From a9fd053b56c6bb14972ab7a19da0b575fe4c5d66 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 19 Nov 2015 10:15:17 +0100 Subject: iio: st_sensors: support active-low interrupts Most ST MEMS Sensors that support interrupts can also handle sending an active low interrupt, i.e. going from high to low on data ready (or other interrupt) and thus triggering on a falling edge to the interrupt controller. Set up logic to inspect the interrupt line we get for a sensor: if it is triggering on rising edge, leave everything alone, but if it triggers on falling edges, set up active low, and if unsupported configurations appear: warn with errors and reconfigure the interrupt to a rising edge, which all interrupt generating sensors support. Create a local header for st_sensors_core.h to share functions between the sensor core and the trigger setup code. Cc: Giuseppe Barba Cc: Denis Ciocca Signed-off-by: Linus Walleij Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 2fe939c73cd2..6670c3d25c58 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -119,6 +119,8 @@ struct st_sensor_bdu { * @addr: address of the register. * @mask_int1: mask to enable/disable IRQ on INT1 pin. * @mask_int2: mask to enable/disable IRQ on INT2 pin. + * @addr_ihl: address to enable/disable active low on the INT lines. + * @mask_ihl: mask to enable/disable active low on the INT lines. * struct ig1 - represents the Interrupt Generator 1 of sensors. * @en_addr: address of the enable ig1 register. * @en_mask: mask to write the on/off value for enable. @@ -127,6 +129,8 @@ struct st_sensor_data_ready_irq { u8 addr; u8 mask_int1; u8 mask_int2; + u8 addr_ihl; + u8 mask_ihl; struct { u8 en_addr; u8 en_mask; -- cgit v1.2.3 From 23a1f8d44c0bca48f04fc2a2f1edafd826ce6133 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 16:04:31 +0200 Subject: mac80211: process and save VHT MU-MIMO group frame The Group ID Management frame is an Action frame of category VHT. It is transmitted by the AP to assign or change the user position of a STA for one or more group IDs. Process and save the group membership data. Notify underlying driver of changes. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 452c0b0d2f32..d9ddb89533a7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -843,6 +843,8 @@ enum ieee80211_vht_opmode_bits { }; #define WLAN_SA_QUERY_TR_ID_LEN 2 +#define WLAN_MEMBERSHIP_LEN 8 +#define WLAN_USER_POSITION_LEN 16 /** * struct ieee80211_tpc_report_ie @@ -989,6 +991,11 @@ struct ieee80211_mgmt { u8 action_code; u8 operating_mode; } __packed vht_opmode_notif; + struct { + u8 action_code; + u8 membership[WLAN_MEMBERSHIP_LEN]; + u8 position[WLAN_USER_POSITION_LEN]; + } __packed vht_group_notif; struct { u8 action_code; u8 dialog_token; -- cgit v1.2.3 From b429fab4467e2320f67c058d7419c03c7221d125 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Tue, 19 Jan 2016 17:14:39 -0800 Subject: regmap: clairify meaning of max_register The exact meaning of max_register is not entierly clear. Follow the common wording and use "address" instead of "index". Signed-off-by: Stefan Agner Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 18394343f489..27aaac9027c4 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -162,7 +162,7 @@ typedef void (*regmap_unlock)(void *); * This field is a duplicate of a similar file in * 'struct regmap_bus' and serves exact same purpose. * Use it only for "no-bus" cases. - * @max_register: Optional, specifies the maximum valid register index. + * @max_register: Optional, specifies the maximum valid register address. * @wr_table: Optional, points to a struct regmap_access_table specifying * valid ranges for write access. * @rd_table: As above, for read access. -- cgit v1.2.3 From c03d996900f9d063b47ef7462885a9085c8a587f Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Wed, 2 Dec 2015 12:01:05 +0100 Subject: mtd: nand: add NAND_NEED_SCRAMBLING option flag Some MLC NANDs are sensitive to repeated patterns and require data to be scrambled in order to limit the number of bitflips. Add a new flag to let the NAND controller know about this constraint. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index bdd68e22b5a5..a13dfd5bc58b 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -168,6 +168,12 @@ typedef enum { /* Device supports subpage reads */ #define NAND_SUBPAGE_READ 0x00001000 +/* + * Some MLC NANDs need data scrambling to limit bitflips caused by repeated + * patterns. + */ +#define NAND_NEED_SCRAMBLING 0x00002000 + /* Options valid for Samsung large page devices */ #define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG -- cgit v1.2.3 From fd2a2f20c7a8173acd4858e5178eb40fd7c025b9 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 14 Jan 2016 15:44:50 +0100 Subject: mtd: onenand: make onenand_scan_bbt() static Like was done in commit 17799359e7b3fa6ef4f2bf926cd6821cf7903ecf ("mtd: nand_bbt: make nand_scan_bbt() static") for the NAND code, this commit makes the onenand_scan_bbt() function static in the OneNAND code, since it is only used in onenand_bbt.c itself. Consequently, the EXPORT_SYMBOL() and declaration in bbm.h are also removed. Signed-off-by: Thomas Petazzoni Reviewed-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/bbm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 36bb6a503f19..3bf8f954b642 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -166,7 +166,6 @@ struct bbm_info { }; /* OneNAND BBT interface */ -extern int onenand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd); extern int onenand_default_bbt(struct mtd_info *mtd); #endif /* __LINUX_MTD_BBM_H */ -- cgit v1.2.3 From 131497acd88a4456d99247cee457baefd2817835 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Sat, 16 Jan 2016 14:24:07 +0100 Subject: iio: add ad5761 DAC driver ad5761 is a 1-channel DAC with configurable output range. The driver uses the regulator interface for its voltage ref. It shares its register layout with ad5761r, ad5721 and ad5721r. Differences: ad5761* are 16 bit, ad5721* are 12 bits. ad57*1r have an internal reference. Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Jonathan Cameron --- include/linux/platform_data/ad5761.h | 44 ++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/platform_data/ad5761.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ad5761.h b/include/linux/platform_data/ad5761.h new file mode 100644 index 000000000000..7bd8ed7d978e --- /dev/null +++ b/include/linux/platform_data/ad5761.h @@ -0,0 +1,44 @@ +/* + * AD5721, AD5721R, AD5761, AD5761R, Voltage Output Digital to Analog Converter + * + * Copyright 2016 Qtechnology A/S + * 2016 Ricardo Ribalda + * + * Licensed under the GPL-2. + */ +#ifndef __LINUX_PLATFORM_DATA_AD5761_H__ +#define __LINUX_PLATFORM_DATA_AD5761_H__ + +/** + * enum ad5761_voltage_range - Voltage range the AD5761 is configured for. + * @AD5761_VOLTAGE_RANGE_M10V_10V: -10V to 10V + * @AD5761_VOLTAGE_RANGE_0V_10V: 0V to 10V + * @AD5761_VOLTAGE_RANGE_M5V_5V: -5V to 5V + * @AD5761_VOLTAGE_RANGE_0V_5V: 0V to 5V + * @AD5761_VOLTAGE_RANGE_M2V5_7V5: -2.5V to 7.5V + * @AD5761_VOLTAGE_RANGE_M3V_3V: -3V to 3V + * @AD5761_VOLTAGE_RANGE_0V_16V: 0V to 16V + * @AD5761_VOLTAGE_RANGE_0V_20V: 0V to 20V + */ + +enum ad5761_voltage_range { + AD5761_VOLTAGE_RANGE_M10V_10V, + AD5761_VOLTAGE_RANGE_0V_10V, + AD5761_VOLTAGE_RANGE_M5V_5V, + AD5761_VOLTAGE_RANGE_0V_5V, + AD5761_VOLTAGE_RANGE_M2V5_7V5, + AD5761_VOLTAGE_RANGE_M3V_3V, + AD5761_VOLTAGE_RANGE_0V_16V, + AD5761_VOLTAGE_RANGE_0V_20V, +}; + +/** + * struct ad5761_platform_data - AD5761 DAC driver platform data + * @voltage_range: Voltage range the AD5761 is configured for + */ + +struct ad5761_platform_data { + enum ad5761_voltage_range voltage_range; +}; + +#endif -- cgit v1.2.3 From 132f5005abbd480b66c58f8113ed876b99b6318e Mon Sep 17 00:00:00 2001 From: Jack Pham Date: Thu, 10 Dec 2015 18:28:53 -0600 Subject: usb: host: ehci-msm: Allow LS devices to work Disable the silicon quirk which is normally enabled for HSIC host mode. This would otherwise prevent low speed devices from enumerating properly. Signed-off-by: Jack Pham Signed-off-by: Timur Tabi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/msm_hsusb_hw.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/msm_hsusb_hw.h b/include/linux/usb/msm_hsusb_hw.h index e159b39f67a2..974c3796a23f 100644 --- a/include/linux/usb/msm_hsusb_hw.h +++ b/include/linux/usb/msm_hsusb_hw.h @@ -22,6 +22,7 @@ #define USB_AHBBURST (MSM_USB_BASE + 0x0090) #define USB_AHBMODE (MSM_USB_BASE + 0x0098) #define USB_GENCONFIG_2 (MSM_USB_BASE + 0x00a0) +#define ULPI_TX_PKT_EN_CLR_FIX BIT(19) #define USB_CAPLENGTH (MSM_USB_BASE + 0x0100) /* 8 bit */ -- cgit v1.2.3 From 203d4f347d86aa9e78342457aa7a3844c4fadd1d Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 14 Jan 2016 16:24:45 +0100 Subject: reset: Make reset_control_ops const The ops pointer is holding a pointer to a structure that is usually not modified. Make it const. Signed-off-by: Maxime Ripard Signed-off-by: Philipp Zabel --- include/linux/reset-controller.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index ce6b962ffed4..a3a5bcdb1d02 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -38,7 +38,7 @@ struct of_phandle_args; * @nr_resets: number of reset controls in this reset controller device */ struct reset_controller_dev { - struct reset_control_ops *ops; + const struct reset_control_ops *ops; struct module *owner; struct list_head list; struct device_node *of_node; -- cgit v1.2.3 From 8d1a0ae724ad74ef7946a45e3b2d3e01f39df02b Mon Sep 17 00:00:00 2001 From: Martin Fuzzey Date: Wed, 13 Jan 2016 23:36:26 -0500 Subject: ARM: perf: Set ARMv7 SDER SUNIDEN bit ARMv7 counters other than the CPU cycle counter only work if the Secure Debug Enable Register (SDER) SUNIDEN bit is set. Since access to the SDER is only possible in secure state, it will only be done if the device tree property "secure-reg-access" is set. Without this: Performance counter stats for 'sleep 1': 14606094 cycles # 0.000 GHz 0 instructions # 0.00 insns per cycle After applying: Performance counter stats for 'sleep 1': 5843809 cycles 2566484 instructions # 0.44 insns per cycle 1.020144000 seconds time elapsed Some platforms (eg i.MX53) may also need additional platform specific setup. Acked-by: Rob Herring Signed-off-by: Martin Fuzzey Signed-off-by: Pooya Keshavarzi Signed-off-by: George G. Davis [will: add warning if property is found on arm64] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 83b5e34c6580..2d5eaaa90078 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -104,6 +104,7 @@ struct arm_pmu { atomic_t active_events; struct mutex reserve_mutex; u64 max_period; + bool secure_access; /* 32-bit ARM only */ struct platform_device *plat_device; struct pmu_hw_events __percpu *hw_events; struct notifier_block hotplug_nb; -- cgit v1.2.3 From f8543c06b3948102d50ee6dfdbb06f1e7945baf1 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Dec 2015 23:25:57 +0100 Subject: mtd: inftl: kill unused oobinfo field Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/inftl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/inftl.h b/include/linux/mtd/inftl.h index 02cd5f9b79b8..8255118be0f0 100644 --- a/include/linux/mtd/inftl.h +++ b/include/linux/mtd/inftl.h @@ -44,7 +44,6 @@ struct INFTLrecord { unsigned int nb_blocks; /* number of physical blocks */ unsigned int nb_boot_blocks; /* number of blocks used by the bios */ struct erase_info instr; - struct nand_ecclayout oobinfo; }; int INFTL_mount(struct INFTLrecord *s); -- cgit v1.2.3 From 2c9e57799f1b7ef35a9e7f774edac6b3feac6399 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Dec 2015 23:25:58 +0100 Subject: mtd: nftl: kill unused oobinfo field Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nftl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nftl.h b/include/linux/mtd/nftl.h index b059629e22bc..044daa02b8ff 100644 --- a/include/linux/mtd/nftl.h +++ b/include/linux/mtd/nftl.h @@ -50,7 +50,6 @@ struct NFTLrecord { unsigned int nb_blocks; /* number of physical blocks */ unsigned int nb_boot_blocks; /* number of blocks used by the bios */ struct erase_info instr; - struct nand_ecclayout oobinfo; }; int NFTL_mount(struct NFTLrecord *s); -- cgit v1.2.3 From f88f44cbf10cf5bd42d6e46ea6625d9bfa5f155d Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Dec 2015 23:25:59 +0100 Subject: mtd: nand: s3c2410: kill the ->ecc_layout field The s3c2410 is allowing board data to overload the default ECC layout defined inside the driver, but this feature is not used by board specific definitions. Kill this field so that we can easily move to a model where ecclayout are dynamically allocated by the NAND controller driver. Signed-off-by: Boris Brezillon Acked-by: Krzysztof Kozlowski Signed-off-by: Brian Norris --- include/linux/platform_data/mtd-nand-s3c2410.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index 36bb92172f47..c55e42ee57fa 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -40,7 +40,6 @@ struct s3c2410_nand_set { char *name; int *nr_map; struct mtd_partition *partitions; - struct nand_ecclayout *ecc_layout; }; struct s3c2410_platform_nand { -- cgit v1.2.3 From 02db97a9de1c80bd5551ba46d901cb4d912f78f2 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Dec 2015 23:26:01 +0100 Subject: mtd: nand: kill unused ->ecclayout field in platform_nand_chip struct This field is not set in any board file and can thus be dropped. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index a13dfd5bc58b..7604f4be3386 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -902,7 +902,6 @@ extern int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len, * @chip_delay: R/B delay value in us * @options: Option flags, e.g. 16bit buswidth * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH - * @ecclayout: ECC layout info structure * @part_probe_types: NULL-terminated array of probe types */ struct platform_nand_chip { @@ -910,7 +909,6 @@ struct platform_nand_chip { int chip_offset; int nr_partitions; struct mtd_partition *partitions; - struct nand_ecclayout *ecclayout; int chip_delay; unsigned int options; unsigned int bbt_options; -- cgit v1.2.3 From 3b5cf20cf439c3e8963c2d2a3f225434d31827e3 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 24 Jan 2016 21:17:59 +0800 Subject: sunrpc: Use skcipher and ahash/shash This patch replaces uses of blkcipher with skcipher and the long obsolete hash interface with either shash (for non-SG users) and ahash. Signed-off-by: Herbert Xu --- include/linux/sunrpc/gss_krb5.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index df02a4188487..7df625d41e35 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -36,7 +36,7 @@ * */ -#include +#include #include #include #include @@ -71,10 +71,10 @@ struct gss_krb5_enctype { const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ const u32 keylength; /* final key len, in bytes */ - u32 (*encrypt) (struct crypto_blkcipher *tfm, + u32 (*encrypt) (struct crypto_skcipher *tfm, void *iv, void *in, void *out, int length); /* encryption function */ - u32 (*decrypt) (struct crypto_blkcipher *tfm, + u32 (*decrypt) (struct crypto_skcipher *tfm, void *iv, void *in, void *out, int length); /* decryption function */ u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, @@ -98,12 +98,12 @@ struct krb5_ctx { u32 enctype; u32 flags; const struct gss_krb5_enctype *gk5e; /* enctype-specific info */ - struct crypto_blkcipher *enc; - struct crypto_blkcipher *seq; - struct crypto_blkcipher *acceptor_enc; - struct crypto_blkcipher *initiator_enc; - struct crypto_blkcipher *acceptor_enc_aux; - struct crypto_blkcipher *initiator_enc_aux; + struct crypto_skcipher *enc; + struct crypto_skcipher *seq; + struct crypto_skcipher *acceptor_enc; + struct crypto_skcipher *initiator_enc; + struct crypto_skcipher *acceptor_enc_aux; + struct crypto_skcipher *initiator_enc_aux; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; @@ -262,24 +262,24 @@ gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, u32 -krb5_encrypt(struct crypto_blkcipher *key, +krb5_encrypt(struct crypto_skcipher *key, void *iv, void *in, void *out, int length); u32 -krb5_decrypt(struct crypto_blkcipher *key, +krb5_decrypt(struct crypto_skcipher *key, void *iv, void *in, void *out, int length); int -gss_encrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *outbuf, +gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *outbuf, int offset, struct page **pages); int -gss_decrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *inbuf, +gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *inbuf, int offset); s32 krb5_make_seq_num(struct krb5_ctx *kctx, - struct crypto_blkcipher *key, + struct crypto_skcipher *key, int direction, u32 seqnum, unsigned char *cksum, unsigned char *buf); @@ -320,12 +320,12 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, int krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, - struct crypto_blkcipher *cipher, + struct crypto_skcipher *cipher, unsigned char *cksum); int krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, - struct crypto_blkcipher *cipher, + struct crypto_skcipher *cipher, s32 seqnum); void gss_krb5_make_confounder(char *p, u32 conflen); -- cgit v1.2.3 From 110492183c4b8f572b16fce096b9d78e2da30baf Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 26 Jan 2016 17:15:03 +0900 Subject: crypto: compress - remove unused pcomp interface It is unused now, so remove it. Signed-off-by: Joonsoo Kim Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e71cb70a1ac2..ab2a745d85f3 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -54,7 +54,6 @@ #define CRYPTO_ALG_TYPE_AHASH 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d -#define CRYPTO_ALG_TYPE_PCOMPRESS 0x0000000f #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000c -- cgit v1.2.3 From c8b710b3e4348119924051551b836c94835331b1 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:13:46 -0800 Subject: tty: Fix ldisc leak in failed tty_init_dev() release_tty() leaks the ldisc instance when called directly (rather than when releasing the file descriptor from tty_release()). Since tty_ldisc_release() clears tty->ldisc, releasing the ldisc instance at tty teardown if tty->ldisc is non-null is not in danger of double-releasing the ldisc. Remove deinitialize_tty_struct() now that free_tty_struct() always performs the tty_ldisc_deinit(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d9fb4b043f56..64e301dbf7b9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -509,7 +509,6 @@ extern int tty_alloc_file(struct file *file); extern void tty_add_file(struct tty_struct *tty, struct file *file); extern void tty_free_file(struct file *file); extern void free_tty_struct(struct tty_struct *tty); -extern void deinitialize_tty_struct(struct tty_struct *tty); extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern int tty_release(struct inode *inode, struct file *filp); extern int tty_init_termios(struct tty_struct *tty); -- cgit v1.2.3 From a3123fd0a4a5f9d71afa0ffa82e2086281d81822 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:13:48 -0800 Subject: tty: Fix tty_init_termios() declaration tty_init_termios() never returns an error; re-declare as void. Remove unnecessary error handling from callers. Remove extern declarations of tty_free_termios() and free_tty_struct() and re-declare in file scope. Signed-off-by: Peter Hurley Acked-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 64e301dbf7b9..d7a7c1efe77f 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -448,7 +448,6 @@ extern int tty_unthrottle_safe(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); extern void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct *tty); -extern void tty_free_termios(struct tty_struct *tty); extern int is_current_pgrp_orphaned(void); extern int is_ignored(int sig); extern int tty_signal(int sig, struct tty_struct *tty); @@ -508,10 +507,9 @@ extern struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx); extern int tty_alloc_file(struct file *file); extern void tty_add_file(struct tty_struct *tty, struct file *file); extern void tty_free_file(struct file *file); -extern void free_tty_struct(struct tty_struct *tty); extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern int tty_release(struct inode *inode, struct file *filp); -extern int tty_init_termios(struct tty_struct *tty); +extern void tty_init_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); -- cgit v1.2.3 From 05de87ed9531dc19d87136c9204d251abebc60d3 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:13:49 -0800 Subject: tty: Re-declare tty_driver_remove_tty() file scope tty_driver_remove_tty() is only local-scope; declare as static. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d7a7c1efe77f..57c4e03ec2aa 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -446,8 +446,6 @@ extern void tty_unthrottle(struct tty_struct *tty); extern int tty_throttle_safe(struct tty_struct *tty); extern int tty_unthrottle_safe(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); -extern void tty_driver_remove_tty(struct tty_driver *driver, - struct tty_struct *tty); extern int is_current_pgrp_orphaned(void); extern int is_ignored(int sig); extern int tty_signal(int sig, struct tty_struct *tty); -- cgit v1.2.3 From c2bb524b2e1a6eddae65139601bee24cb60856a0 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:13:51 -0800 Subject: tty: Remove __lockfunc annotation from tty lock functions The tty lock/unlock code does not belong in the special lockfunc section which is treated specially by stack backtraces. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 57c4e03ec2aa..83f127673bc9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -643,11 +643,11 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* tty_mutex.c */ /* functions for preparation of BKL removal */ -extern void __lockfunc tty_lock(struct tty_struct *tty); +extern void tty_lock(struct tty_struct *tty); extern int tty_lock_interruptible(struct tty_struct *tty); -extern void __lockfunc tty_unlock(struct tty_struct *tty); -extern void __lockfunc tty_lock_slave(struct tty_struct *tty); -extern void __lockfunc tty_unlock_slave(struct tty_struct *tty); +extern void tty_unlock(struct tty_struct *tty); +extern void tty_lock_slave(struct tty_struct *tty); +extern void tty_unlock_slave(struct tty_struct *tty); extern void tty_set_lock_subclass(struct tty_struct *tty); #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From 707b61bba8b16adb6a2cbc72b71a75e09cb0f81a Mon Sep 17 00:00:00 2001 From: Oreste Salerno Date: Wed, 27 Jan 2016 13:55:43 -0800 Subject: Input: cyttsp - switch to using device properties Drop support for platform data passed via a C-structure and switch to device properties instead, which should make the driver compatible with all platforms: OF, ACPI and static boards. Static boards should use property sets to communicate device parameters to the driver. Signed-off-by: Oreste Salerno Acked-by: Rob Herring Signed-off-by: Dmitry Torokhov --- include/linux/input/cyttsp.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input/cyttsp.h b/include/linux/input/cyttsp.h index 5af7c66f1fca..586c8c95dcb0 100644 --- a/include/linux/input/cyttsp.h +++ b/include/linux/input/cyttsp.h @@ -40,19 +40,4 @@ /* Active distance in pixels for a gesture to be reported */ #define CY_ACT_DIST_DFLT 0xF8 /* pixels */ -struct cyttsp_platform_data { - u32 maxx; - u32 maxy; - bool use_hndshk; - u8 act_dist; /* Active distance */ - u8 act_intrvl; /* Active refresh interval; ms */ - u8 tch_tmout; /* Active touch timeout; ms */ - u8 lp_intrvl; /* Low power refresh interval; ms */ - int (*init)(void); - void (*exit)(void); - char *name; - s16 irq_gpio; - u8 *bl_keys; -}; - #endif /* _CYTTSP_H_ */ -- cgit v1.2.3 From fdfb719e93b55a50f90da2059dc450e7c0c48e8f Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 22:40:54 -0800 Subject: tty: Remove chars_in_buffer() line discipline method The chars_in_buffer() line discipline method serves no functional purpose, other than as a (dubious) debugging aid for mostly bit-rotting drivers. Despite being documented as an optional method, every caller is unconditionally executed (although conditionally compiled). Furthermore, direct tty->ldisc access without an ldisc ref is unsafe. Lastly, N_TTY's chars_in_buffer() has warned of removal since 3.12. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 00c9d688d7b7..6101ab8dc148 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -25,12 +25,6 @@ * buffers of any input characters it may have queued to be * delivered to the user mode process. * - * ssize_t (*chars_in_buffer)(struct tty_struct *tty); - * - * This function returns the number of input characters the line - * discipline may have queued up to be delivered to the user mode - * process. - * * ssize_t (*read)(struct tty_struct * tty, struct file * file, * unsigned char * buf, size_t nr); * @@ -188,7 +182,6 @@ struct tty_ldisc_ops { int (*open)(struct tty_struct *); void (*close)(struct tty_struct *); void (*flush_buffer)(struct tty_struct *tty); - ssize_t (*chars_in_buffer)(struct tty_struct *tty); ssize_t (*read)(struct tty_struct *tty, struct file *file, unsigned char __user *buf, size_t nr); ssize_t (*write)(struct tty_struct *tty, struct file *file, -- cgit v1.2.3 From c12da96f801a3f45b0634c966b9e7cda307daa72 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 22:41:04 -0800 Subject: tty: Use 'disc' for line discipline index name tty->ldisc is a ptr to struct tty_ldisc, but unfortunately 'ldisc' is also used as a parameter or local name to refer to the line discipline index value (ie, N_TTY, N_GSM, etc.); instead prefer the name used by the line discipline registration/ref counting functions. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 83f127673bc9..e3b0afbde7b9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -570,7 +570,7 @@ static inline int tty_port_users(struct tty_port *port) extern int tty_register_ldisc(int disc, struct tty_ldisc_ops *new_ldisc); extern int tty_unregister_ldisc(int disc); -extern int tty_set_ldisc(struct tty_struct *tty, int ldisc); +extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); extern void tty_ldisc_release(struct tty_struct *tty); extern void tty_ldisc_init(struct tty_struct *tty); -- cgit v1.2.3 From 892d1fa7eaaed9d3c04954cb140c34ebc3393932 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 22:41:06 -0800 Subject: tty: Destroy ldisc instance on hangup Currently, when the tty is hungup, the ldisc is re-instanced; ie., the current instance is destroyed and a new instance is created. The purpose of this design was to guarantee a valid, open ldisc for the lifetime of the tty. However, now that tty buffers are owned by and have lifetime equivalent to the tty_port (since v3.10), any data received immediately after the ldisc is re-instanced may cause continued driver i/o operations concurrently with the driver's hangup() operation. For drivers that shutdown h/w on hangup, this is unexpected and usually bad. For example, the serial core may free the xmit buffer page concurrently with an in-progress write() operation (triggered by echo). With the existing stable and robust ldisc reference handling, the cleaned-up tty_reopen(), the straggling unsafe ldisc use cleaned up, and the preparation to properly handle a NULL tty->ldisc, the ldisc instance can be destroyed and only re-instanced when the tty is re-opened. If the tty was opened as /dev/console or /dev/tty0, the original behavior of re-instancing the ldisc is retained (the 'reinit' parameter to tty_ldisc_hangup() is true). This is required since those file descriptors are never hungup. This patch has neglible impact on userspace; the tty file_operations ptr is changed to point to the hungup file operations _before_ the ldisc instance is destroyed, so only racing file operations might now retrieve a NULL ldisc reference (which is simply handled as if the hungup file operation had been called instead -- see "tty: Prepare for destroying line discipline on hangup"). This resolves a long-standing FIXME and several crash reports. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index e3b0afbde7b9..95e52c6b9696 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -490,7 +490,8 @@ extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *); -extern void tty_ldisc_hangup(struct tty_struct *tty); +extern void tty_ldisc_hangup(struct tty_struct *tty, bool reset); +extern int tty_ldisc_reinit(struct tty_struct *tty, int disc); extern const struct file_operations tty_ldiscs_proc_fops; extern void tty_wakeup(struct tty_struct *tty); -- cgit v1.2.3 From 27228732aa94f3883433fab2f43eee373c638f2f Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:35:19 -0800 Subject: tty: Eliminate global symbol tty_ldisc_N_TTY Reduce global tty symbols; move and rename tty_ldisc_begin() as n_tty_init() and redefine the N_TTY ldisc ops as file scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 95e52c6b9696..f6c07fd12ef4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -576,7 +576,6 @@ extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); extern void tty_ldisc_release(struct tty_struct *tty); extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); -extern void tty_ldisc_begin(void); static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, char *f, int count) @@ -593,8 +592,8 @@ static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, /* n_tty.c */ -extern struct tty_ldisc_ops tty_ldisc_N_TTY; extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); +extern void __init n_tty_init(void); /* tty_audit.c */ #ifdef CONFIG_AUDIT -- cgit v1.2.3 From de5583d670a8b10f157fdcc7afaddfd1ec423a69 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:35:20 -0800 Subject: tty: Remove declarations to non-existent functions tty_read_raw_data() and tty_signal() no longer exist; remove declarations. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index f6c07fd12ef4..26a9b4b3efe9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -433,8 +433,6 @@ extern struct device *tty_register_device_attr(struct tty_driver *driver, void *drvdata, const struct attribute_group **attr_grp); extern void tty_unregister_device(struct tty_driver *driver, unsigned index); -extern int tty_read_raw_data(struct tty_struct *tty, unsigned char *bufp, - int buflen); extern void tty_write_message(struct tty_struct *tty, char *msg); extern int tty_send_xchar(struct tty_struct *tty, char ch); extern int tty_put_char(struct tty_struct *tty, unsigned char c); @@ -448,7 +446,6 @@ extern int tty_unthrottle_safe(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); extern int is_current_pgrp_orphaned(void); extern int is_ignored(int sig); -extern int tty_signal(int sig, struct tty_struct *tty); extern void tty_hangup(struct tty_struct *tty); extern void tty_vhangup(struct tty_struct *tty); extern int tty_hung_up_p(struct file *filp); -- cgit v1.2.3 From e802ca0e1892865acdde90f1aaed37333c5660c2 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:35:21 -0800 Subject: tty: Move tty_check_change() helper Move is_ignored() to drivers/tty/tty_io.c and re-declare in file scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 26a9b4b3efe9..ba7120dccccb 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -445,7 +445,6 @@ extern int tty_throttle_safe(struct tty_struct *tty); extern int tty_unthrottle_safe(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); extern int is_current_pgrp_orphaned(void); -extern int is_ignored(int sig); extern void tty_hangup(struct tty_struct *tty); extern void tty_vhangup(struct tty_struct *tty); extern int tty_hung_up_p(struct file *filp); -- cgit v1.2.3 From 527ffc11e1c0aa049b3a831d6f07ed98e06a0819 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:35:22 -0800 Subject: tty: Remove unreferenced tty flags macro TTY_DEBUG The TTY_DEBUG macro is not used; remove. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index ba7120dccccb..da16b5980c25 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -336,7 +336,6 @@ struct tty_file_private { #define TTY_IO_ERROR 1 /* Cause an I/O error (may be no ldisc too) */ #define TTY_OTHER_CLOSED 2 /* Other side (if any) has closed */ #define TTY_EXCLUSIVE 3 /* Exclusive open mode */ -#define TTY_DEBUG 4 /* Debugging */ #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ #define TTY_OTHER_DONE 6 /* Closed pty has completed input processing */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ -- cgit v1.2.3 From 4a510969374ab8853451c337e43d28fb864e43fd Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:35:23 -0800 Subject: tty: Make tty_files_lock per-tty Access to tty->tty_files list is always per-tty, never for all ttys simultaneously. Replace global tty_files_lock spinlock with per-tty ->files_lock. Initialize when the ->tty_files list is inited, in alloc_tty_struct(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index da16b5980c25..780adbfc6dce 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -302,6 +302,7 @@ struct tty_struct { struct work_struct hangup_work; void *disc_data; void *driver_data; + spinlock_t files_lock; /* protects tty_files list */ struct list_head tty_files; #define N_TTY_BUF_SIZE 4096 @@ -508,7 +509,6 @@ extern int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); extern struct mutex tty_mutex; -extern spinlock_t tty_files_lock; #define tty_is_writelocked(tty) (mutex_is_locked(&tty->atomic_write_lock)) -- cgit v1.2.3 From 309426ae69cdf35b0d72a8bd59a5081f8ddccddd Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 22:55:27 -0800 Subject: tty: audit: Remove icanon mode from call chain The tty termios bits cannot change while n_tty_read() is in the i/o loop; the termios_rwsem ensures mutual exclusion with termios changes in n_tty_set_termios(). Check L_ICANON() directly and eliminate icanon parameter. NB: tty_audit_add_data() => tty_audit_buf_get() => tty_audit_buf_alloc() is a single path; ie., tty_audit_buf_get() and tty_audit_buf_alloc() have no other callers. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 780adbfc6dce..c011dc205e5c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -593,7 +593,7 @@ extern void __init n_tty_init(void); /* tty_audit.c */ #ifdef CONFIG_AUDIT extern void tty_audit_add_data(struct tty_struct *tty, const void *data, - size_t size, unsigned icanon); + size_t size); extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); @@ -601,7 +601,7 @@ extern void tty_audit_push(struct tty_struct *tty); extern int tty_audit_push_current(void); #else static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, - size_t size, unsigned icanon) + size_t size) { } static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) -- cgit v1.2.3 From b50819f437c094b4beb2e8684fbe12bbe79fb331 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 22:55:30 -0800 Subject: tty: audit: Ignore current association for audit push In canonical read mode, each line read and logged is pushed separately with tty_audit_push(). For all single-threaded processes and multi-threaded processes reading from only one tty, this patch has no effect; the last line read will still be the entry pushed to the audit log because the tty association cannot have changed between tty_audit_add_data() and tty_audit_push(). For multi-threaded processes reading from different ttys concurrently, the audit log will have mixed log entries anyway. Consider two ttys audited concurrently: CPU0 CPU1 ---------- ------------ tty_audit_add_data(ttyA) tty_audit_add_data(ttyB) tty_audit_push() tty_audit_add_data(ttyB) tty_audit_push() This patch will now cause the ttyB output to be split into separate audit log entries. However, this possibility is equally likely without this patch: CPU0 CPU1 ---------- ------------ tty_audit_add_data(ttyB) tty_audit_add_data(ttyA) tty_audit_push() tty_audit_add_data(ttyB) tty_audit_push() Mixed canonical and non-canonical reads have similar races. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index c011dc205e5c..83d74dcfb3c8 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -597,7 +597,7 @@ extern void tty_audit_add_data(struct tty_struct *tty, const void *data, extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); -extern void tty_audit_push(struct tty_struct *tty); +extern void tty_audit_push(void); extern int tty_audit_push_current(void); #else static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, @@ -613,7 +613,7 @@ static inline void tty_audit_exit(void) static inline void tty_audit_fork(struct signal_struct *sig) { } -static inline void tty_audit_push(struct tty_struct *tty) +static inline void tty_audit_push(void) { } static inline int tty_audit_push_current(void) -- cgit v1.2.3 From 37282a77954aa2dbb339d15902290f25b868d2e8 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 22:55:31 -0800 Subject: tty: audit: Combine push functions tty_audit_push() and tty_audit_push_current() perform identical tasks; eliminate the tty_audit_push() implementation and the tty_audit_push_current() name. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 83d74dcfb3c8..dea7d54d00d4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -597,8 +597,7 @@ extern void tty_audit_add_data(struct tty_struct *tty, const void *data, extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); -extern void tty_audit_push(void); -extern int tty_audit_push_current(void); +extern int tty_audit_push(void); #else static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) @@ -613,10 +612,7 @@ static inline void tty_audit_exit(void) static inline void tty_audit_fork(struct signal_struct *sig) { } -static inline void tty_audit_push(void) -{ -} -static inline int tty_audit_push_current(void) +static inline int tty_audit_push(void) { return 0; } -- cgit v1.2.3 From 2e28d38ae1d9ced6ac2deb4001aca3f267304cdb Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 22:55:33 -0800 Subject: tty: audit: Handle tty audit enable atomically The audit_tty and audit_tty_log_passwd fields are actually bool values, so merge into single memory location to access atomically. NB: audit log operations may still occur after tty audit is disabled which is consistent with the existing functionality Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/audit.h | 4 ++++ include/linux/sched.h | 1 - 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b40ed5df5542..e38e3fc13ea8 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -109,6 +109,10 @@ extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 +/* bit values for ->signal->audit_tty */ +#define AUDIT_TTY_ENABLE BIT(0) +#define AUDIT_TTY_LOG_PASSWD BIT(1) + struct filename; extern void audit_log_session_info(struct audit_buffer *ab); diff --git a/include/linux/sched.h b/include/linux/sched.h index a10494a94cc3..a389222e9703 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -775,7 +775,6 @@ struct signal_struct { #endif #ifdef CONFIG_AUDIT unsigned audit_tty; - unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif -- cgit v1.2.3 From bee6741ca022f051ea1b46e16fb2ff0097643181 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:45:09 -0800 Subject: tty, n_tty: Remove fasync() ldisc notification Only the N_TTY line discipline implements the signal-driven i/o notification enabled/disabled by fcntl(F_SETFL, O_ASYNC). The ldisc fasync() notification is sent to the ldisc when the enable state has changed (the tty core is notified via the fasync() VFS file operation). The N_TTY line discipline used the enable state to change the wakeup condition (minimum_to_wake = 1) for notifying the signal handler i/o is available. However, just the presence of data is sufficient and necessary to signal i/o is available, so changing minimum_to_wake is unnecessary (and creates a race condition with read() and poll() which may be concurrently updating minimum_to_wake). Furthermore, since the kill_fasync() VFS helper performs no action if the fasync list is empty, calling unconditionally is preferred; if signal driven i/o just has been disabled, no signal will be sent by kill_fasync() anyway so notification of the change via the ldisc fasync() method is superfluous. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 6101ab8dc148..3971cf0eb467 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -98,11 +98,6 @@ * seek to perform this action quickly but should wait until * any pending driver I/O is completed. * - * void (*fasync)(struct tty_struct *, int on) - * - * Notify line discipline when signal-driven I/O is enabled or - * disabled. - * * void (*dcd_change)(struct tty_struct *tty, unsigned int status) * * Tells the discipline that the DCD pin has changed its status. @@ -202,7 +197,6 @@ struct tty_ldisc_ops { char *fp, int count); void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int); - void (*fasync)(struct tty_struct *tty, int on); int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, char *fp, int count); -- cgit v1.2.3 From f33798deecbd59a2955f40ac0ae2bc7dff54c069 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 20:36:12 -0800 Subject: tty: Fix GPF in flush_to_ldisc(), part 2 commit 9ce119f318ba ("tty: Fix GPF in flush_to_ldisc()") fixed a GPF caused by a line discipline which does not define a receive_buf() method. However, the vt driver (and speakup driver also) pushes selection data directly to the line discipline receive_buf() method via tty_ldisc_receive_buf(). Fix the same problem in tty_ldisc_receive_buf(). Cc: Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index dea7d54d00d4..03e4015fa033 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -579,7 +579,7 @@ static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, count = ld->ops->receive_buf2(ld->tty, p, f, count); else { count = min_t(int, count, ld->tty->receive_room); - if (count) + if (count && ld->ops->receive_buf) ld->ops->receive_buf(ld->tty, p, f, count); } return count; -- cgit v1.2.3 From 8d082cd300ab422b7ee9f4629a1c470e4f0d90d5 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 20:36:13 -0800 Subject: tty: Unify receive_buf() code paths Instead of two distinct code branches for receive_buf() handling, use tty_ldisc_receive_buf() as the single code path. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 03e4015fa033..3b09f235db66 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -571,20 +571,8 @@ extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); extern void tty_ldisc_release(struct tty_struct *tty); extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); - -static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, - char *f, int count) -{ - if (ld->ops->receive_buf2) - count = ld->ops->receive_buf2(ld->tty, p, f, count); - else { - count = min_t(int, count, ld->tty->receive_room); - if (count && ld->ops->receive_buf) - ld->ops->receive_buf(ld->tty, p, f, count); - } - return count; -} - +extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, + char *f, int count); /* n_tty.c */ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); -- cgit v1.2.3 From a657eecd022d82c5b1795243f54389112f42c7f9 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 14:51:39 -0800 Subject: isdn: Remove ASYNC_CLOSING The tty core no longer provides ASYNC_CLOSING. Use private flag for same purpose, which is to disable AT-emulator output (why this is necessary is not clear). Cc: Karsten Keil Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/isdn.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/isdn.h b/include/linux/isdn.h index 1e9a0f2a8626..df97c8444f5d 100644 --- a/include/linux/isdn.h +++ b/include/linux/isdn.h @@ -319,6 +319,7 @@ typedef struct modem_info { int online; /* 1 = B-Channel is up, drop data */ /* 2 = B-Channel is up, deliver d.*/ int dialing; /* Dial in progress or ATA */ + int closing; int rcvsched; /* Receive needs schedule */ int isdn_driver; /* Index to isdn-driver */ int isdn_channel; /* Index to isdn-channel */ -- cgit v1.2.3 From 50359819794b4a16ae35051cd80f2dab025f6019 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2016 21:53:09 +0100 Subject: clk-divider: make sure read-only dividers do not write to their register Commit e6d5e7d90be9 ("clk-divider: Fix READ_ONLY when divider > 1") removed the special ops struct for read-only clocks and instead opted to handle them inside the regular ops. On the rk3368 this results in breakage as aclkm now gets set a value. While it is the same divider value, the A53 core still doesn't like it, which can result in the cpu ending up in a hang. The reason being that "ACLKENMasserts one clock cycle before the rising edge of ACLKM" and the clock should only be touched when STANDBYWFIL2 is asserted. To fix this, reintroduce the read-only ops but do include the round_rate callback. That way no writes that may be unsafe are done to the divider register in any case. The Rockchip use of the clk_divider_ops is adapted to this split again, as is the nxp, lpc18xx-ccu driver that was included since the original commit. On lpc18xx-ccu the divider seems to always be read-only so only uses the new ops now. Fixes: e6d5e7d90be9 ("clk-divider: Fix READ_ONLY when divider > 1") Reported-by: Zhang Qing Signed-off-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1143e38555a4..408a60dca353 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -385,6 +385,7 @@ struct clk_divider { #define CLK_DIVIDER_MAX_AT_ZERO BIT(6) extern const struct clk_ops clk_divider_ops; +extern const struct clk_ops clk_divider_ro_ops; unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate, unsigned int val, const struct clk_div_table *table, -- cgit v1.2.3 From 5fd9c05c846db98319e75496612da24435cee208 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 8 Jan 2016 23:51:46 +0800 Subject: clk: move the common clock's to_clk_*(_hw) macros to clk-provider.h to_clk_*(_hw) macros have been repeatedly defined in many places. This patch moves all the to_clk_*(_hw) definitions in the common clock framework to public header clk-provider.h, and drop the local definitions. Signed-off-by: Geliang Tang Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 408a60dca353..33dc814d0f43 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -276,6 +276,8 @@ struct clk_fixed_rate { u8 flags; }; +#define to_clk_fixed_rate(_hw) container_of(_hw, struct clk_fixed_rate, hw) + extern const struct clk_ops clk_fixed_rate_ops; struct clk *clk_register_fixed_rate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, @@ -314,6 +316,8 @@ struct clk_gate { spinlock_t *lock; }; +#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw) + #define CLK_GATE_SET_TO_DISABLE BIT(0) #define CLK_GATE_HIWORD_MASK BIT(1) @@ -376,6 +380,8 @@ struct clk_divider { spinlock_t *lock; }; +#define to_clk_divider(_hw) container_of(_hw, struct clk_divider, hw) + #define CLK_DIVIDER_ONE_BASED BIT(0) #define CLK_DIVIDER_POWER_OF_TWO BIT(1) #define CLK_DIVIDER_ALLOW_ZERO BIT(2) @@ -441,6 +447,8 @@ struct clk_mux { spinlock_t *lock; }; +#define to_clk_mux(_hw) container_of(_hw, struct clk_mux, hw) + #define CLK_MUX_INDEX_ONE BIT(0) #define CLK_MUX_INDEX_BIT BIT(1) #define CLK_MUX_HIWORD_MASK BIT(2) @@ -484,6 +492,8 @@ struct clk_fixed_factor { unsigned int div; }; +#define to_clk_fixed_factor(_hw) container_of(_hw, struct clk_fixed_factor, hw) + extern const struct clk_ops clk_fixed_factor_ops; struct clk *clk_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, @@ -515,6 +525,8 @@ struct clk_fractional_divider { spinlock_t *lock; }; +#define to_clk_fd(_hw) container_of(_hw, struct clk_fractional_divider, hw) + extern const struct clk_ops clk_fractional_divider_ops; struct clk *clk_register_fractional_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, @@ -551,6 +563,8 @@ struct clk_multiplier { spinlock_t *lock; }; +#define to_clk_multiplier(_hw) container_of(_hw, struct clk_multiplier, hw) + #define CLK_MULTIPLIER_ZERO_BYPASS BIT(0) #define CLK_MULTIPLIER_ROUND_CLOSEST BIT(1) @@ -580,6 +594,8 @@ struct clk_composite { const struct clk_ops *gate_ops; }; +#define to_clk_composite(_hw) container_of(_hw, struct clk_composite, hw) + struct clk *clk_register_composite(struct device *dev, const char *name, const char * const *parent_names, int num_parents, struct clk_hw *mux_hw, const struct clk_ops *mux_ops, @@ -602,6 +618,8 @@ struct clk_gpio { struct gpio_desc *gpiod; }; +#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw) + extern const struct clk_ops clk_gpio_gate_ops; struct clk *clk_register_gpio_gate(struct device *dev, const char *name, const char *parent_name, unsigned gpio, bool active_low, -- cgit v1.2.3 From cbf9591f665d44f40795afe2eee4fcbcd32575d6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 6 Jan 2016 13:25:09 +0900 Subject: clk: add clk_unregister_fixed_factor() Allow to unregister fixed factor clock. Signed-off-by: Masahiro Yamada Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 33dc814d0f43..3641eecf462a 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -498,6 +498,7 @@ extern const struct clk_ops clk_fixed_factor_ops; struct clk *clk_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +void clk_unregister_fixed_factor(struct clk *clk); /** * struct clk_fractional_divider - adjustable fractional divider clock -- cgit v1.2.3 From 0b225e41e369a7e03411bb67988513302a10382f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 6 Jan 2016 13:25:10 +0900 Subject: clk: add clk_unregister_fixed_rate() Allow to unregister fixed rate clock. Signed-off-by: Masahiro Yamada Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 3641eecf462a..fabe5bedbba6 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -285,7 +285,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, struct clk *clk_register_fixed_rate_with_accuracy(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned long fixed_rate, unsigned long fixed_accuracy); - +void clk_unregister_fixed_rate(struct clk *clk); void of_fixed_clk_setup(struct device_node *np); /** -- cgit v1.2.3 From 58f1369216367d27e047bead7221ff977431acaa Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jan 2016 16:45:47 -0500 Subject: SUNRPC: Remove unused function rpc_task_reset_client Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 131032f15cc1..0c5c2cbe96c9 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -139,7 +139,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt *xprt); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, const struct rpc_program *, u32); -void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt); struct rpc_clnt *rpc_clone_client(struct rpc_clnt *); struct rpc_clnt *rpc_clone_client_set_auth(struct rpc_clnt *, rpc_authflavor_t); -- cgit v1.2.3 From 5edd1051f4f3bd7cddcc91e346fdd22eee639c72 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 25 Feb 2015 14:49:16 -0500 Subject: SUNRPC: Reorder rpc_task to put waitqueue related info in same cachelines Try to group all the data required by the waitqueues, their timers and timer callbacks into the same cachelines for performance. With this reordering, "pahole" reports the following structure on x86_64: struct rpc_task { atomic_t tk_count; /* 0 4 */ int tk_status; /* 4 4 */ struct list_head tk_task; /* 8 16 */ void (*tk_callback)(struct rpc_task *); /* 24 void (*tk_action)(struct rpc_task *); /* 32 long unsigned int tk_timeout; /* 40 8 */ long unsigned int tk_runstate; /* 48 8 */ struct rpc_wait_queue * tk_waitqueue; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ union { struct work_struct tk_work; /* 64 */ struct rpc_wait tk_wait; /* 56 */ } u; /* 64 64 */ /* --- cacheline 2 boundary (128 bytes) --- */ struct rpc_message tk_msg; /* 128 32 */ void * tk_calldata; /* 160 8 */ const struct rpc_call_ops * tk_ops; /* 168 8 */ struct rpc_clnt * tk_client; /* 176 8 */ struct rpc_rqst * tk_rqstp; /* 184 8 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct workqueue_struct * tk_workqueue; /* 192 8 */ ktime_t tk_start; /* 200 8 */ pid_t tk_owner; /* 208 4 */ short unsigned int tk_flags; /* 212 2 */ short unsigned int tk_timeouts; /* 214 2 */ short unsigned int tk_pid; /* 216 2 */ unsigned char tk_priority:2; /* 218: 6 1 */ unsigned char tk_garb_retry:2; /* 218: 4 1 */ unsigned char tk_cred_retry:2; /* 218: 2 1 */ unsigned char tk_rebind_retry:2; /* 218: 0 1 */ /* size: 224, cachelines: 4, members: 24 */ /* padding: 5 */ /* last cacheline: 32 bytes */ }; whereas on i386, it reports everything fitting into the 1st cacheline. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index d703f0ef37d8..ee0fbcf9b02e 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -42,40 +42,41 @@ struct rpc_wait { */ struct rpc_task { atomic_t tk_count; /* Reference count */ + int tk_status; /* result of last operation */ struct list_head tk_task; /* global list of tasks */ - struct rpc_clnt * tk_client; /* RPC client */ - struct rpc_rqst * tk_rqstp; /* RPC request */ - - /* - * RPC call state - */ - struct rpc_message tk_msg; /* RPC call info */ /* * callback to be executed after waking up * action next procedure for async tasks - * tk_ops caller callbacks */ void (*tk_callback)(struct rpc_task *); void (*tk_action)(struct rpc_task *); - const struct rpc_call_ops *tk_ops; - void * tk_calldata; unsigned long tk_timeout; /* timeout for rpc_sleep() */ unsigned long tk_runstate; /* Task run status */ - struct workqueue_struct *tk_workqueue; /* Normally rpciod, but could - * be any workqueue - */ + struct rpc_wait_queue *tk_waitqueue; /* RPC wait queue we're on */ union { struct work_struct tk_work; /* Async task work queue */ struct rpc_wait tk_wait; /* RPC wait */ } u; + /* + * RPC call state + */ + struct rpc_message tk_msg; /* RPC call info */ + void * tk_calldata; /* Caller private data */ + const struct rpc_call_ops *tk_ops; /* Caller callbacks */ + + struct rpc_clnt * tk_client; /* RPC client */ + struct rpc_rqst * tk_rqstp; /* RPC request */ + + struct workqueue_struct *tk_workqueue; /* Normally rpciod, but could + * be any workqueue + */ ktime_t tk_start; /* RPC task init timestamp */ pid_t tk_owner; /* Process id for batching tasks */ - int tk_status; /* result of last operation */ unsigned short tk_flags; /* misc flags */ unsigned short tk_timeouts; /* maj timeouts */ -- cgit v1.2.3 From 30c5116b113689c87a711a0963753adadd702c04 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 24 Feb 2015 20:31:39 -0500 Subject: SUNRPC: Uninline xprt_get(); It isn't performance critical. Also allow callers to pass NULL arguments to xprt_get() and xprt_put(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 69ef5b3ab038..1bdb59a2efe8 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -166,7 +167,7 @@ enum xprt_transports { }; struct rpc_xprt { - atomic_t count; /* Reference count */ + struct kref kref; /* Reference count */ struct rpc_xprt_ops * ops; /* transport methods */ const struct rpc_timeout *timeout; /* timeout parms */ @@ -318,24 +319,13 @@ int xprt_adjust_timeout(struct rpc_rqst *req); void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_release(struct rpc_task *task); +struct rpc_xprt * xprt_get(struct rpc_xprt *xprt); void xprt_put(struct rpc_xprt *xprt); struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int num_prealloc, unsigned int max_req); void xprt_free(struct rpc_xprt *); -/** - * xprt_get - return a reference to an RPC transport. - * @xprt: pointer to the transport - * - */ -static inline struct rpc_xprt *xprt_get(struct rpc_xprt *xprt) -{ - if (atomic_inc_not_zero(&xprt->count)) - return xprt; - return NULL; -} - static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p) { return p + xprt->tsh_size; -- cgit v1.2.3 From fda1bfef9e465b28260d27cd9e538dd601c4cdc1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 Feb 2015 17:48:49 -0500 Subject: SUNRPC: Make freeing of struct xprt rcu-safe Have it call kfree_rcu() to ensure that we can use it on rcu-protected lists. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 1bdb59a2efe8..83218129ff28 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -257,6 +257,7 @@ struct rpc_xprt { struct dentry *debugfs; /* debugfs directory */ atomic_t inject_disconnect; #endif + struct rcu_head rcu; }; #if defined(CONFIG_SUNRPC_BACKCHANNEL) -- cgit v1.2.3 From 70d2a3cf2f4ae2e93b7a661842d84c2b5132cee7 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 1 Feb 2016 22:06:56 +0000 Subject: efi: Remove redundant efi_set_variable_nonblocking() prototype There is no need for a separate nonblocking prototype definition for the SetVariable() UEFI Runtime Service, since it is identical to the blocking version. Signed-off-by: Ard Biesheuvel Signed-off-by: Matt Fleming Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1454364428-494-3-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 569b5a866bb1..8706e0aabedc 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -507,10 +507,6 @@ typedef efi_status_t efi_get_next_variable_t (unsigned long *name_size, efi_char typedef efi_status_t efi_set_variable_t (efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data); -typedef efi_status_t -efi_set_variable_nonblocking_t(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, void *data); - typedef efi_status_t efi_get_next_high_mono_count_t (u32 *count); typedef void efi_reset_system_t (int reset_type, efi_status_t status, unsigned long data_size, efi_char16_t *data); @@ -851,7 +847,7 @@ extern struct efi { efi_get_variable_t *get_variable; efi_get_next_variable_t *get_next_variable; efi_set_variable_t *set_variable; - efi_set_variable_nonblocking_t *set_variable_nonblocking; + efi_set_variable_t *set_variable_nonblocking; efi_query_variable_info_t *query_variable_info; efi_update_capsule_t *update_capsule; efi_query_capsule_caps_t *query_capsule_caps; @@ -1091,7 +1087,7 @@ struct efivar_operations { efi_get_variable_t *get_variable; efi_get_next_variable_t *get_next_variable; efi_set_variable_t *set_variable; - efi_set_variable_nonblocking_t *set_variable_nonblocking; + efi_set_variable_t *set_variable_nonblocking; efi_query_variable_store_t *query_variable_store; }; -- cgit v1.2.3 From d3cac1f83c631b9fe5edaebcba49f6989bfff089 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 1 Feb 2016 22:06:57 +0000 Subject: efi/runtime-wrappers: Add a nonblocking version of QueryVariableInfo() This introduces a new runtime wrapper for the QueryVariableInfo() UEFI Runtime Service, which gives up immediately rather than spins on failure to grab the efi_runtime spinlock. This is required in the non-blocking path of the efi-pstore code. Signed-off-by: Ard Biesheuvel Signed-off-by: Matt Fleming Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1454364428-494-4-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8706e0aabedc..ad1e177ba48e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -849,6 +849,7 @@ extern struct efi { efi_set_variable_t *set_variable; efi_set_variable_t *set_variable_nonblocking; efi_query_variable_info_t *query_variable_info; + efi_query_variable_info_t *query_variable_info_nonblocking; efi_update_capsule_t *update_capsule; efi_query_capsule_caps_t *query_capsule_caps; efi_get_next_high_mono_count_t *get_next_high_mono_count; -- cgit v1.2.3 From ca0e30dcaa53a3fcb2dfdf74252d30bc40603eea Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 1 Feb 2016 22:06:58 +0000 Subject: efi: Add nonblocking option to efi_query_variable_store() The function efi_query_variable_store() may be invoked by efivar_entry_set_nonblocking(), which itself takes care to only call a non-blocking version of the SetVariable() runtime wrapper. However, efi_query_variable_store() may call the SetVariable() wrapper directly, as well as the wrapper for QueryVariableInfo(), both of which could deadlock in the same way we are trying to prevent by calling efivar_entry_set_nonblocking() in the first place. So instead, modify efi_query_variable_store() to use the non-blocking variants of QueryVariableInfo() (and give up rather than free up space if the available space is below EFI_MIN_RESERVE) if invoked with the 'nonblocking' argument set to true. Signed-off-by: Ard Biesheuvel Signed-off-by: Matt Fleming Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1454364428-494-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index ad1e177ba48e..09f1559e7525 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -525,7 +525,9 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules, unsigned long count, u64 *max_size, int *reset_type); -typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size); +typedef efi_status_t efi_query_variable_store_t(u32 attributes, + unsigned long size, + bool nonblocking); void efi_native_runtime_setup(void); @@ -881,13 +883,17 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos #ifdef CONFIG_X86 extern void efi_late_init(void); extern void efi_free_boot_services(void); -extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size); +extern efi_status_t efi_query_variable_store(u32 attributes, + unsigned long size, + bool nonblocking); extern void efi_find_mirror(void); #else static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} -static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +static inline efi_status_t efi_query_variable_store(u32 attributes, + unsigned long size, + bool nonblocking) { return EFI_SUCCESS; } -- cgit v1.2.3 From c016ca08f89c6c78ed815f025262bdb87aba3f4c Mon Sep 17 00:00:00 2001 From: Robert Elliott Date: Mon, 1 Feb 2016 22:07:06 +0000 Subject: efi: Add NV memory attribute Add the NV memory attribute introduced in UEFI 2.5 and add a column for it in the types and attributes string used when printing the UEFI memory map. old: efi: mem61: [type=14 | | | | | | | |WB|WT|WC|UC] range=[0x0000000880000000-0x0000000c7fffffff) (16384MB) new: efi: mem61: [type=14 | | |NV| | | | | |WB|WT|WC|UC] range=[0x0000000880000000-0x0000000c7fffffff) (16384MB) Signed-off-by: Robert Elliott Signed-off-by: Matt Fleming Reviewed-by: Laszlo Ersek Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: Brian Gerst Cc: Dan Williams Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Ross Zwisler Cc: Taku Izumi Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1454364428-494-13-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 09f1559e7525..3c6cbbdae4aa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -97,6 +97,7 @@ typedef struct { #define EFI_MEMORY_WP ((u64)0x0000000000001000ULL) /* write-protect */ #define EFI_MEMORY_RP ((u64)0x0000000000002000ULL) /* read-protect */ #define EFI_MEMORY_XP ((u64)0x0000000000004000ULL) /* execute-protect */ +#define EFI_MEMORY_NV ((u64)0x0000000000008000ULL) /* non-volatile */ #define EFI_MEMORY_MORE_RELIABLE \ ((u64)0x0000000000010000ULL) /* higher reliability */ #define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ -- cgit v1.2.3 From 5363de75307e333d89df7531f9dd8310d973ecdb Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 25 Jan 2016 20:30:30 +0100 Subject: usb: core: switch bus numbering to using idr USB bus numbering is based on directly dealing with bitmaps and defines a separate list of busses. This can be simplified and unified by using existing idr functionality. Signed-off-by: Heiner Kallweit Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 1 - include/linux/usb/hcd.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 89533ba38691..0d348fa84a66 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -375,7 +375,6 @@ struct usb_bus { struct usb_devmap devmap; /* device address allocation map */ struct usb_device *root_hub; /* Root hub */ struct usb_bus *hs_companion; /* Companion EHCI bus, if any */ - struct list_head bus_list; /* list of busses */ struct mutex usb_address0_mutex; /* unaddressed device mutex */ diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 4dcf8446dbcd..c293dd044599 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -23,6 +23,7 @@ #include #include +#include #define MAX_TOPO_LEVEL 6 @@ -630,7 +631,7 @@ extern void usb_set_device_state(struct usb_device *udev, /* exported only within usbcore */ -extern struct list_head usb_bus_list; +extern struct idr usb_bus_idr; extern struct mutex usb_bus_list_lock; extern wait_queue_head_t usb_kill_urb_queue; -- cgit v1.2.3 From 7dd9cba5bb90ffa9c60c1533b715dc91c5082cd9 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 21 Jan 2016 15:18:47 +0100 Subject: usb: sysfs: make locking interruptible 232275a USB: fix substandard locking for the sysfs files introduced needed locking into sysfs operations on USB devices It, however, uses uninterruptible sleep and if the error handling is on extreme cases of sleep lengths of 10s of seconds are possible. Unless we are removing the device we should use interruptible sleep. Signed-off-by: Oliver Neukum Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 +++++ include/linux/usb.h | 7 ++++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 6d6f1fec092f..2d0e6e541d52 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -958,6 +958,11 @@ static inline void device_lock(struct device *dev) mutex_lock(&dev->mutex); } +static inline int device_lock_interruptible(struct device *dev) +{ + return mutex_lock_interruptible(&dev->mutex); +} + static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); diff --git a/include/linux/usb.h b/include/linux/usb.h index 0d348fa84a66..dc0ea0de8a81 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -641,9 +641,10 @@ extern struct usb_device *usb_hub_find_child(struct usb_device *hdev, if (!child) continue; else /* USB device locking */ -#define usb_lock_device(udev) device_lock(&(udev)->dev) -#define usb_unlock_device(udev) device_unlock(&(udev)->dev) -#define usb_trylock_device(udev) device_trylock(&(udev)->dev) +#define usb_lock_device(udev) device_lock(&(udev)->dev) +#define usb_unlock_device(udev) device_unlock(&(udev)->dev) +#define usb_lock_device_interruptible(udev) device_lock_interruptible(&(udev)->dev) +#define usb_trylock_device(udev) device_trylock(&(udev)->dev) extern int usb_lock_device_for_reset(struct usb_device *udev, const struct usb_interface *iface); -- cgit v1.2.3 From 1b83349fddd1efa814a83735e44e684a139d2425 Mon Sep 17 00:00:00 2001 From: Antonio Ospite Date: Wed, 27 Jan 2016 15:05:49 +0100 Subject: usb/storage: misc fixes to comments in include/linux/usb/storage.h The fixes are: - fix indentation of a comment - fix a typo in the comment about bulk_cb_wrap.Length - make comment about US_BULK_CB_SIGN look like the one about US_BULK_CS_SIGN below - make the comment about bulk_cs_wrap.Signature look more like the one about bulk_cb_wrap.Signature Signed-off-by: Antonio Ospite Cc: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/storage.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/storage.h b/include/linux/usb/storage.h index cb33fff2ba0b..305ee8db7faf 100644 --- a/include/linux/usb/storage.h +++ b/include/linux/usb/storage.h @@ -45,9 +45,9 @@ #define USB_PR_DEVICE 0xff /* Use device's value */ - /* - * Bulk only data structures - */ +/* + * Bulk only data structures + */ /* command block wrapper */ struct bulk_cb_wrap { @@ -56,18 +56,18 @@ struct bulk_cb_wrap { __le32 DataTransferLength; /* size of data */ __u8 Flags; /* direction in bit 0 */ __u8 Lun; /* LUN normally 0 */ - __u8 Length; /* of of the CDB */ + __u8 Length; /* length of the CDB */ __u8 CDB[16]; /* max command */ }; #define US_BULK_CB_WRAP_LEN 31 -#define US_BULK_CB_SIGN 0x43425355 /*spells out USBC */ +#define US_BULK_CB_SIGN 0x43425355 /* spells out 'USBC' */ #define US_BULK_FLAG_IN (1 << 7) #define US_BULK_FLAG_OUT 0 /* command status wrapper */ struct bulk_cs_wrap { - __le32 Signature; /* should = 'USBS' */ + __le32 Signature; /* contains 'USBS' */ __u32 Tag; /* same as original command */ __le32 Residue; /* amount not transferred */ __u8 Status; /* see below */ -- cgit v1.2.3 From de1df26b7cef702a32ae876ed45c1112f523df48 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 5 Feb 2016 02:37:42 +0100 Subject: cpufreq: Clean up default and fallback governor setup The preprocessor magic used for setting the default cpufreq governor (and for using the performance governor as a fallback one for that matter) is really nasty, so replace it with __weak functions and overrides. Signed-off-by: Rafael J. Wysocki Acked-by: Saravana Kannan Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 25 ++----------------------- 1 file changed, 2 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 88a4215125bc..d0bf555b6bbf 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -464,29 +464,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); -/* CPUFREQ DEFAULT GOVERNOR */ -/* - * Performance governor is fallback governor if any other gov failed to auto - * load due latency restrictions - */ -#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE -extern struct cpufreq_governor cpufreq_gov_performance; -#endif -#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_performance) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE) -extern struct cpufreq_governor cpufreq_gov_powersave; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_powersave) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE) -extern struct cpufreq_governor cpufreq_gov_userspace; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_userspace) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND) -extern struct cpufreq_governor cpufreq_gov_ondemand; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_ondemand) -#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE) -extern struct cpufreq_governor cpufreq_gov_conservative; -#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative) -#endif +struct cpufreq_governor *cpufreq_default_governor(void); +struct cpufreq_governor *cpufreq_fallback_governor(void); /********************************************************************* * FREQUENCY TABLE HELPERS * -- cgit v1.2.3 From b7aad8e2685b0aa58295bc4250c8476c9c7193eb Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 30 Dec 2015 09:55:45 +0900 Subject: extcon: palmas: Add the support for VBUS detection by using GPIO This patch support for VBUS detection by using GPIO pin. Signed-off-by: Felipe Balbi Signed-off-by: Chanwoo Choi Acked-by: Lee Jones --- include/linux/mfd/palmas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index c800dbc42079..5c9a1d44c125 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -580,7 +580,9 @@ struct palmas_usb { int vbus_irq; int gpio_id_irq; + int gpio_vbus_irq; struct gpio_desc *id_gpiod; + struct gpio_desc *vbus_gpiod; unsigned long sw_debounce_jiffies; struct delayed_work wq_detectid; @@ -589,6 +591,7 @@ struct palmas_usb { bool enable_vbus_detection; bool enable_id_detection; bool enable_gpio_id_detection; + bool enable_gpio_vbus_detection; }; #define comparator_to_palmas(x) container_of((x), struct palmas_usb, comparator) -- cgit v1.2.3 From 7e6213f4345c3798b7fb7af41d221e2fd77ec6a6 Mon Sep 17 00:00:00 2001 From: Paul Kocialkowski Date: Fri, 5 Feb 2016 19:42:19 +0100 Subject: regulator: lp872x: Add enable GPIO pin support LP872x regulators are made active via the EN pin, which might be hooked to a GPIO. This adds support for driving the GPIO high when the driver is in use. Signed-off-by: Paul Kocialkowski Signed-off-by: Mark Brown --- include/linux/regulator/lp872x.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/lp872x.h b/include/linux/regulator/lp872x.h index 132e05c46661..6029279f4eed 100644 --- a/include/linux/regulator/lp872x.h +++ b/include/linux/regulator/lp872x.h @@ -18,6 +18,9 @@ #define LP872X_MAX_REGULATORS 9 +#define LP8720_ENABLE_DELAY 200 +#define LP8725_ENABLE_DELAY 30000 + enum lp872x_regulator_id { LP8720_ID_BASE, LP8720_ID_LDO1 = LP8720_ID_BASE, @@ -79,12 +82,14 @@ struct lp872x_regulator_data { * @update_config : if LP872X_GENERAL_CFG register is updated, set true * @regulator_data : platform regulator id and init data * @dvs : dvs data for buck voltage control + * @enable_gpio : gpio pin number for enable control */ struct lp872x_platform_data { u8 general_config; bool update_config; struct lp872x_regulator_data regulator_data[LP872X_MAX_REGULATORS]; struct lp872x_dvs *dvs; + int enable_gpio; }; #endif -- cgit v1.2.3 From 5bbe029ff7bc8ff82ef31d3480d68c95642a3c7a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 5 Feb 2016 14:57:47 -0600 Subject: PCI: Move pci_set_flags() from asm-generic/pci-bridge.h to linux/pci.h The PCI flag management constants and functions were previously declared in include/asm-generic/pci-bridge.h. But they are not specific to bridges, and arches did not include pci-bridge.h consistently. Move the following interfaces and related constants to include/linux/pci.h and remove pci-bridge.h: pci_set_flags() pci_add_flags() pci_clear_flags() pci_has_flag() This fixes these warnings when building for some arches: drivers/pci/host/pcie-designware.c:562:20: error: 'PCI_PROBE_ONLY' undeclared (first use in this function) drivers/pci/host/pcie-designware.c:562:7: error: implicit declaration of function 'pci_has_flag' [-Werror=implicit-function-declaration] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..3d371c150753 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -746,9 +746,26 @@ struct pci_driver { .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 +enum { + PCI_REASSIGN_ALL_RSRC = 0x00000001, /* ignore firmware setup */ + PCI_REASSIGN_ALL_BUS = 0x00000002, /* reassign all bus numbers */ + PCI_PROBE_ONLY = 0x00000004, /* use existing setup */ + PCI_CAN_SKIP_ISA_ALIGN = 0x00000008, /* don't do ISA alignment */ + PCI_ENABLE_PROC_DOMAINS = 0x00000010, /* enable domains in /proc */ + PCI_COMPAT_DOMAIN_0 = 0x00000020, /* ... except domain 0 */ + PCI_SCAN_ALL_PCIE_DEVS = 0x00000040, /* scan all, not just dev 0 */ +}; + /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI +extern unsigned int pci_flags; + +static inline void pci_set_flags(int flags) { pci_flags = flags; } +static inline void pci_add_flags(int flags) { pci_flags |= flags; } +static inline void pci_clear_flags(int flags) { pci_flags &= ~flags; } +static inline int pci_has_flag(int flag) { return pci_flags & flag; } + void pcie_bus_configure_settings(struct pci_bus *bus); enum pcie_bus_config_types { @@ -1405,6 +1422,11 @@ void pci_register_set_vga_state(arch_set_vga_state_t func); #else /* CONFIG_PCI is not enabled */ +static inline void pci_set_flags(int flags) { } +static inline void pci_add_flags(int flags) { } +static inline void pci_clear_flags(int flags) { } +static inline int pci_has_flag(int flag) { return 0; } + /* * If the system does not have PCI, clearly these return errors. Define * these as simple inline functions to avoid hair in drivers. -- cgit v1.2.3 From 80b14d5e61ca6d08e46b4fc72baf6e4f738b30ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 Feb 2015 20:31:59 -0500 Subject: SUNRPC: Add a structure to track multiple transports In order to support multipathing/trunking we will need the ability to track multiple transports. This patch sets up a basic structure for doing so. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 5 +++ include/linux/sunrpc/xprtmultipath.h | 69 ++++++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) create mode 100644 include/linux/sunrpc/xprtmultipath.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 83218129ff28..fb0d212e0d3a 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -197,6 +197,11 @@ struct rpc_xprt { transport */ unsigned int bind_index; /* bind function index */ + /* + * Multipath + */ + struct list_head xprt_switch; + /* * Connection of transports */ diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h new file mode 100644 index 000000000000..5a9acffa41be --- /dev/null +++ b/include/linux/sunrpc/xprtmultipath.h @@ -0,0 +1,69 @@ +/* + * RPC client multipathing definitions + * + * Copyright (c) 2015, 2016, Primary Data, Inc. All rights reserved. + * + * Trond Myklebust + */ +#ifndef _NET_SUNRPC_XPRTMULTIPATH_H +#define _NET_SUNRPC_XPRTMULTIPATH_H + +struct rpc_xprt_iter_ops; +struct rpc_xprt_switch { + spinlock_t xps_lock; + struct kref xps_kref; + + unsigned int xps_nxprts; + struct list_head xps_xprt_list; + + struct net * xps_net; + + const struct rpc_xprt_iter_ops *xps_iter_ops; + + struct rcu_head xps_rcu; +}; + +struct rpc_xprt_iter { + struct rpc_xprt_switch __rcu *xpi_xpswitch; + struct rpc_xprt * xpi_cursor; + + const struct rpc_xprt_iter_ops *xpi_ops; +}; + + +struct rpc_xprt_iter_ops { + void (*xpi_rewind)(struct rpc_xprt_iter *); + struct rpc_xprt *(*xpi_xprt)(struct rpc_xprt_iter *); + struct rpc_xprt *(*xpi_next)(struct rpc_xprt_iter *); +}; + +extern struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, + gfp_t gfp_flags); + +extern struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps); +extern void xprt_switch_put(struct rpc_xprt_switch *xps); + +extern void rpc_xprt_switch_set_roundrobin(struct rpc_xprt_switch *xps); + +extern void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt); +extern void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt); + +extern void xprt_iter_init(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps); + +extern void xprt_iter_init_listall(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps); + +extern void xprt_iter_destroy(struct rpc_xprt_iter *xpi); + +extern struct rpc_xprt_switch *xprt_iter_xchg_switch( + struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *newswitch); + +extern struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi); +extern struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi); +extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); + +#endif -- cgit v1.2.3 From ad01b2c68d0ac5f3d4a3f807bec77b720b1c62a0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jan 2016 14:17:26 -0500 Subject: SUNRPC: Make rpc_clnt store the multipath iterators This is a pre-patch for the RPC multipath code. It sets up the storage in struct rpc_clnt for the multipath code. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 0c5c2cbe96c9..1713e41d65ae 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -25,6 +25,7 @@ #include #include #include +#include struct rpc_inode; @@ -67,6 +68,7 @@ struct rpc_clnt { #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *cl_debugfs; /* debugfs directory */ #endif + struct rpc_xprt_iter cl_xpi; }; /* -- cgit v1.2.3 From fb43d17210baa538e58fc83d2d0f8a32399db73b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jan 2016 16:39:26 -0500 Subject: SUNRPC: Use the multipath iterator to assign a transport to each task Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ee0fbcf9b02e..0b248e98ee3b 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -69,6 +69,8 @@ struct rpc_task { const struct rpc_call_ops *tk_ops; /* Caller callbacks */ struct rpc_clnt * tk_client; /* RPC client */ + struct rpc_xprt * tk_xprt; /* Transport */ + struct rpc_rqst * tk_rqstp; /* RPC request */ struct workqueue_struct *tk_workqueue; /* Normally rpciod, but could -- cgit v1.2.3 From 9d61498d5f6cde68a708781bf2cd33cae21121dc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jan 2016 18:13:05 -0500 Subject: SUNRPC: Allow caller to specify the transport to use This is needed in order to allow the NFSv4.1 backchannel and BIND_CONN_TO_SESSION function to work. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 0b248e98ee3b..05a1809c44d9 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -103,6 +103,7 @@ struct rpc_call_ops { struct rpc_task_setup { struct rpc_task *task; struct rpc_clnt *rpc_client; + struct rpc_xprt *rpc_xprt; const struct rpc_message *rpc_message; const struct rpc_call_ops *callback_ops; void *callback_data; -- cgit v1.2.3 From 3227886c6500e76c17f3b864ff9b7dd84f636a99 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jan 2016 20:39:19 -0500 Subject: SUNRPC: Add a helper to apply a function to all the rpc_clnt's transports Add a helper for tasks that require us to apply a function to all the transports in an rpc_clnt. An example of a usecase would be BIND_CONN_TO_SESSION, where we want to send one RPC call down each transport. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 1713e41d65ae..d6510f64a361 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -182,6 +182,10 @@ size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); int rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t); +int rpc_clnt_iterate_for_each_xprt(struct rpc_clnt *clnt, + int (*fn)(struct rpc_clnt *, struct rpc_xprt *, void *), + void *data); + const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ -- cgit v1.2.3 From 7f554890587c63ca4c087d6bcc4a9fe368e57484 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jan 2016 23:43:35 -0500 Subject: SUNRPC: Allow addition of new transports to a struct rpc_clnt Add a function to allow creation and addition of a new transport to an existing rpc_clnt Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index d6510f64a361..9a7ddbaf116e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -186,6 +186,17 @@ int rpc_clnt_iterate_for_each_xprt(struct rpc_clnt *clnt, int (*fn)(struct rpc_clnt *, struct rpc_xprt *, void *), void *data); +int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, + struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt, + void *dummy); +int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, + int (*setup)(struct rpc_clnt *, + struct rpc_xprt_switch *, + struct rpc_xprt *, + void *), + void *data); + const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ -- cgit v1.2.3 From 896545098777564212b9e91af4c973f094649aa7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 1 Feb 2016 21:36:54 +0800 Subject: crypto: hash - Remove crypto_hash interface This patch removes all traces of the crypto_hash interface, now that everyone has switched over to shash or ahash. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 251 ------------------------------------------------- 1 file changed, 251 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index ab2a745d85f3..99c94899ad0f 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -136,7 +136,6 @@ struct scatterlist; struct crypto_ablkcipher; struct crypto_async_request; struct crypto_blkcipher; -struct crypto_hash; struct crypto_tfm; struct crypto_type; struct skcipher_givcrypt_request; @@ -186,11 +185,6 @@ struct cipher_desc { void *info; }; -struct hash_desc { - struct crypto_hash *tfm; - u32 flags; -}; - /** * DOC: Block Cipher Algorithm Definitions * @@ -518,18 +512,6 @@ struct cipher_tfm { void (*cit_decrypt_one)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; -struct hash_tfm { - int (*init)(struct hash_desc *desc); - int (*update)(struct hash_desc *desc, - struct scatterlist *sg, unsigned int nsg); - int (*final)(struct hash_desc *desc, u8 *out); - int (*digest)(struct hash_desc *desc, struct scatterlist *sg, - unsigned int nsg, u8 *out); - int (*setkey)(struct crypto_hash *tfm, const u8 *key, - unsigned int keylen); - unsigned int digestsize; -}; - struct compress_tfm { int (*cot_compress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, @@ -542,7 +524,6 @@ struct compress_tfm { #define crt_ablkcipher crt_u.ablkcipher #define crt_blkcipher crt_u.blkcipher #define crt_cipher crt_u.cipher -#define crt_hash crt_u.hash #define crt_compress crt_u.compress struct crypto_tfm { @@ -553,7 +534,6 @@ struct crypto_tfm { struct ablkcipher_tfm ablkcipher; struct blkcipher_tfm blkcipher; struct cipher_tfm cipher; - struct hash_tfm hash; struct compress_tfm compress; } crt_u; @@ -580,10 +560,6 @@ struct crypto_comp { struct crypto_tfm base; }; -struct crypto_hash { - struct crypto_tfm base; -}; - enum { CRYPTOA_UNSPEC, CRYPTOA_ALG, @@ -1576,233 +1552,6 @@ static inline void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, dst, src); } -/** - * DOC: Synchronous Message Digest API - * - * The synchronous message digest API is used with the ciphers of type - * CRYPTO_ALG_TYPE_HASH (listed as type "hash" in /proc/crypto) - */ - -static inline struct crypto_hash *__crypto_hash_cast(struct crypto_tfm *tfm) -{ - return (struct crypto_hash *)tfm; -} - -static inline struct crypto_hash *crypto_hash_cast(struct crypto_tfm *tfm) -{ - BUG_ON((crypto_tfm_alg_type(tfm) ^ CRYPTO_ALG_TYPE_HASH) & - CRYPTO_ALG_TYPE_HASH_MASK); - return __crypto_hash_cast(tfm); -} - -/** - * crypto_alloc_hash() - allocate synchronous message digest handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * message digest cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for a message digest. The returned struct - * crypto_hash is the cipher handle that is required for any subsequent - * API invocation for that message digest. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct crypto_hash *crypto_alloc_hash(const char *alg_name, - u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - mask &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_HASH; - mask |= CRYPTO_ALG_TYPE_HASH_MASK; - - return __crypto_hash_cast(crypto_alloc_base(alg_name, type, mask)); -} - -static inline struct crypto_tfm *crypto_hash_tfm(struct crypto_hash *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_hash() - zeroize and free message digest handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_hash(struct crypto_hash *tfm) -{ - crypto_free_tfm(crypto_hash_tfm(tfm)); -} - -/** - * crypto_has_hash() - Search for the availability of a message digest - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * message digest cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the message digest cipher is known to the kernel crypto - * API; false otherwise - */ -static inline int crypto_has_hash(const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - mask &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_HASH; - mask |= CRYPTO_ALG_TYPE_HASH_MASK; - - return crypto_has_alg(alg_name, type, mask); -} - -static inline struct hash_tfm *crypto_hash_crt(struct crypto_hash *tfm) -{ - return &crypto_hash_tfm(tfm)->crt_hash; -} - -/** - * crypto_hash_blocksize() - obtain block size for message digest - * @tfm: cipher handle - * - * The block size for the message digest cipher referenced with the cipher - * handle is returned. - * - * Return: block size of cipher - */ -static inline unsigned int crypto_hash_blocksize(struct crypto_hash *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_hash_tfm(tfm)); -} - -static inline unsigned int crypto_hash_alignmask(struct crypto_hash *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_hash_tfm(tfm)); -} - -/** - * crypto_hash_digestsize() - obtain message digest size - * @tfm: cipher handle - * - * The size for the message digest created by the message digest cipher - * referenced with the cipher handle is returned. - * - * Return: message digest size - */ -static inline unsigned int crypto_hash_digestsize(struct crypto_hash *tfm) -{ - return crypto_hash_crt(tfm)->digestsize; -} - -static inline u32 crypto_hash_get_flags(struct crypto_hash *tfm) -{ - return crypto_tfm_get_flags(crypto_hash_tfm(tfm)); -} - -static inline void crypto_hash_set_flags(struct crypto_hash *tfm, u32 flags) -{ - crypto_tfm_set_flags(crypto_hash_tfm(tfm), flags); -} - -static inline void crypto_hash_clear_flags(struct crypto_hash *tfm, u32 flags) -{ - crypto_tfm_clear_flags(crypto_hash_tfm(tfm), flags); -} - -/** - * crypto_hash_init() - (re)initialize message digest handle - * @desc: cipher request handle that to be filled by caller -- - * desc.tfm is filled with the hash cipher handle; - * desc.flags is filled with either CRYPTO_TFM_REQ_MAY_SLEEP or 0. - * - * The call (re-)initializes the message digest referenced by the hash cipher - * request handle. Any potentially existing state created by previous - * operations is discarded. - * - * Return: 0 if the message digest initialization was successful; < 0 if an - * error occurred - */ -static inline int crypto_hash_init(struct hash_desc *desc) -{ - return crypto_hash_crt(desc->tfm)->init(desc); -} - -/** - * crypto_hash_update() - add data to message digest for processing - * @desc: cipher request handle - * @sg: scatter / gather list pointing to the data to be added to the message - * digest - * @nbytes: number of bytes to be processed from @sg - * - * Updates the message digest state of the cipher handle pointed to by the - * hash cipher request handle with the input data pointed to by the - * scatter/gather list. - * - * Return: 0 if the message digest update was successful; < 0 if an error - * occurred - */ -static inline int crypto_hash_update(struct hash_desc *desc, - struct scatterlist *sg, - unsigned int nbytes) -{ - return crypto_hash_crt(desc->tfm)->update(desc, sg, nbytes); -} - -/** - * crypto_hash_final() - calculate message digest - * @desc: cipher request handle - * @out: message digest output buffer -- The caller must ensure that the out - * buffer has a sufficient size (e.g. by using the crypto_hash_digestsize - * function). - * - * Finalize the message digest operation and create the message digest - * based on all data added to the cipher handle. The message digest is placed - * into the output buffer. - * - * Return: 0 if the message digest creation was successful; < 0 if an error - * occurred - */ -static inline int crypto_hash_final(struct hash_desc *desc, u8 *out) -{ - return crypto_hash_crt(desc->tfm)->final(desc, out); -} - -/** - * crypto_hash_digest() - calculate message digest for a buffer - * @desc: see crypto_hash_final() - * @sg: see crypto_hash_update() - * @nbytes: see crypto_hash_update() - * @out: see crypto_hash_final() - * - * This function is a "short-hand" for the function calls of crypto_hash_init, - * crypto_hash_update and crypto_hash_final. The parameters have the same - * meaning as discussed for those separate three functions. - * - * Return: 0 if the message digest creation was successful; < 0 if an error - * occurred - */ -static inline int crypto_hash_digest(struct hash_desc *desc, - struct scatterlist *sg, - unsigned int nbytes, u8 *out) -{ - return crypto_hash_crt(desc->tfm)->digest(desc, sg, nbytes, out); -} - -/** - * crypto_hash_setkey() - set key for message digest - * @hash: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the message digest cipher. The cipher - * handle must point to a keyed hash in order for this function to succeed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_hash_setkey(struct crypto_hash *hash, - const u8 *key, unsigned int keylen) -{ - return crypto_hash_crt(hash)->setkey(hash, key, keylen); -} - static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { return (struct crypto_comp *)tfm; -- cgit v1.2.3 From 6e7333d315a768170a59ac771297ee0551bdddbf Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 1 Feb 2016 18:51:05 -0500 Subject: net: add rx_nohandler stat counter This adds an rx_nohandler stat counter, along with a sysfs statistics node, and copies the counter out via netlink as well. CC: "David S. Miller" CC: Eric Dumazet CC: Jiri Pirko CC: Daniel Borkmann CC: Tom Herbert CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 289c2314d766..78a20cec2a0a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1397,6 +1397,8 @@ enum netdev_priv_flags { * do not use this in drivers * @tx_dropped: Dropped packets by core network, * do not use this in drivers + * @rx_nohandler: nohandler dropped packets by core network on + * inactive devices, do not use this in drivers * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, @@ -1611,6 +1613,7 @@ struct net_device { atomic_long_t rx_dropped; atomic_long_t tx_dropped; + atomic_long_t rx_nohandler; #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def * wireless_handlers; -- cgit v1.2.3 From bb63daf9efb4f2bcb657d7179a53bd808f978dc9 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 1 Feb 2016 18:51:06 -0500 Subject: team: track sum of rx_nohandler for all slaves CC: Jiri Pirko CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/if_team.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index b84e49c3a738..174f43f43aff 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -24,6 +24,7 @@ struct team_pcpu_stats { struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; + u32 rx_nohandler; }; struct team; -- cgit v1.2.3 From ba905f5e2f63d86ed4cfbd3d9096fb28d156f1ee Mon Sep 17 00:00:00 2001 From: Kim Jones Date: Tue, 2 Feb 2016 03:51:16 +0000 Subject: ethtool: Declare netdev_rss_key as __read_mostly. netdev_rss_key is written to once and thereafter is read by drivers when they are initialising. The fact that it is mostly read and not written to makes it a candidate for a __read_mostly declaration. Signed-off-by: Kim Jones Signed-off-by: Alan Carey Acked-by: Rami Rosen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 78a20cec2a0a..219f53c30cb3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3744,7 +3744,7 @@ void netdev_lower_state_changed(struct net_device *lower_dev, /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 -extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN]; +extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev, -- cgit v1.2.3 From a10423b87a7eae75da79ce80a8d9475047a674ee Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:54 -0800 Subject: bpf: introduce BPF_MAP_TYPE_PERCPU_ARRAY map Primary use case is a histogram array of latency where bpf program computes the latency of block requests or other events and stores histogram of latency into array of 64 elements. All cpus are constantly running, so normal increment is not accurate, bpf_xadd causes cache ping-pong and this per-cpu approach allows fastest collision-free counters. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 83d1926c61e4..141fb0d45731 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -151,6 +151,7 @@ struct bpf_array { union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); + void __percpu *pptrs[0] __aligned(8); }; }; #define MAX_TAIL_CALL_CNT 32 -- cgit v1.2.3 From 15a07b33814d14ca817887dbea8530728dc0fbe4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:55 -0800 Subject: bpf: add lookup/update support for per-cpu hash and array maps The functions bpf_map_lookup_elem(map, key, value) and bpf_map_update_elem(map, key, value, flags) need to get/set values from all-cpus for per-cpu hash and array maps, so that user space can aggregate/update them as necessary. Example of single counter aggregation in user space: unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); long values[nr_cpus]; long value = 0; bpf_lookup_elem(fd, key, values); for (i = 0; i < nr_cpus; i++) value += values[i]; The user space must provide round_up(value_size, 8) * nr_cpus array to get/set values, since kernel will use 'long' copy of per-cpu values to try to copy good counters atomically. It's a best-effort, since bpf programs and user space are racing to access the same memory. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 141fb0d45731..90ee6ab24bc5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -183,6 +183,29 @@ int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname); +int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, + u64 flags); +int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, + u64 flags); + +/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and + * forced to use 'long' read/writes to try to atomically copy long counters. + * Best-effort only. No barriers here, since it _will_ race with concurrent + * updates from BPF programs. Called from bpf syscall and mostly used with + * size 8 or 16 bytes, so ask compiler to inline it. + */ +static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) +{ + const long *lsrc = src; + long *ldst = dst; + + size /= sizeof(long); + while (size--) + *ldst++ = *lsrc++; +} + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else -- cgit v1.2.3 From 7267bcda332e2782e21a559f3b1b859a35b4062d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sat, 16 Jan 2016 00:48:52 +0100 Subject: bcma: identify bus cores (devices) found on BCM47189 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing defines and print proper names. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 3feb1b2d75d8..991ebb4c2015 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -151,6 +151,8 @@ struct bcma_host_ops { #define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ #define BCMA_CORE_USB30_DEV 0x83D #define BCMA_CORE_ARM_CR4 0x83E +#define BCMA_CORE_GCI 0x840 +#define BCMA_CORE_CMEM 0x846 /* CNDS DDR2/3 memory controller */ #define BCMA_CORE_ARM_CA7 0x847 #define BCMA_CORE_SYS_MEM 0x849 #define BCMA_CORE_DEFAULT 0xFFF -- cgit v1.2.3 From 67edf354faaf93156646e741483b2313bc756c0f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 19 Jan 2016 08:45:25 +0100 Subject: bcma: use _PMU_ in all names of PMU registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PMU (Power Management Unit) seems to be a separated piece of hardware, just accessed using ChipCommon core registers. In recent Broadcom chipsets PMU is not bounded to CC but available as separated core. To make code cleaner & easier to review (for a correct R/W access) use clearer names. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index db51a6ffb7d6..96d8d56f240f 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -351,12 +351,12 @@ #define BCMA_CC_PMU_RES_REQTS 0x0640 /* PMU res req timer sel */ #define BCMA_CC_PMU_RES_REQT 0x0644 /* PMU res req timer */ #define BCMA_CC_PMU_RES_REQM 0x0648 /* PMU res req mask */ -#define BCMA_CC_CHIPCTL_ADDR 0x0650 -#define BCMA_CC_CHIPCTL_DATA 0x0654 -#define BCMA_CC_REGCTL_ADDR 0x0658 -#define BCMA_CC_REGCTL_DATA 0x065C -#define BCMA_CC_PLLCTL_ADDR 0x0660 -#define BCMA_CC_PLLCTL_DATA 0x0664 +#define BCMA_CC_PMU_CHIPCTL_ADDR 0x0650 +#define BCMA_CC_PMU_CHIPCTL_DATA 0x0654 +#define BCMA_CC_PMU_REGCTL_ADDR 0x0658 +#define BCMA_CC_PMU_REGCTL_DATA 0x065C +#define BCMA_CC_PMU_PLLCTL_ADDR 0x0660 +#define BCMA_CC_PMU_PLLCTL_DATA 0x0664 #define BCMA_CC_PMU_STRAPOPT 0x0668 /* (corerev >= 28) */ #define BCMA_CC_PMU_XTAL_FREQ 0x066C /* (pmurev >= 10) */ #define BCMA_CC_PMU_XTAL_FREQ_ILPCTL_MASK 0x00001FFF -- cgit v1.2.3 From b3c47afbf54d86daa0473895e8ca9e8b663f5c1a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 19 Jan 2016 08:45:26 +0100 Subject: bcma: support PMU present as separated bus core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On recent Broadcom chipsets PMU is present as separated core and it can't be accessed using ChipCommon anymore as it fails with e.g.: [ 0.000577] Unhandled fault: external abort on non-linefetch (0x1008) at 0xf1000604 Solve it by using a new (PMU) core pointer set to ChipCommon or PMU depending on the hardware capabilities. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 96d8d56f240f..700d0c6f7480 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -217,6 +217,11 @@ #define BCMA_CC_CLKDIV_JTAG_SHIFT 8 #define BCMA_CC_CLKDIV_UART 0x000000FF #define BCMA_CC_CAP_EXT 0x00AC /* Capabilities */ +#define BCMA_CC_CAP_EXT_SECI_PRESENT 0x00000001 +#define BCMA_CC_CAP_EXT_GSIO_PRESENT 0x00000002 +#define BCMA_CC_CAP_EXT_GCI_PRESENT 0x00000004 +#define BCMA_CC_CAP_EXT_SECI_PUART_PRESENT 0x00000008 /* UART present */ +#define BCMA_CC_CAP_EXT_AOB_PRESENT 0x00000040 #define BCMA_CC_PLLONDELAY 0x00B0 /* Rev >= 4 only */ #define BCMA_CC_FREFSELDELAY 0x00B4 /* Rev >= 4 only */ #define BCMA_CC_SLOWCLKCTL 0x00B8 /* 6 <= Rev <= 9 only */ @@ -566,6 +571,7 @@ * Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU) */ struct bcma_chipcommon_pmu { + struct bcma_device *core; /* Can be separated core or just ChipCommon one */ u8 rev; /* PMU revision */ u32 crystalfreq; /* The active crystal frequency (in kHz) */ }; @@ -660,6 +666,19 @@ struct bcma_drv_cc_b { #define bcma_cc_maskset32(cc, offset, mask, set) \ bcma_cc_write32(cc, offset, (bcma_cc_read32(cc, offset) & (mask)) | (set)) +/* PMU registers access */ +#define bcma_pmu_read32(cc, offset) \ + bcma_read32((cc)->pmu.core, offset) +#define bcma_pmu_write32(cc, offset, val) \ + bcma_write32((cc)->pmu.core, offset, val) + +#define bcma_pmu_mask32(cc, offset, mask) \ + bcma_pmu_write32(cc, offset, bcma_pmu_read32(cc, offset) & (mask)) +#define bcma_pmu_set32(cc, offset, set) \ + bcma_pmu_write32(cc, offset, bcma_pmu_read32(cc, offset) | (set)) +#define bcma_pmu_maskset32(cc, offset, mask, set) \ + bcma_pmu_write32(cc, offset, (bcma_pmu_read32(cc, offset) & (mask)) | (set)) + extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks); extern u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc); -- cgit v1.2.3 From 61dba73cdbba8ec5c01b31beaf9e2debc2d2f273 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 24 Jan 2016 16:37:33 +0100 Subject: bcma: add support for BCM47094 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's another SoC with 32 GPIOs and simplified watchdog handling. It was tested on D-Link DIR-885L. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 991ebb4c2015..0367c63f5960 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -201,6 +201,7 @@ struct bcma_host_ops { #define BCMA_PKG_ID_BCM4707 1 #define BCMA_PKG_ID_BCM4708 2 #define BCMA_PKG_ID_BCM4709 0 +#define BCMA_CHIP_ID_BCM47094 53030 #define BCMA_CHIP_ID_BCM53018 53018 /* Board types (on PCI usually equals to the subsystem dev id) */ -- cgit v1.2.3 From a4b5d606b957c6a58e991de63fe999492de1ab92 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 3 Feb 2016 23:35:23 +0100 Subject: usb: core: rename mutex usb_bus_list_lock to usb_bus_idr_lock Now that usb_bus_list has been removed and switched to idr rename the related mutex accordingly. Signed-off-by: Heiner Kallweit Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index c293dd044599..b98f831dcda3 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -632,7 +632,7 @@ extern void usb_set_device_state(struct usb_device *udev, /* exported only within usbcore */ extern struct idr usb_bus_idr; -extern struct mutex usb_bus_list_lock; +extern struct mutex usb_bus_idr_lock; extern wait_queue_head_t usb_kill_urb_queue; -- cgit v1.2.3 From 2eaa790989e03900298ad24f77f1086dbbc1aebd Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 16 Jan 2016 15:23:39 -0800 Subject: earlycon: Use common framework for earlycon declarations Use a single common table of struct earlycon_id for both command line and devicetree. Re-define OF_EARLYCON_DECLARE() macro to instance a unique earlycon declaration (the declaration is only guaranteed to be unique within a compilation unit; separate compilation units must still use unique earlycon names). The semantics of OF_EARLYCON_DECLARE() is different; it declares an earlycon which can matched either on the command line or by devicetree. EARLYCON_DECLARE() is semantically unchanged; it declares an earlycon which is matched by command line only. Remove redundant instances of EARLYCON_DECLARE(). This enables all earlycons to properly initialize struct console with the appropriate name and index, which improves diagnostics and enables direct earlycon-to-console handoff. Acked-by: Rob Herring Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index e03d6ba5e5b4..25e05147f379 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -342,22 +342,26 @@ struct earlycon_device { struct earlycon_id { char name[16]; + char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); } __aligned(32); +extern const struct earlycon_id __earlycon_table[]; +extern const struct earlycon_id __earlycon_table_end[]; + +#define OF_EARLYCON_DECLARE(_name, compat, fn) \ + static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ + __used __section(__earlycon_table) \ + = { .name = __stringify(_name), \ + .compatible = compat, \ + .setup = fn } + +#define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) + extern int setup_earlycon(char *buf); extern int of_setup_earlycon(unsigned long addr, int (*setup)(struct earlycon_device *, const char *)); -#define EARLYCON_DECLARE(_name, func) \ - static const struct earlycon_id __earlycon_##_name \ - __used __section(__earlycon_table) \ - = { .name = __stringify(_name), \ - .setup = func } - -#define OF_EARLYCON_DECLARE(name, compat, fn) \ - _OF_DECLARE(earlycon, name, compat, fn, void *) - struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, unsigned long *addr, -- cgit v1.2.3 From 05d961320ba624c98b16d72b32f947307674b341 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 16 Jan 2016 15:23:41 -0800 Subject: of: earlycon: Fixup earlycon console name and index Use the console name embedded in the OF earlycon table by the OF_EARLYCON_DECLARE() macro to initialize the struct console 'name' and 'index' fields. Acked-by: Rob Herring Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 25e05147f379..63fdb55e4c9d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -359,8 +359,7 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) extern int setup_earlycon(char *buf); -extern int of_setup_earlycon(unsigned long addr, - int (*setup)(struct earlycon_device *, const char *)); +extern int of_setup_earlycon(unsigned long addr, const struct earlycon_id *match); struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); -- cgit v1.2.3 From 4d118c9a866590850dad8689262a95345d2c6e09 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 16 Jan 2016 15:23:42 -0800 Subject: of: earlycon: Add options string handling Pass-through any options string in the 'stdout-path' property to the earlycon "driver" setup. Acked-by: Rob Herring Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 63fdb55e4c9d..62a4df05eaca 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -359,7 +359,8 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) extern int setup_earlycon(char *buf); -extern int of_setup_earlycon(unsigned long addr, const struct earlycon_id *match); +extern int of_setup_earlycon(unsigned long addr, const struct earlycon_id *match, + const char *options); struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); -- cgit v1.2.3 From 088da2a17619cf0113b62a76ad38c6a14470ffa6 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 16 Jan 2016 15:23:43 -0800 Subject: of: earlycon: Initialize port fields from DT properties Read the optional "reg-offset", "reg-shift", "reg-io-width" and endianness properties and initialize the respective struct uart_port field if found. NB: These bindings are common to several drivers and the values merely indicate the default value; the registering earlycon setup() method can simply override the values if required. Acked-by: Rob Herring Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 62a4df05eaca..6d1bed821181 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -360,6 +360,7 @@ extern const struct earlycon_id __earlycon_table_end[]; extern int setup_earlycon(char *buf); extern int of_setup_earlycon(unsigned long addr, const struct earlycon_id *match, + unsigned long node, const char *options); struct uart_port *uart_get_console(struct uart_port *ports, int nr, -- cgit v1.2.3 From c90fe9c0394b068ceca16f66e9f35bcd8d948295 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 16 Jan 2016 15:23:44 -0800 Subject: of: earlycon: Move address translation to of_setup_earlycon() Cleanup the early DT/earlycon separation; remove the 'addr' parameter from of_setup_earlycon() and get the uart phys addr directly with a new wrapper function, of_flat_dt_translate_addr(). Limit fdt_translate_address() to file scope. Acked-by: Rob Herring Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/of_fdt.h | 2 +- include/linux/serial_core.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index df9ef3801812..2fbe8682a66f 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -88,7 +88,7 @@ extern void unflatten_device_tree(void); extern void unflatten_and_copy_device_tree(void); extern void early_init_devtree(void *); extern void early_get_first_memblock_info(void *, phys_addr_t *); -extern u64 fdt_translate_address(const void *blob, int node_offset); +extern u64 of_flat_dt_translate_address(unsigned long node); extern void of_fdt_limit_memory(int limit); #else /* CONFIG_OF_FLATTREE */ static inline void early_init_fdt_scan_reserved_mem(void) {} diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 6d1bed821181..cbfcf38e220d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -359,7 +359,7 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) extern int setup_earlycon(char *buf); -extern int of_setup_earlycon(unsigned long addr, const struct earlycon_id *match, +extern int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, const char *options); -- cgit v1.2.3 From e490c9144cfaa8e2242c1e5d5187230928f27417 Mon Sep 17 00:00:00 2001 From: "Matwey V. Kornilov" Date: Mon, 1 Feb 2016 21:09:21 +0300 Subject: tty: Add software emulated RS485 support for 8250 Implementation of software emulation of RS485 direction handling is based on omap_serial driver. Before and after transmission RTS is set to the appropriate value. Note that before calling serial8250_em485_init() the caller has to ensure that UART will interrupt when shift register empty. Otherwise, emultaion cannot be used. Both serial8250_em485_init() and serial8250_em485_destroy() are idempotent functions. Signed-off-by: Matwey V. Kornilov Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index faa0e0370ce7..434879759725 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -76,6 +76,12 @@ struct uart_8250_ops { void (*release_irq)(struct uart_8250_port *); }; +struct uart_8250_em485 { + struct timer_list start_tx_timer; /* "rs485 start tx" timer */ + struct timer_list stop_tx_timer; /* "rs485 stop tx" timer */ + struct timer_list *active_timer; /* pointer to active timer */ +}; + /* * This should be used by drivers which want to register * their own 8250 ports without registering their own @@ -122,6 +128,8 @@ struct uart_8250_port { /* 8250 specific callbacks */ int (*dl_read)(struct uart_8250_port *); void (*dl_write)(struct uart_8250_port *, int); + + struct uart_8250_em485 *em485; }; static inline struct uart_8250_port *up_to_u8250p(struct uart_port *up) -- cgit v1.2.3 From 1349ba02bf72caafa36a2d6878cdba340d65b2ac Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 21 Jan 2016 09:46:12 +0100 Subject: ARM: OMAP: serial: Rename DRIVER_NAME DRIVER_NAME is too generic to be used in a driver-specific platform data file. Use a name specific to the driver instead, to avoid collisions. Signed-off-by: Jean Delvare Acked-by: Tony Lindgren Cc: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-omap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-omap.h b/include/linux/platform_data/serial-omap.h index d09275f3cde3..2ba2c34ca3d3 100644 --- a/include/linux/platform_data/serial-omap.h +++ b/include/linux/platform_data/serial-omap.h @@ -21,7 +21,7 @@ #include #include -#define DRIVER_NAME "omap_uart" +#define OMAP_SERIAL_DRIVER_NAME "omap_uart" /* * Use tty device name as ttyO, [O -> OMAP] -- cgit v1.2.3 From 47b0eeb3dc8a01848ad62908000b1051d1833eaf Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 2 Feb 2016 17:24:56 -0800 Subject: clk: Deprecate CLK_IS_ROOT We don't use CLK_IS_ROOT but in a few places in the common clk framework core. Let's replace those checks with a check for the number of parents a clk has instead of the flag, freeing up one flag for something else. We don't remove the flag yet so that things keep building, but we'll remove it once all drivers have removed their flag usage. Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index fabe5bedbba6..9c3a18c1a984 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -25,7 +25,7 @@ #define CLK_SET_PARENT_GATE BIT(1) /* must be gated across re-parent */ #define CLK_SET_RATE_PARENT BIT(2) /* propagate rate change up one level */ #define CLK_IGNORE_UNUSED BIT(3) /* do not gate even if unused */ -#define CLK_IS_ROOT BIT(4) /* root clk, has no parent */ +#define CLK_IS_ROOT BIT(4) /* Deprecated: Don't use */ #define CLK_IS_BASIC BIT(5) /* Basic clk, can't do a to_clk_foo() */ #define CLK_GET_RATE_NOCACHE BIT(6) /* do not use the cached clk rate */ #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */ -- cgit v1.2.3 From 1e42754eacdb1c8632c3af47263c56967e04cbd1 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Sat, 6 Feb 2016 23:34:55 -0800 Subject: clk: provider: Remove of_gpio_{gate,mux}_clk_setup() prototypes These functions either never existed or were only used in OF_CLK_DECLARE() macros. Remove the dead prototypes. Cc: Jyri Sarha Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9c3a18c1a984..fce7f027f8a7 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -626,8 +626,6 @@ struct clk *clk_register_gpio_gate(struct device *dev, const char *name, const char *parent_name, unsigned gpio, bool active_low, unsigned long flags); -void of_gpio_clk_gate_setup(struct device_node *node); - /** * struct clk_gpio_mux - gpio controlled clock multiplexer * @@ -643,8 +641,6 @@ struct clk *clk_register_gpio_mux(struct device *dev, const char *name, const char * const *parent_names, u8 num_parents, unsigned gpio, bool active_low, unsigned long flags); -void of_gpio_mux_clk_setup(struct device_node *node); - /** * clk_register - allocate a new clock, register it and return an opaque cookie * @dev: device that is registering this clock -- cgit v1.2.3 From ddf1af6fa00e772fdb67a7d22cb83fac2b8968a8 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 2 Feb 2016 10:33:06 -0800 Subject: tcp: new delivery accounting This patch changes the accounting of how many packets are newly acked or sacked when the sender receives an ACK. The current approach basically computes newly_acked_sacked = (prior_packets - prior_sacked) - (tp->packets_out - tp->sacked_out) where prior_packets and prior_sacked out are snapshot at the beginning of the ACK processing. The new approach tracks the delivery information via a new TCP state variable "delivered" which monotically increases as new packets are delivered in order or out-of-order. The reason for this change is that the current approach is brittle that produces negative or inaccurate estimate. 1) For non-SACK connections, an ACK that advances the SND.UNA could reset the DUPACK counters (tp->sacked_out) in tcp_process_loss() or tcp_fastretrans_alert(). This inflates the inflight suddenly and causes under-estimate or even negative estimate. Here is a real example: before after (processing ACK) packets_out 75 73 sacked_out 23 0 ca state Loss Open The old approach computes (75-23) - (73 - 0) = -21 delivered while the new approach computes 1 delivered since it considers the 2nd-24th packets are delivered OOO. 2) MSS change would re-count packets_out and sacked_out so the estimate is in-accurate and can even become negative. E.g., the inflight is doubled when MSS is halved. 3) Spurious retransmission signaled by DSACK is not accounted The new approach is simpler and more robust. For SACK connections, tp->delivered increments as packets are being acked or sacked in SACK and ACK processing. For non-sack connections, it's done in tcp_remove_reno_sacks() and tcp_add_reno_sack(). When an ACK advances the SND.UNA, tp->delivered is incremented by the number of packets ACKed (less the current number of DUPACKs received plus one packet hole). Upon receiving a DUPACK, tp->delivered is incremented assuming one out-of-order packet is delivered. Upon receiving a DSACK, tp->delivered is incremtened assuming one retransmission is delivered in tcp_sacktag_write_queue(). Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b386361ba3e8..d909feeeaea2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -256,6 +256,7 @@ struct tcp_sock { u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ + u32 delivered; /* Total data packets delivered incl. rexmits */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ -- cgit v1.2.3 From 8b37524962b9c54423374717786198f5c0820a28 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 8 Feb 2016 11:21:50 +1100 Subject: quota: add new quotactl Q_XGETNEXTQUOTA Q_XGETNEXTQUOTA is exactly like Q_XGETQUOTA, except that it will return quota information for the id equal to or greater than the id requested. In other words, if the requested id has no quota, the command will return quota information for the next higher id which does have a quota set. If no higher id has an active quota, -ESRCH is returned. This allows filesystems to do efficient iteration in kernelspace, much like extN filesystems do in userspace when asked to report all active quotas. The patch adds a d_id field to struct qc_dqblk so that we can pass back the id of the quota which was found, and return it to userspace. Today, filesystems such as XFS require getpwent-style iterations, and for systems which have i.e. LDAP backends, this can be very slow, or even impossible if iteration is not allowed in the configuration. Signed-off-by: Eric Sandeen Reviewed-by: Jan Kara Signed-off-by: Dave Chinner --- include/linux/quota.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index b2505acfd3c0..fba92f5c1a63 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -425,6 +425,8 @@ struct quotactl_ops { int (*quota_sync)(struct super_block *, int); int (*set_info)(struct super_block *, int, struct qc_info *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); + int (*get_nextdqblk)(struct super_block *, struct kqid *, + struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_state)(struct super_block *, struct qc_state *); int (*rm_xquota)(struct super_block *, unsigned int); -- cgit v1.2.3 From b55b54b5db330e36cd465adb3fbe274ffb1061d3 Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Thu, 21 Jan 2016 10:49:21 -0200 Subject: staging/android: remove struct sync_pt struct sync_pt was just wrapping around struct fence and creating an extra abstraction layer. The only two members of struct sync_pt, child_list and active_list, were moved to struct fence in an earlier commit. After removing those two members struct sync_pt is nothing more than struct fence, so remove it all and use struct fence directly. Signed-off-by: Gustavo Padovan Reviewed-by: Maarten Lankhorst Signed-off-by: Greg Kroah-Hartman --- include/linux/fence.