diff options
493 files changed, 11576 insertions, 4683 deletions
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index 49b8b8907f36..aac9357d4866 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -434,7 +434,6 @@ <section id="ps-client"> <title>support for powersaving clients</title> !Pinclude/net/mac80211.h AP support for powersaving clients - </section> !Finclude/net/mac80211.h ieee80211_get_buffered_bc !Finclude/net/mac80211.h ieee80211_beacon_get !Finclude/net/mac80211.h ieee80211_sta_eosp @@ -443,6 +442,7 @@ !Finclude/net/mac80211.h ieee80211_sta_ps_transition_ni !Finclude/net/mac80211.h ieee80211_sta_set_buffered !Finclude/net/mac80211.h ieee80211_sta_block_awake + </section> </chapter> <chapter id="multi-iface"> @@ -487,8 +487,8 @@ <title>RX A-MPDU aggregation</title> !Pnet/mac80211/agg-rx.c RX A-MPDU aggregation !Cnet/mac80211/agg-rx.c - </sect1> !Finclude/net/mac80211.h ieee80211_ampdu_mlme_action + </sect1> </chapter> <chapter id="smps"> diff --git a/Documentation/devicetree/bindings/i2c/i2c-st.txt b/Documentation/devicetree/bindings/i2c/i2c-st.txt index 437e0db3823c..4c26fda3844a 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-st.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-st.txt @@ -31,7 +31,7 @@ i2c0: i2c@fed40000 { compatible = "st,comms-ssc4-i2c"; reg = <0xfed40000 0x110>; interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&CLK_S_ICN_REG_0>; + clocks = <&clk_s_a0_ls CLK_ICN_REG>; clock-names = "ssc"; clock-frequency = <400000>; pinctrl-names = "default"; diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt index 9f4e3824e71e..9f41d05be3be 100644 --- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt +++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt @@ -47,6 +47,7 @@ dallas,ds3232 Extremely Accurate I²C RTC with Integrated Crystal and SRAM dallas,ds4510 CPU Supervisor with Nonvolatile Memory and Programmable I/O dallas,ds75 Digital Thermometer and Thermostat dlg,da9053 DA9053: flexible system level PMIC with multicore support +dlg,da9063 DA9063: system PMIC for quad-core application processors epson,rx8025 High-Stability. I2C-Bus INTERFACE REAL TIME CLOCK MODULE epson,rx8581 I2C-BUS INTERFACE REAL TIME CLOCK MODULE fsl,mag3110 MAG3110: Xtrinsic High Accuracy, 3D Magnetometer diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index be6ea8960f20..1e97532a0b79 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -8,7 +8,16 @@ of how to define a PHY. Required properties: - reg : Offset and length of the register set for the device - compatible : Should define the compatible device type for the - mdio. Currently, this is most likely to be "fsl,gianfar-mdio" + mdio. Currently supported strings/devices are: + - "fsl,gianfar-tbi" + - "fsl,gianfar-mdio" + - "fsl,etsec2-tbi" + - "fsl,etsec2-mdio" + - "fsl,ucc-mdio" + - "fsl,fman-mdio" + When device_type is "mdio", the following strings are also considered: + - "gianfar" + - "ucc_geth_phy" Example: diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt index c6af4bac5aa8..54f10478e8e3 100644 --- a/Documentation/networking/netlink_mmap.txt +++ b/Documentation/networking/netlink_mmap.txt @@ -199,16 +199,9 @@ frame header. TX limitations -------------- -Kernel processing usually involves validation of the message received by -user-space, then processing its contents. The kernel must assure that -userspace is not able to modify the message contents after they have been -validated. In order to do so, the message is copied from the ring frame -to an allocated buffer if either of these conditions is false: - -- only a single mapping of the ring exists -- the file descriptor is not shared between processes - -This means that for threaded programs, the kernel will fall back to copying. +As of Jan 2015 the message is always copied from the ring frame to an +allocated buffer due to unresolved security concerns. +See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX."). Example ------- diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index a5c784c89312..5f0922613f1a 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -162,6 +162,27 @@ SOF_TIMESTAMPING_OPT_CMSG: option IP_PKTINFO simultaneously. +SOF_TIMESTAMPING_OPT_TSONLY: + + Applies to transmit timestamps only. Makes the kernel return the + timestamp as a cmsg alongside an empty packet, as opposed to + alongside the original packet. This reduces the amount of memory + charged to the socket's receive budget (SO_RCVBUF) and delivers + the timestamp even if sysctl net.core.tstamp_allow_data is 0. + This option disables SOF_TIMESTAMPING_OPT_CMSG. + + +New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to +disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate +regardless of the setting of sysctl net.core.tstamp_allow_data. + +An exception is when a process needs additional cmsg data, for +instance SOL_IP/IP_PKTINFO to detect the egress network interface. +Then pass option SOF_TIMESTAMPING_OPT_CMSG. This option depends on +having access to the contents of the original packet, so cannot be +combined with SOF_TIMESTAMPING_OPT_TSONLY. + + 1.4 Bytestream Timestamps The SO_TIMESTAMPING interface supports timestamping of bytes in a diff --git a/Documentation/networking/timestamping/txtimestamp.c b/Documentation/networking/timestamping/txtimestamp.c index 05694febc238..8217510d3842 100644 --- a/Documentation/networking/timestamping/txtimestamp.c +++ b/Documentation/networking/timestamping/txtimestamp.c @@ -70,6 +70,7 @@ static int do_ipv6 = 1; static int cfg_payload_len = 10; static bool cfg_show_payload; static bool cfg_do_pktinfo; +static bool cfg_loop_nodata; static uint16_t dest_port = 9000; static struct sockaddr_in daddr; @@ -141,6 +142,9 @@ static void print_payload(char *data, int len) { int i; + if (!len) + return; + if (len > 70) len = 70; @@ -177,6 +181,7 @@ static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len) struct sock_extended_err *serr = NULL; struct scm_timestamping *tss = NULL; struct cmsghdr *cm; + int batch = 0; for (cm = CMSG_FIRSTHDR(msg); cm && cm->cmsg_len; @@ -209,10 +214,18 @@ static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len) } else fprintf(stderr, "unknown cmsg %d,%d\n", cm->cmsg_level, cm->cmsg_type); + + if (serr && tss) { + print_timestamp(tss, serr->ee_info, serr->ee_data, + payload_len); + serr = NULL; + tss = NULL; + batch++; + } } - if (serr && tss) - print_timestamp(tss, serr->ee_info, serr->ee_data, payload_len); + if (batch > 1) + fprintf(stderr, "batched %d timestamps\n", batch); } static int recv_errmsg(int fd) @@ -244,7 +257,7 @@ static int recv_errmsg(int fd) if (ret == -1 && errno != EAGAIN) error(1, errno, "recvmsg"); - if (ret > 0) { + if (ret >= 0) { __recv_errmsg_cmsg(&msg, ret); if (cfg_show_payload) print_payload(data, cfg_payload_len); @@ -309,6 +322,9 @@ static void do_test(int family, unsigned int opt) opt |= SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_CMSG | SOF_TIMESTAMPING_OPT_ID; + if (cfg_loop_nodata) + opt |= SOF_TIMESTAMPING_OPT_TSONLY; + if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, (char *) &opt, sizeof(opt))) error(1, 0, "setsockopt timestamping"); @@ -378,6 +394,7 @@ static void __attribute__((noreturn)) usage(const char *filepath) " -h: show this message\n" " -I: request PKTINFO\n" " -l N: send N bytes at a time\n" + " -n: set no-payload option\n" " -r: use raw\n" " -R: use raw (IP_HDRINCL)\n" " -p N: connect to port N\n" @@ -392,7 +409,7 @@ static void parse_opt(int argc, char **argv) int proto_count = 0; char c; - while ((c = getopt(argc, argv, "46hIl:p:rRux")) != -1) { + while ((c = getopt(argc, argv, "46hIl:np:rRux")) != -1) { switch (c) { case '4': do_ipv6 = 0; @@ -403,6 +420,9 @@ static void parse_opt(int argc, char **argv) case 'I': cfg_do_pktinfo = true; break; + case 'n': + cfg_loop_nodata = true; + break; case 'r': proto_count++; cfg_proto = SOCK_RAW; diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 666594b43cff..6294b5186ae5 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -97,6 +97,14 @@ rmem_max The maximum receive socket buffer size in bytes. +tstamp_allow_data +----------------- +Allow processes to receive tx timestamps looped together with the original +packet contents. If disabled, transmit timestamp requests from unprivileged +processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set. +Default: 1 (on) + + wmem_default ------------ diff --git a/MAINTAINERS b/MAINTAINERS index 3c3bf861d78d..2b3aca7e40b9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -708,6 +708,16 @@ X: drivers/iio/*/adjd* F: drivers/staging/iio/*/ad* F: staging/iio/trigger/iio-trig-bfin-timer.c +ANDROID DRIVERS +M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +M: Arve Hjønnevåg <arve@android.com> +M: Riley Andrews <riandrews@android.com> +T: git git://git.kernel.org/pub/scm/linux/kernel/gregkh/staging.git +L: devel@driverdev.osuosl.org +S: Supported +F: drivers/android/ +F: drivers/staging/android/ + AOA (Apple Onboard Audio) ALSA DRIVER M: Johannes Berg <johannes@sipsolutions.net> L: linuxppc-dev@lists.ozlabs.org @@ -10181,6 +10191,7 @@ USERSPACE I/O (UIO) M: "Hans J. Koch" <hjk@hansjkoch.de> M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git F: Documentation/DocBook/uio-howto.tmpl F: drivers/uio/ F: include/linux/uio*.h @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Diseased Newt # *DOCUMENTATION* diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 98838a05ba6d..9d0ac091a52a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -156,6 +156,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 6f7e3a68803a..563cb27e37f5 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -161,6 +161,8 @@ good_area: if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 68be9017593d..132c70e2d2f1 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -263,16 +263,37 @@ restart: adr r0, LC0 * OK... Let's do some funky business here. * If we do have a DTB appended to zImage, and we do have * an ATAG list around, we want the later to be translated - * and folded into the former here. To be on the safe side, - * let's temporarily move the stack away into the malloc - * area. No GOT fixup has occurred yet, but none of the - * code we're about to call uses any global variable. + * and folded into the former here. No GOT fixup has occurred + * yet, but none of the code we're about to call uses any + * global variable. */ - add sp, sp, #0x10000 + + /* Get the initial DTB size */ + ldr r5, [r6, #4] +#ifndef __ARMEB__ + /* convert to little endian */ + eor r1, r5, r5, ror #16 + bic r1, r1, #0x00ff0000 + mov r5, r5, ror #8 + eor r5, r5, r1, lsr #8 +#endif + /* 50% DTB growth should be good enough */ + add r5, r5, r5, lsr #1 + /* preserve 64-bit alignment */ + add r5, r5, #7 + bic r5, r5, #7 + /* clamp to 32KB min and 1MB max */ + cmp r5, #(1 << 15) + movlo r5, #(1 << 15) + cmp r5, #(1 << 20) + movhi r5, #(1 << 20) + /* temporarily relocate the stack past the DTB work space */ + add sp, sp, r5 + stmfd sp!, {r0-r3, ip, lr} mov r0, r8 mov r1, r6 - sub r2, sp, r6 + mov r2, r5 bl atags_to_fdt /* @@ -285,11 +306,11 @@ restart: adr r0, LC0 bic r0, r0, #1 add r0, r0, #0x100 mov r1, r6 - sub r2, sp, r6 + mov r2, r5 bleq atags_to_fdt ldmfd sp!, {r0-r3, ip, lr} - sub sp, sp, #0x10000 + sub sp, sp, r5 #endif mov r8, r6 @ use the appended device tree @@ -306,7 +327,7 @@ restart: adr r0, LC0 subs r1, r5, r1 addhi r9, r9, r1 - /* Get the dtb's size */ + /* Get the current DTB size */ ldr r5, [r6, #4] #ifndef __ARMEB__ /* convert r5 (dtb size) to little endian */ diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi index 5a452fdd7c5d..c90724bded10 100644 --- a/arch/arm/boot/dts/am3517.dtsi +++ b/arch/arm/boot/dts/am3517.dtsi @@ -31,6 +31,7 @@ status = "disabled"; reg = <0x5c000000 0x30000>; interrupts = <67 68 69 70>; + syscon = <&omap3_scm_general>; ti,davinci-ctrl-reg-offset = <0x10000>; ti,davinci-ctrl-mod-reg-offset = <0>; ti,davinci-ctrl-ram-offset = <0x20000>; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 7b4099fcf817..d5c4669224b1 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -17,14 +17,6 @@ aliases { ethernet0 = &emac; - serial0 = &uart0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; - serial4 = &uart4; - serial5 = &uart5; - serial6 = &uart6; - serial7 = &uart7; }; chosen { @@ -39,6 +31,14 @@ <&ahb_gates 44>; status = "disabled"; }; + + framebuffer@1 { + compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; + allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi"; + clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, + <&ahb_gates 44>, <&ahb_gates 46>; + status = "disabled"; + }; }; cpus { @@ -438,8 +438,8 @@ reg-names = "phy_ctrl", "pmu1", "pmu2"; clocks = <&usb_clk 8>; clock-names = "usb_phy"; - resets = <&usb_clk 1>, <&usb_clk 2>; - reset-names = "usb1_reset", "usb2_reset"; + resets = <&usb_clk 0>, <&usb_clk 1>, <&usb_clk 2>; + reset-names = "usb0_reset", "usb1_reset", "usb2_reset"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts index fe3c559ca6a8..bfa742817690 100644 --- a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts +++ b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts @@ -55,6 +55,12 @@ model = "Olimex A10s-Olinuxino Micro"; compatible = "olimex,a10s-olinuxino-micro", "allwinner,sun5i-a10s"; + aliases { + serial0 = &uart0; + serial1 = &uart2; + serial2 = &uart3; + }; + soc@01c00000 { emac: ethernet@01c0b000 { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index 1b76667f3182..2e7d8263799d 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -18,10 +18,6 @@ aliases { ethernet0 = &emac; - serial0 = &uart0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; }; chosen { @@ -390,8 +386,8 @@ reg-names = "phy_ctrl", "pmu1"; clocks = <&usb_clk 8>; clock-names = "usb_phy"; - resets = <&usb_clk 1>; - reset-names = "usb1_reset"; + resets = <&usb_clk 0>, <&usb_clk 1>; + reset-names = "usb0_reset", "usb1_reset"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts index eeed1f236ee8..c7be3abd9fcc 100644 --- a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts +++ b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts @@ -53,6 +53,10 @@ model = "HSG H702"; compatible = "hsg,h702", "allwinner,sun5i-a13"; + aliases { + serial0 = &uart1; + }; + soc@01c00000 { mmc0: mmc@01c0f000 { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts index 916ee8bb826f..3decefb3c37a 100644 --- a/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts +++ b/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts @@ -54,6 +54,10 @@ model = "Olimex A13-Olinuxino Micro"; compatible = "olimex,a13-olinuxino-micro", "allwinner,sun5i-a13"; + aliases { + serial0 = &uart1; + }; + soc@01c00000 { mmc0: mmc@01c0f000 { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts index e31d291d14cb..b421f7fa197b 100644 --- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts +++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts @@ -55,6 +55,10 @@ model = "Olimex A13-Olinuxino"; compatible = "olimex,a13-olinuxino", "allwinner,sun5i-a13"; + aliases { + serial0 = &uart1; + }; + soc@01c00000 { mmc0: mmc@01c0f000 { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index c35217ea1f64..c556688f8b8b 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -16,11 +16,6 @@ / { interrupt-parent = <&intc>; - aliases { - serial0 = &uart1; - serial1 = &uart3; - }; - cpus { #address-cells = <1>; #size-cells = <0>; @@ -349,8 +344,8 @@ reg-names = "phy_ctrl", "pmu1"; clocks = <&usb_clk 8>; clock-names = "usb_phy"; - resets = <&usb_clk 1>; - reset-names = "usb1_reset"; + resets = <&usb_clk 0>, <&usb_clk 1>; + reset-names = "usb0_reset", "usb1_reset"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index f47156b6572b..1e7e7bcf8307 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -53,12 +53,6 @@ interrupt-parent = <&gic>; aliases { - serial0 = &uart0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; - serial4 = &uart4; - serial5 = &uart5; ethernet0 = &gmac; }; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi.dts b/arch/arm/boot/dts/sun7i-a20-bananapi.dts index 1cf1214cc068..bd7b15add697 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi.dts @@ -55,6 +55,12 @@ model = "LeMaker Banana Pi"; compatible = "lemaker,bananapi", "allwinner,sun7i-a20"; + aliases { + serial0 = &uart0; + serial1 = &uart3; + serial2 = &uart7; + }; + soc@01c00000 { spi0: spi@01c05000 { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sun7i-a20-hummingbird.dts b/arch/arm/boot/dts/sun7i-a20-hummingbird.dts index 0e4bfa3b2b85..0bcefcbbb756 100644 --- a/arch/arm/boot/dts/sun7i-a20-hummingbird.dts +++ b/arch/arm/boot/dts/sun7i-a20-hummingbird.dts @@ -19,6 +19,14 @@ model = "Merrii A20 Hummingbird"; compatible = "merrii,a20-hummingbird", "allwinner,sun7i-a20"; + aliases { + serial0 = &uart0; + serial1 = &uart2; + serial2 = &uart3; + serial3 = &uart4; + serial4 = &uart5; + }; + soc@01c00000 { mmc0: mmc@01c0f000 { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts index 9d669cdf031d..66cc77707198 100644 --- a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts +++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts @@ -20,6 +20,9 @@ compatible = "olimex,a20-olinuxino-micro", "allwinner,sun7i-a20"; aliases { + serial0 = &uart0; + serial1 = &uart6; + serial2 = &uart7; spi0 = &spi1; spi1 = &spi2; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index e21ce5992d56..89749ce34a84 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -54,14 +54,6 @@ aliases { ethernet0 = &gmac; - serial0 = &uart0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; - serial4 = &uart4; - serial5 = &uart5; - serial6 = &uart6; - serial7 = &uart7; }; chosen { diff --git a/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts b/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts index 7f2117ce6985..32ad80804dbb 100644 --- a/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts +++ b/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts @@ -55,6 +55,10 @@ model = "Ippo Q8H Dual Core Tablet (v5)"; compatible = "ippo,q8h-v5", "allwinner,sun8i-a23"; + aliases { + serial0 = &r_uart; + }; + chosen { bootargs = "earlyprintk console=ttyS0,115200"; }; diff --git a/arch/arm/boot/dts/sun8i-a23.dtsi b/arch/arm/boot/dts/sun8i-a23.dtsi index 0746cd1024d7..86584fcf5e32 100644 --- a/arch/arm/boot/dts/sun8i-a23.dtsi +++ b/arch/arm/boot/dts/sun8i-a23.dtsi @@ -52,15 +52,6 @@ / { interrupt-parent = <&gic>; - aliases { - serial0 = &uart0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; - serial4 = &uart4; - serial5 = &r_uart; - }; - cpus { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts index 506948f582ee..11ec71072e81 100644 --- a/arch/arm/boot/dts/sun9i-a80-optimus.dts +++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts @@ -54,6 +54,11 @@ model = "Merrii A80 Optimus Board"; compatible = "merrii,a80-optimus", "allwinner,sun9i-a80"; + aliases { + serial0 = &uart0; + serial1 = &uart4; + }; + chosen { bootargs = "earlyprintk console=ttyS0,115200"; }; diff --git a/arch/arm/boot/dts/sun9i-a80.dtsi b/arch/arm/boot/dts/sun9i-a80.dtsi index 494714f67b57..9ef4438206a9 100644 --- a/arch/arm/boot/dts/sun9i-a80.dtsi +++ b/arch/arm/boot/dts/sun9i-a80.dtsi @@ -52,16 +52,6 @@ / { interrupt-parent = <&gic>; - aliases { - serial0 = &uart0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; - serial4 = &uart4; - serial5 = &uart5; - serial6 = &r_uart; - }; - cpus { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 66ce17655bb9..7b0152321b20 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -38,6 +38,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr = HCR_GUEST_MASK; } +static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hcr; +} + +static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr) +{ + vcpu->arch.hcr = hcr; +} + static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) { return 1; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 254e0650e48b..04b4ea0b550a 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -125,9 +125,6 @@ struct kvm_vcpu_arch { * Anything that is not used directly from assembly code goes * here. */ - /* dcache set/way operation pending */ - int last_pcpu; - cpumask_t require_dcache_flush; /* Don't run the guest on this vcpu */ bool pause; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 63e0ecc04901..1bca8f8af442 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -44,6 +44,7 @@ #ifndef __ASSEMBLY__ +#include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/pgalloc.h> @@ -161,13 +162,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size, - bool ipa_uncached) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { - if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) - kvm_flush_dcache_to_poc((void *)hva, size); - /* * If we are going to insert an instruction page and the icache is * either VIPT or PIPT, there is a potential problem where the host @@ -179,18 +177,77 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, * * VIVT caches are tagged using both the ASID and the VMID and doesn't * need any kind of flushing (DDI 0406C.b - Page B3-1392). + * + * We need to do this through a kernel mapping (using the + * user-space mapping has proved to be the wrong + * solution). For that, we need to kmap one page at a time, + * and iterate over the range. */ - if (icache_is_pipt()) { - __cpuc_coherent_user_range(hva, hva + size); - } else if (!icache_is_vivt_asid_tagged()) { + + bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; + + VM_BUG_ON(size & PAGE_MASK); + + if (!need_flush && !icache_is_pipt()) + goto vipt_cache; + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + if (need_flush) + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + if (icache_is_pipt()) + __cpuc_coherent_user_range((unsigned long)va, + (unsigned long)va + PAGE_SIZE); + + size -= PAGE_SIZE; + pfn++; + + kunmap_atomic(va); + } + +vipt_cache: + if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + void *va = kmap_atomic(pte_page(pte)); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + kunmap_atomic(va); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + unsigned long size = PMD_SIZE; + pfn_t pfn = pmd_pfn(pmd); + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + pfn++; + size -= PAGE_SIZE; + + kunmap_atomic(va); + } +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ +} + #define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) -void stage2_flush_vm(struct kvm *kvm); +void kvm_set_way_flush(struct kvm_vcpu *vcpu); +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S index 2260f1855820..8944f4991c3c 100644 --- a/arch/arm/kernel/entry-v7m.S +++ b/arch/arm/kernel/entry-v7m.S @@ -22,10 +22,12 @@ __invalid_entry: v7m_exception_entry +#ifdef CONFIG_PRINTK adr r0, strerr mrs r1, ipsr mov r2, lr bl printk +#endif mov r0, sp bl show_regs 1: b 1b diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 2d6d91001062..0b0d58a905c4 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -281,15 +281,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state); - /* - * Check whether this vcpu requires the cache to be flushed on - * this physical CPU. This is a consequence of doing dcache - * operations by set/way on this vcpu. We do it here to be in - * a non-preemptible section. - */ - if (cpumask_test_and_clear_cpu(cpu, &vcpu->arch.require_dcache_flush)) - flush_cache_all(); /* We'd really want v7_flush_dcache_all() */ - kvm_arm_set_running_vcpu(vcpu); } @@ -541,7 +532,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; - vcpu->arch.last_pcpu = smp_processor_id(); kvm_guest_exit(); trace_kvm_exit(*vcpu_pc(vcpu)); /* diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 7928dbdf2102..f3d88dc388bc 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -189,82 +189,40 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu, return true; } -/* See note at ARM ARM B1.14.4 */ +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + */ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct coproc_params *p, const struct coproc_reg *r) { - unsigned long val; - int cpu; - if (!p->is_write) return read_from_write_only(vcpu, p); - cpu = get_cpu(); - - cpumask_setall(&vcpu->arch.require_dcache_flush); - cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); - - /* If we were already preempted, take the long way around */ - if (cpu != vcpu->arch.last_pcpu) { - flush_cache_all(); - goto done; - } - - val = *vcpu_reg(vcpu, p->Rt1); - - switch (p->CRm) { - case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */ - case 14: /* DCCISW */ - asm volatile("mcr p15, 0, %0, c7, c14, 2" : : "r" (val)); - break; - - case 10: /* DCCSW */ - asm volatile("mcr p15, 0, %0, c7, c10, 2" : : "r" (val)); - break; - } - -done: - put_cpu(); - + kvm_set_way_flush(vcpu); return true; } /* * Generic accessor for VM registers. Only called as long as HCR_TVM - * is set. + * is set. If the guest enables the MMU, we stop trapping the VM + * sys_regs and leave it in complete control of the caches. + * + * Used by the cpu-specific code. */ -static bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) +bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) { + bool was_enabled = vcpu_has_cache_enabled(vcpu); + BUG_ON(!p->is_write); vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1); if (p->is_64bit) vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2); - return true; -} - -/* - * SCTLR accessor. Only called as long as HCR_TVM is set. If the - * guest enables the MMU, we stop trapping the VM sys_regs and leave - * it in complete control of the caches. - * - * Used by the cpu-specific code. - */ -bool access_sctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - access_vm_reg(vcpu, p, r); - - if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ - vcpu->arch.hcr &= ~HCR_TVM; - stage2_flush_vm(vcpu->kvm); - } - + kvm_toggle_cache(vcpu, was_enabled); return true; } diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index 1a44bbe39643..88d24a3a9778 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -153,8 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1, #define is64 .is_64 = true #define is32 .is_64 = false -bool access_sctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r); +bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r); #endif /* __ARM_KVM_COPROC_LOCAL_H__ */ diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index e6f4ae48bda9..a7136757d373 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -34,7 +34,7 @@ static const struct coproc_reg a15_regs[] = { /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_sctlr, reset_val, c1_SCTLR, 0x00C50078 }, + access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 }, }; static struct kvm_coproc_target_table a15_target_table = { diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c index 17fc7cd479d3..b19e46d1b2c0 100644 --- a/arch/arm/kvm/coproc_a7.c +++ b/arch/arm/kvm/coproc_a7.c @@ -37,7 +37,7 @@ static const struct coproc_reg a7_regs[] = { /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, - access_sctlr, reset_val, c1_SCTLR, 0x00C50878 }, + access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 }, }; static struct kvm_coproc_target_table a7_target_table = { diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 1dc9778a00af..136662547ca6 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); } +/* + * D-Cache management functions. They take the page table entries by + * value, as they are flushing the cache using the kernel mapping (or + * kmap on 32bit). + */ +static void kvm_flush_dcache_pte(pte_t pte) +{ + __kvm_flush_dcache_pte(pte); +} + +static void kvm_flush_dcache_pmd(pmd_t pmd) +{ + __kvm_flush_dcache_pmd(pmd); +} + +static void kvm_flush_dcache_pud(pud_t pud) +{ + __kvm_flush_dcache_pud(pud); +} + static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, int min, int max) { @@ -119,6 +139,26 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) put_page(virt_to_page(pmd)); } +/* + * Unmapping vs dcache management: + * + * If a guest maps certain memory pages as uncached, all writes will + * bypass the data cache and go directly to RAM. However, the CPUs + * can still speculate reads (not writes) and fill cache lines with + * data. + * + * Those cache lines will be *clean* cache lines though, so a + * clean+invalidate operation is equivalent to an invalidate + * operation, because no cache lines are marked dirty. + * + * Those clean cache lines could be filled prior to an uncached write + * by the guest, and the cache coherent IO subsystem would therefore + * end up writing old data to disk. + * + * This is why right after unmapping a page/section and invalidating + * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure + * the IO subsystem will never hit in the cache. + */ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -128,9 +168,16 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, start_pte = pte = pte_offset_kernel(pmd, addr); do { if (!pte_none(*pte)) { + pte_t old_pte = *pte; + kvm_set_pte(pte, __pte(0)); - put_page(virt_to_page(pte)); kvm_tlb_flush_vmid_ipa(kvm, addr); + + /* No need to invalidate the cache for device mappings */ + if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(old_pte); + + put_page(virt_to_page(pte)); } } while (pte++, addr += PAGE_SIZE, addr != end); @@ -149,8 +196,13 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud, next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { if (kvm_pmd_huge(*pmd)) { + pmd_t old_pmd = *pmd; + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pmd(old_pmd); + put_page(virt_to_page(pmd)); } else { unmap_ptes(kvm, pmd, addr, next); @@ -173,8 +225,13 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd, next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { if (pud_huge(*pud)) { + pud_t old_pud = *pud; + pud_clear(pud); kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pud(old_pud); + put_page(virt_to_page(pud)); } else { unmap_pmds(kvm, pud, addr, next); @@ -209,10 +266,9 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE); - } + if (!pte_none(*pte) && + (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -226,12 +282,10 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, do { next = kvm_pmd_addr_end(addr, end); if (!pmd_none(*pmd)) { - if (kvm_pmd_huge(*pmd)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE); - } else { + if (kvm_pmd_huge(*pmd)) + kvm_flush_dcache_pmd(*pmd); + else stage2_flush_ptes(kvm, pmd, addr, next); - } } } while (pmd++, addr = next, addr != end); } @@ -246,12 +300,10 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, do { next = kvm_pud_addr_end(addr, end); if (!pud_none(*pud)) { - if (pud_huge(*pud)) { - hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); - kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE); - } else { + if (pud_huge(*pud)) + kvm_flush_dcache_pud(*pud); + else stage2_flush_pmds(kvm, pud, addr, next); - } } } while (pud++, addr = next, addr != end); } @@ -278,7 +330,7 @@ static void stage2_flush_memslot(struct kvm *kvm, * Go through the stage 2 page tables and invalidate any cache lines * backing memory already mapped to the VM. */ -void stage2_flush_vm(struct kvm *kvm) +static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -905,6 +957,12 @@ static bool kvm_is_device_pfn(unsigned long pfn) return !pfn_valid(pfn); } +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, bool uncached) +{ + __coherent_cache_guest_page(vcpu, pfn, size, uncached); +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -994,8 +1052,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pmd_writable(&new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE, - fault_ipa_uncached); + coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -1003,8 +1060,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva, PAGE_SIZE, - fault_ipa_uncached); + coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } @@ -1411,3 +1467,71 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, unmap_stage2_range(kvm, gpa, size); spin_unlock(&kvm->mmu_lock); } + +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + * + * Main problems: + * - S/W ops are local to a CPU (not broadcast) + * - We have line migration behind our back (speculation) + * - System caches don't support S/W at all (damn!) + * + * In the face of the above, the best we can do is to try and convert + * S/W ops to VA ops. Because the guest is not allowed to infer the + * S/W to PA mapping, it can only use S/W to nuke the whole cache, + * which is a rather good thing for us. + * + * Also, it is only used when turning caches on/off ("The expected + * usage of the cache maintenance instructions that operate by set/way + * is associated with the cache maintenance instructions associated + * with the powerdown and powerup of caches, if this is required by + * the implementation."). + * + * We use the following policy: + * + * - If we trap a S/W operation, we enable VM trapping to detect + * caches being turned on/off, and do a full clean. + * + * - We flush the caches on both caches being turned on and off. + * + * - Once the caches are enabled, we stop trapping VM ops. + */ +void kvm_set_way_flush(struct kvm_vcpu *vcpu) +{ + unsigned long hcr = vcpu_get_hcr(vcpu); + + /* + * If this is the first time we do a S/W operation + * (i.e. HCR_TVM not set) flush the whole memory, and set the + * VM trapping. + * + * Otherwise, rely on the VM trapping to wait for the MMU + + * Caches to be turned off. At that point, we'll be able to + * clean the caches again. + */ + if (!(hcr & HCR_TVM)) { + trace_kvm_set_way_flush(*vcpu_pc(vcpu), + vcpu_has_cache_enabled(vcpu)); + stage2_flush_vm(vcpu->kvm); + vcpu_set_hcr(vcpu, hcr | HCR_TVM); + } +} + +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) +{ + bool now_enabled = vcpu_has_cache_enabled(vcpu); + + /* + * If switching the MMU+caches on, need to invalidate the caches. + * If switching it off, need to clean the caches. + * Clean + invalidate does the trick always. + */ + if (now_enabled != was_enabled) + stage2_flush_vm(vcpu->kvm); + + /* Caches are now on, stop trapping VM ops (until a S/W op) */ + if (now_enabled) + vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) & ~HCR_TVM); + + trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); +} diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index b1d640f78623..b6a6e7102201 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -223,6 +223,45 @@ TRACE_EVENT(kvm_hvc, __entry->vcpu_pc, __entry->r0, __entry->imm) ); +TRACE_EVENT(kvm_set_way_flush, + TP_PROTO(unsigned long vcpu_pc, bool cache), + TP_ARGS(vcpu_pc, cache), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, cache ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->cache = cache; + ), + + TP_printk("S/W flush at 0x%016lx (cache %s)", + __entry->vcpu_pc, __entry->cache ? "on" : "off") +); + +TRACE_EVENT(kvm_toggle_cache, + TP_PROTO(unsigned long vcpu_pc, bool was, bool now), + TP_ARGS(vcpu_pc, was, now), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, was ) + __field( bool, now ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->was = was; + __entry->now = now; + ), + + TP_printk("VM op at 0x%016lx (cache was %s, now %s)", + __entry->vcpu_pc, __entry->was ? "on" : "off", + __entry->now ? "on" : "off") +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index caa21e9b8cd9..ccef8806bb58 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -190,6 +190,13 @@ static void __init armada_375_380_coherency_init(struct device_node *np) arch_ioremap_caller = armada_pcie_wa_ioremap_caller; /* + * We should switch the PL310 to I/O coherency mode only if + * I/O coherency is actually enabled. + */ + if (!coherency_available()) + return; + + /* * Add the PL310 property "arm,io-coherent". This makes sure the * outer sync operation is not used, which allows to * workaround the system erratum that causes deadlocks when diff --git a/arch/arm/mach-shmobile/board-ape6evm.c b/arch/arm/mach-shmobile/board-ape6evm.c index 66f67816a844..444f22d370f0 100644 --- a/arch/arm/mach-shmobile/board-ape6evm.c +++ b/arch/arm/mach-shmobile/board-ape6evm.c @@ -18,6 +18,8 @@ #include <linux/gpio_keys.h> #include <linux/input.h> #include <linux/interrupt.h> +#include <linux/irqchip.h> +#include <linux/irqchip/arm-gic.h> #include <linux/kernel.h> #include <linux/mfd/tmio.h> #include <linux/mmc/host.h> @@ -273,6 +275,22 @@ static void __init ape6evm_add_standard_devices(void) sizeof(ape6evm_leds_pdata)); } +static void __init ape6evm_legacy_init_time(void) +{ + /* Do not invoke DT-based timers via clocksource_of_init() */ +} + +static void __init ape6evm_legacy_init_irq(void) +{ + void __iomem *gic_dist_base = ioremap_nocache(0xf1001000, 0x1000); + void __iomem *gic_cpu_base = ioremap_nocache(0xf1002000, 0x1000); + + gic_init(0, 29, gic_dist_base, gic_cpu_base); + + /* Do not invoke DT-based interrupt code via irqchip_init() */ +} + + static const char *ape6evm_boards_compat_dt[] __initdata = { "renesas,ape6evm", NULL, @@ -280,7 +298,9 @@ static const char *ape6evm_boards_compat_dt[] __initdata = { DT_MACHINE_START(APE6EVM_DT, "ape6evm") .init_early = shmobile_init_delay, + .init_irq = ape6evm_legacy_init_irq, .init_machine = ape6evm_add_standard_devices, .init_late = shmobile_init_late, .dt_compat = ape6evm_boards_compat_dt, + .init_time = ape6evm_legacy_init_time, MACHINE_END diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c index f8197eb6e566..65b128dd4072 100644 --- a/arch/arm/mach-shmobile/board-lager.c +++ b/arch/arm/mach-shmobile/board-lager.c @@ -21,6 +21,8 @@ #include <linux/input.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip.h> +#include <linux/irqchip/arm-gic.h> #include <linux/kernel.h> #include <linux/leds.h> #include <linux/mfd/tmio.h> @@ -811,6 +813,16 @@ static void __init lager_init(void) lager_ksz8041_fixup); } +static void __init lager_legacy_init_irq(void) +{ + void __iomem *gic_dist_base = ioremap_nocache(0xf1001000, 0x1000); + void __iomem *gic_cpu_base = ioremap_nocache(0xf1002000, 0x1000); + + gic_init(0, 29, gic_dist_base, gic_cpu_base); + + /* Do not invoke DT-based interrupt code via irqchip_init() */ +} + static const char * const lager_boards_compat_dt[] __initconst = { "renesas,lager", NULL, @@ -819,6 +831,7 @@ static const char * const lager_boards_compat_dt[] __initconst = { DT_MACHINE_START(LAGER_DT, "lager") .smp = smp_ops(r8a7790_smp_ops), .init_early = shmobile_init_delay, + .init_irq = lager_legacy_init_irq, .init_time = rcar_gen2_timer_init, .init_machine = lager_init, .init_late = shmobile_init_late, diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c index 3dd6edd9bd1d..cc9470dfb1ce 100644 --- a/arch/arm/mach-shmobile/setup-rcar-gen2.c +++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c @@ -133,7 +133,9 @@ void __init rcar_gen2_timer_init(void) #ifdef CONFIG_COMMON_CLK rcar_gen2_clocks_init(mode); #endif +#ifdef CONFIG_ARCH_SHMOBILE_MULTI clocksource_of_init(); +#endif } struct memory_reserve_config { diff --git a/arch/arm/mach-shmobile/timer.c b/arch/arm/mach-shmobile/timer.c index f1d027aa7a81..0edf2a6d2bbe 100644 --- a/arch/arm/mach-shmobile/timer.c +++ b/arch/arm/mach-shmobile/timer.c @@ -70,6 +70,18 @@ void __init shmobile_init_delay(void) if (!max_freq) return; +#ifdef CONFIG_ARCH_SHMOBILE_LEGACY + /* Non-multiplatform r8a73a4 SoC cannot use arch timer due + * to GIC being initialized from C and arch timer via DT */ + if (of_machine_is_compatible("renesas,r8a73a4")) + has_arch_timer = false; + + /* Non-multiplatform r8a7790 SoC cannot use arch timer due + * to GIC being initialized from C and arch timer via DT */ + if (of_machine_is_compatible("renesas,r8a7790")) + has_arch_timer = false; +#endif + if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) { if (is_a7_a8_a9) shmobile_setup_delay_hz(max_freq, 1, 3); diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 03823e784f63..c43c71455566 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -1012,6 +1012,7 @@ config ARCH_SUPPORTS_BIG_ENDIAN config ARM_KERNMEM_PERMS bool "Restrict kernel memory permissions" + depends on MMU help If this is set, kernel memory other than kernel text (and rodata) will be made non-executable. The tradeoff is that each region is diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 91892569710f..845769e41332 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -144,21 +144,17 @@ static void flush_context(unsigned int cpu) /* Update the list of reserved ASIDs and the ASID bitmap. */ bitmap_clear(asid_map, 0, NUM_USER_ASIDS); for_each_possible_cpu(i) { - if (i == cpu) { - asid = 0; - } else { - asid = atomic64_xchg(&per_cpu(active_asids, i), 0); - /* - * If this CPU has already been through a - * rollover, but hasn't run another task in - * the meantime, we must preserve its reserved - * ASID, as this is the only trace we have of - * the process it is still running. - */ - if (asid == 0) - asid = per_cpu(reserved_asids, i); - __set_bit(asid & ~ASID_MASK, asid_map); - } + asid = atomic64_xchg(&per_cpu(active_asids, i), 0); + /* + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. + */ + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); per_cpu(reserved_asids, i) = asid; } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 7864797609b3..903dba064a03 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1940,13 +1940,32 @@ void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping) } EXPORT_SYMBOL_GPL(arm_iommu_release_mapping); +static int __arm_iommu_attach_device(struct device *dev, + struct dma_iommu_mapping *mapping) +{ + int err; + + err = iommu_attach_device(mapping->domain, dev); + if (err) + return err; + + kref_get(&mapping->kref); + dev->archdata.mapping = mapping; + + pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev)); + return 0; +} + /** * arm_iommu_attach_device * @dev: valid struct device pointer * @mapping: io address space mapping structure (returned from * arm_iommu_create_mapping) * - * Attaches specified io address space mapping to the provided device, + * Attaches specified io address space mapping to the provided device. + * This replaces the dma operations (dma_map_ops pointer) with the + * IOMMU aware version. + * * More than one client might be attached to the same io address space * mapping. */ @@ -1955,25 +1974,16 @@ int arm_iommu_attach_device(struct device *dev, { int err; - err = iommu_attach_device(mapping->domain, dev); + err = __arm_iommu_attach_device(dev, mapping); if (err) return err; - kref_get(&mapping->kref); - dev->archdata.mapping = mapping; - - pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev)); + set_dma_ops(dev, &iommu_ops); return 0; } EXPORT_SYMBOL_GPL(arm_iommu_attach_device); -/** - * arm_iommu_detach_device - * @dev: valid struct device pointer - * - * Detaches the provided device from a previously attached map. - */ -void arm_iommu_detach_device(struct device *dev) +static void __arm_iommu_detach_device(struct device *dev) { struct dma_iommu_mapping *mapping; @@ -1989,6 +1999,19 @@ void arm_iommu_detach_device(struct device *dev) pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); } + +/** + * arm_iommu_detach_device + * @dev: valid struct device pointer + * + * Detaches the provided device from a previously attached map. + * This voids the dma operations (dma_map_ops pointer) + */ +void arm_iommu_detach_device(struct device *dev) +{ + __arm_iommu_detach_device(dev); + set_dma_ops(dev, NULL); +} EXPORT_SYMBOL_GPL(arm_iommu_detach_device); static struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent) @@ -2011,7 +2034,7 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, return false; } - if (arm_iommu_attach_device(dev, mapping)) { + if (__arm_iommu_attach_device(dev, mapping)) { pr_warn("Failed to attached device %s to IOMMU_mapping\n", dev_name(dev)); arm_iommu_release_mapping(mapping); @@ -2025,7 +2048,10 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { struct dma_iommu_mapping *mapping = dev->archdata.mapping; - arm_iommu_detach_device(dev); + if (!mapping) + return; + + __arm_iommu_detach_device(dev); arm_iommu_release_mapping(mapping); } diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 865a7e28ea2d..3cb4c856b10d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -45,6 +45,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 &= ~HCR_RW; } +static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hcr_el2; +} + +static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr) +{ + vcpu->arch.hcr_el2 = hcr; +} + static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0b7dfdb931df..acd101a9014d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -116,9 +116,6 @@ struct kvm_vcpu_arch { * Anything that is not used directly from assembly code goes * here. */ - /* dcache set/way operation pending */ - int last_pcpu; - cpumask_t require_dcache_flush; /* Don't run the guest */ bool pause; diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 14a74f136272..adcf49547301 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -243,24 +243,46 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size, - bool ipa_uncached) +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, + unsigned long size, + bool ipa_uncached) { + void *va = page_address(pfn_to_page(pfn)); + if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) - kvm_flush_dcache_to_poc((void *)hva, size); + kvm_flush_dcache_to_poc(va, size); if (!icache_is_aliasing()) { /* PIPT */ - flush_icache_range(hva, hva + size); + flush_icache_range((unsigned long)va, + (unsigned long)va + size); } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */ /* any kind of VIPT cache */ __flush_icache_all(); } } +static inline void __kvm_flush_dcache_pte(pte_t pte) +{ + struct page *page = pte_page(pte); + kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE); +} + +static inline void __kvm_flush_dcache_pmd(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE); +} + +static inline void __kvm_flush_dcache_pud(pud_t pud) +{ + struct page *page = pud_page(pud); + kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE); +} + #define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) -void stage2_flush_vm(struct kvm *kvm); +void kvm_set_way_flush(struct kvm_vcpu *vcpu); +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 3d7c2df89946..f31e8bb2bc5b 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -69,68 +69,31 @@ static u32 get_ccsidr(u32 csselr) return ccsidr; } -static void do_dc_cisw(u32 val) -{ - asm volatile("dc cisw, %x0" : : "r" (val)); - dsb(ish); -} - -static void do_dc_csw(u32 val) -{ - asm volatile("dc csw, %x0" : : "r" (val)); - dsb(ish); -} - -/* See note at ARM ARM B1.14.4 */ +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + */ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct sys_reg_params *p, const struct sys_reg_desc *r) { - unsigned long val; - int cpu; - if (!p->is_write) return read_from_write_only(vcpu, p); - cpu = get_cpu(); - - cpumask_setall(&vcpu->arch.require_dcache_flush); - cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); - - /* If we were already preempted, take the long way around */ - if (cpu != vcpu->arch.last_pcpu) { - flush_cache_all(); - goto done; - } - - val = *vcpu_reg(vcpu, p->Rt); - - switch (p->CRm) { - case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */ - case 14: /* DCCISW */ - do_dc_cisw(val); - break; - - case 10: /* DCCSW */ - do_dc_csw(val); - break; - } - -done: - put_cpu(); - + kvm_set_way_flush(vcpu); return true; } /* * Generic accessor for VM registers. Only called as long as HCR_TVM - * is set. + * is set. If the guest enables the MMU, we stop trapping the VM + * sys_regs and leave it in complete control of the caches. */ static bool access_vm_reg(struct kvm_vcpu *vcpu, const struct sys_reg_params *p, const struct sys_reg_desc *r) { unsigned long val; + bool was_enabled = vcpu_has_cache_enabled(vcpu); BUG_ON(!p->is_write); @@ -143,25 +106,7 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL; } - return true; -} - -/* - * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set. If the - * guest enables the MMU, we stop trapping the VM sys_regs and leave - * it in complete control of the caches. - */ -static bool access_sctlr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - access_vm_reg(vcpu, p, r); - - if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ - vcpu->arch.hcr_el2 &= ~HCR_TVM; - stage2_flush_vm(vcpu->kvm); - } - + kvm_toggle_cache(vcpu, was_enabled); return true; } @@ -377,7 +322,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { NULL, reset_mpidr, MPIDR_EL1 }, /* SCTLR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000), - access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 }, + access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 }, /* CPACR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010), NULL, reset_val, CPACR_EL1, 0 }, @@ -657,7 +602,7 @@ static const struct sys_reg_desc cp14_64_regs[] = { * register). */ static const struct sys_reg_desc cp15_regs[] = { - { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR }, { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index 0eca93327195..d223a8b57c1e 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -142,6 +142,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 1790f22e71a2..2686a7aa8ec8 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -176,6 +176,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 9a66372fc7c7..ec4917ddf678 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 7225dad87094..ba5ba7accd0d 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -172,6 +172,8 @@ retry: */ if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto bad_area; } else if (fault & VM_FAULT_SIGBUS) { signal = SIGBUS; goto bad_area; diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index e9c6a8014bd6..e3d4d4890104 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -200,6 +200,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 2bd7487440c4..b2f04aee46ec 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -145,6 +145,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto map_err; else if (fault & VM_FAULT_SIGBUS) goto bus_err; BUG(); diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 332680e5ebf2..2de5dc695a87 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -141,6 +141,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index fa4cf52aa7a6..d46a5ebb7570 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -224,6 +224,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index becc42bb1849..70ab5d664332 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -158,6 +158,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 3516cbdf1ee9..0c2cc5d39c8e 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -262,6 +262,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 15a0bb5fc06d..34429d5a0ccd 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -135,6 +135,8 @@ survive: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 0703acf7d327..230ac20ae794 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -171,6 +171,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 3ca9c1131cfe..e5120e653240 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -256,6 +256,8 @@ good_area: */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto bad_area; BUG(); diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 5a236f082c78..1b5305d4bdab 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; goto out_unlock; - } else if (*flt & VM_FAULT_SIGBUS) { + } else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { ret = -EFAULT; goto out_unlock; } diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index eb79907f34fa..6154b0a2b063 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -437,6 +437,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (fault & VM_FAULT_SIGSEGV) + goto bad_area; rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) goto bail; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 811937bb90be..9065d5aa3932 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) do_no_context(regs); else pagefault_out_of_memory(); + } else if (fault & VM_FAULT_SIGSEGV) { + /* Kernel mode? Handle exceptions or die */ + if (!user_mode(regs)) + do_no_context(regs); + else + do_sigsegv(regs, SEGV_MAPERR); } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 52238983527d..6860beb2a280 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -114,6 +114,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 541dc6101508..a58fec9b55e0 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & VM_FAULT_SIGBUS) do_sigbus(regs, error_code, address); + else if (fault & VM_FAULT_SIGSEGV) + bad_area(regs, error_code, address); else BUG(); } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 908e8c17c902..70d817154fe8 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -249,6 +249,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 18fcd7167095..479823249429 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -446,6 +446,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 565e25a98334..0f61a73534e6 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -442,6 +442,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 5678c3571e7c..209617302df8 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -80,6 +80,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto out; } else if (fault & VM_FAULT_SIGBUS) { err = -EACCES; goto out; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 944bf019b74f..498b6d967138 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void) break; case 55: /* 22nm Atom "Silvermont" */ + case 76: /* 14nm Atom "Airmont" */ case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 6e434f8e5fc8..c4bb8b8e5017 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -142,7 +142,7 @@ static inline u64 rapl_scale(u64 v) * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __this_cpu_read(rapl_pmu->hw_unit)); + return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit); } static u64 rapl_event_update(struct perf_event *event) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 10b8d3eaaf15..c635b8b49e93 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id box->phys_id = phys_id; box->pci_dev = pdev; box->pmu = pmu; - uncore_box_init(box); pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); @@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu) pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); /* called by uncore_cpu_init? */ - if (box && box->phys_id >= 0) { - uncore_box_init(box); + if (box && box->phys_id >= 0) continue; - } for_each_online_cpu(k) { exist = *per_cpu_ptr(pmu->box, k); @@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu) } } - if (box) { + if (box) box->phys_id = phys_id; - uncore_box_init(box); - } } } return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 863d9b02563e..6c8c1e7e69d8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box) return box->pmu->type->num_counters; } +static inline void uncore_box_init(struct intel_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} + static inline void uncore_disable_box(struct intel_uncore_box *box) { if (box->pmu->type->ops->disable_box) @@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box) static inline void uncore_enable_box(struct intel_uncore_box *box) { + uncore_box_init(box); + if (box->pmu->type->ops->enable_box) box->pmu->type->ops->enable_box(box); } @@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box, return box->pmu->type->ops->read_counter(box, event); } -static inline void uncore_box_init(struct intel_uncore_box *box) -{ - if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { - if (box->pmu->type->ops->init_box) - box->pmu->type->ops->init_box(box); - } -} - static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4f0c0b954686..d52dcf0776ea 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -192,6 +192,9 @@ static void recalculate_apic_map(struct kvm *kvm) u16 cid, lid; u32 ldr, aid; + if (!kvm_apic_present(vcpu)) + continue; + aid = kvm_apic_id(apic); ldr = kvm_apic_get_reg(apic, APIC_LDR); cid = apic_cluster_id(new, ldr); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 38dcec403b46..e3ff27a5b634 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -898,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); else BUG(); } diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 7b20bccf3648..2fb384724ebb 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -448,6 +448,22 @@ static const struct dmi_system_id pciprobe_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"), }, }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"), + }, + }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"), + }, + }, {} }; diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index b57c4f91f487..9e3571a6535c 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -117,6 +117,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 6774a0e69867..1630a20d5dcf 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -15,26 +15,6 @@ static void blk_mq_sysfs_release(struct kobject *kobj) { - struct request_queue *q; - - q = container_of(kobj, struct request_queue, mq_kobj); - free_percpu(q->queue_ctx); -} - -static void blk_mq_ctx_release(struct kobject *kobj) -{ - struct blk_mq_ctx *ctx; - - ctx = container_of(kobj, struct blk_mq_ctx, kobj); - kobject_put(&ctx->queue->mq_kobj); -} - -static void blk_mq_hctx_release(struct kobject *kobj) -{ - struct blk_mq_hw_ctx *hctx; - - hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); - kfree(hctx); } struct blk_mq_ctx_sysfs_entry { @@ -338,13 +318,13 @@ static struct kobj_type blk_mq_ktype = { static struct kobj_type blk_mq_ctx_ktype = { .sysfs_ops = &blk_mq_sysfs_ops, .default_attrs = default_ctx_attrs, - .release = blk_mq_ctx_release, + .release = blk_mq_sysfs_release, }; static struct kobj_type blk_mq_hw_ktype = { .sysfs_ops = &blk_mq_hw_sysfs_ops, .default_attrs = default_hw_ctx_attrs, - .release = blk_mq_hctx_release, + .release = blk_mq_sysfs_release, }; static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx) @@ -375,7 +355,6 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) return ret; hctx_for_each_ctx(hctx, ctx, i) { - kobject_get(&q->mq_kobj); ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu); if (ret) break; diff --git a/block/blk-mq.c b/block/blk-mq.c index 9ee3b87c4498..2390c5541e71 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1867,6 +1867,27 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, mutex_unlock(&set->tag_list_lock); } +/* + * It is the actual release handler for mq, but we do it from + * request queue's release handler for avoiding use-after-free + * and headache because q->mq_kobj shouldn't have been introduced, + * but we can't group ctx/kctx kobj without it. + */ +void blk_mq_release(struct request_queue *q) +{ + struct blk_mq_hw_ctx *hctx; + unsigned int i; + + /* hctx kobj stays in hctx */ + queue_for_each_hw_ctx(q, hctx, i) + kfree(hctx); + + kfree(q->queue_hw_ctx); + + /* ctx kobj stays in queue_ctx */ + free_percpu(q->queue_ctx); +} + struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) { struct blk_mq_hw_ctx **hctxs; @@ -2000,10 +2021,8 @@ void blk_mq_free_queue(struct request_queue *q) percpu_ref_exit(&q->mq_usage_counter); - kfree(q->queue_hw_ctx); kfree(q->mq_map); - q->queue_hw_ctx = NULL; q->mq_map = NULL; mutex_lock(&all_q_mutex); diff --git a/block/blk-mq.h b/block/blk-mq.h index 4f4f943c22c3..6a48c4c0d8a2 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -62,6 +62,8 @@ extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_rq_timed_out(struct request *req, bool reserved); +void blk_mq_release(struct request_queue *q); + /* * Basic implementation of sparser bitmap, allowing the user to spread * the bits over more cachelines. diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 935ea2aa0730..faaf36ade7eb 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -517,6 +517,8 @@ static void blk_release_queue(struct kobject *kobj) if (!q->mq_ops) blk_free_flush_queue(q->fq); + else + blk_mq_release(q); blk_trace_shutdown(q); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 4665b79c729a..eb78fe8a60c8 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -338,49 +338,31 @@ static const struct net_proto_family alg_family = { .owner = THIS_MODULE, }; -int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len, - int write) +int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len) { - unsigned long from = (unsigned long)addr; - unsigned long npages; - unsigned off; - int err; - int i; - - err = -EFAULT; - if (!access_ok(write ? VERIFY_READ : VERIFY_WRITE, addr, len)) - goto out; - - off = from & ~PAGE_MASK; - npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (npages > ALG_MAX_PAGES) - npages = ALG_MAX_PAGES; + size_t off; + ssize_t n; + int npages, i; - err = get_user_pages_fast(from, npages, write, sgl->pages); - if (err < 0) - goto out; + n = iov_iter_get_pages(iter, sgl->pages, len, ALG_MAX_PAGES, &off); + if (n < 0) + return n; - npages = err; - err = -EINVAL; + npages = PAGE_ALIGN(off + n); if (WARN_ON(npages == 0)) - goto out; - - err = 0; + return -EINVAL; sg_init_table(sgl->sg, npages); - for (i = 0; i < npages; i++) { + for (i = 0, len = n; i < npages; i++) { int plen = min_t(int, len, PAGE_SIZE - off); sg_set_page(sgl->sg + i, sgl->pages[i], plen, off); off = 0; len -= plen; - err += plen; } - -out: - return err; + return n; } EXPORT_SYMBOL_GPL(af_alg_make_sg); diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 01f56eb7816e..01da360bdb55 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -41,8 +41,6 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; - unsigned long iovlen; - const struct iovec *iov; long copied = 0; int err; @@ -58,37 +56,28 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock, ctx->more = 0; - for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0; - iovlen--, iov++) { - unsigned long seglen = iov->iov_len; - char __user *from = iov->iov_base; + while (iov_iter_count(&msg->msg_iter)) { + int len = iov_iter_count(&msg->msg_iter); - while (seglen) { - int len = min_t(unsigned long, seglen, limit); - int newlen; + if (len > limit) + len = limit; - newlen = af_alg_make_sg(&ctx->sgl, from, len, 0); - if (newlen < 0) { - err = copied ? 0 : newlen; - goto unlock; - } - - ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL, - newlen); - - err = af_alg_wait_for_completion( - crypto_ahash_update(&ctx->req), - &ctx->completion); + len = af_alg_make_sg(&ctx->sgl, &msg->msg_iter, len); + if (len < 0) { + err = copied ? 0 : len; + goto unlock; + } - af_alg_free_sg(&ctx->sgl); + ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL, len); - if (err) - goto unlock; + err = af_alg_wait_for_completion(crypto_ahash_update(&ctx->req), + &ctx->completion); + af_alg_free_sg(&ctx->sgl); + if (err) + goto unlock; - seglen -= newlen; - from += newlen; - copied += newlen; - } + copied += len; + iov_iter_advance(&msg->msg_iter, len); } err = 0; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index c12207c8dde9..37110fd68adf 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -426,67 +426,59 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock, &ctx->req)); struct skcipher_sg_list *sgl; struct scatterlist *sg; - unsigned long iovlen; - const struct iovec *iov; int err = -EAGAIN; int used; long copied = 0; lock_sock(sk); - for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0; - iovlen--, iov++) { - unsigned long seglen = iov->iov_len; - char __user *from = iov->iov_base; - - while (seglen) { - sgl = list_first_entry(&ctx->tsgl, - struct skcipher_sg_list, list); - sg = sgl->sg; - - while (!sg->length) - sg++; - - if (!ctx->used) { - err = skcipher_wait_for_data(sk, flags); - if (err) - goto unlock; - } + while (iov_iter_count(&msg->msg_iter)) { + sgl = list_first_entry(&ctx->tsgl, + struct skcipher_sg_list, list); + sg = sgl->sg; - used = min_t(unsigned long, ctx->used, seglen); + while (!sg->length) + sg++; - used = af_alg_make_sg(&ctx->rsgl, from, used, 1); - err = used; - if (err < 0) + used = ctx->used; + if (!used) { + err = skcipher_wait_for_data(sk, flags); + if (err) goto unlock; + } + + used = min_t(unsigned long, used, iov_iter_count(&msg->msg_iter)); + + used = af_alg_make_sg(&ctx->rsgl, &msg->msg_iter, used); + err = used; + if (err < 0) + goto unlock; - if (ctx->more || used < ctx->used) - used -= used % bs; + if (ctx->more || used < ctx->used) + used -= used % bs; - err = -EINVAL; - if (!used) - goto free; + err = -EINVAL; + if (!used) + goto free; - ablkcipher_request_set_crypt(&ctx->req, sg, - ctx->rsgl.sg, used, - ctx->iv); + ablkcipher_request_set_crypt(&ctx->req, sg, + ctx->rsgl.sg, used, + ctx->iv); - err = af_alg_wait_for_completion( + err = af_alg_wait_for_completion( ctx->enc ? crypto_ablkcipher_encrypt(&ctx->req) : crypto_ablkcipher_decrypt(&ctx->req), &ctx->completion); free: - af_alg_free_sg(&ctx->rsgl); + af_alg_free_sg(&ctx->rsgl); - if (err) - goto unlock; + if (err) + goto unlock; - copied += used; - from += used; - seglen -= used; - skcipher_pull_sgl(sk, used); - } + copied += used; + skcipher_pull_sgl(sk, used); + iov_iter_advance(&msg->msg_iter, used); } err = 0; diff --git a/drivers/Kconfig b/drivers/Kconfig index 694d5a70d6ce..c70d6e45dc10 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -134,8 +134,6 @@ source "drivers/staging/Kconfig" source "drivers/platform/Kconfig" -source "drivers/soc/Kconfig" - source "drivers/clk/Kconfig" source "drivers/hwspinlock/Kconfig" diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 4f3febf8a589..e75737fd7eef 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -1,7 +1,7 @@ /* * ACPI support for Intel Lynxpoint LPSS. * - * Copyright (C) 2013, 2014, Intel Corporation + * Copyright (C) 2013, Intel Corporation * Authors: Mika Westerberg <mika.westerberg@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * @@ -60,8 +60,6 @@ ACPI_MODULE_NAME("acpi_lpss"); #define LPSS_CLK_DIVIDER BIT(2) #define LPSS_LTR BIT(3) #define LPSS_SAVE_CTX BIT(4) -#define LPSS_DEV_PROXY BIT(5) -#define LPSS_PROXY_REQ BIT(6) struct lpss_private_data; @@ -72,10 +70,8 @@ struct lpss_device_desc { void (*setup)(struct lpss_private_data *pdata); }; -static struct device *proxy_device; - static struct lpss_device_desc lpss_dma_desc = { - .flags = LPSS_CLK | LPSS_PROXY_REQ, + .flags = LPSS_CLK, }; struct lpss_private_data { @@ -150,24 +146,22 @@ static struct lpss_device_desc byt_pwm_dev_desc = { }; static struct lpss_device_desc byt_uart_dev_desc = { - .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX | - LPSS_DEV_PROXY, + .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX, .prv_offset = 0x800, .setup = lpss_uart_setup, }; static struct lpss_device_desc byt_spi_dev_desc = { - .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX | - LPSS_DEV_PROXY, + .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX, .prv_offset = 0x400, }; static struct lpss_device_desc byt_sdio_dev_desc = { - .flags = LPSS_CLK | LPSS_DEV_PROXY, + .flags = LPSS_CLK, }; static struct lpss_device_desc byt_i2c_dev_desc = { - .flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_DEV_PROXY, + .flags = LPSS_CLK | LPSS_SAVE_CTX, .prv_offset = 0x800, .setup = byt_i2c_setup, }; @@ -374,8 +368,6 @@ static int acpi_lpss_create_device(struct acpi_device *adev, adev->driver_data = pdata; pdev = acpi_create_platform_device(adev); if (!IS_ERR_OR_NULL(pdev)) { - if (!proxy_device && dev_desc->flags & LPSS_DEV_PROXY) - proxy_device = &pdev->dev; return 1; } @@ -600,14 +592,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev) if (pdata->dev_desc->flags & LPSS_SAVE_CTX) acpi_lpss_save_ctx(dev, pdata); - ret = acpi_dev_runtime_suspend(dev); - if (ret) - return ret; - - if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device) - return pm_runtime_put_sync_suspend(proxy_device); - - return 0; + return acpi_dev_runtime_suspend(dev); } static int acpi_lpss_runtime_resume(struct device *dev) @@ -615,12 +600,6 @@ static int acpi_lpss_runtime_resume(struct device *dev) struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; - if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device) { - ret = pm_runtime_get_sync(proxy_device); - if (ret) - return ret; - } - ret = acpi_dev_runtime_resume(dev); if (ret) return ret; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 3ec85dfce124..8a86b62466f7 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2098,32 +2098,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev) * If an image has a non-zero parent overlap, get a reference to its * parent. * - * We must get the reference before checking for the overlap to - * coordinate properly with zeroing the parent overlap in - * rbd_dev_v2_parent_info() when an image gets flattened. We - * drop it again if there is no overlap. - * * Returns true if the rbd device has a parent with a non-zero * overlap and a reference for it was successfully taken, or * false otherwise. */ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev) { - int counter; + int counter = 0; if (!rbd_dev->parent_spec) return false; - counter = atomic_inc_return_safe(&rbd_dev->parent_ref); - if (counter > 0 && rbd_dev->parent_overlap) - return true; - - /* Image was flattened, but parent is not yet torn down */ + down_read(&rbd_dev->header_rwsem); + if (rbd_dev->parent_overlap) + counter = atomic_inc_return_safe(&rbd_dev->parent_ref); + up_read(&rbd_dev->header_rwsem); if (counter < 0) rbd_warn(rbd_dev, "parent reference overflow"); - return false; + return counter > 0; } /* @@ -4239,7 +4233,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; - smp_mb(); rbd_dev_parent_put(rbd_dev); pr_info("%s: clone image has been flattened\n", rbd_dev->disk->disk_name); @@ -4285,7 +4278,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * treat it specially. */ rbd_dev->parent_overlap = overlap; - smp_mb(); if (!overlap) { /* A null parent_spec indicates it's the initial probe */ @@ -5114,10 +5106,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev) { struct rbd_image_header *header; - /* Drop parent reference unless it's already been done (or none) */ - - if (rbd_dev->parent_overlap) - rbd_dev_parent_put(rbd_dev); + rbd_dev_parent_put(rbd_dev); /* Free dynamic fields from the header, then zero it out */ diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 1ee27ac18de0..de4c8499cbac 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -108,6 +108,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x13d3, 0x3393) }, { USB_DEVICE(0x13d3, 0x3402) }, { USB_DEVICE(0x13d3, 0x3408) }, + { USB_DEVICE(0x13d3, 0x3423) }, { USB_DEVICE(0x13d3, 0x3432) }, /* Atheros AR5BBU12 with sflash firmware */ @@ -162,6 +163,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU22 with sflash firmware */ @@ -174,6 +176,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = { #define USB_REQ_DFU_DNLOAD 1 #define BULK_SIZE 4096 #define FW_HDR_SIZE 20 +#define TIMEGAP_USEC_MIN 50 +#define TIMEGAP_USEC_MAX 100 static int ath3k_load_firmware(struct usb_device *udev, const struct firmware *firmware) @@ -205,6 +209,9 @@ static int ath3k_load_firmware(struct usb_device *udev, pipe = usb_sndbulkpipe(udev, 0x02); while (count) { + /* workaround the compatibility issue with xHCI controller*/ + usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX); + size = min_t(uint, count, BULK_SIZE); memcpy(send_buf, firmware->data + sent, size); @@ -302,6 +309,9 @@ static int ath3k_load_fwfile(struct usb_device *udev, pipe = usb_sndbulkpipe(udev, 0x02); while (count) { + /* workaround the compatibility issue with xHCI controller*/ + usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX); + size = min_t(uint, count, BULK_SIZE); memcpy(send_buf, firmware->data + sent, size); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 4a6495ab9726..b87688881143 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -28,7 +28,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> -#define VERSION "0.6" +#define VERSION "0.7" static bool disable_scofix; static bool force_scofix; @@ -50,11 +50,16 @@ static struct usb_driver btusb_driver; #define BTUSB_BCM_PATCHRAM 0x400 #define BTUSB_MARVELL 0x800 #define BTUSB_SWAVE 0x1000 +#define BTUSB_INTEL_NEW 0x2000 +#define BTUSB_AMP 0x4000 static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ { USB_DEVICE_INFO(0xe0, 0x01, 0x01) }, + /* Generic Bluetooth AMP device */ + { USB_DEVICE_INFO(0xe0, 0x01, 0x04), .driver_info = BTUSB_AMP }, + /* Apple-specific (Broadcom) devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x05ac, 0xff, 0x01, 0x01) }, @@ -110,16 +115,24 @@ static const struct usb_device_id btusb_table[] = { { USB_DEVICE(0x13d3, 0x3404), .driver_info = BTUSB_BCM_PATCHRAM }, + /* Broadcom BCM20702B0 (Dynex/Insignia) */ + { USB_DEVICE(0x19ff, 0x0239), .driver_info = BTUSB_BCM_PATCHRAM }, + /* Foxconn - Hon Hai */ { USB_VENDOR_AND_INTERFACE_INFO(0x0489, 0xff, 0x01, 0x01), .driver_info = BTUSB_BCM_PATCHRAM }, + /* Lite-On Technology - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x04ca, 0xff, 0x01, 0x01), + .driver_info = BTUSB_BCM_PATCHRAM }, + /* Broadcom devices with vendor specific id */ { USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01), .driver_info = BTUSB_BCM_PATCHRAM }, /* ASUSTek Computer - Broadcom based */ - { USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01), + .driver_info = BTUSB_BCM_PATCHRAM }, /* Belkin F8065bf - Broadcom based */ { USB_VENDOR_AND_INTERFACE_INFO(0x050d, 0xff, 0x01, 0x01) }, @@ -189,6 +202,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU12 with sflash firmware */ @@ -253,13 +267,18 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x16d3, 0x0002), .driver_info = BTUSB_SNIFFER | BTUSB_BROKEN_ISOC }, - /* Intel Bluetooth device */ + /* Marvell Bluetooth devices */ + { USB_DEVICE(0x1286, 0x2044), .driver_info = BTUSB_MARVELL }, + { USB_DEVICE(0x1286, 0x2046), .driver_info = BTUSB_MARVELL }, + + /* Intel Bluetooth devices */ { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL }, { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL }, + { USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_NEW }, - /* Marvell device */ - { USB_DEVICE(0x1286, 0x2044), .driver_info = BTUSB_MARVELL }, - { USB_DEVICE(0x1286, 0x2046), .driver_info = BTUSB_MARVELL }, + /* Other Intel Bluetooth devices */ + { USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01), + .driver_info = BTUSB_IGNORE }, { } /* Terminating entry */ }; @@ -271,6 +290,11 @@ static const struct usb_device_id blacklist_table[] = { #define BTUSB_ISOC_RUNNING 2 #define BTUSB_SUSPENDING 3 #define BTUSB_DID_ISO_RESUME 4 +#define BTUSB_BOOTLOADER 5 +#define BTUSB_DOWNLOADING 6 +#define BTUSB_FIRMWARE_LOADED 7 +#define BTUSB_FIRMWARE_FAILED 8 +#define BTUSB_BOOTING 9 struct btusb_data { struct hci_dev *hdev; @@ -304,6 +328,7 @@ struct btusb_data { struct usb_endpoint_descriptor *isoc_rx_ep; __u8 cmdreq_type; + __u8 cmdreq; unsigned int sco_num; int isoc_altsetting; @@ -313,6 +338,16 @@ struct btusb_data { int (*recv_bulk)(struct btusb_data *data, void *buffer, int count); }; +static int btusb_wait_on_bit_timeout(void *word, int bit, unsigned long timeout, + unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, + mode, timeout); +} + static inline void btusb_free_frags(struct btusb_data *data) { unsigned long flags; @@ -957,7 +992,7 @@ static struct urb *alloc_ctrl_urb(struct hci_dev *hdev, struct sk_buff *skb) } dr->bRequestType = data->cmdreq_type; - dr->bRequest = 0; + dr->bRequest = data->cmdreq; dr->wIndex = 0; dr->wValue = 0; dr->wLength = __cpu_to_le16(skb->len); @@ -1295,6 +1330,26 @@ struct intel_version { u8 fw_patch_num; } __packed; +struct intel_boot_params { + __u8 status; + __u8 otp_format; + __u8 otp_content; + __u8 otp_patch; + __le16 dev_revid; + __u8 secure_boot; + __u8 key_from_hdr; + __u8 key_type; + __u8 otp_lock; + __u8 api_lock; + __u8 debug_lock; + bdaddr_t otp_bdaddr; + __u8 min_fw_build_nn; + __u8 min_fw_build_cw; + __u8 min_fw_build_yy; + __u8 limited_cce; + __u8 unlocked_state; +} __packed; + static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev, struct intel_version *ver) { @@ -1703,6 +1758,562 @@ exit_mfg_deactivate: return 0; } +static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode) +{ + struct sk_buff *skb; + struct hci_event_hdr *hdr; + struct hci_ev_cmd_complete *evt; + + skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + hdr = (struct hci_event_hdr *)skb_put(skb, sizeof(*hdr)); + hdr->evt = HCI_EV_CMD_COMPLETE; + hdr->plen = sizeof(*evt) + 1; + + evt = (struct hci_ev_cmd_complete *)skb_put(skb, sizeof(*evt)); + evt->ncmd = 0x01; + evt->opcode = cpu_to_le16(opcode); + + *skb_put(skb, 1) = 0x00; + + bt_cb(skb)->pkt_type = HCI_EVENT_PKT; + + return hci_recv_frame(hdev, skb); +} + +static int btusb_recv_bulk_intel(struct btusb_data *data, void *buffer, + int count) +{ + /* When the device is in bootloader mode, then it can send + * events via the bulk endpoint. These events are treated the + * same way as the ones received from the interrupt endpoint. + */ + if (test_bit(BTUSB_BOOTLOADER, &data->flags)) + return btusb_recv_intr(data, buffer, count); + + return btusb_recv_bulk(data, buffer, count); +} + +static int btusb_recv_event_intel(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + + if (test_bit(BTUSB_BOOTLOADER, &data->flags)) { + struct hci_event_hdr *hdr = (void *)skb->data; + + /* When the firmware loading completes the device sends + * out a vendor specific event indicating the result of + * the firmware loading. + */ + if (skb->len == 7 && hdr->evt == 0xff && hdr->plen == 0x05 && + skb->data[2] == 0x06) { + if (skb->data[3] != 0x00) + test_bit(BTUSB_FIRMWARE_FAILED, &data->flags); + + if (test_and_clear_bit(BTUSB_DOWNLOADING, + &data->flags) && + test_bit(BTUSB_FIRMWARE_LOADED, &data->flags)) { + smp_mb__after_atomic(); + wake_up_bit(&data->flags, BTUSB_DOWNLOADING); + } + } + + /* When switching to the operational firmware the device + * sends a vendor specific event indicating that the bootup + * completed. + */ + if (skb->len == 9 && hdr->evt == 0xff && hdr->plen == 0x07 && + skb->data[2] == 0x02) { + if (test_and_clear_bit(BTUSB_BOOTING, &data->flags)) { + smp_mb__after_atomic(); + wake_up_bit(&data->flags, BTUSB_BOOTING); + } + } + } + + return hci_recv_frame(hdev, skb); +} + +static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + struct urb *urb; + + BT_DBG("%s", hdev->name); + + if (!test_bit(HCI_RUNNING, &hdev->flags)) + return -EBUSY; + + switch (bt_cb(skb)->pkt_type) { + case HCI_COMMAND_PKT: + if (test_bit(BTUSB_BOOTLOADER, &data->flags)) { + struct hci_command_hdr *cmd = (void *)skb->data; + __u16 opcode = le16_to_cpu(cmd->opcode); + + /* When in bootloader mode and the command 0xfc09 + * is received, it needs to be send down the + * bulk endpoint. So allocate a bulk URB instead. + */ + if (opcode == 0xfc09) + urb = alloc_bulk_urb(hdev, skb); + else + urb = alloc_ctrl_urb(hdev, skb); + + /* When the 0xfc01 command is issued to boot into + * the operational firmware, it will actually not + * send a command complete event. To keep the flow + * control working inject that event here. + */ + if (opcode == 0xfc01) + inject_cmd_complete(hdev, opcode); + } else { + urb = alloc_ctrl_urb(hdev, skb); + } + if (IS_ERR(urb)) + return PTR_ERR(urb); + + hdev->stat.cmd_tx++; + return submit_or_queue_tx_urb(hdev, urb); + + case HCI_ACLDATA_PKT: + urb = alloc_bulk_urb(hdev, skb); + if (IS_ERR(urb)) + return PTR_ERR(urb); + + hdev->stat.acl_tx++; + return submit_or_queue_tx_urb(hdev, urb); + + case HCI_SCODATA_PKT: + if (hci_conn_num(hdev, SCO_LINK) < 1) + return -ENODEV; + + urb = alloc_isoc_urb(hdev, skb); + if (IS_ERR(urb)) + return PTR_ERR(urb); + + hdev->stat.sco_tx++; + return submit_tx_urb(hdev, urb); + } + + return -EILSEQ; +} + +static int btusb_intel_secure_send(struct hci_dev *hdev, u8 fragment_type, + u32 plen, const void *param) +{ + while (plen > 0) { + struct sk_buff *skb; + u8 cmd_param[253], fragment_len = (plen > 252) ? 252 : plen; + + cmd_param[0] = fragment_type; + memcpy(cmd_param + 1, param, fragment_len); + + skb = __hci_cmd_sync(hdev, 0xfc09, fragment_len + 1, + cmd_param, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + kfree_skb(skb); + + plen -= fragment_len; + param += fragment_len; + } + + return 0; +} + +static void btusb_intel_version_info(struct hci_dev *hdev, + struct intel_version *ver) +{ + const char *variant; + + switch (ver->fw_variant) { + case 0x06: + variant = "Bootloader"; + break; + case 0x23: + variant = "Firmware"; + break; + default: + return; + } + + BT_INFO("%s: %s revision %u.%u build %u week %u %u", hdev->name, + variant, ver->fw_revision >> 4, ver->fw_revision & 0x0f, + ver->fw_build_num, ver->fw_build_ww, 2000 + ver->fw_build_yy); +} + +static int btusb_setup_intel_new(struct hci_dev *hdev) +{ + static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01, + 0x00, 0x08, 0x04, 0x00 }; + struct btusb_data *data = hci_get_drvdata(hdev); + struct sk_buff *skb; + struct intel_version *ver; + struct intel_boot_params *params; + const struct firmware *fw; + const u8 *fw_ptr; + char fwname[64]; + ktime_t calltime, delta, rettime; + unsigned long long duration; + int err; + + BT_DBG("%s", hdev->name); + + calltime = ktime_get(); + + /* Read the Intel version information to determine if the device + * is in bootloader mode or if it already has operational firmware + * loaded. + */ + skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: Reading Intel version information failed (%ld)", + hdev->name, PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != sizeof(*ver)) { + BT_ERR("%s: Intel version event size mismatch", hdev->name); + kfree_skb(skb); + return -EILSEQ; + } + + ver = (struct intel_version *)skb->data; + if (ver->status) { + BT_ERR("%s: Intel version command failure (%02x)", + hdev->name, ver->status); + err = -bt_to_errno(ver->status); + kfree_skb(skb); + return err; + } + + /* The hardware platform number has a fixed value of 0x37 and + * for now only accept this single value. + */ + if (ver->hw_platform != 0x37) { + BT_ERR("%s: Unsupported Intel hardware platform (%u)", + hdev->name, ver->hw_platform); + kfree_skb(skb); + return -EINVAL; + } + + /* At the moment only the hardware variant iBT 3.0 (LnP/SfP) is + * supported by this firmware loading method. This check has been + * put in place to ensure correct forward compatibility options + * when newer hardware variants come along. + */ + if (ver->hw_variant != 0x0b) { + BT_ERR("%s: Unsupported Intel hardware variant (%u)", + hdev->name, ver->hw_variant); + kfree_skb(skb); + return -EINVAL; + } + + btusb_intel_version_info(hdev, ver); + + /* The firmware variant determines if the device is in bootloader + * mode or is running operational firmware. The value 0x06 identifies + * the bootloader and the value 0x23 identifies the operational + * firmware. + * + * When the operational firmware is already present, then only + * the check for valid Bluetooth device address is needed. This + * determines if the device will be added as configured or + * unconfigured controller. + * + * It is not possible to use the Secure Boot Parameters in this + * case since that command is only available in bootloader mode. + */ + if (ver->fw_variant == 0x23) { + kfree_skb(skb); + clear_bit(BTUSB_BOOTLOADER, &data->flags); + btusb_check_bdaddr_intel(hdev); + return 0; + } + + /* If the device is not in bootloader mode, then the only possible + * choice is to return an error and abort the device initialization. + */ + if (ver->fw_variant != 0x06) { + BT_ERR("%s: Unsupported Intel firmware variant (%u)", + hdev->name, ver->fw_variant); + kfree_skb(skb); + return -ENODEV; + } + + kfree_skb(skb); + + /* Read the secure boot parameters to identify the operating + * details of the bootloader. + */ + skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: Reading Intel boot parameters failed (%ld)", + hdev->name, PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != sizeof(*params)) { + BT_ERR("%s: Intel boot parameters size mismatch", hdev->name); + kfree_skb(skb); + return -EILSEQ; + } + + params = (struct intel_boot_params *)skb->data; + if (params->status) { + BT_ERR("%s: Intel boot parameters command failure (%02x)", + hdev->name, params->status); + err = -bt_to_errno(params->status); + kfree_skb(skb); + return err; + } + + BT_INFO("%s: Device revision is %u", hdev->name, + le16_to_cpu(params->dev_revid)); + + BT_INFO("%s: Secure boot is %s", hdev->name, + params->secure_boot ? "enabled" : "disabled"); + + BT_INFO("%s: Minimum firmware build %u week %u %u", hdev->name, + params->min_fw_build_nn, params->min_fw_build_cw, + 2000 + params->min_fw_build_yy); + + /* It is required that every single firmware fragment is acknowledged + * with a command complete event. If the boot parameters indicate + * that this bootloader does not send them, then abort the setup. + */ + if (params->limited_cce != 0x00) { + BT_ERR("%s: Unsupported Intel firmware loading method (%u)", + hdev->name, params->limited_cce); + kfree_skb(skb); + return -EINVAL; + } + + /* If the OTP has no valid Bluetooth device address, then there will + * also be no valid address for the operational firmware. + */ + if (!bacmp(¶ms->otp_bdaddr, BDADDR_ANY)) { + BT_INFO("%s: No device address configured", hdev->name); + set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + } + + /* With this Intel bootloader only the hardware variant and device + * revision information are used to select the right firmware. + * + * Currently this bootloader support is limited to hardware variant + * iBT 3.0 (LnP/SfP) which is identified by the value 11 (0x0b). + */ + snprintf(fwname, sizeof(fwname), "intel/ibt-11-%u.sfi", + le16_to_cpu(params->dev_revid)); + + err = request_firmware(&fw, fwname, &hdev->dev); + if (err < 0) { + BT_ERR("%s: Failed to load Intel firmware file (%d)", + hdev->name, err); + kfree_skb(skb); + return err; + } + + BT_INFO("%s: Found device firmware: %s", hdev->name, fwname); + + kfree_skb(skb); + + if (fw->size < 644) { + BT_ERR("%s: Invalid size of firmware file (%zu)", + hdev->name, fw->size); + err = -EBADF; + goto done; + } + + set_bit(BTUSB_DOWNLOADING, &data->flags); + + /* Start the firmware download transaction with the Init fragment + * represented by the 128 bytes of CSS header. + */ + err = btusb_intel_secure_send(hdev, 0x00, 128, fw->data); + if (err < 0) { + BT_ERR("%s: Failed to send firmware header (%d)", + hdev->name, err); + goto done; + } + + /* Send the 256 bytes of public key information from the firmware + * as the PKey fragment. + */ + err = btusb_intel_secure_send(hdev, 0x03, 256, fw->data + 128); + if (err < 0) { + BT_ERR("%s: Failed to send firmware public key (%d)", + hdev->name, err); + goto done; + } + + /* Send the 256 bytes of signature information from the firmware + * as the Sign fragment. + */ + err = btusb_intel_secure_send(hdev, 0x02, 256, fw->data + 388); + if (err < 0) { + BT_ERR("%s: Failed to send firmware signature (%d)", + hdev->name, err); + goto done; + } + + fw_ptr = fw->data + 644; + + while (fw_ptr - fw->data < fw->size) { + struct hci_command_hdr *cmd = (void *)fw_ptr; + u8 cmd_len; + + cmd_len = sizeof(*cmd) + cmd->plen; + + /* Send each command from the firmware data buffer as + * a single Data fragment. + */ + err = btusb_intel_secure_send(hdev, 0x01, cmd_len, fw_ptr); + if (err < 0) { + BT_ERR("%s: Failed to send firmware data (%d)", + hdev->name, err); + goto done; + } + + fw_ptr += cmd_len; + } + + set_bit(BTUSB_FIRMWARE_LOADED, &data->flags); + + BT_INFO("%s: Waiting for firmware download to complete", hdev->name); + + /* Before switching the device into operational mode and with that + * booting the loaded firmware, wait for the bootloader notification + * that all fragments have been successfully received. + * + * When the event processing receives the notification, then the + * BTUSB_DOWNLOADING flag will be cleared. + * + * The firmware loading should not take longer than 5 seconds + * and thus just timeout if that happens and fail the setup + * of this device. + */ + err = btusb_wait_on_bit_timeout(&data->flags, BTUSB_DOWNLOADING, + msecs_to_jiffies(5000), + TASK_INTERRUPTIBLE); + if (err == 1) { + BT_ERR("%s: Firmware loading interrupted", hdev->name); + err = -EINTR; + goto done; + } + + if (err) { + BT_ERR("%s: Firmware loading timeout", hdev->name); + err = -ETIMEDOUT; + goto done; + } + + if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) { + BT_ERR("%s: Firmware loading failed", hdev->name); + err = -ENOEXEC; + goto done; + } + + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + duration = (unsigned long long) ktime_to_ns(delta) >> 10; + + BT_INFO("%s: Firmware loaded in %llu usecs", hdev->name, duration); + +done: + release_firmware(fw); + + if (err < 0) + return err; + + calltime = ktime_get(); + + set_bit(BTUSB_BOOTING, &data->flags); + + skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + kfree_skb(skb); + + /* The bootloader will not indicate when the device is ready. This + * is done by the operational firmware sending bootup notification. + * + * Booting into operational firmware should not take longer than + * 1 second. However if that happens, then just fail the setup + * since something went wrong. + */ + BT_INFO("%s: Waiting for device to boot", hdev->name); + + err = btusb_wait_on_bit_timeout(&data->flags, BTUSB_BOOTING, + msecs_to_jiffies(1000), + TASK_INTERRUPTIBLE); + + if (err == 1) { + BT_ERR("%s: Device boot interrupted", hdev->name); + return -EINTR; + } + + if (err) { + BT_ERR("%s: Device boot timeout", hdev->name); + return -ETIMEDOUT; + } + + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + duration = (unsigned long long) ktime_to_ns(delta) >> 10; + + BT_INFO("%s: Device booted in %llu usecs", hdev->name, duration); + + clear_bit(BTUSB_BOOTLOADER, &data->flags); + + return 0; +} + +static void btusb_hw_error_intel(struct hci_dev *hdev, u8 code) +{ + struct sk_buff *skb; + u8 type = 0x00; + + BT_ERR("%s: Hardware error 0x%2.2x", hdev->name, code); + + skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: Reset after hardware error failed (%ld)", + hdev->name, PTR_ERR(skb)); + return; + } + kfree_skb(skb); + + skb = __hci_cmd_sync(hdev, 0xfc22, 1, &type, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + BT_ERR("%s: Retrieving Intel exception info failed (%ld)", + hdev->name, PTR_ERR(skb)); + return; + } + + if (skb->len != 13) { + BT_ERR("%s: Exception info size mismatch", hdev->name); + kfree_skb(skb); + return; + } + + if (skb->data[0] != 0x00) { + BT_ERR("%s: Exception info command failure (%02x)", + hdev->name, skb->data[0]); + kfree_skb(skb); + return; + } + + BT_ERR("%s: Exception info %s", hdev->name, (char *)(skb->data + 1)); + + kfree_skb(skb); +} + static int btusb_set_bdaddr_intel(struct hci_dev *hdev, const bdaddr_t *bdaddr) { struct sk_buff *skb; @@ -2033,7 +2644,13 @@ static int btusb_probe(struct usb_interface *intf, if (!data->intr_ep || !data->bulk_tx_ep || !data->bulk_rx_ep) return -ENODEV; - data->cmdreq_type = USB_TYPE_CLASS; + if (id->driver_info & BTUSB_AMP) { + data->cmdreq_type = USB_TYPE_CLASS | 0x01; + data->cmdreq = 0x2b; + } else { + data->cmdreq_type = USB_TYPE_CLASS; + data->cmdreq = 0x00; + } data->udev = interface_to_usbdev(intf); data->intf = intf; @@ -2049,8 +2666,14 @@ static int btusb_probe(struct usb_interface *intf, init_usb_anchor(&data->isoc_anchor); spin_lock_init(&data->rxlock); - data->recv_event = hci_recv_frame; - data->recv_bulk = btusb_recv_bulk; + if (id->driver_info & BTUSB_INTEL_NEW) { + data->recv_event = btusb_recv_event_intel; + data->recv_bulk = btusb_recv_bulk_intel; + set_bit(BTUSB_BOOTLOADER, &data->flags); + } else { + data->recv_event = hci_recv_frame; + data->recv_bulk = btusb_recv_bulk; + } hdev = hci_alloc_dev(); if (!hdev) @@ -2059,6 +2682,11 @@ static int btusb_probe(struct usb_interface *intf, hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); + if (id->driver_info & BTUSB_AMP) + hdev->dev_type = HCI_AMP; + else + hdev->dev_type = HCI_BREDR; + data->hdev = hdev; SET_HCIDEV_DEV(hdev, &intf->dev); @@ -2081,6 +2709,15 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_INTEL) { hdev->setup = btusb_setup_intel; hdev->set_bdaddr = btusb_set_bdaddr_intel; + set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); + } + + if (id->driver_info & BTUSB_INTEL_NEW) { + hdev->send = btusb_send_frame_intel; + hdev->setup = btusb_setup_intel_new; + hdev->hw_error = btusb_hw_error_intel; + hdev->set_bdaddr = btusb_set_bdaddr_intel; + set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); } if (id->driver_info & BTUSB_MARVELL) @@ -2094,11 +2731,18 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_INTEL_BOOT) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); - if (id->driver_info & BTUSB_ATH3012) + if (id->driver_info & BTUSB_ATH3012) { hdev->set_bdaddr = btusb_set_bdaddr_ath3012; + set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); + } - /* Interface numbers are hardcoded in the specification */ - data->isoc = usb_ifnum_to_if(data->udev, 1); + if (id->driver_info & BTUSB_AMP) { + /* AMP controllers do not support SCO packets */ + data->isoc = NULL; + } else { + /* Interface numbers are hardcoded in the specification */ + data->isoc = usb_ifnum_to_if(data->udev, 1); + } if (!reset) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); @@ -2192,7 +2836,6 @@ static void btusb_disconnect(struct usb_interface *intf) else if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); - btusb_free_frags(data); hci_free_dev(hdev); } diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c index da9c316059bc..eea5d7e578c9 100644 --- a/drivers/gpio/gpio-mcp23s08.c +++ b/drivers/gpio/gpio-mcp23s08.c @@ -801,9 +801,11 @@ static int mcp230xx_probe(struct i2c_client *client, client->irq = irq_of_parse_and_map(client->dev.of_node, 0); } else { pdata = dev_get_platdata(&client->dev); - if (!pdata || !gpio_is_valid(pdata->base)) { - dev_dbg(&client->dev, "invalid platform data\n"); - return -EINVAL; + if (!pdata) { + pdata = devm_kzalloc(&client->dev, + sizeof(struct mcp23s08_platform_data), + GFP_KERNEL); + pdata->base = -1; } } @@ -924,10 +926,11 @@ static int mcp23s08_probe(struct spi_device *spi) } else { type = spi_get_device_id(spi)->driver_data; pdata = dev_get_platdata(&spi->dev); - if (!pdata || !gpio_is_valid(pdata->base)) { - dev_dbg(&spi->dev, - "invalid or missing platform data\n"); - return -EINVAL; + if (!pdata) { + pdata = devm_kzalloc(&spi->dev, + sizeof(struct mcp23s08_platform_data), + GFP_KERNEL); + pdata->base = -1; } for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) { diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 30646cfe0efa..f476ae2eb0b3 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -88,6 +88,8 @@ struct gpio_bank { #define BANK_USED(bank) (bank->mod_usage || bank->irq_usage) #define LINE_USED(line, offset) (line & (BIT(offset))) +static void omap_gpio_unmask_irq(struct irq_data *d); + static int omap_irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq) { return bank->chip.base + gpio_irq; @@ -477,6 +479,16 @@ static int omap_gpio_is_input(struct gpio_bank *bank, int mask) return readl_relaxed(reg) & mask; } +static void omap_gpio_init_irq(struct gpio_bank *bank, unsigned gpio, + unsigned offset) +{ + if (!LINE_USED(bank->mod_usage, offset)) { + omap_enable_gpio_module(bank, offset); + omap_set_gpio_direction(bank, offset, 1); + } + bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio)); +} + static int omap_gpio_irq_type(struct irq_data *d, unsigned type) { struct gpio_bank *bank = omap_irq_data_get_bank(d); @@ -506,15 +518,11 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type) spin_lock_irqsave(&bank->lock, flags); offset = GPIO_INDEX(bank, gpio); retval = omap_set_gpio_triggering(bank, offset, type); - if (!LINE_USED(bank->mod_usage, offset)) { - omap_enable_gpio_module(bank, offset); - omap_set_gpio_direction(bank, offset, 1); - } else if (!omap_gpio_is_input(bank, BIT(offset))) { + omap_gpio_init_irq(bank, gpio, offset); + if (!omap_gpio_is_input(bank, BIT(offset))) { spin_unlock_irqrestore(&bank->lock, flags); return -EINVAL; } - - bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio)); spin_unlock_irqrestore(&bank->lock, flags); if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) @@ -792,6 +800,24 @@ exit: pm_runtime_put(bank->dev); } +static unsigned int omap_gpio_irq_startup(struct irq_data *d) +{ + struct gpio_bank *bank = omap_irq_data_get_bank(d); + unsigned int gpio = omap_irq_to_gpio(bank, d->hwirq); + unsigned long flags; + unsigned offset = GPIO_INDEX(bank, gpio); + + if (!BANK_USED(bank)) + pm_runtime_get_sync(bank->dev); + + spin_lock_irqsave(&bank->lock, flags); + omap_gpio_init_irq(bank, gpio, offset); + spin_unlock_irqrestore(&bank->lock, flags); + omap_gpio_unmask_irq(d); + + return 0; +} + static void omap_gpio_irq_shutdown(struct irq_data *d) { struct gpio_bank *bank = omap_irq_data_get_bank(d); @@ -1181,6 +1207,7 @@ static int omap_gpio_probe(struct platform_device *pdev) if (!irqc) return -ENOMEM; + irqc->irq_startup = omap_gpio_irq_startup, irqc->irq_shutdown = omap_gpio_irq_shutdown, irqc->irq_ack = omap_gpio_ack_irq, irqc->irq_mask = omap_gpio_mask_irq, diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index f62aa115d79a..7722ed53bd65 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -648,6 +648,7 @@ int gpiod_export_link(struct device *dev, const char *name, if (tdev != NULL) { status = sysfs_create_link(&dev->kobj, &tdev->kobj, name); + put_device(tdev); } else { status = -ENODEV; } @@ -695,7 +696,7 @@ int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value) } status = sysfs_set_active_low(desc, dev, value); - + put_device(dev); unlock: mutex_unlock(&sysfs_lock); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 633532a2e7ec..25bc47f3c1cf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -26,6 +26,7 @@ #include <linux/slab.h> #include "kfd_priv.h" #include "kfd_device_queue_manager.h" +#include "kfd_pm4_headers.h" #define MQD_SIZE_ALIGNED 768 @@ -169,9 +170,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd->shared_resources = *gpu_resources; /* calculate max size of mqds needed for queues */ - size = max_num_of_processes * - max_num_of_queues_per_process * - kfd->device_info->mqd_size_aligned; + size = max_num_of_queues_per_device * + kfd->device_info->mqd_size_aligned; /* add another 512KB for all other allocations on gart */ size += 512 * 1024; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 30c8fda9622e..0fd592799d58 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -183,6 +183,13 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, mutex_lock(&dqm->lock); + if (dqm->total_queue_count >= max_num_of_queues_per_device) { + pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n", + dqm->total_queue_count); + mutex_unlock(&dqm->lock); + return -EPERM; + } + if (list_empty(&qpd->queues_list)) { retval = allocate_vmid(dqm, qpd, q); if (retval != 0) { @@ -207,6 +214,14 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, list_add(&q->list, &qpd->queues_list); dqm->queue_count++; + /* + * Unconditionally increment this counter, regardless of the queue's + * type or whether the queue is active. + */ + dqm->total_queue_count++; + pr_debug("Total of %d queues are accountable so far\n", + dqm->total_queue_count); + mutex_unlock(&dqm->lock); return 0; } @@ -326,6 +341,15 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, if (list_empty(&qpd->queues_list)) deallocate_vmid(dqm, qpd, q); dqm->queue_count--; + + /* + * Unconditionally decrement this counter, regardless of the queue's + * type + */ + dqm->total_queue_count--; + pr_debug("Total of %d queues are accountable so far\n", + dqm->total_queue_count); + out: mutex_unlock(&dqm->lock); return retval; @@ -541,10 +565,14 @@ static int init_pipelines(struct device_queue_manager *dqm, for (i = 0; i < pipes_num; i++) { inx = i + first_pipe; + /* + * HPD buffer on GTT is allocated by amdkfd, no need to waste + * space in GTT for pipelines we don't initialize + */ pipe_hpd_addr = dqm->pipelines_addr + i * CIK_HPD_EOP_BYTES; pr_debug("kfd: pipeline address %llX\n", pipe_hpd_addr); /* = log2(bytes/4)-1 */ - kfd2kgd->init_pipeline(dqm->dev->kgd, i, + kfd2kgd->init_pipeline(dqm->dev->kgd, inx, CIK_HPD_EOP_BYTES_LOG2 - 3, pipe_hpd_addr); } @@ -560,7 +588,7 @@ static int init_scheduler(struct device_queue_manager *dqm) pr_debug("kfd: In %s\n", __func__); - retval = init_pipelines(dqm, get_pipes_num(dqm), KFD_DQM_FIRST_PIPE); + retval = init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm)); if (retval != 0) return retval; @@ -752,6 +780,21 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, pr_debug("kfd: In func %s\n", __func__); mutex_lock(&dqm->lock); + if (dqm->total_queue_count >= max_num_of_queues_per_device) { + pr_warn("amdkfd: Can't create new kernel queue because %d queues were already created\n", + dqm->total_queue_count); + mutex_unlock(&dqm->lock); + return -EPERM; + } + + /* + * Unconditionally increment this counter, regardless of the queue's + * type or whether the queue is active. + */ + dqm->total_queue_count++; + pr_debug("Total of %d queues are accountable so far\n", + dqm->total_queue_count); + list_add(&kq->list, &qpd->priv_queue_list); dqm->queue_count++; qpd->is_debug = true; @@ -775,6 +818,13 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->queue_count--; qpd->is_debug = false; execute_queues_cpsch(dqm, false); + /* + * Unconditionally decrement this counter, regardless of the queue's + * type. + */ + dqm->total_queue_count--; + pr_debug("Total of %d queues are accountable so far\n", + dqm->total_queue_count); mutex_unlock(&dqm->lock); } @@ -793,6 +843,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, mutex_lock(&dqm->lock); + if (dqm->total_queue_count >= max_num_of_queues_per_device) { + pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n", + dqm->total_queue_count); + retval = -EPERM; + goto out; + } + mqd = dqm->get_mqd_manager(dqm, KFD_MQD_TYPE_CIK_CP); if (mqd == NULL) { mutex_unlock(&dqm->lock); @@ -810,6 +867,15 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, retval = execute_queues_cpsch(dqm, false); } + /* + * Unconditionally increment this counter, regardless of the queue's + * type or whether the queue is active. + */ + dqm->total_queue_count++; + + pr_debug("Total of %d queues are accountable so far\n", + dqm->total_queue_count); + out: mutex_unlock(&dqm->lock); return retval; @@ -930,6 +996,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + /* + * Unconditionally decrement this counter, regardless of the queue's + * type + */ + dqm->total_queue_count--; + pr_debug("Total of %d queues are accountable so far\n", + dqm->total_queue_count); + mutex_unlock(&dqm->lock); return 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index c3f189e8ae35..52035bf0c1cb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -130,6 +130,7 @@ struct device_queue_manager { struct list_head queues; unsigned int processes_count; unsigned int queue_count; + unsigned int total_queue_count; unsigned int next_pipe_to_allocate; unsigned int *allocated_queues; unsigned int vmid_bitmap; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c index 95d5af138e6e..1c385c23dd0b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c @@ -50,15 +50,10 @@ module_param(sched_policy, int, 0444); MODULE_PARM_DESC(sched_policy, "Kernel cmdline parameter that defines the amdkfd scheduling policy"); -int max_num_of_processes = KFD_MAX_NUM_OF_PROCESSES_DEFAULT; -module_param(max_num_of_processes, int, 0444); -MODULE_PARM_DESC(max_num_of_processes, - "Kernel cmdline parameter that defines the amdkfd maximum number of supported processes"); - -int max_num_of_queues_per_process = KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT; -module_param(max_num_of_queues_per_process, int, 0444); -MODULE_PARM_DESC(max_num_of_queues_per_process, - "Kernel cmdline parameter that defines the amdkfd maximum number of supported queues per process"); +int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT; +module_param(max_num_of_queues_per_device, int, 0444); +MODULE_PARM_DESC(max_num_of_queues_per_device, + "Maximum number of supported queues per device (1 = Minimum, 4096 = default)"); bool kgd2kfd_init(unsigned interface_version, const struct kfd2kgd_calls *f2g, @@ -100,16 +95,10 @@ static int __init kfd_module_init(void) } /* Verify module parameters */ - if ((max_num_of_processes < 0) || - (max_num_of_processes > KFD_MAX_NUM_OF_PROCESSES)) { - pr_err("kfd: max_num_of_processes must be between 0 to KFD_MAX_NUM_OF_PROCESSES\n"); - return -1; - } - - if ((max_num_of_queues_per_process < 0) || - (max_num_of_queues_per_process > - KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)) { - pr_err("kfd: max_num_of_queues_per_process must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_PROCESS\n"); + if ((max_num_of_queues_per_device < 1) || + (max_num_of_queues_per_device > + KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) { + pr_err("kfd: max_num_of_queues_per_device must be between 1 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n"); return -1; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c index 4c25ef504f79..6cfe7f1f18cf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c @@ -30,7 +30,7 @@ static DEFINE_MUTEX(pasid_mutex); int kfd_pasid_init(void) { - pasid_limit = max_num_of_processes; + pasid_limit = KFD_MAX_NUM_OF_PROCESSES; pasid_bitmap = kcalloc(BITS_TO_LONGS(pasid_limit), sizeof(long), GFP_KERNEL); if (!pasid_bitmap) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index b3dc13c83169..96dc10e8904a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -52,20 +52,19 @@ #define kfd_alloc_struct(ptr_to_struct) \ ((typeof(ptr_to_struct)) kzalloc(sizeof(*ptr_to_struct), GFP_KERNEL)) -/* Kernel module parameter to specify maximum number of supported processes */ -extern int max_num_of_processes; - -#define KFD_MAX_NUM_OF_PROCESSES_DEFAULT 32 #define KFD_MAX_NUM_OF_PROCESSES 512 +#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024 /* - * Kernel module parameter to specify maximum number of supported queues - * per process + * Kernel module parameter to specify maximum number of supported queues per + * device */ -extern int max_num_of_queues_per_process; +extern int max_num_of_queues_per_device; -#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT 128 -#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024 +#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT 4096 +#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE \ + (KFD_MAX_NUM_OF_PROCESSES * \ + KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) #define KFD_KERNEL_QUEUE_SIZE 2048 diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 47526780d736..2fda1927bff7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -54,11 +54,11 @@ static int find_available_queue_slot(struct process_queue_manager *pqm, pr_debug("kfd: in %s\n", __func__); found = find_first_zero_bit(pqm->queue_slot_bitmap, - max_num_of_queues_per_process); + KFD_MAX_NUM_OF_QUEUES_PER_PROCESS); pr_debug("kfd: the new slot id %lu\n", found); - if (found >= max_num_of_queues_per_process) { + if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) { pr_info("amdkfd: Can not open more queues for process with pasid %d\n", pqm->process->pasid); return -ENOMEM; @@ -76,7 +76,7 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p) INIT_LIST_HEAD(&pqm->queues); pqm->queue_slot_bitmap = - kzalloc(DIV_ROUND_UP(max_num_of_queues_per_process, + kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS, BITS_PER_BYTE), GFP_KERNEL); if (pqm->queue_slot_bitmap == NULL) return -ENOMEM; @@ -203,6 +203,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, pqn->kq = NULL; retval = dev->dqm->create_queue(dev->dqm, q, &pdd->qpd, &q->properties.vmid); + pr_debug("DQM returned %d for create_queue\n", retval); print_queue(q); break; case KFD_QUEUE_TYPE_DIQ: @@ -222,7 +223,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, } if (retval != 0) { - pr_err("kfd: error dqm create queue\n"); + pr_debug("Error dqm create queue\n"); goto err_create_queue; } @@ -241,7 +242,10 @@ int pqm_create_queue(struct process_queue_manager *pqm, err_create_queue: kfree(pqn); err_allocate_pqn: + /* check if queues list is empty unregister process from device */ clear_bit(*qid, pqm->queue_slot_bitmap); + if (list_empty(&pqm->queues)) + dev->dqm->unregister_process(dev->dqm, &pdd->qpd); return retval; } @@ -311,7 +315,11 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid, BUG_ON(!pqm); pqn = get_queue_by_qid(pqm, qid); - BUG_ON(!pqn); + if (!pqn) { + pr_debug("amdkfd: No queue %d exists for update operation\n", + qid); + return -EFAULT; + } pqn->q->properties.queue_address = p->queue_address; pqn->q->properties.queue_size = p->queue_size; diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c index c2a1cba1e984..b9140032962d 100644 --- a/drivers/gpu/drm/cirrus/cirrus_drv.c +++ b/drivers/gpu/drm/cirrus/cirrus_drv.c @@ -16,9 +16,12 @@ #include "cirrus_drv.h" int cirrus_modeset = -1; +int cirrus_bpp = 24; MODULE_PARM_DESC(modeset, "Disable/Enable modesetting"); module_param_named(modeset, cirrus_modeset, int, 0400); +MODULE_PARM_DESC(bpp, "Max bits-per-pixel (default:24)"); +module_param_named(bpp, cirrus_bpp, int, 0400); /* * This is the generic driver code. This binds the driver to the drm core, diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h index 693a4565c4ff..705061537a27 100644 --- a/drivers/gpu/drm/cirrus/cirrus_drv.h +++ b/drivers/gpu/drm/cirrus/cirrus_drv.h @@ -262,4 +262,7 @@ static inline void cirrus_bo_unreserve(struct cirrus_bo *bo) int cirrus_bo_push_sysram(struct cirrus_bo *bo); int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr); + +extern int cirrus_bpp; + #endif /* __CIRRUS_DRV_H__ */ diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c index 4c2d68e9102d..e4b976658087 100644 --- a/drivers/gpu/drm/cirrus/cirrus_main.c +++ b/drivers/gpu/drm/cirrus/cirrus_main.c @@ -320,6 +320,8 @@ bool cirrus_check_framebuffer(struct cirrus_device *cdev, int width, int height, const int max_pitch = 0x1FF << 3; /* (4096 - 1) & ~111b bytes */ const int max_size = cdev->mc.vram_size; + if (bpp > cirrus_bpp) + return false; if (bpp > 32) return false; diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index 99d4a74ffeaf..61385f2298bf 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -501,8 +501,13 @@ static int cirrus_vga_get_modes(struct drm_connector *connector) int count; /* Just add a static list of modes */ - count = drm_add_modes_noedid(connector, 1280, 1024); - drm_set_preferred_mode(connector, 1024, 768); + if (cirrus_bpp <= 24) { + count = drm_add_modes_noedid(connector, 1280, 1024); + drm_set_preferred_mode(connector, 1024, 768); + } else { + count = drm_add_modes_noedid(connector, 800, 600); + drm_set_preferred_mode(connector, 800, 600); + } return count; } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index cf775a4449c1..dc386ebe5193 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -145,6 +145,31 @@ int drm_fb_helper_add_one_connector(struct drm_fb_helper *fb_helper, struct drm_ } EXPORT_SYMBOL(drm_fb_helper_add_one_connector); +static void remove_from_modeset(struct drm_mode_set *set, + struct drm_connector *connector) +{ + int i, j; + + for (i = 0; i < set->num_connectors; i++) { + if (set->connectors[i] == connector) + break; + } + + if (i == set->num_connectors) + return; + + for (j = i + 1; j < set->num_connectors; j++) { + set->connectors[j - 1] = set->connectors[j]; + } + set->num_connectors--; + + /* because i915 is pissy about this.. + * TODO maybe need to makes sure we set it back to !