmp_fil->faddr, &src_addr) && + if (ether_addr_equal(tmp_fil->faddr, (u8 *)&src_addr) && tmp_fil->vlan_id == vlan_id) { if (jiffies > (QLCNIC_READD_AGE * HZ + tmp_fil->ftime)) qlcnic_change_filter(adapter, &src_addr, @@ -1599,7 +1618,8 @@ qlcnic_83xx_process_rcv(struct qlcnic_adapter *adapter, struct sk_buff *skb; struct qlcnic_host_rds_ring *rds_ring; int index, length, cksum, is_lb_pkt; - u16 vid = 0xffff, t_vid; + u16 vid = 0xffff; + int err; if (unlikely(ring >= adapter->max_rds_rings)) return NULL; @@ -1617,19 +1637,19 @@ qlcnic_83xx_process_rcv(struct qlcnic_adapter *adapter, if (!skb) return buffer; - if (adapter->drv_mac_learn && - (adapter->flags & QLCNIC_ESWITCH_ENABLED)) { - t_vid = 0; - is_lb_pkt = qlcnic_83xx_is_lb_pkt(sts_data[1], 0); - qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid); - } - if (length > rds_ring->skb_size) skb_put(skb, rds_ring->skb_size); else skb_put(skb, length); - if (unlikely(qlcnic_check_rx_tagging(adapter, skb, &vid))) { + err = qlcnic_check_rx_tagging(adapter, skb, &vid); + + if (adapter->rx_mac_learn) { + is_lb_pkt = qlcnic_83xx_is_lb_pkt(sts_data[1], 0); + qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, vid); + } + + if (unlikely(err)) { adapter->stats.rxdropped++; dev_kfree_skb(skb); return buffer; @@ -1664,7 +1684,8 @@ qlcnic_83xx_process_lro(struct qlcnic_adapter *adapter, int l2_hdr_offset, l4_hdr_offset; int index, is_lb_pkt; u16 lro_length, length, data_offset, gso_size; - u16 vid = 0xffff, t_vid; + u16 vid = 0xffff; + int err; if (unlikely(ring > adapter->max_rds_rings)) return NULL; @@ -1686,12 +1707,6 @@ qlcnic_83xx_process_lro(struct qlcnic_adapter *adapter, if (!skb) return buffer; - if (adapter->drv_mac_learn && - (adapter->flags & QLCNIC_ESWITCH_ENABLED)) { - t_vid = 0; - is_lb_pkt = qlcnic_83xx_is_lb_pkt(sts_data[1], 1); - qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid); - } if (qlcnic_83xx_is_tstamp(sts_data[1])) data_offset = l4_hdr_offset + QLCNIC_TCP_TS_HDR_SIZE; else @@ -1700,7 +1715,14 @@ qlcnic_83xx_process_lro(struct qlcnic_adapter *adapter, skb_put(skb, lro_length + data_offset); skb_pull(skb, l2_hdr_offset); - if (unlikely(qlcnic_check_rx_tagging(adapter, skb, &vid))) { + err = qlcnic_check_rx_tagging(adapter, skb, &vid); + + if (adapter->rx_mac_learn) { + is_lb_pkt = qlcnic_83xx_is_lb_pkt(sts_data[1], 1); + qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, vid); + } + + if (unlikely(err)) { adapter->stats.rxdropped++; dev_kfree_skb(skb); return buffer; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index eeec83a0e664..eec7b412477c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -546,6 +546,7 @@ static struct qlcnic_hardware_ops qlcnic_hw_ops = { .io_error_detected = qlcnic_82xx_io_error_detected, .io_slot_reset = qlcnic_82xx_io_slot_reset, .io_resume = qlcnic_82xx_io_resume, + .get_beacon_state = qlcnic_82xx_get_beacon_state, }; static int qlcnic_check_multi_tx_capability(struct qlcnic_adapter *adapter) @@ -2779,6 +2780,9 @@ static struct net_device_stats *qlcnic_get_stats(struct net_device *netdev) struct qlcnic_adapter *adapter = netdev_priv(netdev); struct net_device_stats *stats = &netdev->stats; + if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) + qlcnic_update_stats(adapter); + stats->rx_packets = adapter->stats.rx_pkts + adapter->stats.lro_pkts; stats->tx_packets = adapter->stats.xmitfinished; stats->rx_bytes = adapter->stats.rxbytes + adapter->stats.lrobytes; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index bf8fca7d874f..f998fdcd7551 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -277,9 +277,7 @@ static void qlcnic_sriov_vf_cleanup(struct qlcnic_adapter *adapter) void qlcnic_sriov_cleanup(struct qlcnic_adapter *adapter) { - struct qlcnic_sriov *sriov = adapter->ahw->sriov; - - if (!sriov) + if (!test_bit(__QLCNIC_SRIOV_ENABLE, &adapter->state)) return; qlcnic_sriov_free_vlans(adapter); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index d14d9a139eef..09acf15c3a56 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -9,9 +9,14 @@ #include "qlcnic.h" #include <linux/types.h> -#define QLCNIC_SRIOV_VF_MAX_MAC 8 +#define QLCNIC_SRIOV_VF_MAX_MAC 7 #define QLC_VF_MIN_TX_RATE 100 #define QLC_VF_MAX_TX_RATE 9999 +#define QLC_MAC_OPCODE_MASK 0x7 +#define QLC_MAC_STAR_ADD 6 +#define QLC_MAC_STAR_DEL 7 +#define QLC_VF_FLOOD_BIT BIT_16 +#define QLC_FLOOD_MODE 0x5 static int qlcnic_sriov_pf_get_vport_handle(struct qlcnic_adapter *, u8); @@ -344,6 +349,28 @@ static int qlcnic_sriov_pf_cfg_vlan_filtering(struct qlcnic_adapter *adapter, return err; } +/* On configuring VF flood bit, PFD will receive traffic from all VFs */ +static int qlcnic_sriov_pf_cfg_flood(struct qlcnic_adapter *adapter) +{ + struct qlcnic_cmd_args cmd; + int err; + + err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_SET_NIC_INFO); + if (err) + return err; + + cmd.req.arg[1] = QLC_FLOOD_MODE | QLC_VF_FLOOD_BIT; + + err = qlcnic_issue_cmd(adapter, &cmd); + if (err) + dev_err(&adapter->pdev->dev, + "Failed to configure VF Flood bit on PF, err=%d\n", + err); + + qlcnic_free_mbx_args(&cmd); + return err; +} + static int qlcnic_sriov_pf_cfg_eswitch(struct qlcnic_adapter *adapter, u8 func, u8 enable) { @@ -471,6 +498,12 @@ static int qlcnic_sriov_pf_init(struct qlcnic_adapter *adapter) if (err) return err; + if (qlcnic_84xx_check(adapter)) { + err = qlcnic_sriov_pf_cfg_flood(adapter); + if (err) + goto disable_vlan_filtering; + } + err = qlcnic_sriov_pf_cfg_eswitch(adapter, func, 1); if (err) goto disable_vlan_filtering; @@ -1173,6 +1206,13 @@ static int qlcnic_sriov_validate_cfg_macvlan(struct qlcnic_adapter *adapter, struct qlcnic_vport *vp = vf->vp; u8 op, new_op; + if (((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_ADD) || + ((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_DEL)) { + netdev_err(adapter->netdev, "MAC + any VLAN filter not allowed from VF %d\n", + vf->pci_func); + return -EINVAL; + } + if (!(cmd->req.arg[1] & BIT_8)) return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index b5296672c447..1c8552f682d6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -6,7 +6,6 @@ */ #include <linux/slab.h> -#include <linux/vmalloc.h> #include <linux/interrupt.h> #include "qlcnic.h" @@ -127,6 +126,8 @@ static int qlcnic_83xx_store_beacon(struct qlcnic_adapter *adapter, if (kstrtoul(buf, 2, &h_beacon)) return -EINVAL; + qlcnic_get_beacon_state(adapter); + if (ahw->beacon_state == h_beacon) return len; @@ -158,7 +159,7 @@ static int qlcnic_82xx_store_beacon(struct qlcnic_adapter *adapter, struct qlcnic_hardware_context *ahw = adapter->ahw; int err, drv_sds_rings = adapter->drv_sds_rings; u16 beacon; - u8 h_beacon_state, b_state, b_rate; + u8 b_state, b_rate; if (len != sizeof(u16)) return QL_STATUS_INVALID_PARAM; @@ -168,18 +169,7 @@ static int qlcnic_82xx_store_beacon(struct qlcnic_adapter *adapter, if (err) return err; - if (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_2_BEACON) { - err = qlcnic_get_beacon_state(adapter, &h_beacon_state); - if (err) { - netdev_err(adapter->netdev, - "Failed to get current beacon state\n"); - } else { - if (h_beacon_state == QLCNIC_BEACON_DISABLE) - ahw->beacon_state = 0; - else if (h_beacon_state == QLCNIC_BEACON_EANBLE) - ahw->beacon_state = 2; - } - } + qlcnic_get_beacon_state(adapter); if (ahw->beacon_state == b_state) return len; @@ -927,38 +917,35 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_pci_func_cfg *pci_cfg; struct qlcnic_pci_info *pci_info; - size_t pci_info_sz, pci_cfg_sz; + size_t pci_cfg_sz; int i, ret; pci_cfg_sz = pci_func_count * sizeof(*pci_cfg); if (size != pci_cfg_sz) return QL_STATUS_INVALID_PARAM; - pci_info_sz = pci_func_count * sizeof(*pci_info); - pci_info = vmalloc(pci_info_sz); + pci_info = kcalloc(pci_func_count, sizeof(*pci_info), GFP_KERNEL); if (!pci_info) return -ENOMEM; - memset(pci_info, 0, pci_info_sz); - memset(buf, 0, pci_cfg_sz); - pci_cfg = (struct qlcnic_pci_func_cfg *)buf; - ret = qlcnic_get_pci_info(adapter, pci_info); if (ret) { - vfree(pci_info); + kfree(pci_info); return ret; } + pci_cfg = (struct qlcnic_pci_func_cfg *)buf; for (i = 0; i < pci_func_count; i++) { pci_cfg[i].pci_func = pci_info[i].id; pci_cfg[i].func_type = pci_info[i].type; + pci_cfg[i].func_state = 0; pci_cfg[i].port_num = pci_info[i].default_port; pci_cfg[i].min_bw = pci_info[i].tx_min_bw; pci_cfg[i].max_bw = pci_info[i].tx_max_bw; memcpy(&pci_cfg[i].def_mac_addr, &pci_info[i].mac, ETH_ALEN); } - vfree(pci_info); + kfree(pci_info); return size; } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 888410737dbd..ba1f6c928b91 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1513,11 +1513,11 @@ ignore_link: if (intr_status & mask) { /* Tx error */ u32 edtrr = sh_eth_read(ndev, EDTRR); + /* dmesg */ - dev_err(&ndev->dev, "TX error. status=%8.8x cur_tx=%8.8x ", - intr_status, mdp->cur_tx); - dev_err(&ndev->dev, "dirty_tx=%8.8x state=%8.8x EDTRR=%8.8x.\n", - mdp->dirty_tx, (u32) ndev->state, edtrr); + dev_err(&ndev->dev, "TX error. status=%8.8x cur_tx=%8.8x dirty_tx=%8.8x state=%8.8x EDTRR=%8.8x.\n", + intr_status, mdp->cur_tx, mdp->dirty_tx, + (u32)ndev->state, edtrr); /* dirty buffer free */ sh_eth_txfree(ndev); diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 96f79f7c4395..a6a9e1ebe30c 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1894,7 +1894,7 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, SMC_SELECT_BANK(lp, 1); val = SMC_GET_BASE(lp); val = ((val & 0x1F00) >> 3) << SMC_IO_SHIFT; - if (((unsigned int)ioaddr & (0x3e0 << SMC_IO_SHIFT)) != val) { + if (((unsigned long)ioaddr & (0x3e0 << SMC_IO_SHIFT)) != val) { netdev_warn(dev, "%s: IOADDR %p doesn't match configuration (%x).\n", CARDNAME, ioaddr, val); } diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 570495be77f3..023237a65720 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -2070,7 +2070,8 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) } /* Return subqueue id on this core (one per core). */ -static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { return smp_processor_id(); } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 09ababe54a5b..8433de4509c7 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -299,7 +299,7 @@ static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, if (vlan->fwd_priv) { skb->dev = vlan->lowerdev; - ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv); + ret = dev_queue_xmit_accel(skb, vlan->fwd_priv); } else { ret = macvlan_queue_xmit(skb, dev); } @@ -337,6 +337,8 @@ static const struct header_ops macvlan_hard_header_ops = { .cache_update = eth_header_cache_update, }; +static struct rtnl_link_ops macvlan_link_ops; + static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -352,7 +354,8 @@ static int macvlan_open(struct net_device *dev) goto hash_add; } - if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) { + if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD && + dev->rtnl_link_ops == &macvlan_link_ops) { vlan->fwd_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); @@ -361,10 +364,8 @@ static int macvlan_open(struct net_device *dev) */ if (IS_ERR_OR_NULL(vlan->fwd_priv)) { vlan->fwd_priv = NULL; - } else { - dev->features &= ~NETIF_F_LLTX; + } else return 0; - } } err = -EBUSY; @@ -698,8 +699,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, features = netdev_increment_features(vlan->lowerdev->features, features, mask); - if (!vlan->fwd_priv) - features |= NETIF_F_LLTX; + features |= NETIF_F_LLTX; return features; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5d81c89ee52b..39794c4d7b21 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -30,6 +30,7 @@ #include <linux/mii.h> #include <linux/ethtool.h> #include <linux/phy.h> +#include <linux/mdio.h> #include <linux/io.h> #include <linux/uaccess.h> @@ -50,14 +51,17 @@ static void phy_device_release(struct device *dev) kfree(to_phy_device(dev)); } -static struct phy_driver genphy_driver; +enum genphy_driver { + GENPHY_DRV_1G, + GENPHY_DRV_10G, + GENPHY_DRV_MAX +}; + +static struct phy_driver genphy_driver[GENPHY_DRV_MAX]; static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock); -static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, - u32 flags, phy_interface_t interface); - /** * phy_register_fixup - creates a new phy_fixup and adds it to the list * @bus_id: A string which matches phydev->dev.bus_id (or PHY_ANY_ID) @@ -560,13 +564,13 @@ EXPORT_SYMBOL(phy_init_hw); * * Description: Called by drivers to attach to a particular PHY * device. The phy_device is found, and properly hooked up - * to the phy_driver. If no driver is attached, then the - * genphy_driver is used. The phy_device is given a ptr to + * to the phy_driver. If no driver is attached, then a + * generic driver is used. The phy_device is given a ptr to * the attaching device, and given a callback for link status * change. The phy_device is returned to the attaching driver. */ -static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, - u32 flags, phy_interface_t interface) +int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, + u32 flags, phy_interface_t interface) { struct device *d = &phydev->dev; int err; @@ -575,12 +579,10 @@ static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, * exist, and we should use the genphy driver. */ if (NULL == d->driver) { - if (phydev->is_c45) { - pr_err("No driver for phy %x\n", phydev->phy_id); - return -ENODEV; - } - - d->driver = &genphy_driver.driver; + if (phydev->is_c45) + d->driver = &genphy_driver[GENPHY_DRV_10G].driver; + else + d->driver = &genphy_driver[GENPHY_DRV_1G].driver; err = d->driver->probe(d); if (err >= 0) @@ -616,6 +618,7 @@ static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, return err; } +EXPORT_SYMBOL(phy_attach_direct); /** * phy_attach - attach a network device to a particular PHY device @@ -658,6 +661,7 @@ EXPORT_SYMBOL(phy_attach); */ void phy_detach(struct phy_device *phydev) { + int i; phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; phy_suspend(phydev); @@ -667,8 +671,12 @@ void phy_detach(struct phy_device *phydev) * from the generic driver so that there's a chance a * real driver could be loaded */ - if (phydev->dev.driver == &genphy_driver.driver) - device_release_driver(&phydev->dev); + for (i = 0; i < ARRAY_SIZE(genphy_driver); i++) { + if (phydev->dev.driver == &genphy_driver[i].driver) { + device_release_driver(&phydev->dev); + break; + } + } } EXPORT_SYMBOL(phy_detach); @@ -759,6 +767,12 @@ static int genphy_config_advert(struct phy_device *phydev) return changed; } +int gen10g_config_advert(struct phy_device *dev) +{ + return 0; +} +EXPORT_SYMBOL(gen10g_config_advert); + /** * genphy_setup_forced - configures/forces speed/duplex from @phydev * @phydev: target phy_device struct @@ -806,6 +820,12 @@ int genphy_restart_aneg(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_restart_aneg); +int gen10g_restart_aneg(struct phy_device *phydev) +{ + return 0; +} +EXPORT_SYMBOL(gen10g_restart_aneg); + /** * genphy_config_aneg - restart auto-negotiation or write BMCR * @phydev: target phy_device struct @@ -847,6 +867,12 @@ int genphy_config_aneg(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_config_aneg); +int gen10g_config_aneg(struct phy_device *phydev) +{ + return 0; +} +EXPORT_SYMBOL(gen10g_config_aneg); + /** * genphy_update_link - update link status in @phydev * @phydev: target phy_device struct @@ -978,6 +1004,34 @@ int genphy_read_status(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_read_status); +int gen10g_read_status(struct phy_device *phydev) +{ + int devad, reg; + u32 mmd_mask = phydev->c45_ids.devices_in_package; + + phydev->link = 1; + + /* For now just lie and say it's 10G all the time */ + phydev->speed = SPEED_10000; + phydev->duplex = DUPLEX_FULL; + + for (devad = 0; mmd_mask; devad++, mmd_mask = mmd_mask >> 1) { + if (!(mmd_mask & 1)) + continue; + + /* Read twice because link state is latched and a + * read moves the current state into the register + */ + phy_read_mmd(phydev, devad, MDIO_STAT1); + reg = phy_read_mmd(phydev, devad, MDIO_STAT1); + if (reg < 0 || !(reg & MDIO_STAT1_LSTATUS)) + phydev->link = 0; + } + + return 0; +} +EXPORT_SYMBOL(gen10g_read_status); + static int genphy_config_init(struct phy_device *phydev) { int val; @@ -1023,6 +1077,16 @@ static int genphy_config_init(struct phy_device *phydev) return 0; } + +static int gen10g_config_init(struct phy_device *phydev) +{ + /* Temporarily just say we support everything */ + phydev->supported = SUPPORTED_10000baseT_Full; + phydev->advertising = SUPPORTED_10000baseT_Full; + + return 0; +} + int genphy_suspend(struct phy_device *phydev) { int value; @@ -1038,6 +1102,12 @@ int genphy_suspend(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_suspend); +int gen10g_suspend(struct phy_device *phydev) +{ + return 0; +} +EXPORT_SYMBOL(gen10g_suspend); + int genphy_resume(struct phy_device *phydev) { int value; @@ -1053,6 +1123,12 @@ int genphy_resume(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_resume); +int gen10g_resume(struct phy_device *phydev) +{ + return 0; +} +EXPORT_SYMBOL(gen10g_resume); + /** * phy_probe - probe and init a PHY device * @dev: device to probe and init @@ -1173,7 +1249,8 @@ void phy_drivers_unregister(struct phy_driver *drv, int n) } EXPORT_SYMBOL(phy_drivers_unregister); -static struct phy_driver genphy_driver = { +static struct phy_driver genphy_driver[] = { +{ .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic PHY", @@ -1184,7 +1261,18 @@ static struct phy_driver genphy_driver = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE, }, -}; +}, { + .phy_id = 0xffffffff, + .phy_id_mask = 0xffffffff, + .name = "Generic 10G PHY", + .config_init = gen10g_config_init, + .features = 0, + .config_aneg = gen10g_config_aneg, + .read_status = gen10g_read_status, + .suspend = gen10g_suspend, + .resume = gen10g_resume, + .driver = {.owner = THIS_MODULE, }, +} }; static int __init phy_init(void) { @@ -1194,7 +1282,8 @@ static int __init phy_init(void) if (rc) return rc; - rc = phy_driver_register(&genphy_driver); + rc = phy_drivers_register(genphy_driver, + ARRAY_SIZE(genphy_driver)); if (rc) mdio_bus_exit(); @@ -1203,7 +1292,8 @@ static int __init phy_init(void) static void __exit phy_exit(void) { - phy_driver_unregister(&genphy_driver); + phy_drivers_unregister(genphy_driver, + ARRAY_SIZE(genphy_driver)); mdio_bus_exit(); } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 736050d6b451..b75ae5bde673 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1647,7 +1647,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 09f66624eaca..34cca74c99ed 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -364,7 +364,8 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) * different rxq no. here. If we could not get rxhash, then we would * hope the rxq no. may help here. */ -static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 56c175ebae3c..4671da755e7b 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1244,7 +1244,7 @@ static int build_dma_sg(const struct sk_buff *skb, struct urb *urb) return -ENOMEM; urb->num_sgs = num_sgs; - sg_init_table(urb->sg, urb->num_sgs); + sg_init_table(urb->sg, urb->num_sgs + 1); sg_set_buf(&urb->sg[s++], skb->data, skb_headlen(skb)); total_len += skb_headlen(skb); diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index e58b8af56c04..3040924f5f3c 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -362,21 +362,27 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095B, 0x5012, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095B, 0x500A, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5020, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x502A, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5420, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5090, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5190, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5590, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5290, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5490, iwl7265_2ac_cfg)}, #endif /* CONFIG_IWLMVM */ diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 9c0cc8ded021..fa41a773b79b 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2018,7 +2018,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2, (hwsim_flags & HWSIM_TX_STAT_ACK)) { if (skb->len >= 16) { hdr = (struct ieee80211_hdr *) skb->data; - mac80211_hwsim_monitor_ack(txi->rate_driver_data[0], + mac80211_hwsim_monitor_ack(data2->channel, hdr->addr2); } txi->flags |= IEEE80211_TX_STAT_ACK; diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index 2d6f5e1721cf..4d79761b9c87 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -747,7 +747,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) } static u16 -mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb) +mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 27385639b6e5..6b62c3eb8e18 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -39,7 +39,6 @@ #include <linux/udp.h> #include <net/tcp.h> -#include <net/ip6_checksum.h> #include <xen/xen.h> #include <xen/events.h> @@ -1051,257 +1050,9 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return 0; } -static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len, - unsigned int max) -{ - if (skb_headlen(skb) >= len) - return 0; - - /* If we need to pullup then pullup to the max, so we - * won't need to do it again. - */ - if (max > skb->len) - max = skb->len; - - if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) - return -ENOMEM; - - if (skb_headlen(skb) < len) - return -EPROTO; - - return 0; -} - -/* This value should be large enough to cover a tagged ethernet header plus - * maximally sized IP and TCP or UDP headers. - */ -#define MAX_IP_HDR_LEN 128 - -static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, - int recalculate_partial_csum) -{ - unsigned int off; - bool fragment; - int err; - - fragment = false; - - err = maybe_pull_tail(skb, - sizeof(struct iphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) - fragment = true; - - off = ip_hdrlen(skb); - - err = -EPROTO; - - if (fragment) - goto out; - - switch (ip_hdr(skb)->protocol) { - case IPPROTO_TCP: - err = maybe_pull_tail(skb, - off + sizeof(struct tcphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate_partial_csum) - tcp_hdr(skb)->check = - ~csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - off, - IPPROTO_TCP, 0); - break; - case IPPROTO_UDP: - err = maybe_pull_tail(skb, - off + sizeof(struct udphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate_partial_csum) - udp_hdr(skb)->check = - ~csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - off, - IPPROTO_UDP, 0); - break; - default: - goto out; - } - - err = 0; - -out: - return err; -} - -/* This value should be large enough to cover a tagged ethernet header plus - * an IPv6 header, all options, and a maximal TCP or UDP header. - */ -#define MAX_IPV6_HDR_LEN 256 - -#define OPT_HDR(type, skb, off) \ - (type *)(skb_network_header(skb) + (off)) - -static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, - int recalculate_partial_csum) -{ - int err; - u8 nexthdr; - unsigned int off; - unsigned int len; - bool fragment; - bool done; - - fragment = false; - done = false; - - off = sizeof(struct ipv6hdr); - - err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - nexthdr = ipv6_hdr(skb)->nexthdr; - - len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); - while (off <= len && !done) { - switch (nexthdr) { - case IPPROTO_DSTOPTS: - case IPPROTO_HOPOPTS: - case IPPROTO_ROUTING: { - struct ipv6_opt_hdr *hp; - - err = maybe_pull_tail(skb, - off + - sizeof(struct ipv6_opt_hdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); - nexthdr = hp->nexthdr; - off += ipv6_optlen(hp); - break; - } - case IPPROTO_AH: { - struct ip_auth_hdr *hp; - - err = maybe_pull_tail(skb, - off + - sizeof(struct ip_auth_hdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - hp = OPT_HDR(struct ip_auth_hdr, skb, off); - nexthdr = hp->nexthdr; - off += ipv6_authlen(hp); - break; - } - case IPPROTO_FRAGMENT: { - struct frag_hdr *hp; - - err = maybe_pull_tail(skb, - off + - sizeof(struct frag_hdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - hp = OPT_HDR(struct frag_hdr, skb, off); - - if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) - fragment = true; - - nexthdr = hp->nexthdr; - off += sizeof(struct frag_hdr); - break; - } - default: - done = true; - break; - } - } - - err = -EPROTO; - - if (!done || fragment) - goto out; - - switch (nexthdr) { - case IPPROTO_TCP: - err = maybe_pull_tail(skb, - off + sizeof(struct tcphdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate_partial_csum) - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - off, - IPPROTO_TCP, 0); - break; - case IPPROTO_UDP: - err = maybe_pull_tail(skb, - off + sizeof(struct udphdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate_partial_csum) - udp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - off, - IPPROTO_UDP, 0); - break; - default: - goto out; - } - - err = 0; - -out: - return err; -} - static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) { - int err = -EPROTO; - int recalculate_partial_csum = 0; + bool recalculate_partial_csum = false; /* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy * peers can fail to set NETRXF_csum_blank when sending a GSO @@ -1311,19 +1062,14 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { vif->rx_gso_checksum_fixup++; skb->ip_summed = CHECKSUM_PARTIAL; - recalculate_partial_csum = 1; + recalculate_partial_csum = true; } /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; - if (skb->protocol == htons(ETH_P_IP)) - err = checksum_setup_ip(vif, skb, recalculate_partial_csum); - else if (skb->protocol == htons(ETH_P_IPV6)) - err = checksum_setup_ipv6(vif, skb, recalculate_partial_csum); - - return err; + return skb_checksum_setup(skb, recalculate_partial_csum); } static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e59acb1daa23..c41537b577a4 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -859,9 +859,7 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np, static int checksum_setup(struct net_device *dev, struct sk_buff *skb) { - struct iphdr *iph; - int err = -EPROTO; - int recalculate_partial_csum = 0; + bool recalculate_partial_csum = false; /* * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy @@ -873,54 +871,14 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb) struct netfront_info *np = netdev_priv(dev); np->rx_gso_checksum_fixup++; skb->ip_summed = CHECKSUM_PARTIAL; - recalculate_partial_csum = 1; + recalculate_partial_csum = true; } /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; - if (skb->protocol != htons(ETH_P_IP)) - goto out; - - iph = (void *)skb->data; - - switch (iph->protocol) { - case IPPROTO_TCP: - if (!skb_partial_csum_set(skb, 4 * iph->ihl, - offsetof(struct tcphdr, check))) - goto out; - - if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - iph->ihl*4, - IPPROTO_TCP, 0); - } - break; - case IPPROTO_UDP: - if (!skb_partial_csum_set(skb, 4 * iph->ihl, - offsetof(struct udphdr, check))) - goto out; - - if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - iph->ihl*4, - IPPROTO_UDP, 0); - } - break; - default: - if (net_ratelimit()) - pr_err("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n", - iph->protocol); - goto out; - } - - err = 0; - -out: - return err; + return skb_checksum_setup(skb, recalculate_partial_csum); } static int handle_incoming_queue(struct net_device *dev, diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index a43b8523c61e..875b7b6f0d2a 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -254,3 +254,23 @@ struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, return IS_ERR(phy) ? NULL : phy; } EXPORT_SYMBOL(of_phy_connect_fixed_link); + +/** + * of_phy_attach - Attach to a PHY without starting the state machine + * @dev: pointer to net_device claiming the phy + * @phy_np: Node pointer for the PHY + * @flags: flags to pass to the PHY + * @iface: PHY data interface type + */ +struct phy_device *of_phy_attach(struct net_device *dev, + struct device_node *phy_np, u32 flags, + phy_interface_t iface) +{ + struct phy_device *phy = of_phy_find_device(phy_np); + + if (!phy) + return NULL; + + return phy_attach_direct(dev, phy, flags, iface) ? NULL : phy; +} +EXPORT_SYMBOL(of_phy_attach); diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index 8f9be2e09937..a208a457558c 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -30,6 +30,7 @@ static const char *phy_modes[] = { [PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid", [PHY_INTERFACE_MODE_RTBI] = "rtbi", [PHY_INTERFACE_MODE_SMII] = "smii", + [PHY_INTERFACE_MODE_XGMII] = "xgmii", }; /** diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 1cf605f67673..e86439283a5d 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -279,7 +279,9 @@ static acpi_status register_slot(acpi_handle handle, u32 lvl, void *data, status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr); if (ACPI_FAILURE(status)) { - acpi_handle_warn(handle, "can't evaluate _ADR (%#x)\n", status); + if (status != AE_NOT_FOUND) + acpi_handle_warn(handle, + "can't evaluate _ADR (%#x)\n", status); return AE_OK; } @@ -643,6 +645,24 @@ static void disable_slot(struct acpiphp_slot *slot) slot->flags &= (~SLOT_ENABLED); } +static bool acpiphp_no_hotplug(acpi_handle handle) +{ + struct acpi_device *adev = NULL; + + acpi_bus_get_device(handle, &adev); + return adev && adev->flags.no_hotplug; +} + +static bool slot_no_hotplug(struct acpiphp_slot *slot) +{ + struct acpiphp_func *func; + + list_for_each_entry(func, &slot->funcs, sibling) + if (acpiphp_no_hotplug(func_to_handle(func))) + return true; + + return false; +} /** * get_slot_status - get ACPI slot status @@ -701,7 +721,8 @@ static void trim_stale_devices(struct pci_dev *dev) unsigned long long sta; status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); - alive = ACPI_SUCCESS(status) && sta == ACPI_STA_ALL; + alive = (ACPI_SUCCESS(status) && sta == ACPI_STA_ALL) + || acpiphp_no_hotplug(handle); } if (!alive) { u32 v; @@ -741,8 +762,9 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge) struct pci_dev *dev, *tmp; mutex_lock(&slot->crit_sect); - /* wake up all functions */ - if (get_slot_status(slot) == ACPI_STA_ALL) { + if (slot_no_hotplug(slot)) { + ; /* do nothing */ + } else if (get_slot_status(slot) == ACPI_STA_ALL) { /* remove stale devices if any */ list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 577074efbe62..f7ebdba14bde 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -330,29 +330,32 @@ static int acpi_pci_find_device(struct device *dev, acpi_handle *handle) static void pci_acpi_setup(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - acpi_handle handle = ACPI_HANDLE(dev); - struct acpi_device *adev; + struct acpi_device *adev = ACPI_COMPANION(dev); - if (acpi_bus_get_device(handle, &adev) || !adev->wakeup.flags.valid) + if (!adev) + return; + + pci_acpi_add_pm_notifier(adev, pci_dev); + if (!adev->wakeup.flags.valid) return; device_set_wakeup_capable(dev, true); acpi_pci_sleep_wake(pci_dev, false); - - pci_acpi_add_pm_notifier(adev, pci_dev); if (adev->wakeup.flags.run_wake) device_set_run_wake(dev, true); } static void pci_acpi_cleanup(struct device *dev) { - acpi_handle handle = ACPI_HANDLE(dev); - struct acpi_device *adev; + struct acpi_device *adev = ACPI_COMPANION(dev); + + if (!adev) + return; - if (!acpi_bus_get_device(handle, &adev) && adev->wakeup.flags.valid) { + pci_acpi_remove_pm_notifier(adev); + if (adev->wakeup.flags.valid) { device_set_wakeup_capable(dev, false); device_set_run_wake(dev, false); - pci_acpi_remove_pm_notifier(adev); } } diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 5e2054afe840..85ad58c6da17 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -196,6 +196,7 @@ config BATTERY_MAX17040 config BATTERY_MAX17042 tristate "Maxim MAX17042/17047/17050/8997/8966 Fuel Gauge" depends on I2C + select REGMAP_I2C help MAX17042 is fuel-gauge systems for lithium-ion (Li+) batteries in handheld and portable equipment. The MAX17042 is configured diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c index 00e667296360..557af943b2f5 100644 --- a/drivers/power/power_supply_core.c +++ b/drivers/power/power_supply_core.c @@ -511,6 +511,10 @@ int power_supply_register(struct device *parent, struct power_supply *psy) dev_set_drvdata(dev, psy); psy->dev = dev; + rc = dev_set_name(dev, "%s", psy->name); + if (rc) + goto dev_set_name_failed; + INIT_WORK(&psy->changed_work, power_supply_changed_work); rc = power_supply_check_supplies(psy); @@ -524,10 +528,6 @@ int power_supply_register(struct device *parent, struct power_supply *psy) if (rc) goto wakeup_init_failed; - rc = kobject_set_name(&dev->kobj, "%s", psy->name); - if (rc) - goto kobject_set_name_failed; - rc = device_add(dev); if (rc) goto device_add_failed; @@ -553,11 +553,11 @@ create_triggers_failed: register_cooler_failed: psy_unregister_thermal(psy); register_thermal_failed: -wakeup_init_failed: device_del(dev); -kobject_set_name_failed: device_add_failed: +wakeup_init_failed: check_supplies_failed: +dev_set_name_failed: put_device(dev); success: return rc; diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index 3f4ca4e09a4c..34629ea913d4 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -942,7 +942,7 @@ static int tty3270_install(struct tty_driver *driver, struct tty_struct *tty) return rc; } - tp->screen = tty3270_alloc_screen(tp->view.cols, tp->view.rows); + tp->screen = tty3270_alloc_screen(tp->view.rows, tp->view.cols); if (IS_ERR(tp->screen)) { rc = PTR_ERR(tp->screen); raw3270_put_view(&tp->view); diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c index 53fee2f9a498..8dfdd2732bdc 100644 --- a/drivers/staging/bcm/Bcmnet.c +++ b/drivers/staging/bcm/Bcmnet.c @@ -39,7 +39,8 @@ static INT bcm_close(struct net_device *dev) return 0; } -static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { return ClassifyPacket(netdev_priv(dev), skb); } diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c index 235d2b1ec593..eedffed17e39 100644 --- a/drivers/staging/netlogic/xlr_net.c +++ b/drivers/staging/netlogic/xlr_net.c @@ -306,7 +306,8 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb) +static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb, + void *accel_priv) { return (u16)smp_processor_id(); } diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index 17659bb04bef..dd69e344e409 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -652,7 +652,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) return dscp >> 5; } -static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index aa3397620342..2c29db6a247e 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -477,9 +477,10 @@ extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon, const int netfid, __u64 *pExtAttrBits, __u64 *pMask); extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb); extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr); -extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr, - const unsigned char *path, - struct cifs_sb_info *cifs_sb, unsigned int xid); +extern int CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, + struct cifs_fattr *fattr, + const unsigned char *path); extern int mdfour(unsigned char *, unsigned char *, int); extern int E_md4hash(const unsigned char *passwd, unsigned char *p16, const struct nls_table *codepage); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 124aa0230c1b..d707edb6b852 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4010,7 +4010,7 @@ QFileInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc); + cifs_dbg(FYI, "Send error in QFileInfo = %d", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4179,7 +4179,7 @@ UnixQFileInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc); + cifs_dbg(FYI, "Send error in UnixQFileInfo = %d", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4263,7 +4263,7 @@ UnixQPathInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc); + cifs_dbg(FYI, "Send error in UnixQPathInfo = %d", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 11ff5f116b20..a514e0a65f69 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -193,7 +193,7 @@ check_name(struct dentry *direntry) static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, struct tcon_link *tlink, unsigned oflags, umode_t mode, - __u32 *oplock, struct cifs_fid *fid, int *created) + __u32 *oplock, struct cifs_fid *fid) { int rc = -ENOENT; int create_options = CREATE_NOT_DIR; @@ -349,7 +349,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, .device = 0, }; - *created |= FILE_CREATED; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { args.uid = current_fsuid(); if (inode->i_mode & S_ISGID) @@ -480,13 +479,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, cifs_add_pending_open(&fid, tlink, &open); rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid, opened); + &oplock, &fid); if (rc) { cifs_del_pending_open(&open); goto out; } + if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + *opened |= FILE_CREATED; + rc = finish_open(file, direntry, generic_file_open, opened); if (rc) { if (server->ops->close) @@ -529,7 +531,6 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, struct TCP_Server_Info *server; struct cifs_fid fid; __u32 oplock; - int created = FILE_CREATED; cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n", inode, direntry->d_name.name, direntry); @@ -546,7 +547,7 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, server->ops->new_lease_key(&fid); rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid, &created); + &oplock, &fid); if (!rc && server->ops->close) server->ops->close(xid, tcon, &fid); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 36f9ebb93ceb..49719b8228e5 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -383,7 +383,8 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* check for Minshall+French symlinks */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { - int tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid); + int tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr, + full_path); if (tmprc) cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc); } @@ -799,7 +800,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, /* check for Minshall+French symlinks */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { - tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid); + tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr, + full_path); if (tmprc) cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc); } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index cc0234710ddb..92aee08483a5 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -354,34 +354,30 @@ open_query_close_cifs_symlink(const unsigned char *path, char *pbuf, int -CIFSCheckMFSymlink(struct cifs_fattr *fattr, - const unsigned char *path, - struct cifs_sb_info *cifs_sb, unsigned int xid) +CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, + const unsigned char *path) { - int rc = 0; + int rc; u8 *buf = NULL; unsigned int link_len = 0; unsigned int bytes_read = 0; - struct cifs_tcon *ptcon; if (!CIFSCouldBeMFSymlink(fattr)) /* it's not a symlink */ return 0; buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - goto out; - } + if (!buf) + return -ENOMEM; - ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb)); - if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink)) - rc = ptcon->ses->server->ops->query_mf_symlink(path, buf, - &bytes_read, cifs_sb, xid); + if (tcon->ses->server->ops->query_mf_symlink) + rc = tcon->ses->server->ops->query_mf_symlink(path, buf, + &bytes_read, cifs_sb, xid); else - goto out; + rc = -ENOSYS; - if (rc != 0) + if (rc) goto out; if (bytes_read == 0) /* not a symlink */ diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8b5e2584c840..af903128891c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1907,10 +1907,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } } } - if (op == EPOLL_CTL_DEL && is_file_epoll(tf.file)) { - tep = tf.file->private_data; - mutex_lock_nested(&tep->mtx, 1); - } /* * Try to lookup the file inside our RB tree, Since we grabbed "mtx" diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4410cc3d6ee2..3384dc4bed40 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4218,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, */ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; newex.ee_block = cpu_to_le32(map->m_lblk); - cluster_offset = EXT4_LBLK_CMASK(sbi, map->m_lblk); + cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index b7fc035a6943..73f3e4ee4037 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -986,6 +986,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + struct address_space *mapping = inode->i_mapping; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; int rv; @@ -1006,6 +1007,35 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, if (rv != 1) goto out; /* dio not valid, fall back to buffered i/o */ + /* + * Now since we are holding a deferred (CW) lock at this point, you + * might be wondering why this is ever needed. There is a case however + * where we've granted a deferred local lock against a cached exclusive + * glock. That is ok provided all granted local locks are deferred, but + * it also means that it is possible to encounter pages which are + * cached and possibly also mapped. So here we check for that and sort + * them out ahead of the dio. The glock state machine will take care of + * everything else. + * + * If in fact the cached glock state (gl->gl_state) is deferred (CW) in + * the first place, mapping->nr_pages will always be zero. + */ + if (mapping->nrpages) { + loff_t lstart = offset & (PAGE_CACHE_SIZE - 1); + loff_t len = iov_length(iov, nr_segs); + loff_t end = PAGE_ALIGN(offset + len) - 1; + + rv = 0; + if (len == 0) + goto out; + if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) + unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len); + rv = filemap_write_and_wait_range(mapping, lstart, end); + if (rv) + return rv; + truncate_inode_pages_range(mapping, lstart, end); + } + rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, gfs2_get_block_direct, NULL, NULL, 0); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c8420f7e4db6..6f7a47c05259 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1655,6 +1655,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) struct task_struct *gh_owner = NULL; char flags_buf[32]; + rcu_read_lock(); if (gh->gh_owner_pid) gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID); gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n", @@ -1664,6 +1665,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1, gh_owner ? gh_owner->comm : "(ended)", (void *)gh->gh_ip); + rcu_read_unlock(); return 0; } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index db908f697139..f88dcd925010 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -192,8 +192,11 @@ static void inode_go_sync(struct gfs2_glock *gl) if (ip && !S_ISREG(ip->i_inode.i_mode)) ip = NULL; - if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) - unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); + if (ip) { + if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) + unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); + inode_dio_wait(&ip->i_inode); + } if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return; @@ -410,6 +413,9 @@ static int inode_go_lock(struct gfs2_holder *gh) return error; } + if (gh->gh_state != LM_ST_DEFERRED) + inode_dio_wait(&ip->i_inode); + if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) && (gl->gl_state == LM_ST_EXCLUSIVE) && (gh->gh_state == LM_ST_EXCLUSIVE)) { diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 610613fb65b5..9dcb9777a5f8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -551,10 +551,10 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct buffer_head *bh = bd->bd_bh; struct gfs2_glock *gl = bd->bd_gl; - gfs2_remove_from_ail(bd); - bd->bd_bh = NULL; bh->b_private = NULL; bd->bd_blkno = bh->b_blocknr; + gfs2_remove_from_ail(bd); /* drops ref on bh */ + bd->bd_bh = NULL; bd->bd_ops = &gfs2_revoke_lops; sdp->sd_log_num_revoke++; atomic_inc(&gl->gl_revokes); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 932415050540..52f177be3bf8 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -258,6 +258,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int struct address_space *mapping = bh->b_page->mapping; struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct gfs2_bufdata *bd = bh->b_private; + int was_pinned = 0; if (test_clear_buffer_pinned(bh)) { trace_gfs2_pin(bd, 0); @@ -273,12 +274,16 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int tr->tr_num_databuf_rm++; } tr->tr_touched = 1; + was_pinned = 1; brelse(bh); } if (bd) { spin_lock(&sdp->sd_ail_lock); if (bd->bd_tr) { gfs2_trans_add_revoke(sdp, bd); + } else if (was_pinned) { + bh->b_private = NULL; + kmem_cache_free(gfs2_bufdata_cachep, bd); } spin_unlock(&sdp->sd_ail_lock); } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 82303b474958..52fa88314f5c 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1366,8 +1366,18 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, if (IS_ERR(s)) goto error_bdev; - if (s->s_root) + if (s->s_root) { + /* + * s_umount nests inside bd_mutex during + * __invalidate_device(). blkdev_put() acquires + * bd_mutex and can't be called under s_umount. Drop + * s_umount temporarily. This is safe as we're + * holding an active reference. + */ + up_write(&s->s_umount); blkdev_put(bdev, mode); + down_write(&s->s_umount); + } memset(&args, 0, sizeof(args)); args.ar_quota = GFS2_QUOTA_DEFAULT; diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c index 739e0a52deda..5549d69ddb45 100644 --- a/fs/xfs/xfs_attr_remote.c +++ b/fs/xfs/xfs_attr_remote.c @@ -110,7 +110,7 @@ xfs_attr3_rmt_verify( if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt)) return false; if (be32_to_cpu(rmt->rm_offset) + - be32_to_cpu(rmt->rm_bytes) >= XATTR_SIZE_MAX) + be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX) return false; if (rmt->rm_owner == 0) return false; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 1394106ed22d..82e0dab46ee5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -287,6 +287,7 @@ xfs_bmapi_allocate( INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); queue_work(xfs_alloc_wq, &args->work); wait_for_completion(&done); + destroy_work_on_stack(&args->work); return args->result; } diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c602c7718421..ddabed1f51c2 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -169,7 +169,8 @@ struct acpi_device_flags { u32 ejectable:1; u32 power_manageable:1; u32 match_driver:1; - u32 reserved:27; + u32 no_hotplug:1; + u32 reserved:26; }; /* File System */ @@ -344,6 +345,7 @@ extern struct kobject *acpi_kobj; extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int); void acpi_bus_private_data_handler(acpi_handle, void *); int acpi_bus_get_private_data(acpi_handle, void **); +void acpi_bus_no_hotplug(acpi_handle handle); extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32); extern int register_acpi_notifier(struct notifier_block *); extern int unregister_acpi_notifier(struct notifier_block *); diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 87578c109e48..49376aec2fbb 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -600,7 +600,7 @@ {0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\ {0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\ - {0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\ + {0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\ {0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ diff --git a/include/linux/net.h b/include/linux/net.h index 69be3e6079c8..94734a6259a4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -245,9 +245,6 @@ do { \ #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) -#define net_random() prandom_u32() -#define net_srandom(seed) prandom_seed((__force u32)(seed)) - bool __net_get_random_once(void *buf, int nbytes, bool *done, struct static_key *done_key); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a2a70cc70e7b..5c88ab19b3eb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -769,7 +769,8 @@ struct netdev_phys_port_id { * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * - * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); + * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, + * void *accel_priv); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -990,7 +991,8 @@ struct net_device_ops { netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb, struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + void *accel_priv); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1532,7 +1534,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, } struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + void *accel_priv); u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* @@ -1834,6 +1837,7 @@ int dev_close(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); +int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); @@ -2486,7 +2490,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq, void *accel_priv); + struct netdev_queue *txq); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); extern int netdev_budget; diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 8163107b94b4..6fe8464ed767 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -19,6 +19,9 @@ extern struct phy_device *of_phy_connect(struct net_device *dev, struct device_node *phy_np, void (*hndlr)(struct net_device *), u32 flags, phy_interface_t iface); +struct phy_device *of_phy_attach(struct net_device *dev, + struct device_node *phy_np, u32 flags, + phy_interface_t iface); extern struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, void (*hndlr)(struct net_device *), phy_interface_t iface); @@ -44,6 +47,13 @@ static inline struct phy_device *of_phy_connect(struct net_device *dev, return NULL; } +static inline struct phy_device *of_phy_attach(struct net_device *dev, + struct device_node *phy_np, + u32 flags, phy_interface_t iface) +{ + return NULL; +} + static inline struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, void (*hndlr)(struct net_device *), phy_interface_t iface) diff --git a/include/linux/phy.h b/include/linux/phy.h index 7c81dd8870d4..565188ca328f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -73,6 +73,7 @@ typedef enum { PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, + PHY_INTERFACE_MODE_XGMII, } phy_interface_t; @@ -488,6 +489,24 @@ struct phy_fixup { }; /** + * phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for phy_read(); + */ +static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) +{ + if (!phydev->is_c45) + return -EOPNOTSUPP; + + return mdiobus_read(phydev->bus, phydev->addr, + MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff)); +} + +/** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read @@ -537,6 +556,27 @@ static inline bool phy_is_internal(struct phy_device *phydev) return phydev->is_internal; } +/** + * phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for phy_write(); + */ +static inline int phy_write_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + if (!phydev->is_c45) + return -EOPNOTSUPP; + + regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff); + + return mdiobus_write(phydev->bus, phydev->addr, regnum, val); +} + struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); @@ -548,6 +588,8 @@ int phy_resume(struct phy_device *phydev); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); +int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, + u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d97f2d07d02b..48b760505cb6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2893,6 +2893,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); +int skb_checksum_setup(struct sk_buff *skb, bool recalculate); + u32 __skb_get_poff(const struct sk_buff *skb); /** diff --git a/include/net/act_api.h b/include/net/act_api.h index d34e1f4d897b..e171387512b3 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -39,6 +39,7 @@ struct tcf_hashinfo { struct hlist_head *htab; unsigned int hmask; spinlock_t lock; + u32 index; }; static inline unsigned int tcf_hash(u32 index, unsigned int hmask) @@ -51,6 +52,7 @@ static inline int tcf_hashinfo_init(struct tcf_hashinfo *hf, unsigned int mask) int i; spin_lock_init(&hf->lock); + hf->index = 0; hf->hmask = mask; hf->htab = kzalloc((mask + 1) * sizeof(struct hlist_head), GFP_KERNEL); @@ -71,10 +73,6 @@ static inline void tcf_hashinfo_destroy(struct tcf_hashinfo *hf) #define ACT_P_CREATED 1 #define ACT_P_DELETED 1 -struct tcf_act_hdr { - struct tcf_common common; -}; - struct tc_action { void *priv; const struct tc_action_ops *ops; @@ -105,13 +103,12 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo); void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo); int tcf_hash_release(struct tcf_common *p, int bind, struct tcf_hashinfo *hinfo); -u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo); +u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind, struct tcf_hashinfo *hinfo); struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, int size, - int bind, u32 *idx_gen, - struct tcf_hashinfo *hinfo); + int bind, struct tcf_hashinfo *hinfo); void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo); int tcf_register_action(struct tc_action_ops *a); diff --git a/include/net/ip.h b/include/net/ip.h index 535664477c4a..7876e3b96ce3 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -90,7 +90,7 @@ struct packet_type; struct rtable; struct sockaddr; -int igmp_mc_proc_init(void); +int igmp_mc_init(void); /* * Functions provided by ip.c @@ -263,6 +263,39 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) !(dst_metric_locked(dst, RTAX_MTU))); } +static inline bool ip_sk_accept_pmtu(const struct sock *sk) +{ + return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE; +} + +static inline bool ip_sk_use_pmtu(const struct sock *sk) +{ + return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE; +} + +static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, + bool forwarding) +{ + struct net *net = dev_net(dst->dev); + + if (net->ipv4.sysctl_ip_fwd_use_pmtu || + dst_metric_locked(dst, RTAX_MTU) || + !forwarding) + return dst_mtu(dst); + + return min(dst->dev->mtu, IP_MAX_MTU); +} + +static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) +{ + if (!skb->sk || ip_sk_use_pmtu(skb->sk)) { + bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; + return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); + } else { + return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); + } +} + void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 929a668e91a9..80f500a29498 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -70,6 +70,7 @@ struct netns_ipv4 { int sysctl_tcp_ecn; int sysctl_ip_no_pmtu_disc; + int sysctl_ip_fwd_use_pmtu; kgid_t sysctl_ping_group_range[2]; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 50ea07969c09..a2441fb1428f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -338,27 +338,27 @@ static inline int tcf_valid_offset(const struct sk_buff *skb, #include <net/net_namespace.h> static inline int -tcf_change_indev(struct tcf_proto *tp, char *indev, struct nlattr *indev_tlv) +tcf_change_indev(struct net *net, struct nlattr *indev_tlv) { + char indev[IFNAMSIZ]; + struct net_device *dev; + if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ) return -EINVAL; - return 0; + dev = __dev_get_by_name(net, indev); + if (!dev) + return -ENODEV; + return dev->ifindex; } -static inline int -tcf_match_indev(struct sk_buff *skb, char *indev) +static inline bool +tcf_match_indev(struct sk_buff *skb, int ifindex) { - struct net_device *dev; - - if (indev[0]) { - if (!skb->skb_iif) - return 0; - dev = __dev_get_by_index(dev_net(skb->dev), skb->skb_iif); - if (!dev || strcmp(indev, dev->name)) - return 0; - } - - return 1; + if (!ifindex) + return true; + if (!skb->skb_iif) + return false; + return ifindex == skb->skb_iif; } #endif /* CONFIG_NET_CLS_IND */ diff --git a/include/net/protocol.h b/include/net/protocol.h index fbf7676c9a02..0e5f8665d7fb 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -43,7 +43,12 @@ struct net_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); unsigned int no_policy:1, - netns_ok:1; + netns_ok:1, + /* does the protocol do more stringent + * icmp tag validation than simple + * socket lookup? + */ + icmp_strict_tag_validation:1; }; #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/red.h b/include/net/red.h index ef46058d35bf..168bb2f495f2 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -303,7 +303,7 @@ static inline unsigned long red_calc_qavg(const struct red_parms *p, static inline u32 red_random(const struct red_parms *p) { - return reciprocal_divide(net_random(), p->max_P_reciprocal); + return reciprocal_divide(prandom_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, diff --git a/include/net/route.h b/include/net/route.h index 638e3ebf76f3..9d1f423d5944 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -36,6 +36,9 @@ #include <linux/cache.h> #include <linux/security.h> +/* IPv4 datagram length is stored into 16bit field (tot_len) */ +#define IP_MAX_MTU 0xFFFFU + #define RTO_ONLINK 0x01 #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) @@ -311,20 +314,4 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) return hoplimit; } -static inline bool ip_sk_accept_pmtu(const struct sock *sk) -{ - return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE; -} - -static inline bool ip_sk_use_pmtu(const struct sock *sk) -{ - return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE; -} - -static inline int ip_skb_dst_mtu(const struct sk_buff *skb) -{ - return (!skb->sk || ip_sk_use_pmtu(skb->sk)) ? - dst_mtu(skb_dst(skb)) : skb_dst(skb)->dev->mtu; -} - #endif /* _ROUTE_H */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 013d96dc6918..d062f81c692f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -204,7 +204,7 @@ struct tcf_proto_ops { void (*walk)(struct tcf_proto*, struct tcf_walker *arg); /* rtnetlink specific */ - int (*dump)(struct tcf_proto*, unsigned long, + int (*dump)(struct net*, struct tcf_proto*, unsigned long, struct sk_buff *skb, struct tcmsg*); struct module *owner; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e9f732fda950..d992ca3145fe 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -649,7 +649,6 @@ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len, struct iovec *data); void sctp_chunk_free(struct sctp_chunk *); void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data); -void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, const void *data); struct sctp_chunk *sctp_chunkify(struct sk_buff *, const struct sctp_association *, struct sock *); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b7635ef4d436..cd7c46ff6f1f 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1421,6 +1421,8 @@ struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid); +struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, + unsigned short family); int xfrm_state_check_expire(struct xfrm_state *x); void xfrm_state_insert(struct xfrm_state *x); int xfrm_state_add(struct xfrm_state *x); diff --git a/include/trace/events/net.h b/include/trace/events/net.h index f99645d05a8f..a34f27b2e394 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -6,9 +6,67 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> +#include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/tracepoint.h> +TRACE_EVENT(net_dev_start_xmit, + + TP_PROTO(const struct sk_buff *skb, const struct net_device *dev), + + TP_ARGS(skb, dev), + + TP_STRUCT__entry( + __string( name, dev->name ) + __field( u16, queue_mapping ) + __field( const void *, skbaddr ) + __field( bool, vlan_tagged ) + __field( u16, vlan_proto ) + __field( u16, vlan_tci ) + __field( u16, protocol ) + __field( u8, ip_summed ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( int, network_offset ) + __field( bool, transport_offset_valid) + __field( int, transport_offset) + __field( u8, tx_flags ) + __field( u16, gso_size ) + __field( u16, gso_segs ) + __field( u16, gso_type ) + ), + + TP_fast_assign( + __assign_str(name, dev->name); + __entry->queue_mapping = skb->queue_mapping; + __entry->skbaddr = skb; + __entry->vlan_tagged = vlan_tx_tag_present(skb); + __entry->vlan_proto = ntohs(skb->vlan_proto); + __entry->vlan_tci = vlan_tx_tag_get(skb); + __entry->protocol = ntohs(skb->protocol); + __entry->ip_summed = skb->ip_summed; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->network_offset = skb_network_offset(skb); + __entry->transport_offset_valid = + skb_transport_header_was_set(skb); + __entry->transport_offset = skb_transport_offset(skb); + __entry->tx_flags = skb_shinfo(skb)->tx_flags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_segs = skb_shinfo(skb)->gso_segs; + __entry->gso_type = skb_shinfo(skb)->gso_type; + ), + + TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", + __get_str(name), __entry->queue_mapping, __entry->skbaddr, + __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, + __entry->protocol, __entry->ip_summed, __entry->len, + __entry->data_len, + __entry->network_offset, __entry->transport_offset_valid, + __entry->transport_offset, __entry->tx_flags, + __entry->gso_size, __entry->gso_segs, __entry->gso_type) +); + TRACE_EVENT(net_dev_xmit, TP_PROTO(struct sk_buff *skb, @@ -78,6 +136,106 @@ DEFINE_EVENT(net_dev_template, netif_rx, TP_ARGS(skb) ); + +DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb), + + TP_STRUCT__entry( + __string( name, skb->dev->name ) + __field( unsigned int, napi_id ) + __field( u16, queue_mapping ) + __field( const void *, skbaddr ) + __field( bool, vlan_tagged ) + __field( u16, vlan_proto ) + __field( u16, vlan_tci ) + __field( u16, protocol ) + __field( u8, ip_summed ) + __field( u32, rxhash ) + __field( bool, l4_rxhash ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( bool, mac_header_valid) + __field( int, mac_header ) + __field( unsigned char, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + ), + + TP_fast_assign( + __assign_str(name, skb->dev->name); +#ifdef CONFIG_NET_RX_BUSY_POLL + __entry->napi_id = skb->napi_id; +#else + __entry->napi_id = 0; +#endif + __entry->queue_mapping = skb->queue_mapping; + __entry->skbaddr = skb; + __entry->vlan_tagged = vlan_tx_tag_present(skb); + __entry->vlan_proto = ntohs(skb->vlan_proto); + __entry->vlan_tci = vlan_tx_tag_get(skb); + __entry->protocol = ntohs(skb->protocol); + __entry->ip_summed = skb->ip_summed; + __entry->rxhash = skb->rxhash; + __entry->l4_rxhash = skb->l4_rxhash; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->mac_header_valid = skb_mac_header_was_set(skb); + __entry->mac_header = skb_mac_header(skb) - skb->data; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + ), + + TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d rxhash=0x%08x