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index bb522011383b..605bd88246a6 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -79,6 +79,8 @@ struct fence { unsigned long flags; ktime_t timestamp; int status; + struct list_head child_list; + struct list_head active_list; }; enum fence_flag_bits { -- cgit v1.2.3 From 9b1b282ccd8195e3264dbb3cd15b9d60b6345230 Mon Sep 17 00:00:00 2001 From: "J. German Rivera" Date: Wed, 6 Jan 2016 16:03:19 -0600 Subject: irqdomain: Added domain bus token DOMAIN_BUS_FSL_MC_MSI Since an FSL-MC bus is a new bus type that is neither PCI nor PLATFORM, we need a new domain bus token to disambiguate the IRQ domain for FSL-MC MSIs. Signed-off-by: J. German Rivera Signed-off-by: Greg Kroah-Hartman --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 04579d9fbce4..0934d06c8b00 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -74,6 +74,7 @@ enum irq_domain_bus_token { DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, + DOMAIN_BUS_FSL_MC_MSI, }; /** -- cgit v1.2.3 From 550308e48cddbc2aa74f7236941b17b55b2e78e9 Mon Sep 17 00:00:00 2001 From: "J. German Rivera" Date: Wed, 6 Jan 2016 16:03:20 -0600 Subject: fsl-mc: msi: Added FSL-MC-specific member to the msi_desc's union FSL-MC is a bus type different from PCI and platform, so it needs its own member in the msi_desc's union. Signed-off-by: J. German Rivera Signed-off-by: Greg Kroah-Hartman --- include/linux/msi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index a2a0068a8387..8b425c66305a 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -32,6 +32,14 @@ struct platform_msi_desc { u16 msi_index; }; +/** + * fsl_mc_msi_desc - FSL-MC device specific msi descriptor data + * @msi_index: The index of the MSI descriptor + */ +struct fsl_mc_msi_desc { + u16 msi_index; +}; + /** * struct msi_desc - Descriptor structure for MSI based interrupts * @list: List head for management @@ -87,6 +95,7 @@ struct msi_desc { * tree wide cleanup. */ struct platform_msi_desc platform; + struct fsl_mc_msi_desc fsl_mc; }; }; -- cgit v1.2.3 From 187372a3b9faff68ed61c291d0135e6739e0dbdf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Feb 2016 14:40:51 +1100 Subject: direct-io: always call ->end_io if non-NULL This way we can pass back errors to the file system, and allow for cleanup required for all direct I/O invocations. Also allow the ->end_io handlers to return errors on their own, so that I/O completion errors can be passed on to the callers. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a2046275cdf..d7f37bfcbdce 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -70,7 +70,7 @@ extern int sysctl_protected_hardlinks; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, +typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate); -- cgit v1.2.3 From 7047f17d70fc0599563d30d0791692cb5fe42ae6 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 25 Dec 2015 20:00:30 -0800 Subject: Drivers: hv: vmbus: Add vendor and device atttributes Add vendor and device attributes to VMBUS devices. These will be used by Hyper-V tools as well user-level RDMA libraries that will use the vendor/device tuple to discover the RDMA device. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 753dbad0bf94..3172521df805 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -633,6 +633,32 @@ enum hv_signal_policy { HV_SIGNAL_POLICY_EXPLICIT, }; +enum vmbus_device_type { + HV_IDE = 0, + HV_SCSI, + HV_FC, + HV_NIC, + HV_ND, + HV_PCIE, + HV_FB, + HV_KBD, + HV_MOUSE, + HV_KVP, + HV_TS, + HV_HB, + HV_SHUTDOWN, + HV_FCOPY, + HV_BACKUP, + HV_DM, + HV_UNKOWN, +}; + +struct vmbus_device { + u16 dev_type; + uuid_le guid; + bool perf_device; +}; + struct vmbus_channel { /* Unique channel id */ int id; @@ -959,6 +985,8 @@ struct hv_device { /* the device instance id of this device */ uuid_le dev_instance; + u16 vendor_id; + u16 device_id; struct device device; -- cgit v1.2.3 From 3c75354d043ad546148d6992e40033ecaefc5ea5 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 27 Jan 2016 22:29:37 -0800 Subject: Drivers: hv: vmbus: add a helper function to set a channel's pending send size This will be used by the coming net/hvsock driver. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 3172521df805..4af51a3f98d9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -816,6 +816,12 @@ static inline void *get_per_channel_state(struct vmbus_channel *c) return c->per_channel_state; } +static inline void set_channel_pending_send_size(struct vmbus_channel *c, + u32 size) +{ + c->outbound.ring_buffer->pending_send_sz = size; +} + void vmbus_onmessage(void *context); int vmbus_request_offers(void); -- cgit v1.2.3 From e8d6ca023efce3bd80050dcd9e708ee3cf8babd4 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 27 Jan 2016 22:29:38 -0800 Subject: Drivers: hv: vmbus: define the new offer type for Hyper-V socket (hvsock) A helper function is also added. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 4af51a3f98d9..79c4aa70eff3 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -235,6 +235,7 @@ struct vmbus_channel_offer { #define VMBUS_CHANNEL_LOOPBACK_OFFER 0x100 #define VMBUS_CHANNEL_PARENT_OFFER 0x200 #define VMBUS_CHANNEL_REQUEST_MONITORED_NOTIFICATION 0x400 +#define VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER 0x2000 struct vmpacket_descriptor { u16 type; @@ -795,6 +796,12 @@ struct vmbus_channel { enum hv_signal_policy signal_policy; }; +static inline bool is_hvsock_channel(const struct vmbus_channel *c) +{ + return !!(c->offermsg.offer.chn_flags & + VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); +} + static inline void set_channel_signal_state(struct vmbus_channel *c, enum hv_signal_policy policy) { -- cgit v1.2.3 From 5c23a1a5c60b0f472cfa61cd7d8279f8aaeb5b64 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 27 Jan 2016 22:29:40 -0800 Subject: Drivers: hv: vmbus: define a new VMBus message type for hvsock A function to send the type of message is also added. The coming net/hvsock driver will use this function to proactively request the host to offer a VMBus channel for a new hvsock connection. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 79c4aa70eff3..898eac9e8c13 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -392,6 +392,10 @@ enum vmbus_channel_message_type { CHANNELMSG_VERSION_RESPONSE = 15, CHANNELMSG_UNLOAD = 16, CHANNELMSG_UNLOAD_RESPONSE = 17, + CHANNELMSG_18 = 18, + CHANNELMSG_19 = 19, + CHANNELMSG_20 = 20, + CHANNELMSG_TL_CONNECT_REQUEST = 21, CHANNELMSG_COUNT }; @@ -562,6 +566,13 @@ struct vmbus_channel_initiate_contact { u64 monitor_page2; } __packed; +/* Hyper-V socket: guest's connect()-ing to host */ +struct vmbus_channel_tl_connect_request { + struct vmbus_channel_message_header header; + uuid_le guest_endpoint_id; + uuid_le host_service_id; +} __packed; + struct vmbus_channel_version_response { struct vmbus_channel_message_header header; u8 version_supported; @@ -1283,4 +1294,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); extern __u32 vmbus_proto_version; +int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id, + const uuid_le *shv_host_servie_id); #endif /* _HYPERV_H */ -- cgit v1.2.3 From 8981da320a11217589aa3c50f9e891bcdef07ece Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 27 Jan 2016 22:29:41 -0800 Subject: Drivers: hv: vmbus: add a hvsock flag in struct hv_driver Only the coming hv_sock driver has a "true" value for this flag. We treat the hvsock offers/channels as special VMBus devices. Since the hv_sock driver handles all the hvsock offers/channels, we need to tweak vmbus_match() for hv_sock driver, so we introduce this flag. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 898eac9e8c13..f636f91f104b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -990,6 +990,20 @@ extern void vmbus_ontimer(unsigned long data); struct hv_driver { const char *name; + /* + * A hvsock offer, which has a VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER + * channel flag, actually doesn't mean a synthetic device because the + * offer's if_type/if_instance can change for every new hvsock + * connection. + * + * However, to facilitate the notification of new-offer/rescind-offer + * from vmbus driver to hvsock driver, we can handle hvsock offer as + * a special vmbus device, and hence we need the below flag to + * indicate if the driver is the hvsock driver or not: we need to + * specially treat the hvosck offer & driver in vmbus_match(). + */ + bool hvsock; + /* the device type supported by this driver */ uuid_le dev_type; const struct hv_vmbus_device_id *id_table; -- cgit v1.2.3 From 499e8401a515d04daa986b995da710d2b9737764 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 27 Jan 2016 22:29:42 -0800 Subject: Drivers: hv: vmbus: add a per-channel rescind callback This will be used by the coming hv_sock driver. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f636f91f104b..2e54e34e5feb 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -765,6 +765,12 @@ struct vmbus_channel { */ void (*sc_creation_callback)(struct vmbus_channel *new_sc); + /* + * Channel rescind callback. Some channels (the hvsock ones), need to + * register a callback which is invoked in vmbus_onoffer_rescind(). + */ + void (*chn_rescind_callback)(struct vmbus_channel *channel); + /* * The spinlock to protect the structure. It is being used to protect * test-and-set access to various attributes of the structure as well @@ -851,6 +857,9 @@ int vmbus_request_offers(void); void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, void (*sc_cr_cb)(struct vmbus_channel *new_sc)); +void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel, + void (*chn_rescind_cb)(struct vmbus_channel *)); + /* * Retrieve the (sub) channel on which to send an outgoing request. * When a primary channel has multiple sub-channels, we choose a -- cgit v1.2.3 From 85d9aa705184a4504d0330017e3956fcdae8a9d6 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 27 Jan 2016 22:29:43 -0800 Subject: Drivers: hv: vmbus: add an API vmbus_hvsock_device_unregister() The hvsock driver needs this API to release all the resources related to the channel. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2e54e34e5feb..c056f058dcf8 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1069,6 +1069,8 @@ int __must_check __vmbus_driver_register(struct hv_driver *hv_driver, const char *mod_name); void vmbus_driver_unregister(struct hv_driver *hv_driver); +void vmbus_hvsock_device_unregister(struct vmbus_channel *channel); + int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, resource_size_t min, resource_size_t max, resource_size_t size, resource_size_t align, -- cgit v1.2.3 From fe760e4d64fe5c17c39e86c410d41f6587ee88bc Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Wed, 27 Jan 2016 22:29:45 -0800 Subject: Drivers: hv: vmbus: Give control over how the ring access is serialized On the channel send side, many of the VMBUS device drivers explicity serialize access to the outgoing ring buffer. Give more control to the VMBUS device drivers in terms how to serialize accesss to the outgoing ring buffer. The default behavior will be to aquire the ring lock to preserve the current behavior. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c056f058dcf8..d23dab0d770b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -811,8 +811,24 @@ struct vmbus_channel { * signaling control. */ enum hv_signal_policy signal_policy; + /* + * On the channel send side, many of the VMBUS + * device drivers explicity serialize access to the + * outgoing ring buffer. Give more control to the + * VMBUS device drivers in terms how to serialize + * accesss to the outgoing ring buffer. + * The default behavior will be to aquire the + * ring lock to preserve the current behavior. + */ + bool acquire_ring_lock; + }; +static inline void set_channel_lock_state(struct vmbus_channel *c, bool state) +{ + c->acquire_ring_lock = state; +} + static inline bool is_hvsock_channel(const struct vmbus_channel *c) { return !!(c->offermsg.offer.chn_flags & -- cgit v1.2.3 From f42a0fd13bd281811e7457b28d939c8e8b808868 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Thu, 12 Nov 2015 01:29:32 -0800 Subject: VMCI: Use 32bit atomics for queue headers on X86_32 This change restricts the reading and setting of the head and tail pointers on 32bit X86 to 32bit for both correctness and performance reasons. On uniprocessor X86_32, the atomic64_read may be implemented as a non-locked cmpxchg8b. This may result in updates to the pointers done by the VMCI device being overwritten. On MP systems, there is no such correctness issue, but using 32bit atomics avoids the overhead of the locked 64bit operation. All this is safe because the queue size on 32bit systems will never exceed a 32bit value. Reviewed-by: Thomas Hellstrom Signed-off-by: Jorgen Hansen Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 43 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 39 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 65ac54c61c18..1bd31a38c51e 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -733,6 +733,41 @@ static inline void *vmci_event_data_payload(struct vmci_event_data *ev_data) return (void *)vmci_event_data_const_payload(ev_data); } +/* + * Helper to read a value from a head or tail pointer. For X86_32, the + * pointer is treated as a 32bit value, since the pointer value + * never exceeds a 32bit value in this case. Also, doing an + * atomic64_read on X86_32 uniprocessor systems may be implemented + * as a non locked cmpxchg8b, that may end up overwriting updates done + * by the VMCI device to the memory location. On 32bit SMP, the lock + * prefix will be used, so correctness isn't an issue, but using a + * 64bit operation still adds unnecessary overhead. + */ +static inline u64 vmci_q_read_pointer(atomic64_t *var) +{ +#if defined(CONFIG_X86_32) + return atomic_read((atomic_t *)var); +#else + return atomic64_read(var); +#endif +} + +/* + * Helper to set the value of a head or tail pointer. For X86_32, the + * pointer is treated as a 32bit value, since the pointer value + * never exceeds a 32bit value in this case. On 32bit SMP, using a + * locked cmpxchg8b adds unnecessary overhead. + */ +static inline void vmci_q_set_pointer(atomic64_t *var, + u64 new_val) +{ +#if defined(CONFIG_X86_32) + return atomic_set((atomic_t *)var, (u32)new_val); +#else + return atomic64_set(var, new_val); +#endif +} + /* * Helper to add a given offset to a head or tail pointer. Wraps the * value of the pointer around the max size of the queue. @@ -741,14 +776,14 @@ static inline void vmci_qp_add_pointer(atomic64_t *var, size_t add, u64 size) { - u64 new_val = atomic64_read(var); + u64 new_val = vmci_q_read_pointer(var); if (new_val >= size - add) new_val -= size; new_val += add; - atomic64_set(var, new_val); + vmci_q_set_pointer(var, new_val); } /* @@ -758,7 +793,7 @@ static inline u64 vmci_q_header_producer_tail(const struct vmci_queue_header *q_header) { struct vmci_queue_header *qh = (struct vmci_queue_header *)q_header; - return atomic64_read(&qh->producer_tail); + return vmci_q_read_pointer(&qh->producer_tail); } /* @@ -768,7 +803,7 @@ static inline u64 vmci_q_header_consumer_head(const struct vmci_queue_header *q_header) { struct vmci_queue_header *qh = (struct vmci_queue_header *)q_header; - return atomic64_read(&qh->consumer_head); + return vmci_q_read_pointer(&qh->consumer_head); } /* -- cgit v1.2.3 From 52210c8745e418f82f3f0aeeee01d7bc4858812a Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 2 Feb 2016 14:14:01 -0700 Subject: coresight: implementing 'cpu_id()' API Other than plainly parsing the device tree there is no way to know which CPU a tracer is affined to. As such adding an interface to lookup the CPU field enclosed in the etm_drvdata structure that was initialised at boot time. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index a7cabfa23b55..bf62b265bf52 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -205,12 +205,15 @@ struct coresight_ops_link { /** * struct coresight_ops_source - basic operations for a source * Operations available for sources. + * @cpu_id: returns the value of the CPU number this component + * is associated to. * @trace_id: returns the value of the component's trace ID as known to the HW. * @enable: enables tracing for a source. * @disable: disables tracing for a source. */ struct coresight_ops_source { + int (*cpu_id)(struct coresight_device *csdev); int (*trace_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev); void (*disable)(struct coresight_device *csdev); -- cgit v1.2.3 From 94e1dec7a9c111419fee328cf6f082059d8bd0f8 Mon Sep 17 00:00:00 2001 From: Jiaxing Wang Date: Sun, 22 Nov 2015 16:05:10 +0800 Subject: debugfs: Add stub function for debugfs_create_automount(). Add stub for debugfs_create_automount() for when debugfs is not configured in. Signed-off-by: Jiaxing Wang Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 19c066dce1da..981e53ab84e8 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -162,6 +162,14 @@ static inline struct dentry *debugfs_create_symlink(const char *name, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_automount(const char *name, + struct dentry *parent, + struct vfsmount *(*f)(void *), + void *data) +{ + return ERR_PTR(-ENODEV); +} + static inline void debugfs_remove(struct dentry *dentry) { } -- cgit v1.2.3 From 2c92c04b6f1f06c3e9752abb02e62b6ee188109d Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Mon, 28 Dec 2015 14:39:20 +0100 Subject: memory: omap-gpmc: Add support for AAD timings In order to support extended timings parameters on hardware supporting the "AAD" mode like the AM335x or DM816x, add these entries into the GPMC driver if the hardware is capable. Tested on DM816x and AM335x. Signed-off-by: Neil Armstrong Acked-by: Tony Lindgren Signed-off-by: Roger Quadros --- include/linux/omap-gpmc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index 7dee00143afd..d833eb4dd446 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -51,6 +51,9 @@ struct gpmc_timings { u32 adv_on; /* Assertion time */ u32 adv_rd_off; /* Read deassertion time */ u32 adv_wr_off; /* Write deassertion time */ + u32 adv_aad_mux_on; /* ADV assertion time for AAD */ + u32 adv_aad_mux_rd_off; /* ADV read deassertion time for AAD */ + u32 adv_aad_mux_wr_off; /* ADV write deassertion time for AAD */ /* WE signals timings corresponding to GPMC_CONFIG4 */ u32 we_on; /* WE assertion time */ @@ -59,6 +62,8 @@ struct gpmc_timings { /* OE signals timings corresponding to GPMC_CONFIG4 */ u32 oe_on; /* OE assertion time */ u32 oe_off; /* OE deassertion time */ + u32 oe_aad_mux_on; /* OE assertion time for AAD */ + u32 oe_aad_mux_off; /* OE deassertion time for AAD */ /* Access time and cycle time timings corresponding to GPMC_CONFIG5 */ u32 page_burst_access; /* Multiple access word delay */ -- cgit v1.2.3 From ee7683a31683c6368a66a83c555600dfd704e543 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 5 Feb 2016 17:31:39 -0800 Subject: spi: Document max_transfer_size Fix kernel-doc warning for missing struct field notation. ..//include/linux/spi/spi.h:540: warning: No description found for parameter 'max_transfer_size' [Meaningful subject -- broonie] Signed-off-by: Randy Dunlap Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 53be3a4c60cb..e9290c335cc4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -303,6 +303,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @min_speed_hz: Lowest supported transfer speed * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver + * @max_transfer_size: function that returns the max transfer size for + * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for SPI bus locking * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use -- cgit v1.2.3 From b41c29b0527c7fd6a95d0f71274abb79933bf960 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Feb 2016 15:38:32 +0100 Subject: Kbuild: provide a __UNIQUE_ID for clang The default __UNIQUE_ID macro in compiler.h fails to work for some drivers: drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c:615:1: error: redefinition of '__UNIQUE_ID_firmware615' BRCMF_FW_NVRAM_DEF(4354, "brcmfmac4354-sdio.bin", "brcmfmac4354-sdio.txt"); This adds a copy of the version we use for gcc-4.3 and higher, as the same one works with all versions of clang that I could find in svn (2.6 and higher). Signed-off-by: Arnd Bergmann Signed-off-by: Michal Marek --- include/linux/compiler-clang.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d1e49d52b640..de179993e039 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -10,3 +10,8 @@ #undef uninitialized_var #define uninitialized_var(x) x = *(&(x)) #endif + +/* same as gcc, this was present in clang-2.6 so we can assume it works + * with any version that can compile the kernel + */ +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -- cgit v1.2.3 From 0118de7b4c04cba1b275d889ad14a39950f30021 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Mon, 8 Feb 2016 17:03:15 +0200 Subject: iio: Fix documentation for iio_dev mlock mlock *must* be used by core and drivers to protect access to devices state changes. Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index b5894118755f..ce9e9c1adf34 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -448,7 +448,7 @@ struct iio_buffer_setup_ops { * @buffer: [DRIVER] any buffer present * @buffer_list: [INTERN] list of all buffers currently attached * @scan_bytes: [INTERN] num bytes captured to be fed to buffer demux - * @mlock: [INTERN] lock used to prevent simultaneous device state + * @mlock: [DRIVER] lock used to prevent simultaneous device state * changes * @available_scan_masks: [DRIVER] optional array of allowed bitmasks * @masklength: [INTERN] the length of the mask established from -- cgit v1.2.3 From a3499e9bf0feeea593a9daae855986c685561893 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Wed, 23 Dec 2015 17:57:19 +0530 Subject: devm: add helper devm_add_action_or_reset() Add a helper function devm_add_action_or_reset() which will internally call devm_add_action(). But if devm_add_action() fails then it will execute the action mentioned and return the error code. Signed-off-by: Sudip Mukherjee Acked-by: Greg Kroah-Hartman Signed-off-by: Stephen Boyd --- include/linux/device.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 6d6f1fec092f..74674e098315 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -682,6 +682,18 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res); int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); +static inline int devm_add_action_or_reset(struct device *dev, + void (*action)(void *), void *data) +{ + int ret; + + ret = devm_add_action(dev, action, data); + if (ret) + action(data); + + return ret; +} + struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about -- cgit v1.2.3 From 6d5bbed30f89acd2ae0d23b3fff5b13b307525d9 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Fri, 22 Jan 2016 19:06:50 +0800 Subject: dmaengine: core: expose max burst capability to clients This patch add max_burst to dma_get_slave_caps for clients to get the burst capability of slave dma controller. Signed-off-by: Shawn Lin Signed-off-by: Caesar Wang Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 16a1cad30c33..0a9a0ba1998b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -401,6 +401,7 @@ enum dma_residue_granularity { * since the enum dma_transfer_direction is not defined as bits for each * type of direction, the dma controller should fill (1 << ) and same * should be checked by controller as well + * @max_burst: max burst capability per-transfer * @cmd_pause: true, if pause and thereby resume is supported * @cmd_terminate: true, if terminate cmd is supported * @residue_granularity: granularity of the reported transfer residue @@ -411,6 +412,7 @@ struct dma_slave_caps { u32 src_addr_widths; u32 dst_addr_widths; u32 directions; + u32 max_burst; bool cmd_pause; bool cmd_terminate; enum dma_residue_granularity residue_granularity; @@ -654,6 +656,7 @@ struct dma_filter { * the enum dma_transfer_direction is not defined as bits for * each type of direction, the dma controller should fill (1 << * ) and same should be checked by controller as well + * @max_burst: max burst capability per-transfer * @residue_granularity: granularity of the transfer residue reported * by tx_status * @device_alloc_chan_resources: allocate resources and return the @@ -712,6 +715,7 @@ struct dma_device { u32 src_addr_widths; u32 dst_addr_widths; u32 directions; + u32 max_burst; bool descriptor_reuse; enum dma_residue_granularity residue_granularity; -- cgit v1.2.3 From 831e9da7dc5c22fd2a5fb64e999f6e077a4338c3 Mon Sep 17 00:00:00 2001 From: Tiago Vignatti Date: Tue, 22 Dec 2015 19:36:45 -0200 Subject: dma-buf: Remove range-based flush MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch removes range-based information used for optimizations in begin_cpu_access and end_cpu_access. We don't have any user nor implementation using range-based flush. It seems a consensus that if we ever want something like that again (or even more robust using 2D, 3D sub-range regions) we can use the upcoming dma-buf sync ioctl for such. Cc: Sumit Semwal Cc: Daniel Vetter Signed-off-by: Tiago Vignatti Reviewed-by: Stéphane Marchesin Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1450820214-12509-3-git-send-email-tiago.vignatti@intel.com --- include/linux/dma-buf.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index f98bd7068d55..532108ea0c1c 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -54,7 +54,7 @@ struct dma_buf_attachment; * @release: release this buffer; to be called after the last dma_buf_put. * @begin_cpu_access: [optional] called before cpu access to invalidate cpu * caches and allocate backing storage (if not yet done) - * respectively pin the objet into memory. + * respectively pin the object into memory. * @end_cpu_access: [optional] called after cpu access to flush caches. * @kmap_atomic: maps a page from the buffer into kernel address * space, users may not block until the subsequent unmap call. @@ -93,10 +93,8 @@ struct dma_buf_ops { /* after final dma_buf_put() */ void (*release)(struct dma_buf *); - int (*begin_cpu_access)(struct dma_buf *, size_t, size_t, - enum dma_data_direction); - void (*end_cpu_access)(struct dma_buf *, size_t, size_t, - enum dma_data_direction); + int (*begin_cpu_access)(struct dma_buf *, enum dma_data_direction); + void (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); void *(*kmap_atomic)(struct dma_buf *, unsigned long); void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*kmap)(struct dma_buf *, unsigned long); @@ -224,9 +222,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *, enum dma_data_direction); void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *, enum dma_data_direction); -int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t len, +int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void dma_buf_end_cpu_access(struct dma_buf *dma_buf, size_t start, size_t len, +void dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); -- cgit v1.2.3 From ff2b1359229927563addbf2f5ad480660c350903 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 20 Oct 2015 11:10:38 +0200 Subject: gpio: make the gpiochip a real device GPIO chips have been around for years, but were never real devices, instead they were piggy-backing on a parent device (such as a platform_device or amba_device) but this was always optional. GPIO chips could also exist without any device at all, with its struct device *parent (ex *dev) pointer being set to null. When sysfs was in use, a mock device would be created, with the optional parent assigned, or just floating orphaned with NULL as parent. If sysfs is active, it will use this device as parent. We now create a gpio_device struct containing a real struct device and move the subsystem over to using that. The list of struct gpio_chip:s is augmented to hold struct gpio_device:s and we find gpio_chips:s by first looking up the struct gpio_device. The struct gpio_device is designed to stay around even if the gpio_chip is removed, so as to satisfy users in userspace that need a backing data structure to hold the state of the session initiated with e.g. a character device even if there is no physical chip anymore. From this point on, gpiochips are devices. Cc: Johan Hovold Cc: Michael Welling Cc: Markus Pargmann Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 82fda487453f..f3f1dbd43c9b 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -1,6 +1,7 @@ #ifndef __LINUX_GPIO_DRIVER_H #define __LINUX_GPIO_DRIVER_H +#include #include #include #include @@ -10,22 +11,22 @@ #include #include -struct device; struct gpio_desc; struct of_phandle_args; struct device_node; struct seq_file; +struct gpio_device; #ifdef CONFIG_GPIOLIB /** * struct gpio_chip - abstract a GPIO controller * @label: for diagnostics + * @gpiodev: the internal state holder, opaque struct * @parent: optional parent device providing the GPIOs * @cdev: class device used by sysfs interface (may be NULL) * @owner: helps prevent removal of modules exporting active GPIOs * @data: per-instance data assigned by the driver - * @list: links gpio_chips together for traversal * @request: optional hook for chip-specific activation, such as * enabling module power and clock; may sleep * @free: optional hook for chip-specific deactivation, such as @@ -107,11 +108,11 @@ struct seq_file; */ struct gpio_chip { const char *label; + struct gpio_device *gpiodev; struct device *parent; struct device *cdev; struct module *owner; void *data; - struct list_head list; int (*request)(struct gpio_chip *chip, unsigned offset); -- cgit v1.2.3 From 156d7d4120e1c860fde667fc30eeae84bc3e7a25 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 11 Jan 2016 20:09:20 +0100 Subject: vga_switcheroo: Add handler flags infrastructure Allow handlers to declare their capabilities and allow clients to obtain that information. So far we have these use cases: * If the handler is able to switch DDC separately, clients need to probe EDID with drm_get_edid_switcheroo(). We should allow them to detect a capable handler to ensure this function only gets called when needed. * Likewise if the handler is unable to switch AUX separately, the active client needs to communicate link training parameters to the inactive client, which may then skip the AUX handshake and set up its output with these pre-calibrated values (DisplayPort specification v1.1a, section 2.5.3.3). Clients need a way to recognize such a situation. The flags for the radeon_atpx_handler and amdgpu_atpx_handler are initially set to 0, this can later on be amended with handler_flags |= VGA_SWITCHEROO_CAN_SWITCH_DDC; when a ->switch_ddc callback is added. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=88861 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=61115 Tested-by: Lukas Wunner [MBP 9,1 2012 intel IVB + nvidia GK107 pre-retina 15"] Signed-off-by: Lukas Wunner Reviewed-by: Darren Hart Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/2b0d93ed6e511ca09e95e45e0b35627f330fabce.1452525860.git.lukas@wunner.de --- include/linux/vga_switcheroo.h | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 69e1d4a1f1b3..a745f4f0f729 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -35,6 +35,26 @@ struct pci_dev; +/** + * enum vga_switcheroo_handler_flags_t - handler flags bitmask + * @VGA_SWITCHEROO_CAN_SWITCH_DDC: whether the handler is able to switch the + * DDC lines separately. This signals to clients that they should call + * drm_get_edid_switcheroo() to probe the EDID + * @VGA_SWITCHEROO_NEEDS_EDP_CONFIG: whether the handler is unable to switch + * the AUX channel separately. This signals to clients that the active + * GPU needs to train the link and communicate the link parameters to the + * inactive GPU (mediated by vga_switcheroo). The inactive GPU may then + * skip the AUX handshake and set up its output with these pre-calibrated + * values (DisplayPort specification v1.1a, section 2.5.3.3) + * + * Handler flags bitmask. Used by handlers to declare their capabilities upon + * registering with vga_switcheroo. + */ +enum vga_switcheroo_handler_flags_t { + VGA_SWITCHEROO_CAN_SWITCH_DDC = (1 << 0), + VGA_SWITCHEROO_NEEDS_EDP_CONFIG = (1 << 1), +}; + /** * enum vga_switcheroo_state - client power state * @VGA_SWITCHEROO_OFF: off @@ -132,8 +152,10 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev, void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info); -int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler); +int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler, + enum vga_switcheroo_handler_flags_t handler_flags); void vga_switcheroo_unregister_handler(void); +enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void); int vga_switcheroo_process_delayed_switch(void); @@ -150,11 +172,13 @@ static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {} static inline int vga_switcheroo_register_client(struct pci_dev *dev, const struct vga_switcheroo_client_ops *ops, bool driver_power_control) { return 0; } static inline void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info) {} -static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler) { return 0; } +static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler, + enum vga_switcheroo_handler_flags_t handler_flags) { return 0; } static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, enum vga_switcheroo_client_id id) { return 0; } static inline void vga_switcheroo_unregister_handler(void) {} +static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void) { return 0; } static inline int vga_switcheroo_process_delayed_switch(void) { return 0; } static inline enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; } -- cgit v1.2.3 From e4cb81d7e49c806fa557cf0ff4f3f40bd7a9cb7c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 11 Jan 2016 20:09:20 +0100 Subject: vga_switcheroo: Add support for switching only the DDC Originally by Seth Forshee , 2012-10-04: During graphics driver initialization it's useful to be able to mux only the DDC to the inactive client in order to read the EDID. Add a switch_ddc callback to allow capable handlers to provide this functionality, and add vga_switcheroo_switch_ddc() to allow DRM to mux only the DDC. Modified by Dave Airlie , 2012-12-22: I can't figure out why I didn't like this, but I rewrote this [...] to lock/unlock the ddc lines [...]. I think I'd prefer something like that otherwise the interface got really ugly. Modified by Lukas Wunner , 2015-04 - 2015-10: Change semantics of ->switch_ddc handler callback to return previous DDC owner. Original version tried to determine previous DDC owner with find_active_client() but this fails if the inactive client registers before the active client. Don't lock vgasr_mutex in _lock_ddc() / _unlock_ddc(), it can cause deadlocks because (a) during switch (with vgasr_mutex already held), GPU is woken and probes its outputs, tries to re-acquire vgasr_mutex to lock DDC lines; (b) Likewise during switch, GPU is suspended and calls cancel_delayed_work_sync() to stop output polling, if poll task is running at this moment we may wait forever for it to finish. Instead, lock mux_hw_lock when unregistering the handler because the only reason why we'd want to lock vgasr_mutex in _lock_ddc() / _unlock_ddc() is to block the handler from disappearing while DDC lines are switched. Also acquire mux_hw_lock in stage2 to avoid race condition where reading the EDID and switching happens simultaneously. Likewise on MIGD / MDIS commands and on runtime suspend. v2.1: Overhaul locking, squash commits (Daniel Vetter) v2.2: Readability improvements (Thierry Reding) v2.3: Overhaul locking once more v2.4: Retain semantics of ->switchto handler callback to switch all pins, including DDC (Daniel Vetter) v5: Rename ddc_lock to mux_hw_lock: Since we acquire this both when calling ->switch_ddc and ->switchto, it protects not just access to the DDC lines but to the mux in general. This is in line with the DRM convention to use low-level locks to avoid concurrent hw access (e.g. i2c, dp_aux) which are often called hw_lock (Daniel Vetter) Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=88861 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=61115 Tested-by: Lukas Wunner [MBP 9,1 2012 intel IVB + nvidia GK107 pre-retina 15"] Cc: Seth Forshee Cc: Dave Airlie Signed-off-by: Lukas Wunner Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/e81ae9722b84c5ed591805fee3ea6dbf5dc6c4b3.1452525860.git.lukas@wunner.de --- include/linux/vga_switcheroo.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index a745f4f0f729..b39a5f3153bd 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -102,6 +102,9 @@ enum vga_switcheroo_client_id { * Mandatory. For muxless machines this should be a no-op. Returning 0 * denotes success, anything else failure (in which case the switch is * aborted) + * @switch_ddc: switch DDC lines to given client. + * Optional. Should return the previous DDC owner on success or a + * negative int on failure * @power_state: cut or reinstate power of given client. * Optional. The return value is ignored * @get_client_id: determine if given pci device is integrated or discrete GPU. @@ -113,6 +116,7 @@ enum vga_switcheroo_client_id { struct vga_switcheroo_handler { int (*init)(void); int (*switchto)(enum vga_switcheroo_client_id id); + int (*switch_ddc)(enum vga_switcheroo_client_id id); int (*power_state)(enum vga_switcheroo_client_id id, enum vga_switcheroo_state state); enum vga_switcheroo_client_id (*get_client_id)(struct pci_dev *pdev); @@ -156,6 +160,8 @@ int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler enum vga_switcheroo_handler_flags_t handler_flags); void vga_switcheroo_unregister_handler(void); enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void); +int vga_switcheroo_lock_ddc(struct pci_dev *pdev); +int vga_switcheroo_unlock_ddc(struct pci_dev *pdev); int vga_switcheroo_process_delayed_switch(void); @@ -179,6 +185,8 @@ static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev, enum vga_switcheroo_client_id id) { return 0; } static inline void vga_switcheroo_unregister_handler(void) {} static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void) { return 0; } +static inline int vga_switcheroo_lock_ddc(struct pci_dev *pdev) { return -ENODEV; } +static inline int vga_switcheroo_unlock_ddc(struct pci_dev *pdev) { return -ENODEV; } static inline int vga_switcheroo_process_delayed_switch(void) { return 0; } static inline enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; } -- cgit v1.2.3 From 2413306c2566b729a9d17a81e9d1181e6f354d6a Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 11 Jan 2016 20:09:20 +0100 Subject: apple-gmux: Add helper for presence detect Centralize gmux' ACPI HID in a header file and add apple_gmux_present(). This can be used by other drivers to activate quirks specific to dual GPU MacBook Pros & Mac Pros. The alternative would be to hardcode DMI or PCI IDs and amend them whenever Apple introduces a new machine. Tested-by: Lukas Wunner [MBP 9,1 2012 intel IVB + nvidia GK107 pre-retina 15"] Signed-off-by: Lukas Wunner Reviewed-by: Darren Hart Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/89c23769058a340e5e11d4a7102f3793d3b0c94c.1452525860.git.lukas@wunner.de --- include/linux/apple-gmux.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/apple-gmux.h (limited to 'include/linux') diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h new file mode 100644 index 000000000000..feebc2840462 --- /dev/null +++ b/include/linux/apple-gmux.h @@ -0,0 +1,39 @@ +/* + * apple-gmux.h - microcontroller built into dual GPU MacBook Pro & Mac Pro + * Copyright (C) 2015 Lukas Wunner + * + * 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. + * + * 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. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#ifndef LINUX_APPLE_GMUX_H +#define LINUX_APPLE_GMUX_H + +#include + +#define GMUX_ACPI_HID "APP000B" + +/** + * apple_gmux_present() - detect if gmux is built into the machine + * + * Drivers may use this to activate quirks specific to dual GPU MacBook Pros + * and Mac Pros, e.g. for deferred probing, runtime pm and backlight. + * + * Return: %true if gmux is present and the kernel was configured + * with CONFIG_APPLE_GMUX, %false otherwise. + */ +static inline bool apple_gmux_present(void) +{ + return IS_ENABLED(CONFIG_APPLE_GMUX) && acpi_dev_present(GMUX_ACPI_HID); +} + +#endif /* LINUX_APPLE_GMUX_H */ -- cgit v1.2.3 From be6257b251cebd2deb8c76d43e387e28e3f7412d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 25 Jan 2016 19:24:50 +0100 Subject: quota: Add support for ->get_nextdqblk() for VFS quota Add infrastructure for supporting get_nextdqblk() callback for VFS quotas. Translate the operation into a callback to appropriate filesystem and consequently to quota format callback. Signed-off-by: Jan Kara --- include/linux/quota.h | 3 +++ include/linux/quotaops.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index fba92f5c1a63..9dfb6bce8c9e 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -306,6 +306,7 @@ struct quota_format_ops { int (*read_dqblk)(struct dquot *dquot); /* Read structure for one user */ int (*commit_dqblk)(struct dquot *dquot); /* Write structure for one user */ int (*release_dqblk)(struct dquot *dquot); /* Called when last reference to dquot is being dropped */ + int (*get_next_id)(struct super_block *sb, struct kqid *qid); /* Get next ID with existing structure in the quota file */ }; /* Operations working with dquots */ @@ -321,6 +322,8 @@ struct dquot_operations { * quota code only */ qsize_t *(*get_reserved_space) (struct inode *); int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */ + /* Get next ID with active quota structure */ + int (*get_next_id) (struct super_block *sb, struct kqid *qid); }; struct path; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 7a57c28eb5e7..f00fa86ac966 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -82,6 +82,7 @@ int dquot_commit(struct dquot *dquot); int dquot_acquire(struct dquot *dquot); int dquot_release(struct dquot *dquot); int dquot_commit_info(struct super_block *sb, int type); +int dquot_get_next_id(struct super_block *sb, struct kqid *qid); int dquot_mark_dquot_dirty(struct dquot *dquot); int dquot_file_open(struct inode *inode, struct file *file); @@ -99,6 +100,8 @@ int dquot_get_state(struct super_block *sb, struct qc_state *state); int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii); int dquot_get_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); +int dquot_get_next_dqblk(struct super_block *sb, struct kqid *id, + struct qc_dqblk *di); int dquot_set_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); -- cgit v1.2.3 From 0066373d9f9320f69f24b080ee00d10f14397355 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 25 Jan 2016 20:39:27 +0100 Subject: quota_v2: Implement get_next_id() for V2 quota format Implement functions to get id of next existing quota structure in quota file for quota tree based formats and thus for V2 quota format. Signed-off-by: Jan Kara --- include/linux/dqblk_qtree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dqblk_qtree.h b/include/linux/dqblk_qtree.h index ff8b55359648..0de21e935976 100644 --- a/include/linux/dqblk_qtree.h +++ b/include/linux/dqblk_qtree.h @@ -15,6 +15,7 @@ #define QTREE_DEL_REWRITE 6 struct dquot; +struct kqid; /* Operations */ struct qtree_fmt_operations { @@ -52,5 +53,6 @@ static inline int qtree_depth(struct qtree_mem_dqinfo *info) entries *= epb; return i; } +int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid); #endif /* _LINUX_DQBLK_QTREE_H */ -- cgit v1.2.3 From 5d2787cf0b210d2925e8d44e2e79241385249d6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Feb 2016 16:40:46 +0000 Subject: KEYS: Add an alloc flag to convey the builtinness of a key Add KEY_ALLOC_BUILT_IN to convey that a key should have KEY_FLAG_BUILTIN set rather than setting it after the fact. Signed-off-by: David Howells Acked-by: Mimi Zohar --- include/linux/key.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 7321ab8ef949..5f5b1129dc92 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -219,6 +219,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */ #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_TRUSTED 0x0004 /* Key should be flagged as trusted */ +#define KEY_ALLOC_BUILT_IN 0x0008 /* Key is built into kernel */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); -- cgit v1.2.3 From a0a90718f18264dc904d34a580f332006f5561e9 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 8 Feb 2016 17:14:28 +0200 Subject: spi: Let drivers translate ACPI DeviceSelection to suitable Linux chip select In Windows it is up to the SPI host controller driver to handle the ACPI DeviceSelection as it likes. The SPI core does not take any part in it. This is different in Linux because we always expect to have chip select in range of 0 .. master->num_chipselect - 1. In order to support this in Linux we need a way to allow the driver to translate between ACPI DeviceSelection field and Linux chip select number so provide a new optional hook ->fw_translate_cs() that can be used by a driver to handle translation and call this hook if set during SPI slave ACPI enumeration. Signed-off-by: Mika Westerberg Reviewed-by: Jarkko Nikula Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 53be3a4c60cb..8a25e6c2fb56 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -369,6 +369,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @dma_rx: DMA receive channel * @dummy_rx: dummy receive buffer for full-duplex devices * @dummy_tx: dummy transmit buffer for full-duplex devices + * @fw_translate_cs: If the boot firmware uses different numbering scheme + * what Linux expects, this optional hook can be used to translate + * between the two. * * Each SPI master controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -537,6 +540,8 @@ struct spi_master { /* dummy data for full duplex devices */ void *dummy_rx; void *dummy_tx; + + int (*fw_translate_cs)(struct spi_master *master, unsigned cs); }; static inline void *spi_master_get_devdata(struct spi_master *master) -- cgit v1.2.3 From 30f3a6ab44d8d06bb3d94f6320e4aa76df59d025 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 8 Feb 2016 17:14:31 +0200 Subject: spi: pxa2xx: Add support for both chip selects on Intel Braswell Intel Braswell LPSS SPI controller actually has two chip selects and there is no capabilities register where this could be found out. These two chip selects are controlled by bits which are in slightly differrent location than Broxton has. Braswell Windows driver also starts chip select (ACPI DeviceSelection) numbering from 1 so translate it to be suitable for Linux as well. Signed-off-by: Mika Westerberg Reviewed-by: Jarkko Nikula Reviewed-by: Andy Shevchenko Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index c2f2574ff61c..2a097d176ba9 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -197,6 +197,7 @@ enum pxa_ssp_type { QUARK_X1000_SSP, LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ LPSS_BYT_SSP, + LPSS_BSW_SSP, LPSS_SPT_SSP, LPSS_BXT_SSP, }; -- cgit v1.2.3 From d780c3711d9df9bacd56b71cf23443b895a331ca Mon Sep 17 00:00:00 2001 From: Martin Sperl Date: Mon, 14 Dec 2015 15:20:18 +0000 Subject: spi: core: added spi_resource management SPI resource management framework used while processing a spi_message via the spi-core. The basic idea is taken from devres, but as the allocation may happen fairly frequently, some provisioning (in the form of an unused spi_device pointer argument to spi_res_alloc) has been made so that at a later stage we may implement reuse objects allocated earlier avoiding the repeated allocation by keeping a cache of objects that we can reuse. This framework can get used for: * rewriting spi_messages * to fullfill alignment requirements of the spi_master HW * to fullfill transfer length requirements (e.g: transfers need to be less than 64k) * consolidate spi_messages with multiple transfers into a single transfer when the total transfer length is below a threshold. * reimplement spi_unmap_buf without explicitly needing to check if it has been mapped Signed-off-by: Martin Sperl Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 53be3a4c60cb..38204b584dc5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -582,6 +582,37 @@ extern void spi_unregister_master(struct spi_master *master); extern struct spi_master *spi_busnum_to_master(u16 busnum); +/* + * SPI resource management while processing a SPI message + */ + +/** + * struct spi_res - spi resource management structure + * @entry: list entry + * @release: release code called prior to freeing this resource + * @data: extra data allocated for the specific use-case + * + * this is based on ideas from devres, but focused on life-cycle + * management during spi_message processing + */ +typedef void (*spi_res_release_t)(struct spi_master *master, + struct spi_message *msg, + void *res); +struct spi_res { + struct list_head entry; + spi_res_release_t release; + unsigned long long data[]; /* guarantee ull alignment */ +}; + +extern void *spi_res_alloc(struct spi_device *spi, + spi_res_release_t release, + size_t size, gfp_t gfp); +extern void spi_res_add(struct spi_message *message, void *res); +extern void spi_res_free(void *res); + +extern void spi_res_release(struct spi_master *master, + struct spi_message *message); + /*---------------------------------------------------------------------------*/ /* @@ -720,6 +751,7 @@ struct spi_transfer { * @status: zero for success, else negative errno * @queue: for use by whichever driver currently owns the message * @state: for use by whichever driver currently owns the message + * @resources: for resource management when the spi message is processed * * A @spi_message is used to execute an atomic sequence of data transfers, * each represented by a struct spi_transfer. The sequence is "atomic" @@ -766,11 +798,15 @@ struct spi_message { */ struct list_head queue; void *state; + + /* list of spi_res reources when the spi message is processed */ + struct list_head resources; }; static inline void spi_message_init_no_memset(struct spi_message *m) { INIT_LIST_HEAD(&m->transfers); + INIT_LIST_HEAD(&m->resources); } static inline void spi_message_init(struct spi_message *m) -- cgit v1.2.3 From 523baf5a0609690cb742b3662b7ccac0ea0b2ef2 Mon Sep 17 00:00:00 2001 From: Martin Sperl Date: Mon, 14 Dec 2015 15:20:19 +0000 Subject: spi: core: add spi_replace_transfers method Add the spi_replace_transfers method that can get used to replace some spi_transfers from a spi_message with other transfers. Signed-off-by: Martin Sperl Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38204b584dc5..d71385756fee 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -890,6 +890,51 @@ spi_max_transfer_size(struct spi_device *spi) /*---------------------------------------------------------------------------*/ +/* SPI transfer replacement methods which make use of spi_res */ + +/** + * struct spi_replaced_transfers - structure describing the spi_transfer + * replacements that have occurred + * so that they can get reverted + * @release: some extra release code to get executed prior to + * relasing this structure + * @extradata: pointer to some extra data if requested or NULL + * @replaced_transfers: transfers that have been replaced and which need + * to get restored + * @replaced_after: the transfer after which the @replaced_transfers + * are to get re-inserted + * @inserted: number of transfers inserted + * @inserted_transfers: array of spi_transfers of array-size @inserted, + * that have been replacing replaced_transfers + * + * note: that @extradata will point to @inserted_transfers[@inserted] + * if some extra allocation is requested, so alignment will be the same + * as for spi_transfers + */ +struct spi_replaced_transfers; +typedef void (*spi_replaced_release_t)(struct spi_master *master, + struct spi_message *msg, + struct spi_replaced_transfers *res); +struct spi_replaced_transfers { + spi_replaced_release_t release; + void *extradata; + struct list_head replaced_transfers; + struct list_head *replaced_after; + size_t inserted; + struct spi_transfer inserted_transfers[]; +}; + +extern struct spi_replaced_transfers *spi_replace_transfers( + struct spi_message *msg, + struct spi_transfer *xfer_first, + size_t remove, + size_t insert, + spi_replaced_release_t release, + size_t extradatasize, + gfp_t gfp); + +/*---------------------------------------------------------------------------*/ + /* All these synchronous SPI transfer routines are utilities layered * over the core async transfer primitive. Here, "synchronous" means * they will sleep uninterruptibly until the async transfer completes. -- cgit v1.2.3 From d9f1212272818420fcde611a940c1ad611a8b785 Mon Sep 17 00:00:00 2001 From: Martin Sperl Date: Mon, 14 Dec 2015 15:20:20 +0000 Subject: spi: core: add spi_split_transfers_maxsize Add spi_split_transfers_maxsize method that splits spi_transfers transparently into multiple transfers that are below the given max-size. This makes use of the spi_res framework via spi_replace_transfers to allocate/free the extra transfers as well as reverting back the changes applied while processing the spi_message. Signed-off-by: Martin Sperl Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index d71385756fee..3c02b4d06268 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -53,6 +53,10 @@ extern struct bus_type spi_bus_type; * * @transfer_bytes_histo: * transfer bytes histogramm + * + * @transfers_split_maxsize: + * number of transfers that have been split because of + * maxsize limit */ struct spi_statistics { spinlock_t lock; /* lock for the whole structure */ @@ -72,6 +76,8 @@ struct spi_statistics { #define SPI_STATISTICS_HISTO_SIZE 17 unsigned long transfer_bytes_histo[SPI_STATISTICS_HISTO_SIZE]; + + unsigned long transfers_split_maxsize; }; void spi_statistics_add_transfer_stats(struct spi_statistics *stats, @@ -935,6 +941,15 @@ extern struct spi_replaced_transfers *spi_replace_transfers( /*---------------------------------------------------------------------------*/ +/* SPI transfer transformation methods */ + +extern int spi_split_transfers_maxsize(struct spi_master *master, + struct spi_message *msg, + size_t maxsize, + gfp_t gfp); + +/*---------------------------------------------------------------------------*/ + /* All these synchronous SPI transfer routines are utilities layered * over the core async transfer primitive. Here, "synchronous" means * they will sleep uninterruptibly until the async transfer completes. -- cgit v1.2.3 From 556351f14e74db4cd3ddde386457edce7bf0b27f Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Fri, 11 Dec 2015 09:39:56 +0530 Subject: spi: introduce accelerated read support for spi flash devices In addition to providing direct access to SPI bus, some spi controller hardwares (like ti-qspi) provide special port (like memory mapped port) that are optimized to improve SPI flash read performance. This means the controller can automatically send the SPI signals required to read data from the SPI flash device. For this, SPI controller needs to know flash specific information like read command to use, dummy bytes and address width. Introduce spi_flash_read() interface to support accelerated read over SPI flash devices. SPI master drivers can implement this callback to support interfaces such as memory mapped read etc. m25p80 flash driver and other flash drivers can call this make use of such interfaces. The interface should only be used with SPI flashes and cannot be used with other SPI devices. Signed-off-by: Vignesh R Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 53be3a4c60cb..ba0dee9d05a3 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -25,6 +25,7 @@ struct dma_chan; struct spi_master; struct spi_transfer; +struct spi_flash_read_message; /* * INTERFACES between SPI master-side drivers and SPI infrastructure. @@ -361,6 +362,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @handle_err: the subsystem calls the driver to handle an error that occurs * in the generic implementation of transfer_one_message(). * @unprepare_message: undo any work done by prepare_message(). + * @spi_flash_read: to support spi-controller hardwares that provide + * accelerated interface to read from flash devices. * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). @@ -513,6 +516,8 @@ struct spi_master { struct spi_message *message); int (*unprepare_message)(struct spi_master *master, struct spi_message *message); + int (*spi_flash_read)(struct spi_device *spi, + struct spi_flash_read_message *msg); /* * These hooks are for drivers that use a generic implementation @@ -1019,6 +1024,42 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd) return be16_to_cpu(result); } +/** + * struct spi_flash_read_message - flash specific information for + * spi-masters that provide accelerated flash read interfaces + * @buf: buffer to read data + * @from: offset within the flash from where data is to be read + * @len: length of data to be read + * @retlen: actual length of data read + * @read_opcode: read_opcode to be used to communicate with flash + * @addr_width: number of address bytes + * @dummy_bytes: number of dummy bytes + * @opcode_nbits: number of lines to send opcode + * @addr_nbits: number of lines to send address + * @data_nbits: number of lines for data + */ +struct spi_flash_read_message { + void *buf; + loff_t from; + size_t len; + size_t retlen; + u8 read_opcode; + u8 addr_width; + u8 dummy_bytes; + u8 opcode_nbits; + u8 addr_nbits; + u8 data_nbits; +}; + +/* SPI core interface for flash read support */ +static inline bool spi_flash_read_supported(struct spi_device *spi) +{ + return spi->master->spi_flash_read ? true : false; +} + +int spi_flash_read(struct spi_device *spi, + struct spi_flash_read_message *msg); + /*---------------------------------------------------------------------------*/ /* -- cgit v1.2.3 From 868f2f0b72068a097508b6e8870a8950fd8eb7ef Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 17 Dec 2015 17:08:14 -0700 Subject: blk-mq: dynamic h/w context count The hardware's provided queue count may change at runtime with resource provisioning. This patch allows a block driver to alter the number of h/w queues available when its resource count changes. The main part is a new blk-mq API to request a new number of h/w queues for a given live tag set. The new API freezes all queues using that set, then adjusts the allocated count prior to remapping these to CPUs. The bulk of the rest just shifts where h/w contexts and all their artifacts are allocated and freed. The number of max h/w contexts is capped to the number of possible cpus since there is no use for more than that. As such, all pre-allocated memory for pointers need to account for the max possible rather than the initial number of queues. A side effect of this is that the blk-mq will proceed successfully as long as it can allocate at least one h/w context. Previously it would fail request queue initialization if less than the requested number was allocated. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Tested-by: Jon Derrick Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7fc9296b5742..15a73d49fd1d 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -244,6 +244,8 @@ void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_mq_freeze_queue_start(struct request_queue *q); +void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. -- cgit v1.2.3 From 9f8ea969d5cfdd4353d2adb004e8e2286b984369 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 9 Feb 2016 10:30:33 +0530 Subject: PM / OPP: get/put regulators from OPP core This allows the OPP core to request/free the regulator resource, attached to a device OPP. The regulator device is fetched using the name provided by the driver, while calling: dev_pm_opp_set_regulator(). This will work for both OPP-v1 and v2 bindings. This is a preliminary step for moving the OPP switching logic into the OPP core. Signed-off-by: Viresh Kumar Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 95403d2ccaf5..c70a18ac9c8a 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -60,6 +60,8 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, void dev_pm_opp_put_supported_hw(struct device *dev); int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); +int dev_pm_opp_set_regulator(struct device *dev, const char *name); +void dev_pm_opp_put_regulator(struct device *dev); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -151,6 +153,13 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) static inline void dev_pm_opp_put_prop_name(struct device *dev) {} +static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_regulator(struct device *dev) {} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -- cgit v1.2.3 From 655c9df961751ce21466f6e97e8033932c27a675 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 9 Feb 2016 10:30:35 +0530 Subject: PM / OPP: Introduce dev_pm_opp_get_max_volt_latency() In few use cases (like: cpufreq), it is desired to get the maximum voltage latency for changing OPPs. Add support for that. Signed-off-by: Viresh Kumar Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index c70a18ac9c8a..5daa43058ac1 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -34,6 +34,7 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev); struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, @@ -88,6 +89,11 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) return 0; } +static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) +{ + return 0; +} + static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) { return NULL; -- cgit v1.2.3 From 2174344765f472895c076d703c9cdc58215e1393 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 9 Feb 2016 10:30:36 +0530 Subject: PM / OPP: Introduce dev_pm_opp_get_max_transition_latency() In few use cases (like: cpufreq), it is desired to get the maximum latency for changing OPPs. Add support for that. Signed-off-by: Viresh Kumar Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 5daa43058ac1..59da3d9e11ea 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -35,6 +35,7 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev); struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, @@ -94,6 +95,11 @@ static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) return 0; } +static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev) +{ + return 0; +} + static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) { return NULL; -- cgit v1.2.3 From 6a0712f6f199e737aa5913d28ec4bd3a25de9660 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 9 Feb 2016 10:30:39 +0530 Subject: PM / OPP: Add dev_pm_opp_set_rate() This adds a routine, dev_pm_opp_set_rate(), responsible for configuring power-supply and clock source for an OPP. The OPP is found by matching against the target_freq passed to the routine. This shall replace similar code present in most of the OPP users and help simplify them a lot. Signed-off-by: Viresh Kumar Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 59da3d9e11ea..cccaf4a29e9f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -64,6 +64,7 @@ int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); int dev_pm_opp_set_regulator(struct device *dev, const char *name); void dev_pm_opp_put_regulator(struct device *dev); +int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -172,6 +173,11 @@ static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) static inline void dev_pm_opp_put_regulator(struct device *dev) {} +static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) +{ + return -EINVAL; +} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -- cgit v1.2.3 From b7172119714781d15128cd1ae029bd028b0bf37a Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 10 Feb 2016 14:17:41 +0100 Subject: apple-gmux: Fix build breakage if !CONFIG_ACPI The DRM drivers i915, nouveau and radeon may be compiled with CONFIG_ACPI not set, in which case acpi_dev_present() is undefined. Add a no-op stub for apple_gmux_present() which is used if CONFIG_APPLE_GMUX is not enabled to avoid build breakage. (CONFIG_APPLE_GMUX depends on CONFIG_ACPI.) Reported-by: Stephen Rothwell Signed-off-by: Lukas Wunner Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20160210131741.GA15492@wunner.de --- include/linux/apple-gmux.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index feebc2840462..b2d32e01dfe4 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -22,6 +22,8 @@ #define GMUX_ACPI_HID "APP000B" +#if IS_ENABLED(CONFIG_APPLE_GMUX) + /** * apple_gmux_present() - detect if gmux is built into the machine * @@ -33,7 +35,16 @@ */ static inline bool apple_gmux_present(void) { - return IS_ENABLED(CONFIG_APPLE_GMUX) && acpi_dev_present(GMUX_ACPI_HID); + return acpi_dev_present(GMUX_ACPI_HID); } +#else /* !CONFIG_APPLE_GMUX */ + +static inline bool apple_gmux_present(void) +{ + return false; +} + +#endif /* !CONFIG_APPLE_GMUX */ + #endif /* LINUX_APPLE_GMUX_H */ -- cgit v1.2.3 From d9b3fca27385eafe61c3ca6feab6cb1e7dc77482 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Wed, 10 Feb 2016 11:50:37 -0500 Subject: tcp: __tcp_hdrlen() helper tcp_hdrlen is wasteful if you already have a pointer to struct tcphdr. This splits the size calculation into a helper function that can be used if a struct tcphdr is already available. Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d909feeeaea2..bcbf51da4e1e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -29,9 +29,14 @@ static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb) return (struct tcphdr *)skb_transport_header(skb); } +static inline unsigned int __tcp_hdrlen(const struct tcphdr *th) +{ + return th->doff * 4; +} + static inline unsigned int tcp_hdrlen(const struct sk_buff *skb) { - return tcp_hdr(skb)->doff * 4; + return __tcp_hdrlen(tcp_hdr(skb)); } static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb) -- cgit v1.2.3 From abbc30436d39dfed8ebfca338d253f211ac7b094 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 Feb 2016 13:31:19 +0100 Subject: ipv6: add option to drop unicast encapsulated in L2 multicast In order to solve a problem with 802.11, the so-called hole-196 attack, add an option (sysctl) called "drop_unicast_in_l2_multicast" which, if enabled, causes the stack to drop IPv6 unicast packets encapsulated in link-layer multi- or broadcast frames. Such frames can (as an attack) be created by any member of the same wireless network and transmitted as valid encrypted frames since the symmetric key for broadcast frames is shared between all stations. Reviewed-by: Julian Anastasov Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 402753bccafa..4a4c1ae826cb 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -50,6 +50,7 @@ struct ipv6_devconf { __s32 mc_forwarding; #endif __s32 disable_ipv6; + __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; -- cgit v1.2.3 From 7a02bf892d8f1e5298af1676f001bee410509d80 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 Feb 2016 13:31:20 +0100 Subject: ipv6: add option to drop unsolicited neighbor advertisements In certain 802.11 wireless deployments, there will be NA proxies that use knowledge of the network to correctly answer requests. To prevent unsolicitd advertisements on the shared medium from being a problem, on such deployments wireless needs to drop them. Enable this by providing an option called "drop_unsolicited_na". Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4a4c1ae826cb..4b2267e1b7c3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -56,6 +56,7 @@ struct ipv6_devconf { __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; + __s32 drop_unsolicited_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; -- cgit v1.2.3 From 76443456227097179c14826425f88a95d81a892e Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 5 Feb 2016 15:27:37 -0800 Subject: net: Move GSO csum into SKB_GSO_CB This patch moves the checksum maintained by GSO out of skb->csum and into the GSO context block in order to allow for us to work on outer checksums while maintaining the inner checksum offsets in the case of the inner checksum being offloaded, while the outer checksums will be computed. While updating the code I also did a minor cleanu-up on gso_make_checksum. The change is mostly to make it so that we store the values and compute the checksum instead of computing the checksum and then storing the values we needed to update. Signed-off-by: Alexander Duyck Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 11f935c1a090..acece7ce376f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3549,6 +3549,7 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb) struct skb_gso_cb { int mac_offset; int encap_level; + __wsum csum; __u16 csum_start; }; #define SKB_SGO_CB_OFFSET 32 @@ -3585,15 +3586,14 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) */ static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) { - int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) - - skb_transport_offset(skb); - __wsum partial; + unsigned char *csum_start = skb_transport_header(skb); + int plen = (skb->head + SKB_GSO_CB(skb)->csum_start) - csum_start; + __wsum partial = SKB_GSO_CB(skb)->csum; - partial = csum_partial(skb_transport_header(skb), plen, skb->csum); - skb->csum = res; - SKB_GSO_CB(skb)->csum_start -= plen; + SKB_GSO_CB(skb)->csum = res; + SKB_GSO_CB(skb)->csum_start = csum_start - skb->head; - return csum_fold(partial); + return csum_fold(csum_partial(csum_start, plen, partial)); } static inline bool skb_is_gso(const struct sk_buff *skb) -- cgit v1.2.3 From 08b64fcca942733413bc5ac2321d57021d3e8578 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 5 Feb 2016 15:27:49 -0800 Subject: net: Store checksum result for offloaded GSO checksums This patch makes it so that we can offload the checksums for a packet up to a certain point and then begin computing the checksums via software. Setting this up is fairly straight forward as all we need to do is reset the values stored in csum and csum_start for the GSO context block. One complication for this is remote checksum offload. In order to allow the inner checksums to be offloaded while computing the outer checksum manually we needed to have some way of indicating that the offload wasn't real. In order to do that I replaced CHECKSUM_PARTIAL with CHECKSUM_UNNECESSARY in the case of us computing checksums for the outer header while skipping computing checksums for the inner headers. We clean up the ip_summed flag and set it to either CHECKSUM_PARTIAL or CHECKSUM_NONE once we hand the packet off to the next lower level. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index acece7ce376f..a8fc2220e8ce 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2161,6 +2161,11 @@ static inline int skb_checksum_start_offset(const struct sk_buff *skb) return skb->csum_start - skb_headroom(skb); } +static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) +{ + return skb->head + skb->csum_start; +} + static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; @@ -3576,6 +3581,16 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) return 0; } +static inline void gso_reset_checksum(struct sk_buff *skb, __wsum res) +{ + /* Do not update partial checksums if remote checksum is enabled. */ + if (skb->remcsum_offload) + return; + + SKB_GSO_CB(skb)->csum = res; + SKB_GSO_CB(skb)->csum_start = skb_checksum_start(skb) - skb->head; +} + /* Compute the checksum for a gso segment. First compute the checksum value * from the start of transport header to SKB_GSO_CB(skb)->csum_start, and * then add in skb->csum (checksum from csum_start to end of packet). -- cgit v1.2.3 From 815c52700746cdcc0874a33390bac334a4b90107 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:21 +0200 Subject: igmp: Namespaceify igmp_max_memberships sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 9c9de11549a7..57d6d06ce0b3 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,6 @@ static inline struct igmpv3_query * } extern int sysctl_igmp_llm_reports; -extern int sysctl_igmp_max_memberships; extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; -- cgit v1.2.3 From 166b6b2d6f01be67a83b87ab5c91350a68b17115 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:22 +0200 Subject: igmp: Namespaceify igmp_max_msf sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 57d6d06ce0b3..a91ec9f575e7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,6 @@ static inline struct igmpv3_query * } extern int sysctl_igmp_llm_reports; -extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; struct ip_sf_socklist { -- cgit v1.2.3 From 87a8a2ae65b7721893c7922f963502be8fa01c94 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 9 Feb 2016 00:13:50 +0200 Subject: igmp: Namespaceify igmp_llm_reports sysctl knob This was initially introduced in df2cf4a78e488d26 ("IGMP: Inhibit reports for local multicast groups") by defining the sysctl in the ipv4_net_table array, however it was never implemented to be namespace aware. Fix this by changing the code accordingly. Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index a91ec9f575e7..c683f4bf642b 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,7 +37,6 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } -extern int sysctl_igmp_llm_reports; extern int sysctl_igmp_qrv; struct ip_sf_socklist { -- cgit v1.2.3 From 165094afcee79e4d5b6e94032a5d3be157460b4a Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:24 +0200 Subject: igmp: Namespacify igmp_qrv sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index c683f4bf642b..12f6fba6d21a 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,8 +37,6 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } -extern int sysctl_igmp_qrv; - struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; -- cgit v1.2.3 From df05c6f6e0bb41380b31ef99b49796ac43a2a2df Mon Sep 17 00:00:00 2001 From: Doug Anderson Date: Fri, 29 Jan 2016 23:07:26 +0100 Subject: ARM: 8506/1: common: DMA-mapping: add DMA_ATTR_ALLOC_SINGLE_PAGES attribute This patch adds the DMA_ATTR_ALLOC_SINGLE_PAGES attribute to the DMA-mapping subsystem. This attribute can be used as a hint to the DMA-mapping subsystem that it's likely not worth it to try to allocate large pages behind the scenes. Large pages are likely to make an IOMMU TLB work more efficiently but may not be worth it. See the Documentation contained in this patch for more details about this attribute and when to use it. Note that the name of the hint (DMA_ATTR_ALLOC_SINGLE_PAGES) is loosely based on the name MADV_NOHUGEPAGE. Just as there is MADV_NOHUGEPAGE vs. MADV_HUGEPAGE we could also add an "opposite" attribute to DMA_ATTR_ALLOC_SINGLE_PAGES. Without having the "opposite" attribute the lack of DMA_ATTR_ALLOC_SINGLE_PAGES means "use your best judgement about whether to use small pages or large pages". Signed-off-by: Douglas Anderson Acked-by: Marek Szyprowski Reviewed-by: Robin Murphy Tested-by: Javier Martinez Canillas Signed-off-by: Russell King --- include/linux/dma-attrs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h index 99c0be00b47c..5246239a4953 100644 --- a/include/linux/dma-attrs.h +++ b/include/linux/dma-attrs.h @@ -18,6 +18,7 @@ enum dma_attr { DMA_ATTR_NO_KERNEL_MAPPING, DMA_ATTR_SKIP_CPU_SYNC, DMA_ATTR_FORCE_CONTIGUOUS, + DMA_ATTR_ALLOC_SINGLE_PAGES, DMA_ATTR_MAX, }; -- cgit v1.2.3 From 8b6f2499ac45d5a0ab2e4b6f9613ab3f60416be1 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 1 Feb 2016 18:01:30 +0100 Subject: ARM: 8511/1: ARM64: kernel: PSCI: move PSCI idle management code to drivers/firmware ARM64 PSCI kernel interfaces that initialize idle states and implement the suspend API to enter them are generic and can be shared with the ARM architecture. To achieve that goal, this patch moves ARM64 PSCI idle management code to drivers/firmware, so that the interface to initialize and enter idle states can actually be shared by ARM and ARM64 arches back-ends. The ARM generic CPUidle implementation also requires the definition of a cpuidle_ops section entry for the kernel to initialize the CPUidle operations at boot based on the enable-method (ie ARM64 has the statically initialized cpu_ops counterparts for that purpose); therefore this patch also adds the required section entry on CONFIG_ARM for PSCI so that the kernel can initialize the PSCI CPUidle back-end when PSCI is the probed enable-method. On ARM64 this patch provides no functional change. Signed-off-by: Lorenzo Pieralisi Acked-by: Daniel Lezcano Acked-by: Catalin Marinas [arch/arm64] Acked-by: Mark Rutland Tested-by: Jisheng Zhang Cc: Will Deacon Cc: Sudeep Holla Cc: Daniel Lezcano Cc: Catalin Marinas Cc: Mark Rutland Cc: Jisheng Zhang Signed-off-by: Russell King --- include/linux/psci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psci.h b/include/linux/psci.h index 12c4865457ad..393efe2edf9a 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -24,6 +24,9 @@ bool psci_tos_resident_on(int cpu); bool psci_power_state_loses_context(u32 state); bool psci_power_state_is_valid(u32 state); +int psci_cpu_init_idle(unsigned int cpu); +int psci_cpu_suspend_enter(unsigned long index); + struct psci_operations { int (*cpu_suspend)(u32 state, unsigned long entry_point); int (*cpu_off)(u32 state); -- cgit v1.2.3 From e2fccf5c15157218f0b6488168f98183f82c1eda Mon Sep 17 00:00:00 2001 From: Markus Pargmann Date: Mon, 14 Dec 2015 14:53:50 +0100 Subject: mfd: fsl-imx25-tsadc: Register touchscreen ADC driver This is the core driver for imx25 touchscreen/adc driver. The module has one shared ADC and two different conversion queues which use the ADC. The two queues are identical. Both can be used for general purpose ADC but one is meant to be used for touchscreens. This driver is the core which manages the central components and registers of the TSC/ADC unit. It manages the IRQs and forwards them to the correct components. Signed-off-by: Markus Pargmann Signed-off-by: Denis Carikli [ensure correct ADC clock depending on the IPG clock] Signed-off-by: Juergen Borleis Acked-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/imx25-tsadc.h | 140 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 140 insertions(+) create mode 100644 include/linux/mfd/imx25-tsadc.h (limited to 'include/linux') diff --git a/include/linux/mfd/imx25-tsadc.h b/include/linux/mfd/imx25-tsadc.h new file mode 100644 index 000000000000..7fe4b8c3baac --- /dev/null +++ b/include/linux/mfd/imx25-tsadc.h @@ -0,0 +1,140 @@ +#ifndef _LINUX_INCLUDE_MFD_IMX25_TSADC_H_ +#define _LINUX_INCLUDE_MFD_IMX25_TSADC_H_ + +struct regmap; +struct clk; + +struct mx25_tsadc { + struct regmap *regs; + struct irq_domain *domain; + struct clk *clk; +}; + +#define MX25_TSC_TGCR 0x00 +#define MX25_TSC_TGSR 0x04 +#define MX25_TSC_TICR 0x08 + +/* The same register layout for TC and GC queue */ +#define MX25_ADCQ_FIFO 0x00 +#define MX25_ADCQ_CR 0x04 +#define MX25_ADCQ_SR 0x08 +#define MX25_ADCQ_MR 0x0c +#define MX25_ADCQ_ITEM_7_0 0x20 +#define MX25_ADCQ_ITEM_15_8 0x24 +#define MX25_ADCQ_CFG(n) (0x40 + ((n) * 0x4)) + +#define MX25_ADCQ_MR_MASK 0xffffffff + +/* TGCR */ +#define MX25_TGCR_PDBTIME(x) ((x) << 25) +#define MX25_TGCR_PDBTIME_MASK GENMASK(31, 25) +#define MX25_TGCR_PDBEN BIT(24) +#define MX25_TGCR_PDEN BIT(23) +#define MX25_TGCR_ADCCLKCFG(x) ((x) << 16) +#define MX25_TGCR_GET_ADCCLK(x) (((x) >> 16) & 0x1f) +#define MX25_TGCR_INTREFEN BIT(10) +#define MX25_TGCR_POWERMODE_MASK GENMASK(9, 8) +#define MX25_TGCR_POWERMODE_SAVE (1 << 8) +#define MX25_TGCR_POWERMODE_ON (2 << 8) +#define MX25_TGCR_STLC BIT(5) +#define MX25_TGCR_SLPC BIT(4) +#define MX25_TGCR_FUNC_RST BIT(2) +#define MX25_TGCR_TSC_RST BIT(1) +#define MX25_TGCR_CLK_EN BIT(0) + +/* TGSR */ +#define MX25_TGSR_SLP_INT BIT(2) +#define MX25_TGSR_GCQ_INT BIT(1) +#define MX25_TGSR_TCQ_INT BIT(0) + +/* ADCQ_ITEM_* */ +#define _MX25_ADCQ_ITEM(item, x) ((x) << ((item) * 4)) +#define MX25_ADCQ_ITEM(item, x) ((item) >= 8 ? \ + _MX25_ADCQ_ITEM((item) - 8, (x)) : _MX25_ADCQ_ITEM((item), (x))) + +/* ADCQ_FIFO (TCQFIFO and GCQFIFO) */ +#define MX25_ADCQ_FIFO_DATA(x) (((x) >> 4) & 0xfff) +#define MX25_ADCQ_FIFO_ID(x) ((x) & 0xf) + +/* ADCQ_CR (TCQR and GCQR) */ +#define MX25_ADCQ_CR_PDCFG_LEVEL BIT(19) +#define MX25_ADCQ_CR_PDMSK BIT(18) +#define MX25_ADCQ_CR_FRST BIT(17) +#define MX25_ADCQ_CR_QRST BIT(16) +#define MX25_ADCQ_CR_RWAIT_MASK GENMASK(15, 12) +#define MX25_ADCQ_CR_RWAIT(x) ((x) << 12) +#define MX25_ADCQ_CR_WMRK_MASK GENMASK(11, 8) +#define MX25_ADCQ_CR_WMRK(x) ((x) << 8) +#define MX25_ADCQ_CR_LITEMID_MASK (0xf << 4) +#define MX25_ADCQ_CR_LITEMID(x) ((x) << 4) +#define MX25_ADCQ_CR_RPT BIT(3) +#define MX25_ADCQ_CR_FQS BIT(2) +#define MX25_ADCQ_CR_QSM_MASK GENMASK(1, 0) +#define MX25_ADCQ_CR_QSM_PD 0x1 +#define MX25_ADCQ_CR_QSM_FQS 0x2 +#define MX25_ADCQ_CR_QSM_FQS_PD 0x3 + +/* ADCQ_SR (TCQSR and GCQSR) */ +#define MX25_ADCQ_SR_FDRY BIT(15) +#define MX25_ADCQ_SR_FULL BIT(14) +#define MX25_ADCQ_SR_EMPT BIT(13) +#define MX25_ADCQ_SR_FDN(x) (((x) >> 8) & 0x1f) +#define MX25_ADCQ_SR_FRR BIT(6) +#define MX25_ADCQ_SR_FUR BIT(5) +#define MX25_ADCQ_SR_FOR BIT(4) +#define MX25_ADCQ_SR_EOQ BIT(1) +#define MX25_ADCQ_SR_PD BIT(0) + +/* ADCQ_MR (TCQMR and GCQMR) */ +#define MX25_ADCQ_MR_FDRY_DMA BIT(31) +#define MX25_ADCQ_MR_FER_DMA BIT(22) +#define MX25_ADCQ_MR_FUR_DMA BIT(21) +#define MX25_ADCQ_MR_FOR_DMA BIT(20) +#define MX25_ADCQ_MR_EOQ_DMA BIT(17) +#define MX25_ADCQ_MR_PD_DMA BIT(16) +#define MX25_ADCQ_MR_FDRY_IRQ BIT(15) +#define MX25_ADCQ_MR_FER_IRQ BIT(6) +#define MX25_ADCQ_MR_FUR_IRQ BIT(5) +#define MX25_ADCQ_MR_FOR_IRQ BIT(4) +#define MX25_ADCQ_MR_EOQ_IRQ BIT(1) +#define MX25_ADCQ_MR_PD_IRQ BIT(0) + +/* ADCQ_CFG (TICR, TCC0-7,GCC0-7) */ +#define MX25_ADCQ_CFG_SETTLING_TIME(x) ((x) << 24) +#define MX25_ADCQ_CFG_IGS (1 << 20) +#define MX25_ADCQ_CFG_NOS_MASK GENMASK(19, 16) +#define MX25_ADCQ_CFG_NOS(x) (((x) - 1) << 16) +#define MX25_ADCQ_CFG_WIPER (1 << 15) +#define MX25_ADCQ_CFG_YNLR (1 << 14) +#define MX25_ADCQ_CFG_YPLL_HIGH (0 << 12) +#define MX25_ADCQ_CFG_YPLL_OFF (1 << 12) +#define MX25_ADCQ_CFG_YPLL_LOW (3 << 12) +#define MX25_ADCQ_CFG_XNUR_HIGH (0 << 10) +#define MX25_ADCQ_CFG_XNUR_OFF (1 << 10) +#define MX25_ADCQ_CFG_XNUR_LOW (3 << 10) +#define MX25_ADCQ_CFG_XPUL_HIGH (0 << 9) +#define MX25_ADCQ_CFG_XPUL_OFF (1 << 9) +#define MX25_ADCQ_CFG_REFP(sel) ((sel) << 7) +#define MX25_ADCQ_CFG_REFP_YP MX25_ADCQ_CFG_REFP(0) +#define MX25_ADCQ_CFG_REFP_XP MX25_ADCQ_CFG_REFP(1) +#define MX25_ADCQ_CFG_REFP_EXT MX25_ADCQ_CFG_REFP(2) +#define MX25_ADCQ_CFG_REFP_INT MX25_ADCQ_CFG_REFP(3) +#define MX25_ADCQ_CFG_REFP_MASK GENMASK(8, 7) +#define MX25_ADCQ_CFG_IN(sel) ((sel) << 4) +#define MX25_ADCQ_CFG_IN_XP MX25_ADCQ_CFG_IN(0) +#define MX25_ADCQ_CFG_IN_YP MX25_ADCQ_CFG_IN(1) +#define MX25_ADCQ_CFG_IN_XN MX25_ADCQ_CFG_IN(2) +#define MX25_ADCQ_CFG_IN_YN MX25_ADCQ_CFG_IN(3) +#define MX25_ADCQ_CFG_IN_WIPER MX25_ADCQ_CFG_IN(4) +#define MX25_ADCQ_CFG_IN_AUX0 MX25_ADCQ_CFG_IN(5) +#define MX25_ADCQ_CFG_IN_AUX1 MX25_ADCQ_CFG_IN(6) +#define MX25_ADCQ_CFG_IN_AUX2 MX25_ADCQ_CFG_IN(7) +#define MX25_ADCQ_CFG_REFN(sel) ((sel) << 2) +#define MX25_ADCQ_CFG_REFN_XN MX25_ADCQ_CFG_REFN(0) +#define MX25_ADCQ_CFG_REFN_YN MX25_ADCQ_CFG_REFN(1) +#define MX25_ADCQ_CFG_REFN_NGND MX25_ADCQ_CFG_REFN(2) +#define MX25_ADCQ_CFG_REFN_NGND2 MX25_ADCQ_CFG_REFN(3) +#define MX25_ADCQ_CFG_REFN_MASK GENMASK(3, 2) +#define MX25_ADCQ_CFG_PENIACK (1 << 1) + +#endif /* _LINUX_INCLUDE_MFD_IMX25_TSADC_H_ */ -- cgit v1.2.3 From 65b6555971d0498b18a0b2fdc6dd7c822f2d69b7 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 25 Jan 2016 09:43:44 -0600 Subject: mfd: tps65912: Remove old driver in preparation for new driver The old tps65912 driver is being replaced, delete old driver. Signed-off-by: Andrew F. Davis Acked-by: Mark Brown Acked-by: Linus Walleij Signed-off-by: Lee Jones --- include/linux/mfd/tps65912.h | 328 ------------------------------------------- 1 file changed, 328 deletions(-) delete mode 100644 include/linux/mfd/tps65912.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h deleted file mode 100644 index 6d309032dc0d..000000000000 --- a/include/linux/mfd/tps65912.h +++ /dev/null @@ -1,328 +0,0 @@ -/* - * tps65912.h -- TI TPS6591x - * - * Copyright 2011 Texas Instruments Inc. - * - * Author: Margarita Olaya - * - * 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. - * - */ - -#ifndef __LINUX_MFD_TPS65912_H -#define __LINUX_MFD_TPS65912_H - -/* TPS regulator type list */ -#define REGULATOR_LDO 0 -#define REGULATOR_DCDC 1 - -/* - * List of registers for TPS65912 - */ - -#define TPS65912_DCDC1_CTRL 0x00 -#define TPS65912_DCDC2_CTRL 0x01 -#define TPS65912_DCDC3_CTRL 0x02 -#define TPS65912_DCDC4_CTRL 0x03 -#define TPS65912_DCDC1_OP 0x04 -#define TPS65912_DCDC1_AVS 0x05 -#define TPS65912_DCDC1_LIMIT 0x06 -#define TPS65912_DCDC2_OP 0x07 -#define TPS65912_DCDC2_AVS 0x08 -#define TPS65912_DCDC2_LIMIT 0x09 -#define TPS65912_DCDC3_OP 0x0A -#define TPS65912_DCDC3_AVS 0x0B -#define TPS65912_DCDC3_LIMIT 0x0C -#define TPS65912_DCDC4_OP 0x0D -#define TPS65912_DCDC4_AVS 0x0E -#define TPS65912_DCDC4_LIMIT 0x0F -#define TPS65912_LDO1_OP 0x10 -#define TPS65912_LDO1_AVS 0x11 -#define TPS65912_LDO1_LIMIT 0x12 -#define TPS65912_LDO2_OP 0x13 -#define TPS65912_LDO2_AVS 0x14 -#define TPS65912_LDO2_LIMIT 0x15 -#define TPS65912_LDO3_OP 0x16 -#define TPS65912_LDO3_AVS 0x17 -#define TPS65912_LDO3_LIMIT 0x18 -#define TPS65912_LDO4_OP 0x19 -#define TPS65912_LDO4_AVS 0x1A -#define TPS65912_LDO4_LIMIT 0x1B -#define TPS65912_LDO5 0x1C -#define TPS65912_LDO6 0x1D -#define TPS65912_LDO7 0x1E -#define TPS65912_LDO8 0x1F -#define TPS65912_LDO9 0x20 -#define TPS65912_LDO10 0x21 -#define TPS65912_THRM 0x22 -#define TPS65912_CLK32OUT 0x23 -#define TPS65912_DEVCTRL 0x24 -#define TPS65912_DEVCTRL2 0x25 -#define TPS65912_I2C_SPI_CFG 0x26 -#define TPS65912_KEEP_ON 0x27 -#define TPS65912_KEEP_ON2 0x28 -#define TPS65912_SET_OFF1 0x29 -#define TPS65912_SET_OFF2 0x2A -#define TPS65912_DEF_VOLT 0x2B -#define TPS65912_DEF_VOLT_MAPPING 0x2C -#define TPS65912_DISCHARGE 0x2D -#define TPS65912_DISCHARGE2 0x2E -#define TPS65912_EN1_SET1 0x2F -#define TPS65912_EN1_SET2 0x30 -#define TPS65912_EN2_SET1 0x31 -#define TPS65912_EN2_SET2 0x32 -#define TPS65912_EN3_SET1 0x33 -#define TPS65912_EN3_SET2 0x34 -#define TPS65912_EN4_SET1 0x35 -#define TPS65912_EN4_SET2 0x36 -#define TPS65912_PGOOD 0x37 -#define TPS65912_PGOOD2 0x38 -#define TPS65912_INT_STS 0x39 -#define TPS65912_INT_MSK 0x3A -#define TPS65912_INT_STS2 0x3B -#define TPS65912_INT_MSK2 0x3C -#define TPS65912_INT_STS3 0x3D -#define TPS65912_INT_MSK3 0x3E -#define TPS65912_INT_STS4 0x3F -#define TPS65912_INT_MSK4 0x40 -#define TPS65912_GPIO1 0x41 -#define TPS65912_GPIO2 0x42 -#define TPS65912_GPIO3 0x43 -#define TPS65912_GPIO4 0x44 -#define TPS65912_GPIO5 0x45 -#define TPS65912_VMON 0x46 -#define TPS65912_LEDA_CTRL1 0x47 -#define TPS65912_LEDA_CTRL2 0x48 -#define TPS65912_LEDA_CTRL3 0x49 -#define TPS65912_LEDA_CTRL4 0x4A -#define TPS65912_LEDA_CTRL5 0x4B -#define TPS65912_LEDA_CTRL6 0x4C -#define TPS65912_LEDA_CTRL7 0x4D -#define TPS65912_LEDA_CTRL8 0x4E -#define TPS65912_LEDB_CTRL1 0x4F -#define TPS65912_LEDB_CTRL2 0x50 -#define TPS65912_LEDB_CTRL3 0x51 -#define TPS65912_LEDB_CTRL4 0x52 -#define TPS65912_LEDB_CTRL5 0x53 -#define TPS65912_LEDB_CTRL6 0x54 -#define TPS65912_LEDB_CTRL7 0x55 -#define TPS65912_LEDB_CTRL8 0x56 -#define TPS65912_LEDC_CTRL1 0x57 -#define TPS65912_LEDC_CTRL2 0x58 -#define TPS65912_LEDC_CTRL3 0x59 -#define TPS65912_LEDC_CTRL4 0x5A -#define TPS65912_LEDC_CTRL5 0x5B -#define TPS65912_LEDC_CTRL6 0x5C -#define TPS65912_LEDC_CTRL7 0x5D -#define TPS65912_LEDC_CTRL8 0x5E -#define TPS65912_LED_RAMP_UP_TIME 0x5F -#define TPS65912_LED_RAMP_DOWN_TIME 0x60 -#define TPS65912_LED_SEQ_EN 0x61 -#define TPS65912_LOADSWITCH 0x62 -#define TPS65912_SPARE 0x63 -#define TPS65912_VERNUM 0x64 -#define TPS6591X_MAX_REGISTER 0x64 - -/* IRQ Definitions */ -#define TPS65912_IRQ_PWRHOLD_F 0 -#define TPS65912_IRQ_VMON 1 -#define TPS65912_IRQ_PWRON 2 -#define TPS65912_IRQ_PWRON_LP 3 -#define TPS65912_IRQ_PWRHOLD_R 4 -#define TPS65912_IRQ_HOTDIE 5 -#define TPS65912_IRQ_GPIO1_R 6 -#define TPS65912_IRQ_GPIO1_F 7 -#define TPS65912_IRQ_GPIO2_R 8 -#define TPS65912_IRQ_GPIO2_F 9 -#define TPS65912_IRQ_GPIO3_R 10 -#define TPS65912_IRQ_GPIO3_F 11 -#define TPS65912_IRQ_GPIO4_R 12 -#define TPS65912_IRQ_GPIO4_F 13 -#define TPS65912_IRQ_GPIO5_R 14 -#define TPS65912_IRQ_GPIO5_F 15 -#define TPS65912_IRQ_PGOOD_DCDC1 16 -#define TPS65912_IRQ_PGOOD_DCDC2 17 -#define TPS65912_IRQ_PGOOD_DCDC3 18 -#define TPS65912_IRQ_PGOOD_DCDC4 19 -#define TPS65912_IRQ_PGOOD_LDO1 20 -#define TPS65912_IRQ_PGOOD_LDO2 21 -#define TPS65912_IRQ_PGOOD_LDO3 22 -#define TPS65912_IRQ_PGOOD_LDO4 23 -#define TPS65912_IRQ_PGOOD_LDO5 24 -#define TPS65912_IRQ_PGOOD_LDO6 25 -#define TPS65912_IRQ_PGOOD_LDO7 26 -#define TPS65912_IRQ_PGOOD_LD08 27 -#define TPS65912_IRQ_PGOOD_LDO9 28 -#define TPS65912_IRQ_PGOOD_LDO10 29 - -#define TPS65912_NUM_IRQ 30 - -/* GPIO 1 and 2 Register Definitions */ -#define GPIO_SLEEP_MASK 0x80 -#define GPIO_SLEEP_SHIFT 7 -#define GPIO_DEB_MASK 0x10 -#define GPIO_DEB_SHIFT 4 -#define GPIO_CFG_MASK 0x04 -#define GPIO_CFG_SHIFT 2 -#define GPIO_STS_MASK 0x02 -#define GPIO_STS_SHIFT 1 -#define GPIO_SET_MASK 0x01 -#define GPIO_SET_SHIFT 0 - -/* GPIO 3 Register Definitions */ -#define GPIO3_SLEEP_MASK 0x80 -#define GPIO3_SLEEP_SHIFT 7 -#define GPIO3_SEL_MASK 0x40 -#define GPIO3_SEL_SHIFT 6 -#define GPIO3_ODEN_MASK 0x20 -#define GPIO3_ODEN_SHIFT 5 -#define GPIO3_DEB_MASK 0x10 -#define GPIO3_DEB_SHIFT 4 -#define GPIO3_PDEN_MASK 0x08 -#define GPIO3_PDEN_SHIFT 3 -#define GPIO3_CFG_MASK 0x04 -#define GPIO3_CFG_SHIFT 2 -#define GPIO3_STS_MASK 0x02 -#define GPIO3_STS_SHIFT 1 -#define GPIO3_SET_MASK 0x01 -#define GPIO3_SET_SHIFT 0 - -/* GPIO 4 Register Definitions */ -#define GPIO4_SLEEP_MASK 0x80 -#define GPIO4_SLEEP_SHIFT 7 -#define GPIO4_SEL_MASK 0x40 -#define GPIO4_SEL_SHIFT 6 -#define GPIO4_ODEN_MASK 0x20 -#define GPIO4_ODEN_SHIFT 5 -#define GPIO4_DEB_MASK 0x10 -#define GPIO4_DEB_SHIFT 4 -#define GPIO4_PDEN_MASK 0x08 -#define GPIO4_PDEN_SHIFT 3 -#define GPIO4_CFG_MASK 0x04 -#define GPIO4_CFG_SHIFT 2 -#define GPIO4_STS_MASK 0x02 -#define GPIO4_STS_SHIFT 1 -#define GPIO4_SET_MASK 0x01 -#define GPIO4_SET_SHIFT 0 - -/* Register THERM (0x80) register.RegisterDescription */ -#define THERM_THERM_HD_MASK 0x20 -#define THERM_THERM_HD_SHIFT 5 -#define THERM_THERM_TS_MASK 0x10 -#define THERM_THERM_TS_SHIFT 4 -#define THERM_THERM_HDSEL_MASK 0x0C -#define THERM_THERM_HDSEL_SHIFT 2 -#define THERM_RSVD1_MASK 0x02 -#define THERM_RSVD1_SHIFT 1 -#define THERM_THERM_STATE_MASK 0x01 -#define THERM_THERM_STATE_SHIFT 0 - -/* Register DCDCCTRL1 register.RegisterDescription */ -#define DCDCCTRL_VCON_ENABLE_MASK 0x80 -#define DCDCCTRL_VCON_ENABLE_SHIFT 7 -#define DCDCCTRL_VCON_RANGE1_MASK 0x40 -#define DCDCCTRL_VCON_RANGE1_SHIFT 6 -#define DCDCCTRL_VCON_RANGE0_MASK 0x20 -#define DCDCCTRL_VCON_RANGE0_SHIFT 5 -#define DCDCCTRL_TSTEP2_MASK 0x10 -#define DCDCCTRL_TSTEP2_SHIFT 4 -#define DCDCCTRL_TSTEP1_MASK 0x08 -#define DCDCCTRL_TSTEP1_SHIFT 3 -#define DCDCCTRL_TSTEP0_MASK 0x04 -#define DCDCCTRL_TSTEP0_SHIFT 2 -#define DCDCCTRL_DCDC1_MODE_MASK 0x02 -#define DCDCCTRL_DCDC1_MODE_SHIFT 1 - -/* Register DCDCCTRL2 and DCDCCTRL3 register.RegisterDescription */ -#define DCDCCTRL_TSTEP2_MASK 0x10 -#define DCDCCTRL_TSTEP2_SHIFT 4 -#define DCDCCTRL_TSTEP1_MASK 0x08 -#define DCDCCTRL_TSTEP1_SHIFT 3 -#define DCDCCTRL_TSTEP0_MASK 0x04 -#define DCDCCTRL_TSTEP0_SHIFT 2 -#define DCDCCTRL_DCDC_MODE_MASK 0x02 -#define DCDCCTRL_DCDC_MODE_SHIFT 1 -#define DCDCCTRL_RSVD0_MASK 0x01 -#define DCDCCTRL_RSVD0_SHIFT 0 - -/* Register DCDCCTRL4 register.RegisterDescription */ -#define DCDCCTRL_RAMP_TIME_MASK 0x01 -#define DCDCCTRL_RAMP_TIME_SHIFT 0 - -/* Register DCDCx_AVS */ -#define DCDC_AVS_ENABLE_MASK 0x80 -#define DCDC_AVS_ENABLE_SHIFT 7 -#define DCDC_AVS_ECO_MASK 0x40 -#define DCDC_AVS_ECO_SHIFT 6 - -/* Register DCDCx_LIMIT */ -#define DCDC_LIMIT_RANGE_MASK 0xC0 -#define DCDC_LIMIT_RANGE_SHIFT 6 -#define DCDC_LIMIT_MAX_SEL_MASK 0x3F -#define DCDC_LIMIT_MAX_SEL_SHIFT 0 - -/** - * struct tps65912_board - * Board platform dat may be used to initialize regulators. - */ -struct tps65912_board { - int is_dcdc1_avs; - int is_dcdc2_avs; - int is_dcdc3_avs; - int is_dcdc4_avs; - int irq; - int irq_base; - int gpio_base; - struct regulator_init_data *tps65912_pmic_init_data; -}; - -/** - * struct tps65912 - tps65912 sub-driver chip access routines - */ - -struct tps65912 { - struct device *dev; - /* for read/write acces */ - struct mutex io_mutex; - - /* For device IO interfaces: I2C or SPI */ - void *control_data; - - int (*read)(struct tps65912 *tps65912, u8 reg, int size, void *dest); - int (*write)(struct tps65912 *tps65912, u8 reg, int size, void *src); - - /* Client devices */ - struct tps65912_pmic *pmic; - - /* GPIO Handling */ - struct gpio_chip gpio; - - /* IRQ Handling */ - struct mutex irq_lock; - int chip_irq; - int irq_base; - int irq_num; - u32 irq_mask; -}; - -struct tps65912_platform_data { - int irq; - int irq_base; -}; - -unsigned int tps_chip(void); - -int tps65912_set_bits(struct tps65912 *tps65912, u8 reg, u8 mask); -int tps65912_clear_bits(struct tps65912 *tps65912, u8 reg, u8 mask); -int tps65912_reg_read(struct tps65912 *tps65912, u8 reg); -int tps65912_reg_write(struct tps65912 *tps65912, u8 reg, u8 val); -int tps65912_device_init(struct tps65912 *tps65912); -void tps65912_device_exit(struct tps65912 *tps65912); -int tps65912_irq_init(struct tps65912 *tps65912, int irq, - struct tps65912_platform_data *pdata); -int tps65912_irq_exit(struct tps65912 *tps65912); - -#endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From 796f5692daac4ea47fa5252af742976cd1955f0b Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 25 Jan 2016 09:43:45 -0600 Subject: mfd: tps65912: Add driver for the TPS65912 PMIC This patch adds support for TPS65912 PMIC MFD core. It provides communication through the I2C and SPI interfaces. It contains the following components: - Regulators - GPIO controller Signed-off-by: Andrew F. Davis Signed-off-by: Lee Jones --- include/linux/mfd/tps65912.h | 341 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 341 insertions(+) create mode 100644 include/linux/mfd/tps65912.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h new file mode 100644 index 000000000000..1a603701550e --- /dev/null +++ b/include/linux/mfd/tps65912.h @@ -0,0 +1,341 @@ +/* + * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis + * + * 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. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether expressed or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License version 2 for more details. + * + * Based on the TPS65218 driver and the previous TPS65912 driver by + * Margarita Olaya Cabrera + */ + +#ifndef __LINUX_MFD_TPS65912_H +#define __LINUX_MFD_TPS65912_H + +#include +#include + +/* List of registers for TPS65912 */ +#define TPS65912_DCDC1_CTRL 0x00 +#define TPS65912_DCDC2_CTRL 0x01 +#define TPS65912_DCDC3_CTRL 0x02 +#define TPS65912_DCDC4_CTRL 0x03 +#define TPS65912_DCDC1_OP 0x04 +#define TPS65912_DCDC1_AVS 0x05 +#define TPS65912_DCDC1_LIMIT 0x06 +#define TPS65912_DCDC2_OP 0x07 +#define TPS65912_DCDC2_AVS 0x08 +#define TPS65912_DCDC2_LIMIT 0x09 +#define TPS65912_DCDC3_OP 0x0A +#define TPS65912_DCDC3_AVS 0x0B +#define TPS65912_DCDC3_LIMIT 0x0C +#define TPS65912_DCDC4_OP 0x0D +#define TPS65912_DCDC4_AVS 0x0E +#define TPS65912_DCDC4_LIMIT 0x0F +#define TPS65912_LDO1_OP 0x10 +#define TPS65912_LDO1_AVS 0x11 +#define TPS65912_LDO1_LIMIT 0x12 +#define TPS65912_LDO2_OP 0x13 +#define TPS65912_LDO2_AVS 0x14 +#define TPS65912_LDO2_LIMIT 0x15 +#define TPS65912_LDO3_OP 0x16 +#define TPS65912_LDO3_AVS 0x17 +#define TPS65912_LDO3_LIMIT 0x18 +#define TPS65912_LDO4_OP 0x19 +#define TPS65912_LDO4_AVS 0x1A +#define TPS65912_LDO4_LIMIT 0x1B +#define TPS65912_LDO5 0x1C +#define TPS65912_LDO6 0x1D +#define TPS65912_LDO7 0x1E +#define TPS65912_LDO8 0x1F +#define TPS65912_LDO9 0x20 +#define TPS65912_LDO10 0x21 +#define TPS65912_THRM 0x22 +#define TPS65912_CLK32OUT 0x23 +#define TPS65912_DEVCTRL 0x24 +#define TPS65912_DEVCTRL2 0x25 +#define TPS65912_I2C_SPI_CFG 0x26 +#define TPS65912_KEEP_ON 0x27 +#define TPS65912_KEEP_ON2 0x28 +#define TPS65912_SET_OFF1 0x29 +#define TPS65912_SET_OFF2 0x2A +#define TPS65912_DEF_VOLT 0x2B +#define TPS65912_DEF_VOLT_MAPPING 0x2C +#define TPS65912_DISCHARGE 0x2D +#define TPS65912_DISCHARGE2 0x2E +#define TPS65912_EN1_SET1 0x2F +#define TPS65912_EN1_SET2 0x30 +#define TPS65912_EN2_SET1 0x31 +#define TPS65912_EN2_SET2 0x32 +#define TPS65912_EN3_SET1 0x33 +#define TPS65912_EN3_SET2 0x34 +#define TPS65912_EN4_SET1 0x35 +#define TPS65912_EN4_SET2 0x36 +#define TPS65912_PGOOD 0x37 +#define TPS65912_PGOOD2 0x38 +#define TPS65912_INT_STS 0x39 +#define TPS65912_INT_MSK 0x3A +#define TPS65912_INT_STS2 0x3B +#define TPS65912_INT_MSK2 0x3C +#define TPS65912_INT_STS3 0x3D +#define TPS65912_INT_MSK3 0x3E +#define TPS65912_INT_STS4 0x3F +#define TPS65912_INT_MSK4 0x40 +#define TPS65912_GPIO1 0x41 +#define TPS65912_GPIO2 0x42 +#define TPS65912_GPIO3 0x43 +#define TPS65912_GPIO4 0x44 +#define TPS65912_GPIO5 0x45 +#define TPS65912_VMON 0x46 +#define TPS65912_LEDA_CTRL1 0x47 +#define TPS65912_LEDA_CTRL2 0x48 +#define TPS65912_LEDA_CTRL3 0x49 +#define TPS65912_LEDA_CTRL4 0x4A +#define TPS65912_LEDA_CTRL5 0x4B +#define TPS65912_LEDA_CTRL6 0x4C +#define TPS65912_LEDA_CTRL7 0x4D +#define TPS65912_LEDA_CTRL8 0x4E +#define TPS65912_LEDB_CTRL1 0x4F +#define TPS65912_LEDB_CTRL2 0x50 +#define TPS65912_LEDB_CTRL3 0x51 +#define TPS65912_LEDB_CTRL4 0x52 +#define TPS65912_LEDB_CTRL5 0x53 +#define TPS65912_LEDB_CTRL6 0x54 +#define TPS65912_LEDB_CTRL7 0x55 +#define TPS65912_LEDB_CTRL8 0x56 +#define TPS65912_LEDC_CTRL1 0x57 +#define TPS65912_LEDC_CTRL2 0x58 +#define TPS65912_LEDC_CTRL3 0x59 +#define TPS65912_LEDC_CTRL4 0x5A +#define TPS65912_LEDC_CTRL5 0x5B +#define TPS65912_LEDC_CTRL6 0x5C +#define TPS65912_LEDC_CTRL7 0x5D +#define TPS65912_LEDC_CTRL8 0x5E +#define TPS65912_LED_RAMP_UP_TIME 0x5F +#define TPS65912_LED_RAMP_DOWN_TIME 0x60 +#define TPS65912_LED_SEQ_EN 0x61 +#define TPS65912_LOADSWITCH 0x62 +#define TPS65912_SPARE 0x63 +#define TPS65912_VERNUM 0x64 +#define TPS6591X_MAX_REGISTER 0x64 + +/* INT_STS Register field definitions */ +#define TPS65912_INT_STS_PWRHOLD_F BIT(0) +#define TPS65912_INT_STS_VMON BIT(1) +#define TPS65912_INT_STS_PWRON BIT(2) +#define TPS65912_INT_STS_PWRON_LP BIT(3) +#define TPS65912_INT_STS_PWRHOLD_R BIT(4) +#define TPS65912_INT_STS_HOTDIE BIT(5) +#define TPS65912_INT_STS_GPIO1_R BIT(6) +#define TPS65912_INT_STS_GPIO1_F BIT(7) + +/* INT_STS Register field definitions */ +#define TPS65912_INT_STS2_GPIO2_R BIT(0) +#define TPS65912_INT_STS2_GPIO2_F BIT(1) +#define TPS65912_INT_STS2_GPIO3_R BIT(2) +#define TPS65912_INT_STS2_GPIO3_F BIT(3) +#define TPS65912_INT_STS2_GPIO4_R BIT(4) +#define TPS65912_INT_STS2_GPIO4_F BIT(5) +#define TPS65912_INT_STS2_GPIO5_R BIT(6) +#define TPS65912_INT_STS2_GPIO5_F BIT(7) + +/* INT_STS Register field definitions */ +#define TPS65912_INT_STS3_PGOOD_DCDC1 BIT(0) +#define TPS65912_INT_STS3_PGOOD_DCDC2 BIT(1) +#define TPS65912_INT_STS3_PGOOD_DCDC3 BIT(2) +#define TPS65912_INT_STS3_PGOOD_DCDC4 BIT(3) +#define TPS65912_INT_STS3_PGOOD_LDO1 BIT(4) +#define TPS65912_INT_STS3_PGOOD_LDO2 BIT(5) +#define TPS65912_INT_STS3_PGOOD_LDO3 BIT(6) +#define TPS65912_INT_STS3_PGOOD_LDO4 BIT(7) + +/* INT_STS Register field definitions */ +#define TPS65912_INT_STS4_PGOOD_LDO5 BIT(0) +#define TPS65912_INT_STS4_PGOOD_LDO6 BIT(1) +#define TPS65912_INT_STS4_PGOOD_LDO7 BIT(2) +#define TPS65912_INT_STS4_PGOOD_LDO8 BIT(3) +#define TPS65912_INT_STS4_PGOOD_LDO9 BIT(4) +#define TPS65912_INT_STS4_PGOOD_LDO10 BIT(5) + +/* GPIO 1 and 2 Register field definitions */ +#define GPIO_SLEEP_MASK 0x80 +#define GPIO_SLEEP_SHIFT 7 +#define GPIO_DEB_MASK 0x10 +#define GPIO_DEB_SHIFT 4 +#define GPIO_CFG_MASK 0x04 +#define GPIO_CFG_SHIFT 2 +#define GPIO_STS_MASK 0x02 +#define GPIO_STS_SHIFT 1 +#define GPIO_SET_MASK 0x01 +#define GPIO_SET_SHIFT 0 + +/* GPIO 3 Register field definitions */ +#define GPIO3_SLEEP_MASK 0x80 +#define GPIO3_SLEEP_SHIFT 7 +#define GPIO3_SEL_MASK 0x40 +#define GPIO3_SEL_SHIFT 6 +#define GPIO3_ODEN_MASK 0x20 +#define GPIO3_ODEN_SHIFT 5 +#define GPIO3_DEB_MASK 0x10 +#define GPIO3_DEB_SHIFT 4 +#define GPIO3_PDEN_MASK 0x08 +#define GPIO3_PDEN_SHIFT 3 +#define GPIO3_CFG_MASK 0x04 +#define GPIO3_CFG_SHIFT 2 +#define GPIO3_STS_MASK 0x02 +#define GPIO3_STS_SHIFT 1 +#define GPIO3_SET_MASK 0x01 +#define GPIO3_SET_SHIFT 0 + +/* GPIO 4 Register field definitions */ +#define GPIO4_SLEEP_MASK 0x80 +#define GPIO4_SLEEP_SHIFT 7 +#define GPIO4_SEL_MASK 0x40 +#define GPIO4_SEL_SHIFT 6 +#define GPIO4_ODEN_MASK 0x20 +#define GPIO4_ODEN_SHIFT 5 +#define GPIO4_DEB_MASK 0x10 +#define GPIO4_DEB_SHIFT 4 +#define GPIO4_PDEN_MASK 0x08 +#define GPIO4_PDEN_SHIFT 3 +#define GPIO4_CFG_MASK 0x04 +#define GPIO4_CFG_SHIFT 2 +#define GPIO4_STS_MASK 0x02 +#define GPIO4_STS_SHIFT 1 +#define GPIO4_SET_MASK 0x01 +#define GPIO4_SET_SHIFT 0 + +/* Register THERM (0x80) register.RegisterDescription */ +#define THERM_THERM_HD_MASK 0x20 +#define THERM_THERM_HD_SHIFT 5 +#define THERM_THERM_TS_MASK 0x10 +#define THERM_THERM_TS_SHIFT 4 +#define THERM_THERM_HDSEL_MASK 0x0C +#define THERM_THERM_HDSEL_SHIFT 2 +#define THERM_RSVD1_MASK 0x02 +#define THERM_RSVD1_SHIFT 1 +#define THERM_THERM_STATE_MASK 0x01 +#define THERM_THERM_STATE_SHIFT 0 + +/* Register DCDCCTRL1 register.RegisterDescription */ +#define DCDCCTRL_VCON_ENABLE_MASK 0x80 +#define DCDCCTRL_VCON_ENABLE_SHIFT 7 +#define DCDCCTRL_VCON_RANGE1_MASK 0x40 +#define DCDCCTRL_VCON_RANGE1_SHIFT 6 +#define DCDCCTRL_VCON_RANGE0_MASK 0x20 +#define DCDCCTRL_VCON_RANGE0_SHIFT 5 +#define DCDCCTRL_TSTEP2_MASK 0x10 +#define DCDCCTRL_TSTEP2_SHIFT 4 +#define DCDCCTRL_TSTEP1_MASK 0x08 +#define DCDCCTRL_TSTEP1_SHIFT 3 +#define DCDCCTRL_TSTEP0_MASK 0x04 +#define DCDCCTRL_TSTEP0_SHIFT 2 +#define DCDCCTRL_DCDC1_MODE_MASK 0x02 +#define DCDCCTRL_DCDC1_MODE_SHIFT 1 + +/* Register DCDCCTRL2 and DCDCCTRL3 register.RegisterDescription */ +#define DCDCCTRL_TSTEP2_MASK 0x10 +#define DCDCCTRL_TSTEP2_SHIFT 4 +#define DCDCCTRL_TSTEP1_MASK 0x08 +#define DCDCCTRL_TSTEP1_SHIFT 3 +#define DCDCCTRL_TSTEP0_MASK 0x04 +#define DCDCCTRL_TSTEP0_SHIFT 2 +#define DCDCCTRL_DCDC_MODE_MASK 0x02 +#define DCDCCTRL_DCDC_MODE_SHIFT 1 +#define DCDCCTRL_RSVD0_MASK 0x01 +#define DCDCCTRL_RSVD0_SHIFT 0 + +/* Register DCDCCTRL4 register.RegisterDescription */ +#define DCDCCTRL_RAMP_TIME_MASK 0x01 +#define DCDCCTRL_RAMP_TIME_SHIFT 0 + +/* Register DCDCx_AVS */ +#define DCDC_AVS_ENABLE_MASK 0x80 +#define DCDC_AVS_ENABLE_SHIFT 7 +#define DCDC_AVS_ECO_MASK 0x40 +#define DCDC_AVS_ECO_SHIFT 6 + +/* Register DCDCx_LIMIT */ +#define DCDC_LIMIT_RANGE_MASK 0xC0 +#define DCDC_LIMIT_RANGE_SHIFT 6 +#define DCDC_LIMIT_MAX_SEL_MASK 0x3F +#define DCDC_LIMIT_MAX_SEL_SHIFT 0 + +/* Define the TPS65912 IRQ numbers */ +enum tps65912_irqs { + /* INT_STS registers */ + TPS65912_IRQ_PWRHOLD_F, + TPS65912_IRQ_VMON, + TPS65912_IRQ_PWRON, + TPS65912_IRQ_PWRON_LP, + TPS65912_IRQ_PWRHOLD_R, + TPS65912_IRQ_HOTDIE, + TPS65912_IRQ_GPIO1_R, + TPS65912_IRQ_GPIO1_F, + /* INT_STS2 registers */ + TPS65912_IRQ_GPIO2_R, + TPS65912_IRQ_GPIO2_F, + TPS65912_IRQ_GPIO3_R, + TPS65912_IRQ_GPIO3_F, + TPS65912_IRQ_GPIO4_R, + TPS65912_IRQ_GPIO4_F, + TPS65912_IRQ_GPIO5_R, + TPS65912_IRQ_GPIO5_F, + /* INT_STS3 registers */ + TPS65912_IRQ_PGOOD_DCDC1, + TPS65912_IRQ_PGOOD_DCDC2, + TPS65912_IRQ_PGOOD_DCDC3, + TPS65912_IRQ_PGOOD_DCDC4, + TPS65912_IRQ_PGOOD_LDO1, + TPS65912_IRQ_PGOOD_LDO2, + TPS65912_IRQ_PGOOD_LDO3, + TPS65912_IRQ_PGOOD_LDO4, + /* INT_STS4 registers */ + TPS65912_IRQ_PGOOD_LDO5, + TPS65912_IRQ_PGOOD_LDO6, + TPS65912_IRQ_PGOOD_LDO7, + TPS65912_IRQ_PGOOD_LDO8, + TPS65912_IRQ_PGOOD_LDO9, + TPS65912_IRQ_PGOOD_LDO10, +}; + +/* + * struct tps65912 - state holder for the tps65912 driver + * + * Device data may be used to access the TPS65912 chip + */ +struct tps65912 { + struct device *dev; + struct regmap *regmap; + + /* IRQ Data */ + int irq; + struct regmap_irq_chip_data *irq_data; +}; + +static const struct regmap_range tps65912_yes_ranges[] = { + regmap_reg_range(TPS65912_INT_STS, TPS65912_GPIO5), +}; + +static const struct regmap_access_table tps65912_volatile_table = { + .yes_ranges = tps65912_yes_ranges, + .n_yes_ranges = ARRAY_SIZE(tps65912_yes_ranges), +}; + +static const struct regmap_config tps65912_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .cache_type = REGCACHE_RBTREE, + .volatile_table = &tps65912_volatile_table, +}; + +int tps65912_device_init(struct tps65912 *tps); +int tps65912_device_exit(struct tps65912 *tps); + +#endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From 795bb1c00dd338aa0d12f9a7f1f4776fb3160416 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 8 Feb 2016 13:14:59 +0100 Subject: net: bulk free infrastructure for NAPI context, use napi_consume_skb Discovered that network stack were hitting the kmem_cache/SLUB slowpath when freeing SKBs. Doing bulk free with kmem_cache_free_bulk can speedup this slowpath. NAPI context is a bit special, lets take advantage of that for bulk free'ing SKBs. In NAPI context we are running in softirq, which gives us certain protection. A softirq can run on several CPUs at once. BUT the important part is a softirq will never preempt another softirq running on the same CPU. This gives us the opportunity to access per-cpu variables in softirq context. Extend napi_alloc_cache (before only contained page_frag_cache) to be a struct with a small array based stack for holding SKBs. Introduce a SKB defer and flush API for accessing this. Introduce napi_consume_skb() as replacement for e.g. dev_consume_skb_any() when running in NAPI context. A small trick to handle/detect if we are called from netpoll is to see if budget is 0. In that case, we need to invoke dev_consume_skb_irq(). Joint work with Alexander Duyck. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a8fc2220e8ce..b56c0103fa15 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2404,6 +2404,9 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, { return __napi_alloc_skb(napi, length, GFP_ATOMIC); } +void napi_consume_skb(struct sk_buff *skb, int budget); + +void __kfree_skb_flush(void); /** * __dev_alloc_pages - allocate page for network Rx -- cgit v1.2.3 From 15fad714be86eab13e7568fecaf475b2a9730d3e Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 8 Feb 2016 13:15:04 +0100 Subject: net: bulk free SKBs that were delay free'ed due to IRQ context The network stack defers SKBs free, in-case free happens in IRQ or when IRQs are disabled. This happens in __dev_kfree_skb_irq() that writes SKBs that were free'ed during IRQ to the softirq completion queue (softnet_data.completion_queue). These SKBs are naturally delayed, and cleaned up during NET_TX_SOFTIRQ in function net_tx_action(). Take advantage of this a use the skb defer and flush API, as we are already in softirq context. For modern drivers this rarely happens. Although most drivers do call dev_kfree_skb_any(), which detects the situation and calls __dev_kfree_skb_irq() when needed. This due to netpoll can call from IRQ context. Signed-off-by: Alexander Duyck Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b56c0103fa15..6ec86f1a2ed9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2407,6 +2407,7 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, void napi_consume_skb(struct sk_buff *skb, int budget); void __kfree_skb_flush(void); +void __kfree_skb_defer(struct sk_buff *skb); /** * __dev_alloc_pages - allocate page for network Rx -- cgit v1.2.3 From afbc4f312b5e6e87fcd383eb6764e09f1324c78e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 9 Feb 2016 13:21:06 +0100 Subject: gpio: move sysfs mock device to the gpio_device Since gpio_device is the struct that survives if the backing gpio_chip is removed, move the sysfs mock device to this state container so it becomes part of the dangling state of the GPIO device on removal. Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f3f1dbd43c9b..4db64ab534ef 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -24,7 +24,6 @@ struct gpio_device; * @label: for diagnostics * @gpiodev: the internal state holder, opaque struct * @parent: optional parent device providing the GPIOs - * @cdev: class device used by sysfs interface (may be NULL) * @owner: helps prevent removal of modules exporting active GPIOs * @data: per-instance data assigned by the driver * @request: optional hook for chip-specific activation, such as @@ -110,7 +109,6 @@ struct gpio_chip { const char *label; struct gpio_device *gpiodev; struct device *parent; - struct device *cdev; struct module *owner; void *data; -- cgit v1.2.3 From 1c3cdb186172ee3be24005a7ff0e849bc17b67b8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 9 Feb 2016 13:51:59 +0100 Subject: gpio: move descriptors into gpio_device We need gpio_device to hold the descriptors so that they can be lifecycled with the struct gpio_device held from userspace. Move the descriptor array into gpio_device. Also rename it from "desc" (singularis) to "descs" (pluralis) to reflect the fact that it is an array. Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 4db64ab534ef..bfc842c2fc57 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -52,7 +52,6 @@ struct gpio_device; * get rid of the static GPIO number space in the long run. * @ngpio: the number of GPIOs handled by this controller; the last GPIO * handled is (base + ngpio - 1). - * @desc: array of ngpio descriptors. Private. * @names: if set, must be an array of strings to use as alternative * names for the GPIOs in this chip. Any entry in the array * may be NULL if there is no alias for the GPIO, however the @@ -140,7 +139,6 @@ struct gpio_chip { struct gpio_chip *chip); int base; u16 ngpio; - struct gpio_desc *desc; const char *const *names; bool can_sleep; bool irq_not_threaded; -- cgit v1.2.3 From 6cee3821e4e4bd6e6cdf0870b6c72d455460bd39 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 11 Feb 2016 20:16:45 +0100 Subject: gpio/pinctrl: sunxi: stop poking around in private vars This kind of hacks disturbs the refactoring of the gpiolib. The descriptor table belongs to the gpiolib, if we want to know something about something in it, use or define the proper accessor functions. Let's add this gpiochip_lins_is_irq() to do what the sunxi driver is trying at so we can privatize the descriptors properly. Cc: Maxime Ripard Cc: Chen-Yu Tsai Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index bfc842c2fc57..41c6144c473b 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -208,6 +208,7 @@ extern struct gpio_chip *gpiochip_find(void *data, /* lock/unlock as IRQ */ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset); void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); +bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); /* get driver data */ static inline void *gpiochip_get_data(struct gpio_chip *chip) -- cgit v1.2.3 From e1379b56e9e88653fcb58cbaa71cd6b1cc304918 Mon Sep 17 00:00:00 2001 From: Cory Tusar Date: Wed, 10 Feb 2016 14:32:07 -0500 Subject: misc: eeprom_93xx46: Add quirks to support Atmel AT93C46D device. Atmel devices in this family have some quirks not found in other similar chips - they do not support a sequential read of the entire EEPROM contents, and the control word sent at the start of each operation varies in bit length. This commit adds quirk support to the driver and modifies the read implementation to support non-sequential reads for consistency with other misc/eeprom drivers. Tested on a custom Freescale VF610-based platform, with an AT93C46D device attached via dspi2. The spi-gpio driver was used to allow the necessary non-byte-sized transfers. Signed-off-by: Cory Tusar Tested-by: Chris Healy Reviewed-by: Vladimir Zapolskiy Signed-off-by: Greg Kroah-Hartman --- include/linux/eeprom_93xx46.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index 06791811e49d..92fa4c37ac1f 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -9,6 +9,12 @@ struct eeprom_93xx46_platform_data { #define EE_ADDR16 0x02 /* 16 bit addr. cfg */ #define EE_READONLY 0x08 /* forbid writing */ + unsigned int quirks; +/* Single word read transfers only; no sequential read. */ +#define EEPROM_93XX46_QUIRK_SINGLE_WORD_READ (1 << 0) +/* Instructions such as EWEN are (addrlen + 2) in length. */ +#define EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH (1 << 1) + /* * optional hooks to control additional logic * before and after spi transfer. -- cgit v1.2.3 From 3ca9b1ac28398c6fe0bed335d2d71a35e1c5f7c9 Mon Sep 17 00:00:00 2001 From: Cory Tusar Date: Wed, 10 Feb 2016 14:32:08 -0500 Subject: misc: eeprom_93xx46: Add support for a GPIO 'select' line. This commit adds support to the eeprom_93x46 driver allowing a GPIO line to function as a 'select' or 'enable' signal prior to accessing the EEPROM. Signed-off-by: Cory Tusar Tested-by: Chris Healy Reviewed-by: Vladimir Zapolskiy Signed-off-by: Greg Kroah-Hartman --- include/linux/eeprom_93xx46.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index 92fa4c37ac1f..885f587a3555 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -3,6 +3,8 @@ * platform description for 93xx46 EEPROMs. */ +struct gpio_desc; + struct eeprom_93xx46_platform_data { unsigned char flags; #define EE_ADDR8 0x01 /* 8 bit addr. cfg */ @@ -21,4 +23,5 @@ struct eeprom_93xx46_platform_data { */ void (*prepare)(void *); void (*finish)(void *); + struct gpio_desc *select; }; -- cgit v1.2.3 From 4fd411514291ae75053003e33a6a4a56f97467d0 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 12 Feb 2016 10:02:42 +0800 Subject: mfd: axp20x: Split the driver into core and i2c bits The axp20x driver assumes the device is i2c based. This is not the case with later chips, which use a proprietary 2 wire serial bus by Allwinner called "Reduced Serial Bus". This patch follows the example of mfd/wm831x and splits it into an interface independent core, and an i2c specific glue layer. MFD_AXP20X and the new MFD_AXP20X_I2C are changed to tristate symbols, allowing the driver to be built as modules. Whitespace and other style errors in the moved i2c specific code have been fixed. Included but unused header files are removed as well. Signed-off-by: Chen-Yu Tsai Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index b24c771cebd5..00697c6ad8b0 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -396,7 +396,7 @@ enum axp288_irqs { struct axp20x_dev { struct device *dev; - struct i2c_client *i2c_client; + int irq; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irqc; long variant; @@ -462,4 +462,35 @@ static inline int axp20x_read_variable_width(struct regmap *regmap, return result; } +/** + * axp20x_match_device(): Setup axp20x variant related fields + * + * @axp20x: axp20x device to setup (.dev field must be set) + * @dev: device associated with this axp20x device + * + * This lets the axp20x core configure the mfd cells and register maps + * for later use. + */ +int axp20x_match_device(struct axp20x_dev *axp20x); + +/** + * axp20x_device_probe(): Probe a configured axp20x device + * + * @axp20x: axp20x device to probe (must be configured) + * + * This function lets the axp20x core register the axp20x mfd devices + * and irqchip. The axp20x device passed in must be fully configured + * with axp20x_match_device, its irq set, and regmap created. + */ +int axp20x_device_probe(struct axp20x_dev *axp20x); + +/** + * axp20x_device_probe(): Remove a axp20x device + * + * @axp20x: axp20x device to remove + * + * This tells the axp20x core to remove the associated mfd devices + */ +int axp20x_device_remove(struct axp20x_dev *axp20x); + #endif /* __LINUX_MFD_AXP20X_H */ -- cgit v1.2.3 From 02071f0f797c989b342f46fbdf472ddb1c2cdee9 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 12 Feb 2016 10:02:44 +0800 Subject: mfd: axp20x: Add support for RSB based AXP223 PMIC The AXP223 is a new PMIC commonly paired with Allwinner A23/A33 SoCs. It is functionally identical to AXP221; only the regulator default voltage/status and the external host interface are different. Signed-off-by: Chen-Yu Tsai Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 00697c6ad8b0..d82e7d51372b 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -18,6 +18,7 @@ enum { AXP202_ID, AXP209_ID, AXP221_ID, + AXP223_ID, AXP288_ID, NR_AXP20X_VARIANTS, }; -- cgit v1.2.3 From 179bc67f69b6cb53ad68cfdec5a917c2a2248355 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:48:04 +0000 Subject: net: local checksum offload for encapsulation The arithmetic properties of the ones-complement checksum mean that a correctly checksummed inner packet, including its checksum, has a ones complement sum depending only on whatever value was used to initialise the checksum field before checksumming (in the case of TCP and UDP, this is the ones complement sum of the pseudo header, complemented). Consequently, if we are going to offload the inner checksum with CHECKSUM_PARTIAL, we can compute the outer checksum based only on the packed data not covered by the inner checksum, and the initial value of the inner checksum field. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6ec86f1a2ed9..cf906d1ce8a7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3702,5 +3702,29 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) return hdr_len + skb_gso_transport_seglen(skb); } +/* Local Checksum Offload. + * Compute outer checksum based on the assumption that the + * inner checksum will be offloaded later. + * Fill in outer checksum adjustment (e.g. with sum of outer + * pseudo-header) before calling. + * Also ensure that inner checksum is in linear data area. + */ +static inline __wsum lco_csum(struct sk_buff *skb) +{ + char *inner_csum_field; + __wsum csum; + + /* Start with complement of inner checksum adjustment */ + inner_csum_field = skb->data + skb_checksum_start_offset(skb) + + skb->csum_offset; + csum = ~csum_unfold(*(__force __sum16 *)inner_csum_field); + /* Add in checksum of our headers (incl. outer checksum + * adjustment filled in by caller) + */ + csum = skb_checksum(skb, 0, skb_checksum_start_offset(skb), csum); + /* The result is the checksum from skb->data to end of packet */ + return csum; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From e8ae7b000e64cf76283c72cae5e3ecd246618ef4 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:03:37 +0000 Subject: Documentation/networking: add checksum-offloads.txt to explain LCO Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf906d1ce8a7..39206751463e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3705,6 +3705,8 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. + * See Documentation/networking/checksum-offloads.txt for + * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. -- cgit v1.2.3 From 95a001f22b1c5717eafd500a43832249ddd93662 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 1 Feb 2016 23:02:48 +0100 Subject: mtd: map: fix .set_vpp() documentation As of commit 876fe76d793d03077eb61ba3afab4a383f46c554 "mtd: maps: physmap: Add reference counter to set_vpp()" the comment in the header file is incorrect and misleading. Fix it up. Cc: Russell King Cc: Paul Parsons Fixes: 876fe76d793d ("mtd: maps: physmap: Add reference counter to set_vpp()") Signed-off-by: Linus Walleij Signed-off-by: Brian Norris --- include/linux/mtd/map.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 58f3ba709ade..5e0eb7ccabd4 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -240,8 +240,11 @@ struct map_info { If there is no cache to care about this can be set to NULL. */ void (*inval_cache)(struct map_info *, unsigned long, ssize_t); - /* set_vpp() must handle being reentered -- enable, enable, disable - must leave it enabled. */ + /* This will be called with 1 as parameter when the first map user + * needs VPP, and called with 0 when the last user exits. The map + * core maintains a reference counter, and assumes that VPP is a + * global resource applying to all mapped flash chips on the system. + */ void (*set_vpp)(struct map_info *, int); unsigned long pfow_base; -- cgit v1.2.3 From b37d83a6a41499d582b8faedff1913ec75d9e70b Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 12 Feb 2016 16:40:13 +0200 Subject: usb: Parse the new USB 3.1 SuperSpeedPlus Isoc endpoint companion descriptor USB 3.1 devices can return a new SuperSpeedPlus isoc endpoint companion descriptor for a isochronous endpoint that requires more than 48K bytes per Service Interval. The new descriptor immediately follows the old USB 3.0 SuperSpeed Endpoint Companion and will provide a new BytesPerInterval value. It is parsed and stored in struct usb_host_endpoint with the other endpoint related descriptors, and should be used by USB3.1 capable hosts to reserve bus time in the schedule. Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index dc0ea0de8a81..8fc881af8735 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -50,6 +50,7 @@ struct ep_device; * struct usb_host_endpoint - host-side endpoint descriptor and queue * @desc: descriptor for this endpoint, wMaxPacketSize in native byteorder * @ss_ep_comp: SuperSpeed companion descriptor for this endpoint + * @ssp_isoc_ep_comp: SuperSpeedPlus isoc companion descriptor for this endpoint * @urb_list: urbs queued to this endpoint; maintained by usbcore * @hcpriv: for use by HCD; typically holds hardware dma queue head (QH) * with one or more transfer descriptors (TDs) per urb @@ -65,6 +66,7 @@ struct ep_device; struct usb_host_endpoint { struct usb_endpoint_descriptor desc; struct usb_ss_ep_comp_descriptor ss_ep_comp; + struct usb_ssp_isoc_ep_comp_descriptor ssp_isoc_ep_comp; struct list_head urb_list; void *hcpriv; struct ep_device *ep_dev; /* For sysfs info */ -- cgit v1.2.3 From faee822c5a7ab99de25cd34fcde3f8d37b6b9923 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 12 Feb 2016 16:40:14 +0200 Subject: usb: Add USB 3.1 Precision time measurement capability descriptor support USB 3.1 devices that support precision time measurement have an additional PTM cabaility descriptor as part of the full BOS descriptor Look for this descriptor while parsing the BOS descriptor, and store it in struct usb_hub_bos if it exists. Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 8fc881af8735..6a9a0c28415d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -332,6 +332,7 @@ struct usb_host_bos { struct usb_ss_cap_descriptor *ss_cap; struct usb_ssp_cap_descriptor *ssp_cap; struct usb_ss_container_id_descriptor *ss_id; + struct usb_ptm_cap_descriptor *ptm_cap; }; int __usb_get_extra_descriptor(char *buffer, unsigned size, -- cgit v1.2.3 From 64024ac7bb82c41265e7ba08235591d9a2709dfc Mon Sep 17 00:00:00 2001 From: Jonathan Tinkham Date: Tue, 2 Feb 2016 23:03:45 -0700 Subject: power: bq24735-charger: add 'ti,external-control' option Implement an 'ti,external-control' option for when the charger shouldn't be configured by the host. Signed-off-by: Jonathan Tinkham Signed-off-by: Sebastian Reichel --- include/linux/power/bq24735-charger.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power/bq24735-charger.h b/include/linux/power/bq24735-charger.h index f536164a6069..6b750c1a45fa 100644 --- a/include/linux/power/bq24735-charger.h +++ b/include/linux/power/bq24735-charger.h @@ -32,6 +32,8 @@ struct bq24735_platform { int status_gpio_active_low; bool status_gpio_valid; + bool ext_control; + char **supplied_to; size_t num_supplicants; }; -- cgit v1.2.3 From 6659b55dae09b2042d8cdd0f4576502c3e81957c Mon Sep 17 00:00:00 2001 From: Benson Leung Date: Fri, 12 Feb 2016 13:56:59 +0100 Subject: power_supply: Add types for USB Type C and PD chargers This adds power supply types for USB chargers defined in the USB Type-C Specification 1.1 and in the USB Power Delivery Specification Revision 2.0 V1.1. The following are added : POWER_SUPPLY_TYPE_USB_TYPE_C, /* Type C Port */ POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ Signed-off-by: Benson Leung [tomeu: remove the mention to Type C from the comments] Signed-off-by: Tomeu Vizoso Reviewed-by: Alec Berg Reviewed-by: Vincent Palatin Reviewed-by: Todd Broch Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index ef9f1592185d..751061790626 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -163,6 +163,9 @@ enum power_supply_type { POWER_SUPPLY_TYPE_USB_DCP, /* Dedicated Charging Port */ POWER_SUPPLY_TYPE_USB_CDP, /* Charging Downstream Port */ POWER_SUPPLY_TYPE_USB_ACA, /* Accessory Charger Adapters */ + POWER_SUPPLY_TYPE_USB_TYPE_C, /* Type C Port */ + POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ + POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ }; enum power_supply_notifier_events { -- cgit v1.2.3 From 800c3a0e683601c4ede490e8525852e63b0f6615 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 10 Feb 2016 14:29:50 +0530 Subject: regmap: irq: add devm apis for regmap_{add,del}_irq_chip Add device managed APIs for regmap_add_irq_chip() and regmap_del_irq_chip() so that it can be managed by device framework for freeing it. This helps on following: 1. Maintaining the sequence of resource allocation and deallocation regmap_add_irq_chip(&d); devm_requested_threaded_irq(virq) On free path: regmap_del_irq_chip(d); and then removing the irq registration. On this case, regmap irq is deleted before the irq is free. This force to use normal irq registration. By using devm apis, the sequence can be maintain properly: devm_regmap_add_irq_chip(&d); devm_requested_threaded_irq(virq); and resource deallocation will be done in reverse order by device framework. 2. No need to delete the regmap_irq_chip in error path or remove callback and hence there is less code on this path. Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 18394343f489..de428962bfe6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -868,6 +868,14 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); + +int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq, + int irq_flags, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); +void devm_regmap_del_irq_chip(struct device *dev, int irq, + struct regmap_irq_chip_data *data); + int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data); int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq); struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data); -- cgit v1.2.3 From fc5cbf0c94b6f7fd62fdddff892207290510945d Mon Sep 17 00:00:00 2001 From: Axel Haslam Date: Mon, 15 Feb 2016 11:10:51 +0100 Subject: PM / Domains: Support for multiple states Some hardware (eg. OMAP), has the ability to enter different low power modes for a given power domain. This allows for more fine grained control over the power state of the platform. As a typical example, some registers of the hardware may be implemented with retention flip-flops and be able to retain their state at lower voltages allowing for faster on/off latencies and an increased window of opportunity to enter an intermediate low power state other than "off" When trying to set a power domain to off, the genpd governor will choose the deepest state that will respect the qos constraints of all the devices and sub-domains on the power domain. The state chosen by the governor is saved in the "state_idx" field of the generic_pm_domain structure and shall be used by the power_off and power_on callbacks to perform the necessary actions to set the power domain into (and out of) the state indicated by state_idx. States must be declared in ascending order from shallowest to deepest, deepest meaning the state which takes longer to enter and exit. For platforms that don't declare any states, a single a single "off" state is used. Once all platforms are converted to use the state array, the legacy on/off latencies will be removed. [ Lina: Modified genpd state initialization and remove use of save_state_latency_ns in genpd timing data ] Suggested-by: Kevin Hilman Signed-off-by: Lina Iyer Signed-off-by: Axel Haslam Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index db21d3995f7e..1726c4ac6529 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -19,6 +19,8 @@ /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ +#define GENPD_MAX_NUM_STATES 8 /* Number of possible low power states */ + enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ GPD_STATE_POWER_OFF, /* PM domain is off */ @@ -37,6 +39,11 @@ struct gpd_dev_ops { bool (*active_wakeup)(struct device *dev); }; +struct genpd_power_state { + s64 power_off_latency_ns; + s64 power_on_latency_ns; +}; + struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ @@ -66,6 +73,10 @@ struct generic_pm_domain { void (*detach_dev)(struct generic_pm_domain *domain, struct device *dev); unsigned int flags; /* Bit field of configs for genpd */ + struct genpd_power_state states[GENPD_MAX_NUM_STATES]; + unsigned int state_count; /* number of states */ + unsigned int state_idx; /* state that genpd will go to when off */ + }; static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) -- cgit v1.2.3 From 90e63452ac3a42c9ff10b12880429e8592cf39ec Mon Sep 17 00:00:00 2001 From: Axel Haslam Date: Mon, 15 Feb 2016 11:10:53 +0100 Subject: PM / Domains: remove old power on/off latencies Now that all known users have been converted to use state latencies, we can remove the latency field in the generic_pm_domain structure. Signed-off-by: Axel Haslam Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1726c4ac6529..49cd8890b873 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -61,9 +61,7 @@ struct generic_pm_domain { unsigned int prepared_count; /* Suspend counter of prepared devices */ bool suspend_power_off; /* Power status before system suspend */ int (*power_off)(struct generic_pm_domain *domain); - s64 power_off_latency_ns; int (*power_on)(struct generic_pm_domain *domain); - s64 power_on_latency_ns; struct gpd_dev_ops dev_ops; s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ bool max_off_time_changed; -- cgit v1.2.3 From 20ec3e39fc12cf3a331ee73eb01d52bddcdd2fa4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 11 Feb 2016 11:03:06 +0100 Subject: gpio: move the pin ranges into gpio_device Instead of keeping this reference to the pin ranges in the client driver-supplied gpio_chip, move it to the internal gpio_device as the drivers have no need to inspect this. Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 41c6144c473b..e2a934ce3e64 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -181,15 +181,6 @@ struct gpio_chip { int (*of_xlate)(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags); #endif -#ifdef CONFIG_PINCTRL - /* - * If CONFIG_PINCTRL is enabled, then gpio controllers can optionally - * describe the actual pin range which they serve in an SoC. This - * information would be used by pinctrl subsystem to configure - * corresponding pins for gpio usage. - */ - struct list_head pin_ranges; -#endif }; extern const char *gpiochip_is_requested(struct gpio_chip *chip, -- cgit v1.2.3 From 43c54ecade400cf6ca8203f960b525fbe5b73a13 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 11 Feb 2016 11:37:48 +0100 Subject: gpio: move the subdriver data pointer into gpio_device We move to manage this pointer under gpiolib control rather than leave it in the subdevice's gpio_chip. We can not NULL it after gpiochip_remove so at to keep things tight. Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index e2a934ce3e64..b92ab9efdb69 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -25,7 +25,6 @@ struct gpio_device; * @gpiodev: the internal state holder, opaque struct * @parent: optional parent device providing the GPIOs * @owner: helps prevent removal of modules exporting active GPIOs - * @data: per-instance data assigned by the driver * @request: optional hook for chip-specific activation, such as * enabling module power and clock; may sleep * @free: optional hook for chip-specific deactivation, such as @@ -109,7 +108,6 @@ struct gpio_chip { struct gpio_device *gpiodev; struct device *parent; struct module *owner; - void *data; int (*request)(struct gpio_chip *chip, unsigned offset); @@ -202,10 +200,7 @@ void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); /* get driver data */ -static inline void *gpiochip_get_data(struct gpio_chip *chip) -{ - return chip->data; -} +void *gpiochip_get_data(struct gpio_chip *chip); struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc); -- cgit v1.2.3 From 1e9877902dc7e11d2be038371c6fbf2dfcd469d7 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:01:54 -0800 Subject: mm/gup: Introduce get_user_pages_remote() For protection keys, we need to understand whether protections should be enforced in software or not. In general, we enforce protections when working on our own task, but not when on others. We call these "current" and "remote" operations. This patch introduces a new get_user_pages() variant: get_user_pages_remote() Which is a replacement for when get_user_pages() is called on non-current tsk/mm. We also introduce a new gup flag: FOLL_REMOTE which can be used for the "__" gup variants to get this new behavior. The uprobes is_trap_at_addr() location holds mmap_sem and calls get_user_pages(current->mm) on an instruction address. This makes it a pretty unique gup caller. Being an instruction access and also really originating from the kernel (vs. the app), I opted to consider this a 'remote' access where protection keys will not be enforced. Without protection keys, this patch should not change any behavior. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Naoya Horiguchi Cc: Peter Zijlstra Cc: Rik van Riel Cc: Srikar Dronamraju Cc: Vlastimil Babka Cc: jack@suse.cz Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210154.3F0E51EA@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b1d4b8c7f7cd..faf3b709eead 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1225,6 +1225,10 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int foll_flags, struct page **pages, struct vm_area_struct **vmas, int *nonblocking); +long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, @@ -2170,6 +2174,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_MLOCK 0x1000 /* lock present pages */ +#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.2.3 From cde70140fed8429acf7a14e2e2cbd3e329036653 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:01:55 -0800 Subject: mm/gup: Overload get_user_pages() functions The concept here was a suggestion from Ingo. The implementation horrors are all mine. This allows get_user_pages(), get_user_pages_unlocked(), and get_user_pages_locked() to be called with or without the leading tsk/mm arguments. We will give a compile-time warning about the old style being __deprecated and we will also WARN_ON() if the non-remote version is used for a remote-style access. Doing this, folks will get nice warnings and will not break the build. This should be nice for -next and will hopefully let developers fix up their own code instead of maintainers needing to do it at merge time. The way we do this is hideous. It uses the __VA_ARGS__ macro functionality to call different functions based on the number of arguments passed to the macro. There's an additional hack to ensure that our EXPORT_SYMBOL() of the deprecated symbols doesn't trigger a warning. We should be able to remove this mess as soon as -rc1 hits in the release after this is merged. Signed-off-by: Dave Hansen Cc: Al Viro Cc: Alexander Kuleshov Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Dan Williams Cc: Dave Hansen Cc: Dominik Dingel Cc: Geliang Tang Cc: Jan Kara Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Leon Romanovsky Cc: Linus Torvalds Cc: Masahiro Yamada Cc: Mateusz Guzik Cc: Maxime Coquelin Cc: Michal Hocko Cc: Naoya Horiguchi Cc: Oleg Nesterov Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Thomas Gleixner Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Xie XiuQi Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210155.73222EE1@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/mm.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 64 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index faf3b709eead..4c7317828fda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1229,24 +1229,78 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); -long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - struct vm_area_struct **vmas); -long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - int *locked); +long get_user_pages6(unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas); +long get_user_pages_locked6(unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, int *locked); long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, unsigned int gup_flags); -long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, +long get_user_pages_unlocked5(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +/* suppress warnings from use in EXPORT_SYMBOL() */ +#ifndef __DISABLE_GUP_DEPRECATED +#define __gup_deprecated __deprecated +#else +#define __gup_deprecated +#endif +/* + * These macros provide backward-compatibility with the old + * get_user_pages() variants which took tsk/mm. These + * functions/macros provide both compile-time __deprecated so we + * can catch old-style use and not break the build. The actual + * functions also have WARN_ON()s to let us know at runtime if + * the get_user_pages() should have been the "remote" variant. + * + * These are hideous, but temporary. + * + * If you run into one of these __deprecated warnings, look + * at how you are calling get_user_pages(). If you are calling + * it with current/current->mm as the first two arguments, + * simply remove those arguments. The behavior will be the same + * as it is now. If you are calling it on another task, use + * get_user_pages_remote() instead. + * + * Any questions? Ask Dave Hansen + */ +long +__gup_deprecated +get_user_pages8(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas); +#define GUP_MACRO(_1, _2, _3, _4, _5, _6, _7, _8, get_user_pages, ...) \ + get_user_pages +#define get_user_pages(...) GUP_MACRO(__VA_ARGS__, \ + get_user_pages8, x, \ + get_user_pages6, x, x, x, x, x)(__VA_ARGS__) + +__gup_deprecated +long get_user_pages_locked8(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked); +#define GUPL_MACRO(_1, _2, _3, _4, _5, _6, _7, _8, get_user_pages_locked, ...) \ + get_user_pages_locked +#define get_user_pages_locked(...) GUPL_MACRO(__VA_ARGS__, \ + get_user_pages_locked8, x, \ + get_user_pages_locked6, x, x, x, x)(__VA_ARGS__) + +__gup_deprecated +long get_user_pages_unlocked7(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages); +#define GUPU_MACRO(_1, _2, _3, _4, _5, _6, _7, get_user_pages_unlocked, ...) \ + get_user_pages_unlocked +#define get_user_pages_unlocked(...) GUPU_MACRO(__VA_ARGS__, \ + get_user_pages_unlocked7, x, \ + get_user_pages_unlocked5, x, x, x, x)(__VA_ARGS__) + /* Container for pinned pfns / pages */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ -- cgit v1.2.3 From 2e8741599cf128ea27674d9ae93b46e847f820b4 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 14 Jan 2016 17:58:02 +0000 Subject: firmware: arm_scpi: add support for 64-bit sensor values SCPI specification version 1.1 extended the sensor from 32-bit to 64-bit values in order to accommodate new sensor class with 64-bit requirements Since the SCPI driver sets the higher 32-bit for older protocol version to zeros, there's no need to explicitly check the SCPI protocol version and the backward compatibility is maintainted. Acked-by: Guenter Roeck Reviewed-by: Punit Agrawal Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index 72ce932c69b2..ecd248d46281 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -68,7 +68,7 @@ struct scpi_ops { struct scpi_dvfs_info *(*dvfs_get_info)(u8); int (*sensor_get_capability)(u16 *sensors); int (*sensor_get_info)(u16 sensor_id, struct scpi_sensor_info *); - int (*sensor_get_value)(u16, u32 *); + int (*sensor_get_value)(u16, u64 *); }; #if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL) -- cgit v1.2.3 From fb3b07ef399bd6984f3361a709829618b75e98d8 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 25 Jan 2016 10:53:38 +0000 Subject: hwmon: (scpi) add energy meter support SCPI specification v1.1 adds support for energy sensors. This patch adds support for the same. Acked-by: Guenter Roeck Reviewed-by: Punit Agrawal Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index ecd248d46281..35de50a65665 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -33,6 +33,7 @@ enum scpi_sensor_class { VOLTAGE, CURRENT, POWER, + ENERGY, }; struct scpi_sensor_info { -- cgit v1.2.3 From 143b65d677a59764e438d457bf2510b3fa5b90f8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 Feb 2016 15:41:42 +0100 Subject: gpio: create an API to detect open drain/source on lines My left hand merges code to privatize the descriptor handling while my right hand merges drivers that poke around and disrespect with the same gpiolib internals. So let's expose the proper APIs for drivers to ask the gpiolib core if a line is marked as open drain or open source and get some order around things so this driver compiles again. Reported-by: Stephen Rothwell Cc: Nicolas Saenz Julienne Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b92ab9efdb69..ff96d0f9fceb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -199,6 +199,10 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset); void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); +/* Line status inquiry for drivers */ +bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); +bool gpiochip_line_is_open_source(struct gpio_chip *chip, unsigned int offset); + /* get driver data */ void *gpiochip_get_data(struct gpio_chip *chip); -- cgit v1.2.3 From 656b8035b0eebcac0172b24ca04e448c70dd047f Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Mon, 15 Feb 2016 09:25:06 +0100 Subject: ARM: 8524/1: driver cohandle -EPROBE_DEFER from bus_type.match() Allow implementations of the match() callback in struct bus_type to return errors and if it's -EPROBE_DEFER then queue the device for deferred probing. This is useful to buses such as AMBA in which devices are registered before their matching information can be retrieved from the HW (typically because a clock driver hasn't probed yet). [changed if-else code structure, adjusted documentation to match the code, extended comments] Signed-off-by: Tomeu Vizoso Signed-off-by: Marek Szyprowski Reviewed-by: Ulf Hansson Acked-by: Greg Kroah-Hartman Signed-off-by: Russell King --- include/linux/device.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 6d6f1fec092f..8f2ec813d215 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -70,8 +70,11 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver - * is added for this bus. It should return a nonzero value if the - * given device can be handled by the given driver. + * is added for this bus. It should return a positive value if the + * given device can be handled by the given driver and zero + * otherwise. It may also return error code if determining that + * the driver supports the device is not possible. In case of + * -EPROBE_DEFER it will queue the device for deferred probing. * @uevent: Called when a device is added, removed, or a few other things * that generate uevents to add the environment variables. * @probe: Called when a new device or driver add to this bus, and callback -- cgit v1.2.3 From 416dd13ad620a14fbabe5d73584b12e07ce8d02e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 26 Jan 2016 01:21:26 +0100 Subject: ARM: 8503/1: clk_register_clkdev: remove format string interface Many callers either use NULL or const strings for the third argument of clk_register_clkdev. For those that do not and use a non-const string, this is a risk for format strings being accidentally processed (for example in device names). As this interface is already used as if it weren't a format string (prints nothing when NULL), and there are zero users of the format strings, remove the format string interface to make sure format strings will not leak into the clkdev. $ git grep '\bclk_register_clkdev\b' | grep % | wc -l 0 Unfortunately, all the internals expect a va_list even though they treat a NULL format string as special. To deal with this, we must pass either (..., "%s", string) or (..., NULL) so that a the va_list will be created correctly (passing the name as an argument, not as a format string). Signed-off-by: Kees Cook Signed-off-by: Russell King --- include/linux/clkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index 08bffcc466de..c2c04f7cbe8a 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -44,8 +44,7 @@ struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id, void clkdev_add_table(struct clk_lookup *, size_t); int clk_add_alias(const char *, const char *, const char *, struct device *); -int clk_register_clkdev(struct clk *, const char *, const char *, ...) - __printf(3, 4); +int clk_register_clkdev(struct clk *, const char *, const char *); int clk_register_clkdevs(struct clk *, struct clk_lookup *, size_t); #ifdef CONFIG_COMMON_CLK -- cgit v1.2.3 From 9f6df573a4041f896cbf51f1b3743494196620a7 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 29 Jan 2016 02:54:04 -0600 Subject: kernfs: Add API to generate relative kernfs path The new function kernfs_path_from_node() generates and returns kernfs path of a given kernfs_node relative to a given parent kernfs_node. Signed-off-by: Aditya Kali Signed-off-by: Serge E. Hallyn Acked-by: Greg Kroah-Hartman Signed-off-by: Tejun Heo --- include/linux/kernfs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index af51df35d749..716bfdede5f5 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -267,8 +267,9 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); size_t kernfs_path_len(struct kernfs_node *kn); -char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, - size_t buflen); +int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, + char *buf, size_t buflen); +char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); @@ -338,8 +339,8 @@ static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) static inline size_t kernfs_path_len(struct kernfs_node *kn) { return 0; } -static inline char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, - size_t buflen) +static inline char *kernfs_path(struct kernfs_node *kn, char *buf, + size_t buflen) { return NULL; } static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { } -- cgit v1.2.3 From a79a908fd2b080977b45bf103184b81c9d11ad07 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 29 Jan 2016 02:54:06 -0600 Subject: cgroup: introduce cgroup namespaces Introduce the ability to create new cgroup namespace. The newly created cgroup namespace remembers the cgroup of the process at the point of creation of the cgroup namespace (referred as cgroupns-root). The main purpose of cgroup namespace is to virtualize the contents of /proc/self/cgroup file. Processes inside a cgroup namespace are only able to see paths relative to their namespace root (unless they are moved outside of their cgroupns-root, at which point they will see a relative path from their cgroupns-root). For a correctly setup container this enables container-tools (like libcontainer, lxc, lmctfy, etc.) to create completely virtualized containers without leaking system level cgroup hierarchy to the task. This patch only implements the 'unshare' part of the cgroupns. Signed-off-by: Aditya Kali Signed-off-by: Serge Hallyn Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nsproxy.h | 2 ++ include/linux/proc_ns.h | 4 ++++ 3 files changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 2162dca88dc0..a20320c666fd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -17,6 +17,11 @@ #include #include #include +#include +#include +#include +#include +#include #include @@ -611,4 +616,48 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ +struct cgroup_namespace { + atomic_t count; + struct ns_common ns; + struct user_namespace *user_ns; + struct css_set *root_cset; +}; + +extern struct cgroup_namespace init_cgroup_ns; + +#ifdef CONFIG_CGROUPS + +void free_cgroup_ns(struct cgroup_namespace *ns); + +struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns); + +char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns); + +#else /* !CONFIG_CGROUPS */ + +static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } +static inline struct cgroup_namespace * +copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + return old_ns; +} + +#endif /* !CONFIG_CGROUPS */ + +static inline void get_cgroup_ns(struct cgroup_namespace *ns) +{ + if (ns) + atomic_inc(&ns->count); +} + +static inline void put_cgroup_ns(struct cgroup_namespace *ns) +{ + if (ns && atomic_dec_and_test(&ns->count)) + free_cgroup_ns(ns); +} + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 35fa08fd7739..ac0d65bef5d0 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -8,6 +8,7 @@ struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; +struct cgroup_namespace; struct fs_struct; /* @@ -33,6 +34,7 @@ struct nsproxy { struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns_for_children; struct net *net_ns; + struct cgroup_namespace *cgroup_ns; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 42dfc615dbf8..de0e7719d4c5 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -9,6 +9,8 @@ struct pid_namespace; struct nsproxy; struct path; +struct task_struct; +struct inode; struct proc_ns_operations { const char *name; @@ -24,6 +26,7 @@ extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; +extern const struct proc_ns_operations cgroupns_operations; /* * We always define these enumerators @@ -34,6 +37,7 @@ enum { PROC_UTS_INIT_INO = 0xEFFFFFFEU, PROC_USER_INIT_INO = 0xEFFFFFFDU, PROC_PID_INIT_INO = 0xEFFFFFFCU, + PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, }; #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From fb3c8315650f89a1993fb3ae3e74e9c7e4a1c9c0 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 29 Jan 2016 02:54:08 -0600 Subject: kernfs: define kernfs_node_dentry Add a new kernfs api is added to lookup the dentry for a particular kernfs path. Signed-off-by: Aditya Kali Signed-off-by: Serge E. Hallyn Acked-by: Greg Kroah-Hartman Signed-off-by: Tejun Heo --- include/linux/kernfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 716bfdede5f5..c06c44242f39 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -284,6 +284,8 @@ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); +struct dentry *kernfs_node_dentry(struct kernfs_node *kn, + struct super_block *sb); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); -- cgit v1.2.3 From d4ab4286276fcd6c155bafdf4422b712068d2516 Mon Sep 17 00:00:00 2001 From: "Keller, Jacob E" Date: Mon, 8 Feb 2016 16:05:03 -0800 Subject: ethtool: correctly ensure {GS}CHANNELS doesn't conflict with GS{RXFH} Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by: Jacob Keller Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 219f53c30cb3..0499569c256d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1291,6 +1291,7 @@ struct net_device_ops { * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device + * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1318,6 +1319,7 @@ enum netdev_priv_flags { IFF_OPENVSWITCH = 1<<22, IFF_L3MDEV_SLAVE = 1<<23, IFF_TEAM = 1<<24, + IFF_RXFH_CONFIGURED = 1<<25, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1345,6 +1347,7 @@ enum netdev_priv_flags { #define IFF_OPENVSWITCH IFF_OPENVSWITCH #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM +#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED /** * struct net_device - The DEVICE structure. @@ -4048,6 +4051,11 @@ static inline bool netif_is_lag_port(const struct net_device *dev) return netif_is_bond_slave(dev) || netif_is_team_port(dev); } +static inline bool netif_is_rxfh_configured(const struct net_device *dev) +{ + return dev->priv_flags & IFF_RXFH_CONFIGURED; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 92016ba5c1d71fbe4e9952df518b5386f2a0556b Mon Sep 17 00:00:00 2001 From: Jake Oshins Date: Tue, 16 Feb 2016 21:56:21 +0000 Subject: PCI: Add fwnode_handle to x86 pci_sysdata Add an fwnode_handle to the x86 struct pci_sysdata, which will be used to locate an IRQ domain associated with a root PCI bus. [bhelgaas: changelog] Signed-off-by: Jake Oshins Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..1bb44af6c9f0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1515,6 +1515,10 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #include +#ifndef pci_root_bus_fwnode +#define pci_root_bus_fwnode(bus) NULL +#endif + /* these helpers provide future and backwards compatibility * for accessing popular PCI BAR info */ #define pci_resource_start(dev, bar) ((dev)->resource[(bar)].start) -- cgit v1.2.3 From e1ab7f39d7e0dbfbdefe148be3ae4ee121e47ecc Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 15 Dec 2015 22:24:14 +0800 Subject: atomics: Allow architectures to define their own __atomic_op_* helpers Some architectures may have their special barriers for acquire, release and fence semantics, so that general memory barriers(smp_mb__*_atomic()) in the default __atomic_op_*() may be too strong, so allow architectures to define their own helpers which can overwrite the default helpers. Signed-off-by: Boqun Feng Signed-off-by: Michael Ellerman --- include/linux/atomic.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 301de78d65f7..5f3ee5a60a81 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -34,20 +34,29 @@ * The idea here is to build acquire/release variants by adding explicit * barriers on top of the relaxed variant. In the case where the relaxed * variant is already fully ordered, no additional barriers are needed. + * + * Besides, if an arch has a special barrier for acquire/release, it could + * implement its own __atomic_op_* and use the same framework for building + * variants */ +#ifndef __atomic_op_acquire #define __atomic_op_acquire(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ smp_mb__after_atomic(); \ __ret; \ }) +#endif +#ifndef __atomic_op_release #define __atomic_op_release(op, args...) \ ({ \ smp_mb__before_atomic(); \ op##_relaxed(args); \ }) +#endif +#ifndef __atomic_op_fence #define __atomic_op_fence(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret; \ @@ -56,6 +65,7 @@ smp_mb__after_atomic(); \ __ret; \ }) +#endif /* atomic_add_return_relaxed */ #ifndef atomic_add_return_relaxed -- cgit v1.2.3 From e4c6734eaab90695db0ea8456307790cb0c1ccb5 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:16:15 -0800 Subject: net: rework ndo tc op to consume additional qdisc handle parameter The ndo_setup_tc() op was added to support drivers offloading tx qdiscs however only support for mqprio was ever added. So we only ever added support for passing the number of traffic classes to the driver. This patch generalizes the ndo_setup_tc op so that a handle can be provided to indicate if the offload is for ingress or egress or potentially even child qdiscs. CC: Murali Karicheri CC: Shradha Shah CC: Or Gerlitz CC: Ariel Elior CC: Jeff Kirsher CC: Bruce Allan CC: Jesse Brandeburg CC: Don Skidmore Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0499569c256d..48928b6f9cb6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -51,6 +51,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -1150,7 +1151,7 @@ struct net_device_ops { int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); - int (*ndo_setup_tc)(struct net_device *dev, u8 tc); + int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u8 tc); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); -- cgit v1.2.3 From 16e5cc647173a97e33b3e3ba81f73eb455561794 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:16:43 -0800 Subject: net: rework setup_tc ndo op to consume general tc operand This patch updates setup_tc so we can pass additional parameters into the ndo op in a generic way. To do this we provide structured union and type flag. This lets each classifier and qdisc provide its own set of attributes without having to add new ndo ops or grow the signature of the callback. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 48928b6f9cb6..e396060f815f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -779,6 +779,21 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); +/* This structure holds attributes of qdisc and classifiers + * that are being passed to the netdevice through the setup_tc op. + */ +enum { + TC_SETUP_MQPRIO, +}; + +struct tc_to_netdev { + unsigned int type; + union { + u8 tc; + }; +}; + + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1151,7 +1166,10 @@ struct net_device_ops { int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); - int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u8 tc); + int (*ndo_setup_tc)(struct net_device *dev, + u32 handle, + __be16 protocol, + struct tc_to_netdev *tc); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); -- cgit v1.2.3 From a1b7c5fd7fe98f51fbbc393ee1fc4c1cdb2f0119 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:17:09 -0800 Subject: net: sched: add cls_u32 offload hooks for netdevs This patch allows netdev drivers to consume cls_u32 offloads via the ndo_setup_tc ndo op. This works aligns with how network drivers have been doing qdisc offloads for mqprio. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e396060f815f..47671ce04ac4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -779,17 +779,21 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -/* This structure holds attributes of qdisc and classifiers +/* These structures hold the attributes of qdisc and classifiers * that are being passed to the netdevice through the setup_tc op. */ enum { TC_SETUP_MQPRIO, + TC_SETUP_CLSU32, }; +struct tc_cls_u32_offload; + struct tc_to_netdev { unsigned int type; union { u8 tc; + struct tc_cls_u32_offload *cls_u32; }; }; -- cgit v1.2.3 From 1c78c64e9c6f43a490427d55cd2d213b7c6795c1 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:17:37 -0800 Subject: net: add tc offload feature flag Its useful to turn off the qdisc offload feature at a per device level. This gives us a big hammer to enable/disable offloading. More fine grained control (i.e. per rule) may be supported later. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index d9654f0eecb3..a734bf43d190 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -67,6 +67,8 @@ enum { NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ + NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ + /* * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe @@ -124,6 +126,7 @@ 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_TC __NETIF_F(HW_TC) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) -- cgit v1.2.3 From af719c18075f76f83e363bd13a97937b2e9f3f7d Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 30 Sep 2015 13:02:01 +0200 Subject: clk: at91: pmc: drop at91_pmc_base at91_pmc_base is not used anymore, remove it along with at91_pmc_read and at91_pmc_write. Signed-off-by: Alexandre Belloni Acked-by: Boris Brezillon Acked-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 1e6932222e11..17f413bbbedf 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -16,18 +16,6 @@ #ifndef AT91_PMC_H #define AT91_PMC_H -#ifndef __ASSEMBLY__ -extern void __iomem *at91_pmc_base; - -#define at91_pmc_read(field) \ - readl_relaxed(at91_pmc_base + field) - -#define at91_pmc_write(field, value) \ - writel_relaxed(value, at91_pmc_base + field) -#else -.extern at91_pmc_base -#endif - #define AT91_PMC_SCER 0x00 /* System Clock Enable Register */ #define AT91_PMC_SCDR 0x04 /* System Clock Disable Register */ -- cgit v1.2.3 From fc48b7a6148af974b49db145812a8b060324a503 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 15 Feb 2016 13:22:35 -0500 Subject: qed/qede: use 8.7.3.0 FW. This patch moves the qed* driver into utilizing the 8.7.3.0 FW. This new FW is required for a lot of new SW features, including: - Vlan filtering offload - Encapsulation offload support - HW ingress aggregations As well as paving the way for the possibility of adding storage protocols in the future. V2: - Fix kbuild test robot error/warnings. Signed-off-by: Yuval Mintz Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 36 ++++++++- include/linux/qed/eth_common.h | 171 ++++++++++++++++++++++++++++++++--------- include/linux/qed/qed_if.h | 8 +- 3 files changed, 173 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 1d1ba2c5ee7a..53ecb37ae563 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -11,9 +11,11 @@ #define CORE_SPQE_PAGE_SIZE_BYTES 4096 +#define X_FINAL_CLEANUP_AGG_INT 1 + #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 4 -#define FW_REVISION_VERSION 2 +#define FW_MINOR_VERSION 7 +#define FW_REVISION_VERSION 3 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -152,6 +154,9 @@ /* number of queues in a PF queue group */ #define QM_PF_QUEUE_GROUP_SIZE 8 +/* the size of a single queue element in bytes */ +#define QM_PQ_ELEMENT_SIZE 4 + /* base number of Tx PQs in the CM PQ representation. * should be used when storing PQ IDs in CM PQ registers and context */ @@ -285,6 +290,16 @@ #define PXP_NUM_ILT_RECORDS_K2 11000 #define MAX_NUM_ILT_RECORDS MAX(PXP_NUM_ILT_RECORDS_BB, PXP_NUM_ILT_RECORDS_K2) +#define SDM_COMP_TYPE_NONE 0 +#define SDM_COMP_TYPE_WAKE_THREAD 1 +#define SDM_COMP_TYPE_AGG_INT 2 +#define SDM_COMP_TYPE_CM 3 +#define SDM_COMP_TYPE_LOADER 4 +#define SDM_COMP_TYPE_PXP 5 +#define SDM_COMP_TYPE_INDICATE_ERROR 6 +#define SDM_COMP_TYPE_RELEASE_THREAD 7 +#define SDM_COMP_TYPE_RAM 8 + /******************/ /* PBF CONSTANTS */ /******************/ @@ -335,7 +350,7 @@ struct event_ring_entry { /* Multi function mode */ enum mf_mode { - SF, + ERROR_MODE /* Unsupported mode */, MF_OVLAN, MF_NPAR, MAX_MF_MODE @@ -606,4 +621,19 @@ struct status_block { #define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 }; +struct tunnel_parsing_flags { + u8 flags; +#define TUNNEL_PARSING_FLAGS_TYPE_MASK 0x3 +#define TUNNEL_PARSING_FLAGS_TYPE_SHIFT 0 +#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_SHIFT 2 +#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_MASK 0x3 +#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_SHIFT 3 +#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_SHIFT 5 +#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_SHIFT 6 +#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_SHIFT 7 +}; #endif /* __COMMON_HSI__ */ diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 320b3373ac1d..092cb0c1afcb 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -17,10 +17,8 @@ #define ETH_MAX_RAMROD_PER_CON 8 #define ETH_TX_BD_PAGE_SIZE_BYTES 4096 #define ETH_RX_BD_PAGE_SIZE_BYTES 4096 -#define ETH_RX_SGE_PAGE_SIZE_BYTES 4096 #define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 #define ETH_RX_NUM_NEXT_PAGE_BDS 2 -#define ETH_RX_NUM_NEXT_PAGE_SGES 2 #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 @@ -34,7 +32,8 @@ #define ETH_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS -#define ETH_REG_CQE_PBL_SIZE 3 +/* Maximum number of buffers, used for RX packet placement */ +#define ETH_RX_MAX_BUFF_PER_PKT 5 /* num of MAC/VLAN filters */ #define ETH_NUM_MAC_FILTERS 512 @@ -54,9 +53,9 @@ /* TPA constants */ #define ETH_TPA_MAX_AGGS_NUM 64 -#define ETH_TPA_CQE_START_SGL_SIZE 3 -#define ETH_TPA_CQE_CONT_SGL_SIZE 6 -#define ETH_TPA_CQE_END_SGL_SIZE 4 +#define ETH_TPA_CQE_START_LEN_LIST_SIZE ETH_RX_MAX_BUFF_PER_PKT +#define ETH_TPA_CQE_CONT_LEN_LIST_SIZE 6 +#define ETH_TPA_CQE_END_LEN_LIST_SIZE 4 /* Queue Zone sizes */ #define TSTORM_QZONE_SIZE 0 @@ -74,18 +73,18 @@ struct coalescing_timeset { struct eth_tx_1st_bd_flags { u8 bitfields; +#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 0 #define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0 +#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 1 #define ETH_TX_1ST_BD_FLAGS_IP_CSUM_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 1 +#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 2 #define ETH_TX_1ST_BD_FLAGS_L4_CSUM_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 2 +#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 3 #define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 3 +#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 4 #define ETH_TX_1ST_BD_FLAGS_LSO_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 4 -#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 5 +#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 5 #define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_MASK 0x1 #define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_SHIFT 6 #define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_MASK 0x1 @@ -97,38 +96,44 @@ struct eth_tx_data_1st_bd { __le16 vlan; u8 nbds; struct eth_tx_1st_bd_flags bd_flags; - __le16 fw_use_only; + __le16 bitfields; +#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_MASK 0x1 +#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_SHIFT 0 +#define ETH_TX_DATA_1ST_BD_RESERVED0_MASK 0x1 +#define ETH_TX_DATA_1ST_BD_RESERVED0_SHIFT 1 +#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_MASK 0x3FFF +#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_SHIFT 2 }; /* The parsing information data for the second tx bd of a given packet. */ struct eth_tx_data_2nd_bd { __le16 tunn_ip_size; - __le16 bitfields; -#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF -#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0 -#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7 -#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 - __le16 bitfields2; + __le16 bitfields1; #define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_MASK 0xF #define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_SHIFT 0 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_MASK 0x3 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_SHIFT 4 #define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_MASK 0x3 #define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_SHIFT 6 +#define ETH_TX_DATA_2ND_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_START_BD_SHIFT 8 #define ETH_TX_DATA_2ND_BD_TUNN_TYPE_MASK 0x3 -#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 8 +#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 9 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 10 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 11 #define ETH_TX_DATA_2ND_BD_IPV6_EXT_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 11 +#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 12 #define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 12 +#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 13 #define ETH_TX_DATA_2ND_BD_L4_UDP_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 13 +#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 14 #define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 14 -#define ETH_TX_DATA_2ND_BD_RESERVED1_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_RESERVED1_SHIFT 15 +#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 15 + __le16 bitfields2; +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0 +#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7 +#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 }; /* Regular ETH Rx FP CQE. */ @@ -145,11 +150,68 @@ struct eth_fast_path_rx_reg_cqe { struct parsing_and_err_flags pars_flags; __le16 vlan_tag; __le32 rss_hash; - __le16 len_on_bd; + __le16 len_on_first_bd; u8 placement_offset; - u8 reserved; - __le16 pbl[ETH_REG_CQE_PBL_SIZE]; - u8 reserved1[10]; + struct tunnel_parsing_flags tunnel_pars_flags; + u8 bd_num; + u8 reserved[7]; + u32 fw_debug; + u8 reserved1[3]; + u8 flags; +#define ETH_FAST_PATH_RX_REG_CQE_VALID_MASK 0x1 +#define ETH_FAST_PATH_RX_REG_CQE_VALID_SHIFT 0 +#define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_MASK 0x1 +#define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_SHIFT 1 +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED2_MASK 0x3F +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED2_SHIFT 2 +}; + +/* TPA-continue ETH Rx FP CQE. */ +struct eth_fast_path_rx_tpa_cont_cqe { + u8 type; + u8 tpa_agg_index; + __le16 len_list[ETH_TPA_CQE_CONT_LEN_LIST_SIZE]; + u8 reserved[5]; + u8 reserved1; + __le16 reserved2[ETH_TPA_CQE_CONT_LEN_LIST_SIZE]; +}; + +/* TPA-end ETH Rx FP CQE. */ +struct eth_fast_path_rx_tpa_end_cqe { + u8 type; + u8 tpa_agg_index; + __le16 total_packet_len; + u8 num_of_bds; + u8 end_reason; + __le16 num_of_coalesced_segs; + __le32 ts_delta; + __le16 len_list[ETH_TPA_CQE_END_LEN_LIST_SIZE]; + u8 reserved1[3]; + u8 reserved2; + __le16 reserved3[ETH_TPA_CQE_END_LEN_LIST_SIZE]; +}; + +/* TPA-start ETH Rx FP CQE. */ +struct eth_fast_path_rx_tpa_start_cqe { + u8 type; + u8 bitfields; +#define ETH_FAST_PATH_RX_TPA_START_CQE_RSS_HASH_TYPE_MASK 0x7 +#define ETH_FAST_PATH_RX_TPA_START_CQE_RSS_HASH_TYPE_SHIFT 0 +#define ETH_FAST_PATH_RX_TPA_START_CQE_TC_MASK 0xF +#define ETH_FAST_PATH_RX_TPA_START_CQE_TC_SHIFT 3 +#define ETH_FAST_PATH_RX_TPA_START_CQE_RESERVED0_MASK 0x1 +#define ETH_FAST_PATH_RX_TPA_START_CQE_RESERVED0_SHIFT 7 + __le16 seg_len; + struct parsing_and_err_flags pars_flags; + __le16 vlan_tag; + __le32 rss_hash; + __le16 len_on_first_bd; + u8 placement_offset; + struct tunnel_parsing_flags tunnel_pars_flags; + u8 tpa_agg_index; + u8 header_len; + __le16 ext_bd_len_list[ETH_TPA_CQE_START_LEN_LIST_SIZE]; + u32 fw_debug; }; /* The L4 pseudo checksum mode for Ethernet */ @@ -168,13 +230,26 @@ struct eth_slow_path_rx_cqe { u8 type; u8 ramrod_cmd_id; u8 error_flag; - u8 reserved[27]; + u8 reserved[25]; __le16 echo; + u8 reserved1; + u8 flags; +/* for PMD mode - valid indication */ +#define ETH_SLOW_PATH_RX_CQE_VALID_MASK 0x1 +#define ETH_SLOW_PATH_RX_CQE_VALID_SHIFT 0 +/* for PMD mode - valid toggle indication */ +#define ETH_SLOW_PATH_RX_CQE_VALID_TOGGLE_MASK 0x1 +#define ETH_SLOW_PATH_RX_CQE_VALID_TOGGLE_SHIFT 1 +#define ETH_SLOW_PATH_RX_CQE_RESERVED2_MASK 0x3F +#define ETH_SLOW_PATH_RX_CQE_RESERVED2_SHIFT 2 }; /* union for all ETH Rx CQE types */ union eth_rx_cqe { struct eth_fast_path_rx_reg_cqe fast_path_regular; + struct eth_fast_path_rx_tpa_start_cqe fast_path_tpa_start; + struct eth_fast_path_rx_tpa_cont_cqe fast_path_tpa_cont; + struct eth_fast_path_rx_tpa_end_cqe fast_path_tpa_end; struct eth_slow_path_rx_cqe slow_path; }; @@ -183,15 +258,18 @@ enum eth_rx_cqe_type { ETH_RX_CQE_TYPE_UNUSED, ETH_RX_CQE_TYPE_REGULAR, ETH_RX_CQE_TYPE_SLOW_PATH, + ETH_RX_CQE_TYPE_TPA_START, + ETH_RX_CQE_TYPE_TPA_CONT, + ETH_RX_CQE_TYPE_TPA_END, MAX_ETH_RX_CQE_TYPE }; /* ETH Rx producers data */ struct eth_rx_prod_data { __le16 bd_prod; - __le16 sge_prod; __le16 cqe_prod; __le16 reserved; + __le16 reserved1; }; /* The first tx bd of a given packet */ @@ -211,12 +289,17 @@ struct eth_tx_2nd_bd { /* The parsing information data for the third tx bd of a given packet. */ struct eth_tx_data_3rd_bd { __le16 lso_mss; - u8 bitfields; + __le16 bitfields; #define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK 0xF #define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT 0 #define ETH_TX_DATA_3RD_BD_HDR_NBD_MASK 0xF #define ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT 4 - u8 resereved0[3]; +#define ETH_TX_DATA_3RD_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_3RD_BD_START_BD_SHIFT 8 +#define ETH_TX_DATA_3RD_BD_RESERVED0_MASK 0x7F +#define ETH_TX_DATA_3RD_BD_RESERVED0_SHIFT 9 + u8 tunn_l4_hdr_start_offset_w; + u8 tunn_hdr_size_w; }; /* The third tx bd of a given packet */ @@ -226,12 +309,24 @@ struct eth_tx_3rd_bd { struct eth_tx_data_3rd_bd data; }; +/* Complementary information for the regular tx bd of a given packet. */ +struct eth_tx_data_bd { + __le16 reserved0; + __le16 bitfields; +#define ETH_TX_DATA_BD_RESERVED1_MASK 0xFF +#define ETH_TX_DATA_BD_RESERVED1_SHIFT 0 +#define ETH_TX_DATA_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_BD_START_BD_SHIFT 8 +#define ETH_TX_DATA_BD_RESERVED2_MASK 0x7F +#define ETH_TX_DATA_BD_RESERVED2_SHIFT 9 + __le16 reserved3; +}; + /* The common non-special TX BD ring element */ struct eth_tx_bd { struct regpair addr; __le16 nbytes; - __le16 reserved0; - __le32 reserved1; + struct eth_tx_data_bd data; }; union eth_tx_bd_types { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index d4a32e878180..3d43c1d4ecef 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -80,7 +80,7 @@ struct qed_dev_info { u8 num_hwfns; u8 hw_mac[ETH_ALEN]; - bool is_mf; + bool is_mf_default; /* FW version */ u16 fw_major; @@ -360,6 +360,12 @@ enum DP_MODULE { /* to be added...up to 0x8000000 */ }; +enum qed_mf_mode { + QED_MF_DEFAULT, + QED_MF_OVLAN, + QED_MF_NPAR, +}; + struct qed_eth_stats { u64 no_buff_discards; u64 packet_too_big_discard; -- cgit v1.2.3 From 3347a0656e7a83b959b1d0ad5396fb4f9c9b2a0e Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Mon, 15 Feb 2016 12:47:42 -0500 Subject: iio: Fix typos in the struct iio_event_spec documentation comments This patch fixes a few minor typos in the documentation comments for the scan_type member of the iio_event_spec structure. The sign member name was improperly capitalized as "Sign" in the comments. The storagebits member name was improperly listed as "storage_bits" in the comments. The endianness member entry in the comments was moved after the repeat member entry in order to maintain consistency with the actual struct iio_event_spec layout. Signed-off-by: William Breathitt Gray Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index ce9e9c1adf34..b2b16772c651 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -180,18 +180,18 @@ struct iio_event_spec { * @address: Driver specific identifier. * @scan_index: Monotonic index to give ordering in scans when read * from a buffer. - * @scan_type: Sign: 's' or 'u' to specify signed or unsigned + * @scan_type: sign: 's' or 'u' to specify signed or unsigned * realbits: Number of valid bits of data - * storage_bits: Realbits + padding + * storagebits: Realbits + padding * shift: Shift right by this before masking out * realbits. - * endianness: little or big endian * repeat: Number of times real/storage bits * repeats. When the repeat element is * more than 1, then the type element in * sysfs will show a repeat value. * Otherwise, the number of repetitions is * omitted. + * endianness: little or big endian * @info_mask_separate: What information is to be exported that is specific to * this channel. * @info_mask_shared_by_type: What information is to be exported that is shared -- cgit v1.2.3 From 7bbf3cae65b6e438bf52033b63fdce4a86e89e17 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 15 Feb 2016 21:25:57 +0000 Subject: ipv4: Remove inet_lro library There are no longer any in-tree drivers that use it. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 142 ----------------------------------------------- 1 file changed, 142 deletions(-) delete mode 100644 include/linux/inet_lro.h (limited to 'include/linux') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h deleted file mode 100644 index 9a715cfa1fe3..000000000000 --- a/include/linux/inet_lro.h +++ /dev/null @@ -1,142 +0,0 @@ -/* - * linux/include/linux/inet_lro.h - * - * Large Receive Offload (ipv4 / tcp) - * - * (C) Copyright IBM Corp. 2007 - * - * Authors: - * Jan-Bernd Themann - * Christoph Raisch - * - * - * 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, 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef __INET_LRO_H_ -#define __INET_LRO_H_ - -#include -#include - -/* - * LRO statistics - */ - -struct net_lro_stats { - unsigned long aggregated; - unsigned long flushed; - unsigned long no_desc; -}; - -/* - * LRO descriptor for a tcp session - */ -struct net_lro_desc { - struct sk_buff *parent; - struct sk_buff *last_skb; - struct skb_frag_struct *next_frag; - struct iphdr *iph; - struct tcphdr *tcph; - __wsum data_csum; - __be32 tcp_rcv_tsecr; - __be32 tcp_rcv_tsval; - __be32 tcp_ack; - u32 tcp_next_seq; - u32 skb_tot_frags_len; - u16 ip_tot_len; - u16 tcp_saw_tstamp; /* timestamps enabled */ - __be16 tcp_window; - int pkt_aggr_cnt; /* counts aggregated packets */ - int vlan_packet; - int mss; - int active; -}; - -/* - * Large Receive Offload (LRO) Manager - * - * Fields must be set by driver - */ - -struct net_lro_mgr { - struct net_device *dev; - struct net_lro_stats stats; - - /* LRO features */ - unsigned long features; -#define LRO_F_NAPI 1 /* Pass packets to stack via NAPI */ -#define LRO_F_EXTRACT_VLAN_ID 2 /* Set flag if VLAN IDs are extracted - from received packets and eth protocol - is still ETH_P_8021Q */ - - /* - * Set for generated SKBs that are not added to - * the frag list in fragmented mode - */ - u32 ip_summed; - u32 ip_summed_aggr; /* Set in aggregated SKBs: CHECKSUM_UNNECESSARY - * or CHECKSUM_NONE */ - - int max_desc; /* Max number of LRO descriptors */ - int max_aggr; /* Max number of LRO packets to be aggregated */ - - int frag_align_pad; /* Padding required to properly align layer 3 - * headers in generated skb when using frags */ - - struct net_lro_desc *lro_arr; /* Array of LRO descriptors */ - - /* - * Optimized driver functions - * - * get_skb_header: returns tcp and ip header for packet in SKB - */ - int (*get_skb_header)(struct sk_buff *skb, void **ip_hdr, - void **tcpudp_hdr, u64 *hdr_flags, void *priv); - - /* hdr_flags: */ -#define LRO_IPV4 1 /* ip_hdr is IPv4 header */ -#define LRO_TCP 2 /* tcpudp_hdr is TCP header */ - - /* - * get_frag_header: returns mac, tcp and ip header for packet in SKB - * - * @hdr_flags: Indicate what kind of LRO has to be done - * (IPv4/IPv6/TCP/UDP) - */ - int (*get_frag_header)(struct skb_frag_struct *frag, void **mac_hdr, - void **ip_hdr, void **tcpudp_hdr, u64 *hdr_flags, - void *priv); -}; - -/* - * Processes a SKB - * - * @lro_mgr: LRO manager to use - * @skb: SKB to aggregate - * @priv: Private data that may be used by driver functions - * (for example get_tcp_ip_hdr) - */ - -void lro_receive_skb(struct net_lro_mgr *lro_mgr, - struct sk_buff *skb, - void *priv); -/* - * Forward all aggregated SKBs held by lro_mgr to network stack - */ - -void lro_flush_all(struct net_lro_mgr *lro_mgr); - -#endif -- cgit v1.2.3 From 63c17fb8e5a46a16e10e82005748837fd11a2024 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:08 -0800 Subject: mm/core, x86/mm/pkeys: Store protection bits in high VMA flags vma->vm_flags is an 'unsigned long', so has space for 32 flags on 32-bit architectures. The high 32 bits are unused on 64-bit platforms. We've steered away from using the unused high VMA bits for things because we would have difficulty supporting it on 32-bit. Protection Keys are not available in 32-bit mode, so there is no concern about supporting this feature in 32-bit mode or on 32-bit CPUs. This patch carves out 4 bits from the high half of vma->vm_flags and allows architectures to set config option to make them available. Sparse complains about these constants unless we explicitly call them "UL". Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dan Williams Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jan Kara Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Linus Torvalds Cc: Mel Gorman Cc: Michal Hocko Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Sasha Levin Cc: Valentin Rothberg Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Xie XiuQi Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210208.81AF00D5@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/mm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4c7317828fda..54d173bcc327 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -170,6 +170,17 @@ extern unsigned int kobjsize(const void *objp); #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ +#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS +#define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) +#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) +#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) +#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) +#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ + #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) -- cgit v1.2.3 From 8f62c883222c9e3c06d60b5e55e307a3d1f18257 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:10 -0800 Subject: x86/mm/pkeys: Add arch-specific VMA protection bits Lots of things seem to do: vma->vm_page_prot = vm_get_page_prot(flags); and the ptes get created right from things we pull out of ->vm_page_prot. So it is very convenient if we can store the protection key in flags and vm_page_prot, just like the existing permission bits (_PAGE_RW/PRESENT). It greatly reduces the amount of plumbing and arch-specific hacking we have to do in generic code. This also takes the new PROT_PKEY{0,1,2,3} flags and turns *those* in to VM_ flags for vma->vm_flags. The protection key values are stored in 4 places: 1. "prot" argument to system calls 2. vma->vm_flags, filled from the mmap "prot" 3. vma->vm_page prot, filled from vma->vm_flags 4. the PTE itself. The pseudocode for these for steps are as follows: mmap(PROT_PKEY*) vma->vm_flags = ... | arch_calc_vm_prot_bits(mmap_prot); vma->vm_page_prot = ... | arch_vm_get_page_prot(vma->vm_flags); pte = pfn | vma->vm_page_prot Note that this provides a new definitions for x86: arch_vm_get_page_prot() Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210210.FE483A42@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 54d173bcc327..3056369bab1d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -183,6 +183,13 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ +#if defined (CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) +# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 +# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ +# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 +# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 +# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 +#endif #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) -- cgit v1.2.3 From 905f0a739ad82c6371fb0cb0e71db14a750702ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 18 Feb 2016 15:03:27 +0100 Subject: nfnetlink: remove nfnetlink_alloc_skb Following mmapped netlink removal this code can be simplified by removing the alloc wrapper. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index ba0d9789eb6e..1d82dd5e9a08 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -34,8 +34,6 @@ int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); int nfnetlink_has_listeners(struct net *net, unsigned int group); -struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size, - u32 dst_portid, gfp_t gfp_mask); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -- cgit v1.2.3 From c5b0db3263b92526bc0c1b6380c0c99f91f069fc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 18 Feb 2016 15:03:28 +0100 Subject: nfnetlink: Revert "nfnetlink: add support for memory mapped netlink" reverts commit 3ab1f683bf8b ("nfnetlink: add support for memory mapped netlink")' Like previous commits in the series, remove wrappers that are not needed after mmapped netlink removal. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netlink.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 0b41959aab9f..da14ab61f363 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -69,16 +69,6 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group) extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); -extern struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, - unsigned int ldiff, u32 dst_portid, - gfp_t gfp_mask); -static inline struct sk_buff * -netlink_alloc_skb(struct sock *ssk, unsigned int size, u32 dst_portid, - gfp_t gfp_mask) -{ - return __netlink_alloc_skb(ssk, size, 0, dst_portid, gfp_mask); -} - extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); -- cgit v1.2.3 From d6497816836da321a46c0e8575c4fa3d0c672bda Mon Sep 17 00:00:00 2001 From: Martin Sperl Date: Thu, 18 Feb 2016 15:53:10 +0000 Subject: spi: docbook: fix parsing error Fixes docbook parsing error because documentation is not directly followed by the structure, but typedef used in structure. Reordering should solve that issue. Signed-off-by: Martin Sperl Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38204b584dc5..5396ee5fc51f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -586,6 +586,10 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * SPI resource management while processing a SPI message */ +typedef void (*spi_res_release_t)(struct spi_master *master, + struct spi_message *msg, + void *res); + /** * struct spi_res - spi resource management structure * @entry: list entry @@ -595,9 +599,6 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * this is based on ideas from devres, but focused on life-cycle * management during spi_message processing */ -typedef void (*spi_res_release_t)(struct spi_master *master, - struct spi_message *msg, - void *res); struct spi_res { struct list_head entry; spi_res_release_t release; -- cgit v1.2.3 From 1b2ee1266ea647713dbaf44825967c180dfc8d76 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:21 -0800 Subject: mm/core: Do not enforce PKEY permissions on remote mm access We try to enforce protection keys in software the same way that we do in hardware. (See long example below). But, we only want to do this when accessing our *own* process's memory. If GDB set PKRU[6].AD=1 (disable access to PKEY 6), then tried to PTRACE_POKE a target process which just happened to have some mprotect_pkey(pkey=6) memory, we do *not* want to deny the debugger access to that memory. PKRU is fundamentally a thread-local structure and we do not want to enforce it on access to _another_ thread's data. This gets especially tricky when we have workqueues or other delayed-work mechanisms that might run in a random process's context. We can check that we only enforce pkeys when operating on our *own* mm, but delayed work gets performed when a random user context is active. We might end up with a situation where a delayed-work gup fails when running randomly under its "own" task but succeeds when running under another process. We want to avoid that. To avoid that, we use the new GUP flag: FOLL_REMOTE and add a fault flag: FAULT_FLAG_REMOTE. They indicate that we are walking an mm which is not guranteed to be the same as current->mm and should not be subject to protection key enforcement. Thanks to Jerome Glisse for pointing out this scenario. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Alexey Kardashevskiy Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Boaz Harrosh Cc: Borislav Petkov Cc: Brian Gerst Cc: Dan Williams Cc: Dave Chinner Cc: Dave Hansen Cc: David Gibson Cc: Denys Vlasenko Cc: Dominik Dingel Cc: Dominik Vogt Cc: Eric B Munson Cc: Geliang Tang Cc: Guan Xuetao Cc: H. Peter Anvin Cc: Heiko Carstens Cc: Hugh Dickins Cc: Jan Kara Cc: Jason Low Cc: Jerome Marchand Cc: Joerg Roedel Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Laurent Dufour Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michael Ellerman Cc: Michal Hocko Cc: Mikulas Patocka Cc: Minchan Kim Cc: Oleg Nesterov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Rik van Riel Cc: Sasha Levin Cc: Shachar Raindel Cc: Vlastimil Babka Cc: Xie XiuQi Cc: iommu@lists.linux-foundation.org Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-s390@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Ingo Molnar --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3056369bab1d..2aaa0f0d67ea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -251,6 +251,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */ #define FAULT_FLAG_TRIED 0x20 /* Second try */ #define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ +#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's -- cgit v1.2.3 From d61172b4b695b821388cdb6088a41d431bcbb93b Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:24 -0800 Subject: mm/core, x86/mm/pkeys: Differentiate instruction fetches As discussed earlier, we attempt to enforce protection keys in software. However, the code checks all faults to ensure that they are not violating protection key permissions. It was assumed that all faults are either write faults where we check PKRU[key].WD (write disable) or read faults where we check the AD (access disable) bit. But, there is a third category of faults for protection keys: instruction faults. Instruction faults never run afoul of protection keys because they do not affect instruction fetches. So, plumb the PF_INSTR bit down in to the arch_vma_access_permitted() function where we do the protection key checks. We also add a new FAULT_FLAG_INSTRUCTION. This is because handle_mm_fault() is not passed the architecture-specific error_code where we keep PF_INSTR, so we need to encode the instruction fetch information in to the arch-generic fault flags. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210224.96928009@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2aaa0f0d67ea..7955c3eb83db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -252,6 +252,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_TRIED 0x20 /* Second try */ #define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ #define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ +#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's -- cgit v1.2.3 From e6bfb70959a0ca6ddedb29e779a293c6f71ed0e7 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:31 -0800 Subject: mm/core, arch, powerpc: Pass a protection key in to calc_vm_flag_bits() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This plumbs a protection key through calc_vm_flag_bits(). We could have done this in calc_vm_prot_bits(), but I did not feel super strongly which way to go. It was pretty arbitrary which one to use. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arve Hjønnevåg Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Brian Gerst Cc: Chen Gang Cc: Dan Williams Cc: Dave Chinner Cc: Dave Hansen Cc: David Airlie Cc: Denys Vlasenko Cc: Eric W. Biederman Cc: Geliang Tang Cc: Greg Kroah-Hartman Cc: H. Peter Anvin Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Leon Romanovsky Cc: Linus Torvalds Cc: Masahiro Yamada Cc: Maxime Coquelin Cc: Mel Gorman Cc: Michael Ellerman Cc: Oleg Nesterov Cc: Paul Gortmaker Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Rik van Riel Cc: Riley Andrews Cc: Vladimir Davydov Cc: devel@driverdev.osuosl.org Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20160212210231.E6F1F0D6@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/mman.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 16373c8f5f57..33e17f6a327a 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -35,7 +35,7 @@ static inline void vm_unacct_memory(long pages) */ #ifndef arch_calc_vm_prot_bits -#define arch_calc_vm_prot_bits(prot) 0 +#define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_vm_get_page_prot @@ -70,12 +70,12 @@ static inline int arch_validate_prot(unsigned long prot) * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_prot_bits(unsigned long prot) +calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | - arch_calc_vm_prot_bits(prot); + arch_calc_vm_prot_bits(prot, pkey); } /* -- cgit v1.2.3 From 66d375709d2c891acc639538fd3179fa0cbb0daf Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:32 -0800 Subject: mm/core, x86/mm/pkeys: Add arch_validate_pkey() The syscall-level code is passed a protection key and need to return an appropriate error code if the protection key is bogus. We will be using this in subsequent patches. Note that this also begins a series of arch-specific calls that we need to expose in otherwise arch-independent code. We create a linux/pkeys.h header where we will put *all* the stubs for these functions. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210232.774EEAAB@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/pkeys.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/pkeys.h (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h new file mode 100644 index 000000000000..55e465f93a28 --- /dev/null +++ b/include/linux/pkeys.h @@ -0,0 +1,25 @@ +#ifndef _LINUX_PKEYS_H +#define _LINUX_PKEYS_H + +#include +#include + +#ifdef CONFIG_ARCH_HAS_PKEYS +#include +#else /* ! CONFIG_ARCH_HAS_PKEYS */ +#define arch_max_pkey() (1) +#endif /* ! CONFIG_ARCH_HAS_PKEYS */ + +/* + * This is called from mprotect_pkey(). + * + * Returns true if the protection keys is valid. + */ +static inline bool validate_pkey(int pkey) +{ + if (pkey < 0) + return false; + return (pkey < arch_max_pkey()); +} + +#endif /* _LINUX_PKEYS_H */ -- cgit v1.2.3 From 8459429693395ca9e8d18101300b120ad9171795 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:36 -0800 Subject: x86/mm/pkeys: Allow kernel to modify user pkey rights register The Protection Key Rights for User memory (PKRU) is a 32-bit user-accessible register. It contains two bits for each protection key: one to write-disable (WD) access to memory covered by the key and another to access-disable (AD). Userspace can read/write the register with the RDPKRU and WRPKRU instructions. But, the register is saved and restored with the XSAVE family of instructions, which means we have to treat it like a floating point register. The kernel needs to write to the register if it wants to implement execute-only memory or if it implements a system call to change PKRU. To do this, we need to create a 'pkru_state' buffer, read the old contents in to it, modify it, and then tell the FPU code that there is modified data in there so it can (possibly) move the buffer back in to the registers. This uses the fpu__xfeature_set_state() function that we defined in the previous patch. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210236.0BE13217@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/pkeys.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 55e465f93a28..fc325b367bd0 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -4,6 +4,11 @@ #include #include +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + #ifdef CONFIG_ARCH_HAS_PKEYS #include #else /* ! CONFIG_ARCH_HAS_PKEYS */ -- cgit v1.2.3 From 62b5f7d013fc455b8db26cf01e421f4c0d264b92 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:40 -0800 Subject: mm/core, x86/mm/pkeys: Add execute-only protection keys support Protection keys provide new page-based protection in hardware. But, they have an interesting attribute: they only affect data accesses and never affect instruction fetches. That means that if we set up some memory which is set as "access-disabled" via protection keys, we can still execute from it. This patch uses protection keys to set up mappings to do just that. If a user calls: mmap(..., PROT_EXEC); or mprotect(ptr, sz, PROT_EXEC); (note PROT_EXEC-only without PROT_READ/WRITE), the kernel will notice this, and set a special protection key on the memory. It also sets the appropriate bits in the Protection Keys User Rights (PKRU) register so that the memory becomes unreadable and unwritable. I haven't found any userspace that does this today. With this facility in place, we expect userspace to move to use it eventually. Userspace _could_ start doing this today. Any PROT_EXEC calls get converted to PROT_READ inside the kernel, and would transparently be upgraded to "true" PROT_EXEC with this code. IOW, userspace never has to do any PROT_EXEC runtime detection. This feature provides enhanced protection against leaking executable memory contents. This helps thwart attacks which are attempting to find ROP gadgets on the fly. But, the security provided by this approach is not comprehensive. The PKRU register which controls access permissions is a normal user register writable from unprivileged userspace. An attacker who can execute the 'wrpkru' instruction can easily disable the protection provided by this feature. The protection key that is used for execute-only support is permanently dedicated at compile time. This is fine for now because there is currently no API to set a protection key other than this one. Despite there being a constant PKRU value across the entire system, we do not set it unless this feature is in use in a process. That is to preserve the PKRU XSAVE 'init state', which can lead to faster context switches. PKRU *is* a user register and the kernel is modifying it. That means that code doing: pkru = rdpkru() pkru |= 0x100; mmap(..., PROT_EXEC); wrpkru(pkru); could lose the bits in PKRU that enforce execute-only permissions. To avoid this, we suggest avoiding ever calling mmap() or mprotect() when the PKRU value is expected to be unstable. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Chen Gang Cc: Dan Williams Cc: Dave Chinner Cc: Dave Hansen Cc: David Hildenbrand Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Kees Cook Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Linus Torvalds Cc: Mel Gorman Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Piotr Kwapulinski Cc: Rik van Riel Cc: Stephen Smalley Cc: Vladimir Murzin Cc: Will Deacon Cc: keescook@google.com Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210240.CB4BB5CA@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/linux/pkeys.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index fc325b367bd0..1d405a2b7272 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -13,6 +13,9 @@ #include #else /* ! CONFIG_ARCH_HAS_PKEYS */ #define arch_max_pkey() (1) +#define execute_only_pkey(mm) (0) +#define arch_override_mprotect_pkey(vma, prot, pkey) (0) +#define PKEY_DEDICATED_EXECUTE_ONLY 0 #endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* -- cgit v1.2.3 From 9e74a6dadbbf31ac18a2712048bf866c8e32aab2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 17 Feb 2016 11:23:55 -0800 Subject: net: Optimize local checksum offload This patch takes advantage of several assumptions we can make about the headers of the frame in order to reduce overall processing overhead for computing the outer header checksum. First we can assume the entire header is in the region pointed to by skb->head as this is what csum_start is based on. Second, as a result of our first assumption, we can just call csum_partial instead of making a call to skb_checksum which would end up having to configure things so that we could walk through the frags list. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 39206751463e..89b536796e53 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3713,19 +3713,18 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) */ static inline __wsum lco_csum(struct sk_buff *skb) { - char *inner_csum_field; - __wsum csum; + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *l4_hdr = skb_transport_header(skb); + __wsum partial; /* Start with complement of inner checksum adjustment */ - inner_csum_field = skb->data + skb_checksum_start_offset(skb) + - skb->csum_offset; - csum = ~csum_unfold(*(__force __sum16 *)inner_csum_field); + partial = ~csum_unfold(*(__force __sum16 *)(csum_start + + skb->csum_offset)); + /* Add in checksum of our headers (incl. outer checksum - * adjustment filled in by caller) + * adjustment filled in by caller) and return result. */ - csum = skb_checksum(skb, 0, skb_checksum_start_offset(skb), csum); - /* The result is the checksum from skb->data to end of packet */ - return csum; + return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 3f9b4a6972d50562613daa649ed064244e6bc7bb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Thu, 18 Feb 2016 17:00:39 +0200 Subject: qed: Lay infrastructure for vlan filtering offload Today, interfaces are working in vlan-promisc mode; But once vlan filtering offloaded would be supported, we'll need a method to control it directly [e.g., when setting device to PROMISC, or when running out of vlan credits]. This adds the necessary API for L2 client to manually choose whether to accept all vlans or only those for which filters were configured. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 81ab178e31c1..e53b0ca49e41 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -33,6 +33,8 @@ struct qed_update_vport_params { u8 vport_id; u8 update_vport_active_flg; u8 vport_active_flg; + u8 update_accept_any_vlan_flg; + u8 accept_any_vlan; u8 update_rss_flg; struct qed_update_vport_rss_params rss_params; }; -- cgit v1.2.3 From b44a7dfc6fa16e01f2497c9fa62c3926f94be174 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 28 Dec 2015 16:02:29 -0500 Subject: vfs: define a generic function to read a file from the kernel For a while it was looked down upon to directly read files from Linux. These days there exists a few mechanisms in the kernel that do just this though to load a file into a local buffer. There are minor but important checks differences on each. This patch set is the first attempt at resolving some of these differences. This patch introduces a common function for reading files from the kernel with the corresponding security post-read hook and function. Changelog v4+: - export security_kernel_post_read_file() - Fengguang Wu v3: - additional bounds checking - Luis v2: - To simplify patch review, re-ordered patches Signed-off-by: Mimi Zohar Reviewed-by: Luis R. Rodriguez Acked-by: Kees Cook Cc: Al Viro --- include/linux/fs.h | 1 + include/linux/lsm_hooks.h | 9 +++++++++ include/linux/security.h | 7 +++++++ 3 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ae681002100a..9a83d82b61ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2577,6 +2577,7 @@ static inline void i_readcount_inc(struct inode *inode) extern int do_pipe_flags(int *, int); extern int kernel_read(struct file *, loff_t, char *, unsigned long); +extern int kernel_read_file(struct file *, void **, loff_t *, loff_t); extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 71969de4058c..f82631cc7248 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -561,6 +561,13 @@ * the kernel module to load. If the module is being loaded from a blob, * this argument will be NULL. * Return 0 if permission is granted. + * @kernel_post_read_file: + * Read a file specified by userspace. + * @file contains the file structure pointing to the file being read + * by the kernel. + * @buf pointer to buffer containing the file contents. + * @size length of the file contents. + * Return 0 if permission is granted. * @task_fix_setuid: * Update the module's state after setting one or more of the user * identity attributes of the current process. The @flags parameter @@ -1457,6 +1464,7 @@ union security_list_options { int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); int (*kernel_module_request)(char *kmod_name); int (*kernel_module_from_file)(struct file *file); + int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size); int (*task_fix_setuid)(struct cred *new, const struct cred *old, int flags); int (*task_setpgid)(struct task_struct *p, pid_t pgid); @@ -1716,6 +1724,7 @@ struct security_hook_heads { struct list_head kernel_act_as; struct list_head kernel_create_files_as; struct list_head kernel_fw_from_file; + struct list_head kernel_post_read_file; struct list_head kernel_module_request; struct list_head kernel_module_from_file; struct list_head task_fix_setuid; diff --git a/include/linux/security.h b/include/linux/security.h index 4824a4ccaf1c..f30f5647d1e1 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -301,6 +301,7 @@ int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_fw_from_file(struct file *file, char *buf, size_t size); int security_kernel_module_request(char *kmod_name); int security_kernel_module_from_file(struct file *file); +int security_kernel_post_read_file(struct file *file, char *buf, loff_t size); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags); int security_task_setpgid(struct task_struct *p, pid_t pgid); @@ -866,6 +867,12 @@ static inline int security_kernel_module_from_file(struct file *file) return 0; } +static inline int security_kernel_post_read_file(struct file *file, + char *buf, loff_t size) +{ + return 0; +} + static inline int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) -- cgit v1.2.3 From bc8ca5b92d54f6f005fa73ad546f02fca26ddd85 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sun, 24 Jan 2016 10:07:32 -0500 Subject: vfs: define kernel_read_file_id enumeration To differentiate between the kernel_read_file() callers, this patch defines a new enumeration named kernel_read_file_id and includes the caller identifier as an argument. Subsequent patches define READING_KEXEC_IMAGE, READING_KEXEC_INITRAMFS, READING_FIRMWARE, READING_MODULE, and READING_POLICY. Changelog v3: - Replace the IMA specific enumeration with a generic one. Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Al Viro --- include/linux/fs.h | 7 ++++++- include/linux/lsm_hooks.h | 4 +++- include/linux/security.h | 7 +++++-- 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9a83d82b61ac..aa84bcb9c368 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2576,8 +2576,13 @@ static inline void i_readcount_inc(struct inode *inode) #endif extern int do_pipe_flags(int *, int); +enum kernel_read_file_id { + READING_MAX_ID +}; + extern int kernel_read(struct file *, loff_t, char *, unsigned long); -extern int kernel_read_file(struct file *, void **, loff_t *, loff_t); +extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, + enum kernel_read_file_id); extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index f82631cc7248..2337f33913c1 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -567,6 +567,7 @@ * by the kernel. * @buf pointer to buffer containing the file contents. * @size length of the file contents. + * @id kernel read file identifier * Return 0 if permission is granted. * @task_fix_setuid: * Update the module's state after setting one or more of the user @@ -1464,7 +1465,8 @@ union security_list_options { int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); int (*kernel_module_request)(char *kmod_name); int (*kernel_module_from_file)(struct file *file); - int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size); + int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size, + enum kernel_read_file_id id); int (*task_fix_setuid)(struct cred *new, const struct cred *old, int flags); int (*task_setpgid)(struct task_struct *p, pid_t pgid); diff --git a/include/linux/security.h b/include/linux/security.h index f30f5647d1e1..b68ce94e4e00 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -28,6 +28,7 @@ #include #include #include +#include struct linux_binprm; struct cred; @@ -301,7 +302,8 @@ int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_fw_from_file(struct file *file, char *buf, size_t size); int security_kernel_module_request(char *kmod_name); int security_kernel_module_from_file(struct file *file); -int security_kernel_post_read_file(struct file *file, char *buf, loff_t size); +int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, + enum kernel_read_file_id id); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags); int security_task_setpgid(struct task_struct *p, pid_t pgid); @@ -868,7 +870,8 @@ static inline int security_kernel_module_from_file(struct file *file) } static inline int security_kernel_post_read_file(struct file *file, - char *buf, loff_t size) + char *buf, loff_t size, + enum kernel_read_file_id id) { return 0; } -- cgit v1.2.3 From 9eb45d5cc541142896f5fe7896d824c1091197c9 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 15 Feb 2016 09:41:59 +0100 Subject: PCI: Update VPD definitions The 'end' tag is actually 0x0f; it's the representation as a small resource data type tag that's 0x78 (i.e., shifted by 3). Correct PCI_VPD_STIN_END and PCI_VPD_SRDT_END accordingly. Also, add helper functions to extract the resource data type tags for both large and small resource data types. [bhelgaas: changelog] Tested-by: Shane Seymour Tested-by: Babu Moger Signed-off-by: Hannes Reinecke Signed-off-by: Bjorn Helgaas Cc: Alexander Duyck --- include/linux/pci.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..49ad85c3e88e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1834,12 +1834,13 @@ bool pci_acs_path_enabled(struct pci_dev *start, #define PCI_VPD_LRDT_RW_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RW_DATA) /* Small Resource Data Type Tag Item Names */ -#define PCI_VPD_STIN_END 0x78 /* End */ +#define PCI_VPD_STIN_END 0x0f /* End */ -#define PCI_VPD_SRDT_END PCI_VPD_STIN_END +#define PCI_VPD_SRDT_END (PCI_VPD_STIN_END << 3) #define PCI_VPD_SRDT_TIN_MASK 0x78 #define PCI_VPD_SRDT_LEN_MASK 0x07 +#define PCI_VPD_LRDT_TIN_MASK 0x7f #define PCI_VPD_LRDT_TAG_SIZE 3 #define PCI_VPD_SRDT_TAG_SIZE 1 @@ -1862,6 +1863,17 @@ static inline u16 pci_vpd_lrdt_size(const u8 *lrdt) return (u16)lrdt[1] + ((u16)lrdt[2] << 8); } +/** + * pci_vpd_lrdt_tag - Extracts the Large Resource Data Type Tag Item + * @lrdt: Pointer to the beginning of the Large Resource Data Type tag + * + * Returns the extracted Large Resource Data Type Tag item. + */ +static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt) +{ + return (u16)(lrdt[0] & PCI_VPD_LRDT_TIN_MASK); +} + /** * pci_vpd_srdt_size - Extracts the Small Resource Data Type length * @lrdt: Pointer to the beginning of the Small Resource Data Type tag @@ -1873,6 +1885,17 @@ static inline u8 pci_vpd_srdt_size(const u8 *srdt) return (*srdt) & PCI_VPD_SRDT_LEN_MASK; } +/** + * pci_vpd_srdt_tag - Extracts the Small Resource Data Type Tag Item + * @lrdt: Pointer to the beginning of the Small Resource Data Type tag + * + * Returns the extracted Small Resource Data Type Tag Item. + */ +static inline u8 pci_vpd_srdt_tag(const u8 *srdt) +{ + return ((*srdt) & PCI_VPD_SRDT_TIN_MASK) >> 3; +} + /** * pci_vpd_info_field_size - Extracts the information field length * @lrdt: Pointer to the beginning of an information field header -- cgit v1.2.3 From ee2204a37957daed80418ea8ffc4f5c3146fb8e7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 Feb 2016 16:40:35 +0100 Subject: gpio: remove broken irq_to_gpio() interface gpiolib has removed the irq_to_gpio() API several years ago, but the global header still provided a non-working stub. To prevent new users of this broken function from showing up, let's remove the stubs as well. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij --- include/linux/gpio.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index d12b5d566e4b..6fc1c9e74854 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -70,11 +70,6 @@ static inline int gpio_to_irq(unsigned int gpio) return __gpio_to_irq(gpio); } -static inline int irq_to_gpio(unsigned int irq) -{ - return -EINVAL; -} - #endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ @@ -222,13 +217,6 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *chip, WARN_ON(1); } -static inline int irq_to_gpio(unsigned irq) -{ - /* irq can never have been returned from gpio_to_irq() */ - WARN_ON(1); - return -EINVAL; -} - static inline int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, -- cgit v1.2.3 From df4878e969ccc047da45d2cd3af5d08031da1593 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 12 Feb 2016 14:48:23 +0100 Subject: gpio: store reflect the label to userspace The gpio_chip label is useful for userspace to understand what kind of GPIO chip it is dealing with. Let's store a copy of this label in the gpio_device, add it to the struct passed to userspace for GPIO_GET_CHIPINFO_IOCTL and modify lsgpio to show it. Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index ff96d0f9fceb..639607658ed8 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -21,7 +21,8 @@ struct gpio_device; /** * struct gpio_chip - abstract a GPIO controller - * @label: for diagnostics + * @label: a functional name for the GPIO device, such as a part + * number or the name of the SoC IP-block implementing it. * @gpiodev: the internal state holder, opaque struct * @parent: optional parent device providing the GPIOs * @owner: helps prevent removal of modules exporting active GPIOs -- cgit v1.2.3 From d07ab6d114774d7fcb53c57d7474aef459713451 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 18 Feb 2016 10:54:11 +0200 Subject: block: Add blk_set_runtime_active() If block device is left runtime suspended during system suspend, resume hook of the driver typically corrects runtime PM status of the device back to "active" after it is resumed. However, this is not enough as queue's runtime PM status is still "suspended". As long as it is in this state blk_pm_peek_request() returns NULL and thus prevents new requests to be processed. Add new function blk_set_runtime_active() that can be used to force the queue status back to "active" as needed. Signed-off-by: Mika Westerberg Acked-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 29189aeace19..8a77c47f8d21 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1026,6 +1026,7 @@ extern int blk_pre_runtime_suspend(struct request_queue *q); extern void blk_post_runtime_suspend(struct request_queue *q, int err); extern void blk_pre_runtime_resume(struct request_queue *q); extern void blk_post_runtime_resume(struct request_queue *q, int err); +extern void blk_set_runtime_active(struct request_queue *q); #else static inline void blk_pm_runtime_init(struct request_queue *q, struct device *dev) {} @@ -1036,6 +1037,7 @@ static inline int blk_pre_runtime_suspend(struct request_queue *q) static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} static inline void blk_pre_runtime_resume(struct request_queue *q) {} static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} +extern inline void blk_set_runtime_active(struct request_queue *q) {} #endif /* -- cgit v1.2.3 From 91d31b9f8e7662726f273fc32b25f4099d78de4a Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:22:18 +0000 Subject: regmap: add regmap_update_bits_base() Current regmap has many similar update functions like below, but the difference is very few. regmap_update_bits() regmap_update_bits_async() regmap_update_bits_check() regmap_update_bits_check_async() Furthermore, we can add *force* write option too in the future. This patch adds new regmap_update_bits_base() which is feature merged function. Above functions can be merged into it by macro. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 18394343f489..28e50a3d2872 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -691,6 +691,9 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); +int regmap_update_bits_base(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change, bool async, bool force); int regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); int regmap_write_bits(struct regmap *map, unsigned int reg, @@ -937,6 +940,14 @@ static inline int regmap_bulk_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change, bool async, bool force) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val) { -- cgit v1.2.3 From ca7a94464b5457a8dc5add19f6fc3bea59d6193f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:22:42 +0000 Subject: regmap: merge regmap_update_bits() into macro Current regmap has many similar update functions like below, but the difference is very few. regmap_update_bits() regmap_update_bits_async() regmap_update_bits_check() regmap_update_bits_check_async() Furthermore, we can add *force* write option too in the future. This patch merges regmap_update_bits() into macro by using regmap_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 28e50a3d2872..500b36cbc7aa 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -65,6 +65,9 @@ struct reg_sequence { unsigned int delay_us; }; +#define regmap_update_bits(map, reg, mask, val) \ + regmap_update_bits_base(map, reg, mask, val, NULL, false, false) + #ifdef CONFIG_REGMAP enum regmap_endian { @@ -694,8 +697,6 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -int regmap_update_bits(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val); int regmap_write_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); int regmap_update_bits_async(struct regmap *map, unsigned int reg, @@ -948,13 +949,6 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, return -EINVAL; } -static inline int regmap_update_bits(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val) -{ - WARN_ONCE(1, "regmap API is disabled"); - return -EINVAL; -} - static inline int regmap_write_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val) { -- cgit v1.2.3 From 30ed9cb7a49b499ebc6061e4ff38e88cb4857cad Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:23:01 +0000 Subject: regmap: merge regmap_update_bits_async() into macro Current regmap has many similar update functions like below, but the difference is very few. regmap_update_bits() regmap_update_bits_async() regmap_update_bits_check() regmap_update_bits_check_async() Furthermore, we can add *force* write option too in the future. This patch merges regmap_update_bits_async() into macro by using regmap_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 500b36cbc7aa..90c8b0e99f9d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -67,6 +67,8 @@ struct reg_sequence { #define regmap_update_bits(map, reg, mask, val) \ regmap_update_bits_base(map, reg, mask, val, NULL, false, false) +#define regmap_update_bits_async(map, reg, mask, val)\ + regmap_update_bits_base(map, reg, mask, val, NULL, true, false) #ifdef CONFIG_REGMAP @@ -699,8 +701,6 @@ int regmap_update_bits_base(struct regmap *map, unsigned int reg, bool *change, bool async, bool force); int regmap_write_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); -int regmap_update_bits_async(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val); int regmap_update_bits_check(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change); @@ -956,14 +956,6 @@ static inline int regmap_write_bits(struct regmap *map, unsigned int reg, return -EINVAL; } -static inline int regmap_update_bits_async(struct regmap *map, - unsigned int reg, - unsigned int mask, unsigned int val) -{ - WARN_ONCE(1, "regmap API is disabled"); - return -EINVAL; -} - static inline int regmap_update_bits_check(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, -- cgit v1.2.3 From 98c2dc48694a47109fff430a216fc13a9b45a4a1 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:23:17 +0000 Subject: regmap: merge regmap_update_bits_check() into macro Current regmap has many similar update functions like below, but the difference is very few. regmap_update_bits() regmap_update_bits_async() regmap_update_bits_check() regmap_update_bits_check_async() Furthermore, we can add *force* write option too in the future. This patch merges regmap_update_bits_check() into macro by using regmap_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 90c8b0e99f9d..dd227dd5e5f8 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -69,6 +69,8 @@ struct reg_sequence { regmap_update_bits_base(map, reg, mask, val, NULL, false, false) #define regmap_update_bits_async(map, reg, mask, val)\ regmap_update_bits_base(map, reg, mask, val, NULL, true, false) +#define regmap_update_bits_check(map, reg, mask, val, change)\ + regmap_update_bits_base(map, reg, mask, val, change, false, false) #ifdef CONFIG_REGMAP @@ -701,9 +703,6 @@ int regmap_update_bits_base(struct regmap *map, unsigned int reg, bool *change, bool async, bool force); int regmap_write_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); -int regmap_update_bits_check(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val, - bool *change); int regmap_update_bits_check_async(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change); @@ -956,15 +955,6 @@ static inline int regmap_write_bits(struct regmap *map, unsigned int reg, return -EINVAL; } -static inline int regmap_update_bits_check(struct regmap *map, - unsigned int reg, - unsigned int mask, unsigned int val, - bool *change) -{ - WARN_ONCE(1, "regmap API is disabled"); - return -EINVAL; -} - static inline int regmap_update_bits_check_async(struct regmap *map, unsigned int reg, unsigned int mask, -- cgit v1.2.3 From 89d8d4b833b0b29e0e95bd0cd51e80f5ee7a6b0a Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:23:37 +0000 Subject: regmap: merge regmap_update_bits_check_async() into macro Current regmap has many similar update functions like below, but the difference is very few. regmap_update_bits() regmap_update_bits_async() regmap_update_bits_check() regmap_update_bits_check_async() Furthermore, we can add *force* write option too in the future. This patch merges regmap_update_bits_check_async() into macro by using regmap_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index dd227dd5e5f8..4d8e1edb4407 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -71,6 +71,8 @@ struct reg_sequence { regmap_update_bits_base(map, reg, mask, val, NULL, true, false) #define regmap_update_bits_check(map, reg, mask, val, change)\ regmap_update_bits_base(map, reg, mask, val, change, false, false) +#define regmap_update_bits_check_async(map, reg, mask, val, change)\ + regmap_update_bits_base(map, reg, mask, val, change, true, false) #ifdef CONFIG_REGMAP @@ -703,9 +705,6 @@ int regmap_update_bits_base(struct regmap *map, unsigned int reg, bool *change, bool async, bool force); int regmap_write_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); -int regmap_update_bits_check_async(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val, - bool *change); int regmap_get_val_bytes(struct regmap *map); int regmap_get_max_register(struct regmap *map); int regmap_get_reg_stride(struct regmap *map); @@ -955,16 +954,6 @@ static inline int regmap_write_bits(struct regmap *map, unsigned int reg, return -EINVAL; } -static inline int regmap_update_bits_check_async(struct regmap *map, - unsigned int reg, - unsigned int mask, - unsigned int val, - bool *change) -{ - WARN_ONCE(1, "regmap API is disabled"); - return -EINVAL; -} - static inline int regmap_get_val_bytes(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); -- cgit v1.2.3 From 28972eaa34f384eef5e33f36e00d8fa21ca44375 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:23:55 +0000 Subject: regmap: add regmap_field_update_bits_base() This patch adds new regmap_field_update_bits_base() which is using regmap_update_bits_base(). Current regmap_field_xxx() can be merged into it by macro. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d8e1edb4407..23bf7657e485 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -773,9 +773,11 @@ void devm_regmap_field_free(struct device *dev, struct regmap_field *field); int regmap_field_read(struct regmap_field *field, unsigned int *val); int regmap_field_write(struct regmap_field *field, unsigned int val); +int regmap_field_update_bits_base(struct regmap_field *field, + unsigned int mask, unsigned int val, + bool *change, bool async, bool force); int regmap_field_update_bits(struct regmap_field *field, unsigned int mask, unsigned int val); - int regmap_fields_write(struct regmap_field *field, unsigned int id, unsigned int val); int regmap_fields_force_write(struct regmap_field *field, unsigned int id, @@ -954,6 +956,14 @@ static inline int regmap_write_bits(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_field_update_bits_base(struct regmap_field *field, + unsigned int mask, unsigned int val, + bool *change, bool async, bool force) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_get_val_bytes(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); -- cgit v1.2.3 From 3674124b35894631f8f4d33ab041e713078bfd4b Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:24:15 +0000 Subject: regmap: merge regmap_field_write() into macro This patch merges regmap_field_write() into macro by using regmap_field_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 23bf7657e485..13e9ebdea1c7 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -74,6 +74,9 @@ struct reg_sequence { #define regmap_update_bits_check_async(map, reg, mask, val, change)\ regmap_update_bits_base(map, reg, mask, val, change, true, false) +#define regmap_field_write(field, val) \ + regmap_field_update_bits_base(field, ~0, val, NULL, false, false) + #ifdef CONFIG_REGMAP enum regmap_endian { @@ -772,7 +775,6 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev, void devm_regmap_field_free(struct device *dev, struct regmap_field *field); int regmap_field_read(struct regmap_field *field, unsigned int *val); -int regmap_field_write(struct regmap_field *field, unsigned int val); int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -- cgit v1.2.3 From 721ed64dda3774c619874866ca4f9a38ae6750af Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:24:33 +0000 Subject: regmap: merge regmap_field_update_bits() into macro This patch merges regmap_field_update_bits() into macro by using regmap_field_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 13e9ebdea1c7..e525beeaa2c6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -76,6 +76,8 @@ struct reg_sequence { #define regmap_field_write(field, val) \ regmap_field_update_bits_base(field, ~0, val, NULL, false, false) +#define regmap_field_update_bits(field, mask, val)\ + regmap_field_update_bits_base(field, mask, val, NULL, false, false) #ifdef CONFIG_REGMAP @@ -778,8 +780,6 @@ int regmap_field_read(struct regmap_field *field, unsigned int *val); int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -int regmap_field_update_bits(struct regmap_field *field, - unsigned int mask, unsigned int val); int regmap_fields_write(struct regmap_field *field, unsigned int id, unsigned int val); int regmap_fields_force_write(struct regmap_field *field, unsigned int id, -- cgit v1.2.3 From e126edec184ea3049cc1f8b652c6eeb06aa65fda Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:24:51 +0000 Subject: regmap: add regmap_fields_update_bits_base() This patch adds new regmap_fields_update_bits_base() which is using regmap_update_bits_base(). Current regmap_fields_xxx() can be merged into it by macro. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e525beeaa2c6..2735a3df7eab 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -788,6 +788,9 @@ int regmap_fields_read(struct regmap_field *field, unsigned int id, unsigned int *val); int regmap_fields_update_bits(struct regmap_field *field, unsigned int id, unsigned int mask, unsigned int val); +int regmap_fields_update_bits_base(struct regmap_field *field, unsigned int id, + unsigned int mask, unsigned int val, + bool *change, bool async, bool force); /** * Description of an IRQ for the generic regmap irq_chip. @@ -966,6 +969,15 @@ static inline int regmap_field_update_bits_base(struct regmap_field *field, return -EINVAL; } +static inline int regmap_fields_update_bits_base(struct regmap_field *field, + unsigned int id, + unsigned int mask, unsigned int val, + bool *change, bool async, bool force) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_get_val_bytes(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); -- cgit v1.2.3 From bbf2c46f46e23a496337e143cd012c013c6c7910 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:25:15 +0000 Subject: regmap: merge regmap_fields_write() into macro This patch merges regmap_fields_write() into macro by using regmap_fields_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 2735a3df7eab..5f438a4df5e6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -79,6 +79,9 @@ struct reg_sequence { #define regmap_field_update_bits(field, mask, val)\ regmap_field_update_bits_base(field, mask, val, NULL, false, false) +#define regmap_fields_write(field, id, val) \ + regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false) + #ifdef CONFIG_REGMAP enum regmap_endian { @@ -780,8 +783,6 @@ int regmap_field_read(struct regmap_field *field, unsigned int *val); int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -int regmap_fields_write(struct regmap_field *field, unsigned int id, - unsigned int val); int regmap_fields_force_write(struct regmap_field *field, unsigned int id, unsigned int val); int regmap_fields_read(struct regmap_field *field, unsigned int id, -- cgit v1.2.3 From 48138609135fc9c363f034596e14bff5dbf9f33f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:25:32 +0000 Subject: regmap: merge regmap_fields_update_bits() into macro This patch merges regmap_fields_update_bits() into macro by using regmap_field_update_bits_base(). Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 5f438a4df5e6..7d3d498fd3e8 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -81,6 +81,8 @@ struct reg_sequence { #define regmap_fields_write(field, id, val) \ regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false) +#define regmap_fields_update_bits(field, id, mask, val)\ + regmap_fields_update_bits_base(field, id, mask, val, NULL, false, false) #ifdef CONFIG_REGMAP @@ -787,8 +789,6 @@ int regmap_fields_force_write(struct regmap_field *field, unsigned int id, unsigned int val); int regmap_fields_read(struct regmap_field *field, unsigned int id, unsigned int *val); -int regmap_fields_update_bits(struct regmap_field *field, unsigned int id, - unsigned int mask, unsigned int val); int regmap_fields_update_bits_base(struct regmap_field *field, unsigned int id, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -- cgit v1.2.3 From e52bc7c28ac9f54db6f86b19ed65c599def18c98 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Fri, 19 Feb 2016 09:23:59 -0500 Subject: lib/bitmap.c: conversion routines to/from u32 array Aimed at transferring bitmaps to/from user-space in a 32/64-bit agnostic way. Tested: unit tests (next patch) on qemu i386, x86_64, ppc, ppc64 BE and LE, ARM. Signed-off-by: David Decotigny Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/bitmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 9653fdb76a42..e9b0b9ab07e5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -59,6 +59,8 @@ * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region + * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words) + * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words) */ /* @@ -163,6 +165,14 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); +extern unsigned int bitmap_from_u32array(unsigned long *bitmap, + unsigned int nbits, + const u32 *buf, + unsigned int nwords); +extern unsigned int bitmap_to_u32array(u32 *buf, + unsigned int nwords, + const unsigned long *bitmap, + unsigned int nbits); #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else -- cgit v1.2.3 From 421797b1aa363cb897f29f7d365e068dc9d9db81 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:02 -0500 Subject: net/ethtool: support get coalesce per queue This patch implements sub command ETHTOOL_GCOALESCE for ioctl ETHTOOL_PERQUEUE. It introduces an interface get_per_queue_coalesce to get coalesce of each masked queue from device driver. Then the interrupt coalescing parameters will be copied back to user space one by one. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 653dc9c4ebac..de56600023a7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -201,6 +201,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * @get_module_eeprom: Get the eeprom information from the plug-in module * @get_eee: Get Energy-Efficient (EEE) supported and status. * @set_eee: Set EEE status (enable/disable) as well as LPI timers. + * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue. + * It must check that the given queue number is valid. If neither a RX nor + * a TX queue has this number, return -EINVAL. If only a RX queue or a TX + * queue has this number, set the inapplicable fields to ~0 and return 0. + * Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -279,7 +284,8 @@ struct ethtool_ops { const struct ethtool_tunable *, void *); int (*set_tunable)(struct net_device *, const struct ethtool_tunable *, const void *); - + int (*get_per_queue_coalesce)(struct net_device *, u32, + struct ethtool_coalesce *); }; #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From f38d138a7da6510a1184e3bc5f425deb187c3265 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:03 -0500 Subject: net/ethtool: support set coalesce per queue This patch implements sub command ETHTOOL_SCOALESCE for ioctl ETHTOOL_PERQUEUE. It introduces an interface set_per_queue_coalesce to set coalesce of each masked queue to device driver. The wanted coalesce information are stored in "data" for each masked queue, which can copy from userspace. If it fails to set coalesce to device driver, the value which already set to specific queue will be tried to rollback. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de56600023a7..472d7d7b01c2 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -206,6 +206,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, set the inapplicable fields to ~0 and return 0. * Returns a negative error code or zero. + * @set_per_queue_coalesce: Set interrupt coalescing parameters per queue. + * It must check that the given queue number is valid. If neither a RX nor + * a TX queue has this number, return -EINVAL. If only a RX queue or a TX + * queue has this number, ignore the inapplicable fields. + * Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -286,6 +291,8 @@ struct ethtool_ops { const struct ethtool_tunable *, const void *); int (*get_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); + int (*set_per_queue_coalesce)(struct net_device *, u32, + struct ethtool_coalesce *); }; #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From 568b329a02f75ed3aaae5eb2cca384cb9e09cb29 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:57 -0800 Subject: perf: generalize perf_callchain . avoid walking the stack when there is no room left in the buffer . generalize get_perf_callchain() to be called from bpf helper Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/perf_event.