=NULL somewhere? + */ + if (set->num_connectors == 0) + set->fb = NULL; +} + int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper, struct drm_connector *connector) { @@ -167,6 +192,11 @@ int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper, } fb_helper->connector_count--; kfree(fb_helper_connector); + + /* also cleanup dangling references to the connector: */ + for (i = 0; i < fb_helper->crtc_count; i++) + remove_from_modeset(&fb_helper->crtc_info[i].mode_set, connector); + return 0; } EXPORT_SYMBOL(drm_fb_helper_remove_one_connector); diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index d4762799351d..a9041d1a8ff0 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -32,6 +32,8 @@ struct tda998x_priv { struct i2c_client *cec; struct i2c_client *hdmi; + struct mutex mutex; + struct delayed_work dwork; uint16_t rev; uint8_t current_page; int dpms; @@ -402,9 +404,10 @@ reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt) uint8_t addr = REG2ADDR(reg); int ret; + mutex_lock(&priv->mutex); ret = set_page(priv, reg); if (ret < 0) - return ret; + goto out; ret = i2c_master_send(client, &addr, sizeof(addr)); if (ret < 0) @@ -414,10 +417,12 @@ reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt) if (ret < 0) goto fail; - return ret; + goto out; fail: dev_err(&client->dev, "Error %d reading from 0x%x\n", ret, reg); +out: + mutex_unlock(&priv->mutex); return ret; } @@ -431,13 +436,16 @@ reg_write_range(struct tda998x_priv *priv, uint16_t reg, uint8_t *p, int cnt) buf[0] = REG2ADDR(reg); memcpy(&buf[1], p, cnt); + mutex_lock(&priv->mutex); ret = set_page(priv, reg); if (ret < 0) - return; + goto out; ret = i2c_master_send(client, buf, cnt + 1); if (ret < 0) dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg); +out: + mutex_unlock(&priv->mutex); } static int @@ -459,13 +467,16 @@ reg_write(struct tda998x_priv *priv, uint16_t reg, uint8_t val) uint8_t buf[] = {REG2ADDR(reg), val}; int ret; + mutex_lock(&priv->mutex); ret = set_page(priv, reg); if (ret < 0) - return; + goto out; ret = i2c_master_send(client, buf, sizeof(buf)); if (ret < 0) dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg); +out: + mutex_unlock(&priv->mutex); } static void @@ -475,13 +486,16 @@ reg_write16(struct tda998x_priv *priv, uint16_t reg, uint16_t val) uint8_t buf[] = {REG2ADDR(reg), val >> 8, val}; int ret; + mutex_lock(&priv->mutex); ret = set_page(priv, reg); if (ret < 0) - return; + goto out; ret = i2c_master_send(client, buf, sizeof(buf)); if (ret < 0) dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg); +out: + mutex_unlock(&priv->mutex); } static void @@ -536,6 +550,17 @@ tda998x_reset(struct tda998x_priv *priv) reg_write(priv, REG_MUX_VP_VIP_OUT, 0x24); } +/* handle HDMI connect/disconnect */ +static void tda998x_hpd(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct tda998x_priv *priv = + container_of(dwork, struct tda998x_priv, dwork); + + if (priv->encoder && priv->encoder->dev) + drm_kms_helper_hotplug_event(priv->encoder->dev); +} + /* * only 2 interrupts may occur: screen plug/unplug and EDID read */ @@ -559,8 +584,7 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data) priv->wq_edid_wait = 0; wake_up(&priv->wq_edid); } else if (cec != 0) { /* HPD change */ - if (priv->encoder && priv->encoder->dev) - drm_helper_hpd_irq_event(priv->encoder->dev); + schedule_delayed_work(&priv->dwork, HZ/10); } return IRQ_HANDLED; } @@ -1170,8 +1194,10 @@ static void tda998x_destroy(struct tda998x_priv *priv) /* disable all IRQs and free the IRQ handler */ cec_write(priv, REG_CEC_RXSHPDINTENA, 0); reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD); - if (priv->hdmi->irq) + if (priv->hdmi->irq) { free_irq(priv->hdmi->irq, priv); + cancel_delayed_work_sync(&priv->dwork); + } i2c_unregister_device(priv->cec); } @@ -1255,6 +1281,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) struct device_node *np = client->dev.of_node; u32 video; int rev_lo, rev_hi, ret; + unsigned short cec_addr; priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3); priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1); @@ -1262,12 +1289,16 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) priv->current_page = 0xff; priv->hdmi = client; - priv->cec = i2c_new_dummy(client->adapter, 0x34); + /* CEC I2C address bound to TDA998x I2C addr by configuration pins */ + cec_addr = 0x34 + (client->addr & 0x03); + priv->cec = i2c_new_dummy(client->adapter, cec_addr); if (!priv->cec) return -ENODEV; priv->dpms = DRM_MODE_DPMS_OFF; + mutex_init(&priv->mutex); /* protect the page access */ + /* wake up the device: */ cec_write(priv, REG_CEC_ENAMODS, CEC_ENAMODS_EN_RXSENS | CEC_ENAMODS_EN_HDMI); @@ -1323,8 +1354,9 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) if (client->irq) { int irqf_trigger; - /* init read EDID waitqueue */ + /* init read EDID waitqueue and HDP work */ init_waitqueue_head(&priv->wq_edid); + INIT_DELAYED_WORK(&priv->dwork, tda998x_hpd); /* clear pending interrupts */ reg_read(priv, REG_INT_FLAGS_0); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 574057cd1d09..7643300828c3 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -462,19 +462,13 @@ void intel_detect_pch(struct drm_device *dev) } else if (id == INTEL_PCH_LPT_DEVICE_ID_TYPE) { dev_priv->pch_type = PCH_LPT; DRM_DEBUG_KMS("Found LynxPoint PCH\n"); - WARN_ON(!IS_HASWELL(dev)); - WARN_ON(IS_HSW_ULT(dev)); - } else if (IS_BROADWELL(dev)) { - dev_priv->pch_type = PCH_LPT; - dev_priv->pch_id = - INTEL_PCH_LPT_LP_DEVICE_ID_TYPE; - DRM_DEBUG_KMS("This is Broadwell, assuming " - "LynxPoint LP PCH\n"); + WARN_ON(!IS_HASWELL(dev) && !IS_BROADWELL(dev)); + WARN_ON(IS_HSW_ULT(dev) || IS_BDW_ULT(dev)); } else if (id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { dev_priv->pch_type = PCH_LPT; DRM_DEBUG_KMS("Found LynxPoint LP PCH\n"); - WARN_ON(!IS_HASWELL(dev)); - WARN_ON(!IS_HSW_ULT(dev)); + WARN_ON(!IS_HASWELL(dev) && !IS_BROADWELL(dev)); + WARN_ON(!IS_HSW_ULT(dev) && !IS_BDW_ULT(dev)); } else if (id == INTEL_PCH_SPT_DEVICE_ID_TYPE) { dev_priv->pch_type = PCH_SPT; DRM_DEBUG_KMS("Found SunrisePoint PCH\n"); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e9f891c432f8..9d7a7155bf02 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2159,8 +2159,7 @@ struct drm_i915_cmd_table { #define IS_HSW_EARLY_SDV(dev) (IS_HASWELL(dev) && \ (INTEL_DEVID(dev) & 0xFF00) == 0x0C00) #define IS_BDW_ULT(dev) (IS_BROADWELL(dev) && \ - ((INTEL_DEVID(dev) & 0xf) == 0x2 || \ - (INTEL_DEVID(dev) & 0xf) == 0x6 || \ + ((INTEL_DEVID(dev) & 0xf) == 0x6 || \ (INTEL_DEVID(dev) & 0xf) == 0xe)) #define IS_BDW_GT3(dev) (IS_BROADWELL(dev) && \ (INTEL_DEVID(dev) & 0x00F0) == 0x0020) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 76354d3ba925..5f614828d365 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3148,6 +3148,13 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, u32 size = i915_gem_obj_ggtt_size(obj); uint64_t val; + /* Adjust fence size to match tiled area */ + if (obj->tiling_mode != I915_TILING_NONE) { + uint32_t row_size = obj->stride * + (obj->tiling_mode == I915_TILING_Y ? 32 : 8); + size = (size / row_size) * row_size; + } + val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) & 0xfffff000) << 32; val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000; @@ -4884,25 +4891,18 @@ i915_gem_init_hw(struct drm_device *dev) for (i = 0; i < NUM_L3_SLICES(dev); i++) i915_gem_l3_remap(&dev_priv->ring[RCS], i); - /* - * XXX: Contexts should only be initialized once. Doing a switch to the - * default context switch however is something we'd like to do after - * reset or thaw (the latter may not actually be necessary for HW, but - * goes with our code better). Context switching requires rings (for - * the do_switch), but before enabling PPGTT. So don't move this. - */ - ret = i915_gem_context_enable(dev_priv); + ret = i915_ppgtt_init_hw(dev); if (ret && ret != -EIO) { - DRM_ERROR("Context enable failed %d\n", ret); + DRM_ERROR("PPGTT enable failed %d\n", ret); i915_gem_cleanup_ringbuffer(dev); - - return ret; } - ret = i915_ppgtt_init_hw(dev); + ret = i915_gem_context_enable(dev_priv); if (ret && ret != -EIO) { - DRM_ERROR("PPGTT enable failed %d\n", ret); + DRM_ERROR("Context enable failed %d\n", ret); i915_gem_cleanup_ringbuffer(dev); + + return ret; } return ret; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 4d63839bd9b4..dfb783a8f2c3 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -962,7 +962,7 @@ void intel_panel_enable_backlight(struct intel_connector *connector) WARN_ON(panel->backlight.max == 0); - if (panel->backlight.level == 0) { + if (panel->backlight.level <= panel->backlight.min) { panel->backlight.level = panel->backlight.max; if (panel->backlight.device) panel->backlight.device->props.brightness = diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c index a0133c74f4cf..42cd0cffe210 100644 --- a/drivers/gpu/drm/radeon/cik_sdma.c +++ b/drivers/gpu/drm/radeon/cik_sdma.c @@ -816,7 +816,6 @@ void cik_sdma_vm_write_pages(struct radeon_device *rdev, for (; ndw > 0; ndw -= 2, --count, pe += 8) { if (flags & R600_PTE_SYSTEM) { value = radeon_vm_map_gart(rdev, addr); - value &= 0xFFFFFFFFFFFFF000ULL; } else if (flags & R600_PTE_VALID) { value = addr; } else { diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c index 4be2bb7cbef3..ce787a9f12c0 100644 --- a/drivers/gpu/drm/radeon/ni_dma.c +++ b/drivers/gpu/drm/radeon/ni_dma.c @@ -372,7 +372,6 @@ void cayman_dma_vm_write_pages(struct radeon_device *rdev, for (; ndw > 0; ndw -= 2, --count, pe += 8) { if (flags & R600_PTE_SYSTEM) { value = radeon_vm_map_gart(rdev, addr); - value &= 0xFFFFFFFFFFFFF000ULL; } else if (flags & R600_PTE_VALID) { value = addr; } else { diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 74f06d540591..279801ca5110 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -644,6 +644,7 @@ int r100_pci_gart_init(struct radeon_device *rdev) return r; rdev->gart.table_size = rdev->gart.num_gpu_pages * 4; rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush; + rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry; rdev->asic->gart.set_page = &r100_pci_gart_set_page; return radeon_gart_table_ram_alloc(rdev); } @@ -681,11 +682,16 @@ void r100_pci_gart_disable(struct radeon_device *rdev) WREG32(RADEON_AIC_HI_ADDR, 0); } +uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags) +{ + return addr; +} + void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags) + uint64_t entry) { u32 *gtt = rdev->gart.ptr; - gtt[i] = cpu_to_le32(lower_32_bits(addr)); + gtt[i] = cpu_to_le32(lower_32_bits(entry)); } void r100_pci_gart_fini(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 064ad5569cca..08d68f3e13e9 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -73,11 +73,8 @@ void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev) #define R300_PTE_WRITEABLE (1 << 2) #define R300_PTE_READABLE (1 << 3) -void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags) +uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags) { - void __iomem *ptr = rdev->gart.ptr; - addr = (lower_32_bits(addr) >> 8) | ((upper_32_bits(addr) & 0xff) << 24); if (flags & RADEON_GART_PAGE_READ) @@ -86,10 +83,18 @@ void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i, addr |= R300_PTE_WRITEABLE; if (!(flags & RADEON_GART_PAGE_SNOOP)) addr |= R300_PTE_UNSNOOPED; + return addr; +} + +void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i, + uint64_t entry) +{ + void __iomem *ptr = rdev->gart.ptr; + /* on x86 we want this to be CPU endian, on powerpc * on powerpc without HW swappers, it'll get swapped on way * into VRAM - so no need for cpu_to_le32 on VRAM tables */ - writel(addr, ((void __iomem *)ptr) + (i * 4)); + writel(entry, ((void __iomem *)ptr) + (i * 4)); } int rv370_pcie_gart_init(struct radeon_device *rdev) @@ -109,6 +114,7 @@ int rv370_pcie_gart_init(struct radeon_device *rdev) DRM_ERROR("Failed to register debugfs file for PCIE gart !\n"); rdev->gart.table_size = rdev->gart.num_gpu_pages * 4; rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush; + rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry; rdev->asic->gart.set_page = &rv370_pcie_gart_set_page; return radeon_gart_table_vram_alloc(rdev); } diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 54529b837afa..3f2a8d3febca 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -242,6 +242,7 @@ bool radeon_get_bios(struct radeon_device *rdev); * Dummy page */ struct radeon_dummy_page { + uint64_t entry; struct page *page; dma_addr_t addr; }; @@ -645,7 +646,7 @@ struct radeon_gart { unsigned num_cpu_pages; unsigned table_size; struct page **pages; - dma_addr_t *pages_addr; + uint64_t *pages_entry; bool ready; }; @@ -1847,8 +1848,9 @@ struct radeon_asic { /* gart */ struct { void (*tlb_flush)(struct radeon_device *rdev); + uint64_t (*get_page_entry)(uint64_t addr, uint32_t flags); void (*set_page)(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags); + uint64_t entry); } gart; struct { int (*init)(struct radeon_device *rdev); @@ -2852,7 +2854,8 @@ static inline void radeon_ring_write(struct radeon_ring *ring, uint32_t v) #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state)) #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev)) #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev)) -#define radeon_gart_set_page(rdev, i, p, f) (rdev)->asic->gart.set_page((rdev), (i), (p), (f)) +#define radeon_gart_get_page_entry(a, f) (rdev)->asic->gart.get_page_entry((a), (f)) +#define radeon_gart_set_page(rdev, i, e) (rdev)->asic->gart.set_page((rdev), (i), (e)) #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev)) #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev)) #define radeon_asic_vm_copy_pages(rdev, ib, pe, src, count) ((rdev)->asic->vm.copy_pages((rdev), (ib), (pe), (src), (count))) diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 121aff6a3b41..ed0e10eee2dc 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -159,11 +159,13 @@ void radeon_agp_disable(struct radeon_device *rdev) DRM_INFO("Forcing AGP to PCIE mode\n"); rdev->flags |= RADEON_IS_PCIE; rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush; + rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry; rdev->asic->gart.set_page = &rv370_pcie_gart_set_page; } else { DRM_INFO("Forcing AGP to PCI mode\n"); rdev->flags |= RADEON_IS_PCI; rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush; + rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry; rdev->asic->gart.set_page = &r100_pci_gart_set_page; } rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024; @@ -199,6 +201,7 @@ static struct radeon_asic r100_asic = { .mc_wait_for_idle = &r100_mc_wait_for_idle, .gart = { .tlb_flush = &r100_pci_gart_tlb_flush, + .get_page_entry = &r100_pci_gart_get_page_entry, .set_page = &r100_pci_gart_set_page, }, .ring = { @@ -265,6 +268,7 @@ static struct radeon_asic r200_asic = { .mc_wait_for_idle = &r100_mc_wait_for_idle, .gart = { .tlb_flush = &r100_pci_gart_tlb_flush, + .get_page_entry = &r100_pci_gart_get_page_entry, .set_page = &r100_pci_gart_set_page, }, .ring = { @@ -359,6 +363,7 @@ static struct radeon_asic r300_asic = { .mc_wait_for_idle = &r300_mc_wait_for_idle, .gart = { .tlb_flush = &r100_pci_gart_tlb_flush, + .get_page_entry = &r100_pci_gart_get_page_entry, .set_page = &r100_pci_gart_set_page, }, .ring = { @@ -425,6 +430,7 @@ static struct radeon_asic r300_asic_pcie = { .mc_wait_for_idle = &r300_mc_wait_for_idle, .gart = { .tlb_flush = &rv370_pcie_gart_tlb_flush, + .get_page_entry = &rv370_pcie_gart_get_page_entry, .set_page = &rv370_pcie_gart_set_page, }, .ring = { @@ -491,6 +497,7 @@ static struct radeon_asic r420_asic = { .mc_wait_for_idle = &r300_mc_wait_for_idle, .gart = { .tlb_flush = &rv370_pcie_gart_tlb_flush, + .get_page_entry = &rv370_pcie_gart_get_page_entry, .set_page = &rv370_pcie_gart_set_page, }, .ring = { @@ -557,6 +564,7 @@ static struct radeon_asic rs400_asic = { .mc_wait_for_idle = &rs400_mc_wait_for_idle, .gart = { .tlb_flush = &rs400_gart_tlb_flush, + .get_page_entry = &rs400_gart_get_page_entry, .set_page = &rs400_gart_set_page, }, .ring = { @@ -623,6 +631,7 @@ static struct radeon_asic rs600_asic = { .mc_wait_for_idle = &rs600_mc_wait_for_idle, .gart = { .tlb_flush = &rs600_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -691,6 +700,7 @@ static struct radeon_asic rs690_asic = { .mc_wait_for_idle = &rs690_mc_wait_for_idle, .gart = { .tlb_flush = &rs400_gart_tlb_flush, + .get_page_entry = &rs400_gart_get_page_entry, .set_page = &rs400_gart_set_page, }, .ring = { @@ -759,6 +769,7 @@ static struct radeon_asic rv515_asic = { .mc_wait_for_idle = &rv515_mc_wait_for_idle, .gart = { .tlb_flush = &rv370_pcie_gart_tlb_flush, + .get_page_entry = &rv370_pcie_gart_get_page_entry, .set_page = &rv370_pcie_gart_set_page, }, .ring = { @@ -825,6 +836,7 @@ static struct radeon_asic r520_asic = { .mc_wait_for_idle = &r520_mc_wait_for_idle, .gart = { .tlb_flush = &rv370_pcie_gart_tlb_flush, + .get_page_entry = &rv370_pcie_gart_get_page_entry, .set_page = &rv370_pcie_gart_set_page, }, .ring = { @@ -919,6 +931,7 @@ static struct radeon_asic r600_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &r600_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1004,6 +1017,7 @@ static struct radeon_asic rv6xx_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &r600_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1095,6 +1109,7 @@ static struct radeon_asic rs780_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &r600_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1199,6 +1214,7 @@ static struct radeon_asic rv770_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &r600_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1317,6 +1333,7 @@ static struct radeon_asic evergreen_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &evergreen_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1409,6 +1426,7 @@ static struct radeon_asic sumo_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &evergreen_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1500,6 +1518,7 @@ static struct radeon_asic btc_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &evergreen_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .ring = { @@ -1635,6 +1654,7 @@ static struct radeon_asic cayman_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &cayman_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .vm = { @@ -1738,6 +1758,7 @@ static struct radeon_asic trinity_asic = { .get_gpu_clock_counter = &r600_get_gpu_clock_counter, .gart = { .tlb_flush = &cayman_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .vm = { @@ -1871,6 +1892,7 @@ static struct radeon_asic si_asic = { .get_gpu_clock_counter = &si_get_gpu_clock_counter, .gart = { .tlb_flush = &si_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .vm = { @@ -2032,6 +2054,7 @@ static struct radeon_asic ci_asic = { .get_gpu_clock_counter = &cik_get_gpu_clock_counter, .gart = { .tlb_flush = &cik_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .vm = { @@ -2139,6 +2162,7 @@ static struct radeon_asic kv_asic = { .get_gpu_clock_counter = &cik_get_gpu_clock_counter, .gart = { .tlb_flush = &cik_pcie_gart_tlb_flush, + .get_page_entry = &rs600_gart_get_page_entry, .set_page = &rs600_gart_set_page, }, .vm = { diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index 2a45d548d5ec..8d787d115653 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -67,8 +67,9 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp); int r100_asic_reset(struct radeon_device *rdev); u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc); void r100_pci_gart_tlb_flush(struct radeon_device *rdev); +uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags); void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags); + uint64_t entry); void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring); int r100_irq_set(struct radeon_device *rdev); int r100_irq_process(struct radeon_device *rdev); @@ -172,8 +173,9 @@ extern void r300_fence_ring_emit(struct radeon_device *rdev, struct radeon_fence *fence); extern int r300_cs_parse(struct radeon_cs_parser *p); extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev); +extern uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags); extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags); + uint64_t entry); extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes); extern int rv370_get_pcie_lanes(struct radeon_device *rdev); extern void r300_set_reg_safe(struct radeon_device *rdev); @@ -208,8 +210,9 @@ extern void rs400_fini(struct radeon_device *rdev); extern int rs400_suspend(struct radeon_device *rdev); extern int rs400_resume(struct radeon_device *rdev); void rs400_gart_tlb_flush(struct radeon_device *rdev); +uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags); void rs400_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags); + uint64_t entry); uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg); void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v); int rs400_gart_init(struct radeon_device *rdev); @@ -232,8 +235,9 @@ int rs600_irq_process(struct radeon_device *rdev); void rs600_irq_disable(struct radeon_device *rdev); u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc); void rs600_gart_tlb_flush(struct radeon_device *rdev); +uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags); void rs600_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags); + uint64_t entry); uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg); void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v); void rs600_bandwidth_update(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c index 9e7f23dd14bd..87d5fb21cb61 100644 --- a/drivers/gpu/drm/radeon/radeon_benchmark.c +++ b/drivers/gpu/drm/radeon/radeon_benchmark.c @@ -34,7 +34,8 @@ static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size, uint64_t saddr, uint64_t daddr, - int flag, int n) + int flag, int n, + struct reservation_object *resv) { unsigned long start_jiffies; unsigned long end_jiffies; @@ -47,12 +48,12 @@ static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size, case RADEON_BENCHMARK_COPY_DMA: fence = radeon_copy_dma(rdev, saddr, daddr, size / RADEON_GPU_PAGE_SIZE, - NULL); + resv); break; case RADEON_BENCHMARK_COPY_BLIT: fence = radeon_copy_blit(rdev, saddr, daddr, size / RADEON_GPU_PAGE_SIZE, - NULL); + resv); break; default: DRM_ERROR("Unknown copy method\n"); @@ -120,7 +121,8 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size, if (rdev->asic->copy.dma) { time = radeon_benchmark_do_move(rdev, size, saddr, daddr, - RADEON_BENCHMARK_COPY_DMA, n); + RADEON_BENCHMARK_COPY_DMA, n, + dobj->tbo.resv); if (time < 0) goto out_cleanup; if (time > 0) @@ -130,7 +132,8 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size, if (rdev->asic->copy.blit) { time = radeon_benchmark_do_move(rdev, size, saddr, daddr, - RADEON_BENCHMARK_COPY_BLIT, n); + RADEON_BENCHMARK_COPY_BLIT, n, + dobj->tbo.resv); if (time < 0) goto out_cleanup; if (time > 0) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 0ec65168f331..bd7519fdd3f4 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -774,6 +774,8 @@ int radeon_dummy_page_init(struct radeon_device *rdev) rdev->dummy_page.page = NULL; return -ENOMEM; } + rdev->dummy_page.entry = radeon_gart_get_page_entry(rdev->dummy_page.addr, + RADEON_GART_PAGE_DUMMY); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 102116902a07..913fafa597ad 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -960,6 +960,9 @@ void radeon_compute_pll_avivo(struct radeon_pll *pll, if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV && pll->flags & RADEON_PLL_USE_REF_DIV) ref_div_max = pll->reference_div; + else if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP) + /* fix for problems on RS880 */ + ref_div_max = min(pll->max_ref_div, 7u); else ref_div_max = pll->max_ref_div; diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index 84146d5901aa..5450fa95a47e 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -165,6 +165,19 @@ int radeon_gart_table_vram_pin(struct radeon_device *rdev) radeon_bo_unpin(rdev->gart.robj); radeon_bo_unreserve(rdev->gart.robj); rdev->gart.table_addr = gpu_addr; + + if (!r) { + int i; + + /* We might have dropped some GART table updates while it wasn't + * mapped, restore all entries + */ + for (i = 0; i < rdev->gart.num_gpu_pages; i++) + radeon_gart_set_page(rdev, i, rdev->gart.pages_entry[i]); + mb(); + radeon_gart_tlb_flush(rdev); + } + return r; } @@ -228,7 +241,6 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset, unsigned t; unsigned p; int i, j; - u64 page_base; if (!rdev->gart.ready) { WARN(1, "trying to unbind memory from uninitialized GART !\n"); @@ -239,14 +251,12 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset, for (i = 0; i < pages; i++, p++) { if (rdev->gart.pages[p]) { rdev->gart.pages[p] = NULL; - rdev->gart.pages_addr[p] = rdev->dummy_page.addr; - page_base = rdev->gart.pages_addr[p]; for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) { + rdev->gart.pages_entry[t] = rdev->dummy_page.entry; if (rdev->gart.ptr) { - radeon_gart_set_page(rdev, t, page_base, - RADEON_GART_PAGE_DUMMY); + radeon_gart_set_page(rdev, t, + rdev->dummy_page.entry); } - page_base += RADEON_GPU_PAGE_SIZE; } } } @@ -274,7 +284,7 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset, { unsigned t; unsigned p; - uint64_t page_base; + uint64_t page_base, page_entry; int i, j; if (!rdev->gart.ready) { @@ -285,14 +295,15 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset, p = t / (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); for (i = 0; i < pages; i++, p++) { - rdev->gart.pages_addr[p] = dma_addr[i]; rdev->gart.pages[p] = pagelist[i]; - if (rdev->gart.ptr) { - page_base = rdev->gart.pages_addr[p]; - for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) { - radeon_gart_set_page(rdev, t, page_base, flags); - page_base += RADEON_GPU_PAGE_SIZE; + page_base = dma_addr[i]; + for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) { + page_entry = radeon_gart_get_page_entry(page_base, flags); + rdev->gart.pages_entry[t] = page_entry; + if (rdev->gart.ptr) { + radeon_gart_set_page(rdev, t, page_entry); } + page_base += RADEON_GPU_PAGE_SIZE; } } mb(); @@ -334,16 +345,15 @@ int radeon_gart_init(struct radeon_device *rdev) radeon_gart_fini(rdev); return -ENOMEM; } - rdev->gart.pages_addr = vzalloc(sizeof(dma_addr_t) * - rdev->gart.num_cpu_pages); - if (rdev->gart.pages_addr == NULL) { + rdev->gart.pages_entry = vmalloc(sizeof(uint64_t) * + rdev->gart.num_gpu_pages); + if (rdev->gart.pages_entry == NULL) { radeon_gart_fini(rdev); return -ENOMEM; } /* set GART entry to point to the dummy page by default */ - for (i = 0; i < rdev->gart.num_cpu_pages; i++) { - rdev->gart.pages_addr[i] = rdev->dummy_page.addr; - } + for (i = 0; i < rdev->gart.num_gpu_pages; i++) + rdev->gart.pages_entry[i] = rdev->dummy_page.entry; return 0; } @@ -356,15 +366,15 @@ int radeon_gart_init(struct radeon_device *rdev) */ void radeon_gart_fini(struct radeon_device *rdev) { - if (rdev->gart.pages && rdev->gart.pages_addr && rdev->gart.ready) { + if (rdev->gart.ready) { /* unbind pages */ radeon_gart_unbind(rdev, 0, rdev->gart.num_cpu_pages); } rdev->gart.ready = false; vfree(rdev->gart.pages); - vfree(rdev->gart.pages_addr); + vfree(rdev->gart.pages_entry); rdev->gart.pages = NULL; - rdev->gart.pages_addr = NULL; + rdev->gart.pages_entry = NULL; radeon_dummy_page_fini(rdev); } diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index d0b4f7d1140d..ac3c1310b953 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -146,7 +146,8 @@ int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri struct radeon_bo_va *bo_va; int r; - if (rdev->family < CHIP_CAYMAN) { + if ((rdev->family < CHIP_CAYMAN) || + (!rdev->accel_working)) { return 0; } @@ -176,7 +177,8 @@ void radeon_gem_object_close(struct drm_gem_object *obj, struct radeon_bo_va *bo_va; int r; - if (rdev->family < CHIP_CAYMAN) { + if ((rdev->family < CHIP_CAYMAN) || + (!rdev->accel_working)) { return; } diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c index 8bf87f1203cc..bef9a0953284 100644 --- a/drivers/gpu/drm/radeon/radeon_kfd.c +++ b/drivers/gpu/drm/radeon/radeon_kfd.c @@ -436,7 +436,7 @@ static int kgd_init_memory(struct kgd_dev *kgd) static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id, uint32_t hpd_size, uint64_t hpd_gpu_addr) { - uint32_t mec = (++pipe_id / CIK_PIPE_PER_MEC) + 1; + uint32_t mec = (pipe_id / CIK_PIPE_PER_MEC) + 1; uint32_t pipe = (pipe_id % CIK_PIPE_PER_MEC); lock_srbm(kgd, mec, pipe, 0, 0); diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 3cf9c1fa6475..686411e4e4f6 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -605,14 +605,14 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) return -ENOMEM; } - vm = &fpriv->vm; - r = radeon_vm_init(rdev, vm); - if (r) { - kfree(fpriv); - return r; - } - if (rdev->accel_working) { + vm = &fpriv->vm; + r = radeon_vm_init(rdev, vm); + if (r) { + kfree(fpriv); + return r; + } + r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false); if (r) { radeon_vm_fini(rdev, vm); @@ -668,9 +668,9 @@ void radeon_driver_postclose_kms(struct drm_device *dev, radeon_vm_bo_rmv(rdev, vm->ib_bo_va); radeon_bo_unreserve(rdev->ring_tmp_bo.bo); } + radeon_vm_fini(rdev, vm); } - radeon_vm_fini(rdev, vm); kfree(fpriv); file_priv->driver_priv = NULL; } diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c index 07b506b41008..791818165c76 100644 --- a/drivers/gpu/drm/radeon/radeon_test.c +++ b/drivers/gpu/drm/radeon/radeon_test.c @@ -119,11 +119,11 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag) if (ring == R600_RING_TYPE_DMA_INDEX) fence = radeon_copy_dma(rdev, gtt_addr, vram_addr, size / RADEON_GPU_PAGE_SIZE, - NULL); + vram_obj->tbo.resv); else fence = radeon_copy_blit(rdev, gtt_addr, vram_addr, size / RADEON_GPU_PAGE_SIZE, - NULL); + vram_obj->tbo.resv); if (IS_ERR(fence)) { DRM_ERROR("Failed GTT->VRAM copy %d\n", i); r = PTR_ERR(fence); @@ -170,11 +170,11 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag) if (ring == R600_RING_TYPE_DMA_INDEX) fence = radeon_copy_dma(rdev, vram_addr, gtt_addr, size / RADEON_GPU_PAGE_SIZE, - NULL); + vram_obj->tbo.resv); else fence = radeon_copy_blit(rdev, vram_addr, gtt_addr, size / RADEON_GPU_PAGE_SIZE, - NULL); + vram_obj->tbo.resv); if (IS_ERR(fence)) { DRM_ERROR("Failed VRAM->GTT copy %d\n", i); r = PTR_ERR(fence); diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index cde48c42b30a..2a5a4a9e772d 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -587,10 +587,8 @@ uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr) uint64_t result; /* page table offset */ - result = rdev->gart.pages_addr[addr >> PAGE_SHIFT]; - - /* in case cpu page size != gpu page size*/ - result |= addr & (~PAGE_MASK); + result = rdev->gart.pages_entry[addr >> RADEON_GPU_PAGE_SHIFT]; + result &= ~RADEON_GPU_PAGE_MASK; return result; } @@ -745,9 +743,11 @@ static void radeon_vm_frag_ptes(struct radeon_device *rdev, */ /* NI is optimized for 256KB fragments, SI and newer for 64KB */ - uint64_t frag_flags = rdev->family == CHIP_CAYMAN ? + uint64_t frag_flags = ((rdev->family == CHIP_CAYMAN) || + (rdev->family == CHIP_ARUBA)) ? R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB; - uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80; + uint64_t frag_align = ((rdev->family == CHIP_CAYMAN) || + (rdev->family == CHIP_ARUBA)) ? 0x200 : 0x80; uint64_t frag_start = ALIGN(pe_start, frag_align); uint64_t frag_end = pe_end & ~(frag_align - 1); diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c index c5799f16aa4b..34e3235f41d2 100644 --- a/drivers/gpu/drm/radeon/rs400.c +++ b/drivers/gpu/drm/radeon/rs400.c @@ -212,11 +212,9 @@ void rs400_gart_fini(struct radeon_device *rdev) #define RS400_PTE_WRITEABLE (1 << 2) #define RS400_PTE_READABLE (1 << 3) -void rs400_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags) +uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags) { uint32_t entry; - u32 *gtt = rdev->gart.ptr; entry = (lower_32_bits(addr) & PAGE_MASK) | ((upper_32_bits(addr) & 0xff) << 4); @@ -226,8 +224,14 @@ void rs400_gart_set_page(struct radeon_device *rdev, unsigned i, entry |= RS400_PTE_WRITEABLE; if (!(flags & RADEON_GART_PAGE_SNOOP)) entry |= RS400_PTE_UNSNOOPED; - entry = cpu_to_le32(entry); - gtt[i] = entry; + return entry; +} + +void rs400_gart_set_page(struct radeon_device *rdev, unsigned i, + uint64_t entry) +{ + u32 *gtt = rdev->gart.ptr; + gtt[i] = cpu_to_le32(lower_32_bits(entry)); } int rs400_mc_wait_for_idle(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 9acb1c3c005b..74bce91aecc1 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -625,11 +625,8 @@ static void rs600_gart_fini(struct radeon_device *rdev) radeon_gart_table_vram_free(rdev); } -void rs600_gart_set_page(struct radeon_device *rdev, unsigned i, - uint64_t addr, uint32_t flags) +uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags) { - void __iomem *ptr = (void *)rdev->gart.ptr; - addr = addr & 0xFFFFFFFFFFFFF000ULL; addr |= R600_PTE_SYSTEM; if (flags & RADEON_GART_PAGE_VALID) @@ -640,7 +637,14 @@ void rs600_gart_set_page(struct radeon_device *rdev, unsigned i, addr |= R600_PTE_WRITEABLE; if (flags & RADEON_GART_PAGE_SNOOP) addr |= R600_PTE_SNOOPED; - writeq(addr, ptr + (i * 8)); + return addr; +} + +void rs600_gart_set_page(struct radeon_device *rdev, unsigned i, + uint64_t entry) +{ + void __iomem *ptr = (void *)rdev->gart.ptr; + writeq(entry, ptr + (i * 8)); } int rs600_irq_set(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c index aa7b872b2c43..83207929fc62 100644 --- a/drivers/gpu/drm/radeon/si_dma.c +++ b/drivers/gpu/drm/radeon/si_dma.c @@ -123,7 +123,6 @@ void si_dma_vm_write_pages(struct radeon_device *rdev, for (; ndw > 0; ndw -= 2, --count, pe += 8) { if (flags & R600_PTE_SYSTEM) { value = radeon_vm_map_gart(rdev, addr); - value &= 0xFFFFFFFFFFFFF000ULL; } else if (flags & R600_PTE_VALID) { value = addr; } else { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 7b5d22110f25..6c6b655defcf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -406,11 +406,9 @@ int vmw_3d_resource_inc(struct vmw_private *dev_priv, if (unlikely(ret != 0)) --dev_priv->num_3d_resources; } else if (unhide_svga) { - mutex_lock(&dev_priv->hw_mutex); vmw_write(dev_priv, SVGA_REG_ENABLE, vmw_read(dev_priv, SVGA_REG_ENABLE) & ~SVGA_REG_ENABLE_HIDE); - mutex_unlock(&dev_priv->hw_mutex); } mutex_unlock(&dev_priv->release_mutex); @@ -433,13 +431,10 @@ void vmw_3d_resource_dec(struct vmw_private *dev_priv, mutex_lock(&dev_priv->release_mutex); if (unlikely(--dev_priv->num_3d_resources == 0)) vmw_release_device(dev_priv); - else if (hide_svga) { - mutex_lock(&dev_priv->hw_mutex); + else if (hide_svga) vmw_write(dev_priv, SVGA_REG_ENABLE, vmw_read(dev_priv, SVGA_REG_ENABLE) | SVGA_REG_ENABLE_HIDE); - mutex_unlock(&dev_priv->hw_mutex); - } n3d = (int32_t) dev_priv->num_3d_resources; mutex_unlock(&dev_priv->release_mutex); @@ -600,12 +595,14 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->dev = dev; dev_priv->vmw_chipset = chipset; dev_priv->last_read_seqno = (uint32_t) -100; - mutex_init(&dev_priv->hw_mutex); mutex_init(&dev_priv->cmdbuf_mutex); mutex_init(&dev_priv->release_mutex); mutex_init(&dev_priv->binding_mutex); rwlock_init(&dev_priv->resource_lock); ttm_lock_init(&dev_priv->reservation_sem); + spin_lock_init(&dev_priv->hw_lock); + spin_lock_init(&dev_priv->waiter_lock); + spin_lock_init(&dev_priv->cap_lock); for (i = vmw_res_context; i < vmw_res_max; ++i) { idr_init(&dev_priv->res_idr[i]); @@ -626,14 +623,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->enable_fb = enable_fbdev; - mutex_lock(&dev_priv->hw_mutex); - vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2); svga_id = vmw_read(dev_priv, SVGA_REG_ID); if (svga_id != SVGA_ID_2) { ret = -ENOSYS; DRM_ERROR("Unsupported SVGA ID 0x%x\n", svga_id); - mutex_unlock(&dev_priv->hw_mutex); goto out_err0; } @@ -683,10 +677,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->prim_bb_mem = dev_priv->vram_size; ret = vmw_dma_masks(dev_priv); - if (unlikely(ret != 0)) { - mutex_unlock(&dev_priv->hw_mutex); + if (unlikely(ret != 0)) goto out_err0; - } /* * Limit back buffer size to VRAM size. Remove this once @@ -695,8 +687,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) if (dev_priv->prim_bb_mem > dev_priv->vram_size) dev_priv->prim_bb_mem = dev_priv->vram_size; - mutex_unlock(&dev_priv->hw_mutex); - vmw_print_capabilities(dev_priv->capabilities); if (dev_priv->capabilities & SVGA_CAP_GMR2) { @@ -1160,9 +1150,7 @@ static int vmw_master_set(struct drm_device *dev, if (unlikely(ret != 0)) return ret; vmw_kms_save_vga(dev_priv); - mutex_lock(&dev_priv->hw_mutex); vmw_write(dev_priv, SVGA_REG_TRACES, 0); - mutex_unlock(&dev_priv->hw_mutex); } if (active) { @@ -1196,9 +1184,7 @@ out_no_active_lock: if (!dev_priv->enable_fb) { vmw_kms_restore_vga(dev_priv); vmw_3d_resource_dec(dev_priv, true); - mutex_lock(&dev_priv->hw_mutex); vmw_write(dev_priv, SVGA_REG_TRACES, 1); - mutex_unlock(&dev_priv->hw_mutex); } return ret; } @@ -1233,9 +1219,7 @@ static void vmw_master_drop(struct drm_device *dev, DRM_ERROR("Unable to clean VRAM on master drop.\n"); vmw_kms_restore_vga(dev_priv); vmw_3d_resource_dec(dev_priv, true); - mutex_lock(&dev_priv->hw_mutex); vmw_write(dev_priv, SVGA_REG_TRACES, 1); - mutex_unlock(&dev_priv->hw_mutex); } dev_priv->active_master = &dev_priv->fbdev_master; @@ -1367,10 +1351,8 @@ static void vmw_pm_complete(struct device *kdev) struct drm_device *dev = pci_get_drvdata(pdev); struct vmw_private *dev_priv = vmw_priv(dev); - mutex_lock(&dev_priv->hw_mutex); vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2); (void) vmw_read(dev_priv, SVGA_REG_ID); - mutex_unlock(&dev_priv->hw_mutex); /** * Reclaim 3d reference held by fbdev and potentially diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 4ee799b43d5d..d26a6daa9719 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -399,7 +399,8 @@ struct vmw_private { uint32_t memory_size; bool has_gmr; bool has_mob; - struct mutex hw_mutex; + spinlock_t hw_lock; + spinlock_t cap_lock; /* * VGA registers. @@ -449,8 +450,9 @@ struct vmw_private { atomic_t marker_seq; wait_queue_head_t fence_queue; wait_queue_head_t fifo_queue; - int fence_queue_waiters; /* Protected by hw_mutex */ - int goal_queue_waiters; /* Protected by hw_mutex */ + spinlock_t waiter_lock; + int fence_queue_waiters; /* Protected by waiter_lock */ + int goal_queue_waiters; /* Protected by waiter_lock */ atomic_t fifo_queue_waiters; uint32_t last_read_seqno; spinlock_t irq_lock; @@ -553,20 +555,35 @@ static inline struct vmw_master *vmw_master(struct drm_master *master) return (struct vmw_master *) master->driver_priv; } +/* + * The locking here is fine-grained, so that it is performed once + * for every read- and write operation. This is of course costly, but we + * don't perform much register access in the timing critical paths anyway. + * Instead we have the extra benefit of being sure that we don't forget + * the hw lock around register accesses. + */ static inline void vmw_write(struct vmw_private *dev_priv, unsigned int offset, uint32_t value) { + unsigned long irq_flags; + + spin_lock_irqsave(&dev_priv->hw_lock, irq_flags); outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT); outl(value, dev_priv->io_start + VMWGFX_VALUE_PORT); + spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags); } static inline uint32_t vmw_read(struct vmw_private *dev_priv, unsigned int offset) { - uint32_t val; + unsigned long irq_flags; + u32 val; + spin_lock_irqsave(&dev_priv->hw_lock, irq_flags); outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT); val = inl(dev_priv->io_start + VMWGFX_VALUE_PORT); + spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags); + return val; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index b7594cb758af..945f1e0dad92 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -35,7 +35,7 @@ struct vmw_fence_manager { struct vmw_private *dev_priv; spinlock_t lock; struct list_head fence_list; - struct work_struct work, ping_work; + struct work_struct work; u32 user_fence_size; u32 fence_size; u32 event_fence_action_size; @@ -134,14 +134,6 @@ static const char *vmw_fence_get_timeline_name(struct fence *f) return "svga"; } -static void vmw_fence_ping_func(struct work_struct *work) -{ - struct vmw_fence_manager *fman = - container_of(work, struct vmw_fence_manager, ping_work); - - vmw_fifo_ping_host(fman->dev_priv, SVGA_SYNC_GENERIC); -} - static bool vmw_fence_enable_signaling(struct fence *f) { struct vmw_fence_obj *fence = @@ -155,11 +147,7 @@ static bool vmw_fence_enable_signaling(struct fence *f) if (seqno - fence->base.seqno < VMW_FENCE_WRAP) return false; - if (mutex_trylock(&dev_priv->hw_mutex)) { - vmw_fifo_ping_host_locked(dev_priv, SVGA_SYNC_GENERIC); - mutex_unlock(&dev_priv->hw_mutex); - } else - schedule_work(&fman->ping_work); + vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC); return true; } @@ -305,7 +293,6 @@ struct vmw_fence_manager *vmw_fence_manager_init(struct vmw_private *dev_priv) INIT_LIST_HEAD(&fman->fence_list); INIT_LIST_HEAD(&fman->cleanup_list); INIT_WORK(&fman->work, &vmw_fence_work_func); - INIT_WORK(&fman->ping_work, &vmw_fence_ping_func); fman->fifo_down = true; fman->user_fence_size = ttm_round_pot(sizeof(struct vmw_user_fence)); fman->fence_size = ttm_round_pot(sizeof(struct vmw_fence_obj)); @@ -323,7 +310,6 @@ void vmw_fence_manager_takedown(struct vmw_fence_manager *fman) bool lists_empty; (void) cancel_work_sync(&fman->work); - (void) cancel_work_sync(&fman->ping_work); spin_lock_irqsave(&fman->lock, irq_flags); lists_empty = list_empty(&fman->fence_list) && diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index 09e10aefcd8e..39f2b03888e7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -44,10 +44,10 @@ bool vmw_fifo_have_3d(struct vmw_private *dev_priv) if (!dev_priv->has_mob) return false; - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->cap_lock); vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_3D); result = vmw_read(dev_priv, SVGA_REG_DEV_CAP); - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->cap_lock); return (result != 0); } @@ -120,7 +120,6 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) DRM_INFO("height %d\n", vmw_read(dev_priv, SVGA_REG_HEIGHT)); DRM_INFO("bpp %d\n", vmw_read(dev_priv, SVGA_REG_BITS_PER_PIXEL)); - mutex_lock(&dev_priv->hw_mutex); dev_priv->enable_state = vmw_read(dev_priv, SVGA_REG_ENABLE); dev_priv->config_done_state = vmw_read(dev_priv, SVGA_REG_CONFIG_DONE); dev_priv->traces_state = vmw_read(dev_priv, SVGA_REG_TRACES); @@ -143,7 +142,6 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) mb(); vmw_write(dev_priv, SVGA_REG_CONFIG_DONE, 1); - mutex_unlock(&dev_priv->hw_mutex); max = ioread32(fifo_mem + SVGA_FIFO_MAX); min = ioread32(fifo_mem + SVGA_FIFO_MIN); @@ -160,31 +158,28 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) return vmw_fifo_send_fence(dev_priv, &dummy); } -void vmw_fifo_ping_host_locked(struct vmw_private *dev_priv, uint32_t reason) +void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason) { __le32 __iomem *fifo_mem = dev_priv->mmio_virt; + static DEFINE_SPINLOCK(ping_lock); + unsigned long irq_flags; + /* + * The ping_lock is needed because we don't have an atomic + * test-and-set of the SVGA_FIFO_BUSY register. + */ + spin_lock_irqsave(&ping_lock, irq_flags); if (unlikely(ioread32(fifo_mem + SVGA_FIFO_BUSY) == 0)) { iowrite32(1, fifo_mem + SVGA_FIFO_BUSY); vmw_write(dev_priv, SVGA_REG_SYNC, reason); } -} - -void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason) -{ - mutex_lock(&dev_priv->hw_mutex); - - vmw_fifo_ping_host_locked(dev_priv, reason); - - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock_irqrestore(&ping_lock, irq_flags); } void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) { __le32 __iomem *fifo_mem = dev_priv->mmio_virt; - mutex_lock(&dev_priv->hw_mutex); - vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0) ; @@ -198,7 +193,6 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) vmw_write(dev_priv, SVGA_REG_TRACES, dev_priv->traces_state); - mutex_unlock(&dev_priv->hw_mutex); vmw_marker_queue_takedown(&fifo->marker_queue); if (likely(fifo->static_buffer != NULL)) { @@ -271,7 +265,7 @@ static int vmw_fifo_wait(struct vmw_private *dev_priv, return vmw_fifo_wait_noirq(dev_priv, bytes, interruptible, timeout); - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->waiter_lock); if (atomic_add_return(1, &dev_priv->fifo_queue_waiters) > 0) { spin_lock_irqsave(&dev_priv->irq_lock, irq_flags); outl(SVGA_IRQFLAG_FIFO_PROGRESS, @@ -280,7 +274,7 @@ static int vmw_fifo_wait(struct vmw_private *dev_priv, vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask); spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->waiter_lock); if (interruptible) ret = wait_event_interruptible_timeout @@ -296,14 +290,14 @@ static int vmw_fifo_wait(struct vmw_private *dev_priv, else if (likely(ret > 0)) ret = 0; - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->waiter_lock); if (atomic_dec_and_test(&dev_priv->fifo_queue_waiters)) { spin_lock_irqsave(&dev_priv->irq_lock, irq_flags); dev_priv->irq_mask &= ~SVGA_IRQFLAG_FIFO_PROGRESS; vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask); spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->waiter_lock); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index 37881ecf5d7a..69c8ce23123c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -135,13 +135,13 @@ static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce, (pair_offset + max_size * sizeof(SVGA3dCapPair)) / sizeof(u32); compat_cap->header.type = SVGA3DCAPS_RECORD_DEVCAPS; - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->cap_lock); for (i = 0; i < max_size; ++i) { vmw_write(dev_priv, SVGA_REG_DEV_CAP, i); compat_cap->pairs[i][0] = i; compat_cap->pairs[i][1] = vmw_read(dev_priv, SVGA_REG_DEV_CAP); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->cap_lock); return 0; } @@ -191,12 +191,12 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data, if (num > SVGA3D_DEVCAP_MAX) num = SVGA3D_DEVCAP_MAX; - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->cap_lock); for (i = 0; i < num; ++i) { vmw_write(dev_priv, SVGA_REG_DEV_CAP, i); *bounce32++ = vmw_read(dev_priv, SVGA_REG_DEV_CAP); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->cap_lock); } else if (gb_objects) { ret = vmw_fill_compat_cap(dev_priv, bounce, size); if (unlikely(ret != 0)) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c index 0c423766c441..9fe9827ee499 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c @@ -62,13 +62,8 @@ irqreturn_t vmw_irq_handler(int irq, void *arg) static bool vmw_fifo_idle(struct vmw_private *dev_priv, uint32_t seqno) { - uint32_t busy; - mutex_lock(&dev_priv->hw_mutex); - busy = vmw_read(dev_priv, SVGA_REG_BUSY); - mutex_unlock(&dev_priv->hw_mutex); - - return (busy == 0); + return (vmw_read(dev_priv, SVGA_REG_BUSY) == 0); } void vmw_update_seqno(struct vmw_private *dev_priv, @@ -184,7 +179,7 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, void vmw_seqno_waiter_add(struct vmw_private *dev_priv) { - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->waiter_lock); if (dev_priv->fence_queue_waiters++ == 0) { unsigned long irq_flags; @@ -195,12 +190,12 @@ void vmw_seqno_waiter_add(struct vmw_private *dev_priv) vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask); spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->waiter_lock); } void vmw_seqno_waiter_remove(struct vmw_private *dev_priv) { - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->waiter_lock); if (--dev_priv->fence_queue_waiters == 0) { unsigned long irq_flags; @@ -209,13 +204,13 @@ void vmw_seqno_waiter_remove(struct vmw_private *dev_priv) vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask); spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->waiter_lock); } void vmw_goal_waiter_add(struct vmw_private *dev_priv) { - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->waiter_lock); if (dev_priv->goal_queue_waiters++ == 0) { unsigned long irq_flags; @@ -226,12 +221,12 @@ void vmw_goal_waiter_add(struct vmw_private *dev_priv) vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask); spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->waiter_lock); } void vmw_goal_waiter_remove(struct vmw_private *dev_priv) { - mutex_lock(&dev_priv->hw_mutex); + spin_lock(&dev_priv->waiter_lock); if (--dev_priv->goal_queue_waiters == 0) { unsigned long irq_flags; @@ -240,7 +235,7 @@ void vmw_goal_waiter_remove(struct vmw_private *dev_priv) vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask); spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags); } - mutex_unlock(&dev_priv->hw_mutex); + spin_unlock(&dev_priv->waiter_lock); } int vmw_wait_seqno(struct vmw_private *dev_priv, @@ -315,9 +310,7 @@ void vmw_irq_uninstall(struct drm_device *dev) if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK)) return; - mutex_lock(&dev_priv->hw_mutex); vmw_write(dev_priv, SVGA_REG_IRQMASK, 0); - mutex_unlock(&dev_priv->hw_mutex); status = inl(dev_priv->io_start + VMWGFX_IRQSTATUS_PORT); outl(status, dev_priv->io_start + VMWGFX_IRQSTATUS_PORT); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 3725b521d931..8725b79e7847 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1828,9 +1828,7 @@ vmw_du_connector_detect(struct drm_connector *connector, bool force) struct vmw_private *dev_priv = vmw_priv(dev); struct vmw_display_unit *du = vmw_connector_to_du(connector); - mutex_lock(&dev_priv->hw_mutex); num_displays = vmw_read(dev_priv, SVGA_REG_NUM_DISPLAYS); - mutex_unlock(&dev_priv->hw_mutex); return ((vmw_connector_to_du(connector)->unit < num_displays && du->pref_active) ? diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 31e8308ba899..ab838d9e28b6 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -881,6 +881,7 @@ config I2C_XLR config I2C_RCAR tristate "Renesas R-Car I2C Controller" depends on ARCH_SHMOBILE || COMPILE_TEST + select I2C_SLAVE help If you say yes to this option, support will be included for the R-Car I2C controller. diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index bff20a589621..958c8db4ec30 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -785,14 +785,16 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, int ret; pm_runtime_get_sync(&adap->dev); - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; for (retry = 0; retry < adap->retries; retry++) { ret = s3c24xx_i2c_doxfer(i2c, msgs, num); if (ret != -EAGAIN) { - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); pm_runtime_put(&adap->dev); return ret; } @@ -802,7 +804,7 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, udelay(100); } - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); pm_runtime_put(&adap->dev); return -EREMOTEIO; } @@ -1197,7 +1199,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) clk_prepare_enable(i2c->clk); ret = s3c24xx_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); if (ret != 0) { dev_err(&pdev->dev, "I2C controller init failed\n"); return ret; @@ -1210,6 +1212,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) i2c->irq = ret = platform_get_irq(pdev, 0); if (ret <= 0) { dev_err(&pdev->dev, "cannot find IRQ\n"); + clk_unprepare(i2c->clk); return ret; } @@ -1218,6 +1221,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) if (ret != 0) { dev_err(&pdev->dev, "cannot claim IRQ %d\n", i2c->irq); + clk_unprepare(i2c->clk); return ret; } } @@ -1225,6 +1229,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) ret = s3c24xx_i2c_register_cpufreq(i2c); if (ret < 0) { dev_err(&pdev->dev, "failed to register cpufreq notifier\n"); + clk_unprepare(i2c->clk); return ret; } @@ -1241,6 +1246,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) if (ret < 0) { dev_err(&pdev->dev, "failed to add bus to i2c core\n"); s3c24xx_i2c_deregister_cpufreq(i2c); + clk_unprepare(i2c->clk); return ret; } @@ -1262,6 +1268,8 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev) { struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); + clk_unprepare(i2c->clk); + pm_runtime_disable(&i2c->adap.dev); pm_runtime_disable(&pdev->dev); @@ -1293,13 +1301,16 @@ static int s3c24xx_i2c_resume_noirq(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); + int ret; if (!IS_ERR(i2c->sysreg)) regmap_write(i2c->sysreg, EXYNOS5_SYS_I2C_CFG, i2c->sys_i2c_cfg); - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; s3c24xx_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); i2c->suspended = 0; return 0; diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c index 440d5dbc8b5f..007818b3e174 100644 --- a/drivers/i2c/busses/i2c-sh_mobile.c +++ b/drivers/i2c/busses/i2c-sh_mobile.c @@ -139,6 +139,7 @@ struct sh_mobile_i2c_data { int pos; int sr; bool send_stop; + bool stop_after_dma; struct resource *res; struct dma_chan *dma_tx; @@ -407,7 +408,7 @@ static int sh_mobile_i2c_isr_tx(struct sh_mobile_i2c_data *pd) if (pd->pos == pd->msg->len) { /* Send stop if we haven't yet (DMA case) */ - if (pd->send_stop && (iic_rd(pd, ICCR) & ICCR_BBSY)) + if (pd->send_stop && pd->stop_after_dma) i2c_op(pd, OP_TX_STOP, 0); return 1; } @@ -449,6 +450,13 @@ static int sh_mobile_i2c_isr_rx(struct sh_mobile_i2c_data *pd) real_pos = pd->pos - 2; if (pd->pos == pd->msg->len) { + if (pd->stop_after_dma) { + /* Simulate PIO end condition after DMA transfer */ + i2c_op(pd, OP_RX_STOP, 0); + pd->pos++; + break; + } + if (real_pos < 0) { i2c_op(pd, OP_RX_STOP, 0); break; @@ -536,6 +544,7 @@ static void sh_mobile_i2c_dma_callback(void *data) sh_mobile_i2c_dma_unmap(pd); pd->pos = pd->msg->len; + pd->stop_after_dma = true; iic_set_clr(pd, ICIC, 0, ICIC_TDMAE | ICIC_RDMAE); } @@ -726,6 +735,7 @@ static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, bool do_start = pd->send_stop || !i; msg = &msgs[i]; pd->send_stop = i == num - 1 || msg->flags & I2C_M_STOP; + pd->stop_after_dma = false; err = start_ch(pd, msg, do_start); if (err) diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 39d25a8cb1ad..e9eae57a2b50 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -2972,6 +2972,7 @@ trace: } EXPORT_SYMBOL(i2c_smbus_xfer); +#if IS_ENABLED(CONFIG_I2C_SLAVE) int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb) { int ret; @@ -3019,6 +3020,7 @@ int i2c_slave_unregister(struct i2c_client *client) return ret; } EXPORT_SYMBOL_GPL(i2c_slave_unregister); +#endif MODULE_AUTHOR("Simon G. Vogl <simon@tk.uni-linz.ac.at>"); MODULE_DESCRIPTION("I2C-Bus main module"); diff --git a/drivers/i2c/i2c-slave-eeprom.c b/drivers/i2c/i2c-slave-eeprom.c index 6631400b5f02..cf9b09db092f 100644 --- a/drivers/i2c/i2c-slave-eeprom.c +++ b/drivers/i2c/i2c-slave-eeprom.c @@ -74,7 +74,7 @@ static ssize_t i2c_slave_eeprom_bin_read(struct file *filp, struct kobject *kobj struct eeprom_data *eeprom; unsigned long flags; - if (off + count >= attr->size) + if (off + count > attr->size) return -EFBIG; eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj)); @@ -92,7 +92,7 @@ static ssize_t i2c_slave_eeprom_bin_write(struct file *filp, struct kobject *kob struct eeprom_data *eeprom; unsigned long flags; - if (off + count >= attr->size) + if (off + count > attr->size) return -EFBIG; eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj)); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index e6c23b9eab33..5db1a8cc388d 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -123,7 +123,6 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file, struct ib_udata *uhw) = { [IB_USER_VERBS_EX_CMD_CREATE_FLOW] = ib_uverbs_ex_create_flow, [IB_USER_VERBS_EX_CMD_DESTROY_FLOW] = ib_uverbs_ex_destroy_flow, - [IB_USER_VERBS_EX_CMD_QUERY_DEVICE] = ib_uverbs_ex_query_device }; static void ib_uverbs_add_one(struct ib_device *device); diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 2d8c3397774f..f50a546224ad 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include <linux/inet.h> #include <linux/string.h> +#include <linux/mlx4/driver.h> #include "mlx4_ib.h" diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 9db258f7c804..2ed5b996b2f4 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -351,6 +351,7 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, enum ib_mtu tmp; struct mlx4_cmd_mailbox *mailbox; int err = 0; + int is_bonded = mlx4_is_bonded(mdev->dev); mailbox = mlx4_alloc_cmd_mailbox(mdev->dev); if (IS_ERR(mailbox)) @@ -374,8 +375,12 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->state = IB_PORT_DOWN; props->phys_state = state_to_phys_state(props->state); props->active_mtu = IB_MTU_256; + if (is_bonded) + rtnl_lock(); /* required to get upper dev */ spin_lock_bh(&iboe->lock); ndev = iboe->netdevs[port - 1]; + if (ndev && is_bonded) + ndev = netdev_master_upper_dev_get(ndev); if (!ndev) goto out_unlock; @@ -387,6 +392,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->phys_state = state_to_phys_state(props->state); out_unlock: spin_unlock_bh(&iboe->lock); + if (is_bonded) + rtnl_unlock(); out: mlx4_free_cmd_mailbox(mdev->dev, mailbox); return err; @@ -844,7 +851,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, struct mlx4_ib_steering { struct list_head list; - u64 reg_id; + struct mlx4_flow_reg_id reg_id; union ib_gid gid; }; @@ -1135,9 +1142,11 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain) { - int err = 0, i = 0; + int err = 0, i = 0, j = 0; struct mlx4_ib_flow *mflow; enum mlx4_net_trans_promisc_mode type[2]; + struct mlx4_dev *dev = (to_mdev(qp->device))->dev; + int is_bonded = mlx4_is_bonded(dev); memset(type, 0, sizeof(type)); @@ -1172,26 +1181,55 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, while (i < ARRAY_SIZE(type) && type[i]) { err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i], - &mflow->reg_id[i]); + &mflow->reg_id[i].id); if (err) goto err_create_flow; i++; + if (is_bonded) { + flow_attr->port = 2; + err = __mlx4_ib_create_flow(qp, flow_attr, + domain, type[j], + &mflow->reg_id[j].mirror); + flow_attr->port = 1; + if (err) + goto err_create_flow; + j++; + } + } if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) { - err = mlx4_ib_tunnel_steer_add(qp, flow_attr, &mflow->reg_id[i]); + err = mlx4_ib_tunnel_steer_add(qp, flow_attr, + &mflow->reg_id[i].id); if (err) goto err_create_flow; i++; + if (is_bonded) { + flow_attr->port = 2; + err = mlx4_ib_tunnel_steer_add(qp, flow_attr, + &mflow->reg_id[j].mirror); + flow_attr->port = 1; + if (err) + goto err_create_flow; + j++; + } + /* function to create mirror rule */ } return &mflow->ibflow; err_create_flow: while (i) { - (void)__mlx4_ib_destroy_flow(to_mdev(qp->device)->dev, mflow->reg_id[i]); + (void)__mlx4_ib_destroy_flow(to_mdev(qp->device)->dev, + mflow->reg_id[i].id); i--; } + + while (j) { + (void)__mlx4_ib_destroy_flow(to_mdev(qp->device)->dev, + mflow->reg_id[j].mirror); + j--; + } err_free: kfree(mflow); return ERR_PTR(err); @@ -1204,10 +1242,16 @@ static int mlx4_ib_destroy_flow(struct ib_flow *flow_id) struct mlx4_ib_dev *mdev = to_mdev(flow_id->qp->device); struct mlx4_ib_flow *mflow = to_mflow(flow_id); - while (i < ARRAY_SIZE(mflow->reg_id) && mflow->reg_id[i]) { - err = __mlx4_ib_destroy_flow(mdev->dev, mflow->reg_id[i]); + while (i < ARRAY_SIZE(mflow->reg_id) && mflow->reg_id[i].id) { + err = __mlx4_ib_destroy_flow(mdev->dev, mflow->reg_id[i].id); if (err) ret = err; + if (mflow->reg_id[i].mirror) { + err = __mlx4_ib_destroy_flow(mdev->dev, + mflow->reg_id[i].mirror); + if (err) + ret = err; + } i++; } @@ -1219,11 +1263,12 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { int err; struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); + struct mlx4_dev *dev = mdev->dev; struct mlx4_ib_qp *mqp = to_mqp(ibqp); - u64 reg_id; struct mlx4_ib_steering *ib_steering = NULL; enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ? MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6; + struct mlx4_flow_reg_id reg_id; if (mdev->dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) { @@ -1235,10 +1280,20 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port, !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), - prot, ®_id); + prot, ®_id.id); if (err) goto err_malloc; + reg_id.mirror = 0; + if (mlx4_is_bonded(dev)) { + err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, 2, + !!(mqp->flags & + MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), + prot, ®_id.mirror); + if (err) + goto err_add; + } + err = add_gid_entry(ibqp, gid); if (err) goto err_add; @@ -1254,7 +1309,10 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) err_add: mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, - prot, reg_id); + prot, reg_id.id); + if (reg_id.mirror) + mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, + prot, reg_id.mirror); err_malloc: kfree(ib_steering); @@ -1281,10 +1339,12 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { int err; struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); + struct mlx4_dev *dev = mdev->dev; struct mlx4_ib_qp *mqp = to_mqp(ibqp); struct net_device *ndev; struct mlx4_ib_gid_entry *ge; - u64 reg_id = 0; + struct mlx4_flow_reg_id reg_id = {0, 0}; + enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ? MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6; @@ -1309,10 +1369,17 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) } err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, - prot, reg_id); + prot, reg_id.id); if (err) return err; + if (mlx4_is_bonded(dev)) { + err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, + prot, reg_id.mirror); + if (err) + return err; + } + mutex_lock(&mqp->mutex); ge = find_gid_entry(mqp, gid->raw); if (ge) { @@ -1440,6 +1507,7 @@ static void update_gids_task(struct work_struct *work) union ib_gid *gids; int err; struct mlx4_dev *dev = gw->dev->dev; + int is_bonded = mlx4_is_bonded(dev); if (!gw->dev->ib_active) return; @@ -1459,7 +1527,10 @@ static void update_gids_task(struct work_struct *work) if (err) pr_warn("set port command failed\n"); else - mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE); + if ((gw->port == 1) || !is_bonded) + mlx4_ib_dispatch_event(gw->dev, + is_bonded ? 1 : gw->port, + IB_EVENT_GID_CHANGE); mlx4_free_cmd_mailbox(dev, mailbox); kfree(gw); @@ -1875,7 +1946,8 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev, * don't want the bond IP based gids in the table since * flows that select port by gid may get the down port. */ - if (port_state == IB_PORT_DOWN) { + if (port_state == IB_PORT_DOWN && + !mlx4_is_bonded(ibdev->dev)) { reset_gid_table(ibdev, port); mlx4_ib_set_default_gid(ibdev, curr_netdev, @@ -2047,6 +2119,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) int err; struct mlx4_ib_iboe *iboe; int ib_num_ports = 0; + int num_req_counters; pr_info_once("%s", mlx4_ib_version); @@ -2080,13 +2153,15 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock); ibdev->dev = dev; + ibdev->bond_next_port = 0; strlcpy(ibdev->ib_dev.name, "mlx4_%d", IB_DEVICE_NAME_MAX); ibdev->ib_dev.owner = THIS_MODULE; ibdev->ib_dev.node_type = RDMA_NODE_IB_CA; ibdev->ib_dev.local_dma_lkey = dev->caps.reserved_lkey; ibdev->num_ports = num_ports; - ibdev->ib_dev.phys_port_cnt = ibdev->num_ports; + ibdev->ib_dev.phys_port_cnt = mlx4_is_bonded(dev) ? + 1 : ibdev->num_ports; ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors; ibdev->ib_dev.dma_device = &dev->persist->pdev->dev; @@ -2207,7 +2282,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (init_node_data(ibdev)) goto err_map; - for (i = 0; i < ibdev->num_ports; ++i) { + num_req_counters = mlx4_is_bonded(dev) ? 1 : ibdev->num_ports; + for (i = 0; i < num_req_counters; ++i) { mutex_init(&ibdev->qp1_proxy_lock[i]); if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) == IB_LINK_LAYER_ETHERNET) { @@ -2218,6 +2294,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->counters[i] = -1; } } + if (mlx4_is_bonded(dev)) + for (i = 1; i < ibdev->num_ports ; ++i) + ibdev->counters[i] = ibdev->counters[0]; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) ib_num_ports++; @@ -2538,6 +2618,38 @@ out: return; } +static void handle_bonded_port_state_event(struct work_struct *work) +{ + struct ib_event_work *ew = + container_of(work, struct ib_event_work, work); + struct mlx4_ib_dev *ibdev = ew->ib_dev; + enum ib_port_state bonded_port_state = IB_PORT_NOP; + int i; + struct ib_event ibev; + + kfree(ew); + spin_lock_bh(&ibdev->iboe.lock); + for (i = 0; i < MLX4_MAX_PORTS; ++i) { + struct net_device *curr_netdev = ibdev->iboe.netdevs[i]; + + enum ib_port_state curr_port_state = + (netif_running(curr_netdev) && + netif_carrier_ok(curr_netdev)) ? + IB_PORT_ACTIVE : IB_PORT_DOWN; + + bonded_port_state = (bonded_port_state != IB_PORT_ACTIVE) ? + curr_port_state : IB_PORT_ACTIVE; + } + spin_unlock_bh(&ibdev->iboe.lock); + + ibev.device = &ibdev->ib_dev; + ibev.element.port_num = 1; + ibev.event = (bonded_port_state == IB_PORT_ACTIVE) ? + IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR; + + ib_dispatch_event(&ibev); +} + static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, enum mlx4_dev_event event, unsigned long param) { @@ -2547,6 +2659,18 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, struct ib_event_work *ew; int p = 0; + if (mlx4_is_bonded(dev) && + ((event == MLX4_DEV_EVENT_PORT_UP) || + (event == MLX4_DEV_EVENT_PORT_DOWN))) { + ew = kmalloc(sizeof(*ew), GFP_ATOMIC); + if (!ew) + return; + INIT_WORK(&ew->work, handle_bonded_port_state_event); + ew->ib_dev = ibdev; + queue_work(wq, &ew->work); + return; + } + if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE) eqe = (struct mlx4_eqe *)param; else @@ -2607,7 +2731,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, } ibev.device = ibdev_ptr; - ibev.element.port_num = (u8) p; + ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p; ib_dispatch_event(&ibev); } @@ -2616,7 +2740,8 @@ static struct mlx4_interface mlx4_ib_interface = { .add = mlx4_ib_add, .remove = mlx4_ib_remove, .event = mlx4_ib_event, - .protocol = MLX4_PROT_IB_IPV6 + .protocol = MLX4_PROT_IB_IPV6, + .flags = MLX4_INTFF_BONDING }; static int __init mlx4_ib_init(void) diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 6eb743f65f6f..721540c9163d 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -134,10 +134,17 @@ struct mlx4_ib_fmr { struct mlx4_fmr mfmr; }; +#define MAX_REGS_PER_FLOW 2 + +struct mlx4_flow_reg_id { + u64 id; + u64 mirror; +}; + struct mlx4_ib_flow { struct ib_flow ibflow; /* translating DMFS verbs sniffer rule to FW API requires two reg IDs */ - u64 reg_id[2]; + struct mlx4_flow_reg_id reg_id[MAX_REGS_PER_FLOW]; }; struct mlx4_ib_wq { @@ -527,6 +534,7 @@ struct mlx4_ib_dev { struct mlx4_ib_qp *qp1_proxy[MLX4_MAX_PORTS]; /* lock when destroying qp1_proxy and getting netdev events */ struct mutex qp1_proxy_lock[MLX4_MAX_PORTS]; + u8 bond_next_port; }; struct ib_event_work { @@ -622,6 +630,13 @@ static inline struct mlx4_ib_ah *to_mah(struct ib_ah *ibah) return container_of(ibah, struct mlx4_ib_ah, ibah); } +static inline u8 mlx4_ib_bond_next_port(struct mlx4_ib_dev *dev) +{ + dev->bond_next_port = (dev->bond_next_port + 1) % dev->num_ports; + + return dev->bond_next_port + 1; +} + int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev); void mlx4_ib_close_sriov(struct mlx4_ib_dev *dev); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index cf000b7ad64f..792f9dc86ada 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -40,6 +40,7 @@ #include <rdma/ib_addr.h> #include <rdma/ib_mad.h> +#include <linux/mlx4/driver.h> #include <linux/mlx4/qp.h> #include "mlx4_ib.h" @@ -93,17 +94,6 @@ enum { #ifndef ETH_ALEN #define ETH_ALEN 6 #endif -static inline u64 mlx4_mac_to_u64(u8 *addr) -{ - u64 mac = 0; - int i; - - for (i = 0; i < ETH_ALEN; i++) { - mac <<= 8; - mac |= addr[i]; - } - return mac; -} static const __be32 mlx4_ib_opcode[] = { [IB_WR_SEND] = cpu_to_be32(MLX4_OPCODE_SEND), @@ -1915,6 +1905,22 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, goto out; } + if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT)) { + if ((cur_state == IB_QPS_RESET) && (new_state == IB_QPS_INIT)) { + if ((ibqp->qp_type == IB_QPT_RC) || + (ibqp->qp_type == IB_QPT_UD) || + (ibqp->qp_type == IB_QPT_UC) || + (ibqp->qp_type == IB_QPT_RAW_PACKET) || + (ibqp->qp_type == IB_QPT_XRC_INI)) { + attr->port_num = mlx4_ib_bond_next_port(dev); + } + } else { + /* no sense in changing port_num + * when ports are bonded */ + attr_mask &= ~IB_QP_PORT; + } + } + if ((attr_mask & IB_QP_PORT) && (attr->port_num == 0 || attr->port_num > dev->num_ports)) { pr_debug("qpn 0x%x: invalid port number (%d) specified " @@ -1965,6 +1971,9 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, err = __mlx4_ib_modify_qp(ibqp, attr, attr_mask, cur_state, new_state); + if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT)) + attr->port_num = 1; + out: mutex_unlock(&qp->mutex); return err; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 8ba80a6d3a46..d7562beb5423 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -98,15 +98,9 @@ enum { IPOIB_MCAST_FLAG_FOUND = 0, /* used in set_multicast_list */ IPOIB_MCAST_FLAG_SENDONLY = 1, - /* - * For IPOIB_MCAST_FLAG_BUSY - * When set, in flight join and mcast->mc is unreliable - * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or - * haven't started yet - * When clear and mcast->mc is valid pointer, join was successful - */ - IPOIB_MCAST_FLAG_BUSY = 2, + IPOIB_MCAST_FLAG_BUSY = 2, /* joining or already joined */ IPOIB_MCAST_FLAG_ATTACHED = 3, + IPOIB_MCAST_JOIN_STARTED = 4, MAX_SEND_CQE = 16, IPOIB_CM_COPYBREAK = 256, @@ -323,7 +317,6 @@ struct ipoib_dev_priv { struct list_head multicast_list; struct rb_root multicast_tree; - struct workqueue_struct *wq; struct delayed_work mcast_task; struct work_struct carrier_on_task; struct work_struct flush_light; @@ -484,10 +477,10 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work); void ipoib_pkey_event(struct work_struct *work); void ipoib_ib_dev_cleanup(struct net_device *dev); -int ipoib_ib_dev_open(struct net_device *dev); +int ipoib_ib_dev_open(struct net_device *dev, int flush); int ipoib_ib_dev_up(struct net_device *dev); -int ipoib_ib_dev_down(struct net_device *dev); -int ipoib_ib_dev_stop(struct net_device *dev); +int ipoib_ib_dev_down(struct net_device *dev, int flush); +int ipoib_ib_dev_stop(struct net_device *dev, int flush); void ipoib_pkey_dev_check_presence(struct net_device *dev); int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port); @@ -499,7 +492,7 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb); void ipoib_mcast_restart_task(struct work_struct *work); int ipoib_mcast_start_thread(struct net_device *dev); -int ipoib_mcast_stop_thread(struct net_device *dev); +int ipoib_mcast_stop_thread(struct net_device *dev, int flush); void ipoib_mcast_dev_down(struct net_device *dev); void ipoib_mcast_dev_flush(struct net_device *dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 56959adb6c7d..933efcea0d03 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -474,7 +474,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even } spin_lock_irq(&priv->lock); - queue_delayed_work(priv->wq, + queue_delayed_work(ipoib_workqueue, &priv->cm.stale_task, IPOIB_CM_RX_DELAY); /* Add this entry to passive ids list head, but do not re-add it * if IB_EVENT_QP_LAST_WQE_REACHED has moved it to flush list. */ @@ -576,7 +576,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->cm.rx_drain_list, &priv->cm.rx_reap_list); ipoib_cm_start_rx_drain(priv); - queue_work(priv->wq, &priv->cm.rx_reap_task); + queue_work(ipoib_workqueue, &priv->cm.rx_reap_task); spin_unlock_irqrestore(&priv->lock, flags); } else ipoib_warn(priv, "cm recv completion event with wrid %d (> %d)\n", @@ -603,7 +603,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) spin_lock_irqsave(&priv->lock, flags); list_move(&p->list, &priv->cm.rx_reap_list); spin_unlock_irqrestore(&priv->lock, flags); - queue_work(priv->wq, &priv->cm.rx_reap_task); + queue_work(ipoib_workqueue, &priv->cm.rx_reap_task); } return; } @@ -827,7 +827,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { list_move(&tx->list, &priv->cm.reap_list); - queue_work(priv->wq, &priv->cm.reap_task); + queue_work(ipoib_workqueue, &priv->cm.reap_task); } clear_bit(IPOIB_FLAG_OPER_UP, &tx->flags); @@ -1255,7 +1255,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id, if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { list_move(&tx->list, &priv->cm.reap_list); - queue_work(priv->wq, &priv->cm.reap_task); + queue_work(ipoib_workqueue, &priv->cm.reap_task); } spin_unlock_irqrestore(&priv->lock, flags); @@ -1284,7 +1284,7 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path tx->dev = dev; list_add(&tx->list, &priv->cm.start_list); set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags); - queue_work(priv->wq, &priv->cm.start_task); + queue_work(ipoib_workqueue, &priv->cm.start_task); return tx; } @@ -1295,7 +1295,7 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx) if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { spin_lock_irqsave(&priv->lock, flags); list_move(&tx->list, &priv->cm.reap_list); - queue_work(priv->wq, &priv->cm.reap_task); + queue_work(ipoib_workqueue, &priv->cm.reap_task); ipoib_dbg(priv, "Reap connection for gid %pI6\n", tx->neigh->daddr + 4); tx->neigh = NULL; @@ -1417,7 +1417,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, skb_queue_tail(&priv->cm.skb_queue, skb); if (e) - queue_work(priv->wq, &priv->cm.skb_task); + queue_work(ipoib_workqueue, &priv->cm.skb_task); } static void ipoib_cm_rx_reap(struct work_struct *work) @@ -1450,7 +1450,7 @@ static void ipoib_cm_stale_task(struct work_struct *work) } if (!list_empty(&priv->cm.passive_ids)) - queue_delayed_work(priv->wq, + queue_delayed_work(ipoib_workqueue, &priv->cm.stale_task, IPOIB_CM_RX_DELAY); spin_unlock_irq(&priv->lock); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index fe65abb5150c..72626c348174 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -655,7 +655,7 @@ void ipoib_reap_ah(struct work_struct *work) __ipoib_reap_ah(dev); if (!test_bit(IPOIB_STOP_REAPER, &priv->flags)) - queue_delayed_work(priv->wq, &priv->ah_reap_task, + queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, round_jiffies_relative(HZ)); } @@ -664,7 +664,7 @@ static void ipoib_ib_tx_timer_func(unsigned long ctx) drain_tx_cq((struct net_device *)ctx); } -int ipoib_ib_dev_open(struct net_device *dev) +int ipoib_ib_dev_open(struct net_device *dev, int flush) { struct ipoib_dev_priv *priv = netdev_priv(dev); int ret; @@ -696,7 +696,7 @@ int ipoib_ib_dev_open(struct net_device *dev) } clear_bit(IPOIB_STOP_REAPER, &priv->flags); - queue_delayed_work(priv->wq, &priv->ah_reap_task, + queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, round_jiffies_relative(HZ)); if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) @@ -706,7 +706,7 @@ int ipoib_ib_dev_open(struct net_device *dev) dev_stop: if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) napi_enable(&priv->napi); - ipoib_ib_dev_stop(dev); + ipoib_ib_dev_stop(dev, flush); return -1; } @@ -738,7 +738,7 @@ int ipoib_ib_dev_up(struct net_device *dev) return ipoib_mcast_start_thread(dev); } -int ipoib_ib_dev_down(struct net_device *dev) +int ipoib_ib_dev_down(struct net_device *dev, int flush) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -747,7 +747,7 @@ int ipoib_ib_dev_down(struct net_device *dev) clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags); netif_carrier_off(dev); - ipoib_mcast_stop_thread(dev); + ipoib_mcast_stop_thread(dev, flush); ipoib_mcast_dev_flush(dev); ipoib_flush_paths(dev); @@ -807,7 +807,7 @@ void ipoib_drain_cq(struct net_device *dev) local_bh_enable(); } -int ipoib_ib_dev_stop(struct net_device *dev) +int ipoib_ib_dev_stop(struct net_device *dev, int flush) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_qp_attr qp_attr; @@ -880,7 +880,8 @@ timeout: /* Wait for all AHs to be reaped */ set_bit(IPOIB_STOP_REAPER, &priv->flags); cancel_delayed_work(&priv->ah_reap_task); - flush_workqueue(priv->wq); + if (flush) + flush_workqueue(ipoib_workqueue); begin = jiffies; @@ -917,7 +918,7 @@ int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port) (unsigned long) dev); if (dev->flags & IFF_UP) { - if (ipoib_ib_dev_open(dev)) { + if (ipoib_ib_dev_open(dev, 1)) { ipoib_transport_dev_cleanup(dev); return -ENODEV; } @@ -1039,12 +1040,12 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, } if (level >= IPOIB_FLUSH_NORMAL) - ipoib_ib_dev_down(dev); + ipoib_ib_dev_down(dev, 0); if (level == IPOIB_FLUSH_HEAVY) { if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - ipoib_ib_dev_stop(dev); - if (ipoib_ib_dev_open(dev) != 0) + ipoib_ib_dev_stop(dev, 0); + if (ipoib_ib_dev_open(dev, 0) != 0) return; if (netif_queue_stopped(dev)) netif_start_queue(dev); @@ -1096,7 +1097,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) */ ipoib_flush_paths(dev); - ipoib_mcast_stop_thread(dev); + ipoib_mcast_stop_thread(dev, 1); ipoib_mcast_dev_flush(dev); ipoib_transport_dev_cleanup(dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 6bad17d4d588..58b5aa3b6f2d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -108,7 +108,7 @@ int ipoib_open(struct net_device *dev) set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); - if (ipoib_ib_dev_open(dev)) { + if (ipoib_ib_dev_open(dev, 1)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; @@ -139,7 +139,7 @@ int ipoib_open(struct net_device *dev) return 0; err_stop: - ipoib_ib_dev_stop(dev); + ipoib_ib_dev_stop(dev, 1); err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); @@ -157,8 +157,8 @@ static int ipoib_stop(struct net_device *dev) netif_stop_queue(dev); - ipoib_ib_dev_down(dev); - ipoib_ib_dev_stop(dev); + ipoib_ib_dev_down(dev, 1); + ipoib_ib_dev_stop(dev, 0); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; @@ -839,7 +839,7 @@ static void ipoib_set_mcast_list(struct net_device *dev) return; } - queue_work(priv->wq, &priv->restart_task); + queue_work(ipoib_workqueue, &priv->restart_task); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) @@ -954,7 +954,7 @@ static void ipoib_reap_neigh(struct work_struct *work) __ipoib_reap_neigh(priv); if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags)) - queue_delayed_work(priv->wq, &priv->neigh_reap_task, + queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task, arp_tbl.gc_interval); } @@ -1133,7 +1133,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) /* start garbage collection */ clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); - queue_delayed_work(priv->wq, &priv->neigh_reap_task, + queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; @@ -1262,13 +1262,15 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) { struct ipoib_dev_priv *priv = netdev_priv(dev); + if (ipoib_neigh_hash_init(priv) < 0) + goto out; /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring, GFP_KERNEL); if (!priv->rx_ring) { printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n", ca->name, ipoib_recvq_size); - goto out; + goto out_neigh_hash_cleanup; } priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring); @@ -1283,24 +1285,16 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) if (ipoib_ib_dev_init(dev, ca, port)) goto out_tx_ring_cleanup; - /* - * Must be after ipoib_ib_dev_init so we can allocate a per - * device wq there and use it here - */ - if (ipoib_neigh_hash_init(priv) < 0) - goto out_dev_uninit; - return 0; -out_dev_uninit: - ipoib_ib_dev_cleanup(dev); - out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); +out_neigh_hash_cleanup: + ipoib_neigh_hash_uninit(dev); out: return -ENOMEM; } @@ -1323,12 +1317,6 @@ void ipoib_dev_cleanup(struct net_device *dev) } unregister_netdevice_many(&head); - /* - * Must be before ipoib_ib_dev_cleanup or we delete an in use - * work queue - */ - ipoib_neigh_hash_uninit(dev); - ipoib_ib_dev_cleanup(dev); kfree(priv->rx_ring); @@ -1336,6 +1324,8 @@ void ipoib_dev_cleanup(struct net_device *dev) priv->rx_ring = NULL; priv->tx_ring = NULL; + + ipoib_neigh_hash_uninit(dev); } static const struct header_ops ipoib_header_ops = { @@ -1646,7 +1636,7 @@ register_failed: /* Stop GC if started before flush */ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); cancel_delayed_work(&priv->neigh_reap_task); - flush_workqueue(priv->wq); + flush_workqueue(ipoib_workqueue); event_failed: ipoib_dev_cleanup(priv->dev); @@ -1717,7 +1707,7 @@ static void ipoib_remove_one(struct ib_device *device) /* Stop GC */ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); cancel_delayed_work(&priv->neigh_reap_task); - flush_workqueue(priv->wq); + flush_workqueue(ipoib_workqueue); unregister_netdev(priv->dev); free_netdev(priv->dev); @@ -1758,13 +1748,8 @@ static int __init ipoib_init_module(void) * unregister_netdev() and linkwatch_event take the rtnl lock, * so flush_scheduled_work() can deadlock during device * removal. - * - * In addition, bringing one device up and another down at the - * same time can deadlock a single workqueue, so we have this - * global fallback workqueue, but we also attempt to open a - * per device workqueue each time we bring an interface up */ - ipoib_workqueue = create_singlethread_workqueue("ipoib_flush"); + ipoib_workqueue = create_singlethread_workqueue("ipoib"); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index bc50dd0d0e4d..ffb83b5f7e80 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -190,6 +190,12 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, spin_unlock_irq(&priv->lock); priv->tx_wr.wr.ud.remote_qkey = priv->qkey; set_qkey = 1; + + if (!ipoib_cm_admin_enabled(dev)) { + rtnl_lock(); + dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu)); + rtnl_unlock(); + } } if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) { @@ -271,27 +277,16 @@ ipoib_mcast_sendonly_join_complete(int status, struct ipoib_mcast *mcast = multicast->context; struct net_device *dev = mcast->dev; - /* - * We have to take the mutex to force mcast_sendonly_join to - * return from ib_sa_multicast_join and set mcast->mc to a - * valid value. Otherwise we were racing with ourselves in - * that we might fail here, but get a valid return from - * ib_sa_multicast_join after we had cleared mcast->mc here, - * resulting in mis-matched joins and leaves and a deadlock - */ - mutex_lock(&mcast_mutex); - /* We trap for port events ourselves. */ if (status == -ENETRESET) - goto out; + return 0; if (!status) status = ipoib_mcast_join_finish(mcast, &multicast->rec); if (status) { if (mcast->logcount++ < 20) - ipoib_dbg_mcast(netdev_priv(dev), "sendonly multicast " - "join failed for %pI6, status %d\n", + ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for %pI6, status %d\n", mcast->mcmember.mgid.raw, status); /* Flush out any queued packets */ @@ -301,15 +296,11 @@ ipoib_mcast_sendonly_join_complete(int status, dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue)); } netif_tx_unlock_bh(dev); + + /* Clear the busy flag so we try again */ + status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, + &mcast->flags); } -out: - clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - if (status) - mcast->mc = NULL; - complete(&mcast->done); - if (status == -ENETRESET) - status = 0; - mutex_unlock(&mcast_mutex); return status; } @@ -327,14 +318,12 @@ static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast) int ret = 0; if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { - ipoib_dbg_mcast(priv, "device shutting down, no sendonly " - "multicast joins\n"); + ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n"); return -ENODEV; } - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) { - ipoib_dbg_mcast(priv, "multicast entry busy, skipping " - "sendonly join\n"); + if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) { + ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n"); return -EBUSY; } @@ -342,9 +331,6 @@ static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast) rec.port_gid = priv->local_gid; rec.pkey = cpu_to_be16(priv->pkey); - mutex_lock(&mcast_mutex); - init_completion(&mcast->done); - set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, &rec, IB_SA_MCMEMBER_REC_MGID | @@ -357,14 +343,12 @@ static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast) if (IS_ERR(mcast->mc)) { ret = PTR_ERR(mcast->mc); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - complete(&mcast->done); - ipoib_warn(priv, "ib_sa_join_multicast for sendonly join " - "failed (ret = %d)\n", ret); + ipoib_warn(priv, "ib_sa_join_multicast failed (ret = %d)\n", + ret); } else { - ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting " - "sendonly join\n", mcast->mcmember.mgid.raw); + ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting join\n", + mcast->mcmember.mgid.raw); } - mutex_unlock(&mcast_mutex); return ret; } @@ -375,29 +359,18 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work) carrier_on_task); struct ib_port_attr attr; + /* + * Take rtnl_lock to avoid racing with ipoib_stop() and + * turning the carrier back on while a device is being + * removed. + */ if (ib_query_port(priv->ca, priv->port, &attr) || attr.state != IB_PORT_ACTIVE) { ipoib_dbg(priv, "Keeping carrier off until IB port is active\n"); return; } - /* - * Take rtnl_lock to avoid racing with ipoib_stop() and - * turning the carrier back on while a device is being - * removed. However, ipoib_stop() will attempt to flush - * the workqueue while holding the rtnl lock, so loop - * on trylock until either we get the lock or we see - * FLAG_ADMIN_UP go away as that signals that we are bailing - * and can safely ignore the carrier on work. - */ - while (!rtnl_trylock()) { - if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) - return; - else - msleep(20); - } - if (!ipoib_cm_admin_enabled(priv->dev)) - dev_set_mtu(priv->dev, min(priv->mcast_mtu, priv->admin_mtu)); + rtnl_lock(); netif_carrier_on(priv->dev); rtnl_unlock(); } @@ -412,63 +385,60 @@ static int ipoib_mcast_join_complete(int status, ipoib_dbg_mcast(priv, "join completion for %pI6 (status %d)\n", mcast->mcmember.mgid.raw, status); - /* - * We have to take the mutex to force mcast_join to - * return from ib_sa_multicast_join and set mcast->mc to a - * valid value. Otherwise we were racing with ourselves in - * that we might fail here, but get a valid return from - * ib_sa_multicast_join after we had cleared mcast->mc here, - * resulting in mis-matched joins and leaves and a deadlock - */ - mutex_lock(&mcast_mutex); - /* We trap for port events ourselves. */ - if (status == -ENETRESET) + if (status == -ENETRESET) { + status = 0; goto out; + } if (!status) status = ipoib_mcast_join_finish(mcast, &multicast->rec); if (!status) { mcast->backoff = 1; + mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(priv->wq, &priv->mcast_task, 0); + queue_delayed_work(ipoib_workqueue, + &priv->mcast_task, 0); + mutex_unlock(&mcast_mutex); /* - * Defer carrier on work to priv->wq to avoid a + * Defer carrier on work to ipoib_workqueue to avoid a * deadlock on rtnl_lock here. */ if (mcast == priv->broadcast) - queue_work(priv->wq, &priv->carrier_on_task); - } else { - if (mcast->logcount++ < 20) { - if (status == -ETIMEDOUT || status == -EAGAIN) { - ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n", - mcast->mcmember.mgid.raw, status); - } else { - ipoib_warn(priv, "multicast join failed for %pI6, status %d\n", - mcast->mcmember.mgid.raw, status); - } - } + queue_work(ipoib_workqueue, &priv->carrier_on_task); - mcast->backoff *= 2; - if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) - mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; + status = 0; + goto out; } -out: + + if (mcast->logcount++ < 20) { + if (status == -ETIMEDOUT || status == -EAGAIN) { + ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n", + mcast->mcmember.mgid.raw, status); + } else { + ipoib_warn(priv, "multicast join failed for %pI6, status %d\n", + mcast->mcmember.mgid.raw, status); + } + } + + mcast->backoff *= 2; + if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) + mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; + + /* Clear the busy flag so we try again */ + status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + + mutex_lock(&mcast_mutex); spin_lock_irq(&priv->lock); - clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - if (status) - mcast->mc = NULL; - complete(&mcast->done); - if (status == -ENETRESET) - status = 0; - if (status && test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(priv->wq, &priv->mcast_task, + if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) + queue_delayed_work(ipoib_workqueue, &priv->mcast_task, mcast->backoff * HZ); spin_unlock_irq(&priv->lock); mutex_unlock(&mcast_mutex); - +out: + complete(&mcast->done); return status; } @@ -517,9 +487,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast, rec.hop_limit = priv->broadcast->mcmember.hop_limit; } - mutex_lock(&mcast_mutex); - init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + init_completion(&mcast->done); + set_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags); + mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, &rec, comp_mask, GFP_KERNEL, ipoib_mcast_join_complete, mcast); @@ -533,11 +504,13 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast, if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; + mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(priv->wq, &priv->mcast_task, + queue_delayed_work(ipoib_workqueue, + &priv->mcast_task, mcast->backoff * HZ); + mutex_unlock(&mcast_mutex); } - mutex_unlock(&mcast_mutex); } void ipoib_mcast_join_task(struct work_struct *work) @@ -574,8 +547,8 @@ void ipoib_mcast_join_task(struct work_struct *work) ipoib_warn(priv, "failed to allocate broadcast group\n"); mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(priv->wq, &priv->mcast_task, - HZ); + queue_delayed_work(ipoib_workqueue, + &priv->mcast_task, HZ); mutex_unlock(&mcast_mutex); return; } @@ -590,8 +563,7 @@ void ipoib_mcast_join_task(struct work_struct *work) } if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) { - if (IS_ERR_OR_NULL(priv->broadcast->mc) && - !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) + if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) ipoib_mcast_join(dev, priv->broadcast, 0); return; } @@ -599,33 +571,23 @@ void ipoib_mcast_join_task(struct work_struct *work) while (1) { struct ipoib_mcast *mcast = NULL; - /* - * Need the mutex so our flags are consistent, need the - * priv->lock so we don't race with list removals in either - * mcast_dev_flush or mcast_restart_task - */ - mutex_lock(&mcast_mutex); spin_lock_irq(&priv->lock); list_for_each_entry(mcast, &priv->multicast_list, list) { - if (IS_ERR_OR_NULL(mcast->mc) && - !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) && - !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) { + if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) + && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) + && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) { /* Found the next unjoined group */ break; } } spin_unlock_irq(&priv->lock); - mutex_unlock(&mcast_mutex); if (&mcast->list == &priv->multicast_list) { /* All done */ break; } - if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) - ipoib_mcast_sendonly_join(mcast); - else - ipoib_mcast_join(dev, mcast, 1); + ipoib_mcast_join(dev, mcast, 1); return; } @@ -642,13 +604,13 @@ int ipoib_mcast_start_thread(struct net_device *dev) mutex_lock(&mcast_mutex); if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(priv->wq, &priv->mcast_task, 0); + queue_delayed_work(ipoib_workqueue, &priv->mcast_task, 0); mutex_unlock(&mcast_mutex); return 0; } -int ipoib_mcast_stop_thread(struct net_device *dev) +int ipoib_mcast_stop_thread(struct net_device *dev, int flush) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -659,7 +621,8 @@ int ipoib_mcast_stop_thread(struct net_device *dev) cancel_delayed_work(&priv->mcast_task); mutex_unlock(&mcast_mutex); - flush_workqueue(priv->wq); + if (flush) + flush_workqueue(ipoib_workqueue); return 0; } @@ -670,9 +633,6 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) int ret = 0; if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - ipoib_warn(priv, "ipoib_mcast_leave on an in-flight join\n"); - - if (!IS_ERR_OR_NULL(mcast->mc)) ib_sa_free_multicast(mcast->mc); if (test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) { @@ -725,8 +685,6 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) memcpy(mcast->mcmember.mgid.raw, mgid, sizeof (union ib_gid)); __ipoib_mcast_add(dev, mcast); list_add_tail(&mcast->list, &priv->multicast_list); - if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(priv->wq, &priv->mcast_task, 0); } if (!mcast->ah) { @@ -740,6 +698,8 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) ipoib_dbg_mcast(priv, "no address vector, " "but multicast join already started\n"); + else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) + ipoib_mcast_sendonly_join(mcast); /* * If lookup completes between here and out:, don't @@ -799,12 +759,9 @@ void ipoib_mcast_dev_flush(struct net_device *dev) spin_unlock_irqrestore(&priv->lock, flags); - /* - * make sure the in-flight joins have finished before we attempt - * to leave - */ + /* seperate between the wait to the leave*/ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) + if (test_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags)) wait_for_completion(&mcast->done); list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { @@ -837,6 +794,8 @@ void ipoib_mcast_restart_task(struct work_struct *work) ipoib_dbg_mcast(priv, "restarting multicast task\n"); + ipoib_mcast_stop_thread(dev, 0); + local_irq_save(flags); netif_addr_lock(dev); spin_lock(&priv->lock); @@ -921,38 +880,14 @@ void ipoib_mcast_restart_task(struct work_struct *work) netif_addr_unlock(dev); local_irq_restore(flags); - /* - * make sure the in-flight joins have finished before we attempt - * to leave - */ - list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - wait_for_completion(&mcast->done); - - /* - * We have to cancel outside of the spinlock, but we have to - * take the rtnl lock or else we race with the removal of - * entries from the remove list in mcast_dev_flush as part - * of ipoib_stop(). We detect the drop of the ADMIN_UP flag - * to signal that we have hit this particular race, and we - * return since we know we don't need to do anything else - * anyway. - */ - while (!rtnl_trylock()) { - if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) - return; - else - msleep(20); - } + /* We have to cancel outside of the spinlock */ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { ipoib_mcast_leave(mcast->dev, mcast); ipoib_mcast_free(mcast); } - /* - * Restart our join task if needed - */ - ipoib_mcast_start_thread(dev); - rtnl_unlock(); + + if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) + ipoib_mcast_start_thread(dev); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index b72a753eb41d..c56d5d44c53b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -145,20 +145,10 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) int ret, size; int i; - /* - * the various IPoIB tasks assume they will never race against - * themselves, so always use a single thread workqueue - */ - priv->wq = create_singlethread_workqueue("ipoib_wq"); - if (!priv->wq) { - printk(KERN_WARNING "ipoib: failed to allocate device WQ\n"); - return -ENODEV; - } - priv->pd = ib_alloc_pd(priv->ca); if (IS_ERR(priv->pd)) { printk(KERN_WARNING "%s: failed to allocate PD\n", ca->name); - goto out_free_wq; + return -ENODEV; } priv->mr = ib_get_dma_mr(priv->pd, IB_ACCESS_LOCAL_WRITE); @@ -252,10 +242,6 @@ out_free_mr: out_free_pd: ib_dealloc_pd(priv->pd); - -out_free_wq: - destroy_workqueue(priv->wq); - priv->wq = NULL; return -ENODEV; } @@ -284,12 +270,6 @@ void ipoib_transport_dev_cleanup(struct net_device *dev) if (ib_dealloc_pd(priv->pd)) ipoib_warn(priv, "ib_dealloc_pd failed\n"); - - if (priv->wq) { - flush_workqueue(priv->wq); - destroy_workqueue(priv->wq); - priv->wq = NULL; - } } void ipoib_event(struct ib_event_handler *handler, diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 77ecf6d32237..6e22682c8255 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1097,6 +1097,8 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX31 0x361f00 20, 15, 0e clickpad * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad + * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) * Gigabyte U2442 0x450f01 58, 17, 0c 2 hw buttons * Lenovo L430 0x350f02 b9, 15, 0c 2 hw buttons (*) @@ -1475,6 +1477,20 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H730"), }, }, + { + /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"), + }, + }, + { + /* Fujitsu LIFEBOOK E544 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E544"), + }, + }, #endif { } }; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index f9472920d986..23e26e0768b5 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -135,8 +135,9 @@ static const struct min_max_quirk min_max_pnpid_table[] = { 1232, 5710, 1156, 4696 }, { - (const char * const []){"LEN0034", "LEN0036", "LEN0039", - "LEN2002", "LEN2004", NULL}, + (const char * const []){"LEN0034", "LEN0036", "LEN0037", + "LEN0039", "LEN2002", "LEN2004", + NULL}, 1024, 5112, 2024, 4832 }, { @@ -165,7 +166,7 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */ "LEN0035", /* X240 */ "LEN0036", /* T440 */ - "LEN0037", + "LEN0037", /* X1 Carbon 2nd */ "LEN0038", "LEN0039", /* T440s */ "LEN0041", diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 764857b4e268..c11556563ef0 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -152,6 +152,14 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, }, { + /* Medion Akoya E7225 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Medion"), + DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + }, + }, + { /* Blue FB5601 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "blue"), diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index f722a0c466cf..c48da057dbb1 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -315,6 +315,7 @@ static const struct iommu_ops gart_iommu_ops = { .attach_dev = gart_iommu_attach_dev, .detach_dev = gart_iommu_detach_dev, .map = gart_iommu_map, + .map_sg = default_iommu_map_sg, .unmap = gart_iommu_unmap, .iova_to_phys = gart_iommu_iova_to_phys, .pgsize_bitmap = GART_IOMMU_PGSIZES, @@ -395,7 +396,7 @@ static int tegra_gart_probe(struct platform_device *pdev) do_gart_setup(gart, NULL); gart_handle = gart; - bus_set_iommu(&platform_bus_type, &gart_iommu_ops); + return 0; } diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c index 0b380603a578..d7c286656a25 100644 --- a/drivers/isdn/hardware/eicon/message.c +++ b/drivers/isdn/hardware/eicon/message.c @@ -1474,7 +1474,7 @@ static byte connect_res(dword Id, word Number, DIVA_CAPI_ADAPTER *a, add_ai(plci, &parms[5]); sig_req(plci, REJECT, 0); } - else if (Reject == 1 || Reject > 9) + else if (Reject == 1 || Reject >= 9) { add_ai(plci, &parms[5]); sig_req(plci, HANGUP, 0); diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c index 5a4da94aefb0..ef9c8e4f1fa2 100644 --- a/drivers/isdn/isdnloop/isdnloop.c +++ b/drivers/isdn/isdnloop/isdnloop.c @@ -59,7 +59,8 @@ isdnloop_bchan_send(isdnloop_card *card, int ch) isdn_ctrl cmd; while (card->sndcount[ch]) { - if ((skb = skb_dequeue(&card->bqueue[ch]))) { + skb = skb_dequeue(&card->bqueue[ch]); + if (skb) { len = skb->len; card->sndcount[ch] -= len; ack = *(skb->head); /* used as scratch area */ @@ -149,8 +150,7 @@ typedef struct isdnloop_stat { int action; } isdnloop_stat; /* *INDENT-OFF* */ -static isdnloop_stat isdnloop_stat_table[] = -{ +static isdnloop_stat isdnloop_stat_table[] = { {"BCON_", ISDN_STAT_BCONN, 1}, /* B-Channel connected */ {"BDIS_", ISDN_STAT_BHUP, 2}, /* B-Channel disconnected */ {"DCON_", ISDN_STAT_DCONN, 0}, /* D-Channel connected */ @@ -317,7 +317,8 @@ isdnloop_polldchan(unsigned long data) u_char *p; isdn_ctrl cmd; - if ((skb = skb_dequeue(&card->dqueue))) + skb = skb_dequeue(&card->dqueue); + if (skb) avail = skb->len; else avail = 0; @@ -471,8 +472,8 @@ isdnloop_fake(isdnloop_card *card, char *s, int ch) { struct sk_buff *skb; int len = strlen(s) + ((ch >= 0) ? 3 : 0); - - if (!(skb = dev_alloc_skb(len))) { + skb = dev_alloc_skb(len); + if (!skb) { printk(KERN_WARNING "isdnloop: Out of memory in isdnloop_fake\n"); return 1; } @@ -483,8 +484,7 @@ isdnloop_fake(isdnloop_card *card, char *s, int ch) return 0; } /* *INDENT-OFF* */ -static isdnloop_stat isdnloop_cmd_table[] = -{ +static isdnloop_stat isdnloop_cmd_table[] = { {"BCON_R", 0, 1}, /* B-Channel connect */ {"BCON_I", 0, 17}, /* B-Channel connect ind */ {"BDIS_R", 0, 2}, /* B-Channel disconnect */ @@ -525,10 +525,8 @@ isdnloop_fake_err(isdnloop_card *card) isdnloop_fake(card, "NAK", -1); } -static u_char ctable_eu[] = -{0x00, 0x11, 0x01, 0x12}; -static u_char ctable_1t[] = -{0x00, 0x3b, 0x01, 0x3a}; +static u_char ctable_eu[] = {0x00, 0x11, 0x01, 0x12}; +static u_char ctable_1t[] = {0x00, 0x3b, 0x01, 0x3a}; /* * Assemble a simplified cause message depending on the @@ -554,9 +552,9 @@ isdnloop_unicause(isdnloop_card *card, int loc, int cau) sprintf(buf, "%02X44", ctable_1t[cau]); break; default: - return ("0000"); + return "0000"; } - return (buf); + return buf; } /* @@ -647,10 +645,8 @@ isdnloop_kill_ctimer(isdnloop_card *card, int ch) spin_unlock_irqrestore(&card->isdnloop_lock, flags); } -static u_char si2bit[] = -{0, 1, 0, 0, 0, 2, 0, 4, 0, 0}; -static u_char bit2si[] = -{1, 5, 7}; +static u_char si2bit[] = {0, 1, 0, 0, 0, 2, 0, 4, 0, 0}; +static u_char bit2si[] = {1, 5, 7}; /* * Try finding a listener for an outgoing call. @@ -754,17 +750,17 @@ isdnloop_vstphone(isdnloop_card *card, char *phone, int caller) if (caller) { for (i = 0; i < 2; i++) if (!(strcmp(card->s0num[i], phone))) - return (phone); - return (card->s0num[0]); + return phone; + return card->s0num[0]; } - return (phone); + return phone; break; case ISDN_PTYPE_1TR6: if (caller) { sprintf(nphone, "%s%c", card->s0num[0], phone[0]); - return (nphone); + return nphone; } else - return (&phone[strlen(phone) - 1]); + return &phone[strlen(phone) - 1]; break; } return ""; @@ -1148,14 +1144,14 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card) case ISDNLOOP_IOCTL_STARTUP: if (!access_ok(VERIFY_READ, (void *) a, sizeof(isdnloop_sdef))) return -EFAULT; - return (isdnloop_start(card, (isdnloop_sdef *) a)); + return isdnloop_start(card, (isdnloop_sdef *) a); break; case ISDNLOOP_IOCTL_ADDCARD: if (copy_from_user((char *)&cdef, (char *)a, sizeof(cdef))) return -EFAULT; - return (isdnloop_addcard(cdef.id1)); + return isdnloop_addcard(cdef.id1); break; case ISDNLOOP_IOCTL_LEASEDCFG: if (a) { @@ -1377,7 +1373,7 @@ if_command(isdn_ctrl *c) isdnloop_card *card = isdnloop_findcard(c->driver); if (card) - return (isdnloop_command(c, card)); + return isdnloop_command(c, card); printk(KERN_ERR "isdnloop: if_command called with invalid driverId!\n"); return -ENODEV; @@ -1391,7 +1387,7 @@ if_writecmd(const u_char __user *buf, int len, int id, int channel) if (card) { if (!(card->flags & ISDNLOOP_FLAGS_RUNNING)) return -ENODEV; - return (isdnloop_writecmd(buf, len, 1, card)); + return isdnloop_writecmd(buf, len, 1, card); } printk(KERN_ERR "isdnloop: if_writecmd called with invalid driverId!\n"); @@ -1406,7 +1402,7 @@ if_readstatus(u_char __user *buf, int len, int id, int channel) if (card) { if (!(card->flags & ISDNLOOP_FLAGS_RUNNING)) return -ENODEV; - return (isdnloop_readstatus(buf, len, card)); + return isdnloop_readstatus(buf, len, card); } printk(KERN_ERR "isdnloop: if_readstatus called with invalid driverId!\n"); @@ -1423,7 +1419,7 @@ if_sendbuf(int id, int channel, int ack, struct sk_buff *skb) return -ENODEV; /* ack request stored in skb scratch area */ *(skb->head) = ack; - return (isdnloop_sendbuf(channel, skb, card)); + return isdnloop_sendbuf(channel, skb, card); } printk(KERN_ERR "isdnloop: if_sendbuf called with invalid driverId!\n"); @@ -1439,8 +1435,8 @@ isdnloop_initcard(char *id) { isdnloop_card *card; int i; - - if (!(card = kzalloc(sizeof(isdnloop_card), GFP_KERNEL))) { + card = kzalloc(sizeof(isdnloop_card), GFP_KERNEL); + if (!card) { printk(KERN_WARNING "isdnloop: (%s) Could not allocate card-struct.\n", id); return (isdnloop_card *) 0; @@ -1489,8 +1485,8 @@ static int isdnloop_addcard(char *id1) { isdnloop_card *card; - - if (!(card = isdnloop_initcard(id1))) { + card = isdnloop_initcard(id1); + if (!card) { return -EIO; } printk(KERN_INFO @@ -1503,7 +1499,7 @@ static int __init isdnloop_init(void) { if (isdnloop_id) - return (isdnloop_addcard(isdnloop_id)); + return isdnloop_addcard(isdnloop_id); return 0; } diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index da3604e73e8a..1695ee5f3ffc 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -72,6 +72,19 @@ __acquires(bitmap->lock) /* this page has not been allocated yet */ spin_unlock_irq(&bitmap->lock); + /* It is possible that this is being called inside a + * prepare_to_wait/finish_wait loop from raid5c:make_request(). + * In general it is not permitted to sleep in that context as it + * can cause the loop to spin freely. + * That doesn't apply here as we can only reach this point + * once with any loop. + * When this function completes, either bp[page].map or + * bp[page].hijacked. In either case, this function will + * abort before getting to this point again. So there is + * no risk of a free-spin, and so it is safe to assert + * that sleeping here is allowed. + */ + sched_annotate_sleep(); mappage = kzalloc(PAGE_SIZE, GFP_NOIO); spin_lock_irq(&bitmap->lock); diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 21b156242e42..c1c010498a21 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -683,7 +683,7 @@ static struct dm_cache_metadata *metadata_open(struct block_device *bdev, cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) { DMERR("could not allocate metadata struct"); - return NULL; + return ERR_PTR(-ENOMEM); } atomic_set(&cmd->ref_count, 1); @@ -745,7 +745,7 @@ static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev, return cmd; cmd = metadata_open(bdev, data_block_size, may_format_device, policy_hint_size); - if (cmd) { + if (!IS_ERR(cmd)) { mutex_lock(&table_lock); cmd2 = lookup(bdev); if (cmd2) { @@ -780,9 +780,10 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, { struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size, may_format_device, policy_hint_size); - if (cmd && !same_params(cmd, data_block_size)) { + + if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) { dm_cache_metadata_close(cmd); - return NULL; + return ERR_PTR(-EINVAL); } return cmd; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 493478989dbd..07705ee181e3 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3385,6 +3385,12 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv) struct pool_c *pt = ti->private; struct pool *pool = pt->pool; + if (get_pool_mode(pool) >= PM_READ_ONLY) { + DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode", + dm_device_name(pool->pool_md)); + return -EINVAL; + } + if (!strcasecmp(argv[0], "create_thin")) r = process_create_thin_mesg(argc, argv, pool); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c1b0d52bfcb0..b98765f6f77f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3195,6 +3195,11 @@ static void handle_stripe_dirtying(struct r5conf *conf, (unsigned long long)sh->sector, rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); } + + if (rcw > disks && rmw > disks && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + set_bit(STRIPE_DELAYED, &sh->state); + /* now if nothing is locked, and if we have enough data, * we can start a write request */ diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index 7aaaf51e1596..35f19a683822 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -370,12 +370,12 @@ static int __qp_memcpy_to_queue(struct vmci_queue *queue, to_copy = size - bytes_copied; if (is_iovec) { - struct iovec *iov = (struct iovec *)src; + struct msghdr *msg = (struct msghdr *)src; int err; /* The iovec will track bytes_copied internally. */ - err = memcpy_fromiovec((u8 *)va + page_offset, - iov, to_copy); + err = memcpy_from_msg((u8 *)va + page_offset, + msg, to_copy); if (err != 0) { if (kernel_if->host) kunmap(kernel_if->u.h.page[page_index]); @@ -580,7 +580,7 @@ static int qp_memcpy_from_queue(void *dest, */ static int qp_memcpy_to_queue_iov(struct vmci_queue *queue, u64 queue_offset, - const void *src, + const void *msg, size_t src_offset, size_t size) { @@ -588,7 +588,7 @@ static int qp_memcpy_to_queue_iov(struct vmci_queue *queue, * We ignore src_offset because src is really a struct iovec * and will * maintain offset internally. */ - return __qp_memcpy_to_queue(queue, queue_offset, src, size, true); + return __qp_memcpy_to_queue(queue, queue_offset, msg, size, true); } /* @@ -3223,13 +3223,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_peek); * of bytes enqueued or < 0 on error. */ ssize_t vmci_qpair_enquev(struct vmci_qp *qpair, - void *iov, + struct msghdr *msg, size_t iov_size, int buf_type) { ssize_t result; - if (!qpair || !iov) + if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); @@ -3238,7 +3238,7 @@ ssize_t vmci_qpair_enquev(struct vmci_qp *qpair, result = qp_enqueue_locked(qpair->produce_q, qpair->consume_q, qpair->produce_q_size, - iov, iov_size, + msg, iov_size, qp_memcpy_to_queue_iov); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e229a8657de8..679ef00d6b16 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -77,6 +77,7 @@ #include <net/pkt_sched.h> #include <linux/rculist.h> #include <net/flow_keys.h> +#include <net/switchdev.h> #include <net/bonding.