l4_rxhash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", + __get_str(name), __entry->napi_id, __entry->queue_mapping, + __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, + __entry->vlan_tci, __entry->protocol, __entry->ip_summed, + __entry->rxhash, __entry->l4_rxhash, __entry->len, + __entry->data_len, __entry->truesize, + __entry->mac_header_valid, __entry->mac_header, + __entry->nr_frags, __entry->gso_size, __entry->gso_type) +); + +DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + +DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_receive_entry, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + +DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + +DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + +DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + #endif /* _TRACE_NET_H */ /* This part must be outside protection */ diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h index 2f3f7ea8c77b..fe421e8a431b 100644 --- a/include/uapi/drm/radeon_drm.h +++ b/include/uapi/drm/radeon_drm.h @@ -983,6 +983,8 @@ struct drm_radeon_cs { #define RADEON_INFO_SI_CP_DMA_COMPUTE 0x17 /* CIK macrotile mode array */ #define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY 0x18 +/* query the number of render backends */ +#define RADEON_INFO_SI_BACKEND_ENABLED_MASK 0x19 struct drm_radeon_info { diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ecc88592ecbe..bd24470d24a2 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -464,7 +464,8 @@ struct input_keymap_entry { #define KEY_BRIGHTNESS_ZERO 244 /* brightness off, use ambient */ #define KEY_DISPLAY_OFF 245 /* display device to off state */ -#define KEY_WIMAX 246 +#define KEY_WWAN 246 /* Wireless WAN (LTE, UMTS, GSM, etc.) */ +#define KEY_WIMAX KEY_WWAN #define KEY_RFKILL 247 /* Key that controls all radios */ #define KEY_MICMUTE 248 /* Mute / unmute the microphone */ diff --git a/mm/fremap.c b/mm/fremap.c index 5bff08147768..bbc4d660221a 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -208,9 +208,10 @@ get_write_lock: if (mapping_cap_account_dirty(mapping)) { unsigned long addr; struct file *file = get_file(vma->vm_file); + /* mmap_region may free vma; grab the info now */ + vm_flags = vma->vm_flags; - addr = mmap_region(file, start, size, - vma->vm_flags, pgoff); + addr = mmap_region(file, start, size, vm_flags, pgoff); fput(file); if (IS_ERR_VALUE(addr)) { err = addr; @@ -218,7 +219,7 @@ get_write_lock: BUG_ON(addr != start); err = 0; } - goto out; + goto out_freed; } mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); @@ -253,6 +254,7 @@ get_write_lock: out: if (vma) vm_flags = vma->vm_flags; +out_freed: if (likely(!has_write_lock)) up_read(&mm->mmap_sem); else diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7de1bf85f683..9c0b17295ba0 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -883,9 +883,6 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - /* mmap_sem prevents this happening but warn if that changes */ - WARN_ON(pmd_trans_migrating(pmd)); - if (unlikely(pmd_trans_splitting(pmd))) { /* split huge page running from under us */ spin_unlock(src_ptl); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bf5e89457149..7f1a356153c0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -338,7 +338,7 @@ struct mem_cgroup { static size_t memcg_size(void) { return sizeof(struct mem_cgroup) + - nr_node_ids * sizeof(struct mem_cgroup_per_node); + nr_node_ids * sizeof(struct mem_cgroup_per_node *); } /* internal only representation about the status of kmem accounting. */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index db08af92c6fc..fabe55046c1d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -938,6 +938,16 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, BUG_ON(!PageHWPoison(p)); return SWAP_FAIL; } + /* + * We pinned the head page for hwpoison handling, + * now we split the thp and we are interested in + * the hwpoisoned raw page, so move the refcount + * to it. + */ + if (hpage != p) { + put_page(hpage); + get_page(p); + } /* THP is split, so ppage should be the real poisoned page. */ ppage = p; } diff --git a/mm/mlock.c b/mm/mlock.c index d480cd6fc475..192e6eebe4f2 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -133,7 +133,10 @@ static void __munlock_isolation_failed(struct page *page) /** * munlock_vma_page - munlock a vma page - * @page - page to be unlocked + * @page - page to be unlocked, either a normal page or THP page head + * + * returns the size of the page as a page mask (0 for normal page, + * HPAGE_PMD_NR - 1 for THP head page) * * called from munlock()/munmap() path with page supposedly on the LRU. * When we munlock a page, because the vma where we found the page is being @@ -148,21 +151,30 @@ static void __munlock_isolation_failed(struct page *page) */ unsigned int munlock_vma_page(struct page *page) { - unsigned int page_mask = 0; + unsigned int nr_pages; BUG_ON(!PageLocked(page)); if (TestClearPageMlocked(page)) { - unsigned int nr_pages = hpage_nr_pages(page); + nr_pages = hpage_nr_pages(page); mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); - page_mask = nr_pages - 1; if (!isolate_lru_page(page)) __munlock_isolated_page(page); else __munlock_isolation_failed(page); + } else { + nr_pages = hpage_nr_pages(page); } - return page_mask; + /* + * Regardless of the original PageMlocked flag, we determine nr_pages + * after touching the flag. This leaves a possible race with a THP page + * split, such that a whole THP page was munlocked, but nr_pages == 1. + * Returning a smaller mask due to that is OK, the worst that can + * happen is subsequent useless scanning of the former tail pages. + * The NR_MLOCK accounting can however become broken. + */ + return nr_pages - 1; } /** @@ -286,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) { int i; int nr = pagevec_count(pvec); - int delta_munlocked = -nr; + int delta_munlocked; struct pagevec pvec_putback; int pgrescued = 0; + pagevec_init(&pvec_putback, 0); + /* Phase 1: page isolation */ spin_lock_irq(&zone->lru_lock); for (i = 0; i < nr; i++) { @@ -318,18 +332,21 @@ skip_munlock: /* * We won't be munlocking this page in the next phase * but we still need to release the follow_page_mask() - * pin. + * pin. We cannot do it under lru_lock however. If it's + * the last pin, __page_cache_release would deadlock. */ + pagevec_add(&pvec_putback, pvec->pages[i]); pvec->pages[i] = NULL; - put_page(page); - delta_munlocked++; } } + delta_munlocked = -nr + pagevec_count(&pvec_putback); __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); spin_unlock_irq(&zone->lru_lock); + /* Now we can release pins of pages that we are not munlocking */ + pagevec_release(&pvec_putback); + /* Phase 2: page munlock */ - pagevec_init(&pvec_putback, 0); for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; @@ -440,7 +457,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, while (start < end) { struct page *page = NULL; - unsigned int page_mask, page_increm; + unsigned int page_mask; + unsigned long page_increm; struct pagevec pvec; struct zone *zone; int zoneid; @@ -490,7 +508,9 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, goto next; } } - page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); + /* It's a bug to munlock in the middle of a THP page */ + VM_BUG_ON((start >> PAGE_SHIFT) & page_mask); + page_increm = 1 + page_mask; start += page_increm * PAGE_SIZE; next: cond_resched(); diff --git a/net/802/garp.c b/net/802/garp.c index 5d9630a0eb93..b38ee6dcba45 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -397,7 +397,7 @@ static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(garp_join_time) * net_random() >> 32; + delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/802/mrp.c b/net/802/mrp.c index 3ed616215870..72db2785ef2c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -583,7 +583,7 @@ static void mrp_join_timer_arm(struct mrp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(mrp_join_time) * net_random() >> 32; + delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index fa780b76630e..2b2dc473e1f7 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -5,7 +5,6 @@ config BATMAN_ADV tristate "B.A.T.M.A.N. Advanced Meshing Protocol" depends on NET - select CRC16 select LIBCRC32C default n help diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index e5954152cfe0..42df18f877e9 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 92435bfc7471..4e49666f8c65 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 278d78bd7735..921ac20cf690 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -272,7 +272,14 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, if (!neigh_node) goto out; - spin_lock_init(&neigh_node->bat_iv.lq_update_lock); + if (!atomic_inc_not_zero(&hard_iface->refcount)) { + kfree(neigh_node); + neigh_node = NULL; + goto out; + } + + neigh_node->orig_node = orig_neigh; + neigh_node->if_incoming = hard_iface; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", @@ -459,17 +466,9 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* send a batman ogm packet */ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) { - struct batadv_hard_iface *hard_iface; struct net_device *soft_iface; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; - struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char directlink; - uint8_t *packet_pos; - - packet_pos = forw_packet->skb->data; - batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos; - directlink = (batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0); if (!forw_packet->if_incoming) { pr_err("Error - can't forward packet: incoming iface not specified\n"); @@ -479,59 +478,48 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) soft_iface = forw_packet->if_incoming->soft_iface; bat_priv = netdev_priv(soft_iface); - if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) + if (WARN_ON(!forw_packet->if_outgoing)) goto out; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) + if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) goto out; - /* multihomed peer assumed - * non-primary OGMs are only broadcasted on their interface - */ - if ((directlink && (batadv_ogm_packet->ttl == 1)) || - (forw_packet->own && (forw_packet->if_incoming != primary_if))) { - /* FIXME: what about aggregated packets ? */ - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n", - (forw_packet->own ? "Sending own" : "Forwarding"), - batadv_ogm_packet->orig, - ntohl(batadv_ogm_packet->seqno), - batadv_ogm_packet->ttl, - forw_packet->if_incoming->net_dev->name, - forw_packet->if_incoming->net_dev->dev_addr); - - /* skb is only used once and than forw_packet is free'd */ - batadv_send_skb_packet(forw_packet->skb, - forw_packet->if_incoming, - batadv_broadcast_addr); - forw_packet->skb = NULL; - + if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) goto out; - } - /* broadcast on every interface */ - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->soft_iface != soft_iface) - continue; + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; - batadv_iv_ogm_send_to_if(forw_packet, hard_iface); - } - rcu_read_unlock(); + /* only for one specific outgoing interface */ + batadv_iv_ogm_send_to_if(forw_packet, forw_packet->if_outgoing); out: if (primary_if) batadv_hardif_free_ref(primary_if); } -/* return true if new_packet can be aggregated with forw_packet */ +/** + * batadv_iv_ogm_can_aggregate - find out if an OGM can be aggregated on an + * existing forward packet + * @new_bat_ogm_packet: OGM packet to be aggregated + * @bat_priv: the bat priv with all the soft interface information + * @packet_len: (total) length of the OGM + * @send_time: timestamp (jiffies) when the packet is to be sent + * @direktlink: true if this is a direct link packet + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @forw_packet: the forwarded packet which should be checked + * + * Returns true if new_packet can be aggregated with forw_packet + */ static bool batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, struct batadv_priv *bat_priv, int packet_len, unsigned long send_time, bool directlink, const struct batadv_hard_iface *if_incoming, + const struct batadv_hard_iface *if_outgoing, const struct batadv_forw_packet *forw_packet) { struct batadv_ogm_packet *batadv_ogm_packet; @@ -565,6 +553,10 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, if (!primary_if) goto out; + /* packet is not leaving on the same interface. */ + if (forw_packet->if_outgoing != if_outgoing) + goto out; + /* packets without direct link flag and high TTL * are flooded through the net */ @@ -606,11 +598,21 @@ out: return res; } -/* create a new aggregated packet and add this packet to it */ +/* batadv_iv_ogm_aggregate_new - create a new aggregated packet and add this + * packet to it. + * @packet_buff: pointer to the OGM + * @packet_len: (total) length of the OGM + * @send_time: timestamp (jiffies) when the packet is to be sent + * @direct_link: whether this OGM has direct link status + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @own_packet: true if it is a self-generated ogm + */ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, int packet_len, unsigned long send_time, bool direct_link, struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing, int own_packet) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); @@ -621,6 +623,9 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, if (!atomic_inc_not_zero(&if_incoming->refcount)) return; + if (!atomic_inc_not_zero(&if_outgoing->refcount)) + goto out_free_incoming; + /* own packet should always be scheduled */ if (!own_packet) { if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) { @@ -661,6 +666,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, forw_packet_aggr->own = own_packet; forw_packet_aggr->if_incoming = if_incoming; + forw_packet_aggr->if_outgoing = if_outgoing; forw_packet_aggr->num_packets = 0; forw_packet_aggr->direct_link_flags = BATADV_NO_FLAGS; forw_packet_aggr->send_time = send_time; @@ -683,6 +689,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, return; out: + batadv_hardif_free_ref(if_outgoing); +out_free_incoming: batadv_hardif_free_ref(if_incoming); } @@ -706,10 +714,21 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, } } +/** + * batadv_iv_ogm_queue_add - queue up an OGM for transmission + * @bat_priv: the bat priv with all the soft interface information + * @packet_buff: pointer to the OGM + * @packet_len: (total) length of the OGM + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @own_packet: true if it is a self-generated ogm + * @send_time: timestamp (jiffies) when the packet is to be sent + */ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, unsigned char *packet_buff, int packet_len, struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing, int own_packet, unsigned long send_time) { /* _aggr -> pointer to the packet we want to aggregate with @@ -735,6 +754,7 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, bat_priv, packet_len, send_time, direct_link, if_incoming, + if_outgoing, forw_packet_pos)) { forw_packet_aggr = forw_packet_pos; break; @@ -758,7 +778,8 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, batadv_iv_ogm_aggregate_new(packet_buff, packet_len, send_time, direct_link, - if_incoming, own_packet); + if_incoming, if_outgoing, + own_packet); } else { batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff, packet_len, direct_link); @@ -771,7 +792,8 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, struct batadv_ogm_packet *batadv_ogm_packet, bool is_single_hop_neigh, bool is_from_best_next_hop, - struct batadv_hard_iface *if_incoming) + struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); uint16_t tvlv_len; @@ -816,7 +838,8 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, batadv_iv_ogm_queue_add(bat_priv, (unsigned char *)batadv_ogm_packet, BATADV_OGM_HLEN + tvlv_len, - if_incoming, 0, batadv_iv_ogm_fwd_send_time()); + if_incoming, if_outgoing, 0, + batadv_iv_ogm_fwd_send_time()); } /** @@ -861,10 +884,11 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; struct batadv_ogm_packet *batadv_ogm_packet; - struct batadv_hard_iface *primary_if; + struct batadv_hard_iface *primary_if, *tmp_hard_iface; int *ogm_buff_len = &hard_iface->bat_iv.ogm_buff_len; uint32_t seqno; uint16_t tvlv_len = 0; + unsigned long send_time; primary_if = batadv_primary_if_get_selected(bat_priv); @@ -887,23 +911,60 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) atomic_inc(&hard_iface->bat_iv.ogm_seqno); batadv_iv_ogm_slide_own_bcast_window(hard_iface); - batadv_iv_ogm_queue_add(bat_priv, hard_iface->bat_iv.ogm_buff, - hard_iface->bat_iv.ogm_buff_len, hard_iface, 1, - batadv_iv_ogm_emit_send_time(bat_priv)); + send_time = batadv_iv_ogm_emit_send_time(bat_priv); + + if (hard_iface != primary_if) { + /* OGMs from secondary interfaces are only scheduled on their + * respective interfaces. + */ + batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, + hard_iface, hard_iface, 1, send_time); + goto out; + } + + /* OGMs from primary interfaces are scheduled on all + * interfaces. + */ + rcu_read_lock(); + list_for_each_entry_rcu(tmp_hard_iface, &batadv_hardif_list, list) { + if (tmp_hard_iface->soft_iface != hard_iface->soft_iface) + continue; + batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, + *ogm_buff_len, hard_iface, + tmp_hard_iface, 1, send_time); + } + rcu_read_unlock(); + +out: if (primary_if) batadv_hardif_free_ref(primary_if); } +/** + * batadv_iv_ogm_orig_update - use OGM to update corresponding data in an + * originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: the orig node who originally emitted the ogm packet + * @orig_ifinfo: ifinfo for the outgoing interface of the orig_node + * @ethhdr: Ethernet header of the OGM + * @batadv_ogm_packet: the ogm packet + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @dup_status: the duplicate status of this ogm packet. + */ static void batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_orig_ifinfo *orig_ifinfo, const struct ethhdr *ethhdr, const struct batadv_ogm_packet *batadv_ogm_packet, struct batadv_hard_iface *if_incoming, - const unsigned char *tt_buff, + struct batadv_hard_iface *if_outgoing, enum batadv_dup_status dup_status) { + struct batadv_neigh_ifinfo *neigh_ifinfo = NULL; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; @@ -931,12 +992,21 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, if (dup_status != BATADV_NO_DUP) continue; - spin_lock_bh(&tmp_neigh_node->bat_iv.lq_update_lock); - batadv_ring_buffer_set(tmp_neigh_node->bat_iv.tq_recv, - &tmp_neigh_node->bat_iv.tq_index, 0); - tq_avg = batadv_ring_buffer_avg(tmp_neigh_node->bat_iv.tq_recv); - tmp_neigh_node->bat_iv.tq_avg = tq_avg; - spin_unlock_bh(&tmp_neigh_node->bat_iv.lq_update_lock); + /* only update the entry for this outgoing interface */ + neigh_ifinfo = batadv_neigh_ifinfo_get(tmp_neigh_node, + if_outgoing); + if (!neigh_ifinfo) + continue; + + spin_lock_bh(&tmp_neigh_node->ifinfo_lock); + batadv_ring_buffer_set(neigh_ifinfo->bat_iv.tq_recv, + &neigh_ifinfo->bat_iv.tq_index, 0); + tq_avg = batadv_ring_buffer_avg(neigh_ifinfo->bat_iv.tq_recv); + neigh_ifinfo->bat_iv.tq_avg = tq_avg; + spin_unlock_bh(&tmp_neigh_node->ifinfo_lock); + + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + neigh_ifinfo = NULL; } if (!neigh_node) { @@ -958,39 +1028,49 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, "Updating existing last-hop neighbor of originator\n"); rcu_read_unlock(); + neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); + if (!neigh_ifinfo) + goto out; neigh_node->last_seen = jiffies; - spin_lock_bh(&neigh_node->bat_iv.lq_update_lock); - batadv_ring_buffer_set(neigh_node->bat_iv.tq_recv, - &neigh_node->bat_iv.tq_index, + spin_lock_bh(&neigh_node->ifinfo_lock); + batadv_ring_buffer_set(neigh_ifinfo->bat_iv.tq_recv, + &neigh_ifinfo->bat_iv.tq_index, batadv_ogm_packet->tq); - tq_avg = batadv_ring_buffer_avg(neigh_node->bat_iv.tq_recv); - neigh_node->bat_iv.tq_avg = tq_avg; - spin_unlock_bh(&neigh_node->bat_iv.lq_update_lock); + tq_avg = batadv_ring_buffer_avg(neigh_ifinfo->bat_iv.tq_recv); + neigh_ifinfo->bat_iv.tq_avg = tq_avg; + spin_unlock_bh(&neigh_node->ifinfo_lock); if (dup_status == BATADV_NO_DUP) { - orig_node->last_ttl = batadv_ogm_packet->ttl; - neigh_node->last_ttl = batadv_ogm_packet->ttl; + orig_ifinfo->last_ttl = batadv_ogm_packet->ttl; + neigh_ifinfo->last_ttl = batadv_ogm_packet->ttl; } - batadv_bonding_candidate_add(bat_priv, orig_node, neigh_node); - /* if this neighbor already is our next hop there is nothing * to change */ - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, if_outgoing); if (router == neigh_node) goto out; - /* if this neighbor does not offer a better TQ we won't consider it */ - if (router && (router->bat_iv.tq_avg > neigh_node->bat_iv.tq_avg)) - goto out; + if (router) { + router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); + if (!router_ifinfo) + goto out; + + /* if this neighbor does not offer a better TQ we won't + * consider it + */ + if (router_ifinfo->bat_iv.tq_avg > neigh_ifinfo->bat_iv.tq_avg) + goto out; + } /* if the TQ is the same and the link not more symmetric we * won't consider it either */ - if (router && (neigh_node->bat_iv.tq_avg == router->bat_iv.tq_avg)) { + if (router_ifinfo && + (neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg)) { orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if_num = router->if_incoming->if_num; @@ -1007,7 +1087,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, goto out; } - batadv_update_route(bat_priv, orig_node, neigh_node); + batadv_update_route(bat_priv, orig_node, if_outgoing, neigh_node); goto out; unlock: @@ -1017,20 +1097,37 @@ out: batadv_neigh_node_free_ref(neigh_node); if (router) batadv_neigh_node_free_ref(router); + if (neigh_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); } +/** + * batadv_iv_ogm_calc_tq - calculate tq for current received ogm packet + * @orig_node: the orig node who originally emitted the ogm packet + * @orig_neigh_node: the orig node struct of the neighbor who sent the packet + * @batadv_ogm_packet: the ogm packet + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * + * Returns 1 if the link can be considered bidirectional, 0 otherwise + */ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, struct batadv_ogm_packet *batadv_ogm_packet, - struct batadv_hard_iface *if_incoming) + struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node; + struct batadv_neigh_ifinfo *neigh_ifinfo; uint8_t total_count; uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; int tq_asym_penalty, inv_asym_penalty, if_num, ret = 0; unsigned int combined_tq; + int tq_iface_penalty; /* find corresponding one hop neighbor */ rcu_read_lock(); @@ -1070,7 +1167,13 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); if_num = if_incoming->if_num; orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; - neigh_rq_count = neigh_node->bat_iv.real_packet_count; + neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); + if (neigh_ifinfo) { + neigh_rq_count = neigh_ifinfo->bat_iv.real_packet_count; + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + } else { + neigh_rq_count = 0; + } spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ @@ -1106,15 +1209,31 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, inv_asym_penalty /= neigh_rq_max_cube; tq_asym_penalty = BATADV_TQ_MAX_VALUE - inv_asym_penalty; - combined_tq = batadv_ogm_packet->tq * tq_own * tq_asym_penalty; - combined_tq /= BATADV_TQ_MAX_VALUE * BATADV_TQ_MAX_VALUE; + /* penalize if the OGM is forwarded on the same interface. WiFi + * interfaces and other half duplex devices suffer from throughput + * drops as they can't send and receive at the same time. + */ + tq_iface_penalty = BATADV_TQ_MAX_VALUE; + if (if_outgoing && (if_incoming == if_outgoing) && + batadv_is_wifi_netdev(if_outgoing->net_dev)) + tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE, + bat_priv); + + combined_tq = batadv_ogm_packet->tq * + tq_own * + tq_asym_penalty * + tq_iface_penalty; + combined_tq /= BATADV_TQ_MAX_VALUE * + BATADV_TQ_MAX_VALUE * + BATADV_TQ_MAX_VALUE; batadv_ogm_packet->tq = combined_tq; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, total tq: %3i\n", + "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, iface_penalty: %3i, total tq: %3i, if_incoming = %s, if_outgoing = %s\n", orig_node->orig, orig_neigh_node->orig, total_count, - neigh_rq_count, tq_own, - tq_asym_penalty, batadv_ogm_packet->tq); + neigh_rq_count, tq_own, tq_asym_penalty, tq_iface_penalty, + batadv_ogm_packet->tq, if_incoming->net_dev->name, + if_outgoing ? if_outgoing->net_dev->name : "DEFAULT"); /* if link has the minimum required transmission quality * consider it bidirectional @@ -1134,17 +1253,21 @@ out: * @ethhdr: ethernet header of the packet * @batadv_ogm_packet: OGM packet to be considered * @if_incoming: interface on which the OGM packet was received + * @if_outgoing: interface for which the retransmission should be considered * * Returns duplicate status as enum batadv_dup_status */ static enum batadv_dup_status batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, const struct batadv_ogm_packet *batadv_ogm_packet, - const struct batadv_hard_iface *if_incoming) + const struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_orig_node *orig_node; - struct batadv_neigh_node *tmp_neigh_node; + struct batadv_orig_ifinfo *orig_ifinfo = NULL; + struct batadv_neigh_node *neigh_node; + struct batadv_neigh_ifinfo *neigh_ifinfo; int is_dup; int32_t seq_diff; int need_update = 0; @@ -1159,27 +1282,37 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, if (!orig_node) return BATADV_NO_DUP; + orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing); + if (WARN_ON(!orig_ifinfo)) { + batadv_orig_node_free_ref(orig_node); + return 0; + } + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); - seq_diff = seqno - orig_node->last_real_seqno; + seq_diff = seqno - orig_ifinfo->last_real_seqno; /* signalize caller that the packet is to be dropped. */ if (!hlist_empty(&orig_node->neigh_list) && batadv_window_protected(bat_priv, seq_diff, - &orig_node->batman_seqno_reset)) { + &orig_ifinfo->batman_seqno_reset)) { ret = BATADV_PROTECTED; goto out; } rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, - &orig_node->neigh_list, list) { - neigh_addr = tmp_neigh_node->addr; - is_dup = batadv_test_bit(tmp_neigh_node->bat_iv.real_bits, - orig_node->last_real_seqno, + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, + if_outgoing); + if (!neigh_ifinfo) + continue; + + neigh_addr = neigh_node->addr; + is_dup = batadv_test_bit(neigh_ifinfo->bat_iv.real_bits, + orig_ifinfo->last_real_seqno, seqno); if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && - tmp_neigh_node->if_incoming == if_incoming) { + neigh_node->if_incoming == if_incoming) { set_mark = 1; if (is_dup) ret = BATADV_NEIGH_DUP; @@ -1190,173 +1323,78 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, } /* if the window moved, set the update flag. */ - bitmap = tmp_neigh_node->bat_iv.real_bits; + bitmap = neigh_ifinfo->bat_iv.real_bits; need_update |= batadv_bit_get_packet(bat_priv, bitmap, seq_diff, set_mark); - packet_count = bitmap_weight(tmp_neigh_node->bat_iv.real_bits, + packet_count = bitmap_weight(bitmap, BATADV_TQ_LOCAL_WINDOW_SIZE); - tmp_neigh_node->bat_iv.real_packet_count = packet_count; + neigh_ifinfo->bat_iv.real_packet_count = packet_count; + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); } rcu_read_unlock(); if (need_update) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "updating last_seqno: old %u, new %u\n", - orig_node->last_real_seqno, seqno); - orig_node->last_real_seqno = seqno; + "%s updating last_seqno: old %u, new %u\n", + if_outgoing ? if_outgoing->net_dev->name : "DEFAULT", + orig_ifinfo->last_real_seqno, seqno); + orig_ifinfo->last_real_seqno = seqno; } out: spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); batadv_orig_node_free_ref(orig_node); + if (orig_ifinfo) + batadv_orig_ifinfo_free_ref(orig_ifinfo); return ret; } -static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, - struct batadv_ogm_packet *batadv_ogm_packet, - const unsigned char *tt_buff, - struct batadv_hard_iface *if_incoming) + +/** + * batadv_iv_ogm_process_per_outif - process a batman iv OGM for an outgoing if + * @skb: the skb containing the OGM + * @orig_node: the (cached) orig node for the originator of this OGM + * @if_incoming: the interface where this packet was received + * @if_outgoing: the interface for which the packet should be considered + */ +static void +batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct batadv_hard_iface *hard_iface; - struct batadv_orig_node *orig_neigh_node, *orig_node, *orig_node_tmp; struct batadv_neigh_node *router = NULL, *router_router = NULL; + struct batadv_orig_node *orig_neigh_node; + struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *orig_neigh_router = NULL; - int has_directlink_flag; - int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - int is_bidirect; - bool is_single_hop_neigh = false; - bool is_from_best_next_hop = false; - int sameseq, similar_ttl; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + struct batadv_ogm_packet *ogm_packet; enum batadv_dup_status dup_status; - uint32_t if_incoming_seqno; + bool is_from_best_next_hop = false; + bool is_single_hop_neigh = false; + bool sameseq, similar_ttl; + struct sk_buff *skb_priv; + struct ethhdr *ethhdr; uint8_t *prev_sender; + int is_bidirect; - /* Silently drop when the batman packet is actually not a - * correct packet. - * - * This might happen if a packet is padded (e.g. Ethernet has a - * minimum frame length of 64 byte) and the aggregation interprets - * it as an additional length. - * - * TODO: A more sane solution would be to have a bit in the - * batadv_ogm_packet to detect whether the packet is the last - * packet in an aggregation. Here we expect that the padding - * is always zero (or not 0x01) + /* create a private copy of the skb, as some functions change tq value + * and/or flags. */ - if (batadv_ogm_packet->packet_type != BATADV_IV_OGM) + skb_priv = skb_copy(skb, GFP_ATOMIC); + if (!skb_priv) return; - /* could be changed by schedule_own_packet() */ - if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno); - - if (batadv_ogm_packet->flags & BATADV_DIRECTLINK) - has_directlink_flag = 1; - else - has_directlink_flag = 0; + ethhdr = eth_hdr(skb_priv); + ogm_packet = (struct batadv_ogm_packet *)(skb_priv->data + ogm_offset); - if (batadv_compare_eth(ethhdr->h_source, batadv_ogm_packet->orig)) + dup_status = batadv_iv_ogm_update_seqnos(ethhdr, ogm_packet, + if_incoming, if_outgoing); + if (batadv_compare_eth(ethhdr->h_source, ogm_packet->orig)) is_single_hop_neigh = true; - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, tq %d, TTL %d, V %d, IDF %d)\n", - ethhdr->h_source, if_incoming->net_dev->name, - if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig, - batadv_ogm_packet->prev_sender, - ntohl(batadv_ogm_packet->seqno), batadv_ogm_packet->tq, - batadv_ogm_packet->ttl, - batadv_ogm_packet->version, has_directlink_flag); - - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->if_status != BATADV_IF_ACTIVE) - continue; - - if (hard_iface->soft_iface != if_incoming->soft_iface) - continue; - - if (batadv_compare_eth(ethhdr->h_source, - hard_iface->net_dev->dev_addr)) - is_my_addr = 1; - - if (batadv_compare_eth(batadv_ogm_packet->orig, - hard_iface->net_dev->dev_addr)) - is_my_orig = 1; - - if (batadv_compare_eth(batadv_ogm_packet->prev_sender, - hard_iface->net_dev->dev_addr)) - is_my_oldorig = 1; - } - rcu_read_unlock(); - - if (is_my_addr) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: received my own broadcast (sender: %pM)\n", - ethhdr->h_source); - return; - } - - if (is_my_orig) { - unsigned long *word; - int offset; - int32_t bit_pos; - int16_t if_num; - uint8_t *weight; - - orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, - ethhdr->h_source); - if (!orig_neigh_node) - return; - - /* neighbor has to indicate direct link and it has to - * come via the corresponding interface - * save packet seqno for bidirectional check - */ - if (has_directlink_flag && - batadv_compare_eth(if_incoming->net_dev->dev_addr, - batadv_ogm_packet->orig)) { - if_num = if_incoming->if_num; - offset = if_num * BATADV_NUM_WORDS; - - spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - word = &(orig_neigh_node->bat_iv.bcast_own[offset]); - bit_pos = if_incoming_seqno - 2; - bit_pos -= ntohl(batadv_ogm_packet->seqno); - batadv_set_bit(word, bit_pos); - weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num]; - *weight = bitmap_weight(word, - BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - } - - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: originator packet from myself (via neighbor)\n"); - batadv_orig_node_free_ref(orig_neigh_node); - return; - } - - if (is_my_oldorig) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n", - ethhdr->h_source); - return; - } - - if (batadv_ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", - ethhdr->h_source); - return; - } - - orig_node = batadv_iv_ogm_orig_get(bat_priv, batadv_ogm_packet->orig); - if (!orig_node) - return; - - dup_status = batadv_iv_ogm_update_seqnos(ethhdr, batadv_ogm_packet, - if_incoming); - if (dup_status == BATADV_PROTECTED) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: packet within seqno protection time (sender: %pM)\n", @@ -1364,27 +1402,28 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, goto out; } - if (batadv_ogm_packet->tq == 0) { + if (ogm_packet->tq == 0) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: originator packet with tq equal 0\n"); goto out; } - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, if_outgoing); if (router) { - orig_node_tmp = router->orig_node; - router_router = batadv_orig_node_get_router(orig_node_tmp); + router_router = batadv_orig_router_get(router->orig_node, + if_outgoing); + router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); } - if ((router && router->bat_iv.tq_avg != 0) && + if ((router_ifinfo && router_ifinfo->bat_iv.tq_avg != 0) && (batadv_compare_eth(router->addr, ethhdr->h_source))) is_from_best_next_hop = true; - prev_sender = batadv_ogm_packet->prev_sender; + prev_sender = ogm_packet->prev_sender; /* avoid temporary routing loops */ if (router && router_router && (batadv_compare_eth(router->addr, prev_sender)) && - !