From 0bc09f9cdc589e0b54724096138996a00b19babb Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Tue, 16 Dec 2014 14:52:50 +0530 Subject: phy: phy-ti-pipe3: fix inconsistent enumeration of PCIe gen2 cards Prior to DRA74x silicon rev 1.1, pcie_pcs register bits 8-15 and bits 16-23 were used to configure RC delay count for phy1 and phy2 respectively. phyid was used as index to distinguish the phys and to configure the delay values appropriately. As of DRA74x silicon rev 1.1, pcie_pcs register definition has changed. Bits 16-23 are used to configure delay values for *both* phy1 and phy2. Hence phyid is no longer required. So, drop id field from ti_pipe3 structure and its subsequent references for configuring pcie_pcs register. Also, pcie_pcs register now needs to be configured with delay value of 0x96 at bit positions 16-23. See register description of CTRL_CORE_PCIE_PCS in ARM572x TRM, SPRUHZ6, October 2014, section 18.5.2.2, table 18-1804. This is needed to ensure Gen2 cards are enumerated consistently. DRA72x silicon behaves same way as DRA74x rev 1.1 as far as this functionality is considered. Test results on DRA74x and DRA72x EVMs: Before patch ------------ DRA74x ES 1.0: Gen1 cards work, Gen2 cards do not work (expected result due to silicon errata) DRA74x ES 1.1: Gen1 cards work, Gen2 cards do not work sometimes due to incorrect programming of register DRA72x: Gen1 cards work, Gen2 cards do not work sometimes due to incorrect programming of register After patch ----------- DRA74x ES 1.0: Gen1 cards work, Gen2 cards do not work (expected result due to silicon errata) DRA74x ES 1.1: Gen1 cards work, Gen2 cards work consistently. DRA72x: Gen1 and Gen2 cards enumerate consistently. Signed-off-by: Vignesh R Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/omap_control_phy.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/phy/omap_control_phy.h b/include/linux/phy/omap_control_phy.h index e9e6cfbfbb58..eb7d4a135a9e 100644 --- a/include/linux/phy/omap_control_phy.h +++ b/include/linux/phy/omap_control_phy.h @@ -66,7 +66,7 @@ enum omap_control_usb_mode { #define OMAP_CTRL_PIPE3_PHY_TX_RX_POWEROFF 0x0 #define OMAP_CTRL_PCIE_PCS_MASK 0xff -#define OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT 0x8 +#define OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT 16 #define OMAP_CTRL_USB2_PHY_PD BIT(28) @@ -79,7 +79,7 @@ enum omap_control_usb_mode { void omap_control_phy_power(struct device *dev, int on); void omap_control_usb_set_mode(struct device *dev, enum omap_control_usb_mode mode); -void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay); +void omap_control_pcie_pcs(struct device *dev, u8 delay); #else static inline void omap_control_phy_power(struct device *dev, int on) @@ -91,7 +91,7 @@ static inline void omap_control_usb_set_mode(struct device *dev, { } -static inline void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay) +static inline void omap_control_pcie_pcs(struct device *dev, u8 delay) { } #endif -- cgit v1.2.3 From ceb3a16c070c403f5f9ca46b46cf2bb79ea11750 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 3 Jan 2015 15:16:04 -0500 Subject: NFSv4: Cache the NFSv4/v4.1 client owner_id in the struct nfs_client Ensure that we cache the NFSv4/v4.1 client owner_id so that we can verify it when we're doing trunking detection. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4client.c | 1 + fs/nfs/nfs4proc.c | 19 +++++++++++++++---- include/linux/nfs_fs_sb.h | 3 +++ 3 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d949d0f378ec..6ee9bf69a7a6 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -228,6 +228,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) kfree(clp->cl_serverowner); kfree(clp->cl_serverscope); kfree(clp->cl_implid); + kfree(clp->cl_owner_id); } void nfs4_free_client(struct nfs_client *clp) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e7f8d5ff2581..1fab51682042 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4917,11 +4917,14 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, } static unsigned int -nfs4_init_nonuniform_client_string(const struct nfs_client *clp, +nfs4_init_nonuniform_client_string(struct nfs_client *clp, char *buf, size_t len) { unsigned int result; + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); + rcu_read_lock(); result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s", clp->cl_ipaddr, @@ -4930,24 +4933,32 @@ nfs4_init_nonuniform_client_string(const struct nfs_client *clp, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO)); rcu_read_unlock(); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); return result; } static unsigned int -nfs4_init_uniform_client_string(const struct nfs_client *clp, +nfs4_init_uniform_client_string(struct nfs_client *clp, char *buf, size_t len) { const char *nodename = clp->cl_rpcclient->cl_nodename; + unsigned int result; + + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); if (nfs4_client_id_uniquifier[0] != '\0') - return scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", + result = scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", clp->rpc_ops->version, clp->cl_minorversion, nfs4_client_id_uniquifier, nodename); - return scnprintf(buf, len, "Linux NFSv%u.%u %s", + else + result = scnprintf(buf, len, "Linux NFSv%u.%u %s", clp->rpc_ops->version, clp->cl_minorversion, nodename); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); + return result; } /* diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1e37fbb78f7a..ddea982355f3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -74,6 +74,9 @@ struct nfs_client { /* idmapper */ struct idmap * cl_idmap; + /* Client owner identifier */ + const char * cl_owner_id; + /* Our own IP address, as a null-terminated string. * This is used to generate the mv0 callback address. */ -- cgit v1.2.3 From 6ada1fc0e1c4775de0e043e1bd3ae9d065491aa5 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 3 Dec 2014 19:22:48 -0500 Subject: time: settimeofday: Validate the values of tv from user An unvalidated user input is multiplied by a constant, which can result in an undefined behaviour for large values. While this is validated later, we should avoid triggering undefined behaviour. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: stable Signed-off-by: Sasha Levin [jstultz: include trivial milisecond->microsecond correction noticed by Andy] Signed-off-by: John Stultz --- include/linux/time.h | 13 +++++++++++++ kernel/time/time.c | 4 ++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/time.h b/include/linux/time.h index 8c42cf8d2444..5989b0ead1ec 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -99,6 +99,19 @@ static inline bool timespec_valid_strict(const struct timespec *ts) return true; } +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + extern struct timespec timespec_trunc(struct timespec t, unsigned gran); #define CURRENT_TIME (current_kernel_time()) diff --git a/kernel/time/time.c b/kernel/time/time.c index a9ae20fb0b11..22d5d3b73970 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -196,6 +196,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, if (tv) { if (copy_from_user(&user_tv, tv, sizeof(*tv))) return -EFAULT; + + if (!timeval_valid(&user_tv)) + return -EINVAL; + new_ts.tv_sec = user_tv.tv_sec; new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; } -- cgit v1.2.3 From e61f7d1c3c07a7e51036b0796749edb00deff845 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 8 Jan 2015 10:34:27 -0500 Subject: libata: Whitelist SSDs that are known to properly return zeroes after TRIM As defined, the DRAT (Deterministic Read After Trim) and RZAT (Return Zero After Trim) flags in the ATA Command Set are unreliable in the sense that they only define what happens if the device successfully executed the DSM TRIM command. TRIM is only advisory, however, and the device is free to silently ignore all or parts of the request. In practice this renders the DRAT and RZAT flags completely useless and because the results are unpredictable we decided to disable discard in MD for 3.18 to avoid the risk of data corruption. Hardware vendors in the real world obviously need better guarantees than what the standards bodies provide. Unfortuntely those guarantees are encoded in product requirements documents rather than somewhere we can key off of them programatically. So we are compelled to disabling discard_zeroes_data for all devices unless we explicitly have data to support whitelisting them. This patch whitelists SSDs from a few of the main vendors. None of the whitelists are based on written guarantees. They are purely based on empirical evidence collected from internal and external users that have tested or qualified these drives in RAID deployments. The whitelist is only meant as a starting point and is by no means comprehensive: - All intel SSD models except for 510 - Micron M5?0/M600 - Samsung SSDs - Seagate SSDs Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 31 +++++++++++++++++++++++++++---- drivers/ata/libata-scsi.c | 10 ++++++---- include/linux/libata.h | 1 + 3 files changed, 34 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 5c84fb5c3372..23c2ae03a7ab 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4233,10 +4233,33 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* devices that don't properly handle queued TRIM commands */ - { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Micron_M550*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT*M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Micron_M[56]*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Crucial_CT*SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + + /* + * As defined, the DRAT (Deterministic Read After Trim) and RZAT + * (Return Zero After Trim) flags in the ATA Command Set are + * unreliable in the sense that they only define what happens if + * the device successfully executed the DSM TRIM command. TRIM + * is only advisory, however, and the device is free to silently + * ignore all or parts of the request. + * + * Whitelist drives that are known to reliably return zeroes + * after TRIM. + */ + + /* + * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude + * that model before whitelisting all other intel SSDs. + */ + { "INTEL*SSDSC2MH*", NULL, 0, }, + + { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e364e86e84d7..6abd17a85b13 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2532,13 +2532,15 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) rbuf[15] = lowest_aligned; if (ata_id_has_trim(args->id)) { - rbuf[14] |= 0x80; /* TPE */ + rbuf[14] |= 0x80; /* LBPME */ - if (ata_id_has_zero_after_trim(args->id)) - rbuf[14] |= 0x40; /* TPRZ */ + if (ata_id_has_zero_after_trim(args->id) && + dev->horkage & ATA_HORKAGE_ZERO_AFTER_TRIM) { + ata_dev_info(dev, "Enabling discard_zeroes_data\n"); + rbuf[14] |= 0x40; /* LBPRZ */ + } } } - return 0; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 2d182413b1db..f2b440e44fd7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -422,6 +422,7 @@ enum { ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ + ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From ad26aa6c60974acf3228ed0ade97ba5793093dbe Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Thu, 8 Jan 2015 11:04:07 +0900 Subject: regulator: s2mps11: Fix wrong calculation of register offset This patch adds missing registers('BUCK7_SW' & 'LDO29_CTRL'). Since BUCK7 has 1 more register (BUCK7_SW) than others, register offset should be added one more for which has bigger address than BUCK7 registers. Fixes: 76b9840b24ae04(regulator: s2mps11: Add support S2MPS13 regulator device) Signed-off-by: Jonghwa Lee Signed-off-by: Chanwoo Choi Signed-off-by: Mark Brown Cc: --- drivers/regulator/s2mps11.c | 42 +++++++++++++++++++++++++++++++++---- include/linux/mfd/samsung/s2mps13.h | 2 ++ 2 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index c1444c3d84c2..13ca20ed33a6 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -405,6 +405,40 @@ static struct regulator_ops s2mps14_reg_ops; .enable_mask = S2MPS14_ENABLE_MASK \ } +#define regulator_desc_s2mps13_buck7(num, min, step, min_sel) { \ + .name = "BUCK"#num, \ + .id = S2MPS13_BUCK##num, \ + .ops = &s2mps14_reg_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = min, \ + .uV_step = step, \ + .linear_min_sel = min_sel, \ + .n_voltages = S2MPS14_BUCK_N_VOLTAGES, \ + .ramp_delay = S2MPS13_BUCK_RAMP_DELAY, \ + .vsel_reg = S2MPS13_REG_B1OUT + (num) * 2 - 1, \ + .vsel_mask = S2MPS14_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS13_REG_B1CTRL + (num - 1) * 2, \ + .enable_mask = S2MPS14_ENABLE_MASK \ +} + +#define regulator_desc_s2mps13_buck8_10(num, min, step, min_sel) { \ + .name = "BUCK"#num, \ + .id = S2MPS13_BUCK##num, \ + .ops = &s2mps14_reg_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = min, \ + .uV_step = step, \ + .linear_min_sel = min_sel, \ + .n_voltages = S2MPS14_BUCK_N_VOLTAGES, \ + .ramp_delay = S2MPS13_BUCK_RAMP_DELAY, \ + .vsel_reg = S2MPS13_REG_B1OUT + (num) * 2 - 1, \ + .vsel_mask = S2MPS14_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS13_REG_B1CTRL + (num) * 2 - 1, \ + .enable_mask = S2MPS14_ENABLE_MASK \ +} + static const struct regulator_desc s2mps13_regulators[] = { regulator_desc_s2mps13_ldo(1, MIN_800_MV, STEP_12_5_MV, 0x00), regulator_desc_s2mps13_ldo(2, MIN_1400_MV, STEP_50_MV, 0x0C), @@ -452,10 +486,10 @@ static const struct regulator_desc s2mps13_regulators[] = { regulator_desc_s2mps13_buck(4, MIN_500_MV, STEP_6_25_MV, 0x10), regulator_desc_s2mps13_buck(5, MIN_500_MV, STEP_6_25_MV, 0x10), regulator_desc_s2mps13_buck(6, MIN_500_MV, STEP_6_25_MV, 0x10), - regulator_desc_s2mps13_buck(7, MIN_500_MV, STEP_6_25_MV, 0x10), - regulator_desc_s2mps13_buck(8, MIN_1000_MV, STEP_12_5_MV, 0x20), - regulator_desc_s2mps13_buck(9, MIN_1000_MV, STEP_12_5_MV, 0x20), - regulator_desc_s2mps13_buck(10, MIN_500_MV, STEP_6_25_MV, 0x10), + regulator_desc_s2mps13_buck7(7, MIN_500_MV, STEP_6_25_MV, 0x10), + regulator_desc_s2mps13_buck8_10(8, MIN_1000_MV, STEP_12_5_MV, 0x20), + regulator_desc_s2mps13_buck8_10(9, MIN_1000_MV, STEP_12_5_MV, 0x20), + regulator_desc_s2mps13_buck8_10(10, MIN_500_MV, STEP_6_25_MV, 0x10), }; static int s2mps14_regulator_enable(struct regulator_dev *rdev) diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h index ce5dda8958fe..b1fd675fa36f 100644 --- a/include/linux/mfd/samsung/s2mps13.h +++ b/include/linux/mfd/samsung/s2mps13.h @@ -59,6 +59,7 @@ enum s2mps13_reg { S2MPS13_REG_B6CTRL, S2MPS13_REG_B6OUT, S2MPS13_REG_B7CTRL, + S2MPS13_REG_B7SW, S2MPS13_REG_B7OUT, S2MPS13_REG_B8CTRL, S2MPS13_REG_B8OUT, @@ -102,6 +103,7 @@ enum s2mps13_reg { S2MPS13_REG_L26CTRL, S2MPS13_REG_L27CTRL, S2MPS13_REG_L28CTRL, + S2MPS13_REG_L29CTRL, S2MPS13_REG_L30CTRL, S2MPS13_REG_L31CTRL, S2MPS13_REG_L32CTRL, -- cgit v1.2.3 From 029b18361921a0a07b17bd89a2cf20df3d115de8 Mon Sep 17 00:00:00 2001 From: Gabriel Laskar Date: Sun, 11 Jan 2015 16:18:06 -0800 Subject: Input: uinput - fix ioctl nr overflow for UI_GET_SYSNAME/VERSION Request number for ioctls are encoded as 8bit numbers, but unfortunately UI_GET_SYSNAME and UI_GET_VERSION specifu values larger than that, so they get truncated to 44 (0x2c) and 45 (0x2d). This change makes requested values match their effective values (the ABI stays intact). Signed-off-by: Gabriel Laskar Signed-off-by: Dmitry Torokhov --- include/uapi/linux/uinput.