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> @@ -789,7 +790,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } new_active->delay = 0; - new_active->link = BOND_LINK_UP; + bond_set_slave_link_state(new_active, BOND_LINK_UP); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(new_active, BOND_LINK_UP); @@ -979,7 +980,11 @@ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t mask; struct slave *slave; - mask = features; + /* If any slave has the offload feature flag set, + * set the offload flag on the bond. + */ + mask = features | NETIF_F_HW_SWITCH_OFFLOAD; + features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; @@ -1176,6 +1181,62 @@ static void bond_free_slave(struct slave *slave) kfree(slave); } +static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) +{ + info->bond_mode = BOND_MODE(bond); + info->miimon = bond->params.miimon; + info->num_slaves = bond->slave_cnt; +} + +static void bond_fill_ifslave(struct slave *slave, struct ifslave *info) +{ + strcpy(info->slave_name, slave->dev->name); + info->link = slave->link; + info->state = bond_slave_state(slave); + info->link_failure_count = slave->link_failure_count; +} + +static void bond_netdev_notify(struct slave *slave, struct net_device *dev) +{ + struct bonding *bond = slave->bond; + struct netdev_bonding_info bonding_info; + + rtnl_lock(); + /* make sure that slave is still valid */ + if (dev->priv_flags & IFF_BONDING) { + bond_fill_ifslave(slave, &bonding_info.slave); + bond_fill_ifbond(bond, &bonding_info.master); + netdev_bonding_info_change(slave->dev, &bonding_info); + } + rtnl_unlock(); +} + +static void bond_netdev_notify_work(struct work_struct *_work) +{ + struct netdev_notify_work *w = + container_of(_work, struct netdev_notify_work, work.work); + + bond_netdev_notify(w->slave, w->dev); + dev_put(w->dev); +} + +void bond_queue_slave_event(struct slave *slave) +{ + struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC); + + if (!nnw) + return; + + INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work); + nnw->slave = slave; + nnw->dev = slave->dev; + + if (queue_delayed_work(slave->bond->wq, &nnw->work, 0)) + dev_hold(slave->dev); + else + kfree(nnw); +} + /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { @@ -1439,19 +1500,22 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) if (bond->params.miimon) { if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { if (bond->params.updelay) { - new_slave->link = BOND_LINK_BACK; + bond_set_slave_link_state(new_slave, + BOND_LINK_BACK); new_slave->delay = bond->params.updelay; } else { - new_slave->link = BOND_LINK_UP; + bond_set_slave_link_state(new_slave, + BOND_LINK_UP); } } else { - new_slave->link = BOND_LINK_DOWN; + bond_set_slave_link_state(new_slave, BOND_LINK_DOWN); } } else if (bond->params.arp_interval) { - new_slave->link = (netif_carrier_ok(slave_dev) ? - BOND_LINK_UP : BOND_LINK_DOWN); + bond_set_slave_link_state(new_slave, + (netif_carrier_ok(slave_dev) ? + BOND_LINK_UP : BOND_LINK_DOWN)); } else { - new_slave->link = BOND_LINK_UP; + bond_set_slave_link_state(new_slave, BOND_LINK_UP); } if (new_slave->link != BOND_LINK_DOWN) @@ -1567,6 +1631,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ + bond_queue_slave_event(new_slave); return 0; /* Undo stages on error */ @@ -1816,11 +1881,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = netdev_priv(bond_dev); - - info->bond_mode = BOND_MODE(bond); - info->miimon = bond->params.miimon; - info->num_slaves = bond->slave_cnt; - + bond_fill_ifbond(bond, info); return 0; } @@ -1834,10 +1895,7 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in bond_for_each_slave(bond, slave, iter) { if (i++ == (int)info->slave_id) { res = 0; - strcpy(info->slave_name, slave->dev->name); - info->link = slave->link; - info->state = bond_slave_state(slave); - info->link_failure_count = slave->link_failure_count; + bond_fill_ifslave(slave, info); break; } } @@ -1867,7 +1925,7 @@ static int bond_miimon_inspect(struct bonding *bond) if (link_state) continue; - slave->link = BOND_LINK_FAIL; + bond_set_slave_link_state(slave, BOND_LINK_FAIL); slave->delay = bond->params.downdelay; if (slave->delay) { netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n", @@ -1882,7 +1940,7 @@ static int bond_miimon_inspect(struct bonding *bond) case BOND_LINK_FAIL: if (link_state) { /* recovered before downdelay expired */ - slave->link = BOND_LINK_UP; + bond_set_slave_link_state(slave, BOND_LINK_UP); slave->last_link_up = jiffies; netdev_info(bond->dev, "link status up again after %d ms for interface %s\n", (bond->params.downdelay - slave->delay) * @@ -1904,7 +1962,7 @@ static int bond_miimon_inspect(struct bonding *bond) if (!link_state) continue; - slave->link = BOND_LINK_BACK; + bond_set_slave_link_state(slave, BOND_LINK_BACK); slave->delay = bond->params.updelay; if (slave->delay) { @@ -1917,7 +1975,8 @@ static int bond_miimon_inspect(struct bonding *bond) /*FALLTHRU*/ case BOND_LINK_BACK: if (!link_state) { - slave->link = BOND_LINK_DOWN; + bond_set_slave_link_state(slave, + BOND_LINK_DOWN); netdev_info(bond->dev, "link status down again after %d ms for interface %s\n", (bond->params.updelay - slave->delay) * bond->params.miimon, @@ -1955,7 +2014,7 @@ static void bond_miimon_commit(struct bonding *bond) continue; case BOND_LINK_UP: - slave->link = BOND_LINK_UP; + bond_set_slave_link_state(slave, BOND_LINK_UP); slave->last_link_up = jiffies; primary = rtnl_dereference(bond->primary_slave); @@ -1995,7 +2054,7 @@ static void bond_miimon_commit(struct bonding *bond) if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - slave->link = BOND_LINK_DOWN; + bond_set_slave_link_state(slave, BOND_LINK_DOWN); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_8023AD) @@ -2578,7 +2637,7 @@ static void bond_ab_arp_commit(struct bonding *bond) struct slave *current_arp_slave; current_arp_slave = rtnl_dereference(bond->current_arp_slave); - slave->link = BOND_LINK_UP; + bond_set_slave_link_state(slave, BOND_LINK_UP); if (current_arp_slave) { bond_set_slave_inactive_flags( current_arp_slave, @@ -2601,7 +2660,7 @@ static void bond_ab_arp_commit(struct bonding *bond) if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - slave->link = BOND_LINK_DOWN; + bond_set_slave_link_state(slave, BOND_LINK_DOWN); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); @@ -2680,7 +2739,7 @@ static bool bond_ab_arp_probe(struct bonding *bond) * up when it is actually down */ if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { - slave->link = BOND_LINK_DOWN; + bond_set_slave_link_state(slave, BOND_LINK_DOWN); if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; @@ -2700,7 +2759,7 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (!new_slave) goto check_state; - new_slave->link = BOND_LINK_BACK; + bond_set_slave_link_state(new_slave, BOND_LINK_BACK); bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); bond_arp_send_all(bond, new_slave); new_slave->last_link_up = jiffies; @@ -3952,6 +4011,8 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, + .ndo_bridge_setlink = ndo_dflt_netdev_switch_port_bridge_setlink, + .ndo_bridge_dellink = ndo_dflt_netdev_switch_port_bridge_dellink, }; static const struct device_type bond_type = { diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c index 5e40a8b68cbe..b3b922adc0e4 100644 --- a/drivers/net/caif/caif_hsi.c +++ b/drivers/net/caif/caif_hsi.c @@ -1415,7 +1415,6 @@ static int caif_hsi_newlink(struct net *src_net, struct net_device *dev, cfhsi = netdev_priv(dev); cfhsi_netlink_parms(data, cfhsi); - dev_net_set(cfhsi->ndev, src_net); get_ops = symbol_get(cfhsi_get_ops); if (!get_ops) { diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 0eb4d181ae4d..4dd183a3643a 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1679,8 +1679,7 @@ static int ican3_get_berr_counter(const struct net_device *ndev, if (ret) return ret; - ret = wait_for_completion_timeout(&mod->buserror_comp, HZ); - if (ret == 0) { + if (!wait_for_completion_timeout(&mod->buserror_comp, HZ)) { netdev_info(mod->ndev, "%s timed out\n", __func__); return -ETIMEDOUT; } @@ -1705,8 +1704,7 @@ static ssize_t ican3_sysfs_show_term(struct device *dev, if (ret) return ret; - ret = wait_for_completion_timeout(&mod->termination_comp, HZ); - if (ret == 0) { + if (!wait_for_completion_timeout(&mod->termination_comp, HZ)) { netdev_info(mod->ndev, "%s timed out\n", __func__); return -ETIMEDOUT; } diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index a77db919363c..bcb272f6c68a 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -25,7 +25,7 @@ config CAN_KVASER_USB tristate "Kvaser CAN/USB interface" ---help--- This driver adds support for Kvaser CAN/USB devices like Kvaser - Leaf Light. + Leaf Light and Kvaser USBcan II. The driver provides support for the following devices: - Kvaser Leaf Light @@ -46,6 +46,12 @@ config CAN_KVASER_USB - Kvaser USBcan R - Kvaser Leaf Light v2 - Kvaser Mini PCI Express HS + - Kvaser USBcan II HS/HS + - Kvaser USBcan II HS/LS + - Kvaser USBcan Rugged ("USBcan Rev B") + - Kvaser Memorator HS/HS + - Kvaser Memorator HS/LS + - Scania VCI2 (if you have the Kvaser logo on top) If unsure, say N. @@ -53,10 +59,18 @@ config CAN_KVASER_USB module will be called kvaser_usb. config CAN_PEAK_USB - tristate "PEAK PCAN-USB/USB Pro interfaces" + tristate "PEAK PCAN-USB/USB Pro interfaces for CAN 2.0b/CAN-FD" ---help--- - This driver supports the PCAN-USB and PCAN-USB Pro adapters - from PEAK-System Technik (http://www.peak-system.com). + This driver supports the PEAK-System Technik USB adapters that enable + access to the CAN bus, with repect to the CAN 2.0b and/or CAN-FD + standards, that is: + + PCAN-USB single CAN 2.0b channel USB adapter + PCAN-USB Pro dual CAN 2.0b channels USB adapter + PCAN-USB FD single CAN-FD channel USB adapter + PCAN-USB Pro FD dual CAN-FD channels USB adapter + + (see also http://www.peak-system.com). config CAN_8DEV_USB tristate "8 devices USB2CAN interface" diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 7af379ca861b..2928f7003041 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -6,10 +6,12 @@ * Parts of this driver are based on the following: * - Kvaser linux leaf driver (version 4.78) * - CAN driver for esd CAN-USB/2 + * - Kvaser linux usbcanII driver (version 5.3) * * Copyright (C) 2002-2006 KVASER AB, Sweden. All rights reserved. * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be> + * Copyright (C) 2015 Valeo S.A. */ #include <linux/completion.h> @@ -30,8 +32,9 @@ #define RX_BUFFER_SIZE 3072 #define CAN_USB_CLOCK 8000000 #define MAX_NET_DEVICES 3 +#define MAX_USBCAN_NET_DEVICES 2 -/* Kvaser USB devices */ +/* Kvaser Leaf USB devices */ #define KVASER_VENDOR_ID 0x0bfd #define USB_LEAF_DEVEL_PRODUCT_ID 10 #define USB_LEAF_LITE_PRODUCT_ID 11 @@ -56,6 +59,24 @@ #define USB_LEAF_LITE_V2_PRODUCT_ID 288 #define USB_MINI_PCIE_HS_PRODUCT_ID 289 +static inline bool kvaser_is_leaf(const struct usb_device_id *id) +{ + return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID && + id->idProduct <= USB_MINI_PCIE_HS_PRODUCT_ID; +} + +/* Kvaser USBCan-II devices */ +#define USB_USBCAN_REVB_PRODUCT_ID 2 +#define USB_VCI2_PRODUCT_ID 3 +#define USB_USBCAN2_PRODUCT_ID 4 +#define USB_MEMORATOR_PRODUCT_ID 5 + +static inline bool kvaser_is_usbcan(const struct usb_device_id *id) +{ + return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID && + id->idProduct <= USB_MEMORATOR_PRODUCT_ID; +} + /* USB devices features */ #define KVASER_HAS_SILENT_MODE BIT(0) #define KVASER_HAS_TXRX_ERRORS BIT(1) @@ -73,7 +94,7 @@ #define MSG_FLAG_TX_ACK BIT(6) #define MSG_FLAG_TX_REQUEST BIT(7) -/* Can states */ +/* Can states (M16C CxSTRH register) */ #define M16C_STATE_BUS_RESET BIT(0) #define M16C_STATE_BUS_ERROR BIT(4) #define M16C_STATE_BUS_PASSIVE BIT(5) @@ -98,7 +119,11 @@ #define CMD_START_CHIP_REPLY 27 #define CMD_STOP_CHIP 28 #define CMD_STOP_CHIP_REPLY 29 -#define CMD_GET_CARD_INFO2 32 + +#define CMD_LEAF_GET_CARD_INFO2 32 +#define CMD_USBCAN_RESET_CLOCK 32 +#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT 33 + #define CMD_GET_CARD_INFO 34 #define CMD_GET_CARD_INFO_REPLY 35 #define CMD_GET_SOFTWARE_INFO 38 @@ -108,8 +133,9 @@ #define CMD_RESET_ERROR_COUNTER 49 #define CMD_TX_ACKNOWLEDGE 50 #define CMD_CAN_ERROR_EVENT 51 -#define CMD_USB_THROTTLE 77 -#define CMD_LOG_MESSAGE 106 + +#define CMD_LEAF_USB_THROTTLE 77 +#define CMD_LEAF_LOG_MESSAGE 106 /* error factors */ #define M16C_EF_ACKE BIT(0) @@ -121,6 +147,14 @@ #define M16C_EF_RCVE BIT(6) #define M16C_EF_TRE BIT(7) +/* Only Leaf-based devices can report M16C error factors, + * thus define our own error status flags for USBCANII + */ +#define USBCAN_ERROR_STATE_NONE 0 +#define USBCAN_ERROR_STATE_TX_ERROR BIT(0) +#define USBCAN_ERROR_STATE_RX_ERROR BIT(1) +#define USBCAN_ERROR_STATE_BUSERROR BIT(2) + /* bittiming parameters */ #define KVASER_USB_TSEG1_MIN 1 #define KVASER_USB_TSEG1_MAX 16 @@ -137,9 +171,18 @@ #define KVASER_CTRL_MODE_SELFRECEPTION 3 #define KVASER_CTRL_MODE_OFF 4 -/* log message */ +/* Extended CAN identifier flag */ #define KVASER_EXTENDED_FRAME BIT(31) +/* Kvaser USB CAN dongles are divided into two major families: + * - Leaf: Based on Renesas M32C, running firmware labeled as 'filo' + * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios' + */ +enum kvaser_usb_family { + KVASER_LEAF, + KVASER_USBCAN, +}; + struct kvaser_msg_simple { u8 tid; u8 channel; @@ -148,30 +191,55 @@ struct kvaser_msg_simple { struct kvaser_msg_cardinfo { u8 tid; u8 nchannels; - __le32 serial_number; - __le32 padding; + union { + struct { + __le32 serial_number; + __le32 padding; + } __packed leaf0; + struct { + __le32 serial_number_low; + __le32 serial_number_high; + } __packed usbcan0; + } __packed; __le32 clock_resolution; __le32 mfgdate; u8 ean[8]; u8 hw_revision; - u8 usb_hs_mode; - __le16 padding2; + union { + struct { + u8 usb_hs_mode; + } __packed leaf1; + struct { + u8 padding; + } __packed usbcan1; + } __packed; + __le16 padding; } __packed; struct kvaser_msg_cardinfo2 { u8 tid; - u8 channel; + u8 reserved; u8 pcb_id[24]; __le32 oem_unlock_code; } __packed; -struct kvaser_msg_softinfo { +struct leaf_msg_softinfo { u8 tid; - u8 channel; + u8 padding0; __le32 sw_options; __le32 fw_version; __le16 max_outstanding_tx; - __le16 padding[9]; + __le16 padding1[9]; +} __packed; + +struct usbcan_msg_softinfo { + u8 tid; + u8 fw_name[5]; + __le16 max_outstanding_tx; + u8 padding[6]; + __le32 fw_version; + __le16 checksum; + __le16 sw_options; } __packed; struct kvaser_msg_busparams { @@ -188,36 +256,86 @@ struct kvaser_msg_tx_can { u8 channel; u8 tid; u8 msg[14]; - u8 padding; - u8 flags; + union { + struct { + u8 padding; + u8 flags; + } __packed leaf; + struct { + u8 flags; + u8 padding; + } __packed usbcan; + } __packed; +} __packed; + +struct kvaser_msg_rx_can_header { + u8 channel; + u8 flag; } __packed; -struct kvaser_msg_rx_can { +struct leaf_msg_rx_can { u8 channel; u8 flag; + __le16 time[3]; u8 msg[14]; } __packed; -struct kvaser_msg_chip_state_event { +struct usbcan_msg_rx_can { + u8 channel; + u8 flag; + + u8 msg[14]; + __le16 time; +} __packed; + +struct leaf_msg_chip_state_event { u8 tid; u8 channel; + __le16 time[3]; u8 tx_errors_count; u8 rx_errors_count; + u8 status; u8 padding[3]; } __packed; -struct kvaser_msg_tx_acknowledge { +struct usbcan_msg_chip_state_event { + u8 tid; + u8 channel; + + u8 tx_errors_count; + u8 rx_errors_count; + __le16 time; + + u8 status; + u8 padding[3]; +} __packed; + +struct kvaser_msg_tx_acknowledge_header { u8 channel; u8 tid; +} __packed; + +struct leaf_msg_tx_acknowledge { + u8 channel; + u8 tid; + __le16 time[3]; u8 flags; u8 time_offset; } __packed; -struct kvaser_msg_error_event { +struct usbcan_msg_tx_acknowledge { + u8 channel; + u8 tid; + + __le16 time; + __le16 padding; +} __packed; + +struct leaf_msg_error_event { u8 tid; u8 flags; __le16 time[3]; @@ -229,6 +347,18 @@ struct kvaser_msg_error_event { u8 error_factor; } __packed; +struct usbcan_msg_error_event { + u8 tid; + u8 padding; + u8 tx_errors_count_ch0; + u8 rx_errors_count_ch0; + u8 tx_errors_count_ch1; + u8 rx_errors_count_ch1; + u8 status_ch0; + u8 status_ch1; + __le16 time; +} __packed; + struct kvaser_msg_ctrl_mode { u8 tid; u8 channel; @@ -243,7 +373,7 @@ struct kvaser_msg_flush_queue { u8 padding[3]; } __packed; -struct kvaser_msg_log_message { +struct leaf_msg_log_message { u8 channel; u8 flags; __le16 time[3]; @@ -260,19 +390,57 @@ struct kvaser_msg { struct kvaser_msg_simple simple; struct kvaser_msg_cardinfo cardinfo; struct kvaser_msg_cardinfo2 cardinfo2; - struct kvaser_msg_softinfo softinfo; struct kvaser_msg_busparams busparams; + + struct kvaser_msg_rx_can_header rx_can_header; + struct kvaser_msg_tx_acknowledge_header tx_acknowledge_header; + + union { + struct leaf_msg_softinfo softinfo; + struct leaf_msg_rx_can rx_can; + struct leaf_msg_chip_state_event chip_state_event; + struct leaf_msg_tx_acknowledge tx_acknowledge; + struct leaf_msg_error_event error_event; + struct leaf_msg_log_message log_message; + } __packed leaf; + + union { + struct usbcan_msg_softinfo softinfo; + struct usbcan_msg_rx_can rx_can; + struct usbcan_msg_chip_state_event chip_state_event; + struct usbcan_msg_tx_acknowledge tx_acknowledge; + struct usbcan_msg_error_event error_event; + } __packed usbcan; + struct kvaser_msg_tx_can tx_can; - struct kvaser_msg_rx_can rx_can; - struct kvaser_msg_chip_state_event chip_state_event; - struct kvaser_msg_tx_acknowledge tx_acknowledge; - struct kvaser_msg_error_event error_event; struct kvaser_msg_ctrl_mode ctrl_mode; struct kvaser_msg_flush_queue flush_queue; - struct kvaser_msg_log_message log_message; } u; } __packed; +/* Summary of a kvaser error event, for a unified Leaf/Usbcan error + * handling. Some discrepancies between the two families exist: + * + * - USBCAN firmware does not report M16C "error factors" + * - USBCAN controllers has difficulties reporting if the raised error + * event is for ch0 or ch1. They leave such arbitration to the OS + * driver by letting it compare error counters with previous values + * and decide the error event's channel. Thus for USBCAN, the channel + * field is only advisory. + */ +struct kvaser_usb_error_summary { + u8 channel, status, txerr, rxerr; + union { + struct { + u8 error_factor; + } leaf; + struct { + u8 other_ch_status; + u8 error_state; + } usbcan; + }; +}; + struct kvaser_usb_tx_urb_context { struct kvaser_usb_net_priv *priv; u32 echo_index; @@ -288,6 +456,7 @@ struct kvaser_usb { u32 fw_version; unsigned int nchannels; + enum kvaser_usb_family family; bool rxinitdone; void *rxbuf[MAX_RX_URBS]; @@ -311,6 +480,7 @@ struct kvaser_usb_net_priv { }; static const struct usb_device_id kvaser_usb_table[] = { + /* Leaf family IDs */ { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID), @@ -360,6 +530,17 @@ static const struct usb_device_id kvaser_usb_table[] = { .driver_info = KVASER_HAS_TXRX_ERRORS }, { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) }, + + /* USBCANII family IDs */ + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID), + .driver_info = KVASER_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID), + .driver_info = KVASER_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID), + .driver_info = KVASER_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID), + .driver_info = KVASER_HAS_TXRX_ERRORS }, + { } }; MODULE_DEVICE_TABLE(usb, kvaser_usb_table); @@ -463,7 +644,14 @@ static int kvaser_usb_get_software_info(struct kvaser_usb *dev) if (err) return err; - dev->fw_version = le32_to_cpu(msg.u.softinfo.fw_version); + switch (dev->family) { + case KVASER_LEAF: + dev->fw_version = le32_to_cpu(msg.u.leaf.softinfo.fw_version); + break; + case KVASER_USBCAN: + dev->fw_version = le32_to_cpu(msg.u.usbcan.softinfo.fw_version); + break; + } return 0; } @@ -482,7 +670,9 @@ static int kvaser_usb_get_card_info(struct kvaser_usb *dev) return err; dev->nchannels = msg.u.cardinfo.nchannels; - if (dev->nchannels > MAX_NET_DEVICES) + if ((dev->nchannels > MAX_NET_DEVICES) || + (dev->family == KVASER_USBCAN && + dev->nchannels > MAX_USBCAN_NET_DEVICES)) return -EINVAL; return 0; @@ -496,8 +686,10 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev, struct kvaser_usb_net_priv *priv; struct sk_buff *skb; struct can_frame *cf; - u8 channel = msg->u.tx_acknowledge.channel; - u8 tid = msg->u.tx_acknowledge.tid; + u8 channel, tid; + + channel = msg->u.tx_acknowledge_header.channel; + tid = msg->u.tx_acknowledge_header.tid; if (channel >= dev->nchannels) { dev_err(dev->udev->dev.parent, @@ -615,158 +807,280 @@ static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) priv->tx_contexts[i].echo_index = MAX_TX_URBS; } -static void kvaser_usb_rx_error(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) +static void kvaser_usb_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, + const struct kvaser_usb_error_summary *es, + struct can_frame *cf) { - struct can_frame *cf; - struct sk_buff *skb; - struct net_device_stats *stats; - struct kvaser_usb_net_priv *priv; - unsigned int new_state; - u8 channel, status, txerr, rxerr, error_factor; + struct kvaser_usb *dev = priv->dev; + struct net_device_stats *stats = &priv->netdev->stats; + enum can_state cur_state, new_state, tx_state, rx_state; - switch (msg->id) { - case CMD_CAN_ERROR_EVENT: - channel = msg->u.error_event.channel; - status = msg->u.error_event.status; - txerr = msg->u.error_event.tx_errors_count; - rxerr = msg->u.error_event.rx_errors_count; - error_factor = msg->u.error_event.error_factor; - break; - case CMD_LOG_MESSAGE: - channel = msg->u.log_message.channel; - status = msg->u.log_message.data[0]; - txerr = msg->u.log_message.data[2]; - rxerr = msg->u.log_message.data[3]; - error_factor = msg->u.log_message.data[1]; + netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status); + + new_state = cur_state = priv->can.state; + + if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) + new_state = CAN_STATE_BUS_OFF; + else if (es->status & M16C_STATE_BUS_PASSIVE) + new_state = CAN_STATE_ERROR_PASSIVE; + else if (es->status & M16C_STATE_BUS_ERROR) { + /* Guard against spurious error events after a busoff */ + if (cur_state < CAN_STATE_BUS_OFF) { + if ((es->txerr >= 128) || (es->rxerr >= 128)) + new_state = CAN_STATE_ERROR_PASSIVE; + else if ((es->txerr >= 96) || (es->rxerr >= 96)) + new_state = CAN_STATE_ERROR_WARNING; + else if (cur_state > CAN_STATE_ERROR_ACTIVE) + new_state = CAN_STATE_ERROR_ACTIVE; + } + } + + if (!es->status) + new_state = CAN_STATE_ERROR_ACTIVE; + + if (new_state != cur_state) { + tx_state = (es->txerr >= es->rxerr) ? new_state : 0; + rx_state = (es->txerr <= es->rxerr) ? new_state : 0; + + can_change_state(priv->netdev, cf, tx_state, rx_state); + } + + if (priv->can.restart_ms && + (cur_state >= CAN_STATE_BUS_OFF) && + (new_state < CAN_STATE_BUS_OFF)) { + priv->can.can_stats.restarts++; + } + + switch (dev->family) { + case KVASER_LEAF: + if (es->leaf.error_factor) { + priv->can.can_stats.bus_error++; + stats->rx_errors++; + } break; - case CMD_CHIP_STATE_EVENT: - channel = msg->u.chip_state_event.channel; - status = msg->u.chip_state_event.status; - txerr = msg->u.chip_state_event.tx_errors_count; - rxerr = msg->u.chip_state_event.rx_errors_count; - error_factor = 0; + case KVASER_USBCAN: + if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR) + stats->tx_errors++; + if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR) + stats->rx_errors++; + if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) { + priv->can.can_stats.bus_error++; + } break; - default: - dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n", - msg->id); - return; } - if (channel >= dev->nchannels) { + priv->bec.txerr = es->txerr; + priv->bec.rxerr = es->rxerr; +} + +static void kvaser_usb_rx_error(const struct kvaser_usb *dev, + const struct kvaser_usb_error_summary *es) +{ + struct can_frame *cf, tmp_cf = { .can_id = CAN_ERR_FLAG, .can_dlc = CAN_ERR_DLC }; + struct sk_buff *skb; + struct net_device_stats *stats; + struct kvaser_usb_net_priv *priv; + enum can_state old_state, new_state; + + if (es->channel >= dev->nchannels) { dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", channel); + "Invalid channel number (%d)\n", es->channel); return; } - priv = dev->nets[channel]; + priv = dev->nets[es->channel]; stats = &priv->netdev->stats; + /* Update all of the can interface's state and error counters before + * trying any memory allocation that can actually fail with -ENOMEM. + * + * We send a temporary stack-allocated error can frame to + * can_change_state() for the very same reason. + * + * TODO: Split can_change_state() responsibility between updating the + * can interface's state and counters, and the setting up of can error + * frame ID and data to userspace. Remove stack allocation afterwards. + */ + old_state = priv->can.state; + kvaser_usb_rx_error_update_can_state(priv, es, &tmp_cf); + new_state = priv->can.state; + skb = alloc_can_err_skb(priv->netdev, &cf); if (!skb) { stats->rx_dropped++; return; } + memcpy(cf, &tmp_cf, sizeof(*cf)); + + if (new_state != old_state) { + if (es->status & + (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { + if (!priv->can.restart_ms) + kvaser_usb_simple_msg_async(priv, CMD_STOP_CHIP); + netif_carrier_off(priv->netdev); + } - new_state = priv->can.state; - - netdev_dbg(priv->netdev, "Error status: 0x%02x\n", status); + if (priv->can.restart_ms && + (old_state >= CAN_STATE_BUS_OFF) && + (new_state < CAN_STATE_BUS_OFF)) { + cf->can_id |= CAN_ERR_RESTARTED; + netif_carrier_on(priv->netdev); + } + } - if (status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { - cf->can_id |= CAN_ERR_BUSOFF; + switch (dev->family) { + case KVASER_LEAF: + if (es->leaf.error_factor) { + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT; + + if (es->leaf.error_factor & M16C_EF_ACKE) + cf->data[3] |= (CAN_ERR_PROT_LOC_ACK); + if (es->leaf.error_factor & M16C_EF_CRCE) + cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ | + CAN_ERR_PROT_LOC_CRC_DEL); + if (es->leaf.error_factor & M16C_EF_FORME) + cf->data[2] |= CAN_ERR_PROT_FORM; + if (es->leaf.error_factor & M16C_EF_STFE) + cf->data[2] |= CAN_ERR_PROT_STUFF; + if (es->leaf.error_factor & M16C_EF_BITE0) + cf->data[2] |= CAN_ERR_PROT_BIT0; + if (es->leaf.error_factor & M16C_EF_BITE1) + cf->data[2] |= CAN_ERR_PROT_BIT1; + if (es->leaf.error_factor & M16C_EF_TRE) + cf->data[2] |= CAN_ERR_PROT_TX; + } + break; + case KVASER_USBCAN: + if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) { + cf->can_id |= CAN_ERR_BUSERROR; + } + break; + } - priv->can.can_stats.bus_off++; - if (!priv->can.restart_ms) - kvaser_usb_simple_msg_async(priv, CMD_STOP_CHIP); + cf->data[6] = es->txerr; + cf->data[7] = es->rxerr; - netif_carrier_off(priv->netdev); + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); +} - new_state = CAN_STATE_BUS_OFF; - } else if (status & M16C_STATE_BUS_PASSIVE) { - if (priv->can.state != CAN_STATE_ERROR_PASSIVE) { - cf->can_id |= CAN_ERR_CRTL; - - if (txerr || rxerr) - cf->data[1] = (txerr > rxerr) - ? CAN_ERR_CRTL_TX_PASSIVE - : CAN_ERR_CRTL_RX_PASSIVE; - else - cf->data[1] = CAN_ERR_CRTL_TX_PASSIVE | - CAN_ERR_CRTL_RX_PASSIVE; - - priv->can.can_stats.error_passive++; - } +/* For USBCAN, report error to userspace iff the channels's errors counter + * has changed, or we're the only channel seeing a bus error state. + */ +static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev, + struct kvaser_usb_error_summary *es) +{ + struct kvaser_usb_net_priv *priv; + int channel; + bool report_error; - new_state = CAN_STATE_ERROR_PASSIVE; - } else if (status & M16C_STATE_BUS_ERROR) { - if ((priv->can.state < CAN_STATE_ERROR_WARNING) && - ((txerr >= 96) || (rxerr >= 96))) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = (txerr > rxerr) - ? CAN_ERR_CRTL_TX_WARNING - : CAN_ERR_CRTL_RX_WARNING; - - priv->can.can_stats.error_warning++; - new_state = CAN_STATE_ERROR_WARNING; - } else if ((priv->can.state > CAN_STATE_ERROR_ACTIVE) && - ((txerr < 96) && (rxerr < 96))) { - cf->can_id |= CAN_ERR_PROT; - cf->data[2] = CAN_ERR_PROT_ACTIVE; - - new_state = CAN_STATE_ERROR_ACTIVE; - } + channel = es->channel; + if (channel >= dev->nchannels) { + dev_err(dev->udev->dev.parent, + "Invalid channel number (%d)\n", channel); + return; } - if (!status) { - cf->can_id |= CAN_ERR_PROT; - cf->data[2] = CAN_ERR_PROT_ACTIVE; + priv = dev->nets[channel]; + report_error = false; - new_state = CAN_STATE_ERROR_ACTIVE; + if (es->txerr != priv->bec.txerr) { + es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR; + report_error = true; + } + if (es->rxerr != priv->bec.rxerr) { + es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR; + report_error = true; + } + if ((es->status & M16C_STATE_BUS_ERROR) && + !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) { + es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR; + report_error = true; } - if (priv->can.restart_ms && - (priv->can.state >= CAN_STATE_BUS_OFF) && - (new_state < CAN_STATE_BUS_OFF)) { - cf->can_id |= CAN_ERR_RESTARTED; - netif_carrier_on(priv->netdev); + if (report_error) + kvaser_usb_rx_error(dev, es); +} - priv->can.can_stats.restarts++; - } +static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev, + const struct kvaser_msg *msg) +{ + struct kvaser_usb_error_summary es = { }; - if (error_factor) { - priv->can.can_stats.bus_error++; - stats->rx_errors++; + switch (msg->id) { + /* Sometimes errors are sent as unsolicited chip state events */ + case CMD_CHIP_STATE_EVENT: + es.channel = msg->u.usbcan.chip_state_event.channel; + es.status = msg->u.usbcan.chip_state_event.status; + es.txerr = msg->u.usbcan.chip_state_event.tx_errors_count; + es.rxerr = msg->u.usbcan.chip_state_event.rx_errors_count; + kvaser_usbcan_conditionally_rx_error(dev, &es); + break; - cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT; - - if (error_factor & M16C_EF_ACKE) - cf->data[3] |= (CAN_ERR_PROT_LOC_ACK); - if (error_factor & M16C_EF_CRCE) - cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ | - CAN_ERR_PROT_LOC_CRC_DEL); - if (error_factor & M16C_EF_FORME) - cf->data[2] |= CAN_ERR_PROT_FORM; - if (error_factor & M16C_EF_STFE) - cf->data[2] |= CAN_ERR_PROT_STUFF; - if (error_factor & M16C_EF_BITE0) - cf->data[2] |= CAN_ERR_PROT_BIT0; - if (error_factor & M16C_EF_BITE1) - cf->data[2] |= CAN_ERR_PROT_BIT1; - if (error_factor & M16C_EF_TRE) - cf->data[2] |= CAN_ERR_PROT_TX; - } + case CMD_CAN_ERROR_EVENT: + es.channel = 0; + es.status = msg->u.usbcan.error_event.status_ch0; + es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch0; + es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch0; + es.usbcan.other_ch_status = + msg->u.usbcan.error_event.status_ch1; + kvaser_usbcan_conditionally_rx_error(dev, &es); + + /* The USBCAN firmware supports up to 2 channels. + * Now that ch0 was checked, check if ch1 has any errors. + */ + if (dev->nchannels == MAX_USBCAN_NET_DEVICES) { + es.channel = 1; + es.status = msg->u.usbcan.error_event.status_ch1; + es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch1; + es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch1; + es.usbcan.other_ch_status = + msg->u.usbcan.error_event.status_ch0; + kvaser_usbcan_conditionally_rx_error(dev, &es); + } + break; - cf->data[6] = txerr; - cf->data[7] = rxerr; + default: + dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n", + msg->id); + } +} - priv->bec.txerr = txerr; - priv->bec.rxerr = rxerr; +static void kvaser_leaf_rx_error(const struct kvaser_usb *dev, + const struct kvaser_msg *msg) +{ + struct kvaser_usb_error_summary es = { }; - priv->can.state = new_state; + switch (msg->id) { + case CMD_CAN_ERROR_EVENT: + es.channel = msg->u.leaf.error_event.channel; + es.status = msg->u.leaf.error_event.status; + es.txerr = msg->u.leaf.error_event.tx_errors_count; + es.rxerr = msg->u.leaf.error_event.rx_errors_count; + es.leaf.error_factor = msg->u.leaf.error_event.error_factor; + break; + case CMD_LEAF_LOG_MESSAGE: + es.channel = msg->u.leaf.log_message.channel; + es.status = msg->u.leaf.log_message.data[0]; + es.txerr = msg->u.leaf.log_message.data[2]; + es.rxerr = msg->u.leaf.log_message.data[3]; + es.leaf.error_factor = msg->u.leaf.log_message.data[1]; + break; + case CMD_CHIP_STATE_EVENT: + es.channel = msg->u.leaf.chip_state_event.channel; + es.status = msg->u.leaf.chip_state_event.status; + es.txerr = msg->u.leaf.chip_state_event.tx_errors_count; + es.rxerr = msg->u.leaf.chip_state_event.rx_errors_count; + es.leaf.error_factor = 0; + break; + default: + dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n", + msg->id); + return; + } - stats->rx_packets++; - stats->rx_bytes += cf->can_dlc; - netif_rx(skb); + kvaser_usb_rx_error(dev, &es); } static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, @@ -776,16 +1090,19 @@ static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, struct sk_buff *skb; struct net_device_stats *stats = &priv->netdev->stats; - if (msg->u.rx_can.flag & (MSG_FLAG_ERROR_FRAME | + if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | MSG_FLAG_NERR)) { netdev_err(priv->netdev, "Unknow error (flags: 0x%02x)\n", - msg->u.rx_can.flag); + msg->u.rx_can_header.flag); stats->rx_errors++; return; } - if (msg->u.rx_can.flag & MSG_FLAG_OVERRUN) { + if (msg->u.rx_can_header.flag & MSG_FLAG_OVERRUN) { + stats->rx_over_errors++; + stats->rx_errors++; + skb = alloc_can_err_skb(priv->netdev, &cf); if (!skb) { stats->rx_dropped++; @@ -795,9 +1112,6 @@ static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, cf->can_id |= CAN_ERR_CRTL; cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; - stats->rx_over_errors++; - stats->rx_errors++; - stats->rx_packets++; stats->rx_bytes += cf->can_dlc; netif_rx(skb); @@ -811,7 +1125,8 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev, struct can_frame *cf; struct sk_buff *skb; struct net_device_stats *stats; - u8 channel = msg->u.rx_can.channel; + u8 channel = msg->u.rx_can_header.channel; + const u8 *rx_msg = NULL; /* GCC */ if (channel >= dev->nchannels) { dev_err(dev->udev->dev.parent, @@ -822,60 +1137,68 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev, priv = dev->nets[channel]; stats = &priv->netdev->stats; - if ((msg->u.rx_can.flag & MSG_FLAG_ERROR_FRAME) && - (msg->id == CMD_LOG_MESSAGE)) { - kvaser_usb_rx_error(dev, msg); + if ((msg->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) && + (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE)) { + kvaser_leaf_rx_error(dev, msg); return; - } else if (msg->u.rx_can.flag & (MSG_FLAG_ERROR_FRAME | - MSG_FLAG_NERR | - MSG_FLAG_OVERRUN)) { + } else if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | + MSG_FLAG_NERR | + MSG_FLAG_OVERRUN)) { kvaser_usb_rx_can_err(priv, msg); return; - } else if (msg->u.rx_can.flag & ~MSG_FLAG_REMOTE_FRAME) { + } else if (msg->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) { netdev_warn(priv->netdev, "Unhandled frame (flags: 0x%02x)", - msg->u.rx_can.flag); + msg->u.rx_can_header.flag); return; } + switch (dev->family) { + case KVASER_LEAF: + rx_msg = msg->u.leaf.rx_can.msg; + break; + case KVASER_USBCAN: + rx_msg = msg->u.usbcan.rx_can.msg; + break; + } + skb = alloc_can_skb(priv->netdev, &cf); if (!skb) { stats->tx_dropped++; return; } - if (msg->id == CMD_LOG_MESSAGE) { - cf->can_id = le32_to_cpu(msg->u.log_message.id); + if (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE) { + cf->can_id = le32_to_cpu(msg->u.leaf.log_message.id); if (cf->can_id & KVASER_EXTENDED_FRAME) cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG; else cf->can_id &= CAN_SFF_MASK; - cf->can_dlc = get_can_dlc(msg->u.log_message.dlc); + cf->can_dlc = get_can_dlc(msg->u.leaf.log_message.dlc); - if (msg->u.log_message.flags & MSG_FLAG_REMOTE_FRAME) + if (msg->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME) cf->can_id |= CAN_RTR_FLAG; else - memcpy(cf->data, &msg->u.log_message.data, + memcpy(cf->data, &msg->u.leaf.log_message.data, cf->can_dlc); } else { - cf->can_id = ((msg->u.rx_can.msg[0] & 0x1f) << 6) | - (msg->u.rx_can.msg[1] & 0x3f); + cf->can_id = ((rx_msg[0] & 0x1f) << 6) | (rx_msg[1] & 0x3f); if (msg->id == CMD_RX_EXT_MESSAGE) { cf->can_id <<= 18; - cf->can_id |= ((msg->u.rx_can.msg[2] & 0x0f) << 14) | - ((msg->u.rx_can.msg[3] & 0xff) << 6) | - (msg->u.rx_can.msg[4] & 0x3f); + cf->can_id |= ((rx_msg[2] & 0x0f) << 14) | + ((rx_msg[3] & 0xff) << 6) | + (rx_msg[4] & 0x3f); cf->can_id |= CAN_EFF_FLAG; } - cf->can_dlc = get_can_dlc(msg->u.rx_can.msg[5]); + cf->can_dlc = get_can_dlc(rx_msg[5]); - if (msg->u.rx_can.flag & MSG_FLAG_REMOTE_FRAME) + if (msg->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME) cf->can_id |= CAN_RTR_FLAG; else - memcpy(cf->data, &msg->u.rx_can.msg[6], + memcpy(cf->data, &rx_msg[6], cf->can_dlc); } @@ -938,21 +1261,35 @@ static void kvaser_usb_handle_message(const struct kvaser_usb *dev, case CMD_RX_STD_MESSAGE: case CMD_RX_EXT_MESSAGE: - case CMD_LOG_MESSAGE: + kvaser_usb_rx_can_msg(dev, msg); + break; + + case CMD_LEAF_LOG_MESSAGE: + if (dev->family != KVASER_LEAF) + goto warn; kvaser_usb_rx_can_msg(dev, msg); break; case CMD_CHIP_STATE_EVENT: case CMD_CAN_ERROR_EVENT: - kvaser_usb_rx_error(dev, msg); + if (dev->family == KVASER_LEAF) + kvaser_leaf_rx_error(dev, msg); + else + kvaser_usbcan_rx_error(dev, msg); break; case CMD_TX_ACKNOWLEDGE: kvaser_usb_tx_acknowledge(dev, msg); break; + /* Ignored messages */ + case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: + if (dev->family != KVASER_USBCAN) + goto warn; + break; + default: - dev_warn(dev->udev->dev.parent, +warn: dev_warn(dev->udev->dev.parent, "Unhandled message (%d)\n", msg->id); break; } @@ -1172,7 +1509,7 @@ static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev) dev->rxbuf[i], dev->rxbuf_dma[i]); - for (i = 0; i < MAX_NET_DEVICES; i++) { + for (i = 0; i < dev->nchannels; i++) { struct kvaser_usb_net_priv *priv = dev->nets[i]; if (priv) @@ -1280,6 +1617,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, struct kvaser_msg *msg; int i, err; int ret = NETDEV_TX_OK; + u8 *msg_tx_can_flags = NULL; /* GCC */ if (can_dropped_invalid_skb(netdev, skb)) return NETDEV_TX_OK; @@ -1301,9 +1639,19 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, msg = buf; msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_tx_can); - msg->u.tx_can.flags = 0; msg->u.tx_can.channel = priv->channel; + switch (dev->family) { + case KVASER_LEAF: + msg_tx_can_flags = &msg->u.tx_can.leaf.flags; + break; + case KVASER_USBCAN: + msg_tx_can_flags = &msg->u.tx_can.usbcan.flags; + break; + } + + *msg_tx_can_flags = 0; + if (cf->can_id & CAN_EFF_FLAG) { msg->id = CMD_TX_EXT_MESSAGE; msg->u.tx_can.msg[0] = (cf->can_id >> 24) & 0x1f; @@ -1321,7 +1669,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, memcpy(&msg->u.tx_can.msg[6], cf->data, cf->can_dlc); if (cf->can_id & CAN_RTR_FLAG) - msg->u.tx_can.flags |= MSG_FLAG_REMOTE_FRAME; + *msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME; for (i = 0; i < ARRAY_SIZE(priv->tx_contexts); i++) { if (priv->tx_contexts[i].echo_index == MAX_TX_URBS) { @@ -1590,6 +1938,17 @@ static int kvaser_usb_probe(struct usb_interface *intf, if (!dev) return -ENOMEM; + if (kvaser_is_leaf(id)) { + dev->family = KVASER_LEAF; + } else if (kvaser_is_usbcan(id)) { + dev->family = KVASER_USBCAN; + } else { + dev_err(&intf->dev, + "Product ID (%d) does not belong to any known Kvaser USB family", + id->idProduct); + return -ENODEV; + } + err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out); if (err) { dev_err(&intf->dev, "Cannot get usb endpoint(s)"); diff --git a/drivers/net/can/usb/peak_usb/Makefile b/drivers/net/can/usb/peak_usb/Makefile index 1aefbc88d643..1839e9ca62e7 100644 --- a/drivers/net/can/usb/peak_usb/Makefile +++ b/drivers/net/can/usb/peak_usb/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_CAN_PEAK_USB) += peak_usb.o -peak_usb-y = pcan_usb_core.o pcan_usb.o pcan_usb_pro.o +peak_usb-y = pcan_usb_core.o pcan_usb.o pcan_usb_pro.o pcan_usb_fd.o diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/drivers/net/can/usb/peak_usb/pcan_ucan.h new file mode 100644 index 000000000000..1ba7c25002e1 --- /dev/null +++ b/drivers/net/can/usb/peak_usb/pcan_ucan.h @@ -0,0 +1,222 @@ +/* + * CAN driver for PEAK System micro-CAN based adapters + * + * Copyright (C) 2003-2011 PEAK System-Technik GmbH + * Copyright (C) 2011-2013 Stephane Grosjean <s.grosjean@peak-system.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published + * by the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef PUCAN_H +#define PUCAN_H + +/* uCAN commands opcodes list (low-order 10 bits) */ +#define PUCAN_CMD_NOP 0x000 +#define PUCAN_CMD_RESET_MODE 0x001 +#define PUCAN_CMD_NORMAL_MODE 0x002 +#define PUCAN_CMD_LISTEN_ONLY_MODE 0x003 +#define PUCAN_CMD_TIMING_SLOW 0x004 +#define PUCAN_CMD_TIMING_FAST 0x005 +#define PUCAN_CMD_FILTER_STD 0x008 +#define PUCAN_CMD_TX_ABORT 0x009 +#define PUCAN_CMD_WR_ERR_CNT 0x00a +#define PUCAN_CMD_RX_FRAME_ENABLE 0x00b +#define PUCAN_CMD_RX_FRAME_DISABLE 0x00c +#define PUCAN_CMD_END_OF_COLLECTION 0x3ff + +/* uCAN received messages list */ +#define PUCAN_MSG_CAN_RX 0x0001 +#define PUCAN_MSG_ERROR 0x0002 +#define PUCAN_MSG_STATUS 0x0003 +#define PUCAN_MSG_BUSLOAD 0x0004 +#define PUCAN_MSG_CAN_TX 0x1000 + +/* uCAN command common header */ +struct __packed pucan_command { + __le16 opcode_channel; + u16 args[3]; +}; + +/* uCAN TIMING_SLOW command fields */ +#define PUCAN_TSLOW_SJW_T(s, t) (((s) & 0xf) | ((!!(t)) << 7)) +#define PUCAN_TSLOW_TSEG2(t) ((t) & 0xf) +#define PUCAN_TSLOW_TSEG1(t) ((t) & 0x3f) +#define PUCAN_TSLOW_BRP(b) ((b) & 0x3ff) + +struct __packed pucan_timing_slow { + __le16 opcode_channel; + + u8 ewl; /* Error Warning limit */ + u8 sjw_t; /* Sync Jump Width + Triple sampling */ + u8 tseg2; /* Timing SEGment 2 */ + u8 tseg1; /* Timing SEGment 1 */ + + __le16 brp; /* BaudRate Prescaler */ +}; + +/* uCAN TIMING_FAST command fields */ +#define PUCAN_TFAST_SJW(s) ((s) & 0x3) +#define PUCAN_TFAST_TSEG2(t) ((t) & 0x7) +#define PUCAN_TFAST_TSEG1(t) ((t) & 0xf) +#define PUCAN_TFAST_BRP(b) ((b) & 0x3ff) + +struct __packed pucan_timing_fast { + __le16 opcode_channel; + + u8 unused; + u8 sjw; /* Sync Jump Width */ + u8 tseg2; /* Timing SEGment 2 */ + u8 tseg1; /* Timing SEGment 1 */ + + __le16 brp; /* BaudRate Prescaler */ +}; + +/* uCAN FILTER_STD command fields */ +#define PUCAN_FLTSTD_ROW_IDX_BITS 6 + +struct __packed pucan_filter_std { + __le16 opcode_channel; + + __le16 idx; + __le32 mask; /* CAN-ID bitmask in idx range */ +}; + +/* uCAN WR_ERR_CNT command fields */ +#define PUCAN_WRERRCNT_TE 0x4000 /* Tx error cntr write Enable */ +#define PUCAN_WRERRCNT_RE 0x8000 /* Rx error cntr write Enable */ + +struct __packed pucan_wr_err_cnt { + __le16 opcode_channel; + + __le16 sel_mask; + u8 tx_counter; /* Tx error counter new value */ + u8 rx_counter; /* Rx error counter new value */ + + u16 unused; +}; + +/* uCAN RX_FRAME_ENABLE command fields */ +#define PUCAN_FLTEXT_ERROR 0x0001 +#define PUCAN_FLTEXT_BUSLOAD 0x0002 + +struct __packed pucan_filter_ext { + __le16 opcode_channel; + + __le16 ext_mask; + u32 unused; +}; + +/* uCAN received messages global format */ +struct __packed pucan_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; +}; + +/* uCAN flags for CAN/CANFD messages */ +#define PUCAN_MSG_SELF_RECEIVE 0x80 +#define PUCAN_MSG_ERROR_STATE_IND 0x40 /* error state indicator */ +#define PUCAN_MSG_BITRATE_SWITCH 0x20 /* bitrate switch */ +#define PUCAN_MSG_EXT_DATA_LEN 0x10 /* extended data length */ +#define PUCAN_MSG_SINGLE_SHOT 0x08 +#define PUCAN_MSG_LOOPED_BACK 0x04 +#define PUCAN_MSG_EXT_ID 0x02 +#define PUCAN_MSG_RTR 0x01 + +struct __packed pucan_rx_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + __le32 tag_low; + __le32 tag_high; + u8 channel_dlc; + u8 client; + __le16 flags; + __le32 can_id; + u8 d[0]; +}; + +/* uCAN error types */ +#define PUCAN_ERMSG_BIT_ERROR 0 +#define PUCAN_ERMSG_FORM_ERROR 1 +#define PUCAN_ERMSG_STUFF_ERROR 2 +#define PUCAN_ERMSG_OTHER_ERROR 3 +#define PUCAN_ERMSG_ERR_CNT_DEC 4 + +struct __packed pucan_error_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + u8 channel_type_d; + u8 code_g; + u8 tx_err_cnt; + u8 rx_err_cnt; +}; + +#define PUCAN_BUS_PASSIVE 0x20 +#define PUCAN_BUS_WARNING 0x40 +#define PUCAN_BUS_BUSOFF 0x80 + +struct __packed pucan_status_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + u8 channel_p_w_b; + u8 unused[3]; +}; + +/* uCAN transmitted message format */ +#define PUCAN_MSG_CHANNEL_DLC(c, d) (((c) & 0xf) | ((d) << 4)) + +struct __packed pucan_tx_msg { + __le16 size; + __le16 type; + __le32 tag_low; + __le32 tag_high; + u8 channel_dlc; + u8 client; + __le16 flags; + __le32 can_id; + u8 d[0]; +}; + +/* build the cmd opcode_channel field with respect to the correct endianness */ +static inline __le16 pucan_cmd_opcode_channel(struct peak_usb_device *dev, + int opcode) +{ + return cpu_to_le16(((dev->ctrl_idx) << 12) | ((opcode) & 0x3ff)); +} + +/* return the channel number part from any received message channel_dlc field */ +static inline int pucan_msg_get_channel(struct pucan_rx_msg *rm) +{ + return rm->channel_dlc & 0xf; +} + +/* return the dlc value from any received message channel_dlc field */ +static inline int pucan_msg_get_dlc(struct pucan_rx_msg *rm) +{ + return rm->channel_dlc >> 4; +} + +static inline int pucan_ermsg_get_channel(struct pucan_error_msg *em) +{ + return em->channel_type_d & 0x0f; +} + +static inline int pucan_stmsg_get_channel(struct pucan_status_msg *sm) +{ + return sm->channel_p_w_b & 0x0f; +} + +#endif diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 2a1c9ce53fae..72427f21edff 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -855,10 +855,11 @@ static int pcan_usb_probe(struct usb_interface *intf) /* * describe the PCAN-USB adapter */ -struct peak_usb_adapter pcan_usb = { +const struct peak_usb_adapter pcan_usb = { .name = "PCAN-USB", .device_id = PCAN_USB_PRODUCT_ID, .ctrl_count = 1, + .ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, .clock = { .freq = PCAN_USB_CRYSTAL_HZ / 2 , }, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c62f48a1161d..7921cff93a63 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -37,16 +37,19 @@ MODULE_LICENSE("GPL v2"); static struct usb_device_id peak_usb_table[] = { {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USB_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)}, + {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)}, + {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)}, {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, peak_usb_table); /* List of supported PCAN-USB adapters (NULL terminated list) */ -static struct peak_usb_adapter *peak_usb_adapters_list[] = { +static const struct peak_usb_adapter *const peak_usb_adapters_list[] = { &pcan_usb, &pcan_usb_pro, - NULL, + &pcan_usb_fd, + &pcan_usb_pro_fd, }; /* @@ -65,7 +68,7 @@ void pcan_dump_mem(char *prompt, void *p, int l) * initialize a time_ref object with usb adapter own settings */ void peak_usb_init_time_ref(struct peak_time_ref *time_ref, - struct peak_usb_adapter *adapter) + const struct peak_usb_adapter *adapter) { if (time_ref) { memset(time_ref, 0, sizeof(struct peak_time_ref)); @@ -165,6 +168,21 @@ void peak_usb_get_ts_tv(struct peak_time_ref *time_ref, u32 ts, } /* + * post received skb after having set any hw timestamp + */ +int peak_usb_netif_rx(struct sk_buff *skb, + struct peak_time_ref *time_ref, u32 ts_low, u32 ts_high) +{ + struct skb_shared_hwtstamps *hwts = skb_hwtstamps(skb); + struct timeval tv; + + peak_usb_get_ts_tv(time_ref, ts_low, &tv); + hwts->hwtstamp = timeval_to_ktime(tv); + + return netif_rx(skb); +} + +/* * callback for bulk Rx urb */ static void peak_usb_read_bulk_callback(struct urb *urb) @@ -253,7 +271,7 @@ static void peak_usb_write_bulk_callback(struct urb *urb) case 0: /* transmission complete */ netdev->stats.tx_packets++; - netdev->stats.tx_bytes += context->dlc; + netdev->stats.tx_bytes += context->data_len; /* prevent tx timeout */ netdev->trans_start = jiffies; @@ -289,7 +307,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, struct peak_usb_device *dev = netdev_priv(netdev); struct peak_tx_urb_context *context = NULL; struct net_device_stats *stats = &netdev->stats; - struct can_frame *cf = (struct can_frame *)skb->data; + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; struct urb *urb; u8 *obuf; int i, err; @@ -322,7 +340,9 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, } context->echo_index = i; - context->dlc = cf->can_dlc; + + /* Note: this works with CANFD frames too */ + context->data_len = cfd->len; usb_anchor_urb(urb, &dev->tx_submitted); @@ -679,19 +699,43 @@ static int peak_usb_set_mode(struct net_device *netdev, enum can_mode mode) } /* - * candev callback used to set device bitrate. + * candev callback used to set device nominal/arbitration bitrate. */ static int peak_usb_set_bittiming(struct net_device *netdev) { struct peak_usb_device *dev = netdev_priv(netdev); - struct can_bittiming *bt = &dev->can.bittiming; + const struct peak_usb_adapter *pa = dev->adapter; - if (dev->adapter->dev_set_bittiming) { - int err = dev->adapter->dev_set_bittiming(dev, bt); + if (pa->dev_set_bittiming) { + struct can_bittiming *bt = &dev->can.bittiming; + int err = pa->dev_set_bittiming(dev, bt); if (err) netdev_info(netdev, "couldn't set bitrate (err %d)\n", - err); + err); + return err; + } + + return 0; +} + +/* + * candev callback used to set device data bitrate. + */ +static int peak_usb_set_data_bittiming(struct net_device *netdev) +{ + struct peak_usb_device *dev = netdev_priv(netdev); + const struct peak_usb_adapter *pa = dev->adapter; + + if (pa->dev_set_data_bittiming) { + struct can_bittiming *bt = &dev->can.data_bittiming; + int err = pa->dev_set_data_bittiming(dev, bt); + + if (err) + netdev_info(netdev, + "couldn't set data bitrate (err %d)\n", + err); + return err; } @@ -709,7 +753,7 @@ static const struct net_device_ops peak_usb_netdev_ops = { * create one device which is attached to CAN controller #ctrl_idx of the * usb adapter. */ -static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, +static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, struct usb_interface *intf, int ctrl_idx) { struct usb_device *usb_dev = interface_to_usbdev(intf); @@ -750,9 +794,11 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, dev->can.clock = peak_usb_adapter->clock; dev->can.bittiming_const = &peak_usb_adapter->bittiming_const; dev->can.do_set_bittiming = peak_usb_set_bittiming; + dev->can.data_bittiming_const = &peak_usb_adapter->data_bittiming_const; + dev->can.do_set_data_bittiming = peak_usb_set_data_bittiming; dev->can.do_set_mode = peak_usb_set_mode; - dev->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | - CAN_CTRLMODE_LISTENONLY; + dev->can.do_get_berr_counter = peak_usb_adapter->do_get_berr_counter; + dev->can.ctrlmode_supported = peak_usb_adapter->ctrlmode_supported; netdev->netdev_ops = &peak_usb_netdev_ops; @@ -857,17 +903,18 @@ static int peak_usb_probe(struct usb_interface *intf, { struct usb_device *usb_dev = interface_to_usbdev(intf); const u16 usb_id_product = le16_to_cpu(usb_dev->descriptor.idProduct); - struct peak_usb_adapter *peak_usb_adapter, **pp; + const struct peak_usb_adapter *peak_usb_adapter = NULL; int i, err = -ENOMEM; usb_dev = interface_to_usbdev(intf); /* get corresponding PCAN-USB adapter */ - for (pp = peak_usb_adapters_list; *pp; pp++) - if ((*pp)->device_id == usb_id_product) + for (i = 0; i < ARRAY_SIZE(peak_usb_adapters_list); i++) + if (peak_usb_adapters_list[i]->device_id == usb_id_product) { + peak_usb_adapter = peak_usb_adapters_list[i]; break; + } - peak_usb_adapter = *pp; if (!peak_usb_adapter) { /* should never come except device_id bad usage in this file */ pr_err("%s: didn't find device id. 0x%x in devices list\n", diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index 073b47ff8eee..9e624f05ad4d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -25,6 +25,8 @@ /* supported device ids. */ #define PCAN_USB_PRODUCT_ID 0x000c #define PCAN_USBPRO_PRODUCT_ID 0x000d +#define PCAN_USBPROFD_PRODUCT_ID 0x0011 +#define PCAN_USBFD_PRODUCT_ID 0x0012 #define PCAN_USB_DRIVER_NAME "peak_usb" @@ -44,8 +46,10 @@ struct peak_usb_device; struct peak_usb_adapter { char *name; u32 device_id; + u32 ctrlmode_supported; struct can_clock clock; const struct can_bittiming_const bittiming_const; + const struct can_bittiming_const data_bittiming_const; unsigned int ctrl_count; int (*intf_probe)(struct usb_interface *intf); @@ -57,6 +61,8 @@ struct peak_usb_adapter { int (*dev_close)(struct peak_usb_device *dev); int (*dev_set_bittiming)(struct peak_usb_device *dev, struct can_bittiming *bt); + int (*dev_set_data_bittiming)(struct peak_usb_device *dev, + struct can_bittiming *bt); int (*dev_set_bus)(struct peak_usb_device *dev, u8 onoff); int (*dev_get_device_id)(struct peak_usb_device *dev, u32 *device_id); int (*dev_decode_buf)(struct peak_usb_device *dev, struct urb *urb); @@ -66,6 +72,8 @@ struct peak_usb_adapter { int (*dev_stop)(struct peak_usb_device *dev); int (*dev_restart_async)(struct peak_usb_device *dev, struct urb *urb, u8 *buf); + int (*do_get_berr_counter)(const struct net_device *netdev, + struct can_berr_counter *bec); u8 ep_msg_in; u8 ep_msg_out[PCAN_USB_MAX_CHANNEL]; u8 ts_used_bits; @@ -78,21 +86,23 @@ struct peak_usb_adapter { int sizeof_dev_private; }; -extern struct peak_usb_adapter pcan_usb; -extern struct peak_usb_adapter pcan_usb_pro; +extern const struct peak_usb_adapter pcan_usb; +extern const struct peak_usb_adapter pcan_usb_pro; +extern const struct peak_usb_adapter pcan_usb_fd; +extern const struct peak_usb_adapter pcan_usb_pro_fd; struct peak_time_ref { struct timeval tv_host_0, tv_host; u32 ts_dev_1, ts_dev_2; u64 ts_total; u32 tick_count; - struct peak_usb_adapter *adapter; + const struct peak_usb_adapter *adapter; }; struct peak_tx_urb_context { struct peak_usb_device *dev; u32 echo_index; - u8 dlc; + u8 data_len; struct urb *urb; }; @@ -102,7 +112,7 @@ struct peak_tx_urb_context { /* PEAK-System USB device */ struct peak_usb_device { struct can_priv can; - struct peak_usb_adapter *adapter; + const struct peak_usb_adapter *adapter; unsigned int ctrl_idx; u32 state; @@ -134,12 +144,14 @@ void pcan_dump_mem(char *prompt, void *p, int l); /* common timestamp management */ void peak_usb_init_time_ref(struct peak_time_ref *time_ref, - struct peak_usb_adapter *adapter); + const struct peak_usb_adapter *adapter); void peak_usb_update_ts_now(struct peak_time_ref *time_ref, u32 ts_now); void peak_usb_set_ts_now(struct peak_time_ref *time_ref, u32 ts_now); void peak_usb_get_ts_tv(struct peak_time_ref *time_ref, u32 ts, struct timeval *tv); - +int peak_usb_netif_rx(struct sk_buff *skb, + struct peak_time_ref *time_ref, u32 ts_low, u32 ts_high); void peak_usb_async_complete(struct urb *urb); void peak_usb_restart_complete(struct peak_usb_device *dev); + #endif diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c new file mode 100644 index 000000000000..962c3f027383 --- /dev/null +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -0,0 +1,1095 @@ +/* + * CAN driver for PEAK System PCAN-USB FD / PCAN-USB Pro FD adapter + * + * Copyright (C) 2013-2014 Stephane Grosjean <s.grosjean@peak-system.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published + * by the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include <linux/netdevice.h> +#include <linux/usb.h> +#include <linux/module.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> + +#include "pcan_usb_core.h" +#include "pcan_usb_pro.h" +#include "pcan_ucan.h" + +MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter"); +MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter"); + +#define PCAN_USBPROFD_CHANNEL_COUNT 2 +#define PCAN_USBFD_CHANNEL_COUNT 1 + +/* PCAN-USB Pro FD adapter internal clock (Hz) */ +#define PCAN_UFD_CRYSTAL_HZ 80000000 + +#define PCAN_UFD_CMD_BUFFER_SIZE 512 +#define PCAN_UFD_LOSPD_PKT_SIZE 64 + +/* PCAN-USB Pro FD command timeout (ms.) */ +#define PCAN_UFD_CMD_TIMEOUT_MS 1000 + +/* PCAN-USB Pro FD rx/tx buffers size */ +#define PCAN_UFD_RX_BUFFER_SIZE 2048 +#define PCAN_UFD_TX_BUFFER_SIZE 512 + +/* read some versions info from the hw devcie */ +struct __packed pcan_ufd_fw_info { + __le16 size_of; /* sizeof this */ + __le16 type; /* type of this structure */ + u8 hw_type; /* Type of hardware (HW_TYPE_xxx) */ + u8 bl_version[3]; /* Bootloader version */ + u8 hw_version; /* Hardware version (PCB) */ + u8 fw_version[3]; /* Firmware version */ + __le32 dev_id[2]; /* "device id" per CAN */ + __le32 ser_no; /* S/N */ + __le32 flags; /* special functions */ +}; + +/* handle device specific info used by the netdevices */ +struct pcan_usb_fd_if { + struct peak_usb_device *dev[PCAN_USB_MAX_CHANNEL]; + struct pcan_ufd_fw_info fw_info; + struct peak_time_ref time_ref; + int cm_ignore_count; + int dev_opened_count; +}; + +/* device information */ +struct pcan_usb_fd_device { + struct peak_usb_device dev; + struct can_berr_counter bec; + struct pcan_usb_fd_if *usb_if; + u8 *cmd_buffer_addr; +}; + +/* Extended USB commands (non uCAN commands) */ + +/* Clock Modes command */ +#define PCAN_UFD_CMD_CLK_SET 0x80 + +#define PCAN_UFD_CLK_80MHZ 0x0 +#define PCAN_UFD_CLK_60MHZ 0x1 +#define PCAN_UFD_CLK_40MHZ 0x2 +#define PCAN_UFD_CLK_30MHZ 0x3 +#define PCAN_UFD_CLK_24MHZ 0x4 +#define PCAN_UFD_CLK_20MHZ 0x5 +#define PCAN_UFD_CLK_DEF PCAN_UFD_CLK_80MHZ + +struct __packed pcan_ufd_clock { + __le16 opcode_channel; + + u8 mode; + u8 unused[5]; +}; + +/* LED control command */ +#define PCAN_UFD_CMD_LED_SET 0x86 + +#define PCAN_UFD_LED_DEV 0x00 +#define PCAN_UFD_LED_FAST 0x01 +#define PCAN_UFD_LED_SLOW 0x02 +#define PCAN_UFD_LED_ON 0x03 +#define PCAN_UFD_LED_OFF 0x04 +#define PCAN_UFD_LED_DEF PCAN_UFD_LED_DEV + +struct __packed pcan_ufd_led { + __le16 opcode_channel; + + u8 mode; + u8 unused[5]; +}; + +/* Extended usage of uCAN commands CMD_RX_FRAME_xxxABLE for PCAN-USB Pro FD */ +#define PCAN_UFD_FLTEXT_CALIBRATION 0x8000 + +struct __packed pcan_ufd_filter_ext { + __le16 opcode_channel; + + __le16 ext_mask; + u16 unused; + __le16 usb_mask; +}; + +/* Extended usage of uCAN messages for PCAN-USB Pro FD */ +#define PCAN_UFD_MSG_CALIBRATION 0x100 + +struct __packed pcan_ufd_ts_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + __le16 usb_frame_index; + u16 unused; +}; + +#define PCAN_UFD_MSG_OVERRUN 0x101 + +#define PCAN_UFD_OVMSG_CHANNEL(o) ((o)->channel & 0xf) + +struct __packed pcan_ufd_ovr_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + u8 channel; + u8 unused[3]; +}; + +static inline int pufd_omsg_get_channel(struct pcan_ufd_ovr_msg *om) +{ + return om->channel & 0xf; +} + +/* Clock mode frequency values */ +static const u32 pcan_usb_fd_clk_freq[6] = { + [PCAN_UFD_CLK_80MHZ] = 80000000, + [PCAN_UFD_CLK_60MHZ] = 60000000, + [PCAN_UFD_CLK_40MHZ] = 40000000, + [PCAN_UFD_CLK_30MHZ] = 30000000, + [PCAN_UFD_CLK_24MHZ] = 24000000, + [PCAN_UFD_CLK_20MHZ] = 20000000 +}; + +/* return a device USB interface */ +static inline +struct pcan_usb_fd_if *pcan_usb_fd_dev_if(struct peak_usb_device *dev) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + return pdev->usb_if; +} + +/* return a device USB commands buffer */ +static inline void *pcan_usb_fd_cmd_buffer(struct peak_usb_device *dev) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + return pdev->cmd_buffer_addr; +} + +/* send PCAN-USB Pro FD commands synchronously */ +static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail) +{ + void *cmd_head = pcan_usb_fd_cmd_buffer(dev); + int err; + u8 *packet_ptr; + int i, n = 1, packet_len; + ptrdiff_t cmd_len; + + /* usb device unregistered? */ + if (!(dev->state & PCAN_USB_STATE_CONNECTED)) + return 0; + + /* if a packet is not filled completely by commands, the command list + * is terminated with an "end of collection" record. + */ + cmd_len = cmd_tail - cmd_head; + if (cmd_len <= (PCAN_UFD_CMD_BUFFER_SIZE - sizeof(u64))) { + memset(cmd_tail, 0xff, sizeof(u64)); + cmd_len += sizeof(u64); + } + + packet_ptr = cmd_head; + + /* firmware is not able to re-assemble 512 bytes buffer in full-speed */ + if ((dev->udev->speed != USB_SPEED_HIGH) && + (cmd_len > PCAN_UFD_LOSPD_PKT_SIZE)) { + packet_len = PCAN_UFD_LOSPD_PKT_SIZE; + n += cmd_len / packet_len; + } else { + packet_len = cmd_len; + } + + for (i = 0; i < n; i++) { + err = usb_bulk_msg(dev->udev, + usb_sndbulkpipe(dev->udev, + PCAN_USBPRO_EP_CMDOUT), + packet_ptr, packet_len, + NULL, PCAN_UFD_CMD_TIMEOUT_MS); + if (err) { + netdev_err(dev->netdev, + "sending command failure: %d\n", err); + break; + } + + packet_ptr += packet_len; + } + + return err; +} + +/* build the commands list in the given buffer, to enter operational mode */ +static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf) +{ + struct pucan_wr_err_cnt *prc; + struct pucan_command *cmd; + u8 *pc = buf; + + /* 1st, reset error counters: */ + prc = (struct pucan_wr_err_cnt *)pc; + prc->opcode_channel = pucan_cmd_opcode_channel(dev, + PUCAN_CMD_WR_ERR_CNT); + + /* select both counters */ + prc->sel_mask = cpu_to_le16(PUCAN_WRERRCNT_TE|PUCAN_WRERRCNT_RE); + + /* and reset their values */ + prc->tx_counter = 0; + prc->rx_counter = 0; + + /* moves the pointer forward */ + pc += sizeof(struct pucan_wr_err_cnt); + + /* next, go back to operational mode */ + cmd = (struct pucan_command *)pc; + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + (dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) ? + PUCAN_CMD_LISTEN_ONLY_MODE : + PUCAN_CMD_NORMAL_MODE); + pc += sizeof(struct pucan_command); + + return pc - buf; +} + +/* set CAN bus on/off */ +static int pcan_usb_fd_set_bus(struct peak_usb_device *dev, u8 onoff) +{ + u8 *pc = pcan_usb_fd_cmd_buffer(dev); + int l; + + if (onoff) { + /* build the cmds list to enter operational mode */ + l = pcan_usb_fd_build_restart_cmd(dev, pc); + } else { + struct pucan_command *cmd = (struct pucan_command *)pc; + + /* build cmd to go back to reset mode */ + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + PUCAN_CMD_RESET_MODE); + l = sizeof(struct pucan_command); + } + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, pc + l); +} + +/* set filtering masks: + * + * idx in range [0..63] selects a row #idx, all rows otherwise + * mask in range [0..0xffffffff] defines up to 32 CANIDs in the row(s) + * + * Each bit of this 64 x 32 bits array defines a CANID value: + * + * bit[i,j] = 1 implies that CANID=(i x 32)+j will be received, while + * bit[i,j] = 0 implies that CANID=(i x 32)+j will be discarded. + */ +static int pcan_usb_fd_set_filter_std(struct peak_usb_device *dev, int idx, + u32 mask) +{ + struct pucan_filter_std *cmd = pcan_usb_fd_cmd_buffer(dev); + int i, n; + + /* select all rows when idx is out of range [0..63] */ + if ((idx < 0) || (idx >= (1 << PUCAN_FLTSTD_ROW_IDX_BITS))) { + n = 1 << PUCAN_FLTSTD_ROW_IDX_BITS; + idx = 0; + + /* select the row (and only the row) otherwise */ + } else { + n = idx + 1; + } + + for (i = idx; i < n; i++, cmd++) { + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + PUCAN_CMD_FILTER_STD); + cmd->idx = cpu_to_le16(i); + cmd->mask = cpu_to_le32(mask); + } + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, cmd); +} + +/* set/unset notifications filter: + * + * onoff sets(1)/unset(0) notifications + * mask each bit defines a kind of notification to set/unset + */ +static int pcan_usb_fd_set_filter_ext(struct peak_usb_device *dev, + bool onoff, u16 ext_mask, u16 usb_mask) +{ + struct pcan_ufd_filter_ext *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + (onoff) ? PUCAN_CMD_RX_FRAME_ENABLE : + PUCAN_CMD_RX_FRAME_DISABLE); + + cmd->ext_mask = cpu_to_le16(ext_mask); + cmd->usb_mask = cpu_to_le16(usb_mask); + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + +/* setup LED control */ +static int pcan_usb_fd_set_can_led(struct peak_usb_device *dev, u8 led_mode) +{ + struct pcan_ufd_led *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + PCAN_UFD_CMD_LED_SET); + cmd->mode = led_mode; + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + +/* set CAN clock domain */ +static int pcan_usb_fd_set_clock_domain(struct peak_usb_device *dev, + u8 clk_mode) +{ + struct pcan_ufd_clock *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + PCAN_UFD_CMD_CLK_SET); + cmd->mode = clk_mode; + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + +/* set bittiming for CAN and CAN-FD header */ +static int pcan_usb_fd_set_bittiming_slow(struct peak_usb_device *dev, + struct can_bittiming *bt) +{ + struct pucan_timing_slow *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + PUCAN_CMD_TIMING_SLOW); + cmd->sjw_t = PUCAN_TSLOW_SJW_T(bt->sjw - 1, + dev->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES); + + cmd->tseg2 = PUCAN_TSLOW_TSEG2(bt->phase_seg2 - 1); + cmd->tseg1 = PUCAN_TSLOW_TSEG1(bt->prop_seg + bt->phase_seg1 - 1); + cmd->brp = cpu_to_le16(PUCAN_TSLOW_BRP(bt->brp - 1)); + + cmd->ewl = 96; /* default */ + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + +/* set CAN-FD bittiming for data */ +static int pcan_usb_fd_set_bittiming_fast(struct peak_usb_device *dev, + struct can_bittiming *bt) +{ + struct pucan_timing_fast *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev, + PUCAN_CMD_TIMING_FAST); + cmd->sjw = PUCAN_TFAST_SJW(bt->sjw - 1); + cmd->tseg2 = PUCAN_TFAST_TSEG2(bt->phase_seg2 - 1); + cmd->tseg1 = PUCAN_TFAST_TSEG1(bt->prop_seg + bt->phase_seg1 - 1); + cmd->brp = cpu_to_le16(PUCAN_TFAST_BRP(bt->brp - 1)); + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + +/* handle restart but in asynchronously way + * (uses PCAN-USB Pro code to complete asynchronous request) + */ +static int pcan_usb_fd_restart_async(struct peak_usb_device *dev, + struct urb *urb, u8 *buf) +{ + u8 *pc = buf; + + /* build the entire cmds list in the provided buffer, to go back into + * operational mode. + */ + pc += pcan_usb_fd_build_restart_cmd(dev, pc); + + /* add EOC */ + memset(pc, 0xff, sizeof(struct pucan_command)); + pc += sizeof(struct pucan_command); + + /* complete the URB */ + usb_fill_bulk_urb(urb, dev->udev, + usb_sndbulkpipe(dev->udev, PCAN_USBPRO_EP_CMDOUT), + buf, pc - buf, + pcan_usb_pro_restart_complete, dev); + + /* and submit it. */ + return usb_submit_urb(urb, GFP_ATOMIC); +} + +static int pcan_usb_fd_drv_loaded(struct peak_usb_device *dev, bool loaded) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + + pdev->cmd_buffer_addr[0] = 0; + pdev->cmd_buffer_addr[1] = !!loaded; + + return pcan_usb_pro_send_req(dev, + PCAN_USBPRO_REQ_FCT, + PCAN_USBPRO_FCT_DRVLD, + pdev->cmd_buffer_addr, + PCAN_USBPRO_FCT_DRVLD_REQ_LEN); +} + +static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if, + struct pucan_msg *rx_msg) +{ + struct pucan_rx_msg *rm = (struct pucan_rx_msg *)rx_msg; + struct peak_usb_device *dev = usb_if->dev[pucan_msg_get_channel(rm)]; + struct net_device *netdev = dev->netdev; + struct canfd_frame *cfd; + struct sk_buff *skb; + const u16 rx_msg_flags = le16_to_cpu(rm->flags); + + if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) { + /* CANFD frame case */ + skb = alloc_canfd_skb(netdev, &cfd); + if (!skb) + return -ENOMEM; + + if (rx_msg_flags & PUCAN_MSG_BITRATE_SWITCH) + cfd->flags |= CANFD_BRS; + + if (rx_msg_flags & PUCAN_MSG_ERROR_STATE_IND) + cfd->flags |= CANFD_ESI; + + cfd->len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(rm))); + } else { + /* CAN 2.0 frame case */ + skb = alloc_can_skb(netdev, (struct can_frame **)&cfd); + if (!skb) + return -ENOMEM; + + cfd->len = get_can_dlc(pucan_msg_get_dlc(rm)); + } + + cfd->can_id = le32_to_cpu(rm->can_id); + + if (rx_msg_flags & PUCAN_MSG_EXT_ID) + cfd->can_id |= CAN_EFF_FLAG; + + if (rx_msg_flags & PUCAN_MSG_RTR) + cfd->can_id |= CAN_RTR_FLAG; + else + memcpy(cfd->data, rm->d, cfd->len); + + peak_usb_netif_rx(skb, &usb_if->time_ref, + le32_to_cpu(rm->ts_low), le32_to_cpu(rm->ts_high)); + + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += cfd->len; + + return 0; +} + +/* handle uCAN status message */ +static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if, + struct pucan_msg *rx_msg) +{ + struct pucan_status_msg *sm = (struct pucan_status_msg *)rx_msg; + struct peak_usb_device *dev = usb_if->dev[pucan_stmsg_get_channel(sm)]; + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + enum can_state new_state = CAN_STATE_ERROR_ACTIVE; + enum can_state rx_state, tx_state; + struct net_device *netdev = dev->netdev; + struct can_frame *cf; + struct sk_buff *skb; + + /* nothing should be sent while in BUS_OFF state */ + if (dev->can.state == CAN_STATE_BUS_OFF) + return 0; + + if (sm->channel_p_w_b & PUCAN_BUS_BUSOFF) { + new_state = CAN_STATE_BUS_OFF; + } else if (sm->channel_p_w_b & PUCAN_BUS_PASSIVE) { + new_state = CAN_STATE_ERROR_PASSIVE; + } else if (sm->channel_p_w_b & PUCAN_BUS_WARNING) { + new_state = CAN_STATE_ERROR_WARNING; + } else { + /* no error bit (so, no error skb, back to active state) */ + dev->can.state = CAN_STATE_ERROR_ACTIVE; + pdev->bec.txerr = 0; + pdev->bec.rxerr = 0; + return 0; + } + + /* state hasn't changed */ + if (new_state == dev->can.state) + return 0; + + /* handle bus state change */ + tx_state = (pdev->bec.txerr >= pdev->bec.rxerr) ? new_state : 0; + rx_state = (pdev->bec.txerr <= pdev->bec.rxerr) ? new_state : 0; + + /* allocate an skb to store the error frame */ + skb = alloc_can_err_skb(netdev, &cf); + if (skb) + can_change_state(netdev, cf, tx_state, rx_state); + + /* things must be done even in case of OOM */ + if (new_state == CAN_STATE_BUS_OFF) + can_bus_off(netdev); + + if (!skb) + return -ENOMEM; + + peak_usb_netif_rx(skb, &usb_if->time_ref, + le32_to_cpu(sm->ts_low), le32_to_cpu(sm->ts_high)); + + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += cf->can_dlc; + + return 0; +} + +/* handle uCAN error message */ +static int pcan_usb_fd_decode_error(struct pcan_usb_fd_if *usb_if, + struct pucan_msg *rx_msg) +{ + struct pucan_error_msg *er = (struct pucan_error_msg *)rx_msg; + struct peak_usb_device *dev = usb_if->dev[pucan_ermsg_get_channel(er)]; + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + + /* keep a trace of tx and rx error counters for later use */ + pdev->bec.txerr = er->tx_err_cnt; + pdev->bec.rxerr = er->rx_err_cnt; + + return 0; +} + +/* handle uCAN overrun message */ +static int pcan_usb_fd_decode_overrun(struct pcan_usb_fd_if *usb_if, + struct pucan_msg *rx_msg) +{ + struct pcan_ufd_ovr_msg *ov = (struct pcan_ufd_ovr_msg *)rx_msg; + struct peak_usb_device *dev = usb_if->dev[pufd_omsg_get_channel(ov)]; + struct net_device *netdev = dev->netdev; + struct can_frame *cf; + struct sk_buff *skb; + + /* allocate an skb to store the error frame */ + skb = alloc_can_err_skb(netdev, &cf); + if (!skb) + return -ENOMEM; + + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW; + + peak_usb_netif_rx(skb, &usb_if->time_ref, + le32_to_cpu(ov->ts_low), le32_to_cpu(ov->ts_high)); + + netdev->stats.rx_over_errors++; + netdev->stats.rx_errors++; + + return 0; +} + +/* handle USB calibration message */ +static void pcan_usb_fd_decode_ts(struct pcan_usb_fd_if *usb_if, + struct pucan_msg *rx_msg) +{ + struct pcan_ufd_ts_msg *ts = (struct pcan_ufd_ts_msg *)rx_msg; + + /* should wait until clock is stabilized */ + if (usb_if->cm_ignore_count > 0) + usb_if->cm_ignore_count--; + else + peak_usb_set_ts_now(&usb_if->time_ref, le32_to_cpu(ts->ts_low)); +} + +/* callback for bulk IN urb */ +static int pcan_usb_fd_decode_buf(struct peak_usb_device *dev, struct urb *urb) +{ + struct pcan_usb_fd_if *usb_if = pcan_usb_fd_dev_if(dev); + struct net_device *netdev = dev->netdev; + struct pucan_msg *rx_msg; + u8 *msg_ptr, *msg_end; + int err = 0; + + /* loop reading all the records from the incoming message */ + msg_ptr = urb->transfer_buffer; + msg_end = urb->transfer_buffer + urb->actual_length; + for (; msg_ptr < msg_end;) { + u16 rx_msg_type, rx_msg_size; + + rx_msg = (struct pucan_msg *)msg_ptr; + if (!rx_msg->size) { + /* null packet found: end of list */ + break; + } + + rx_msg_size = le16_to_cpu(rx_msg->size); + rx_msg_type = le16_to_cpu(rx_msg->type); + + /* check if the record goes out of current packet */ + if (msg_ptr + rx_msg_size > msg_end) { + netdev_err(netdev, + "got frag rec: should inc usb rx buf sze\n"); + err = -EBADMSG; + break; + } + + switch (rx_msg_type) { + case PUCAN_MSG_CAN_RX: + err = pcan_usb_fd_decode_canmsg(usb_if, rx_msg); + if (err < 0) + goto fail; + break; + + case PCAN_UFD_MSG_CALIBRATION: + pcan_usb_fd_decode_ts(usb_if, rx_msg); + break; + + case PUCAN_MSG_ERROR: + err = pcan_usb_fd_decode_error(usb_if, rx_msg); + if (err < 0) + goto fail; + break; + + case PUCAN_MSG_STATUS: + err = pcan_usb_fd_decode_status(usb_if, rx_msg); + if (err < 0) + goto fail; + break; + + case PCAN_UFD_MSG_OVERRUN: + err = pcan_usb_fd_decode_overrun(usb_if, rx_msg); + if (err < 0) + goto fail; + break; + + default: + netdev_err(netdev, + "unhandled msg type 0x%02x (%d): ignored\n", + rx_msg_type, rx_msg_type); + break; + } + + msg_ptr += rx_msg_size; + } + +fail: + if (err) + pcan_dump_mem("received msg", + urb->transfer_buffer, urb->actual_length); + return err; +} + +/* CAN/CANFD frames encoding callback */ +static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev, + struct sk_buff *skb, u8 *obuf, size_t *size) +{ + struct pucan_tx_msg *tx_msg = (struct pucan_tx_msg *)obuf; + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + u16 tx_msg_size, tx_msg_flags; + u8 can_dlc; + + tx_msg_size = ALIGN(sizeof(struct pucan_tx_msg) + cfd->len, 4); + tx_msg->size = cpu_to_le16(tx_msg_size); + tx_msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX); + + tx_msg_flags = 0; + if (cfd->can_id & CAN_EFF_FLAG) { + tx_msg_flags |= PUCAN_MSG_EXT_ID; + tx_msg->can_id = cpu_to_le32(cfd->can_id & CAN_EFF_MASK); + } else { + tx_msg->can_id = cpu_to_le32(cfd->can_id & CAN_SFF_MASK); + } + + if (can_is_canfd_skb(skb)) { + /* considering a CANFD frame */ + can_dlc = can_len2dlc(cfd->len); + + tx_msg_flags |= PUCAN_MSG_EXT_DATA_LEN; + + if (cfd->flags & CANFD_BRS) + tx_msg_flags |= PUCAN_MSG_BITRATE_SWITCH; + + if (cfd->flags & CANFD_ESI) + tx_msg_flags |= PUCAN_MSG_ERROR_STATE_IND; + } else { + /* CAND 2.0 frames */ + can_dlc = cfd->len; + + if (cfd->can_id & CAN_RTR_FLAG) + tx_msg_flags |= PUCAN_MSG_RTR; + } + + tx_msg->flags = cpu_to_le16(tx_msg_flags); + tx_msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(dev->ctrl_idx, can_dlc); + memcpy(tx_msg->d, cfd->data, cfd->len); + + /* add null size message to tag the end (messages are 32-bits aligned) + */ + tx_msg = (struct pucan_tx_msg *)(obuf + tx_msg_size); + + tx_msg->size = 0; + + /* set the whole size of the USB packet to send */ + *size = tx_msg_size + sizeof(u32); + + return 0; +} + +/* start the interface (last chance before set bus on) */ +static int pcan_usb_fd_start(struct peak_usb_device *dev) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + int err; + + /* set filter mode: all acceptance */ + err = pcan_usb_fd_set_filter_std(dev, -1, 0xffffffff); + if (err) + return err; + + /* opening first device: */ + if (pdev->usb_if->dev_opened_count == 0) { + /* reset time_ref */ + peak_usb_init_time_ref(&pdev->usb_if->time_ref, + &pcan_usb_pro_fd); + + /* enable USB calibration messages */ + err = pcan_usb_fd_set_filter_ext(dev, 1, + PUCAN_FLTEXT_ERROR, + PCAN_UFD_FLTEXT_CALIBRATION); + } + + pdev->usb_if->dev_opened_count++; + + /* reset cached error counters */ + pdev->bec.txerr = 0; + pdev->bec.rxerr = 0; + + return err; +} + +/* socket callback used to copy berr counters values receieved through USB */ +static int pcan_usb_fd_get_berr_counter(const struct net_device *netdev, + struct can_berr_counter *bec) +{ + struct peak_usb_device *dev = netdev_priv(netdev); + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + + *bec = pdev->bec; + + /* must return 0 */ + return 0; +} + +/* stop interface (last chance before set bus off) */ +static int pcan_usb_fd_stop(struct peak_usb_device *dev) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + + /* turn off special msgs for that interface if no other dev opened */ + if (pdev->usb_if->dev_opened_count == 1) + pcan_usb_fd_set_filter_ext(dev, 0, + PUCAN_FLTEXT_ERROR, + PCAN_UFD_FLTEXT_CALIBRATION); + pdev->usb_if->dev_opened_count--; + + return 0; +} + +/* called when probing, to initialize a device object */ +static int pcan_usb_fd_init(struct peak_usb_device *dev) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + int i, err = -ENOMEM; + + /* do this for 1st channel only */ + if (!dev->prev_siblings) { + /* allocate netdevices common structure attached to first one */ + pdev->usb_if = kzalloc(sizeof(*pdev->usb_if), GFP_KERNEL); + if (!pdev->usb_if) + goto err_out; + + /* allocate command buffer once for all for the interface */ + pdev->cmd_buffer_addr = kmalloc(PCAN_UFD_CMD_BUFFER_SIZE, + GFP_KERNEL); + if (!pdev->cmd_buffer_addr) + goto err_out_1; + + /* number of ts msgs to ignore before taking one into account */ + pdev->usb_if->cm_ignore_count = 5; + + err = pcan_usb_pro_send_req(dev, PCAN_USBPRO_REQ_INFO, + PCAN_USBPRO_INFO_FW, + &pdev->usb_if->fw_info, + sizeof(pdev->usb_if->fw_info)); + if (err) { + dev_err(dev->netdev->dev.parent, + "unable to read %s firmware info (err %d)\n", + dev->adapter->name, err); + goto err_out_2; + } + + /* explicit use of dev_xxx() instead of netdev_xxx() here: + * information displayed are related to the device itself, not + * to the canx (channel) device. + */ + dev_info(dev->netdev->dev.parent, + "PEAK-System %s v%u fw v%u.%u.%u (%u channels)\n", + dev->adapter->name, pdev->usb_if->fw_info.hw_version, + pdev->usb_if->fw_info.fw_version[0], + pdev->usb_if->fw_info.fw_version[1], + pdev->usb_if->fw_info.fw_version[2], + dev->adapter->ctrl_count); + + /* the currently supported hw is non-ISO */ + dev->can.ctrlmode = CAN_CTRLMODE_FD_NON_ISO; + + /* tell the hardware the can driver is running */ + err = pcan_usb_fd_drv_loaded(dev, 1); + if (err) { + dev_err(dev->netdev->dev.parent, + "unable to tell %s driver is loaded (err %d)\n", + dev->adapter->name, err); + goto err_out_2; + } + } else { + /* otherwise, simply copy previous sibling's values */ + struct pcan_usb_fd_device *ppdev = + container_of(dev->prev_siblings, + struct pcan_usb_fd_device, dev); + + pdev->usb_if = ppdev->usb_if; + pdev->cmd_buffer_addr = ppdev->cmd_buffer_addr; + } + + pdev->usb_if->dev[dev->ctrl_idx] = dev; + dev->device_number = + le32_to_cpu(pdev->usb_if->fw_info.dev_id[dev->ctrl_idx]); + + /* set clock domain */ + for (i = 0; i < ARRAY_SIZE(pcan_usb_fd_clk_freq); i++) + if (dev->adapter->clock.freq == pcan_usb_fd_clk_freq[i]) + break; + + if (i >= ARRAY_SIZE(pcan_usb_fd_clk_freq)) { + dev_warn(dev->netdev->dev.parent, + "incompatible clock frequencies\n"); + err = -EINVAL; + goto err_out_2; + } + + pcan_usb_fd_set_clock_domain(dev, i); + + /* set LED in default state (end of init phase) */ + pcan_usb_fd_set_can_led(dev, PCAN_UFD_LED_DEF); + + return 0; + +err_out_2: + kfree(pdev->cmd_buffer_addr); +err_out_1: + kfree(pdev->usb_if); +err_out: + return err; +} + +/* called when driver module is being unloaded */ +static void pcan_usb_fd_exit(struct peak_usb_device *dev) +{ + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + + /* when rmmod called before unplug and if down, should reset things + * before leaving + */ + if (dev->can.state != CAN_STATE_STOPPED) { + /* set bus off on the corresponding channel */ + pcan_usb_fd_set_bus(dev, 0); + } + + /* switch off corresponding CAN LEDs */ + pcan_usb_fd_set_can_led(dev, PCAN_UFD_LED_OFF); + + /* if channel #0 (only) */ + if (dev->ctrl_idx == 0) { + /* turn off calibration message if any device were opened */ + if (pdev->usb_if->dev_opened_count > 0) + pcan_usb_fd_set_filter_ext(dev, 0, + PUCAN_FLTEXT_ERROR, + PCAN_UFD_FLTEXT_CALIBRATION); + + /* tell USB adapter that the driver is being unloaded */ + pcan_usb_fd_drv_loaded(dev, 0); + } +} + +/* called when the USB adapter is unplugged */ +static void pcan_usb_fd_free(struct peak_usb_device *dev) +{ + /* last device: can free shared objects now */ + if (!dev->prev_siblings && !dev->next_siblings) { + struct pcan_usb_fd_device *pdev = + container_of(dev, struct pcan_usb_fd_device, dev); + + /* free commands buffer */ + kfree(pdev->cmd_buffer_addr); + + /* free usb interface object */ + kfree(pdev->usb_if); + } +} + +/* describes the PCAN-USB FD adapter */ +const struct peak_usb_adapter pcan_usb_fd = { + .name = "PCAN-USB FD", + .device_id = PCAN_USBFD_PRODUCT_ID, + .ctrl_count = PCAN_USBFD_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_FD | + CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, + .clock = { + .freq = PCAN_UFD_CRYSTAL_HZ, + }, + .bittiming_const = { + .name = "pcan_usb_fd", + .tseg1_min = 1, + .tseg1_max = 64, + .tseg2_min = 1, + .tseg2_max = 16, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 1024, + .brp_inc = 1, + }, + .data_bittiming_const = { + .name = "pcan_usb_fd", + .tseg1_min = 1, + .tseg1_max = 16, + .tseg2_min = 1, + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 1024, + .brp_inc = 1, + }, + + /* size of device private data */ + .sizeof_dev_private = sizeof(struct pcan_usb_fd_device), + + /* timestamps usage */ + .ts_used_bits = 32, + .ts_period = 1000000, /* calibration period in ts. */ + .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */ + .us_per_ts_shift = 0, + + /* give here messages in/out endpoints */ + .ep_msg_in = PCAN_USBPRO_EP_MSGIN, + .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0}, + + /* size of rx/tx usb buffers */ + .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE, + .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE, + + /* device callbacks */ + .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */ + .dev_init = pcan_usb_fd_init, + + .dev_exit = pcan_usb_fd_exit, + .dev_free = pcan_usb_fd_free, + .dev_set_bus = pcan_usb_fd_set_bus, + .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, + .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_decode_buf = pcan_usb_fd_decode_buf, + .dev_start = pcan_usb_fd_start, + .dev_stop = pcan_usb_fd_stop, + .dev_restart_async = pcan_usb_fd_restart_async, + .dev_encode_msg = pcan_usb_fd_encode_msg, + + .do_get_berr_counter = pcan_usb_fd_get_berr_counter, +}; + +/* describes the PCAN-USB Pro FD adapter */ +const struct peak_usb_adapter pcan_usb_pro_fd = { + .name = "PCAN-USB Pro FD", + .device_id = PCAN_USBPROFD_PRODUCT_ID, + .ctrl_count = PCAN_USBPROFD_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_FD | + CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, + .clock = { + .freq = PCAN_UFD_CRYSTAL_HZ, + }, + .bittiming_const = { + .name = "pcan_usb_pro_fd", + .tseg1_min = 1, + .tseg1_max = 64, + .tseg2_min = 1, + .tseg2_max = 16, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 1024, + .brp_inc = 1, + }, + .data_bittiming_const = { + .name = "pcan_usb_pro_fd", + .tseg1_min = 1, + .tseg1_max = 16, + .tseg2_min = 1, + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 1024, + .brp_inc = 1, + }, + + /* size of device private data */ + .sizeof_dev_private = sizeof(struct pcan_usb_fd_device), + + /* timestamps usage */ + .ts_used_bits = 32, + .ts_period = 1000000, /* calibration period in ts. */ + .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */ + .us_per_ts_shift = 0, + + /* give here messages in/out endpoints */ + .ep_msg_in = PCAN_USBPRO_EP_MSGIN, + .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0, PCAN_USBPRO_EP_MSGOUT_1}, + + /* size of rx/tx usb buffers */ + .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE, + .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE, + + /* device callbacks */ + .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */ + .dev_init = pcan_usb_fd_init, + + .dev_exit = pcan_usb_fd_exit, + .dev_free = pcan_usb_fd_free, + .dev_set_bus = pcan_usb_fd_set_bus, + .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, + .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_decode_buf = pcan_usb_fd_decode_buf, + .dev_start = pcan_usb_fd_start, + .dev_stop = pcan_usb_fd_stop, + .dev_restart_async = pcan_usb_fd_restart_async, + .dev_encode_msg = pcan_usb_fd_encode_msg, + + .do_get_berr_counter = pcan_usb_fd_get_berr_counter, +}; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 145fa87c31b9..dec51717635e 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -27,14 +27,6 @@ MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro adapter"); -/* PCAN-USB Pro Endpoints */ -#define PCAN_USBPRO_EP_CMDOUT 1 -#define PCAN_USBPRO_EP_CMDIN (PCAN_USBPRO_EP_CMDOUT | USB_DIR_IN) -#define PCAN_USBPRO_EP_MSGOUT_0 2 -#define PCAN_USBPRO_EP_MSGIN (PCAN_USBPRO_EP_MSGOUT_0 | USB_DIR_IN) -#define PCAN_USBPRO_EP_MSGOUT_1 3 -#define PCAN_USBPRO_EP_UNUSED (PCAN_USBPRO_EP_MSGOUT_1 | USB_DIR_IN) - #define PCAN_USBPRO_CHANNEL_COUNT 2 /* PCAN-USB Pro adapter internal clock (MHz) */ @@ -322,8 +314,8 @@ static int pcan_usb_pro_wait_rsp(struct peak_usb_device *dev, return (i >= PCAN_USBPRO_RSP_SUBMIT_MAX) ? -ERANGE : err; } -static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, - int req_value, void *req_addr, int req_size) +int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, + int req_value, void *req_addr, int req_size) { int err; u8 req_type; @@ -475,7 +467,7 @@ static int pcan_usb_pro_set_bittiming(struct peak_usb_device *dev, return pcan_usb_pro_set_bitrate(dev, ccbt); } -static void pcan_usb_pro_restart_complete(struct urb *urb) +void pcan_usb_pro_restart_complete(struct urb *urb) { /* can delete usb resources */ peak_usb_async_complete(urb); @@ -978,7 +970,7 @@ static void pcan_usb_pro_free(struct peak_usb_device *dev) /* * probe function for new PCAN-USB Pro usb interface */ -static int pcan_usb_pro_probe(struct usb_interface *intf) +int pcan_usb_pro_probe(struct usb_interface *intf) { struct usb_host_interface *if_desc; int i; @@ -1012,10 +1004,11 @@ static int pcan_usb_pro_probe(struct usb_interface *intf) /* * describe the PCAN-USB Pro adapter */ -struct peak_usb_adapter pcan_usb_pro = { +const struct peak_usb_adapter pcan_usb_pro = { .name = "PCAN-USB Pro", .device_id = PCAN_USBPRO_PRODUCT_ID, .ctrl_count = PCAN_USBPRO_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, .clock = { .freq = PCAN_USBPRO_CRYSTAL_HZ, }, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h index 837cee267132..a62f7ab8980f 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h @@ -27,6 +27,14 @@ #define PCAN_USBPRO_INFO_BL 0 #define PCAN_USBPRO_INFO_FW 1 +/* PCAN-USB Pro (FD) Endpoints */ +#define PCAN_USBPRO_EP_CMDOUT 1 +#define PCAN_USBPRO_EP_CMDIN (PCAN_USBPRO_EP_CMDOUT | USB_DIR_IN) +#define PCAN_USBPRO_EP_MSGOUT_0 2 +#define PCAN_USBPRO_EP_MSGIN (PCAN_USBPRO_EP_MSGOUT_0 | USB_DIR_IN) +#define PCAN_USBPRO_EP_MSGOUT_1 3 +#define PCAN_USBPRO_EP_UNUSED (PCAN_USBPRO_EP_MSGOUT_1 | USB_DIR_IN) + /* Vendor Request value for XXX_FCT */ #define PCAN_USBPRO_FCT_DRVLD 5 /* tell device driver is loaded */ #define PCAN_USBPRO_FCT_DRVLD_REQ_LEN 16 @@ -176,4 +184,9 @@ union pcan_usb_pro_rec { struct pcan_usb_pro_txmsg tx_msg; }; +int pcan_usb_pro_probe(struct usb_interface *intf); +int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, + int req_value, void *req_addr, int req_size); +void pcan_usb_pro_restart_complete(struct urb *urb); + #endif diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index 5d3b5202327c..c638c85f3954 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -45,7 +45,7 @@ config AMD8111_ETH config LANCE tristate "AMD LANCE and PCnet (AT1500 and NE2100) support" - depends on ISA && ISA_DMA_API + depends on ISA && ISA_DMA_API && !ARM ---help--- If you have a network (Ethernet) card of this type, say Y and read the Ethernet-HOWTO, available from @@ -142,7 +142,7 @@ config PCMCIA_NMCLAN config NI65 tristate "NI6510 support" - depends on ISA && ISA_DMA_API + depends on ISA && ISA_DMA_API && !ARM ---help--- If you have a network (Ethernet) card of this type, say Y and read the Ethernet-HOWTO, available from diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 5b22764ba88d..27245efe9f50 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -952,6 +952,8 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) do { /* WARNING: MACE_IR is a READ/CLEAR port! */ status = inb(ioaddr + AM2150_MACE_BASE + MACE_IR); + if (!(status & ~MACE_IMR_DEFAULT) && IntrCnt == MACE_MAX_IR_ITERATIONS) + return IRQ_NONE; pr_debug("mace_interrupt: irq 0x%X status 0x%X.\n", irq, status); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index c036a0e61bba..d41f9f468688 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -522,6 +522,7 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) hw_feat->sph = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, SPHEN); hw_feat->tso = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, TSOEN); hw_feat->dma_debug = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DBGMEMA); + hw_feat->rss = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, RSSEN); hw_feat->tc_cnt = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, NUMTC); hw_feat->hash_table_size = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, HASHTBLSZ); @@ -551,13 +552,14 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) break; } - /* The Queue and Channel counts are zero based so increment them + /* The Queue, Channel and TC counts are zero based so increment them * to get the actual number */ hw_feat->rx_q_cnt++; hw_feat->tx_q_cnt++; hw_feat->rx_ch_cnt++; hw_feat->tx_ch_cnt++; + hw_feat->tc_cnt++; DBGPR("<--xgbe_get_all_hw_features\n"); } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 02add385a33d..44b15373d6b3 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -373,6 +373,8 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring, if (unlikely(xgene_enet_is_desc_slot_empty(raw_desc))) break; + /* read fpqnum field after dataaddr field */ + dma_rmb(); if (is_rx_desc(raw_desc)) ret = xgene_enet_rx_frame(ring, raw_desc); else diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 0758c8bef4ba..7155e1d2c208 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9169,7 +9169,7 @@ static void bnx2x_disable_ptp(struct bnx2x *bp) } /* Called during unload, to stop PTP-related stuff */ -void bnx2x_stop_ptp(struct bnx2x *bp) +static void bnx2x_stop_ptp(struct bnx2x *bp) { /* Cancel PTP work queue. Should be done after the Tx queues are * drained to prevent additional scheduling. @@ -13318,7 +13318,7 @@ static int bnx2x_ptp_enable(struct ptp_clock_info *ptp, return -ENOTSUPP; } -void bnx2x_register_phc(struct bnx2x *bp) +static void bnx2x_register_phc(struct bnx2x *bp) { /* Fill the ptp_clock_info struct and register PTP clock*/ bp->ptp_clock_info.owner = THIS_MODULE; @@ -14635,7 +14635,7 @@ static int bnx2x_send_reset_timesync_ramrod(struct bnx2x *bp) return bnx2x_func_state_change(bp, &func_params); } -int bnx2x_enable_ptp_packets(struct bnx2x *bp) +static int bnx2x_enable_ptp_packets(struct bnx2x *bp) { struct bnx2x_queue_state_params q_params; int rc, i; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 4f7bd13796b8..ad76b8e35a00 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2035,7 +2035,7 @@ const struct ethtool_ops macb_ethtool_ops = { }; EXPORT_SYMBOL_GPL(macb_ethtool_ops); -const struct ethtool_ops gem_ethtool_ops = { +static const struct ethtool_ops gem_ethtool_ops = { .get_settings = macb_get_settings, .set_settings = macb_set_settings, .get_regs_len = macb_get_regs_len, @@ -2046,7 +2046,6 @@ const struct ethtool_ops gem_ethtool_ops = { .get_strings = gem_get_ethtool_strings, .get_sset_count = gem_get_sset_count, }; -EXPORT_SYMBOL_GPL(gem_ethtool_ops); int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index fb6980a09981..55019c93387d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -476,6 +476,22 @@ struct sge_rspq { /* state for an SGE response queue */ struct adapter *adap; struct net_device *netdev; /* associated net device */ rspq_handler_t handler; +#ifdef CONFIG_NET_RX_BUSY_POLL +#define CXGB_POLL_STATE_IDLE 0 +#define CXGB_POLL_STATE_NAPI BIT(0) /* NAPI owns this poll */ +#define CXGB_POLL_STATE_POLL BIT(1) /* poll owns this poll */ +#define CXGB_POLL_STATE_NAPI_YIELD BIT(2) /* NAPI yielded this poll */ +#define CXGB_POLL_STATE_POLL_YIELD BIT(3) /* poll yielded this poll */ +#define CXGB_POLL_YIELD (CXGB_POLL_STATE_NAPI_YIELD | \ + CXGB_POLL_STATE_POLL_YIELD) +#define CXGB_POLL_LOCKED (CXGB_POLL_STATE_NAPI | \ + CXGB_POLL_STATE_POLL) +#define CXGB_POLL_USER_PEND (CXGB_POLL_STATE_POLL | \ + CXGB_POLL_STATE_POLL_YIELD) + unsigned int bpoll_state; + spinlock_t bpoll_lock; /* lock for busy poll */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ + }; struct sge_eth_stats { /* Ethernet queue statistics */ @@ -880,6 +896,102 @@ static inline struct adapter *netdev2adap(const struct net_device *dev) return netdev2pinfo(dev)->adapter; } +#ifdef CONFIG_NET_RX_BUSY_POLL +static inline void cxgb_busy_poll_init_lock(struct sge_rspq *q) +{ + spin_lock_init(&q->bpoll_lock); + q->bpoll_state = CXGB_POLL_STATE_IDLE; +} + +static inline bool cxgb_poll_lock_napi(struct sge_rspq *q) +{ + bool rc = true; + + spin_lock(&q->bpoll_lock); + if (q->bpoll_state & CXGB_POLL_LOCKED) { + q->bpoll_state |= CXGB_POLL_STATE_NAPI_YIELD; + rc = false; + } else { + q->bpoll_state = CXGB_POLL_STATE_NAPI; + } + spin_unlock(&q->bpoll_lock); + return rc; +} + +static inline bool cxgb_poll_unlock_napi(struct sge_rspq *q) +{ + bool rc = false; + + spin_lock(&q->bpoll_lock); + if (q->bpoll_state & CXGB_POLL_STATE_POLL_YIELD) + rc = true; + q->bpoll_state = CXGB_POLL_STATE_IDLE; + spin_unlock(&q->bpoll_lock); + return rc; +} + +static inline bool cxgb_poll_lock_poll(struct sge_rspq *q) +{ + bool rc = true; + + spin_lock_bh(&q->bpoll_lock); + if (q->bpoll_state & CXGB_POLL_LOCKED) { + q->bpoll_state |= CXGB_POLL_STATE_POLL_YIELD; + rc = false; + } else { + q->bpoll_state |= CXGB_POLL_STATE_POLL; + } + spin_unlock_bh(&q->bpoll_lock); + return rc; +} + +static inline bool cxgb_poll_unlock_poll(struct sge_rspq *q) +{ + bool rc = false; + + spin_lock_bh(&q->bpoll_lock); + if (q->bpoll_state & CXGB_POLL_STATE_POLL_YIELD) + rc = true; + q->bpoll_state = CXGB_POLL_STATE_IDLE; + spin_unlock_bh(&q->bpoll_lock); + return rc; +} + +static inline bool cxgb_poll_busy_polling(struct sge_rspq *q) +{ + return q->bpoll_state & CXGB_POLL_USER_PEND; +} +#else +static inline void cxgb_busy_poll_init_lock(struct sge_rspq *q) +{ +} + +static inline bool cxgb_poll_lock_napi(struct sge_rspq *q) +{ + return true; +} + +static inline bool cxgb_poll_unlock_napi(struct sge_rspq *q) +{ + return false; +} + +static inline bool cxgb_poll_lock_poll(struct sge_rspq *q) +{ + return false; +} + +static inline bool cxgb_poll_unlock_poll(struct sge_rspq *q) +{ + return false; +} + +static inline bool cxgb_poll_busy_polling(struct sge_rspq *q) +{ + return false; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + void t4_os_portmod_changed(const struct adapter *adap, int port_id); void t4_os_link_changed(struct adapter *adap, int port_id, int link_stat); @@ -908,6 +1020,7 @@ irqreturn_t t4_sge_intr_msix(int irq, void *cookie); int t4_sge_init(struct adapter *adap); void t4_sge_start(struct adapter *adap); void t4_sge_stop(struct adapter *adap); +int cxgb_busy_poll(struct napi_struct *napi); extern int dbfifo_int_thresh; #define for_each_port(adapter, iter) \ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c index a35d1ec6950e..6074680bc985 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c @@ -22,7 +22,7 @@ /* DCBx version control */ -char *dcb_ver_array[] = { +static const char * const dcb_ver_array[] = { "Unknown", "DCBx-CIN", "DCBx-CEE 1.01", @@ -428,7 +428,10 @@ static void cxgb4_getpgtccfg(struct net_device *dev, int tc, } *pgid = (be32_to_cpu(pcmd.u.dcb.pgid.pgid) >> (tc * 4)) & 0xf; - INIT_PORT_DCB_READ_PEER_CMD(pcmd, pi->port_id); + if (local) + INIT_PORT_DCB_READ_LOCAL_CMD(pcmd, pi->port_id); + else + INIT_PORT_DCB_READ_PEER_CMD(pcmd, pi->port_id); pcmd.u.dcb.pgrate.type = FW_PORT_DCB_TYPE_PGRATE; err = t4_wr_mbox(adap, adap->mbox, &pcmd, sizeof(pcmd), &pcmd); if (err != FW_PORT_DCB_CFG_SUCCESS) { @@ -900,6 +903,88 @@ cxgb4_ieee_negotiation_complete(struct net_device *dev, (dcb->supported & DCB_CAP_DCBX_VER_IEEE)); } +static int cxgb4_ieee_read_ets(struct net_device *dev, struct ieee_ets *ets, + int local) +{ + struct port_info *pi = netdev2pinfo(dev); + struct port_dcb_info *dcb = &pi->dcb; + struct adapter *adap = pi->adapter; + uint32_t tc_info; + struct fw_port_cmd pcmd; + int i, bwg, err; + + if (!(dcb->msgs & (CXGB4_DCB_FW_PGID | CXGB4_DCB_FW_PGRATE))) + return 0; + + ets->ets_cap = dcb->pg_num_tcs_supported; + + if (local) { + ets->willing = 1; + INIT_PORT_DCB_READ_LOCAL_CMD(pcmd, pi->port_id); + } else { + INIT_PORT_DCB_READ_PEER_CMD(pcmd, pi->port_id); + } + + pcmd.u.dcb.pgid.type = FW_PORT_DCB_TYPE_PGID; + err = t4_wr_mbox(adap, adap->mbox, &pcmd, sizeof(pcmd), &pcmd); + if (err != FW_PORT_DCB_CFG_SUCCESS) { + dev_err(adap->pdev_dev, "DCB read PGID failed with %d\n", -err); + return err; + } + + tc_info = be32_to_cpu(pcmd.u.dcb.pgid.pgid); + + if (local) + INIT_PORT_DCB_READ_LOCAL_CMD(pcmd, pi->port_id); + else + INIT_PORT_DCB_READ_PEER_CMD(pcmd, pi->port_id); + + pcmd.u.dcb.pgrate.type = FW_PORT_DCB_TYPE_PGRATE; + err = t4_wr_mbox(adap, adap->mbox, &pcmd, sizeof(pcmd), &pcmd); + if (err != FW_PORT_DCB_CFG_SUCCESS) { + dev_err(adap->pdev_dev, "DCB read PGRATE failed with %d\n", + -err); + return err; + } + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + bwg = (tc_info >> ((7 - i) * 4)) & 0xF; + ets->prio_tc[i] = bwg; + ets->tc_tx_bw[i] = pcmd.u.dcb.pgrate.pgrate[i]; + ets->tc_rx_bw[i] = ets->tc_tx_bw[i]; + ets->tc_tsa[i] = pcmd.u.dcb.pgrate.tsa[i]; + } + + return 0; +} + +static int cxgb4_ieee_get_ets(struct net_device *dev, struct ieee_ets *ets) +{ + return cxgb4_ieee_read_ets(dev, ets, 1); +} + +/* We reuse this for peer PFC as well, as we can't have it enabled one way */ +static int cxgb4_ieee_get_pfc(struct net_device *dev, struct ieee_pfc *pfc) +{ + struct port_info *pi = netdev2pinfo(dev); + struct port_dcb_info *dcb = &pi->dcb; + + memset(pfc, 0, sizeof(struct ieee_pfc)); + + if (!(dcb->msgs & CXGB4_DCB_FW_PFC)) + return 0; + + pfc->pfc_cap = dcb->pfc_num_tcs_supported; + pfc->pfc_en = bitswap_1(dcb->pfcen); + + return 0; +} + +static int cxgb4_ieee_peer_ets(struct net_device *dev, struct ieee_ets *ets) +{ + return cxgb4_ieee_read_ets(dev, ets, 0); +} + /* Fill in the Application User Priority Map associated with the * specified Application. * Priority for IEEE dcb_app is an integer, with 0 being a valid value @@ -1106,14 +1191,23 @@ static int cxgb4_cee_peer_getpfc(struct net_device *dev, struct cee_pfc *pfc) struct port_info *pi = netdev2pinfo(dev); cxgb4_getnumtcs(dev, DCB_NUMTCS_ATTR_PFC, &(pfc->tcs_supported)); - pfc->pfc_en = pi->dcb.pfcen; + + /* Firmware sends this to us in a formwat that is a bit flipped version + * of spec, correct it before we send it to host. This is taken care of + * by bit shifting in other uses of pfcen + */ + pfc->pfc_en = bitswap_1(pi->dcb.pfcen); return 0; } const struct dcbnl_rtnl_ops cxgb4_dcb_ops = { + .ieee_getets = cxgb4_ieee_get_ets, + .ieee_getpfc = cxgb4_ieee_get_pfc, .ieee_getapp = cxgb4_ieee_getapp, .ieee_setapp = cxgb4_ieee_setapp, + .ieee_peer_getets = cxgb4_ieee_peer_ets, + .ieee_peer_getpfc = cxgb4_ieee_get_pfc, /* CEE std */ .getstate = cxgb4_getstate, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h index 31ce425616c9..ccf24d3dc982 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h @@ -136,6 +136,17 @@ void cxgb4_dcb_handle_fw_update(struct adapter *, const struct fw_port_cmd *); void cxgb4_dcb_set_caps(struct adapter *, const struct fw_port_cmd *); extern const struct dcbnl_rtnl_ops cxgb4_dcb_ops; +static inline __u8 bitswap_1(unsigned char val) +{ + return ((val & 0x80) >> 7) | + ((val & 0x40) >> 5) | + ((val & 0x20) >> 3) | + ((val & 0x10) >> 1) | + ((val & 0x08) << 1) | + ((val & 0x04) << 3) | + ((val & 0x02) << 5) | + ((val & 0x01) << 7); +} #define CXGB4_DCB_ENABLED true #else /* !CONFIG_CHELSIO_T4_DCB */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 47c0869f34ca..61c000a08ebb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -1229,6 +1229,28 @@ static const struct file_operations rss_vf_config_debugfs_fops = { .release = seq_release_private }; +/** + * ethqset2pinfo - return port_info of an Ethernet Queue Set + * @adap: the adapter + * @qset: Ethernet Queue Set + */ +static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset) +{ + int pidx; + + for_each_port(adap, pidx) { + struct port_info *pi = adap2pinfo(adap, pidx); + + if (qset >= pi->first_qset && + qset < pi->first_qset + pi->nqsets) + return pi; + } + + /* should never happen! */ + BUG_ON(1); + return NULL; +} + static int sge_qinfo_show(struct seq_file *seq, void *v) { struct adapter *adap = seq->private; @@ -1272,7 +1294,7 @@ do { \ T("TxQ inuse:", q.in_use); T("TxQ CIDX:", q.cidx); T("TxQ PIDX:", q.pidx); -#ifdef CONFIG_CXGB4_DCB +#ifdef CONFIG_CHELSIO_T4_DCB T("DCB Prio:", dcb_prio); S3("u", "DCB PGID:", (ethqset2pinfo(adap, base_qset + i)->dcb.pgid >> diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 5bf490a781aa..5db5b4f7b94d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -923,8 +923,14 @@ static void quiesce_rx(struct adapter *adap) for (i = 0; i < ARRAY_SIZE(adap->sge.ingr_map); i++) { struct sge_rspq *q = adap->sge.ingr_map[i]; - if (q && q->handler) + if (q && q->handler) { napi_disable(&q->napi); + local_bh_disable(); + while (!cxgb_poll_lock_napi(q)) + mdelay(1); + local_bh_enable(); + } + } } @@ -940,8 +946,10 @@ static void enable_rx(struct adapter *adap) if (!q) continue; - if (q->handler) + if (q->handler) { + cxgb_busy_poll_init_lock(q); napi_enable(&q->napi); + } /* 0-increment GTS to start the timer and enable interrupts */ t4_write_reg(adap, MYPF_REG(SGE_PF_GTS_A), SEINTARM_V(q->intr_params) | @@ -4563,6 +4571,10 @@ static const struct net_device_ops cxgb4_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = cxgb_netpoll, #endif +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = cxgb_busy_poll, +#endif + }; void t4_fatal_err(struct adapter *adap) @@ -5130,8 +5142,7 @@ static int adap_init0(struct adapter *adap) state, &reset); /* Cleaning up */ - if (fw != NULL) - release_firmware(fw); + release_firmware(fw); t4_free_mem(card_fw); if (ret < 0) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 619156112b21..b4b9f6048fe7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -43,6 +43,9 @@ #include <linux/export.h> #include <net/ipv6.h> #include <net/tcp.h> +#ifdef CONFIG_NET_RX_BUSY_POLL +#include <net/busy_poll.h> +#endif /* CONFIG_NET_RX_BUSY_POLL */ #include "cxgb4.h" #include "t4_regs.h" #include "t4_values.h" @@ -1720,6 +1723,7 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, skb->truesize += skb->data_len; skb->ip_summed = CHECKSUM_UNNECESSARY; skb_record_rx_queue(skb, rxq->rspq.idx); + skb_mark_napi_id(skb, &rxq->rspq.napi); if (rxq->rspq.netdev->features & NETIF_F_RXHASH) skb_set_hash(skb, (__force u32)pkt->rsshdr.hash_val, PKT_HASH_TYPE_L3); @@ -1763,6 +1767,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, csum_ok = pkt->csum_calc && !pkt->err_vec && (q->netdev->features & NETIF_F_RXCSUM); if ((pkt->l2info & htonl(RXF_TCP_F)) && + !(cxgb_poll_busy_polling(q)) && (q->netdev->features & NETIF_F_GRO) && csum_ok && !pkt->ip_frag) { do_gro(rxq, si, pkt); return 0; @@ -1801,6 +1806,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(pkt->vlan)); rxq->stats.vlan_ex++; } + skb_mark_napi_id(skb, &q->napi); netif_receive_skb(skb); return 0; } @@ -1963,6 +1969,38 @@ static int process_responses(struct sge_rspq *q, int budget) return budget - budget_left; } +#ifdef CONFIG_NET_RX_BUSY_POLL +int cxgb_busy_poll(struct napi_struct *napi) +{ + struct sge_rspq *q = container_of(napi, struct sge_rspq, napi); + unsigned int params, work_done; + u32 val; + + if (!cxgb_poll_lock_poll(q)) + return LL_FLUSH_BUSY; + + work_done = process_responses(q, 4); + params = QINTR_TIMER_IDX(TIMERREG_COUNTER0_X) | QINTR_CNT_EN; + q->next_intr_params = params; + val = CIDXINC_V(work_done) | SEINTARM_V(params); + + /* If we don't have access to the new User GTS (T5+), use the old + * doorbell mechanism; otherwise use the new BAR2 mechanism. + */ + if (unlikely(!q->bar2_addr)) + t4_write_reg(q->adap, MYPF_REG(SGE_PF_GTS_A), + val | INGRESSQID_V((u32)q->cntxt_id)); + else { + writel(val | INGRESSQID_V(q->bar2_qid), + q->bar2_addr + SGE_UDB_GTS); + wmb(); + } + + cxgb_poll_unlock_poll(q); + return work_done; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + /** * napi_rx_handler - the NAPI handler for Rx processing * @napi: the napi instance @@ -1978,9 +2016,13 @@ static int napi_rx_handler(struct napi_struct *napi, int budget) { unsigned int params; struct sge_rspq *q = container_of(napi, struct sge_rspq, napi); - int work_done = process_responses(q, budget); + int work_done; u32 val; + if (!cxgb_poll_lock_napi(q)) + return budget; + + work_done = process_responses(q, budget); if (likely(work_done < budget)) { int timer_index; @@ -2018,6 +2060,7 @@ static int napi_rx_handler(struct napi_struct *napi, int budget) q->bar2_addr + SGE_UDB_GTS); wmb(); } + cxgb_poll_unlock_napi(q); return work_done; } @@ -2341,6 +2384,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, goto err; netif_napi_add(dev, &iq->napi, napi_rx_handler, 64); + napi_hash_add(&iq->napi); iq->cur_desc = iq->desc; iq->cidx = 0; iq->gen = 1; @@ -2598,6 +2642,7 @@ static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, rq->cntxt_id, fl_id, 0xffff); dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len, rq->desc, rq->phys_addr); + napi_hash_del(&rq->napi); netif_napi_del(&rq->napi); rq->netdev = NULL; rq->cntxt_id = rq->abs_id = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h index a40484432ebf..997ec87470c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h @@ -59,6 +59,7 @@ /* GTS register */ #define SGE_TIMERREGS 6 +#define TIMERREG_COUNTER0_X 0 /* T5 and later support a new BAR2-based doorbell mechanism for Egress Queues. * The User Doorbells are each 128 bytes in length with a Simple Doorbell at diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig index 7403dff8f14a..905ac5f5d9a6 100644 --- a/drivers/net/ethernet/cirrus/Kconfig +++ b/drivers/net/ethernet/cirrus/Kconfig @@ -32,7 +32,8 @@ config CS89x0 will be called cs89x0. config CS89x0_PLATFORM - bool "CS89x0 platform driver support" + bool "CS89x0 platform driver support" if HAS_IOPORT_MAP + default !HAS_IOPORT_MAP depends on CS89x0 help Say Y to compile the cs89x0 driver as a platform driver. This diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index 3a12c096ea1c..de9f7c97d916 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -475,8 +475,7 @@ static void ep93xx_free_buffers(struct ep93xx_priv *ep) if (d) dma_unmap_single(dev, d, PKT_BUF_SIZE, DMA_FROM_DEVICE); - if (ep->rx_buf[i] != NULL) - kfree(ep->rx_buf[i]); + kfree(ep->rx_buf[i]); } for (i = 0; i < TX_QUEUE_ENTRIES; i++) { @@ -486,8 +485,7 @@ static void ep93xx_free_buffers(struct ep93xx_priv *ep) if (d) dma_unmap_single(dev, d, PKT_BUF_SIZE, DMA_TO_DEVICE); - if (ep->tx_buf[i] != NULL) - kfree(ep->tx_buf[i]); + kfree(ep->tx_buf[i]); } dma_free_coherent(dev, sizeof(struct ep93xx_descs), ep->descs, diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 0c396c1f55dc..28d9ca675a27 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -92,7 +92,7 @@ static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats); static const unsigned int enic_n_rx_stats = ARRAY_SIZE(enic_rx_stats); static const unsigned int enic_n_gen_stats = ARRAY_SIZE(enic_gen_stats); -void enic_intr_coal_set_rx(struct enic *enic, u32 timer) +static void enic_intr_coal_set_rx(struct enic *enic, u32 timer) { int i; int intr; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index ee44c827164d..9cbe038a388e 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -89,7 +89,7 @@ MODULE_DEVICE_TABLE(pci, enic_id_table); * coalescing timer values * {rx_rate in Mbps, mapping percentage of the range} */ -struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = { +static struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = { {4000, 0}, {4400, 10}, {5060, 20}, @@ -106,7 +106,7 @@ struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = { /* This table helps the driver to pick different ranges for rx coalescing * timer depending on the link speed. */ -struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = { +static struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = { {0, 0}, /* 0 - 4 Gbps */ {0, 3}, /* 4 - 10 Gbps */ {3, 6}, /* 10 - 40 Gbps */ @@ -1303,7 +1303,7 @@ static void enic_set_rx_cpu_rmap(struct enic *enic) #endif /* CONFIG_RFS_ACCEL */ #ifdef CONFIG_NET_RX_BUSY_POLL -int enic_busy_poll(struct napi_struct *napi) +static int enic_busy_poll(struct napi_struct *napi) { struct net_device *netdev = napi->dev; struct enic *enic = netdev_priv(netdev); diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 6aa887e0e1cb..9beb3d34d4ba 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -904,7 +904,7 @@ static void init_registers(struct net_device *dev) } #elif defined(__powerpc__) || defined(__i386__) || defined(__alpha__) || defined(__ia64__) || defined(__x86_64__) i |= 0xE000; -#elif defined(CONFIG_SPARC) || defined (CONFIG_PARISC) +#elif defined(CONFIG_SPARC) || defined (CONFIG_PARISC) || defined(CONFIG_ARM) i |= 0x4800; #else #warning Processor architecture undefined diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 4bd425ea3421..b5aa77284508 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -2747,7 +2747,7 @@ err: return status; } -int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain) +static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain) { struct be_mcc_wrb *wrb; struct be_cmd_req_set_qos *req; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 598c5070c629..efed92c7b731 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4327,7 +4327,8 @@ fw_exit: return status; } -static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh) +static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, + u16 flags) { struct be_adapter *adapter = netdev_priv(dev); struct nlattr *attr, *br_spec; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 58cabee00abf..9bb6220663b2 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2596,12 +2596,9 @@ static void fec_enet_free_queue(struct net_device *ndev) } for (i = 0; i < fep->num_rx_queues; i++) - if (fep->rx_queue[i]) - kfree(fep->rx_queue[i]); - + kfree(fep->rx_queue[i]); for (i = 0; i < fep->num_tx_queues; i++) - if (fep->tx_queue[i]) - kfree(fep->tx_queue[i]); + kfree(fep->tx_queue[i]); } static int fec_enet_alloc_queue(struct net_device *ndev) diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 9e2bcb807923..a17628769a1f 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -278,14 +278,20 @@ static int fs_enet_tx_napi(struct napi_struct *napi, int budget) fep->stats.collisions++; /* unmap */ - dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp), - skb->len, DMA_TO_DEVICE); + if (fep->mapped_as_page[dirtyidx]) + dma_unmap_page(fep->dev, CBDR_BUFADDR(bdp), + CBDR_DATLEN(bdp), DMA_TO_DEVICE); + else + dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp), + CBDR_DATLEN(bdp), DMA_TO_DEVICE); /* * Free the sk buffer associated with this last transmit. */ - dev_kfree_skb(skb); - fep->tx_skbuff[dirtyidx] = NULL; + if (skb) { + dev_kfree_skb(skb); + fep->tx_skbuff[dirtyidx] = NULL; + } /* * Update pointer to next buffer descriptor to be transmitted. @@ -299,7 +305,7 @@ static int fs_enet_tx_napi(struct napi_struct *napi, int budget) * Since we have freed up a buffer, the ring is no longer * full. */ - if (!fep->tx_free++) + if (++fep->tx_free >= MAX_SKB_FRAGS) do_wake = 1; has_tx_work = 1; } @@ -509,6 +515,9 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) cbd_t __iomem *bdp; int curidx; u16 sc; + int nr_frags = skb_shinfo(skb)->nr_frags; + skb_frag_t *frag; + int len; #ifdef CONFIG_FS_ENET_MPC5121_FEC if (((unsigned long)skb->data) & 0x3) { @@ -530,7 +539,7 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) */ bdp = fep->cur_tx; - if (!fep->tx_free || (CBDR_SC(bdp) & BD_ENET_TX_READY)) { + if (fep->tx_free <= nr_frags || (CBDR_SC(bdp) & BD_ENET_TX_READY)) { netif_stop_queue(dev); spin_unlock(&fep->tx_lock); @@ -543,35 +552,42 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) } curidx = bdp - fep->tx_bd_base; - /* - * Clear all of the status flags. - */ - CBDC_SC(bdp, BD_ENET_TX_STATS); - - /* - * Save skb pointer. - */ - fep->tx_skbuff[curidx] = skb; - - fep->stats.tx_bytes += skb->len; + len = skb->len; + fep->stats.tx_bytes += len; + if (nr_frags) + len -= skb->data_len; + fep->tx_free -= nr_frags + 1; /* * Push the data cache so the CPM does not get stale memory data. */ CBDW_BUFADDR(bdp, dma_map_single(fep->dev, - skb->data, skb->len, DMA_TO_DEVICE)); - CBDW_DATLEN(bdp, skb->len); + skb->data, len, DMA_TO_DEVICE)); + CBDW_DATLEN(bdp, len); + + fep->mapped_as_page[curidx] = 0; + frag = skb_shinfo(skb)->frags; + while (nr_frags) { + CBDC_SC(bdp, + BD_ENET_TX_STATS | BD_ENET_TX_LAST | BD_ENET_TX_TC); + CBDS_SC(bdp, BD_ENET_TX_READY); + + if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) + bdp++, curidx++; + else + bdp = fep->tx_bd_base, curidx = 0; - /* - * If this was the last BD in the ring, start at the beginning again. - */ - if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) - fep->cur_tx++; - else - fep->cur_tx = fep->tx_bd_base; + len = skb_frag_size(frag); + CBDW_BUFADDR(bdp, skb_frag_dma_map(fep->dev, frag, 0, len, + DMA_TO_DEVICE)); + CBDW_DATLEN(bdp, len); - if (!