(batadv_compare_eth(batadv_ogm_packet->orig, prev_sender)) && + !(batadv_compare_eth(ogm_packet->orig, prev_sender)) && (batadv_compare_eth(router->addr, router_router->addr))) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: ignoring all rebroadcast packets that may make me loop (sender: %pM)\n", @@ -1392,7 +1431,8 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, goto out; } - batadv_tvlv_ogm_receive(bat_priv, batadv_ogm_packet, orig_node); + if (if_outgoing == BATADV_IF_DEFAULT) + batadv_tvlv_ogm_receive(bat_priv, ogm_packet, orig_node); /* if sender is a direct neighbor the sender mac equals * originator mac @@ -1408,9 +1448,10 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, /* Update nc_nodes of the originator */ batadv_nc_update_nc_node(bat_priv, orig_node, orig_neigh_node, - batadv_ogm_packet, is_single_hop_neigh); + ogm_packet, is_single_hop_neigh); - orig_neigh_router = batadv_orig_node_get_router(orig_neigh_node); + orig_neigh_router = batadv_orig_router_get(orig_neigh_node, + if_outgoing); /* drop packet if sender is not a direct neighbor and if we * don't route towards it @@ -1422,28 +1463,48 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, } is_bidirect = batadv_iv_ogm_calc_tq(orig_node, orig_neigh_node, - batadv_ogm_packet, if_incoming); - - batadv_bonding_save_primary(orig_node, orig_neigh_node, - batadv_ogm_packet); + ogm_packet, if_incoming, + if_outgoing); /* update ranking if it is not a duplicate or has the same * seqno and similar ttl as the non-duplicate */ - sameseq = orig_node->last_real_seqno == ntohl(batadv_ogm_packet->seqno); - similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->ttl; + orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing); + if (!orig_ifinfo) + goto out_neigh; + + sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno); + similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl; + if (is_bidirect && ((dup_status == BATADV_NO_DUP) || - (sameseq && similar_ttl))) - batadv_iv_ogm_orig_update(bat_priv, orig_node, ethhdr, - batadv_ogm_packet, if_incoming, - tt_buff, dup_status); + (sameseq && similar_ttl))) { + batadv_iv_ogm_orig_update(bat_priv, orig_node, + orig_ifinfo, ethhdr, + ogm_packet, if_incoming, + if_outgoing, dup_status); + } + batadv_orig_ifinfo_free_ref(orig_ifinfo); + + /* only forward for specific interface, not for the default one. */ + if (if_outgoing == BATADV_IF_DEFAULT) + goto out_neigh; /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { + /* OGMs from secondary interfaces should only scheduled once + * per interface where it has been received, not multiple times + */ + if ((ogm_packet->ttl <= 2) && + (if_incoming != if_outgoing)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: OGM from secondary interface and wrong outgoing interface\n"); + goto out_neigh; + } /* mark direct link on incoming interface */ - batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, + batadv_iv_ogm_forward(orig_node, ethhdr, ogm_packet, is_single_hop_neigh, - is_from_best_next_hop, if_incoming); + is_from_best_next_hop, if_incoming, + if_outgoing); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast neighbor packet with direct link flag\n"); @@ -1465,9 +1526,9 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast originator packet\n"); - batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, + batadv_iv_ogm_forward(orig_node, ethhdr, ogm_packet, is_single_hop_neigh, is_from_best_next_hop, - if_incoming); + if_incoming, if_outgoing); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) @@ -1480,6 +1541,165 @@ out: if (orig_neigh_router) batadv_neigh_node_free_ref(orig_neigh_router); + kfree_skb(skb_priv); +} + +/** + * batadv_iv_ogm_process - process an incoming batman iv OGM + * @skb: the skb containing the OGM + * @ogm_offset: offset to the OGM which should be processed (for aggregates) + * @if_incoming: the interface where this packet was receved + */ +static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, + struct batadv_hard_iface *if_incoming) +{ + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_orig_node *orig_neigh_node, *orig_node; + struct batadv_hard_iface *hard_iface; + struct batadv_ogm_packet *ogm_packet; + uint32_t if_incoming_seqno; + bool has_directlink_flag; + struct ethhdr *ethhdr; + bool is_my_oldorig = false; + bool is_my_addr = false; + bool is_my_orig = false; + + ogm_packet = (struct batadv_ogm_packet *)(skb->data + ogm_offset); + ethhdr = eth_hdr(skb); + + /* Silently drop when the batman packet is actually not a + * correct packet. + * + * This might happen if a packet is padded (e.g. Ethernet has a + * minimum frame length of 64 byte) and the aggregation interprets + * it as an additional length. + * + * TODO: A more sane solution would be to have a bit in the + * batadv_ogm_packet to detect whether the packet is the last + * packet in an aggregation. Here we expect that the padding + * is always zero (or not 0x01) + */ + if (ogm_packet->packet_type != BATADV_IV_OGM) + return; + + /* could be changed by schedule_own_packet() */ + if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno); + + if (ogm_packet->flags & BATADV_DIRECTLINK) + has_directlink_flag = true; + else + has_directlink_flag = false; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, tq %d, TTL %d, V %d, IDF %d)\n", + ethhdr->h_source, if_incoming->net_dev->name, + if_incoming->net_dev->dev_addr, ogm_packet->orig, + ogm_packet->prev_sender, ntohl(ogm_packet->seqno), + ogm_packet->tq, ogm_packet->ttl, + ogm_packet->version, has_directlink_flag); + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != if_incoming->soft_iface) + continue; + + if (batadv_compare_eth(ethhdr->h_source, + hard_iface->net_dev->dev_addr)) + is_my_addr = true; + + if (batadv_compare_eth(ogm_packet->orig, + hard_iface->net_dev->dev_addr)) + is_my_orig = true; + + if (batadv_compare_eth(ogm_packet->prev_sender, + hard_iface->net_dev->dev_addr)) + is_my_oldorig = true; + } + rcu_read_unlock(); + + if (is_my_addr) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: received my own broadcast (sender: %pM)\n", + ethhdr->h_source); + return; + } + + if (is_my_orig) { + unsigned long *word; + int offset; + int32_t bit_pos; + int16_t if_num; + uint8_t *weight; + + orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, + ethhdr->h_source); + if (!orig_neigh_node) + return; + + /* neighbor has to indicate direct link and it has to + * come via the corresponding interface + * save packet seqno for bidirectional check + */ + if (has_directlink_flag && + batadv_compare_eth(if_incoming->net_dev->dev_addr, + ogm_packet->orig)) { + if_num = if_incoming->if_num; + offset = if_num * BATADV_NUM_WORDS; + + spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); + word = &(orig_neigh_node->bat_iv.bcast_own[offset]); + bit_pos = if_incoming_seqno - 2; + bit_pos -= ntohl(ogm_packet->seqno); + batadv_set_bit(word, bit_pos); + weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num]; + *weight = bitmap_weight(word, + BATADV_TQ_LOCAL_WINDOW_SIZE); + spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); + } + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet from myself (via neighbor)\n"); + batadv_orig_node_free_ref(orig_neigh_node); + return; + } + + if (is_my_oldorig) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n", + ethhdr->h_source); + return; + } + + if (ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", + ethhdr->h_source); + return; + } + + orig_node = batadv_iv_ogm_orig_get(bat_priv, ogm_packet->orig); + if (!orig_node) + return; + + batadv_iv_ogm_process_per_outif(skb, ogm_offset, orig_node, + if_incoming, BATADV_IF_DEFAULT); + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + batadv_iv_ogm_process_per_outif(skb, ogm_offset, orig_node, + if_incoming, hard_iface); + } + rcu_read_unlock(); + batadv_orig_node_free_ref(orig_node); } @@ -1487,11 +1707,9 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, struct batadv_hard_iface *if_incoming) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct batadv_ogm_packet *batadv_ogm_packet; - struct ethhdr *ethhdr; - int buff_pos = 0, packet_len; - unsigned char *tvlv_buff, *packet_buff; + struct batadv_ogm_packet *ogm_packet; uint8_t *packet_pos; + int ogm_offset; bool ret; ret = batadv_check_management_packet(skb, if_incoming, BATADV_OGM_HLEN); @@ -1508,42 +1726,68 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, skb->len + ETH_HLEN); - packet_len = skb_headlen(skb); - ethhdr = eth_hdr(skb); - packet_buff = skb->data; - batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; + ogm_offset = 0; + ogm_packet = (struct batadv_ogm_packet *)skb->data; /* unpack the aggregated packets and process them one by one */ - while (batadv_iv_ogm_aggr_packet(buff_pos, packet_len, - batadv_ogm_packet->tvlv_len)) { - tvlv_buff = packet_buff + buff_pos + BATADV_OGM_HLEN; + while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb), + ogm_packet->tvlv_len)) { + batadv_iv_ogm_process(skb, ogm_offset, if_incoming); - batadv_iv_ogm_process(ethhdr, batadv_ogm_packet, - tvlv_buff, if_incoming); + ogm_offset += BATADV_OGM_HLEN; + ogm_offset += ntohs(ogm_packet->tvlv_len); - buff_pos += BATADV_OGM_HLEN; - buff_pos += ntohs(batadv_ogm_packet->tvlv_len); - - packet_pos = packet_buff + buff_pos; - batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos; + packet_pos = skb->data + ogm_offset; + ogm_packet = (struct batadv_ogm_packet *)packet_pos; } kfree_skb(skb); return NET_RX_SUCCESS; } +/* batadv_iv_ogm_orig_print_neigh - print neighbors for the originator table + * @orig_node: the orig_node for which the neighbors are printed + * @if_outgoing: outgoing interface for these entries + * @seq: debugfs table seq_file struct + * + * Must be called while holding an rcu lock. + */ +static void +batadv_iv_ogm_orig_print_neigh(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing, + struct seq_file *seq) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_neigh_ifinfo *n_ifinfo; + + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); + if (!n_ifinfo) + continue; + + seq_printf(seq, " %pM (%3i)", + neigh_node->addr, + n_ifinfo->bat_iv.tq_avg); + + batadv_neigh_ifinfo_free_ref(n_ifinfo); + } +} + /** * batadv_iv_ogm_orig_print - print the originator table * @bat_priv: the bat priv with all the soft interface information * @seq: debugfs table seq_file struct + * @if_outgoing: the outgoing interface for which this should be printed */ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, - struct seq_file *seq) + struct seq_file *seq, + struct batadv_hard_iface *if_outgoing) { - struct batadv_neigh_node *neigh_node, *neigh_node_tmp; + struct batadv_neigh_node *neigh_node; struct batadv_hashtable *hash = bat_priv->orig_hash; int last_seen_msecs, last_seen_secs; struct batadv_orig_node *orig_node; + struct batadv_neigh_ifinfo *n_ifinfo; unsigned long last_seen_jiffies; struct hlist_head *head; int batman_count = 0; @@ -1558,11 +1802,17 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - neigh_node = batadv_orig_node_get_router(orig_node); + neigh_node = batadv_orig_router_get(orig_node, + if_outgoing); if (!neigh_node) continue; - if (neigh_node->bat_iv.tq_avg == 0) + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, + if_outgoing); + if (!n_ifinfo) + goto next; + + if (n_ifinfo->bat_iv.tq_avg == 0) goto next; last_seen_jiffies = jiffies - orig_node->last_seen; @@ -1572,22 +1822,19 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", orig_node->orig, last_seen_secs, - last_seen_msecs, neigh_node->bat_iv.tq_avg, + last_seen_msecs, n_ifinfo->bat_iv.tq_avg, neigh_node->addr, neigh_node->if_incoming->net_dev->name); - hlist_for_each_entry_rcu(neigh_node_tmp, - &orig_node->neigh_list, list) { - seq_printf(seq, " %pM (%3i)", - neigh_node_tmp->addr, - neigh_node_tmp->bat_iv.tq_avg); - } - + batadv_iv_ogm_orig_print_neigh(orig_node, if_outgoing, + seq); seq_puts(seq, "\n"); batman_count++; next: batadv_neigh_node_free_ref(neigh_node); + if (n_ifinfo) + batadv_neigh_ifinfo_free_ref(n_ifinfo); } rcu_read_unlock(); } @@ -1599,37 +1846,84 @@ next: /** * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors * @neigh1: the first neighbor object of the comparison + * @if_outgoing1: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison + * @if_outgoing2: outgoing interface for the second neighbor * * Returns a value less, equal to or greater than 0 if the metric via neigh1 is * lower, the same as or higher than the metric via neigh2 */ static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2) + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2) { + struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; uint8_t tq1, tq2; + int diff; + + neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); + neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); + + if (!neigh1_ifinfo || !neigh2_ifinfo) { + diff = 0; + goto out; + } + + tq1 = neigh1_ifinfo->bat_iv.tq_avg; + tq2 = neigh2_ifinfo->bat_iv.tq_avg; + diff = tq1 - tq2; - tq1 = neigh1->bat_iv.tq_avg; - tq2 = neigh2->bat_iv.tq_avg; +out: + if (neigh1_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh1_ifinfo); + if (neigh2_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh2_ifinfo); - return tq1 - tq2; + return diff; } /** * batadv_iv_ogm_neigh_is_eob - check if neigh1 is equally good or better than * neigh2 from the metric prospective * @neigh1: the first neighbor object of the comparison + * @if_outgoing: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison - * - * Returns true if the metric via neigh1 is equally good or better than the - * metric via neigh2, false otherwise. + * @if_outgoing2: outgoing interface for the second neighbor + + * Returns true if the metric via neigh1 is equally good or better than + * the metric via neigh2, false otherwise. */ -static bool batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2) +static bool +batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2) { - int diff = batadv_iv_ogm_neigh_cmp(neigh1, neigh2); + struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; + uint8_t tq1, tq2; + bool ret; - return diff > -BATADV_TQ_SIMILARITY_THRESHOLD; + neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); + neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); + + /* we can't say that the metric is better */ + if (!neigh1_ifinfo || !neigh2_ifinfo) { + ret = false; + goto out; + } + + tq1 = neigh1_ifinfo->bat_iv.tq_avg; + tq2 = neigh2_ifinfo->bat_iv.tq_avg; + ret = (tq1 - tq2) > -BATADV_TQ_SIMILARITY_THRESHOLD; + +out: + if (neigh1_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh1_ifinfo); + if (neigh2_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh2_ifinfo); + + return ret; } static struct batadv_algo_ops batadv_batman_iv __read_mostly = { diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 89d3a5bcacc1..9586750022f5 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 685e0af1fef2..cc2407351d36 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index b164a073a215..5c0eda48d7a2 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 377dae069177..43c985d92c3e 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 0adbcee80d24..b758881be108 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -248,6 +248,19 @@ static int batadv_originators_open(struct inode *inode, struct file *file) return single_open(file, batadv_orig_seq_print_text, net_dev); } +/** + * batadv_originators_hardif_open - handles debugfs output for the + * originator table of an hard interface + * @inode: inode pointer to debugfs file + * @file: pointer to the seq_file + */ +static int batadv_originators_hardif_open(struct inode *inode, + struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_orig_hardif_seq_print_text, net_dev); +} + static int batadv_gateways_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; @@ -369,6 +382,28 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = { NULL, }; +#define BATADV_HARDIF_DEBUGINFO(_name, _mode, _open) \ +struct batadv_debuginfo batadv_hardif_debuginfo_##_name = { \ + .attr = { \ + .name = __stringify(_name), \ + .mode = _mode, \ + }, \ + .fops = { \ + .owner = THIS_MODULE, \ + .open = _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ + }, \ +}; +static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO, + batadv_originators_hardif_open); + +static struct batadv_debuginfo *batadv_hardif_debuginfos[] = { + &batadv_hardif_debuginfo_originators, + NULL, +}; + void batadv_debugfs_init(void) { struct batadv_debuginfo **bat_debug; @@ -396,6 +431,7 @@ void batadv_debugfs_init(void) return; err: debugfs_remove_recursive(batadv_debugfs); + batadv_debugfs = NULL; } void batadv_debugfs_destroy(void) @@ -404,6 +440,59 @@ void batadv_debugfs_destroy(void) batadv_debugfs = NULL; } +/** + * batadv_debugfs_add_hardif - creates the base directory for a hard interface + * in debugfs. + * @hard_iface: hard interface which should be added. + */ +int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) +{ + struct batadv_debuginfo **bat_debug; + struct dentry *file; + + if (!batadv_debugfs) + goto out; + + hard_iface->debug_dir = debugfs_create_dir(hard_iface->net_dev->name, + batadv_debugfs); + if (!hard_iface->debug_dir) + goto out; + + for (bat_debug = batadv_hardif_debuginfos; *bat_debug; ++bat_debug) { + file = debugfs_create_file(((*bat_debug)->attr).name, + S_IFREG | ((*bat_debug)->attr).mode, + hard_iface->debug_dir, + hard_iface->net_dev, + &(*bat_debug)->fops); + if (!file) + goto rem_attr; + } + + return 0; +rem_attr: + debugfs_remove_recursive(hard_iface->debug_dir); + hard_iface->debug_dir = NULL; +out: +#ifdef CONFIG_DEBUG_FS + return -ENOMEM; +#else + return 0; +#endif /* CONFIG_DEBUG_FS */ +} + +/** + * batadv_debugfs_del_hardif - delete the base directory for a hard interface + * in debugfs. + * @hard_iface: hard interface which is deleted. + */ +void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) +{ + if (batadv_debugfs) { + debugfs_remove_recursive(hard_iface->debug_dir); + hard_iface->debug_dir = NULL; + } +} + int batadv_debugfs_add_meshif(struct net_device *dev) { struct batadv_priv *bat_priv = netdev_priv(dev); diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 0861b629e1a8..37c4d6ddd04d 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -24,5 +24,7 @@ void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); +int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); +void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 997ae6ac51ff..edee50411892 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -589,7 +589,8 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, if (cand[i].type == BATADV_DAT_CANDIDATE_NOT_FOUND) continue; - neigh_node = batadv_orig_node_get_router(cand[i].orig_node); + neigh_node = batadv_orig_router_get(cand[i].orig_node, + BATADV_IF_DEFAULT); if (!neigh_node) goto free_orig; diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index afa13ca2371a..ac9be9b67a25 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 43185ca9da17..88df9b1d552d 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 0347f0ce0f61..5d7a0e66a22b 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 4150a641c52e..55cf2260d295 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -129,6 +129,7 @@ static struct batadv_gw_node * batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) { struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo; struct batadv_gw_node *gw_node, *curr_gw = NULL; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; uint32_t gw_divisor; @@ -145,14 +146,19 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) continue; orig_node = gw_node->orig_node; - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); if (!router) continue; + router_ifinfo = batadv_neigh_ifinfo_get(router, + BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto next; + if (!atomic_inc_not_zero(&gw_node->refcount)) goto next; - tq_avg = router->bat_iv.tq_avg; + tq_avg = router_ifinfo->bat_iv.tq_avg; switch (atomic_read(&bat_priv->gw_sel_class)) { case 1: /* fast connection */ @@ -197,6 +203,8 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) next: batadv_neigh_node_free_ref(router); + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); } rcu_read_unlock(); @@ -239,6 +247,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv) { struct batadv_gw_node *curr_gw = NULL, *next_gw = NULL; struct batadv_neigh_node *router = NULL; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; char gw_addr[18] = { '\0' }; if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT) @@ -257,11 +266,19 @@ void batadv_gw_election(struct batadv_priv *bat_priv) if (next_gw) { sprintf(gw_addr, "%pM", next_gw->orig_node->orig); - router = batadv_orig_node_get_router(next_gw->orig_node); + router = batadv_orig_router_get(next_gw->orig_node, + BATADV_IF_DEFAULT); if (!router) { batadv_gw_reselect(bat_priv); goto out; } + + router_ifinfo = batadv_neigh_ifinfo_get(router, + BATADV_IF_DEFAULT); + if (!router_ifinfo) { + batadv_gw_reselect(bat_priv); + goto out; + } } if ((curr_gw) && (!next_gw)) { @@ -276,7 +293,8 @@ void batadv_gw_election(struct batadv_priv *bat_priv) next_gw->bandwidth_down / 10, next_gw->bandwidth_down % 10, next_gw->bandwidth_up / 10, - next_gw->bandwidth_up % 10, router->bat_iv.tq_avg); + next_gw->bandwidth_up % 10, + router_ifinfo->bat_iv.tq_avg); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_ADD, gw_addr); } else { @@ -286,7 +304,8 @@ void batadv_gw_election(struct batadv_priv *bat_priv) next_gw->bandwidth_down / 10, next_gw->bandwidth_down % 10, next_gw->bandwidth_up / 10, - next_gw->bandwidth_up % 10, router->bat_iv.tq_avg); + next_gw->bandwidth_up % 10, + router_ifinfo->bat_iv.tq_avg); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_CHANGE, gw_addr); } @@ -300,11 +319,15 @@ out: batadv_gw_node_free_ref(next_gw); if (router) batadv_neigh_node_free_ref(router); + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); } void batadv_gw_check_election(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { + struct batadv_neigh_ifinfo *router_orig_tq = NULL; + struct batadv_neigh_ifinfo *router_gw_tq = NULL; struct batadv_orig_node *curr_gw_orig; struct batadv_neigh_node *router_gw = NULL, *router_orig = NULL; uint8_t gw_tq_avg, orig_tq_avg; @@ -313,20 +336,30 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv, if (!curr_gw_orig) goto reselect; - router_gw = batadv_orig_node_get_router(curr_gw_orig); + router_gw = batadv_orig_router_get(curr_gw_orig, BATADV_IF_DEFAULT); if (!router_gw) goto reselect; + router_gw_tq = batadv_neigh_ifinfo_get(router_gw, + BATADV_IF_DEFAULT); + if (!router_gw_tq) + goto reselect; + /* this node already is the gateway */ if (curr_gw_orig == orig_node) goto out; - router_orig = batadv_orig_node_get_router(orig_node); + router_orig = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); if (!router_orig) goto out; - gw_tq_avg = router_gw->bat_iv.tq_avg; - orig_tq_avg = router_orig->bat_iv.tq_avg; + router_orig_tq = batadv_neigh_ifinfo_get(router_orig, + BATADV_IF_DEFAULT); + if (!router_orig_tq) + goto out; + + gw_tq_avg = router_gw_tq->bat_iv.tq_avg; + orig_tq_avg = router_orig_tq->bat_iv.tq_avg; /* the TQ value has to be better */ if (orig_tq_avg < gw_tq_avg) @@ -352,6 +385,10 @@ out: batadv_neigh_node_free_ref(router_gw); if (router_orig) batadv_neigh_node_free_ref(router_orig); + if (router_gw_tq) + batadv_neigh_ifinfo_free_ref(router_gw_tq); + if (router_orig_tq) + batadv_neigh_ifinfo_free_ref(router_orig_tq); return; } @@ -537,28 +574,36 @@ static int batadv_write_buffer_text(struct batadv_priv *bat_priv, { struct batadv_gw_node *curr_gw; struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; int ret = -1; - router = batadv_orig_node_get_router(gw_node->orig_node); + router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); if (!router) goto out; + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", (curr_gw == gw_node ? "=>" : " "), gw_node->orig_node->orig, - router->bat_iv.tq_avg, router->addr, + router_ifinfo->bat_iv.tq_avg, router->addr, router->if_incoming->net_dev->name, gw_node->bandwidth_down / 10, gw_node->bandwidth_down % 10, gw_node->bandwidth_up / 10, gw_node->bandwidth_up % 10); - batadv_neigh_node_free_ref(router); if (curr_gw) batadv_gw_node_free_ref(curr_gw); out: + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); + if (router) + batadv_neigh_node_free_ref(router); return ret; } @@ -746,6 +791,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL; struct batadv_orig_node *orig_dst_node = NULL; struct batadv_gw_node *gw_node = NULL, *curr_gw = NULL; + struct batadv_neigh_ifinfo *curr_ifinfo, *old_ifinfo; struct ethhdr *ethhdr = (struct ethhdr *)skb->data; bool out_of_range = false; uint8_t curr_tq_avg; @@ -787,7 +833,14 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!neigh_curr) goto out; - curr_tq_avg = neigh_curr->bat_iv.tq_avg; + curr_ifinfo = batadv_neigh_ifinfo_get(neigh_curr, + BATADV_IF_DEFAULT); + if (!curr_ifinfo) + goto out; + + curr_tq_avg = curr_ifinfo->bat_iv.tq_avg; + batadv_neigh_ifinfo_free_ref(curr_ifinfo); + break; case BATADV_GW_MODE_OFF: default: @@ -798,8 +851,13 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!neigh_old) goto out; - if (curr_tq_avg - neigh_old->bat_iv.tq_avg > BATADV_GW_THRESHOLD) + old_ifinfo = batadv_neigh_ifinfo_get(neigh_old, BATADV_IF_DEFAULT); + if (!old_ifinfo) + goto out; + + if ((curr_tq_avg - old_ifinfo->bat_iv.tq_avg) > BATADV_GW_THRESHOLD) out_of_range = true; + batadv_neigh_ifinfo_free_ref(old_ifinfo); out: if (orig_dst_node) diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 006befb8c7b8..7ee53bb7d50f 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index f76816ce9faf..6f5e621f220a 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index c47b17a0a6b6..aa5116561947 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index bebd46ce0ebd..1b12573bcf83 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -23,6 +23,7 @@ #include "translation-table.h" #include "routing.h" #include "sysfs.h" +#include "debugfs.h" #include "originator.h" #include "hash.h" #include "bridge_loop_avoidance.h" @@ -539,6 +540,7 @@ static void batadv_hardif_remove_interface_finish(struct work_struct *work) hard_iface = container_of(work, struct batadv_hard_iface, cleanup_work); + batadv_debugfs_del_hardif(hard_iface); batadv_sysfs_del_hardif(&hard_iface->hardif_obj); batadv_hardif_free_ref(hard_iface); } @@ -569,6 +571,11 @@ batadv_hardif_add_interface(struct net_device *net_dev) hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; + + ret = batadv_debugfs_add_hardif(hard_iface); + if (ret) + goto free_sysfs; + INIT_LIST_HEAD(&hard_iface->list); INIT_WORK(&hard_iface->cleanup_work, batadv_hardif_remove_interface_finish); @@ -585,6 +592,8 @@ batadv_hardif_add_interface(struct net_device *net_dev) return hard_iface; +free_sysfs: + batadv_sysfs_del_hardif(&hard_iface->hardif_obj); free_if: kfree(hard_iface); release_dev: diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index d8ca8ac829c1..1918cd50b62e 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -40,6 +40,7 @@ enum batadv_hard_if_cleanup { extern struct notifier_block batadv_hard_if_notifier; bool batadv_is_wifi_netdev(struct net_device *net_device); +bool batadv_is_wifi_iface(int ifindex); struct batadv_hard_iface* batadv_hardif_get_by_netdev(const struct net_device *net_dev); int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, @@ -51,6 +52,11 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_free_rcu(struct rcu_head *rcu); +/** + * batadv_hardif_free_ref - decrement the hard interface refcounter and + * possibly free it + * @hard_iface: the hard interface to free + */ static inline void batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) { @@ -58,6 +64,18 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } +/** + * batadv_hardif_free_ref_now - decrement the hard interface refcounter and + * possibly free it (without rcu callback) + * @hard_iface: the hard interface to free + */ +static inline void +batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface) +{ + if (atomic_dec_and_test(&hard_iface->refcount)) + batadv_hardif_free_rcu(&hard_iface->rcu); +} + static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index d9cfa03b9e12..63bdf7e94f1e 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index df5ece96ac12..539fc1266793 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 3c08eee1b920..abb9d6e0388b 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -215,7 +215,8 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, if (!orig_node) goto dst_unreach; - neigh_node = batadv_orig_node_get_router(orig_node); + neigh_node = batadv_orig_router_get(orig_node, + BATADV_IF_DEFAULT); if (!neigh_node) goto dst_unreach; diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 559e54ad64a2..0c33950aa4aa 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 945e441b579d..e56b4d6a43b6 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -419,13 +419,23 @@ static void batadv_recv_handler_init(void) for (i = BATADV_UNICAST_MIN; i <= BATADV_UNICAST_MAX; i++) batadv_rx_handler[i] = batadv_recv_unhandled_unicast_packet; - /* compile time checks for struct member offsets */ - BUILD_BUG_ON(offsetof(struct batadv_unicast_4addr_packet, src) != 10); - BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, dest) != 4); - BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, dst) != 4); - BUILD_BUG_ON(offsetof(struct batadv_frag_packet, dest) != 4); - BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, dst) != 4); - BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, dst) != 4); + /* compile time checks for sizes */ + BUILD_BUG_ON(sizeof(struct batadv_bla_claim_dst) != 6); + BUILD_BUG_ON(sizeof(struct batadv_ogm_packet) != 24); + BUILD_BUG_ON(sizeof(struct batadv_icmp_header) != 20); + BUILD_BUG_ON(sizeof(struct batadv_icmp_packet) != 20); + BUILD_BUG_ON(sizeof(struct batadv_icmp_packet_rr) != 116); + BUILD_BUG_ON(sizeof(struct batadv_unicast_packet) != 10); + BUILD_BUG_ON(sizeof(struct batadv_unicast_4addr_packet) != 18); + BUILD_BUG_ON(sizeof(struct batadv_frag_packet) != 20); + BUILD_BUG_ON(sizeof(struct batadv_bcast_packet) != 14); + BUILD_BUG_ON(sizeof(struct batadv_coded_packet) != 46); + BUILD_BUG_ON(sizeof(struct batadv_unicast_tvlv_packet) != 20); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_hdr) != 4); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_gateway_data) != 8); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_vlan_data) != 8); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8); /* broadcast packet */ batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index a468760b11ea..9374f1a51348 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2013.5.0" +#define BATADV_SOURCE_VERSION "2014.1.0" #endif /* B.A.T.M.A.N. parameters */ @@ -72,6 +72,12 @@ #define BATADV_NO_MARK 0 +/* default interface for multi interface operation. The default interface is + * used for communication which originated locally (i.e. is not forwarded) + * or where special forwarding is not desired/necessary. + */ +#define BATADV_IF_DEFAULT ((struct batadv_hard_iface *)NULL) + #define BATADV_NUM_WORDS BITS_TO_LONGS(BATADV_TQ_LOCAL_WINDOW_SIZE) #define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index d6f0be346a3d..f1b604d88dc3 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * @@ -718,9 +718,21 @@ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_ogm_packet *ogm_packet) { - if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno)) + struct batadv_orig_ifinfo *orig_ifinfo; + uint32_t last_real_seqno; + uint8_t last_ttl; + + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, BATADV_IF_DEFAULT); + if (!orig_ifinfo) return false; - if (orig_node->last_ttl != ogm_packet->ttl + 1) + + last_ttl = orig_ifinfo->last_ttl; + last_real_seqno = orig_ifinfo->last_real_seqno; + batadv_orig_ifinfo_free_ref(orig_ifinfo); + + if (last_real_seqno != ntohl(ogm_packet->seqno)) + return false; + if (last_ttl != ogm_packet->ttl + 1) return false; if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender)) return false; @@ -1008,6 +1020,8 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct batadv_coded_packet *coded_packet; struct batadv_neigh_node *neigh_tmp, *router_neigh; struct batadv_neigh_node *router_coding = NULL; + struct batadv_neigh_ifinfo *router_neigh_ifinfo = NULL; + struct batadv_neigh_ifinfo *router_coding_ifinfo = NULL; uint8_t *first_source, *first_dest, *second_source, *second_dest; __be32 packet_id1, packet_id2; size_t count; @@ -1017,19 +1031,34 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, int coded_size = sizeof(*coded_packet); int header_add = coded_size - unicast_size; - router_neigh = batadv_orig_node_get_router(neigh_node->orig_node); + /* TODO: do we need to consider the outgoing interface for + * coded packets? + */ + router_neigh = batadv_orig_router_get(neigh_node->orig_node, + BATADV_IF_DEFAULT); if (!router_neigh) goto out; + router_neigh_ifinfo = batadv_neigh_ifinfo_get(router_neigh, + BATADV_IF_DEFAULT); + if (!router_neigh_ifinfo) + goto out; + neigh_tmp = nc_packet->neigh_node; - router_coding = batadv_orig_node_get_router(neigh_tmp->orig_node); + router_coding = batadv_orig_router_get(neigh_tmp->orig_node, + BATADV_IF_DEFAULT); if (!router_coding) goto out; - tq_tmp = batadv_nc_random_weight_tq(router_neigh->bat_iv.tq_avg); - tq_weighted_neigh = tq_tmp; - tq_tmp = batadv_nc_random_weight_tq(router_coding->bat_iv.tq_avg); - tq_weighted_coding = tq_tmp; + router_coding_ifinfo = batadv_neigh_ifinfo_get(router_coding, + BATADV_IF_DEFAULT); + if (!router_coding_ifinfo) + goto out; + + tq_tmp = router_neigh_ifinfo->bat_iv.tq_avg; + tq_weighted_neigh = batadv_nc_random_weight_tq(tq_tmp); + tq_tmp = router_coding_ifinfo->bat_iv.tq_avg; + tq_weighted_coding = batadv_nc_random_weight_tq(tq_tmp); /* Select one destination for the MAC-header dst-field based on * weighted TQ-values. @@ -1153,6 +1182,10 @@ out: batadv_neigh_node_free_ref(router_neigh); if (router_coding) batadv_neigh_node_free_ref(router_coding); + if (router_neigh_ifinfo) + batadv_neigh_ifinfo_free_ref(router_neigh_ifinfo); + if (router_coding_ifinfo) + batadv_neigh_ifinfo_free_ref(router_coding_ifinfo); return res; } diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index ab59b3d7cf0f..358c0d686ab0 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * @@ -62,7 +62,6 @@ static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv) static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { - return; } static inline void @@ -72,7 +71,6 @@ batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_ogm_packet *ogm_packet, int is_single_hop_neigh) { - return; } static inline void @@ -81,17 +79,14 @@ batadv_nc_purge_orig(struct batadv_priv *bat_priv, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_node *)) { - return; } static inline void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) { - return; } static inline void batadv_nc_init_orig(struct batadv_orig_node *orig_node) { - return; } static inline bool batadv_nc_skb_forward(struct sk_buff *skb, @@ -104,14 +99,12 @@ static inline void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, struct sk_buff *skb) { - return; } static inline void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb) { - return; } static inline int batadv_nc_nodes_seq_print_text(struct seq_file *seq, diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 04a6d51f1d58..6df12a2e3605 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -148,20 +148,114 @@ err: return -ENOMEM; } +/** + * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object + * @rcu: rcu pointer of the neigh_ifinfo object + */ +static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + + neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu); + + if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing); + + kfree(neigh_ifinfo); +} + +/** + * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free + * the neigh_ifinfo (without rcu callback) + * @neigh_ifinfo: the neigh_ifinfo object to release + */ +static void +batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo) +{ + if (atomic_dec_and_test(&neigh_ifinfo->refcount)) + batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu); +} + +/** + * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free + * the neigh_ifinfo + * @neigh_ifinfo: the neigh_ifinfo object to release + */ +void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) +{ + if (atomic_dec_and_test(&neigh_ifinfo->refcount)) + call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu); +} + +/** + * batadv_neigh_node_free_rcu - free the neigh_node + * @rcu: rcu pointer of the neigh_node + */ +static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) +{ + struct hlist_node *node_tmp; + struct batadv_neigh_node *neigh_node; + struct batadv_neigh_ifinfo *neigh_ifinfo; + + neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); + + hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, + &neigh_node->ifinfo_list, list) { + batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); + } + batadv_hardif_free_ref_now(neigh_node->if_incoming); + + kfree(neigh_node); +} + +/** + * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter + * and possibly free it (without rcu callback) + * @neigh_node: neigh neighbor to free + */ +static void +batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node) +{ + if (atomic_dec_and_test(&neigh_node->refcount)) + batadv_neigh_node_free_rcu(&neigh_node->rcu); +} + +/** + * batadv_neigh_node_free_ref - decrement the neighbors refcounter + * and possibly free it + * @neigh_node: neigh neighbor to free + */ void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) - kfree_rcu(neigh_node, rcu); + call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu); } -/* increases the refcounter of a found router */ +/** + * batadv_orig_node_get_router - router to the originator depending on iface + * @orig_node: the orig node for the router + * @if_outgoing: the interface where the payload packet has been received or + * the OGM should be sent to + * + * Returns the neighbor which should be router for this orig_node/iface. + * + * The object is returned with refcounter increased by 1. + */ struct batadv_neigh_node * -batadv_orig_node_get_router(struct batadv_orig_node *orig_node) +batadv_orig_router_get(struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *if_outgoing) { - struct batadv_neigh_node *router; + struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_neigh_node *router = NULL; rcu_read_lock(); - router = rcu_dereference(orig_node->router); + hlist_for_each_entry_rcu(orig_ifinfo, &orig_node->ifinfo_list, list) { + if (orig_ifinfo->if_outgoing != if_outgoing) + continue; + + router = rcu_dereference(orig_ifinfo->router); + break; + } if (router && !atomic_inc_not_zero(&router->refcount)) router = NULL; @@ -171,6 +265,164 @@ batadv_orig_node_get_router(struct batadv_orig_node *orig_node) } /** + * batadv_orig_ifinfo_get - find the ifinfo from an orig_node + * @orig_node: the orig node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * Returns the requested orig_ifinfo or NULL if not found. + * + * The object is returned with refcounter increased by 1. + */ +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_orig_ifinfo *tmp, *orig_ifinfo = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp, &orig_node->ifinfo_list, + list) { + if (tmp->if_outgoing != if_outgoing) + continue; + + if (!atomic_inc_not_zero(&tmp->refcount)) + continue; + + orig_ifinfo = tmp; + break; + } + rcu_read_unlock(); + + return orig_ifinfo; +} + +/** + * batadv_orig_ifinfo_new - search and possibly create an orig_ifinfo object + * @orig_node: the orig node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * Returns NULL in case of failure or the orig_ifinfo object for the if_outgoing + * interface otherwise. The object is created and added to the list + * if it does not exist. + * + * The object is returned with refcounter increased by 1. + */ +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_orig_ifinfo *orig_ifinfo = NULL; + unsigned long reset_time; + + spin_lock_bh(&orig_node->neigh_list_lock); + + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_outgoing); + if (orig_ifinfo) + goto out; + + orig_ifinfo = kzalloc(sizeof(*orig_ifinfo), GFP_ATOMIC); + if (!orig_ifinfo) + goto out; + + if (if_outgoing != BATADV_IF_DEFAULT && + !atomic_inc_not_zero(&if_outgoing->refcount)) { + kfree(orig_ifinfo); + orig_ifinfo = NULL; + goto out; + } + + reset_time = jiffies - 1; + reset_time -= msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); + orig_ifinfo->batman_seqno_reset = reset_time; + orig_ifinfo->if_outgoing = if_outgoing; + INIT_HLIST_NODE(&orig_ifinfo->list); + atomic_set(&orig_ifinfo->refcount, 2); + hlist_add_head_rcu(&orig_ifinfo->list, + &orig_node->ifinfo_list); +out: + spin_unlock_bh(&orig_node->neigh_list_lock); + return orig_ifinfo; +} + +/** + * batadv_neigh_ifinfo_get - find the ifinfo from an neigh_node + * @neigh_node: the neigh node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * The object is returned with refcounter increased by 1. + * + * Returns the requested neigh_ifinfo or NULL if not found + */ +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo = NULL, + *tmp_neigh_ifinfo; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_ifinfo, &neigh->ifinfo_list, + list) { + if (tmp_neigh_ifinfo->if_outgoing != if_outgoing) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_ifinfo->refcount)) + continue; + + neigh_ifinfo = tmp_neigh_ifinfo; + break; + } + rcu_read_unlock(); + + return neigh_ifinfo; +} + +/** + * batadv_neigh_ifinfo_new - search and possibly create an neigh_ifinfo object + * @neigh_node: the neigh node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * Returns NULL in case of failure or the neigh_ifinfo object for the + * if_outgoing interface otherwise. The object is created and added to the list + * if it does not exist. + * + * The object is returned with refcounter increased by 1. + */ +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + + spin_lock_bh(&neigh->ifinfo_lock); + + neigh_ifinfo = batadv_neigh_ifinfo_get(neigh, if_outgoing); + if (neigh_ifinfo) + goto out; + + neigh_ifinfo = kzalloc(sizeof(*neigh_ifinfo), GFP_ATOMIC); + if (!neigh_ifinfo) + goto out; + + if (if_outgoing && !atomic_inc_not_zero(&if_outgoing->refcount)) { + kfree(neigh_ifinfo); + neigh_ifinfo = NULL; + goto out; + } + + INIT_HLIST_NODE(&neigh_ifinfo->list); + atomic_set(&neigh_ifinfo->refcount, 2); + neigh_ifinfo->if_outgoing = if_outgoing; + + hlist_add_head_rcu(&neigh_ifinfo->list, &neigh->ifinfo_list); + +out: + spin_unlock_bh(&neigh->ifinfo_lock); + + return neigh_ifinfo; +} + +/** * batadv_neigh_node_new - create and init a new neigh_node object * @hard_iface: the interface where the neighbour is connected to * @neigh_addr: the mac address of the neighbour interface @@ -191,13 +443,13 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, goto out; INIT_HLIST_NODE(&neigh_node->list); + INIT_HLIST_HEAD(&neigh_node->ifinfo_list); + spin_lock_init(&neigh_node->ifinfo_lock); memcpy(neigh_node->addr, neigh_addr, ETH_ALEN); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; - INIT_LIST_HEAD(&neigh_node->bonding_list); - /* extra reference for return */ atomic_set(&neigh_node->refcount, 2); @@ -205,30 +457,68 @@ out: return neigh_node; } +/** + * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object + * @rcu: rcu pointer of the orig_ifinfo object + */ +static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) +{ + struct batadv_orig_ifinfo *orig_ifinfo; + + orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); + + if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + + kfree(orig_ifinfo); +} + +/** + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free + * the orig_ifinfo (without rcu callback) + * @orig_ifinfo: the orig_ifinfo object to release + */ +static void +batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo) +{ + if (atomic_dec_and_test(&orig_ifinfo->refcount)) + batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu); +} + +/** + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free + * the orig_ifinfo + * @orig_ifinfo: the orig_ifinfo object to release + */ +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) +{ + if (atomic_dec_and_test(&orig_ifinfo->refcount)) + call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); +} + static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node, *tmp_neigh_node; + struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; + struct batadv_orig_ifinfo *orig_ifinfo; orig_node = container_of(rcu, struct batadv_orig_node, rcu); spin_lock_bh(&orig_node->neigh_list_lock); - /* for all bonding members ... */ - list_for_each_entry_safe(neigh_node, tmp_neigh_node, - &orig_node->bond_list, bonding_list) { - list_del_rcu(&neigh_node->bonding_list); - batadv_neigh_node_free_ref(neigh_node); - } - /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); - batadv_neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref_now(neigh_node); } + hlist_for_each_entry_safe(orig_ifinfo, node_tmp, + &orig_node->ifinfo_list, list) { + hlist_del_rcu(&orig_ifinfo->list); + batadv_orig_ifinfo_free_ref_now(orig_ifinfo); + } spin_unlock_bh(&orig_node->neigh_list_lock); /* Free nc_nodes */ @@ -325,8 +615,8 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, return NULL; INIT_HLIST_HEAD(&orig_node->neigh_list); - INIT_LIST_HEAD(&orig_node->bond_list); INIT_LIST_HEAD(&orig_node->vlan_list); + INIT_HLIST_HEAD(&orig_node->ifinfo_list); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); spin_lock_init(&orig_node->tt_buff_lock); @@ -342,15 +632,11 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, orig_node->bat_priv = bat_priv; memcpy(orig_node->orig, addr, ETH_ALEN); batadv_dat_init_orig_node_addr(orig_node); - orig_node->router = NULL; atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; - orig_node->batman_seqno_reset = reset_time; - - atomic_set(&orig_node->bond_candidates, 0); /* create a vlan object for the "untagged" LAN */ vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS); @@ -374,20 +660,76 @@ free_orig_node: return NULL; } +/** + * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * + * Returns true if any ifinfo entry was purged, false otherwise. + */ +static bool +batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) +{ + struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_hard_iface *if_outgoing; + struct hlist_node *node_tmp; + bool ifinfo_purged = false; + + spin_lock_bh(&orig_node->neigh_list_lock); + + /* for all ifinfo objects for this originator */ + hlist_for_each_entry_safe(orig_ifinfo, node_tmp, + &orig_node->ifinfo_list, list) { + if_outgoing = orig_ifinfo->if_outgoing; + + /* always keep the default interface */ + if (if_outgoing == BATADV_IF_DEFAULT) + continue; + + /* don't purge if the interface is not (going) down */ + if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && + (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && + (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + continue; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "router/ifinfo purge: originator %pM, iface: %s\n", + orig_node->orig, if_outgoing->net_dev->name); + + ifinfo_purged = true; + + hlist_del_rcu(&orig_ifinfo->list); + batadv_orig_ifinfo_free_ref(orig_ifinfo); + if (orig_node->last_bonding_candidate == orig_ifinfo) { + orig_node->last_bonding_candidate = NULL; + batadv_orig_ifinfo_free_ref(orig_ifinfo); + } + } + + spin_unlock_bh(&orig_node->neigh_list_lock); + + return ifinfo_purged; +} + + +/** + * batadv_purge_orig_neighbors - purges neighbors from originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * + * Returns true if any neighbor was purged, false otherwise + */ static bool batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - struct batadv_neigh_node **best_neigh) + struct batadv_orig_node *orig_node) { - struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; struct batadv_hard_iface *if_incoming; - *best_neigh = NULL; - spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ @@ -416,15 +758,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, neigh_purged = true; hlist_del_rcu(&neigh_node->list); - batadv_bonding_candidate_del(orig_node, neigh_node); batadv_neigh_node_free_ref(neigh_node); - } else { - /* store the best_neighbour if this is the first - * iteration or if a better neighbor has been found - */ - if (!*best_neigh || - bao->bat_neigh_cmp(neigh_node, *best_neigh) > 0) - *best_neigh = neigh_node; } } @@ -432,10 +766,57 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, return neigh_purged; } +/** + * batadv_find_best_neighbor - finds the best neighbor after purging + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * @if_outgoing: the interface for which the metric should be compared + * + * Returns the current best neighbor, with refcount increased. + */ +static struct batadv_neigh_node * +batadv_find_best_neighbor(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *best = NULL, *neigh; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; + + rcu_read_lock(); + hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) { + if (best && (bao->bat_neigh_cmp(neigh, if_outgoing, + best, if_outgoing) <= 0)) + continue; + + if (!atomic_inc_not_zero(&neigh->refcount)) + continue; + + if (best) + batadv_neigh_node_free_ref(best); + + best = neigh; + } + rcu_read_unlock(); + + return best; +} + +/** + * batadv_purge_orig_node - purges obsolete information from an orig_node + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * + * This function checks if the orig_node or substructures of it have become + * obsolete, and purges this information if that's the case. + * + * Returns true if the orig_node is to be removed, false otherwise. + */ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_neigh_node *best_neigh_node; + struct batadv_hard_iface *hard_iface; + bool changed; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { @@ -444,12 +825,39 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, orig_node->orig, jiffies_to_msecs(orig_node->last_seen)); return true; - } else { - if (batadv_purge_orig_neighbors(bat_priv, orig_node, - &best_neigh_node)) - batadv_update_route(bat_priv, orig_node, - best_neigh_node); } + changed = batadv_purge_orig_ifinfo(bat_priv, orig_node); + changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node); + + if (!changed) + return false; + + /* first for NULL ... */ + best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node, + BATADV_IF_DEFAULT); + batadv_update_route(bat_priv, orig_node, BATADV_IF_DEFAULT, + best_neigh_node); + if (best_neigh_node) + batadv_neigh_node_free_ref(best_neigh_node); + + /* ... then for all other interfaces. */ + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + best_neigh_node = batadv_find_best_neighbor(bat_priv, + orig_node, + hard_iface); + batadv_update_route(bat_priv, orig_node, hard_iface, + best_neigh_node); + if (best_neigh_node) + batadv_neigh_node_free_ref(best_neigh_node); + } + rcu_read_unlock(); return false; } @@ -532,8 +940,54 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) return 0; } - bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq); + bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, + BATADV_IF_DEFAULT); + + return 0; +} + +/** + * batadv_orig_hardif_seq_print_text - writes originator infos for a specific + * outgoing interface + * @seq: debugfs table seq_file struct + * @offset: not used + * + * Returns 0 + */ +int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; + + hard_iface = batadv_hardif_get_by_netdev(net_dev); + + if (!hard_iface || !hard_iface->soft_iface) { + seq_puts(seq, "Interface not known to B.A.T.M.A.N.\n"); + goto out; + } + + bat_priv = netdev_priv(hard_iface->soft_iface); + if (!bat_priv->bat_algo_ops->bat_orig_print) { + seq_puts(seq, + "No printing function for this routing protocol\n"); + goto out; + } + + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + seq_puts(seq, "Interface not active\n"); + goto out; + } + seq_printf(seq, "[B.A.T.M.A.N. adv %s, IF/MAC: %s/%pM (%s %s)]\n", + BATADV_SOURCE_VERSION, hard_iface->net_dev->name, + hard_iface->net_dev->dev_addr, + hard_iface->soft_iface->name, bat_priv->bat_algo_ops->name); + + bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface); + +out: + batadv_hardif_free_ref(hard_iface); return 0; } diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 99ed3c61e4f9..37be290f63f6 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -34,8 +34,26 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, struct batadv_orig_node *orig_node); void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node); struct batadv_neigh_node * -batadv_orig_node_get_router(struct batadv_orig_node *orig_node); +batadv_orig_router_get(struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *if_outgoing); +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing); +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing); +void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo); + +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing); +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing); +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo); + int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); +int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index ef2010c27146..0a381d1174c1 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 7e8aa177eb1d..1ed9f7c9ecea 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -33,13 +33,32 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); +/** + * _batadv_update_route - set the router for this originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be configured + * @recv_if: the receive interface for which this route is set + * @neigh_node: neighbor which should be the next router + * + * This function does not perform any error checks + */ static void _batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if, struct batadv_neigh_node *neigh_node) { + struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *curr_router; - curr_router = batadv_orig_node_get_router(orig_node); + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, recv_if); + if (!orig_ifinfo) + return; + + rcu_read_lock(); + curr_router = rcu_dereference(orig_ifinfo->router); + if (curr_router && !atomic_inc_not_zero(&curr_router->refcount)) + curr_router = NULL; + rcu_read_unlock(); /* route deleted */ if ((curr_router) && (!neigh_node)) { @@ -69,16 +88,25 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, neigh_node = NULL; spin_lock_bh(&orig_node->neigh_list_lock); - rcu_assign_pointer(orig_node->router, neigh_node); + rcu_assign_pointer(orig_ifinfo->router, neigh_node); spin_unlock_bh(&orig_node->neigh_list_lock); + batadv_orig_ifinfo_free_ref(orig_ifinfo); /* decrease refcount of previous best neighbor */ if (curr_router) batadv_neigh_node_free_ref(curr_router); } +/** + * batadv_update_route - set the router for this originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be configured + * @recv_if: the receive interface for which this route is set + * @neigh_node: neighbor which should be the next router + */ void batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if, struct batadv_neigh_node *neigh_node) { struct batadv_neigh_node *router = NULL; @@ -86,125 +114,16 @@ void batadv_update_route(struct batadv_priv *bat_priv, if (!orig_node) goto out; - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, recv_if); if (router != neigh_node) - _batadv_update_route(bat_priv, orig_node, neigh_node); + _batadv_update_route(bat_priv, orig_node, recv_if, neigh_node); out: if (router) batadv_neigh_node_free_ref(router); } -/* caller must hold the neigh_list_lock */ -void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node) -{ - /* this neighbor is not part of our candidate list */ - if (list_empty(&neigh_node->bonding_list)) - goto out; - - list_del_rcu(&neigh_node->bonding_list); - INIT_LIST_HEAD(&neigh_node->bonding_list); - batadv_neigh_node_free_ref(neigh_node); - atomic_dec(&orig_node->bond_candidates); - -out: - return; -} - -/** - * batadv_bonding_candidate_add - consider a new link for bonding mode towards - * the given originator - * @bat_priv: the bat priv with all the soft interface information - * @orig_node: the target node - * @neigh_node: the neighbor representing the new link to consider for bonding - * mode - */ -void batadv_bonding_candidate_add(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node) -{ - struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; - struct batadv_neigh_node *tmp_neigh_node, *router = NULL; - uint8_t interference_candidate = 0; - - spin_lock_bh(&orig_node->neigh_list_lock); - - /* only consider if it has the same primary address ... */ - if (!batadv_compare_eth(orig_node->orig, - neigh_node->orig_node->primary_addr)) - goto candidate_del; - - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto candidate_del; - - - /* ... and is good enough to be considered */ - if (bao->bat_neigh_is_equiv_or_better(neigh_node, router)) - goto candidate_del; - - /* check if we have another candidate with the same mac address or - * interface. If we do, we won't select this candidate because of - * possible interference. - */ - hlist_for_each_entry_rcu(tmp_neigh_node, - &orig_node->neigh_list, list) { - if (tmp_neigh_node == neigh_node) - continue; - - /* we only care if the other candidate is even - * considered as candidate. - */ - if (list_empty(&tmp_neigh_node->bonding_list)) - continue; - - if ((neigh_node->if_incoming == tmp_neigh_node->if_incoming) || - (batadv_compare_eth(neigh_node->addr, - tmp_neigh_node->addr))) { - interference_candidate = 1; - break; - } - } - - /* don't care further if it is an interference candidate */ - if (interference_candidate) - goto candidate_del; - - /* this neighbor already is part of our candidate list */ - if (!list_empty(&neigh_node->bonding_list)) - goto out; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) - goto out; - - list_add_rcu(&neigh_node->bonding_list, &orig_node->bond_list); - atomic_inc(&orig_node->bond_candidates); - goto out; - -candidate_del: - batadv_bonding_candidate_del(orig_node, neigh_node); - -out: - spin_unlock_bh(&orig_node->neigh_list_lock); - - if (router) - batadv_neigh_node_free_ref(router); -} - -/* copy primary address for bonding */ -void -batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh_node, - const struct batadv_ogm_packet *batman_ogm_packet) -{ - if (!