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/uinput.h b/include/uapi/linux/uinput.h index baeab83deb64..013c9d8db372 100644 --- a/include/uapi/linux/uinput.h +++ b/include/uapi/linux/uinput.h @@ -82,7 +82,7 @@ struct uinput_ff_erase { * The complete sysfs path is then /sys/devices/virtual/input/--NAME-- * Usually, it is in the form "inputN" */ -#define UI_GET_SYSNAME(len) _IOC(_IOC_READ, UINPUT_IOCTL_BASE, 300, len) +#define UI_GET_SYSNAME(len) _IOC(_IOC_READ, UINPUT_IOCTL_BASE, 44, len) /** * UI_GET_VERSION - Return version of uinput protocol @@ -91,7 +91,7 @@ struct uinput_ff_erase { * the integer pointed to by the ioctl argument. The protocol version * is hard-coded in the kernel and is independent of the uinput device. */ -#define UI_GET_VERSION _IOR(UINPUT_IOCTL_BASE, 301, unsigned int) +#define UI_GET_VERSION _IOR(UINPUT_IOCTL_BASE, 45, unsigned int) /* * To write a force-feedback-capable driver, the upload_effect -- cgit v1.2.3 From d6613aa750ad66b25737231415050f1dca924eb7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 10 Dec 2014 14:54:28 +0100 Subject: ARM: dt: GIC: Spelling s/specific/specifier/, s/flaggs/flags/ Signed-off-by: Geert Uytterhoeven Cc: Stephen Warren Cc: Rob Herring Signed-off-by: Rob Herring --- include/dt-bindings/interrupt-controller/arm-gic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/interrupt-controller/arm-gic.h b/include/dt-bindings/interrupt-controller/arm-gic.h index 1ea1b702fec2..d4110d5caa3e 100644 --- a/include/dt-bindings/interrupt-controller/arm-gic.h +++ b/include/dt-bindings/interrupt-controller/arm-gic.h @@ -7,14 +7,14 @@ #include -/* interrupt specific cell 0 */ +/* interrupt specifier cell 0 */ #define GIC_SPI 0 #define GIC_PPI 1 /* * Interrupt specifier cell 2. - * The flaggs in irq.h are valid, plus those below. + * The flags in irq.h are valid, plus those below. */ #define GIC_CPU_MASK_RAW(x) ((x) << 8) #define GIC_CPU_MASK_SIMPLE(num) GIC_CPU_MASK_RAW((1 << (num)) - 1) -- cgit v1.2.3 From 6cfda7fbebe8a4fd33ea5722fa0212f98f643c35 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 5 Jan 2015 19:47:43 +0100 Subject: can: m_can: tag current CAN FD controllers as non-ISO During the CAN FD standardization process within the ISO it turned out that the failure detection capability has to be improved. The CAN in Automation organization (CiA) defined the already implemented CAN FD controllers as 'non-ISO' and the upcoming improved CAN FD controllers as 'ISO' compliant. See at http://www.can-cia.com/index.php?id=1937 Finally there will be three types of CAN FD controllers in the future: 1. ISO compliant (fixed) 2. non-ISO compliant (fixed, like the M_CAN IP v3.0.1 in m_can.c) 3. ISO/non-ISO CAN FD controllers (switchable, like the PEAK USB FD) So the current M_CAN driver for the M_CAN IP v3.0.1 has to expose its non-ISO implementation by setting the CAN_CTRLMODE_FD_NON_ISO ctrlmode at startup. As this bit cannot be switched at configuration time CAN_CTRLMODE_FD_NON_ISO must not be set in ctrlmode_supported of the current M_CAN driver. Signed-off-by: Oliver Hartkopp Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 5 +++++ include/uapi/linux/can/netlink.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index d7bc462aafdc..244529881be9 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -955,6 +955,11 @@ static struct net_device *alloc_m_can_dev(void) priv->can.data_bittiming_const = &m_can_data_bittiming_const; priv->can.do_set_mode = m_can_set_mode; priv->can.do_get_berr_counter = m_can_get_berr_counter; + + /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.1 */ + priv->can.ctrlmode = CAN_CTRLMODE_FD_NON_ISO; + + /* CAN_CTRLMODE_FD_NON_ISO can not be changed with M_CAN IP v3.0.1 */ priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING | diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 3e4323a3918d..94ffe0c83ce7 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -98,6 +98,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ #define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */ #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ +#define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ /* * CAN device statistics -- cgit v1.2.3 From f331a859e0ee5a898c1f47596eddad4c4f02d657 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 15 Jan 2015 18:16:04 -0600 Subject: PCI: Add flag for devices where we can't use bus reset Enable a mechanism for devices to quirk that they do not behave when doing a PCI bus reset. We require a modest level of spec compliant behavior in order to do a reset, for instance the device should come out of reset without throwing errors and PCI config space should be accessible after reset. This is too much to ask for some devices. Link: http://lkml.kernel.org/r/20140923210318.498dacbd@dualc.maya.org Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.14+ --- drivers/pci/pci.c | 40 ++++++++++++++++++++++++++++++++++++---- include/linux/pci.h | 2 ++ 2 files changed, 38 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index cab05f31223f..e9d4fd861ba1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3271,7 +3271,8 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) + if (pci_is_root_bus(dev->bus) || dev->subordinate || + !dev->bus->self || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3305,7 +3306,8 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (dev->subordinate || !dev->slot) + if (dev->subordinate || !dev->slot || + dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3557,6 +3559,20 @@ int pci_try_reset_function(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_try_reset_function); +/* Do any devices on or below this bus prevent a bus reset? */ +static bool pci_bus_resetable(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_bus_lock(struct pci_bus *bus) { @@ -3607,6 +3623,22 @@ unlock: return 0; } +/* Do any devices on or below this slot prevent a bus reset? */ +static bool pci_slot_resetable(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_slot_lock(struct pci_slot *slot) { @@ -3728,7 +3760,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe) { int rc; - if (!slot) + if (!slot || !pci_slot_resetable(slot)) return -ENOTTY; if (!probe) @@ -3820,7 +3852,7 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot); static int pci_bus_reset(struct pci_bus *bus, int probe) { - if (!bus->self) + if (!bus->self || !pci_bus_resetable(bus)) return -ENOTTY; if (probe) diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..44627f1df4ca 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -175,6 +175,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4), /* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */ PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), + /* Do not use bus resets for device */ + PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From 8505e729a2f6eb0803ff943a15f133dd10afff3a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 15 Jan 2015 16:21:49 -0600 Subject: PCI: Add pci_claim_bridge_resource() to