--fep->tx_free) - netif_stop_queue(dev); + fep->tx_skbuff[curidx] = NULL; + fep->mapped_as_page[curidx] = 1; + + frag++; + nr_frags--; + } /* Trigger transmission start */ sc = BD_ENET_TX_READY | BD_ENET_TX_INTR | @@ -582,8 +598,22 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) * yay for hw reuse :) */ if (skb->len <= 60) sc |= BD_ENET_TX_PAD; + CBDC_SC(bdp, BD_ENET_TX_STATS); CBDS_SC(bdp, sc); + /* Save skb pointer. */ + fep->tx_skbuff[curidx] = skb; + + /* If this was the last BD in the ring, start at the beginning again. */ + if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) + bdp++; + else + bdp = fep->tx_bd_base; + fep->cur_tx = bdp; + + if (fep->tx_free < MAX_SKB_FRAGS) + netif_stop_queue(dev); + skb_tx_timestamp(skb); (*fep->ops->tx_kickstart)(dev); @@ -917,7 +947,7 @@ static int fs_enet_probe(struct platform_device *ofdev) } fpi->rx_ring = 32; - fpi->tx_ring = 32; + fpi->tx_ring = 64; fpi->rx_copybreak = 240; fpi->napi_weight = 17; fpi->phy_node = of_parse_phandle(ofdev->dev.of_node, "phy-handle", 0); @@ -955,7 +985,8 @@ static int fs_enet_probe(struct platform_device *ofdev) privsize = sizeof(*fep) + sizeof(struct sk_buff **) * - (fpi->rx_ring + fpi->tx_ring); + (fpi->rx_ring + fpi->tx_ring) + + sizeof(char) * fpi->tx_ring; ndev = alloc_etherdev(privsize); if (!ndev) { @@ -978,6 +1009,8 @@ static int fs_enet_probe(struct platform_device *ofdev) fep->rx_skbuff = (struct sk_buff **)&fep[1]; fep->tx_skbuff = fep->rx_skbuff + fpi->rx_ring; + fep->mapped_as_page = (char *)(fep->rx_skbuff + fpi->rx_ring + + fpi->tx_ring); spin_lock_init(&fep->lock); spin_lock_init(&fep->tx_lock); @@ -1007,6 +1040,8 @@ static int fs_enet_probe(struct platform_device *ofdev) netif_carrier_off(ndev); + ndev->features |= NETIF_F_SG; + ret = register_netdev(ndev); if (ret) goto out_free_bd; diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h index 3a4b49e0e717..f184d8f952e2 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h @@ -134,6 +134,7 @@ struct fs_enet_private { void __iomem *ring_base; struct sk_buff **rx_skbuff; struct sk_buff **tx_skbuff; + char *mapped_as_page; cbd_t __iomem *rx_bd_base; /* Address of Rx and Tx buffers. */ cbd_t __iomem *tx_bd_base; cbd_t __iomem *dirty_tx; /* ring entries to be free()ed. */ diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 93ff846e96f1..43df78882e48 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -764,7 +764,7 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) u32 *tx_queues, *rx_queues; unsigned short mode, poll_mode; - if (!np || !of_device_is_available(np)) + if (!np) return -ENODEV; if (of_device_is_compatible(np, "fsl,etsec2")) { diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 3e1a9c1a67a9..fda12fb32ec7 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -1586,7 +1586,7 @@ static int gfar_write_filer_table(struct gfar_private *priv, return -EBUSY; /* Fill regular entries */ - for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].ctrl); + for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop); i++) gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop); /* Fill the rest with fall-troughs */ diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index c02b81bcfffb..b72d238695d7 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -968,3 +968,4 @@ static struct platform_driver hip04_mac_driver = { module_platform_driver(hip04_mac_driver); MODULE_DESCRIPTION("HISILICON P04 Ethernet driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 9388a83818f2..162762d1a12c 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2367,7 +2367,7 @@ static int emac_wait_deps(struct emac_instance *dev) err = emac_check_deps(dev, deps) ? 0 : -ENODEV; for (i = 0; i < EMAC_DEP_COUNT; i++) { of_node_put(deps[i].node); - if (err && deps[i].ofdev) + if (err) of_dev_put(deps[i].ofdev); } if (err == 0) { diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index ad2b4897b392..ebf9d4a42fdd 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1907,7 +1907,8 @@ static void igbvf_watchdog_task(struct work_struct *work) static int igbvf_tso(struct igbvf_adapter *adapter, struct igbvf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags, u8 *hdr_len) + struct sk_buff *skb, u32 tx_flags, u8 *hdr_len, + __be16 protocol) { struct e1000_adv_tx_context_desc *context_desc; struct igbvf_buffer *buffer_info; @@ -1927,7 +1928,7 @@ static int igbvf_tso(struct igbvf_adapter *adapter, l4len = tcp_hdrlen(skb); *hdr_len += l4len; - if (skb->protocol == htons(ETH_P_IP)) { + if (protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -1958,7 +1959,7 @@ static int igbvf_tso(struct igbvf_adapter *adapter, /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT); - if (skb->protocol == htons(ETH_P_IP)) + if (protocol == htons(ETH_P_IP)) tu_cmd |= E1000_ADVTXD_TUCMD_IPV4; tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP; @@ -1984,7 +1985,8 @@ static int igbvf_tso(struct igbvf_adapter *adapter, static inline bool igbvf_tx_csum(struct igbvf_adapter *adapter, struct igbvf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags) + struct sk_buff *skb, u32 tx_flags, + __be16 protocol) { struct e1000_adv_tx_context_desc *context_desc; unsigned int i; @@ -2011,7 +2013,7 @@ static inline bool igbvf_tx_csum(struct igbvf_adapter *adapter, tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT); if (skb->ip_summed == CHECKSUM_PARTIAL) { - switch (skb->protocol) { + switch (protocol) { case htons(ETH_P_IP): tu_cmd |= E1000_ADVTXD_TUCMD_IPV4; if (ip_hdr(skb)->protocol == IPPROTO_TCP) @@ -2211,6 +2213,7 @@ static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb, u8 hdr_len = 0; int count = 0; int tso = 0; + __be16 protocol = vlan_get_protocol(skb); if (test_bit(__IGBVF_DOWN, &adapter->state)) { dev_kfree_skb_any(skb); @@ -2240,13 +2243,13 @@ static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb, IGBVF_TX_FLAGS_VLAN_SHIFT); } - if (skb->protocol == htons(ETH_P_IP)) + if (protocol == htons(ETH_P_IP)) tx_flags |= IGBVF_TX_FLAGS_IPV4; first = tx_ring->next_to_use; tso = skb_is_gso(skb) ? - igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len) : 0; + igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len, protocol) : 0; if (unlikely(tso < 0)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -2254,7 +2257,7 @@ static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb, if (tso) tx_flags |= IGBVF_TX_FLAGS_TSO; - else if (igbvf_tx_csum(adapter, tx_ring, skb, tx_flags) && + else if (igbvf_tx_csum(adapter, tx_ring, skb, tx_flags, protocol) && (skb->ip_summed == CHECKSUM_PARTIAL)) tx_flags |= IGBVF_TX_FLAGS_CSUM; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 7bb421bfd84e..e9e3a1eb9a97 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7227,11 +7227,11 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, if (!vhdr) goto out_drop; - protocol = vhdr->h_vlan_encapsulated_proto; tx_flags |= ntohs(vhdr->h_vlan_TCI) << IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_SW_VLAN; } + protocol = vlan_get_protocol(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && adapter->ptp_clock && @@ -7786,7 +7786,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } static int ixgbe_ndo_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, u16 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct nlattr *attr, *br_spec; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index c9b49bfb51bb..fe2e10f40df8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3099,7 +3099,7 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; - if (skb->protocol == htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -3156,7 +3156,7 @@ static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, if (skb->ip_summed == CHECKSUM_PARTIAL) { u8 l4_hdr = 0; - switch (skb->protocol) { + switch (first->protocol) { case htons(ETH_P_IP): vlan_macip_lens |= skb_network_header_len(skb); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 154effbfd8be..a681d7c0bb9f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1583,6 +1583,15 @@ static struct mlx4_cmd_info cmd_info[] = { .verify = NULL, .wrapper = mlx4_CMD_EPERM_wrapper }, + { + .opcode = MLX4_CMD_VIRT_PORT_MAP, + .has_inbox = false, + .has_outbox = false, + .out_is_imm = false, + .encode_slave_id = false, + .verify = NULL, + .wrapper = mlx4_CMD_EPERM_wrapper + }, }; static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index c643d2bbb7b9..58d5a07d0ff4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -214,6 +214,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) iounmap(mdev->uar_map); mlx4_uar_free(dev, &mdev->priv_uar); mlx4_pd_free(dev, mdev->priv_pdn); + if (mdev->nb.notifier_call) + unregister_netdevice_notifier(&mdev->nb); kfree(mdev); } @@ -298,6 +300,12 @@ static void *mlx4_en_add(struct mlx4_dev *dev) if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i])) mdev->pndev[i] = NULL; } + /* register notifier */ + mdev->nb.notifier_call = mlx4_en_netdev_event; + if (register_netdevice_notifier(&mdev->nb)) { + mdev->nb.notifier_call = NULL; + mlx4_err(mdev, "Failed to create notifier\n"); + } return mdev; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index e075ff1f4e80..2a210c4efb89 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2062,6 +2062,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) /* Detach the netdev so tasks would not attempt to access it */ mutex_lock(&mdev->state_lock); mdev->pndev[priv->port] = NULL; + mdev->upper[priv->port] = NULL; mutex_unlock(&mdev->state_lock); mlx4_en_free_resources(priv); @@ -2201,6 +2202,10 @@ static int mlx4_en_set_features(struct net_device *netdev, return ret; } + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_HW_VLAN_CTAG_TX)) + en_info(priv, "Turn %s TX vlan strip offload\n", + (features & NETIF_F_HW_VLAN_CTAG_TX) ? "ON" : "OFF"); + if (features & NETIF_F_LOOPBACK) priv->ctrl_flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); else @@ -2441,6 +2446,180 @@ static const struct net_device_ops mlx4_netdev_ops_master = { #endif }; +struct mlx4_en_bond { + struct work_struct work; + struct mlx4_en_priv *priv; + int is_bonded; + struct mlx4_port_map port_map; +}; + +static void mlx4_en_bond_work(struct work_struct *work) +{ + struct mlx4_en_bond *bond = container_of(work, + struct mlx4_en_bond, + work); + int err = 0; + struct mlx4_dev *dev = bond->priv->mdev->dev; + + if (bond->is_bonded) { + if (!mlx4_is_bonded(dev)) { + err = mlx4_bond(dev); + if (err) + en_err(bond->priv, "Fail to bond device\n"); + } + if (!err) { + err = mlx4_port_map_set(dev, &bond->port_map); + if (err) + en_err(bond->priv, "Fail to set port map [%d][%d]: %d\n", + bond->port_map.port1, + bond->port_map.port2, + err); + } + } else if (mlx4_is_bonded(dev)) { + err = mlx4_unbond(dev); + if (err) + en_err(bond->priv, "Fail to unbond device\n"); + } + dev_put(bond->priv->dev); + kfree(bond); +} + +static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded, + u8 v2p_p1, u8 v2p_p2) +{ + struct mlx4_en_bond *bond = NULL; + + bond = kzalloc(sizeof(*bond), GFP_ATOMIC); + if (!bond) + return -ENOMEM; + + INIT_WORK(&bond->work, mlx4_en_bond_work); + bond->priv = priv; + bond->is_bonded = is_bonded; + bond->port_map.port1 = v2p_p1; + bond->port_map.port2 = v2p_p2; + dev_hold(priv->dev); + queue_work(priv->mdev->workqueue, &bond->work); + return 0; +} + +int mlx4_en_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + u8 port = 0; + struct mlx4_en_dev *mdev; + struct mlx4_dev *dev; + int i, num_eth_ports = 0; + bool do_bond = true; + struct mlx4_en_priv *priv; + u8 v2p_port1 = 0; + u8 v2p_port2 = 0; + + if (!net_eq(dev_net(ndev), &init_net)) + return NOTIFY_DONE; + + mdev = container_of(this, struct mlx4_en_dev, nb); + dev = mdev->dev; + + /* Go into this mode only when two network devices set on two ports + * of the same mlx4 device are slaves of the same bonding master + */ + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { + ++num_eth_ports; + if (!port && (mdev->pndev[i] == ndev)) + port = i; + mdev->upper[i] = mdev->pndev[i] ? + netdev_master_upper_dev_get(mdev->pndev[i]) : NULL; + /* condition not met: network device is a slave */ + if (!mdev->upper[i]) + do_bond = false; + if (num_eth_ports < 2) + continue; + /* condition not met: same master */ + if (mdev->upper[i] != mdev->upper[i-1]) + do_bond = false; + } + /* condition not met: 2 salves */ + do_bond = (num_eth_ports == 2) ? do_bond : false; + + /* handle only events that come with enough info */ + if ((do_bond && (event != NETDEV_BONDING_INFO)) || !port) + return NOTIFY_DONE; + + priv = netdev_priv(ndev); + if (do_bond) { + struct netdev_notifier_bonding_info *notifier_info = ptr; + struct netdev_bonding_info *bonding_info = + ¬ifier_info->bonding_info; + + /* required mode 1, 2 or 4 */ + if ((bonding_info->master.bond_mode != BOND_MODE_ACTIVEBACKUP) && + (bonding_info->master.bond_mode != BOND_MODE_XOR) && + (bonding_info->master.bond_mode != BOND_MODE_8023AD)) + do_bond = false; + + /* require exactly 2 slaves */ + if (bonding_info->master.num_slaves != 2) + do_bond = false; + + /* calc v2p */ + if (do_bond) { + if (bonding_info->master.bond_mode == + BOND_MODE_ACTIVEBACKUP) { + /* in active-backup mode virtual ports are + * mapped to the physical port of the active + * slave */ + if (bonding_info->slave.state == + BOND_STATE_BACKUP) { + if (port == 1) { + v2p_port1 = 2; + v2p_port2 = 2; + } else { + v2p_port1 = 1; + v2p_port2 = 1; + } + } else { /* BOND_STATE_ACTIVE */ + if (port == 1) { + v2p_port1 = 1; + v2p_port2 = 1; + } else { + v2p_port1 = 2; + v2p_port2 = 2; + } + } + } else { /* Active-Active */ + /* in active-active mode a virtual port is + * mapped to the native physical port if and only + * if the physical port is up */ + __s8 link = bonding_info->slave.link; + + if (port == 1) + v2p_port2 = 2; + else + v2p_port1 = 1; + if ((link == BOND_LINK_UP) || + (link == BOND_LINK_FAIL)) { + if (port == 1) + v2p_port1 = 1; + else + v2p_port2 = 2; + } else { /* BOND_LINK_DOWN || BOND_LINK_BACK */ + if (port == 1) + v2p_port1 = 2; + else + v2p_port2 = 1; + } + } + } + } + + mlx4_en_queue_bond_work(priv, do_bond, + v2p_port1, v2p_port2); + + return NOTIFY_DONE; +} + int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, struct mlx4_en_port_profile *prof) { @@ -2623,6 +2802,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } mdev->pndev[port] = dev; + mdev->upper[port] = NULL; netif_carrier_off(dev); mlx4_en_set_default_moderation(priv); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index f1a5500ff72d..34f2fdf4fe5d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -50,10 +50,14 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, context->mtu_msgmax = 0xff; if (!is_tx && !rss) context->rq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4); - if (is_tx) + if (is_tx) { context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4); - else + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP) + context->params2 |= MLX4_QP_BIT_FPP; + + } else { context->sq_size_stride = ilog2(TXBB_SIZE) - 4; + } context->usr_page = cpu_to_be32(mdev->priv_uar.index); context->local_qpn = cpu_to_be32(qpn); context->pri_path.ackto = 1 & 0x07; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 2ba5d368edce..698d60de1255 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -162,6 +162,10 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, if (mlx4_alloc_pages(priv, &ring->page_alloc[i], frag_info, GFP_KERNEL | __GFP_COLD)) goto out; + + en_dbg(DRV, priv, " frag %d allocator: - size:%d frags:%d\n", + i, ring->page_alloc[i].page_size, + atomic_read(&ring->page_alloc[i].page->_count)); } return 0; @@ -1059,8 +1063,9 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) (eff_mtu > buf_size + frag_sizes[i]) ? frag_sizes[i] : eff_mtu - buf_size; priv->frag_info[i].frag_prefix_size = buf_size; - priv->frag_info[i].frag_stride = ALIGN(frag_sizes[i], - SMP_CACHE_BYTES); + priv->frag_info[i].frag_stride = + ALIGN(priv->frag_info[i].frag_size, + SMP_CACHE_BYTES); buf_size += priv->frag_info[i].frag_size; i++; } diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index dbabfae3a3de..5a21e5dc94cb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -142,7 +142,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [17] = "Asymmetric EQs support", [18] = "More than 80 VFs support", [19] = "Performance optimized for limited rule configuration flow steering support", - [20] = "Recoverable error events support" + [20] = "Recoverable error events support", + [21] = "Port Remap support" }; int i; @@ -863,6 +864,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE; MLX4_GET(dev_cap->bmme_flags, outbox, QUERY_DEV_CAP_BMME_FLAGS_OFFSET); + if (dev_cap->bmme_flags & MLX4_FLAG_PORT_REMAP) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PORT_REMAP; MLX4_GET(field, outbox, QUERY_DEV_CAP_CONFIG_DEV_OFFSET); if (field & 0x20) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CONFIG_DEV; @@ -1120,9 +1123,10 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, field &= 0x7f; MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET); - /* For guests, disable mw type 2 */ + /* For guests, disable mw type 2 and port remap*/ MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET); bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN; + bmme_flags &= ~MLX4_FLAG_PORT_REMAP; MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET); /* turn off device-managed steering capability if not enabled */ @@ -2100,13 +2104,16 @@ struct mlx4_config_dev { __be32 rsvd1[3]; __be16 vxlan_udp_dport; __be16 rsvd2; - __be32 rsvd3[27]; - __be16 rsvd4; - u8 rsvd5; + __be32 rsvd3; + __be32 roce_flags; + __be32 rsvd4[25]; + __be16 rsvd5; + u8 rsvd6; u8 rx_checksum_val; }; #define MLX4_VXLAN_UDP_DPORT (1 << 0) +#define MLX4_DISABLE_RX_PORT BIT(18) static int mlx4_CONFIG_DEV_set(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev) { @@ -2162,7 +2169,7 @@ static const u8 config_dev_csum_flags[] = { int mlx4_config_dev_retrieval(struct mlx4_dev *dev, struct mlx4_config_dev_params *params) { - struct mlx4_config_dev config_dev; + struct mlx4_config_dev config_dev = {0}; int err; u8 csum_mask; @@ -2209,6 +2216,45 @@ int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port) } EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port); +#define CONFIG_DISABLE_RX_PORT BIT(15) +int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis) +{ + struct mlx4_config_dev config_dev; + + memset(&config_dev, 0, sizeof(config_dev)); + config_dev.update_flags = cpu_to_be32(MLX4_DISABLE_RX_PORT); + if (dis) + config_dev.roce_flags = + cpu_to_be32(CONFIG_DISABLE_RX_PORT); + + return mlx4_CONFIG_DEV_set(dev, &config_dev); +} + +int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2) +{ + struct mlx4_cmd_mailbox *mailbox; + struct { + __be32 v_port1; + __be32 v_port2; + } *v2p; + int err; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return -ENOMEM; + + v2p = mailbox->buf; + v2p->v_port1 = cpu_to_be32(port1); + v2p->v_port2 = cpu_to_be32(port2); + + err = mlx4_cmd(dev, mailbox->dma, 0, + MLX4_SET_PORT_VIRT2PHY, MLX4_CMD_VIRT_PORT_MAP, + MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); + + mlx4_free_cmd_mailbox(dev, mailbox); + return err; +} + int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages) { diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 68d2bad325d5..6fce58718837 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -33,11 +33,13 @@ #include <linux/slab.h> #include <linux/export.h> +#include <linux/errno.h> #include "mlx4.h" struct mlx4_device_context { struct list_head list; + struct list_head bond_list; struct mlx4_interface *intf; void *context; }; @@ -115,6 +117,58 @@ void mlx4_unregister_interface(struct mlx4_interface *intf) } EXPORT_SYMBOL_GPL(mlx4_unregister_interface); +int mlx4_do_bond(struct mlx4_dev *dev, bool enable) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx; + unsigned long flags; + int ret; + LIST_HEAD(bond_list); + + if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)) + return -ENOTSUPP; + + ret = mlx4_disable_rx_port_check(dev, enable); + if (ret) { + mlx4_err(dev, "Fail to %s rx port check\n", + enable ? "enable" : "disable"); + return ret; + } + if (enable) { + dev->flags |= MLX4_FLAG_BONDED; + } else { + ret = mlx4_virt2phy_port_map(dev, 1, 2); + if (ret) { + mlx4_err(dev, "Fail to reset port map\n"); + return ret; + } + dev->flags &= ~MLX4_FLAG_BONDED; + } + + spin_lock_irqsave(&priv->ctx_lock, flags); + list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) { + if (dev_ctx->intf->flags & MLX4_INTFF_BONDING) { + list_add_tail(&dev_ctx->bond_list, &bond_list); + list_del(&dev_ctx->list); + } + } + spin_unlock_irqrestore(&priv->ctx_lock, flags); + + list_for_each_entry(dev_ctx, &bond_list, bond_list) { + dev_ctx->intf->remove(dev, dev_ctx->context); + dev_ctx->context = dev_ctx->intf->add(dev); + + spin_lock_irqsave(&priv->ctx_lock, flags); + list_add_tail(&dev_ctx->list, &priv->ctx_list); + spin_unlock_irqrestore(&priv->ctx_lock, flags); + + mlx4_dbg(dev, "Inrerface for protocol %d restarted with when bonded mode is %s\n", + dev_ctx->intf->protocol, enable ? + "enabled" : "disabled"); + } + return 0; +} + void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, unsigned long param) { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index cc9f48439244..7e487223489a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -251,7 +251,8 @@ static void mlx4_enable_cqe_eqe_stride(struct mlx4_dev *dev) if (mlx4_is_master(dev)) dev_cap->function_caps |= MLX4_FUNC_CAP_EQE_CQE_STRIDE; } else { - mlx4_dbg(dev, "Disabling CQE stride cacheLine unsupported\n"); + if (cache_line_size() != 32 && cache_line_size() != 64) + mlx4_dbg(dev, "Disabling CQE stride, cacheLine size unsupported\n"); dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE; dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE; } @@ -1160,6 +1161,91 @@ err_set_port: return err ? err : count; } +int mlx4_bond(struct mlx4_dev *dev) +{ + int ret = 0; + struct mlx4_priv *priv = mlx4_priv(dev); + + mutex_lock(&priv->bond_mutex); + + if (!mlx4_is_bonded(dev)) + ret = mlx4_do_bond(dev, true); + else + ret = 0; + + mutex_unlock(&priv->bond_mutex); + if (ret) + mlx4_err(dev, "Failed to bond device: %d\n", ret); + else + mlx4_dbg(dev, "Device is bonded\n"); + return ret; +} +EXPORT_SYMBOL_GPL(mlx4_bond); + +int mlx4_unbond(struct mlx4_dev *dev) +{ + int ret = 0; + struct mlx4_priv *priv = mlx4_priv(dev); + + mutex_lock(&priv->bond_mutex); + + if (mlx4_is_bonded(dev)) + ret = mlx4_do_bond(dev, false); + + mutex_unlock(&priv->bond_mutex); + if (ret) + mlx4_err(dev, "Failed to unbond device: %d\n", ret); + else + mlx4_dbg(dev, "Device is unbonded\n"); + return ret; +} +EXPORT_SYMBOL_GPL(mlx4_unbond); + + +int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p) +{ + u8 port1 = v2p->port1; + u8 port2 = v2p->port2; + struct mlx4_priv *priv = mlx4_priv(dev); + int err; + + if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)) + return -ENOTSUPP; + + mutex_lock(&priv->bond_mutex); + + /* zero means keep current mapping for this port */ + if (port1 == 0) + port1 = priv->v2p.port1; + if (port2 == 0) + port2 = priv->v2p.port2; + + if ((port1 < 1) || (port1 > MLX4_MAX_PORTS) || + (port2 < 1) || (port2 > MLX4_MAX_PORTS) || + (port1 == 2 && port2 == 1)) { + /* besides boundary checks cross mapping makes + * no sense and therefore not allowed */ + err = -EINVAL; + } else if ((port1 == priv->v2p.port1) && + (port2 == priv->v2p.port2)) { + err = 0; + } else { + err = mlx4_virt2phy_port_map(dev, port1, port2); + if (!err) { + mlx4_dbg(dev, "port map changed: [%d][%d]\n", + port1, port2); + priv->v2p.port1 = port1; + priv->v2p.port2 = port2; + } else { + mlx4_err(dev, "Failed to change port mape: %d\n", err); + } + } + + mutex_unlock(&priv->bond_mutex); + return err; +} +EXPORT_SYMBOL_GPL(mlx4_port_map_set); + static int mlx4_load_fw(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -2638,6 +2724,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, spin_lock_init(&priv->ctx_lock); mutex_init(&priv->port_mutex); + mutex_init(&priv->bond_mutex); INIT_LIST_HEAD(&priv->pgdir_list); mutex_init(&priv->pgdir_mutex); @@ -2934,6 +3021,9 @@ slave_start: goto err_port; } + priv->v2p.port1 = 1; + priv->v2p.port2 = 2; + err = mlx4_register_device(dev); if (err) goto err_port; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 148dc0945aab..1409d0cd6143 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -244,7 +244,8 @@ extern int mlx4_log_num_mgm_entry_size; extern int log_mtts_per_seg; extern int mlx4_internal_err_reset; -#define MLX4_MAX_NUM_SLAVES (MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF) +#define MLX4_MAX_NUM_SLAVES (min(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF, \ + MLX4_MFUNC_MAX)) #define ALL_SLAVES 0xff struct mlx4_bitmap { @@ -885,6 +886,8 @@ struct mlx4_priv { int reserved_mtts; int fs_hash_mode; u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; + struct mlx4_port_map v2p; /* cached port mapping configuration */ + struct mutex bond_mutex; /* for bond mode */ __be64 slave_node_guids[MLX4_MFUNC_MAX]; atomic_t opreq_count; @@ -1364,6 +1367,7 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port); /* Returns the VF index of slave */ int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave); int mlx4_config_mad_demux(struct mlx4_dev *dev); +int mlx4_do_bond(struct mlx4_dev *dev, bool enable); enum mlx4_zone_flags { MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO = 1UL << 0, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 944a112dff37..2a8268e6be15 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -390,6 +390,7 @@ struct mlx4_en_dev { struct pci_dev *pdev; struct mutex state_lock; struct net_device *pndev[MLX4_MAX_PORTS + 1]; + struct net_device *upper[MLX4_MAX_PORTS + 1]; u32 port_cnt; bool device_up; struct mlx4_en_profile profile; @@ -410,6 +411,7 @@ struct mlx4_en_dev { unsigned long overflow_period; struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_info; + struct notifier_block nb; }; @@ -845,6 +847,9 @@ int mlx4_en_reset_config(struct net_device *dev, struct hwtstamp_config ts_config, netdev_features_t new_features); +int mlx4_en_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr); + /* * Functions for time stamping */ diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index d21e884a0838..78f51e103880 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -598,14 +598,11 @@ int mlx4_mr_rereg_mem_write(struct mlx4_dev *dev, struct mlx4_mr *mr, if (err) return err; - mpt_entry->start = cpu_to_be64(mr->iova); - mpt_entry->length = cpu_to_be64(mr->size); - mpt_entry->entity_size = cpu_to_be32(mr->mtt.page_shift); - - mpt_entry->pd_flags &= cpu_to_be32(MLX4_MPT_PD_MASK | - MLX4_MPT_PD_FLAG_EN_INV); - mpt_entry->flags &= cpu_to_be32(MLX4_MPT_FLAG_FREE | - MLX4_MPT_FLAG_SW_OWNS); + mpt_entry->start = cpu_to_be64(iova); + mpt_entry->length = cpu_to_be64(size); + mpt_entry->entity_size = cpu_to_be32(page_shift); + mpt_entry->flags &= ~(cpu_to_be32(MLX4_MPT_FLAG_FREE | + MLX4_MPT_FLAG_SW_OWNS)); if (mr->mtt.order < 0) { mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_PHYSICAL); mpt_entry->mtt_addr = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 1586ecce13c7..2bb8553bd905 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -882,6 +882,8 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt, for (i = 0; i < ARRAY_SIZE(states) - 1; i++) { context->flags &= cpu_to_be32(~(0xf << 28)); context->flags |= cpu_to_be32(states[i + 1] << 28); + if (states[i + 1] != MLX4_QP_STATE_RTR) + context->params2 &= ~MLX4_QP_BIT_FPP; err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1], context, 0, 0, qp); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 79feeb6b0d87..486e3d26cd4a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2541,7 +2541,7 @@ int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave, /* Make sure that the PD bits related to the slave id are zeros. */ pd = mr_get_pd(inbox->buf); pd_slave = (pd >> 17) & 0x7f; - if (pd_slave != 0 && pd_slave != slave) { + if (pd_slave != 0 && --pd_slave != slave) { err = -EPERM; goto ex_abort; } @@ -2944,6 +2944,9 @@ static int verify_qp_parameters(struct mlx4_dev *dev, qp_type = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; optpar = be32_to_cpu(*(__be32 *) inbox->buf); + if (slave != mlx4_master_func_num(dev)) + qp_ctx->params2 &= ~MLX4_QP_BIT_FPP; + switch (qp_type) { case MLX4_QP_ST_RC: case MLX4_QP_ST_XRC: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3f4525619a07..d6651937d899 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -903,12 +903,12 @@ static void remove_one(struct pci_dev *pdev) } static const struct pci_device_id mlx5_core_pci_table[] = { - { PCI_VDEVICE(MELLANOX, 4113) }, /* Connect-IB */ - { PCI_VDEVICE(MELLANOX, 4114) }, /* Connect-IB VF */ - { PCI_VDEVICE(MELLANOX, 4115) }, /* ConnectX-4 */ - { PCI_VDEVICE(MELLANOX, 4116) }, /* ConnectX-4 VF */ - { PCI_VDEVICE(MELLANOX, 4117) }, /* ConnectX-4LX */ - { PCI_VDEVICE(MELLANOX, 4118) }, /* ConnectX-4LX VF */ + { PCI_VDEVICE(MELLANOX, 0x1011) }, /* Connect-IB */ + { PCI_VDEVICE(MELLANOX, 0x1012) }, /* Connect-IB VF */ + { PCI_VDEVICE(MELLANOX, 0x1013) }, /* ConnectX-4 */ + { PCI_VDEVICE(MELLANOX, 0x1014) }, /* ConnectX-4 VF */ + { PCI_VDEVICE(MELLANOX, 0x1015) }, /* ConnectX-4LX */ + { PCI_VDEVICE(MELLANOX, 0x1016) }, /* ConnectX-4LX VF */ { 0, } }; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 71af98bb72cb..1412f5af05ec 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -4226,8 +4226,7 @@ static void myri10ge_remove(struct pci_dev *pdev) mtrr_del(mgp->mtrr, mgp->iomem_base, mgp->board_span); #endif myri10ge_free_slices(mgp); - if (mgp->msix_vectors != NULL) - kfree(mgp->msix_vectors); + kfree(mgp->msix_vectors); dma_free_coherent(&pdev->dev, sizeof(*mgp->cmd), mgp->cmd, mgp->cmd_bus); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 2bbd01fcb9b0..6223930a8155 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -4637,7 +4637,7 @@ static void __vxge_hw_vp_terminate(struct __vxge_hw_device *hldev, u32 vp_id) vpath->ringh = NULL; vpath->fifoh = NULL; memset(&vpath->vpath_handles, 0, sizeof(struct list_head)); - vpath->stats_block = 0; + vpath->stats_block = NULL; vpath->hw_stats = NULL; vpath->hw_stats_sav = NULL; vpath->sw_stats = NULL; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index afb8efb25781..e0c31e3947d1 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -176,9 +176,7 @@ netxen_alloc_sds_rings(struct netxen_recv_context *recv_ctx, int count) static void netxen_free_sds_rings(struct netxen_recv_context *recv_ctx) { - if (recv_ctx->sds_rings != NULL) - kfree(recv_ctx->sds_rings); - + kfree(recv_ctx->sds_rings); recv_ctx->sds_rings = NULL; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 4d2496f28b85..d4b5085a21fa 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -968,7 +968,12 @@ static int qlcnic_poll(struct napi_struct *napi, int budget) tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget); work_done = qlcnic_process_rcv_ring(sds_ring, budget); - if ((work_done < budget) && tx_complete) { + + /* Check if we need a repoll */ + if (!tx_complete) + work_done = budget; + + if (work_done < budget) { napi_complete(&sds_ring->napi); if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) { qlcnic_enable_sds_intr(adapter, sds_ring); @@ -993,6 +998,9 @@ static int qlcnic_tx_poll(struct napi_struct *napi, int budget) napi_complete(&tx_ring->napi); if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) qlcnic_enable_tx_intr(adapter, tx_ring); + } else { + /* As qlcnic_process_cmd_ring() returned 0, we need a repoll*/ + work_done = budget; } return work_done; @@ -1951,7 +1959,12 @@ static int qlcnic_83xx_msix_sriov_vf_poll(struct napi_struct *napi, int budget) tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget); work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget); - if ((work_done < budget) && tx_complete) { + + /* Check if we need a repoll */ + if (!tx_complete) + work_done = budget; + + if (work_done < budget) { napi_complete(&sds_ring->napi); qlcnic_enable_sds_intr(adapter, sds_ring); } @@ -1974,7 +1987,12 @@ static int qlcnic_83xx_poll(struct napi_struct *napi, int budget) tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget); work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget); - if ((work_done < budget) && tx_complete) { + + /* Check if we need a repoll */ + if (!tx_complete) + work_done = budget; + + if (work_done < budget) { napi_complete(&sds_ring->napi); qlcnic_enable_sds_intr(adapter, sds_ring); } @@ -1996,6 +2014,9 @@ static int qlcnic_83xx_msix_tx_poll(struct napi_struct *napi, int budget) napi_complete(&tx_ring->napi); if (test_bit(__QLCNIC_DEV_UP , &adapter->state)) qlcnic_enable_tx_intr(adapter, tx_ring); + } else { + /* need a repoll */ + work_done = budget; } return work_done; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 2528c3fb6b90..a430a34a4434 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -294,9 +294,7 @@ int qlcnic_alloc_sds_rings(struct qlcnic_recv_context *recv_ctx, int count) void qlcnic_free_sds_rings(struct qlcnic_recv_context *recv_ctx) { - if (recv_ctx->sds_rings != NULL) - kfree(recv_ctx->sds_rings); - + kfree(recv_ctx->sds_rings); recv_ctx->sds_rings = NULL; } @@ -1257,8 +1255,7 @@ qlcnic_check_options(struct qlcnic_adapter *adapter) if (ahw->op_mode != QLCNIC_NON_PRIV_FUNC) { if (fw_dump->tmpl_hdr == NULL || adapter->fw_version > prev_fw_version) { - if (fw_dump->tmpl_hdr) - vfree(fw_dump->tmpl_hdr); + vfree(fw_dump->tmpl_hdr); if (!qlcnic_fw_cmd_get_minidump_temp(adapter)) dev_info(&pdev->dev, "Supports FW dump capability\n"); @@ -2374,13 +2371,12 @@ void qlcnic_free_tx_rings(struct qlcnic_adapter *adapter) for (ring = 0; ring < adapter->drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; - if (tx_ring && tx_ring->cmd_buf_arr != NULL) { + if (tx_ring) { vfree(tx_ring->cmd_buf_arr); tx_ring->cmd_buf_arr = NULL; } } - if (adapter->tx_ring != NULL) - kfree(adapter->tx_ring); + kfree(adapter->tx_ring); } int qlcnic_alloc_tx_rings(struct qlcnic_adapter *adapter, @@ -2758,13 +2754,9 @@ static void qlcnic_remove(struct pci_dev *pdev) } qlcnic_dcb_free(adapter->dcb); - qlcnic_detach(adapter); - - if (adapter->npars != NULL) - kfree(adapter->npars); - if (adapter->eswitch != NULL) - kfree(adapter->eswitch); + kfree(adapter->npars); + kfree(adapter->eswitch); if (qlcnic_82xx_check(adapter)) qlcnic_clr_all_drv_state(adapter, 0); @@ -2932,13 +2924,13 @@ void qlcnic_alloc_lb_filters_mem(struct qlcnic_adapter *adapter) static void qlcnic_free_lb_filters_mem(struct qlcnic_adapter *adapter) { - if (adapter->fhash.fmax && adapter->fhash.fhead) + if (adapter->fhash.fmax) kfree(adapter->fhash.fhead); adapter->fhash.fhead = NULL; adapter->fhash.fmax = 0; - if (adapter->rx_fhash.fmax && adapter->rx_fhash.fhead) + if (adapter->rx_fhash.fmax) kfree(adapter->rx_fhash.fhead); adapter->rx_fhash.fmax = 0; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index c9f57fb84b9e..332bb8a3f430 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1407,8 +1407,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) current_version = qlcnic_83xx_get_fw_version(adapter); if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) { - if (fw_dump->tmpl_hdr) - vfree(fw_dump->tmpl_hdr); + vfree(fw_dump->tmpl_hdr); if (!qlcnic_fw_cmd_get_minidump_temp(adapter)) dev_info(&pdev->dev, "Supports FW dump capability\n"); } diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index dc0058f90370..8011ef3e7707 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -2351,23 +2351,29 @@ static int qlge_update_hw_vlan_features(struct net_device *ndev, { struct ql_adapter *qdev = netdev_priv(ndev); int status = 0; + bool need_restart = netif_running(ndev); - status = ql_adapter_down(qdev); - if (status) { - netif_err(qdev, link, qdev->ndev, - "Failed to bring down the adapter\n"); - return status; + if (need_restart) { + status = ql_adapter_down(qdev); + if (status) { + netif_err(qdev, link, qdev->ndev, + "Failed to bring down the adapter\n"); + return status; + } } /* update the features with resent change */ ndev->features = features; - status = ql_adapter_up(qdev); - if (status) { - netif_err(qdev, link, qdev->ndev, - "Failed to bring up the adapter\n"); - return status; + if (need_restart) { + status = ql_adapter_up(qdev); + if (status) { + netif_err(qdev, link, qdev->ndev, + "Failed to bring up the adapter\n"); + return status; + } } + return status; } diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 11f4ffcc113d..34389b6aa67c 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3722,7 +3722,7 @@ skip: } static int rocker_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, u16 flags) { struct rocker_port *rocker_port = netdev_priv(dev); struct nlattr *protinfo; @@ -3833,11 +3833,145 @@ static void rocker_port_get_drvinfo(struct net_device *dev, strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version)); } +static struct rocker_port_stats { + char str[ETH_GSTRING_LEN]; + int type; +} rocker_port_stats[] = { + { "rx_packets", ROCKER_TLV_CMD_PORT_STATS_RX_PKTS, }, + { "rx_bytes", ROCKER_TLV_CMD_PORT_STATS_RX_BYTES, }, + { "rx_dropped", ROCKER_TLV_CMD_PORT_STATS_RX_DROPPED, }, + { "rx_errors", ROCKER_TLV_CMD_PORT_STATS_RX_ERRORS, }, + + { "tx_packets", ROCKER_TLV_CMD_PORT_STATS_TX_PKTS, }, + { "tx_bytes", ROCKER_TLV_CMD_PORT_STATS_TX_BYTES, }, + { "tx_dropped", ROCKER_TLV_CMD_PORT_STATS_TX_DROPPED, }, + { "tx_errors", ROCKER_TLV_CMD_PORT_STATS_TX_ERRORS, }, +}; + +#define ROCKER_PORT_STATS_LEN ARRAY_SIZE(rocker_port_stats) + +static void rocker_port_get_strings(struct net_device *netdev, u32 stringset, + u8 *data) +{ + u8 *p = data; + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < ARRAY_SIZE(rocker_port_stats); i++) { + memcpy(p, rocker_port_stats[i].str, ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + break; + } +} + +static int +rocker_cmd_get_port_stats_prep(struct rocker *rocker, + struct rocker_port *rocker_port, + struct rocker_desc_info *desc_info, + void *priv) +{ + struct rocker_tlv *cmd_stats; + + if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, + ROCKER_TLV_CMD_TYPE_GET_PORT_STATS)) + return -EMSGSIZE; + + cmd_stats = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO); + if (!cmd_stats) + return -EMSGSIZE; + + if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_STATS_LPORT, + rocker_port->lport)) + return -EMSGSIZE; + + rocker_tlv_nest_end(desc_info, cmd_stats); + + return 0; +} + +static int +rocker_cmd_get_port_stats_ethtool_proc(struct rocker *rocker, + struct rocker_port *rocker_port, + struct rocker_desc_info *desc_info, + void *priv) +{ + struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; + struct rocker_tlv *stats_attrs[ROCKER_TLV_CMD_PORT_STATS_MAX + 1]; + struct rocker_tlv *pattr; + u32 lport; + u64 *data = priv; + int i; + + rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info); + + if (!attrs[ROCKER_TLV_CMD_INFO]) + return -EIO; + + rocker_tlv_parse_nested(stats_attrs, ROCKER_TLV_CMD_PORT_STATS_MAX, + attrs[ROCKER_TLV_CMD_INFO]); + + if (!stats_attrs[ROCKER_TLV_CMD_PORT_STATS_LPORT]) + return -EIO; + + lport = rocker_tlv_get_u32(stats_attrs[ROCKER_TLV_CMD_PORT_STATS_LPORT]); + if (lport != rocker_port->lport) + return -EIO; + + for (i = 0; i < ARRAY_SIZE(rocker_port_stats); i++) { + pattr = stats_attrs[rocker_port_stats[i].type]; + if (!pattr) + continue; + + data[i] = rocker_tlv_get_u64(pattr); + } + + return 0; +} + +static int rocker_cmd_get_port_stats_ethtool(struct rocker_port *rocker_port, + void *priv) +{ + return rocker_cmd_exec(rocker_port->rocker, rocker_port, + rocker_cmd_get_port_stats_prep, NULL, + rocker_cmd_get_port_stats_ethtool_proc, + priv, false); +} + +static void rocker_port_get_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + + if (rocker_cmd_get_port_stats_ethtool(rocker_port, data) != 0) { + int i; + + for (i = 0; i < ARRAY_SIZE(rocker_port_stats); ++i) + data[i] = 0; + } + + return; +} + +static int rocker_port_get_sset_count(struct net_device *netdev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ROCKER_PORT_STATS_LEN; + default: + return -EOPNOTSUPP; + } +} + static const struct ethtool_ops rocker_port_ethtool_ops = { .get_settings = rocker_port_get_settings, .set_settings = rocker_port_set_settings, .get_drvinfo = rocker_port_get_drvinfo, .get_link = ethtool_op_get_link, + .get_strings = rocker_port_get_strings, + .get_ethtool_stats = rocker_port_get_stats, + .get_sset_count = rocker_port_get_sset_count, }; /***************** @@ -4030,7 +4164,8 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) NAPI_POLL_WEIGHT); rocker_carrier_init(rocker_port); - dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_SWITCH_OFFLOAD; err = register_netdev(dev); if (err) { diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index 8d2865ba634c..a5bc432feada 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -127,6 +127,9 @@ enum { ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL, ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_GET_STATS, + ROCKER_TLV_CMD_TYPE_CLEAR_PORT_STATS, + ROCKER_TLV_CMD_TYPE_GET_PORT_STATS, + __ROCKER_TLV_CMD_TYPE_MAX, ROCKER_TLV_CMD_TYPE_MAX = __ROCKER_TLV_CMD_TYPE_MAX - 1, }; @@ -146,6 +149,24 @@ enum { __ROCKER_TLV_CMD_PORT_SETTINGS_MAX - 1, }; +enum { + ROCKER_TLV_CMD_PORT_STATS_UNSPEC, + ROCKER_TLV_CMD_PORT_STATS_LPORT, /* u32 */ + + ROCKER_TLV_CMD_PORT_STATS_RX_PKTS, /* u64 */ + ROCKER_TLV_CMD_PORT_STATS_RX_BYTES, /* u64 */ + ROCKER_TLV_CMD_PORT_STATS_RX_DROPPED, /* u64 */ + ROCKER_TLV_CMD_PORT_STATS_RX_ERRORS, /* u64 */ + + ROCKER_TLV_CMD_PORT_STATS_TX_PKTS, /* u64 */ + ROCKER_TLV_CMD_PORT_STATS_TX_BYTES, /* u64 */ + ROCKER_TLV_CMD_PORT_STATS_TX_DROPPED, /* u64 */ + ROCKER_TLV_CMD_PORT_STATS_TX_ERRORS, /* u64 */ + + __ROCKER_TLV_CMD_PORT_STATS_MAX, + ROCKER_TLV_CMD_PORT_STATS_MAX = __ROCKER_TLV_CMD_PORT_STATS_MAX - 1, +}; + enum rocker_port_mode { ROCKER_PORT_MODE_OF_DPA, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9c11c4d0f3fd..55e89b3838f1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1288,7 +1288,7 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) * that needs to not insert csum in the TDES. */ priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE); - tc = SF_DMA_MODE; + priv->xstats.threshold = SF_DMA_MODE; } else priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE); } @@ -1452,7 +1452,8 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) } if (unlikely(status & tx_hard_error_bump_tc)) { /* Try to bump up the dma threshold on this failure */ - if (unlikely(tc != SF_DMA_MODE) && (tc <= 256)) { + if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && + (tc <= 256)) { tc += 64; if (priv->plat->force_thresh_dma_mode) priv->hw->dma->dma_mode(priv->ioaddr, tc, tc); diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 2b719ccd6e7c..2b10b85d8a08 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1123,6 +1123,7 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies) skb_shinfo(nskb)->gso_size = skb_shinfo(skb)->gso_size; skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type; } + nskb->queue_mapping = skb->queue_mapping; dev_kfree_skb(skb); skb = nskb; } diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 4ea1663f3dea..3bc992cd70b7 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -56,12 +56,18 @@ config TI_CPSW_PHY_SEL This driver supports configuring of the phy mode connected to the CPSW. +config TI_CPSW_ALE + tristate "TI CPSW ALE Support" + ---help--- + This driver supports TI's CPSW ALE module. + config TI_CPSW tristate "TI CPSW Switch Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS select TI_DAVINCI_CPDMA select TI_DAVINCI_MDIO select TI_CPSW_PHY_SEL + select TI_CPSW_ALE select MFD_SYSCON select REGMAP ---help--- @@ -80,15 +86,24 @@ config TI_CPTS and Layer 2 packets, and the driver offers a PTP Hardware Clock. config TI_KEYSTONE_NETCP - tristate "TI Keystone NETCP Ethernet subsystem Support" + tristate "TI Keystone NETCP Core Support" + select TI_CPSW_ALE depends on OF depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS ---help--- - This driver supports TI's Keystone NETCP Ethernet subsystem. + This driver supports TI's Keystone NETCP Core. To compile this driver as a module, choose M here: the module will be called keystone_netcp. +config TI_KEYSTONE_NETCP_ETHSS + depends on TI_KEYSTONE_NETCP + tristate "TI Keystone NETCP Ethernet subsystem Support" + ---help--- + + To compile this driver as a module, choose M here: the module + will be called keystone_netcp_ethss. + config TLAN tristate "TI ThunderLAN support" depends on (PCI || EISA) diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 0a9813bc0451..d420d9413e4a 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -2,15 +2,20 @@ # Makefile for the TI network device drivers. # +obj-$(CONFIG_TI_CPSW) += cpsw-common.o +obj-$(CONFIG_TI_DAVINCI_EMAC) += cpsw-common.o + obj-$(CONFIG_TLAN) += tlan.o obj-$(CONFIG_CPMAC) += cpmac.o obj-$(CONFIG_TI_DAVINCI_EMAC) += davinci_emac.o obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o obj-$(CONFIG_TI_DAVINCI_CPDMA) += davinci_cpdma.o obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o +obj-$(CONFIG_TI_CPSW_ALE) += cpsw_ale.o obj-$(CONFIG_TI_CPSW) += ti_cpsw.o -ti_cpsw-y := cpsw_ale.o cpsw.o cpts.o +ti_cpsw-y := cpsw.o cpts.o obj-$(CONFIG_TI_KEYSTONE_NETCP) += keystone_netcp.o -keystone_netcp-y := netcp_core.o netcp_ethss.o netcp_sgmii.o \ - netcp_xgbepcsr.o cpsw_ale.o +keystone_netcp-y := netcp_core.o +obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o +keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c new file mode 100644 index 000000000000..f59509486113 --- /dev/null +++ b/drivers/net/ethernet/ti/cpsw-common.c @@ -0,0 +1,55 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/regmap.h> +#include <linux/mfd/syscon.h> + +#include "cpsw.h" + +#define AM33XX_CTRL_MAC_LO_REG(offset, id) ((offset) + 0x8 * (id)) +#define AM33XX_CTRL_MAC_HI_REG(offset, id) ((offset) + 0x8 * (id) + 0x4) + +int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, + u8 *mac_addr) +{ + u32 macid_lo; + u32 macid_hi; + struct regmap *syscon; + + syscon = syscon_regmap_lookup_by_phandle(dev->of_node, "syscon"); + if (IS_ERR(syscon)) { + if (PTR_ERR(syscon) == -ENODEV) + return 0; + return PTR_ERR(syscon); + } + + regmap_read(syscon, AM33XX_CTRL_MAC_LO_REG(offset, slave), + &macid_lo); + regmap_read(syscon, AM33XX_CTRL_MAC_HI_REG(offset, slave), + &macid_hi); + + mac_addr[5] = (macid_lo >> 8) & 0xff; + mac_addr[4] = macid_lo & 0xff; + mac_addr[3] = (macid_hi >> 24) & 0xff; + mac_addr[2] = (macid_hi >> 16) & 0xff; + mac_addr[1] = (macid_hi >> 8) & 0xff; + mac_addr[0] = macid_hi & 0xff; + + return 0; +} +EXPORT_SYMBOL_GPL(cpsw_am33xx_cm_get_macid); + +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 2b9d404f8586..7d8dd0d2182e 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -33,8 +33,6 @@ #include <linux/of_net.h> #include <linux/of_device.h> #include <linux/if_vlan.h> -#include <linux/mfd/syscon.h> -#include <linux/regmap.h> #include <linux/pinctrl/consumer.h> @@ -1936,36 +1934,6 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, slave->port_vlan = data->dual_emac_res_vlan; } -#define AM33XX_CTRL_MAC_LO_REG(id) (0x630 + 0x8 * id) -#define AM33XX_CTRL_MAC_HI_REG(id) (0x630 + 0x8 * id + 0x4) - -static int cpsw_am33xx_cm_get_macid(struct device *dev, int slave, - u8 *mac_addr) -{ - u32 macid_lo; - u32 macid_hi; - struct regmap *syscon; - - syscon = syscon_regmap_lookup_by_phandle(dev->of_node, "syscon"); - if (IS_ERR(syscon)) { - if (PTR_ERR(syscon) == -ENODEV) - return 0; - return PTR_ERR(syscon); - } - - regmap_read(syscon, AM33XX_CTRL_MAC_LO_REG(slave), &macid_lo); - regmap_read(syscon, AM33XX_CTRL_MAC_HI_REG(slave), &macid_hi); - - mac_addr[5] = (macid_lo >> 8) & 0xff; - mac_addr[4] = macid_lo & 0xff; - mac_addr[3] = (macid_hi >> 24) & 0xff; - mac_addr[2] = (macid_hi >> 16) & 0xff; - mac_addr[1] = (macid_hi >> 8) & 0xff; - mac_addr[0] = macid_hi & 0xff; - - return 0; -} - static int cpsw_probe_dt(struct cpsw_platform_data *data, struct platform_device *pdev) { @@ -2090,7 +2058,8 @@ no_phy_slave: memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); } else { if (of_machine_is_compatible("ti,am33xx")) { - ret = cpsw_am33xx_cm_get_macid(&pdev->dev, i, + ret = cpsw_am33xx_cm_get_macid(&pdev->dev, + 0x630, i, slave_data->mac_addr); if (ret) return ret; diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h index 1b710674630c..ca90efafd156 100644 --- a/drivers/net/ethernet/ti/cpsw.h +++ b/drivers/net/ethernet/ti/cpsw.h @@ -41,5 +41,7 @@ struct cpsw_platform_data { }; void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave); +int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, + u8 *mac_addr); #endif /* __CPSW_H__ */ diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 5246b3a18ff8..6e927b4583aa 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -13,6 +13,7 @@ * GNU General Public License for more details. */ #include <linux/kernel.h> +#include <linux/module.h> #include <linux/platform_device.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -146,7 +147,7 @@ static int cpsw_ale_write(struct cpsw_ale *ale, int idx, u32 *ale_entry) return idx; } -int cpsw_ale_match_addr(struct cpsw_ale *ale, u8 *addr, u16 vid) +static int cpsw_ale_match_addr(struct cpsw_ale *ale, u8 *addr, u16 vid) { u32 ale_entry[ALE_ENTRY_WORDS]; int type, idx; @@ -167,7 +168,7 @@ int cpsw_ale_match_addr(struct cpsw_ale *ale, u8 *addr, u16 vid) return -ENOENT; } -int cpsw_ale_match_vlan(struct cpsw_ale *ale, u16 vid) +static int cpsw_ale_match_vlan(struct cpsw_ale *ale, u16 vid) { u32 ale_entry[ALE_ENTRY_WORDS]; int type, idx; @@ -265,6 +266,7 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) } return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_flush_multicast); static void cpsw_ale_flush_ucast(struct cpsw_ale *ale, u32 *ale_entry, int port_mask) @@ -297,6 +299,7 @@ int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask) } return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_flush); static inline void cpsw_ale_set_vlan_entry_type(u32 *ale_entry, int flags, u16 vid) @@ -334,6 +337,7 @@ int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_add_ucast); int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port, int flags, u16 vid) @@ -349,6 +353,7 @@ int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_del_ucast); int cpsw_ale_add_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, int flags, u16 vid, int mcast_state) @@ -380,6 +385,7 @@ int cpsw_ale_add_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_add_mcast); int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, int flags, u16 vid) @@ -401,6 +407,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_del_mcast); int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port, int untag, int reg_mcast, int unreg_mcast) @@ -430,6 +437,7 @@ int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port, int untag, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_add_vlan); int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) { @@ -450,6 +458,7 @@ int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_del_vlan); void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti) { @@ -479,6 +488,7 @@ void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti) cpsw_ale_write(ale, idx, ale_entry); } } +EXPORT_SYMBOL_GPL(cpsw_ale_set_allmulti); struct ale_control_info { const char *name; @@ -704,6 +714,7 @@ int cpsw_ale_control_set(struct cpsw_ale *ale, int port, int control, return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_control_set); int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control) { @@ -727,6 +738,7 @@ int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control) tmp = __raw_readl(ale->params.ale_regs + offset) >> shift; return tmp & BITMASK(info->bits); } +EXPORT_SYMBOL_GPL(cpsw_ale_control_get); static void cpsw_ale_timer(unsigned long arg) { @@ -750,6 +762,7 @@ int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout) } return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_set_ageout); void cpsw_ale_start(struct cpsw_ale *ale) { @@ -769,11 +782,13 @@ void cpsw_ale_start(struct cpsw_ale *ale) add_timer(&ale->timer); } } +EXPORT_SYMBOL_GPL(cpsw_ale_start); void cpsw_ale_stop(struct cpsw_ale *ale) { del_timer_sync(&ale->timer); } +EXPORT_SYMBOL_GPL(cpsw_ale_stop); struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params) { @@ -788,6 +803,7 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params) return ale; } +EXPORT_SYMBOL_GPL(cpsw_ale_create); int cpsw_ale_destroy(struct cpsw_ale *ale) { @@ -797,6 +813,7 @@ int cpsw_ale_destroy(struct cpsw_ale *ale) kfree(ale); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_destroy); void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data) { @@ -807,3 +824,8 @@ void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data) data += ALE_ENTRY_WORDS; } } +EXPORT_SYMBOL_GPL(cpsw_ale_dump); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("TI CPSW ALE driver"); +MODULE_AUTHOR("Texas Instruments"); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 5fae4354722c..aeebc0a7bf47 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -52,6 +52,7 @@ #include <linux/dma-mapping.h> #include <linux/clk.h> #include <linux/platform_device.h> +#include <linux/regmap.h> #include <linux/semaphore.h> #include <linux/phy.h> #include <linux/bitops.h> @@ -65,10 +66,12 @@ #include <linux/of_mdio.h> #include <linux/of_irq.h> #include <linux/of_net.h> +#include <linux/mfd/syscon.h> #include <asm/irq.h> #include <asm/page.h> +#include "cpsw.h" #include "davinci_cpdma.h" static int debug_level; @@ -1838,7 +1841,7 @@ davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv) if (!is_valid_ether_addr(pdata->mac_addr)) { mac_addr = of_get_mac_address(np); if (mac_addr) - memcpy(pdata->mac_addr, mac_addr, ETH_ALEN); + ether_addr_copy(pdata->mac_addr, mac_addr); } of_property_read_u32(np, "ti,davinci-ctrl-reg-offset", @@ -1879,6 +1882,53 @@ davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv) return pdata; } +static int davinci_emac_3517_get_macid(struct device *dev, u16 offset, + int slave, u8 *mac_addr) +{ + u32 macid_lsb; + u32 macid_msb; + struct regmap *syscon; + + syscon = syscon_regmap_lookup_by_phandle(dev->of_node, "syscon"); + if (IS_ERR(syscon)) { + if (PTR_ERR(syscon) == -ENODEV) + return 0; + return PTR_ERR(syscon); + } + + regmap_read(syscon, offset, &macid_lsb); + regmap_read(syscon, offset + 4, &macid_msb); + + mac_addr[0] = (macid_msb >> 16) & 0xff; + mac_addr[1] = (macid_msb >> 8) & 0xff; + mac_addr[2] = macid_msb & 0xff; + mac_addr[3] = (macid_lsb >> 16) & 0xff; + mac_addr[4] = (macid_lsb >> 8) & 0xff; + mac_addr[5] = macid_lsb & 0xff; + + return 0; +} + +static int davinci_emac_try_get_mac(struct platform_device *pdev, + int instance, u8 *mac_addr) +{ + int error = -EINVAL; + + if (!pdev->dev.of_node) + return error; + + if (of_device_is_compatible(pdev->dev.of_node, "ti,am3517-emac")) + error = davinci_emac_3517_get_macid(&pdev->dev, 0x110, + 0, mac_addr); + else if (of_device_is_compatible(pdev->dev.of_node, + "ti,dm816-emac")) + error = cpsw_am33xx_cm_get_macid(&pdev->dev, 0x30, + instance, + mac_addr); + + return error; +} + /** * davinci_emac_probe - EMAC device probe * @pdev: The DaVinci EMAC device that we are removing @@ -2009,6 +2059,10 @@ static int davinci_emac_probe(struct platform_device *pdev) } ndev->irq = res->start; + rc = davinci_emac_try_get_mac(pdev, res_ctrl ? 0 : 1, priv->mac_addr); + if (!rc) + ether_addr_copy(ndev->dev_addr, priv->mac_addr); + if (!is_valid_ether_addr(priv->mac_addr)) { /* Use random MAC if none passed */ eth_hw_addr_random(ndev); diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index ba3002ec710a..a31a8c3c8e7c 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -354,6 +354,7 @@ fail: netcp_unregister_module(module); return ret; } +EXPORT_SYMBOL_GPL(netcp_register_module); static void netcp_release_module(struct netcp_device *netcp_device, struct netcp_module *module) @@ -414,6 +415,7 @@ void netcp_unregister_module(struct netcp_module *module) mutex_unlock(&netcp_modules_lock); } +EXPORT_SYMBOL_GPL(netcp_unregister_module); void *netcp_module_get_intf_data(struct netcp_module *module, struct netcp_intf *intf) @@ -425,6 +427,7 @@ void *netcp_module_get_intf_data(struct netcp_module *module, return intf_modpriv->module_priv; return NULL; } +EXPORT_SYMBOL_GPL(netcp_module_get_intf_data); /* Module TX and RX Hook management */ struct netcp_hook_list { @@ -459,6 +462,7 @@ int netcp_register_txhook(struct netcp_intf *netcp_priv, int order, return 0; } +EXPORT_SYMBOL_GPL(netcp_register_txhook); int netcp_unregister_txhook(struct netcp_intf *netcp_priv, int order, netcp_hook_rtn *hook_rtn, void *hook_data) @@ -480,6 +484,7 @@ int netcp_unregister_txhook(struct netcp_intf *netcp_priv, int order, spin_unlock_irqrestore(&netcp_priv->lock, flags); return -ENOENT; } +EXPORT_SYMBOL_GPL(netcp_unregister_txhook); int netcp_register_rxhook(struct netcp_intf *netcp_priv, int order, netcp_hook_rtn *hook_rtn, void *hook_data) @@ -1226,6 +1231,7 @@ int netcp_txpipe_close(struct netcp_tx_pipe *tx_pipe) } return 0; } +EXPORT_SYMBOL_GPL(netcp_txpipe_close); int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) { @@ -1267,6 +1273,7 @@ err: tx_pipe->dma_channel = NULL; return ret; } +EXPORT_SYMBOL_GPL(netcp_txpipe_open); int netcp_txpipe_init(struct netcp_tx_pipe *tx_pipe, struct netcp_device *netcp_device, @@ -1278,6 +1285,7 @@ int netcp_txpipe_init(struct netcp_tx_pipe *tx_pipe, tx_pipe->dma_queue_id = dma_queue_id; return 0; } +EXPORT_SYMBOL_GPL(netcp_txpipe_init); static struct netcp_addr *netcp_addr_find(struct netcp_intf *netcp, const u8 *addr, diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index fa1041a78b46..84f5ce525750 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -19,6 +19,7 @@ */ #include <linux/io.h> +#include <linux/module.h> #include <linux/of_mdio.h> #include <linux/of_address.h> #include <linux/if_vlan.h> @@ -2010,12 +2011,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, quit: if (gbe_dev->hw_stats) devm_kfree(dev, gbe_dev->hw_stats); - if (gbe_dev->ale) - cpsw_ale_destroy(gbe_dev->ale); + cpsw_ale_destroy(gbe_dev->ale); if (gbe_dev->ss_regs) devm_iounmap(dev, gbe_dev->ss_regs); - if (interfaces) - of_node_put(interfaces); + of_node_put(interfaces); devm_kfree(dev, gbe_dev); return ret; } @@ -2154,3 +2153,7 @@ static void __exit keystone_gbe_exit(void) netcp_unregister_module(&xgbe_module); } module_exit(keystone_gbe_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("TI NETCP ETHSS driver for Keystone SOCs"); +MODULE_AUTHOR("Sandeep Nair <sandeep_n@ti.com"); diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index f2ff0074aac9..691ec936e88d 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -2540,7 +2540,7 @@ static void tlan_phy_power_down(struct net_device *dev) * This is abitrary. It is intended to make sure the * transceiver settles. */ - tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_PUP); + tlan_set_timer(dev, msecs_to_jiffies(50), TLAN_TIMER_PHY_PUP); } @@ -2561,7 +2561,7 @@ static void tlan_phy_power_up(struct net_device *dev) * transceiver. The TLAN docs say both 50 ms and * 500 ms, so do the longer, just in case. */ - tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_RESET); + tlan_set_timer(dev, msecs_to_jiffies(500), TLAN_TIMER_PHY_RESET); } @@ -2593,7 +2593,7 @@ static void tlan_phy_reset(struct net_device *dev) * I don't remember why I wait this long. * I've changed this to 50ms, as it seems long enough. */ - tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_START_LINK); + tlan_set_timer(dev, msecs_to_jiffies(50), TLAN_TIMER_PHY_START_LINK); } @@ -2658,7 +2658,7 @@ static void tlan_phy_start_link(struct net_device *dev) data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, data); - tlan_set_timer(dev, (40*HZ/1000), TLAN_TIMER_PHY_PDOWN); + tlan_set_timer(dev, msecs_to_jiffies(40), TLAN_TIMER_PHY_PDOWN); return; } else if (priv->phy_num == 0) { control = 0; @@ -2725,7 +2725,7 @@ static void tlan_phy_finish_auto_neg(struct net_device *dev) (priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10) && (priv->phy_num != 0)) { priv->phy_num = 0; - tlan_set_timer(dev, (400*HZ/1000), TLAN_TIMER_PHY_PDOWN); + tlan_set_timer(dev, msecs_to_jiffies(400), TLAN_TIMER_PHY_PDOWN); return; } @@ -2744,7 +2744,7 @@ static void tlan_phy_finish_auto_neg(struct net_device *dev) /* Wait for 100 ms. No reason in partiticular. */ - tlan_set_timer(dev, (HZ/10), TLAN_TIMER_FINISH_RESET); + tlan_set_timer(dev, msecs_to_jiffies(100), TLAN_TIMER_FINISH_RESET); } @@ -2796,7 +2796,7 @@ static void tlan_phy_monitor(unsigned long data) /* set to external PHY */ priv->phy_num = 1; /* restart autonegotiation */ - tlan_set_timer(dev, 4 * HZ / 10, + tlan_set_timer(dev, msecs_to_jiffies(400), TLAN_TIMER_PHY_PDOWN); return; } diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d2af032ff225..208eb05446ba 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -685,9 +685,9 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device) return ret_val; } -u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device, - unsigned int section_index, - struct hv_netvsc_packet *packet) +static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device, + unsigned int section_index, + struct hv_netvsc_packet *packet) { char *start = net_device->send_buf; char *dest = (start + (section_index * net_device->send_section_size)); @@ -717,7 +717,7 @@ int netvsc_send(struct hv_device *device, u64 req_id; unsigned int section_index = NETVSC_INVALID_INDEX; u32 msg_size = 0; - struct sk_buff *skb; + struct sk_buff *skb = NULL; u16 q_idx = packet->q_idx; @@ -744,8 +744,6 @@ int netvsc_send(struct hv_device *device, packet); skb = (struct sk_buff *) (unsigned long)packet->send_completion_tid; - if (skb) - dev_kfree_skb_any(skb); packet->page_buf_cnt = 0; } } @@ -811,6 +809,13 @@ int netvsc_send(struct hv_device *device, packet, ret); } + if (ret != 0) { + if (section_index != NETVSC_INVALID_INDEX) + netvsc_free_send_slot(net_device, section_index); + } else if (skb) { + dev_kfree_skb_any(skb); + } + return ret; } diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 7bd83870b2a7..7816d98bdddc 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -624,7 +624,8 @@ cleanup: return ret; } -int rndis_filter_set_offload_params(struct hv_device *hdev, +static int +rndis_filter_set_offload_params(struct hv_device *hdev, struct ndis_offload_params *req_offloads) { struct netvsc_device *nvdev = hv_get_drvdata(hdev); @@ -699,7 +700,7 @@ u8 netvsc_hash_key[HASH_KEYLEN] = { 0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa }; -int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue) +static int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue) { struct net_device *ndev = rdev->net_dev->ndev; struct rndis_request *request; diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index a43c8acb7268..181b349b060e 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -44,9 +44,9 @@ #define CC2520_FREG_MASK 0x3F /* status byte values */ -#define CC2520_STATUS_XOSC32M_STABLE (1 << 7) -#define CC2520_STATUS_RSSI_VALID (1 << 6) -#define CC2520_STATUS_TX_UNDERFLOW (1 << 3) +#define CC2520_STATUS_XOSC32M_STABLE BIT(7) +#define CC2520_STATUS_RSSI_VALID BIT(6) +#define CC2520_STATUS_TX_UNDERFLOW BIT(3) /* IEEE-802.15.4 defined constants (2.4 GHz logical channels) */ #define CC2520_MINCHANNEL 11 @@ -549,14 +549,14 @@ cc2520_ed(struct ieee802154_hw *hw, u8 *level) u8 rssi; int ret; - ret = cc2520_read_register(priv , CC2520_RSSISTAT, &status); + ret = cc2520_read_register(priv, CC2520_RSSISTAT, &status); if (ret) return ret; if (status != RSSI_VALID) return -EINVAL; - ret = cc2520_read_register(priv , CC2520_RSSI, &rssi); + ret = cc2520_read_register(priv, CC2520_RSSI, &rssi); if (ret) return ret; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2e195289ddf4..2a175006028b 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -9,7 +9,7 @@ #include "ipvlan.h" -static u32 ipvlan_jhash_secret; +static u32 ipvlan_jhash_secret __read_mostly; void ipvlan_init_secret(void) { diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index d0ed5694dd7d..e40fdfccc9c1 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -17,7 +17,6 @@ #include <linux/fs.h> #include <linux/uio.h> -#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> @@ -81,7 +80,7 @@ static struct cdev macvtap_cdev; static const struct proto_ops macvtap_socket_ops; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ - NETIF_F_TSO6) + NETIF_F_TSO6 | NETIF_F_UFO) #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) @@ -586,11 +585,7 @@ static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q, gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n", - current->comm); gso_type = SKB_GSO_UDP; - if (skb->protocol == htons(ETH_P_IPV6)) - ipv6_proxy_select_ident(skb); break; default: return -EINVAL; @@ -636,6 +631,8 @@ static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q, vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (sinfo->gso_type & SKB_GSO_TCP_ECN) @@ -965,6 +962,9 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) if (arg & TUN_F_TSO6) feature_mask |= NETIF_F_TSO6; } + + if (arg & TUN_F_UFO) + feature_mask |= NETIF_F_UFO; } /* tun/tap driver inverts the usage for TSO offloads, where @@ -975,7 +975,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) * When user space turns off TSO, we turn off GSO/LRO so that * user-space will not receive TSO frames. */ - if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6)) + if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO)) features |= RX_OFFLOADS; else features &= ~RX_OFFLOADS; @@ -1090,7 +1090,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN)) + TUN_F_TSO_ECN | TUN_F_UFO)) return -EINVAL; rtnl_lock(); diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c index 602c625d95d5..b5edc7f96a39 100644 --- a/drivers/net/ppp/ppp_deflate.c +++ b/drivers/net/ppp/ppp_deflate.c @@ -246,7 +246,7 @@ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf, /* * See if we managed to reduce the size of the packet. */ - if (olen < isize) { + if (olen < isize && olen <= osize) { state->stats.comp_bytes += olen; state->stats.comp_packets++; } else { diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 4b2bfc52c52f..0e62274e884a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -28,6 +28,7 @@ #include <net/genetlink.h> #include <net/netlink.h> #include <net/sch_generic.h> +#include <net/switchdev.h> #include <generated/utsrelease.h> #include <linux/if_team.h> @@ -1925,7 +1926,7 @@ static netdev_features_t team_fix_features(struct net_device *dev, struct team *team = netdev_priv(dev); netdev_features_t mask; - mask = features; + mask = features | NETIF_F_HW_SWITCH_OFFLOAD; features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; @@ -1975,6 +1976,8 @@ static const struct net_device_ops team_netdev_ops = { .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, + .ndo_bridge_setlink = ndo_dflt_netdev_switch_port_bridge_setlink, + .ndo_bridge_dellink = ndo_dflt_netdev_switch_port_bridge_dellink, }; /*********************** diff --git a/drivers/net/tun.c b/drivers/net/tun.c index be196e89ab6c..ad7d3d5f3ee5 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -65,7 +65,6 @@ #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> -#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> @@ -186,7 +185,7 @@ struct tun_struct { struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ - NETIF_F_TSO6) + NETIF_F_TSO6|NETIF_F_UFO) int vnet_hdr_sz; int sndbuf; @@ -1166,8 +1165,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; } - skb_reset_network_header(skb); - if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -1178,20 +1175,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - { - static bool warned; - - if (!warned) { - warned = true; - netdev_warn(tun->dev, - "%s: using disabled UFO feature; please fix this program\n", - current->comm); - } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - if (skb->protocol == htons(ETH_P_IPV6)) - ipv6_proxy_select_ident(skb); break; - } default: tun->dev->stats.rx_frame_errors++; kfree_skb(skb); @@ -1220,6 +1205,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } + skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); rxhash = skb_get_hash(skb); @@ -1297,6 +1283,8 @@ static ssize_t tun_put_user(struct tun_struct *tun, gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + gso.gso_type = VIRTIO_NET_HDR_GSO_UDP; else { pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", @@ -1565,6 +1553,17 @@ static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL); static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL); static DEVICE_ATTR(group, 0444, tun_show_group, NULL); +static struct attribute *tun_dev_attrs[] = { + &dev_attr_tun_flags.attr, + &dev_attr_owner.attr, + &dev_attr_group.attr, + NULL +}; + +static const struct attribute_group tun_attr_group = { + .attrs = tun_dev_attrs +}; + static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) { struct tun_struct *tun; @@ -1645,6 +1644,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; + dev->sysfs_groups[0] = &tun_attr_group; tun = netdev_priv(dev); tun->dev = dev; @@ -1680,11 +1680,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) err = register_netdevice(tun->dev); if (err < 0) goto err_detach; - - if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) || - device_create_file(&tun->dev->dev, &dev_attr_owner) || - device_create_file(&tun->dev->dev, &dev_attr_group)) - pr_err("Failed to create tun sysfs files\n"); } netif_carrier_on(tun->dev); @@ -1745,6 +1740,11 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } + + if (arg & TUN_F_UFO) { + features |= NETIF_F_UFO; + arg &= ~TUN_F_UFO; + } } /* This gives the user a way to test for new features in future by diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 9c5aa922a9f4..6b8efcabb816 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -58,7 +58,6 @@ #include <linux/module.h> #include <linux/ethtool.h> #include <linux/usb.h> -#include <linux/timer.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> @@ -154,6 +153,7 @@ struct hso_net { struct hso_device *parent; struct net_device *net; struct rfkill *rfkill; + char name[24]; struct usb_endpoint_descriptor *in_endp; struct usb_endpoint_descriptor *out_endp; @@ -274,7 +274,6 @@ struct hso_device { u8 usb_gone; struct work_struct async_get_intf; struct work_struct async_put_intf; - struct work_struct reset_device; struct usb_device *usb; struct usb_interface *interface; @@ -340,7 +339,6 @@ static void async_put_intf(struct work_struct *data); static int hso_put_activity(struct hso_device *hso_dev); static int hso_get_activity(struct hso_device *hso_dev); static void tiocmget_intr_callback(struct urb *urb); -static void reset_device(struct work_struct *data); /*****************************************************************************/ /* Helping functions */ /*****************************************************************************/ @@ -533,6 +531,13 @@ static ssize_t hso_sysfs_show_porttype(struct device *dev, } static DEVICE_ATTR(hsotype, S_IRUGO, hso_sysfs_show_porttype, NULL); +static struct attribute *hso_serial_dev_attrs[] = { + &dev_attr_hsotype.attr, + NULL +}; + +ATTRIBUTE_GROUPS(hso_serial_dev); + static int hso_urb_to_index(struct hso_serial *serial, struct urb *urb) { int idx; @@ -696,7 +701,7 @@ static void handle_usb_error(int status, const char *function, case -ETIMEDOUT: explanation = "protocol error"; if (hso_dev) - schedule_work(&hso_dev->reset_device); + usb_queue_reset_device(hso_dev->interface); break; default: explanation = "unknown status"; @@ -1271,7 +1276,6 @@ static int hso_serial_open(struct tty_struct *tty, struct file *filp) goto err_out; D1("Opening %d", serial->minor); - kref_get(&serial->parent->ref); /* setup */ tty->driver_data = serial; @@ -1290,7 +1294,8 @@ static int hso_serial_open(struct tty_struct *tty, struct file *filp) if (result) { hso_stop_serial_device(serial->parent); serial->port.count--; - kref_put(&serial->parent->ref, hso_serial_ref_free); + } else { + kref_get(&serial->parent->ref); } } else { D1("Port was already open"); @@ -1340,8 +1345,6 @@ static void hso_serial_close(struct tty_struct *tty, struct file *filp) usb_autopm_put_interface(serial->parent->interface); mutex_unlock(&serial->parent->mutex); - - kref_put(&serial->parent->ref, hso_serial_ref_free); } /* close the requested serial port */ @@ -1392,6 +1395,16 @@ static int hso_serial_write_room(struct tty_struct *tty) return room; } +static void hso_serial_cleanup(struct tty_struct *tty) +{ + struct hso_serial *serial = tty->driver_data; + + if (!serial) + return; + + kref_put(&serial->parent->ref, hso_serial_ref_free); +} + /* setup the term */ static void hso_serial_set_termios(struct tty_struct *tty, struct ktermios *old) { @@ -2198,8 +2211,8 @@ static int hso_stop_serial_device(struct hso_device *hso_dev) for (i = 0; i < serial->num_rx_urbs; i++) { if (serial->rx_urb[i]) { - usb_kill_urb(serial->rx_urb[i]); - serial->rx_urb_filled[i] = 0; + usb_kill_urb(serial->rx_urb[i]); + serial->rx_urb_filled[i] = 0; } } serial->curr_rx_urb_idx = 0; @@ -2228,15 +2241,15 @@ static int hso_stop_serial_device(struct hso_device *hso_dev) return 0; } +static void hso_serial_tty_unregister(struct hso_serial *serial) +{ + tty_unregister_device(tty_drv, serial->minor); +} + static void hso_serial_common_free(struct hso_serial *serial) { int i; - if (serial->parent->dev) - device_remove_file(serial->parent->dev, &dev_attr_hsotype); - - tty_unregister_device(tty_drv, serial->minor); - for (i = 0; i < serial->num_rx_urbs; i++) { /* unlink and free RX URB */ usb_free_urb(serial->rx_urb[i]); @@ -2246,6 +2259,7 @@ static void hso_serial_common_free(struct hso_serial *serial) /* unlink and free TX URB */ usb_free_urb(serial->tx_urb); + kfree(serial->tx_buffer); kfree(serial->tx_data); tty_port_destroy(&serial->port); } @@ -2264,11 +2278,10 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, goto exit; /* register our minor number */ - serial->parent->dev = tty_port_register_device(&serial->port, tty_drv, - minor, &serial->parent->interface->dev); + serial->parent->dev = tty_port_register_device_attr(&serial->port, + tty_drv, minor, &serial->parent->interface->dev, + serial->parent, hso_serial_dev_groups); dev = serial->parent->dev; - dev_set_drvdata(dev, serial->parent); - i = device_create_file(dev, &dev_attr_hsotype); /* fill in specific data for later use */ serial->minor = minor; @@ -2316,6 +2329,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, return 0; exit: + hso_serial_tty_unregister(serial); hso_serial_common_free(serial); return -1; } @@ -2338,7 +2352,6 @@ static struct hso_device *hso_create_device(struct usb_interface *intf, INIT_WORK(&hso_dev->async_get_intf, async_get_intf); INIT_WORK(&hso_dev->async_put_intf, async_put_intf); - INIT_WORK(&hso_dev->reset_device, reset_device); return hso_dev; } @@ -2459,27 +2472,21 @@ static void hso_create_rfkill(struct hso_device *hso_dev, { struct hso_net *hso_net = dev2net(hso_dev); struct device *dev = &hso_net->net->dev; - char *rfkn; + static u32 rfkill_counter; - rfkn = kzalloc(20, GFP_KERNEL); - if (!rfkn) - dev_err(dev, "%s - Out of memory\n", __func__); - - snprintf(rfkn, 20, "hso-%d", - interface->altsetting->desc.bInterfaceNumber); + snprintf(hso_net->name, sizeof(hso_net->name), "hso-%d", + rfkill_counter++); - hso_net->rfkill = rfkill_alloc(rfkn, + hso_net->rfkill = rfkill_alloc(hso_net->name, &interface_to_usbdev(interface)->dev, RFKILL_TYPE_WWAN, &hso_rfkill_ops, hso_dev); if (!hso_net->rfkill) { dev_err(dev, "%s - Out of memory\n", __func__); - kfree(rfkn); return; } if (rfkill_register(hso_net->rfkill) < 0) { rfkill_destroy(hso_net->rfkill); - kfree(rfkn); hso_net->rfkill = NULL; dev_err(dev, "%s - Failed to register rfkill\n", __func__); return; @@ -2594,7 +2601,6 @@ static void hso_free_serial_device(struct hso_device *hso_dev) if (!serial) return; - set_serial_by_index(serial->minor, NULL); hso_serial_common_free(serial); @@ -2684,6 +2690,7 @@ static struct hso_device *hso_create_bulk_serial_device( return hso_dev; exit2: + hso_serial_tty_unregister(serial); hso_serial_common_free(serial); exit: hso_free_tiomget(serial); @@ -3083,26 +3090,6 @@ out: return result; } -static void reset_device(struct work_struct *data) -{ - struct hso_device *hso_dev = - container_of(data, struct hso_device, reset_device); - struct usb_device *usb = hso_dev->usb; - int result; - - if (hso_dev->usb_gone) { - D1("No reset during disconnect\n"); - } else { - result = usb_lock_device_for_reset(usb, hso_dev->interface); - if (result < 0) - D1("unable to lock device for reset: %d\n", result); - else { - usb_reset_device(usb); - usb_unlock_device(usb); - } - } -} - static void hso_serial_ref_free(struct kref *ref) { struct hso_device *hso_dev = container_of(ref, struct hso_device, ref); @@ -3112,18 +3099,22 @@ static void hso_serial_ref_free(struct kref *ref) static void hso_free_interface(struct usb_interface *interface) { - struct hso_serial *hso_dev; + struct hso_serial *serial; int i; for (i = 0; i < HSO_SERIAL_TTY_MINORS; i++) { if (serial_table[i] && (serial_table[i]->interface == interface)) { - hso_dev = dev2ser(serial_table[i]); - tty_port_tty_hangup(&hso_dev->port, false); - mutex_lock(&hso_dev->parent->mutex); - hso_dev->parent->usb_gone = 1; - mutex_unlock(&hso_dev->parent->mutex); + serial = dev2ser(serial_table[i]); + tty_port_tty_hangup(&serial->port, false); + mutex_lock(&serial->parent->mutex); + serial->parent->usb_gone = 1; + mutex_unlock(&serial->parent->mutex); + cancel_work_sync(&serial_table[i]->async_put_intf); + cancel_work_sync(&serial_table[i]->async_get_intf); + hso_serial_tty_unregister(serial); kref_put(&serial_table[i]->ref, hso_serial_ref_free); + set_serial_by_index(i, NULL); } } @@ -3215,6 +3206,7 @@ static const struct tty_operations hso_serial_ops = { .close = hso_serial_close, .write = hso_serial_write, .write_room = hso_serial_write_room, + .cleanup = hso_serial_cleanup, .ioctl = hso_serial_ioctl, .set_termios = hso_serial_set_termios, .chars_in_buffer = hso_serial_chars_in_buffer, diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 99b69af14274..4a1e9c489f1f 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -77,7 +77,7 @@ static int wait_phy_eeprom_ready(struct usbnet *dev, int phy) int ret; udelay(1); - ret = sr_read_reg(dev, EPCR, &tmp); + ret = sr_read_reg(dev, SR_EPCR, &tmp); if (ret < 0) return ret; @@ -98,15 +98,15 @@ static int sr_share_read_word(struct usbnet *dev, int phy, u8 reg, mutex_lock(&dev->phy_mutex); - sr_write_reg(dev, EPAR, phy ? (reg | EPAR_PHY_ADR) : reg); - sr_write_reg(dev, EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR); + sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg); + sr_write_reg(dev, SR_EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR); ret = wait_phy_eeprom_ready(dev, phy); if (ret < 0) goto out_unlock; - sr_write_reg(dev, EPCR, 0x0); - ret = sr_read(dev, EPDR, 2, value); + sr_write_reg(dev, SR_EPCR, 0x0); + ret = sr_read(dev, SR_EPDR, 2, value); netdev_dbg(dev->net, "read shared %d 0x%02x returned 0x%04x, %d\n", phy, reg, *value, ret); @@ -123,19 +123,19 @@ static int sr_share_write_word(struct usbnet *dev, int phy, u8 reg, mutex_lock(&dev->phy_mutex); - ret = sr_write(dev, EPDR, 2, &value); + ret = sr_write(dev, SR_EPDR, 2, &value); if (ret < 0) goto out_unlock; - sr_write_reg(dev, EPAR, phy ? (reg | EPAR_PHY_ADR) : reg); - sr_write_reg(dev, EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) : + sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg); + sr_write_reg(dev, SR_EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) : (EPCR_WEP | EPCR_ERPRW)); ret = wait_phy_eeprom_ready(dev, phy); if (ret < 0) goto out_unlock; - sr_write_reg(dev, EPCR, 0x0); + sr_write_reg(dev, SR_EPCR, 0x0); out_unlock: mutex_unlock(&dev->phy_mutex); @@ -188,7 +188,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) if (loc == MII_BMSR) { u8 value; - sr_read_reg(dev, NSR, &value); + sr_read_reg(dev, SR_NSR, &value); if (value & NSR_LINKST) rc = 1; } @@ -228,7 +228,7 @@ static u32 sr9700_get_link(struct net_device *netdev) int rc = 0; /* Get the Link Status directly */ - sr_read_reg(dev, NSR, &value); + sr_read_reg(dev, SR_NSR, &value); if (value & NSR_LINKST) rc = 1; @@ -281,8 +281,8 @@ static void sr9700_set_multicast(struct net_device *netdev) } } - sr_write_async(dev, MAR, SR_MCAST_SIZE, hashes); - sr_write_reg_async(dev, RCR, rx_ctl); + sr_write_async(dev, SR_MAR, SR_MCAST_SIZE, hashes); + sr_write_reg_async(dev, SR_RCR, rx_ctl); } static int sr9700_set_mac_address(struct net_device *netdev, void *p) @@ -297,7 +297,7 @@ static int sr9700_set_mac_address(struct net_device *netdev, void *p) } memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); - sr_write_async(dev, PAR, 6, netdev->dev_addr); + sr_write_async(dev, SR_PAR, 6, netdev->dev_addr); return 0; } @@ -340,7 +340,7 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf) mii->phy_id_mask = 0x1f; mii->reg_num_mask = 0x1f; - sr_write_reg(dev, NCR, NCR_RST); + sr_write_reg(dev, SR_NCR, NCR_RST); udelay(20); /* read MAC @@ -348,17 +348,17 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf) * EEPROM automatically to PAR. In case there is no EEPROM externally, * a default MAC address is stored in PAR for making chip work properly. */ - if (sr_read(dev, PAR, ETH_ALEN, netdev->dev_addr) < 0) { + if (sr_read(dev, SR_PAR, ETH_ALEN, netdev->dev_addr) < 0) { netdev_err(netdev, "Error reading MAC address\n"); ret = -ENODEV; goto out; } /* power up and reset phy */ - sr_write_reg(dev, PRR, PRR_PHY_RST); + sr_write_reg(dev, SR_PRR, PRR_PHY_RST); /* at least 10ms, here 20ms for safe */ mdelay(20); - sr_write_reg(dev, PRR, 0); + sr_write_reg(dev, SR_PRR, 0); /* at least 1ms, here 2ms for reading right register */ udelay(2 * 1000); diff --git a/drivers/net/usb/sr9700.h b/drivers/net/usb/sr9700.h index fd687c575e74..258b030277e7 100644 --- a/drivers/net/usb/sr9700.h +++ b/drivers/net/usb/sr9700.h @@ -14,13 +14,13 @@ /* sr9700 spec. register table on Linux platform */ /* Network Control Reg */ -#define NCR 0x00 +#define SR_NCR 0x00 #define NCR_RST (1 << 0) #define NCR_LBK (3 << 1) #define NCR_FDX (1 << 3) #define NCR_WAKEEN (1 << 6) /* Network Status Reg */ -#define NSR 0x01 +#define SR_NSR 0x01 #define NSR_RXRDY (1 << 0) #define NSR_RXOV (1 << 1) #define NSR_TX1END (1 << 2) @@ -30,7 +30,7 @@ #define NSR_LINKST (1 << 6) #define NSR_SPEED (1 << 7) /* Tx Control Reg */ -#define TCR 0x02 +#define SR_TCR 0x02 #define TCR_CRC_DIS (1 << 1) #define TCR_PAD_DIS (1 << 2) #define TCR_LC_CARE (1 << 3) @@ -38,7 +38,7 @@ #define TCR_EXCECM (1 << 5) #define TCR_LF_EN (1 << 6) /* Tx Status Reg for Packet Index 1 */ -#define TSR1 0x03 +#define SR_TSR1 0x03 #define TSR1_EC (1 << 2) #define TSR1_COL (1 << 3) #define TSR1_LC (1 << 4) @@ -46,7 +46,7 @@ #define TSR1_LOC (1 << 6) #define TSR1_TLF (1 << 7) /* Tx Status Reg for Packet Index 2 */ -#define TSR2 0x04 +#define SR_TSR2 0x04 #define TSR2_EC (1 << 2) #define TSR2_COL (1 << 3) #define TSR2_LC (1 << 4) @@ -54,7 +54,7 @@ #define TSR2_LOC (1 << 6) #define TSR2_TLF (1 << 7) /* Rx Control Reg*/ -#define RCR 0x05 +#define SR_RCR 0x05 #define RCR_RXEN (1 << 0) #define RCR_PRMSC (1 << 1) #define RCR_RUNT (1 << 2) @@ -62,87 +62,87 @@ #define RCR_DIS_CRC (1 << 4) #define RCR_DIS_LONG (1 << 5) /* Rx Status Reg */ -#define RSR 0x06 +#define SR_RSR 0x06 #define RSR_AE (1 << 2) #define RSR_MF (1 << 6) #define RSR_RF (1 << 7) /* Rx Overflow Counter Reg */ -#define ROCR 0x07 +#define SR_ROCR 0x07 #define ROCR_ROC (0x7F << 0) #define ROCR_RXFU (1 << 7) /* Back Pressure Threshold Reg */ -#define BPTR 0x08 +#define SR_BPTR 0x08 #define BPTR_JPT (0x0F << 0) #define BPTR_BPHW (0x0F << 4) /* Flow Control Threshold Reg */ -#define FCTR 0x09 +#define SR_FCTR 0x09 #define FCTR_LWOT (0x0F << 0) #define FCTR_HWOT (0x0F << 4) /* rx/tx Flow Control Reg */ -#define FCR 0x0A +#define SR_FCR 0x0A #define FCR_FLCE (1 << 0) #define FCR_BKPA (1 << 4) #define FCR_TXPEN (1 << 5) #define FCR_TXPF (1 << 6) #define FCR_TXP0 (1 << 7) /* Eeprom & Phy Control Reg */ -#define EPCR 0x0B +#define SR_EPCR 0x0B #define EPCR_ERRE (1 << 0) #define EPCR_ERPRW (1 << 1) #define EPCR_ERPRR (1 << 2) #define EPCR_EPOS (1 << 3) #define EPCR_WEP (1 << 4) /* Eeprom & Phy Address Reg */ -#define EPAR 0x0C +#define SR_EPAR 0x0C #define EPAR_EROA (0x3F << 0) #define EPAR_PHY_ADR_MASK (0x03 << 6) #define EPAR_PHY_ADR (0x01 << 6) /* Eeprom & Phy Data Reg */ -#define EPDR 0x0D /* 0x0D ~ 0x0E for Data Reg Low & High */ +#define SR_EPDR 0x0D /* 0x0D ~ 0x0E for Data Reg Low & High */ /* Wakeup Control Reg */ -#define WCR 0x0F +#define SR_WCR 0x0F #define WCR_MAGICST (1 << 0) #define WCR_LINKST (1 << 2) #define WCR_MAGICEN (1 << 3) #define WCR_LINKEN (1 << 5) /* Physical Address Reg */ -#define PAR 0x10 /* 0x10 ~ 0x15 6 bytes for PAR */ +#define SR_PAR 0x10 /* 0x10 ~ 0x15 6 bytes for PAR */ /* Multicast Address Reg */ -#define MAR 0x16 /* 0x16 ~ 0x1D 8 bytes for MAR */ +#define SR_MAR 0x16 /* 0x16 ~ 0x1D 8 bytes for MAR */ /* 0x1e unused */ /* Phy Reset Reg */ -#define PRR 0x1F +#define SR_PRR 0x1F #define PRR_PHY_RST (1 << 0) /* Tx sdram Write Pointer Address Low */ -#define TWPAL 0x20 +#define SR_TWPAL 0x20 /* Tx sdram Write Pointer Address High */ -#define TWPAH 0x21 +#define SR_TWPAH 0x21 /* Tx sdram Read Pointer Address Low */ -#define TRPAL 0x22 +#define SR_TRPAL 0x22 /* Tx sdram Read Pointer Address High */ -#define TRPAH 0x23 +#define SR_TRPAH 0x23 /* Rx sdram Write Pointer Address Low */ -#define RWPAL 0x24 +#define SR_RWPAL 0x24 /* Rx sdram Write Pointer Address High */ -#define RWPAH 0x25 +#define SR_RWPAH 0x25 /* Rx sdram Read Pointer Address Low */ -#define RRPAL 0x26 +#define SR_RRPAL 0x26 /* Rx sdram Read Pointer Address High */ -#define RRPAH 0x27 +#define SR_RRPAH 0x27 /* Vendor ID register */ -#define VID 0x28 /* 0x28 ~ 0x29 2 bytes for VID */ +#define SR_VID 0x28 /* 0x28 ~ 0x29 2 bytes for VID */ /* Product ID register */ -#define PID 0x2A /* 0x2A ~ 0x2B 2 bytes for PID */ +#define SR_PID 0x2A /* 0x2A ~ 0x2B 2 bytes for PID */ /* CHIP Revision register */ -#define CHIPR 0x2C +#define SR_CHIPR 0x2C /* 0x2D --> 0xEF unused */ /* USB Device Address */ -#define USBDA 0xF0 +#define SR_USBDA 0xF0 #define USBDA_USBFA (0x7F << 0) /* RX packet Counter Reg */ -#define RXC 0xF1 +#define SR_RXC 0xF1 /* Tx packet Counter & USB Status Reg */ -#define TXC_USBS 0xF2 +#define SR_TXC_USBS 0xF2 #define TXC_USBS_TXC0 (1 << 0) #define TXC_USBS_TXC1 (1 << 1) #define TXC_USBS_TXC2 (1 << 2) @@ -150,7 +150,7 @@ #define TXC_USBS_SUSFLAG (1 << 6) #define TXC_USBS_RXFAULT (1 << 7) /* USB Control register */ -#define USBC 0xF4 +#define SR_USBC 0xF4 #define USBC_EP3NAK (1 << 4) #define USBC_EP3ACK (1 << 5) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 9bd71d53c5e0..110a2cf67244 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -490,17 +490,8 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: - { - static bool warned; - - if (!warned) { - warned = true; - netdev_warn(dev, - "host using disabled UFO feature; please fix it\n"); - } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; break; - } case VIRTIO_NET_HDR_GSO_TCPV6: skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; @@ -888,6 +879,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN) @@ -1752,7 +1745,7 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { - dev->hw_features |= NETIF_F_TSO + dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO | NETIF_F_TSO_ECN | NETIF_F_TSO6; } /* Individual feature bits: what can host handle? */ @@ -1762,11 +1755,13 @@ static int virtnet_probe(struct virtio_device *vdev) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; + if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO)) + dev->hw_features |= NETIF_F_UFO; dev->features |= NETIF_F_GSO_ROBUST; if (gso) - dev->features |= dev->hw_features & NETIF_F_ALL_TSO; + dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO); /* (!csum && gso) case will be fixed by register_netdev() */ } if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) @@ -1804,7 +1799,8 @@ static int virtnet_probe(struct virtio_device *vdev) /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) || + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) @@ -2000,9 +1996,9 @@ static struct virtio_device_id id_table[] = { static unsigned int features[] = { VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC, - VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6, + VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, - VIRTIO_NET_F_GUEST_ECN, + VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 31bac2a21ce3..e6ed3e66964d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -558,7 +558,6 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, u32 data) { size_t start, offset, plen; - __wsum delta; if (skb->remcsum_offload) return vh; @@ -580,12 +579,7 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, return NULL; } - delta = remcsum_adjust((void *)vh + hdrlen, - NAPI_GRO_CB(skb)->csum, start, offset); - - /* Adjust skb->csum since we changed the packet */ - skb->csum = csum_add(skb->csum, delta); - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + skb_gro_remcsum_process(skb, (void *)vh + hdrlen, start, offset); skb->remcsum_offload = 1; @@ -1159,7 +1153,6 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, size_t hdrlen, u32 data) { size_t start, offset, plen; - __wsum delta; if (skb->remcsum_offload) { /* Already processed in GRO path */ @@ -1179,14 +1172,7 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, vh = (struct vxlanhdr *)(udp_hdr(skb) + 1); - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) - __skb_checksum_complete(skb); - - delta = remcsum_adjust((void *)vh + hdrlen, - skb->csum, start, offset); - - /* Adjust skb->csum since we changed the packet */ - skb->csum = csum_add(skb->csum, delta); + skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset); return vh; } @@ -1681,6 +1667,9 @@ static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags, { struct vxlanhdr_gbp *gbp; + if (!md->gbp) + return; + gbp = (struct vxlanhdr_gbp *)vxh; vxh->vx_flags |= htonl(VXLAN_HF_GBP); @@ -2636,10 +2625,10 @@ static void vxlan_sock_work(struct work_struct *work) dev_put(vxlan->dev); } -static int vxlan_newlink(struct net *net, struct net_device *dev, +static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; __u32 vni; @@ -2649,7 +2638,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (!data[IFLA_VXLAN_ID]) return -EINVAL; - vxlan->net = dev_net(dev); + vxlan->net = src_net; vni = nla_get_u32(data[IFLA_VXLAN_ID]); dst->remote_vni = vni; @@ -2685,7 +2674,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (data[IFLA_VXLAN_LINK] && (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) { struct net_device *lowerdev - = __dev_get_by_index(net, dst->remote_ifindex); + = __dev_get_by_index(src_net, dst->remote_ifindex); if (!lowerdev) { pr_info("ifindex %d does not exist\n", dst->remote_ifindex); @@ -2772,7 +2761,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (data[IFLA_VXLAN_GBP]) vxlan->flags |= VXLAN_F_GBP; - if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET, + if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET, vxlan->dst_port, vxlan->flags)) { pr_info("duplicate VNI %u\n", vni); return -EEXIST; diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig index 94e234975c61..a2fdd15f285a 100644 --- a/drivers/net/wan/Kconfig +++ b/drivers/net/wan/Kconfig @@ -25,7 +25,7 @@ if WAN # There is no way to detect a comtrol sv11 - force it modular for now. config HOSTESS_SV11 tristate "Comtrol Hostess SV-11 support" - depends on ISA && m && ISA_DMA_API && INET && HDLC + depends on ISA && m && ISA_DMA_API && INET && HDLC && VIRT_TO_BUS help Driver for Comtrol Hostess SV-11 network card which operates on low speed synchronous serial links at up to @@ -37,7 +37,7 @@ config HOSTESS_SV11 # The COSA/SRP driver has not been tested as non-modular yet. config COSA tristate "COSA/SRP sync serial boards support" - depends on ISA && m && ISA_DMA_API && HDLC + depends on ISA && m && ISA_DMA_API && HDLC && VIRT_TO_BUS ---help--- Driver for COSA and SRP synchronous serial boards. @@ -87,7 +87,7 @@ config LANMEDIA # There is no way to detect a Sealevel board. Force it modular config SEALEVEL_4021 tristate "Sealevel Systems 4021 support" - depends on ISA && m && ISA_DMA_API && INET && HDLC + depends on ISA && m && ISA_DMA_API && INET && HDLC && VIRT_TO_BUS help This is a driver for the Sealevel Systems ACB 56 serial I/O adapter. diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 08f293411bf0..60a524b73207 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -76,6 +76,9 @@ static int ath10k_send_key(struct ath10k_vif *arvif, if (memcmp(macaddr, arvif->vif->addr, ETH_ALEN)) arg.key_flags = WMI_KEY_PAIRWISE; break; + case WLAN_CIPHER_SUITE_AES_CMAC: + /* this one needs to be done in software */ + return 1; default: ath10k_warn(ar, "cipher %d is not supported\n", key->cipher); return -EOPNOTSUPP; @@ -5035,6 +5038,13 @@ struct ath10k_vif *ath10k_get_arvif(struct ath10k *ar, u32 vdev_id) int ath10k_mac_register(struct ath10k *ar) { + static const u32 cipher_suites[] = { + WLAN_CIPHER_SUITE_WEP40, + WLAN_CIPHER_SUITE_WEP104, + WLAN_CIPHER_SUITE_TKIP, + WLAN_CIPHER_SUITE_CCMP, + WLAN_CIPHER_SUITE_AES_CMAC, + }; struct ieee80211_supported_band *band; struct ieee80211_sta_vht_cap vht_cap; struct ieee80211_sta_ht_cap ht_cap; @@ -5108,7 +5118,8 @@ int ath10k_mac_register(struct ath10k *ar) IEEE80211_HW_REPORTS_TX_ACK_STATUS | IEEE80211_HW_HAS_RATE_CONTROL | IEEE80211_HW_AP_LINK_PS | - IEEE80211_HW_SPECTRUM_MGMT; + IEEE80211_HW_SPECTRUM_MGMT | + IEEE80211_HW_SW_CRYPTO_CONTROL; ar->hw->wiphy->features |= NL80211_FEATURE_STATIC_SMPS; @@ -5182,6 +5193,9 @@ int ath10k_mac_register(struct ath10k *ar) goto err_free; } + ar->hw->wiphy->cipher_suites = cipher_suites; + ar->hw->wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); + ret = ieee80211_register_hw(ar->hw); if (ret) { ath10k_err(ar, "failed to register ieee80211: %d\n", ret); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 9259a732e8a4..2b2484b4cc29 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -80,7 +80,7 @@ static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -int xenvif_poll(struct napi_struct *napi, int budget) +static int xenvif_poll(struct napi_struct *napi, int budget) { struct xenvif_queue *queue = container_of(napi, struct xenvif_queue, napi); @@ -578,6 +578,7 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, goto err_rx_unbind; } queue->task = task; + get_task_struct(task); task = kthread_create(xenvif_dealloc_kthread, (void *)queue, "%s-dealloc", queue->name); @@ -634,6 +635,7 @@ void xenvif_disconnect(struct xenvif *vif) if (queue->task) { kthread_stop(queue->task); + put_task_struct(queue->task); queue->task = NULL; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 49322b6c32df..13899d5099e5 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -2008,8 +2008,7 @@ int xenvif_kthread_guest_rx(void *data) */ if (unlikely(vif->disabled && queue->id == 0)) { xenvif_carrier_off(vif); - xenvif_rx_queue_purge(queue); - continue; + break; } if (!skb_queue_empty(&queue->rx_queue)) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 7cfa6c027c0c..e9b960f0ff32 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -219,11 +219,7 @@ static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue, } #ifdef CONFIG_SYSFS -static int xennet_sysfs_addif(struct net_device *netdev); -static void xennet_sysfs_delif(struct net_device *netdev); -#else /* !CONFIG_SYSFS */ -#define xennet_sysfs_addif(dev) (0) -#define xennet_sysfs_delif(dev) do { } while (0) +static const struct attribute_group xennet_dev_group; #endif static bool xennet_can_sg(struct net_device *dev) @@ -1317,20 +1313,15 @@ static int netfront_probe(struct xenbus_device *dev, info = netdev_priv(netdev); dev_set_drvdata(&dev->dev, info); - +#ifdef CONFIG_SYSFS + info->netdev->sysfs_groups[0] = &xennet_dev_group; +#endif err = register_netdev(info->netdev); if (err) { pr_warn("%s: register_netdev err=%d\n", __func__, err); goto fail; } - err = xennet_sysfs_addif(info->netdev); - if (err) { - unregister_netdev(info->netdev); - pr_warn("%s: add sysfs failed err=%d\n", __func__, err); - goto fail; - } - return 0; fail: @@ -2094,39 +2085,20 @@ static ssize_t store_rxbuf(struct device *dev, return len; } -static struct device_attribute xennet_attrs[] = { - __ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf), - __ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf), - __ATTR(rxbuf_cur, S_IRUGO, show_rxbuf, NULL), -}; +static DEVICE_ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf); +static DEVICE_ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf, store_rxbuf); +static DEVICE_ATTR(rxbuf_cur, S_IRUGO, show_rxbuf, NULL); -static int xennet_sysfs_addif(struct net_device *netdev) -{ - int i; - int err; - - for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++) { - err = device_create_file(&netdev->dev, - &xennet_attrs[i]); - if (err) - goto fail; - } - return 0; - - fail: - while (--i >= 0) - device_remove_file(&netdev->dev, &xennet_attrs[i]); - return err; -} - -static void xennet_sysfs_delif(struct net_device *netdev) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++) - device_remove_file(&netdev->dev, &xennet_attrs[i]); -} +static struct attribute *xennet_dev_attrs[] = { + &dev_attr_rxbuf_min.attr, + &dev_attr_rxbuf_max.attr, + &dev_attr_rxbuf_cur.attr, + NULL +}; +static const struct attribute_group xennet_dev_group = { + .attrs = xennet_dev_attrs +}; #endif /* CONFIG_SYSFS */ static int xennet_remove(struct xenbus_device *dev) @@ -2140,8 +2112,6 @@ static int xennet_remove(struct xenbus_device *dev) xennet_disconnect_backend(info); - xennet_sysfs_delif(info->netdev); - unregister_netdev(info->netdev); for (i = 0; i < num_queues; ++i) { diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c index df781cdf13c1..17ca98657a28 100644 --- a/drivers/pci/host/pcie-designware.c +++ b/drivers/pci/host/pcie-designware.c @@ -283,6 +283,9 @@ static int dw_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev, struct msi_msg msg; struct pcie_port *pp = sys_to_pcie(pdev->bus->sysdata); + if (desc->msi_attrib.is_msix) + return -EINVAL; + irq = assign_irq(1, desc, &pos); if (irq < 0) return irq; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e52356aa09b8..903d5078b5ed 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -324,18 +324,52 @@ static void quirk_s3_64M(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3, PCI_DEVICE_ID_S3_868, quirk_s3_64M); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3, PCI_DEVICE_ID_S3_968, quirk_s3_64M); +static void quirk_io(struct pci_dev *dev, int pos, unsigned size, + const char *name) +{ + u32 region; + struct pci_bus_region bus_region; + struct resource *res = dev->resource + pos; + + pci_read_config_dword(dev, PCI_BASE_ADDRESS_0 + (pos << 2), ®ion); + + if (!region) + return; + + res->name = pci_name(dev); + res->flags = region & ~PCI_BASE_ADDRESS_IO_MASK; + res->flags |= + (IORESOURCE_IO | IORESOURCE_PCI_FIXED | IORESOURCE_SIZEALIGN); + region &= ~(size - 1); + + /* Convert from PCI bus to resource space */ + bus_region.start = region; + bus_region.end = region + size - 1; + pcibios_bus_to_resource(dev->bus, res, &bus_region); + + dev_info(&dev->dev, FW_BUG "%s quirk: reg 0x%x: %pR\n", + name, PCI_BASE_ADDRESS_0 + (pos << 2), res); +} + /* * Some CS5536 BIOSes (for example, the Soekris NET5501 board w/ comBIOS * ver. 1.33 20070103) don't set the correct ISA PCI region header info. * BAR0 should be 8 bytes; instead, it may be set to something like 8k * (which conflicts w/ BAR1's memory range). + * + * CS553x's ISA PCI BARs may also be read-only (ref: + * https://bugzilla.kernel.org/show_bug.cgi?id=85991 - Comment #4 forward). */ static void quirk_cs5536_vsa(struct pci_dev *dev) { + static char *name = "CS5536 ISA bridge"; + if (pci_resource_len(dev, 0) != 8) { - struct resource *res = &dev->resource[0]; - res->end = res->start + 8 - 1; - dev_info(&dev->dev, "CS5536 ISA bridge bug detected (incorrect header); workaround applied\n"); + quirk_io(dev, 0, 8, name); /* SMB */ + quirk_io(dev, 1, 256, name); /* GPIO */ + quirk_io(dev, 2, 64, name); /* MFGPT */ + dev_info(&dev->dev, "%s bug detected (incorrect header); workaround applied\n", + name); } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa); diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index dfd021e8268f..f4cd0b9b2438 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -177,7 +177,7 @@ struct at91_pinctrl { struct device *dev; struct pinctrl_dev *pctl; - int nbanks; + int nactive_banks; uint32_t *mux_mask; int nmux; @@ -653,12 +653,18 @@ static int pin_check_config(struct at91_pinctrl *info, const char *name, int mux; /* check if it's a valid config */ - if (pin->bank >= info->nbanks) { + if (pin->bank >= gpio_banks) { dev_err(info->dev, "%s: pin conf %d bank_id %d >= nbanks %d\n", - name, index, pin->bank, info->nbanks); + name, index, pin->bank, gpio_banks); return -EINVAL; } + if (!gpio_chips[pin->bank]) { + dev_err(info->dev, "%s: pin conf %d bank_id %d not enabled\n", + name, index, pin->bank); + return -ENXIO; + } + if (pin->pin >= MAX_NB_GPIO_PER_BANK) { dev_err(info->dev, "%s: pin conf %d pin_bank_id %d >= %d\n", name, index, pin->pin, MAX_NB_GPIO_PER_BANK); @@ -981,7 +987,8 @@ static void at91_pinctrl_child_count(struct at91_pinctrl *info, for_each_child_of_node(np, child) { if (of_device_is_compatible(child, gpio_compat)) { - info->nbanks++; + if (of_device_is_available(child)) + info->nactive_banks++; } else { info->nfunctions++; info->ngroups += of_get_child_count(child); @@ -1003,11 +1010,11 @@ static int at91_pinctrl_mux_mask(struct at91_pinctrl *info, } size /= sizeof(*list); - if (!size || size % info->nbanks) { - dev_err(info->dev, "wrong mux mask array should be by %d\n", info->nbanks); + if (!size || size % gpio_banks) { + dev_err(info->dev, "wrong mux mask array should be by %d\n", gpio_banks); return -EINVAL; } - info->nmux = size / info->nbanks; + info->nmux = size / gpio_banks; info->mux_mask = devm_kzalloc(info->dev, sizeof(u32) * size, GFP_KERNEL); if (!info->mux_mask) { @@ -1131,7 +1138,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, of_match_device(at91_pinctrl_of_match, &pdev->dev)->data; at91_pinctrl_child_count(info, np); - if (info->nbanks < 1) { + if (gpio_banks < 1) { dev_err(&pdev->dev, "you need to specify at least one gpio-controller\n"); return -EINVAL; } @@ -1144,7 +1151,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, dev_dbg(&pdev->dev, "mux-mask\n"); tmp = info->mux_mask; - for (i = 0; i < info->nbanks; i++) { + for (i = 0; i < gpio_banks; i++) { for (j = 0; j < info->nmux; j++, tmp++) { dev_dbg(&pdev->dev, "%d:%d\t0x%x\n", i, j, tmp[0]); } @@ -1162,7 +1169,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, if (!info->groups) return -ENOMEM; - dev_dbg(&pdev->dev, "nbanks = %d\n", info->nbanks); + dev_dbg(&pdev->dev, "nbanks = %d\n", gpio_banks); dev_dbg(&pdev->dev, "nfunctions = %d\n", info->nfunctions); dev_dbg(&pdev->dev, "ngroups = %d\n", info->ngroups); @@ -1185,7 +1192,7 @@ static int at91_pinctrl_probe(struct platform_device *pdev) { struct at91_pinctrl *info; struct pinctrl_pin_desc *pdesc; - int ret, i, j, k; + int ret, i, j, k, ngpio_chips_enabled = 0; info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); if (!info) @@ -1200,23 +1207,27 @@ static int at91_pinctrl_probe(struct platform_device *pdev) * to obtain references to the struct gpio_chip * for them, and we * need this to proceed. */ - for (i = 0; i < info->nbanks; i++) { - if (!gpio_chips[i]) { - dev_warn(&pdev->dev, "GPIO chip %d not registered yet\n", i); - devm_kfree(&pdev->dev, info); - return -EPROBE_DEFER; - } + for (i = 0; i < gpio_banks; i++) + if (gpio_chips[i]) + ngpio_chips_enabled++; + + if (ngpio_chips_enabled < info->nactive_banks) { + dev_warn(&pdev->dev, + "All GPIO chips are not registered yet (%d/%d)\n", + ngpio_chips_enabled, info->nactive_banks); + devm_kfree(&pdev->dev, info); + return -EPROBE_DEFER; } at91_pinctrl_desc.name = dev_name(&pdev->dev); - at91_pinctrl_desc.npins = info->nbanks * MAX_NB_GPIO_PER_BANK; + at91_pinctrl_desc.npins = gpio_banks * MAX_NB_GPIO_PER_BANK; at91_pinctrl_desc.pins = pdesc = devm_kzalloc(&pdev->dev, sizeof(*pdesc) * at91_pinctrl_desc.npins, GFP_KERNEL); if (!at91_pinctrl_desc.pins) return -ENOMEM; - for (i = 0 , k = 0; i < info->nbanks; i++) { + for (i = 0, k = 0; i < gpio_banks; i++) { for (j = 0; j < MAX_NB_GPIO_PER_BANK; j++, k++) { pdesc->number = k; pdesc->name = kasprintf(GFP_KERNEL, "pio%c%d", i + 'A', j); @@ -1234,8 +1245,9 @@ static int at91_pinctrl_probe(struct platform_device *pdev) } /* We will handle a range of GPIO pins */ - for (i = 0; i < info->nbanks; i++) - pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range); + for (i = 0; i < gpio_banks; i++) + if (gpio_chips[i]) + pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range); dev_info(&pdev->dev, "initialized AT91 pinctrl driver\n"); @@ -1613,9 +1625,10 @@ static void gpio_irq_handler(unsigned irq, struct irq_desc *desc) static int at91_gpio_of_irq_setup(struct platform_device *pdev, struct at91_gpio_chip *at91_gpio) { + struct gpio_chip *gpiochip_prev = NULL; struct at91_gpio_chip *prev = NULL; struct irq_data *d = irq_get_irq_data(at91_gpio->pioc_virq); - int ret; + int ret, i; at91_gpio->pioc_hwirq = irqd_to_hwirq(d); @@ -1641,24 +1654,33 @@ static int at91_gpio_of_irq_setup(struct platform_device *pdev, return ret; } - /* Setup chained handler */ - if (at91_gpio->pioc_idx) - prev = gpio_chips[at91_gpio->pioc_idx - 1]; - /* The top level handler handles one bank of GPIOs, except * on some SoC it can handle up to three... * We only set up the handler for the first of the list. */ - if (prev && prev->next == at91_gpio) + gpiochip_prev = irq_get_handler_data(at91_gpio->pioc_virq); + if (!gpiochip_prev) { + /* Then register the chain on the parent IRQ */ + gpiochip_set_chained_irqchip(&at91_gpio->chip, + &gpio_irqchip, + at91_gpio->pioc_virq, + gpio_irq_handler); return 0; + } - /* Then register the chain on the parent IRQ */ - gpiochip_set_chained_irqchip(&at91_gpio->chip, - &gpio_irqchip, - at91_gpio->pioc_virq, - gpio_irq_handler); + prev = container_of(gpiochip_prev, struct at91_gpio_chip, chip); - return 0; + /* we can only have 2 banks before */ + for (i = 0; i < 2; i++) { + if (prev->next) { + prev = prev->next; + } else { + prev->next = at91_gpio; + return 0; + } + } + + return -EINVAL; } /* This structure is replicated for each GPIO block allocated at probe time */ @@ -1675,24 +1697,6 @@ static struct gpio_chip at91_gpio_template = { .ngpio = MAX_NB_GPIO_PER_BANK, }; -static void at91_gpio_probe_fixup(void) -{ - unsigned i; - struct at91_gpio_chip *at91_gpio, *last = NULL; - - for (i = 0; i < gpio_banks; i++) { - at91_gpio = gpio_chips[i]; - - /* - * GPIO controller are grouped on some SoC: - * PIOC, PIOD and PIOE can share the same IRQ line - */ - if (last && last->pioc_virq == at91_gpio->pioc_virq) - last->next = at91_gpio; - last = at91_gpio; - } -} - static struct of_device_id at91_gpio_of_match[] = { { .compatible = "atmel,at91sam9x5-gpio", .data = &at91sam9x5_ops, }, { .compatible = "atmel,at91rm9200-gpio", .data = &at91rm9200_ops }, @@ -1805,8 +1809,6 @@ static int at91_gpio_probe(struct platform_device *pdev) gpio_chips[alias_idx] = at91_chip; gpio_banks = max(gpio_banks, alias_idx + 1); - at91_gpio_probe_fixup(); - ret = at91_gpio_of_irq_setup(pdev, at91_chip); if (ret) goto irq_setup_err; diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index c81b06bcf827..2e66f34ebb79 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -1372,7 +1372,8 @@ csio_config_device_caps(struct csio_hw *hw) } /* Validate device capabilities */ - if (csio_hw_validate_caps(hw, mbp)) + rv = csio_hw_validate_caps(hw, mbp); + if (rv != 0) goto out; /* Don't config device capabilities if already configured */ @@ -1776,7 +1777,8 @@ csio_hw_use_fwconfig(struct csio_hw *hw, int reset, u32 *fw_cfg_param) } /* Validate device capabilities */ - if (csio_hw_validate_caps(hw, mbp)) + rv = csio_hw_validate_caps(hw, mbp); + if (rv != 0) goto bye; /* * Note that we're operating with parameters diff --git a/drivers/scsi/csiostor/csio_hw_chip.h b/drivers/scsi/csiostor/csio_hw_chip.h index a5f624f755df..b56a11d817be 100644 --- a/drivers/scsi/csiostor/csio_hw_chip.h +++ b/drivers/scsi/csiostor/csio_hw_chip.h @@ -45,11 +45,6 @@ #define FW_FNAME_T5 "cxgb4/t5fw.bin" #define FW_CFG_NAME_T5 "cxgb4/t5-config.txt" -#define T5FW_VERSION_MAJOR 0x01 -#define T5FW_VERSION_MINOR 0x0B -#define T5FW_VERSION_MICRO 0x1B -#define T5FW_VERSION_BUILD 0x00 - #define CHELSIO_CHIP_CODE(version, revision) (((version) << 4) | (revision)) #define CHELSIO_CHIP_FPGA 0x100 #define CHELSIO_CHIP_VERSION(code) (((code) >> 12) & 0xf) @@ -74,6 +69,7 @@ static inline int csio_is_t5(uint16_t chip) { PCI_VENDOR_ID_CHELSIO, (devid), PCI_ANY_ID, PCI_ANY_ID, 0, 0, (idx) } #include "t4fw_api.h" +#include "t4fw_version.h" #define FW_VERSION(chip) ( \ FW_HDR_FW_VER_MAJOR_G(chip##FW_VERSION_MAJOR) | \ diff --git a/drivers/scsi/csiostor/csio_mb.c b/drivers/scsi/csiostor/csio_mb.c index 1132c41d99ce..9451787ca7f2 100644 --- a/drivers/scsi/csiostor/csio_mb.c +++ b/drivers/scsi/csiostor/csio_mb.c @@ -327,7 +327,8 @@ csio_mb_caps_config(struct csio_hw *hw, struct csio_mb *mbp, uint32_t tmo, } #define CSIO_ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\ - FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_ANEG) + FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G |\ + FW_PORT_CAP_ANEG) /* * csio_mb_port- FW PORT command helper diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c index 1dba62c5cf6a..1efebc9eedfb 100644 --- a/drivers/scsi/device_handler/scsi_dh.c +++ b/drivers/scsi/device_handler/scsi_dh.c @@ -136,11 +136,12 @@ static void __detach_handler (struct kref *kref) struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh; struct scsi_device *sdev = scsi_dh_data->sdev; + scsi_dh->detach(sdev); + spin_lock_irq(sdev->request_queue->queue_lock); sdev->scsi_dh_data = NULL; spin_unlock_irq(sdev->request_queue->queue_lock); - scsi_dh->detach(sdev); sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", scsi_dh->name); module_put(scsi_dh->module); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 399516925d80..05ea0d49a3a3 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2800,9 +2800,11 @@ static int sd_revalidate_disk(struct gendisk *disk) */ sd_set_flush_flag(sdkp); - max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), - sdkp->max_xfer_blocks); + max_xfer = sdkp->max_xfer_blocks; max_xfer <<= ilog2(sdp->sector_size) - 9; + + max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), + max_xfer); blk_queue_max_hw_sectors(sdkp->disk->queue, max_xfer); set_capacity(disk, sdkp->capacity); sd_config_write_same(sdkp); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 4cda994d3f40..9b80d54d4ddb 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -342,8 +342,7 @@ static int dspi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) /* Only alloc on first setup */ chip = spi_get_ctldata(spi); if (chip == NULL) { - chip = devm_kzalloc(&spi->dev, sizeof(struct chip_data), - GFP_KERNEL); + chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL); if (!chip) return -ENOMEM; } @@ -382,6 +381,16 @@ static int dspi_setup(struct spi_device *spi) return dspi_setup_transfer(spi, NULL); } +static void dspi_cleanup(struct spi_device *spi) +{ + struct chip_data *chip = spi_get_ctldata((struct spi_device *)spi); + + dev_dbg(&spi->dev, "spi_device %u.