(batman_ogm_packet->flags & BATADV_PRIMARIES_FIRST_HOP)) - return; - - memcpy(orig_neigh_node->primary_addr, orig_node->orig, ETH_ALEN); -} - /* checks whether the host restarted and is in the protection time. * returns: * 0 if the packet is to be accepted @@ -459,114 +378,6 @@ out: return ret; } -/* In the bonding case, send the packets in a round - * robin fashion over the remaining interfaces. - * - * This method rotates the bonding list and increases the - * returned router's refcount. - */ -static struct batadv_neigh_node * -batadv_find_bond_router(struct batadv_orig_node *primary_orig, - const struct batadv_hard_iface *recv_if) -{ - struct batadv_neigh_node *tmp_neigh_node; - struct batadv_neigh_node *router = NULL, *first_candidate = NULL; - - rcu_read_lock(); - list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, - bonding_list) { - if (!first_candidate) - first_candidate = tmp_neigh_node; - - /* recv_if == NULL on the first node. */ - if (tmp_neigh_node->if_incoming == recv_if) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - router = tmp_neigh_node; - break; - } - - /* use the first candidate if nothing was found. */ - if (!router && first_candidate && - atomic_inc_not_zero(&first_candidate->refcount)) - router = first_candidate; - - if (!router) - goto out; - - /* selected should point to the next element - * after the current router - */ - spin_lock_bh(&primary_orig->neigh_list_lock); - /* this is a list_move(), which unfortunately - * does not exist as rcu version - */ - list_del_rcu(&primary_orig->bond_list); - list_add_rcu(&primary_orig->bond_list, - &router->bonding_list); - spin_unlock_bh(&primary_orig->neigh_list_lock); - -out: - rcu_read_unlock(); - return router; -} - -/** - * batadv_find_ifalter_router - find the best of the remaining candidates which - * are not using this interface - * @bat_priv: the bat priv with all the soft interface information - * @primary_orig: the destination - * @recv_if: the interface that the router returned by this function has to not - * use - * - * Returns the best candidate towards primary_orig that is not using recv_if. - * Increases the returned neighbor's refcount - */ -static struct batadv_neigh_node * -batadv_find_ifalter_router(struct batadv_priv *bat_priv, - struct batadv_orig_node *primary_orig, - const struct batadv_hard_iface *recv_if) -{ - struct batadv_neigh_node *router = NULL, *first_candidate = NULL; - struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; - struct batadv_neigh_node *tmp_neigh_node; - - rcu_read_lock(); - list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, - bonding_list) { - if (!first_candidate) - first_candidate = tmp_neigh_node; - - /* recv_if == NULL on the first node. */ - if (tmp_neigh_node->if_incoming == recv_if) - continue; - - if (router && bao->bat_neigh_cmp(tmp_neigh_node, router)) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - /* decrement refcount of previously selected router */ - if (router) - batadv_neigh_node_free_ref(router); - - /* we found a better router (or at least one valid router) */ - router = tmp_neigh_node; - } - - /* use the first candidate if nothing was found. */ - if (!router && first_candidate && - atomic_inc_not_zero(&first_candidate->refcount)) - router = first_candidate; - - rcu_read_unlock(); - return router; -} - /** * batadv_check_unicast_packet - Check for malformed unicast packets * @bat_priv: the bat priv with all the soft interface information @@ -604,95 +415,141 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, return 0; } -/* find a suitable router for this originator, and use - * bonding if possible. increases the found neighbors - * refcount. +/** + * batadv_find_router - find a suitable router for this originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: the destination node + * @recv_if: pointer to interface this packet was received on + * + * Returns the router which should be used for this orig_node on + * this interface, or NULL if not available. */ struct batadv_neigh_node * batadv_find_router(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const struct batadv_hard_iface *recv_if) + struct batadv_hard_iface *recv_if) { - struct batadv_orig_node *primary_orig_node; - struct batadv_orig_node *router_orig; - struct batadv_neigh_node *router; - static uint8_t zero_mac[ETH_ALEN] = {0, 0, 0, 0, 0, 0}; - int bonding_enabled; - uint8_t *primary_addr; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; + struct batadv_neigh_node *first_candidate_router = NULL; + struct batadv_neigh_node *next_candidate_router = NULL; + struct batadv_neigh_node *router, *cand_router = NULL; + struct batadv_neigh_node *last_cand_router = NULL; + struct batadv_orig_ifinfo *cand, *first_candidate = NULL; + struct batadv_orig_ifinfo *next_candidate = NULL; + struct batadv_orig_ifinfo *last_candidate; + bool last_candidate_found = false; if (!orig_node) return NULL; - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto err; + router = batadv_orig_router_get(orig_node, recv_if); - /* without bonding, the first node should - * always choose the default router. + /* only consider bonding for recv_if == BATADV_IF_DEFAULT (first hop) + * and if activated. + */ + if (recv_if == BATADV_IF_DEFAULT || !atomic_read(&bat_priv->bonding) || + !router) + return router; + + /* bonding: loop through the list of possible routers found + * for the various outgoing interfaces and find a candidate after + * the last chosen bonding candidate (next_candidate). If no such + * router is found, use the first candidate found (the previously + * chosen bonding candidate might have been the last one in the list). + * If this can't be found either, return the previously choosen + * router - obviously there are no other candidates. */ - bonding_enabled = atomic_read(&bat_priv->bonding); - rcu_read_lock(); - /* select default router to output */ - router_orig = router->orig_node; - if (!router_orig) - goto err_unlock; + last_candidate = orig_node->last_bonding_candidate; + if (last_candidate) + last_cand_router = rcu_dereference(last_candidate->router); - if ((!recv_if) && (!bonding_enabled)) - goto return_router; + hlist_for_each_entry_rcu(cand, &orig_node->ifinfo_list, list) { + /* acquire some structures and references ... */ + if (!atomic_inc_not_zero(&cand->refcount)) + continue; - primary_addr = router_orig->primary_addr; + cand_router = rcu_dereference(cand->router); + if (!cand_router) + goto next; - /* if we have something in the primary_addr, we can search - * for a potential bonding candidate. - */ - if (batadv_compare_eth(primary_addr, zero_mac)) - goto return_router; + if (!atomic_inc_not_zero(&cand_router->refcount)) { + cand_router = NULL; + goto next; + } - /* find the orig_node which has the primary interface. might - * even be the same as our router_orig in many cases - */ - if (batadv_compare_eth(primary_addr, router_orig->orig)) { - primary_orig_node = router_orig; - } else { - primary_orig_node = batadv_orig_hash_find(bat_priv, - primary_addr); - if (!primary_orig_node) - goto return_router; + /* alternative candidate should be good enough to be + * considered + */ + if (!bao->bat_neigh_is_equiv_or_better(cand_router, + cand->if_outgoing, + router, recv_if)) + goto next; + + /* don't use the same router twice */ + if (last_cand_router == cand_router) + goto next; + + /* mark the first possible candidate */ + if (!first_candidate) { + atomic_inc(&cand_router->refcount); + atomic_inc(&cand->refcount); + first_candidate = cand; + first_candidate_router = cand_router; + } + + /* check if the loop has already passed the previously selected + * candidate ... this function should select the next candidate + * AFTER the previously used bonding candidate. + */ + if (!last_candidate || last_candidate_found) { + next_candidate = cand; + next_candidate_router = cand_router; + break; + } - batadv_orig_node_free_ref(primary_orig_node); + if (last_candidate == cand) + last_candidate_found = true; +next: + /* free references */ + if (cand_router) { + batadv_neigh_node_free_ref(cand_router); + cand_router = NULL; + } + batadv_orig_ifinfo_free_ref(cand); } + rcu_read_unlock(); - /* with less than 2 candidates, we can't do any - * bonding and prefer the original router. - */ - if (atomic_read(&primary_orig_node->bond_candidates) < 2) - goto return_router; + /* last_bonding_candidate is reset below, remove the old reference. */ + if (orig_node->last_bonding_candidate) + batadv_orig_ifinfo_free_ref(orig_node->last_bonding_candidate); - /* all nodes between should choose a candidate which - * is is not on the interface where the packet came - * in. + /* After finding candidates, handle the three cases: + * 1) there is a next candidate, use that + * 2) there is no next candidate, use the first of the list + * 3) there is no candidate at all, return the default router */ - batadv_neigh_node_free_ref(router); + if (next_candidate) { + batadv_neigh_node_free_ref(router); - if (bonding_enabled) - router = batadv_find_bond_router(primary_orig_node, recv_if); - else - router = batadv_find_ifalter_router(bat_priv, primary_orig_node, - recv_if); + /* remove references to first candidate, we don't need it. */ + if (first_candidate) { + batadv_neigh_node_free_ref(first_candidate_router); + batadv_orig_ifinfo_free_ref(first_candidate); + } + router = next_candidate_router; + orig_node->last_bonding_candidate = next_candidate; + } else if (first_candidate) { + batadv_neigh_node_free_ref(router); -return_router: - if (router && router->if_incoming->if_status != BATADV_IF_ACTIVE) - goto err_unlock; + /* refcounting has already been done in the loop above. */ + router = first_candidate_router; + orig_node->last_bonding_candidate = first_candidate; + } else { + orig_node->last_bonding_candidate = NULL; + } - rcu_read_unlock(); return router; -err_unlock: - rcu_read_unlock(); -err: - if (router) - batadv_neigh_node_free_ref(router); - return NULL; } static int batadv_route_unicast_packet(struct sk_buff *skb, diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index c1eadfa67945..557d3d12a9ab 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -23,6 +23,7 @@ bool batadv_check_management_packet(struct sk_buff *skb, int header_len); void batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if, struct batadv_neigh_node *neigh_node); int batadv_recv_icmp_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); @@ -43,16 +44,7 @@ int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb, struct batadv_neigh_node * batadv_find_router(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const struct batadv_hard_iface *recv_if); -void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node); -void batadv_bonding_candidate_add(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node); -void batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh_node, - const struct batadv_ogm_packet - *batman_ogm_packet); + struct batadv_hard_iface *recv_if); int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff, unsigned long *last_reset); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 30d12c445ea3..579f5f00a385 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -387,6 +387,8 @@ static void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet) kfree_skb(forw_packet->skb); if (forw_packet->if_incoming) batadv_hardif_free_ref(forw_packet->if_incoming); + if (forw_packet->if_outgoing) + batadv_hardif_free_ref(forw_packet->if_outgoing); kfree(forw_packet); } @@ -450,6 +452,7 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, forw_packet->skb = newskb; forw_packet->if_incoming = primary_if; + forw_packet->if_outgoing = NULL; /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; @@ -545,11 +548,16 @@ void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work) bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet); - /* we have to have at least one packet in the queue - * to determine the queues wake up time unless we are - * shutting down + /* we have to have at least one packet in the queue to determine the + * queues wake up time unless we are shutting down. + * + * only re-schedule if this is the "original" copy, e.g. the OGM of the + * primary interface should only be rescheduled once per period, but + * this function will be called for the forw_packet instances of the + * other secondary interfaces as well. */ - if (forw_packet->own) + if (forw_packet->own && + forw_packet->if_incoming == forw_packet->if_outgoing) batadv_schedule_bat_ogm(forw_packet->if_incoming); out: @@ -610,7 +618,8 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, * we delete only packets belonging to the given interface */ if ((hard_iface) && - (forw_packet->if_incoming != hard_iface)) + (forw_packet->if_incoming != hard_iface) && + (forw_packet->if_outgoing != hard_iface)) continue; spin_unlock_bh(&bat_priv->forw_bat_list_lock); diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 0b17f8d56f2e..aaddaa9661ce 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c50f64337f55..f82c267e1886 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -697,7 +697,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->gw.bandwidth_down, 100); atomic_set(&bat_priv->gw.bandwidth_up, 20); atomic_set(&bat_priv->orig_interval, 1000); - atomic_set(&bat_priv->hop_penalty, 30); + atomic_set(&bat_priv->hop_penalty, 15); #ifdef CONFIG_BATMAN_ADV_DEBUG atomic_set(&bat_priv->log_level, 0); #endif diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 4ab0167ac6ac..dbab22fd89a5 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index b6a4403b7007..e456bf6bb284 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index ed80b727dfd8..b715b60db7cd 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 63d25705cec6..a6fb1ff25f50 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -1400,12 +1400,14 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv, head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) { - router = batadv_orig_node_get_router(orig_entry->orig_node); + router = batadv_orig_router_get(orig_entry->orig_node, + BATADV_IF_DEFAULT); if (!router) continue; if (best_router && - bao->bat_neigh_cmp(router, best_router) <= 0) { + bao->bat_neigh_cmp(router, BATADV_IF_DEFAULT, + best_router, BATADV_IF_DEFAULT) <= 0) { batadv_neigh_node_free_ref(router); continue; } diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index daa8ab728f71..20a1d7861ded 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 0430a0474506..b53f90d85db9 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -84,6 +84,7 @@ struct batadv_hard_iface_bat_iv { * @rcu: struct used for freeing in an RCU-safe manner * @bat_iv: BATMAN IV specific per hard interface data * @cleanup_work: work queue callback item for hard interface deinit + * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs */ struct batadv_hard_iface { struct list_head list; @@ -98,6 +99,29 @@ struct batadv_hard_iface { struct rcu_head rcu; struct batadv_hard_iface_bat_iv bat_iv; struct work_struct cleanup_work; + struct dentry *debug_dir; +}; + +/** + * struct batadv_orig_ifinfo - originator info per outgoing interface + * @list: list node for orig_node::ifinfo_list + * @if_outgoing: pointer to outgoing hard interface + * @router: router that should be used to reach this originator + * @last_real_seqno: last and best known sequence number + * @last_ttl: ttl of last received packet + * @batman_seqno_reset: time when the batman seqno window was reset + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +struct batadv_orig_ifinfo { + struct hlist_node list; + struct batadv_hard_iface *if_outgoing; + struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ + uint32_t last_real_seqno; + uint8_t last_ttl; + unsigned long batman_seqno_reset; + atomic_t refcount; + struct rcu_head rcu; }; /** @@ -175,11 +199,11 @@ struct batadv_orig_bat_iv { * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh * @orig: originator ethernet address * @primary_addr: hosts primary interface address - * @router: router that should be used to reach this originator + * @ifinfo_list: list for routers per outgoing interface + * @last_bonding_candidate: pointer to last ifinfo of last used router * @batadv_dat_addr_t: address of the orig node in the distributed hash * @last_seen: time when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset - * @batman_seqno_reset: time when the batman seqno window was reset * @capabilities: announced capabilities of this originator * @last_ttvn: last seen translation table version number * @tt_buff: last tt changeset this node received from the orig node @@ -192,19 +216,15 @@ struct batadv_orig_bat_iv { * made up by two operations (data structure update and metdata -CRC/TTVN- * recalculation) and they have to be executed atomically in order to avoid * another thread to read the table/metadata between those. - * @last_real_seqno: last and best known sequence number - * @last_ttl: ttl of last received packet * @bcast_bits: bitfield containing the info which payload broadcast originated * from this orig node this host already has seen (relative to * last_bcast_seqno) * @last_bcast_seqno: last broadcast sequence number received by this host * @neigh_list: list of potential next hop neighbor towards this orig node - * @neigh_list_lock: lock protecting neigh_list, router and bonding_list + * @neigh_list_lock: lock protecting neigh_list and router * @hash_entry: hlist node for batadv_priv::orig_hash * @bat_priv: pointer to soft_iface this orig node belongs to * @bcast_seqno_lock: lock protecting bcast_bits & last_bcast_seqno - * @bond_candidates: how many candidates are available - * @bond_list: list of bonding candidates * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner * @in_coding_list: list of nodes this orig can hear @@ -220,13 +240,13 @@ struct batadv_orig_bat_iv { struct batadv_orig_node { uint8_t orig[ETH_ALEN]; uint8_t primary_addr[ETH_ALEN]; - struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ + struct hlist_head ifinfo_list; + struct batadv_orig_ifinfo *last_bonding_candidate; #ifdef CONFIG_BATMAN_ADV_DAT batadv_dat_addr_t dat_addr; #endif unsigned long last_seen; unsigned long bcast_seqno_reset; - unsigned long batman_seqno_reset; uint8_t capabilities; atomic_t last_ttvn; unsigned char *tt_buff; @@ -235,19 +255,15 @@ struct batadv_orig_node { bool tt_initialised; /* prevents from changing the table while reading it */ spinlock_t tt_lock; - uint32_t last_real_seqno; - uint8_t last_ttl; DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); uint32_t last_bcast_seqno; struct hlist_head neigh_list; - /* neigh_list_lock protects: neigh_list, router & bonding_list */ + /* neigh_list_lock protects: neigh_list and router */ spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; /* bcast_seqno_lock protects: bcast_bits & last_bcast_seqno */ spinlock_t bcast_seqno_lock; - atomic_t bond_candidates; - struct list_head bond_list; atomic_t refcount; struct rcu_head rcu; #ifdef CONFIG_BATMAN_ADV_NC @@ -293,49 +309,62 @@ struct batadv_gw_node { }; /** - * struct batadv_neigh_bat_iv - B.A.T.M.A.N. IV specific structure for single - * hop neighbors + * struct batadv_neigh_node - structure for single hops neighbors + * @list: list node for batadv_orig_node::neigh_list + * @orig_node: pointer to corresponding orig_node + * @addr: the MAC address of the neighboring interface + * @ifinfo_list: list for routing metrics per outgoing interface + * @ifinfo_lock: lock protecting private ifinfo members and list + * @if_incoming: pointer to incoming hard interface + * @last_seen: when last packet via this neighbor was received + * @last_ttl: last received ttl from this neigh node + * @rcu: struct used for freeing in an RCU-safe manner + * @bat_iv: B.A.T.M.A.N. IV private structure + */ +struct batadv_neigh_node { + struct hlist_node list; + struct batadv_orig_node *orig_node; + uint8_t addr[ETH_ALEN]; + struct hlist_head ifinfo_list; + spinlock_t ifinfo_lock; /* protects ifinfo_list and its members */ + struct batadv_hard_iface *if_incoming; + unsigned long last_seen; + atomic_t refcount; + struct rcu_head rcu; +}; + +/* struct batadv_neigh_node_bat_iv - neighbor information per outgoing + * interface for BATMAN IV * @tq_recv: ring buffer of received TQ values from this neigh node * @tq_index: ring buffer index * @tq_avg: averaged tq of all tq values in the ring buffer (tq_recv) * @real_bits: bitfield containing the number of OGMs received from this neigh * node (relative to orig_node->last_real_seqno) * @real_packet_count: counted result of real_bits - * @lq_update_lock: lock protecting tq_recv & tq_index */ -struct batadv_neigh_bat_iv { +struct batadv_neigh_ifinfo_bat_iv { uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; uint8_t tq_index; uint8_t tq_avg; DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); uint8_t real_packet_count; - spinlock_t lq_update_lock; /* protects tq_recv & tq_index */ }; -/** - * struct batadv_neigh_node - structure for single hops neighbors - * @list: list node for batadv_orig_node::neigh_list - * @orig_node: pointer to corresponding orig_node - * @addr: the MAC address of the neighboring interface - * @if_incoming: pointer to incoming hard interface - * @last_seen: when last packet via this neighbor was received +/* struct batadv_neigh_ifinfo - neighbor information per outgoing interface + * @list: list node for batadv_neigh_node::ifinfo_list + * @if_outgoing: pointer to outgoing hard interface + * @bat_iv: B.A.T.M.A.N. IV private structure * @last_ttl: last received ttl from this neigh node - * @bonding_list: list node for batadv_orig_node::bond_list * @refcount: number of contexts the object is used - * @rcu: struct used for freeing in an RCU-safe manner - * @bat_iv: B.A.T.M.A.N. IV private structure + * @rcu: struct used for freeing in a RCU-safe manner */ -struct batadv_neigh_node { +struct batadv_neigh_ifinfo { struct hlist_node list; - struct batadv_orig_node *orig_node; - uint8_t addr[ETH_ALEN]; - struct batadv_hard_iface *if_incoming; - unsigned long last_seen; + struct batadv_hard_iface *if_outgoing; + struct batadv_neigh_ifinfo_bat_iv bat_iv; uint8_t last_ttl; - struct list_head bonding_list; atomic_t refcount; struct rcu_head rcu; - struct batadv_neigh_bat_iv bat_iv; }; /** @@ -993,8 +1022,10 @@ struct batadv_skb_cb { * @direct_link_flags: direct link flags for aggregated OGM packets * @num_packets: counter for bcast packet retransmission * @delayed_work: work queue callback item for packet sending - * @if_incoming: pointer incoming hard-iface or primary iface if locally - * generated packet + * @if_incoming: pointer to incoming hard-iface or primary iface if + * locally generated packet + * @if_outgoing: packet where the packet should be sent to, or NULL if + * unspecified */ struct batadv_forw_packet { struct hlist_node list; @@ -1006,6 +1037,7 @@ struct batadv_forw_packet { uint8_t num_packets; struct delayed_work delayed_work; struct batadv_hard_iface *if_incoming; + struct batadv_hard_iface *if_outgoing; }; /** @@ -1019,9 +1051,11 @@ struct batadv_forw_packet { * @bat_primary_iface_set: called when primary interface is selected / changed * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue * @bat_ogm_emit: send scheduled OGM - * @bat_neigh_cmp: compare the metrics of two neighbors - * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or - * better than neigh2 from the metric prospective + * @bat_neigh_cmp: compare the metrics of two neighbors for their respective + * outgoing interfaces + * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or better + * than neigh2 for their respective outgoing interface from the metric + * prospective * @bat_orig_print: print the originator table (optional) * @bat_orig_free: free the resources allocated by the routing algorithm for an * orig_node object @@ -1040,11 +1074,17 @@ struct batadv_algo_ops { void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2); - bool (*bat_neigh_is_equiv_or_better)(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2); + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2); + bool (*bat_neigh_is_equiv_or_better) + (struct batadv_neigh_node *neigh1, + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2); /* orig_node handling API */ - void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq); + void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq, + struct batadv_hard_iface *hard_iface); void (*bat_orig_free)(struct batadv_orig_node *orig_node); int (*bat_orig_add_if)(struct batadv_orig_node *orig_node, int max_if_num); diff --git a/net/bridge/br.c b/net/bridge/br.c index ba780cc8e515..19311aafcf5a 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -22,14 +22,29 @@ #include "br_private.h" -static const struct stp_proto br_stp_proto = { - .rcv = br_stp_rcv, -}; +static void __net_exit br_net_exit(struct net *net) +{ + struct net_device *dev; + LIST_HEAD(list); + + rtnl_lock(); + for_each_netdev(net, dev) + if (dev->priv_flags & IFF_EBRIDGE) + br_dev_delete(dev, &list); + + unregister_netdevice_many(&list); + rtnl_unlock(); + +} static struct pernet_operations br_net_ops = { .exit = br_net_exit, }; +static const struct stp_proto br_stp_proto = { + .rcv = br_stp_rcv, +}; + static int __init br_init(void) { int err; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 1f6bd1e2e8a4..cffe1d666ba1 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -455,18 +455,3 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) return 0; } - -void __net_exit br_net_exit(struct net *net) -{ - struct net_device *dev; - LIST_HEAD(list); - - rtnl_lock(); - for_each_netdev(net, dev) - if (dev->priv_flags & IFF_EBRIDGE) - br_dev_delete(dev, &list); - - unregister_netdevice_many(&list); - rtnl_unlock(); - -} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3733f152351c..fcd12333c59b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -407,7 +407,6 @@ void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, void br_port_carrier_check(struct net_bridge_port *p); int br_add_bridge(struct net *net, const char *name); int br_del_bridge(struct net *net, const char *name); -void br_net_exit(struct net *net); int br_add_if(struct net_bridge *br, struct net_device *dev); int br_del_if(struct net_bridge *br, struct net_device *dev); int br_min_mtu(const struct net_bridge *br); diff --git a/net/core/dev.c b/net/core/dev.c index ce01847793c0..20c834e3c7ca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -147,6 +147,8 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ static struct list_head offload_base __read_mostly; +static int netif_rx_internal(struct sk_buff *skb); + /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. @@ -1698,7 +1700,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_scrub_packet(skb, true); skb->protocol = eth_type_trans(skb, dev); - return netif_rx(skb); + return netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -2530,7 +2532,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) EXPORT_SYMBOL(netif_skb_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq, void *accel_priv) + struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; int rc = NETDEV_TX_OK; @@ -2596,13 +2598,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); skb_len = skb->len; - if (accel_priv) - rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv); - else - rc = ops->ndo_start_xmit(skb, dev); - + trace_net_dev_start_xmit(skb, dev); + rc = ops->ndo_start_xmit(skb, dev); trace_net_dev_xmit(skb, rc, dev, skb_len); - if (rc == NETDEV_TX_OK && txq) + if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; } @@ -2618,10 +2617,8 @@ gso: dev_queue_xmit_nit(nskb, dev); skb_len = nskb->len; - if (accel_priv) - rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv); - else - rc = ops->ndo_start_xmit(nskb, dev); + trace_net_dev_start_xmit(nskb, dev); + rc = ops->ndo_start_xmit(nskb, dev); trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) @@ -2802,7 +2799,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -int dev_queue_xmit(struct sk_buff *skb) +int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -2818,7 +2815,7 @@ int dev_queue_xmit(struct sk_buff *skb) skb_update_prio(skb); - txq = netdev_pick_tx(dev, skb); + txq = netdev_pick_tx(dev, skb, accel_priv); q = rcu_dereference_bh(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT @@ -2854,7 +2851,7 @@ int dev_queue_xmit(struct sk_buff *skb) if (!netif_xmit_stopped(txq)) { __this_cpu_inc(xmit_recursion); - rc = dev_hard_start_xmit(skb, dev, txq, NULL); + rc = dev_hard_start_xmit(skb, dev, txq); __this_cpu_dec(xmit_recursion); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); @@ -2883,8 +2880,19 @@ out: rcu_read_unlock_bh(); return rc; } + +int dev_queue_xmit(struct sk_buff *skb) +{ + return __dev_queue_xmit(skb, NULL); +} EXPORT_SYMBOL(dev_queue_xmit); +int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) +{ + return __dev_queue_xmit(skb, accel_priv); +} +EXPORT_SYMBOL(dev_queue_xmit_accel); + /*======================================================================= Receiver routines @@ -3213,22 +3221,7 @@ enqueue: return NET_RX_DROP; } -/** - * netif_rx - post buffer to the network code - * @skb: buffer to post - * - * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. - * - * return values: - * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) - * - */ - -int netif_rx(struct sk_buff *skb) +static int netif_rx_internal(struct sk_buff *skb) { int ret; @@ -3264,14 +3257,38 @@ int netif_rx(struct sk_buff *skb) } return ret; } + +/** + * netif_rx - post buffer to the network code + * @skb: buffer to post + * + * This function receives a packet from a device driver and queues it for + * the upper (protocol) levels to process. It always succeeds. The buffer + * may be dropped during processing for congestion control or by the + * protocol layers. + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + */ + +int netif_rx(struct sk_buff *skb) +{ + trace_netif_rx_entry(skb); + + return netif_rx_internal(skb); +} EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { int err; + trace_netif_rx_ni_entry(skb); + preempt_disable(); - err = netif_rx(skb); + err = netif_rx_internal(skb); if (local_softirq_pending()) do_softirq(); preempt_enable(); @@ -3656,22 +3673,7 @@ static int __netif_receive_skb(struct sk_buff *skb) return ret; } -/** - * netif_receive_skb - process receive buffer from network - * @skb: buffer to process - * - * netif_receive_skb() is the main receive data processing function. - * It always succeeds. The buffer may be dropped during processing - * for congestion control or by the protocol layers. - * - * This function may only be called from softirq context and interrupts - * should be enabled. - * - * Return values (usually ignored): - * NET_RX_SUCCESS: no congestion - * NET_RX_DROP: packet was dropped - */ -int netif_receive_skb(struct sk_buff *skb) +static int netif_receive_skb_internal(struct sk_buff *skb) { net_timestamp_check(netdev_tstamp_prequeue, skb); @@ -3697,6 +3699,28 @@ int netif_receive_skb(struct sk_buff *skb) #endif return __netif_receive_skb(skb); } + +/** + * netif_receive_skb - process receive buffer from network + * @skb: buffer to process + * + * netif_receive_skb() is the main receive data processing function. + * It always succeeds. The buffer may be dropped during processing + * for congestion control or by the protocol layers. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb(struct sk_buff *skb) +{ + trace_netif_receive_skb_entry(skb); + + return netif_receive_skb_internal(skb); +} EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending @@ -3758,7 +3782,7 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb(skb); + return netif_receive_skb_internal(skb); } /* napi->gro_list contains packets ordered by age. @@ -3882,10 +3906,23 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) + if (NAPI_GRO_CB(skb)->flush) goto normal; - napi->gro_count++; + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_count++; + } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; skb_shinfo(skb)->gso_size = skb_gro_len(skb); @@ -3953,7 +3990,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -3978,6 +4015,8 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { + trace_napi_gro_receive_entry(skb); + return napi_skb_finish(dev_gro_receive(napi, skb), skb); } EXPORT_SYMBOL(napi_gro_receive); @@ -4011,7 +4050,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -4050,6 +4089,8 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) if (!skb) return GRO_DROP; + trace_napi_gro_frags_entry(skb); + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); @@ -5287,6 +5328,17 @@ int dev_change_flags(struct net_device *dev, unsigned int flags) } EXPORT_SYMBOL(dev_change_flags); +static int __dev_set_mtu(struct net_device *dev, int new_mtu) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_change_mtu) + return ops->ndo_change_mtu(dev, new_mtu); + + dev->mtu = new_mtu; + return 0; +} + /** * dev_set_mtu - Change maximum transfer unit * @dev: device @@ -5296,8 +5348,7 @@ EXPORT_SYMBOL(dev_change_flags); */ int dev_set_mtu(struct net_device *dev, int new_mtu) { - const struct net_device_ops *ops = dev->netdev_ops; - int err; + int err, orig_mtu; if (new_mtu == dev->mtu) return 0; @@ -5309,14 +5360,20 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; - err = 0; - if (ops->ndo_change_mtu) - err = ops->ndo_change_mtu(dev, new_mtu); - else - dev->mtu = new_mtu; + orig_mtu = dev->mtu; + err = __dev_set_mtu(dev, new_mtu); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + if (!err) { + err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) { + /* setting mtu back and notifying everyone again, + * so that they have a chance to revert changes. + */ + __dev_set_mtu(dev, orig_mtu); + call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + } + } return err; } EXPORT_SYMBOL(dev_set_mtu); @@ -6586,11 +6643,11 @@ static int dev_cpu_callback(struct notifier_block *nfb, /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b324bfa3485c..87577d447554 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -395,17 +395,21 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + void *accel_priv) { int queue_index = 0; if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb); + queue_index = ops->ndo_select_queue(dev, skb, + accel_priv); else queue_index = __netdev_pick_tx(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); + + if (!accel_priv) + queue_index = dev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ea97361f0e9b..e360d9e65c04 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -117,7 +117,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (net_random() % base) + (base >> 1) : 0; + return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -1415,7 +1415,8 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % + + unsigned long sched_next = now + (prandom_u32() % NEIGH_VAR(p, PROXY_DELAY)); if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 303097874633..19fe9c717ced 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -375,7 +375,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { struct netdev_queue *txq; - txq = netdev_pick_tx(dev, skb); + txq = netdev_pick_tx(dev, skb, NULL); /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a797fff7f222..fa3e128eb5e9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -389,6 +389,9 @@ struct pktgen_dev { #ifdef CONFIG_XFRM __u8 ipsmode; /* IPSEC mode (config) */ __u8 ipsproto; /* IPSEC type (config) */ + __u32 spi; + struct dst_entry dst; + struct dst_ops dstops; #endif char result[512]; }; @@ -654,8 +657,11 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } #ifdef CONFIG_XFRM - if (pkt_dev->flags & F_IPSEC_ON) + if (pkt_dev->flags & F_IPSEC_ON) { seq_printf(seq, "IPSEC "); + if (pkt_dev->spi) + seq_printf(seq, "spi:%u", pkt_dev->spi); + } #endif if (pkt_dev->flags & F_MACSRC_RND) @@ -1476,7 +1482,18 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows); return count; } +#ifdef CONFIG_XFRM + if (!strcmp(name, "spi")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + i += len; + pkt_dev->spi = value; + sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); + return count; + } +#endif if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); if (len < 0) @@ -2233,13 +2250,21 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) struct xfrm_state *x = pkt_dev->flows[flow].x; struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { - /*slow path: we dont already have xfrm_state*/ - x = xfrm_stateonly_find(pn->net, DUMMY_MARK, - (xfrm_address_t *)&pkt_dev->cur_daddr, - (xfrm_address_t *)&pkt_dev->cur_saddr, - AF_INET, - pkt_dev->ipsmode, - pkt_dev->ipsproto, 0); + + if (pkt_dev->spi) { + /* We need as quick as possible to find the right SA + * Searching with minimum criteria to archieve this. + */ + x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); + } else { + /* slow path: we dont already have xfrm_state */ + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + (xfrm_address_t *)&pkt_dev->cur_daddr, + (xfrm_address_t *)&pkt_dev->cur_saddr, + AF_INET, + pkt_dev->ipsmode, + pkt_dev->ipsproto, 0); + } if (x) { pkt_dev->flows[flow].x = x; set_pkt_overhead(pkt_dev); @@ -2475,31 +2500,47 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) #ifdef CONFIG_XFRM +static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { + + [RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */ +}; + static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int err = 0; + struct net *net = dev_net(pkt_dev->odev); if (!x) return 0; /* XXX: we dont support tunnel mode for now until * we resolve the dst issue */ - if (x->props.mode != XFRM_MODE_TRANSPORT) + if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0)) return 0; - spin_lock(&x->lock); + /* But when user specify an valid SPI, transformation + * supports both transport/tunnel mode + ESP/AH type. + */ + if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0)) + skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF; + rcu_read_lock_bh(); err = x->outer_mode->output(x, skb); - if (err) + rcu_read_unlock_bh(); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error; + } err = x->type->output(x, skb); - if (err) + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error; - + } + spin_lock_bh(&x->lock); x->curlft.bytes += skb->len; x->curlft.packets++; + spin_unlock_bh(&x->lock); error: - spin_unlock(&x->lock); return err; } @@ -3542,6 +3583,17 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) #ifdef CONFIG_XFRM pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; + + /* xfrm tunnel mode needs additional dst to extract outter + * ip header protocol/ttl/id field, here creat a phony one. + * instead of looking for a valid rt, which definitely hurting + * performance under such circumstance. + */ + pkt_dev->dstops.family = AF_INET; + pkt_dev->dst.dev = pkt_dev->odev; + dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false); + pkt_dev->dst.child = &pkt_dev->dst; + pkt_dev->dst.ops = &pkt_dev->dstops; #endif return add_dev_to_thread(t, pkt_dev); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d641e781f85..15057d29b010 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -65,6 +65,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/ip6_checksum.h> #include <net/xfrm.h> #include <asm/uaccess.h> @@ -3549,6 +3550,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) } EXPORT_SYMBOL_GPL(skb_partial_csum_set); +static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) +{ + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + +static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) +{ + unsigned int off; + bool fragment; + int err; + + fragment = false; + + err = skb_maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + goto out; + + switch (ip_hdr(skb)->protocol) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; + + if (!done || fragment) + goto out; + + switch (nexthdr) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/** + * skb_checksum_setup - set up partial checksum offset + * @skb: the skb to set up + * @recalculate: if true the pseudo-header checksum will be recalculated + */ +int skb_checksum_setup(struct sk_buff *skb, bool recalculate) +{ + int err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + err = skb_checksum_setup_ip(skb, recalculate); + break; + + case htons(ETH_P_IPV6): + err = skb_checksum_setup_ipv6(skb, recalculate); + break; + + default: + err = -EPROTO; + break; + } + + return err; +} +EXPORT_SYMBOL(skb_checksum_setup); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", diff --git a/net/core/stream.c b/net/core/stream.c index 512f0a24269b..301c05f26060 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -122,7 +122,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2; + current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 88299c29101d..22b5d818b200 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -989,6 +989,7 @@ static const struct net_protocol dccp_v4_protocol = { .err_handler = dccp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; static const struct proto_ops inet_dccp_ops = { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6268a4751e64..ecd2c3f245ce 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1545,6 +1545,7 @@ static const struct net_protocol tcp_protocol = { .err_handler = tcp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; static const struct net_protocol udp_protocol = { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 9809f7b69728..646023bd5449 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -464,7 +464,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { - net_srandom(ifa->ifa_local); + prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 746a7b10d434..29512e3e7e7c 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -26,7 +26,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, { struct sk_buff *segs = ERR_PTR(-EINVAL); netdev_features_t enc_features; - int ghl = GRE_HEADER_SECTION; + int ghl; struct gre_base_hdr *greh; u16 mac_offset = skb->mac_header; int mac_len = skb->mac_len; @@ -49,15 +49,11 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); - if (greh->flags & GRE_KEY) - ghl += GRE_HEADER_SECTION; - if (greh->flags & GRE_SEQ) - ghl += GRE_HEADER_SECTION; - if (greh->flags & GRE_CSUM) { - ghl += GRE_HEADER_SECTION; - csum = true; - } else - csum = false; + ghl = skb_inner_network_header(skb) - skb_transport_header(skb); + if (unlikely(ghl < sizeof(*greh))) + goto out; + + csum = !!(greh->flags & GRE_CSUM); if (unlikely(!pskb_may_pull(skb, ghl))) goto out; @@ -250,7 +246,7 @@ out: return pp; } -int gre_gro_complete(struct sk_buff *skb, int nhoff) +static int gre_gro_complete(struct sk_buff *skb, int nhoff) { struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff); struct packet_offload *ptype; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index fb3c5637199d..0134663fdbce 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -668,6 +668,16 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) rcu_read_unlock(); } +static bool icmp_tag_validation(int proto) +{ + bool ok; + + rcu_read_lock(); + ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation; + rcu_read_unlock(); + return ok; +} + /* * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. @@ -705,12 +715,22 @@ static void icmp_unreach(struct sk_buff *skb) case ICMP_PORT_UNREACH: break; case ICMP_FRAG_NEEDED: - if (net->ipv4.sysctl_ip_no_pmtu_disc == 2) { - goto out; - } else if (net->ipv4.sysctl_ip_no_pmtu_disc) { + /* for documentation of the ip_no_pmtu_disc + * values please see + * Documentation/networking/ip-sysctl.txt + */ + switch (net->ipv4.sysctl_ip_no_pmtu_disc) { + default: LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), &iph->daddr); - } else { + break; + case 2: + goto out; + case 3: + if (!icmp_tag_validation(iph->protocol)) + goto out; + /* fall through */ + case 0: info = ntohs(icmph->un.frag.mtu); if (!info) goto out; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 84c4329cbd30..97e4d1655d26 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -211,7 +211,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = net_random() % max_delay; + int tv = prandom_u32() % max_delay; im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -220,7 +220,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = net_random() % in_dev->mr_maxdelay; + int tv = prandom_u32() % in_dev->mr_maxdelay; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2)) @@ -229,7 +229,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = net_random() % delay; + int tv = prandom_u32() % delay; if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); @@ -2762,6 +2762,7 @@ static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; +#endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) @@ -2785,8 +2786,9 @@ static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; -int __init igmp_mc_proc_init(void) +int __init igmp_mc_init(void) { +#if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); @@ -2800,5 +2802,7 @@ int __init igmp_mc_proc_init(void) reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; -} +#else + return register_netdevice_notifier(&igmp_notifier); #endif +} diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fc0e649cc002..0d1e2cb877ec 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -109,7 +109,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) again: inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - smallest_rover = rover = net_random() % remaining + low; + smallest_rover = rover = prandom_u32() % remaining + low; smallest_size = -1; do { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a0f52dac8940..e34dccbc4d70 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -930,12 +930,15 @@ skip_listen_ht: spin_lock_bh(lock); sk_nulls_for_each(sk, node, &head->chain) { int res; + int state; if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next_normal; - if (!(r->idiag_states & (1 << sk->sk_state))) + state = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_substate : sk->sk_state; + if (!(r->idiag_states & (1 << state))) goto next_normal; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 694de3b7aebf..e9f1217a8afd 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -54,6 +54,7 @@ static int ip_forward_finish(struct sk_buff *skb) int ip_forward(struct sk_buff *skb) { + u32 mtu; struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); @@ -88,11 +89,13 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && + IPCB(skb)->flags |= IPSKB_FORWARDED; + mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); + if (unlikely(skb->len > mtu && !skb_is_gso(skb) && (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(dst_mtu(&rt->dst))); + htonl(mtu)); goto drop; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index df184616493f..8971780aec7c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -449,6 +449,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); int err = 0; + bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; dev = rt->dst.dev; @@ -458,12 +459,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); + mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || (IPCB(skb)->frag_max_size && - IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) { + IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(ip_skb_dst_mtu(skb))); + htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } @@ -473,7 +475,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) */ hlen = iph->ihl * 4; - mtu = dst_mtu(&rt->dst) - hlen; /* Size of data space */ + mtu = mtu - hlen; /* Size of data space */ #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge) mtu -= nf_bridge_mtu_reduction(skb); @@ -1551,7 +1553,7 @@ void __init ip_init(void) ip_rt_init(); inet_initpeers(); -#if defined(CONFIG_IP_MULTICAST) && defined(CONFIG_PROC_FS) - igmp_mc_proc_init(); +#if defined(CONFIG_IP_MULTICAST) + igmp_mc_init(); #endif } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f8da28278014..25071b48921c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,9 +112,6 @@ #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) -/* IPv4 datagram length is stored into 16bit field (tot_len) */ -#define IP_MAX_MTU 0xFFFF - #define RT_GC_TIMEOUT (300*HZ) static int ip_rt_max_size; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1d2480ac2bb6..44eba052b43d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -831,6 +831,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_forward_use_pmtu", + .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { } }; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 80f649fbee63..3d3141fd0580 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -223,7 +223,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rand = net_random(); + rand = prandom_u32(); first = (((u64)rand * remaining) >> 32) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a9fa6c1feed5..5329cccf55dc 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2529,7 +2529,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, struct inet6_ifaddr *ifp; ifp = ipv6_add_addr(idev, addr, NULL, plen, - scope, IFA_F_PERMANENT, 0, 0); + scope, IFA_F_PERMANENT, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -2657,7 +2658,8 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr #endif - ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, 0, 0); + ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); addrconf_dad_start(ifp); @@ -3102,7 +3104,7 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); + rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); ifp->dad_probes = idev->cnf.dad_transmits; addrconf_mod_dad_timer(ifp, rand_num); @@ -3115,7 +3117,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp) addrconf_join_solict(dev, &ifp->addr); - net_srandom(ifp->addr.s6_addr32[3]); + prandom_seed((__force u32) ifp->addr.s6_addr32[3]); read_lock_bh(&idev->lock); spin_lock(&ifp->lock); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 9a809a4b3d86..8003b4930267 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -67,6 +67,7 @@ #include <net/icmp.h> #include <net/xfrm.h> #include <net/inet_common.h> +#include <net/dsfield.h> #include <asm/uaccess.h> @@ -553,6 +554,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct dst_entry *dst; int err = 0; int hlimit; + u8 tclass; saddr = &ipv6_hdr(skb)->daddr; @@ -603,8 +605,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.offset = 0; msg.type = ICMPV6_ECHO_REPLY; + tclass = ipv6_get_dsfield(ipv6_hdr(skb)); err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6, + sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index e7fb7106550f..cbc93517b455 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -210,7 +210,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { - fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK; + fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (lfl == NULL) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d1de9560c421..ef02b26ccf81 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -321,6 +321,27 @@ static inline int ip6_forward_finish(struct sk_buff *skb) return dst_output(skb); } +static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) +{ + unsigned int mtu; + struct inet6_dev *idev; + + if (dst_metric_locked(dst, RTAX_MTU)) { + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + } + + mtu = IPV6_MIN_MTU; + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); + if (idev) + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + + return mtu; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -441,7 +462,7 @@ int ip6_forward(struct sk_buff *skb) } } - mtu = dst_mtu(dst); + mtu = ip6_dst_mtu_forward(dst); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index b50acd5e75d2..2d19272b8cee 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -731,12 +731,18 @@ static void vti6_dev_setup(struct net_device *dev) static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + int i; t->dev = dev; t->net = dev_net(dev); dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + for_each_possible_cpu(i) { + struct pcpu_sw_netstats *stats; + stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&stats->syncp); + } return 0; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d18f9f903db6..7ff82b3e54b6 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -999,7 +999,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, static void mld_gq_start_timer(struct inet6_dev *idev) { - unsigned long tv = net_random() % idev->mc_maxdelay; + unsigned long tv = prandom_u32() % idev->mc_maxdelay; idev->mc_gq_running = 1; if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2)) @@ -1015,7 +1015,7 @@ static void mld_gq_stop_timer(struct inet6_dev *idev) static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = net_random() % delay; + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1030,7 +1030,7 @@ static void mld_ifc_stop_timer(struct inet6_dev *idev) static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = net_random() % delay; + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1061,7 +1061,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) } if (delay >= resptime) - delay = net_random() % resptime; + delay = prandom_u32() % resptime; ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) @@ -2328,7 +2328,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = net_random() % unsolicited_report_interval(ma->idev); + delay = prandom_u32() % unsolicited_report_interval(ma->idev); spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 9af77d9c0ec9..735d0f60c83a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -176,7 +176,7 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) * owned by userspace. A struct sock returned from this function must be * released using l2tp_tunnel_sock_put once you're done with it. */ -struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) +static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) { int err = 0; struct socket *sock = NULL; @@ -202,10 +202,9 @@ struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) out: return sk; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup); /* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ -void l2tp_tunnel_sock_put(struct sock *sk) +static void l2tp_tunnel_sock_put(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); if (tunnel) { @@ -217,7 +216,6 @@ void l2tp_tunnel_sock_put(struct sock *sk) } sock_put(sk); } -EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); /* Lookup a session by id in the global session list */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 1ee9f6965d68..1f01ba3435bc 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -238,8 +238,6 @@ out: return tunnel; } -struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel); -void l2tp_tunnel_sock_put(struct sock *sk); struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b2c83c0f06d0..3dfd20a453ab 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1045,7 +1045,8 @@ static void ieee80211_uninit(struct net_device *dev) } static u16 ieee80211_netdev_select_queue(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + void *accel_priv) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1062,7 +1063,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { }; static u16 ieee80211_monitor_select_queue(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + void *accel_priv) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 377cf974d97d..ef3555e16cf9 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -464,7 +464,6 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) { struct sta_info *sta = tx->sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_local *local = tx->local; if (unlikely(!sta)) @@ -475,15 +474,6 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) { int ac = skb_get_queue_mapping(tx->skb); - /* only deauth, disassoc and action are bufferable MMPDUs */ - if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_deauth(hdr->frame_control) && - !ieee80211_is_disassoc(hdr->frame_control) && - !ieee80211_is_action(hdr->frame_control)) { - info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; - return TX_CONTINUE; - } - ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n", sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) @@ -526,9 +516,22 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; + if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; + /* only deauth, disassoc and action are bufferable MMPDUs */ + if (ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_is_deauth(hdr->frame_control) && + !ieee80211_is_disassoc(hdr->frame_control) && + !ieee80211_is_action(hdr->frame_control)) { + if (tx->flags & IEEE80211_TX_UNICAST) + info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; + return TX_CONTINUE; + } + if (tx->flags & IEEE80211_TX_UNICAST) return ieee80211_tx_h_unicast_ps_buf(tx); else diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4c8e5c0aa1ab..59a1a85bcb3e 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1209,7 +1209,7 @@ void ip_vs_random_dropentry(struct net *net) * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { - unsigned int hash = net_random() & ip_vs_conn_tab_mask; + unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask; hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index b2d38da67822..f6e2ae91a80b 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -37,7 +37,7 @@ int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, return 0; if (unlikely(!seqadj)) { - WARN(1, "Wrong seqadj usage, missing nfct_seqadj_ext_add()\n"); + WARN_ONCE(1, "Missing nfct_seqadj_ext_add() setup call\n"); return 0; } diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index f02b3605823e..1fb2258c3535 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -34,10 +34,14 @@ static unsigned int help(struct sk_buff *skb, struct nf_conntrack_expect *exp) { char buffer[sizeof("4294967296 65635")]; + struct nf_conn *ct = exp->master; + union nf_inet_addr newaddr; u_int16_t port; unsigned int ret; /* Reply comes from server. */ + newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3; + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; @@ -57,17 +61,35 @@ static unsigned int help(struct sk_buff *skb, } if (port == 0) { - nf_ct_helper_log(skb, exp->master, "all ports in use"); + nf_ct_helper_log(skb, ct, "all ports in use"); return NF_DROP; } - ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, - protoff, matchoff, matchlen, buffer, - strlen(buffer)); + /* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27 + * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28 + * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26 + * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26 + * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27 + * + * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits, + * 255.255.255.255==4294967296, 10 digits) + * P: bound port (min 1 d, max 5d (65635)) + * F: filename (min 1 d ) + * S: size (min 1 d ) + * 0x01, \n: terminators + */ + /* AAA = "us", ie. where server normally talks to. */ + snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port); + pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n", + buffer, &newaddr.ip, port); + + ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, + matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) { - nf_ct_helper_log(skb, exp->master, "cannot mangle packet"); + nf_ct_helper_log(skb, ct, "cannot mangle packet"); nf_ct_unexpect_related(exp); } + return ret; } diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index 4fe4fb4276d0..11de55e7a868 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -37,7 +37,7 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par) switch (info->mode) { case XT_STATISTIC_MODE_RANDOM: - if ((net_random() & 0x7FFFFFFF) < info->u.random.probability) + if ((prandom_u32() & 0x7FFFFFFF) < info->u.random.probability) ret = !ret; break; case XT_STATISTIC_MODE_NTH: diff --git a/net/nfc/core.c b/net/nfc/core.c index 02ab34132157..b675fa4a6f19 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -382,7 +382,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, { dev->dep_link_up = true; - if (!dev->active_target) { + if (!dev->active_target && rf_mode == NFC_RF_INITIATOR) { struct nfc_target *target; target = nfc_find_target(dev, target_idx); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 716b7eebfe70..2c77e7b1a913 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -445,7 +445,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { switch (nla_type(a)) { case OVS_SAMPLE_ATTR_PROBABILITY: - if (net_random() >= nla_get_u32(a)) + if (prandom_u32() >= nla_get_u32(a)) return 0; break; diff --git a/net/rds/bind.c b/net/rds/bind.c index b5ad65a0067e..a2e6562da751 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -117,7 +117,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) rover = be16_to_cpu(*port); last = rover; } else { - rover = max_t(u16, net_random(), 2); + rover = max_t(u16, prandom_u32(), 2); last = rover - 1; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f63e1467cd3a..35f89e9ce49c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -173,16 +173,16 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) } EXPORT_SYMBOL(tcf_hash_lookup); -u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo) +u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo) { - u32 val = *idx_gen; + u32 val = hinfo->index; do { if (++val == 0) val = 1; } while (tcf_hash_lookup(val, hinfo)); - *idx_gen = val; + hinfo->index = val; return val; } EXPORT_SYMBOL(tcf_hash_new_index); @@ -215,7 +215,7 @@ EXPORT_SYMBOL(tcf_hash_check); struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, int size, int bind, - u32 *idx_gen, struct tcf_hashinfo *hinfo) + struct tcf_hashinfo *hinfo) { struct tcf_common *p = kzalloc(size, GFP_KERNEL); @@ -227,7 +227,7 @@ struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, spin_lock_init(&p->tcfc_lock); INIT_HLIST_NODE(&p->tcfc_head); - p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo); + p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { @@ -556,9 +556,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, { int err = 0; struct gnet_dump d; - struct tcf_act_hdr *h = a->priv; + struct tcf_common *p = a->priv; - if (h == NULL) + if (p == NULL) goto errout; /* compat_mode being true specifies a call that is supposed @@ -567,20 +567,20 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (compat_mode) { if (a->type == TCA_OLD_COMPAT) err = gnet_stats_start_copy_compat(skb, 0, - TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d); + TCA_STATS, TCA_XSTATS, &p->tcfc_lock, &d); else return 0; } else err = gnet_stats_start_copy(skb, TCA_ACT_STATS, - &h->tcf_lock, &d); + &p->tcfc_lock, &d); if (err < 0) goto errout; - if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 || - gnet_stats_copy_rate_est(&d, &h->tcf_bstats, - &h->tcf_rate_est) < 0 || - gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0) + if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 || + gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, + &p->tcfc_rate_est) < 0 || + gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) @@ -789,6 +789,33 @@ noflush_out: } static int +tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, + u32 portid) +{ + int ret; + struct sk_buff *skb; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, + 0, 1) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + /* now do the delete */ + tcf_action_destroy(actions, 0); + + ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (ret > 0) + return 0; + return ret; +} + +static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid, int event) { @@ -821,27 +848,9 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, if (event == RTM_GETACTION) ret = act_get_notify(net, portid, n, &actions, event); else { /* delete */ - struct sk_buff *skb; - - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - ret = -ENOBUFS; - goto err; - } - - if (tca_get_fill(skb, &actions, portid, n->nlmsg_seq, 0, event, - 0, 1) <= 0) { - kfree_skb(skb); - ret = -EINVAL; + ret = tcf_del_notify(net, n, &actions, portid); + if (ret) goto err; - } - - /* now do the delete */ - tcf_action_destroy(&actions, 0); - ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; return ret; } err: @@ -849,60 +858,36 @@ err: return ret; } -static int tcf_add_notify(struct net *net, struct list_head *actions, - u32 portid, u32 seq, int event, u16 flags) +static int +tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, + u32 portid) { - struct tcamsg *t; - struct nlmsghdr *nlh; struct sk_buff *skb; - struct nlattr *nest; - unsigned char *b; int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - b = skb_tail_pointer(skb); - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags); - if (!nlh) - goto out_kfree_skb; - t = nlmsg_data(nlh); - t->tca_family = AF_UNSPEC; - t->tca__pad1 = 0; - t->tca__pad2 = 0; - - nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) - goto out_kfree_skb; - - if (tcf_action_dump(skb, actions, 0, 0) < 0) - goto out_kfree_skb; - - nla_nest_end(skb, nest); - - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - NETLINK_CB(skb).dst_group = RTNLGRP_TC; + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, + RTM_NEWACTION, 0, 0) <= 0) { + kfree_skb(skb); + return -EINVAL; + } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err > 0) err = 0; return err; - -out_kfree_skb: - kfree_skb(skb); - return -1; } - static int tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid, int ovr) { int ret = 0; LIST_HEAD(actions); - u32 seq = n->nlmsg_seq; ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); if (ret) @@ -911,7 +896,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* dump then free all the actions after update; inserted policy * stays intact */ - ret = tcf_add_notify(net, &actions, portid, seq, RTM_NEWACTION, n->nlmsg_flags); + ret = tcf_add_notify(net, n, &actions, portid); cleanup_a(&actions); done: return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 8b1d65772a8d..ee28e1ccbbd5 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -37,7 +37,6 @@ #include <net/tc_act/tc_csum.h> #define CSUM_TAB_MASK 15 -static u32 csum_idx_gen; static struct tcf_hashinfo csum_hash_info; static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { @@ -67,7 +66,7 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(parm->index, a, bind, &csum_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &csum_idx_gen, &csum_hash_info); + &csum_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index af5641c290fa..31333073cd80 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -24,13 +24,12 @@ #include <net/tc_act/tc_gact.h> #define GACT_TAB_MASK 15 -static u32 gact_idx_gen; static struct tcf_hashinfo gact_hash_info; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { - if (!gact->tcfg_pval || net_random() % gact->tcfg_pval) + if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } @@ -90,7 +89,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), - bind, &gact_idx_gen, &gact_hash_info); + bind, &gact_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 242636950ea5..484bd19601e3 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -29,7 +29,6 @@ #define IPT_TAB_MASK 15 -static u32 ipt_idx_gen; static struct tcf_hashinfo ipt_hash_info; static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) @@ -129,7 +128,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(index, a, bind, &ipt_hash_info); if (!pc) { pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, - &ipt_idx_gen, &ipt_hash_info); + &ipt_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9dbb8cd64cb0..5d05b573a622 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -30,7 +30,6 @@ #include <linux/if_arp.h> #define MIRRED_TAB_MASK 7 -static u32 mirred_idx_gen; static LIST_HEAD(mirred_list); static struct tcf_hashinfo mirred_hash_info; @@ -107,7 +106,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (dev == NULL) return -EINVAL; pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind, - &mirred_idx_gen, &mirred_hash_info); + &mirred_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 584e65503edb..a49fa23b49dd 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -30,7 +30,6 @@ #define NAT_TAB_MASK 15 -static u32 nat_idx_gen; static struct tcf_hashinfo nat_hash_info; @@ -61,7 +60,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(parm->index, a, bind, &nat_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &nat_idx_gen, &nat_hash_info); + &nat_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 729189341933..f361e4e3c314 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -24,7 +24,6 @@ #include <net/tc_act/tc_pedit.h> #define PEDIT_TAB_MASK 15 -static u32 pedit_idx_gen; static struct tcf_hashinfo pedit_hash_info; @@ -63,7 +62,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!parm->nkeys) return -EINVAL; pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &pedit_idx_gen, &pedit_hash_info); + &pedit_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); p = to_pedit(pc); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 9295b86d5319..a719fdff575e 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -41,7 +41,6 @@ struct tcf_police { container_of(pc, struct tcf_police, common) #define POL_TAB_MASK 15 -static u32 police_idx_gen; static struct tcf_hashinfo police_hash_info; /* old policer structure from before tc actions */ @@ -251,7 +250,7 @@ override: police->tcfp_t_c = ktime_to_ns(ktime_get()); police->tcf_index = parm->index ? parm->index : - tcf_hash_new_index(&police_idx_gen, &police_hash_info); + tcf_hash_new_index(&police_hash_info); h = tcf_hash(police->tcf_index, POL_TAB_MASK); spin_lock_bh(&police_hash_info.lock); hlist_add_head(&police->tcf_head, &police_hash_info.htab[h]); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index b44491e3ec17..f7d5406c1fe2 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -25,7 +25,6 @@ #include <net/tc_act/tc_defact.h> #define SIMP_TAB_MASK 7 -static u32 simp_idx_gen; static struct tcf_hashinfo simp_hash_info; #define SIMP_MAX_DATA 32 @@ -118,7 +117,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, pc = tcf_hash_check(parm->index, a, bind, &simp_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, - &simp_idx_gen, &simp_hash_info); + &simp_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 0fa1aad6e204..74af46127060 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -28,7 +28,6 @@ #include <net/tc_act/tc_skbedit.h> #define SKBEDIT_TAB_MASK 15 -static u32 skbedit_idx_gen; static struct tcf_hashinfo skbedit_hash_info; static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, @@ -104,7 +103,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, pc = tcf_hash_check(parm->index, a, bind, &skbedit_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, - &skbedit_idx_gen, &skbedit_hash_info); + &skbedit_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d8c42b1b88e5..29a30a14c315 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -340,7 +340,7 @@ errout: return err; } -static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, +static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, unsigned long fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; @@ -362,7 +362,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; - if (tp->ops->dump && tp->ops->dump(tp, fh, skb, tcm) < 0) + if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) goto nla_put_failure; } nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -385,7 +385,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -404,8 +404,9 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, struct tcf_walker *arg) { struct tcf_dump_args *a = (void *)arg; + struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } @@ -463,7 +464,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).portid, + if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) break; diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index b6552035d1f4..e98ca99c202b 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -38,7 +38,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { int r; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { @@ -56,7 +56,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long basic_get(struct tcf_proto *tp, u32 handle) { unsigned long l = 0UL; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; if (head == NULL) @@ -107,7 +107,7 @@ static void basic_destroy(struct tcf_proto *tp) static int basic_delete(struct tcf_proto *tp, unsigned long arg) { - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *t, *f = (struct basic_filter *) arg; list_for_each_entry(t, &head->flist, link) @@ -164,7 +164,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg) { int err; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *f = (struct basic_filter *) *arg; @@ -225,7 +225,7 @@ errout: static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { @@ -241,7 +241,7 @@ skip: } } -static int basic_dump(struct tcf_proto *tp, unsigned long fh, +static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct basic_filter *f = (struct basic_filter *) fh; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 00a5a585e5f1..8e3cf49118e3 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -295,7 +295,7 @@ errout: return ret; } -static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh, +static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *tm) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 8349fcdc50f3..8e2158ab551c 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -164,7 +164,7 @@ skip: arg->count++; } -static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh, +static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct cls_cgroup_head *head = tp->root; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index dfd18a5c3e81..257029c54332 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -563,7 +563,7 @@ static void flow_put(struct tcf_proto *tp, unsigned long f) { } -static int flow_dump(struct tcf_proto *tp, unsigned long fh, +static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct flow_filter *f = (struct flow_filter *)fh; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 3f9cece13807..ed00e8c21cea 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -41,7 +41,7 @@ struct fw_filter { u32 id; struct tcf_result res; #ifdef CONFIG_NET_CLS_IND - char indev[IFNAMSIZ]; + int ifindex; #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; }; @@ -75,7 +75,7 @@ static inline int fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f; int r; u32 id = skb->mark; @@ -86,7 +86,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND - if (!tcf_match_indev(skb, f->indev)) + if (!tcf_match_indev(skb, f->ifindex)) continue; #endif /* CONFIG_NET_CLS_IND */ r = tcf_exts_exec(skb, &f->exts, res); @@ -111,7 +111,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f; if (head == NULL) @@ -160,7 +160,7 @@ static void fw_destroy(struct tcf_proto *tp) static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *)arg; struct fw_filter **fp; @@ -190,7 +190,7 @@ static int fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, struct nlattr **tca, unsigned long base) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct tcf_exts e; u32 mask; int err; @@ -207,9 +207,11 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FW_INDEV]) { - err = tcf_change_indev(tp, f->indev, tb[TCA_FW_INDEV]); - if (err < 0) + int ret; + ret = tcf_change_indev(net, tb[TCA_FW_INDEV]); + if (ret < 0) goto errout; + f->ifindex = ret; } #endif /* CONFIG_NET_CLS_IND */ @@ -235,7 +237,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -298,7 +300,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; int h; if (head == NULL) @@ -324,10 +326,10 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int fw_dump(struct tcf_proto *tp, unsigned long fh, +static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -348,9 +350,12 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid)) goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(f->indev) && - nla_put_string(skb, TCA_FW_INDEV, f->indev)) - goto nla_put_failure; + if (f->ifindex) { + struct net_device *dev; + dev = __dev_get_by_index(net, f->ifindex); + if (dev && nla_put_string(skb, TCA_FW_INDEV, dev->name)) + goto nla_put_failure; + } #endif /* CONFIG_NET_CLS_IND */ if (head->mask != 0xFFFFFFFF && nla_put_u32(skb, TCA_FW_MASK, head->mask)) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 2473953a5948..1ad3068f2ce1 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -123,7 +123,7 @@ static inline int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; @@ -213,7 +213,7 @@ static inline u32 from_hash(u32 id) static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct route4_bucket *b; struct route4_filter *f; unsigned int h1, h2; @@ -284,7 +284,7 @@ static void route4_destroy(struct tcf_proto *tp) static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct route4_filter **fp, *f = (struct route4_filter *)arg; unsigned int h = 0; struct route4_bucket *b; @@ -551,7 +551,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int route4_dump(struct tcf_proto *tp, unsigned long fh, +static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct route4_filter *f = (struct route4_filter *)fh; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 4f25c2ac825b..19f8e5dfa8bd 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -594,7 +594,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, +static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct rsvp_filter *f = (struct rsvp_filter *)fh; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index ffad18791c93..eed8404443d8 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -24,9 +24,6 @@ #define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ -#define PRIV(tp) ((struct tcindex_data *) (tp)->root) - - struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; @@ -77,7 +74,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key) static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *f; int key = (skb->tc_index & p->mask) >> p->shift; @@ -102,7 +99,7 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r; pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); @@ -140,7 +137,7 @@ static int tcindex_init(struct tcf_proto *tp) static int __tcindex_delete(struct tcf_proto *tp, unsigned long arg, int lock) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; struct tcindex_filter *f = NULL; @@ -338,7 +335,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg; int err; @@ -360,7 +357,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter *f, *next; int i; @@ -407,7 +404,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp, static void tcindex_destroy(struct tcf_proto *tp) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcf_walker walker; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); @@ -422,10 +419,10 @@ static void tcindex_destroy(struct tcf_proto *tp) } -static int tcindex_dump(struct tcf_proto *tp, unsigned long fh, +static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 20f2fb79c747..84c28daff848 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -48,7 +48,7 @@ struct tc_u_knode { struct tc_u_hnode *ht_up; struct tcf_exts exts; #ifdef CONFIG_NET_CLS_IND - char indev[IFNAMSIZ]; + int ifindex; #endif u8 fshift; struct tcf_result res; @@ -95,7 +95,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root; + struct tc_u_hnode *ht = tp->root; unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -152,7 +152,7 @@ check_terminal: *res = n->res; #ifdef CONFIG_NET_CLS_IND - if (!tcf_match_indev(skb, n->indev)) { + if (!tcf_match_indev(skb, n->ifindex)) { n = n->next; goto next_knode; } @@ -527,9 +527,11 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_U32_INDEV]) { - err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV]); - if (err < 0) + int ret; + ret = tcf_change_indev(net, tb[TCA_U32_INDEV]); + if (ret < 0) goto errout; + n->ifindex = ret; } #endif tcf_exts_change(tp, &n->exts, &e); @@ -712,7 +714,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int u32_dump(struct tcf_proto *tp, unsigned long fh, +static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct tc_u_knode *n = (struct tc_u_knode *)fh; @@ -760,9 +762,12 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(n->indev) && - nla_put_string(skb, TCA_U32_INDEV, n->indev)) - goto nla_put_failure; + if (n->ifindex) { + struct net_device *dev; + dev = __dev_get_by_index(net, n->ifindex); + if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name)) + goto nla_put_failure; + } #endif #ifdef CONFIG_CLS_U32_PERF if (nla_put(skb, TCA_U32_PCNT, diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 55786283a3df..ba5bc929eac7 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -390,7 +390,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = 10*1024; q->flows_cnt = 1024; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); codel_params_init(&q->cparams); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 32bb942d2faa..e82e43b69c33 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) - ret = dev_hard_start_xmit(skb, dev, txq, NULL); + ret = dev_hard_start_xmit(skb, dev, txq); HARD_TX_UNLOCK(dev, txq); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index cf7f614e841b..647680b1c625 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -574,18 +574,18 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]); if (tb[TCA_HHF_RESET_TIMEOUT]) { - u32 ms = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); + u32 us = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); - q->hhf_reset_timeout = msecs_to_jiffies(ms); + q->hhf_reset_timeout = usecs_to_jiffies(us); } if (tb[TCA_HHF_ADMIT_BYTES]) q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]); if (tb[TCA_HHF_EVICT_TIMEOUT]) { - u32 ms = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); + u32 us = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); - q->hhf_evict_timeout = msecs_to_jiffies(ms); + q->hhf_evict_timeout = usecs_to_jiffies(us); } qlen = sch->q.qlen; @@ -607,7 +607,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); @@ -684,10 +684,10 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) || nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT, - jiffies_to_msecs(q->hhf_reset_timeout)) || + jiffies_to_usecs(q->hhf_reset_timeout)) || nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) || nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT, - jiffies_to_msecs(q->hhf_evict_timeout)) || + jiffies_to_usecs(q->hhf_evict_timeout)) || nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) goto nla_put_failure; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 090a4e3ecd0d..3019c10d6c56 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -169,7 +169,7 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; - state->last = net_random(); + state->last = prandom_u32(); } /* get_crandom - correlated random number generator @@ -182,9 +182,9 @@ static u32 get_crandom(struct crndstate *state) unsigned long answer; if (state->rho == 0) /* no correlation */ - return net_random(); + return prandom_u32(); - value = net_random(); + value = prandom_u32(); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; @@ -198,7 +198,7 @@ static u32 get_crandom(struct crndstate *state) static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; - u32 rnd = net_random(); + u32 rnd = prandom_u32(); /* * Makes a comparison between rnd and the transition @@ -264,15 +264,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) switch (clg->state) { case 1: - if (net_random() < clg->a1) + if (prandom_u32() < clg->a1) clg->state = 2; - if (net_random() < clg->a4) + if (prandom_u32() < clg->a4) return true; break; case 2: - if (net_random() < clg->a2) + if (prandom_u32() < clg->a2) clg->state = 1; - if (net_random() > clg->a3) + if (prandom_u32() > clg->a3) return true; } @@ -457,7 +457,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb_checksum_help(skb))) return qdisc_drop(skb, sch); - skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); + skb->data[prandom_u32() % skb_headlen(skb)] ^= + 1<<(prandom_u32() % 8); } if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index fe65340c8eb4..a255d0200a59 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -122,7 +122,7 @@ static bool drop_early(struct Qdisc *sch, u32 packet_size) else local_prob = q->vars.prob; - rnd = net_random(); + rnd = prandom_u32(); if (rnd < local_prob) return true; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 30ea4674cabd..9b0f7093d970 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -220,7 +220,7 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = net_random(); + q->bins[slot].perturbation = prandom_u32(); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -381,7 +381,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) goto enqueue; } - r = net_random() & SFB_MAX_PROB; + r = prandom_u32() & SFB_MAX_PROB; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 76f01e0258df..87317ff0b4ec 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -629,7 +629,7 @@ static void sfq_perturbation(unsigned long arg) spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -698,7 +698,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); } sch_tree_unlock(sch); kfree(p); @@ -759,7 +759,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = net_random(); + q->perturbation = prandom_u32(); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 34b7726bcd7f..7c161084f241 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1030,6 +1030,7 @@ static const struct net_protocol sctp_protocol = { .err_handler = sctp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; /* IPv4 address related functions. */ diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e5f7cdb42a85..632090b961c3 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -78,6 +78,8 @@ static int sctp_process_param(struct sctp_association *asoc, gfp_t gfp); static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data); +static void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, + const void *data); /* Control chunk destructor */ static void sctp_control_release_owner(struct sk_buff *skb) @@ -1475,8 +1477,8 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) /* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient * space in the chunk */ -void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, - int len, const void *data) +static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, + int len, const void *data) { if (skb_tailroom(chunk->skb) >= len) return sctp_addto_chunk(chunk, len, data); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d32dae78a486..7cc62b922f12 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5926,7 +5926,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) inet_get_local_port_range(sock_net(sk), &low, &high); remaining = (high - low) + 1; - rover = net_random() % remaining + low; + rover = prandom_u32() % remaining + low; do { rover++; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index a72de074172d..e521d20e1970 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -619,7 +619,7 @@ static void cache_limit_defers(void) /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { - if (net_random() & 1) + if (prandom_u32() & 1) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 04199bc8416f..1750048130a7 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1188,7 +1188,7 @@ static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) static inline void xprt_init_xid(struct rpc_xprt *xprt) { - xprt->xid = net_random(); + xprt->xid = prandom_u32(); } static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index dd9d295813cf..75b045e1cd50 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1674,7 +1674,7 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task) static unsigned short xs_get_random_port(void) { unsigned short range = xprt_max_resvport - xprt_min_resvport; - unsigned short rand = (unsigned short) net_random() % range; + unsigned short rand = (unsigned short) prandom_u32() % range; return rand + xprt_min_resvport; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 471973ff134f..d4b5de41b682 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1438,6 +1438,7 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) int type; head = head->next; + buf->next = NULL; /* Ensure bearer is still enabled */ if (unlikely(!b_ptr->active)) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 88843996f935..6c7ac016ce3a 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -67,7 +67,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) case IPPROTO_COMP: if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr))) return -EINVAL; - *spi = htonl(ntohs(*(__be16*)(skb_transport_header(skb) + 2))); + *spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2))); *seq = 0; return 0; default: @@ -77,8 +77,8 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) if (!pskb_may_pull(skb, hlen)) return -EINVAL; - *spi = *(__be32*)(skb_transport_header(skb) + offset); - *seq = *(__be32*)(skb_transport_header(skb) + offset_seq); + *spi = *(__be32 *)(skb_transport_header(skb) + offset); + *seq = *(__be32 *)(skb_transport_header(skb) + offset_seq); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e205c4b56afb..01770826a15a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -171,7 +171,7 @@ static inline unsigned long make_jiffies(long secs) static void xfrm_policy_timer(unsigned long data) { - struct xfrm_policy *xp = (struct xfrm_policy*)data; + struct xfrm_policy *xp = (struct xfrm_policy *)data; unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -1286,7 +1286,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; - for (nx=0, i = 0; i < policy->xfrm_nr; i++) { + for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; @@ -1316,9 +1316,9 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); - } - else if (error == -ESRCH) + } else if (error == -ESRCH) { error = -EAGAIN; + } if (!tmpl->optional) goto fail; @@ -1326,7 +1326,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, return nx; fail: - for (nx--; nx>=0; nx--) + for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } @@ -1363,7 +1363,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, return cnx; fail: - for (cnx--; cnx>=0; cnx--) + for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; @@ -1706,7 +1706,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, xfrm_pols_put(pols, *num_pols); return PTR_ERR(pols[1]); } - (*num_pols) ++; + (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } @@ -1760,7 +1760,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, } xdst->num_pols = num_pols; - memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; @@ -2029,7 +2029,7 @@ make_dummy_bundle: } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; - memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); dst_hold(&xdst->u.dst); return &xdst->flo; @@ -2138,7 +2138,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; - memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } @@ -2334,7 +2334,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (skb->sp) { int i; - for (i=skb->sp->len-1; i>=0; i--) { + for (i = skb->sp->len-1; i >= 0; i--) { struct xfrm_state *x = skb->sp->xvec[i]; if (!xfrm_selector_match(&x->sel, &fl, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); @@ -2380,7 +2380,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol->curlft.use_time = get_seconds(); pols[0] = pol; - npols ++; + npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, @@ -2392,7 +2392,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 0; } pols[1]->curlft.use_time = get_seconds(); - npols ++; + npols++; } } #endif @@ -2989,7 +2989,7 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(sel->family) { + switch (sel->family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) @@ -3066,8 +3066,8 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, return false; } -static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel, - u8 dir, u8 type, struct net *net) +static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, + u8 dir, u8 type, struct net *net) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 80cd1e55b834..fc5abd0b456f 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -52,7 +52,7 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; int i; - for (i=0; xfrm_mib_list[i].name; i++) + for (i = 0; xfrm_mib_list[i].name; i++) seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name, snmp_fold_field((void __percpu **) net->mib.xfrm_statistics, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a62c25ea3631..8d11d28991a4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -382,7 +382,7 @@ static inline unsigned long make_jiffies(long secs) return secs*HZ; } -static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) +static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); @@ -448,7 +448,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) if (warn) km_state_expired(x, 0, 0); resched: - if (next != LONG_MAX){ + if (next != LONG_MAX) { tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL); } @@ -890,7 +890,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; - spin_lock(&net->xfrm.xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && @@ -908,13 +908,35 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (rx) xfrm_state_hold(rx); - spin_unlock(&net->xfrm.xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; } EXPORT_SYMBOL(xfrm_stateonly_find); +struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, + unsigned short family) +{ + struct xfrm_state *x; + struct xfrm_state_walk *w; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + list_for_each_entry(w, &net->xfrm.state_all, all) { + x = container_of(w, struct xfrm_state, km); + if (x->props.family != family || + x->id.spi != spi) + continue; + + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + xfrm_state_hold(x); + return x; + } + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + return NULL; +} +EXPORT_SYMBOL(xfrm_state_lookup_byspi); + static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -1237,8 +1259,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n } EXPORT_SYMBOL(xfrm_migrate_state_find); -struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, - struct xfrm_migrate *m) +struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, + struct xfrm_migrate *m) { struct xfrm_state *xc; int err; @@ -1348,7 +1370,7 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; - tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL); + tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL); return -EINVAL; } @@ -1542,8 +1564,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) x->id.spi = minspi; } else { u32 spi = 0; - for (h=0; h<high-low+1; h++) { - spi = low + net_random()%(high-low+1); + for (h = 0; h < high-low+1; h++) { + spi = low + prandom_u32()%(high-low+1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { x->id.spi = htonl(spi); @@ -1630,7 +1652,7 @@ EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(unsigned long data) { - struct xfrm_state *x = (struct xfrm_state*)data; + struct xfrm_state *x = (struct xfrm_state *)data; spin_lock(&x->lock); @@ -2079,7 +2101,7 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(x->props.family) { + switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); @@ -2109,7 +2131,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", - &iph6->saddr,&iph6->daddr, + &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 97681a390402..334856689b0d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1731,11 +1731,11 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct return -EMSGSIZE; id = nlmsg_data(nlh); - memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr)); + memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr)); id->sa_id.spi = x->id.spi; id->sa_id.family = x->props.family; id->sa_id.proto = x->id.proto; - memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr)); + memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr)); id->reqid = x->props.reqid; id->flags = c->data.aevent; @@ -1824,7 +1824,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct km_event c; - int err = - EINVAL; + int err = -EINVAL; u32 mark = 0; struct xfrm_mark m; struct xfrm_aevent_id *p = nlmsg_data(nlh); |