clip window if necessary Add pci_claim_bridge_resource() to claim a PCI-PCI bridge window. This is like regular pci_claim_resource(), except that if we fail to claim the window, we check to see if we can reduce the size of the window and try again. This is for scenarios like this: pci_bus 0000:00: root bus resource [mem 0xc0000000-0xffffffff] pci 0000:00:01.0: bridge window [mem 0xbdf00000-0xddefffff 64bit pref] pci 0000:01:00.0: reg 0x10: [mem 0xc0000000-0xcfffffff pref] The 00:01.0 window is illegal: it starts before the host bridge window, so we have to assume the [0xbdf00000-0xbfffffff] region is inaccessible. We can make it legal by clipping it to [mem 0xc0000000-0xddefffff 64bit pref]. Previously we discarded the 00:01.0 window and tried to reassign that part of the hierarchy from scratch. That is a problem because Linux doesn't always assign things optimally. For example, in this case, BIOS put the 01:00.0 device in a prefetchable window below 4GB, but after 5b28541552ef, Linux puts the prefetchable window above 4GB where the 32-bit 01:00.0 device can't use it. Clipping the 00:01.0 window is less intrusive than completely reassigning things and is sufficient to let us use most of the BIOS configuration. Of course, it's possible that devices below 00:01.0 will no longer fit. If that's the case, we'll have to reassign things. But that's a separate problem. [bhelgaas: changelog, split into separate patch] Link: https://bugzilla.kernel.org/show_bug.cgi?id=85491 Reported-by: Marek Kordik Fixes: 5b28541552ef ("PCI: Restrict 64-bit prefetchable bridge windows to 64-bit resources") Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.16+ --- drivers/pci/setup-bus.c | 35 +++++++++++++++++++++++++++++++++++ include/linux/pci.h | 1 + 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 802f56be2149..e3e17f3c0f0f 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -646,6 +646,41 @@ void pci_setup_bridge(struct pci_bus *bus) __pci_setup_bridge(bus, type); } + +int pci_claim_bridge_resource(struct pci_dev *bridge, int i) +{ + if (i < PCI_BRIDGE_RESOURCES || i > PCI_BRIDGE_RESOURCE_END) + return 0; + + if (pci_claim_resource(bridge, i) == 0) + return 0; /* claimed the window */ + + if ((bridge->class >> 8) != PCI_CLASS_BRIDGE_PCI) + return 0; + + if (!pci_bus_clip_resource(bridge, i)) + return -EINVAL; /* clipping didn't change anything */ + + switch (i - PCI_BRIDGE_RESOURCES) { + case 0: + pci_setup_bridge_io(bridge); + break; + case 1: + pci_setup_bridge_mmio(bridge); + break; + case 2: + pci_setup_bridge_mmio_pref(bridge); + break; + default: + return -EINVAL; + } + + if (pci_claim_resource(bridge, i) == 0) + return 0; /* claimed a smaller window */ + + return -EINVAL; +} + /* Check whether the bridge supports optional I/O and prefetchable memory ranges. If not, the respective base/limit registers must be read-only and read as 0. */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 44627f1df4ca..9603094ed59b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1067,6 +1067,7 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); void pci_bus_assign_resources(const struct pci_bus *bus); void pci_bus_size_bridges(struct pci_bus *bus); int pci_claim_resource(struct pci_dev *, int); +int pci_claim_bridge_resource(struct pci_dev *bridge, int i); void pci_assign_unassigned_resources(void); void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge); void pci_assign_unassigned_bus_resources(struct pci_bus *bus); -- cgit v1.2.3 From f555f3d76aaade29c7e221a37ee64fe722955c09 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 11:37:12 +0100 Subject: genetlink: document parallel_ops The kernel-doc for the parallel_ops family struct member is missing, add it. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 84125088c309..2ea2c55bdc87 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -27,6 +27,8 @@ struct genl_info; * @maxattr: maximum number of attributes supported * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them + * @parallel_ops: operations can be called in parallel and aren't + * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may -- cgit v1.2.3 From ee1c244219fd652964710a6cc3e4f922e86aa492 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 11:37:14 +0100 Subject: genetlink: synchronize socket closing and family removal In addition to the problem Jeff Layton reported, I looked at the code and reproduced the same warning by subscribing and removing the genl family with a socket still open. This is a fairly tricky race which originates in the fact that generic netlink allows the family to go away while sockets are still open - unlike regular netlink which has a module refcount for every open socket so in general this cannot be triggered. Trying to resolve this issue by the obvious locking isn't possible as it will result in deadlocks between unregistration and group unbind notification (which incidentally lockdep doesn't find due to the home grown locking in the netlink table.) To really resolve this, introduce a "closing socket" reference counter (for generic netlink only, as it's the only affected family) in the core netlink code and use that in generic netlink to wait for all the sockets that are being closed at the same time as a generic netlink family is removed. This fixes the race that when a socket is closed, it will should call the unbind, but if the family is removed at the same time the unbind will not find it, leading to the warning. The real problem though is that in this case the unbind could actually find a new family that is registered to have a multicast group with the same ID, and call its mcast_unbind() leading to confusing. Also remove the warning since it would still trigger, but is now no longer a problem. This also moves the code in af_netlink.c to before unreferencing the module to avoid having the same problem in the normal non-genl case. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genetlink.h | 4 ++++ include/net/genetlink.h | 5 ++++- net/netlink/af_netlink.c | 24 +++++++++++++++++------- net/netlink/af_netlink.h | 1 + net/netlink/genetlink.c | 16 +++++++++------- 5 files changed, 35 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 55b685719d52..09460d6d6682 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -11,6 +11,10 @@ extern void genl_unlock(void); extern int lockdep_genl_is_held(void); #endif +/* for synchronisation between af_netlink and genetlink */ +extern atomic_t genl_sk_destructing_cnt; +extern wait_queue_head_t genl_sk_destructing_waitq; + /** * rcu_dereference_genl - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 2ea2c55bdc87..6c92415311ca 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -35,7 +35,10 @@ struct genl_info; * undo operations done by pre_doit, for example release locks * @mcast_bind: a socket bound to the given multicast group (which * is given as the offset into the groups array) - * @mcast_unbind: a socket was unbound from the given multicast group + * @mcast_unbind: a socket was unbound from the given multicast group. + * Note that unbind() will not be called symmetrically if the + * generic netlink family is removed while there are still open + * sockets. * @attrbuf: buffer to store parsed attributes * @family_list: family list * @mcgrps: multicast groups used by this family (private) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 84ea76ca3f1f..02fdde28dada 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -61,6 +61,7 @@ #include #include #include +#include #include #include @@ -1095,6 +1096,8 @@ static void netlink_remove(struct sock *sk) __sk_del_bind_node(sk); netlink_update_listeners(sk); } + if (sk->sk_protocol == NETLINK_GENERIC) + atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } @@ -1211,6 +1214,20 @@ static int netlink_release(struct socket *sock) * will be purged. */ + /* must not acquire netlink_table_lock in any way again before unbind + * and notifying genetlink is done as otherwise it might deadlock + */ + if (nlk->netlink_unbind) { + int i; + + for (i = 0; i < nlk->ngroups; i++) + if (test_bit(i, nlk->groups)) + nlk->netlink_unbind(sock_net(sk), i + 1); + } + if (sk->sk_protocol == NETLINK_GENERIC && + atomic_dec_return(&genl_sk_destructing_cnt) == 0) + wake_up(&genl_sk_destructing_waitq); + sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); @@ -1246,13 +1263,6 @@ static int netlink_release(struct socket *sock) netlink_table_ungrab(); } - if (nlk->netlink_unbind) { - int i; - - for (i = 0; i < nlk->ngroups; i++) - if (test_bit(i, nlk->groups)) - nlk->netlink_unbind(sock_net(sk), i + 1); - } kfree(nlk->groups); nlk->groups = NULL; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index f123a88496f8..f1c31b39aa3e 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -2,6 +2,7 @@ #define _AF_NETLINK_H #include +#include #include #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c18d3f5624b2..ee57459fc258 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -23,6 +23,9 @@ static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); +atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); +DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); + void genl_lock(void) { mutex_lock(&genl_mutex); @@ -435,15 +438,18 @@ int genl_unregister_family(struct genl_family *family) genl_lock_all(); - genl_unregister_mc_groups(family); - list_for_each_entry(rc, genl_family_chain(family->id), family_list) { if (family->id != rc->id || strcmp(rc->name, family->name)) continue; + genl_unregister_mc_groups(family); + list_del(&rc->family_list); family->n_ops = 0; - genl_unlock_all(); + up_write(&cb_lock); + wait_event(genl_sk_destructing_waitq, + atomic_read(&genl_sk_destructing_cnt) == 0); + genl_unlock(); kfree(family->attrbuf); genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); @@ -1014,7 +1020,6 @@ static int genl_bind(struct net *net, int group) static void genl_unbind(struct net *net, int group) { int i; - bool found = false; down_read(&cb_lock); for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { @@ -1027,14 +1032,11 @@ static void genl_unbind(struct net *net, int group) if (f->mcast_unbind) f->mcast_unbind(net, fam_grp); - found = true; break; } } } up_read(&cb_lock); - - WARN_ON(!found); } static int __net_init genl_pernet_init(struct net *net) -- cgit v1.2.3 From cdef511985374dd042a40bb32c1c346c2662c9dc Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 15 Jan 2015 15:21:19 +0100 Subject: KVM: fix sparse warning in include/trace/events/kvm.h sparse complains about include/trace/events/kvm.h:163:1: error: directive in argument list include/trace/events/kvm.h:167:1: error: directive in argument list include/trace/events/kvm.h:169:1: error: directive in argument list and sparse is right. Preprocessing directives in an argument of a macro are undefined behaviour as of C99 6.10.3p11. Lets use an indirection to fix this. Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/trace/events/kvm.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 6edf1f2028cd..86b399c66c3d 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -146,6 +146,14 @@ TRACE_EVENT(kvm_msi_set_irq, #if defined(CONFIG_HAVE_KVM_IRQFD) +#ifdef kvm_irqchips +#define kvm_ack_irq_string "irqchip %s pin %u" +#define kvm_ack_irq_parm __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin +#else +#define kvm_ack_irq_string "irqchip %d pin %u" +#define kvm_ack_irq_parm __entry->irqchip, __entry->pin +#endif + TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), TP_ARGS(irqchip, pin), @@ -160,13 +168,7 @@ TRACE_EVENT(kvm_ack_irq, __entry->pin = pin; ), -#ifdef kvm_irqchips - TP_printk("irqchip %s pin %u", - __print_symbolic(__entry->irqchip, kvm_irqchips), - __entry->pin) -#else - TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin) -#endif + TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm) ); #endif /* defined(CONFIG_HAVE_KVM_IRQFD) */ -- cgit v1.2.3 From 72dd299d5039a336493993dcc63413cf31d0e662 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 16 Jan 2015 15:13:02 -0800 Subject: libata: allow sata_sil24 to opt-out of tag ordered submission Ronny reports: https://bugzilla.kernel.org/show_bug.cgi?id=87101 "Since commit 8a4aeec8d "libata/ahci: accommodate tag ordered controllers" the access to the harddisk on the first SATA-port is failing on its first access. The access to the harddisk on the second port is working normal. When reverting the above commit, access to both harddisks is working fine again." Maintain tag ordered submission as the default, but allow sata_sil24 to continue with the old behavior. Cc: Cc: Tejun Heo Reported-by: Ronny Hegewald Signed-off-by: Dan Williams Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 5 ++++- drivers/ata/sata_sil24.c | 2 +- include/linux/libata.h | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 23c2ae03a7ab..d1a05f9bb91f 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4771,7 +4771,10 @@ static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap) return NULL; for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) { - tag = tag < max_queue ? tag : 0; + if (ap->flags & ATA_FLAG_LOWTAG) + tag = i; + else + tag = tag < max_queue ? tag : 0; /* the last tag is reserved for internal command. */ if (tag == ATA_TAG_INTERNAL) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index d81b20ddb527..ea655949023f 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -246,7 +246,7 @@ enum { /* host flags */ SIL24_COMMON_FLAGS = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA | - ATA_FLAG_AN | ATA_FLAG_PMP, + ATA_FLAG_AN | ATA_FLAG_PMP | ATA_FLAG_LOWTAG, SIL24_FLAG_PCIX_IRQ_WOC = (1 << 24), /* IRQ loss errata on PCI-X */ IRQ_STAT_4PORTS = 0xf, diff --git a/include/linux/libata.h b/include/linux/libata.h index f2b440e44fd7..91f705de2c0b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -231,6 +231,7 @@ enum { ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity * led */ ATA_FLAG_NO_DIPM = (1 << 23), /* host not happy with DIPM */ + ATA_FLAG_LOWTAG = (1 << 24), /* host wants lowest available tag */ /* bits 24:31 of ap->flags are reserved for LLD specific flags */ -- cgit v1.2.3 From d453cded05ee219b77815ea194dc36efa5398bca Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 20 Jan 2015 09:07:04 +1030 Subject: module_arch_freeing_init(): new hook for archs before module->module_init freed. Archs have been abusing module_free() to clean up their arch-specific allocations. Since module_free() is also (ab)used by BPF and trace code, let's keep it to simple allocations, and provide a hook called before that. This means that avr32, ia64, parisc and s390 no longer need to implement their own module_free() at all. avr32 doesn't need module_finalize() either. Signed-off-by: Rusty Russell Cc: Chris Metcalf Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Tony Luck Cc: Fenghua Yu Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux-kernel@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linux-s390@vger.kernel.org --- arch/avr32/kernel/module.c | 13 +------------ arch/ia64/kernel/module.c | 6 ++---- arch/parisc/kernel/module.c | 6 +----- arch/s390/kernel/module.c | 10 +++------- arch/tile/kernel/module.c | 2 +- include/linux/moduleloader.h | 2 ++ kernel/module.c | 7 +++++++ 7 files changed, 17 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 2c9412908024..164efa009e5b 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -19,12 +19,10 @@ #include #include -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { vfree(mod->arch.syminfo); mod->arch.syminfo = NULL; - - vfree(module_region); } static inline int check_rela(Elf32_Rela *rela, struct module *module, @@ -291,12 +289,3 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, return ret; } - -int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, - struct module *module) -{ - vfree(module->arch.syminfo); - module->arch.syminfo = NULL; - - return 0; -} diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 24603be24c14..29754aae5177 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -305,14 +305,12 @@ plt_target (struct plt_entry *plt) #endif /* !USE_BRL */ void -module_free (struct module *mod, void *module_region) +module_arch_freeing_init (struct module *mod) { - if (mod && mod->arch.init_unw_table && - module_region == mod->module_init) { + if (mod->arch.init_unw_table) { unw_remove_unwind_table(mod->arch.init_unw_table); mod->arch.init_unw_table = NULL; } - vfree(module_region); } /* Have we already seen one of these relocations? */ diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 50dfafc3f2c1..5822e8e200e6 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -298,14 +298,10 @@ static inline unsigned long count_stubs(const Elf_Rela *rela, unsigned long n) } #endif - -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { kfree(mod->arch.section); mod->arch.section = NULL; - - vfree(module_region); } /* Additional bytes needed in front of individual sections */ diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index b89b59158b95..409d152585be 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,14 +55,10 @@ void *module_alloc(unsigned long size) } #endif -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { - if (mod) { - vfree(mod->arch.syminfo); - mod->arch.syminfo = NULL; - } - vfree(module_region); + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; } static void check_rela(Elf_Rela *rela, struct module *me) diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c index 96447c9160a0..62a597e810d6 100644 --- a/arch/tile/kernel/module.c +++ b/arch/tile/kernel/module.c @@ -83,7 +83,7 @@ void module_free(struct module *mod, void *module_region) 0, 0, 0, NULL, NULL, 0); /* - * FIXME: If module_region == mod->module_init, trim exception + * FIXME: Add module_arch_freeing_init to trim exception * table entries. */ } diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 7eeb9bbfb816..054eac853090 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -82,4 +82,6 @@ int module_finalize(const Elf_Ehdr *hdr, /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); +/* Any cleanup before freeing mod->module_init */ +void module_arch_freeing_init(struct module *mod); #endif diff --git a/kernel/module.c b/kernel/module.c index 3965511ae133..68be0b1f9e7f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1804,6 +1804,10 @@ void __weak module_arch_cleanup(struct module *mod) { } +void __weak module_arch_freeing_init(struct module *mod) +{ +} + /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { @@ -1841,6 +1845,7 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ unset_module_init_ro_nx(mod); + module_arch_freeing_init(mod); module_free(mod, mod->module_init); kfree(mod->args); percpu_modfree(mod); @@ -2930,6 +2935,7 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); + module_arch_freeing_init(mod); module_free(mod, mod->module_init); module_free(mod, mod->module_core); } @@ -3055,6 +3061,7 @@ static int do_init_module(struct module *mod) mod->strtab = mod->core_strtab; #endif unset_module_init_ro_nx(mod); + module_arch_freeing_init(mod); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; -- cgit v1.2.3 From be1f221c0445a4157d177197c236f888d3581914 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 20 Jan 2015 09:07:05 +1030 Subject: module: remove mod arg from module_free, rename module_memfree(). Nothing needs the module pointer any more, and the next patch will call it from RCU, where the module itself might no longer exist. Removing the arg is the safest approach. This just codifies the use of the module_alloc/module_free pattern which ftrace and bpf use. Signed-off-by: Rusty Russell Acked-by: Alexei Starovoitov Cc: Mikael Starvik Cc: Jesper Nilsson Cc: Ralf Baechle Cc: Ley Foon Tan Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Steven Rostedt Cc: x86@kernel.org Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: Masami Hiramatsu Cc: linux-cris-kernel@axis.com Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: nios2-dev@lists.rocketboards.org Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Cc: netdev@vger.kernel.org --- arch/cris/kernel/module.c | 2 +- arch/mips/net/bpf_jit.c | 2 +- arch/nios2/kernel/module.c | 2 +- arch/powerpc/net/bpf_jit_comp.c | 2 +- arch/sparc/net/bpf_jit_comp.c | 4 ++-- arch/tile/kernel/module.c | 2 +- arch/x86/kernel/ftrace.c | 2 +- include/linux/moduleloader.h | 2 +- kernel/bpf/core.c | 2 +- kernel/kprobes.c | 2 +- kernel/module.c | 14 +++++++------- 11 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/arch/cris/kernel/module.c b/arch/cris/kernel/module.c index 51123f985eb5..af04cb6b6dc9 100644 --- a/arch/cris/kernel/module.c +++ b/arch/cris/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) } /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { kfree(module_region); } diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 9fd6834a2172..5d6139390bf8 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1388,7 +1388,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c index cc924a38f22a..e2e3f13f98d5 100644 --- a/arch/nios2/kernel/module.c +++ b/arch/nios2/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) } /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { kfree(module_region); } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 1ca125b9c226..d1916b577f2c 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -699,7 +699,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index f33e7c7a3bf7..7931eeeb649a 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -776,7 +776,7 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; if (unlikely(proglen + ilen > oldproglen)) { pr_err("bpb_jit_compile fatal error\n"); kfree(addrs); - module_free(NULL, image); + module_memfree(image); return; } memcpy(image + proglen, temp, ilen); @@ -822,7 +822,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c index 62a597e810d6..2305084c9b93 100644 --- a/arch/tile/kernel/module.c +++ b/arch/tile/kernel/module.c @@ -74,7 +74,7 @@ error: /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { vfree(module_region); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 2142376dc8c6..8b7b0a51e742 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size) } static inline void tramp_free(void *tramp) { - module_free(NULL, tramp); + module_memfree(tramp); } #else /* Trampolines can only be created if modules are supported */ diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 