%u cleanup\n", + spi->master->bus_num, spi->chip_select); + + kfree(chip); +} + static irqreturn_t dspi_interrupt(int irq, void *dev_id) { struct fsl_dspi *dspi = (struct fsl_dspi *)dev_id; @@ -467,6 +476,7 @@ static int dspi_probe(struct platform_device *pdev) dspi->bitbang.master->setup = dspi_setup; dspi->bitbang.master->dev.of_node = pdev->dev.of_node; + master->cleanup = dspi_cleanup; master->mode_bits = SPI_CPOL | SPI_CPHA; master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) | SPI_BPW_MASK(16); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 961b97d43b43..fe1b7699fab6 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -823,6 +823,10 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx, struct dma_slave_config slave_config = {}; int ret; + /* use pio mode for i.mx6dl chip TKT238285 */ + if (of_machine_is_compatible("fsl,imx6dl")) + return 0; + /* Prepare for TX DMA: */ master->dma_tx = dma_request_slave_channel(dev, "tx"); if (!master->dma_tx) { diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c index 930f6010203e..65d610abe06e 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_io.c +++ b/drivers/staging/lustre/lustre/llite/vvp_io.c @@ -632,7 +632,7 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio) return 0; } - if (cfio->fault.ft_flags & VM_FAULT_SIGBUS) { + if (cfio->fault.ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address); return -EFAULT; } diff --git a/drivers/staging/nvec/nvec.c b/drivers/staging/nvec/nvec.c index 093535c6217b..120b70d72d79 100644 --- a/drivers/staging/nvec/nvec.c +++ b/drivers/staging/nvec/nvec.c @@ -85,23 +85,20 @@ static struct nvec_chip *nvec_power_handle; static const struct mfd_cell nvec_devices[] = { { .name = "nvec-kbd", - .id = 1, }, { .name = "nvec-mouse", - .id = 1, }, { .name = "nvec-power", - .id = 1, + .id = 0, }, { .name = "nvec-power", - .id = 2, + .id = 1, }, { .name = "nvec-paz00", - .id = 1, }, }; @@ -891,7 +888,7 @@ static int tegra_nvec_probe(struct platform_device *pdev) nvec_msg_free(nvec, msg); } - ret = mfd_add_devices(nvec->dev, -1, nvec_devices, + ret = mfd_add_devices(nvec->dev, 0, nvec_devices, ARRAY_SIZE(nvec_devices), NULL, 0, NULL); if (ret) dev_err(nvec->dev, "error adding subdevices\n"); diff --git a/drivers/usb/core/otg_whitelist.h b/drivers/usb/core/otg_whitelist.h index de0c9c9d7091..a6315abe7b7c 100644 --- a/drivers/usb/core/otg_whitelist.h +++ b/drivers/usb/core/otg_whitelist.h @@ -55,6 +55,11 @@ static int is_targeted(struct usb_device *dev) le16_to_cpu(dev->descriptor.idProduct) == 0xbadd)) return 0; + /* OTG PET device is always targeted (see OTG 2.0 ECN 6.4.2) */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x1a0a && + le16_to_cpu(dev->descriptor.idProduct) == 0x0200)) + return 1; + /* NOTE: can't use usb_match_id() since interface caches * aren't set up yet. this is cut/paste from that code. */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 0ffb4ed0a945..41e510ae8c83 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -179,6 +179,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Protocol and OTG Electrical Test Device */ + { USB_DEVICE(0x1a0a, 0x0200), .driver_info = + USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index ad43c5bc1ef1..02e3e2d4ea56 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -476,13 +476,13 @@ irqreturn_t dwc2_handle_common_intr(int irq, void *dev) u32 gintsts; irqreturn_t retval = IRQ_NONE; + spin_lock(&hsotg->lock); + if (!dwc2_is_controller_alive(hsotg)) { dev_warn(hsotg->dev, "Controller is dead\n"); goto out; } - spin_lock(&hsotg->lock); - gintsts = dwc2_read_common_intr(hsotg); if (gintsts & ~GINTSTS_PRTINT) retval = IRQ_HANDLED; @@ -515,8 +515,8 @@ irqreturn_t dwc2_handle_common_intr(int irq, void *dev) } } - spin_unlock(&hsotg->lock); out: + spin_unlock(&hsotg->lock); return retval; } EXPORT_SYMBOL_GPL(dwc2_handle_common_intr); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index ccfdfb24b240..2f9735b35338 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -34,7 +34,7 @@ static struct usb_phy *__usb_find_phy(struct list_head *list, return phy; } - return ERR_PTR(-EPROBE_DEFER); + return ERR_PTR(-ENODEV); } static struct usb_phy *__usb_find_phy_dev(struct device *dev, diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 11c7a9676441..d684b4b8108f 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -507,7 +507,7 @@ UNUSUAL_DEV( 0x04e6, 0x000c, 0x0100, 0x0100, UNUSUAL_DEV( 0x04e6, 0x000f, 0x0000, 0x9999, "SCM Microsystems", "eUSB SCSI Adapter (Bus Powered)", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + USB_SC_SCSI, USB_PR_BULK, usb_stor_euscsi_init, US_FL_SCM_MULT_TARG ), UNUSUAL_DEV( 0x04e6, 0x0101, 0x0200, 0x0200, @@ -1995,6 +1995,13 @@ UNUSUAL_DEV( 0x152d, 0x2329, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ), +/* Reported by Dmitry Nezhevenko <dion@dion.org.ua> */ +UNUSUAL_DEV( 0x152d, 0x2566, 0x0114, 0x0114, + "JMicron", + "USB to ATA/ATAPI Bridge", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_BROKEN_FUA ), + /* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI) * and Mac USB Dock USB-SCSI */ UNUSUAL_DEV( 0x1645, 0x0007, 0x0100, 0x0133, diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 6df4357d9ee3..dbc00e56c7f5 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -140,3 +140,10 @@ UNUSUAL_DEV(0x4971, 0x1012, 0x0000, 0x9999, "External HDD", USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_UAS), + +/* Reported-by: Richard Henderson <rth@redhat.com> */ +UNUSUAL_DEV(0x4971, 0x8017, 0x0000, 0x9999, + "SimpleTech", + "External HDD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 6906f76332f4..8dccca9013ed 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -84,10 +84,6 @@ struct vhost_net_ubuf_ref { struct vhost_net_virtqueue { struct vhost_virtqueue vq; - /* hdr is used to store the virtio header. - * Since each iovec has >= 1 byte length, we never need more than - * header length entries to store the header. */ - struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)]; size_t vhost_hlen; size_t sock_hlen; /* vhost zerocopy support fields below: */ @@ -235,44 +231,6 @@ static bool vhost_sock_zcopy(struct socket *sock) sock_flag(sock->sk, SOCK_ZEROCOPY); } -/* Pop first len bytes from iovec. Return number of segments used. */ -static int move_iovec_hdr(struct iovec *from, struct iovec *to, - size_t len, int iov_count) -{ - int seg = 0; - size_t size; - - while (len && seg < iov_count) { - size = min(from->iov_len, len); - to->iov_base = from->iov_base; - to->iov_len = size; - from->iov_len -= size; - from->iov_base += size; - len -= size; - ++from; - ++to; - ++seg; - } - return seg; -} -/* Copy iovec entries for len bytes from iovec. */ -static void copy_iovec_hdr(const struct iovec *from, struct iovec *to, - size_t len, int iovcount) -{ - int seg = 0; - size_t size; - - while (len && seg < iovcount) { - size = min(from->iov_len, len); - to->iov_base = from->iov_base; - to->iov_len = size; - len -= size; - ++from; - ++to; - ++seg; - } -} - /* In case of DMA done not in order in lower device driver for some reason. * upend_idx is used to track end of used idx, done_idx is used to track head * of used idx. Once lower device DMA done contiguously, we will signal KVM @@ -336,7 +294,7 @@ static void handle_tx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; - unsigned out, in, s; + unsigned out, in; int head; struct msghdr msg = { .msg_name = NULL, @@ -395,16 +353,17 @@ static void handle_tx(struct vhost_net *net) break; } /* Skip header. TODO: support TSO. */ - s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out); len = iov_length(vq->iov, out); iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len); + iov_iter_advance(&msg.msg_iter, hdr_size); /* Sanity check */ - if (!len) { + if (!iov_iter_count(&msg.msg_iter)) { vq_err(vq, "Unexpected header len for TX: " "%zd expected %zd\n", - iov_length(nvq->hdr, s), hdr_size); + len, hdr_size); break; } + len = iov_iter_count(&msg.msg_iter); zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN && (nvq->upend_idx + 1) % UIO_MAXIOV != @@ -579,6 +538,7 @@ static void handle_rx(struct vhost_net *net) size_t vhost_hlen, sock_hlen; size_t vhost_len, sock_len; struct socket *sock; + struct iov_iter fixup; mutex_lock(&vq->mutex); sock = vq->private_data; @@ -623,14 +583,19 @@ static void handle_rx(struct vhost_net *net) break; } /* We don't need to be notified again. */ - if (unlikely((vhost_hlen))) - /* Skip header. TODO: support TSO. */ - move_iovec_hdr(vq->iov, nvq->hdr, vhost_hlen, in); - else - /* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF: - * needed because recvmsg can modify msg_iov. */ - copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in); - iov_iter_init(&msg.msg_iter, READ, vq->iov, in, sock_len); + iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len); + fixup = msg.msg_iter; + if (unlikely((vhost_hlen))) { + /* We will supply the header ourselves + * TODO: support TSO. + */ + iov_iter_advance(&msg.msg_iter, vhost_hlen); + } else { + /* It'll come from socket; we'll need to patch + * ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF + */ + iov_iter_advance(&fixup, sizeof(hdr)); + } err = sock->ops->recvmsg(NULL, sock, &msg, sock_len, MSG_DONTWAIT | MSG_TRUNC); /* Userspace might have consumed the packet meanwhile: @@ -642,18 +607,18 @@ static void handle_rx(struct vhost_net *net) vhost_discard_vq_desc(vq, headcount); continue; } + /* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */ if (unlikely(vhost_hlen) && - memcpy_toiovecend(nvq->hdr, (unsigned char *)&hdr, 0, - vhost_hlen)) { + copy_to_iter(&hdr, sizeof(hdr), &fixup) != sizeof(hdr)) { vq_err(vq, "Unable to write vnet_hdr at addr %p\n", vq->iov->iov_base); break; } /* TODO: Should check and handle checksum. */ + + hdr.num_buffers = cpu_to_vhost16(vq, headcount); if (likely(mergeable) && - memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount, - offsetof(typeof(hdr), num_buffers), - sizeof hdr.num_buffers)) { + copy_to_iter(&hdr.num_buffers, 2, &fixup) != 2) { vq_err(vq, "Failed num_buffers write"); vhost_discard_vq_desc(vq, headcount); break; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index d695b1673ae5..dc78d87e0fc2 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1079,7 +1079,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) req_size, vq->iov[0].iov_len); break; } - ret = memcpy_fromiovecend(req, &vq->iov[0], 0, req_size); + ret = copy_from_user(req, vq->iov[0].iov_base, req_size); if (unlikely(ret)) { vq_err(vq, "Faulted on virtio_scsi_cmd_req\n"); break; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index cb807d0ea498..2ee28266fd07 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1125,6 +1125,7 @@ static int get_indirect(struct vhost_virtqueue *vq, struct vring_desc desc; unsigned int i = 0, count, found = 0; u32 len = vhost32_to_cpu(vq, indirect->len); + struct iov_iter from; int ret; /* Sanity check */ @@ -1142,6 +1143,7 @@ static int get_indirect(struct vhost_virtqueue *vq, vq_err(vq, "Translation failure %d in indirect.\n", ret); return ret; } + iov_iter_init(&from, READ, vq->indirect, ret, len); /* We will use the result as an address to read from, so most * architectures only need a compiler barrier here. */ @@ -1164,8 +1166,8 @@ static int get_indirect(struct vhost_virtqueue *vq, i, count); return -EINVAL; } - if (unlikely(memcpy_fromiovec((unsigned char *)&desc, - vq->indirect, sizeof desc))) { + if (unlikely(copy_from_iter(&desc, sizeof(desc), &from) != + sizeof(desc))) { vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n", i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc); return -EINVAL; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 06e14bfb3496..dbc732e9a5c0 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, _debug("- range %u-%u%s", offset, to, msg->msg_flags ? " [more]" : ""); - iov_iter_init(&msg->msg_iter, WRITE, - (struct iovec *) iov, 1, to - offset); + iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, + iov, 1, to - offset); /* have to change the state *before* sending the last * packet as RxRPC might give us the reply before it @@ -384,7 +384,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1, + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; @@ -770,7 +770,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, void afs_send_empty_reply(struct afs_call *call) { struct msghdr msg; - struct iovec iov[1]; + struct kvec iov[1]; _enter(""); @@ -778,7 +778,7 @@ void afs_send_empty_reply(struct afs_call *call) iov[0].iov_len = 0; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0); /* WTF? */ + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 0, 0); /* WTF? */ msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -805,7 +805,7 @@ void afs_send_empty_reply(struct afs_call *call) void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) { struct msghdr msg; - struct iovec iov[1]; + struct kvec iov[1]; int n; _enter(""); @@ -814,7 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) iov[0].iov_len = len; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len); + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 2f0fbc374e87..e427cb7ee12c 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3065,6 +3065,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, path->search_commit_root = 1; path->skip_locking = 1; + ppath->search_commit_root = 1; + ppath->skip_locking = 1; /* * trigger the readahead for extent tree csum tree and wait for * completion. During readahead, the scrub is officially paused diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 9c56ef776407..7febcf2475c5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -606,9 +606,11 @@ cifs_security_flags_handle_must_flags(unsigned int *flags) *flags = CIFSSEC_MUST_NTLMV2; else if ((*flags & CIFSSEC_MUST_NTLM) == CIFSSEC_MUST_NTLM) *flags = CIFSSEC_MUST_NTLM; - else if ((*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN) + else if (CIFSSEC_MUST_LANMAN && + (*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN) *flags = CIFSSEC_MUST_LANMAN; - else if ((*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT) + else if (CIFSSEC_MUST_PLNTXT && + (*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT) *flags = CIFSSEC_MUST_PLNTXT; *flags |= signflags; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 96b7e9b7706d..74f12877493a 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; + bool oplock_break_cancelled; spin_lock(&cifs_file_list_lock); if (--cifs_file->count > 0) { @@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); - cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) _free_xid(xid); } + if (oplock_break_cancelled) + cifs_done_oplock_break(cifsi); + cifs_del_pending_open(&open); /* diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index 6c1566366a66..a4232ec4f2ba 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -221,7 +221,7 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16, } rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16)); - memset(wpwd, 0, 129 * sizeof(__le16)); + memzero_explicit(wpwd, sizeof(wpwd)); return rc; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c8b148bbdc8b..3e193cb36996 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -667,7 +667,7 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, s64 change, struct gfs2_quota_data *qd, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct inode *inode = &ip->i_inode; struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -697,16 +697,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, be64_add_cpu(&q.qu_value, change); qd->qd_qb.qb_value = q.qu_value; if (fdq) { - if (fdq->d_fieldmask & FS_DQ_BSOFT) { - q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPC_SOFT) { + q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_warn = q.qu_warn; } - if (fdq->d_fieldmask & FS_DQ_BHARD) { - q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPC_HARD) { + q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_limit = q.qu_limit; } - if (fdq->d_fieldmask & FS_DQ_BCOUNT) { - q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPACE) { + q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_value = q.qu_value; } } @@ -1497,7 +1497,7 @@ static int gfs2_quota_get_xstate(struct super_block *sb, } static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_lvb *qlvb; @@ -1505,7 +1505,7 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, struct gfs2_holder q_gh; int error; - memset(fdq, 0, sizeof(struct fs_disk_quota)); + memset(fdq, 0, sizeof(*fdq)); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ @@ -1522,12 +1522,9 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, goto out; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; - fdq->d_version = FS_DQUOT_VERSION; - fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA; - fdq->d_id = from_kqid_munged(current_user_ns(), qid); - fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift; - fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift; - fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift; + fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift; + fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift; + fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift; gfs2_glock_dq_uninit(&q_gh); out: @@ -1536,10 +1533,10 @@ out: } /* GFS2 only supports a subset of the XFS fields */ -#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT) +#define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE) static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); @@ -1583,17 +1580,17 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, goto out_i; /* If nothing has changed, this is a no-op */ - if ((fdq->d_fieldmask & FS_DQ_BSOFT) && - ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) - fdq->d_fieldmask ^= FS_DQ_BSOFT; + if ((fdq->d_fieldmask & QC_SPC_SOFT) && + ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) + fdq->d_fieldmask ^= QC_SPC_SOFT; - if ((fdq->d_fieldmask & FS_DQ_BHARD) && - ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) - fdq->d_fieldmask ^= FS_DQ_BHARD; + if ((fdq->d_fieldmask & QC_SPC_HARD) && + ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) + fdq->d_fieldmask ^= QC_SPC_HARD; - if ((fdq->d_fieldmask & FS_DQ_BCOUNT) && - ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value))) - fdq->d_fieldmask ^= FS_DQ_BCOUNT; + if ((fdq->d_fieldmask & QC_SPACE) && + ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value))) + fdq->d_fieldmask ^= QC_SPACE; if (fdq->d_fieldmask == 0) goto out_i; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 10bf07280f4a..294692ff83b1 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -212,6 +212,12 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, */ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { + struct inode *inode = iocb->ki_filp->f_mapping->host; + + /* we only support swap file calling nfs_direct_IO */ + if (!IS_SWAPFILE(inode)) + return 0; + #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp, (long long) pos, iter->nr_segs); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 4bffe637ea32..2211f6ba8736 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -352,8 +352,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_attr_check_mountpoint(sb, fattr); - if (((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) && - !nfs_attr_use_mounted_on_fileid(fattr)) + if (nfs_attr_use_mounted_on_fileid(fattr)) + fattr->fileid = fattr->mounted_on_fileid; + else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index efaa31c70fbe..b6f34bfa6fe8 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -31,8 +31,6 @@ static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; - - fattr->fileid = fattr->mounted_on_fileid; return 1; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 953daa44a282..706ad10b8186 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -639,7 +639,7 @@ int nfs41_walk_client_list(struct nfs_client *new, prev = pos; status = nfs_wait_client_init_complete(pos); - if (status == 0) { + if (pos->cl_cons_state == NFS_CS_SESSION_INITING) { nfs4_schedule_lease_recovery(pos); status = nfs4_wait_clnt_recover(pos); } diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8f0acef3d184..69df5b239844 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2396,30 +2396,25 @@ static inline qsize_t stoqb(qsize_t space) } /* Generic routine for getting common part of quota structure */ -static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di) +static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; memset(di, 0, sizeof(*di)); - di->d_version = FS_DQUOT_VERSION; - di->d_flags = dquot->dq_id.type == USRQUOTA ? - FS_USER_QUOTA : FS_GROUP_QUOTA; - di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id); - spin_lock(&dq_data_lock); - di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit); - di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit); + di->d_spc_hardlimit = dm->dqb_bhardlimit; + di->d_spc_softlimit = dm->dqb_bsoftlimit; di->d_ino_hardlimit = dm->dqb_ihardlimit; di->d_ino_softlimit = dm->dqb_isoftlimit; - di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace; - di->d_icount = dm->dqb_curinodes; - di->d_btimer = dm->dqb_btime; - di->d_itimer = dm->dqb_itime; + di->d_space = dm->dqb_curspace + dm->dqb_rsvspace; + di->d_ino_count = dm->dqb_curinodes; + di->d_spc_timer = dm->dqb_btime; + di->d_ino_timer = dm->dqb_itime; spin_unlock(&dq_data_lock); } int dquot_get_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *di) + struct qc_dqblk *di) { struct dquot *dquot; @@ -2433,70 +2428,70 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid, } EXPORT_SYMBOL(dquot_get_dqblk); -#define VFS_FS_DQ_MASK \ - (FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \ - FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \ - FS_DQ_BTIMER | FS_DQ_ITIMER) +#define VFS_QC_MASK \ + (QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \ + QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \ + QC_SPC_TIMER | QC_INO_TIMER) /* Generic routine for setting common part of quota structure */ -static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) +static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; int check_blim = 0, check_ilim = 0; struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - if (di->d_fieldmask & ~VFS_FS_DQ_MASK) + if (di->d_fieldmask & ~VFS_QC_MASK) return -EINVAL; - if (((di->d_fieldmask & FS_DQ_BSOFT) && - (di->d_blk_softlimit > dqi->dqi_maxblimit)) || - ((di->d_fieldmask & FS_DQ_BHARD) && - (di->d_blk_hardlimit > dqi->dqi_maxblimit)) || - ((di->d_fieldmask & FS_DQ_ISOFT) && + if (((di->d_fieldmask & QC_SPC_SOFT) && + stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) || + ((di->d_fieldmask & QC_SPC_HARD) && + stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) || + ((di->d_fieldmask & QC_INO_SOFT) && (di->d_ino_softlimit > dqi->dqi_maxilimit)) || - ((di->d_fieldmask & FS_DQ_IHARD) && + ((di->d_fieldmask & QC_INO_HARD) && (di->d_ino_hardlimit > dqi->dqi_maxilimit))) return -ERANGE; spin_lock(&dq_data_lock); - if (di->d_fieldmask & FS_DQ_BCOUNT) { - dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace; + if (di->d_fieldmask & QC_SPACE) { + dm->dqb_curspace = di->d_space - dm->dqb_rsvspace; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_BSOFT) - dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit); - if (di->d_fieldmask & FS_DQ_BHARD) - dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit); - if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) { + if (di->d_fieldmask & QC_SPC_SOFT) + dm->dqb_bsoftlimit = di->d_spc_softlimit; + if (di->d_fieldmask & QC_SPC_HARD) + dm->dqb_bhardlimit = di->d_spc_hardlimit; + if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) { check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ICOUNT) { - dm->dqb_curinodes = di->d_icount; + if (di->d_fieldmask & QC_INO_COUNT) { + dm->dqb_curinodes = di->d_ino_count; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ISOFT) + if (di->d_fieldmask & QC_INO_SOFT) dm->dqb_isoftlimit = di->d_ino_softlimit; - if (di->d_fieldmask & FS_DQ_IHARD) + if (di->d_fieldmask & QC_INO_HARD) dm->dqb_ihardlimit = di->d_ino_hardlimit; - if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) { + if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) { check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_BTIMER) { - dm->dqb_btime = di->d_btimer; + if (di->d_fieldmask & QC_SPC_TIMER) { + dm->dqb_btime = di->d_spc_timer; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ITIMER) { - dm->dqb_itime = di->d_itimer; + if (di->d_fieldmask & QC_INO_TIMER) { + dm->dqb_itime = di->d_ino_timer; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags); } @@ -2506,7 +2501,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) dm->dqb_curspace < dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); - } else if (!(di->d_fieldmask & FS_DQ_BTIMER)) + } else if (!(di->d_fieldmask & QC_SPC_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_btime = get_seconds() + dqi->dqi_bgrace; } @@ -2515,7 +2510,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) dm->dqb_curinodes < dm->dqb_isoftlimit) { dm->dqb_itime = 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); - } else if (!(di->d_fieldmask & FS_DQ_ITIMER)) + } else if (!(di->d_fieldmask & QC_INO_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_itime = get_seconds() + dqi->dqi_igrace; } @@ -2531,7 +2526,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) } int dquot_set_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *di) + struct qc_dqblk *di) { struct dquot *dquot; int rc; diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 2aa4151f99d2..6f3856328eea 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -118,17 +118,27 @@ static int quota_setinfo(struct super_block *sb, int type, void __user *addr) return sb->s_qcop->set_info(sb, type, &info); } -static void copy_to_if_dqblk(struct if_dqblk *dst, struct fs_disk_quota *src) +static inline qsize_t qbtos(qsize_t blocks) +{ + return blocks << QIF_DQBLKSIZE_BITS; +} + +static inline qsize_t stoqb(qsize_t space) +{ + return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; +} + +static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src) { memset(dst, 0, sizeof(*dst)); - dst->dqb_bhardlimit = src->d_blk_hardlimit; - dst->dqb_bsoftlimit = src->d_blk_softlimit; - dst->dqb_curspace = src->d_bcount; + dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit); + dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit); + dst->dqb_curspace = src->d_space; dst->dqb_ihardlimit = src->d_ino_hardlimit; dst->dqb_isoftlimit = src->d_ino_softlimit; - dst->dqb_curinodes = src->d_icount; - dst->dqb_btime = src->d_btimer; - dst->dqb_itime = src->d_itimer; + dst->dqb_curinodes = src->d_ino_count; + dst->dqb_btime = src->d_spc_timer; + dst->dqb_itime = src->d_ino_timer; dst->dqb_valid = QIF_ALL; } @@ -136,7 +146,7 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; - struct fs_disk_quota fdq; + struct qc_dqblk fdq; struct if_dqblk idq; int ret; @@ -154,36 +164,36 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, return 0; } -static void copy_from_if_dqblk(struct fs_disk_quota *dst, struct if_dqblk *src) +static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src) { - dst->d_blk_hardlimit = src->dqb_bhardlimit; - dst->d_blk_softlimit = src->dqb_bsoftlimit; - dst->d_bcount = src->dqb_curspace; + dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit); + dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit); + dst->d_space = src->dqb_curspace; dst->d_ino_hardlimit = src->dqb_ihardlimit; dst->d_ino_softlimit = src->dqb_isoftlimit; - dst->d_icount = src->dqb_curinodes; - dst->d_btimer = src->dqb_btime; - dst->d_itimer = src->dqb_itime; + dst->d_ino_count = src->dqb_curinodes; + dst->d_spc_timer = src->dqb_btime; + dst->d_ino_timer = src->dqb_itime; dst->d_fieldmask = 0; if (src->dqb_valid & QIF_BLIMITS) - dst->d_fieldmask |= FS_DQ_BSOFT | FS_DQ_BHARD; + dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD; if (src->dqb_valid & QIF_SPACE) - dst->d_fieldmask |= FS_DQ_BCOUNT; + dst->d_fieldmask |= QC_SPACE; if (src->dqb_valid & QIF_ILIMITS) - dst->d_fieldmask |= FS_DQ_ISOFT | FS_DQ_IHARD; + dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD; if (src->dqb_valid & QIF_INODES) - dst->d_fieldmask |= FS_DQ_ICOUNT; + dst->d_fieldmask |= QC_INO_COUNT; if (src->dqb_valid & QIF_BTIME) - dst->d_fieldmask |= FS_DQ_BTIMER; + dst->d_fieldmask |= QC_SPC_TIMER; if (src->dqb_valid & QIF_ITIME) - dst->d_fieldmask |= FS_DQ_ITIMER; + dst->d_fieldmask |= QC_INO_TIMER; } static int quota_setquota(struct super_block *sb, int type, qid_t id, void __user *addr) { - struct fs_disk_quota fdq; + struct qc_dqblk fdq; struct if_dqblk idq; struct kqid qid; @@ -247,10 +257,78 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr) return ret; } +/* + * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them + * out of there as xfsprogs rely on definitions being in that header file. So + * just define same functions here for quota purposes. + */ +#define XFS_BB_SHIFT 9 + +static inline u64 quota_bbtob(u64 blocks) +{ + return blocks << XFS_BB_SHIFT; +} + +static inline u64 quota_btobb(u64 bytes) +{ + return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT; +} + +static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src) +{ + dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit); + dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit); + dst->d_ino_hardlimit = src->d_ino_hardlimit; + dst->d_ino_softlimit = src->d_ino_softlimit; + dst->d_space = quota_bbtob(src->d_bcount); + dst->d_ino_count = src->d_icount; + dst->d_ino_timer = src->d_itimer; + dst->d_spc_timer = src->d_btimer; + dst->d_ino_warns = src->d_iwarns; + dst->d_spc_warns = src->d_bwarns; + dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit); + dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit); + dst->d_rt_space = quota_bbtob(src->d_rtbcount); + dst->d_rt_spc_timer = src->d_rtbtimer; + dst->d_rt_spc_warns = src->d_rtbwarns; + dst->d_fieldmask = 0; + if (src->d_fieldmask & FS_DQ_ISOFT) + dst->d_fieldmask |= QC_INO_SOFT; + if (src->d_fieldmask & FS_DQ_IHARD) + dst->d_fieldmask |= QC_INO_HARD; + if (src->d_fieldmask & FS_DQ_BSOFT) + dst->d_fieldmask |= QC_SPC_SOFT; + if (src->d_fieldmask & FS_DQ_BHARD) + dst->d_fieldmask |= QC_SPC_HARD; + if (src->d_fieldmask & FS_DQ_RTBSOFT) + dst->d_fieldmask |= QC_RT_SPC_SOFT; + if (src->d_fieldmask & FS_DQ_RTBHARD) + dst->d_fieldmask |= QC_RT_SPC_HARD; + if (src->d_fieldmask & FS_DQ_BTIMER) + dst->d_fieldmask |= QC_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_ITIMER) + dst->d_fieldmask |= QC_INO_TIMER; + if (src->d_fieldmask & FS_DQ_RTBTIMER) + dst->d_fieldmask |= QC_RT_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_BWARNS) + dst->d_fieldmask |= QC_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_IWARNS) + dst->d_fieldmask |= QC_INO_WARNS; + if (src->d_fieldmask & FS_DQ_RTBWARNS) + dst->d_fieldmask |= QC_RT_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_BCOUNT) + dst->d_fieldmask |= QC_SPACE; + if (src->d_fieldmask & FS_DQ_ICOUNT) + dst->d_fieldmask |= QC_INO_COUNT; + if (src->d_fieldmask & FS_DQ_RTBCOUNT) + dst->d_fieldmask |= QC_RT_SPACE; +} + static int quota_setxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; + struct qc_dqblk qdq; struct kqid qid; if (copy_from_user(&fdq, addr, sizeof(fdq))) @@ -260,13 +338,44 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; - return sb->s_qcop->set_dqblk(sb, qid, &fdq); + copy_from_xfs_dqblk(&qdq, &fdq); + return sb->s_qcop->set_dqblk(sb, qid, &qdq); +} + +static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src, + int type, qid_t id) +{ + memset(dst, 0, sizeof(*dst)); + dst->d_version = FS_DQUOT_VERSION; + dst->d_id = id; + if (type == USRQUOTA) + dst->d_flags = FS_USER_QUOTA; + else if (type == PRJQUOTA) + dst->d_flags = FS_PROJ_QUOTA; + else + dst->d_flags = FS_GROUP_QUOTA; + dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit); + dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit); + dst->d_ino_hardlimit = src->d_ino_hardlimit; + dst->d_ino_softlimit = src->d_ino_softlimit; + dst->d_bcount = quota_btobb(src->d_space); + dst->d_icount = src->d_ino_count; + dst->d_itimer = src->d_ino_timer; + dst->d_btimer = src->d_spc_timer; + dst->d_iwarns = src->d_ino_warns; + dst->d_bwarns = src->d_spc_warns; + dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit); + dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit); + dst->d_rtbcount = quota_btobb(src->d_rt_space); + dst->d_rtbtimer = src->d_rt_spc_timer; + dst->d_rtbwarns = src->d_rt_spc_warns; } static int quota_getxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; + struct qc_dqblk qdq; struct kqid qid; int ret; @@ -275,8 +384,11 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; - ret = sb->s_qcop->get_dqblk(sb, qid, &fdq); - if (!ret && copy_to_user(addr, &fdq, sizeof(fdq))) + ret = sb->s_qcop->get_dqblk(sb, qid, &qdq); + if (ret) + return ret; + copy_to_xfs_dqblk(&fdq, &qdq, type, id); + if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } diff --git a/fs/udf/file.c b/fs/udf/file.c index bb15771b92ae..08f3555fbeac 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -224,7 +224,7 @@ out: static int udf_release_file(struct inode *inode, struct file *filp) { if (filp->f_mode & FMODE_WRITE && - atomic_read(&inode->i_writecount) > 1) { + atomic_read(&inode->i_writecount) == 1) { /* * Grab i_mutex to avoid races with writes changing i_size * while we are running. diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 3a07a937e232..41f6c0b9d51c 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -166,9 +166,9 @@ extern void xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint); /* quota ops */ extern int xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint); extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t, - uint, struct fs_disk_quota *); + uint, struct qc_dqblk *); extern int xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint, - struct fs_disk_quota *); + struct qc_dqblk *); extern int xfs_qm_scall_getqstat(struct xfs_mount *, struct fs_quota_stat *); extern int xfs_qm_scall_getqstatv(struct xfs_mount *, diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 74fca68e43b6..cb6168ec92c9 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -39,7 +39,6 @@ STATIC int xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint); STATIC int xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *, uint); STATIC uint xfs_qm_export_flags(uint); -STATIC uint xfs_qm_export_qtype_flags(uint); /* * Turn off quota accounting and/or enforcement for all udquots and/or @@ -573,8 +572,8 @@ xfs_qm_scall_getqstatv( return 0; } -#define XFS_DQ_MASK \ - (FS_DQ_LIMIT_MASK | FS_DQ_TIMER_MASK | FS_DQ_WARNS_MASK) +#define XFS_QC_MASK \ + (QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK) /* * Adjust quota limits, and start/stop timers accordingly. @@ -584,7 +583,7 @@ xfs_qm_scall_setqlim( struct xfs_mount *mp, xfs_dqid_t id, uint type, - fs_disk_quota_t *newlim) + struct qc_dqblk *newlim) { struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_disk_dquot *ddq; @@ -593,9 +592,9 @@ xfs_qm_scall_setqlim( int error; xfs_qcnt_t hard, soft; - if (newlim->d_fieldmask & ~XFS_DQ_MASK) + if (newlim->d_fieldmask & ~XFS_QC_MASK) return -EINVAL; - if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0) + if ((newlim->d_fieldmask & XFS_QC_MASK) == 0) return 0; /* @@ -633,11 +632,11 @@ xfs_qm_scall_setqlim( /* * Make sure that hardlimits are >= soft limits before changing. */ - hard = (newlim->d_fieldmask & FS_DQ_BHARD) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) : + hard = (newlim->d_fieldmask & QC_SPC_HARD) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) : be64_to_cpu(ddq->d_blk_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) : + soft = (newlim->d_fieldmask & QC_SPC_SOFT) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) : be64_to_cpu(ddq->d_blk_softlimit); if (hard == 0 || hard >= soft) { ddq->d_blk_hardlimit = cpu_to_be64(hard); @@ -650,11 +649,11 @@ xfs_qm_scall_setqlim( } else { xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft); } - hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) : + hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) : be64_to_cpu(ddq->d_rtb_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) : + soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) : be64_to_cpu(ddq->d_rtb_softlimit); if (hard == 0 || hard >= soft) { ddq->d_rtb_hardlimit = cpu_to_be64(hard); @@ -667,10 +666,10 @@ xfs_qm_scall_setqlim( xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft); } - hard = (newlim->d_fieldmask & FS_DQ_IHARD) ? + hard = (newlim->d_fieldmask & QC_INO_HARD) ? (xfs_qcnt_t) newlim->d_ino_hardlimit : be64_to_cpu(ddq->d_ino_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ? + soft = (newlim->d_fieldmask & QC_INO_SOFT) ? (xfs_qcnt_t) newlim->d_ino_softlimit : be64_to_cpu(ddq->d_ino_softlimit); if (hard == 0 || hard >= soft) { @@ -687,12 +686,12 @@ xfs_qm_scall_setqlim( /* * Update warnings counter(s) if requested */ - if (newlim->d_fieldmask & FS_DQ_BWARNS) - ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns); - if (newlim->d_fieldmask & FS_DQ_IWARNS) - ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns); - if (newlim->d_fieldmask & FS_DQ_RTBWARNS) - ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns); + if (newlim->d_fieldmask & QC_SPC_WARNS) + ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns); + if (newlim->d_fieldmask & QC_INO_WARNS) + ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns); + if (newlim->d_fieldmask & QC_RT_SPC_WARNS) + ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns); if (id == 0) { /* @@ -702,24 +701,24 @@ xfs_qm_scall_setqlim( * soft and hard limit values (already done, above), and * for warnings. */ - if (newlim->d_fieldmask & FS_DQ_BTIMER) { - q->qi_btimelimit = newlim->d_btimer; - ddq->d_btimer = cpu_to_be32(newlim->d_btimer); + if (newlim->d_fieldmask & QC_SPC_TIMER) { + q->qi_btimelimit = newlim->d_spc_timer; + ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer); } - if (newlim->d_fieldmask & FS_DQ_ITIMER) { - q->qi_itimelimit = newlim->d_itimer; - ddq->d_itimer = cpu_to_be32(newlim->d_itimer); + if (newlim->d_fieldmask & QC_INO_TIMER) { + q->qi_itimelimit = newlim->d_ino_timer; + ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer); } - if (newlim->d_fieldmask & FS_DQ_RTBTIMER) { - q->qi_rtbtimelimit = newlim->d_rtbtimer; - ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer); + if (newlim->d_fieldmask & QC_RT_SPC_TIMER) { + q->qi_rtbtimelimit = newlim->d_rt_spc_timer; + ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer); } - if (newlim->d_fieldmask & FS_DQ_BWARNS) - q->qi_bwarnlimit = newlim->d_bwarns; - if (newlim->d_fieldmask & FS_DQ_IWARNS) - q->qi_iwarnlimit = newlim->d_iwarns; - if (newlim->d_fieldmask & FS_DQ_RTBWARNS) - q->qi_rtbwarnlimit = newlim->d_rtbwarns; + if (newlim->d_fieldmask & QC_SPC_WARNS) + q->qi_bwarnlimit = newlim->d_spc_warns; + if (newlim->d_fieldmask & QC_INO_WARNS) + q->qi_iwarnlimit = newlim->d_ino_warns; + if (newlim->d_fieldmask & QC_RT_SPC_WARNS) + q->qi_rtbwarnlimit = newlim->d_rt_spc_warns; } else { /* * If the user is now over quota, start the timelimit. @@ -824,7 +823,7 @@ xfs_qm_scall_getquota( struct xfs_mount *mp, xfs_dqid_t id, uint type, - struct fs_disk_quota *dst) + struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; @@ -848,28 +847,25 @@ xfs_qm_scall_getquota( } memset(dst, 0, sizeof(*dst)); - dst->d_version = FS_DQUOT_VERSION; - dst->d_flags = xfs_qm_export_qtype_flags(dqp->q_core.d_flags); - dst->d_id = be32_to_cpu(dqp->q_core.d_id); - dst->d_blk_hardlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); - dst->d_blk_softlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit)); + dst->d_spc_hardlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); + dst->d_spc_softlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit)); dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit); dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit); - dst->d_bcount = XFS_FSB_TO_BB(mp, dqp->q_res_bcount); - dst->d_icount = dqp->q_res_icount; - dst->d_btimer = be32_to_cpu(dqp->q_core.d_btimer); - dst->d_itimer = be32_to_cpu(dqp->q_core.d_itimer); - dst->d_iwarns = be16_to_cpu(dqp->q_core.d_iwarns); - dst->d_bwarns = be16_to_cpu(dqp->q_core.d_bwarns); - dst->d_rtb_hardlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit)); - dst->d_rtb_softlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit)); - dst->d_rtbcount = XFS_FSB_TO_BB(mp, dqp->q_res_rtbcount); - dst->d_rtbtimer = be32_to_cpu(dqp->q_core.d_rtbtimer); - dst->d_rtbwarns = be16_to_cpu(dqp->q_core.d_rtbwarns); + dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount); + dst->d_ino_count = dqp->q_res_icount; + dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer); + dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer); + dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns); + dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns); + dst->d_rt_spc_hardlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit)); + dst->d_rt_spc_softlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit)); + dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount); + dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer); + dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns); /* * Internally, we don't reset all the timers when quota enforcement @@ -882,23 +878,23 @@ xfs_qm_scall_getquota( dqp->q_core.d_flags == XFS_DQ_GROUP) || (!XFS_IS_PQUOTA_ENFORCED(mp) && dqp->q_core.d_flags == XFS_DQ_PROJ)) { - dst->d_btimer = 0; - dst->d_itimer = 0; - dst->d_rtbtimer = 0; + dst->d_spc_timer = 0; + dst->d_ino_timer = 0; + dst->d_rt_spc_timer = 0; } #ifdef DEBUG - if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == FS_USER_QUOTA) || - (XFS_IS_GQUOTA_ENFORCED(mp) && dst->d_flags == FS_GROUP_QUOTA) || - (XFS_IS_PQUOTA_ENFORCED(mp) && dst->d_flags == FS_PROJ_QUOTA)) && - dst->d_id != 0) { - if ((dst->d_bcount > dst->d_blk_softlimit) && - (dst->d_blk_softlimit > 0)) { - ASSERT(dst->d_btimer != 0); + if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) || + (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) || + (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) && + id != 0) { + if ((dst->d_space > dst->d_spc_softlimit) && + (dst->d_spc_softlimit > 0)) { + ASSERT(dst->d_spc_timer != 0); } - if ((dst->d_icount > dst->d_ino_softlimit) && + if ((dst->d_ino_count > dst->d_ino_softlimit) && (dst->d_ino_softlimit > 0)) { - ASSERT(dst->d_itimer != 0); + ASSERT(dst->d_ino_timer != 0); } } #endif @@ -908,26 +904,6 @@ out_put: } STATIC uint -xfs_qm_export_qtype_flags( - uint flags) -{ - /* - * Can't be more than one, or none. - */ - ASSERT((flags & (FS_PROJ_QUOTA | FS_USER_QUOTA)) != - (FS_PROJ_QUOTA | FS_USER_QUOTA)); - ASSERT((flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)) != - (FS_PROJ_QUOTA | FS_GROUP_QUOTA)); - ASSERT((flags & (FS_USER_QUOTA | FS_GROUP_QUOTA)) != - (FS_USER_QUOTA | FS_GROUP_QUOTA)); - ASSERT((flags & (FS_PROJ_QUOTA|FS_USER_QUOTA|FS_GROUP_QUOTA)) != 0); - - return (flags & XFS_DQ_USER) ? - FS_USER_QUOTA : (flags & XFS_DQ_PROJ) ? - FS_PROJ_QUOTA : FS_GROUP_QUOTA; -} - -STATIC uint xfs_qm_export_flags( uint flags) { diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 7542bbeca6a1..801a84c1cdc3 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -131,7 +131,7 @@ STATIC int xfs_fs_get_dqblk( struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); @@ -141,14 +141,14 @@ xfs_fs_get_dqblk( return -ESRCH; return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), fdq); + xfs_quota_type(qid.type), qdq); } STATIC int xfs_fs_set_dqblk( struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); @@ -160,7 +160,7 @@ xfs_fs_set_dqblk( return -ESRCH; return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), fdq); + xfs_quota_type(qid.type), qdq); } const struct quotactl_ops xfs_quotactl_operations = { diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index cd62bf4289e9..88ea64e9a91c 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -67,8 +67,7 @@ int af_alg_unregister_type(const struct af_alg_type *type); int af_alg_release(struct socket *sock); int af_alg_accept(struct sock *sk, struct socket *newsock); -int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len, - int write); +int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e3a1721c8354..7c7695940ddd 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -228,7 +228,9 @@ struct i2c_client { struct device dev; /* the device structure */ int irq; /* irq issued by device */ struct list_head detected; +#if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ +#endif }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) @@ -253,6 +255,7 @@ static inline void i2c_set_clientdata(struct i2c_client *dev, void *data) /* I2C slave support */ +#if IS_ENABLED(CONFIG_I2C_SLAVE) enum i2c_slave_event { I2C_SLAVE_REQ_READ_START, I2C_SLAVE_REQ_READ_END, @@ -269,6 +272,7 @@ static inline int i2c_slave_event(struct i2c_client *client, { return client->slave_cb(client, event, val); } +#endif /** * struct i2c_board_info - template for device creation @@ -404,8 +408,10 @@ struct i2c_algorithm { /* To determine what the adapter supports */ u32 (*functionality) (struct i2c_adapter *); +#if IS_ENABLED(CONFIG_I2C_SLAVE) int (*reg_slave)(struct i2c_client *client); int (*unreg_slave)(struct i2c_client *client); +#endif }; /** diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4f4eea8a6288..b9c7897dc566 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1017,6 +1017,15 @@ struct ieee80211_mmie { u8 mic[8]; } __packed; +/* Management MIC information element (IEEE 802.11w) for GMAC and CMAC-256 */ +struct ieee80211_mmie_16 { + u8 element_id; + u8 length; + __le16 key_id; + u8 sequence_number[6]; + u8 mic[16]; +} __packed; + struct ieee80211_vendor_ie { u8 element_id; u8 len; @@ -1994,9 +2003,15 @@ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, WLAN_KEY_LEN_WEP104 = 13, WLAN_KEY_LEN_CCMP = 16, + WLAN_KEY_LEN_CCMP_256 = 32, WLAN_KEY_LEN_TKIP = 32, WLAN_KEY_LEN_AES_CMAC = 16, WLAN_KEY_LEN_SMS4 = 32, + WLAN_KEY_LEN_GCMP = 16, + WLAN_KEY_LEN_GCMP_256 = 32, + WLAN_KEY_LEN_BIP_CMAC_256 = 32, + WLAN_KEY_LEN_BIP_GMAC_128 = 16, + WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; #define IEEE80211_WEP_IV_LEN 4 @@ -2004,9 +2019,16 @@ enum ieee80211_key_len { #define IEEE80211_CCMP_HDR_LEN 8 #define IEEE80211_CCMP_MIC_LEN 8 #define IEEE80211_CCMP_PN_LEN 6 +#define IEEE80211_CCMP_256_HDR_LEN 8 +#define IEEE80211_CCMP_256_MIC_LEN 16 +#define IEEE80211_CCMP_256_PN_LEN 6 #define IEEE80211_TKIP_IV_LEN 8 #define IEEE80211_TKIP_ICV_LEN 4 #define IEEE80211_CMAC_PN_LEN 6 +#define IEEE80211_GMAC_PN_LEN 6 +#define IEEE80211_GCMP_HDR_LEN 8 +#define IEEE80211_GCMP_MIC_LEN 16 +#define IEEE80211_GCMP_PN_LEN 6 /* Public action codes */ enum ieee80211_pub_actioncode { @@ -2230,6 +2252,11 @@ enum ieee80211_sa_query_action { #define WLAN_CIPHER_SUITE_WEP104 0x000FAC05 #define WLAN_CIPHER_SUITE_AES_CMAC 0x000FAC06 #define WLAN_CIPHER_SUITE_GCMP 0x000FAC08 +#define WLAN_CIPHER_SUITE_GCMP_256 0x000FAC09 +#define WLAN_CIPHER_SUITE_CCMP_256 0x000FAC0A +#define WLAN_CIPHER_SUITE_BIP_GMAC_128 0x000FAC0B +#define WLAN_CIPHER_SUITE_BIP_GMAC_256 0x000FAC0C +#define WLAN_CIPHER_SUITE_BIP_CMAC_256 0x000FAC0D #define WLAN_CIPHER_SUITE_SMS4 0x00147201 diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index bea465f24ebb..b11b28a30b9e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -472,27 +472,59 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query + * @type: first vlan protocol + * @depth: buffer to store length of eth and vlan tags in bytes * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 vlan_get_protocol(const struct sk_buff *skb) +static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, + int *depth) { - __be16 protocol = 0; - - if (skb_vlan_tag_present(skb) || - skb->protocol != cpu_to_be16(ETH_P_8021Q)) - protocol = skb->protocol; - else { - __be16 proto, *protop; - protop = skb_header_pointer(skb, offsetof(struct vlan_ethhdr, - h_vlan_encapsulated_proto), - sizeof(proto), &proto); - if (likely(protop)) - protocol = *protop; + unsigned int vlan_depth = skb->mac_len; + + /* if type is 802.1Q/AD then the header should already be + * present at mac_len - VLAN_HLEN (if mac_len > 0), or at + * ETH_HLEN otherwise + */ + if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { + if (vlan_depth) { + if (WARN_ON(vlan_depth < VLAN_HLEN)) + return 0; + vlan_depth -= VLAN_HLEN; + } else { + vlan_depth = ETH_HLEN; + } + do { + struct vlan_hdr *vh; + + if (unlikely(!pskb_may_pull(skb, + vlan_depth + VLAN_HLEN))) + return 0; + + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } while (type == htons(ETH_P_8021Q) || + type == htons(ETH_P_8021AD)); } - return protocol; + if (depth) + *depth = vlan_depth; + + return type; +} + +/** + * vlan_get_protocol - get protocol EtherType. + * @skb: skbuff to query + * + * Returns the EtherType of the packet, regardless of whether it is + * vlan encapsulated (normal or hardware accelerated) or not. + */ +static inline __be16 vlan_get_protocol(struct sk_buff *skb) +{ + return __vlan_get_protocol(skb, skb->protocol, NULL); } static inline void vlan_set_encap_proto(struct sk_buff *skb, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2805062c013f..4d5169f5d7d1 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -125,6 +125,12 @@ struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; +struct inet6_cork { + struct ipv6_txoptions *opt; + u8 hop_limit; + u8 tclass; +}; + /** * struct ipv6_pinfo - ipv6 private area * @@ -217,11 +223,7 @@ struct ipv6_pinfo { struct ipv6_txoptions *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; - struct { - struct ipv6_txoptions *opt; - u8 hop_limit; - u8 tclass; - } cork; + struct inet6_cork cork; }; /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5449d2f4a1ef..64ce58bee6f5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -176,7 +176,7 @@ extern int _cond_resched(void); */ # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) -# define sched_annotate_sleep() __set_current_state(TASK_RUNNING) +# define sched_annotate_sleep() (current->task_state_change = 0) #else static inline void ___might_sleep(const char *file, int line, int preempt_offset) { } diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index ae95adc78509..7b6d4e9ff603 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -71,6 +71,7 @@ enum { /*master notify fw on finish for slave's flr*/ MLX4_CMD_INFORM_FLR_DONE = 0x5b, + MLX4_CMD_VIRT_PORT_MAP = 0x5c, MLX4_CMD_GET_OP_REQ = 0x59, /* TPT commands */ @@ -171,6 +172,12 @@ enum { }; enum { + /* virtual to physical port mapping opcode modifiers */ + MLX4_GET_PORT_VIRT2PHY = 0x0, + MLX4_SET_PORT_VIRT2PHY = 0x1, +}; + +enum { MLX4_MAILBOX_SIZE = 4096, MLX4_ACCESS_MEM_ALIGN = 256, }; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c95d659a39f2..c116cb02475c 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -70,6 +70,7 @@ enum { MLX4_FLAG_SLAVE = 1 << 3, MLX4_FLAG_SRIOV = 1 << 4, MLX4_FLAG_OLD_REG_MAC = 1 << 6, + MLX4_FLAG_BONDED = 1 << 7 }; enum { @@ -97,7 +98,7 @@ enum { MLX4_MAX_NUM_PF = 16, MLX4_MAX_NUM_VF = 126, MLX4_MAX_NUM_VF_P_PORT = 64, - MLX4_MFUNC_MAX = 80, + MLX4_MFUNC_MAX = 128, MLX4_MAX_EQ_NUM = 1024, MLX4_MFUNC_EQ_NUM = 4, MLX4_MFUNC_MAX_EQES = 8, @@ -201,7 +202,8 @@ enum { MLX4_DEV_CAP_FLAG2_SYS_EQS = 1LL << 17, MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18, MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19, - MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20 + MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20, + MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21 }; enum { @@ -253,9 +255,14 @@ enum { MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9, MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10, MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11, + MLX4_BMME_FLAG_PORT_REMAP = 1 << 24, MLX4_BMME_FLAG_VSD_INIT2RTR = 1 << 28, }; +enum { + MLX4_FLAG_PORT_REMAP = MLX4_BMME_FLAG_PORT_REMAP +}; + enum mlx4_event { MLX4_EVENT_TYPE_COMP = 0x00, MLX4_EVENT_TYPE_PATH_MIG = 0x01, @@ -1378,6 +1385,8 @@ int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port); int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port); int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port); +int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis); +int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2); int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port, diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 022055c8fb26..9553a73d2049 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -49,6 +49,10 @@ enum mlx4_dev_event { MLX4_DEV_EVENT_SLAVE_SHUTDOWN, }; +enum { + MLX4_INTFF_BONDING = 1 << 0 +}; + struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); @@ -57,11 +61,26 @@ struct mlx4_interface { void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); struct list_head list; enum mlx4_protocol protocol; + int flags; }; int mlx4_register_interface(struct mlx4_interface *intf); void mlx4_unregister_interface(struct mlx4_interface *intf); +int mlx4_bond(struct mlx4_dev *dev); +int mlx4_unbond(struct mlx4_dev *dev); +static inline int mlx4_is_bonded(struct mlx4_dev *dev) +{ + return !!(dev->flags & MLX4_FLAG_BONDED); +} + +struct mlx4_port_map { + u8 port1; + u8 port2; +}; + +int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); + void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); static inline u64 mlx4_mac_to_u64(u8 *addr) diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 467ccdf94c98..2bbc62aa818a 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -96,6 +96,7 @@ enum { MLX4_QP_BIT_RRE = 1 << 15, MLX4_QP_BIT_RWE = 1 << 14, MLX4_QP_BIT_RAE = 1 << 13, + MLX4_QP_BIT_FPP = 1 << 3, MLX4_QP_BIT_RIC = 1 << 4, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 80fc92a49649..dd5ea3016fc4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1070,6 +1070,7 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ #define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ +#define VM_FAULT_SIGSEGV 0x0040 #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ @@ -1078,8 +1079,9 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ - VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE) +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \ + VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \ + VM_FAULT_FALLBACK) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 8e30685affeb..7d59dc6ab789 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -66,6 +66,7 @@ enum { NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ + NETIF_F_HW_SWITCH_OFFLOAD_BIT, /* HW switch offload */ /* * Add your fresh new feature above and remember to update @@ -124,6 +125,7 @@ enum { #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) +#define NETIF_F_HW_SWITCH_OFFLOAD __NETIF_F(HW_SWITCH_OFFLOAD) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ @@ -159,7 +161,9 @@ enum { */ #define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \ NETIF_F_SG | NETIF_F_HIGHDMA | \ - NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED) + NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED | \ + NETIF_F_HW_SWITCH_OFFLOAD) + /* * If one device doesn't support one of these features, then disable it * for all in netdev_increment_features. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 642d426a668f..ce784d5018e0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -51,6 +51,7 @@ #include <linux/netdev_features.h> #include <linux/neighbour.h> #include <uapi/linux/netdevice.h> +#include <uapi/linux/if_bonding.h> struct netpoll_info; struct device; @@ -1154,13 +1155,15 @@ struct net_device_ops { int idx); int (*ndo_bridge_setlink)(struct net_device *dev, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, + u16 flags); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask); int (*ndo_bridge_dellink)(struct net_device *dev, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, + u16 flags); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, @@ -1514,6 +1517,8 @@ struct net_device { struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; + struct list_head ptype_all; + struct list_head ptype_specific; struct { struct list_head upper; @@ -2052,6 +2057,7 @@ struct pcpu_sw_netstats { #define NETDEV_RESEND_IGMP 0x0016 #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 +#define NETDEV_BONDING_INFO 0x0019 int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -2314,6 +2320,21 @@ do { \ compute_pseudo(skb, proto)); \ } while (0) +static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + int start, int offset) +{ + __wsum delta; + + BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); + + delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); + + /* Adjust skb->csum since we changed the packet */ + skb->csum = csum_add(skb->csum, delta); + NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); +} + + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3475,6 +3496,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); +struct netdev_bonding_info { + ifslave slave; + ifbond master; +}; + +struct netdev_notifier_bonding_info { + struct netdev_notifier_info info; /* must be first */ + struct netdev_bonding_info bonding_info; +}; + +void netdev_bonding_info_change(struct net_device *dev, + struct netdev_bonding_info *bonding_info); + static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4f7a61ca4b39..664de5a4ec46 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -450,11 +450,6 @@ struct perf_event { #endif /* CONFIG_PERF_EVENTS */ }; -enum perf_event_context_type { - task_context, - cpu_context, -}; - /** * struct perf_event_context - event context structure * @@ -462,7 +457,6 @@ enum perf_event_context_type { */ struct perf_event_context { struct pmu *pmu; - enum perf_event_context_type type; /* * Protect the states of the events in the list, * nr_active, and the list: diff --git a/include/linux/quota.h b/include/linux/quota.h index 50978b781a19..097d7eb2441e 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -321,6 +321,49 @@ struct dquot_operations { struct path; +/* Structure for communicating via ->get_dqblk() & ->set_dqblk() */ +struct qc_dqblk { + int d_fieldmask; /* mask of fields to change in ->set_dqblk() */ + u64 d_spc_hardlimit; /* absolute limit on used space */ + u64 d_spc_softlimit; /* preferred limit on used space */ + u64 d_ino_hardlimit; /* maximum # allocated inodes */ + u64 d_ino_softlimit; /* preferred inode limit */ + u64 d_space; /* Space owned by the user */ + u64 d_ino_count; /* # inodes owned by the user */ + s64 d_ino_timer; /* zero if within inode limits */ + /* if not, we refuse service */ + s64 d_spc_timer; /* similar to above; for space */ + int d_ino_warns; /* # warnings issued wrt num inodes */ + int d_spc_warns; /* # warnings issued wrt used space */ + u64 d_rt_spc_hardlimit; /* absolute limit on realtime space */ + u64 d_rt_spc_softlimit; /* preferred limit on RT space */ + u64 d_rt_space; /* realtime space owned */ + s64 d_rt_spc_timer; /* similar to above; for RT space */ + int d_rt_spc_warns; /* # warnings issued wrt RT space */ +}; + +/* Field specifiers for ->set_dqblk() in struct qc_dqblk */ +#define QC_INO_SOFT (1<<0) +#define QC_INO_HARD (1<<1) +#define QC_SPC_SOFT (1<<2) +#define QC_SPC_HARD (1<<3) +#define QC_RT_SPC_SOFT (1<<4) +#define QC_RT_SPC_HARD (1<<5) +#define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \ + QC_RT_SPC_SOFT | QC_RT_SPC_HARD) +#define QC_SPC_TIMER (1<<6) +#define QC_INO_TIMER (1<<7) +#define QC_RT_SPC_TIMER (1<<8) +#define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER) +#define QC_SPC_WARNS (1<<9) +#define QC_INO_WARNS (1<<10) +#define QC_RT_SPC_WARNS (1<<11) +#define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS) +#define QC_SPACE (1<<12) +#define QC_INO_COUNT (1<<13) +#define QC_RT_SPACE (1<<14) +#define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE) + /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); @@ -329,8 +372,8 @@ struct quotactl_ops { int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); - int (*get_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *); - int (*set_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *); + int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); + int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); int (*set_xstate)(struct super_block *, unsigned int, int); int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index f23538a6e411..29e3455f7d41 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -98,9 +98,9 @@ int dquot_quota_sync(struct super_block *sb, int type); int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int dquot_get_dqblk(struct super_block *sb, struct kqid id, - struct fs_disk_quota *di); + struct qc_dqblk *di); int dquot_set_dqblk(struct super_block *sb, struct kqid id, - struct fs_disk_quota *di); + struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); int dquot_transfer(struct inode *inode, struct iattr *iattr); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e0337844358e..58851275fed9 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -18,6 +18,7 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H +#include <linux/compiler.h> #include <linux/list_nulls.h> #include <linux/workqueue.h> #include <linux/mutex.h> @@ -111,6 +112,7 @@ struct rhashtable_params { * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping + * @walkers: List of active walkers * @being_destroyed: True if table is set up for destruction */ struct rhashtable { @@ -121,9 +123,36 @@ struct rhashtable { struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; + struct list_head walkers; bool being_destroyed; }; +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @resize: Resize event occured + */ +struct rhashtable_walker { + struct list_head list; + bool resize; +}; + +/** + * struct rhashtable_iter - Hash table iterator, fits into netlink cb + * @ht: Table to iterate through + * @p: Current pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhashtable_walker *walker; + unsigned int slot; + unsigned int skip; +}; + static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) { return NULLS_MARKER(ht->p.nulls_base + hash); @@ -179,6 +208,12 @@ bool rhashtable_lookup_compare_insert(struct rhashtable *ht, bool (*compare)(void *, void *), void *arg); +int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); +void rhashtable_walk_exit(struct rhashtable_iter *iter); +int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); +void *rhashtable_walk_next(struct rhashtable_iter *iter); +void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); + void rhashtable_destroy(struct rhashtable *ht); #define rht_dereference(p, ht) \ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 85ab7d72b54c..111e665455c3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -626,8 +626,11 @@ struct sk_buff { __u32 hash; __be16 vlan_proto; __u16 vlan_tci; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned int napi_id; +#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) + union { + unsigned int napi_id; + unsigned int sender_cpu; + }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; @@ -2484,19 +2487,18 @@ static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) } static inline int skb_add_data(struct sk_buff *skb, - char __user *from, int copy) + struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { - int err = 0; - __wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy), - copy, 0, &err); - if (!err) { + __wsum csum = 0; + if (csum_and_copy_from_iter(skb_put(skb, copy), copy, + &csum, from) == copy) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } - } else if (!copy_from_user(skb_put(skb, copy), from, copy)) + } else if (copy_from_iter(skb_put(skb, copy), copy, from) == copy) return 0; __skb_trim(skb, off); @@ -2693,8 +2695,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { - /* XXX: stripping const */ - return memcpy_fromiovec(data, (struct iovec *)msg->msg_iter.iov, len); + return copy_from_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) @@ -3096,6 +3097,27 @@ do { \ compute_pseudo(skb, proto)); \ } while (0) +/* Update skbuf and packet to reflect the remote checksum offload operation. + * When called, ptr indicates the starting point for skb->csum when + * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete + * here, skb_postpull_rcsum is done so skb->csum start is ptr. + */ +static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, + int start, int offset) +{ + __wsum delta; + + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + __skb_checksum_complete(skb); + skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); + } + + delta = remcsum_adjust(ptr, skb->csum, start, offset); + + /* Adjust skb->csum since we changed the packet */ + skb->csum = csum_add(skb->csum, delta); +} + #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) diff --git a/include/linux/socket.h b/include/linux/socket.h index 6e49a14365dc..5c19cba34dce 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -318,13 +318,6 @@ struct ucred { /* IPX options */ #define IPX_TYPE 1 -extern int csum_partial_copy_fromiovecend(unsigned char *kdata, - struct iovec *iov, - int offset, - unsigned int len, __wsum *csump); -extern unsigned long iov_pages(const struct iovec *iov, int offset, - unsigned long nr_segs); - extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); diff --git a/include/linux/uio.h b/include/linux/uio.h index 1c5e453f7ea9..3e0cb4ea3905 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -135,10 +135,4 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); -int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); -int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, - int offset, int len); -int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, - int offset, int len); - #endif diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index 5691f752ce8f..63df3a2a8ce5 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -74,7 +74,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair, ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size, int mode); ssize_t vmci_qpair_enquev(struct vmci_qp *qpair, - void *iov, size_t iov_size, int mode); + struct msghdr *msg, size_t iov_size, int mode); ssize_t vmci_qpair_dequev(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, int mode); ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7777124bff55..52863c3e0b13 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -79,6 +79,8 @@ struct discovery_state { s8 rssi; u16 uuid_count; u8 (*uuids)[16]; + unsigned long scan_start; + unsigned long scan_duration; }; struct hci_conn_hash { @@ -145,6 +147,7 @@ struct oob_data { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; + u8 present; u8 hash192[16]; u8 rand192[16]; u8 hash256[16]; @@ -232,6 +235,7 @@ struct hci_dev { __u16 conn_info_min_age; __u16 conn_info_max_age; __u8 ssp_debug_mode; + __u8 hw_error_code; __u32 clock; __u16 devid_source; @@ -293,6 +297,7 @@ struct hci_dev { struct work_struct power_on; struct delayed_work power_off; + struct work_struct error_reset; __u16 discov_timeout; struct delayed_work discov_off; @@ -351,6 +356,7 @@ struct hci_dev { unsigned long dev_flags; struct delayed_work le_scan_disable; + struct delayed_work le_scan_restart; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_AD_LENGTH]; @@ -369,6 +375,7 @@ struct hci_dev { int (*setup)(struct hci_dev *hdev); int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); + void (*hw_error)(struct hci_dev *hdev, u8 code); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); }; @@ -527,6 +534,8 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev) hdev->discovery.uuid_count = 0; kfree(hdev->discovery.uuids); hdev->discovery.uuids = NULL; + hdev->discovery.scan_start = 0; + hdev->discovery.scan_duration = 0; } bool hci_discovery_active(struct hci_dev *hdev); @@ -1325,6 +1334,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event); #define DISCOV_INTERLEAVED_TIMEOUT 5120 /* msec */ #define DISCOV_INTERLEAVED_INQUIRY_LEN 0x04 #define DISCOV_BREDR_INQUIRY_LEN 0x08 +#define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len); int mgmt_new_settings(struct hci_dev *hdev); @@ -1369,7 +1379,6 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, void mgmt_auth_failed(struct hci_conn *conn, u8 status); void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status); void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); -void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 95c34d5180fa..e218a30f2061 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -301,10 +301,6 @@ struct mgmt_cp_user_passkey_neg_reply { #define MGMT_OP_READ_LOCAL_OOB_DATA 0x0020 #define MGMT_READ_LOCAL_OOB_DATA_SIZE 0 struct mgmt_rp_read_local_oob_data { - __u8 hash[16]; - __u8 rand[16]; -} __packed; -struct mgmt_rp_read_local_oob_ext_data { __u8 hash192[16]; __u8 rand192[16]; __u8 hash256[16]; diff --git a/include/net/bonding.h b/include/net/bonding.h index 29f53eacac0a..4e17095ad46a 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -150,6 +150,12 @@ struct bond_parm_tbl { int mode; }; +struct netdev_notify_work { + struct delayed_work work; + struct slave *slave; + struct net_device *dev; +}; + struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ @@ -243,6 +249,8 @@ struct bonding { #define bond_slave_get_rtnl(dev) \ ((struct slave *) rtnl_dereference(dev->rx_handler_data)) +void bond_queue_slave_event(struct slave *slave); + struct bond_vlan_tag { __be16 vlan_proto; unsigned short vlan_id; @@ -315,6 +323,7 @@ static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; + bond_queue_slave_event(slave); rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); } } @@ -323,6 +332,7 @@ static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; + bond_queue_slave_event(slave); rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); } } @@ -336,6 +346,7 @@ static inline void bond_set_slave_state(struct slave *slave, slave->backup = slave_state; if (notify) { rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + bond_queue_slave_event(slave); slave->should_notify = 0; } else { if (slave->should_notify) @@ -490,6 +501,12 @@ static inline bool bond_is_slave_inactive(struct slave *slave) return slave->inactive; } +static inline void bond_set_slave_link_state(struct slave *slave, int state) +{ + slave->link = state; + bond_queue_slave_event(slave); +} + static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) { struct in_device *in_dev; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7b44ba0a7632..64e09e1e8099 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1493,6 +1493,10 @@ struct cfg80211_match_set { * @rcu_head: RCU callback used to free the struct * @owner_nlportid: netlink portid of owner (if this should is a request * owned by a particular socket) + * @delay: delay in seconds to use before starting the first scan + * cycle. The driver may ignore this parameter and start + * immediately (or at any other time), if this feature is not + * supported. */ struct cfg80211_sched_scan_request { struct cfg80211_ssid *ssids; @@ -1506,6 +1510,7 @@ struct cfg80211_sched_scan_request { struct cfg80211_match_set *match_sets; int n_match_sets; s32 min_rssi_thold; + u32 delay; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h index 7ee2df083542..dc8fd81412bf 100644 --- a/include/net/flow_keys.h +++ b/include/net/flow_keys.h @@ -22,9 +22,9 @@ struct flow_keys { __be32 ports; __be16 port16[2]; }; - u16 thoff; - u16 n_proto; - u8 ip_proto; + u16 thoff; + __be16 n_proto; + u8 ip_proto; }; bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, diff --git a/include/net/ip.h b/include/net/ip.h index 14211eaff17f..025c61c0dffb 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -181,7 +181,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4292929392b0..8ae7c9edbd3c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -671,6 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } +u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, + struct in6_addr *src); +void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt); void ipv6_proxy_select_ident(struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); @@ -708,7 +711,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel) { if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) { - __be32 hash; + u32 hash; hash = skb_get_hash(skb); @@ -718,7 +721,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, */ hash ^= hash >> 12; - flowlabel = hash & IPV6_FLOWLABEL_MASK; + flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; } return flowlabel; @@ -788,6 +791,25 @@ int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); +int ip6_send_skb(struct sk_buff *skb); + +struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, + struct inet_cork_full *cork, + struct inet6_cork *v6_cork); +struct sk_buff *ip6_make_skb(struct sock *sk, + int getfrag(void *from, char *to, int offset, + int len, int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + int hlimit, int tclass, struct ipv6_txoptions *opt, + struct flowi6 *fl6, struct rt6_info *rt, + unsigned int flags, int dontfrag); + +static inline struct sk_buff *ip6_finish_skb(struct sock *sk) +{ + return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, + &inet6_sk(sk)->cork); +} + int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 275ee56152ad..d52914b75331 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -376,6 +376,12 @@ enum ieee80211_rssi_event { * @ssid_len: Length of SSID given in @ssid. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm + * @txpower_type: TX power adjustment used to control per packet Transmit + * Power Control (TPC) in lower driver for the current vif. In particular + * TPC is enabled if value passed in %txpower_type is + * NL80211_TX_POWER_LIMITED (allow using less than specified from + * userspace), whereas TPC is disabled if %txpower_type is set to + * NL80211_TX_POWER_FIXED (use value configured from userspace) * @p2p_noa_attr: P2P NoA attribute for P2P powersave */ struct ieee80211_bss_conf { @@ -411,6 +417,7 @@ struct ieee80211_bss_conf { size_t ssid_len; bool hidden_ssid; int txpower; + enum nl80211_tx_power_setting txpower_type; struct ieee80211_p2p_noa_attr p2p_noa_attr; }; @@ -1287,8 +1294,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); * @IEEE80211_KEY_FLAG_PAIRWISE: Set by mac80211, this flag indicates * that the key is pairwise rather then a shared key. * @IEEE80211_KEY_FLAG_SW_MGMT_TX: This flag should be set by the driver for a - * CCMP key if it requires CCMP encryption of management frames (MFP) to - * be done in software. + * CCMP/GCMP key if it requires CCMP/GCMP encryption of management frames + * (MFP) to be done in software. * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver * if space should be prepared for the IV, but the IV * itself should not be generated. Do not set together with @@ -1303,7 +1310,7 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); * RX, if your crypto engine can't deal with TX you can also set the * %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW. * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the - * driver for a CCMP key to indicate that is requires IV generation + * driver for a CCMP/GCMP key to indicate that is requires IV generation * only for managment frames (MFP). * @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the * driver for a key to indicate that sufficient tailroom must always @@ -1634,6 +1641,12 @@ struct ieee80211_tx_control { * be created. It is expected user-space will create vifs as * desired (and thus have them named as desired). * + * @IEEE80211_HW_SW_CRYPTO_CONTROL: The driver wants to control which of the + * crypto algorithms can be done in software - so don't automatically + * try to fall back to it if hardware crypto fails, but do so only if + * the driver returns 1. This also forces the driver to advertise its + * supported cipher suites. + * * @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface * queue mapping in order to use different queues (not just one per AC) * for different virtual interfaces. See the doc section on HW queue @@ -1681,6 +1694,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_MFP_CAPABLE = 1<<13, IEEE80211_HW_WANT_MONITOR_VIF = 1<<14, IEEE80211_HW_NO_AUTO_VIF = 1<<15, + IEEE80211_HW_SW_CRYPTO_CONTROL = 1<<16, /* free slots */ IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, IEEE80211_HW_CONNECTION_MONITOR = 1<<19, @@ -1955,6 +1969,11 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * added; if you return 0 then hw_key_idx must be assigned to the * hardware key index, you are free to use the full u8 range. * + * Note that in the case that the @IEEE80211_HW_SW_CRYPTO_CONTROL flag is + * set, mac80211 will not automatically fall back to software crypto if + * enabling hardware crypto failed. The set_key() call may also return the + * value 1 to permit this specific key/algorithm to be done in software. + * * When the cmd is %DISABLE_KEY then it must succeed. * * Note that it is permissible to not decrypt a frame even if a key @@ -4079,6 +4098,10 @@ void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf, * reverse order than in packet) * @aes_cmac: PN data, most significant byte first (big endian, * reverse order than in packet) + * @aes_gmac: PN data, most significant byte first (big endian, + * reverse order than in packet) + * @gcmp: PN data, most significant byte first (big endian, + * reverse order than in packet) */ struct ieee80211_key_seq { union { @@ -4092,6 +4115,12 @@ struct ieee80211_key_seq { struct { u8 pn[6]; } aes_cmac; + struct { + u8 pn[6]; + } aes_gmac; + struct { + u8 pn[6]; + } gcmp; }; }; @@ -4116,7 +4145,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, * ieee80211_get_key_rx_seq - get key RX sequence counter * * @keyconf: the parameter passed with the set key - * @tid: The TID, or -1 for the management frame value (CCMP only); + * @tid: The TID, or -1 for the management frame value (CCMP/GCMP only); * the value on TID 0 is also used for non-QoS frames. For * CMAC, only TID 0 is valid. * @seq: buffer to receive the sequence data @@ -4152,7 +4181,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, * ieee80211_set_key_rx_seq - set key RX sequence counter * * @keyconf: the parameter passed with the set key - * @tid: The TID, or -1 for the management frame value (CCMP only); + * @tid: The TID, or -1 for the management frame value (CCMP/GCMP only); * the value on TID 0 is also used for non-QoS frames. For * CMAC, only TID 0 is valid. * @seq: new sequence data diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3ae969e3acf0..9eaaa7884586 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -530,6 +530,8 @@ enum nft_chain_type { int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_type type); +int nft_chain_validate_hooks(const struct nft_chain *chain, + unsigned int hook_flags); struct nft_stats { u64 bytes; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 24945cefc4fd..e0bdcb147326 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -48,10 +48,12 @@ struct netns_ipv4 { struct hlist_head *fib_table_hash; struct sock *fibnl; - struct sock **icmp_sk; + struct sock * __percpu *icmp_sk; + struct inet_peer_base *peers; struct tcpm_hash_bucket *tcp_metrics_hash; unsigned int tcp_metrics_hash_log; + struct sock * __percpu *tcp_sk; struct netns_frags frags; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; diff --git a/include/net/ping.h b/include/net/ping.h index f074060bc5de..cc16d413f681 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -59,7 +59,7 @@ extern struct pingv6_ops pingv6_ops; struct pingfakehdr { struct icmphdr icmph; - struct iovec *iov; + struct msghdr *msg; sa_family_t family; __wsum wcheck; }; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 3d282cbb66bf..c605d305c577 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -79,6 +79,9 @@ struct Qdisc { struct netdev_queue *dev_queue; struct gnet_stats_rate_est64 rate_est; + struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_queue __percpu *cpu_qstats; + struct Qdisc *next_sched; struct sk_buff *gso_skb; /* @@ -86,15 +89,9 @@ struct Qdisc { */ unsigned long state; struct sk_buff_head q; - union { - struct gnet_stats_basic_packed bstats; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; - } __packed; + struct gnet_stats_basic_packed bstats; unsigned int __state; - union { - struct gnet_stats_queue qstats; - struct gnet_stats_queue __percpu *cpu_qstats; - } __packed; + struct gnet_stats_queue qstats; struct rcu_head rcu_head; int padded; atomic_t refcnt; diff --git a/include/net/sock.h b/include/net/sock.h index 15341499786c..d28b8fededd6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1803,27 +1803,25 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, - char __user *from, char *to, + struct iov_iter *from, char *to, int copy, int offset) { if (skb->ip_summed == CHECKSUM_NONE) { - int err = 0; - __wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err); - if (err) - return err; + __wsum csum = 0; + if (csum_and_copy_from_iter(to, copy, &csum, from) != copy) + return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { - if (!access_ok(VERIFY_READ, from, copy) || - __copy_from_user_nocache(to, from, copy)) + if (copy_from_iter_nocache(to, copy, from) != copy) return -EFAULT; - } else if (copy_from_user(to, from, copy)) + } else if (copy_from_iter(to, copy, from) != copy) return -EFAULT; return 0; } static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, - char __user *from, int copy) + struct iov_iter *from, int copy) { int err, offset = skb->len; @@ -1835,7 +1833,7 @@ static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, return err; } -static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from, +static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from, struct sk_buff *skb, struct page *page, int off, int copy) @@ -2239,6 +2237,7 @@ bool sk_net_capable(const struct sock *sk, int cap); extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; +extern int sysctl_tstamp_allow_data; extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 205e63698da9..cfcdac2e5d25 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,7 +43,14 @@ int register_netdev_switch_notifier(struct notifier_block *nb); int unregister_netdev_switch_notifier(struct notifier_block *nb); int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, struct netdev_switch_notifier_info *info); - +int netdev_switch_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int netdev_switch_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); #else static inline int netdev_switch_parent_id_get(struct net_device *dev, @@ -74,6 +81,34 @@ static inline int call_netdev_switch_notifiers(unsigned long val, struct net_dev return NOTIFY_DONE; } +static inline int netdev_switch_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int netdev_switch_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) +{ + return 0; +} + +static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) +{ + return 0; +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ diff --git a/include/net/tcp.h b/include/net/tcp.h index b8fdc6bab3f3..28e9bd3abceb 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -843,8 +843,8 @@ void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name); -void tcp_slow_start(struct tcp_sock *tp, u32 acked); -void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w); +u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); +void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); @@ -1713,4 +1713,19 @@ static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb) return dopt; } +/* locally generated TCP pure ACKs have skb->truesize == 2 + * (check tcp_send_ack() in net/ipv4/tcp_output.c ) + * This is much faster than dissecting the packet to find out. + * (Think of GRE encapsulations, IPv4, IPv6, ...) + */ +static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) +{ + return skb->truesize == 2; +} + +static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) +{ + skb->truesize = 2; +} + #endif /* _TCP_H */ diff --git a/include/net/udplite.h b/include/net/udplite.h index ae7c8d1fbcad..80761938b9a7 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -20,8 +20,7 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; - /* XXX: stripping const */ - return memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len); + return copy_from_iter(to, len, &msg->msg_iter) != len ? -EFAULT : 0; } /* Designate sk as UDP-Lite socket */ diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index edbc888ceb51..6d1abea9746e 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -24,8 +24,9 @@ enum { SOF_TIMESTAMPING_TX_SCHED = (1<<8), SOF_TIMESTAMPING_TX_ACK = (1<<9), SOF_TIMESTAMPING_OPT_CMSG = (1<<10), + SOF_TIMESTAMPING_OPT_TSONLY = (1<<11), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_CMSG, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TSONLY, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f52797a90816..68b294e83944 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -180,8 +180,8 @@ * %NL80211_ATTR_WIPHY and %NL80211_ATTR_WIPHY_NAME. * * @NL80211_CMD_GET_INTERFACE: Request an interface's configuration; - * either a dump request on a %NL80211_ATTR_WIPHY or a specific get - * on an %NL80211_ATTR_IFINDEX is supported. + * either a dump request for all interfaces or a specific get with a + * single %NL80211_ATTR_IFINDEX is supported. * @NL80211_CMD_SET_INTERFACE: Set type of a virtual interface, requires * %NL80211_ATTR_IFINDEX and %NL80211_ATTR_IFTYPE. * @NL80211_CMD_NEW_INTERFACE: Newly created virtual interface or response @@ -324,7 +324,9 @@ * if passed, define which channels should be scanned; if not * passed, all channels allowed for the current regulatory domain * are used. Extra IEs can also be passed from the userspace by - * using the %NL80211_ATTR_IE attribute. + * using the %NL80211_ATTR_IE attribute. The first cycle of the + * scheduled scan can be delayed by %NL80211_ATTR_SCHED_SCAN_DELAY + * is supplied. * @NL80211_CMD_STOP_SCHED_SCAN: stop a scheduled scan. Returns -ENOENT if * scheduled scan is not running. The caller may assume that as soon * as the call returns, it is safe to start a new scheduled scan again. @@ -1735,6 +1737,9 @@ enum nl80211_commands { * should be contained in the result as the sum of the respective counters * over all channels. * + * @NL80211_ATTR_SCHED_SCAN_DELAY: delay before a scheduled scan (or a + * WoWLAN net-detect scan) is started, u32 in seconds. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2098,6 +2103,10 @@ enum nl80211_attrs { NL80211_ATTR_SURVEY_RADIO_STATS, + NL80211_ATTR_NETNS_FD, + + NL80211_ATTR_SCHED_SCAN_DELAY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3741,11 +3750,12 @@ struct nl80211_pattern_support { * @NL80211_WOWLAN_TRIG_NET_DETECT: wake up when a configured network * is detected. This is a nested attribute that contains the * same attributes used with @NL80211_CMD_START_SCHED_SCAN. It - * specifies how the scan is performed (e.g. the interval and the - * channels to scan) as well as the scan results that will - * trigger a wake (i.e. the matchsets). This attribute is also - * sent in a response to @NL80211_CMD_GET_WIPHY, indicating the - * number of match sets supported by the driver (u32). + * specifies how the scan is performed (e.g. the interval, the + * channels to scan and the initial delay) as well as the scan + * results that will trigger a wake (i.e. the matchsets). This + * attribute is also sent in a response to + * @NL80211_CMD_GET_WIPHY, indicating the number of match sets + * supported by the driver (u32). * @NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS: nested attribute * containing an array with information about what triggered the * wake up. If no elements are present in the array, it means diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index d62316baae94..534b84710745 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -774,6 +774,8 @@ enum { TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */ + TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */ + __TCA_FQ_MAX }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 882f835a0d85..19efcf13375a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6776,7 +6776,6 @@ skip_type: __perf_event_init_context(&cpuctx->ctx); lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex); lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock); - cpuctx->ctx.type = cpu_context; cpuctx->ctx.pmu = pmu; __perf_cpu_hrtimer_init(cpuctx, cpu); @@ -7420,7 +7419,19 @@ SYSCALL_DEFINE5(perf_event_open, * task or CPU context: */ if (move_group) { - if (group_leader->ctx->type != ctx->type) + /* + * Make sure we're both on the same task, or both + * per-cpu events. + */ + if (group_leader->ctx->task != ctx->task) + goto err_context; + + /* + * Make sure we're both events for the same CPU; + * grouping events for different CPUs is broken; since + * you can never concurrently schedule them anyhow. + */ + if (group_leader->cpu != event->cpu) goto err_context; } else { if (group_leader->ctx != ctx) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c0accc00566e..e628cb11b560 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7292,13 +7292,12 @@ void __might_sleep(const char *file, int line, int preempt_offset) * since we will exit with TASK_RUNNING make sure we enter with it, * otherwise we will destroy state. */ - if (WARN_ONCE(current->state != TASK_RUNNING, + WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, "do not call blocking ops when !TASK_RUNNING; " "state=%lx set at [<%p>] %pS\n", current->state, (void *)current->task_state_change, - (void *)current->task_state_change)) - __set_current_state(TASK_RUNNING); + (void *)current->task_state_change); ___might_sleep(file, line, preempt_offset); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 5f2ce616c046..a8f3c9993229 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1586,7 +1586,7 @@ config TEST_KSTRTOX tristate "Test kstrto*() family of functions at runtime" config TEST_RHASHTABLE - bool "Perform selftest on resizable hash table" + tristate "Perform selftest on resizable hash table" default n help Enable this option to test the rhashtable functions at boot. diff --git a/lib/Makefile b/lib/Makefile index 3c3b30b9e020..7db78934ec07 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -24,7 +24,7 @@ obj-y += lockref.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ - gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \ + gcd.o lcm.o list_sort.o uuid.o flex_array.o clz_ctz.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \ percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o obj-y += string_helpers.o @@ -35,6 +35,7 @@ obj-$(CONFIG_TEST_LKM) += test_module.o obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o obj-$(CONFIG_TEST_BPF) += test_bpf.o obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o +obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG diff --git a/lib/checksum.c b/lib/checksum.c index 129775eb6de6..8b39e86dbab5 100644 --- a/lib/checksum.c +++ b/lib/checksum.c @@ -181,6 +181,15 @@ csum_partial_copy(const void *src, void *dst, int len, __wsum sum) EXPORT_SYMBOL(csum_partial_copy); #ifndef csum_tcpudp_nofold +static inline u32 from64to32(u64 x) +{ + /* add up 32-bit and 32-bit for 32+c bit */ + x = (x & 0xffffffff) + (x >> 32); + /* add up carry.. */ + x = (x & 0xffffffff) + (x >> 32); + return (u32)x; +} + __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len, unsigned short proto, @@ -195,8 +204,7 @@ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, #else s += (proto + len) << 8; #endif - s += (s >> 32); - return (__force __wsum)s; + return (__force __wsum)from64to32(s); } EXPORT_SYMBOL(csum_tcpudp_nofold); #endif diff --git a/lib/iovec.c b/lib/iovec.c deleted file mode 100644 index 2d99cb4a5006..000000000000 --- a/lib/iovec.c +++ /dev/null @@ -1,87 +0,0 @@ -#include <linux/uaccess.h> -#include <linux/export.h> -#include <linux/uio.h> - -/* - * Copy iovec to kernel. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, len, iov->iov_len); - if (copy_from_user(kdata, iov->iov_base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov->iov_base += copy; - iov->iov_len -= copy; - } - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_fromiovec); - -/* - * Copy kernel to iovec. Returns -EFAULT on error. - */ - -int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, - int offset, int len) -{ - int copy; - for (; len > 0; ++iov) { - /* Skip over the finished iovecs */ - if (unlikely(offset >= iov->iov_len)) { - offset -= iov->iov_len; - continue; - } - copy = min_t(unsigned int, iov->iov_len - offset, len); - if (copy_to_user(iov->iov_base + offset, kdata, copy)) - return -EFAULT; - offset = 0; - kdata += copy; - len -= copy; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_toiovecend); - -/* - * Copy iovec to kernel. Returns -EFAULT on error. - */ - -int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, - int offset, int len) -{ - /* No data? Done! */ - if (len == 0) - return 0; - - /* Skip over the finished iovecs */ - while (offset >= iov->iov_len) { - offset -= iov->iov_len; - iov++; - } - - while (len > 0) { - u8 __user *base = iov->iov_base + offset; - int copy = min_t(unsigned int, len, iov->iov_len - offset); - - offset = 0; - if (copy_from_user(kdata, base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_fromiovecend); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index bc2d0d80d1f9..e96fc00208bc 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -1,7 +1,7 @@ /* * Resizable, Scalable, Concurrent Hash Table * - * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch> + * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * Based on the following paper: @@ -34,12 +34,17 @@ enum { RHT_LOCK_NORMAL, RHT_LOCK_NESTED, - RHT_LOCK_NESTED2, }; /* The bucket lock is selected based on the hash and protects mutations * on a group of hash buckets. * + * A maximum of tbl->size/2 bucket locks is allocated. This ensures that + * a single lock always covers both buckets which may both contains + * entries which link to the same bucket of the old table during resizing. + * This allows to simplify the locking as locking the bucket in both + * tables during resize always guarantee protection. + * * IMPORTANT: When holding the bucket lock of both the old and new table * during expansions and shrinking, the old bucket lock must always be * acquired first. @@ -49,26 +54,6 @@ static spinlock_t *bucket_lock(const struct bucket_table *tbl, u32 hash) return &tbl->locks[hash & tbl->locks_mask]; } -#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT)) -#define ASSERT_BUCKET_LOCK(TBL, HASH) \ - BUG_ON(!lockdep_rht_bucket_is_held(TBL, HASH)) - -#ifdef CONFIG_PROVE_LOCKING -int lockdep_rht_mutex_is_held(struct rhashtable *ht) -{ - return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1; -} -EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); - -int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) -{ - spinlock_t *lock = bucket_lock(tbl, hash); - - return (debug_locks) ? lockdep_is_held(lock) : 1; -} -EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); -#endif - static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) { return (void *) he - ht->p.head_offset; @@ -94,13 +79,7 @@ static u32 obj_raw_hashfn(const struct rhashtable *ht, const void *ptr) static u32 key_hashfn(struct rhashtable *ht, const void *key, u32 len) { - struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); - u32 hash; - - hash = ht->p.hashfn(key, len, ht->p.hash_rnd); - hash >>= HASH_RESERVED_SPACE; - - return rht_bucket_index(tbl, hash); + return ht->p.hashfn(key, len, ht->p.hash_rnd) >> HASH_RESERVED_SPACE; } static u32 head_hashfn(const struct rhashtable *ht, @@ -110,6 +89,77 @@ static u32 head_hashfn(const struct rhashtable *ht, return rht_bucket_index(tbl, obj_raw_hashfn(ht, rht_obj(ht, he))); } +#ifdef CONFIG_PROVE_LOCKING +static void debug_dump_buckets(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + struct rhash_head *he; + unsigned int i, hash; + + for (i = 0; i < tbl->size; i++) { + pr_warn(" [Bucket %d] ", i); + rht_for_each_rcu(he, tbl, i) { + hash = head_hashfn(ht, tbl, he); + pr_cont("[hash = %#x, lock = %p] ", + hash, bucket_lock(tbl, hash)); + } + pr_cont("\n"); + } + +} + +static void debug_dump_table(struct rhashtable *ht, + const struct bucket_table *tbl, + unsigned int hash) +{ + struct bucket_table *old_tbl, *future_tbl; + + pr_emerg("BUG: lock for hash %#x in table %p not held\n", + hash, tbl); + + rcu_read_lock(); + future_tbl = rht_dereference_rcu(ht->future_tbl, ht); + old_tbl = rht_dereference_rcu(ht->tbl, ht); + if (future_tbl != old_tbl) { + pr_warn("Future table %p (size: %zd)\n", + future_tbl, future_tbl->size); + debug_dump_buckets(ht, future_tbl); + } + + pr_warn("Table %p (size: %zd)\n", old_tbl, old_tbl->size); + debug_dump_buckets(ht, old_tbl); + + rcu_read_unlock(); +} + +#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT)) +#define ASSERT_BUCKET_LOCK(HT, TBL, HASH) \ + do { \ + if (unlikely(!lockdep_rht_bucket_is_held(TBL, HASH))) { \ + debug_dump_table(HT, TBL, HASH); \ + BUG(); \ + } \ + } while (0) + +int lockdep_rht_mutex_is_held(struct rhashtable *ht) +{ + return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1; +} +EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); + +int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) +{ + spinlock_t *lock = bucket_lock(tbl, hash); + + return (debug_locks) ? lockdep_is_held(lock) : 1; +} +EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); +#else +#define ASSERT_RHT_MUTEX(HT) +#define ASSERT_BUCKET_LOCK(HT, TBL, HASH) +#endif + + static struct rhash_head __rcu **bucket_tail(struct bucket_table *tbl, u32 n) { struct rhash_head __rcu **pprev; @@ -134,8 +184,8 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl) nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul); - /* Never allocate more than one lock per bucket */ - size = min_t(unsigned int, size, tbl->size); + /* Never allocate more than 0.5 locks per bucket */ + size = min_t(unsigned int, size, tbl->size >> 1); if (sizeof(spinlock_t) != 0) { #ifdef CONFIG_NUMA @@ -217,25 +267,48 @@ bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size) } EXPORT_SYMBOL_GPL(rht_shrink_below_30); -static void hashtable_chain_unzip(const struct rhashtable *ht, +static void lock_buckets(struct bucket_table *new_tbl, + struct bucket_table *old_tbl, unsigned int hash) + __acquires(old_bucket_lock) +{ + spin_lock_bh(bucket_lock(old_tbl, hash)); + if (new_tbl != old_tbl) + spin_lock_bh_nested(bucket_lock(new_tbl, hash), + RHT_LOCK_NESTED); +} + +static void unlock_buckets(struct bucket_table *new_tbl, + struct bucket_table *old_tbl, unsigned int hash) + __releases(old_bucket_lock) +{ + if (new_tbl != old_tbl) + spin_unlock_bh(bucket_lock(new_tbl, hash)); + spin_unlock_bh(bucket_lock(old_tbl, hash)); +} + +/** + * Unlink entries on bucket which hash to different bucket. + * + * Returns true if no more work needs to be performed on the bucket. + */ +static bool hashtable_chain_unzip(struct rhashtable *ht, const struct bucket_table *new_tbl, struct bucket_table *old_tbl, size_t old_hash) { struct rhash_head *he, *p, *next; - spinlock_t *new_bucket_lock, *new_bucket_lock2 = NULL; unsigned int new_hash, new_hash2; - ASSERT_BUCKET_LOCK(old_tbl, old_hash); + ASSERT_BUCKET_LOCK(ht, old_tbl, old_hash); /* Old bucket empty, no work needed. */ p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl, old_hash); if (rht_is_a_nulls(p)) - return; + return false; - new_hash = new_hash2 = head_hashfn(ht, new_tbl, p); - new_bucket_lock = bucket_lock(new_tbl, new_hash); + new_hash = head_hashfn(ht, new_tbl, p); + ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash); /* Advance the old bucket pointer one or more times until it * reaches a node that doesn't hash to the same bucket as the @@ -243,22 +316,14 @@ static void hashtable_chain_unzip(const struct rhashtable *ht, */ rht_for_each_continue(he, p->next, old_tbl, old_hash) { new_hash2 = head_hashfn(ht, new_tbl, he); + ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash2); + if (new_hash != new_hash2) break; p = he; } rcu_assign_pointer(old_tbl->buckets[old_hash], p->next); - spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED); - - /* If we have encountered an entry that maps to a different bucket in - * the new table, lock down that bucket as well as we might cut off - * the end of the chain. - */ - new_bucket_lock2 = bucket_lock(new_tbl, new_hash); - if (new_bucket_lock != new_bucket_lock2) - spin_lock_bh_nested(new_bucket_lock2, RHT_LOCK_NESTED2); - /* Find the subsequent node which does hash to the same * bucket as node P, or NULL if no such node exists. */ @@ -277,21 +342,18 @@ static void hashtable_chain_unzip(const struct rhashtable *ht, */ rcu_assign_pointer(p->next, next); - if (new_bucket_lock != new_bucket_lock2) - spin_unlock_bh(new_bucket_lock2); - spin_unlock_bh(new_bucket_lock); + p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl, + old_hash); + + return !rht_is_a_nulls(p); } -static void link_old_to_new(struct bucket_table *new_tbl, +static void link_old_to_new(struct rhashtable *ht, struct bucket_table *new_tbl, unsigned int new_hash, struct rhash_head *entry) { - spinlock_t *new_bucket_lock; + ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash); - new_bucket_lock = bucket_lock(new_tbl, new_hash); - - spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED); rcu_assign_pointer(*bucket_tail(new_tbl, new_hash), entry); - spin_unlock_bh(new_bucket_lock); } /** @@ -314,7 +376,6 @@ int rhashtable_expand(struct rhashtable *ht) { struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); struct rhash_head *he; - spinlock_t *old_bucket_lock; unsigned int new_hash, old_hash; bool complete = false; @@ -344,24 +405,16 @@ int rhashtable_expand(struct rhashtable *ht) */ for (new_hash = 0; new_hash < new_tbl->size; new_hash++) { old_hash = rht_bucket_index(old_tbl, new_hash); - old_bucket_lock = bucket_lock(old_tbl, old_hash); - - spin_lock_bh(old_bucket_lock); + lock_buckets(new_tbl, old_tbl, new_hash); rht_for_each(he, old_tbl, old_hash) { if (head_hashfn(ht, new_tbl, he) == new_hash) { - link_old_to_new(new_tbl, new_hash, he); + link_old_to_new(ht, new_tbl, new_hash, he); break; } } - spin_unlock_bh(old_bucket_lock); + unlock_buckets(new_tbl, old_tbl, new_hash); } - /* Publish the new table pointer. Lookups may now traverse - * the new table, but they will not benefit from any - * additional efficiency until later steps unzip the buckets. - */ - rcu_assign_pointer(ht->tbl, new_tbl); - /* Unzip interleaved hash chains */ while (!complete && !ht->being_destroyed) { /* Wait for readers. All new readers will see the new @@ -376,21 +429,19 @@ int rhashtable_expand(struct rhashtable *ht) */ complete = true; for (old_hash = 0; old_hash < old_tbl->size; old_hash++) { - struct rhash_head *head; - - old_bucket_lock = bucket_lock(old_tbl, old_hash); - spin_lock_bh(old_bucket_lock); + lock_buckets(new_tbl, old_tbl, old_hash); - hashtable_chain_unzip(ht, new_tbl, old_tbl, old_hash); - head = rht_dereference_bucket(old_tbl->buckets[old_hash], - old_tbl, old_hash); - if (!rht_is_a_nulls(head)) + if (hashtable_chain_unzip(ht, new_tbl, old_tbl, + old_hash)) complete = false; - spin_unlock_bh(old_bucket_lock); + unlock_buckets(new_tbl, old_tbl, old_hash); } } + rcu_assign_pointer(ht->tbl, new_tbl); + synchronize_rcu(); + bucket_table_free(old_tbl); return 0; } @@ -415,7 +466,6 @@ EXPORT_SYMBOL_GPL(rhashtable_expand); int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *new_tbl, *tbl = rht_dereference(ht->tbl, ht); - spinlock_t *new_bucket_lock, *old_bucket_lock1, *old_bucket_lock2; unsigned int new_hash; ASSERT_RHT_MUTEX(ht); @@ -433,36 +483,17 @@ int rhashtable_shrink(struct rhashtable *ht) * always divide the size in half when shrinking, each bucket * in the new table maps to exactly two buckets in the old * table. - * - * As removals can occur concurrently on the old table, we need - * to lock down both matching buckets in the old table. */ for (new_hash = 0; new_hash < new_tbl->size; new_hash++) { - old_bucket_lock1 = bucket_lock(tbl, new_hash); - old_bucket_lock2 = bucket_lock(tbl, new_hash + new_tbl->size); - new_bucket_lock = bucket_lock(new_tbl, new_hash); - - spin_lock_bh(old_bucket_lock1); - - /* Depending on the lock per buckets mapping, the bucket in - * the lower and upper region may map to the same lock. - */ - if (old_bucket_lock1 != old_bucket_lock2) { - spin_lock_bh_nested(old_bucket_lock2, RHT_LOCK_NESTED); - spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED2); - } else { - spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED); - } + lock_buckets(new_tbl, tbl, new_hash); rcu_assign_pointer(*bucket_tail(new_tbl, new_hash), tbl->buckets[new_hash]); + ASSERT_BUCKET_LOCK(ht, tbl, new_hash + new_tbl->size); rcu_assign_pointer(*bucket_tail(new_tbl, new_hash), tbl->buckets[new_hash + new_tbl->size]); - spin_unlock_bh(new_bucket_lock); - if (old_bucket_lock1 != old_bucket_lock2) - spin_unlock_bh(old_bucket_lock2); - spin_unlock_bh(old_bucket_lock1); + unlock_buckets(new_tbl, tbl, new_hash); } /* Publish the new, valid hash table */ @@ -484,16 +515,24 @@ static void rht_deferred_worker(struct work_struct *work) { struct rhashtable *ht; struct bucket_table *tbl; + struct rhashtable_walker *walker; ht = container_of(work, struct rhashtable, run_work); mutex_lock(&ht->mutex); + if (ht->being_destroyed) + goto unlock; + tbl = rht_dereference(ht->tbl, ht); + list_for_each_entry(walker, &ht->walkers, list) + walker->resize = true; + if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size)) rhashtable_expand(ht); else if (ht->p.shrink_decision && ht->p.shrink_decision(ht, tbl->size)) rhashtable_shrink(ht); +unlock: mutex_unlock(&ht->mutex); } @@ -513,8 +552,12 @@ static void rhashtable_wakeup_worker(struct rhashtable *ht) static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj, struct bucket_table *tbl, u32 hash) { - struct rhash_head *head = rht_dereference_bucket(tbl->buckets[hash], - tbl, hash); + struct rhash_head *head; + + hash = rht_bucket_index(tbl, hash); + head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); + + ASSERT_BUCKET_LOCK(ht, tbl, hash); if (rht_is_a_nulls(head)) INIT_RHT_NULLS_HEAD(obj->next, ht, hash); @@ -545,19 +588,18 @@ static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj, */ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj) { - struct bucket_table *tbl; - spinlock_t *lock; + struct bucket_table *tbl, *old_tbl; unsigned hash; rcu_read_lock(); tbl = rht_dereference_rcu(ht->future_tbl, ht); - hash = head_hashfn(ht, tbl, obj); - lock = bucket_lock(tbl, hash); + old_tbl = rht_dereference_rcu(ht->tbl, ht); + hash = obj_raw_hashfn(ht, rht_obj(ht, obj)); - spin_lock_bh(lock); + lock_buckets(tbl, old_tbl, hash); __rhashtable_insert(ht, obj, tbl, hash); - spin_unlock_bh(lock); + unlock_buckets(tbl, old_tbl, hash); rcu_read_unlock(); } @@ -580,21 +622,20 @@ EXPORT_SYMBOL_GPL(rhashtable_insert); */ bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj) { - struct bucket_table *tbl; + struct bucket_table *tbl, *new_tbl, *old_tbl; struct rhash_head __rcu **pprev; - struct rhash_head *he; - spinlock_t *lock; - unsigned int hash; + struct rhash_head *he, *he2; + unsigned int hash, new_hash; bool ret = false; rcu_read_lock(); - tbl = rht_dereference_rcu(ht->tbl, ht); - hash = head_hashfn(ht, tbl, obj); - - lock = bucket_lock(tbl, hash); - spin_lock_bh(lock); + old_tbl = rht_dereference_rcu(ht->tbl, ht); + tbl = new_tbl = rht_dereference_rcu(ht->future_tbl, ht); + new_hash = obj_raw_hashfn(ht, rht_obj(ht, obj)); + lock_buckets(new_tbl, old_tbl, new_hash); restart: + hash = rht_bucket_index(tbl, new_hash); pprev = &tbl->buckets[hash]; rht_for_each(he, tbl, hash) { if (he != obj) { @@ -602,8 +643,26 @@ restart: continue; } - rcu_assign_pointer(*pprev, obj->next); + ASSERT_BUCKET_LOCK(ht, tbl, hash); + + if (old_tbl->size > new_tbl->size && tbl == old_tbl && + !rht_is_a_nulls(obj->next) && + head_hashfn(ht, tbl, obj->next) != hash) { + rcu_assign_pointer(*pprev, (struct rhash_head *) rht_marker(ht, hash)); + } else if (unlikely(old_tbl->size < new_tbl->size && tbl == new_tbl)) { + rht_for_each_continue(he2, obj->next, tbl, hash) { + if (head_hashfn(ht, tbl, he2) == hash) { + rcu_assign_pointer(*pprev, he2); + goto found; + } + } + + rcu_assign_pointer(*pprev, (struct rhash_head *) rht_marker(ht, hash)); + } else { + rcu_assign_pointer(*pprev, obj->next); + } +found: ret = true; break; } @@ -613,18 +672,12 @@ restart: * resizing. Thus traversing both is fine and the added cost is * very rare. */ - if (tbl != rht_dereference_rcu(ht->future_tbl, ht)) { - spin_unlock_bh(lock); - - tbl = rht_dereference_rcu(ht->future_tbl, ht); - hash = head_hashfn(ht, tbl, obj); - - lock = bucket_lock(tbl, hash); - spin_lock_bh(lock); + if (tbl != old_tbl) { + tbl = old_tbl; goto restart; } - spin_unlock_bh(lock); + unlock_buckets(new_tbl, old_tbl, new_hash); if (ret) { atomic_dec(&ht->nelems); @@ -780,24 +833,17 @@ bool rhashtable_lookup_compare_insert(struct rhashtable *ht, void *arg) { struct bucket_table *new_tbl, *old_tbl; - spinlock_t *new_bucket_lock, *old_bucket_lock; - u32 new_hash, old_hash; + u32 new_hash; bool success = true; BUG_ON(!ht->p.key_len); rcu_read_lock(); - old_tbl = rht_dereference_rcu(ht->tbl, ht); - old_hash = head_hashfn(ht, old_tbl, obj); - old_bucket_lock = bucket_lock(old_tbl, old_hash); - spin_lock_bh(old_bucket_lock); - new_tbl = rht_dereference_rcu(ht->future_tbl, ht); - new_hash = head_hashfn(ht, new_tbl, obj); - new_bucket_lock = bucket_lock(new_tbl, new_hash); - if (unlikely(old_tbl != new_tbl)) - spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED); + new_hash = obj_raw_hashfn(ht, rht_obj(ht, obj)); + + lock_buckets(new_tbl, old_tbl, new_hash); if (rhashtable_lookup_compare(ht, rht_obj(ht, obj) + ht->p.key_offset, compare, arg)) { @@ -808,16 +854,171 @@ bool rhashtable_lookup_compare_insert(struct rhashtable *ht, __rhashtable_insert(ht, obj, new_tbl, new_hash); exit: - if (unlikely(old_tbl != new_tbl)) - spin_unlock_bh(new_bucket_lock); - spin_unlock_bh(old_bucket_lock); - + unlock_buckets(new_tbl, old_tbl, new_hash); rcu_read_unlock(); return success; } EXPORT_SYMBOL_GPL(rhashtable_lookup_compare_insert); +/** + * rhashtable_walk_init - Initialise an iterator + * @ht: Table to walk over + * @iter: Hash table Iterator + * + * This function prepares a hash table walk. + * + * Note that if you restart a walk after rhashtable_walk_stop you + * may see the same object twice. Also, you may miss objects if + * there are removals in between rhashtable_walk_stop and the next + * call to rhashtable_walk_start. + * + * For a completely stable walk you should construct your own data + * structure outside the hash table. + * + * This function may sleep so you must not call it from interrupt + * context or with spin locks held. + * + * You must call rhashtable_walk_exit if this function returns + * successfully. + */ +int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter) +{ + iter->ht = ht; + iter->p = NULL; + iter->slot = 0; + iter->skip = 0; + + iter->walker = kmalloc(sizeof(*iter->walker), GFP_KERNEL); + if (!iter->walker) + return -ENOMEM; + + mutex_lock(&ht->mutex); + list_add(&iter->walker->list, &ht->walkers); + mutex_unlock(&ht->mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_init); + +/** + * rhashtable_walk_exit - Free an iterator + * @iter: Hash table Iterator + * + * This function frees resources allocated by rhashtable_walk_init. + */ +void rhashtable_walk_exit(struct rhashtable_iter *iter) +{ + mutex_lock(&iter->ht->mutex); + list_del(&iter->walker->list); + mutex_unlock(&iter->ht->mutex); + kfree(iter->walker); +} +EXPORT_SYMBOL_GPL(rhashtable_walk_exit); + +/** + * rhashtable_walk_start - Start a hash table walk + * @iter: Hash table iterator + * + * Start a hash table walk. Note that we take the RCU lock in all + * cases including when we return an error. So you must always call + * rhashtable_walk_stop to clean up. + * + * Returns zero if successful. + * + * Returns -EAGAIN if resize event occured. Note that the iterator + * will rewind back to the beginning and you may use it immediately + * by calling rhashtable_walk_next. + */ +int rhashtable_walk_start(struct rhashtable_iter *iter) +{ + rcu_read_lock(); + + if (iter->walker->resize) { + iter->slot = 0; + iter->skip = 0; + iter->walker->resize = false; + return -EAGAIN; + } + + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_start); + +/** + * rhashtable_walk_next - Return the next object and advance the iterator + * @iter: Hash table iterator + * + * Note that you must call rhashtable_walk_stop when you are finished + * with the walk. + * + * Returns the next object or NULL when the end of the table is reached. + * + * Returns -EAGAIN if resize event occured. Note that the iterator + * will rewind back to the beginning and you may continue to use it. + */ +void *rhashtable_walk_next(struct rhashtable_iter *iter) +{ + const struct bucket_table *tbl; + struct rhashtable *ht = iter->ht; + struct rhash_head *p = iter->p; + void *obj = NULL; + + tbl = rht_dereference_rcu(ht->tbl, ht); + + if (p) { + p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot); + goto next; + } + + for (; iter->slot < tbl->size; iter->slot++) { + int skip = iter->skip; + + rht_for_each_rcu(p, tbl, iter->slot) { + if (!skip) + break; + skip--; + } + +next: + if (!rht_is_a_nulls(p)) { + iter->skip++; + iter->p = p; + obj = rht_obj(ht, p); + goto out; + } + + iter->skip = 0; + } + + iter->p = NULL; + +out: + if (iter->walker->resize) { + iter->p = NULL; + iter->slot = 0; + iter->skip = 0; + iter->walker->resize = false; + return ERR_PTR(-EAGAIN); + } + + return obj; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_next); + +/** + * rhashtable_walk_stop - Finish a hash table walk + * @iter: Hash table iterator + * + * Finish a hash table walk. + */ +void rhashtable_walk_stop(struct rhashtable_iter *iter) +{ + rcu_read_unlock(); + iter->p = NULL; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_stop); + static size_t rounded_hashtable_size(struct rhashtable_params *params) { return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), @@ -890,6 +1091,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params) memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); memcpy(&ht->p, params, sizeof(*params)); + INIT_LIST_HEAD(&ht->walkers); if (params->locks_mul) ht->p.locks_mul = roundup_pow_of_two(params->locks_mul); @@ -935,208 +1137,3 @@ void rhashtable_destroy(struct rhashtable *ht) mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_destroy); - -/************************************************************************** - * Self Test - **************************************************************************/ - -#ifdef CONFIG_TEST_RHASHTABLE - -#define TEST_HT_SIZE 8 -#define TEST_ENTRIES 2048 -#define TEST_PTR ((void *) 0xdeadbeef) -#define TEST_NEXPANDS 4 - -struct test_obj { - void *ptr; - int value; - struct rhash_head node; -}; - -static int __init test_rht_lookup(struct rhashtable *ht) -{ - unsigned int i; - - for (i = 0; i < TEST_ENTRIES * 2; i++) { - struct test_obj *obj; - bool expected = !(i % 2); - u32 key = i; - - obj = rhashtable_lookup(ht, &key); - - if (expected && !obj) { - pr_warn("Test failed: Could not find key %u\n", key); - return -ENOENT; - } else if (!expected && obj) { - pr_warn("Test failed: Unexpected entry found for key %u\n", - key); - return -EEXIST; - } else if (expected && obj) { - if (obj->ptr != TEST_PTR || obj->value != i) { - pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n", - obj->ptr, TEST_PTR, obj->value, i); - return -EINVAL; - } - } - } - - return 0; -} - -static void test_bucket_stats(struct rhashtable *ht, bool quiet) -{ - unsigned int cnt, rcu_cnt, i, total = 0; - struct rhash_head *pos; - struct test_obj *obj; - struct bucket_table *tbl; - - tbl = rht_dereference_rcu(ht->tbl, ht); - for (i = 0; i < tbl->size; i++) { - rcu_cnt = cnt = 0; - - if (!quiet) - pr_info(" [%#4x/%zu]", i, tbl->size); - - rht_for_each_entry_rcu(obj, pos, tbl, i, node) { - cnt++; - total++; - if (!quiet) - pr_cont(" [%p],", obj); - } - - rht_for_each_entry_rcu(obj, pos, tbl, i, node) - rcu_cnt++; - - if (rcu_cnt != cnt) - pr_warn("Test failed: Chain count mismach %d != %d", - cnt, rcu_cnt); - - if (!quiet) - pr_cont("\n [%#x] first element: %p, chain length: %u\n", - i, tbl->buckets[i], cnt); - } - - pr_info(" Traversal complete: counted=%u, nelems=%u, entries=%d\n", - total, atomic_read(&ht->nelems), TEST_ENTRIES); - - if (total != atomic_read(&ht->nelems) || total != TEST_ENTRIES) - pr_warn("Test failed: Total count mismatch ^^^"); -} - -static int __init test_rhashtable(struct rhashtable *ht) -{ - struct bucket_table *tbl; - struct test_obj *obj; - struct rhash_head *pos, *next; - int err; - unsigned int i; - - /* - * Insertion Test: - * Insert TEST_ENTRIES into table with all keys even numbers - */ - pr_info(" Adding %d keys\n", TEST_ENTRIES); - for (i = 0; i < TEST_ENTRIES; i++) { - struct test_obj *obj; - - obj = kzalloc(sizeof(*obj), GFP_KERNEL); - if (!obj) { - err = -ENOMEM; - goto error; - } - - obj->ptr = TEST_PTR; - obj->value = i * 2; - - rhashtable_insert(ht, &obj->node); - } - - rcu_read_lock(); - test_bucket_stats(ht, true); - test_rht_lookup(ht); - rcu_read_unlock(); - - for (i = 0; i < TEST_NEXPANDS; i++) { - pr_info(" Table expansion iteration %u...\n", i); - mutex_lock(&ht->mutex); - rhashtable_expand(ht); - mutex_unlock(&ht->mutex); - - rcu_read_lock(); - pr_info(" Verifying lookups...\n"); - test_rht_lookup(ht); - rcu_read_unlock(); - } - - for (i = 0; i < TEST_NEXPANDS; i++) { - pr_info(" Table shrinkage iteration %u...\n", i); - mutex_lock(&ht->mutex); - rhashtable_shrink(ht); - mutex_unlock(&ht->mutex); - - rcu_read_lock(); - pr_info(" Verifying lookups...\n"); - test_rht_lookup(ht); - rcu_read_unlock(); - } - - rcu_read_lock(); - test_bucket_stats(ht, true); - rcu_read_unlock(); - - pr_info(" Deleting %d keys\n", TEST_ENTRIES); - for (i = 0; i < TEST_ENTRIES; i++) { - u32 key = i * 2; - - obj = rhashtable_lookup(ht, &key); - BUG_ON(!obj); - - rhashtable_remove(ht, &obj->node); - kfree(obj); - } - - return 0; - -error: - tbl = rht_dereference_rcu(ht->tbl, ht); - for (i = 0; i < tbl->size; i++) - rht_for_each_entry_safe(obj, pos, next, tbl, i, node) - kfree(obj); - - return err; -} - -static int __init test_rht_init(void) -{ - struct rhashtable ht; - struct rhashtable_params params = { - .nelem_hint = TEST_HT_SIZE, - .head_offset = offsetof(struct test_obj, node), - .key_offset = offsetof(struct test_obj, value), - .key_len = sizeof(int), - .hashfn = jhash, - .nulls_base = (3U << RHT_BASE_SHIFT), - .grow_decision = rht_grow_above_75, - .shrink_decision = rht_shrink_below_30, - }; - int err; - - pr_info("Running resizable hashtable tests...\n"); - - err = rhashtable_init(&ht, ¶ms); - if (err < 0) { - pr_warn("Test failed: Unable to initialize hashtable: %d\n", - err); - return err; - } - - err = test_rhashtable(&ht); - - rhashtable_destroy(&ht); - - return err; -} - -subsys_initcall(test_rht_init); - -#endif /* CONFIG_TEST_RHASHTABLE */ diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c new file mode 100644 index 000000000000..1dfeba73fc74 --- /dev/null +++ b/lib/test_rhashtable.c @@ -0,0 +1,227 @@ +/* + * Resizable, Scalable, Concurrent Hash Table + * + * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch> + * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> + * + * Based on the following paper: + * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf + * + * Code partially derived from nft_hash + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/************************************************************************** + * Self Test + **************************************************************************/ + +#include <linux/init.h> +#include <linux/jhash.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/rcupdate.h> +#include <linux/rhashtable.h> +#include <linux/slab.h> + + +#define TEST_HT_SIZE 8 +#define TEST_ENTRIES 2048 +#define TEST_PTR ((void *) 0xdeadbeef) +#define TEST_NEXPANDS 4 + +struct test_obj { + void *ptr; + int value; + struct rhash_head node; +}; + +static int __init test_rht_lookup(struct rhashtable *ht) +{ + unsigned int i; + + for (i = 0; i < TEST_ENTRIES * 2; i++) { + struct test_obj *obj; + bool expected = !(i % 2); + u32 key = i; + + obj = rhashtable_lookup(ht, &key); + + if (expected && !obj) { + pr_warn("Test failed: Could not find key %u\n", key); + return -ENOENT; + } else if (!expected && obj) { + pr_warn("Test failed: Unexpected entry found for key %u\n", + key); + return -EEXIST; + } else if (expected && obj) { + if (obj->ptr != TEST_PTR || obj->value != i) { + pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n", + obj->ptr, TEST_PTR, obj->value, i); + return -EINVAL; + } + } + } + + return 0; +} + +static void test_bucket_stats(struct rhashtable *ht, bool quiet) +{ + unsigned int cnt, rcu_cnt, i, total = 0; + struct rhash_head *pos; + struct test_obj *obj; + struct bucket_table *tbl; + + tbl = rht_dereference_rcu(ht->tbl, ht); + for (i = 0; i < tbl->size; i++) { + rcu_cnt = cnt = 0; + + if (!quiet) + pr_info(" [%#4x/%zu]", i, tbl->size); + + rht_for_each_entry_rcu(obj, pos, tbl, i, node) { + cnt++; + total++; + if (!quiet) + pr_cont(" [%p],", obj); + } + + rht_for_each_entry_rcu(obj, pos, tbl, i, node) + rcu_cnt++; + + if (rcu_cnt != cnt) + pr_warn("Test failed: Chain count mismach %d != %d", + cnt, rcu_cnt); + + if (!quiet) + pr_cont("\n [%#x] first element: %p, chain length: %u\n", + i, tbl->buckets[i], cnt); + } + + pr_info(" Traversal complete: counted=%u, nelems=%u, entries=%d\n", + total, atomic_read(&ht->nelems), TEST_ENTRIES); + + if (total != atomic_read(&ht->nelems) || total != TEST_ENTRIES) + pr_warn("Test failed: Total count mismatch ^^^"); +} + +static int __init test_rhashtable(struct rhashtable *ht) +{ + struct bucket_table *tbl; + struct test_obj *obj; + struct rhash_head *pos, *next; + int err; + unsigned int i; + + /* + * Insertion Test: + * Insert TEST_ENTRIES into table with all keys even numbers + */ + pr_info(" Adding %d keys\n", TEST_ENTRIES); + for (i = 0; i < TEST_ENTRIES; i++) { + struct test_obj *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) { + err = -ENOMEM; + goto error; + } + + obj->ptr = TEST_PTR; + obj->value = i * 2; + + rhashtable_insert(ht, &obj->node); + } + + rcu_read_lock(); + test_bucket_stats(ht, true); + test_rht_lookup(ht); + rcu_read_unlock(); + + for (i = 0; i < TEST_NEXPANDS; i++) { + pr_info(" Table expansion iteration %u...\n", i); + mutex_lock(&ht->mutex); + rhashtable_expand(ht); + mutex_unlock(&ht->mutex); + + rcu_read_lock(); + pr_info(" Verifying lookups...\n"); + test_rht_lookup(ht); + rcu_read_unlock(); + } + + for (i = 0; i < TEST_NEXPANDS; i++) { + pr_info(" Table shrinkage iteration %u...\n", i); + mutex_lock(&ht->mutex); + rhashtable_shrink(ht); + mutex_unlock(&ht->mutex); + + rcu_read_lock(); + pr_info(" Verifying lookups...\n"); + test_rht_lookup(ht); + rcu_read_unlock(); + } + + rcu_read_lock(); + test_bucket_stats(ht, true); + rcu_read_unlock(); + + pr_info(" Deleting %d keys\n", TEST_ENTRIES); + for (i = 0; i < TEST_ENTRIES; i++) { + u32 key = i * 2; + + obj = rhashtable_lookup(ht, &key); + BUG_ON(!obj); + + rhashtable_remove(ht, &obj->node); + kfree(obj); + } + + return 0; + +error: + tbl = rht_dereference_rcu(ht->tbl, ht); + for (i = 0; i < tbl->size; i++) + rht_for_each_entry_safe(obj, pos, next, tbl, i, node) + kfree(obj); + + return err; +} + +static int __init test_rht_init(void) +{ + struct rhashtable ht; + struct rhashtable_params params = { + .nelem_hint = TEST_HT_SIZE, + .head_offset = offsetof(struct test_obj, node), + .key_offset = offsetof(struct test_obj, value), + .key_len = sizeof(int), + .hashfn = jhash, + .nulls_base = (3U << RHT_BASE_SHIFT), + .grow_decision = rht_grow_above_75, + .shrink_decision = rht_shrink_below_30, + }; + int err; + + pr_info("Running resizable hashtable tests...\n"); + + err = rhashtable_init(&ht, ¶ms); + if (err < 0) { + pr_warn("Test failed: Unable to initialize hashtable: %d\n", + err); + return err; + } + + err = test_rhashtable(&ht); + + rhashtable_destroy(&ht); + + return err; +} + +module_init(test_rht_init); + +MODULE_LICENSE("GPL v2"); @@ -296,7 +296,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } @@ -571,7 +571,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } @@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) else ret = VM_FAULT_WRITE; put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM))); + } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop because handle_mm_fault() may back out if there's * any difficulty e.g. if pte accessed bit gets updated concurrently. diff --git a/mm/memory.c b/mm/memory.c index 54f3a9b00956..2c3536cc6c63 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2632,7 +2632,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Check if we need to add a guard page to the stack */ if (check_stack_guard_page(vma, address) < 0) - return VM_FAULT_SIGBUS; + return VM_FAULT_SIGSEGV; /* Use the zero-page for reads */ if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) { diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index ce82722d049b..05f57e491ccb 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -511,13 +511,12 @@ static int bnep_session(void *arg) static struct device *bnep_get_device(struct bnep_session *session) { - struct hci_conn *conn; + struct l2cap_conn *conn = l2cap_pi(session->sock->sk)->chan->conn; - conn = l2cap_pi(session->sock->sk)->chan->conn->hcon; - if (!conn) + if (!conn || !conn->hcon) return NULL; - return &conn->dev; + return &conn->hcon->dev; } static struct device_type bnep_type = { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 34c17a0645ce..3322d3f4c85a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -609,6 +609,7 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt) if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { u8 mode = 0x01; + hci_req_add(req, HCI_OP_WRITE_SSP_MODE, sizeof(mode), &mode); } else { @@ -870,8 +871,10 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL); /* Enable Secure Connections if supported and configured */ - if (bredr_sc_enabled(hdev)) { + if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && + bredr_sc_enabled(hdev)) { u8 support = 0x01; + hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT, sizeof(support), &support); } @@ -1614,6 +1617,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) cancel_delayed_work(&hdev->service_cache); cancel_delayed_work_sync(&hdev->le_scan_disable); + cancel_delayed_work_sync(&hdev->le_scan_restart); if (test_bit(HCI_MGMT, &hdev->dev_flags)) cancel_delayed_work_sync(&hdev->rpa_expired); @@ -1625,6 +1629,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_dev_lock(hdev); + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + if (!test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { if (hdev->dev_type == HCI_BREDR) mgmt_powered(hdev, 0); @@ -1635,6 +1641,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_conn_hash_flush(hdev); hci_dev_unlock(hdev); + smp_unregister(hdev); + hci_notify(hdev, HCI_DEV_DOWN); if (hdev->flush) @@ -1714,32 +1722,14 @@ done: return err; } -int hci_dev_reset(__u16 dev) +static int hci_dev_do_reset(struct hci_dev *hdev) { - struct hci_dev *hdev; - int ret = 0; + int ret; - hdev = hci_dev_get(dev); - if (!hdev) - return -ENODEV; + BT_DBG("%s %p", hdev->name, hdev); hci_req_lock(hdev); - if (!test_bit(HCI_UP, &hdev->flags)) { - ret = -ENETDOWN; - goto done; - } - - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { - ret = -EBUSY; - goto done; - } - - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { - ret = -EOPNOTSUPP; - goto done; - } - /* Drop queues */ skb_queue_purge(&hdev->rx_q); skb_queue_purge(&hdev->cmd_q); @@ -1762,12 +1752,41 @@ int hci_dev_reset(__u16 dev) ret = __hci_req_sync(hdev, hci_reset_req, 0, HCI_INIT_TIMEOUT); -done: hci_req_unlock(hdev); - hci_dev_put(hdev); return ret; } +int hci_dev_reset(__u16 dev) +{ + struct hci_dev *hdev; + int err; + + hdev = hci_dev_get(dev); + if (!hdev) + return -ENODEV; + + if (!test_bit(HCI_UP, &hdev->flags)) { + err = -ENETDOWN; + goto done; + } + + if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + err = -EBUSY; + goto done; + } + + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + err = -EOPNOTSUPP; + goto done; + } + + err = hci_dev_do_reset(hdev); + +done: + hci_dev_put(hdev); + return err; +} + int hci_dev_reset_stat(__u16 dev) { struct hci_dev *hdev; @@ -2131,8 +2150,24 @@ static void hci_power_off(struct work_struct *work) BT_DBG("%s", hdev->name); hci_dev_do_close(hdev); +} - smp_unregister(hdev); +static void hci_error_reset(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); + + BT_DBG("%s", hdev->name); + + if (hdev->hw_error) + hdev->hw_error(hdev, hdev->hw_error_code); + else + BT_ERR("%s hardware error 0x%2.2x", hdev->name, + hdev->hw_error_code); + + if (hci_dev_do_close(hdev)) + return; + + hci_dev_do_open(hdev); } static void hci_discov_off(struct work_struct *work) @@ -2547,9 +2582,15 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, if (hash192 && rand192) { memcpy(data->hash192, hash192, sizeof(data->hash192)); memcpy(data->rand192, rand192, sizeof(data->rand192)); + if (hash256 && rand256) + data->present = 0x03; } else { memset(data->hash192, 0, sizeof(data->hash192)); memset(data->rand192, 0, sizeof(data->rand192)); + if (hash256 && rand256) + data->present = 0x02; + else + data->present = 0x00; } if (hash256 && rand256) { @@ -2558,6 +2599,8 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, } else { memset(data->hash256, 0, sizeof(data->hash256)); memset(data->rand256, 0, sizeof(data->rand256)); + if (hash192 && rand192) + data->present = 0x01; } BT_DBG("%s for %pMR", hdev->name, bdaddr); @@ -2788,6 +2831,8 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status, return; } + hdev->discovery.scan_start = 0; + switch (hdev->discovery.type) { case DISCOV_TYPE_LE: hci_dev_lock(hdev); @@ -2827,6 +2872,8 @@ static void le_scan_disable_work(struct work_struct *work) BT_DBG("%s", hdev->name); + cancel_delayed_work_sync(&hdev->le_scan_restart); + hci_req_init(&req, hdev); hci_req_add_le_scan_disable(&req); @@ -2836,6 +2883,74 @@ static void le_scan_disable_work(struct work_struct *work) BT_ERR("Disable LE scanning request failed: err %d", err); } +static void le_scan_restart_work_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + unsigned long timeout, duration, scan_start, now; + + BT_DBG("%s", hdev->name); + + if (status) { + BT_ERR("Failed to restart LE scan: status %d", status); + return; + } + + if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) || + !hdev->discovery.scan_start) + return; + + /* When the scan was started, hdev->le_scan_disable has been queued + * after duration from scan_start. During scan restart this job + * has been canceled, and we need to queue it again after proper + * timeout, to make sure that scan does not run indefinitely. + */ + duration = hdev->discovery.scan_duration; + scan_start = hdev->discovery.scan_start; + now = jiffies; + if (now - scan_start <= duration) { + int elapsed; + + if (now >= scan_start) + elapsed = now - scan_start; + else + elapsed = ULONG_MAX - scan_start + now; + + timeout = duration - elapsed; + } else { + timeout = 0; + } + queue_delayed_work(hdev->workqueue, + &hdev->le_scan_disable, timeout); +} + +static void le_scan_restart_work(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + le_scan_restart.work); + struct hci_request req; + struct hci_cp_le_set_scan_enable cp; + int err; + + BT_DBG("%s", hdev->name); + + /* If controller is not scanning we are done. */ + if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + return; + + hci_req_init(&req, hdev); + + hci_req_add_le_scan_disable(&req); + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_ENABLE; + cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + + err = hci_req_run(&req, le_scan_restart_work_complete); + if (err) + BT_ERR("Restart LE scan request failed: err %d", err); +} + /* Copy the Identity Address of the controller. * * If the controller has a public BD_ADDR, then by default use that one. @@ -2927,10 +3042,12 @@ struct hci_dev *hci_alloc_dev(void) INIT_WORK(&hdev->cmd_work, hci_cmd_work); INIT_WORK(&hdev->tx_work, hci_tx_work); INIT_WORK(&hdev->power_on, hci_power_on); + INIT_WORK(&hdev->error_reset, hci_error_reset); INIT_DELAYED_WORK(&hdev->power_off, hci_power_off); INIT_DELAYED_WORK(&hdev->discov_off, hci_discov_off); INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable_work); + INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart_work); skb_queue_head_init(&hdev->rx_q); skb_queue_head_init(&hdev->cmd_q); @@ -3100,8 +3217,6 @@ void hci_unregister_dev(struct hci_dev *hdev) rfkill_destroy(hdev->rfkill); } - smp_unregister(hdev); - device_del(&hdev->dev); debugfs_remove_recursive(hdev->debugfs); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index ead89a5ad9ce..65261e5d4b84 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -156,6 +156,35 @@ static const struct file_operations uuids_fops = { .release = single_release, }; +static int remote_oob_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct oob_data *data; + + hci_dev_lock(hdev); + list_for_each_entry(data, &hdev->remote_oob_data, list) { + seq_printf(f, "%pMR (type %u) %u %*phN %*phN %*phN %*phN\n", + &data->bdaddr, data->bdaddr_type, data->present, + 16, data->hash192, 16, data->rand192, + 16, data->hash256, 19, data->rand256); + } + hci_dev_unlock(hdev); + + return 0; +} + +static int remote_oob_open(struct inode *inode, struct file *file) +{ + return single_open(file, remote_oob_show, inode->i_private); +} + +static const struct file_operations remote_oob_fops = { + .open = remote_oob_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -212,6 +241,24 @@ static int conn_info_max_age_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(conn_info_max_age_fops, conn_info_max_age_get, conn_info_max_age_set, "%llu\n"); +static ssize_t use_debug_keys_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static const struct file_operations use_debug_keys_fops = { + .open = simple_open, + .read = use_debug_keys_read, + .llseek = default_llseek, +}; + static ssize_t sc_only_mode_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -238,17 +285,26 @@ void hci_debugfs_create_common(struct hci_dev *hdev) &hdev->manufacturer); debugfs_create_u8("hci_version", 0444, hdev->debugfs, &hdev->hci_ver); debugfs_create_u16("hci_revision", 0444, hdev->debugfs, &hdev->hci_rev); + debugfs_create_u8("hardware_error", 0444, hdev->debugfs, + &hdev->hw_error_code); + debugfs_create_file("device_list", 0444, hdev->debugfs, hdev, &device_list_fops); debugfs_create_file("blacklist", 0444, hdev->debugfs, hdev, &blacklist_fops); debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops); + debugfs_create_file("remote_oob", 0400, hdev->debugfs, hdev, + &remote_oob_fops); debugfs_create_file("conn_info_min_age", 0644, hdev->debugfs, hdev, &conn_info_min_age_fops); debugfs_create_file("conn_info_max_age", 0644, hdev->debugfs, hdev, &conn_info_max_age_fops); + if (lmp_ssp_capable(hdev) || lmp_le_capable(hdev)) + debugfs_create_file("use_debug_keys", 0444, hdev->debugfs, + hdev, &use_debug_keys_fops); + if (lmp_sc_capable(hdev) || lmp_le_capable(hdev)) debugfs_create_file("sc_only_mode", 0444, hdev->debugfs, hdev, &sc_only_mode_fops); @@ -354,6 +410,24 @@ static int voice_setting_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(voice_setting_fops, voice_setting_get, NULL, "0x%4.4llx\n"); +static ssize_t ssp_debug_mode_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = hdev->ssp_debug_mode ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static const struct file_operations ssp_debug_mode_fops = { + .open = simple_open, + .read = ssp_debug_mode_read, + .llseek = default_llseek, +}; + static int auto_accept_delay_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -474,9 +548,12 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev) debugfs_create_file("voice_setting", 0444, hdev->debugfs, hdev, &voice_setting_fops); - if (lmp_ssp_capable(hdev)) + if (lmp_ssp_capable(hdev)) { + debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs, + hdev, &ssp_debug_mode_fops); debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs, hdev, &auto_accept_delay_fops); + } if (lmp_sniff_capable(hdev)) { debugfs_create_file("idle_timeout", 0644, hdev->debugfs, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a58845e98921..a3fb094822b6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -36,6 +36,9 @@ #include "amp.h" #include "smp.h" +#define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ + "\x00\x00\x00\x00\x00\x00\x00\x00" + /* Handle HCI Event packets */ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) @@ -197,7 +200,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) /* Reset all non-persistent flags */ hdev->dev_flags &= ~HCI_PERSISTENT_MASK; - hdev->discovery.state = DISCOVERY_STOPPED; + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + hdev->inq_tx_power = HCI_TX_POWER_INVALID; hdev->adv_tx_power = HCI_TX_POWER_INVALID; @@ -525,9 +529,7 @@ static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb) hdev->features[1][0] &= ~LMP_HOST_SC; } - if (test_bit(HCI_MGMT, &hdev->dev_flags)) - mgmt_sc_enable_complete(hdev, sent->support, status); - else if (!status) { + if (!test_bit(HCI_MGMT, &hdev->dev_flags) && !status) { if (sent->support) set_bit(HCI_SC_ENABLED, &hdev->dev_flags); else @@ -1487,6 +1489,21 @@ unlock: hci_dev_unlock(hdev); } +static void hci_cc_write_ssp_debug_mode(struct hci_dev *hdev, struct sk_buff *skb) +{ + u8 status = *((u8 *) skb->data); + u8 *mode; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + mode = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE); + if (mode) + hdev->ssp_debug_mode = *mode; +} + static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -2669,7 +2686,8 @@ static void hci_remote_features_evt(struct hci_dev *hdev, if (conn->state != BT_CONFIG) goto unlock; - if (!ev->status && lmp_ssp_capable(hdev) && lmp_ssp_capable(conn)) { + if (!ev->status && lmp_ext_feat_capable(hdev) && + lmp_ext_feat_capable(conn)) { struct hci_cp_read_remote_ext_features cp; cp.handle = ev->handle; cp.page = 0x01; @@ -2980,6 +2998,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_read_tx_power(hdev, skb); break; + case HCI_OP_WRITE_SSP_DEBUG_MODE: + hci_cc_write_ssp_debug_mode(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; @@ -3098,7 +3120,9 @@ static void hci_hardware_error_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_hardware_error *ev = (void *) skb->data; - BT_ERR("%s hardware error 0x%2.2x", hdev->name, ev->code); + hdev->hw_error_code = ev->code; + + queue_work(hdev->req_workqueue, &hdev->error_reset); } static void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -3857,6 +3881,52 @@ static u8 hci_get_auth_req(struct hci_conn *conn) return (conn->remote_auth & ~0x01) | (conn->auth_type & 0x01); } +static u8 bredr_oob_data_present(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + struct oob_data *data; + + data = hci_find_remote_oob_data(hdev, &conn->dst, BDADDR_BREDR); + if (!data) + return 0x00; + + if (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)) { + if (bredr_sc_enabled(hdev)) { + /* When Secure Connections is enabled, then just + * return the present value stored with the OOB + * data. The stored value contains the right present + * information. However it can only be trusted when + * not in Secure Connection Only mode. + */ + if (!test_bit(HCI_SC_ONLY, &hdev->dev_flags)) + return data->present; + + /* When Secure Connections Only mode is enabled, then + * the P-256 values are required. If they are not + * available, then do not declare that OOB data is + * present. + */ + if (!memcmp(data->rand256, ZERO_KEY, 16) || + !memcmp(data->hash256, ZERO_KEY, 16)) + return 0x00; + + return 0x02; + } + + /* When Secure Connections is not enabled or actually + * not supported by the hardware, then check that if + * P-192 data values are present. + */ + if (!memcmp(data->rand192, ZERO_KEY, 16) || + !memcmp(data->hash192, ZERO_KEY, 16)) + return 0x00; + + return 0x01; + } + + return 0x00; +} + static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_io_capa_request *ev = (void *) skb->data; @@ -3908,12 +3978,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->auth_type &= HCI_AT_NO_BONDING_MITM; cp.authentication = conn->auth_type; - - if (hci_find_remote_oob_data(hdev, &conn->dst, BDADDR_BREDR) && - (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags))) - cp.oob_data = 0x01; - else - cp.oob_data = 0x00; + cp.oob_data = bredr_oob_data_present(conn); hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_REPLY, sizeof(cp), &cp); @@ -4165,33 +4230,39 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, goto unlock; data = hci_find_remote_oob_data(hdev, &ev->bdaddr, BDADDR_BREDR); - if (data) { - if (bredr_sc_enabled(hdev)) { - struct hci_cp_remote_oob_ext_data_reply cp; - - bacpy(&cp.bdaddr, &ev->bdaddr); - memcpy(cp.hash192, data->hash192, sizeof(cp.hash192)); - memcpy(cp.rand192, data->rand192, sizeof(cp.rand192)); - memcpy(cp.hash256, data->hash256, sizeof(cp.hash256)); - memcpy(cp.rand256, data->rand256, sizeof(cp.rand256)); + if (!data) { + struct hci_cp_remote_oob_data_neg_reply cp; - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY, - sizeof(cp), &cp); - } else { - struct hci_cp_remote_oob_data_reply cp; + bacpy(&cp.bdaddr, &ev->bdaddr); + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, + sizeof(cp), &cp); + goto unlock; + } - bacpy(&cp.bdaddr, &ev->bdaddr); - memcpy(cp.hash, data->hash192, sizeof(cp.hash)); - memcpy(cp.rand, data->rand192, sizeof(cp.rand)); + if (bredr_sc_enabled(hdev)) { + struct hci_cp_remote_oob_ext_data_reply cp; - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, - sizeof(cp), &cp); + bacpy(&cp.bdaddr, &ev->bdaddr); + if (test_bit(HCI_SC_ONLY, &hdev->dev_flags)) { + memset(cp.hash192, 0, sizeof(cp.hash192)); + memset(cp.rand192, 0, sizeof(cp.rand192)); + } else { + memcpy(cp.hash192, data->hash192, sizeof(cp.hash192)); + memcpy(cp.rand192, data->rand192, sizeof(cp.rand192)); } + memcpy(cp.hash256, data->hash256, sizeof(cp.hash256)); + memcpy(cp.rand256, data->rand256, sizeof(cp.rand256)); + + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY, + sizeof(cp), &cp); } else { - struct hci_cp_remote_oob_data_neg_reply cp; + struct hci_cp_remote_oob_data_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, + memcpy(cp.hash, data->hash192, sizeof(cp.hash)); + memcpy(cp.rand, data->rand192, sizeof(cp.rand)); + + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, sizeof(cp), &cp); } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 20206cd3acbc..60694f0f4c73 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -302,7 +302,7 @@ done: static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags) { - DECLARE_WAITQUEUE(wait, current); + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; long timeo; int err = 0; @@ -316,8 +316,6 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { - set_current_state(TASK_INTERRUPTIBLE); - if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; @@ -338,10 +336,11 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, } release_sock(sk); - timeo = schedule_timeout(timeo); + + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + lock_sock_nested(sk, L2CAP_NESTING_PARENT); } - __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (err) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f5c4d2eed9a1..9ec5390c85eb 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -131,6 +131,9 @@ static const u16 mgmt_events[] = { #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) +#define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ + "\x00\x00\x00\x00\x00\x00\x00\x00" + struct pending_cmd { struct list_head list; u16 opcode; @@ -3633,10 +3636,16 @@ unlock: static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { + struct mgmt_addr_info *addr = data; int err; BT_DBG("%s ", hdev->name); + if (!bdaddr_type_is_valid(addr->type)) + return cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS, addr, + sizeof(*addr)); + hci_dev_lock(hdev); if (len == MGMT_ADD_REMOTE_OOB_DATA_SIZE) { @@ -3663,28 +3672,53 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, status, &cp->addr, sizeof(cp->addr)); } else if (len == MGMT_ADD_REMOTE_OOB_EXT_DATA_SIZE) { struct mgmt_cp_add_remote_oob_ext_data *cp = data; - u8 *rand192, *hash192; + u8 *rand192, *hash192, *rand256, *hash256; u8 status; - if (cp->addr.type != BDADDR_BREDR) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_ADD_REMOTE_OOB_DATA, - MGMT_STATUS_INVALID_PARAMS, - &cp->addr, sizeof(cp->addr)); - goto unlock; - } - if (bdaddr_type_is_le(cp->addr.type)) { + /* Enforce zero-valued 192-bit parameters as + * long as legacy SMP OOB isn't implemented. + */ + if (memcmp(cp->rand192, ZERO_KEY, 16) || + memcmp(cp->hash192, ZERO_KEY, 16)) { + err = cmd_complete(sk, hdev->id, + MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS, + addr, sizeof(*addr)); + goto unlock; + } + rand192 = NULL; hash192 = NULL; } else { - rand192 = cp->rand192; - hash192 = cp->hash192; + /* In case one of the P-192 values is set to zero, + * then just disable OOB data for P-192. + */ + if (!memcmp(cp->rand192, ZERO_KEY, 16) || + !memcmp(cp->hash192, ZERO_KEY, 16)) { + rand192 = NULL; + hash192 = NULL; + } else { + rand192 = cp->rand192; + hash192 = cp->hash192; + } + } + + /* In case one of the P-256 values is set to zero, then just + * disable OOB data for P-256. + */ + if (!memcmp(cp->rand256, ZERO_KEY, 16) || + !memcmp(cp->hash256, ZERO_KEY, 16)) { + rand256 = NULL; + hash256 = NULL; + } else { + rand256 = cp->rand256; + hash256 = cp->hash256; } err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr, cp->addr.type, hash192, rand192, - cp->hash256, cp->rand256); + hash256, rand256); if (err < 0) status = MGMT_STATUS_FAILED; else @@ -3862,6 +3896,9 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status, hci_discovery_set_state(hdev, DISCOVERY_FINDING); + /* If the scan involves LE scan, pick proper timeout to schedule + * hdev->le_scan_disable that will stop it. + */ switch (hdev->discovery.type) { case DISCOV_TYPE_LE: timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT); @@ -3878,9 +3915,23 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status, break; } - if (timeout) + if (timeout) { + /* When service discovery is used and the controller has + * a strict duplicate filter, it is important to remember + * the start and duration of the scan. This is required + * for restarting scanning during the discovery phase. + */ + if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, + &hdev->quirks) && + (hdev->discovery.uuid_count > 0 || + hdev->discovery.rssi != HCI_RSSI_INVALID)) { + hdev->discovery.scan_start = jiffies; + hdev->discovery.scan_duration = timeout; + } + queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable, timeout); + } unlock: hci_dev_unlock(hdev); @@ -4691,9 +4742,16 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) * Dual-mode controllers shall operate with the public * address as its identity address for BR/EDR and LE. So * reject the attempt to create an invalid configuration. + * + * The same restrictions applies when secure connections + * has been enabled. For BR/EDR this is a controller feature + * while for LE it is a host stack feature. This means that + * switching BR/EDR back on when secure connections has been + * enabled is not a supported transaction. */ if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && - bacmp(&hdev->static_addr, BDADDR_ANY)) { + (bacmp(&hdev->static_addr, BDADDR_ANY) || + test_bit(HCI_SC_ENABLED, &hdev->dev_flags))) { err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, MGMT_STATUS_REJECTED); goto unlock; @@ -4736,11 +4794,57 @@ unlock: return err; } +static void sc_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) +{ + struct pending_cmd *cmd; + struct mgmt_mode *cp; + + BT_DBG("%s status %u", hdev->name, status); + + hci_dev_lock(hdev); + + cmd = mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev); + if (!cmd) + goto unlock; + + if (status) { + cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status)); + goto remove; + } + + cp = cmd->param; + + switch (cp->val) { + case 0x00: + clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + break; + case 0x01: + set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + break; + case 0x02: + set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + set_bit(HCI_SC_ONLY, &hdev->dev_flags); + break; + } + + send_settings_rsp(cmd->sk, MGMT_OP_SET_SECURE_CONN, hdev); + new_settings(hdev, cmd->sk); + +remove: + mgmt_pending_remove(cmd); +unlock: + hci_dev_unlock(hdev); +} + static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; struct pending_cmd *cmd; + struct hci_request req; u8 val; int err; @@ -4751,6 +4855,12 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, MGMT_STATUS_NOT_SUPPORTED); + if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && + lmp_sc_capable(hdev) && + !test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_REJECTED); + if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, MGMT_STATUS_INVALID_PARAMS); @@ -4804,17 +4914,14 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, goto failed; } - err = hci_send_cmd(hdev, HCI_OP_WRITE_SC_SUPPORT, 1, &val); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT, 1, &val); + err = hci_req_run(&req, sc_enable_complete); if (err < 0) { mgmt_pending_remove(cmd); goto failed; } - if (cp->val == 0x02) - set_bit(HCI_SC_ONLY, &hdev->dev_flags); - else - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); - failed: hci_dev_unlock(hdev); return err; @@ -6262,14 +6369,16 @@ static int powered_update_hci(struct hci_dev *hdev) if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && !lmp_host_ssp_capable(hdev)) { - u8 ssp = 1; + u8 mode = 0x01; - hci_req_add(&req, HCI_OP_WRITE_SSP_MODE, 1, &ssp); - } + hci_req_add(&req, HCI_OP_WRITE_SSP_MODE, sizeof(mode), &mode); - if (bredr_sc_enabled(hdev) && !lmp_host_sc_capable(hdev)) { - u8 sc = 0x01; - hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT, sizeof(sc), &sc); + if (bredr_sc_enabled(hdev) && !lmp_host_sc_capable(hdev)) { + u8 support = 0x01; + + hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT, + sizeof(support), &support); + } } if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags) && @@ -6989,43 +7098,6 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) hci_req_run(&req, NULL); } -void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) -{ - struct cmd_lookup match = { NULL, hdev }; - bool changed = false; - - if (status) { - u8 mgmt_err = mgmt_status(status); - - if (enable) { - if (test_and_clear_bit(HCI_SC_ENABLED, - &hdev->dev_flags)) - new_settings(hdev, NULL); - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); - } - - mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev, - cmd_status_rsp, &mgmt_err); - return; - } - - if (enable) { - changed = !test_and_set_bit(HCI_SC_ENABLED, &hdev->dev_flags); - } else { - changed = test_and_clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); - } - - mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev, - settings_rsp, &match); - - if (changed) - new_settings(hdev, match.sk); - - if (match.sk) - sock_put(match.sk); -} - static void sk_lookup(struct pending_cmd *cmd, void *data) { struct cmd_lookup *match = data; @@ -7096,28 +7168,21 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, mgmt_status(status)); } else { - if (bredr_sc_enabled(hdev) && hash256 && rand256) { - struct mgmt_rp_read_local_oob_ext_data rp; + struct mgmt_rp_read_local_oob_data rp; + size_t rp_size = sizeof(rp); - memcpy(rp.hash192, hash192, sizeof(rp.hash192)); - memcpy(rp.rand192, rand192, sizeof(rp.rand192)); + memcpy(rp.hash192, hash192, sizeof(rp.hash192)); + memcpy(rp.rand192, rand192, sizeof(rp.rand192)); + if (bredr_sc_enabled(hdev) && hash256 && rand256) { memcpy(rp.hash256, hash256, sizeof(rp.hash256)); memcpy(rp.rand256, rand256, sizeof(rp.rand256)); - - cmd_complete(cmd->sk, hdev->id, - MGMT_OP_READ_LOCAL_OOB_DATA, 0, - &rp, sizeof(rp)); } else { - struct mgmt_rp_read_local_oob_data rp; - - memcpy(rp.hash, hash192, sizeof(rp.hash)); - memcpy(rp.rand, rand192, sizeof(rp.rand)); - - cmd_complete(cmd->sk, hdev->id, - MGMT_OP_READ_LOCAL_OOB_DATA, 0, - &rp, sizeof(rp)); + rp_size -= sizeof(rp.hash256) + sizeof(rp.rand256); } + + cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, 0, + &rp, rp_size); } mgmt_pending_remove(cmd); @@ -7190,6 +7255,21 @@ static bool eir_has_uuids(u8 *eir, u16 eir_len, u16 uuid_count, u8 (*uuids)[16]) return false; } +static void restart_le_scan(struct hci_dev *hdev) +{ + /* If controller is not scanning we are done. */ + if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + return; + + if (time_after(jiffies + DISCOV_LE_RESTART_DELAY, + hdev->discovery.scan_start + + hdev->discovery.scan_duration)) + return; + + queue_delayed_work(hdev->workqueue, &hdev->le_scan_restart, + DISCOV_LE_RESTART_DELAY); +} + void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len) @@ -7212,14 +7292,18 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, /* When using service discovery with a RSSI threshold, then check * if such a RSSI threshold is specified. If a RSSI threshold has - * been specified, then all results with a RSSI smaller than the - * RSSI threshold will be dropped. + * been specified, and HCI_QUIRK_STRICT_DUPLICATE_FILTER is not set, + * then all results with a RSSI smaller than the RSSI threshold will be + * dropped. If the quirk is set, let it through for further processing, + * as we might need to restart the scan. * * For BR/EDR devices (pre 1.2) providing no RSSI during inquiry, * the results are also dropped. */ if (hdev->discovery.rssi != HCI_RSSI_INVALID && - (rssi < hdev->discovery.rssi || rssi == HCI_RSSI_INVALID)) + (rssi == HCI_RSSI_INVALID || + (rssi < hdev->discovery.rssi && + !test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)))) return; /* Make sure that the buffer is big enough. The 5 extra bytes @@ -7238,7 +7322,8 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, * However when using service discovery, the value 127 will be * returned when the RSSI is not available. */ - if (rssi == HCI_RSSI_INVALID && !hdev->discovery.report_invalid_rssi) + if (rssi == HCI_RSSI_INVALID && !hdev->discovery.report_invalid_rssi && + link_type == ACL_LINK) rssi = 0; bacpy(&ev->addr.bdaddr, bdaddr); @@ -7253,12 +7338,20 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, * kept and checking possible scan response data * will be skipped. */ - if (hdev->discovery.uuid_count > 0) + if (hdev->discovery.uuid_count > 0) { match = eir_has_uuids(eir, eir_len, hdev->discovery.uuid_count, hdev->discovery.uuids); - else + /* If duplicate filtering does not report RSSI changes, + * then restart scanning to ensure updated result with + * updated RSSI values. + */ + if (match && test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, + &hdev->quirks)) + restart_le_scan(hdev); + } else { match = true; + } if (!match && !scan_rsp_len) return; @@ -7291,6 +7384,14 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, hdev->discovery.uuid_count, hdev->discovery.uuids)) return; + + /* If duplicate filtering does not report RSSI changes, + * then restart scanning to ensure updated result with + * updated RSSI values. + */ + if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, + &hdev->quirks)) + restart_le_scan(hdev); } /* Append scan response data to event */ @@ -7304,6 +7405,14 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, return; } + /* Validate the reported RSSI value against the RSSI threshold once more + * incase HCI_QUIRK_STRICT_DUPLICATE_FILTER forced a restart of LE + * scanning. + */ + if (hdev->discovery.rssi != HCI_RSSI_INVALID && + rssi < hdev->discovery.rssi) + return; + ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len); ev_size = sizeof(*ev) + eir_len + scan_rsp_len; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index d8a95755a8a8..3c6d2c8ac1a4 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -468,7 +468,7 @@ done: static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags) { - DECLARE_WAITQUEUE(wait, current); + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; long timeo; int err = 0; @@ -487,8 +487,6 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { - set_current_state(TASK_INTERRUPTIBLE); - if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; @@ -509,10 +507,11 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f } release_sock(sk); - timeo = schedule_timeout(timeo); + + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } - __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (err) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 07ec7d23b843..76321b546e84 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -618,7 +618,7 @@ done: static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flags) { - DECLARE_WAITQUEUE(wait, current); + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; @@ -632,8 +632,6 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { - set_current_state(TASK_INTERRUPTIBLE); - if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; @@ -654,10 +652,10 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag } release_sock(sk); - timeo = schedule_timeout(timeo); + + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); } - __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (err) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 37d9180bfe1c..c09a821f381d 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -620,7 +620,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, oob_data = hci_find_remote_oob_data(hdev, &hcon->dst, bdaddr_type); - if (oob_data) { + if (oob_data && oob_data->present) { set_bit(SMP_FLAG_OOB, &smp->flags); oob_flag = SMP_OOB_PRESENT; memcpy(smp->rr, oob_data->rand256, 16); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3875ea51f6fe..b93f42c515da 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,6 +16,7 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> +#include <net/switchdev.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" @@ -494,13 +495,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) } /* Change state and parameters on port. */ -int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) +int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct nlattr *protinfo; struct nlattr *afspec; struct net_bridge_port *p; struct nlattr *tb[IFLA_BRPORT_MAX + 1]; - int err = 0; + int err = 0, ret_offload = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); @@ -542,19 +543,28 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) afspec, RTM_SETLINK); } + if (!(flags & BRIDGE_FLAGS_SELF)) { + /* set bridge attributes in hardware if supported + */ + ret_offload = netdev_switch_port_bridge_setlink(dev, nlh, + flags); + if (ret_offload && ret_offload != -EOPNOTSUPP) + br_warn(p->br, "error setting attrs on port %u(%s)\n", + (unsigned int)p->port_no, p->dev->name); + } + if (err == 0) br_ifinfo_notify(RTM_NEWLINK, p); - out: return err; } /* Delete port information */ -int br_dellink(struct net_device *dev, struct nlmsghdr *nlh) +int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct nlattr *afspec; struct net_bridge_port *p; - int err; + int err = 0, ret_offload = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) @@ -573,6 +583,16 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh) */ br_ifinfo_notify(RTM_NEWLINK, p); + if (!(flags & BRIDGE_FLAGS_SELF)) { + /* del bridge attributes in hardware + */ + ret_offload = netdev_switch_port_bridge_dellink(dev, nlh, + flags); + if (ret_offload && ret_offload != -EOPNOTSUPP) + br_warn(p->br, "error deleting attrs on port %u (%s)\n", + (unsigned int)p->port_no, p->dev->name); + } + return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -701,7 +721,7 @@ static size_t br_get_link_af_size(const struct net_device *dev) return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); } -static struct rtnl_af_ops br_af_ops = { +static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size, }; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e8e3f3681680..de0919975a25 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -819,8 +819,8 @@ extern struct rtnl_link_ops br_link_ops; int br_netlink_init(void); void br_netlink_fini(void); void br_ifinfo_notify(int event, struct net_bridge_port *port); -int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg); -int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg); +int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); +int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask); diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index b0330aecbf97..3244aead0926 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -265,22 +265,12 @@ out: data[NFT_REG_VERDICT].verdict = NF_DROP; } -static int nft_reject_bridge_validate_hooks(const struct nft_chain *chain) +static int nft_reject_bridge_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { - struct nft_base_chain *basechain; - - if (chain->flags & NFT_BASE_CHAIN) { - basechain = nft_base_chain(chain); - - switch (basechain->ops[0].hooknum) { - case NF_BR_PRE_ROUTING: - case NF_BR_LOCAL_IN: - break; - default: - return -EOPNOTSUPP; - } - } - return 0; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) | + (1 << NF_BR_LOCAL_IN)); } static int nft_reject_bridge_init(const struct nft_ctx *ctx, @@ -290,7 +280,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx, struct nft_reject *priv = nft_expr_priv(expr); int icmp_code, err; - err = nft_reject_bridge_validate_hooks(ctx->chain); + err = nft_reject_bridge_validate(ctx, expr, NULL); if (err < 0) return err; @@ -341,13 +331,6 @@ nla_put_failure: return -1; } -static int nft_reject_bridge_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) -{ - return nft_reject_bridge_validate_hooks(ctx->chain); -} - static struct nft_expr_type nft_reject_bridge_type; static const struct nft_expr_ops nft_reject_bridge_ops = { .type = &nft_reject_bridge_type, diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 4589ff67bfa9..67a4a36febd1 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -470,7 +470,6 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev, ASSERT_RTNL(); caifdev = netdev_priv(dev); caif_netlink_parms(data, &caifdev->conn_req); - dev_net_set(caifdev->netdev, src_net); ret = register_netdevice(dev); if (ret) diff --git a/net/core/Makefile b/net/core/Makefile index 235e6c50708d..fec0856dd6c0 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -2,7 +2,7 @@ # Makefile for the Linux networking core. # -obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ +obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \ gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o diff --git a/net/core/dev.c b/net/core/dev.c index 7f028d441e98..a3a96ffc67f4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -371,9 +371,10 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) - return &ptype_all; + return pt->dev ? &pt->dev->ptype_all : &ptype_all; else - return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; + return pt->dev ? &pt->dev->ptype_specific : + &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } /** @@ -1734,6 +1735,23 @@ static inline int deliver_skb(struct sk_buff *skb, return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } +static inline void deliver_ptype_list_skb(struct sk_buff *skb, + struct packet_type **pt, + struct net_device *dev, __be16 type, + struct list_head *ptype_list) +{ + struct packet_type *ptype, *pt_prev = *pt; + + list_for_each_entry_rcu(ptype, ptype_list, list) { + if (ptype->type != type) + continue; + if (pt_prev) + deliver_skb(skb, pt_prev, dev); + pt_prev = ptype; + } + *pt = pt_prev; +} + static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { if (!ptype->af_packet_priv || !skb->sk) @@ -1757,45 +1775,54 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) struct packet_type *ptype; struct sk_buff *skb2 = NULL; struct packet_type *pt_prev = NULL; + struct list_head *ptype_list = &ptype_all; rcu_read_lock(); - list_for_each_entry_rcu(ptype, &ptype_all, list) { +again: + list_for_each_entry_rcu(ptype, ptype_list, list) { /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ - if ((ptype->dev == dev || !ptype->dev) && - (!skb_loop_sk(ptype, skb))) { - if (pt_prev) { - deliver_skb(skb2, pt_prev, skb->dev); - pt_prev = ptype; - continue; - } + if (skb_loop_sk(ptype, skb)) + continue; - skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) - break; + if (pt_prev) { + deliver_skb(skb2, pt_prev, skb->dev); + pt_prev = ptype; + continue; + } - net_timestamp_set(skb2); + /* need to clone skb, done only once */ + skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + goto out_unlock; - /* skb->nh should be correctly - set by sender, so that the second statement is - just protection against buggy protocols. - */ - skb_reset_mac_header(skb2); - - if (skb_network_header(skb2) < skb2->data || - skb_network_header(skb2) > skb_tail_pointer(skb2)) { - net_crit_ratelimited("protocol %04x is buggy, dev %s\n", - ntohs(skb2->protocol), - dev->name); - skb_reset_network_header(skb2); - } + net_timestamp_set(skb2); - skb2->transport_header = skb2->network_header; - skb2->pkt_type = PACKET_OUTGOING; - pt_prev = ptype; + /* skb->nh should be correctly + * set by sender, so that the second statement is + * just protection against buggy protocols. + */ + skb_reset_mac_header(skb2); + + if (skb_network_header(skb2) < skb2->data || + skb_network_header(skb2) > skb_tail_pointer(skb2)) { + net_crit_ratelimited("protocol %04x is buggy, dev %s\n", + ntohs(skb2->protocol), + dev->name); + skb_reset_network_header(skb2); } + + skb2->transport_header = skb2->network_header; + skb2->pkt_type = PACKET_OUTGOING; + pt_prev = ptype; + } + + if (ptype_list == &ptype_all) { + ptype_list = &dev->ptype_all; + goto again; } +out_unlock: if (pt_prev) pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); rcu_read_unlock(); @@ -2352,7 +2379,6 @@ EXPORT_SYMBOL(skb_checksum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { - unsigned int vlan_depth = skb->mac_len; __be16 type = skb->protocol; /* Tunnel gso handlers can set protocol to ethernet. */ @@ -2366,35 +2392,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) type = eth->h_proto; } - /* if skb->protocol is 802.1Q/AD then the header should already be - * present at mac_len - VLAN_HLEN (if mac_len > 0), or at - * ETH_HLEN otherwise - */ - if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { - if (vlan_depth) { - if (WARN_ON(vlan_depth < VLAN_HLEN)) - return 0; - vlan_depth -= VLAN_HLEN; - } else { - vlan_depth = ETH_HLEN; - } - do { - struct vlan_hdr *vh; - - if (unlikely(!pskb_may_pull(skb, - vlan_depth + VLAN_HLEN))) - return 0; - - vh = (struct vlan_hdr *)(skb->data + vlan_depth); - type = vh->h_vlan_encapsulated_proto; - vlan_depth += VLAN_HLEN; - } while (type == htons(ETH_P_8021Q) || - type == htons(ETH_P_8021AD)); - } - - *depth = vlan_depth; - - return type; + return __vlan_get_protocol(skb, type, depth); } /** @@ -2617,7 +2615,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, unsigned int len; int rc; - if (!list_empty(&ptype_all)) + if (!list_empty(&ptype_all) || !list_empty(&dev->ptype_all)) dev_queue_xmit_nit(skb, dev); len = skb->len; @@ -3615,7 +3613,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct net_device *orig_dev; - struct net_device *null_or_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; @@ -3658,11 +3655,15 @@ another_round: goto skip_taps; list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == skb->dev) { - if (pt_prev) - ret = deliver_skb(skb, pt_prev, orig_dev); - pt_prev = ptype; - } + if (pt_prev) + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = ptype; + } + + list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { + if (pt_prev) + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = ptype; } skip_taps: @@ -3718,19 +3719,21 @@ ncls: skb->vlan_tci = 0; } + type = skb->protocol; + /* deliver only exact match when indicated */ - null_or_dev = deliver_exact ? skb->dev : NULL; + if (likely(!deliver_exact)) { + deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, + &ptype_base[ntohs(type) & + PTYPE_HASH_MASK]); + } - type = skb->protocol; - list_for_each_entry_rcu(ptype, - &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && - (ptype->dev == null_or_dev || ptype->dev == skb->dev || - ptype->dev == orig_dev)) { - if (pt_prev) - ret = deliver_skb(skb, pt_prev, orig_dev); - pt_prev = ptype; - } + deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, + &orig_dev->ptype_specific); + + if (unlikely(skb->dev != orig_dev)) { + deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, + &skb->dev->ptype_specific); } if (pt_prev) { @@ -5323,7 +5326,27 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); -void netdev_adjacent_add_links(struct net_device *dev) +/** + * netdev_bonding_info_change - Dispatch event about slave change + * @dev: device + * @netdev_bonding_info: info to dispatch + * + * Send NETDEV_BONDING_INFO to netdev notifiers with info. + * The caller must hold the RTNL lock. + */ +void netdev_bonding_info_change(struct net_device *dev, + struct netdev_bonding_info *bonding_info) +{ + struct netdev_notifier_bonding_info info; + + memcpy(&info.bonding_info, bonding_info, + sizeof(struct netdev_bonding_info)); + call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev, + &info.info); +} +EXPORT_SYMBOL(netdev_bonding_info_change); + +static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; @@ -5348,7 +5371,7 @@ void netdev_adjacent_add_links(struct net_device *dev) } } -void netdev_adjacent_del_links(struct net_device *dev) +static void netdev_adjacent_del_links(struct net_device *dev) { struct netdev_adjacent *iter; @@ -6579,6 +6602,8 @@ void netdev_run_todo(void) /* paranoia */ BUG_ON(netdev_refcnt_read(dev)); + BUG_ON(!list_empty(&dev->ptype_all)); + BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); WARN_ON(dev->dn_ptr); @@ -6659,7 +6684,7 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) if (!queue) return NULL; netdev_init_one_queue(dev, queue, NULL); - queue->qdisc = &noop_qdisc; + RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); queue->qdisc_sleeping = &noop_qdisc; rcu_assign_pointer(dev->ingress_queue, queue); #endif @@ -6761,6 +6786,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->all_adj_list.upper); INIT_LIST_HEAD(&dev->all_adj_list.lower); + INIT_LIST_HEAD(&dev->ptype_all); + INIT_LIST_HEAD(&dev->ptype_specific); dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index beb83d1ac1c6..2c35c02a931e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -422,7 +422,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) dev_maps = rcu_dereference(dev->xps_maps); if (dev_maps) { map = rcu_dereference( - dev_maps->cpu_map[raw_smp_processor_id()]); + dev_maps->cpu_map[skb->sender_cpu - 1]); if (map) { if (map->len == 1) queue_index = map->queues[0]; @@ -468,6 +468,11 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, { int queue_index = 0; +#ifdef CONFIG_XPS + if (skb->sender_cpu == 0) + skb->sender_cpu = raw_smp_processor_id() + 1; +#endif + if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) diff --git a/net/core/iovec.c b/net/core/iovec.c deleted file mode 100644 index dcbe98b3726a..000000000000 --- a/net/core/iovec.c +++ /dev/null @@ -1,137 +0,0 @@ -/* - * iovec manipulation routines. - * - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Fixes: - * Andrew Lunn : Errors in iovec copying. - * Pedro Roque : Added memcpy_fromiovecend and - * csum_..._fromiovecend. - * Andi Kleen : fixed error handling for 2.1 - * Alexey Kuznetsov: 2.1 optimisations - * Andi Kleen : Fix csum*fromiovecend for IPv6. - */ - -#include <linux/errno.h> -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/net.h> -#include <linux/in6.h> -#include <asm/uaccess.h> -#include <asm/byteorder.h> -#include <net/checksum.h> -#include <net/sock.h> - -/* - * And now for the all-in-one: copy and checksum from a user iovec - * directly to a datagram - * Calls to csum_partial but the last must be in 32 bit chunks - * - * ip_build_xmit must ensure that when fragmenting only the last - * call to this function will be unaligned also. - */ -int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, - int offset, unsigned int len, __wsum *csump) -{ - __wsum csum = *csump; - int partial_cnt = 0, err = 0; - - /* Skip over the finished iovecs */ - while (offset >= iov->iov_len) { - offset -= iov->iov_len; - iov++; - } - - while (len > 0) { - u8 __user *base = iov->iov_base + offset; - int copy = min_t(unsigned int, len, iov->iov_len - offset); - - offset = 0; - - /* There is a remnant from previous iov. */ - if (partial_cnt) { - int par_len = 4 - partial_cnt; - - /* iov component is too short ... */ - if (par_len > copy) { - if (copy_from_user(kdata, base, copy)) - goto out_fault; - kdata += copy; - base += copy; - partial_cnt += copy; - len -= copy; - iov++; - if (len) - continue; - *csump = csum_partial(kdata - partial_cnt, - partial_cnt, csum); - goto out; - } - if (copy_from_user(kdata, base, par_len)) - goto out_fault; - csum = csum_partial(kdata - partial_cnt, 4, csum); - kdata += par_len; - base += par_len; - copy -= par_len; - len -= par_len; - partial_cnt = 0; - } - - if (len > copy) { - partial_cnt = copy % 4; - if (partial_cnt) { - copy -= partial_cnt; - if (copy_from_user(kdata + copy, base + copy, - partial_cnt)) - goto out_fault; - } - } - - if (copy) { - csum = csum_and_copy_from_user(base, kdata, copy, - csum, &err); - if (err) - goto out; - } - len -= copy + partial_cnt; - kdata += copy + partial_cnt; - iov++; - } - *csump = csum; -out: - return err; - -out_fault: - err = -EFAULT; - goto out; -} -EXPORT_SYMBOL(csum_partial_copy_fromiovecend); - -unsigned long iov_pages(const struct iovec *iov, int offset, - unsigned long nr_segs) -{ - unsigned long seg, base; - int pages = 0, len, size; - - while (nr_segs && (offset >= iov->iov_len)) { - offset -= iov->iov_len; - ++iov; - --nr_segs; - } - - for (seg = 0; seg < nr_segs; seg++) { - base = (unsigned long)iov[seg].iov_base + offset; - len = iov[seg].iov_len - offset; - size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; - pages += size; - offset = 0; - } - - return pages; -} -EXPORT_SYMBOL(iov_pages); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b7bde551ef76..cb5290b8c428 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -446,6 +446,7 @@ struct net *get_net_ns_by_fd(int fd) return ERR_PTR(-EINVAL); } #endif +EXPORT_SYMBOL_GPL(get_net_ns_by_fd); struct net *get_net_ns_by_pid(pid_t pid) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 07447d1665e6..5dad4f782f03 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2148,7 +2148,7 @@ replay: dev->ifindex = ifm->ifi_index; if (ops->newlink) { - err = ops->newlink(net, dev, tb, data); + err = ops->newlink(link_net ? : net, dev, tb, data); /* Drivers should call free_netdev() in ->destructor * and unregister it on failure after registration * so that device could be finally freed in rtnl_unlock. @@ -2937,12 +2937,16 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout; + if (!skb->len) + goto errout; + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; errout: WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + if (err) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return err; } @@ -2991,7 +2995,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) goto out; } - err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh); + err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags); if (err) goto out; @@ -3002,7 +3006,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (!dev->netdev_ops->ndo_bridge_setlink) err = -EOPNOTSUPP; else - err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh); + err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh, + flags); if (!err) { flags &= ~BRIDGE_FLAGS_SELF; @@ -3064,7 +3069,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) goto out; } - err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh, flags); if (err) goto out; @@ -3075,7 +3080,8 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) if (!dev->netdev_ops->ndo_bridge_dellink) err = -EOPNOTSUPP; else - err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh, + flags); if (!err) { flags &= ~BRIDGE_FLAGS_SELF; @@ -3178,6 +3184,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_UNREGISTER_FINAL: case NETDEV_RELEASE: case NETDEV_JOIN: + case NETDEV_BONDING_INFO: break; default: rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 56db472e9b86..88c613eab142 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -74,6 +74,8 @@ #include <asm/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> +#include <linux/capability.h> +#include <linux/user_namespace.h> struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; @@ -823,6 +825,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif +#ifdef CONFIG_XPS + CHECK_SKB_FIELD(sender_cpu); +#endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #ifdef CONFIG_NET_CLS_ACT @@ -3690,11 +3695,28 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, kfree_skb(skb); } +static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) +{ + bool ret; + + if (likely(sysctl_tstamp_allow_data || tsonly)) + return true; + + read_lock_bh(&sk->sk_callback_lock); + ret = sk->sk_socket && sk->sk_socket->file && + file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW); + read_unlock_bh(&sk->sk_callback_lock); + return ret; +} + void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { struct sock *sk = skb->sk; + if (!skb_may_tx_timestamp(sk, false)) + return; + /* take a reference to prevent skb_orphan() from freeing the socket */ sock_hold(sk); @@ -3710,19 +3732,28 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, struct sock *sk, int tstype) { struct sk_buff *skb; + bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; - if (!sk) + if (!sk || !skb_may_tx_timestamp(sk, tsonly)) return; - if (hwtstamps) - *skb_hwtstamps(orig_skb) = *hwtstamps; + if (tsonly) + skb = alloc_skb(0, GFP_ATOMIC); else - orig_skb->tstamp = ktime_get_real(); - - skb = skb_clone(orig_skb, GFP_ATOMIC); + skb = skb_clone(orig_skb, GFP_ATOMIC); if (!skb) return; + if (tsonly) { + skb_shinfo(skb)->tx_flags = skb_shinfo(orig_skb)->tx_flags; + skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; + } + + if (hwtstamps) + *skb_hwtstamps(skb) = *hwtstamps; + else + skb->tstamp = ktime_get_real(); + __skb_complete_tx_timestamp(skb, sk, tstype); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); @@ -4141,6 +4172,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->ignore_df = 0; skb_dst_drop(skb); skb->mark = 0; + skb->sender_cpu = 0; skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); diff --git a/net/core/sock.c b/net/core/sock.c index 1c7a33db1314..93c8b20c91e4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -325,6 +325,8 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); +int sysctl_tstamp_allow_data __read_mostly = 1; + struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; EXPORT_SYMBOL_GPL(memalloc_socks); @@ -840,6 +842,7 @@ set_rcvbuf: ret = -EINVAL; break; } + if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk->sk_protocol == IPPROTO_TCP) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 31baba2a71ce..fde21d19e61b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -321,6 +321,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tstamp_allow_data", + .data = &sysctl_tstamp_allow_data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one + }, #ifdef CONFIG_RPS { .procname = "rps_sock_flow_entries", diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 59ebe16d06fc..f0b4a31d7bd6 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2322,7 +2322,7 @@ static __net_initdata struct pernet_operations devinet_ops = { .exit = devinet_exit_net, }; -static struct rtnl_af_ops inet_af_ops = { +static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 3bc0cf07661c..92ddea1e6457 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -70,7 +70,6 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - __wsum delta; if (skb->remcsum_offload) { /* Already processed in GRO path */ @@ -82,14 +81,7 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, return NULL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) - __skb_checksum_complete(skb); - - delta = remcsum_adjust((void *)guehdr + hdrlen, - skb->csum, start, offset); - - /* Adjust skb->csum since we changed the packet */ - skb->csum = csum_add(skb->csum, delta); + skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset); return guehdr; } @@ -228,7 +220,6 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - __wsum delta; if (skb->remcsum_offload) return guehdr; @@ -243,12 +234,7 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, return NULL; } - delta = remcsum_adjust((void *)guehdr + hdrlen, - NAPI_GRO_CB(skb)->csum, start, offset); - - /* Adjust skb->csum since we changed the packet */ - skb->csum = csum_add(skb->csum, delta); - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset); skb->remcsum_offload = 1; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 36f5584d93c5..5e564014a0b7 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -205,7 +205,7 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; */ static struct sock *icmp_sk(struct net *net) { - return net->ipv4.icmp_sk[smp_processor_id()]; + return *this_cpu_ptr(net->ipv4.icmp_sk); } static inline struct sock *icmp_xmit_lock(struct net *net) @@ -1140,8 +1140,8 @@ static void __net_exit icmp_sk_exit(struct net *net) int i; for_each_possible_cpu(i) - inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]); - kfree(net->ipv4.icmp_sk); + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i)); + free_percpu(net->ipv4.icmp_sk); net->ipv4.icmp_sk = NULL; } @@ -1149,9 +1149,8 @@ static int __net_init icmp_sk_init(struct net *net) { int i, err; - net->ipv4.icmp_sk = - kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL); - if (net->ipv4.icmp_sk == NULL) + net->ipv4.icmp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.icmp_sk) return -ENOMEM; for_each_possible_cpu(i) { @@ -1162,7 +1161,7 @@ static int __net_init icmp_sk_init(struct net *net) if (err < 0) goto fail; - net->ipv4.icmp_sk[i] = sk; + *per_cpu_ptr(net->ipv4.icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff/skb_shared_info struct overhead. @@ -1203,8 +1202,8 @@ static int __net_init icmp_sk_init(struct net *net) fail: for_each_possible_cpu(i) - inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]); - kfree(net->ipv4.icmp_sk); + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i)); + free_percpu(net->ipv4.icmp_sk); return err; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b50861b22b6b..d68199d9b2b0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -755,13 +755,11 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { - /* XXX: stripping const */ - if (memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len) < 0) + if (copy_from_iter(to, len, &msg->msg_iter) != len) return -EFAULT; } else { __wsum csum = 0; - /* XXX: stripping const */ - if (csum_partial_copy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len, &csum) < 0) + if (csum_and_copy_from_iter(to, len, &csum, &msg->msg_iter) != len) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } @@ -1506,23 +1504,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. - * - * Use a fake percpu inet socket to avoid false sharing and contention. */ -static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { - .sk = { - .__sk_common = { - .skc_refcnt = ATOMIC_INIT(1), - }, - .sk_wmem_alloc = ATOMIC_INIT(1), - .sk_allocation = GFP_ATOMIC, - .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), - }, - .pmtudisc = IP_PMTUDISC_WANT, - .uc_ttl = -1, -}; - -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, @@ -1532,9 +1515,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct sk_buff *nskb; - struct sock *sk; - struct inet_sock *inet; int err; if (__ip_options_echo(&replyopts.opt.opt, skb, sopt)) @@ -1565,15 +1547,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, if (IS_ERR(rt)) return; - inet = &get_cpu_var(unicast_sock); + inet_sk(sk)->tos = arg->tos; - inet->tos = arg->tos; - sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sock_net_set(sk, net); - __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); @@ -1589,13 +1567,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } out: - put_cpu_var(unicast_sock); - ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index db5e0f81ce0a..31d8c71986b4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -483,7 +483,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr = SKB_EXT_ERR(skb); - if (sin) { + if (sin && skb->len) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); @@ -496,8 +496,9 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || - ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin)) { + if (skb->len && + (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || + ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin))) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; if (inet_sk(sk)->cmsg_flags) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2a3720fb5a5f..e9f66e1cda50 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -599,18 +599,18 @@ int ping_getfrag(void *from, char *to, struct pingfakehdr *pfh = (struct pingfakehdr *)from; if (offset == 0) { - if (fraglen < sizeof(struct icmphdr)) + fraglen -= sizeof(struct icmphdr); + if (fraglen < 0) BUG(); - if (csum_partial_copy_fromiovecend(to + sizeof(struct icmphdr), - pfh->iov, 0, fraglen - sizeof(struct icmphdr), - &pfh->wcheck)) + if (csum_and_copy_from_iter(to + sizeof(struct icmphdr), + fraglen, &pfh->wcheck, + &pfh->msg->msg_iter) != fraglen) return -EFAULT; } else if (offset < sizeof(struct icmphdr)) { BUG(); } else { - if (csum_partial_copy_fromiovecend - (to, pfh->iov, offset - sizeof(struct icmphdr), - fraglen, &pfh->wcheck)) + if (csum_and_copy_from_iter(to, fraglen, &pfh->wcheck, + &pfh->msg->msg_iter) != fraglen) return -EFAULT; } @@ -811,8 +811,7 @@ back_from_confirm: pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; - /* XXX: stripping const */ - pfh.iov = (struct iovec *)msg->msg_iter.iov; + pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 0bb68df5055d..f027a708b7e0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -337,7 +337,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) } static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, - void *from, size_t length, + struct msghdr *msg, size_t length, struct rtable **rtp, unsigned int flags) { @@ -382,7 +382,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->transport_header = skb->network_header; err = -EFAULT; - if (memcpy_fromiovecend((void *)iph, from, 0, length)) + if (memcpy_from_msg(iph, msg, length)) goto error_free; iphlen = iph->ihl * 4; @@ -625,8 +625,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, back_from_confirm: if (inet->hdrincl) - /* XXX: stripping const */ - err = raw_send_hdrinc(sk, &fl4, (struct iovec *)msg->msg_iter.iov, len, + err = raw_send_hdrinc(sk, &fl4, msg, len, &rt, msg->msg_flags); else { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0c63b2abd873..ad5064362c5c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -966,6 +966,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (dst->dev->mtu < mtu) return; + if (rt->rt_pmtu && rt->rt_pmtu < mtu) + return; + if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3075723c729b..9d72a0fcd928 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1067,11 +1067,10 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { - const struct iovec *iov; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int iovlen, flags, err, copied = 0; - int mss_now = 0, size_goal, copied_syn = 0, offset = 0; + int flags, err, copied = 0; + int mss_now = 0, size_goal, copied_syn = 0; bool sg; long timeo; @@ -1084,7 +1083,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto out; else if (err) goto out_err; - offset = copied_syn; } timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); @@ -1118,8 +1116,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, mss_now = tcp_send_mss(sk, &size_goal, flags); /* Ok commence sending. */ - iovlen = msg->msg_iter.nr_segs; - iov = msg->msg_iter.iov; copied = 0; err = -EPIPE; @@ -1128,151 +1124,134 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = !!(sk->sk_route_caps & NETIF_F_SG); - while (--iovlen >= 0) { - size_t seglen = iov->iov_len; - unsigned char __user *from = iov->iov_base; + while (iov_iter_count(&msg->msg_iter)) { + int copy = 0; + int max = size_goal; - iov++; - if (unlikely(offset > 0)) { /* Skip bytes copied in SYN */ - if (offset >= seglen) { - offset -= seglen; - continue; - } - seglen -= offset; - from += offset; - offset = 0; + skb = tcp_write_queue_tail(sk); + if (tcp_send_head(sk)) { + if (skb->ip_summed == CHECKSUM_NONE) + max = mss_now; + copy = max - skb->len; } - while (seglen > 0) { - int copy = 0; - int max = size_goal; - - skb = tcp_write_queue_tail(sk); - if (tcp_send_head(sk)) { - if (skb->ip_summed == CHECKSUM_NONE) - max = mss_now; - copy = max - skb->len; - } - - if (copy <= 0) { + if (copy <= 0) { new_segment: - /* Allocate new segment. If the interface is SG, - * allocate skb fitting to single page. - */ - if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; + /* Allocate new segment. If the interface is SG, + * allocate skb fitting to single page. + */ + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; - skb = sk_stream_alloc_skb(sk, - select_size(sk, sg), - sk->sk_allocation); - if (!skb) - goto wait_for_memory; + skb = sk_stream_alloc_skb(sk, + select_size(sk, sg), + sk->sk_allocation); + if (!skb) + goto wait_for_memory; - /* - * Check whether we can use HW checksum. - */ - if (sk->sk_route_caps & NETIF_F_ALL_CSUM) - skb->ip_summed = CHECKSUM_PARTIAL; + /* + * Check whether we can use HW checksum. + */ + if (sk->sk_route_caps & NETIF_F_ALL_CSUM) + skb->ip_summed = CHECKSUM_PARTIAL; - skb_entail(sk, skb); - copy = size_goal; - max = size_goal; + skb_entail(sk, skb); + copy = size_goal; + max = size_goal; - /* All packets are restored as if they have - * already been sent. skb_mstamp isn't set to - * avoid wrong rtt estimation. - */ - if (tp->repair) - TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; - } + /* All packets are restored as if they have + * already been sent. skb_mstamp isn't set to + * avoid wrong rtt estimation. + */ + if (tp->repair) + TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; + } - /* Try to append data to the end of skb. */ - if (copy > seglen) - copy = seglen; - - /* Where to copy to? */ - if (skb_availroom(skb) > 0) { - /* We have some space in skb head. Superb! */ - copy = min_t(int, copy, skb_availroom(skb)); - err = skb_add_data_nocache(sk, skb, from, copy); - if (err) - goto do_fault; - } else { - bool merge = true; - int i = skb_shinfo(skb)->nr_frags; - struct page_frag *pfrag = sk_page_frag(sk); - - if (!sk_page_frag_refill(sk, pfrag)) - goto wait_for_memory; - - if (!skb_can_coalesce(skb, i, pfrag->page, - pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { - tcp_mark_push(tp, skb); - goto new_segment; - } - merge = false; - } + /* Try to append data to the end of skb. */ + if (copy > iov_iter_count(&msg->msg_iter)) + copy = iov_iter_count(&msg->msg_iter); + + /* Where to copy to? */ + if (skb_availroom(skb) > 0) { + /* We have some space in skb head. Superb! */ + copy = min_t(int, copy, skb_availroom(skb)); + err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy); + if (err) + goto do_fault; + } else { + bool merge = true; + int i = skb_shinfo(skb)->nr_frags; + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + goto wait_for_memory; - copy = min_t(int, copy, pfrag->size - pfrag->offset); - - if (!sk_wmem_schedule(sk, copy)) - goto wait_for_memory; - - err = skb_copy_to_page_nocache(sk, from, skb, - pfrag->page, - pfrag->offset, - copy); - if (err) - goto do_error; - - /* Update the skb. */ - if (merge) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); - } else { - skb_fill_page_desc(skb, i, pfrag->page, - pfrag->offset, copy); - get_page(pfrag->page); + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + if (i == MAX_SKB_FRAGS || !sg) { + tcp_mark_push(tp, skb); + goto new_segment; } - pfrag->offset += copy; + merge = false; } - if (!copied) - TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; + copy = min_t(int, copy, pfrag->size - pfrag->offset); - tp->write_seq += copy; - TCP_SKB_CB(skb)->end_seq += copy; - tcp_skb_pcount_set(skb, 0); + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_memory; - from += copy; - copied += copy; - if ((seglen -= copy) == 0 && iovlen == 0) { - tcp_tx_timestamp(sk, skb); - goto out; + err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, + pfrag->page, + pfrag->offset, + copy); + if (err) + goto do_error; + + /* Update the skb. */ + if (merge) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + } else { + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); } + pfrag->offset += copy; + } - if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) - continue; + if (!copied) + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; + + tp->write_seq += copy; + TCP_SKB_CB(skb)->end_seq += copy; + tcp_skb_pcount_set(skb, 0); + + copied += copy; + if (!iov_iter_count(&msg->msg_iter)) { + tcp_tx_timestamp(sk, skb); + goto out; + } - if (forced_push(tp)) { - tcp_mark_push(tp, skb); - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); - } else if (skb == tcp_send_head(sk)) - tcp_push_one(sk, mss_now); + if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) continue; + if (forced_push(tp)) { + tcp_mark_push(tp, skb); + __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); + } else if (skb == tcp_send_head(sk)) + tcp_push_one(sk, mss_now); + continue; + wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied) - tcp_push(sk, flags & ~MSG_MORE, mss_now, - TCP_NAGLE_PUSH, size_goal); + if (copied) + tcp_push(sk, flags & ~MSG_MORE, mss_now, + TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) - goto do_error; + if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + goto do_error; - mss_now = tcp_send_mss(sk, &size_goal, flags); - } + mss_now = tcp_send_mss(sk, &size_goal, flags); } out: diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index bb395d46a389..c037644eafb7 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -150,7 +150,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) tcp_slow_start(tp, acked); else { bictcp_update(ca, tp->snd_cwnd); - tcp_cong_avoid_ai(tp, ca->cnt); + tcp_cong_avoid_ai(tp, ca->cnt, 1); } } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 63c29dba68a8..d694088214cd 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -360,26 +360,32 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ -void tcp_slow_start(struct tcp_sock *tp, u32 acked) +u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { u32 cwnd = tp->snd_cwnd + acked; if (cwnd > tp->snd_ssthresh) cwnd = tp->snd_ssthresh + 1; + acked -= cwnd - tp->snd_cwnd; tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); + + return acked; } EXPORT_SYMBOL_GPL(tcp_slow_start); -/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */ -void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w) +/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), + * for every packet that was ACKed. + */ +void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { + tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { - if (tp->snd_cwnd < tp->snd_cwnd_clamp) - tp->snd_cwnd++; - tp->snd_cwnd_cnt = 0; - } else { - tp->snd_cwnd_cnt++; + u32 delta = tp->snd_cwnd_cnt / w; + + tp->snd_cwnd_cnt -= delta * w; + tp->snd_cwnd += delta; } + tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); @@ -398,11 +404,13 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In "safe" area, increase. */ - if (tp->snd_cwnd <= tp->snd_ssthresh) - tcp_slow_start(tp, acked); + if (tp->snd_cwnd <= tp->snd_ssthresh) { + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } /* In dangerous area, increase slowly. */ - else - tcp_cong_avoid_ai(tp, tp->snd_cwnd); + tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked); } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 6b6002416a73..4b276d1ed980 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -93,9 +93,7 @@ struct bictcp { u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ -#define ACK_RATIO_SHIFT 4 -#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT) - u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ + u16 unused; u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ u32 round_start; /* beginning of each round */ @@ -114,7 +112,6 @@ static inline void bictcp_reset(struct bictcp *ca) ca->bic_K = 0; ca->delay_min = 0; ca->epoch_start = 0; - ca->delayed_ack = 2 << ACK_RATIO_SHIFT; ca->ack_cnt = 0; ca->tcp_cwnd = 0; ca->found = 0; @@ -205,23 +202,30 @@ static u32 cubic_root(u64 a) /* * Compute congestion window to use. */ -static inline void bictcp_update(struct bictcp *ca, u32 cwnd) +static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) { u32 delta, bic_target, max_cnt; u64 offs, t; - ca->ack_cnt++; /* count the number of ACKs */ + ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32) return; + /* The CUBIC function can update ca->cnt at most once per jiffy. + * On all cwnd reduction events, ca->epoch_start is set to 0, + * which will force a recalculation of ca->cnt. + */ + if (ca->epoch_start && tcp_time_stamp == ca->last_time) + goto tcp_friendliness; + ca->last_cwnd = cwnd; ca->last_time = tcp_time_stamp; if (ca->epoch_start == 0) { ca->epoch_start = tcp_time_stamp; /* record beginning */ - ca->ack_cnt = 1; /* start counting */ + ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ if (ca->last_max_cwnd <= cwnd) { @@ -283,6 +287,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) if (ca->last_max_cwnd == 0 && ca->cnt > 20) ca->cnt = 20; /* increase cwnd 5% per RTT */ +tcp_friendliness: /* TCP Friendly */ if (tcp_friendliness) { u32 scale = beta_scale; @@ -301,7 +306,6 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) } } - ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack; if (ca->cnt == 0) /* cannot be zero */ ca->cnt = 1; } @@ -317,11 +321,12 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (tp->snd_cwnd <= tp->snd_ssthresh) { if (hystart && after(ack, ca->end_seq)) bictcp_hystart_reset(sk); - tcp_slow_start(tp, acked); - } else { - bictcp_update(ca, tp->snd_cwnd); - tcp_cong_avoid_ai(tp, ca->cnt); + acked = tcp_slow_start(tp, acked); + if (!acked) + return; } + bictcp_update(ca, tp->snd_cwnd, acked); + tcp_cong_avoid_ai(tp, ca->cnt, acked); } static u32 bictcp_recalc_ssthresh(struct sock *sk) @@ -411,20 +416,10 @@ static void hystart_update(struct sock *sk, u32 delay) */ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) { - const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 delay; - if (icsk->icsk_ca_state == TCP_CA_Open) { - u32 ratio = ca->delayed_ack; - - ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; - ratio += cnt; - - ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT); - } - /* Some calls are for duplicates without timetamps */ if (rtt_us < 0) return; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 71fb37c70581..d3dfff78fa19 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3183,8 +3183,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); - if (ca_ops->pkts_acked) - ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us); + if (ca_ops->pkts_acked) { + long rtt_us = min_t(ulong, ca_seq_rtt_us, sack_rtt_us); + ca_ops->pkts_acked(sk, pkts_acked, rtt_us); + } } else if (skb && rtt_update && sack_rtt_us >= 0 && sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { @@ -5870,10 +5872,9 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) * TCP ECN negotiation. * * Exception: tcp_ca wants ECN. This is required for DCTCP - * congestion control; it requires setting ECT on all packets, - * including SYN. We inverse the test in this case: If our - * local socket wants ECN, but peer only set ece/cwr (but not - * ECT in IP header) its probably a non-DCTCP aware sender. + * congestion control: Linux DCTCP asserts ECT on all packets, + * including SYN, which is most optimal solution; however, + * others, such as FreeBSD do not. */ static void tcp_ecn_create_request(struct request_sock *req, const struct sk_buff *skb, @@ -5883,18 +5884,15 @@ static void tcp_ecn_create_request(struct request_sock *req, const struct tcphdr *th = tcp_hdr(skb); const struct net *net = sock_net(listen_sk); bool th_ecn = th->ece && th->cwr; - bool ect, need_ecn, ecn_ok; + bool ect, ecn_ok; if (!th_ecn) return; ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield); - need_ecn = tcp_ca_needs_ecn(listen_sk); ecn_ok = net->ipv4.sysctl_tcp_ecn || dst_feature(dst, RTAX_FEATURE_ECN); - if (!ect && !need_ecn && ecn_ok) - inet_rsk(req)->ecn_ok = 1; - else if (ect && need_ecn) + if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk)) inet_rsk(req)->ecn_ok = 1; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ad3e65bdd368..67bc95fb5d9e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -683,7 +683,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.bound_dev_if = sk->sk_bound_dev_if; arg.tos = ip_hdr(skb)->tos; - ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); @@ -767,7 +768,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); @@ -2430,14 +2432,39 @@ struct proto tcp_prot = { }; EXPORT_SYMBOL(tcp_prot); +static void __net_exit tcp_sk_exit(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); +} + static int __net_init tcp_sk_init(struct net *net) { + int res, cpu; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; return 0; -} -static void __net_exit tcp_sk_exit(struct net *net) -{ +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 20ab06b228ac..4fcc9a768849 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -948,7 +948,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; - skb->destructor = tcp_wfree; + skb->destructor = skb_is_tcp_pure_ack(skb) ? sock_wfree : tcp_wfree; skb_set_hash_from_sk(skb, sk); atomic_add(skb->truesize, &sk->sk_wmem_alloc); @@ -3055,7 +3055,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, err = 0; + int syn_loss = 0, space, err = 0, copied; unsigned long last_syn_loss = 0; struct sk_buff *syn_data; @@ -3093,11 +3093,16 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); - if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space), - fo->data->msg_iter.iov, 0, space))) { + copied = copy_from_iter(skb_put(syn_data, space), space, + &fo->data->msg_iter); + if (unlikely(!copied)) { kfree_skb(syn_data); goto fallback; } + if (copied != space) { + skb_trim(syn_data, copied); + space = copied; + } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) @@ -3265,6 +3270,14 @@ void tcp_send_ack(struct sock *sk) skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); + /* We do not want pure acks influencing TCP Small Queues or fq/pacing + * too much. + * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784 + * We also avoid tcp_wfree() overhead (cache line miss accessing + * tp->tsq_flags) by using regular sock_wfree() + */ + skb_set_tcp_pure_ack(buff); + /* Send it off, this clears delayed acks for us. */ skb_mstamp_get(&buff->skb_mstamp); tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 6824afb65d93..333bcb2415ff 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -25,7 +25,8 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (tp->snd_cwnd <= tp->snd_ssthresh) tcp_slow_start(tp, acked); else - tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT)); + tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT), + 1); } static u32 tcp_scalable_ssthresh(struct sock *sk) diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index a4d2d2d88dca..112151eeee45 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -159,7 +159,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) /* In the "non-congestive state", increase cwnd * every rtt. */ - tcp_cong_avoid_ai(tp, tp->snd_cwnd); + tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1); } else { /* In the "congestive state", increase cwnd * every other rtt. diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index cd7273218598..17d35662930d 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -92,7 +92,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) } else { /* Reno */ - tcp_cong_avoid_ai(tp, tp->snd_cwnd); + tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1); } /* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7dcc065e2160..8623118cb2bb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5405,7 +5405,7 @@ static struct pernet_operations addrconf_ops = { .exit = addrconf_exit_net, }; -static struct rtnl_af_ops inet6_ops = { +static struct rtnl_af_ops inet6_ops __read_mostly = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, .get_link_af_size = inet6_get_link_af_size, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 49f5e73db122..c215be70cac0 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -369,7 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr = SKB_EXT_ERR(skb); - if (sin) { + if (sin && skb->len) { const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; @@ -394,8 +394,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); - - if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { + if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL && skb->len) { sin->sin6_family = AF_INET6; if (np->rxopt.all) { if (serr->ee.ee_origin != SO_EE_ORIGIN_ICMP && diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 6dee2a8ca0a9..bc28b7d42a6d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -417,7 +417,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (code == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); - if (teli && teli == info - 2) { + if (teli && teli == be32_to_cpu(info) - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", @@ -429,7 +429,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } break; case ICMPV6_PKT_TOOBIG: - mtu = info - offset; + mtu = be32_to_cpu(info) - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; t->dev->mtu = mtu; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ce69a12ae48c..d33df4cbd872 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -537,20 +537,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static u32 ip6_idents_hashrnd __read_mostly; - u32 hash, id; - - net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - - hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); - hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); - - id = ip_idents_reserve(hash, 1); - fhdr->identification = htonl(id); -} - int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -1041,6 +1027,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); static inline int ip6_ufo_append_data(struct sock *sk, + struct sk_buff_head *queue, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, @@ -1056,7 +1043,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, * device, so create one single skb packet containing complete * udp datagram */ - skb = skb_peek_tail(&sk->sk_write_queue); + skb = skb_peek_tail(queue); if (skb == NULL) { skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, @@ -1079,7 +1066,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->csum = 0; - __skb_queue_tail(&sk->sk_write_queue, skb); + __skb_queue_tail(queue, skb); } else if (skb_is_gso(skb)) { goto append; } @@ -1135,99 +1122,106 @@ static void ip6_append_data_mtu(unsigned int *mtu, } } -int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, - int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, - int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, int dontfrag) +static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, + struct inet6_cork *v6_cork, + int hlimit, int tclass, struct ipv6_txoptions *opt, + struct rt6_info *rt, struct flowi6 *fl6) { - struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_cork *cork; + unsigned int mtu; + + /* + * setup for corking + */ + if (opt) { + if (WARN_ON(v6_cork->opt)) + return -EINVAL; + + v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation); + if (unlikely(v6_cork->opt == NULL)) + return -ENOBUFS; + + v6_cork->opt->tot_len = opt->tot_len; + v6_cork->opt->opt_flen = opt->opt_flen; + v6_cork->opt->opt_nflen = opt->opt_nflen; + + v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt, + sk->sk_allocation); + if (opt->dst0opt && !v6_cork->opt->dst0opt) + return -ENOBUFS; + + v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt, + sk->sk_allocation); + if (opt->dst1opt && !v6_cork->opt->dst1opt) + return -ENOBUFS; + + v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt, + sk->sk_allocation); + if (opt->hopopt && !v6_cork->opt->hopopt) + return -ENOBUFS; + + v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt, + sk->sk_allocation); + if (opt->srcrt && !v6_cork->opt->srcrt) + return -ENOBUFS; + + /* need source address above miyazawa*/ + } + dst_hold(&rt->dst); + cork->base.dst = &rt->dst; + cork->fl.u.ip6 = *fl6; + v6_cork->hop_limit = hlimit; + v6_cork->tclass = tclass; + if (rt->dst.flags & DST_XFRM_TUNNEL) + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? + rt->dst.dev->mtu : dst_mtu(&rt->dst); + else + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? + rt->dst.dev->mtu : dst_mtu(rt->dst.path); + if (np->frag_size < mtu) { + if (np->frag_size) + mtu = np->frag_size; + } + cork->base.fragsize = mtu; + if (dst_allfrag(rt->dst.path)) + cork->base.flags |= IPCORK_ALLFRAG; + cork->base.length = 0; + + return 0; +} + +static int __ip6_append_data(struct sock *sk, + struct flowi6 *fl6, + struct sk_buff_head *queue, + struct inet_cork *cork, + struct inet6_cork *v6_cork, + struct page_frag *pfrag, + int getfrag(void *from, char *to, int offset, + int len, int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + unsigned int flags, int dontfrag) +{ struct sk_buff *skb, *skb_prev = NULL; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; - int exthdrlen; - int dst_exthdrlen; + int exthdrlen = 0; + int dst_exthdrlen = 0; int hh_len; int copy; int err; int offset = 0; __u8 tx_flags = 0; u32 tskey = 0; + struct rt6_info *rt = (struct rt6_info *)cork->dst; + struct ipv6_txoptions *opt = v6_cork->opt; + int csummode = CHECKSUM_NONE; - if (flags&MSG_PROBE) - return 0; - cork = &inet->cork.base; - if (skb_queue_empty(&sk->sk_write_queue)) { - /* - * setup for corking - */ - if (opt) { - if (WARN_ON(np->cork.opt)) - return -EINVAL; - - np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation); - if (unlikely(np->cork.opt == NULL)) - return -ENOBUFS; - - np->cork.opt->tot_len = opt->tot_len; - np->cork.opt->opt_flen = opt->opt_flen; - np->cork.opt->opt_nflen = opt->opt_nflen; - - np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt, - sk->sk_allocation); - if (opt->dst0opt && !np->cork.opt->dst0opt) - return -ENOBUFS; - - np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt, - sk->sk_allocation); - if (opt->dst1opt && !np->cork.opt->dst1opt) - return -ENOBUFS; - - np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt, - sk->sk_allocation); - if (opt->hopopt && !np->cork.opt->hopopt) - return -ENOBUFS; - - np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt, - sk->sk_allocation); - if (opt->srcrt && !np->cork.opt->srcrt) - return -ENOBUFS; - - /* need source address above miyazawa*/ - } - dst_hold(&rt->dst); - cork->dst = &rt->dst; - inet->cork.fl.u.ip6 = *fl6; - np->cork.hop_limit = hlimit; - np->cork.tclass = tclass; - if (rt->dst.flags & DST_XFRM_TUNNEL) - mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(&rt->dst); - else - mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); - if (np->frag_size < mtu) { - if (np->frag_size) - mtu = np->frag_size; - } - cork->fragsize = mtu; - if (dst_allfrag(rt->dst.path)) - cork->flags |= IPCORK_ALLFRAG; - cork->length = 0; - exthdrlen = (opt ? opt->opt_flen : 0); - length += exthdrlen; - transhdrlen += exthdrlen; + skb = skb_peek_tail(queue); + if (!skb) { + exthdrlen = opt ? opt->opt_flen : 0; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; - } else { - rt = (struct rt6_info *)cork->dst; - fl6 = &inet->cork.fl.u.ip6; - opt = np->cork.opt; - transhdrlen = 0; - exthdrlen = 0; - dst_exthdrlen = 0; - mtu = cork->fragsize; } + + mtu = cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1276,6 +1270,14 @@ emsgsize: tskey = sk->sk_tskey++; } + /* If this is the first and only packet and device + * supports checksum offloading, let's use it. + */ + if (!skb && + length + fragheaderlen < mtu && + rt->dst.dev->features & NETIF_F_V6_CSUM && + !exthdrlen) + csummode = CHECKSUM_PARTIAL; /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1292,13 +1294,12 @@ emsgsize: * --yoshfuji */ - skb = skb_peek_tail(&sk->sk_write_queue); cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { - err = ip6_ufo_append_data(sk, getfrag, from, length, + err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); if (err) @@ -1389,7 +1390,7 @@ alloc_new_skb: * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = csummode; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + @@ -1439,7 +1440,7 @@ alloc_new_skb: /* * Put the packet on the pending queue */ - __skb_queue_tail(&sk->sk_write_queue, skb); + __skb_queue_tail(queue, skb); continue; } @@ -1458,7 +1459,6 @@ alloc_new_skb: } } else { int i = skb_shinfo(skb)->nr_frags; - struct page_frag *pfrag = sk_page_frag(sk); err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) @@ -1501,43 +1501,81 @@ error: IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } + +int ip6_append_data(struct sock *sk, + int getfrag(void *from, char *to, int offset, int len, + int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, int hlimit, + int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, + struct rt6_info *rt, unsigned int flags, int dontfrag) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + int exthdrlen; + int err; + + if (flags&MSG_PROBE) + return 0; + if (skb_queue_empty(&sk->sk_write_queue)) { + /* + * setup for corking + */ + err = ip6_setup_cork(sk, &inet->cork, &np->cork, hlimit, + tclass, opt, rt, fl6); + if (err) + return err; + + exthdrlen = (opt ? opt->opt_flen : 0); + length += exthdrlen; + transhdrlen += exthdrlen; + } else { + fl6 = &inet->cork.fl.u.ip6; + transhdrlen = 0; + } + + return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base, + &np->cork, sk_page_frag(sk), getfrag, + from, length, transhdrlen, flags, dontfrag); +} EXPORT_SYMBOL_GPL(ip6_append_data); -static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np) +static void ip6_cork_release(struct inet_cork_full *cork, + struct inet6_cork *v6_cork) { - if (np->cork.opt) { - kfree(np->cork.opt->dst0opt); - kfree(np->cork.opt->dst1opt); - kfree(np->cork.opt->hopopt); - kfree(np->cork.opt->srcrt); - kfree(np->cork.opt); - np->cork.opt = NULL; + if (v6_cork->opt) { + kfree(v6_cork->opt->dst0opt); + kfree(v6_cork->opt->dst1opt); + kfree(v6_cork->opt->hopopt); + kfree(v6_cork->opt->srcrt); + kfree(v6_cork->opt); + v6_cork->opt = NULL; } - if (inet->cork.base.dst) { - dst_release(inet->cork.base.dst); - inet->cork.base.dst = NULL; - inet->cork.base.flags &= ~IPCORK_ALLFRAG; + if (cork->base.dst) { + dst_release(cork->base.dst); + cork->base.dst = NULL; + cork->base.flags &= ~IPCORK_ALLFRAG; } - memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); + memset(&cork->fl, 0, sizeof(cork->fl)); } -int ip6_push_pending_frames(struct sock *sk) +struct sk_buff *__ip6_make_skb(struct sock *sk, + struct sk_buff_head *queue, + struct inet_cork_full *cork, + struct inet6_cork *v6_cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; - struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; - struct ipv6_txoptions *opt = np->cork.opt; - struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst; - struct flowi6 *fl6 = &inet->cork.fl.u.ip6; + struct ipv6_txoptions *opt = v6_cork->opt; + struct rt6_info *rt = (struct rt6_info *)cork->base.dst; + struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; - int err = 0; - skb = __skb_dequeue(&sk->sk_write_queue); + skb = __skb_dequeue(queue); if (skb == NULL) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); @@ -1545,7 +1583,7 @@ int ip6_push_pending_frames(struct sock *sk) /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); - while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { + while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); @@ -1570,10 +1608,10 @@ int ip6_push_pending_frames(struct sock *sk) skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, np->cork.tclass, + ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, np->autoflowlabel)); - hdr->hop_limit = np->cork.hop_limit; + hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; @@ -1590,34 +1628,104 @@ int ip6_push_pending_frames(struct sock *sk) ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } + ip6_cork_release(cork, v6_cork); +out: + return skb; +} + +int ip6_send_skb(struct sk_buff *skb) +{ + struct net *net = sock_net(skb->sk); + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + int err; + err = ip6_local_out(skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) - goto error; + IP6_INC_STATS(net, rt->rt6i_idev, + IPSTATS_MIB_OUTDISCARDS); } -out: - ip6_cork_release(inet, np); return err; -error: - IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); - goto out; +} + +int ip6_push_pending_frames(struct sock *sk) +{ + struct sk_buff *skb; + + skb = ip6_finish_skb(sk); + if (!skb) + return 0; + + return ip6_send_skb(skb); } EXPORT_SYMBOL_GPL(ip6_push_pending_frames); -void ip6_flush_pending_frames(struct sock *sk) +static void __ip6_flush_pending_frames(struct sock *sk, + struct sk_buff_head *queue, + struct inet_cork_full *cork, + struct inet6_cork *v6_cork) { struct sk_buff *skb; - while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { + while ((skb = __skb_dequeue_tail(queue)) != NULL) { if (skb_dst(skb)) IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } - ip6_cork_release(inet_sk(sk), inet6_sk(sk)); + ip6_cork_release(cork, v6_cork); +} + +void ip6_flush_pending_frames(struct sock *sk) +{ + __ip6_flush_pending_frames(sk, &sk->sk_write_queue, + &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); + +struct sk_buff *ip6_make_skb(struct sock *sk, + int getfrag(void *from, char *to, int offset, + int len, int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + int hlimit, int tclass, + struct ipv6_txoptions *opt, struct flowi6 *fl6, + struct rt6_info *rt, unsigned int flags, + int dontfrag) +{ + struct inet_cork_full cork; + struct inet6_cork v6_cork; + struct sk_buff_head queue; + int exthdrlen = (opt ? opt->opt_flen : 0); + int err; + + if (flags & MSG_PROBE) + return NULL; + + __skb_queue_head_init(&queue); + + cork.base.flags = 0; + cork.base.addr = 0; + cork.base.opt = NULL; + v6_cork.opt = NULL; + err = ip6_setup_cork(sk, &cork, &v6_cork, hlimit, tclass, opt, rt, fl6); + if (err) + return ERR_PTR(err); + + if (dontfrag < 0) + dontfrag = inet6_sk(sk)->dontfrag; + + err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork, + ¤t->task_frag, getfrag, from, + length + exthdrlen, transhdrlen + exthdrlen, + flags, dontfrag); + if (err) { + __ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork); + return ERR_PTR(err); + } + + return __ip6_make_skb(sk, &queue, &cork, &v6_cork); +} diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 97f41a3e68d9..54520a0bd5e3 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -9,6 +9,24 @@ #include <net/addrconf.h> #include <net/secure_seq.h> +u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src) +{ + u32 hash, id; + + hash = __ipv6_addr_jhash(dst, hashrnd); + hash = __ipv6_addr_jhash(src, hash); + + /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, + * set the hight order instead thus minimizing possible future + * collisions. + */ + id = ip_idents_reserve(hash, 1); + if (unlikely(!id)) + id = 1 << 31; + + return id; +} + /* This function exists only for tap drivers that must support broken * clients requesting UFO without specifying an IPv6 fragment ID. * @@ -22,7 +40,7 @@ void ipv6_proxy_select_ident(struct sk_buff *skb) static u32 ip6_proxy_idents_hashrnd __read_mostly; struct in6_addr buf[2]; struct in6_addr *addrs; - u32 hash, id; + u32 id; addrs = skb_header_pointer(skb, skb_network_offset(skb) + @@ -34,14 +52,25 @@ void ipv6_proxy_select_ident(struct sk_buff *skb) net_get_random_once(&ip6_proxy_idents_hashrnd, sizeof(ip6_proxy_idents_hashrnd)); - hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd); - hash = __ipv6_addr_jhash(&addrs[0], hash); - - id = ip_idents_reserve(hash, 1); - skb_shinfo(skb)->ip6_frag_id = htonl(id); + id = __ipv6_select_ident(ip6_proxy_idents_hashrnd, + &addrs[1], &addrs[0]); + skb_shinfo(skb)->ip6_frag_id = id; } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); +void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static u32 ip6_idents_hashrnd __read_mostly; + u32 id; + + net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + + id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr, + &rt->rt6i_src.addr); + fhdr->identification = htonl(id); +} +EXPORT_SYMBOL(ipv6_select_ident); + int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { u16 offset = sizeof(struct ipv6hdr); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 2d3148378a1f..bd46f736f61d 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -163,8 +163,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; - /* XXX: stripping const */ - pfh.iov = (struct iovec *)msg->msg_iter.iov; + pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET6; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ee25631f8c29..dae7f1a1e464 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -609,7 +609,7 @@ out: return err; } -static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, +static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags) { @@ -648,7 +648,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, skb->ip_summed = CHECKSUM_NONE; skb->transport_header = skb->network_header; - err = memcpy_fromiovecend((void *)iph, from, 0, length); + err = memcpy_from_msg(iph, msg, length); if (err) goto error_fault; @@ -886,8 +886,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, back_from_confirm: if (inet->hdrincl) - /* XXX: stripping const */ - err = rawv6_send_hdrinc(sk, (struct iovec *)msg->msg_iter.iov, len, &fl6, &dst, msg->msg_flags); + err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags); else { lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3cc197c72b59..e4cbd5798eba 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1506,12 +1506,12 @@ static bool ipip6_netlink_encap_parms(struct nlattr *data[], if (data[IFLA_IPTUN_ENCAP_SPORT]) { ret = true; - ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]); + ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]); } if (data[IFLA_IPTUN_ENCAP_DPORT]) { ret = true; - ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]); + ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]); } return ret; @@ -1707,9 +1707,9 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || - nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT, + nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || - nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT, + nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e41f017cd479..d048d46779fc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -990,9 +990,10 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, { unsigned int offset; struct udphdr *uh = udp_hdr(skb); + struct sk_buff *frags = skb_shinfo(skb)->frag_list; __wsum csum = 0; - if (skb_queue_len(&sk->sk_write_queue) == 1) { + if (!frags) { /* Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); @@ -1008,9 +1009,9 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, skb->ip_summed = CHECKSUM_NONE; - skb_queue_walk(&sk->sk_write_queue, skb) { - csum = csum_add(csum, skb->csum); - } + do { + csum = csum_add(csum, frags->csum); + } while ((frags = frags->next)); uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, csum); @@ -1023,26 +1024,15 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, * Sending */ -static int udp_v6_push_pending_frames(struct sock *sk) +static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6) { - struct sk_buff *skb; + struct sock *sk = skb->sk; struct udphdr *uh; - struct udp_sock *up = udp_sk(sk); - struct inet_sock *inet = inet_sk(sk); - struct flowi6 *fl6; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; - - if (up->pending == AF_INET) - return udp_push_pending_frames(sk); - - fl6 = &inet->cork.fl.u.ip6; - - /* Grab the skbuff where UDP header space exists. */ - skb = skb_peek(&sk->sk_write_queue); - if (skb == NULL) - goto out; + int offset = skb_transport_offset(skb); + int len = skb->len - offset; /* * Create a UDP header @@ -1050,29 +1040,28 @@ static int udp_v6_push_pending_frames(struct sock *sk) uh = udp_hdr(skb); uh->source = fl6->fl6_sport; uh->dest = fl6->fl6_dport; - uh->len = htons(up->len); + uh->len = htons(len); uh->check = 0; if (is_udplite) - csum = udplite_csum_outgoing(sk, skb); - else if (up->no_check6_tx) { /* UDP csum disabled */ + csum = udplite_csum(skb); + else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ - udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, - up->len); + udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len); goto send; } else - csum = udp_csum_outgoing(sk, skb); + csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, - up->len, fl6->flowi6_proto, csum); + len, fl6->flowi6_proto, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: - err = ip6_push_pending_frames(sk); + err = ip6_send_skb(skb); if (err) { if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { UDP6_INC_STATS_USER(sock_net(sk), @@ -1082,6 +1071,30 @@ send: } else UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_OUTDATAGRAMS, is_udplite); + return err; +} + +static int udp_v6_push_pending_frames(struct sock *sk) +{ + struct sk_buff *skb; + struct udp_sock *up = udp_sk(sk); + struct flowi6 fl6; + int err = 0; + + if (up->pending == AF_INET) + return udp_push_pending_frames(sk); + + /* ip6_finish_skb will release the cork, so make a copy of + * fl6 here. + */ + fl6 = inet_sk(sk)->cork.fl.u.ip6; + + skb = ip6_finish_skb(sk); + if (!skb) + goto out; + + err = udp_v6_send_skb(skb, &fl6); + out: up->len = 0; up->pending = 0; @@ -1164,6 +1177,7 @@ do_udp_sendmsg: if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; if (up->pending) { /* * There are pending frames. @@ -1294,6 +1308,20 @@ do_udp_sendmsg: goto do_confirm; back_from_confirm: + /* Lockless fast path for the non-corking case */ + if (!corkreq) { + struct sk_buff *skb; + + skb = ip6_make_skb(sk, getfrag, msg, ulen, + sizeof(struct udphdr), hlimit, tclass, opt, + &fl6, (struct rt6_info *)dst, + msg->msg_flags, dontfrag); + err = PTR_ERR(skb); + if (!IS_ERR_OR_NULL(skb)) + err = udp_v6_send_skb(skb, &fl6); + goto release_dst; + } + lock_sock(sk); if (unlikely(up->pending)) { /* The socket is already corked while preparing it. */ @@ -1311,7 +1339,6 @@ do_append_data: if (dontfrag < 0) dontfrag = np->dontfrag; up->len += ulen; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, @@ -1323,6 +1350,11 @@ do_append_data: else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) up->pending = 0; + if (err > 0) + err = np->recverr ? net_xmit_errno(err) : 0; + release_sock(sk); + +release_dst: if (dst) { if (connected) { ip6_dst_store(sk, dst, @@ -1339,9 +1371,6 @@ do_append_data: dst = NULL; } - if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; - release_sock(sk); out: dst_release(dst); fl6_sock_release(flowlabel); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index b6aa8ed18257..a56276996b72 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -52,6 +52,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + /* Set the IPv6 fragment id if not set yet */ + if (!skb_shinfo(skb)->ip6_frag_id) + ipv6_proxy_select_ident(skb); + segs = NULL; goto out; } @@ -108,7 +112,11 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - fptr->identification = skb_shinfo(skb)->ip6_frag_id; + if (skb_shinfo(skb)->ip6_frag_id) + fptr->identification = skb_shinfo(skb)->ip6_frag_id; + else + ipv6_select_ident(fptr, + (struct rt6_info *)skb_dst(skb)); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 7f2cafddfb6e..1cde711bcab5 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -533,7 +533,7 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery) info.discovery = discovery; /* sysctl_slot_timeout bounds are checked in irsysctl.c - Jean II */ - self->slot_timeout = sysctl_slot_timeout * HZ / 1000; + self->slot_timeout = msecs_to_jiffies(sysctl_slot_timeout); irlap_do_event(self, DISCOVERY_REQUEST, NULL, &info); } @@ -1015,13 +1015,15 @@ void irlap_apply_connection_parameters(struct irlap_cb *self, int now) * Or, this is how much we can keep the pf bit in primary mode. * Therefore, it must be lower or equal than our *OWN* max turn around. * Jean II */ - self->poll_timeout = self->qos_tx.max_turn_time.value * HZ / 1000; + self->poll_timeout = msecs_to_jiffies( + self->qos_tx.max_turn_time.value); /* The Final timeout applies only to the primary station. * It defines the maximum time the primary wait (mostly in RECV mode) * for an answer from the secondary station before polling it again. * Therefore, it must be greater or equal than our *PARTNER* * max turn around time - Jean II */ - self->final_timeout = self->qos_rx.max_turn_time.value * HZ / 1000; + self->final_timeout = msecs_to_jiffies( + self->qos_rx.max_turn_time.value); /* The Watchdog Bit timeout applies only to the secondary station. * It defines the maximum time the secondary wait (mostly in RECV mode) * for poll from the primary station before getting annoyed. diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 75cc6801a431..64a012a0c6e5 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -5,6 +5,7 @@ config MAC80211 select CRYPTO_ARC4 select CRYPTO_AES select CRYPTO_CCM + select CRYPTO_GCM select CRC32 select AVERAGE ---help--- diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index e53671b1105e..3275f01881be 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -15,7 +15,9 @@ mac80211-y := \ michael.o \ tkip.o \ aes_ccm.o \ + aes_gcm.o \ aes_cmac.o \ + aes_gmac.o \ cfg.o \ ethtool.o \ rx.o \ diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index 09d9caaec591..7869bb40acaa 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -20,7 +20,8 @@ #include "aes_ccm.h" void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) + u8 *data, size_t data_len, u8 *mic, + size_t mic_len) { struct scatterlist assoc, pt, ct[2]; @@ -35,7 +36,7 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); sg_init_table(ct, 2); sg_set_buf(&ct[0], data, data_len); - sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN); + sg_set_buf(&ct[1], mic, mic_len); aead_request_set_tfm(aead_req, tfm); aead_request_set_assoc(aead_req, &assoc, assoc.length); @@ -45,7 +46,8 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, } int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) + u8 *data, size_t data_len, u8 *mic, + size_t mic_len) { struct scatterlist assoc, pt, ct[2]; char aead_req_data[sizeof(struct aead_request) + @@ -62,17 +64,18 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); sg_init_table(ct, 2); sg_set_buf(&ct[0], data, data_len); - sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN); + sg_set_buf(&ct[1], mic, mic_len); aead_request_set_tfm(aead_req, tfm); aead_request_set_assoc(aead_req, &assoc, assoc.length); - aead_request_set_crypt(aead_req, ct, &pt, - data_len + IEEE80211_CCMP_MIC_LEN, b_0); + aead_request_set_crypt(aead_req, ct, &pt, data_len + mic_len, b_0); return crypto_aead_decrypt(aead_req); } -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[]) +struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], + size_t key_len, + size_t mic_len) { struct crypto_aead *tfm; int err; @@ -81,9 +84,9 @@ struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[]) if (IS_ERR(tfm)) return tfm; - err = crypto_aead_setkey(tfm, key, WLAN_KEY_LEN_CCMP); + err = crypto_aead_setkey(tfm, key, key_len); if (!err) - err = crypto_aead_setauthsize(tfm, IEEE80211_CCMP_MIC_LEN); + err = crypto_aead_setauthsize(tfm, mic_len); if (!err) return tfm; diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h index 2c7ab1948a2e..6a73d1e4d186 100644 --- a/net/mac80211/aes_ccm.h +++ b/net/mac80211/aes_ccm.h @@ -12,11 +12,15 @@ #include <linux/crypto.h> -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[]); +struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], + size_t key_len, + size_t mic_len); void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); + u8 *data, size_t data_len, u8 *mic, + size_t mic_len); int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); + u8 *data, size_t data_len, u8 *mic, + size_t mic_len); void ieee80211_aes_key_free(struct crypto_aead *tfm); #endif /* AES_CCM_H */ diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 9b9009f99551..4192806be3d3 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -18,8 +18,8 @@ #include "key.h" #include "aes_cmac.h" -#define AES_CMAC_KEY_LEN 16 #define CMAC_TLEN 8 /* CMAC TLen = 64 bits (8 octets) */ +#define CMAC_TLEN_256 16 /* CMAC TLen = 128 bits (16 octets) */ #define AAD_LEN 20 @@ -35,9 +35,9 @@ static void gf_mulx(u8 *pad) pad[AES_BLOCK_SIZE - 1] ^= 0x87; } - -static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem, - const u8 *addr[], const size_t *len, u8 *mac) +static void aes_cmac_vector(struct crypto_cipher *tfm, size_t num_elem, + const u8 *addr[], const size_t *len, u8 *mac, + size_t mac_len) { u8 cbc[AES_BLOCK_SIZE], pad[AES_BLOCK_SIZE]; const u8 *pos, *end; @@ -88,7 +88,7 @@ static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem, for (i = 0; i < AES_BLOCK_SIZE; i++) pad[i] ^= cbc[i]; crypto_cipher_encrypt_one(tfm, pad, pad); - memcpy(mac, pad, CMAC_TLEN); + memcpy(mac, pad, mac_len); } @@ -107,17 +107,35 @@ void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad, addr[2] = zero; len[2] = CMAC_TLEN; - aes_128_cmac_vector(tfm, 3, addr, len, mic); + aes_cmac_vector(tfm, 3, addr, len, mic, CMAC_TLEN); } +void ieee80211_aes_cmac_256(struct crypto_cipher *tfm, const u8 *aad, + const u8 *data, size_t data_len, u8 *mic) +{ + const u8 *addr[3]; + size_t len[3]; + u8 zero[CMAC_TLEN_256]; + + memset(zero, 0, CMAC_TLEN_256); + addr[0] = aad; + len[0] = AAD_LEN; + addr[1] = data; + len[1] = data_len - CMAC_TLEN_256; + addr[2] = zero; + len[2] = CMAC_TLEN_256; + + aes_cmac_vector(tfm, 3, addr, len, mic, CMAC_TLEN_256); +} -struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[]) +struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[], + size_t key_len) { struct crypto_cipher *tfm; tfm = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC); if (!IS_ERR(tfm)) - crypto_cipher_setkey(tfm, key, AES_CMAC_KEY_LEN); + crypto_cipher_setkey(tfm, key, key_len); return tfm; } diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h index 0ce6487af795..3702041f44fd 100644 --- a/net/mac80211/aes_cmac.h +++ b/net/mac80211/aes_cmac.h @@ -11,9 +11,12 @@ #include <linux/crypto.h> -struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[]); +struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[], + size_t key_len); void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic); +void ieee80211_aes_cmac_256(struct crypto_cipher *tfm, const u8 *aad, + const u8 *data, size_t data_len, u8 *mic); void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm); #endif /* AES_CMAC_H */ diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c new file mode 100644 index 000000000000..c2bf6698d738 --- /dev/null +++ b/net/mac80211/aes_gcm.c @@ -0,0 +1,95 @@ +/* + * Copyright 2014-2015, Qualcomm Atheros, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <crypto/aes.h> + +#include <net/mac80211.h> +#include "key.h" +#include "aes_gcm.h" + +void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, + u8 *data, size_t data_len, u8 *mic) +{ + struct scatterlist assoc, pt, ct[2]; + + char aead_req_data[sizeof(struct aead_request) + + crypto_aead_reqsize(tfm)] + __aligned(__alignof__(struct aead_request)); + struct aead_request *aead_req = (void *)aead_req_data; + + memset(aead_req, 0, sizeof(aead_req_data)); + + sg_init_one(&pt, data, data_len); + sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); + sg_init_table(ct, 2); + sg_set_buf(&ct[0], data, data_len); + sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN); + + aead_request_set_tfm(aead_req, tfm); + aead_request_set_assoc(aead_req, &assoc, assoc.length); + aead_request_set_crypt(aead_req, &pt, ct, data_len, j_0); + + crypto_aead_encrypt(aead_req); +} + +int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, + u8 *data, size_t data_len, u8 *mic) +{ + struct scatterlist assoc, pt, ct[2]; + char aead_req_data[sizeof(struct aead_request) + + crypto_aead_reqsize(tfm)] + __aligned(__alignof__(struct aead_request)); + struct aead_request *aead_req = (void *)aead_req_data; + + if (data_len == 0) + return -EINVAL; + + memset(aead_req, 0, sizeof(aead_req_data)); + + sg_init_one(&pt, data, data_len); + sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); + sg_init_table(ct, 2); + sg_set_buf(&ct[0], data, data_len); + sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN); + + aead_request_set_tfm(aead_req, tfm); + aead_request_set_assoc(aead_req, &assoc, assoc.length); + aead_request_set_crypt(aead_req, ct, &pt, + data_len + IEEE80211_GCMP_MIC_LEN, j_0); + + return crypto_aead_decrypt(aead_req); +} + +struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], + size_t key_len) +{ + struct crypto_aead *tfm; + int err; + + tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return tfm; + + err = crypto_aead_setkey(tfm, key, key_len); + if (!err) + err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN); + if (!err) + return tfm; + + crypto_free_aead(tfm); + return ERR_PTR(err); +} + +void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) +{ + crypto_free_aead(tfm); +} diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h new file mode 100644 index 000000000000..1347fda6b76a --- /dev/null +++ b/net/mac80211/aes_gcm.h @@ -0,0 +1,22 @@ +/* + * Copyright 2014-2015, Qualcomm Atheros, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef AES_GCM_H +#define AES_GCM_H + +#include <linux/crypto.h> + +void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, + u8 *data, size_t data_len, u8 *mic); +int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, + u8 *data, size_t data_len, u8 *mic); +struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], + size_t key_len); +void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm); + +#endif /* AES_GCM_H */ diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c new file mode 100644 index 000000000000..1c72edcb0083 --- /dev/null +++ b/net/mac80211/aes_gmac.c @@ -0,0 +1,84 @@ +/* + * AES-GMAC for IEEE 802.11 BIP-GMAC-128 and BIP-GMAC-256 + * Copyright 2015, Qualcomm Atheros, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <crypto/aes.h> + +#include <net/mac80211.h> +#include "key.h" +#include "aes_gmac.h" + +#define GMAC_MIC_LEN 16 +#define GMAC_NONCE_LEN 12 +#define AAD_LEN 20 + +int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, + const u8 *data, size_t data_len, u8 *mic) +{ + struct scatterlist sg[3], ct[1]; + char aead_req_data[sizeof(struct aead_request) + + crypto_aead_reqsize(tfm)] + __aligned(__alignof__(struct aead_request)); + struct aead_request *aead_req = (void *)aead_req_data; + u8 zero[GMAC_MIC_LEN], iv[AES_BLOCK_SIZE]; + + if (data_len < GMAC_MIC_LEN) + return -EINVAL; + + memset(aead_req, 0, sizeof(aead_req_data)); + + memset(zero, 0, GMAC_MIC_LEN); + sg_init_table(sg, 3); + sg_set_buf(&sg[0], aad, AAD_LEN); + sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); + sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); + + memcpy(iv, nonce, GMAC_NONCE_LEN); + memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN); + iv[AES_BLOCK_SIZE - 1] = 0x01; + + sg_init_table(ct, 1); + sg_set_buf(&ct[0], mic, GMAC_MIC_LEN); + + aead_request_set_tfm(aead_req, tfm); + aead_request_set_assoc(aead_req, sg, AAD_LEN + data_len); + aead_request_set_crypt(aead_req, NULL, ct, 0, iv); + + crypto_aead_encrypt(aead_req); + + return 0; +} + +struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[], + size_t key_len) +{ + struct crypto_aead *tfm; + int err; + + tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return tfm; + + err = crypto_aead_setkey(tfm, key, key_len); + if (!err) + return tfm; + if (!err) + err = crypto_aead_setauthsize(tfm, GMAC_MIC_LEN); + + crypto_free_aead(tfm); + return ERR_PTR(err); +} + +void ieee80211_aes_gmac_key_free(struct crypto_aead *tfm) +{ + crypto_free_aead(tfm); +} diff --git a/net/mac80211/aes_gmac.h b/net/mac80211/aes_gmac.h new file mode 100644 index 000000000000..d328204d73a8 --- /dev/null +++ b/net/mac80211/aes_gmac.h @@ -0,0 +1,20 @@ +/* + * Copyright 2015, Qualcomm Atheros, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef AES_GMAC_H +#define AES_GMAC_H + +#include <linux/crypto.h> + +struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[], + size_t key_len); +int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, + const u8 *data, size_t data_len, u8 *mic); +void ieee80211_aes_gmac_key_free(struct crypto_aead *tfm); + +#endif /* AES_GMAC_H */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index ff090ef1ea2c..dd4ff36c557a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -162,8 +162,13 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: break; default: cs = ieee80211_cs_get(local, params->cipher, sdata->vif.type); @@ -348,6 +353,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, params.seq_len = 6; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: pn64 = atomic64_read(&key->u.ccmp.tx_pn); seq[0] = pn64; seq[1] = pn64 >> 8; @@ -359,6 +365,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, params.seq_len = 6; break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: pn64 = atomic64_read(&key->u.aes_cmac.tx_pn); seq[0] = pn64; seq[1] = pn64 >> 8; @@ -369,6 +376,30 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, params.seq = seq; params.seq_len = 6; break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + pn64 = atomic64_read(&key->u.aes_gmac.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; + params.seq = seq; + params.seq_len = 6; + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + pn64 = atomic64_read(&key->u.gcmp.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; + params.seq = seq; + params.seq_len = 6; + break; } params.key = key->conf.key; @@ -2110,6 +2141,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; + enum nl80211_tx_power_setting txp_type = type; + bool update_txp_type = false; if (wdev) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); @@ -2117,6 +2150,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, switch (type) { case NL80211_TX_POWER_AUTOMATIC: sdata->user_power_level = IEEE80211_UNSET_POWER_LEVEL; + txp_type = NL80211_TX_POWER_LIMITED; break; case NL80211_TX_POWER_LIMITED: case NL80211_TX_POWER_FIXED: @@ -2126,7 +2160,12 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, break; } - ieee80211_recalc_txpower(sdata); + if (txp_type != sdata->vif.bss_conf.txpower_type) { + update_txp_type = true; + sdata->vif.bss_conf.txpower_type = txp_type; + } + + ieee80211_recalc_txpower(sdata, update_txp_type); return 0; } @@ -2134,6 +2173,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, switch (type) { case NL80211_TX_POWER_AUTOMATIC: local->user_power_level = IEEE80211_UNSET_POWER_LEVEL; + txp_type = NL80211_TX_POWER_LIMITED; break; case NL80211_TX_POWER_LIMITED: case NL80211_TX_POWER_FIXED: @@ -2144,10 +2184,14 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, } mutex_lock(&local->iflist_mtx); - list_for_each_entry(sdata, &local->interfaces, list) + list_for_each_entry(sdata, &local->interfaces, list) { sdata->user_power_level = local->user_power_level; + if (txp_type != sdata->vif.bss_conf.txpower_type) + update_txp_type = true; + sdata->vif.bss_conf.txpower_type = txp_type; + } list_for_each_entry(sdata, &local->interfaces, list) - ieee80211_recalc_txpower(sdata); + ieee80211_recalc_txpower(sdata, update_txp_type); mutex_unlock(&local->iflist_mtx); return 0; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 35b11e11e0c4..ff0d2db09df9 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -655,7 +655,7 @@ out: } if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) { - ieee80211_recalc_txpower(sdata); + ieee80211_recalc_txpower(sdata, false); ieee80211_recalc_chanctx_min_def(local, new_ctx); } @@ -1387,7 +1387,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_bss_info_change_notify(sdata, changed); - ieee80211_recalc_txpower(sdata); + ieee80211_recalc_txpower(sdata, false); } ieee80211_recalc_chanctx_chantype(local, ctx); diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 5523b94c7c90..71ac1b5f4da5 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -94,17 +94,33 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf, key->u.tkip.tx.iv16); break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: pn = atomic64_read(&key->u.ccmp.tx_pn); len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: pn = atomic64_read(&key->u.aes_cmac.tx_pn); len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + pn = atomic64_read(&key->u.aes_gmac.tx_pn); + len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", + (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), + (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + pn = atomic64_read(&key->u.gcmp.tx_pn); + len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", + (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), + (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); + break; default: return 0; } @@ -134,6 +150,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, len = p - buf; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { rpn = key->u.ccmp.rx_pn[i]; p += scnprintf(p, sizeof(buf)+buf-p, @@ -144,6 +161,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, len = p - buf; break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: rpn = key->u.aes_cmac.rx_pn; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", @@ -151,6 +169,26 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, rpn[3], rpn[4], rpn[5]); len = p - buf; break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + rpn = key->u.aes_gmac.rx_pn; + p += scnprintf(p, sizeof(buf)+buf-p, + "%02x%02x%02x%02x%02x%02x\n", + rpn[0], rpn[1], rpn[2], + rpn[3], rpn[4], rpn[5]); + len = p - buf; + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { + rpn = key->u.gcmp.rx_pn[i]; + p += scnprintf(p, sizeof(buf)+buf-p, + "%02x%02x%02x%02x%02x%02x\n", + rpn[0], rpn[1], rpn[2], + rpn[3], rpn[4], rpn[5]); + } + len = p - buf; + break; default: return 0; } @@ -167,12 +205,23 @@ static ssize_t key_replays_read(struct file *file, char __user *userbuf, switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays); break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_cmac.replays); break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + len = scnprintf(buf, sizeof(buf), "%u\n", + key->u.aes_gmac.replays); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + len = scnprintf(buf, sizeof(buf), "%u\n", key->u.gcmp.replays); + break; default: return 0; } @@ -189,9 +238,15 @@ static ssize_t key_icverrors_read(struct file *file, char __user *userbuf, switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_cmac.icverrors); break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + len = scnprintf(buf, sizeof(buf), "%u\n", + key->u.aes_gmac.icverrors); + break; default: return 0; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 156ea79e0157..3afe36824703 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1621,7 +1621,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local); void ieee80211_del_virtual_monitor(struct ieee80211_local *local); bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); -void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); +void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata, + bool update_bss); static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata) { @@ -1751,7 +1752,8 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); - WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), + WARN(test_bit(SCAN_HW_SCANNING, &local->scanning) && + !test_bit(SCAN_COMPLETED, &local->scanning), "%s: resume with hardware scan still in progress\n", wiphy_name(hw->wiphy)); @@ -1885,6 +1887,36 @@ void __ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, unsigned int queues, bool drop); +static inline bool ieee80211_can_run_worker(struct ieee80211_local *local) +{ + /* + * If quiescing is set, we are racing with __ieee80211_suspend. + * __ieee80211_suspend flushes the workers after setting quiescing, + * and we check quiescing / suspended before enqueing new workers. + * We should abort the worker to avoid the races below. + */ + if (local->quiescing) + return false; + + /* + * We might already be suspended if the following scenario occurs: + * __ieee80211_suspend Control path + * + * if (local->quiescing) + * return; + * local->quiescing = true; + * flush_workqueue(); + * queue_work(...); + * local->suspended = true; + * local->quiescing = false; + * worker starts running... + */ + if (local->suspended) + return false; + + return true; +} + void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 677422e11e07..81a27516813e 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -73,9 +73,10 @@ bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) return false; } -void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) +void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata, + bool update_bss) { - if (__ieee80211_recalc_txpower(sdata)) + if (__ieee80211_recalc_txpower(sdata) || update_bss) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER); } @@ -1169,12 +1170,7 @@ static void ieee80211_iface_work(struct work_struct *work) if (local->scanning) return; - /* - * ieee80211_queue_work() should have picked up most cases, - * here we'll pick the rest. - */ - if (WARN(local->suspended, - "interface work scheduled while going to suspend\n")) + if (!ieee80211_can_run_worker(local)) return; /* first process frames */ diff --git a/net/mac80211/key.c b/net/mac80211/key.c index f8d9f0ee59bf..0825d76edcfc 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -24,6 +24,8 @@ #include "debugfs_key.h" #include "aes_ccm.h" #include "aes_cmac.h" +#include "aes_gmac.h" +#include "aes_gcm.h" /** @@ -90,7 +92,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; struct sta_info *sta; - int ret; + int ret = -EOPNOTSUPP; might_sleep(); @@ -150,7 +152,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) return 0; } - if (ret != -ENOSPC && ret != -EOPNOTSUPP) + if (ret != -ENOSPC && ret != -EOPNOTSUPP && ret != 1) sdata_err(sdata, "failed to set key (%d, %pM) to hardware (%d)\n", key->conf.keyidx, @@ -162,8 +164,18 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) case WLAN_CIPHER_SUITE_WEP104: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: - /* all of these we can do in software */ + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + /* all of these we can do in software - if driver can */ + if (ret == 1) + return 0; + if (key->local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL) + return -EINVAL; return 0; default: return -EINVAL; @@ -382,7 +394,26 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, * Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ - key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt(key_data); + key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt( + key_data, key_len, IEEE80211_CCMP_MIC_LEN); + if (IS_ERR(key->u.ccmp.tfm)) { + err = PTR_ERR(key->u.ccmp.tfm); + kfree(key); + return ERR_PTR(err); + } + break; + case WLAN_CIPHER_SUITE_CCMP_256: + key->conf.iv_len = IEEE80211_CCMP_256_HDR_LEN; + key->conf.icv_len = IEEE80211_CCMP_256_MIC_LEN; + for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++) + for (j = 0; j < IEEE80211_CCMP_256_PN_LEN; j++) + key->u.ccmp.rx_pn[i][j] = + seq[IEEE80211_CCMP_256_PN_LEN - j - 1]; + /* Initialize AES key state here as an optimization so that + * it does not need to be initialized for every packet. + */ + key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt( + key_data, key_len, IEEE80211_CCMP_256_MIC_LEN); if (IS_ERR(key->u.ccmp.tfm)) { err = PTR_ERR(key->u.ccmp.tfm); kfree(key); @@ -390,8 +421,12 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, } break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->conf.iv_len = 0; - key->conf.icv_len = sizeof(struct ieee80211_mmie); + if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) + key->conf.icv_len = sizeof(struct ieee80211_mmie); + else + key->conf.icv_len = sizeof(struct ieee80211_mmie_16); if (seq) for (j = 0; j < IEEE80211_CMAC_PN_LEN; j++) key->u.aes_cmac.rx_pn[j] = @@ -401,13 +436,51 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, * it does not need to be initialized for every packet. */ key->u.aes_cmac.tfm = - ieee80211_aes_cmac_key_setup(key_data); + ieee80211_aes_cmac_key_setup(key_data, key_len); if (IS_ERR(key->u.aes_cmac.tfm)) { err = PTR_ERR(key->u.aes_cmac.tfm); kfree(key); return ERR_PTR(err); } break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + key->conf.iv_len = 0; + key->conf.icv_len = sizeof(struct ieee80211_mmie_16); + if (seq) + for (j = 0; j < IEEE80211_GMAC_PN_LEN; j++) + key->u.aes_gmac.rx_pn[j] = + seq[IEEE80211_GMAC_PN_LEN - j - 1]; + /* Initialize AES key state here as an optimization so that + * it does not need to be initialized for every packet. + */ + key->u.aes_gmac.tfm = + ieee80211_aes_gmac_key_setup(key_data, key_len); + if (IS_ERR(key->u.aes_gmac.tfm)) { + err = PTR_ERR(key->u.aes_gmac.tfm); + kfree(key); + return ERR_PTR(err); + } + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + key->conf.iv_len = IEEE80211_GCMP_HDR_LEN; + key->conf.icv_len = IEEE80211_GCMP_MIC_LEN; + for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++) + for (j = 0; j < IEEE80211_GCMP_PN_LEN; j++) + key->u.gcmp.rx_pn[i][j] = + seq[IEEE80211_GCMP_PN_LEN - j - 1]; + /* Initialize AES key state here as an optimization so that + * it does not need to be initialized for every packet. + */ + key->u.gcmp.tfm = ieee80211_aes_gcm_key_setup_encrypt(key_data, + key_len); + if (IS_ERR(key->u.gcmp.tfm)) { + err = PTR_ERR(key->u.gcmp.tfm); + kfree(key); + return ERR_PTR(err); + } + break; default: if (cs) { size_t len = (seq_len > MAX_PN_LEN) ? @@ -429,10 +502,24 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, static void ieee80211_key_free_common(struct ieee80211_key *key) { - if (key->conf.cipher == WLAN_CIPHER_SUITE_CCMP) + switch (key->conf.cipher) { + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: ieee80211_aes_key_free(key->u.ccmp.tfm); - if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC) + break; + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm); + break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + ieee80211_aes_gmac_key_free(key->u.aes_gmac.tfm); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + ieee80211_aes_gcm_key_free(key->u.gcmp.tfm); + break; + } kzfree(key); } @@ -739,6 +826,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, seq->tkip.iv16 = key->u.tkip.tx.iv16; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: pn64 = atomic64_read(&key->u.ccmp.tx_pn); seq->ccmp.pn[5] = pn64; seq->ccmp.pn[4] = pn64 >> 8; @@ -748,6 +836,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, seq->ccmp.pn[0] = pn64 >> 40; break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: pn64 = atomic64_read(&key->u.aes_cmac.tx_pn); seq->ccmp.pn[5] = pn64; seq->ccmp.pn[4] = pn64 >> 8; @@ -756,6 +845,26 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, seq->ccmp.pn[1] = pn64 >> 32; seq->ccmp.pn[0] = pn64 >> 40; break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + pn64 = atomic64_read(&key->u.aes_gmac.tx_pn); + seq->ccmp.pn[5] = pn64; + seq->ccmp.pn[4] = pn64 >> 8; + seq->ccmp.pn[3] = pn64 >> 16; + seq->ccmp.pn[2] = pn64 >> 24; + seq->ccmp.pn[1] = pn64 >> 32; + seq->ccmp.pn[0] = pn64 >> 40; + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + pn64 = atomic64_read(&key->u.gcmp.tx_pn); + seq->gcmp.pn[5] = pn64; + seq->gcmp.pn[4] = pn64 >> 8; + seq->gcmp.pn[3] = pn64 >> 16; + seq->gcmp.pn[2] = pn64 >> 24; + seq->gcmp.pn[1] = pn64 >> 32; + seq->gcmp.pn[0] = pn64 >> 40; + break; default: WARN_ON(1); } @@ -778,6 +887,7 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, seq->tkip.iv16 = key->u.tkip.rx[tid].iv16; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) @@ -787,11 +897,29 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, memcpy(seq->ccmp.pn, pn, IEEE80211_CCMP_PN_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_cmac.rx_pn; memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN); break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + if (WARN_ON(tid != 0)) + return; + pn = key->u.aes_gmac.rx_pn; + memcpy(seq->aes_gmac.pn, pn, IEEE80211_GMAC_PN_LEN); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) + return; + if (tid < 0) + pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS]; + else + pn = key->u.gcmp.rx_pn[tid]; + memcpy(seq->gcmp.pn, pn, IEEE80211_GCMP_PN_LEN); + break; } } EXPORT_SYMBOL(ieee80211_get_key_rx_seq); @@ -810,6 +938,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, key->u.tkip.tx.iv16 = seq->tkip.iv16; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: pn64 = (u64)seq->ccmp.pn[5] | ((u64)seq->ccmp.pn[4] << 8) | ((u64)seq->ccmp.pn[3] << 16) | @@ -819,6 +948,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, atomic64_set(&key->u.ccmp.tx_pn, pn64); break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: pn64 = (u64)seq->aes_cmac.pn[5] | ((u64)seq->aes_cmac.pn[4] << 8) | ((u64)seq->aes_cmac.pn[3] << 16) | @@ -827,6 +957,26 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, ((u64)seq->aes_cmac.pn[0] << 40); atomic64_set(&key->u.aes_cmac.tx_pn, pn64); break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + pn64 = (u64)seq->aes_gmac.pn[5] | + ((u64)seq->aes_gmac.pn[4] << 8) | + ((u64)seq->aes_gmac.pn[3] << 16) | + ((u64)seq->aes_gmac.pn[2] << 24) | + ((u64)seq->aes_gmac.pn[1] << 32) | + ((u64)seq->aes_gmac.pn[0] << 40); + atomic64_set(&key->u.aes_gmac.tx_pn, pn64); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + pn64 = (u64)seq->gcmp.pn[5] | + ((u64)seq->gcmp.pn[4] << 8) | + ((u64)seq->gcmp.pn[3] << 16) | + ((u64)seq->gcmp.pn[2] << 24) | + ((u64)seq->gcmp.pn[1] << 32) | + ((u64)seq->gcmp.pn[0] << 40); + atomic64_set(&key->u.gcmp.tx_pn, pn64); + break; default: WARN_ON(1); break; @@ -850,6 +1000,7 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, key->u.tkip.rx[tid].iv16 = seq->tkip.iv16; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) @@ -859,11 +1010,29 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, memcpy(pn, seq->ccmp.pn, IEEE80211_CCMP_PN_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_cmac.rx_pn; memcpy(pn, seq->aes_cmac.pn, IEEE80211_CMAC_PN_LEN); break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + if (WARN_ON(tid != 0)) + return; + pn = key->u.aes_gmac.rx_pn; + memcpy(pn, seq->aes_gmac.pn, IEEE80211_GMAC_PN_LEN); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) + return; + if (tid < 0) + pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS]; + else + pn = key->u.gcmp.rx_pn[tid]; + memcpy(pn, seq->gcmp.pn, IEEE80211_GCMP_PN_LEN); + break; default: WARN_ON(1); break; diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 19db68663d75..d57a9915494f 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -95,6 +95,24 @@ struct ieee80211_key { u32 icverrors; /* dot11RSNAStatsCMACICVErrors */ } aes_cmac; struct { + atomic64_t tx_pn; + u8 rx_pn[IEEE80211_GMAC_PN_LEN]; + struct crypto_aead *tfm; + u32 replays; /* dot11RSNAStatsCMACReplays */ + u32 icverrors; /* dot11RSNAStatsCMACICVErrors */ + } aes_gmac; + struct { + atomic64_t tx_pn; + /* Last received packet number. The first + * IEEE80211_NUM_TIDS counters are used with Data + * frames and the last counter is used with Robust + * Management frames. + */ + u8 rx_pn[IEEE80211_NUM_TIDS + 1][IEEE80211_GCMP_PN_LEN]; + struct crypto_aead *tfm; + u32 replays; /* dot11RSNAStatsGCMPReplays */ + } gcmp; + struct { /* generic cipher scheme */ u8 rx_pn[IEEE80211_NUM_TIDS + 1][MAX_PN_LEN]; } gen; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d9ce33663c73..5e09d354c5a5 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -658,7 +658,6 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) bool have_wep = !(IS_ERR(local->wep_tx_tfm) || IS_ERR(local->wep_rx_tfm)); bool have_mfp = local->hw.flags & IEEE80211_HW_MFP_CAPABLE; - const struct ieee80211_cipher_scheme *cs = local->hw.cipher_schemes; int n_suites = 0, r = 0, w = 0; u32 *suites; static const u32 cipher_suites[] = { @@ -667,79 +666,109 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) WLAN_CIPHER_SUITE_WEP104, WLAN_CIPHER_SUITE_TKIP, WLAN_CIPHER_SUITE_CCMP, + WLAN_CIPHER_SUITE_CCMP_256, + WLAN_CIPHER_SUITE_GCMP, + WLAN_CIPHER_SUITE_GCMP_256, /* keep last -- depends on hw flags! */ - WLAN_CIPHER_SUITE_AES_CMAC + WLAN_CIPHER_SUITE_AES_CMAC, + WLAN_CIPHER_SUITE_BIP_CMAC_256, + WLAN_CIPHER_SUITE_BIP_GMAC_128, + WLAN_CIPHER_SUITE_BIP_GMAC_256, }; - /* Driver specifies the ciphers, we have nothing to do... */ - if (local->hw.wiphy->cipher_suites && have_wep) - return 0; + if (local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL || + local->hw.wiphy->cipher_suites) { + /* If the driver advertises, or doesn't support SW crypto, + * we only need to remove WEP if necessary. + */ + if (have_wep) + return 0; + + /* well if it has _no_ ciphers ... fine */ + if (!local->hw.wiphy->n_cipher_suites) + return 0; + + /* Driver provides cipher suites, but we need to exclude WEP */ + suites = kmemdup(local->hw.wiphy->cipher_suites, + sizeof(u32) * local->hw.wiphy->n_cipher_suites, + GFP_KERNEL); + if (!suites) + return -ENOMEM; + + for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) { + u32 suite = local->hw.wiphy->cipher_suites[r]; - /* Set up cipher suites if driver relies on mac80211 cipher defs */ - if (!local->hw.wiphy->cipher_suites && !cs) { + if (suite == WLAN_CIPHER_SUITE_WEP40 || + suite == WLAN_CIPHER_SUITE_WEP104) + continue; + suites[w++] = suite; + } + } else if (!local->hw.cipher_schemes) { + /* If the driver doesn't have cipher schemes, there's nothing + * else to do other than assign the (software supported and + * perhaps offloaded) cipher suites. + */ local->hw.wiphy->cipher_suites = cipher_suites; local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); if (!have_mfp) - local->hw.wiphy->n_cipher_suites--; + local->hw.wiphy->n_cipher_suites -= 4; if (!have_wep) { local->hw.wiphy->cipher_suites += 2; local->hw.wiphy->n_cipher_suites -= 2; } + /* not dynamically allocated, so just return */ return 0; - } + } else { + const struct ieee80211_cipher_scheme *cs; - if (!local->hw.wiphy->cipher_suites) { - /* - * Driver specifies cipher schemes only - * We start counting ciphers defined by schemes, TKIP and CCMP + cs = local->hw.cipher_schemes; + + /* Driver specifies cipher schemes only (but not cipher suites + * including the schemes) + * + * We start counting ciphers defined by schemes, TKIP, CCMP, + * CCMP-256, GCMP, and GCMP-256 */ - n_suites = local->hw.n_cipher_schemes + 2; + n_suites = local->hw.n_cipher_schemes + 5; /* check if we have WEP40 and WEP104 */ if (have_wep) n_suites += 2; - /* check if we have AES_CMAC */ + /* check if we have AES_CMAC, BIP-CMAC-256, BIP-GMAC-128, + * BIP-GMAC-256 + */ if (have_mfp) - n_suites++; + n_suites += 4; suites = kmalloc(sizeof(u32) * n_suites, GFP_KERNEL); if (!suites) return -ENOMEM; suites[w++] = WLAN_CIPHER_SUITE_CCMP; + suites[w++] = WLAN_CIPHER_SUITE_CCMP_256; suites[w++] = WLAN_CIPHER_SUITE_TKIP; + suites[w++] = WLAN_CIPHER_SUITE_GCMP; + suites[w++] = WLAN_CIPHER_SUITE_GCMP_256; if (have_wep) { suites[w++] = WLAN_CIPHER_SUITE_WEP40; suites[w++] = WLAN_CIPHER_SUITE_WEP104; } - if (have_mfp) + if (have_mfp) { suites[w++] = WLAN_CIPHER_SUITE_AES_CMAC; + suites[w++] = WLAN_CIPHER_SUITE_BIP_CMAC_256; + suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_128; + suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_256; + } for (r = 0; r < local->hw.n_cipher_schemes; r++) suites[w++] = cs[r].cipher; - } else { - /* Driver provides cipher suites, but we need to exclude WEP */ - suites = kmemdup(local->hw.wiphy->cipher_suites, - sizeof(u32) * local->hw.wiphy->n_cipher_suites, - GFP_KERNEL); - if (!suites) - return -ENOMEM; - - for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) { - u32 suite = local->hw.wiphy->cipher_suites[r]; - - if (suite == WLAN_CIPHER_SUITE_WEP40 || - suite == WLAN_CIPHER_SUITE_WEP104) - continue; - suites[w++] = suite; - } } local->hw.wiphy->cipher_suites = suites; @@ -1041,10 +1070,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_max_network_latency; result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY, &local->network_latency_notifier); - if (result) { - rtnl_lock(); + if (result) goto fail_pm_qos; - } #ifdef CONFIG_INET local->ifa_notifier.notifier_call = ieee80211_ifa_changed; @@ -1072,15 +1099,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) fail_ifa: pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY, &local->network_latency_notifier); - rtnl_lock(); #endif fail_pm_qos: - ieee80211_led_exit(local); + rtnl_lock(); + rate_control_deinitialize(local); ieee80211_remove_interfaces(local); fail_rate: rtnl_unlock(); + ieee80211_led_exit(local); ieee80211_wep_free(local); - sta_info_stop(local); destroy_workqueue(local->workqueue); fail_workqueue: wiphy_unregister(local->hw.wiphy); @@ -1176,6 +1203,8 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) kfree(rcu_access_pointer(local->tx_latency)); + sta_info_stop(local); + wiphy_free(local->hw.wiphy); } EXPORT_SYMBOL(ieee80211_free_hw); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index fa94ca15ba95..b488e1859b18 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -523,13 +523,6 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshcfg.auto_open_plinks && rssi_threshold_check(sdata, sta)) changed = mesh_plink_open(sta); - else if (sta->plink_state == NL80211_PLINK_LISTEN && - (sdata->u.mesh.user_mpm || - sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED)) - cfg80211_notify_new_peer_candidate(sdata->dev, hw_addr, - elems->ie_start, - elems->total_len, - GFP_ATOMIC); ieee80211_mps_frame_release(sta, elems); out: diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index c1460e635c7f..10ac6324c1d0 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2011,6 +2011,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, /* disable per-vif ps */ ieee80211_recalc_ps_vif(sdata); + /* make sure ongoing transmission finishes */ + synchronize_net(); + /* * drop any frame before deauth/disassoc, this can be data or * management frame. Since we are disconnecting, we should not diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9491e8689a9d..1101563357ea 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -647,6 +647,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) { struct ieee80211_mgmt *hdr = (struct ieee80211_mgmt *) skb->data; struct ieee80211_mmie *mmie; + struct ieee80211_mmie_16 *mmie16; if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da)) return -1; @@ -656,11 +657,18 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) mmie = (struct ieee80211_mmie *) (skb->data + skb->len - sizeof(*mmie)); - if (mmie->element_id != WLAN_EID_MMIE || - mmie->length != sizeof(*mmie) - 2) - return -1; - - return le16_to_cpu(mmie->key_id); + if (mmie->element_id == WLAN_EID_MMIE && + mmie->length == sizeof(*mmie) - 2) + return le16_to_cpu(mmie->key_id); + + mmie16 = (struct ieee80211_mmie_16 *) + (skb->data + skb->len - sizeof(*mmie16)); + if (skb->len >= 24 + sizeof(*mmie16) && + mmie16->element_id == WLAN_EID_MMIE && + mmie16->length == sizeof(*mmie16) - 2) + return le16_to_cpu(mmie16->key_id); + + return -1; } static int iwl80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs, @@ -1650,11 +1658,27 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) result = ieee80211_crypto_tkip_decrypt(rx); break; case WLAN_CIPHER_SUITE_CCMP: - result = ieee80211_crypto_ccmp_decrypt(rx); + result = ieee80211_crypto_ccmp_decrypt( + rx, IEEE80211_CCMP_MIC_LEN); + break; + case WLAN_CIPHER_SUITE_CCMP_256: + result = ieee80211_crypto_ccmp_decrypt( + rx, IEEE80211_CCMP_256_MIC_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: result = ieee80211_crypto_aes_cmac_decrypt(rx); break; + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + result = ieee80211_crypto_aes_cmac_256_decrypt(rx); + break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + result = ieee80211_crypto_aes_gmac_decrypt(rx); + break; + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + result = ieee80211_crypto_gcmp_decrypt(rx); + break; default: result = ieee80211_crypto_hw_decrypt(rx); } @@ -1781,7 +1805,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* This is the first fragment of a new frame. */ entry = ieee80211_reassemble_add(rx->sdata, frag, seq, rx->seqno_idx, &(rx->skb)); - if (rx->key && rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP && + if (rx->key && + (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; /* Store CCMP PN so that we can verify that the next @@ -1810,7 +1836,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; - if (!rx->key || rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP) + if (!rx->key || + (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { @@ -2310,12 +2338,12 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; if (rx->sta) { - /* The security index has the same property as needed + /* The seqno index has the same property as needed * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS * for non-QoS-data frames. Here we know it's a data * frame, so count MSDUs. */ - rx->sta->rx_msdu[rx->security_idx]++; + rx->sta->rx_msdu[rx->seqno_idx]++; } /* diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 7807fa42ed3f..05f0d711b6d8 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -828,6 +828,11 @@ void ieee80211_scan_work(struct work_struct *work) mutex_lock(&local->mtx); + if (!ieee80211_can_run_worker(local)) { + aborted = true; + goto out_complete; + } + sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx)); scan_req = rcu_dereference_protected(local->scan_req, diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 79383ef0c264..00ca8dcc2bcf 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1764,6 +1764,13 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->generation = sdata->local->sta_generation; + /* do before driver, so beacon filtering drivers have a + * chance to e.g. just add the number of filtered beacons + * (or just modify the value entirely, of course) + */ + if (sdata->vif.type == NL80211_IFTYPE_STATION) + sinfo->rx_beacon = sdata->u.mgd.count_beacon_signal; + drv_sta_statistics(local, sdata, &sta->sta, sinfo); sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) | @@ -1816,6 +1823,13 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->rx_dropped_misc = sta->rx_dropped; sinfo->beacon_loss_count = sta->beacon_loss_count; + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) { + sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX) | + BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG); + sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif); + } + if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) { diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 917088dfd696..c9f9752217ac 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -345,24 +345,24 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, */ sband = local->hw.wiphy->bands[band]; memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap)); - if ((action_code == WLAN_TDLS_SETUP_REQUEST || - action_code == WLAN_TDLS_SETUP_RESPONSE) && - ht_cap.ht_supported && (!sta || sta->sta.ht_cap.ht_supported)) { - if (action_code == WLAN_TDLS_SETUP_REQUEST) { - ieee80211_apply_htcap_overrides(sdata, &ht_cap); - - /* disable SMPS in TDLS initiator */ - ht_cap.cap |= (WLAN_HT_CAP_SM_PS_DISABLED - << IEEE80211_HT_CAP_SM_PS_SHIFT); - } else { - /* disable SMPS in TDLS responder */ - sta->sta.ht_cap.cap |= - (WLAN_HT_CAP_SM_PS_DISABLED - << IEEE80211_HT_CAP_SM_PS_SHIFT); - - /* the peer caps are already intersected with our own */ - memcpy(&ht_cap, &sta->sta.ht_cap, sizeof(ht_cap)); - } + + if (action_code == WLAN_TDLS_SETUP_REQUEST && ht_cap.ht_supported) { + ieee80211_apply_htcap_overrides(sdata, &ht_cap); + + /* disable SMPS in TDLS initiator */ + ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED + << IEEE80211_HT_CAP_SM_PS_SHIFT; + + pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2); + ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); + } else if (action_code == WLAN_TDLS_SETUP_RESPONSE && + ht_cap.ht_supported && sta->sta.ht_cap.ht_supported) { + /* disable SMPS in TDLS responder */ + sta->sta.ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED + << IEEE80211_HT_CAP_SM_PS_SHIFT; + + /* the peer caps are already intersected with our own */ + memcpy(&ht_cap, &sta->sta.ht_cap, sizeof(ht_cap)); pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2); ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); @@ -852,7 +852,6 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, */ if ((action_code == WLAN_TDLS_TEARDOWN) && (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)) { - struct sta_info *sta = NULL; bool try_resend; /* Should we keep skb for possible resend */ /* If not sending directly to peer - no point in keeping skb */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 02ed6f60629a..88a18ffe2975 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -626,6 +626,9 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) tx->key = NULL; break; case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: if (!ieee80211_is_data_present(hdr->frame_control) && !ieee80211_use_mfp(hdr->frame_control, tx->sta, tx->skb)) @@ -636,6 +639,9 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) ieee80211_is_mgmt(hdr->frame_control); break; case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (!ieee80211_is_mgmt(hdr->frame_control)) tx->key = NULL; break; @@ -1011,9 +1017,21 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx) case WLAN_CIPHER_SUITE_TKIP: return ieee80211_crypto_tkip_encrypt(tx); case WLAN_CIPHER_SUITE_CCMP: - return ieee80211_crypto_ccmp_encrypt(tx); + return ieee80211_crypto_ccmp_encrypt( + tx, IEEE80211_CCMP_MIC_LEN); + case WLAN_CIPHER_SUITE_CCMP_256: + return ieee80211_crypto_ccmp_encrypt( + tx, IEEE80211_CCMP_256_MIC_LEN); case WLAN_CIPHER_SUITE_AES_CMAC: return ieee80211_crypto_aes_cmac_encrypt(tx); + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + return ieee80211_crypto_aes_cmac_256_encrypt(tx); + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + return ieee80211_crypto_aes_gmac_encrypt(tx); + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + return ieee80211_crypto_gcmp_encrypt(tx); default: return ieee80211_crypto_hw_encrypt(tx); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index fbd37d43dfce..8428f4a95479 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -744,16 +744,19 @@ EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif); /* * Nothing should have been stuffed into the workqueue during - * the suspend->resume cycle. If this WARN is seen then there - * is a bug with either the driver suspend or something in - * mac80211 stuffing into the workqueue which we haven't yet - * cleared during mac80211's suspend cycle. + * the suspend->resume cycle. Since we can't check each caller + * of this function if we are already quiescing / suspended, + * check here and don't WARN since this can actually happen when + * the rx path (for example) is racing against __ieee80211_suspend + * and suspending / quiescing was set after the rx path checked + * them. */ static bool ieee80211_can_queue_work(struct ieee80211_local *local) { - if (WARN(local->suspended && !local->resuming, - "queueing ieee80211 work while going to suspend\n")) + if (local->quiescing || (local->suspended && !local->resuming)) { + pr_warn("queueing ieee80211 work while going to suspend\n"); return false; + } return true; } @@ -2057,6 +2060,18 @@ int ieee80211_reconfig(struct ieee80211_local *local) mb(); local->resuming = false; + /* It's possible that we don't handle the scan completion in + * time during suspend, so if it's still marked as completed + * here, queue the work and flush it to clean things up. + * Instead of calling the worker function directly here, we + * really queue it to avoid potential races with other flows + * scheduling the same work. + */ + if (test_bit(SCAN_COMPLETED, &local->scanning)) { + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); + flush_delayed_work(&local->scan_work); + } + if (local->open_count && !reconfig_due_to_wowlan) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND); diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 12398fde02e8..75de6fac40d1 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -22,6 +22,8 @@ #include "tkip.h" #include "aes_ccm.h" #include "aes_cmac.h" +#include "aes_gmac.h" +#include "aes_gcm.h" #include "wpa.h" ieee80211_tx_result @@ -393,7 +395,8 @@ static inline void ccmp_hdr2pn(u8 *pn, u8 *hdr) } -static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) +static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb, + unsigned int mic_len) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_key *key = tx->key; @@ -424,7 +427,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) if (info->control.hw_key) tail = 0; else - tail = IEEE80211_CCMP_MIC_LEN; + tail = mic_len; if (WARN_ON(skb_tailroom(skb) < tail || skb_headroom(skb) < IEEE80211_CCMP_HDR_LEN)) @@ -459,21 +462,22 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) pos += IEEE80211_CCMP_HDR_LEN; ccmp_special_blocks(skb, pn, b_0, aad); ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, - skb_put(skb, IEEE80211_CCMP_MIC_LEN)); + skb_put(skb, mic_len), mic_len); return 0; } ieee80211_tx_result -ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx) +ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx, + unsigned int mic_len) { struct sk_buff *skb; ieee80211_tx_set_protected(tx); skb_queue_walk(&tx->skbs, skb) { - if (ccmp_encrypt_skb(tx, skb) < 0) + if (ccmp_encrypt_skb(tx, skb, mic_len) < 0) return TX_DROP; } @@ -482,7 +486,8 @@ ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx) ieee80211_rx_result -ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) +ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, + unsigned int mic_len) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; int hdrlen; @@ -499,8 +504,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) !ieee80211_is_robust_mgmt_frame(skb)) return RX_CONTINUE; - data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - - IEEE80211_CCMP_MIC_LEN; + data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; @@ -531,14 +535,14 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) key->u.ccmp.tfm, b_0, aad, skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, data_len, - skb->data + skb->len - IEEE80211_CCMP_MIC_LEN)) + skb->data + skb->len - mic_len, mic_len)) return RX_DROP_UNUSABLE; } memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); /* Remove CCMP header and MIC */ - if (pskb_trim(skb, skb->len - IEEE80211_CCMP_MIC_LEN)) + if (pskb_trim(skb, skb->len - mic_len)) return RX_DROP_UNUSABLE; memmove(skb->data + IEEE80211_CCMP_HDR_LEN, skb->data, hdrlen); skb_pull(skb, IEEE80211_CCMP_HDR_LEN); @@ -546,6 +550,229 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } +static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad) +{ + __le16 mask_fc; + u8 qos_tid; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + + memcpy(j_0, hdr->addr2, ETH_ALEN); + memcpy(&j_0[ETH_ALEN], pn, IEEE80211_GCMP_PN_LEN); + j_0[13] = 0; + j_0[14] = 0; + j_0[AES_BLOCK_SIZE - 1] = 0x01; + + /* AAD (extra authenticate-only data) / masked 802.11 header + * FC | A1 | A2 | A3 | SC | [A4] | [QC] + */ + put_unaligned_be16(ieee80211_hdrlen(hdr->frame_control) - 2, &aad[0]); + /* Mask FC: zero subtype b4 b5 b6 (if not mgmt) + * Retry, PwrMgt, MoreData; set Protected + */ + mask_fc = hdr->frame_control; + mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_RETRY | + IEEE80211_FCTL_PM | IEEE80211_FCTL_MOREDATA); + if (!ieee80211_is_mgmt(hdr->frame_control)) + mask_fc &= ~cpu_to_le16(0x0070); + mask_fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); + + put_unaligned(mask_fc, (__le16 *)&aad[2]); + memcpy(&aad[4], &hdr->addr1, 3 * ETH_ALEN); + + /* Mask Seq#, leave Frag# */ + aad[22] = *((u8 *)&hdr->seq_ctrl) & 0x0f; + aad[23] = 0; + + if (ieee80211_is_data_qos(hdr->frame_control)) + qos_tid = *ieee80211_get_qos_ctl(hdr) & + IEEE80211_QOS_CTL_TID_MASK; + else + qos_tid = 0; + + if (ieee80211_has_a4(hdr->frame_control)) { + memcpy(&aad[24], hdr->addr4, ETH_ALEN); + aad[30] = qos_tid; + aad[31] = 0; + } else { + memset(&aad[24], 0, ETH_ALEN + IEEE80211_QOS_CTL_LEN); + aad[24] = qos_tid; + } +} + +static inline void gcmp_pn2hdr(u8 *hdr, const u8 *pn, int key_id) +{ + hdr[0] = pn[5]; + hdr[1] = pn[4]; + hdr[2] = 0; + hdr[3] = 0x20 | (key_id << 6); + hdr[4] = pn[3]; + hdr[5] = pn[2]; + hdr[6] = pn[1]; + hdr[7] = pn[0]; +} + +static inline void gcmp_hdr2pn(u8 *pn, const u8 *hdr) +{ + pn[0] = hdr[7]; + pn[1] = hdr[6]; + pn[2] = hdr[5]; + pn[3] = hdr[4]; + pn[4] = hdr[1]; + pn[5] = hdr[0]; +} + +static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_key *key = tx->key; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + int hdrlen, len, tail; + u8 *pos; + u8 pn[6]; + u64 pn64; + u8 aad[2 * AES_BLOCK_SIZE]; + u8 j_0[AES_BLOCK_SIZE]; + + if (info->control.hw_key && + !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) && + !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && + !((info->control.hw_key->flags & + IEEE80211_KEY_FLAG_GENERATE_IV_MGMT) && + ieee80211_is_mgmt(hdr->frame_control))) { + /* hwaccel has no need for preallocated room for GCMP + * header or MIC fields + */ + return 0; + } + + hdrlen = ieee80211_hdrlen(hdr->frame_control); + len = skb->len - hdrlen; + + if (info->control.hw_key) + tail = 0; + else + tail = IEEE80211_GCMP_MIC_LEN; + + if (WARN_ON(skb_tailroom(skb) < tail || + skb_headroom(skb) < IEEE80211_GCMP_HDR_LEN)) + return -1; + + pos = skb_push(skb, IEEE80211_GCMP_HDR_LEN); + memmove(pos, pos + IEEE80211_GCMP_HDR_LEN, hdrlen); + skb_set_network_header(skb, skb_network_offset(skb) + + IEEE80211_GCMP_HDR_LEN); + + /* the HW only needs room for the IV, but not the actual IV */ + if (info->control.hw_key && + (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) + return 0; + + hdr = (struct ieee80211_hdr *)pos; + pos += hdrlen; + + pn64 = atomic64_inc_return(&key->u.gcmp.tx_pn); + + pn[5] = pn64; + pn[4] = pn64 >> 8; + pn[3] = pn64 >> 16; + pn[2] = pn64 >> 24; + pn[1] = pn64 >> 32; + pn[0] = pn64 >> 40; + + gcmp_pn2hdr(pos, pn, key->conf.keyidx); + + /* hwaccel - with software GCMP header */ + if (info->control.hw_key) + return 0; + + pos += IEEE80211_GCMP_HDR_LEN; + gcmp_special_blocks(skb, pn, j_0, aad); + ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len, + skb_put(skb, IEEE80211_GCMP_MIC_LEN)); + + return 0; +} + +ieee80211_tx_result +ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx) +{ + struct sk_buff *skb; + + ieee80211_tx_set_protected(tx); + + skb_queue_walk(&tx->skbs, skb) { + if (gcmp_encrypt_skb(tx, skb) < 0) + return TX_DROP; + } + + return TX_CONTINUE; +} + +ieee80211_rx_result +ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; + int hdrlen; + struct ieee80211_key *key = rx->key; + struct sk_buff *skb = rx->skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + u8 pn[IEEE80211_GCMP_PN_LEN]; + int data_len; + int queue; + + hdrlen = ieee80211_hdrlen(hdr->frame_control); + + if (!ieee80211_is_data(hdr->frame_control) && + !ieee80211_is_robust_mgmt_frame(skb)) + return RX_CONTINUE; + + data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - + IEEE80211_GCMP_MIC_LEN; + if (!rx->sta || data_len < 0) + return RX_DROP_UNUSABLE; + + if (status->flag & RX_FLAG_DECRYPTED) { + if (!pskb_may_pull(rx->skb, hdrlen + IEEE80211_GCMP_HDR_LEN)) + return RX_DROP_UNUSABLE; + } else { + if (skb_linearize(rx->skb)) + return RX_DROP_UNUSABLE; + } + + gcmp_hdr2pn(pn, skb->data + hdrlen); + + queue = rx->security_idx; + + if (memcmp(pn, key->u.gcmp.rx_pn[queue], IEEE80211_GCMP_PN_LEN) <= 0) { + key->u.gcmp.replays++; + return RX_DROP_UNUSABLE; + } + + if (!(status->flag & RX_FLAG_DECRYPTED)) { + u8 aad[2 * AES_BLOCK_SIZE]; + u8 j_0[AES_BLOCK_SIZE]; + /* hardware didn't decrypt/verify MIC */ + gcmp_special_blocks(skb, pn, j_0, aad); + + if (ieee80211_aes_gcm_decrypt( + key->u.gcmp.tfm, j_0, aad, + skb->data + hdrlen + IEEE80211_GCMP_HDR_LEN, + data_len, + skb->data + skb->len - IEEE80211_GCMP_MIC_LEN)) + return RX_DROP_UNUSABLE; + } + + memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); + + /* Remove GCMP header and MIC */ + if (pskb_trim(skb, skb->len - IEEE80211_GCMP_MIC_LEN)) + return RX_DROP_UNUSABLE; + memmove(skb->data + IEEE80211_GCMP_HDR_LEN, skb->data, hdrlen); + skb_pull(skb, IEEE80211_GCMP_HDR_LEN); + + return RX_CONTINUE; +} + static ieee80211_tx_result ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx, struct sk_buff *skb) @@ -729,6 +956,48 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) return TX_CONTINUE; } +ieee80211_tx_result +ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx) +{ + struct sk_buff *skb; + struct ieee80211_tx_info *info; + struct ieee80211_key *key = tx->key; + struct ieee80211_mmie_16 *mmie; + u8 aad[20]; + u64 pn64; + + if (WARN_ON(skb_queue_len(&tx->skbs) != 1)) + return TX_DROP; + + skb = skb_peek(&tx->skbs); + + info = IEEE80211_SKB_CB(skb); + + if (info->control.hw_key) + return TX_CONTINUE; + + if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) + return TX_DROP; + + mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie)); + mmie->element_id = WLAN_EID_MMIE; + mmie->length = sizeof(*mmie) - 2; + mmie->key_id = cpu_to_le16(key->conf.keyidx); + + /* PN = PN + 1 */ + pn64 = atomic64_inc_return(&key->u.aes_cmac.tx_pn); + + bip_ipn_set64(mmie->sequence_number, pn64); + + bip_aad(skb, aad); + + /* MIC = AES-256-CMAC(IGTK, AAD || Management Frame Body || MMIE, 128) + */ + ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mmie->mic); + + return TX_CONTINUE; +} ieee80211_rx_result ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx) @@ -780,6 +1049,160 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } +ieee80211_rx_result +ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx) +{ + struct sk_buff *skb = rx->skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_key *key = rx->key; + struct ieee80211_mmie_16 *mmie; + u8 aad[20], mic[16], ipn[6]; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + + if (!ieee80211_is_mgmt(hdr->frame_control)) + return RX_CONTINUE; + + /* management frames are already linear */ + + if (skb->len < 24 + sizeof(*mmie)) + return RX_DROP_UNUSABLE; + + mmie = (struct ieee80211_mmie_16 *) + (skb->data + skb->len - sizeof(*mmie)); + if (mmie->element_id != WLAN_EID_MMIE || + mmie->length != sizeof(*mmie) - 2) + return RX_DROP_UNUSABLE; /* Invalid MMIE */ + + bip_ipn_swap(ipn, mmie->sequence_number); + + if (memcmp(ipn, key->u.aes_cmac.rx_pn, 6) <= 0) { + key->u.aes_cmac.replays++; + return RX_DROP_UNUSABLE; + } + + if (!(status->flag & RX_FLAG_DECRYPTED)) { + /* hardware didn't decrypt/verify MIC */ + bip_aad(skb, aad); + ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mic); + if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) { + key->u.aes_cmac.icverrors++; + return RX_DROP_UNUSABLE; + } + } + + memcpy(key->u.aes_cmac.rx_pn, ipn, 6); + + /* Remove MMIE */ + skb_trim(skb, skb->len - sizeof(*mmie)); + + return RX_CONTINUE; +} + +ieee80211_tx_result +ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx) +{ + struct sk_buff *skb; + struct ieee80211_tx_info *info; + struct ieee80211_key *key = tx->key; + struct ieee80211_mmie_16 *mmie; + struct ieee80211_hdr *hdr; + u8 aad[20]; + u64 pn64; + u8 nonce[12]; + + if (WARN_ON(skb_queue_len(&tx->skbs) != 1)) + return TX_DROP; + + skb = skb_peek(&tx->skbs); + + info = IEEE80211_SKB_CB(skb); + + if (info->control.hw_key) + return TX_CONTINUE; + + if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) + return TX_DROP; + + mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie)); + mmie->element_id = WLAN_EID_MMIE; + mmie->length = sizeof(*mmie) - 2; + mmie->key_id = cpu_to_le16(key->conf.keyidx); + + /* PN = PN + 1 */ + pn64 = atomic64_inc_return(&key->u.aes_gmac.tx_pn); + + bip_ipn_set64(mmie->sequence_number, pn64); + + bip_aad(skb, aad); + + hdr = (struct ieee80211_hdr *)skb->data; + memcpy(nonce, hdr->addr2, ETH_ALEN); + bip_ipn_swap(nonce + ETH_ALEN, mmie->sequence_number); + + /* MIC = AES-GMAC(IGTK, AAD || Management Frame Body || MMIE, 128) */ + if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce, + skb->data + 24, skb->len - 24, mmie->mic) < 0) + return TX_DROP; + + return TX_CONTINUE; +} + +ieee80211_rx_result +ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx) +{ + struct sk_buff *skb = rx->skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_key *key = rx->key; + struct ieee80211_mmie_16 *mmie; + u8 aad[20], mic[16], ipn[6], nonce[12]; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + + if (!ieee80211_is_mgmt(hdr->frame_control)) + return RX_CONTINUE; + + /* management frames are already linear */ + + if (skb->len < 24 + sizeof(*mmie)) + return RX_DROP_UNUSABLE; + + mmie = (struct ieee80211_mmie_16 *) + (skb->data + skb->len - sizeof(*mmie)); + if (mmie->element_id != WLAN_EID_MMIE || + mmie->length != sizeof(*mmie) - 2) + return RX_DROP_UNUSABLE; /* Invalid MMIE */ + + bip_ipn_swap(ipn, mmie->sequence_number); + + if (memcmp(ipn, key->u.aes_gmac.rx_pn, 6) <= 0) { + key->u.aes_gmac.replays++; + return RX_DROP_UNUSABLE; + } + + if (!(status->flag & RX_FLAG_DECRYPTED)) { + /* hardware didn't decrypt/verify MIC */ + bip_aad(skb, aad); + + memcpy(nonce, hdr->addr2, ETH_ALEN); + memcpy(nonce + ETH_ALEN, ipn, 6); + + if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce, + skb->data + 24, skb->len - 24, + mic) < 0 || + memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) { + key->u.aes_gmac.icverrors++; + return RX_DROP_UNUSABLE; + } + } + + memcpy(key->u.aes_gmac.rx_pn, ipn, 6); + + /* Remove MMIE */ + skb_trim(skb, skb->len - sizeof(*mmie)); + + return RX_CONTINUE; +} + ieee80211_tx_result ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) { diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h index 62e5a12dfe0a..d98011ee8f55 100644 --- a/net/mac80211/wpa.h +++ b/net/mac80211/wpa.h @@ -24,17 +24,32 @@ ieee80211_rx_result ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx); ieee80211_tx_result -ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx); +ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx, + unsigned int mic_len); ieee80211_rx_result -ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx); +ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, + unsigned int mic_len); ieee80211_tx_result ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx); +ieee80211_tx_result +ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx); ieee80211_rx_result ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx); +ieee80211_rx_result +ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx); +ieee80211_tx_result +ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx); +ieee80211_rx_result +ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx); ieee80211_tx_result ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx); ieee80211_rx_result ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx); +ieee80211_tx_result +ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx); +ieee80211_rx_result +ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx); + #endif /* WPA_H */ diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 349295d21946..809df534a720 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -60,14 +60,14 @@ out: return segs; } -static struct packet_offload mpls_mc_offload = { +static struct packet_offload mpls_mc_offload __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_MC), .callbacks = { .gso_segment = mpls_gso_segment, }, }; -static struct packet_offload mpls_uc_offload = { +static struct packet_offload mpls_uc_offload __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_UC), .callbacks = { .gso_segment = mpls_gso_segment, diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 990decba1fe4..b87ca32efa0b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -659,16 +659,24 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } -static int ip_vs_route_me_harder(int af, struct sk_buff *skb) +static int ip_vs_route_me_harder(int af, struct sk_buff *skb, + unsigned int hooknum) { + if (!sysctl_snat_reroute(skb)) + return 0; + /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ + if (NF_INET_LOCAL_IN == hooknum) + return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0) + struct dst_entry *dst = skb_dst(skb); + + if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && + ip6_route_me_harder(skb) != 0) return 1; } else #endif - if ((sysctl_snat_reroute(skb) || - skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) return 1; @@ -791,7 +799,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl) + unsigned int offset, unsigned int ihl, + unsigned int hooknum) { unsigned int verdict = NF_DROP; @@ -821,7 +830,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto out; /* do the statistics and put it back */ @@ -916,7 +925,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl); + pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -981,7 +990,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, snet.in6 = ciph.saddr.in6; writable = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, writable, sizeof(struct ipv6hdr)); + pp, writable, sizeof(struct ipv6hdr), + hooknum); } #endif @@ -1040,7 +1050,8 @@ static inline bool is_new_conn(const struct sk_buff *skb, */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, + unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; @@ -1078,7 +1089,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * if it came from this machine itself. So re-compute * the routing information. */ - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); @@ -1181,7 +1192,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) cp = pp->conn_out_get(af, skb, &iph, 0); if (likely(cp)) - return handle_response(af, skb, pd, cp, &iph); + return handle_response(af, skb, pd, cp, &iph, hooknum); if (sysctl_nat_icmp_send(net) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 70f697827b9b..199fd0f27b0e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1136,9 +1136,11 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) /* Restore old counters on this cpu, no problem. Per-cpu statistics * are not exposed to userspace. */ + preempt_disable(); stats = this_cpu_ptr(newstats); stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + preempt_enable(); return newstats; } @@ -1264,8 +1266,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); - if (trans == NULL) + if (trans == NULL) { + free_percpu(stats); return -ENOMEM; + } nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -1321,8 +1325,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, hookfn = type->hooks[hooknum]; basechain = kzalloc(sizeof(*basechain), GFP_KERNEL); - if (basechain == NULL) + if (basechain == NULL) { + module_put(type->owner); return -ENOMEM; + } if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); @@ -3759,6 +3765,24 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, } EXPORT_SYMBOL_GPL(nft_chain_validate_dependency); +int nft_chain_validate_hooks(const struct nft_chain *chain, + unsigned int hook_flags) +{ + struct nft_base_chain *basechain; + + if (chain->flags & NFT_BASE_CHAIN) { + basechain = nft_base_chain(chain); + + if ((1 << basechain->ops[0].hooknum) & hook_flags) + return 0; + + return -EOPNOTSUPP; + } + + return 0; +} +EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); + /* * Loop detection - walk through the ruleset beginning at the destination chain * of a new jump until either the source chain is reached (loop) or all diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 75887d7d2c6a..61e6c407476a 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -130,31 +130,50 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { struct rhashtable *priv = nft_set_priv(set); - const struct bucket_table *tbl; const struct nft_hash_elem *he; + struct rhashtable_iter hti; struct nft_set_elem elem; - unsigned int i; + int err; - tbl = rht_dereference_rcu(priv->tbl, priv); - for (i = 0; i < tbl->size; i++) { - struct rhash_head *pos; + err = rhashtable_walk_init(priv, &hti); + iter->err = err; + if (err) + return; + + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) { + iter->err = err; + goto out; + } - rht_for_each_entry_rcu(he, pos, tbl, i, node) { - if (iter->count < iter->skip) - goto cont; + while ((he = rhashtable_walk_next(&hti))) { + if (IS_ERR(he)) { + err = PTR_ERR(he); + if (err != -EAGAIN) { + iter->err = err; + goto out; + } + } + + if (iter->count < iter->skip) + goto cont; + + memcpy(&elem.key, &he->key, sizeof(elem.key)); + if (set->flags & NFT_SET_MAP) + memcpy(&elem.data, he->data, sizeof(elem.data)); + elem.flags = 0; - memcpy(&elem.key, &he->key, sizeof(elem.key)); - if (set->flags & NFT_SET_MAP) - memcpy(&elem.data, he->data, sizeof(elem.data)); - elem.flags = 0; + iter->err = iter->fn(ctx, set, iter, &elem); + if (iter->err < 0) + goto out; - iter->err = iter->fn(ctx, set, iter, &elem); - if (iter->err < 0) - return; cont: - iter->count++; - } + iter->count++; } + +out: + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); } static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index d1ffd5eb3a9b..9aea747b43ea 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -21,6 +21,21 @@ const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { }; EXPORT_SYMBOL_GPL(nft_masq_policy); +int nft_masq_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + int err; + + err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); + if (err < 0) + return err; + + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_POST_ROUTING)); +} +EXPORT_SYMBOL_GPL(nft_masq_validate); + int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -28,8 +43,8 @@ int nft_masq_init(const struct nft_ctx *ctx, struct nft_masq *priv = nft_expr_priv(expr); int err; - err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); - if (err < 0) + err = nft_masq_validate(ctx, expr, NULL); + if (err) return err; if (tb[NFTA_MASQ_FLAGS] == NULL) @@ -60,12 +75,5 @@ nla_put_failure: } EXPORT_SYMBOL_GPL(nft_masq_dump); -int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data) -{ - return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); -} -EXPORT_SYMBOL_GPL(nft_masq_validate); - MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>"); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index aff54fb1c8a0..a0837c6c9283 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -88,17 +88,40 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = { [NFTA_NAT_FLAGS] = { .type = NLA_U32 }, }; -static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_nat_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { struct nft_nat *priv = nft_expr_priv(expr); - u32 family; int err; err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); if (err < 0) return err; + switch (priv->type) { + case NFT_NAT_SNAT: + err = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN)); + break; + case NFT_NAT_DNAT: + err = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT)); + break; + } + + return err; +} + +static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_nat *priv = nft_expr_priv(expr); + u32 family; + int err; + if (tb[NFTA_NAT_TYPE] == NULL || (tb[NFTA_NAT_REG_ADDR_MIN] == NULL && tb[NFTA_NAT_REG_PROTO_MIN] == NULL)) @@ -115,6 +138,10 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; } + err = nft_nat_validate(ctx, expr, NULL); + if (err < 0) + return err; + if (tb[NFTA_NAT_FAMILY] == NULL) return -EINVAL; @@ -219,13 +246,6 @@ nla_put_failure: return -1; } -static int nft_nat_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) -{ - return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); -} - static struct nft_expr_type nft_nat_type; static const struct nft_expr_ops nft_nat_ops = { .type = &nft_nat_type, diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 9e8093f28311..d7e9e93a4e90 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -23,6 +23,22 @@ const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = { }; EXPORT_SYMBOL_GPL(nft_redir_policy); +int nft_redir_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + int err; + + err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); + if (err < 0) + return err; + + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT)); +} +EXPORT_SYMBOL_GPL(nft_redir_validate); + int nft_redir_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -30,7 +46,7 @@ int nft_redir_init(const struct nft_ctx *ctx, struct nft_redir *priv = nft_expr_priv(expr); int err; - err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); + err = nft_redir_validate(ctx, expr, NULL); if (err < 0) return err; @@ -88,12 +104,5 @@ nla_put_failure: } EXPORT_SYMBOL_GPL(nft_redir_dump); -int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data) -{ - return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); -} -EXPORT_SYMBOL_GPL(nft_redir_validate); - MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>"); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 179625353cac..7fd1104ba900 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -324,8 +324,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, return 0; add_std_failure: - if (doi_def) - cipso_v4_doi_free(doi_def); + cipso_v4_doi_free(doi_def); return ret_val; } diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 8b3b789c43c2..70440748fe5c 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -93,23 +93,20 @@ static int netlbl_mgmt_add_common(struct genl_info *info, struct netlbl_audit *audit_info) { int ret_val = -EINVAL; - struct netlbl_dom_map *entry = NULL; struct netlbl_domaddr_map *addrmap = NULL; struct cipso_v4_doi *cipsov4 = NULL; u32 tmp_val; + struct netlbl_dom_map *entry = kzalloc(sizeof(*entry), GFP_KERNEL); - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (entry == NULL) { - ret_val = -ENOMEM; - goto add_failure; - } + if (!entry) + return -ENOMEM; entry->def.type = nla_get_u32(info->attrs[NLBL_MGMT_A_PROTOCOL]); if (info->attrs[NLBL_MGMT_A_DOMAIN]) { size_t tmp_size = nla_len(info->attrs[NLBL_MGMT_A_DOMAIN]); entry->domain = kmalloc(tmp_size, GFP_KERNEL); if (entry->domain == NULL) { ret_val = -ENOMEM; - goto add_failure; + goto add_free_entry; } nla_strlcpy(entry->domain, info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size); @@ -125,16 +122,16 @@ static int netlbl_mgmt_add_common(struct genl_info *info, break; case NETLBL_NLTYPE_CIPSOV4: if (!info->attrs[NLBL_MGMT_A_CV4DOI]) - goto add_failure; + goto add_free_domain; tmp_val = nla_get_u32(info->attrs[NLBL_MGMT_A_CV4DOI]); cipsov4 = cipso_v4_doi_getdef(tmp_val); if (cipsov4 == NULL) - goto add_failure; + goto add_free_domain; entry->def.cipso = cipsov4; break; default: - goto add_failure; + goto add_free_domain; } if (info->attrs[NLBL_MGMT_A_IPV4ADDR]) { @@ -145,7 +142,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, addrmap = kzalloc(sizeof(*addrmap), GFP_KERNEL); if (addrmap == NULL) { ret_val = -ENOMEM; - goto add_failure; + goto add_doi_put_def; } INIT_LIST_HEAD(&addrmap->list4); INIT_LIST_HEAD(&addrmap->list6); @@ -153,12 +150,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, if (nla_len(info->attrs[NLBL_MGMT_A_IPV4ADDR]) != sizeof(struct in_addr)) { ret_val = -EINVAL; - goto add_failure; + goto add_free_addrmap; } if (nla_len(info->attrs[NLBL_MGMT_A_IPV4MASK]) != sizeof(struct in_addr)) { ret_val = -EINVAL; - goto add_failure; + goto add_free_addrmap; } addr = nla_data(info->attrs[NLBL_MGMT_A_IPV4ADDR]); mask = nla_data(info->attrs[NLBL_MGMT_A_IPV4MASK]); @@ -166,7 +163,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) { ret_val = -ENOMEM; - goto add_failure; + goto add_free_addrmap; } map->list.addr = addr->s_addr & mask->s_addr; map->list.mask = mask->s_addr; @@ -178,7 +175,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = netlbl_af4list_add(&map->list, &addrmap->list4); if (ret_val != 0) { kfree(map); - goto add_failure; + goto add_free_addrmap; } entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -192,7 +189,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, addrmap = kzalloc(sizeof(*addrmap), GFP_KERNEL); if (addrmap == NULL) { ret_val = -ENOMEM; - goto add_failure; + goto add_doi_put_def; } INIT_LIST_HEAD(&addrmap->list4); INIT_LIST_HEAD(&addrmap->list6); @@ -200,12 +197,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, if (nla_len(info->attrs[NLBL_MGMT_A_IPV6ADDR]) != sizeof(struct in6_addr)) { ret_val = -EINVAL; - goto add_failure; + goto add_free_addrmap; } if (nla_len(info->attrs[NLBL_MGMT_A_IPV6MASK]) != sizeof(struct in6_addr)) { ret_val = -EINVAL; - goto add_failure; + goto add_free_addrmap; } addr = nla_data(info->attrs[NLBL_MGMT_A_IPV6ADDR]); mask = nla_data(info->attrs[NLBL_MGMT_A_IPV6MASK]); @@ -213,7 +210,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) { ret_val = -ENOMEM; - goto add_failure; + goto add_free_addrmap; } map->list.addr = *addr; map->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; @@ -227,7 +224,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = netlbl_af6list_add(&map->list, &addrmap->list6); if (ret_val != 0) { kfree(map); - goto add_failure; + goto add_free_addrmap; } entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -237,16 +234,17 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = netlbl_domhsh_add(entry, audit_info); if (ret_val != 0) - goto add_failure; + goto add_free_addrmap; return 0; -add_failure: - if (cipsov4) - cipso_v4_doi_putdef(cipsov4); - if (entry) - kfree(entry->domain); +add_free_addrmap: kfree(addrmap); +add_doi_put_def: + cipso_v4_doi_putdef(cipsov4); +add_free_domain: + kfree(entry->domain); +add_free_entry: kfree(entry); return ret_val; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a36777b7cfb6..2702673f0f23 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1438,7 +1438,7 @@ static void netlink_undo_bind(int group, long unsigned int groups, for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) - nlk->netlink_unbind(sock_net(sk), undo); + nlk->netlink_unbind(sock_net(sk), undo + 1); } static int netlink_bind(struct socket *sock, struct sockaddr *addr, @@ -1476,7 +1476,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, for (group = 0; group < nlk->ngroups; group++) { if (!test_bit(group, &groups)) continue; - err = nlk->netlink_bind(net, group); + err = nlk->netlink_bind(net, group + 1); if (!err) continue; netlink_undo_bind(group, groups, sk); @@ -2298,7 +2298,12 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; } + /* It's a really convoluted way for userland to ask for mmaped + * sendmsg(), but that's what we've got... + */ if (netlink_tx_is_mmaped(sk) && + msg->msg_iter.type == ITER_IOVEC && + msg->msg_iter.nr_segs == 1 && msg->msg_iter.iov->iov_base == NULL) { err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, &scm); @@ -2886,99 +2891,97 @@ EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { struct seq_net_private p; + struct rhashtable_iter hti; int link; - int hash_idx; }; -static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) +static int netlink_walk_start(struct nl_seq_iter *iter) { - struct nl_seq_iter *iter = seq->private; - int i, j; - struct netlink_sock *nlk; - struct sock *s; - loff_t off = 0; - - for (i = 0; i < MAX_LINKS; i++) { - struct rhashtable *ht = &nl_table[i].hash; - const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); - - for (j = 0; j < tbl->size; j++) { - struct rhash_head *node; - - rht_for_each_entry_rcu(nlk, node, tbl, j, node) { - s = (struct sock *)nlk; + int err; - if (sock_net(s) != seq_file_net(seq)) - continue; - if (off == pos) { - iter->link = i; - iter->hash_idx = j; - return s; - } - ++off; - } - } + err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti); + if (err) { + iter->link = MAX_LINKS; + return err; } - return NULL; + + err = rhashtable_walk_start(&iter->hti); + return err == -EAGAIN ? 0 : err; } -static void *netlink_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) +static void netlink_walk_stop(struct nl_seq_iter *iter) { - rcu_read_lock(); - return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN; + rhashtable_walk_stop(&iter->hti); + rhashtable_walk_exit(&iter->hti); } -static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *__netlink_seq_next(struct seq_file *seq) { - struct rhashtable *ht; - const struct bucket_table *tbl; - struct rhash_head *node; + struct nl_seq_iter *iter = seq->private; struct netlink_sock *nlk; - struct nl_seq_iter *iter; - struct net *net; - int i, j; - ++*pos; + do { + for (;;) { + int err; - if (v == SEQ_START_TOKEN) - return netlink_seq_socket_idx(seq, 0); + nlk = rhashtable_walk_next(&iter->hti); - net = seq_file_net(seq); - iter = seq->private; - nlk = v; + if (IS_ERR(nlk)) { + if (PTR_ERR(nlk) == -EAGAIN) + continue; - i = iter->link; - ht = &nl_table[i].hash; - tbl = rht_dereference_rcu(ht->tbl, ht); - rht_for_each_entry_rcu_continue(nlk, node, nlk->node.next, tbl, iter->hash_idx, node) - if (net_eq(sock_net((struct sock *)nlk), net)) - return nlk; + return nlk; + } - j = iter->hash_idx + 1; + if (nlk) + break; - do { + netlink_walk_stop(iter); + if (++iter->link >= MAX_LINKS) + return NULL; - for (; j < tbl->size; j++) { - rht_for_each_entry_rcu(nlk, node, tbl, j, node) { - if (net_eq(sock_net((struct sock *)nlk), net)) { - iter->link = i; - iter->hash_idx = j; - return nlk; - } - } + err = netlink_walk_start(iter); + if (err) + return ERR_PTR(err); } + } while (sock_net(&nlk->sk) != seq_file_net(seq)); - j = 0; - } while (++i < MAX_LINKS); + return nlk; +} - return NULL; +static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) +{ + struct nl_seq_iter *iter = seq->private; + void *obj = SEQ_START_TOKEN; + loff_t pos; + int err; + + iter->link = 0; + + err = netlink_walk_start(iter); + if (err) + return ERR_PTR(err); + + for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) + obj = __netlink_seq_next(seq); + + return obj; +} + +static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return __netlink_seq_next(seq); } static void netlink_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) { - rcu_read_unlock(); + struct nl_seq_iter *iter = seq->private; + + if (iter->link >= MAX_LINKS) + return; + + netlink_walk_stop(iter); } diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index c3b0cd43eb56..c173f69e1479 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -71,14 +71,14 @@ static struct ctl_table rds_sysctl_rds_table[] = { { .procname = "max_unacked_packets", .data = &rds_sysctl_max_unacked_packets, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_unacked_bytes", .data = &rds_sysctl_max_unacked_bytes, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 3f4a0bbeed3d..d978f2f46ff3 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -170,6 +170,7 @@ static const struct acpi_device_id rfkill_acpi_match[] = { { "BCM2E1A", RFKILL_TYPE_BLUETOOTH }, { "BCM2E39", RFKILL_TYPE_BLUETOOTH }, { "BCM2E3D", RFKILL_TYPE_BLUETOOTH }, + { "BCM2E40", RFKILL_TYPE_BLUETOOTH }, { "BCM2E64", RFKILL_TYPE_BLUETOOTH }, { "BCM4752", RFKILL_TYPE_GPS }, { "LNV4752", RFKILL_TYPE_GPS }, diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index 74c0fcd36838..5394b6be46ec 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -42,6 +42,11 @@ void rxrpc_UDP_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } + if (!skb->len) { + _leave("UDP empty message"); + kfree_skb(skb); + return; + } rxrpc_new_skb(skb); diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index e1a9373e5979..8331c95e1522 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -232,10 +232,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, call->state != RXRPC_CALL_SERVER_SEND_REPLY) { ret = -EPROTO; /* request phase complete for this client call */ } else { - mm_segment_t oldfs = get_fs(); - set_fs(KERNEL_DS); ret = rxrpc_send_data(NULL, call->socket, call, msg, len); - set_fs(oldfs); } release_sock(&call->socket->sk); @@ -529,13 +526,11 @@ static int rxrpc_send_data(struct kiocb *iocb, struct msghdr *msg, size_t len) { struct rxrpc_skb_priv *sp; - unsigned char __user *from; struct sk_buff *skb; - const struct iovec *iov; struct sock *sk = &rx->sk; long timeo; bool more; - int ret, ioc, segment, copied; + int ret, copied; timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -545,25 +540,17 @@ static int rxrpc_send_data(struct kiocb *iocb, if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) return -EPIPE; - iov = msg->msg_iter.iov; - ioc = msg->msg_iter.nr_segs - 1; - from = iov->iov_base; - segment = iov->iov_len; - iov++; more = msg->msg_flags & MSG_MORE; skb = call->tx_pending; call->tx_pending = NULL; copied = 0; - do { + if (len > iov_iter_count(&msg->msg_iter)) + len = iov_iter_count(&msg->msg_iter); + while (len) { int copy; - if (segment > len) - segment = len; - - _debug("SEGMENT %d @%p", segment, from); - if (!skb) { size_t size, chunk, max, space; @@ -631,13 +618,13 @@ static int rxrpc_send_data(struct kiocb *iocb, /* append next segment of data to the current buffer */ copy = skb_tailroom(skb); ASSERTCMP(copy, >, 0); - if (copy > segment) - copy = segment; + if (copy > len) + copy = len; if (copy > sp->remain) copy = sp->remain; _debug("add"); - ret = skb_add_data(skb, from, copy); + ret = skb_add_data(skb, &msg->msg_iter, copy); _debug("added"); if (ret < 0) goto efault; @@ -646,18 +633,6 @@ static int rxrpc_send_data(struct kiocb *iocb, copied += copy; len -= copy; - segment -= copy; - from += copy; - while (segment == 0 && ioc > 0) { - from = iov->iov_base; - segment = iov->iov_len; - iov++; - ioc--; - } - if (len == 0) { - segment = 0; - ioc = 0; - } /* check for the far side aborting the call or a network error * occurring */ @@ -665,7 +640,7 @@ static int rxrpc_send_data(struct kiocb *iocb, goto call_aborted; /* add the packet to the send queue if it's now full */ - if (sp->remain <= 0 || (segment == 0 && !more)) { + if (sp->remain <= 0 || (!len && !more)) { struct rxrpc_connection *conn = call->conn; uint32_t seq; size_t pad; @@ -711,11 +686,10 @@ static int rxrpc_send_data(struct kiocb *iocb, memcpy(skb->head, &sp->hdr, sizeof(struct rxrpc_header)); - rxrpc_queue_packet(call, skb, segment == 0 && !more); + rxrpc_queue_packet(call, skb, !iov_iter_count(&msg->msg_iter) && !more); skb = NULL; } - - } while (segment > 0); + } success: ret = copied; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index aad6a679fb13..baef987fe2c0 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -556,8 +556,9 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, } EXPORT_SYMBOL(tcf_exts_change); -#define tcf_exts_first_act(ext) \ - list_first_entry(&(exts)->actions, struct tc_action, list) +#define tcf_exts_first_act(ext) \ + list_first_entry_or_null(&(exts)->actions, \ + struct tc_action, list) int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { @@ -603,7 +604,7 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT struct tc_action *a = tcf_exts_first_act(exts); - if (tcf_action_copy_stats(skb, a, 1) < 0) + if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0) return -1; #endif return 0; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 2a50f5c62070..dfcea20e3171 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -52,6 +52,7 @@ #include <net/pkt_sched.h> #include <net/sock.h> #include <net/tcp_states.h> +#include <net/tcp.h> /* * Per flow structure, dynamically allocated @@ -92,6 +93,7 @@ struct fq_sched_data { u32 flow_refill_delay; u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ + u32 orphan_mask; /* mask for orphaned skb */ struct rb_root *fq_root; u8 rate_enable; u8 fq_trees_log; @@ -222,11 +224,20 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) return &q->internal; - if (unlikely(!sk)) { + /* SYNACK messages are attached to a listener socket. + * 1) They are not part of a 'flow' yet + * 2) We do not want to rate limit them (eg SYNFLOOD attack), + * especially if the listener set SO_MAX_PACING_RATE + * 3) We pretend they are orphaned + */ + if (!sk || sk->sk_state == TCP_LISTEN) { + unsigned long hash = skb_get_hash(skb) & q->orphan_mask; + /* By forcing low order bit to 1, we make sure to not * collide with a local flow (socket pointers are word aligned) */ - sk = (struct sock *)(skb_get_hash(skb) | 1L); + sk = (struct sock *)((hash << 1) | 1UL); + skb_orphan(skb); } root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)]; @@ -445,7 +456,9 @@ begin: goto begin; } - if (unlikely(f->head && now < f->time_next_packet)) { + skb = f->head; + if (unlikely(skb && now < f->time_next_packet && + !skb_is_tcp_pure_ack(skb))) { head->first = f->next; fq_flow_set_throttled(q, f); goto begin; @@ -464,12 +477,15 @@ begin: goto begin; } prefetch(&skb->end); - f->time_next_packet = now; f->credit -= qdisc_pkt_len(skb); if (f->credit > 0 || !q->rate_enable) goto out; + /* Do not pace locally generated ack packets */ + if (skb_is_tcp_pure_ack(skb)) + goto out; + rate = q->flow_max_rate; if (skb->sk) rate = min(skb->sk->sk_pacing_rate, rate); @@ -670,8 +686,14 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_FQ_FLOW_PLIMIT]) q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]); - if (tb[TCA_FQ_QUANTUM]) - q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); + if (tb[TCA_FQ_QUANTUM]) { + u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); + + if (quantum > 0) + q->quantum = quantum; + else + err = -EINVAL; + } if (tb[TCA_FQ_INITIAL_QUANTUM]) q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); @@ -698,6 +720,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->flow_refill_delay = usecs_to_jiffies(usecs_delay); } + if (tb[TCA_FQ_ORPHAN_MASK]) + q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]); + if (!err) { sch_tree_unlock(sch); err = fq_resize(sch, fq_log); @@ -743,6 +768,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->delayed = RB_ROOT; q->fq_root = NULL; q->fq_trees_log = ilog2(1024); + q->orphan_mask = 1024 - 1; qdisc_watchdog_init(&q->watchdog, sch); if (opt) @@ -772,6 +798,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, jiffies_to_usecs(q->flow_refill_delay)) || + nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 26d06dbcc1c8..197c3f59ecbf 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -391,8 +391,7 @@ void sctp_association_free(struct sctp_association *asoc) sctp_asconf_queue_teardown(asoc); /* Free pending address space being deleted */ - if (asoc->asconf_addr_del_pending != NULL) - kfree(asoc->asconf_addr_del_pending); + kfree(asoc->asconf_addr_del_pending); /* AUTH - Free the endpoint shared keys */ sctp_auth_destroy_keys(&asoc->endpoint_shared_keys); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e49e231cef52..06320c8c1c86 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2608,7 +2608,7 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); - af = sctp_get_af_specific(param_type2af(param.p->type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (af == NULL) break; diff --git a/net/socket.c b/net/socket.c index 3326d67482ac..bbedbfcb42c2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -113,10 +113,8 @@ unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif -static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); +static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to); +static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); @@ -142,8 +140,10 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .llseek = no_llseek, - .aio_read = sock_aio_read, - .aio_write = sock_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = sock_read_iter, + .write_iter = sock_write_iter, .poll = sock_poll, .unlocked_ioctl = sock_ioctl, #ifdef CONFIG_COMPAT @@ -845,63 +845,47 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, return sock->ops->splice_read(sock, ppos, pipe, len, flags); } -static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, - struct file *file, const struct iovec *iov, - unsigned long nr_segs) +static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { + struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; + struct msghdr msg = {.msg_iter = *to}; + ssize_t res; - msg->msg_name = NULL; - msg->msg_namelen = 0; - msg->msg_control = NULL; - msg->msg_controllen = 0; - iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, iocb->ki_nbytes); - msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; + if (file->f_flags & O_NONBLOCK) + msg.msg_flags = MSG_DONTWAIT; - return __sock_recvmsg(iocb, sock, msg, iocb->ki_nbytes, msg->msg_flags); -} - -static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - struct msghdr msg; - - if (pos != 0) + if (iocb->ki_pos != 0) return -ESPIPE; if (iocb->ki_nbytes == 0) /* Match SYS5 behaviour */ return 0; - return do_sock_read(&msg, iocb, iocb->ki_filp, iov, nr_segs); + res = __sock_recvmsg(iocb, sock, &msg, + iocb->ki_nbytes, msg.msg_flags); + *to = msg.msg_iter; + return res; } -static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, - struct file *file, const struct iovec *iov, - unsigned long nr_segs) +static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { + struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; + struct msghdr msg = {.msg_iter = *from}; + ssize_t res; - msg->msg_name = NULL; - msg->msg_namelen = 0; - msg->msg_control = NULL; - msg->msg_controllen = 0; - iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, iocb->ki_nbytes); - msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; - if (sock->type == SOCK_SEQPACKET) - msg->msg_flags |= MSG_EOR; - - return __sock_sendmsg(iocb, sock, msg, iocb->ki_nbytes); -} + if (iocb->ki_pos != 0) + return -ESPIPE; -static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - struct msghdr msg; + if (file->f_flags & O_NONBLOCK) + msg.msg_flags = MSG_DONTWAIT; - if (pos != 0) - return -ESPIPE; + if (sock->type == SOCK_SEQPACKET) + msg.msg_flags |= MSG_EOR; - return do_sock_write(&msg, iocb, iocb->ki_filp, iov, nr_segs); + res = __sock_sendmsg(iocb, sock, &msg, iocb->ki_nbytes); + *from = msg.msg_iter; + return res; } /* diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 22e02f4edd99..8c1e558db118 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -115,3 +115,113 @@ int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, return err; } EXPORT_SYMBOL(call_netdev_switch_notifiers); + +/** + * netdev_switch_port_bridge_setlink - Notify switch device port of bridge + * port attributes + * + * @dev: port device + * @nlh: netlink msg with bridge port attributes + * @flags: bridge setlink flags + * + * Notify switch device port of bridge port attributes + */ +int netdev_switch_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) + return 0; + + if (!ops->ndo_bridge_setlink) + return -EOPNOTSUPP; + + return ops->ndo_bridge_setlink(dev, nlh, flags); +} +EXPORT_SYMBOL(netdev_switch_port_bridge_setlink); + +/** + * netdev_switch_port_bridge_dellink - Notify switch device port of bridge + * port attribute delete + * + * @dev: port device + * @nlh: netlink msg with bridge port attributes + * @flags: bridge setlink flags + * + * Notify switch device port of bridge port attribute delete + */ +int netdev_switch_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) + return 0; + + if (!ops->ndo_bridge_dellink) + return -EOPNOTSUPP; + + return ops->ndo_bridge_dellink(dev, nlh, flags); +} +EXPORT_SYMBOL(netdev_switch_port_bridge_dellink); + +/** + * ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink + * op for master devices + * + * @dev: port device + * @nlh: netlink msg with bridge port attributes + * @flags: bridge setlink flags + * + * Notify master device slaves of bridge port attributes + */ +int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) +{ + struct net_device *lower_dev; + struct list_head *iter; + int ret = 0, err = 0; + + if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) + return ret; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = netdev_switch_port_bridge_setlink(lower_dev, nlh, flags); + if (err && err != -EOPNOTSUPP) + ret = err; + } + + return ret; +} +EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_setlink); + +/** + * ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink + * op for master devices + * + * @dev: port device + * @nlh: netlink msg with bridge port attributes + * @flags: bridge dellink flags + * + * Notify master device slaves of bridge port attribute deletes + */ +int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) +{ + struct net_device *lower_dev; + struct list_head *iter; + int ret = 0, err = 0; + + if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) + return ret; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = netdev_switch_port_bridge_dellink(lower_dev, nlh, flags); + if (err && err != -EOPNOTSUPP) + ret = err; + } + + return ret; +} +EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 53f8bf059fec..81b1fef1f5e0 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -1,7 +1,7 @@ /* * net/tipc/bcast.c: TIPC broadcast code * - * Copyright (c) 2004-2006, 2014, Ericsson AB + * Copyright (c) 2004-2006, 2014-2015, Ericsson AB * Copyright (c) 2004, Intel Corporation. * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. @@ -79,6 +79,13 @@ static void tipc_bclink_unlock(struct net *net) tipc_link_reset_all(node); } +void tipc_bclink_input(struct net *net) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + tipc_sk_mcast_rcv(net, &tn->bclink->arrvq, &tn->bclink->inputq); +} + uint tipc_bclink_get_mtu(void) { return MAX_PKT_DEFAULT_MCAST; @@ -189,10 +196,8 @@ static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) void tipc_bclink_wakeup_users(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct sk_buff *skb; - while ((skb = skb_dequeue(&tn->bclink->link.waiting_sks))) - tipc_sk_rcv(net, skb); + tipc_sk_rcv(net, &tn->bclink->link.wakeupq); } /** @@ -271,9 +276,8 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) tipc_link_push_packets(tn->bcl); bclink_set_last_sent(net); } - if (unlikely(released && !skb_queue_empty(&tn->bcl->waiting_sks))) + if (unlikely(released && !skb_queue_empty(&tn->bcl->wakeupq))) n_ptr->action_flags |= TIPC_WAKEUP_BCAST_USERS; - exit: tipc_bclink_unlock(net); } @@ -283,10 +287,11 @@ exit: * * RCU and node lock set */ -void tipc_bclink_update_link_state(struct net *net, struct tipc_node *n_ptr, +void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) { struct sk_buff *buf; + struct net *net = n_ptr->net; struct tipc_net *tn = net_generic(net, tipc_net_id); /* Ignore "stale" link state info */ @@ -317,7 +322,7 @@ void tipc_bclink_update_link_state(struct net *net, struct tipc_node *n_ptr, struct sk_buff *skb = skb_peek(&n_ptr->bclink.deferred_queue); u32 to = skb ? buf_seqno(skb) - 1 : n_ptr->bclink.last_sent; - tipc_msg_init(net, msg, BCAST_PROTOCOL, STATE_MSG, + tipc_msg_init(tn->own_addr, msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, n_ptr->addr); msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tn->net_id); @@ -358,7 +363,7 @@ static void bclink_peek_nack(struct net *net, struct tipc_msg *msg) tipc_node_unlock(n_ptr); } -/* tipc_bclink_xmit - broadcast buffer chain to all nodes in cluster +/* tipc_bclink_xmit - deliver buffer chain to all nodes in cluster * and to identified node local sockets * @net: the applicable net namespace * @list: chain of buffers containing message @@ -373,6 +378,8 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) int rc = 0; int bc = 0; struct sk_buff *skb; + struct sk_buff_head arrvq; + struct sk_buff_head inputq; /* Prepare clone of message for local node */ skb = tipc_msg_reassemble(list); @@ -381,7 +388,7 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) return -EHOSTUNREACH; } - /* Broadcast to all other nodes */ + /* Broadcast to all nodes */ if (likely(bclink)) { tipc_bclink_lock(net); if (likely(bclink->bcast_nodes.count)) { @@ -401,12 +408,15 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) if (unlikely(!bc)) __skb_queue_purge(list); - /* Deliver message clone */ - if (likely(!rc)) - tipc_sk_mcast_rcv(net, skb); - else + if (unlikely(rc)) { kfree_skb(skb); - + return rc; + } + /* Deliver message clone */ + __skb_queue_head_init(&arrvq); + skb_queue_head_init(&inputq); + __skb_queue_tail(&arrvq, skb); + tipc_sk_mcast_rcv(net, &arrvq, &inputq); return rc; } @@ -449,6 +459,9 @@ void tipc_bclink_rcv(struct net *net, struct sk_buff *buf) u32 next_in; u32 seqno; int deferred = 0; + int pos = 0; + struct sk_buff *iskb; + struct sk_buff_head *arrvq, *inputq; /* Screen out unwanted broadcast messages */ if (msg_mc_netid(msg) != tn->net_id) @@ -485,6 +498,8 @@ void tipc_bclink_rcv(struct net *net, struct sk_buff *buf) /* Handle in-sequence broadcast message */ seqno = msg_seqno(msg); next_in = mod(node->bclink.last_in + 1); + arrvq = &tn->bclink->arrvq; + inputq = &tn->bclink->inputq; if (likely(seqno == next_in)) { receive: @@ -492,20 +507,26 @@ receive: if (likely(msg_isdata(msg))) { tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); + spin_lock_bh(&inputq->lock); + __skb_queue_tail(arrvq, buf); + spin_unlock_bh(&inputq->lock); + node->action_flags |= TIPC_BCAST_MSG_EVT; tipc_bclink_unlock(net); tipc_node_unlock(node); - if (likely(msg_mcast(msg))) - tipc_sk_mcast_rcv(net, buf); - else - kfree_skb(buf); } else if (msg_user(msg) == MSG_BUNDLER) { tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); bcl->stats.recv_bundles++; bcl->stats.recv_bundled += msg_msgcnt(msg); + pos = 0; + while (tipc_msg_extract(buf, &iskb, &pos)) { + spin_lock_bh(&inputq->lock); + __skb_queue_tail(arrvq, iskb); + spin_unlock_bh(&inputq->lock); + } + node->action_flags |= TIPC_BCAST_MSG_EVT; tipc_bclink_unlock(net); tipc_node_unlock(node); - tipc_link_bundle_rcv(net, buf); } else if (msg_user(msg) == MSG_FRAGMENTER) { tipc_buf_append(&node->bclink.reasm_buf, &buf); if (unlikely(!buf && !node->bclink.reasm_buf)) @@ -521,12 +542,6 @@ receive: } tipc_bclink_unlock(net); tipc_node_unlock(node); - } else if (msg_user(msg) == NAME_DISTRIBUTOR) { - tipc_bclink_lock(net); - bclink_accept_pkt(node, seqno); - tipc_bclink_unlock(net); - tipc_node_unlock(node); - tipc_named_rcv(net, buf); } else { tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); @@ -943,10 +958,11 @@ int tipc_bclink_init(struct net *net) spin_lock_init(&bclink->lock); __skb_queue_head_init(&bcl->outqueue); __skb_queue_head_init(&bcl->deferred_queue); - skb_queue_head_init(&bcl->waiting_sks); + skb_queue_head_init(&bcl->wakeupq); bcl->next_out_no = 1; spin_lock_init(&bclink->node.lock); - __skb_queue_head_init(&bclink->node.waiting_sks); + __skb_queue_head_init(&bclink->arrvq); + skb_queue_head_init(&bclink->inputq); bcl->owner = &bclink->node; bcl->owner->net = net; bcl->max_pkt = MAX_PKT_DEFAULT_MCAST; @@ -954,6 +970,8 @@ int tipc_bclink_init(struct net *net) bcl->bearer_id = MAX_BEARERS; rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer); bcl->state = WORKING_WORKING; + bcl->pmsg = (struct tipc_msg *)&bcl->proto_msg; + msg_set_prevnode(bcl->pmsg, tn->own_addr); strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); tn->bcbearer = bcbearer; tn->bclink = bclink; @@ -1032,50 +1050,3 @@ static void tipc_nmap_diff(struct tipc_node_map *nm_a, } } } - -/** - * tipc_port_list_add - add a port to a port list, ensuring no duplicates - */ -void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port) -{ - struct tipc_port_list *item = pl_ptr; - int i; - int item_sz = PLSIZE; - int cnt = pl_ptr->count; - - for (; ; cnt -= item_sz, item = item->next) { - if (cnt < PLSIZE) - item_sz = cnt; - for (i = 0; i < item_sz; i++) - if (item->ports[i] == port) - return; - if (i < PLSIZE) { - item->ports[i] = port; - pl_ptr->count++; - return; - } - if (!item->next) { - item->next = kmalloc(sizeof(*item), GFP_ATOMIC); - if (!item->next) { - pr_warn("Incomplete multicast delivery, no memory\n"); - return; - } - item->next->next = NULL; - } - } -} - -/** - * tipc_port_list_free - free dynamically created entries in port_list chain - * - */ -void tipc_port_list_free(struct tipc_port_list *pl_ptr) -{ - struct tipc_port_list *item; - struct tipc_port_list *next; - - for (item = pl_ptr->next; item; item = next) { - next = item->next; - kfree(item); - } -} diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index a4583a109486..a910c0b9f249 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -1,7 +1,7 @@ /* * net/tipc/bcast.h: Include file for TIPC broadcast code * - * Copyright (c) 2003-2006, 2014, Ericsson AB + * Copyright (c) 2003-2006, 2014-2015, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -41,22 +41,6 @@ #include "link.h" #include "node.h" -#define TIPC_BCLINK_RESET 1 -#define PLSIZE 32 -#define BCBEARER MAX_BEARERS - -/** - * struct tipc_port_list - set of node local destination ports - * @count: # of ports in set (only valid for first entry in list) - * @next: pointer to next entry in list - * @ports: array of port references - */ -struct tipc_port_list { - int count; - struct tipc_port_list *next; - u32 ports[PLSIZE]; -}; - /** * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link * @primary: pointer to primary bearer @@ -71,6 +55,9 @@ struct tipc_bcbearer_pair { struct tipc_bearer *secondary; }; +#define TIPC_BCLINK_RESET 1 +#define BCBEARER MAX_BEARERS + /** * struct tipc_bcbearer - bearer used by broadcast link * @bearer: (non-standard) broadcast bearer structure @@ -110,6 +97,8 @@ struct tipc_bclink { struct tipc_link link; struct tipc_node node; unsigned int flags; + struct sk_buff_head arrvq; + struct sk_buff_head inputq; struct tipc_node_map bcast_nodes; struct tipc_node *retransmit_to; }; @@ -126,9 +115,6 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, return !memcmp(nm_a, nm_b, sizeof(*nm_a)); } -void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port); -void tipc_port_list_free(struct tipc_port_list *pl_ptr); - int tipc_bclink_init(struct net *net); void tipc_bclink_stop(struct net *net); void tipc_bclink_set_flags(struct net *tn, unsigned int flags); @@ -139,7 +125,7 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked); void tipc_bclink_rcv(struct net *net, struct sk_buff *buf); u32 tipc_bclink_get_last_sent(struct net *net); u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr); -void tipc_bclink_update_link_state(struct net *net, struct tipc_node *n_ptr, +void tipc_bclink_update_link_state(struct tipc_node *node, u32 last_sent); int tipc_bclink_stats(struct net *net, char *stats_buf, const u32 buf_size); int tipc_bclink_reset_stats(struct net *net); @@ -150,5 +136,6 @@ uint tipc_bclink_get_mtu(void); int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list); void tipc_bclink_wakeup_users(struct net *net); int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); +void tipc_bclink_input(struct net *net); #endif diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 5b40cb89ff0a..feef3753615d 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -1,7 +1,7 @@ /* * net/tipc/discover.c * - * Copyright (c) 2003-2006, 2014, Ericsson AB + * Copyright (c) 2003-2006, 2014-2015, Ericsson AB * Copyright (c) 2005-2006, 2010-2011, Wind River Systems * All rights reserved. * @@ -47,7 +47,6 @@ /* indicates no timer in use */ #define TIPC_LINK_REQ_INACTIVE 0xffffffff - /** * struct tipc_link_req - information about an ongoing link setup request * @bearer_id: identity of bearer issuing requests @@ -86,7 +85,8 @@ static void tipc_disc_init_msg(struct net *net, struct sk_buff *buf, u32 type, u32 dest_domain = b_ptr->domain; msg = buf_msg(buf); - tipc_msg_init(net, msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain); + tipc_msg_init(tn->own_addr, msg, LINK_CONFIG, type, + INT_H_SIZE, dest_domain); msg_set_non_seq(msg, 1); msg_set_node_sig(msg, tn->random); msg_set_dest_domain(msg, dest_domain); @@ -163,13 +163,9 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, if (!tipc_in_scope(bearer->domain, onode)) return; - /* Locate, or if necessary, create, node: */ - node = tipc_node_find(net, onode); - if (!node) - node = tipc_node_create(net, onode); + node = tipc_node_create(net, onode); if (!node) return; - tipc_node_lock(node); link = node->links[bearer->identity]; diff --git a/net/tipc/link.c b/net/tipc/link.c index 2846ad802e43..942491234099 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -101,23 +101,20 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { */ #define START_CHANGEOVER 100000u -static void link_handle_out_of_seq_msg(struct net *net, - struct tipc_link *l_ptr, - struct sk_buff *buf); -static void tipc_link_proto_rcv(struct net *net, struct tipc_link *l_ptr, - struct sk_buff *buf); -static int tipc_link_tunnel_rcv(struct net *net, struct tipc_node *n_ptr, - struct sk_buff **buf); +static void link_handle_out_of_seq_msg(struct tipc_link *link, + struct sk_buff *skb); +static void tipc_link_proto_rcv(struct tipc_link *link, + struct sk_buff *skb); +static int tipc_link_tunnel_rcv(struct tipc_node *node, + struct sk_buff **skb); static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); static void tipc_link_sync_xmit(struct tipc_link *l); static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); -static int tipc_link_input(struct net *net, struct tipc_link *l, - struct sk_buff *buf); -static int tipc_link_prepare_input(struct net *net, struct tipc_link *l, - struct sk_buff **buf); +static void tipc_link_input(struct tipc_link *l, struct sk_buff *skb); +static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb); /* * Simple link routines @@ -127,6 +124,21 @@ static unsigned int align(unsigned int i) return (i + 3) & ~3u; } +static void tipc_link_release(struct kref *kref) +{ + kfree(container_of(kref, struct tipc_link, ref)); +} + +static void tipc_link_get(struct tipc_link *l_ptr) +{ + kref_get(&l_ptr->ref); +} + +static void tipc_link_put(struct tipc_link *l_ptr) +{ + kref_put(&l_ptr->ref, tipc_link_release); +} + static void link_init_max_pkt(struct tipc_link *l_ptr) { struct tipc_node *node = l_ptr->owner; @@ -222,11 +234,13 @@ static void link_timeout(unsigned long data) tipc_link_push_packets(l_ptr); tipc_node_unlock(l_ptr->owner); + tipc_link_put(l_ptr); } static void link_set_timer(struct tipc_link *link, unsigned long time) { - mod_timer(&link->timer, jiffies + time); + if (!mod_timer(&link->timer, jiffies + time)) + tipc_link_get(link); } /** @@ -267,7 +281,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, pr_warn("Link creation failed, no memory\n"); return NULL; } - + kref_init(&l_ptr->ref); l_ptr->addr = peer; if_name = strchr(b_ptr->name, ':') + 1; sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown", @@ -286,7 +300,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; msg = l_ptr->pmsg; - tipc_msg_init(n_ptr->net, msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, + tipc_msg_init(tn->own_addr, msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, l_ptr->addr); msg_set_size(msg, sizeof(l_ptr->proto_msg)); msg_set_session(msg, (tn->random & 0xffff)); @@ -302,49 +316,52 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, l_ptr->next_out_no = 1; __skb_queue_head_init(&l_ptr->outqueue); __skb_queue_head_init(&l_ptr->deferred_queue); - skb_queue_head_init(&l_ptr->waiting_sks); - + skb_queue_head_init(&l_ptr->wakeupq); + skb_queue_head_init(&l_ptr->inputq); + skb_queue_head_init(&l_ptr->namedq); link_reset_statistics(l_ptr); - tipc_node_attach_link(n_ptr, l_ptr); - setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr); - link_state_event(l_ptr, STARTING_EVT); return l_ptr; } +/** + * link_delete - Conditional deletion of link. + * If timer still running, real delete is done when it expires + * @link: link to be deleted + */ +void tipc_link_delete(struct tipc_link *link) +{ + tipc_link_reset_fragments(link); + tipc_node_detach_link(link->owner, link); + tipc_link_put(link); +} + void tipc_link_delete_list(struct net *net, unsigned int bearer_id, bool shutting_down) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_link *l_ptr; - struct tipc_node *n_ptr; + struct tipc_link *link; + struct tipc_node *node; rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { - tipc_node_lock(n_ptr); - l_ptr = n_ptr->links[bearer_id]; - if (l_ptr) { - tipc_link_reset(l_ptr); - if (shutting_down || !tipc_node_is_up(n_ptr)) { - tipc_node_detach_link(l_ptr->owner, l_ptr); - tipc_link_reset_fragments(l_ptr); - tipc_node_unlock(n_ptr); - - /* Nobody else can access this link now: */ - del_timer_sync(&l_ptr->timer); - kfree(l_ptr); - } else { - /* Detach/delete when failover is finished: */ - l_ptr->flags |= LINK_STOPPED; - tipc_node_unlock(n_ptr); - del_timer_sync(&l_ptr->timer); - } + list_for_each_entry_rcu(node, &tn->node_list, list) { + tipc_node_lock(node); + link = node->links[bearer_id]; + if (!link) { + tipc_node_unlock(node); continue; } - tipc_node_unlock(n_ptr); + tipc_link_reset(link); + if (del_timer(&link->timer)) + tipc_link_put(link); + link->flags |= LINK_STOPPED; + /* Delete link now, or when failover is finished: */ + if (shutting_down || !tipc_node_is_up(node)) + tipc_link_delete(link); + tipc_node_unlock(node); } rcu_read_unlock(); } @@ -360,17 +377,16 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id, static bool link_schedule_user(struct tipc_link *link, u32 oport, uint chain_sz, uint imp) { - struct net *net = link->owner->net; - struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *buf; - buf = tipc_msg_create(net, SOCK_WAKEUP, 0, INT_H_SIZE, 0, tn->own_addr, - tn->own_addr, oport, 0, 0); + buf = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, + link_own_addr(link), link_own_addr(link), + oport, 0, 0); if (!buf) return false; TIPC_SKB_CB(buf)->chain_sz = chain_sz; TIPC_SKB_CB(buf)->chain_imp = imp; - skb_queue_tail(&link->waiting_sks, buf); + skb_queue_tail(&link->wakeupq, buf); link->stats.link_congs++; return true; } @@ -381,17 +397,19 @@ static bool link_schedule_user(struct tipc_link *link, u32 oport, * Move a number of waiting users, as permitted by available space in * the send queue, from link wait queue to node wait queue for wakeup */ -static void link_prepare_wakeup(struct tipc_link *link) +void link_prepare_wakeup(struct tipc_link *link) { uint pend_qsz = skb_queue_len(&link->outqueue); struct sk_buff *skb, *tmp; - skb_queue_walk_safe(&link->waiting_sks, skb, tmp) { + skb_queue_walk_safe(&link->wakeupq, skb, tmp) { if (pend_qsz >= link->queue_limit[TIPC_SKB_CB(skb)->chain_imp]) break; pend_qsz += TIPC_SKB_CB(skb)->chain_sz; - skb_unlink(skb, &link->waiting_sks); - skb_queue_tail(&link->owner->waiting_sks, skb); + skb_unlink(skb, &link->wakeupq); + skb_queue_tail(&link->inputq, skb); + link->owner->inputq = &link->inputq; + link->owner->action_flags |= TIPC_MSG_EVT; } } @@ -444,13 +462,13 @@ void tipc_link_reset(struct tipc_link *l_ptr) l_ptr->exp_msg_count = START_CHANGEOVER; } - /* Clean up all queues: */ + /* Clean up all queues, except inputq: */ __skb_queue_purge(&l_ptr->outqueue); __skb_queue_purge(&l_ptr->deferred_queue); - if (!skb_queue_empty(&l_ptr->waiting_sks)) { - skb_queue_splice_init(&l_ptr->waiting_sks, &owner->waiting_sks); - owner->action_flags |= TIPC_WAKEUP_USERS; - } + skb_queue_splice_init(&l_ptr->wakeupq, &l_ptr->inputq); + if (!skb_queue_empty(&l_ptr->inputq)) + owner->action_flags |= TIPC_MSG_EVT; + owner->inputq = &l_ptr->inputq; l_ptr->next_out = NULL; l_ptr->unacked_window = 0; l_ptr->checkpoint = 1; @@ -630,7 +648,9 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) break; case STARTING_EVT: l_ptr->flags |= LINK_STARTED; - /* fall through */ + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; case TIMEOUT_EVT: tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; @@ -757,7 +777,7 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, } else if (tipc_msg_bundle(outqueue, skb, mtu)) { link->stats.sent_bundled++; continue; - } else if (tipc_msg_make_bundle(net, outqueue, skb, mtu, + } else if (tipc_msg_make_bundle(outqueue, skb, mtu, link->addr)) { link->stats.sent_bundled++; link->stats.sent_bundles++; @@ -776,7 +796,7 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, static void skb2list(struct sk_buff *skb, struct sk_buff_head *list) { - __skb_queue_head_init(list); + skb_queue_head_init(list); __skb_queue_tail(list, skb); } @@ -822,19 +842,13 @@ int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, rc = __tipc_link_xmit(net, link, list); tipc_node_unlock(node); } - if (link) return rc; - if (likely(in_own_node(net, dnode))) { - /* As a node local message chain never contains more than one - * buffer, we just need to dequeue one SKB buffer from the - * head list. - */ - return tipc_sk_rcv(net, __skb_dequeue(list)); - } - __skb_queue_purge(list); + if (likely(in_own_node(net, dnode))) + return tipc_sk_rcv(net, list); + __skb_queue_purge(list); return rc; } @@ -856,7 +870,7 @@ static void tipc_link_sync_xmit(struct tipc_link *link) return; msg = buf_msg(skb); - tipc_msg_init(link->owner->net, msg, BCAST_PROTOCOL, STATE_MSG, + tipc_msg_init(link_own_addr(link), msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, link->addr); msg_set_last_bcast(msg, link->owner->bclink.acked); __tipc_link_xmit_skb(link, skb); @@ -1143,7 +1157,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) /* Locate unicast link endpoint that should handle message */ l_ptr = n_ptr->links[b_ptr->identity]; if (unlikely(!l_ptr)) - goto unlock_discard; + goto unlock; /* Verify that communication with node is currently allowed */ if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) && @@ -1154,7 +1168,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN; if (tipc_node_blocked(n_ptr)) - goto unlock_discard; + goto unlock; /* Validate message sequence number info */ seq_no = msg_seqno(msg); @@ -1178,18 +1192,16 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) if (unlikely(l_ptr->next_out)) tipc_link_push_packets(l_ptr); - if (released && !skb_queue_empty(&l_ptr->waiting_sks)) { + if (released && !skb_queue_empty(&l_ptr->wakeupq)) link_prepare_wakeup(l_ptr); - l_ptr->owner->action_flags |= TIPC_WAKEUP_USERS; - } /* Process the incoming packet */ if (unlikely(!link_working_working(l_ptr))) { if (msg_user(msg) == LINK_PROTOCOL) { - tipc_link_proto_rcv(net, l_ptr, skb); + tipc_link_proto_rcv(l_ptr, skb); link_retrieve_defq(l_ptr, &head); - tipc_node_unlock(n_ptr); - continue; + skb = NULL; + goto unlock; } /* Traffic message. Conditionally activate link */ @@ -1198,18 +1210,18 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) if (link_working_working(l_ptr)) { /* Re-insert buffer in front of queue */ __skb_queue_head(&head, skb); - tipc_node_unlock(n_ptr); - continue; + skb = NULL; + goto unlock; } - goto unlock_discard; + goto unlock; } /* Link is now in state WORKING_WORKING */ if (unlikely(seq_no != mod(l_ptr->next_in_no))) { - link_handle_out_of_seq_msg(net, l_ptr, skb); + link_handle_out_of_seq_msg(l_ptr, skb); link_retrieve_defq(l_ptr, &head); - tipc_node_unlock(n_ptr); - continue; + skb = NULL; + goto unlock; } l_ptr->next_in_no++; if (unlikely(!skb_queue_empty(&l_ptr->deferred_queue))) @@ -1219,97 +1231,102 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) l_ptr->stats.sent_acks++; tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } - - if (tipc_link_prepare_input(net, l_ptr, &skb)) { - tipc_node_unlock(n_ptr); - continue; - } - tipc_node_unlock(n_ptr); - - if (tipc_link_input(net, l_ptr, skb) != 0) - goto discard; - continue; -unlock_discard: + tipc_link_input(l_ptr, skb); + skb = NULL; +unlock: tipc_node_unlock(n_ptr); discard: - kfree_skb(skb); + if (unlikely(skb)) + kfree_skb(skb); } } -/** - * tipc_link_prepare_input - process TIPC link messages - * - * returns nonzero if the message was consumed +/* tipc_data_input - deliver data and name distr msgs to upper layer * + * Consumes buffer if message is of right type * Node lock must be held */ -static int tipc_link_prepare_input(struct net *net, struct tipc_link *l, - struct sk_buff **buf) +static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) { - struct tipc_node *n; - struct tipc_msg *msg; - int res = -EINVAL; + struct tipc_node *node = link->owner; + struct tipc_msg *msg = buf_msg(skb); + u32 dport = msg_destport(msg); - n = l->owner; - msg = buf_msg(*buf); switch (msg_user(msg)) { - case CHANGEOVER_PROTOCOL: - if (tipc_link_tunnel_rcv(net, n, buf)) - res = 0; - break; - case MSG_FRAGMENTER: - l->stats.recv_fragments++; - if (tipc_buf_append(&l->reasm_buf, buf)) { - l->stats.recv_fragmented++; - res = 0; - } else if (!l->reasm_buf) { - tipc_link_reset(l); + case TIPC_LOW_IMPORTANCE: + case TIPC_MEDIUM_IMPORTANCE: + case TIPC_HIGH_IMPORTANCE: + case TIPC_CRITICAL_IMPORTANCE: + case CONN_MANAGER: + if (tipc_skb_queue_tail(&link->inputq, skb, dport)) { + node->inputq = &link->inputq; + node->action_flags |= TIPC_MSG_EVT; } - break; - case MSG_BUNDLER: - l->stats.recv_bundles++; - l->stats.recv_bundled += msg_msgcnt(msg); - res = 0; - break; + return true; case NAME_DISTRIBUTOR: - n->bclink.recv_permitted = true; - res = 0; - break; + node->bclink.recv_permitted = true; + node->namedq = &link->namedq; + skb_queue_tail(&link->namedq, skb); + if (skb_queue_len(&link->namedq) == 1) + node->action_flags |= TIPC_NAMED_MSG_EVT; + return true; + case MSG_BUNDLER: + case CHANGEOVER_PROTOCOL: + case MSG_FRAGMENTER: case BCAST_PROTOCOL: - tipc_link_sync_rcv(n, *buf); - break; + return false; default: - res = 0; - } - return res; + pr_warn("Dropping received illegal msg type\n"); + kfree_skb(skb); + return false; + }; } -/** - * tipc_link_input - Deliver message too higher layers + +/* tipc_link_input - process packet that has passed link protocol check + * + * Consumes buffer + * Node lock must be held */ -static int tipc_link_input(struct net *net, struct tipc_link *l, - struct sk_buff *buf) +static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) { - struct tipc_msg *msg = buf_msg(buf); - int res = 0; + struct tipc_node *node = link->owner; + struct tipc_msg *msg = buf_msg(skb); + struct sk_buff *iskb; + int pos = 0; + + if (likely(tipc_data_input(link, skb))) + return; switch (msg_user(msg)) { - case TIPC_LOW_IMPORTANCE: - case TIPC_MEDIUM_IMPORTANCE: - case TIPC_HIGH_IMPORTANCE: - case TIPC_CRITICAL_IMPORTANCE: - case CONN_MANAGER: - tipc_sk_rcv(net, buf); + case CHANGEOVER_PROTOCOL: + if (!tipc_link_tunnel_rcv(node, &skb)) + break; + if (msg_user(buf_msg(skb)) != MSG_BUNDLER) { + tipc_data_input(link, skb); + break; + } + case MSG_BUNDLER: + link->stats.recv_bundles++; + link->stats.recv_bundled += msg_msgcnt(msg); + + while (tipc_msg_extract(skb, &iskb, &pos)) + tipc_data_input(link, iskb); break; - case NAME_DISTRIBUTOR: - tipc_named_rcv(net, buf); + case MSG_FRAGMENTER: + link->stats.recv_fragments++; + if (tipc_buf_append(&link->reasm_buf, &skb)) { + link->stats.recv_fragmented++; + tipc_data_input(link, skb); + } else if (!link->reasm_buf) { + tipc_link_reset(link); + } break; - case MSG_BUNDLER: - tipc_link_bundle_rcv(net, buf); + case BCAST_PROTOCOL: + tipc_link_sync_rcv(node, skb); break; default: - res = -EINVAL; - } - return res; + break; + }; } /** @@ -1354,14 +1371,13 @@ u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) /* * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet */ -static void link_handle_out_of_seq_msg(struct net *net, - struct tipc_link *l_ptr, +static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, struct sk_buff *buf) { u32 seq_no = buf_seqno(buf); if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - tipc_link_proto_rcv(net, l_ptr, buf); + tipc_link_proto_rcv(l_ptr, buf); return; } @@ -1486,10 +1502,9 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, * Note that network plane id propagates through the network, and may * change at any time. The node with lowest address rules */ -static void tipc_link_proto_rcv(struct net *net, struct tipc_link *l_ptr, +static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) { - struct tipc_net *tn = net_generic(net, tipc_net_id); u32 rec_gap = 0; u32 max_pkt_info; u32 max_pkt_ack; @@ -1501,7 +1516,7 @@ static void tipc_link_proto_rcv(struct net *net, struct tipc_link *l_ptr, goto exit; if (l_ptr->net_plane != msg_net_plane(msg)) - if (tn->own_addr > msg_prevnode(msg)) + if (link_own_addr(l_ptr) > msg_prevnode(msg)) l_ptr->net_plane = msg_net_plane(msg); switch (msg_type(msg)) { @@ -1604,7 +1619,7 @@ static void tipc_link_proto_rcv(struct net *net, struct tipc_link *l_ptr, /* Protocol message before retransmits, reduce loss risk */ if (l_ptr->owner->bclink.recv_permitted) - tipc_bclink_update_link_state(net, l_ptr->owner, + tipc_bclink_update_link_state(l_ptr->owner, msg_last_bcast(msg)); if (rec_gap || (msg_probe(msg))) { @@ -1669,7 +1684,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) if (!tunnel) return; - tipc_msg_init(l_ptr->owner->net, &tunnel_hdr, CHANGEOVER_PROTOCOL, + tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, CHANGEOVER_PROTOCOL, ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); msg_set_msgcnt(&tunnel_hdr, msgcount); @@ -1727,7 +1742,7 @@ void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct sk_buff *skb; struct tipc_msg tunnel_hdr; - tipc_msg_init(l_ptr->owner->net, &tunnel_hdr, CHANGEOVER_PROTOCOL, + tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, CHANGEOVER_PROTOCOL, DUPLICATE_MSG, INT_H_SIZE, l_ptr->addr); msg_set_msgcnt(&tunnel_hdr, skb_queue_len(&l_ptr->outqueue)); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); @@ -1762,7 +1777,7 @@ void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, * @from_pos: offset to extract from * * Returns a new message buffer containing an embedded message. The - * encapsulating message itself is left unchanged. + * encapsulating buffer is left unchanged. */ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) { @@ -1776,12 +1791,10 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) return eb; } - - /* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet. * Owner node is locked. */ -static void tipc_link_dup_rcv(struct net *net, struct tipc_link *l_ptr, +static void tipc_link_dup_rcv(struct tipc_link *l_ptr, struct sk_buff *t_buf) { struct sk_buff *buf; @@ -1796,7 +1809,7 @@ static void tipc_link_dup_rcv(struct net *net, struct tipc_link *l_ptr, } /* Add buffer to deferred queue, if applicable: */ - link_handle_out_of_seq_msg(net, l_ptr, buf); + link_handle_out_of_seq_msg(l_ptr, buf); } /* tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet @@ -1837,10 +1850,8 @@ static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr, } } exit: - if ((l_ptr->exp_msg_count == 0) && (l_ptr->flags & LINK_STOPPED)) { - tipc_node_detach_link(l_ptr->owner, l_ptr); - kfree(l_ptr); - } + if ((!l_ptr->exp_msg_count) && (l_ptr->flags & LINK_STOPPED)) + tipc_link_delete(l_ptr); return buf; } @@ -1850,7 +1861,7 @@ exit: * returned to the active link for delivery upwards. * Owner node is locked. */ -static int tipc_link_tunnel_rcv(struct net *net, struct tipc_node *n_ptr, +static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, struct sk_buff **buf) { struct sk_buff *t_buf = *buf; @@ -1868,7 +1879,7 @@ static int tipc_link_tunnel_rcv(struct net *net, struct tipc_node *n_ptr, goto exit; if (msg_type(t_msg) == DUPLICATE_MSG) - tipc_link_dup_rcv(net, l_ptr, t_buf); + tipc_link_dup_rcv(l_ptr, t_buf); else if (msg_type(t_msg) == ORIGINAL_MSG) *buf = tipc_link_failover_rcv(l_ptr, t_buf); else @@ -1878,41 +1889,6 @@ exit: return *buf != NULL; } -/* - * Bundler functionality: - */ -void tipc_link_bundle_rcv(struct net *net, struct sk_buff *buf) -{ - u32 msgcount = msg_msgcnt(buf_msg(buf)); - u32 pos = INT_H_SIZE; - struct sk_buff *obuf; - struct tipc_msg *omsg; - - while (msgcount--) { - obuf = buf_extract(buf, pos); - if (obuf == NULL) { - pr_warn("Link unable to unbundle message(s)\n"); - break; - } - omsg = buf_msg(obuf); - pos += align(msg_size(omsg)); - if (msg_isdata(omsg)) { - if (unlikely(msg_type(omsg) == TIPC_MCAST_MSG)) - tipc_sk_mcast_rcv(net, obuf); - else - tipc_sk_rcv(net, obuf); - } else if (msg_user(omsg) == CONN_MANAGER) { - tipc_sk_rcv(net, obuf); - } else if (msg_user(omsg) == NAME_DISTRIBUTOR) { - tipc_named_rcv(net, obuf); - } else { - pr_warn("Illegal bundled msg: %u\n", msg_user(omsg)); - kfree_skb(obuf); - } - } - kfree_skb(buf); -} - static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) { unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; diff --git a/net/tipc/link.h b/net/tipc/link.h index 9df7fa4d3bdd..34d3f55c4cea 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -103,6 +103,7 @@ struct tipc_stats { * @media_addr: media address to use when sending messages over link * @timer: link timer * @owner: pointer to peer node + * @refcnt: reference counter for permanent references (owner node & timer) * @flags: execution state flags for link endpoint instance * @checkpoint: reference point for triggering link continuity checking * @peer_session: link session # being used by peer end of link @@ -130,8 +131,10 @@ struct tipc_stats { * @next_in_no: next sequence number to expect for inbound messages * @deferred_queue: deferred queue saved OOS b'cast message received from node * @unacked_window: # of inbound messages rx'd without ack'ing back to peer + * @inputq: buffer queue for messages to be delivered upwards + * @namedq: buffer queue for name table messages to be delivered upwards * @next_out: ptr to first unsent outbound message in queue - * @waiting_sks: linked list of sockets waiting for link congestion to abate + * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate * @long_msg_seq_no: next identifier to use for outbound fragmented messages * @reasm_buf: head of partially reassembled inbound message fragments * @stats: collects statistics regarding link activity @@ -142,6 +145,7 @@ struct tipc_link { struct tipc_media_addr media_addr; struct timer_list timer; struct tipc_node *owner; + struct kref ref; /* Management and link supervision data */ unsigned int flags; @@ -182,10 +186,12 @@ struct tipc_link { u32 next_in_no; struct sk_buff_head deferred_queue; u32 unacked_window; + struct sk_buff_head inputq; + struct sk_buff_head namedq; /* Congestion handling */ struct sk_buff *next_out; - struct sk_buff_head waiting_sks; + struct sk_buff_head wakeupq; /* Fragmentation/reassembly */ u32 long_msg_seq_no; @@ -200,6 +206,7 @@ struct tipc_port; struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr); +void tipc_link_delete(struct tipc_link *link); void tipc_link_delete_list(struct net *net, unsigned int bearer_id, bool shutting_down); void tipc_link_failover_send_queue(struct tipc_link *l_ptr); @@ -225,7 +232,6 @@ int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, u32 selector); int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list); -void tipc_link_bundle_rcv(struct net *net, struct sk_buff *buf); void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, u32 gap, u32 tolerance, u32 priority, u32 acked_mtu); void tipc_link_push_packets(struct tipc_link *l_ptr); @@ -241,6 +247,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]); +void link_prepare_wakeup(struct tipc_link *l); /* * Link sequence number manipulation routines (uses modulo 2**16 arithmetic) @@ -275,6 +282,10 @@ static inline u32 lesser(u32 left, u32 right) return less_eq(left, right) ? left : right; } +static inline u32 link_own_addr(struct tipc_link *l) +{ + return msg_prevnode(l->pmsg); +} /* * Link status checking routines diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 18aba9e99345..b6eb90cd3ef7 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -70,25 +70,23 @@ struct sk_buff *tipc_buf_acquire(u32 size) return skb; } -void tipc_msg_init(struct net *net, struct tipc_msg *m, u32 user, u32 type, - u32 hsize, u32 destnode) +void tipc_msg_init(u32 own_node, struct tipc_msg *m, u32 user, u32 type, + u32 hsize, u32 dnode) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - memset(m, 0, hsize); msg_set_version(m); msg_set_user(m, user); msg_set_hdr_sz(m, hsize); msg_set_size(m, hsize); - msg_set_prevnode(m, tn->own_addr); + msg_set_prevnode(m, own_node); msg_set_type(m, type); if (hsize > SHORT_H_SIZE) { - msg_set_orignode(m, tn->own_addr); - msg_set_destnode(m, destnode); + msg_set_orignode(m, own_node); + msg_set_destnode(m, dnode); } } -struct sk_buff *tipc_msg_create(struct net *net, uint user, uint type, +struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode) { @@ -100,9 +98,8 @@ struct sk_buff *tipc_msg_create(struct net *net, uint user, uint type, return NULL; msg = buf_msg(buf); - tipc_msg_init(net, msg, user, type, hdr_sz, dnode); + tipc_msg_init(onode, msg, user, type, hdr_sz, dnode); msg_set_size(msg, hdr_sz + data_sz); - msg_set_prevnode(msg, onode); msg_set_origport(msg, oport); msg_set_destport(msg, dport); msg_set_errcode(msg, errcode); @@ -189,14 +186,13 @@ err: * tipc_msg_build - create buffer chain containing specified header and data * @mhdr: Message header, to be prepended to data * @m: User message - * @offset: Posision in iov to start copying from * @dsz: Total length of user data * @pktmax: Max packet size that can be used * @list: Buffer or chain of buffers to be returned to caller * * Returns message data size or errno: -ENOMEM, -EFAULT */ -int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m, +int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int pktmax, struct sk_buff_head *list) { int mhsz = msg_hdr_sz(mhdr); @@ -221,16 +217,15 @@ int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m, __skb_queue_tail(list, skb); skb_copy_to_linear_data(skb, mhdr, mhsz); pktpos = skb->data + mhsz; - if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, - dsz)) + if (copy_from_iter(pktpos, dsz, &m->msg_iter) == dsz) return dsz; rc = -EFAULT; goto error; } /* Prepare reusable fragment header */ - tipc_msg_init(net, &pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, - msg_destnode(mhdr)); + tipc_msg_init(msg_prevnode(mhdr), &pkthdr, MSG_FRAGMENTER, + FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr)); msg_set_size(&pkthdr, pktmax); msg_set_fragm_no(&pkthdr, pktno); @@ -252,12 +247,11 @@ int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m, if (drem < pktrem) pktrem = drem; - if (memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, pktrem)) { + if (copy_from_iter(pktpos, pktrem, &m->msg_iter) != pktrem) { rc = -EFAULT; goto error; } drem -= pktrem; - offset += pktrem; if (!drem) break; @@ -333,6 +327,40 @@ bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu) } /** + * tipc_msg_extract(): extract bundled inner packet from buffer + * @skb: linear outer buffer, to be extracted from. + * @iskb: extracted inner buffer, to be returned + * @pos: position of msg to be extracted. Returns with pointer of next msg + * Consumes outer buffer when last packet extracted + * Returns true when when there is an extracted buffer, otherwise false + */ +bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) +{ + struct tipc_msg *msg = buf_msg(skb); + int imsz; + struct tipc_msg *imsg = (struct tipc_msg *)(msg_data(msg) + *pos); + + /* Is there space left for shortest possible message? */ + if (*pos > (msg_data_sz(msg) - SHORT_H_SIZE)) + goto none; + imsz = msg_size(imsg); + + /* Is there space left for current message ? */ + if ((*pos + imsz) > msg_data_sz(msg)) + goto none; + *iskb = tipc_buf_acquire(imsz); + if (!*iskb) + goto none; + skb_copy_to_linear_data(*iskb, imsg, imsz); + *pos += align(imsz); + return true; +none: + kfree_skb(skb); + *iskb = NULL; + return false; +} + +/** * tipc_msg_make_bundle(): Create bundle buf and append message to its tail * @list: the buffer chain * @skb: buffer to be appended and replaced @@ -341,7 +369,7 @@ bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu) * Replaces buffer if successful * Returns true if success, otherwise false */ -bool tipc_msg_make_bundle(struct net *net, struct sk_buff_head *list, +bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu, u32 dnode) { struct sk_buff *bskb; @@ -365,7 +393,8 @@ bool tipc_msg_make_bundle(struct net *net, struct sk_buff_head *list, skb_trim(bskb, INT_H_SIZE); bmsg = buf_msg(bskb); - tipc_msg_init(net, bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode); + tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0, + INT_H_SIZE, dnode); msg_set_seqno(bmsg, msg_seqno(msg)); msg_set_ack(bmsg, msg_ack(msg)); msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); @@ -382,10 +411,9 @@ bool tipc_msg_make_bundle(struct net *net, struct sk_buff_head *list, * Consumes buffer if failure * Returns true if success, otherwise false */ -bool tipc_msg_reverse(struct net *net, struct sk_buff *buf, u32 *dnode, +bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, int err) { - struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_msg *msg = buf_msg(buf); uint imp = msg_importance(msg); struct tipc_msg ohdr; @@ -405,7 +433,7 @@ bool tipc_msg_reverse(struct net *net, struct sk_buff *buf, u32 *dnode, msg_set_errcode(msg, err); msg_set_origport(msg, msg_destport(&ohdr)); msg_set_destport(msg, msg_origport(&ohdr)); - msg_set_prevnode(msg, tn->own_addr); + msg_set_prevnode(msg, own_addr); if (!msg_short(msg)) { msg_set_orignode(msg, msg_destnode(&ohdr)); msg_set_destnode(msg, msg_orignode(&ohdr)); @@ -417,43 +445,43 @@ bool tipc_msg_reverse(struct net *net, struct sk_buff *buf, u32 *dnode, return true; exit: kfree_skb(buf); + *dnode = 0; return false; } /** - * tipc_msg_eval: determine fate of message that found no destination - * @buf: the buffer containing the message. - * @dnode: return value: next-hop node, if message to be forwarded - * @err: error code to use, if message to be rejected - * + * tipc_msg_lookup_dest(): try to find new destination for named message + * @skb: the buffer containing the message. + * @dnode: return value: next-hop node, if destination found + * @err: return value: error code to use, if message to be rejected * Does not consume buffer - * Returns 0 (TIPC_OK) if message ok and we can try again, -TIPC error - * code if message to be rejected + * Returns true if a destination is found, false otherwise */ -int tipc_msg_eval(struct net *net, struct sk_buff *buf, u32 *dnode) +bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, + u32 *dnode, int *err) { - struct tipc_msg *msg = buf_msg(buf); + struct tipc_msg *msg = buf_msg(skb); u32 dport; - if (msg_type(msg) != TIPC_NAMED_MSG) - return -TIPC_ERR_NO_PORT; - if (skb_linearize(buf)) - return -TIPC_ERR_NO_NAME; - if (msg_data_sz(msg) > MAX_FORWARD_SIZE) - return -TIPC_ERR_NO_NAME; + if (!msg_isdata(msg)) + return false; + if (!msg_named(msg)) + return false; + *err = -TIPC_ERR_NO_NAME; + if (skb_linearize(skb)) + return false; if (msg_reroute_cnt(msg) > 0) - return -TIPC_ERR_NO_NAME; - + return false; *dnode = addr_domain(net, msg_lookup_scope(msg)); dport = tipc_nametbl_translate(net, msg_nametype(msg), - msg_nameinst(msg), - dnode); + msg_nameinst(msg), dnode); if (!dport) - return -TIPC_ERR_NO_NAME; + return false; msg_incr_reroute_cnt(msg); msg_set_destnode(msg, *dnode); msg_set_destport(msg, dport); - return TIPC_OK; + *err = TIPC_OK; + return true; } /* tipc_msg_reassemble() - clone a buffer chain of fragments and diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 526ef345b70e..9ace47f44a69 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -45,6 +45,7 @@ * Note: Some items are also used with TIPC internal message headers */ #define TIPC_VERSION 2 +struct plist; /* * Payload message users are defined in TIPC's public API: @@ -748,20 +749,110 @@ static inline u32 msg_tot_origport(struct tipc_msg *m) } struct sk_buff *tipc_buf_acquire(u32 size); -bool tipc_msg_reverse(struct net *net, struct sk_buff *buf, u32 *dnode, +bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, int err); -int tipc_msg_eval(struct net *net, struct sk_buff *buf, u32 *dnode); -void tipc_msg_init(struct net *net, struct tipc_msg *m, u32 user, u32 type, +void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); -struct sk_buff *tipc_msg_create(struct net *net, uint user, uint type, - uint hdr_sz, uint data_sz, u32 dnode, - u32 onode, u32 dport, u32 oport, int errcode); +struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, + uint data_sz, u32 dnode, u32 onode, + u32 dport, u32 oport, int errcode); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu); -bool tipc_msg_make_bundle(struct net *net, struct sk_buff_head *list, +bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu, u32 dnode); -int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m, +bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); +int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); +bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, u32 *dnode, + int *err); struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list); +/* tipc_skb_peek(): peek and reserve first buffer in list + * @list: list to be peeked in + * Returns pointer to first buffer in list, if any + */ +static inline struct sk_buff *tipc_skb_peek(struct sk_buff_head *list, + spinlock_t *lock) +{ + struct sk_buff *skb; + + spin_lock_bh(lock); + skb = skb_peek(list); + if (skb) + skb_get(skb); + spin_unlock_bh(lock); + return skb; +} + +/* tipc_skb_peek_port(): find a destination port, ignoring all destinations + * up to and including 'filter'. + * Note: ignoring previously tried destinations minimizes the risk of + * contention on the socket lock + * @list: list to be peeked in + * @filter: last destination to be ignored from search + * Returns a destination port number, of applicable. + */ +static inline u32 tipc_skb_peek_port(struct sk_buff_head *list, u32 filter) +{ + struct sk_buff *skb; + u32 dport = 0; + bool ignore = true; + + spin_lock_bh(&list->lock); + skb_queue_walk(list, skb) { + dport = msg_destport(buf_msg(skb)); + if (!filter || skb_queue_is_last(list, skb)) + break; + if (dport == filter) + ignore = false; + else if (!ignore) + break; + } + spin_unlock_bh(&list->lock); + return dport; +} + +/* tipc_skb_dequeue(): unlink first buffer with dest 'dport' from list + * @list: list to be unlinked from + * @dport: selection criteria for buffer to unlink + */ +static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list, + u32 dport) +{ + struct sk_buff *_skb, *tmp, *skb = NULL; + + spin_lock_bh(&list->lock); + skb_queue_walk_safe(list, _skb, tmp) { + if (msg_destport(buf_msg(_skb)) == dport) { + __skb_unlink(_skb, list); + skb = _skb; + break; + } + } + spin_unlock_bh(&list->lock); + return skb; +} + +/* tipc_skb_queue_tail(): add buffer to tail of list; + * @list: list to be appended to + * @skb: buffer to append. Always appended + * @dport: the destination port of the buffer + * returns true if dport differs from previous destination + */ +static inline bool tipc_skb_queue_tail(struct sk_buff_head *list, + struct sk_buff *skb, u32 dport) +{ + struct sk_buff *_skb = NULL; + bool rv = false; + + spin_lock_bh(&list->lock); + _skb = skb_peek_tail(list); + if (!_skb || (msg_destport(buf_msg(_skb)) != dport) || + (skb_queue_len(list) > 32)) + rv = true; + __skb_queue_tail(list, skb); + spin_unlock_bh(&list->lock); + return rv; +} + #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 7f31cd4badc4..fcb07915aaac 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -71,13 +71,14 @@ static void publ_to_item(struct distr_item *i, struct publication *p) static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, u32 dest) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size); struct tipc_msg *msg; if (buf != NULL) { msg = buf_msg(buf); - tipc_msg_init(net, msg, NAME_DISTRIBUTOR, type, INT_H_SIZE, - dest); + tipc_msg_init(tn->own_addr, msg, NAME_DISTRIBUTOR, type, + INT_H_SIZE, dest); msg_set_size(msg, INT_H_SIZE + size); } return buf; @@ -380,25 +381,34 @@ void tipc_named_process_backlog(struct net *net) } /** - * tipc_named_rcv - process name table update message sent by another node + * tipc_named_rcv - process name table update messages sent by another node */ -void tipc_named_rcv(struct net *net, struct sk_buff *buf) +void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_msg *msg = buf_msg(buf); - struct distr_item *item = (struct distr_item *)msg_data(msg); - u32 count = msg_data_sz(msg) / ITEM_SIZE; - u32 node = msg_orignode(msg); + struct tipc_msg *msg; + struct distr_item *item; + uint count; + u32 node; + struct sk_buff *skb; + int mtype; spin_lock_bh(&tn->nametbl_lock); - while (count--) { - if (!tipc_update_nametbl(net, item, node, msg_type(msg))) - tipc_named_add_backlog(item, msg_type(msg), node); - item++; + for (skb = skb_dequeue(inputq); skb; skb = skb_dequeue(inputq)) { + msg = buf_msg(skb); + mtype = msg_type(msg); + item = (struct distr_item *)msg_data(msg); + count = msg_data_sz(msg) / ITEM_SIZE; + node = msg_orignode(msg); + while (count--) { + if (!tipc_update_nametbl(net, item, node, mtype)) + tipc_named_add_backlog(item, mtype, node); + item++; + } + kfree_skb(skb); + tipc_named_process_backlog(net); } - tipc_named_process_backlog(net); spin_unlock_bh(&tn->nametbl_lock); - kfree_skb(buf); } /** diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index 5ec10b59527b..dd2d9fd80da2 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -71,7 +71,7 @@ struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ); struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ); void named_cluster_distribute(struct net *net, struct sk_buff *buf); void tipc_named_node_up(struct net *net, u32 dnode); -void tipc_named_rcv(struct net *net, struct sk_buff *buf); +void tipc_named_rcv(struct net *net, struct sk_buff_head *msg_queue); void tipc_named_reinit(struct net *net); void tipc_named_process_backlog(struct net *net); void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ce09b863528c..18a3d44238bc 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -1,7 +1,7 @@ /* * net/tipc/name_table.c: TIPC name table code * - * Copyright (c) 2000-2006, 2014, Ericsson AB + * Copyright (c) 2000-2006, 2014-2015, Ericsson AB * Copyright (c) 2004-2008, 2010-2014, Wind River Systems * All rights reserved. * @@ -618,7 +618,7 @@ not_found: * Returns non-zero if any off-node ports overlap */ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, - u32 limit, struct tipc_port_list *dports) + u32 limit, struct tipc_plist *dports) { struct name_seq *seq; struct sub_seq *sseq; @@ -643,7 +643,7 @@ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, info = sseq->info; list_for_each_entry(publ, &info->node_list, node_list) { if (publ->scope <= limit) - tipc_port_list_add(dports, publ->ref); + tipc_plist_push(dports, publ->ref); } if (info->cluster_list_size != info->node_list_size) @@ -1212,3 +1212,41 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } + +void tipc_plist_push(struct tipc_plist *pl, u32 port) +{ + struct tipc_plist *nl; + + if (likely(!pl->port)) { + pl->port = port; + return; + } + if (pl->port == port) + return; + list_for_each_entry(nl, &pl->list, list) { + if (nl->port == port) + return; + } + nl = kmalloc(sizeof(*nl), GFP_ATOMIC); + if (nl) { + nl->port = port; + list_add(&nl->list, &pl->list); + } +} + +u32 tipc_plist_pop(struct tipc_plist *pl) +{ + struct tipc_plist *nl; + u32 port = 0; + + if (likely(list_empty(&pl->list))) { + port = pl->port; + pl->port = 0; + return port; + } + nl = list_first_entry(&pl->list, typeof(*nl), list); + port = nl->port; + list_del(&nl->list); + kfree(nl); + return port; +} diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index f67b3d8d4b2f..0304ddc6b101 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -1,7 +1,7 @@ /* * net/tipc/name_table.h: Include file for TIPC name table code * - * Copyright (c) 2000-2006, 2014, Ericsson AB + * Copyright (c) 2000-2006, 2014-2015, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -38,7 +38,7 @@ #define _TIPC_NAME_TABLE_H struct tipc_subscription; -struct tipc_port_list; +struct tipc_plist; /* * TIPC name types reserved for internal TIPC use (both current and planned) @@ -101,7 +101,7 @@ struct sk_buff *tipc_nametbl_get(struct net *net, const void *req_tlv_area, int req_tlv_space); u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node); int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, - u32 limit, struct tipc_port_list *dports); + u32 limit, struct tipc_plist *dports); struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, u32 upper, u32 scope, u32 port_ref, u32 key); @@ -118,4 +118,18 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); +struct tipc_plist { + struct list_head list; + u32 port; +}; + +static inline void tipc_plist_init(struct tipc_plist *pl) +{ + INIT_LIST_HEAD(&pl->list); + pl->port = 0; +} + +void tipc_plist_push(struct tipc_plist *pl, u32 port); +u32 tipc_plist_pop(struct tipc_plist *pl); + #endif diff --git a/net/tipc/node.c b/net/tipc/node.c index ee5d33cfcf80..52308498f208 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -96,14 +96,14 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) struct tipc_node *n_ptr, *temp_node; spin_lock_bh(&tn->node_list_lock); - + n_ptr = tipc_node_find(net, addr); + if (n_ptr) + goto exit; n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC); if (!n_ptr) { - spin_unlock_bh(&tn->node_list_lock); pr_warn("Node creation failed, no memory\n"); - return NULL; + goto exit; } - n_ptr->addr = addr; n_ptr->net = net; spin_lock_init(&n_ptr->lock); @@ -111,11 +111,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) INIT_LIST_HEAD(&n_ptr->list); INIT_LIST_HEAD(&n_ptr->publ_list); INIT_LIST_HEAD(&n_ptr->conn_sks); - skb_queue_head_init(&n_ptr->waiting_sks); __skb_queue_head_init(&n_ptr->bclink.deferred_queue); - hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tn->node_list, list) { if (n_ptr->addr < temp_node->addr) break; @@ -123,9 +120,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) list_add_tail_rcu(&n_ptr->list, &temp_node->list); n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; n_ptr->signature = INVALID_NODE_SIG; - tn->num_nodes++; - +exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; } @@ -198,25 +194,6 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) tipc_node_unlock(node); } -void tipc_node_abort_sock_conns(struct net *net, struct list_head *conns) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_sock_conn *conn, *safe; - struct sk_buff *buf; - - list_for_each_entry_safe(conn, safe, conns, list) { - buf = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, - TIPC_CONN_MSG, SHORT_H_SIZE, 0, - tn->own_addr, conn->peer_node, - conn->port, conn->peer_port, - TIPC_ERR_NO_NODE); - if (likely(buf)) - tipc_sk_rcv(net, buf); - list_del(&conn->list); - kfree(conn); - } -} - /** * tipc_node_link_up - handle addition of link * @@ -378,7 +355,11 @@ static void node_established_contact(struct tipc_node *n_ptr) static void node_lost_contact(struct tipc_node *n_ptr) { char addr_string[16]; - u32 i; + struct tipc_sock_conn *conn, *safe; + struct list_head *conns = &n_ptr->conn_sks; + struct sk_buff *skb; + struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); + uint i; pr_debug("Lost contact with %s\n", tipc_addr_string_fill(addr_string, n_ptr->addr)); @@ -406,15 +387,33 @@ static void node_lost_contact(struct tipc_node *n_ptr) l_ptr->reset_checkpoint = l_ptr->next_in_no; l_ptr->exp_msg_count = 0; tipc_link_reset_fragments(l_ptr); + + /* Link marked for deletion after failover? => do it now */ + if (l_ptr->flags & LINK_STOPPED) + tipc_link_delete(l_ptr); } n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN; - /* Notify subscribers and prevent re-contact with node until - * cleanup is done. - */ - n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN | - TIPC_NOTIFY_NODE_DOWN; + /* Prevent re-contact with node until cleanup is done */ + n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN; + + /* Notify publications from this node */ + n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN; + + /* Notify sockets connected to node */ + list_for_each_entry_safe(conn, safe, conns, list) { + skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, + SHORT_H_SIZE, 0, tn->own_addr, + conn->peer_node, conn->port, + conn->peer_port, TIPC_ERR_NO_NODE); + if (likely(skb)) { + skb_queue_tail(n_ptr->inputq, skb); + n_ptr->action_flags |= TIPC_MSG_EVT; + } + list_del(&conn->list); + kfree(conn); + } } struct sk_buff *tipc_node_get_nodes(struct net *net, const void *req_tlv_area, @@ -563,44 +562,36 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, void tipc_node_unlock(struct tipc_node *node) { struct net *net = node->net; - LIST_HEAD(nsub_list); - LIST_HEAD(conn_sks); - struct sk_buff_head waiting_sks; u32 addr = 0; - int flags = node->action_flags; + u32 flags = node->action_flags; u32 link_id = 0; + struct list_head *publ_list; + struct sk_buff_head *inputq = node->inputq; + struct sk_buff_head *namedq; - if (likely(!flags)) { + if (likely(!flags || (flags == TIPC_MSG_EVT))) { + node->action_flags = 0; spin_unlock_bh(&node->lock); + if (flags == TIPC_MSG_EVT) + tipc_sk_rcv(net, inputq); return; } addr = node->addr; link_id = node->link_id; - __skb_queue_head_init(&waiting_sks); + namedq = node->namedq; + publ_list = &node->publ_list; - if (flags & TIPC_WAKEUP_USERS) - skb_queue_splice_init(&node->waiting_sks, &waiting_sks); - - if (flags & TIPC_NOTIFY_NODE_DOWN) { - list_replace_init(&node->publ_list, &nsub_list); - list_replace_init(&node->conn_sks, &conn_sks); - } - node->action_flags &= ~(TIPC_WAKEUP_USERS | TIPC_NOTIFY_NODE_DOWN | - TIPC_NOTIFY_NODE_UP | TIPC_NOTIFY_LINK_UP | - TIPC_NOTIFY_LINK_DOWN | - TIPC_WAKEUP_BCAST_USERS); + node->action_flags &= ~(TIPC_MSG_EVT | + TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | + TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP | + TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT | + TIPC_NAMED_MSG_EVT); spin_unlock_bh(&node->lock); - while (!skb_queue_empty(&waiting_sks)) - tipc_sk_rcv(net, __skb_dequeue(&waiting_sks)); - - if (!list_empty(&conn_sks)) - tipc_node_abort_sock_conns(net, &conn_sks); - - if (!list_empty(&nsub_list)) - tipc_publ_notify(net, &nsub_list, addr); + if (flags & TIPC_NOTIFY_NODE_DOWN) + tipc_publ_notify(net, publ_list, addr); if (flags & TIPC_WAKEUP_BCAST_USERS) tipc_bclink_wakeup_users(net); @@ -615,6 +606,15 @@ void tipc_node_unlock(struct tipc_node *node) if (flags & TIPC_NOTIFY_LINK_DOWN) tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr, link_id, addr); + + if (flags & TIPC_MSG_EVT) + tipc_sk_rcv(net, inputq); + + if (flags & TIPC_NAMED_MSG_EVT) + tipc_named_rcv(net, namedq); + + if (flags & TIPC_BCAST_MSG_EVT) + tipc_bclink_input(net); } /* Caller should hold node lock for the passed node */ diff --git a/net/tipc/node.h b/net/tipc/node.h index 43ef88ef3035..20ec13f9bede 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -1,7 +1,7 @@ /* * net/tipc/node.h: Include file for TIPC node management routines * - * Copyright (c) 2000-2006, 2014, Ericsson AB + * Copyright (c) 2000-2006, 2014-2015, Ericsson AB * Copyright (c) 2005, 2010-2014, Wind River Systems * All rights reserved. * @@ -55,14 +55,16 @@ * TIPC_DISTRIBUTE_NAME: publish or withdraw link state name type */ enum { + TIPC_MSG_EVT = 1, TIPC_WAIT_PEER_LINKS_DOWN = (1 << 1), TIPC_WAIT_OWN_LINKS_DOWN = (1 << 2), TIPC_NOTIFY_NODE_DOWN = (1 << 3), TIPC_NOTIFY_NODE_UP = (1 << 4), - TIPC_WAKEUP_USERS = (1 << 5), - TIPC_WAKEUP_BCAST_USERS = (1 << 6), - TIPC_NOTIFY_LINK_UP = (1 << 7), - TIPC_NOTIFY_LINK_DOWN = (1 << 8) + TIPC_WAKEUP_BCAST_USERS = (1 << 5), + TIPC_NOTIFY_LINK_UP = (1 << 6), + TIPC_NOTIFY_LINK_DOWN = (1 << 7), + TIPC_NAMED_MSG_EVT = (1 << 8), + TIPC_BCAST_MSG_EVT = (1 << 9) }; /** @@ -73,6 +75,7 @@ enum { * @oos_state: state tracker for handling OOS b'cast messages * @deferred_queue: deferred queue saved OOS b'cast message received from node * @reasm_buf: broadcast reassembly queue head from node + * @inputq_map: bitmap indicating which inqueues should be kicked * @recv_permitted: true if node is allowed to receive b'cast messages */ struct tipc_node_bclink { @@ -83,6 +86,7 @@ struct tipc_node_bclink { u32 deferred_size; struct sk_buff_head deferred_queue; struct sk_buff *reasm_buf; + int inputq_map; bool recv_permitted; }; @@ -92,6 +96,9 @@ struct tipc_node_bclink { * @lock: spinlock governing access to structure * @net: the applicable net namespace * @hash: links to adjacent nodes in unsorted hash chain + * @inputq: pointer to input queue containing messages for msg event + * @namedq: pointer to name table input queue with name table messages + * @curr_link: the link holding the node lock, if any * @active_links: pointers to active links to node * @links: pointers to all links to node * @action_flags: bit mask of different types of node actions @@ -109,10 +116,12 @@ struct tipc_node { spinlock_t lock; struct net *net; struct hlist_node hash; + struct sk_buff_head *inputq; + struct sk_buff_head *namedq; struct tipc_link *active_links[2]; u32 act_mtus[2]; struct tipc_link *links[MAX_BEARERS]; - unsigned int action_flags; + int action_flags; struct tipc_node_bclink bclink; struct list_head list; int link_cnt; @@ -120,7 +129,6 @@ struct tipc_node { u32 signature; u32 link_id; struct list_head publ_list; - struct sk_buff_head waiting_sks; struct list_head conn_sks; struct rcu_head rcu; }; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 679a22082fcb..66666805b53c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2014, Ericsson AB + * Copyright (c) 2001-2007, 2012-2015, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -41,6 +41,7 @@ #include "node.h" #include "link.h" #include "config.h" +#include "name_distr.h" #include "socket.h" #define SS_LISTENING -1 /* socket is listening */ @@ -69,8 +70,6 @@ * @pub_count: total # of publications port has made during its lifetime * @probing_state: * @probing_intv: - * @port: port - interacts with 'sk' and with the rest of the TIPC stack - * @peer_name: the peer of the connection, if any * @conn_timeout: the time we can wait for an unresponded setup request * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue * @link_cong: non-zero if owner must sleep because of link congestion @@ -177,6 +176,11 @@ static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { * - port reference */ +static u32 tsk_own_node(struct tipc_sock *tsk) +{ + return msg_prevnode(&tsk->phdr); +} + static u32 tsk_peer_node(struct tipc_sock *tsk) { return msg_destnode(&tsk->phdr); @@ -249,11 +253,11 @@ static void tsk_rej_rx_queue(struct sock *sk) { struct sk_buff *skb; u32 dnode; - struct net *net = sock_net(sk); + u32 own_node = tsk_own_node(tipc_sk(sk)); while ((skb = __skb_dequeue(&sk->sk_receive_queue))) { - if (tipc_msg_reverse(net, skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(net, skb, dnode, 0); + if (tipc_msg_reverse(own_node, skb, &dnode, TIPC_ERR_NO_PORT)) + tipc_link_xmit_skb(sock_net(sk), skb, dnode, 0); } } @@ -305,6 +309,7 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg) static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, int kern) { + struct tipc_net *tn; const struct proto_ops *ops; socket_state state; struct sock *sk; @@ -346,7 +351,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk->max_pkt = MAX_PKT_DEFAULT; INIT_LIST_HEAD(&tsk->publications); msg = &tsk->phdr; - tipc_msg_init(net, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG, + tn = net_generic(sock_net(sk), tipc_net_id); + tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG, NAMED_H_SIZE, 0); /* Finish initializing socket data structures */ @@ -471,7 +477,6 @@ static int tipc_release(struct socket *sock) { struct sock *sk = sock->sk; struct net *net; - struct tipc_net *tn; struct tipc_sock *tsk; struct sk_buff *skb; u32 dnode, probing_state; @@ -484,8 +489,6 @@ static int tipc_release(struct socket *sock) return 0; net = sock_net(sk); - tn = net_generic(net, tipc_net_id); - tsk = tipc_sk(sk); lock_sock(sk); @@ -507,7 +510,7 @@ static int tipc_release(struct socket *sock) tsk->connected = 0; tipc_node_remove_conn(net, dnode, tsk->portid); } - if (tipc_msg_reverse(net, skb, &dnode, + if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, TIPC_ERR_NO_PORT)) tipc_link_xmit_skb(net, skb, dnode, 0); } @@ -520,9 +523,9 @@ static int tipc_release(struct socket *sock) sock_put(sk); tipc_sk_remove(tsk); if (tsk->connected) { - skb = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, + skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, - tn->own_addr, tsk_peer_port(tsk), + tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, TIPC_ERR_NO_PORT); if (skb) tipc_link_xmit_skb(net, skb, dnode, tsk->portid); @@ -730,9 +733,11 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct msghdr *msg, size_t dsz, long timeo) { struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); - struct tipc_msg *mhdr = &tipc_sk(sk)->phdr; - struct sk_buff_head head; + struct tipc_msg *mhdr = &tsk->phdr; + struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct iov_iter save = msg->msg_iter; uint mtu; int rc; @@ -747,80 +752,97 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, new_mtu: mtu = tipc_bclink_get_mtu(); - __skb_queue_head_init(&head); - rc = tipc_msg_build(net, mhdr, msg, 0, dsz, mtu, &head); + rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bclink_xmit(net, &head); + rc = tipc_bclink_xmit(net, pktchain); if (likely(rc >= 0)) { rc = dsz; break; } - if (rc == -EMSGSIZE) + if (rc == -EMSGSIZE) { + msg->msg_iter = save; goto new_mtu; + } if (rc != -ELINKCONG) break; tipc_sk(sk)->link_cong = 1; rc = tipc_wait_for_sndmsg(sock, &timeo); if (rc) - __skb_queue_purge(&head); + __skb_queue_purge(pktchain); } while (!rc); return rc; } -/* tipc_sk_mcast_rcv - Deliver multicast message to all destination sockets +/** + * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets + * @arrvq: queue with arriving messages, to be cloned after destination lookup + * @inputq: queue with cloned messages, delivered to socket after dest lookup + * + * Multi-threaded: parallel calls with reference to same queues may occur */ -void tipc_sk_mcast_rcv(struct net *net, struct sk_buff *buf) +void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, + struct sk_buff_head *inputq) { - struct tipc_msg *msg = buf_msg(buf); - struct tipc_port_list dports = {0, NULL, }; - struct tipc_port_list *item; - struct sk_buff *b; - uint i, last, dst = 0; + struct tipc_msg *msg; + struct tipc_plist dports; + u32 portid; u32 scope = TIPC_CLUSTER_SCOPE; - - if (in_own_node(net, msg_orignode(msg))) - scope = TIPC_NODE_SCOPE; - - /* Create destination port list: */ - tipc_nametbl_mc_translate(net, msg_nametype(msg), msg_namelower(msg), - msg_nameupper(msg), scope, &dports); - last = dports.count; - if (!last) { - kfree_skb(buf); - return; - } - - for (item = &dports; item; item = item->next) { - for (i = 0; i < PLSIZE && ++dst <= last; i++) { - b = (dst != last) ? skb_clone(buf, GFP_ATOMIC) : buf; - if (!b) { - pr_warn("Failed do clone mcast rcv buffer\n"); + struct sk_buff_head tmpq; + uint hsz; + struct sk_buff *skb, *_skb; + + __skb_queue_head_init(&tmpq); + tipc_plist_init(&dports); + + skb = tipc_skb_peek(arrvq, &inputq->lock); + for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { + msg = buf_msg(skb); + hsz = skb_headroom(skb) + msg_hdr_sz(msg); + + if (in_own_node(net, msg_orignode(msg))) + scope = TIPC_NODE_SCOPE; + + /* Create destination port list and message clones: */ + tipc_nametbl_mc_translate(net, + msg_nametype(msg), msg_namelower(msg), + msg_nameupper(msg), scope, &dports); + portid = tipc_plist_pop(&dports); + for (; portid; portid = tipc_plist_pop(&dports)) { + _skb = __pskb_copy(skb, hsz, GFP_ATOMIC); + if (_skb) { + msg_set_destport(buf_msg(_skb), portid); + __skb_queue_tail(&tmpq, _skb); continue; } - msg_set_destport(msg, item->ports[i]); - tipc_sk_rcv(net, b); + pr_warn("Failed to clone mcast rcv buffer\n"); } + /* Append to inputq if not already done by other thread */ + spin_lock_bh(&inputq->lock); + if (skb_peek(arrvq) == skb) { + skb_queue_splice_tail_init(&tmpq, inputq); + kfree_skb(__skb_dequeue(arrvq)); + } + spin_unlock_bh(&inputq->lock); + __skb_queue_purge(&tmpq); + kfree_skb(skb); } - tipc_port_list_free(&dports); + tipc_sk_rcv(net, inputq); } /** * tipc_sk_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket - * @dnode: node to send response message to, if any - * @buf: buffer containing protocol message - * Returns 0 (TIPC_OK) if message was consumed, 1 (TIPC_FWD_MSG) if - * (CONN_PROBE_REPLY) message should be forwarded. + * @skb: pointer to message buffer. Set to NULL if buffer is consumed. */ -static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode, - struct sk_buff *buf) +static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff **skb) { - struct tipc_msg *msg = buf_msg(buf); + struct tipc_msg *msg = buf_msg(*skb); int conn_cong; - + u32 dnode; + u32 own_node = tsk_own_node(tsk); /* Ignore if connection cannot be validated: */ if (!tsk_peer_msg(tsk, msg)) goto exit; @@ -833,15 +855,15 @@ static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode, if (conn_cong) tsk->sk.sk_write_space(&tsk->sk); } else if (msg_type(msg) == CONN_PROBE) { - if (!tipc_msg_reverse(sock_net(&tsk->sk), buf, dnode, TIPC_OK)) - return TIPC_OK; - msg_set_type(msg, CONN_PROBE_REPLY); - return TIPC_FWD_MSG; + if (tipc_msg_reverse(own_node, *skb, &dnode, TIPC_OK)) { + msg_set_type(msg, CONN_PROBE_REPLY); + return; + } } /* Do nothing if msg_type() == CONN_PROBE_REPLY */ exit: - kfree_skb(buf); - return TIPC_OK; + kfree_skb(*skb); + *skb = NULL; } static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) @@ -892,9 +914,10 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; - struct sk_buff_head head; + struct sk_buff_head *pktchain = &sk->sk_write_queue; struct sk_buff *skb; struct tipc_name_seq *seq = &dest->addr.nameseq; + struct iov_iter save; u32 mtu; long timeo; int rc; @@ -963,31 +986,33 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, msg_set_hdr_sz(mhdr, BASIC_H_SIZE); } + save = m->msg_iter; new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); - __skb_queue_head_init(&head); - rc = tipc_msg_build(net, mhdr, m, 0, dsz, mtu, &head); + rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); if (rc < 0) goto exit; do { - skb = skb_peek(&head); + skb = skb_peek(pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_link_xmit(net, &head, dnode, tsk->portid); + rc = tipc_link_xmit(net, pktchain, dnode, tsk->portid); if (likely(rc >= 0)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; rc = dsz; break; } - if (rc == -EMSGSIZE) + if (rc == -EMSGSIZE) { + m->msg_iter = save; goto new_mtu; + } if (rc != -ELINKCONG) break; tsk->link_cong = 1; rc = tipc_wait_for_sndmsg(sock, &timeo); if (rc) - __skb_queue_purge(&head); + __skb_queue_purge(pktchain); } while (!rc); exit: if (iocb) @@ -1045,13 +1070,14 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head head; + struct sk_buff_head *pktchain = &sk->sk_write_queue; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); u32 portid = tsk->portid; int rc = -EINVAL; long timeo; u32 dnode; uint mtu, send, sent = 0; + struct iov_iter save; /* Handle implied connection establishment */ if (unlikely(dest)) { @@ -1078,15 +1104,15 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, dnode = tsk_peer_node(tsk); next: + save = m->msg_iter; mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); - __skb_queue_head_init(&head); - rc = tipc_msg_build(net, mhdr, m, sent, send, mtu, &head); + rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); if (unlikely(rc < 0)) goto exit; do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_link_xmit(net, &head, dnode, portid); + rc = tipc_link_xmit(net, pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1097,6 +1123,7 @@ next: if (rc == -EMSGSIZE) { tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); + m->msg_iter = save; goto next; } if (rc != -ELINKCONG) @@ -1105,7 +1132,7 @@ next: } rc = tipc_wait_for_sndpkt(sock, &timeo); if (rc) - __skb_queue_purge(&head); + __skb_queue_purge(pktchain); } while (!rc); exit: if (iocb) @@ -1253,7 +1280,6 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg, static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) { struct net *net = sock_net(&tsk->sk); - struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *skb = NULL; struct tipc_msg *msg; u32 peer_port = tsk_peer_port(tsk); @@ -1261,9 +1287,9 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) if (!tsk->connected) return; - skb = tipc_msg_create(net, CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, - dnode, tn->own_addr, peer_port, tsk->portid, - TIPC_OK); + skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, + dnode, tsk_own_node(tsk), peer_port, + tsk->portid, TIPC_OK); if (!skb) return; msg = buf_msg(skb); @@ -1554,16 +1580,16 @@ static void tipc_data_ready(struct sock *sk) /** * filter_connect - Handle all incoming messages for a connection-based socket * @tsk: TIPC socket - * @msg: message + * @skb: pointer to message buffer. Set to NULL if buffer is consumed * * Returns 0 (TIPC_OK) if everything ok, -TIPC_ERR_NO_PORT otherwise */ -static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) +static int filter_connect(struct tipc_sock *tsk, struct sk_buff **skb) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); struct socket *sock = sk->sk_socket; - struct tipc_msg *msg = buf_msg(*buf); + struct tipc_msg *msg = buf_msg(*skb); int retval = -TIPC_ERR_NO_PORT; if (msg_mcast(msg)) @@ -1613,8 +1639,8 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) * connect() routine if sleeping. */ if (msg_data_sz(msg) == 0) { - kfree_skb(*buf); - *buf = NULL; + kfree_skb(*skb); + *skb = NULL; if (waitqueue_active(sk_sleep(sk))) wake_up_interruptible(sk_sleep(sk)); } @@ -1666,32 +1692,33 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) /** * filter_rcv - validate incoming message * @sk: socket - * @buf: message + * @skb: pointer to message. Set to NULL if buffer is consumed. * * Enqueues message on receive queue if acceptable; optionally handles * disconnect indication for a connected socket. * - * Called with socket lock already taken; port lock may also be taken. + * Called with socket lock already taken * - * Returns 0 (TIPC_OK) if message was consumed, -TIPC error code if message - * to be rejected, 1 (TIPC_FWD_MSG) if (CONN_MANAGER) message to be forwarded + * Returns 0 (TIPC_OK) if message was ok, -TIPC error code if rejected */ -static int filter_rcv(struct sock *sk, struct sk_buff *buf) +static int filter_rcv(struct sock *sk, struct sk_buff **skb) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_msg *msg = buf_msg(buf); - unsigned int limit = rcvbuf_limit(sk, buf); - u32 onode; + struct tipc_msg *msg = buf_msg(*skb); + unsigned int limit = rcvbuf_limit(sk, *skb); int rc = TIPC_OK; - if (unlikely(msg_user(msg) == CONN_MANAGER)) - return tipc_sk_proto_rcv(tsk, &onode, buf); + if (unlikely(msg_user(msg) == CONN_MANAGER)) { + tipc_sk_proto_rcv(tsk, skb); + return TIPC_OK; + } if (unlikely(msg_user(msg) == SOCK_WAKEUP)) { - kfree_skb(buf); + kfree_skb(*skb); tsk->link_cong = 0; sk->sk_write_space(sk); + *skb = NULL; return TIPC_OK; } @@ -1703,21 +1730,22 @@ static int filter_rcv(struct sock *sk, struct sk_buff *buf) if (msg_connected(msg)) return -TIPC_ERR_NO_PORT; } else { - rc = filter_connect(tsk, &buf); - if (rc != TIPC_OK || buf == NULL) + rc = filter_connect(tsk, skb); + if (rc != TIPC_OK || !*skb) return rc; } /* Reject message if there isn't room to queue it */ - if (sk_rmem_alloc_get(sk) + buf->truesize >= limit) + if (sk_rmem_alloc_get(sk) + (*skb)->truesize >= limit) return -TIPC_ERR_OVERLOAD; /* Enqueue message */ - TIPC_SKB_CB(buf)->handle = NULL; - __skb_queue_tail(&sk->sk_receive_queue, buf); - skb_set_owner_r(buf, sk); + TIPC_SKB_CB(*skb)->handle = NULL; + __skb_queue_tail(&sk->sk_receive_queue, *skb); + skb_set_owner_r(*skb, sk); sk->sk_data_ready(sk); + *skb = NULL; return TIPC_OK; } @@ -1726,79 +1754,126 @@ static int filter_rcv(struct sock *sk, struct sk_buff *buf) * @sk: socket * @skb: message * - * Caller must hold socket lock, but not port lock. + * Caller must hold socket lock * * Returns 0 */ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - int rc; - u32 onode; + int err; + atomic_t *dcnt; + u32 dnode; struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); uint truesize = skb->truesize; - rc = filter_rcv(sk, skb); - - if (likely(!rc)) { - if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT) - atomic_add(truesize, &tsk->dupl_rcvcnt); + err = filter_rcv(sk, &skb); + if (likely(!skb)) { + dcnt = &tsk->dupl_rcvcnt; + if (atomic_read(dcnt) < TIPC_CONN_OVERLOAD_LIMIT) + atomic_add(truesize, dcnt); return 0; } - - if ((rc < 0) && !tipc_msg_reverse(net, skb, &onode, -rc)) - return 0; - - tipc_link_xmit_skb(net, skb, onode, 0); - + if (!err || tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, -err)) + tipc_link_xmit_skb(net, skb, dnode, tsk->portid); return 0; } /** - * tipc_sk_rcv - handle incoming message - * @skb: buffer containing arriving message - * Consumes buffer - * Returns 0 if success, or errno: -EHOSTUNREACH + * tipc_sk_enqueue - extract all buffers with destination 'dport' from + * inputq and try adding them to socket or backlog queue + * @inputq: list of incoming buffers with potentially different destinations + * @sk: socket where the buffers should be enqueued + * @dport: port number for the socket + * @_skb: returned buffer to be forwarded or rejected, if applicable + * + * Caller must hold socket lock + * + * Returns TIPC_OK if all buffers enqueued, otherwise -TIPC_ERR_OVERLOAD + * or -TIPC_ERR_NO_PORT */ -int tipc_sk_rcv(struct net *net, struct sk_buff *skb) +static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, + u32 dport, struct sk_buff **_skb) { - struct tipc_sock *tsk; - struct sock *sk; - u32 dport = msg_destport(buf_msg(skb)); - int rc = TIPC_OK; - uint limit; - u32 dnode; + unsigned int lim; + atomic_t *dcnt; + int err; + struct sk_buff *skb; + unsigned long time_limit = jiffies + 2; - /* Validate destination and message */ - tsk = tipc_sk_lookup(net, dport); - if (unlikely(!tsk)) { - rc = tipc_msg_eval(net, skb, &dnode); - goto exit; + while (skb_queue_len(inputq)) { + skb = tipc_skb_dequeue(inputq, dport); + if (unlikely(!skb)) + return TIPC_OK; + /* Return if softirq window exhausted */ + if (unlikely(time_after_eq(jiffies, time_limit))) + return TIPC_OK; + if (!sock_owned_by_user(sk)) { + err = filter_rcv(sk, &skb); + if (likely(!skb)) + continue; + *_skb = skb; + return err; + } + dcnt = &tipc_sk(sk)->dupl_rcvcnt; + if (sk->sk_backlog.len) + atomic_set(dcnt, 0); + lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt); + if (likely(!sk_add_backlog(sk, skb, lim))) + continue; + *_skb = skb; + return -TIPC_ERR_OVERLOAD; } - sk = &tsk->sk; + return TIPC_OK; +} - /* Queue message */ - spin_lock_bh(&sk->sk_lock.slock); +/** + * tipc_sk_rcv - handle a chain of incoming buffers + * @inputq: buffer list containing the buffers + * Consumes all buffers in list until inputq is empty + * Note: may be called in multiple threads referring to the same queue + * Returns 0 if last buffer was accepted, otherwise -EHOSTUNREACH + * Only node local calls check the return value, sending single-buffer queues + */ +int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) +{ + u32 dnode, dport = 0; + int err = -TIPC_ERR_NO_PORT; + struct sk_buff *skb; + struct tipc_sock *tsk; + struct tipc_net *tn; + struct sock *sk; - if (!sock_owned_by_user(sk)) { - rc = filter_rcv(sk, skb); - } else { - if (sk->sk_backlog.len == 0) - atomic_set(&tsk->dupl_rcvcnt, 0); - limit = rcvbuf_limit(sk, skb) + atomic_read(&tsk->dupl_rcvcnt); - if (sk_add_backlog(sk, skb, limit)) - rc = -TIPC_ERR_OVERLOAD; + while (skb_queue_len(inputq)) { + skb = NULL; + dport = tipc_skb_peek_port(inputq, dport); + tsk = tipc_sk_lookup(net, dport); + if (likely(tsk)) { + sk = &tsk->sk; + if (likely(spin_trylock_bh(&sk->sk_lock.slock))) { + err = tipc_sk_enqueue(inputq, sk, dport, &skb); + spin_unlock_bh(&sk->sk_lock.slock); + dport = 0; + } + sock_put(sk); + } else { + skb = tipc_skb_dequeue(inputq, dport); + } + if (likely(!skb)) + continue; + if (tipc_msg_lookup_dest(net, skb, &dnode, &err)) + goto xmit; + if (!err) { + dnode = msg_destnode(buf_msg(skb)); + goto xmit; + } + tn = net_generic(net, tipc_net_id); + if (!tipc_msg_reverse(tn->own_addr, skb, &dnode, -err)) + continue; +xmit: + tipc_link_xmit_skb(net, skb, dnode, dport); } - spin_unlock_bh(&sk->sk_lock.slock); - sock_put(sk); - if (likely(!rc)) - return 0; -exit: - if ((rc < 0) && !tipc_msg_reverse(net, skb, &dnode, -rc)) - return -EHOSTUNREACH; - - tipc_link_xmit_skb(net, skb, dnode, 0); - return (rc < 0) ? -EHOSTUNREACH : 0; + return err ? -EHOSTUNREACH : 0; } static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) @@ -2055,7 +2130,6 @@ static int tipc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); - struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_sock *tsk = tipc_sk(sk); struct sk_buff *skb; u32 dnode; @@ -2078,16 +2152,17 @@ restart: kfree_skb(skb); goto restart; } - if (tipc_msg_reverse(net, skb, &dnode, + if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, TIPC_CONN_SHUTDOWN)) tipc_link_xmit_skb(net, skb, dnode, tsk->portid); tipc_node_remove_conn(net, dnode, tsk->portid); } else { dnode = tsk_peer_node(tsk); - skb = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, + + skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, - 0, dnode, tn->own_addr, + 0, dnode, tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, TIPC_CONN_SHUTDOWN); tipc_link_xmit_skb(net, skb, dnode, tsk->portid); @@ -2119,10 +2194,9 @@ static void tipc_sk_timeout(unsigned long data) { struct tipc_sock *tsk = (struct tipc_sock *)data; struct sock *sk = &tsk->sk; - struct net *net = sock_net(sk); - struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *skb = NULL; u32 peer_port, peer_node; + u32 own_node = tsk_own_node(tsk); bh_lock_sock(sk); if (!tsk->connected) { @@ -2134,13 +2208,13 @@ static void tipc_sk_timeout(unsigned long data) if (tsk->probing_state == TIPC_CONN_PROBING) { /* Previous probe not answered -> self abort */ - skb = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, + skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, - tn->own_addr, peer_node, tsk->portid, + own_node, peer_node, tsk->portid, peer_port, TIPC_ERR_NO_PORT); } else { - skb = tipc_msg_create(net, CONN_MANAGER, CONN_PROBE, INT_H_SIZE, - 0, peer_node, tn->own_addr, + skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, + INT_H_SIZE, 0, peer_node, own_node, peer_port, tsk->portid, TIPC_OK); tsk->probing_state = TIPC_CONN_PROBING; sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv); diff --git a/net/tipc/socket.h b/net/tipc/socket.h index f56c3fded51f..8be0da7df8fc 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -1,6 +1,6 @@ /* net/tipc/socket.h: Include file for TIPC socket code * - * Copyright (c) 2014, Ericsson AB + * Copyright (c) 2014-2015, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -42,16 +42,16 @@ #define TIPC_FLOWCTRL_WIN (TIPC_CONNACK_INTV * 2) #define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) - int tipc_socket_init(void); void tipc_socket_stop(void); int tipc_sock_create_local(struct net *net, int type, struct socket **res); void tipc_sock_release_local(struct socket *sock); int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, int flags); -int tipc_sk_rcv(struct net *net, struct sk_buff *buf); +int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); struct sk_buff *tipc_sk_socks_show(struct net *net); -void tipc_sk_mcast_rcv(struct net *net, struct sk_buff *buf); +void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, + struct sk_buff_head *inputq); void tipc_sk_reinit(struct net *net); int tipc_sk_rht_init(struct net *net); void tipc_sk_rht_destroy(struct net *net); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 02d2e5229240..7f3255084a6c 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1850,8 +1850,7 @@ static ssize_t vmci_transport_stream_enqueue( struct msghdr *msg, size_t len) { - /* XXX: stripping const */ - return vmci_qpair_enquev(vmci_trans(vsk)->qpair, (struct iovec *)msg->msg_iter.iov, len, 0); + return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); } static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7d60f4bf95d2..d78fd8b54515 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -397,6 +397,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 }, [NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN }, [NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG }, + [NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -5778,7 +5780,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->ssids = (void *)&request->channels[n_channels]; request->n_ssids = n_ssids; if (ie_len) { - if (request->ssids) + if (n_ssids) request->ie = (void *)(request->ssids + n_ssids); else request->ie = (void *)(request->channels + n_channels); @@ -5834,7 +5836,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->n_channels = i; i = 0; - if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) { + if (n_ssids) { nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) { if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; @@ -6032,7 +6034,7 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->ssids = (void *)&request->channels[n_channels]; request->n_ssids = n_ssids; if (ie_len) { - if (request->ssids) + if (n_ssids) request->ie = (void *)(request->ssids + n_ssids); else request->ie = (void *)(request->channels + n_channels); @@ -6041,7 +6043,7 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (n_match_sets) { if (request->ie) request->match_sets = (void *)(request->ie + ie_len); - else if (request->ssids) + else if (n_ssids) request->match_sets = (void *)(request->ssids + n_ssids); else @@ -6100,7 +6102,7 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->n_channels = i; i = 0; - if (attrs[NL80211_ATTR_SCAN_SSIDS]) { + if (n_ssids) { nla_for_each_nested(attr, attrs[NL80211_ATTR_SCAN_SSIDS], tmp) { if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { @@ -6208,6 +6210,10 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, } } + if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY]) + request->delay = + nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_DELAY]); + request->interval = interval; request->scan_start = jiffies; @@ -7768,14 +7774,19 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net *net; int err; - u32 pid; - if (!info->attrs[NL80211_ATTR_PID]) - return -EINVAL; + if (info->attrs[NL80211_ATTR_PID]) { + u32 pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]); + + net = get_net_ns_by_pid(pid); + } else if (info->attrs[NL80211_ATTR_NETNS_FD]) { + u32 fd = nla_get_u32(info->attrs[NL80211_ATTR_NETNS_FD]); - pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]); + net = get_net_ns_by_fd(fd); + } else { + return -EINVAL; + } - net = get_net_ns_by_pid(pid); if (IS_ERR(net)) return PTR_ERR(net); diff --git a/net/wireless/util.c b/net/wireless/util.c index 0d1966d54aaa..6903dbdcb8c1 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -227,18 +227,32 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, if (pairwise && !mac_addr) return -EINVAL; - /* - * Disallow pairwise keys with non-zero index unless it's WEP - * or a vendor specific cipher (because current deployments use - * pairwise WEP keys with non-zero indices and for vendor specific - * ciphers this should be validated in the driver or hardware level - * - but 802.11i clearly specifies to use zero) - */ - if (pairwise && key_idx && - ((params->cipher == WLAN_CIPHER_SUITE_TKIP) || - (params->cipher == WLAN_CIPHER_SUITE_CCMP) || - (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC))) - return -EINVAL; + switch (params->cipher) { + case WLAN_CIPHER_SUITE_TKIP: + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + /* Disallow pairwise keys with non-zero index unless it's WEP + * or a vendor specific cipher (because current deployments use + * pairwise WEP keys with non-zero indices and for vendor + * specific ciphers this should be validated in the driver or + * hardware level - but 802.11i clearly specifies to use zero) + */ + if (pairwise && key_idx) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + /* Disallow BIP (group-only) cipher as pairwise cipher */ + if (pairwise) + return -EINVAL; + break; + default: + break; + } switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: @@ -253,6 +267,18 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, if (params->key_len != WLAN_KEY_LEN_CCMP) return -EINVAL; break; + case WLAN_CIPHER_SUITE_CCMP_256: + if (params->key_len != WLAN_KEY_LEN_CCMP_256) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_GCMP: + if (params->key_len != WLAN_KEY_LEN_GCMP) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_GCMP_256: + if (params->key_len != WLAN_KEY_LEN_GCMP_256) + return -EINVAL; + break; case WLAN_CIPHER_SUITE_WEP104: if (params->key_len != WLAN_KEY_LEN_WEP104) return -EINVAL; @@ -261,6 +287,18 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, if (params->key_len != WLAN_KEY_LEN_AES_CMAC) return -EINVAL; break; + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + if (params->key_len != WLAN_KEY_LEN_BIP_CMAC_256) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_128) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_256) + return -EINVAL; + break; default: /* * We don't know anything about this algorithm, @@ -280,7 +318,13 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, return -EINVAL; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->seq_len != 6) return -EINVAL; break; diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c index ec667f158f19..5d905d90d504 100644 --- a/sound/core/seq/seq_dummy.c +++ b/sound/core/seq/seq_dummy.c @@ -82,36 +82,6 @@ struct snd_seq_dummy_port { static int my_client = -1; /* - * unuse callback - send ALL_SOUNDS_OFF and RESET_CONTROLLERS events - * to subscribers. - * Note: this callback is called only after all subscribers are removed. - */ -static int -dummy_unuse(void *private_data, struct snd_seq_port_subscribe *info) -{ - struct snd_seq_dummy_port *p; - int i; - struct snd_seq_event ev; - - p = private_data; - memset(&ev, 0, sizeof(ev)); - if (p->duplex) - ev.source.port = p->connect; - else - ev.source.port = p->port; - ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; - ev.type = SNDRV_SEQ_EVENT_CONTROLLER; - for (i = 0; i < 16; i++) { - ev.data.control.channel = i; - ev.data.control.param = MIDI_CTL_ALL_SOUNDS_OFF; - snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0); - ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS; - snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0); - } - return 0; -} - -/* * event input callback - just redirect events to subscribers */ static int @@ -175,7 +145,6 @@ create_port(int idx, int type) | SNDRV_SEQ_PORT_TYPE_PORT; memset(&pcb, 0, sizeof(pcb)); pcb.owner = THIS_MODULE; - pcb.unuse = dummy_unuse; pcb.event_input = dummy_input; pcb.private_free = dummy_free; pcb.private_data = rec; diff --git a/sound/soc/adi/axi-i2s.c b/sound/soc/adi/axi-i2s.c index 7752860f7230..4c23381727a1 100644 --- a/sound/soc/adi/axi-i2s.c +++ b/sound/soc/adi/axi-i2s.c @@ -240,6 +240,8 @@ static int axi_i2s_probe(struct platform_device *pdev) if (ret) goto err_clk_disable; + return 0; + err_clk_disable: clk_disable_unprepare(i2s->clk); return ret; diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c index e5f2fb884bf3..30c673cdc12e 100644 --- a/sound/soc/codecs/pcm512x.c +++ b/sound/soc/codecs/pcm512x.c @@ -188,8 +188,8 @@ static const DECLARE_TLV_DB_SCALE(boost_tlv, 0, 80, 0); static const char * const pcm512x_dsp_program_texts[] = { "FIR interpolation with de-emphasis", "Low latency IIR with de-emphasis", - "Fixed process flow", "High attenuation with de-emphasis", + "Fixed process flow", "Ringing-less low latency FIR", }; diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c index 2cd4fe463102..1d1c7f8a9af2 100644 --- a/sound/soc/codecs/rt286.c +++ b/sound/soc/codecs/rt286.c @@ -861,10 +861,8 @@ static int rt286_hw_params(struct snd_pcm_substream *substream, RT286_I2S_CTRL1, 0x0018, d_len_code << 3); dev_dbg(codec->dev, "format val = 0x%x\n", val); - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - snd_soc_update_bits(codec, RT286_DAC_FORMAT, 0x407f, val); - else - snd_soc_update_bits(codec, RT286_ADC_FORMAT, 0x407f, val); + snd_soc_update_bits(codec, RT286_DAC_FORMAT, 0x407f, val); + snd_soc_update_bits(codec, RT286_ADC_FORMAT, 0x407f, val); return 0; } diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index c0fbe1881439..918ada9738b0 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -2083,10 +2083,14 @@ static int rt5677_set_pll1_event(struct snd_soc_dapm_widget *w, struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec); switch (event) { - case SND_SOC_DAPM_POST_PMU: + case SND_SOC_DAPM_PRE_PMU: regmap_update_bits(rt5677->regmap, RT5677_PLL1_CTRL2, 0x2, 0x2); + break; + + case SND_SOC_DAPM_POST_PMU: regmap_update_bits(rt5677->regmap, RT5677_PLL1_CTRL2, 0x2, 0x0); break; + default: return 0; } @@ -2101,10 +2105,14 @@ static int rt5677_set_pll2_event(struct snd_soc_dapm_widget *w, struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec); switch (event) { - case SND_SOC_DAPM_POST_PMU: + case SND_SOC_DAPM_PRE_PMU: regmap_update_bits(rt5677->regmap, RT5677_PLL2_CTRL2, 0x2, 0x2); + break; + + case SND_SOC_DAPM_POST_PMU: regmap_update_bits(rt5677->regmap, RT5677_PLL2_CTRL2, 0x2, 0x0); break; + default: return 0; } @@ -2212,9 +2220,11 @@ static int rt5677_vref_event(struct snd_soc_dapm_widget *w, static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("PLL1", RT5677_PWR_ANLG2, RT5677_PWR_PLL1_BIT, - 0, rt5677_set_pll1_event, SND_SOC_DAPM_POST_PMU), + 0, rt5677_set_pll1_event, SND_SOC_DAPM_PRE_PMU | + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("PLL2", RT5677_PWR_ANLG2, RT5677_PWR_PLL2_BIT, - 0, rt5677_set_pll2_event, SND_SOC_DAPM_POST_PMU), + 0, rt5677_set_pll2_event, SND_SOC_DAPM_PRE_PMU | + SND_SOC_DAPM_POST_PMU), /* Input Side */ /* micbias */ diff --git a/sound/soc/codecs/ts3a227e.c b/sound/soc/codecs/ts3a227e.c index 1d1205702d23..9f2dced046de 100644 --- a/sound/soc/codecs/ts3a227e.c +++ b/sound/soc/codecs/ts3a227e.c @@ -254,6 +254,7 @@ static int ts3a227e_i2c_probe(struct i2c_client *i2c, struct ts3a227e *ts3a227e; struct device *dev = &i2c->dev; int ret; + unsigned int acc_reg; ts3a227e = devm_kzalloc(&i2c->dev, sizeof(*ts3a227e), GFP_KERNEL); if (ts3a227e == NULL) @@ -283,6 +284,11 @@ static int ts3a227e_i2c_probe(struct i2c_client *i2c, INTB_DISABLE | ADC_COMPLETE_INT_DISABLE, ADC_COMPLETE_INT_DISABLE); + /* Read jack status because chip might not trigger interrupt at boot. */ + regmap_read(ts3a227e->regmap, TS3A227E_REG_ACCESSORY_STATUS, &acc_reg); + ts3a227e_new_jack_state(ts3a227e, acc_reg); + ts3a227e_jack_report(ts3a227e); + return 0; } diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 4d2d2b1380d5..75b87c5c0f04 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -1076,10 +1076,13 @@ static const struct snd_soc_dapm_route adc_intercon[] = { { "Right Capture PGA", NULL, "Right Capture Mux" }, { "Right Capture PGA", NULL, "Right Capture Inverting Mux" }, - { "AIFOUTL", "Left", "ADCL" }, - { "AIFOUTL", "Right", "ADCR" }, - { "AIFOUTR", "Left", "ADCL" }, - { "AIFOUTR", "Right", "ADCR" }, + { "AIFOUTL Mux", "Left", "ADCL" }, + { "AIFOUTL Mux", "Right", "ADCR" }, + { "AIFOUTR Mux", "Left", "ADCL" }, + { "AIFOUTR Mux", "Right", "ADCR" }, + + { "AIFOUTL", NULL, "AIFOUTL Mux" }, + { "AIFOUTR", NULL, "AIFOUTR Mux" }, { "ADCL", NULL, "CLK_DSP" }, { "ADCL", NULL, "Left Capture PGA" }, @@ -1089,12 +1092,16 @@ static const struct snd_soc_dapm_route adc_intercon[] = { }; static const struct snd_soc_dapm_route dac_intercon[] = { - { "DACL", "Right", "AIFINR" }, - { "DACL", "Left", "AIFINL" }, + { "DACL Mux", "Left", "AIFINL" }, + { "DACL Mux", "Right", "AIFINR" }, + + { "DACR Mux", "Left", "AIFINL" }, + { "DACR Mux", "Right", "AIFINR" }, + + { "DACL", NULL, "DACL Mux" }, { "DACL", NULL, "CLK_DSP" }, - { "DACR", "Right", "AIFINR" }, - { "DACR", "Left", "AIFINL" }, + { "DACR", NULL, "DACR Mux" }, { "DACR", NULL, "CLK_DSP" }, { "Charge pump", NULL, "SYSCLK" }, diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index 031a1ae71d94..a96eb497a379 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -556,7 +556,7 @@ static struct { { 22050, 2 }, { 24000, 2 }, { 16000, 3 }, - { 11250, 4 }, + { 11025, 4 }, { 12000, 4 }, { 8000, 5 }, }; diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h index 91a550f4a10d..5e793bbb6b02 100644 --- a/sound/soc/fsl/fsl_esai.h +++ b/sound/soc/fsl/fsl_esai.h @@ -302,7 +302,7 @@ #define ESAI_xCCR_xFP_MASK (((1 << ESAI_xCCR_xFP_WIDTH) - 1) << ESAI_xCCR_xFP_SHIFT) #define ESAI_xCCR_xFP(v) ((((v) - 1) << ESAI_xCCR_xFP_SHIFT) & ESAI_xCCR_xFP_MASK) #define ESAI_xCCR_xDC_SHIFT 9 -#define ESAI_xCCR_xDC_WIDTH 4 +#define ESAI_xCCR_xDC_WIDTH 5 #define ESAI_xCCR_xDC_MASK (((1 << ESAI_xCCR_xDC_WIDTH) - 1) << ESAI_xCCR_xDC_SHIFT) #define ESAI_xCCR_xDC(v) ((((v) - 1) << ESAI_xCCR_xDC_SHIFT) & ESAI_xCCR_xDC_MASK) #define ESAI_xCCR_xPSR_SHIFT 8 diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index a65f17d57ffb..059496ed9ad7 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -1362,9 +1362,9 @@ static int fsl_ssi_probe(struct platform_device *pdev) } ssi_private->irq = platform_get_irq(pdev, 0); - if (!ssi_private->irq) { + if (ssi_private->irq < 0) { dev_err(&pdev->dev, "no irq for node %s\n", np->full_name); - return -ENXIO; + return ssi_private->irq; } /* Are the RX and the TX clocks locked? */ diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c index 4caacb05a623..cd146d4fa805 100644 --- a/sound/soc/fsl/imx-wm8962.c +++ b/sound/soc/fsl/imx-wm8962.c @@ -257,6 +257,7 @@ static int imx_wm8962_probe(struct platform_device *pdev) if (ret) goto clk_fail; data->card.num_links = 1; + data->card.owner = THIS_MODULE; data->card.dai_link = &data->dai; data->card.dapm_widgets = imx_wm8962_dapm_widgets; data->card.num_dapm_widgets = ARRAY_SIZE(imx_wm8962_dapm_widgets); diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index fb9240fdc9b7..7fe3009b1c43 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -452,9 +452,8 @@ static int asoc_simple_card_parse_of(struct device_node *node, } /* Decrease the reference count of the device nodes */ -static int asoc_simple_card_unref(struct platform_device *pdev) +static int asoc_simple_card_unref(struct snd_soc_card *card) { - struct snd_soc_card *card = platform_get_drvdata(pdev); struct snd_soc_dai_link *dai_link; int num_links; @@ -556,7 +555,7 @@ static int asoc_simple_card_probe(struct platform_device *pdev) return ret; err: - asoc_simple_card_unref(pdev); + asoc_simple_card_unref(&priv->snd_card); return ret; } @@ -572,7 +571,7 @@ static int asoc_simple_card_remove(struct platform_device *pdev) snd_soc_jack_free_gpios(&simple_card_mic_jack, 1, &simple_card_mic_jack_gpio); - return asoc_simple_card_unref(pdev); + return asoc_simple_card_unref(card); } static const struct of_device_id asoc_simple_of_match[] = { diff --git a/sound/soc/intel/sst-firmware.c b/sound/soc/intel/sst-firmware.c index ef2e8b5766a1..b3f9489794a6 100644 --- a/sound/soc/intel/sst-firmware.c +++ b/sound/soc/intel/sst-firmware.c @@ -706,6 +706,7 @@ static int block_alloc_fixed(struct sst_dsp *dsp, struct sst_block_allocator *ba struct list_head *block_list) { struct sst_mem_block *block, *tmp; + struct sst_block_allocator ba_tmp = *ba; u32 end = ba->offset + ba->size, block_end; int err; @@ -730,9 +731,9 @@ static int block_alloc_fixed(struct sst_dsp *dsp, struct sst_block_allocator *ba if (ba->offset >= block->offset && ba->offset < block_end) { /* align ba to block boundary */ - ba->size -= block_end - ba->offset; - ba->offset = block_end; - err = block_alloc_contiguous(dsp, ba, block_list); + ba_tmp.size -= block_end - ba->offset; + ba_tmp.offset = block_end; + err = block_alloc_contiguous(dsp, &ba_tmp, block_list); if (err < 0) return -ENOMEM; @@ -767,10 +768,10 @@ static int block_alloc_fixed(struct sst_dsp *dsp, struct sst_block_allocator *ba list_move(&block->list, &dsp->used_block_list); list_add(&block->module_list, block_list); /* align ba to block boundary */ - ba->size -= block_end - ba->offset; - ba->offset = block_end; + ba_tmp.size -= block_end - ba->offset; + ba_tmp.offset = block_end; - err = block_alloc_contiguous(dsp, ba, block_list); + err = block_alloc_contiguous(dsp, &ba_tmp, block_list); if (err < 0) return -ENOMEM; diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c index 3f8c48231364..5bf14040c24a 100644 --- a/sound/soc/intel/sst-haswell-ipc.c +++ b/sound/soc/intel/sst-haswell-ipc.c @@ -1228,6 +1228,11 @@ int sst_hsw_stream_free(struct sst_hsw *hsw, struct sst_hsw_stream *stream) struct sst_dsp *sst = hsw->dsp; unsigned long flags; + if (!stream) { + dev_warn(hsw->dev, "warning: stream is NULL, no stream to free, ignore it.\n"); + return 0; + } + /* dont free DSP streams that are not commited */ if (!stream->commited) goto out; @@ -1415,6 +1420,16 @@ int sst_hsw_stream_commit(struct sst_hsw *hsw, struct sst_hsw_stream *stream) u32 header; int ret; + if (!stream) { + dev_warn(hsw->dev, "warning: stream is NULL, no stream to commit, ignore it.\n"); + return 0; + } + + if (stream->commited) { + dev_warn(hsw->dev, "warning: stream is already committed, ignore it.\n"); + return 0; + } + trace_ipc_request("stream alloc", stream->host_id); header = IPC_GLB_TYPE(IPC_GLB_ALLOCATE_STREAM); @@ -1519,6 +1534,11 @@ int sst_hsw_stream_pause(struct sst_hsw *hsw, struct sst_hsw_stream *stream, { int ret; + if (!stream) { + dev_warn(hsw->dev, "warning: stream is NULL, no stream to pause, ignore it.\n"); + return 0; + } + trace_ipc_request("stream pause", stream->reply.stream_hw_id); ret = sst_hsw_stream_operations(hsw, IPC_STR_PAUSE, @@ -1535,6 +1555,11 @@ int sst_hsw_stream_resume(struct sst_hsw *hsw, struct sst_hsw_stream *stream, { int ret; + if (!stream) { + dev_warn(hsw->dev, "warning: stream is NULL, no stream to resume, ignore it.\n"); + return 0; + } + trace_ipc_request("stream resume", stream->reply.stream_hw_id); ret = sst_hsw_stream_operations(hsw, IPC_STR_RESUME, @@ -1550,6 +1575,11 @@ int sst_hsw_stream_reset(struct sst_hsw *hsw, struct sst_hsw_stream *stream) { int ret, tries = 10; + if (!stream) { + dev_warn(hsw->dev, "warning: stream is NULL, no stream to reset, ignore it.\n"); + return 0; + } + /* dont reset streams that are not commited */ if (!stream->commited) return 0; diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c index 8b79cafab1e2..c7eb9dd67f60 100644 --- a/sound/soc/omap/omap-mcbsp.c +++ b/sound/soc/omap/omap-mcbsp.c @@ -434,7 +434,7 @@ static int omap_mcbsp_dai_set_dai_fmt(struct snd_soc_dai *cpu_dai, case SND_SOC_DAIFMT_CBM_CFS: /* McBSP slave. FS clock as output */ regs->srgr2 |= FSGM; - regs->pcr0 |= FSXM; + regs->pcr0 |= FSXM | FSRM; break; case SND_SOC_DAIFMT_CBM_CFM: /* McBSP slave */ diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c index 13d8507333b8..dcc26eda0539 100644 --- a/sound/soc/rockchip/rockchip_i2s.c +++ b/sound/soc/rockchip/rockchip_i2s.c @@ -335,6 +335,7 @@ static struct snd_soc_dai_driver rockchip_i2s_dai = { SNDRV_PCM_FMTBIT_S24_LE), }, .ops = &rockchip_i2s_dai_ops, + .symmetric_rates = 1, }; static const struct snd_soc_component_driver rockchip_i2s_component = { diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 590a82f01d0b..025c38fbe3c0 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -659,7 +659,8 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->dai_link->stream_name); ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num, - 1, 0, &be_pcm); + rtd->dai_link->dpcm_playback, + rtd->dai_link->dpcm_capture, &be_pcm); if (ret < 0) { dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n", rtd->dai_link->name); @@ -668,8 +669,10 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->pcm = be_pcm; rtd->fe_compr = 1; - be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; - be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; + if (rtd->dai_link->dpcm_playback) + be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; + else if (rtd->dai_link->dpcm_capture) + be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops)); } else memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops)); diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c index 790ceba6ad3f..28431d1bbcf5 100644 --- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c @@ -5,7 +5,10 @@ * ANY CHANGES MADE HERE WILL BE LOST! * */ - +#include <stdbool.h> +#ifndef HAS_BOOL +# define HAS_BOOL 1 +#endif #line 1 "Context.xs" /* * Context.xs. XS interfaces for perf script. diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 79999ceaf2be..01bc4e23a2cf 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -177,14 +177,17 @@ static int lock__parse(struct ins_operands *ops) goto out_free_ops; ops->locked.ins = ins__find(name); + free(name); + if (ops->locked.ins == NULL) goto out_free_ops; if (!ops->locked.ins->ops) return 0; - if (ops->locked.ins->ops->parse) - ops->locked.ins->ops->parse(ops->locked.ops); + if (ops->locked.ins->ops->parse && + ops->locked.ins->ops->parse(ops->locked.ops) < 0) + goto out_free_ops; return 0; @@ -208,6 +211,13 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size, static void lock__delete(struct ins_operands *ops) { + struct ins *ins = ops->locked.ins; + + if (ins && ins->ops->free) + ins->ops->free(ops->locked.ops); + else + ins__delete(ops->locked.ops); + zfree(&ops->locked.ops); zfree(&ops->target.raw); zfree(&ops->target.name); @@ -531,8 +541,8 @@ static void disasm_line__init_ins(struct disasm_line *dl) if (!dl->ins->ops) return; - if (dl->ins->ops->parse) - dl->ins->ops->parse(&dl->ops); + if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0) + dl->ins = NULL; } static int disasm_line__parse(char *line, char **namep, char **rawp) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index cbab1fb77b1d..2e507b5025a3 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1445,7 +1445,7 @@ int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused, case ENOENT: scnprintf(buf, size, "%s", "Error:\tUnable to find debugfs\n" - "Hint:\tWas your kernel was compiled with debugfs support?\n" + "Hint:\tWas your kernel compiled with debugfs support?\n" "Hint:\tIs the debugfs filesystem mounted?\n" "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); break; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 6951a9d42339..0e42438b1e59 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -116,6 +116,22 @@ struct thread; #define map__for_each_symbol(map, pos, n) \ dso__for_each_symbol(map->dso, pos, n, map->type) +/* map__for_each_symbol_with_name - iterate over the symbols in the given map + * that have the given name + * + * @map: the 'struct map *' in which symbols itereated + * @sym_name: the symbol name + * @pos: the 'struct symbol *' to use as a loop cursor + * @filter: to use when loading the DSO + */ +#define __map__for_each_symbol_by_name(map, sym_name, pos, filter) \ + for (pos = map__find_symbol_by_name(map, sym_name, filter); \ + pos && strcmp(pos->name, sym_name) == 0; \ + pos = symbol__next_by_name(pos)) + +#define map__for_each_symbol_by_name(map, sym_name, pos) \ + __map__for_each_symbol_by_name(map, sym_name, (pos), NULL) + typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 94a717bf007d..919937eb0be2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -446,7 +446,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs, } for (i = 0; i < ntevs; i++) { - if (tevs[i].point.address) { + if (tevs[i].point.address && !tevs[i].point.retprobe) { tmp = strdup(reloc_sym->name); if (!tmp) return -ENOMEM; @@ -2193,18 +2193,17 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, return ret; } -static char *looking_function_name; -static int num_matched_functions; - -static int probe_function_filter(struct map *map __maybe_unused, - struct symbol *sym) +static int find_probe_functions(struct map *map, char *name) { - if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && - strcmp(looking_function_name, sym->name) == 0) { - num_matched_functions++; - return 0; + int found = 0; + struct symbol *sym; + + map__for_each_symbol_by_name(map, name, sym) { + if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) + found++; } - return 1; + + return found; } #define strdup_or_goto(str, label) \ @@ -2222,10 +2221,10 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, struct kmap *kmap = NULL; struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; - struct rb_node *nd; struct probe_trace_event *tev; struct perf_probe_point *pp = &pev->point; struct probe_trace_point *tp; + int num_matched_functions; int ret, i; /* Init maps of given executable or kernel */ @@ -2242,10 +2241,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, * Load matched symbols: Since the different local symbols may have * same name but different addresses, this lists all the symbols. */ - num_matched_functions = 0; - looking_function_name = pp->function; - ret = map__load(map, probe_function_filter); - if (ret || num_matched_functions == 0) { + num_matched_functions = find_probe_functions(map, pp->function); + if (num_matched_functions == 0) { pr_err("Failed to find symbol %s in %s\n", pp->function, target ? : "kernel"); ret = -ENOENT; @@ -2257,7 +2254,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, goto out; } - if (!pev->uprobes) { + if (!pev->uprobes && !pp->retprobe) { kmap = map__kmap(map); reloc_sym = kmap->ref_reloc_sym; if (!reloc_sym) { @@ -2275,7 +2272,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } ret = 0; - map__for_each_symbol(map, sym, nd) { + + map__for_each_symbol_by_name(map, pp->function, sym) { tev = (*tevs) + ret; tp = &tev->point; if (ret == num_matched_functions) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index c24c5b83156c..a194702a0a2f 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -396,6 +396,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, const char *name) { struct rb_node *n; + struct symbol_name_rb_node *s; if (symbols == NULL) return NULL; @@ -403,7 +404,6 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, n = symbols->rb_node; while (n) { - struct symbol_name_rb_node *s; int cmp; s = rb_entry(n, struct symbol_name_rb_node, rb_node); @@ -414,10 +414,24 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, else if (cmp > 0) n = n->rb_right; else - return &s->sym; + break; } - return NULL; + if (n == NULL) + return NULL; + + /* return first symbol that has same name (if any) */ + for (n = rb_prev(n); n; n = rb_prev(n)) { + struct symbol_name_rb_node *tmp; + + tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); + if (strcmp(tmp->sym.name, s->sym.name)) + break; + + s = tmp; + } + + return &s->sym; } struct symbol *dso__find_symbol(struct dso *dso, @@ -436,6 +450,17 @@ struct symbol *dso__next_symbol(struct symbol *sym) return symbols__next(sym); } +struct symbol *symbol__next_by_name(struct symbol *sym) +{ + struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym); + struct rb_node *n = rb_next(&s->rb_node); + + return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL; +} + + /* + * Teturns first symbol that matched with @name. + */ struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 9d602e9c6f59..1650dcb3a67b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -231,6 +231,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); +struct symbol *symbol__next_by_name(struct symbol *sym); struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); struct symbol *dso__next_symbol(struct symbol *sym); |