054eac853090..f7556261fe3c 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -26,7 +26,7 @@ unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section); void *module_alloc(unsigned long size); /* Free memory returned from module_alloc. */ -void module_free(struct module *mod, void *module_region); +void module_memfree(void *module_region); /* * Apply the given relocation to the (simplified) ELF. Return -error diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d6594e457a25..a64e7a207d2b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -163,7 +163,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { - module_free(NULL, hdr); + module_memfree(hdr); } #endif /* CONFIG_BPF_JIT */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 06f58309fed2..ee619929cf90 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -127,7 +127,7 @@ static void *alloc_insn_page(void) static void free_insn_page(void *page) { - module_free(NULL, page); + module_memfree(page); } struct kprobe_insn_cache kprobe_insn_slots = { diff --git a/kernel/module.c b/kernel/module.c index 68be0b1f9e7f..1f85fd5c89d3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1795,7 +1795,7 @@ static void unset_module_core_ro_nx(struct module *mod) { } static void unset_module_init_ro_nx(struct module *mod) { } #endif -void __weak module_free(struct module *mod, void *module_region) +void __weak module_memfree(void *module_region) { vfree(module_region); } @@ -1846,7 +1846,7 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - module_free(mod, mod->module_init); + module_memfree(mod->module_init); kfree(mod->args); percpu_modfree(mod); @@ -1855,7 +1855,7 @@ static void free_module(struct module *mod) /* Finally, free the core (containing the module structure) */ unset_module_core_ro_nx(mod); - module_free(mod, mod->module_core); + module_memfree(mod->module_core); #ifdef CONFIG_MPU update_protections(current->mm); @@ -2790,7 +2790,7 @@ static int move_module(struct module *mod, struct load_info *info) */ kmemleak_ignore(ptr); if (!ptr) { - module_free(mod, mod->module_core); + module_memfree(mod->module_core); return -ENOMEM; } memset(ptr, 0, mod->init_size); @@ -2936,8 +2936,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_free(mod, mod->module_init); - module_free(mod, mod->module_core); + module_memfree(mod->module_init); + module_memfree(mod->module_core); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3062,7 +3062,7 @@ static int do_init_module(struct module *mod) #endif unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - module_free(mod, mod->module_init); + module_memfree(mod->module_init); mod->module_init = NULL; mod->init_size = 0; mod->init_ro_size = 0; -- cgit v1.2.3 From d5db139ab3764640e0882a1746e7b9fdee33fd87 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 22 Jan 2015 11:13:14 +1030 Subject: module: make module_refcount() a signed integer. James Bottomley points out that it will be -1 during unload. It's only used for diagnostics, so let's not hide that as it could be a clue as to what's gone wrong. Cc: Jason Wessel Acked-and-documention-added-by: James Bottomley Reviewed-by: Masami Hiramatsu Signed-off-by: Rusty Russell --- include/linux/module.h | 2 +- kernel/debug/kdb/kdb_main.c | 2 +- kernel/module.c | 17 +++++++++++++---- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index ebfb0e153c6a..b653d7c0a05a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -444,7 +444,7 @@ extern void __module_put_and_exit(struct module *mod, long code) #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD -unsigned long module_refcount(struct module *mod); +int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(VMLINUX_SYMBOL_STR(x)) void symbol_put_addr(void *addr); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 379650b984f8..2934889f2cce 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1979,7 +1979,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf("%-20s%8u 0x%p ", mod->name, mod->core_size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD - kdb_printf("%4ld ", module_refcount(mod)); + kdb_printf("%4d ", module_refcount(mod)); #endif if (mod->state == MODULE_STATE_GOING) kdb_printf(" (Unloading)"); diff --git a/kernel/module.c b/kernel/module.c index ed4ec9c30bd2..d856e96a3cce 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -772,9 +772,18 @@ static int try_stop_module(struct module *mod, int flags, int *forced) return 0; } -unsigned long module_refcount(struct module *mod) +/** + * module_refcount - return the refcount or -1 if unloading + * + * @mod: the module we're checking + * + * Returns: + * -1 if the module is in the process of unloading + * otherwise the number of references in the kernel to the module + */ +int module_refcount(struct module *mod) { - return (unsigned long)atomic_read(&mod->refcnt) - MODULE_REF_BASE; + return atomic_read(&mod->refcnt) - MODULE_REF_BASE; } EXPORT_SYMBOL(module_refcount); @@ -856,7 +865,7 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod) struct module_use *use; int printed_something = 0; - seq_printf(m, " %lu ", module_refcount(mod)); + seq_printf(m, " %i ", module_refcount(mod)); /* * Always include a trailing , so userspace can differentiate @@ -908,7 +917,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr); static ssize_t show_refcnt(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%lu\n", module_refcount(mk->mod)); + return sprintf(buffer, "%i\n", module_refcount(mk->mod)); } static struct module_attribute modinfo_refcnt = -- cgit v1.2.3 From 9879de7373fcfb466ec198293b6ccc1ad7a42dd8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 26 Jan 2015 12:58:32 -0800 Subject: mm: page_alloc: embed OOM killing naturally into allocation slowpath The OOM killing invocation does a lot of duplicative checks against the task's allocation context. Rework it to take advantage of the existing checks in the allocator slowpath. The OOM killer is invoked when the allocator is unable to reclaim any pages but the allocation has to keep looping. Instead of having a check for __GFP_NORETRY hidden in oom_gfp_allowed(), just move the OOM invocation to the true branch of should_alloc_retry(). The __GFP_FS check from oom_gfp_allowed() can then be moved into the OOM avoidance branch in __alloc_pages_may_oom(), along with the PF_DUMPCORE test. __alloc_pages_may_oom() can then signal to the caller whether the OOM killer was invoked, instead of requiring it to duplicate the order and high_zoneidx checks to guess this when deciding whether to continue. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 5 ---- mm/page_alloc.c | 82 +++++++++++++++++++++++------------------------------ 2 files changed, 35 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index 853698c721f7..76200984d1e2 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -85,11 +85,6 @@ static inline void oom_killer_enable(void) oom_killer_disabled = false; } -static inline bool oom_gfp_allowed(gfp_t gfp_mask) -{ - return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY); -} - extern struct task_struct *find_lock_task_mm(struct task_struct *p); static inline bool task_will_free_mem(struct task_struct *task) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7633c503a116..8e20f9c2fa5a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2332,12 +2332,21 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int classzone_idx, int migratetype) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page; - /* Acquire the per-zone oom lock for each zone */ + *did_some_progress = 0; + + if (oom_killer_disabled) + return NULL; + + /* + * Acquire the per-zone oom lock for each zone. If that + * fails, somebody else is making progress for us. + */ if (!oom_zonelist_trylock(zonelist, gfp_mask)) { + *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; } @@ -2363,12 +2372,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; if (!(gfp_mask & __GFP_NOFAIL)) { + /* Coredumps can quickly deplete all memory reserves */ + if (current->flags & PF_DUMPCORE) + goto out; /* The OOM killer will not help higher order allocs */ if (order > PAGE_ALLOC_COSTLY_ORDER) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ if (high_zoneidx < ZONE_NORMAL) goto out; + /* The OOM killer does not compensate for light reclaim */ + if (!(gfp_mask & __GFP_FS)) + goto out; /* * GFP_THISNODE contains __GFP_NORETRY and we never hit this. * Sanity check for bare calls of __GFP_THISNODE, not real OOM. @@ -2381,7 +2396,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* Exhausted what can be done so it's blamo time */ out_of_memory(zonelist, gfp_mask, order, nodemask, false); - + *did_some_progress = 1; out: oom_zonelist_unlock(zonelist, gfp_mask); return page; @@ -2658,7 +2673,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; -restart: +retry: if (!(gfp_mask & __GFP_NO_KSWAPD)) wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone, nodemask); @@ -2681,7 +2696,6 @@ restart: classzone_idx = zonelist_zone_idx(preferred_zoneref); } -rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, @@ -2788,54 +2802,28 @@ rebalance: if (page) goto got_pg; - /* - * If we failed to make any progress reclaiming, then we are - * running out of options and have to consider going OOM - */ - if (!did_some_progress) { - if (oom_gfp_allowed(gfp_mask)) { - if (oom_killer_disabled) - goto nopage; - /* Coredumps can quickly deplete all memory reserves */ - if ((current->flags & PF_DUMPCORE) && - !(gfp_mask & __GFP_NOFAIL)) - goto nopage; - page = __alloc_pages_may_oom(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, preferred_zone, - classzone_idx, migratetype); - if (page) - goto got_pg; - - if (!(gfp_mask & __GFP_NOFAIL)) { - /* - * The oom killer is not called for high-order - * allocations that may fail, so if no progress - * is being made, there are no other options and - * retrying is unlikely to help. - */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - goto nopage; - /* - * The oom killer is not called for lowmem - * allocations to prevent needlessly killing - * innocent tasks. - */ - if (high_zoneidx < ZONE_NORMAL) - goto nopage; - } - - goto restart; - } - } - /* Check if we should retry the allocation */ pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, did_some_progress, pages_reclaimed)) { + /* + * If we fail to make progress by freeing individual + * pages, but the allocation wants us to keep going, + * start OOM killing tasks. + */ + if (!did_some_progress) { + page = __alloc_pages_may_oom(gfp_mask, order, zonelist, + high_zoneidx, nodemask, + preferred_zone, classzone_idx, + migratetype,&did_some_progress); + if (page) + goto got_pg; + if (!did_some_progress) + goto nopage; + } /* Wait for some write requests to complete then retry */ wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); - goto rebalance; + goto retry; } else { /* * High-order allocations do not necessarily loop after -- cgit v1.2.3 From 07261edb971492c6b41b44d7b1b51f76807d30ad Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Mon, 26 Jan 2015 12:58:43 -0800 Subject: printk: add dummy routine for when CONFIG_PRINTK=n There are missing dummy routines for log_buf_addr_get() and log_buf_len_get() for when CONFIG_PRINTK is not set causing build failures. This patch adds these dummy routines at the appropriate location. Signed-off-by: Pranith Kumar Cc: Michael Ellerman Reviewed-by: Petr Mladek Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index c8f170324e64..4d5bf5726578 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -10,9 +10,6 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -extern char *log_buf_addr_get(void); -extern u32 log_buf_len_get(void); - static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { @@ -163,6 +160,8 @@ extern int kptr_restrict; extern void wake_up_klogd(void); +char *log_buf_addr_get(void); +u32 log_buf_len_get(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); void dump_stack_set_arch_desc(const char *fmt, ...); @@ -198,6 +197,16 @@ static inline void wake_up_klogd(void) { } +static inline char *log_buf_addr_get(void) +{ + return NULL; +} + +static inline u32 log_buf_len_get(void) +{ + return 0; +} + static inline void log_buf_kexec_setup(void) { } -- cgit v1.2.3 From df4d92549f23e1c037e83323aff58a21b3de7fe0 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 23 Jan 2015 12:01:26 +0100 Subject: ipv4: try to cache dst_entries which would cause a redirect Not caching dst_entries which cause redirects could be exploited by hosts on the same subnet, causing a severe DoS attack. This effect aggravated since commit f88649721268999 ("ipv4: fix dst race in sk_dst_get()"). Lookups causing redirects will be allocated with DST_NOCACHE set which will force dst_release to free them via RCU. Unfortunately waiting for RCU grace period just takes too long, we can end up with >1M dst_entries waiting to be released and the system will run OOM. rcuos threads cannot catch up under high softirq load. Attaching the flag to emit a redirect later on to the specific skb allows us to cache those dst_entries thus reducing the pressure on allocation and deallocation. This issue was discovered by Marcelo Leitner. Cc: Julian Anastasov Signed-off-by: Marcelo Leitner Signed-off-by: Florian Westphal Signed-off-by: Hannes Frederic Sowa Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- include/net/ip.h | 11 ++++++----- net/ipv4/ip_forward.c | 3 ++- net/ipv4/route.c | 9 +++++---- 3 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 0bb620702929..f7cbd703d15d 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -39,11 +39,12 @@ struct inet_skb_parm { struct ip_options opt; /* Compiled IP options */ unsigned char flags; -#define IPSKB_FORWARDED 1 -#define IPSKB_XFRM_TUNNEL_SIZE 2 -#define IPSKB_XFRM_TRANSFORMED 4 -#define IPSKB_FRAG_COMPLETE 8 -#define IPSKB_REROUTED 16 +#define IPSKB_FORWARDED BIT(0) +#define IPSKB_XFRM_TUNNEL_SIZE BIT(1) +#define IPSKB_XFRM_TRANSFORMED BIT(2) +#define IPSKB_FRAG_COMPLETE BIT(3) +#define IPSKB_REROUTED BIT(4) +#define IPSKB_DOREDIRECT BIT(5) u16 frag_max_size; }; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3a83ce5efa80..787b3c294ce6 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -129,7 +129,8 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) + if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr && + !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6a2155b02602..d58dd0ec3e53 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1554,11 +1554,10 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && + skb->protocol == htons(ETH_P_IP) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { - flags |= RTCF_DOREDIRECT; - do_cache = false; - } + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -2303,6 +2302,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; + if (IPCB(skb)->flags & IPSKB_DOREDIRECT) + r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; -- cgit v1.2.3