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b35a61a481fa..7da3c25999df 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -964,11 +964,20 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs); +extern struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark); +extern int get_callchain_buffers(void); +extern void put_callchain_buffers(void); -static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) +static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) { - if (entry->nr < PERF_MAX_STACK_DEPTH) + if (entry->nr < PERF_MAX_STACK_DEPTH) { entry->ip[entry->nr++] = ip; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } extern int sysctl_perf_event_paranoid; -- cgit v1.2.3 From d5a3b1f691865be576c2bffa708549b8cdccda19 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:58 -0800 Subject: bpf: introduce BPF_MAP_TYPE_STACK_TRACE add new map type to store stack traces and corresponding helper bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id @ctx: struct pt_regs* @map: pointer to stack_trace map @flags: bits 0-7 - numer of stack frames to skip bit 8 - collect user stack instead of kernel bit 9 - compare stacks by hash only bit 10 - if two different stacks hash into the same stackid discard old other bits - reserved Return: >= 0 stackid on success or negative error stackid is a 32-bit integer handle that can be further combined with other data (including other stackid) and used as a key into maps. Userspace will access stackmap using standard lookup/delete syscall commands to retrieve full stack trace for given stackid. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 90ee6ab24bc5..0cadbb7456c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -237,6 +237,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); -- cgit v1.2.3 From 2307f3aab887bc43e0f262d298977fd9c6b9eee3 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 20 Feb 2016 12:53:31 +0100 Subject: Revert "gpio: remove broken irq_to_gpio() interface" This reverts commit ee2204a37957daed80418ea8ffc4f5c3146fb8e7. --- include/linux/gpio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 6fc1c9e74854..d12b5d566e4b 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -70,6 +70,11 @@ static inline int gpio_to_irq(unsigned int gpio) return __gpio_to_irq(gpio); } +static inline int irq_to_gpio(unsigned int irq) +{ + return -EINVAL; +} + #endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ @@ -217,6 +222,13 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *chip, WARN_ON(1); } +static inline int irq_to_gpio(unsigned irq) +{ + /* irq can never have been returned from gpio_to_irq() */ + WARN_ON(1); + return -EINVAL; +} + static inline int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, -- cgit v1.2.3 From f8560a9bc76b2cd5c06fa412cb7b5481d70fcf34 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Mon, 15 Feb 2016 19:12:01 +0200 Subject: stm class: Use driver's packet callback return value STM drivers provide a callback to generate/send individual STP packets; it also tells the stm core how many bytes of payload it has consumed. However, we would also need to use the negative space of this return value to communicate errors that occur during the packet generation, in which case the stm core will have to take appropriate action. For now, we need to account for the possibility that the stm driver may not support certain combinations of packet type/flags, in which case it is expected to signal an error. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/stm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stm.h b/include/linux/stm.h index 9d0083d364e6..ab8ceca4f570 100644 --- a/include/linux/stm.h +++ b/include/linux/stm.h @@ -67,6 +67,13 @@ struct stm_device; * description. That is, the lowest master that can be allocated to software * writers is @sw_start and data from this writer will appear is @sw_start * master in the STP stream. + * + * The @packet callback should adhere to the following rules: + * 1) it must return the number of bytes it consumed from the payload; + * 2) therefore, if it sent a packet that does not have payload (like FLAG), + * it must return zero; + * 3) if it does not support the requested packet type/flag combination, + * it must return -ENOTSUPP. */ struct stm_data { const char *name; -- cgit v1.2.3 From cc8424074e51355e0c6ba717d8edc50d408f2802 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Mon, 15 Feb 2016 19:12:09 +0200 Subject: stm class: Plug stm device's unlink callback STM device's unlink callback is never actually called from anywhere in the stm class code. This patch adds calls to stm driver's unlink method after the unlinking has succeeded. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- include/linux/stm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stm.h b/include/linux/stm.h index ab8ceca4f570..1a79ed8e43da 100644 --- a/include/linux/stm.h +++ b/include/linux/stm.h @@ -74,6 +74,9 @@ struct stm_device; * it must return zero; * 3) if it does not support the requested packet type/flag combination, * it must return -ENOTSUPP. + * + * The @unlink callback is called when there are no more active writers so + * that the master/channel can be quiesced. */ struct stm_data { const char *name; -- cgit v1.2.3 From b3e94405941e6916d5e365454d74560c2bea47ca Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:51:45 -0700 Subject: coresight: associating path with session rather than tracer When using the Coresight framework from the sysFS interface a tracer is always handling a single session and as such, a path can be associated with a tracer. But when supporting multiple session per tracer there is no guarantee that sessions will always have the same path from source to sink. This patch is removing the automatic association between path and tracers. The building of a path and enablement of the components in the path are decoupled, allowing for the association of a path with a session rather than a tracer. To keep backward functionality with the current sysFS access methods a per-cpu place holder is used to keep a handle on the path built when tracers are enabled. Lastly APIs to build paths and enable tracers are made public so that other subsystem can interact with the Coresight framework. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index bf62b265bf52..851ecb22397e 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -152,7 +152,6 @@ struct coresight_connection { by @coresight_ops. * @dev: The device entity associated to this component. * @refcnt: keep track of what is in use. - * @path_link: link of current component into the path being enabled. * @orphan: true if the component has connections that haven't been linked. * @enable: 'true' if component is currently part of an active path. * @activated: 'true' only if a _sink_ has been activated. A sink can be @@ -168,7 +167,6 @@ struct coresight_device { const struct coresight_ops *ops; struct device dev; atomic_t *refcnt; - struct list_head path_link; bool orphan; bool enable; /* true only if configured as part of a path */ bool activated; /* true only if a sink is part of a path */ -- cgit v1.2.3 From 22fd532eaa0c24d86e23d8e9e3b7feac4a8cac80 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:51:52 -0700 Subject: coresight: etm3x: adding operation mode for etm_enable() Adding a new mode to source API enable() in order to distinguish where the request comes from. That way it is possible to perform different operations based on where the request was issued from. The ETM4x driver is also modified to keep in sync with the new interface. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 851ecb22397e..61dfb8d511ea 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -213,7 +213,7 @@ struct coresight_ops_link { struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); int (*trace_id)(struct coresight_device *csdev); - int (*enable)(struct coresight_device *csdev); + int (*enable)(struct coresight_device *csdev, u32 mode); void (*disable)(struct coresight_device *csdev); }; -- cgit v1.2.3 From 882d5e112491c875ab7c8c336b8beaeec54d0509 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:51:57 -0700 Subject: coresight: etm3x: implementing perf_enable/disable() API That way traces can be enabled and disabled automatically from the Perf subystem using the PMU abstraction. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 61dfb8d511ea..6801dd64ee5d 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -14,6 +14,7 @@ #define _LINUX_CORESIGHT_H #include +#include #include /* Peripheral id registers (0xFD0-0xFEC) */ @@ -206,14 +207,15 @@ struct coresight_ops_link { * @cpu_id: returns the value of the CPU number this component * is associated to. * @trace_id: returns the value of the component's trace ID as known - to the HW. + * to the HW. * @enable: enables tracing for a source. * @disable: disables tracing for a source. */ struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); int (*trace_id)(struct coresight_device *csdev); - int (*enable)(struct coresight_device *csdev, u32 mode); + int (*enable)(struct coresight_device *csdev, + struct perf_event_attr *attr, u32 mode); void (*disable)(struct coresight_device *csdev); }; -- cgit v1.2.3 From e827d4550aa3225b8965ce4c266208cfe0297509 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:51:59 -0700 Subject: coresight: etb10: adding operation mode for sink->enable() Adding an operation mode to the sink->enable() API in order to prevent simultaneous access from different callers. TPIU and TMC won't be supplemented with the AUX area API immediately and as such ignore the new mode. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 6801dd64ee5d..9fa92dcdd2ea 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -186,7 +186,7 @@ struct coresight_device { * @disable: disables the sink. */ struct coresight_ops_sink { - int (*enable)(struct coresight_device *csdev); + int (*enable)(struct coresight_device *csdev, u32 mode); void (*disable)(struct coresight_device *csdev); }; -- cgit v1.2.3 From 2997aa4063d97fdb39450c6078bd81a7b0504f22 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:52:00 -0700 Subject: coresight: etb10: implementing AUX API Adding an ETB10 specific AUX area operations to be used by the perf framework when events are initialised. Part of this operation involves modeling the mmap'ed area based on the specific ways a sink buffer gathers information. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 9fa92dcdd2ea..385d62e64abb 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -182,12 +182,29 @@ struct coresight_device { /** * struct coresight_ops_sink - basic operations for a sink * Operations available for sinks - * @enable: enables the sink. - * @disable: disables the sink. + * @enable: enables the sink. + * @disable: disables the sink. + * @alloc_buffer: initialises perf's ring buffer for trace collection. + * @free_buffer: release memory allocated in @get_config. + * @set_buffer: initialises buffer mechanic before a trace session. + * @reset_buffer: finalises buffer mechanic after a trace session. + * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { int (*enable)(struct coresight_device *csdev, u32 mode); void (*disable)(struct coresight_device *csdev); + void *(*alloc_buffer)(struct coresight_device *csdev, int cpu, + void **pages, int nr_pages, bool overwrite); + void (*free_buffer)(void *config); + int (*set_buffer)(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config); + unsigned long (*reset_buffer)(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config, bool *lost); + void (*update_buffer)(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config); }; /** -- cgit v1.2.3 From 0bcbf2e30ff2271b54f54c8697a185f7d86ec6e4 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:52:01 -0700 Subject: coresight: etm-perf: new PMU driver for ETM tracers Perf is a well known and used tool for performance monitoring and much more. A such it is an ideal candidate for integration with coresight based HW tracing. This patch introduces a PMU that represent a coresight tracer to the Perf core. Cc: Alexander Shishkin Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight-pmu.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/coresight-pmu.h (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h new file mode 100644 index 000000000000..6c5386b23b10 --- /dev/null +++ b/include/linux/coresight-pmu.h @@ -0,0 +1,27 @@ +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier + * + * 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. + * + * 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. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + */ + +#ifndef _LINUX_CORESIGHT_PMU_H +#define _LINUX_CORESIGHT_PMU_H + +#define CORESIGHT_ETM_PMU_NAME "cs_etm" + +/* ETMv3.5/PTM's ETMCR config bit */ +#define ETM_OPT_CYCACC 12 +#define ETM_OPT_TS 28 + +#endif -- cgit v1.2.3 From 17534ceb835a1a96eb921a2a80df168723d6570a Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 17 Feb 2016 17:52:02 -0700 Subject: coresight: introducing a global trace ID function TraceID values have to be unique for all tracers and consistent between drivers and user space. As such introducing a central function to be used whenever a traceID value is required. The patch also account for data traceIDs, which are usually I(N) + 1. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight-pmu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 6c5386b23b10..7d410260661b 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -19,9 +19,21 @@ #define _LINUX_CORESIGHT_PMU_H #define CORESIGHT_ETM_PMU_NAME "cs_etm" +#define CORESIGHT_ETM_PMU_SEED 0x10 /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_TS 28 +static inline int coresight_get_trace_id(int cpu) +{ + /* + * A trace ID of value 0 is invalid, so let's start at some + * random value that fits in 7 bits and go from there. Since + * the common convention is to have data trace IDs be I(N) + 1, + * set instruction trace IDs as a function of the CPU number. + */ + return (CORESIGHT_ETM_PMU_SEED + (cpu * 2)); +} + #endif -- cgit v1.2.3 From 941943cf519f7cacbbcecee5c4ef4b77b466bd5c Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 17 Feb 2016 17:52:03 -0700 Subject: drivers/hwtracing: make coresight-* explicitly non-modular None of the Kconfig currently controlling compilation of any of the files here are tristate, meaning that none of it currently is being built as a module by anyone. We need not be concerned about .remove functions and blocking the unbind sysfs operations, since that was already done in a recent commit. Lets remove any remaining modular references, so that when reading the drivers there is no doubt they are builtin-only. All drivers get mostly the same changes, so they are handled in batch. Changes are (1) convert to builtin_amba_driver, (2) delete module.h include where unused, and (3) relocate the description into the comments so we don't need MODULE_DESCRIPTION and associated tags. The etm3x and etm4x use module_param_named, and have been adjusted to just include moduleparam.h for that purpose. In commit f309d4443130bf814e991f836e919dca22df37ae ("platform_device: better support builtin boilerplate avoidance") we introduced the builtin_driver macro. Here we use that support and extend it to amba driver registration, so where a driver is clearly non-modular and builtin-only, we can update with the simple mapping of module_amba_driver(...) ---> builtin_amba_driver(...) Since module_amba_driver() uses the same init level priority as builtin_amba_driver() the init ordering remains unchanged with this commit. Cc: Mathieu Poirier Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Paul Gortmaker Signed-off-by: Mathieu Poirier Acked-by: Russell King Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/bus.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 9006c4e75cf7..3d8dcdd1aeae 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -163,4 +163,13 @@ struct amba_device name##_device = { \ #define module_amba_driver(__amba_drv) \ module_driver(__amba_drv, amba_driver_register, amba_driver_unregister) +/* + * builtin_amba_driver() - Helper macro for drivers that don't do anything + * special in driver initcall. This eliminates a lot of boilerplate. Each + * driver may only use this macro once, and calling it replaces the instance + * device_initcall(). + */ +#define builtin_amba_driver(__amba_drv) \ + builtin_driver(__amba_drv, amba_driver_register) + #endif -- cgit v1.2.3 From cf2222178645e545e96717b2825601321ce4745c Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 14 Jan 2016 17:57:47 -0500 Subject: ima: define a new hook to measure and appraise a file already in memory This patch defines a new IMA hook ima_post_read_file() for measuring and appraising files read by the kernel. The caller loads the file into memory before calling this function, which calculates the hash followed by the normal IMA policy based processing. Changelog v5: - fail ima_post_read_file() if either file or buf is NULL v3: - rename ima_hash_and_process_file() to ima_post_read_file() v1: - split patch Signed-off-by: Mimi Zohar Acked-by: Dmitry Kasatkin --- include/linux/ima.h | 8 ++++++++ include/linux/security.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 120ccc53fcb7..d29a6a23fc19 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -20,6 +20,8 @@ extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_module_check(struct file *file); extern int ima_fw_from_file(struct file *file, char *buf, size_t size); +extern int ima_post_read_file(struct file *file, void *buf, loff_t size, + enum kernel_read_file_id id); #else static inline int ima_bprm_check(struct linux_binprm *bprm) @@ -52,6 +54,12 @@ static inline int ima_fw_from_file(struct file *file, char *buf, size_t size) return 0; } +static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, + enum kernel_read_file_id id) +{ + return 0; +} + #endif /* CONFIG_IMA */ #ifdef CONFIG_IMA_APPRAISE diff --git a/include/linux/security.h b/include/linux/security.h index b68ce94e4e00..d920718dc845 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -24,6 +24,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From 09596b94f7d28595602482e69ed954deab707437 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 19 Nov 2015 12:39:22 -0500 Subject: vfs: define kernel_read_file_from_path This patch defines kernel_read_file_from_path(), a wrapper for the VFS common kernel_read_file(). Changelog: - revert error msg regression - reported by Sergey Senozhatsky - Separated from the IMA patch Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index aa84bcb9c368..00fa5c45fd63 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2583,6 +2583,8 @@ enum kernel_read_file_id { extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, enum kernel_read_file_id); +extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, + enum kernel_read_file_id); extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); -- cgit v1.2.3 From e40ba6d56b41754b37b995dbc8035b2b3a6afd8a Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 19 Nov 2015 12:39:22 -0500 Subject: firmware: replace call to fw_read_file_contents() with kernel version Replace the fw_read_file_contents with kernel_file_read_from_path(). Although none of the upstreamed LSMs define a kernel_fw_from_file hook, IMA is called by the security function to prevent unsigned firmware from being loaded and to measure/appraise signed firmware, based on policy. Instead of reading the firmware twice, once for measuring/appraising the firmware and again for reading the firmware contents into memory, the kernel_post_read_file() security hook calculates the file hash based on the in memory file buffer. The firmware is read once. This patch removes the LSM kernel_fw_from_file() hook and security call. Changelog v4+: - revert dropped buf->size assignment - reported by Sergey Senozhatsky v3: - remove kernel_fw_from_file hook - use kernel_file_read_from_path() - requested by Luis v2: - reordered and squashed firmware patches - fix MAX firmware size (Kees Cook) Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez --- include/linux/fs.h | 1 + include/linux/ima.h | 6 ------ include/linux/lsm_hooks.h | 11 ----------- include/linux/security.h | 7 ------- 4 files changed, 1 insertion(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 00fa5c45fd63..c8bc4d8c843f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2577,6 +2577,7 @@ static inline void i_readcount_inc(struct inode *inode) extern int do_pipe_flags(int *, int); enum kernel_read_file_id { + READING_FIRMWARE = 1, READING_MAX_ID }; diff --git a/include/linux/ima.h b/include/linux/ima.h index d29a6a23fc19..7aea4863c244 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -19,7 +19,6 @@ extern int ima_file_check(struct file *file, int mask, int opened); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_module_check(struct file *file); -extern int ima_fw_from_file(struct file *file, char *buf, size_t size); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -49,11 +48,6 @@ static inline int ima_module_check(struct file *file) return 0; } -static inline int ima_fw_from_file(struct file *file, char *buf, size_t size) -{ - return 0; -} - static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id) { diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 2337f33913c1..7d04a1220223 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -541,15 +541,6 @@ * @inode points to the inode to use as a reference. * The current task must be the one that nominated @inode. * Return 0 if successful. - * @kernel_fw_from_file: - * Load firmware from userspace (not called for built-in firmware). - * @file contains the file structure pointing to the file containing - * the firmware to load. This argument will be NULL if the firmware - * was loaded via the uevent-triggered blob-based interface exposed - * by CONFIG_FW_LOADER_USER_HELPER. - * @buf pointer to buffer containing firmware contents. - * @size length of the firmware contents. - * Return 0 if permission is granted. * @kernel_module_request: * Ability to trigger the kernel to automatically upcall to userspace for * userspace to load a kernel module with the given name. @@ -1462,7 +1453,6 @@ union security_list_options { void (*cred_transfer)(struct cred *new, const struct cred *old); int (*kernel_act_as)(struct cred *new, u32 secid); int (*kernel_create_files_as)(struct cred *new, struct inode *inode); - int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); int (*kernel_module_request)(char *kmod_name); int (*kernel_module_from_file)(struct file *file); int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size, @@ -1725,7 +1715,6 @@ struct security_hook_heads { struct list_head cred_transfer; struct list_head kernel_act_as; struct list_head kernel_create_files_as; - struct list_head kernel_fw_from_file; struct list_head kernel_post_read_file; struct list_head kernel_module_request; struct list_head kernel_module_from_file; diff --git a/include/linux/security.h b/include/linux/security.h index d920718dc845..cee1349e1155 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -300,7 +300,6 @@ int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp); void security_transfer_creds(struct cred *new, const struct cred *old); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); -int security_kernel_fw_from_file(struct file *file, char *buf, size_t size); int security_kernel_module_request(char *kmod_name); int security_kernel_module_from_file(struct file *file); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, @@ -854,12 +853,6 @@ static inline int security_kernel_create_files_as(struct cred *cred, return 0; } -static inline int security_kernel_fw_from_file(struct file *file, - char *buf, size_t size) -{ - return 0; -} - static inline int security_kernel_module_request(char *kmod_name) { return 0; -- cgit v1.2.3 From 39eeb4fb97f60dbdfc823c1a673a8844b9226b60 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sat, 30 Jan 2016 22:23:26 -0500 Subject: security: define kernel_read_file hook The kernel_read_file security hook is called prior to reading the file into memory. Changelog v4+: - export security_kernel_read_file() Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Acked-by: Casey Schaufler --- include/linux/ima.h | 6 ++++++ include/linux/lsm_hooks.h | 8 ++++++++ include/linux/security.h | 7 +++++++ 3 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 7aea4863c244..6adcaea8101c 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -19,6 +19,7 @@ extern int ima_file_check(struct file *file, int mask, int opened); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_module_check(struct file *file); +extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -48,6 +49,11 @@ static inline int ima_module_check(struct file *file) return 0; } +static inline int ima_read_file(struct file *file, enum kernel_read_file_id id) +{ + return 0; +} + static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id) { diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7d04a1220223..d32b7bd13635 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -552,6 +552,12 @@ * the kernel module to load. If the module is being loaded from a blob, * this argument will be NULL. * Return 0 if permission is granted. + * @kernel_read_file: + * Read a file specified by userspace. + * @file contains the file structure pointing to the file being read + * by the kernel. + * @id kernel read file identifier + * Return 0 if permission is granted. * @kernel_post_read_file: * Read a file specified by userspace. * @file contains the file structure pointing to the file being read @@ -1455,6 +1461,7 @@ union security_list_options { int (*kernel_create_files_as)(struct cred *new, struct inode *inode); int (*kernel_module_request)(char *kmod_name); int (*kernel_module_from_file)(struct file *file); + int (*kernel_read_file)(struct file *file, enum kernel_read_file_id id); int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); int (*task_fix_setuid)(struct cred *new, const struct cred *old, @@ -1715,6 +1722,7 @@ struct security_hook_heads { struct list_head cred_transfer; struct list_head kernel_act_as; struct list_head kernel_create_files_as; + struct list_head kernel_read_file; struct list_head kernel_post_read_file; struct list_head kernel_module_request; struct list_head kernel_module_from_file; diff --git a/include/linux/security.h b/include/linux/security.h index cee1349e1155..071fb747fdbb 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -302,6 +302,7 @@ int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); int security_kernel_module_from_file(struct file *file); +int security_kernel_read_file(struct file *file, enum kernel_read_file_id id); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); int security_task_fix_setuid(struct cred *new, const struct cred *old, @@ -863,6 +864,12 @@ static inline int security_kernel_module_from_file(struct file *file) return 0; } +static inline int security_kernel_read_file(struct file *file, + enum kernel_read_file_id id) +{ + return 0; +} + static inline int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) -- cgit v1.2.3 From b844f0ecbc5626ec26cfc70cb144a4c9b85dc3f2 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 1 Feb 2016 08:36:21 -0500 Subject: vfs: define kernel_copy_file_from_fd() This patch defines kernel_read_file_from_fd(), a wrapper for the VFS common kernel_read_file(). Changelog: - Separated from the kernel modules patch Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Al Viro Signed-off-by: Mimi Zohar --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c8bc4d8c843f..9c85deae1bf2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2586,6 +2586,8 @@ extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, enum kernel_read_file_id); extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, enum kernel_read_file_id); +extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, + enum kernel_read_file_id); extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); -- cgit v1.2.3 From a1db74209483a24c861c848b4bb79a4d945ef6fa Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 30 Dec 2015 07:35:30 -0500 Subject: module: replace copy_module_from_fd with kernel version Replace copy_module_from_fd() with kernel_read_file_from_fd(). Although none of the upstreamed LSMs define a kernel_module_from_file hook, IMA is called, based on policy, to prevent unsigned kernel modules from being loaded by the original kernel module syscall and to measure/appraise signed kernel modules. The security function security_kernel_module_from_file() was called prior to reading a kernel module. Preventing unsigned kernel modules from being loaded by the original kernel module syscall remains on the pre-read kernel_read_file() security hook. Instead of reading the kernel module twice, once for measuring/appraising and again for loading the kernel module, the signature validation is moved to the kernel_post_read_file() security hook. This patch removes the security_kernel_module_from_file() hook and security call. Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Rusty Russell --- include/linux/fs.h | 1 + include/linux/ima.h | 6 ------ include/linux/lsm_hooks.h | 7 ------- include/linux/security.h | 5 ----- 4 files changed, 1 insertion(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9c85deae1bf2..fb08b668c37a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2578,6 +2578,7 @@ extern int do_pipe_flags(int *, int); enum kernel_read_file_id { READING_FIRMWARE = 1, + READING_MODULE, READING_MAX_ID }; diff --git a/include/linux/ima.h b/include/linux/ima.h index 6adcaea8101c..e6516cbbe9bf 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,7 +18,6 @@ extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask, int opened); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); -extern int ima_module_check(struct file *file); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -44,11 +43,6 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } -static inline int ima_module_check(struct file *file) -{ - return 0; -} - static inline int ima_read_file(struct file *file, enum kernel_read_file_id id) { return 0; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d32b7bd13635..cdee11cbcdf1 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -546,12 +546,6 @@ * userspace to load a kernel module with the given name. * @kmod_name name of the module requested by the kernel * Return 0 if successful. - * @kernel_module_from_file: - * Load a kernel module from userspace. - * @file contains the file structure pointing to the file containing - * the kernel module to load. If the module is being loaded from a blob, - * this argument will be NULL. - * Return 0 if permission is granted. * @kernel_read_file: * Read a file specified by userspace. * @file contains the file structure pointing to the file being read @@ -1725,7 +1719,6 @@ struct security_hook_heads { struct list_head kernel_read_file; struct list_head kernel_post_read_file; struct list_head kernel_module_request; - struct list_head kernel_module_from_file; struct list_head task_fix_setuid; struct list_head task_setpgid; struct list_head task_getpgid; diff --git a/include/linux/security.h b/include/linux/security.h index 071fb747fdbb..157f0cb1e4d2 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -859,11 +859,6 @@ static inline int security_kernel_module_request(char *kmod_name) return 0; } -static inline int security_kernel_module_from_file(struct file *file) -{ - return 0; -} - static inline int security_kernel_read_file(struct file *file, enum kernel_read_file_id id) { -- cgit v1.2.3 From b804defe4297157a9ff45863769efe9a01953398 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 14 Jan 2016 20:59:14 -0500 Subject: kexec: replace call to copy_file_from_fd() with kernel version Replace copy_file_from_fd() with kernel_read_file_from_fd(). Two new identifiers named READING_KEXEC_IMAGE and READING_KEXEC_INITRAMFS are defined for measuring, appraising or auditing the kexec image and initramfs. Changelog v3: - return -EBADF, not -ENOEXEC - identifier change - split patch, moving copy_file_from_fd() to a separate patch - split patch, moving IMA changes to a separate patch v0: - use kstat file size type loff_t, not size_t - Calculate the file hash from the in memory buffer - Dave Young Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Eric Biederman Acked-by: Dave Young --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fb08b668c37a..52567252288e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2579,6 +2579,8 @@ extern int do_pipe_flags(int *, int); enum kernel_read_file_id { READING_FIRMWARE = 1, READING_MODULE, + READING_KEXEC_IMAGE, + READING_KEXEC_INITRAMFS, READING_MAX_ID }; -- cgit v1.2.3 From 7429b092811fb20c6a5b261c2c116a6a90cb9a29 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Fri, 11 Apr 2014 17:47:01 +0300 Subject: ima: load policy using path We currently cannot do appraisal or signature vetting of IMA policies since we currently can only load IMA policies by writing the contents of the policy directly in, as follows: cat policy-file > /ima/policy If we provide the kernel the path to the IMA policy so it can load the policy itself it'd be able to later appraise or vet the file signature if it has one. This patch adds support to load the IMA policy with a given path as follows: echo /etc/ima/ima_policy > /sys/kernel/security/ima/policy Changelog v4+: - moved kernel_read_file_from_path() error messages to callers v3: - moved kernel_read_file_from_path() to a separate patch v2: - after re-ordering the patches, replace calling integrity_kernel_read() to read the file with kernel_read_file_from_path() (Mimi) - Patch description re-written by Luis R. Rodriguez Signed-off-by: Dmitry Kasatkin Signed-off-by: Mimi Zohar --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 52567252288e..e514f76db04f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2581,6 +2581,7 @@ enum kernel_read_file_id { READING_MODULE, READING_KEXEC_IMAGE, READING_KEXEC_INITRAMFS, + READING_POLICY, READING_MAX_ID }; -- cgit v1.2.3 From 8e2fe1d9f1a20924f98ea46931a1d7fb092aa876 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:22 +0100 Subject: bpf: add new arg_type that allows for 0 sized stack buffer Currently, when we pass a buffer from the eBPF stack into a helper function, the function proto indicates argument types as ARG_PTR_TO_STACK and ARG_CONST_STACK_SIZE pair. If R contains the former, then R must be of the latter type. Then, verifier checks whether the buffer points into eBPF stack, is initialized, etc. The verifier also guarantees that the constant value passed in R is greater than 0, so helper functions don't need to test for it and can always assume a non-NULL initialized buffer as well as non-0 buffer size. This patch adds a new argument types ARG_CONST_STACK_SIZE_OR_ZERO that allows to also pass NULL as R and 0 as R into the helper function. Such helper functions, of course, need to be able to handle these cases internally then. Verifier guarantees that either R == NULL && R == 0 or R != NULL && R != 0 (like the case of ARG_CONST_STACK_SIZE), any other combinations are not possible to load. I went through various options of extending the verifier, and introducing the type ARG_CONST_STACK_SIZE_OR_ZERO seems to have most minimal changes needed to the verifier. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0cadbb7456c0..51e498e5470e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -65,6 +65,7 @@ enum bpf_arg_type { */ ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ -- cgit v1.2.3 From 3697649ff29e0f647565eed04b27a7779c646a22 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:25 +0100 Subject: bpf: try harder on clones when writing into skb When we're dealing with clones and the area is not writeable, try harder and get a copy via pskb_expand_head(). Replace also other occurences in tc actions with the new skb_try_make_writable(). Reported-by: Ashhad Sheikh Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89b536796e53..6a57757a86cf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2630,6 +2630,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len skb_headroom(skb) + len <= skb->hdr_len; } +static inline int skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC); +} + static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { -- cgit v1.2.3 From 944945986f125bdbbeaa78dac0c0eadb963eb34a Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 11:40:10 +0200 Subject: qed: Introduce DMA_REGPAIR_LE FW hsi contains regpairs, mostly for 64-bit address representations. Since same paradigm is applied each time a regpair is filled, this introduces a new utility macro for setting such regpairs. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 41b9049b57e2..5f8fcaaa6504 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -19,6 +19,10 @@ /* dma_addr_t manip */ #define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) #define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) +#define DMA_REGPAIR_LE(x, val) do { \ + (x).hi = DMA_HI_LE((val)); \ + (x).lo = DMA_LO_LE((val)); \ + } while (0) #define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo)) #define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t) -- cgit v1.2.3 From 662b1d890c593673964758fe5b6f22067bffba7a Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Wed, 17 Feb 2016 12:35:54 +0000 Subject: efi: Reformat GUID tables to follow the format in UEFI spec This makes it much easier to hunt for typos in the GUID definitions. It also makes checkpatch complain less about efi.h GUID additions, so that if you add another one with the same style, checkpatch won't complain about it. Signed-off-by: Peter Jones Signed-off-by: Matt Fleming Cc: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1455712566-16727-2-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 63 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 42 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 1acd72364297..42be9c92fdf0 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -536,67 +536,88 @@ void efi_native_runtime_setup(void); * EFI Configuration Table and GUID definitions */ #define NULL_GUID \ - EFI_GUID( 0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ) + EFI_GUID(0x00000000, 0x0000, 0x0000, \ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00) #define MPS_TABLE_GUID \ - EFI_GUID( 0xeb9d2d2f, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d ) + EFI_GUID(0xeb9d2d2f, 0x2d88, 0x11d3, \ + 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define ACPI_TABLE_GUID \ - EFI_GUID( 0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d ) + EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, \ + 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define ACPI_20_TABLE_GUID \ - EFI_GUID( 0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x0, 0x80, 0xc7, 0x3c, 0x88, 0x81 ) + EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, \ + 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) #define SMBIOS_TABLE_GUID \ - EFI_GUID( 0xeb9d2d31, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d ) + EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3, \ + 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define SMBIOS3_TABLE_GUID \ - EFI_GUID( 0xf2fd1544, 0x9794, 0x4a2c, 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94 ) + EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c, \ + 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94) #define SAL_SYSTEM_TABLE_GUID \ - EFI_GUID( 0xeb9d2d32, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d ) + EFI_GUID(0xeb9d2d32, 0x2d88, 0x11d3, \ + 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define HCDP_TABLE_GUID \ - EFI_GUID( 0xf951938d, 0x620b, 0x42ef, 0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98 ) + EFI_GUID(0xf951938d, 0x620b, 0x42ef, \ + 0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98) #define UGA_IO_PROTOCOL_GUID \ - EFI_GUID( 0x61a4d49e, 0x6f68, 0x4f1b, 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0xb, 0x7, 0xa2 ) + EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b, \ + 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2) #define EFI_GLOBAL_VARIABLE_GUID \ - EFI_GUID( 0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c ) + EFI_GUID(0x8be4df61, 0x93ca, 0x11d2, \ + 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c) #define UV_SYSTEM_TABLE_GUID \ - EFI_GUID( 0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93 ) + EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, \ + 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93) #define LINUX_EFI_CRASH_GUID \ - EFI_GUID( 0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0 ) + EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, \ + 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0) #define LOADED_IMAGE_PROTOCOL_GUID \ - EFI_GUID( 0x5b1b31a1, 0x9562, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) + EFI_GUID(0x5b1b31a1, 0x9562, 0x11d2, \ + 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID \ - EFI_GUID( 0x9042a9de, 0x23dc, 0x4a38, 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a ) + EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, \ + 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a) #define EFI_UGA_PROTOCOL_GUID \ - EFI_GUID( 0x982c298b, 0xf4fa, 0x41cb, 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39 ) + EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, \ + 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39) #define EFI_PCI_IO_PROTOCOL_GUID \ - EFI_GUID( 0x4cf5b200, 0x68b8, 0x4ca5, 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x2, 0x9a ) + EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, \ + 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a) #define EFI_FILE_INFO_ID \ - EFI_GUID( 0x9576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) + EFI_GUID(0x9576e92, 0x6d3f, 0x11d2, \ + 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_SYSTEM_RESOURCE_TABLE_GUID \ - EFI_GUID( 0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 ) + EFI_GUID(0xb122a263, 0x3661, 0x4f68, \ + 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80) #define EFI_FILE_SYSTEM_GUID \ - EFI_GUID( 0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) + EFI_GUID(0x964e5b22, 0x6459, 0x11d2, \ + 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define DEVICE_TREE_GUID \ - EFI_GUID( 0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0 ) + EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5, \ + 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0) #define EFI_PROPERTIES_TABLE_GUID \ - EFI_GUID( 0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5 ) + EFI_GUID(0x880aaca3, 0x4adc, 0x4a04, \ + 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5) typedef struct { efi_guid_t guid; -- cgit v1.2.3 From 9575632052bacc2fda38d845eb17b0fb808e13eb Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 15 Feb 2016 22:27:02 +0530 Subject: dmaengine: make slave address physical MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The slave dmaengine semantics required the client to map dma addresses and pass DMA address to dmaengine drivers. This was a convenient notion coming from generic dma offload cases where dmaengines are interchangeable and client is not aware of which engine to map to. But in case of slave, we know the dmaengine and always use a specific one. Further the IOMMU cases can lead to failure of this notion, so make this as physical address and now dmaengine driver will do the required mapping. Original-patch-by: Linus Walleij Original-patch-Acked-by: Lee Jones Reviewed-by: Laurent Pinchart Acked-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Acked-by: Wolfram Sang Tested-by: Wolfram Sang Tested-by: Niklas Söderlund Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 16a1cad30c33..d85ecd20af50 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -357,8 +357,8 @@ enum dma_slave_buswidth { */ struct dma_slave_config { enum dma_transfer_direction direction; - dma_addr_t src_addr; - dma_addr_t dst_addr; + phys_addr_t src_addr; + phys_addr_t dst_addr; enum dma_slave_buswidth src_addr_width; enum dma_slave_buswidth dst_addr_width; u32 src_maxburst; -- cgit v1.2.3 From f083b09b7819c785db4f82a81f68da3bccfb04bf Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Sat, 6 Feb 2016 18:38:46 -0500 Subject: dm: set DM_TARGET_WILDCARD feature on "error" target The DM_TARGET_WILDCARD feature indicates that the "error" target may replace any target; even immutable targets. This feature will be useful to preserve the ability to replace the "multipath" target even once it is formally converted over to having the DM_TARGET_IMMUTABLE feature. Also, implicit in the DM_TARGET_WILDCARD feature flag being set is that .map, .map_rq, .clone_and_map_rq and .release_clone_rq are all defined in the target_type. Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ec1c61c87d89..87d50ecbc9df 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -189,6 +189,13 @@ struct target_type { #define DM_TARGET_IMMUTABLE 0x00000004 #define dm_target_is_immutable(type) ((type)->features & DM_TARGET_IMMUTABLE) +/* + * Indicates that a target may replace any target; even immutable targets. + * .map, .map_rq, .clone_and_map_rq and .release_clone_rq are all defined. + */ +#define DM_TARGET_WILDCARD 0x00000008 +#define dm_target_is_wildcard(type) ((type)->features & DM_TARGET_WILDCARD) + /* * Some targets need to be sent the same WRITE bio severals times so * that they can send copies of it to different devices. This function -- cgit v1.2.3 From f9a61eb4e2471c56a63cd804c7474128138c38ac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 11:49:09 -0500 Subject: mbcache2: reimplement mbcache Original mbcache was designed to have more features than what ext? filesystems ended up using. It supported entry being in more hashes, it had a home-grown rwlocking of each entry, and one cache could cache entries from multiple filesystems. This genericity also resulted in more complex locking, larger cache entries, and generally more code complexity. This is reimplementation of the mbcache functionality to exactly fit the purpose ext? filesystems use it for. Cache entries are now considerably smaller (7 instead of 13 longs), the code is considerably smaller as well (414 vs 913 lines of code), and IMO also simpler. The new code is also much more lightweight. I have measured the speed using artificial xattr-bench benchmark, which spawns P processes, each process sets xattr for F different files, and the value of xattr is randomly chosen from a pool of V values. Averages of runtimes for 5 runs for various combinations of parameters are below. The first value in each cell is old mbache, the second value is the new mbcache. V=10 F\P 1 2 4 8 16 32 64 10 0.158,0.157 0.208,0.196 0.500,0.277 0.798,0.400 3.258,0.584 13.807,1.047 61.339,2.803 100 0.172,0.167 0.279,0.222 0.520,0.275 0.825,0.341 2.981,0.505 12.022,1.202 44.641,2.943 1000 0.185,0.174 0.297,0.239 0.445,0.283 0.767,0.340 2.329,0.480 6.342,1.198 16.440,3.888 V=100 F\P 1 2 4 8 16 32 64 10 0.162,0.153 0.200,0.186 0.362,0.257 0.671,0.496 1.433,0.943 3.801,1.345 7.938,2.501 100 0.153,0.160 0.221,0.199 0.404,0.264 0.945,0.379 1.556,0.485 3.761,1.156 7.901,2.484 1000 0.215,0.191 0.303,0.246 0.471,0.288 0.960,0.347 1.647,0.479 3.916,1.176 8.058,3.160 V=1000 F\P 1 2 4 8 16 32 64 10 0.151,0.129 0.210,0.163 0.326,0.245 0.685,0.521 1.284,0.859 3.087,2.251 6.451,4.801 100 0.154,0.153 0.211,0.191 0.276,0.282 0.687,0.506 1.202,0.877 3.259,1.954 8.738,2.887 1000 0.145,0.179 0.202,0.222 0.449,0.319 0.899,0.333 1.577,0.524 4.221,1.240 9.782,3.579 V=10000 F\P 1 2 4 8 16 32 64 10 0.161,0.154 0.198,0.190 0.296,0.256 0.662,0.480 1.192,0.818 2.989,2.200 6.362,4.746 100 0.176,0.174 0.236,0.203 0.326,0.255 0.696,0.511 1.183,0.855 4.205,3.444 19.510,17.760 1000 0.199,0.183 0.240,0.227 1.159,1.014 2.286,2.154 6.023,6.039 ---,10.933 ---,36.620 V=100000 F\P 1 2 4 8 16 32 64 10 0.171,0.162 0.204,0.198 0.285,0.230 0.692,0.500 1.225,0.881 2.990,2.243 6.379,4.771 100 0.151,0.171 0.220,0.210 0.295,0.255 0.720,0.518 1.226,0.844 3.423,2.831 19.234,17.544 1000 0.192,0.189 0.249,0.225 1.162,1.043 2.257,2.093 5.853,4.997 ---,10.399 ---,32.198 We see that the new code is faster in pretty much all the cases and starting from 4 processes there are significant gains with the new code resulting in upto 20-times shorter runtimes. Also for large numbers of cached entries all values for the old code could not be measured as the kernel started hitting softlockups and died before the test completed. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/mbcache2.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/linux/mbcache2.h (limited to 'include/linux') diff --git a/include/linux/mbcache2.h b/include/linux/mbcache2.h new file mode 100644 index 000000000000..b6f160ff2533 --- /dev/null +++ b/include/linux/mbcache2.h @@ -0,0 +1,50 @@ +#ifndef _LINUX_MB2CACHE_H +#define _LINUX_MB2CACHE_H + +#include +#include +#include +#include +#include + +struct mb2_cache; + +struct mb2_cache_entry { + /* LRU list - protected by cache->c_lru_list_lock */ + struct list_head e_lru_list; + /* Hash table list - protected by bitlock in e_hash_list_head */ + struct hlist_bl_node e_hash_list; + atomic_t e_refcnt; + /* Key in hash - stable during lifetime of the entry */ + u32 e_key; + /* Block number of hashed block - stable during lifetime of the entry */ + sector_t e_block; + /* Head of hash list (for list bit lock) - stable */ + struct hlist_bl_head *e_hash_list_head; +}; + +struct mb2_cache *mb2_cache_create(int bucket_bits); +void mb2_cache_destroy(struct mb2_cache *cache); + +int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key, + sector_t block); +void __mb2_cache_entry_free(struct mb2_cache_entry *entry); +static inline int mb2_cache_entry_put(struct mb2_cache *cache, + struct mb2_cache_entry *entry) +{ + if (!atomic_dec_and_test(&entry->e_refcnt)) + return 0; + __mb2_cache_entry_free(entry); + return 1; +} + +void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key, + sector_t block); +struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache, + u32 key); +struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache, + struct mb2_cache_entry *entry); +void mb2_cache_entry_touch(struct mb2_cache *cache, + struct mb2_cache_entry *entry); + +#endif /* _LINUX_MB2CACHE_H */ -- cgit v1.2.3 From ecd1e64412d5242b8afdef58a714bab3c5464f79 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 12:21:14 -0500 Subject: mbcache: remove mbcache Both ext2 and ext4 are now converted to mbcache2. Remove the old mbcache code. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/mbcache.h | 55 ------------------------------------------------- 1 file changed, 55 deletions(-) delete mode 100644 include/linux/mbcache.h (limited to 'include/linux') diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h deleted file mode 100644 index 6a392e7a723a..000000000000 --- a/include/linux/mbcache.h +++ /dev/null @@ -1,55 +0,0 @@ -/* - File: linux/mbcache.h - - (C) 2001 by Andreas Gruenbacher, -*/ -struct mb_cache_entry { - struct list_head e_lru_list; - struct mb_cache *e_cache; - unsigned short e_used; - unsigned short e_queued; - atomic_t e_refcnt; - struct block_device *e_bdev; - sector_t e_block; - struct hlist_bl_node e_block_list; - struct { - struct hlist_bl_node o_list; - unsigned int o_key; - } e_index; - struct hlist_bl_head *e_block_hash_p; - struct hlist_bl_head *e_index_hash_p; -}; - -struct mb_cache { - struct list_head c_cache_list; - const char *c_name; - atomic_t c_entry_count; - int c_max_entries; - int c_bucket_bits; - struct kmem_cache *c_entry_cache; - struct hlist_bl_head *c_block_hash; - struct hlist_bl_head *c_index_hash; -}; - -/* Functions on caches */ - -struct mb_cache *mb_cache_create(const char *, int); -void mb_cache_shrink(struct block_device *); -void mb_cache_destroy(struct mb_cache *); - -/* Functions on cache entries */ - -struct mb_cache_entry *mb_cache_entry_alloc(struct mb_cache *, gfp_t); -int mb_cache_entry_insert(struct mb_cache_entry *, struct block_device *, - sector_t, unsigned int); -void mb_cache_entry_release(struct mb_cache_entry *); -void mb_cache_entry_free(struct mb_cache_entry *); -struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *, - struct block_device *, - sector_t); -struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, - struct block_device *, - unsigned int); -struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache_entry *, - struct block_device *, - unsigned int); -- cgit v1.2.3 From b6f5128459a40410f9afefddc0ad688ea5b22c28 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Sat, 20 Feb 2016 13:24:26 +0200 Subject: clk: ti: dpll: convert DPLL support code to use clk_hw instead of clk ptrs Convert DPLL support code to use clk_hw pointers for reference and bypass clocks. This allows us to use clk_hw_* APIs for accessing any required parameters for these clocks, avoiding some locking problems at least with DPLL enable code; this used clk_get_rate which uses mutex but isn't good under clk_enable / clk_disable. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Stephen Boyd --- include/linux/clk/ti.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 9a638601cb09..dc5164a6df29 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -23,8 +23,8 @@ * @mult_div1_reg: register containing the DPLL M and N bitfields * @mult_mask: mask of the DPLL M bitfield in @mult_div1_reg * @div1_mask: mask of the DPLL N bitfield in @mult_div1_reg - * @clk_bypass: struct clk pointer to the clock's bypass clock input - * @clk_ref: struct clk pointer to the clock's reference clock input + * @clk_bypass: struct clk_hw pointer to the clock's bypass clock input + * @clk_ref: struct clk_hw pointer to the clock's reference clock input * @control_reg: register containing the DPLL mode bitfield * @enable_mask: mask of the DPLL mode bitfield in @control_reg * @last_rounded_rate: cache of the last rate result of omap2_dpll_round_rate() @@ -69,8 +69,8 @@ struct dpll_data { void __iomem *mult_div1_reg; u32 mult_mask; u32 div1_mask; - struct clk *clk_bypass; - struct clk *clk_ref; + struct clk_hw *clk_bypass; + struct clk_hw *clk_ref; void __iomem *control_reg; u32 enable_mask; unsigned long last_rounded_rate; -- cgit v1.2.3 From d7a8d5ed876970ac7f9bafbb6708500a7838c1d7 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 22 Feb 2016 16:02:33 -0700 Subject: vfio: Add capability chain helpers Allow sub-modules to easily reallocate a buffer for managing capability chains for info ioctls. Signed-off-by: Alex Williamson --- include/linux/vfio.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 610a86a892b8..0ecae0b1cd34 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -92,6 +92,17 @@ extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); +/* + * Sub-module helpers + */ +struct vfio_info_cap { + struct vfio_info_cap_header *buf; + size_t size; +}; +extern struct vfio_info_cap_header *vfio_info_cap_add( + struct vfio_info_cap *caps, size_t size, u16 id, u16 version); +extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset); + struct pci_dev; #ifdef CONFIG_EEH extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); -- cgit v1.2.3 From f0c8b46238db9d51ef9ea0858259958d0c601cec Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 18:23:47 -0500 Subject: mbcache2: Use referenced bit instead of LRU Currently we maintain perfect LRU list by moving entry to the tail of the list when it gets used. However these operations on cache-global list are relatively expensive. In this patch we switch to lazy updates of LRU list. Whenever entry gets used, we set a referenced bit in it. When reclaiming entries, we give referenced entries another round in the LRU. Since the list is not a real LRU anymore, rename it to just 'list'. In my testing this logic gives about 30% boost to workloads with mostly unique xattr blocks (e.g. xattr-bench with 10 files and 10000 unique xattr values). Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/mbcache2.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mbcache2.h b/include/linux/mbcache2.h index b6f160ff2533..c934843a6a31 100644 --- a/include/linux/mbcache2.h +++ b/include/linux/mbcache2.h @@ -10,8 +10,8 @@ struct mb2_cache; struct mb2_cache_entry { - /* LRU list - protected by cache->c_lru_list_lock */ - struct list_head e_lru_list; + /* List of entries in cache - protected by cache->c_list_lock */ + struct list_head e_list; /* Hash table list - protected by bitlock in e_hash_list_head */ struct hlist_bl_node e_hash_list; atomic_t e_refcnt; @@ -19,8 +19,11 @@ struct mb2_cache_entry { u32 e_key; /* Block number of hashed block - stable during lifetime of the entry */ sector_t e_block; - /* Head of hash list (for list bit lock) - stable */ - struct hlist_bl_head *e_hash_list_head; + /* + * Head of hash list (for list bit lock) - stable. Combined with + * referenced bit of entry + */ + unsigned long _e_hash_list_head; }; struct mb2_cache *mb2_cache_create(int bucket_bits); -- cgit v1.2.3 From 8f1dbbbbdfe9bada7e2f8041e07c6373f787c043 Mon Sep 17 00:00:00 2001 From: Shuoran Liu Date: Wed, 27 Jan 2016 09:57:30 +0800 Subject: f2fs: introduce lifetime write IO statistics This patch introduces lifetime IO write statistics exposed to the sysfs interface. The write IO amount is obtained from block layer, accumulated in the file system and stored in the hot node summary of checkpoint. Signed-off-by: Shuoran Liu Signed-off-by: Pengyang Hou [Jaegeuk Kim: add sysfs documentation] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index e59c3be92106..67aa01df777d 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -358,6 +358,12 @@ struct summary_footer { sizeof(struct sit_journal_entry)) #define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\ sizeof(struct sit_journal_entry)) + +/* Reserved area should make size of f2fs_extra_info equals to + * that of nat_journal and sit_journal. + */ +#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8) + /* * frequently updated NAT/SIT entries can be stored in the spare area in * summary blocks @@ -387,6 +393,11 @@ struct sit_journal { __u8 reserved[SIT_JOURNAL_RESERVED]; } __packed; +struct f2fs_extra_info { + __le64 kbytes_written; + __u8 reserved[EXTRA_INFO_RESERVED]; +} __packed; + /* 4KB-sized summary block structure */ struct f2fs_summary_block { struct f2fs_summary entries[ENTRIES_IN_SUM]; @@ -394,10 +405,11 @@ struct f2fs_summary_block { __le16 n_nats; __le16 n_sits; }; - /* spare area is used by NAT or SIT journals */ + /* spare area is used by NAT or SIT journals or extra info */ union { struct nat_journal nat_j; struct sit_journal sit_j; + struct f2fs_extra_info info; }; struct summary_footer footer; } __packed; -- cgit v1.2.3 From 81ca7350ce5ed438547ea769b0c33cb0abbd74ba Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 26 Jan 2016 15:39:35 +0800 Subject: f2fs: remove unneeded pointer conversion There are redundant pointer conversion in following call stack: - at position a, inode was been converted to f2fs_file_info. - at position b, f2fs_file_info was been converted to inode again. - truncate_blocks(inode,..) - fi = F2FS_I(inode) ---a - ADDRS_PER_PAGE(node_page, fi) - addrs_per_inode(fi) - inode = &fi->vfs_inode ---b - f2fs_has_inline_xattr(inode) - fi = F2FS_I(inode) - is_inode_flag_set(fi,..) In order to avoid unneeded conversion, alter ADDRS_PER_PAGE and addrs_per_inode to acept parameter with type of inode pointer. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 67aa01df777d..44ae822e154f 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -170,12 +170,12 @@ struct f2fs_extent { #define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ -#define ADDRS_PER_INODE(fi) addrs_per_inode(fi) +#define ADDRS_PER_INODE(inode) addrs_per_inode(inode) #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ -#define ADDRS_PER_PAGE(page, fi) \ - (IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK) +#define ADDRS_PER_PAGE(page, inode) \ + (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) -- cgit v1.2.3 From 479c8bc40c51535bf496440aa1d6af26e4ff9362 Mon Sep 17 00:00:00 2001 From: Sheng Yong Date: Thu, 28 Jan 2016 11:40:26 +0000 Subject: f2fs: fix endianness of on-disk summary_footer Signed-off-by: Sheng Yong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 44ae822e154f..ac8040278f69 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -345,7 +345,7 @@ struct f2fs_summary { struct summary_footer { unsigned char entry_type; /* SUM_TYPE_XXX */ - __u32 check_sum; /* summary checksum */ + __le32 check_sum; /* summary checksum */ } __packed; #define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\ -- cgit v1.2.3 From 24b8491251cde66879e74092167cc0f27a1f11ce Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 3 Feb 2016 13:49:44 -0800 Subject: f2fs: preallocate blocks for buffered aio writes This patch preallocates data blocks for buffered aio writes. With this patch, we can avoid redundant locking and unlocking of node pages given consecutive aio request. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index ac8040278f69..f43e6a01a023 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -21,7 +21,7 @@ #define F2FS_BLKSIZE 4096 /* support only 4KB block */ #define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ -#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE) +#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ #define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ -- cgit v1.2.3 From 5eb385cc5ae1b31fbcdd727854a00c5a083f6b9b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:46 -0500 Subject: Revert "cgroup: add cgroup_subsys->css_e_css_changed()" This reverts commit 56c807ba4e91f0980567b6a69de239677879b17f. cgroup_subsys->css_e_css_changed() was supposed to be used by cgroup writeback support; however, the change to per-inode cgroup association made it unnecessary and the callback doesn't have any user. Remove it. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- include/linux/cgroup-defs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 789471dba6fb..4f3c0dac26b5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -434,7 +434,6 @@ struct cgroup_subsys { void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); - void (*css_e_css_changed)(struct cgroup_subsys_state *css); int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); -- cgit v1.2.3 From 8699b7762a623c46ced891b3cf490058b56cf99c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:46 -0500 Subject: cgroup: s/child_subsys_mask/subtree_ss_mask/ For consistency with cgroup->subtree_control. * cgroup->child_subsys_mask -> cgroup->subtree_ss_mask * cgroup_calc_child_subsys_mask() -> cgroup_calc_subtree_ss_mask() * cgroup_refresh_child_subsys_mask() -> cgroup_refresh_subtree_ss_mask() No functional changes. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- include/linux/cgroup-defs.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4f3c0dac26b5..c68ae7f0fb5f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -253,13 +253,12 @@ struct cgroup { /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_subsys_mask is the - * effective one which may have more subsystems enabled. - * Controller knobs are made available iff it's enabled in - * ->subtree_control. + * "cgroup.subtree_control" while ->child_ss_mask is the effective + * one which may have more subsystems enabled. Controller knobs + * are made available iff it's enabled in ->subtree_control. */ - unsigned int subtree_control; - unsigned int child_subsys_mask; + unsigned long subtree_control; + unsigned long subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; -- cgit v1.2.3 From 6e5c830770f9045a17b1b931c3e11fbd5591e630 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:47 -0500 Subject: cgroup: make cgroup subsystem masks u16 After the recent do_each_subsys_mask() conversion, there's no reason to use ulong for subsystem masks. We'll be adding more subsystem masks to persistent data structures, let's reduce its size to u16 which should be enough for now and the foreseeable future. This doesn't create any noticeable behavior differences. v2: Johannes spotted that the initial patch missed cgroup_no_v1_mask. Converted. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- include/linux/cgroup-defs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index c68ae7f0fb5f..0abf6aa86c81 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -257,8 +257,8 @@ struct cgroup { * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ - unsigned long subtree_control; - unsigned long subtree_ss_mask; + u16 subtree_control; + u16 subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; -- cgit v1.2.3 From 30187e1d48a258e304af184c45c3140c8509d219 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Sun, 31 Jan 2016 13:28:26 -0500 Subject: dm: rename target's per_bio_data_size to per_io_data_size Request-based DM will also make use of per_bio_data_size. Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 87d50ecbc9df..82ae3b5e2c45 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -238,10 +238,10 @@ struct dm_target { unsigned num_write_same_bios; /* - * The minimum number of extra bytes allocated in each bio for the - * target to use. dm_per_bio_data returns the data location. + * The minimum number of extra bytes allocated in each io for the + * target to use. */ - unsigned per_bio_data_size; + unsigned per_io_data_size; /* * If defined, this function is called to find out how many -- cgit v1.2.3 From 7a2508e1b657cfc7e1371550f88c7a7bc4288f32 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 22:35:22 -0500 Subject: mbcache2: rename to mbcache Since old mbcache code is gone, let's rename new code to mbcache since number 2 is now meaningless. This is just a mechanical replacement. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/mbcache.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mbcache2.h | 53 ------------------------------------------------ 2 files changed, 53 insertions(+), 53 deletions(-) create mode 100644 include/linux/mbcache.h delete mode 100644 include/linux/mbcache2.h (limited to 'include/linux') diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h new file mode 100644 index 000000000000..a74a1f3082fb --- /dev/null +++ b/include/linux/mbcache.h @@ -0,0 +1,53 @@ +#ifndef _LINUX_MBCACHE_H +#define _LINUX_MBCACHE_H + +#include +#include +#include +#include +#include + +struct mb_cache; + +struct mb_cache_entry { + /* List of entries in cache - protected by cache->c_list_lock */ + struct list_head e_list; + /* Hash table list - protected by bitlock in e_hash_list_head */ + struct hlist_bl_node e_hash_list; + atomic_t e_refcnt; + /* Key in hash - stable during lifetime of the entry */ + u32 e_key; + /* Block number of hashed block - stable during lifetime of the entry */ + sector_t e_block; + /* + * Head of hash list (for list bit lock) - stable. Combined with + * referenced bit of entry + */ + unsigned long _e_hash_list_head; +}; + +struct mb_cache *mb_cache_create(int bucket_bits); +void mb_cache_destroy(struct mb_cache *cache); + +int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, + sector_t block); +void __mb_cache_entry_free(struct mb_cache_entry *entry); +static inline int mb_cache_entry_put(struct mb_cache *cache, + struct mb_cache_entry *entry) +{ + if (!atomic_dec_and_test(&entry->e_refcnt)) + return 0; + __mb_cache_entry_free(entry); + return 1; +} + +void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, + sector_t block); +struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, + u32 key); +struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, + struct mb_cache_entry *entry); +void mb_cache_entry_touch(struct mb_cache *cache, + struct mb_cache_entry *entry); + +#endif /* _LINUX_MBCACHE_H */ diff --git a/include/linux/mbcache2.h b/include/linux/mbcache2.h deleted file mode 100644 index c934843a6a31..000000000000 --- a/include/linux/mbcache2.h +++ /dev/null @@ -1,53 +0,0 @@ -#ifndef _LINUX_MB2CACHE_H -#define _LINUX_MB2CACHE_H - -#include -#include -#include -#include -#include - -struct mb2_cache; - -struct mb2_cache_entry { - /* List of entries in cache - protected by cache->c_list_lock */ - struct list_head e_list; - /* Hash table list - protected by bitlock in e_hash_list_head */ - struct hlist_bl_node e_hash_list; - atomic_t e_refcnt; - /* Key in hash - stable during lifetime of the entry */ - u32 e_key; - /* Block number of hashed block - stable during lifetime of the entry */ - sector_t e_block; - /* - * Head of hash list (for list bit lock) - stable. Combined with - * referenced bit of entry - */ - unsigned long _e_hash_list_head; -}; - -struct mb2_cache *mb2_cache_create(int bucket_bits); -void mb2_cache_destroy(struct mb2_cache *cache); - -int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key, - sector_t block); -void __mb2_cache_entry_free(struct mb2_cache_entry *entry); -static inline int mb2_cache_entry_put(struct mb2_cache *cache, - struct mb2_cache_entry *entry) -{ - if (!atomic_dec_and_test(&entry->e_refcnt)) - return 0; - __mb2_cache_entry_free(entry); - return 1; -} - -void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key, - sector_t block); -struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache, - u32 key); -struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache, - struct mb2_cache_entry *entry); -void mb2_cache_entry_touch(struct mb2_cache *cache, - struct mb2_cache_entry *entry); - -#endif /* _LINUX_MB2CACHE_H */ -- cgit v1.2.3 From dc8d5e565f00c9442fa1cbf9acc115475628527c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 22 Feb 2016 22:42:05 -0500 Subject: mbcache: get rid of _e_hash_list_head Get rid of field _e_hash_list_head in cache entries and add bit field e_referenced instead. Signed-off-by: Andreas Gruenbacher Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/mbcache.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index a74a1f3082fb..607e6968542e 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -12,18 +12,14 @@ struct mb_cache; struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; - /* Hash table list - protected by bitlock in e_hash_list_head */ + /* Hash table list - protected by hash chain bitlock */ struct hlist_bl_node e_hash_list; atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; + u32 e_referenced:1; /* Block number of hashed block - stable during lifetime of the entry */ sector_t e_block; - /* - * Head of hash list (for list bit lock) - stable. Combined with - * referenced bit of entry - */ - unsigned long _e_hash_list_head; }; struct mb_cache *mb_cache_create(int bucket_bits); -- cgit v1.2.3 From 6048c64b26097a0ffbd966866b599f990e674e9b Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 22 Feb 2016 22:44:04 -0500 Subject: mbcache: add reusable flag to cache entries To reduce amount of damage caused by single bad block, we limit number of inodes sharing an xattr block to 1024. Thus there can be more xattr blocks with the same contents when there are lots of files with the same extended attributes. These xattr blocks naturally result in hash collisions and can form long hash chains and we unnecessarily check each such block only to find out we cannot use it because it is already shared by too many inodes. Add a reusable flag to cache entries which is cleared when a cache entry has reached its maximum refcount. Cache entries which are not marked reusable are skipped by mb_cache_entry_find_{first,next}. This significantly speeds up mbcache when there are many same xattr blocks. For example for xattr-bench with 5 values and each process handling 20000 files, the run for 64 processes is 25x faster with this patch. Even for 8 processes the speedup is almost 3x. We have also verified that for situations where there is only one xattr block of each kind, the patch doesn't have a measurable cost. [JK: Remove handling of setting the same value since it is not needed anymore, check for races in e_reusable setting, improve changelog, add measurements] Signed-off-by: Andreas Gruenbacher Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/mbcache.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 607e6968542e..86c9a8b480c5 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -18,6 +18,7 @@ struct mb_cache_entry { /* Key in hash - stable during lifetime of the entry */ u32 e_key; u32 e_referenced:1; + u32 e_reusable:1; /* Block number of hashed block - stable during lifetime of the entry */ sector_t e_block; }; @@ -26,7 +27,7 @@ struct mb_cache *mb_cache_create(int bucket_bits); void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, - sector_t block); + sector_t block, bool reusable); void __mb_cache_entry_free(struct mb_cache_entry *entry); static inline int mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) @@ -39,6 +40,8 @@ static inline int mb_cache_entry_put(struct mb_cache *cache, void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, sector_t block); +struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, + sector_t block); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key); struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, -- cgit v1.2.3 From 9bcf976cb8b86eb40e0c0b495a14e4cb967b9c6e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 23:07:30 -0500 Subject: jbd2: remove unnecessary arguments of jbd2_journal_write_revoke_records jbd2_journal_write_revoke_records() takes journal pointer and write_op, although journal can be obtained from the passed transaction and write_op is always WRITE_SYNC. Remove these superfluous arguments. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 65407f6c9120..5716d9554e77 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1327,10 +1327,8 @@ extern int jbd2_journal_init_revoke_caches(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); -extern void jbd2_journal_write_revoke_records(journal_t *journal, - transaction_t *transaction, - struct list_head *log_bufs, - int write_op); +extern void jbd2_journal_write_revoke_records(transaction_t *transaction, + struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); -- cgit v1.2.3 From 32ab671599a89534f37e97d146c27690e371b661 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 23:17:15 -0500 Subject: jbd2: factor out common descriptor block initialization Descriptor block header is initialized in several places. Factor out the common code into jbd2_journal_get_descriptor_buffer(). Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5716d9554e77..3649cb8d3a41 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1137,7 +1137,7 @@ static inline void jbd2_unfile_log_bh(struct buffer_head *bh) } /* Log buffer allocation */ -struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal); +struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); -- cgit v1.2.3 From 1101cd4d13ba2f42c5da4c1b9081f35a73b5df31 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 23:19:09 -0500 Subject: jbd2: unify revoke and tag block checksum handling Revoke and tag descriptor blocks are just different kinds of descriptor blocks and thus have checksum in the same place. Unify computation and checking of checksums for these. Reviewed-by: Darrick J. Wong Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 3649cb8d3a41..fd1083c46c61 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -200,7 +200,7 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -/* Tail of descriptor block, for checksumming */ +/* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; @@ -215,11 +215,6 @@ typedef struct jbd2_journal_revoke_header_s __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; -/* Tail of revoke block, for checksumming */ -struct jbd2_journal_revoke_tail { - __be32 r_checksum; /* crc32c(uuid+revoke_block) */ -}; - /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ @@ -1138,6 +1133,7 @@ static inline void jbd2_unfile_log_bh(struct buffer_head *bh) /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); +void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); -- cgit v1.2.3 From dfc08a12e49a64f97d8b474da1d7745230cec5eb Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sun, 14 Feb 2016 18:50:40 +0800 Subject: f2fs: introduce f2fs_journal struct to wrap journal info Introduce a new structure f2fs_journal to wrap journal info in struct f2fs_summary_block for readability. struct f2fs_journal { union { __le16 n_nats; __le16 n_sits; }; union { struct nat_journal nat_j; struct sit_journal sit_j; struct f2fs_extra_info info; }; } __packed; struct f2fs_summary_block { struct f2fs_summary entries[ENTRIES_IN_SUM]; struct f2fs_journal journal; struct summary_footer footer; } __packed; Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f43e6a01a023..9eb215a155e0 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -398,9 +398,7 @@ struct f2fs_extra_info { __u8 reserved[EXTRA_INFO_RESERVED]; } __packed; -/* 4KB-sized summary block structure */ -struct f2fs_summary_block { - struct f2fs_summary entries[ENTRIES_IN_SUM]; +struct f2fs_journal { union { __le16 n_nats; __le16 n_sits; @@ -411,6 +409,12 @@ struct f2fs_summary_block { struct sit_journal sit_j; struct f2fs_extra_info info; }; +} __packed; + +/* 4KB-sized summary block structure */ +struct f2fs_summary_block { + struct f2fs_summary entries[ENTRIES_IN_SUM]; + struct f2fs_journal journal; struct summary_footer footer; } __packed; -- cgit v1.2.3 From 0cf3292cde22f8843ae5d1eeb8466d8121243c1a Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Mon, 15 Feb 2016 16:32:09 +0530 Subject: gpio: Add devm_ apis for gpiochip_add_data and gpiochip_remove Add device managed APIs devm_gpiochip_add_data() and devm_gpiochip_remove() for the APIs gpiochip_add_data() and gpiochip_remove(). This helps in reducing code in error path and sometimes removal of .remove callback for driver unbind. Signed-off-by: Laxman Dewangan --- include/linux/gpio/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 639607658ed8..bee976f82788 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -192,6 +192,10 @@ static inline int gpiochip_add(struct gpio_chip *chip) return gpiochip_add_data(chip, NULL); } extern void gpiochip_remove(struct gpio_chip *chip); +extern int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *chip, + void *data); +extern void devm_gpiochip_remove(struct device *dev, struct gpio_chip *chip); + extern struct gpio_chip *gpiochip_find(void *data, int (*match)(struct gpio_chip *chip, void *data)); -- cgit v1.2.3 From b38e42e962dbc2fbc3839ce70750881db7c9277e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 23 Feb 2016 10:00:50 -0500 Subject: cgroup: convert cgroup_subsys flag fields to bool bitfields Signed-off-by: Tejun Heo Cc: Li Zefan Cc: Ingo Molnar Cc: Peter Zijlstra --- include/linux/cgroup-defs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 0abf6aa86c81..8fc3f0452289 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -444,7 +444,7 @@ struct cgroup_subsys { void (*free)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); - int early_init; + bool early_init:1; /* * If %false, this subsystem is properly hierarchical - @@ -458,8 +458,8 @@ struct cgroup_subsys { * cases. Eventually, all subsystems will be made properly * hierarchical and this will go away. */ - bool broken_hierarchy; - bool warned_broken_hierarchy; + bool broken_hierarchy:1; + bool warned_broken_hierarchy:1; /* the following two fields are initialized automtically during boot */ int id; -- cgit v1.2.3 From d6dde63e90cf0d34ae61e885a5eb254c59eb3358 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andreas=20Irest=C3=A5l?= Date: Tue, 16 Feb 2016 13:56:42 +0100 Subject: ASoC: adau17x1: Correct typos in file headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Andreas Irestål Signed-off-by: Mark Brown --- include/linux/platform_data/adau17x1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/adau17x1.h b/include/linux/platform_data/adau17x1.h index a81766cae230..9db1b905df24 100644 --- a/include/linux/platform_data/adau17x1.h +++ b/include/linux/platform_data/adau17x1.h @@ -1,5 +1,5 @@ /* - * Driver for ADAU1761/ADAU1461/ADAU1761/ADAU1961/ADAU1781/ADAU1781 codecs + * Driver for ADAU1361/ADAU1461/ADAU1761/ADAU1961/ADAU1381/ADAU1781 codecs * * Copyright 2011-2014 Analog Devices Inc. * Author: Lars-Peter Clausen -- cgit v1.2.3 From 506bcfa8abebdbcebdc17b03e96e38dc0b8ce765 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 13 Dec 2015 15:41:05 +0200 Subject: mac80211: limit the A-MSDU Tx based on peer's capabilities In VHT, the specification allows to limit the number of MSDUs in an A-MSDU in the Extended Capabilities IE. There is also a limitation on the byte size in the VHT IE. In HT, the only limitation is on the byte size. Parse the capabilities from the peer and make them available to the driver. In HT, there is another limitation when a BA agreement is active: the byte size can't be greater than 4095. This is not enforced here. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9ddb89533a7..3b1f6cef9513 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -163,6 +163,14 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 +/* Maximal size of an A-MSDU */ +#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 +#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 + +#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 +#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 +#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 + #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_MAX_MESH_ID_LEN 32 @@ -1505,6 +1513,7 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C @@ -2086,6 +2095,16 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) +/* Defines the maximal number of MSDUs in an A-MSDU. */ +#define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7) +#define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0) + +/* + * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY + * information element + */ +#define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7) + /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 -- cgit v1.2.3 From dd21dfc645d5dce0657af78761b3fa11a3a95398 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jan 2016 10:39:23 +0100 Subject: rfkill: disentangle polling pause and suspend When suspended while polling is paused, polling will erroneously resume at resume time. Fix this by tracking pause and suspend in separate state variable and adding the necessary checks. Clarify the documentation on this as well. Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index d9010789b4e8..7af625f6d226 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -104,7 +104,8 @@ int __must_check rfkill_register(struct rfkill *rfkill); * * Pause polling -- say transmitter is off for other reasons. * NOTE: not necessary for suspend/resume -- in that case the - * core stops polling anyway + * core stops polling anyway (but will also correctly handle + * the case of polling having been paused before suspend.) */ void rfkill_pause_polling(struct rfkill *rfkill); -- cgit v1.2.3 From 648b50dd6abf8e6e5b589bb8e6873a4596389dbe Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Jan 2016 12:03:46 +0300 Subject: net: rfkill: add rfkill_find_type function Helper for finding the type based on name. Useful if the type needs to be determined based on device property. Signed-off-by: Heikki Krogerus [modify rfkill_types array and BUILD_BUG_ON to not cause errors] Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 7af625f6d226..e6a0031d1b1f 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -213,6 +213,15 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); * @rfkill: rfkill struct to query */ bool rfkill_blocked(struct rfkill *rfkill); + +/** + * rfkill_find_type - Helpper for finding rfkill type by name + * @name: the name of the type + * + * Returns enum rfkill_type that conrresponds the name. + */ +enum rfkill_type rfkill_find_type(const char *name); + #else /* !RFKILL */ static inline struct rfkill * __must_check rfkill_alloc(const char *name, @@ -269,6 +278,12 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) { return false; } + +static inline enum rfkill_type rfkill_find_type(const char *name) +{ + return RFKILL_TYPE_ALL; +} + #endif /* RFKILL || RFKILL_MODULE */ -- cgit v1.2.3 From fb2e6b7b7b02ab35a9d5355a69097a6f60c69d38 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Jan 2016 12:03:49 +0300 Subject: net: rfkill: gpio: remove rfkill_gpio_platform_data No more users for it. Signed-off-by: Heikki Krogerus Signed-off-by: Johannes Berg --- include/linux/rfkill-gpio.h | 37 ------------------------------------- 1 file changed, 37 deletions(-) delete mode 100644 include/linux/rfkill-gpio.h (limited to 'include/linux') diff --git a/include/linux/rfkill-gpio.h b/include/linux/rfkill-gpio.h deleted file mode 100644 index 20bcb55498cd..000000000000 --- a/include/linux/rfkill-gpio.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Copyright (c) 2011, NVIDIA Corporation. - * - * 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. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - - -#ifndef __RFKILL_GPIO_H -#define __RFKILL_GPIO_H - -#include -#include - -/** - * struct rfkill_gpio_platform_data - platform data for rfkill gpio device. - * for unused gpio's, the expected value is -1. - * @name: name for the gpio rf kill instance - */ - -struct rfkill_gpio_platform_data { - char *name; - enum rfkill_type type; -}; - -#endif /* __RFKILL_GPIO_H */ -- cgit v1.2.3 From e4fbf4767440472f9d23b0f25a2b905e1c63b6a8 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 10 Jan 2016 11:29:07 +0100 Subject: efi: stub: implement efi_get_random_bytes() based on EFI_RNG_PROTOCOL This exposes the firmware's implementation of EFI_RNG_PROTOCOL via a new function efi_get_random_bytes(). Reviewed-by: Matt Fleming Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- include/linux/efi.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 569b5a866bb1..e747eb08b2be 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -299,7 +299,7 @@ typedef struct { void *open_protocol_information; void *protocols_per_handle; void *locate_handle_buffer; - void *locate_protocol; + efi_status_t (*locate_protocol)(efi_guid_t *, void *, void **); void *install_multiple_protocol_interfaces; void *uninstall_multiple_protocol_interfaces; void *calculate_crc32; @@ -599,6 +599,10 @@ void efi_native_runtime_setup(void); #define EFI_PROPERTIES_TABLE_GUID \ EFI_GUID( 0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5 ) +#define EFI_RNG_PROTOCOL_GUID \ + EFI_GUID(0x3152bca5, 0xeade, 0x433d, \ + 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) + typedef struct { efi_guid_t guid; u64 table; -- cgit v1.2.3 From ada68c31ba9c02d7aabdd87db979fe670b499d54 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Mon, 22 Feb 2016 18:17:23 +0200 Subject: net/mlx5: Introduce a new header file for physical port functions All the device physical port access functions are implemented in the port.c file. We just extract the exposure of these functions from driver.h into a dedicated header file called port.h. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 31 -------------------- include/linux/mlx5/port.h | 69 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+), 31 deletions(-) create mode 100644 include/linux/mlx5/port.h (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e3006dcf35d..02adc67720ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -794,37 +794,6 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); -int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, - int ptys_size, int proto_mask, u8 local_port); -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask); -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask); -int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, - u8 *link_width_oper, u8 local_port); -int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, - u8 *proto_oper, int proto_mask, - u8 local_port); -int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, - int proto_mask); -int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status *status); - -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, - u8 port); - -int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, - u8 *vl_hw_cap, u8 local_port); - -int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); -int mlx5_query_port_pause(struct mlx5_core_dev *dev, - u32 *rx_pause, u32 *tx_pause); - int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h new file mode 100644 index 000000000000..7accd4a65da5 --- /dev/null +++ b/include/linux/mlx5/port.h @@ -0,0 +1,69 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_PORT_H__ +#define __MLX5_PORT_H__ + +#include + +int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask, u8 local_port); +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask); +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask); +int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, + u8 *link_width_oper, u8 local_port); +int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, + u8 *proto_oper, int proto_mask, + u8 local_port); +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask); +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status); + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, + u8 port); + +int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, + u8 *vl_hw_cap, u8 local_port); + +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause); + +#endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From ad909eb064219a64fd10e9c7d9f39a3042760025 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Mon, 22 Feb 2016 18:17:24 +0200 Subject: net/mlx5: Introduce physical port PFC access functions Add access functions to set and query a physical port PFC (Priority Flow Control) parameters. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/port.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 7accd4a65da5..4b3644caa936 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -66,4 +66,8 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); int mlx5_query_port_pause(struct mlx5_core_dev *dev, u32 *rx_pause, u32 *tx_pause); +int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); +int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, + u8 *pfc_en_rx); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 4f3961eeafe0aca8f6b0933899ef0d91f561352d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 22 Feb 2016 18:17:25 +0200 Subject: net/mlx5: Introduce physical port TC/prio access functions Add access functions to set and query a physical port TC groups and prio parameters. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 49 ++++++++++++++++++++++++++++++++++++++++++- include/linux/mlx5/port.h | 6 ++++++ 3 files changed, 56 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 02adc67720ce..a815da92d4eb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -99,6 +99,8 @@ enum { }; enum { + MLX5_REG_QETCR = 0x4005, + MLX5_REG_QTCT = 0x400a, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..ec957e059de8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -729,7 +729,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_1bf[0x3]; u8 log_max_msg[0x5]; - u8 reserved_at_1c7[0x18]; + u8 reserved_at_1c7[0x4]; + u8 max_tc[0x4]; + u8 reserved_at_1cf[0x10]; u8 stat_rate_support[0x10]; u8 reserved_at_1ef[0xc]; @@ -7061,4 +7063,49 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_ets_tcn_config_reg_bits { + u8 g[0x1]; + u8 b[0x1]; + u8 r[0x1]; + u8 reserved_at_3[0x9]; + u8 group[0x4]; + u8 reserved_at_10[0x9]; + u8 bw_allocation[0x7]; + + u8 reserved_at_20[0xc]; + u8 max_bw_units[0x4]; + u8 reserved_at_30[0x8]; + u8 max_bw_value[0x8]; +}; + +struct mlx5_ifc_ets_global_config_reg_bits { + u8 reserved_at_0[0x2]; + u8 r[0x1]; + u8 reserved_at_3[0x1d]; + + u8 reserved_at_20[0xc]; + u8 max_bw_units[0x4]; + u8 reserved_at_30[0x8]; + u8 max_bw_value[0x8]; +}; + +struct mlx5_ifc_qetc_reg_bits { + u8 reserved_at_0[0x8]; + u8 port_number[0x8]; + u8 reserved_at_10[0x30]; + + struct mlx5_ifc_ets_tcn_config_reg_bits tc_configuration[0x8]; + struct mlx5_ifc_ets_global_config_reg_bits global_configuration; +}; + +struct mlx5_ifc_qtct_reg_bits { + u8 reserved_at_0[0x8]; + u8 port_number[0x8]; + u8 reserved_at_10[0xd]; + u8 prio[0x3]; + + u8 reserved_at_20[0x1d]; + u8 tclass[0x3]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 4b3644caa936..0c67e699d017 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -70,4 +70,10 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx); +int mlx5_max_tc(struct mlx5_core_dev *mdev); + +int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); +int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); +int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From d8880795dabf2381ed1e98348f6d9c7ea6fab950 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Feb 2016 18:17:28 +0200 Subject: net/mlx5e: Implement DCBNL IEEE max rate Add support for DCBNL IEEE get/set max rate. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 6 ++++++ include/linux/mlx5/port.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..bfc1ab0552d3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -350,6 +350,12 @@ enum { MLX5_SET_PORT_PKEY_TABLE = 20, }; +enum { + MLX5_BW_NO_LIMIT = 0, + MLX5_100_MBPS_UNIT = 3, + MLX5_GBPS_UNIT = 4, +}; + enum { MLX5_MAX_PAGE_SHIFT = 31 }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 0c67e699d017..595c7b2d9bfa 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -75,5 +75,11 @@ int mlx5_max_tc(struct mlx5_core_dev *mdev); int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); +int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_unit); +int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_unit); #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 928cfe8745a62e60c1e8e06676a74724e7786024 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Feb 2016 18:17:29 +0200 Subject: net/mlx5e: Wake On LAN support Implement set/get WOL by ethtool and added the needed device commands and structures to mlx5_ifc. Signed-off-by: Tariq Toukan Signed-off-by: Rana Shahout Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 11 ++++++++ include/linux/mlx5/mlx5_ifc.h | 62 ++++++++++++++++++++++++++++++++++++++++++- include/linux/mlx5/port.h | 2 ++ 3 files changed, 74 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index bfc1ab0552d3..68a56bc37df2 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1183,6 +1183,17 @@ enum { MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, }; +enum mlx5_wol_mode { + MLX5_WOL_DISABLE = 0, + MLX5_WOL_SECURED_MAGIC = 1 << 1, + MLX5_WOL_MAGIC = 1 << 2, + MLX5_WOL_ARP = 1 << 3, + MLX5_WOL_BROADCAST = 1 << 4, + MLX5_WOL_MULTICAST = 1 << 5, + MLX5_WOL_UNICAST = 1 << 6, + MLX5_WOL_PHY_ACTIVITY = 1 << 7, +}; + /* MLX5 DEV CAPs */ /* TODO: EAT.ME */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ec957e059de8..03ffe9530365 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -166,6 +166,8 @@ enum { MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829, MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a, MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b, + MLX5_CMD_OP_SET_WOL_ROL = 0x830, + MLX5_CMD_OP_QUERY_WOL_ROL = 0x831, MLX5_CMD_OP_CREATE_TIR = 0x900, MLX5_CMD_OP_MODIFY_TIR = 0x901, MLX5_CMD_OP_DESTROY_TIR = 0x902, @@ -731,7 +733,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_msg[0x5]; u8 reserved_at_1c7[0x4]; u8 max_tc[0x4]; - u8 reserved_at_1cf[0x10]; + u8 reserved_at_1cf[0x6]; + u8 rol_s[0x1]; + u8 rol_g[0x1]; + u8 reserved_at_1d7[0x1]; + u8 wol_s[0x1]; + u8 wol_g[0x1]; + u8 wol_a[0x1]; + u8 wol_b[0x1]; + u8 wol_m[0x1]; + u8 wol_u[0x1]; + u8 wol_p[0x1]; u8 stat_rate_support[0x10]; u8 reserved_at_1ef[0xc]; @@ -6873,6 +6885,54 @@ struct mlx5_ifc_mtt_bits { u8 rd_en[0x1]; }; +struct mlx5_ifc_query_wol_rol_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x10]; + u8 rol_mode[0x8]; + u8 wol_mode[0x8]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_wol_rol_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_wol_rol_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_wol_rol_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 rol_mode_valid[0x1]; + u8 wol_mode_valid[0x1]; + u8 reserved_at_42[0xe]; + u8 rol_mode[0x8]; + u8 wol_mode[0x8]; + + u8 reserved_at_60[0x20]; +}; + enum { MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 595c7b2d9bfa..a1d145abd4eb 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -81,5 +81,7 @@ int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, u8 *max_bw_value, u8 *max_bw_unit); +int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode); +int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode); #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 2262d6ef517f9f0d427015cb9a790b86a2c95fed Mon Sep 17 00:00:00 2001 From: Pankaj Dubey Date: Fri, 18 Dec 2015 09:02:11 +0530 Subject: ARM: EXYNOS: Move pmu specific headers under "linux/soc/samsung" Moving Exynos PMU specific header file into "include/linux/soc/samsung" thus updated affected files under "mach-exynos" to use new location of these header files. Signed-off-by: Amit Daniel Kachhap [tested on Peach-Pi (Exynos5880)] Signed-off-by: Pankaj Dubey Reviewed-by: Krzysztof Kozlowski [for testing on Trats2 (Exynos4412) and Odroid XU3 (Exynos5422)] Tested-by: Krzysztof Kozlowski Signed-off-by: Krzysztof Kozlowski --- include/linux/soc/samsung/exynos-pmu.h | 24 + include/linux/soc/samsung/exynos-regs-pmu.h | 693 ++++++++++++++++++++++++++++ 2 files changed, 717 insertions(+) create mode 100644 include/linux/soc/samsung/exynos-pmu.h create mode 100644 include/linux/soc/samsung/exynos-regs-pmu.h (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-pmu.h b/include/linux/soc/samsung/exynos-pmu.h new file mode 100644 index 000000000000..e2e9de1acc5b --- /dev/null +++ b/include/linux/soc/samsung/exynos-pmu.h @@ -0,0 +1,24 @@ +/* + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Header for EXYNOS PMU Driver support + * + * 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 __LINUX_SOC_EXYNOS_PMU_H +#define __LINUX_SOC_EXYNOS_PMU_H + +enum sys_powerdown { + SYS_AFTR, + SYS_LPA, + SYS_SLEEP, + NUM_SYS_POWERDOWN, +}; + +extern void exynos_sys_powerdown_conf(enum sys_powerdown mode); + +#endif /* __LINUX_SOC_EXYNOS_PMU_H */ diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h new file mode 100644 index 000000000000..d30186e2b609 --- /dev/null +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -0,0 +1,693 @@ +/* + * Copyright (c) 2010-2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * EXYNOS - Power management unit definition + * + * 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 __LINUX_SOC_EXYNOS_REGS_PMU_H +#define __LINUX_SOC_EXYNOS_REGS_PMU_H __FILE__ + +#define S5P_CENTRAL_SEQ_CONFIGURATION 0x0200 + +#define S5P_CENTRAL_LOWPWR_CFG (1 << 16) + +#define S5P_CENTRAL_SEQ_OPTION 0x0208 + +#define S5P_USE_STANDBY_WFI0 (1 << 16) +#define S5P_USE_STANDBY_WFI1 (1 << 17) +#define S5P_USE_STANDBY_WFI2 (1 << 19) +#define S5P_USE_STANDBY_WFI3 (1 << 20) +#define S5P_USE_STANDBY_WFE0 (1 << 24) +#define S5P_USE_STANDBY_WFE1 (1 << 25) +#define S5P_USE_STANDBY_WFE2 (1 << 27) +#define S5P_USE_STANDBY_WFE3 (1 << 28) + +#define S5P_USE_STANDBY_WFI_ALL \ + (S5P_USE_STANDBY_WFI0 | S5P_USE_STANDBY_WFI1 | \ + S5P_USE_STANDBY_WFI2 | S5P_USE_STANDBY_WFI3 | \ + S5P_USE_STANDBY_WFE0 | S5P_USE_STANDBY_WFE1 | \ + S5P_USE_STANDBY_WFE2 | S5P_USE_STANDBY_WFE3) + +#define S5P_USE_DELAYED_RESET_ASSERTION BIT(12) + +#define EXYNOS_CORE_PO_RESET(n) ((1 << 4) << n) +#define EXYNOS_WAKEUP_FROM_LOWPWR (1 << 28) +#define EXYNOS_SWRESET 0x0400 +#define EXYNOS5440_SWRESET 0x00C4 + +#define S5P_WAKEUP_STAT 0x0600 +#define S5P_EINT_WAKEUP_MASK 0x0604 +#define S5P_WAKEUP_MASK 0x0608 +#define S5P_WAKEUP_MASK2 0x0614 + +#define S5P_INFORM0 0x0800 +#define S5P_INFORM1 0x0804 +#define S5P_INFORM5 0x0814 +#define S5P_INFORM6 0x0818 +#define S5P_INFORM7 0x081C +#define S5P_PMU_SPARE2 0x0908 +#define S5P_PMU_SPARE3 0x090C + +#define EXYNOS_IROM_DATA2 0x0988 +#define S5P_ARM_CORE0_LOWPWR 0x1000 +#define S5P_DIS_IRQ_CORE0 0x1004 +#define S5P_DIS_IRQ_CENTRAL0 0x1008 +#define S5P_ARM_CORE1_LOWPWR 0x1010 +#define S5P_DIS_IRQ_CORE1 0x1014 +#define S5P_DIS_IRQ_CENTRAL1 0x1018 +#define S5P_ARM_COMMON_LOWPWR 0x1080 +#define S5P_L2_0_LOWPWR 0x10C0 +#define S5P_L2_1_LOWPWR 0x10C4 +#define S5P_CMU_ACLKSTOP_LOWPWR 0x1100 +#define S5P_CMU_SCLKSTOP_LOWPWR 0x1104 +#define S5P_CMU_RESET_LOWPWR 0x110C +#define S5P_APLL_SYSCLK_LOWPWR 0x1120 +#define S5P_MPLL_SYSCLK_LOWPWR 0x1124 +#define S5P_VPLL_SYSCLK_LOWPWR 0x1128 +#define S5P_EPLL_SYSCLK_LOWPWR 0x112C +#define S5P_CMU_CLKSTOP_GPS_ALIVE_LOWPWR 0x1138 +#define S5P_CMU_RESET_GPSALIVE_LOWPWR 0x113C +#define S5P_CMU_CLKSTOP_CAM_LOWPWR 0x1140 +#define S5P_CMU_CLKSTOP_TV_LOWPWR 0x1144 +#define S5P_CMU_CLKSTOP_MFC_LOWPWR 0x1148 +#define S5P_CMU_CLKSTOP_G3D_LOWPWR 0x114C +#define S5P_CMU_CLKSTOP_LCD0_LOWPWR 0x1150 +#define S5P_CMU_CLKSTOP_MAUDIO_LOWPWR 0x1158 +#define S5P_CMU_CLKSTOP_GPS_LOWPWR 0x115C +#define S5P_CMU_RESET_CAM_LOWPWR 0x1160 +#define S5P_CMU_RESET_TV_LOWPWR 0x1164 +#define S5P_CMU_RESET_MFC_LOWPWR 0x1168 +#define S5P_CMU_RESET_G3D_LOWPWR 0x116C +#define S5P_CMU_RESET_LCD0_LOWPWR 0x1170 +#define S5P_CMU_RESET_MAUDIO_LOWPWR 0x1178 +#define S5P_CMU_RESET_GPS_LOWPWR 0x117C +#define S5P_TOP_BUS_LOWPWR 0x1180 +#define S5P_TOP_RETENTION_LOWPWR 0x1184 +#define S5P_TOP_PWR_LOWPWR 0x1188 +#define S5P_LOGIC_RESET_LOWPWR 0x11A0 +#define S5P_ONENAND_MEM_LOWPWR 0x11C0 +#define S5P_G2D_ACP_MEM_LOWPWR 0x11C8 +#define S5P_USBOTG_MEM_LOWPWR 0x11CC +#define S5P_HSMMC_MEM_LOWPWR 0x11D0 +#define S5P_CSSYS_MEM_LOWPWR 0x11D4 +#define S5P_SECSS_MEM_LOWPWR 0x11D8 +#define S5P_PAD_RETENTION_DRAM_LOWPWR 0x1200 +#define S5P_PAD_RETENTION_MAUDIO_LOWPWR 0x1204 +#define S5P_PAD_RETENTION_GPIO_LOWPWR 0x1220 +#define S5P_PAD_RETENTION_UART_LOWPWR 0x1224 +#define S5P_PAD_RETENTION_MMCA_LOWPWR 0x1228 +#define S5P_PAD_RETENTION_MMCB_LOWPWR 0x122C +#define S5P_PAD_RETENTION_EBIA_LOWPWR 0x1230 +#define S5P_PAD_RETENTION_EBIB_LOWPWR 0x1234 +#define S5P_PAD_RETENTION_ISOLATION_LOWPWR 0x1240 +#define S5P_PAD_RETENTION_ALV_SEL_LOWPWR 0x1260 +#define S5P_XUSBXTI_LOWPWR 0x1280 +#define S5P_XXTI_LOWPWR 0x1284 +#define S5P_EXT_REGULATOR_LOWPWR 0x12C0 +#define S5P_GPIO_MODE_LOWPWR 0x1300 +#define S5P_GPIO_MODE_MAUDIO_LOWPWR 0x1340 +#define S5P_CAM_LOWPWR 0x1380 +#define S5P_TV_LOWPWR 0x1384 +#define S5P_MFC_LOWPWR 0x1388 +#define S5P_G3D_LOWPWR 0x138C +#define S5P_LCD0_LOWPWR 0x1390 +#define S5P_MAUDIO_LOWPWR 0x1398 +#define S5P_GPS_LOWPWR 0x139C +#define S5P_GPS_ALIVE_LOWPWR 0x13A0 + +#define EXYNOS_ARM_CORE0_CONFIGURATION 0x2000 +#define EXYNOS_ARM_CORE_CONFIGURATION(_nr) \ + (EXYNOS_ARM_CORE0_CONFIGURATION + (0x80 * (_nr))) +#define EXYNOS_ARM_CORE_STATUS(_nr) \ + (EXYNOS_ARM_CORE_CONFIGURATION(_nr) + 0x4) +#define EXYNOS_ARM_CORE_OPTION(_nr) \ + (EXYNOS_ARM_CORE_CONFIGURATION(_nr) + 0x8) + +#define EXYNOS_ARM_COMMON_CONFIGURATION 0x2500 +#define EXYNOS_COMMON_CONFIGURATION(_nr) \ + (EXYNOS_ARM_COMMON_CONFIGURATION + (0x80 * (_nr))) +#define EXYNOS_COMMON_STATUS(_nr) \ + (EXYNOS_COMMON_CONFIGURATION(_nr) + 0x4) +#define EXYNOS_COMMON_OPTION(_nr) \ + (EXYNOS_COMMON_CONFIGURATION(_nr) + 0x8) + +#define EXYNOS_CORE_LOCAL_PWR_EN 0x3 + +#define EXYNOS_ARM_COMMON_STATUS 0x2504 +#define EXYNOS_COMMON_OPTION(_nr) \ + (EXYNOS_COMMON_CONFIGURATION(_nr) + 0x8) + +#define EXYNOS_ARM_L2_CONFIGURATION 0x2600 +#define EXYNOS_L2_CONFIGURATION(_nr) \ + (EXYNOS_ARM_L2_CONFIGURATION + ((_nr) * 0x80)) +#define EXYNOS_L2_STATUS(_nr) \ + (EXYNOS_L2_CONFIGURATION(_nr) + 0x4) +#define EXYNOS_L2_OPTION(_nr) \ + (EXYNOS_L2_CONFIGURATION(_nr) + 0x8) +#define EXYNOS_L2_COMMON_PWR_EN 0x3 + +#define EXYNOS_ARM_CORE_X_STATUS_OFFSET 0x4 + +#define EXYNOS5_APLL_SYSCLK_CONFIGURATION 0x2A00 +#define EXYNOS5_APLL_SYSCLK_STATUS 0x2A04 + +#define EXYNOS5_ARM_L2_OPTION 0x2608 +#define EXYNOS5_USE_RETENTION BIT(4) + +#define EXYNOS5_L2RSTDISABLE_VALUE BIT(3) + +#define S5P_PAD_RET_MAUDIO_OPTION 0x3028 +#define S5P_PAD_RET_MMC2_OPTION 0x30c8 +#define S5P_PAD_RET_GPIO_OPTION 0x3108 +#define S5P_PAD_RET_UART_OPTION 0x3128 +#define S5P_PAD_RET_MMCA_OPTION 0x3148 +#define S5P_PAD_RET_MMCB_OPTION 0x3168 +#define S5P_PAD_RET_EBIA_OPTION 0x3188 +#define S5P_PAD_RET_EBIB_OPTION 0x31A8 +#define S5P_PAD_RET_SPI_OPTION 0x31c8 + +#define S5P_PS_HOLD_CONTROL 0x330C +#define S5P_PS_HOLD_EN (1 << 31) +#define S5P_PS_HOLD_OUTPUT_HIGH (3 << 8) + +#define S5P_CAM_OPTION 0x3C08 +#define S5P_MFC_OPTION 0x3C48 +#define S5P_G3D_OPTION 0x3C68 +#define S5P_LCD0_OPTION 0x3C88 +#define S5P_LCD1_OPTION 0x3CA8 +#define S5P_ISP_OPTION S5P_LCD1_OPTION + +#define S5P_CORE_LOCAL_PWR_EN 0x3 +#define S5P_CORE_WAKEUP_FROM_LOCAL_CFG (0x3 << 8) +#define S5P_CORE_AUTOWAKEUP_EN (1 << 31) + +/* Only for EXYNOS4210 */ +#define S5P_CMU_CLKSTOP_LCD1_LOWPWR 0x1154 +#define S5P_CMU_RESET_LCD1_LOWPWR 0x1174 +#define S5P_MODIMIF_MEM_LOWPWR 0x11C4 +#define S5P_PCIE_MEM_LOWPWR 0x11E0 +#define S5P_SATA_MEM_LOWPWR 0x11E4 +#define S5P_LCD1_LOWPWR 0x1394 + +/* Only for EXYNOS4x12 */ +#define S5P_ISP_ARM_LOWPWR 0x1050 +#define S5P_DIS_IRQ_ISP_ARM_LOCAL_LOWPWR 0x1054 +#define S5P_DIS_IRQ_ISP_ARM_CENTRAL_LOWPWR 0x1058 +#define S5P_CMU_ACLKSTOP_COREBLK_LOWPWR 0x1110 +#define S5P_CMU_SCLKSTOP_COREBLK_LOWPWR 0x1114 +#define S5P_CMU_RESET_COREBLK_LOWPWR 0x111C +#define S5P_MPLLUSER_SYSCLK_LOWPWR 0x1130 +#define S5P_CMU_CLKSTOP_ISP_LOWPWR 0x1154 +#define S5P_CMU_RESET_ISP_LOWPWR 0x1174 +#define S5P_TOP_BUS_COREBLK_LOWPWR 0x1190 +#define S5P_TOP_RETENTION_COREBLK_LOWPWR 0x1194 +#define S5P_TOP_PWR_COREBLK_LOWPWR 0x1198 +#define S5P_OSCCLK_GATE_LOWPWR 0x11A4 +#define S5P_LOGIC_RESET_COREBLK_LOWPWR 0x11B0 +#define S5P_OSCCLK_GATE_COREBLK_LOWPWR 0x11B4 +#define S5P_HSI_MEM_LOWPWR 0x11C4 +#define S5P_ROTATOR_MEM_LOWPWR 0x11DC +#define S5P_PAD_RETENTION_GPIO_COREBLK_LOWPWR 0x123C +#define S5P_PAD_ISOLATION_COREBLK_LOWPWR 0x1250 +#define S5P_GPIO_MODE_COREBLK_LOWPWR 0x1320 +#define S5P_TOP_ASB_RESET_LOWPWR 0x1344 +#define S5P_TOP_ASB_ISOLATION_LOWPWR 0x1348 +#define S5P_ISP_LOWPWR 0x1394 +#define S5P_DRAM_FREQ_DOWN_LOWPWR 0x13B0 +#define S5P_DDRPHY_DLLOFF_LOWPWR 0x13B4 +#define S5P_CMU_SYSCLK_ISP_LOWPWR 0x13B8 +#define S5P_CMU_SYSCLK_GPS_LOWPWR 0x13BC +#define S5P_LPDDR_PHY_DLL_LOCK_LOWPWR 0x13C0 + +#define S5P_ARM_L2_0_OPTION 0x2608 +#define S5P_ARM_L2_1_OPTION 0x2628 +#define S5P_ONENAND_MEM_OPTION 0x2E08 +#define S5P_HSI_MEM_OPTION 0x2E28 +#define S5P_G2D_ACP_MEM_OPTION 0x2E48 +#define S5P_USBOTG_MEM_OPTION 0x2E68 +#define S5P_HSMMC_MEM_OPTION 0x2E88 +#define S5P_CSSYS_MEM_OPTION 0x2EA8 +#define S5P_SECSS_MEM_OPTION 0x2EC8 +#define S5P_ROTATOR_MEM_OPTION 0x2F48 + +/* Only for EXYNOS4412 */ +#define S5P_ARM_CORE2_LOWPWR 0x1020 +#define S5P_DIS_IRQ_CORE2 0x1024 +#define S5P_DIS_IRQ_CENTRAL2 0x1028 +#define S5P_ARM_CORE3_LOWPWR 0x1030 +#define S5P_DIS_IRQ_CORE3 0x1034 +#define S5P_DIS_IRQ_CENTRAL3 0x1038 + +/* Only for EXYNOS3XXX */ +#define EXYNOS3_ARM_CORE0_SYS_PWR_REG 0x1000 +#define EXYNOS3_DIS_IRQ_ARM_CORE0_LOCAL_SYS_PWR_REG 0x1004 +#define EXYNOS3_DIS_IRQ_ARM_CORE0_CENTRAL_SYS_PWR_REG 0x1008 +#define EXYNOS3_ARM_CORE1_SYS_PWR_REG 0x1010 +#define EXYNOS3_DIS_IRQ_ARM_CORE1_LOCAL_SYS_PWR_REG 0x1014 +#define EXYNOS3_DIS_IRQ_ARM_CORE1_CENTRAL_SYS_PWR_REG 0x1018 +#define EXYNOS3_ISP_ARM_SYS_PWR_REG 0x1050 +#define EXYNOS3_DIS_IRQ_ISP_ARM_LOCAL_SYS_PWR_REG 0x1054 +#define EXYNOS3_DIS_IRQ_ISP_ARM_CENTRAL_SYS_PWR_REG 0x1058 +#define EXYNOS3_ARM_COMMON_SYS_PWR_REG 0x1080 +#define EXYNOS3_ARM_L2_SYS_PWR_REG 0x10C0 +#define EXYNOS3_CMU_ACLKSTOP_SYS_PWR_REG 0x1100 +#define EXYNOS3_CMU_SCLKSTOP_SYS_PWR_REG 0x1104 +#define EXYNOS3_CMU_RESET_SYS_PWR_REG 0x110C +#define EXYNOS3_CMU_ACLKSTOP_COREBLK_SYS_PWR_REG 0x1110 +#define EXYNOS3_CMU_SCLKSTOP_COREBLK_SYS_PWR_REG 0x1114 +#define EXYNOS3_CMU_RESET_COREBLK_SYS_PWR_REG 0x111C +#define EXYNOS3_APLL_SYSCLK_SYS_PWR_REG 0x1120 +#define EXYNOS3_MPLL_SYSCLK_SYS_PWR_REG 0x1124 +#define EXYNOS3_VPLL_SYSCLK_SYS_PWR_REG 0x1128 +#define EXYNOS3_EPLL_SYSCLK_SYS_PWR_REG 0x112C +#define EXYNOS3_MPLLUSER_SYSCLK_SYS_PWR_REG 0x1130 +#define EXYNOS3_BPLLUSER_SYSCLK_SYS_PWR_REG 0x1134 +#define EXYNOS3_EPLLUSER_SYSCLK_SYS_PWR_REG 0x1138 +#define EXYNOS3_CMU_CLKSTOP_CAM_SYS_PWR_REG 0x1140 +#define EXYNOS3_CMU_CLKSTOP_MFC_SYS_PWR_REG 0x1148 +#define EXYNOS3_CMU_CLKSTOP_G3D_SYS_PWR_REG 0x114C +#define EXYNOS3_CMU_CLKSTOP_LCD0_SYS_PWR_REG 0x1150 +#define EXYNOS3_CMU_CLKSTOP_ISP_SYS_PWR_REG 0x1154 +#define EXYNOS3_CMU_CLKSTOP_MAUDIO_SYS_PWR_REG 0x1158 +#define EXYNOS3_CMU_RESET_CAM_SYS_PWR_REG 0x1160 +#define EXYNOS3_CMU_RESET_MFC_SYS_PWR_REG 0x1168 +#define EXYNOS3_CMU_RESET_G3D_SYS_PWR_REG 0x116C +#define EXYNOS3_CMU_RESET_LCD0_SYS_PWR_REG 0x1170 +#define EXYNOS3_CMU_RESET_ISP_SYS_PWR_REG 0x1174 +#define EXYNOS3_CMU_RESET_MAUDIO_SYS_PWR_REG 0x1178 +#define EXYNOS3_TOP_BUS_SYS_PWR_REG 0x1180 +#define EXYNOS3_TOP_RETENTION_SYS_PWR_REG 0x1184 +#define EXYNOS3_TOP_PWR_SYS_PWR_REG 0x1188 +#define EXYNOS3_TOP_BUS_COREBLK_SYS_PWR_REG 0x1190 +#define EXYNOS3_TOP_RETENTION_COREBLK_SYS_PWR_REG 0x1194 +#define EXYNOS3_TOP_PWR_COREBLK_SYS_PWR_REG 0x1198 +#define EXYNOS3_LOGIC_RESET_SYS_PWR_REG 0x11A0 +#define EXYNOS3_OSCCLK_GATE_SYS_PWR_REG 0x11A4 +#define EXYNOS3_LOGIC_RESET_COREBLK_SYS_PWR_REG 0x11B0 +#define EXYNOS3_OSCCLK_GATE_COREBLK_SYS_PWR_REG 0x11B4 +#define EXYNOS3_PAD_RETENTION_DRAM_SYS_PWR_REG 0x1200 +#define EXYNOS3_PAD_RETENTION_MAUDIO_SYS_PWR_REG 0x1204 +#define EXYNOS3_PAD_RETENTION_SPI_SYS_PWR_REG 0x1208 +#define EXYNOS3_PAD_RETENTION_MMC2_SYS_PWR_REG 0x1218 +#define EXYNOS3_PAD_RETENTION_GPIO_SYS_PWR_REG 0x1220 +#define EXYNOS3_PAD_RETENTION_UART_SYS_PWR_REG 0x1224 +#define EXYNOS3_PAD_RETENTION_MMC0_SYS_PWR_REG 0x1228 +#define EXYNOS3_PAD_RETENTION_MMC1_SYS_PWR_REG 0x122C +#define EXYNOS3_PAD_RETENTION_EBIA_SYS_PWR_REG 0x1230 +#define EXYNOS3_PAD_RETENTION_EBIB_SYS_PWR_REG 0x1234 +#define EXYNOS3_PAD_RETENTION_JTAG_SYS_PWR_REG 0x1238 +#define EXYNOS3_PAD_ISOLATION_SYS_PWR_REG 0x1240 +#define EXYNOS3_PAD_ALV_SEL_SYS_PWR_REG 0x1260 +#define EXYNOS3_XUSBXTI_SYS_PWR_REG 0x1280 +#define EXYNOS3_XXTI_SYS_PWR_REG 0x1284 +#define EXYNOS3_EXT_REGULATOR_SYS_PWR_REG 0x12C0 +#define EXYNOS3_EXT_REGULATOR_COREBLK_SYS_PWR_REG 0x12C4 +#define EXYNOS3_GPIO_MODE_SYS_PWR_REG 0x1300 +#define EXYNOS3_GPIO_MODE_MAUDIO_SYS_PWR_REG 0x1340 +#define EXYNOS3_TOP_ASB_RESET_SYS_PWR_REG 0x1344 +#define EXYNOS3_TOP_ASB_ISOLATION_SYS_PWR_REG 0x1348 +#define EXYNOS3_TOP_ASB_RESET_COREBLK_SYS_PWR_REG 0x1350 +#define EXYNOS3_TOP_ASB_ISOLATION_COREBLK_SYS_PWR_REG 0x1354 +#define EXYNOS3_CAM_SYS_PWR_REG 0x1380 +#define EXYNOS3_MFC_SYS_PWR_REG 0x1388 +#define EXYNOS3_G3D_SYS_PWR_REG 0x138C +#define EXYNOS3_LCD0_SYS_PWR_REG 0x1390 +#define EXYNOS3_ISP_SYS_PWR_REG 0x1394 +#define EXYNOS3_MAUDIO_SYS_PWR_REG 0x1398 +#define EXYNOS3_DRAM_FREQ_DOWN_SYS_PWR_REG 0x13B0 +#define EXYNOS3_DDRPHY_DLLOFF_SYS_PWR_REG 0x13B4 +#define EXYNOS3_CMU_SYSCLK_ISP_SYS_PWR_REG 0x13B8 +#define EXYNOS3_LPDDR_PHY_DLL_LOCK_SYS_PWR_REG 0x13C0 +#define EXYNOS3_BPLL_SYSCLK_SYS_PWR_REG 0x13C4 +#define EXYNOS3_UPLL_SYSCLK_SYS_PWR_REG 0x13C8 + +#define EXYNOS3_ARM_CORE0_OPTION 0x2008 +#define EXYNOS3_ARM_CORE_OPTION(_nr) \ + (EXYNOS3_ARM_CORE0_OPTION + ((_nr) * 0x80)) + +#define EXYNOS3_ARM_COMMON_OPTION 0x2408 +#define EXYNOS3_ARM_L2_OPTION 0x2608 +#define EXYNOS3_TOP_PWR_OPTION 0x2C48 +#define EXYNOS3_CORE_TOP_PWR_OPTION 0x2CA8 +#define EXYNOS3_XUSBXTI_DURATION 0x341C +#define EXYNOS3_XXTI_DURATION 0x343C +#define EXYNOS3_EXT_REGULATOR_DURATION 0x361C +#define EXYNOS3_EXT_REGULATOR_COREBLK_DURATION 0x363C +#define XUSBXTI_DURATION 0x00000BB8 +#define XXTI_DURATION XUSBXTI_DURATION +#define EXT_REGULATOR_DURATION 0x00001D4C +#define EXT_REGULATOR_COREBLK_DURATION EXT_REGULATOR_DURATION + +/* for XXX_OPTION */ +#define EXYNOS3_OPTION_USE_SC_COUNTER (1 << 0) +#define EXYNOS3_OPTION_USE_SC_FEEDBACK (1 << 1) +#define EXYNOS3_OPTION_SKIP_DEACTIVATE_ACEACP_IN_PWDN (1 << 7) + +/* For EXYNOS5 */ + +#define EXYNOS5_AUTO_WDTRESET_DISABLE 0x0408 +#define EXYNOS5_MASK_WDTRESET_REQUEST 0x040C + +#define EXYNOS5_USE_RETENTION BIT(4) +#define EXYNOS5_SYS_WDTRESET (1 << 20) + +#define EXYNOS5_ARM_CORE0_SYS_PWR_REG 0x1000 +#define EXYNOS5_DIS_IRQ_ARM_CORE0_LOCAL_SYS_PWR_REG 0x1004 +#define EXYNOS5_DIS_IRQ_ARM_CORE0_CENTRAL_SYS_PWR_REG 0x1008 +#define EXYNOS5_ARM_CORE1_SYS_PWR_REG 0x1010 +#define EXYNOS5_DIS_IRQ_ARM_CORE1_LOCAL_SYS_PWR_REG 0x1014 +#define EXYNOS5_DIS_IRQ_ARM_CORE1_CENTRAL_SYS_PWR_REG 0x1018 +#define EXYNOS5_FSYS_ARM_SYS_PWR_REG 0x1040 +#define EXYNOS5_DIS_IRQ_FSYS_ARM_CENTRAL_SYS_PWR_REG 0x1048 +#define EXYNOS5_ISP_ARM_SYS_PWR_REG 0x1050 +#define EXYNOS5_DIS_IRQ_ISP_ARM_LOCAL_SYS_PWR_REG 0x1054 +#define EXYNOS5_DIS_IRQ_ISP_ARM_CENTRAL_SYS_PWR_REG 0x1058 +#define EXYNOS5_ARM_COMMON_SYS_PWR_REG 0x1080 +#define EXYNOS5_ARM_L2_SYS_PWR_REG 0x10C0 +#define EXYNOS5_CMU_ACLKSTOP_SYS_PWR_REG 0x1100 +#define EXYNOS5_CMU_SCLKSTOP_SYS_PWR_REG 0x1104 +#define EXYNOS5_CMU_RESET_SYS_PWR_REG 0x110C +#define EXYNOS5_CMU_ACLKSTOP_SYSMEM_SYS_PWR_REG 0x1120 +#define EXYNOS5_CMU_SCLKSTOP_SYSMEM_SYS_PWR_REG 0x1124 +#define EXYNOS5_CMU_RESET_SYSMEM_SYS_PWR_REG 0x112C +#define EXYNOS5_DRAM_FREQ_DOWN_SYS_PWR_REG 0x1130 +#define EXYNOS5_DDRPHY_DLLOFF_SYS_PWR_REG 0x1134 +#define EXYNOS5_DDRPHY_DLLLOCK_SYS_PWR_REG 0x1138 +#define EXYNOS5_APLL_SYSCLK_SYS_PWR_REG 0x1140 +#define EXYNOS5_MPLL_SYSCLK_SYS_PWR_REG 0x1144 +#define EXYNOS5_VPLL_SYSCLK_SYS_PWR_REG 0x1148 +#define EXYNOS5_EPLL_SYSCLK_SYS_PWR_REG 0x114C +#define EXYNOS5_BPLL_SYSCLK_SYS_PWR_REG 0x1150 +#define EXYNOS5_CPLL_SYSCLK_SYS_PWR_REG 0x1154 +#define EXYNOS5_MPLLUSER_SYSCLK_SYS_PWR_REG 0x1164 +#define EXYNOS5_BPLLUSER_SYSCLK_SYS_PWR_REG 0x1170 +#define EXYNOS5_TOP_BUS_SYS_PWR_REG 0x1180 +#define EXYNOS5_TOP_RETENTION_SYS_PWR_REG 0x1184 +#define EXYNOS5_TOP_PWR_SYS_PWR_REG 0x1188 +#define EXYNOS5_TOP_BUS_SYSMEM_SYS_PWR_REG 0x1190 +#define EXYNOS5_TOP_RETENTION_SYSMEM_SYS_PWR_REG 0x1194 +#define EXYNOS5_TOP_PWR_SYSMEM_SYS_PWR_REG 0x1198 +#define EXYNOS5_LOGIC_RESET_SYS_PWR_REG 0x11A0 +#define EXYNOS5_OSCCLK_GATE_SYS_PWR_REG 0x11A4 +#define EXYNOS5_LOGIC_RESET_SYSMEM_SYS_PWR_REG 0x11B0 +#define EXYNOS5_OSCCLK_GATE_SYSMEM_SYS_PWR_REG 0x11B4 +#define EXYNOS5_USBOTG_MEM_SYS_PWR_REG 0x11C0 +#define EXYNOS5_G2D_MEM_SYS_PWR_REG 0x11C8 +#define EXYNOS5_USBDRD_MEM_SYS_PWR_REG 0x11CC +#define EXYNOS5_SDMMC_MEM_SYS_PWR_REG 0x11D0 +#define EXYNOS5_CSSYS_MEM_SYS_PWR_REG 0x11D4 +#define EXYNOS5_SECSS_MEM_SYS_PWR_REG 0x11D8 +#define EXYNOS5_ROTATOR_MEM_SYS_PWR_REG 0x11DC +#define EXYNOS5_INTRAM_MEM_SYS_PWR_REG 0x11E0 +#define EXYNOS5_INTROM_MEM_SYS_PWR_REG 0x11E4 +#define EXYNOS5_JPEG_MEM_SYS_PWR_REG 0x11E8 +#define EXYNOS5_HSI_MEM_SYS_PWR_REG 0x11EC +#define EXYNOS5_MCUIOP_MEM_SYS_PWR_REG 0x11F4 +#define EXYNOS5_SATA_MEM_SYS_PWR_REG 0x11FC +#define EXYNOS5_PAD_RETENTION_DRAM_SYS_PWR_REG 0x1200 +#define EXYNOS5_PAD_RETENTION_MAU_SYS_PWR_REG 0x1204 +#define EXYNOS5_PAD_RETENTION_EFNAND_SYS_PWR_REG 0x1208 +#define EXYNOS5_PAD_RETENTION_GPIO_SYS_PWR_REG 0x1220 +#define EXYNOS5_PAD_RETENTION_UART_SYS_PWR_REG 0x1224 +#define EXYNOS5_PAD_RETENTION_MMCA_SYS_PWR_REG 0x1228 +#define EXYNOS5_PAD_RETENTION_MMCB_SYS_PWR_REG 0x122C +#define EXYNOS5_PAD_RETENTION_EBIA_SYS_PWR_REG 0x1230 +#define EXYNOS5_PAD_RETENTION_EBIB_SYS_PWR_REG 0x1234 +#define EXYNOS5_PAD_RETENTION_SPI_SYS_PWR_REG 0x1238 +#define EXYNOS5_PAD_RETENTION_GPIO_SYSMEM_SYS_PWR_REG 0x123C +#define EXYNOS5_PAD_ISOLATION_SYS_PWR_REG 0x1240 +#define EXYNOS5_PAD_ISOLATION_SYSMEM_SYS_PWR_REG 0x1250 +#define EXYNOS5_PAD_ALV_SEL_SYS_PWR_REG 0x1260 +#define EXYNOS5_XUSBXTI_SYS_PWR_REG 0x1280 +#define EXYNOS5_XXTI_SYS_PWR_REG 0x1284 +#define EXYNOS5_EXT_REGULATOR_SYS_PWR_REG 0x12C0 +#define EXYNOS5_GPIO_MODE_SYS_PWR_REG 0x1300 +#define EXYNOS5_GPIO_MODE_SYSMEM_SYS_PWR_REG 0x1320 +#define EXYNOS5_GPIO_MODE_MAU_SYS_PWR_REG 0x1340 +#define EXYNOS5_TOP_ASB_RESET_SYS_PWR_REG 0x1344 +#define EXYNOS5_TOP_ASB_ISOLATION_SYS_PWR_REG 0x1348 +#define EXYNOS5_GSCL_SYS_PWR_REG 0x1400 +#define EXYNOS5_ISP_SYS_PWR_REG 0x1404 +#define EXYNOS5_MFC_SYS_PWR_REG 0x1408 +#define EXYNOS5_G3D_SYS_PWR_REG 0x140C +#define EXYNOS5_DISP1_SYS_PWR_REG 0x1414 +#define EXYNOS5_MAU_SYS_PWR_REG 0x1418 +#define EXYNOS5_CMU_CLKSTOP_GSCL_SYS_PWR_REG 0x1480 +#define EXYNOS5_CMU_CLKSTOP_ISP_SYS_PWR_REG 0x1484 +#define EXYNOS5_CMU_CLKSTOP_MFC_SYS_PWR_REG 0x1488 +#define EXYNOS5_CMU_CLKSTOP_G3D_SYS_PWR_REG 0x148C +#define EXYNOS5_CMU_CLKSTOP_DISP1_SYS_PWR_REG 0x1494 +#define EXYNOS5_CMU_CLKSTOP_MAU_SYS_PWR_REG 0x1498 +#define EXYNOS5_CMU_SYSCLK_GSCL_SYS_PWR_REG 0x14C0 +#define EXYNOS5_CMU_SYSCLK_ISP_SYS_PWR_REG 0x14C4 +#define EXYNOS5_CMU_SYSCLK_MFC_SYS_PWR_REG 0x14C8 +#define EXYNOS5_CMU_SYSCLK_G3D_SYS_PWR_REG 0x14CC +#define EXYNOS5_CMU_SYSCLK_DISP1_SYS_PWR_REG 0x14D4 +#define EXYNOS5_CMU_SYSCLK_MAU_SYS_PWR_REG 0x14D8 +#define EXYNOS5_CMU_RESET_GSCL_SYS_PWR_REG 0x1580 +#define EXYNOS5_CMU_RESET_ISP_SYS_PWR_REG 0x1584 +#define EXYNOS5_CMU_RESET_MFC_SYS_PWR_REG 0x1588 +#define EXYNOS5_CMU_RESET_G3D_SYS_PWR_REG 0x158C +#define EXYNOS5_CMU_RESET_DISP1_SYS_PWR_REG 0x1594 +#define EXYNOS5_CMU_RESET_MAU_SYS_PWR_REG 0x1598 + +#define EXYNOS5_ARM_CORE0_OPTION 0x2008 +#define EXYNOS5_ARM_CORE1_OPTION 0x2088 +#define EXYNOS5_FSYS_ARM_OPTION 0x2208 +#define EXYNOS5_ISP_ARM_OPTION 0x2288 +#define EXYNOS5_ARM_COMMON_OPTION 0x2408 +#define EXYNOS5_ARM_L2_OPTION 0x2608 +#define EXYNOS5_TOP_PWR_OPTION 0x2C48 +#define EXYNOS5_TOP_PWR_SYSMEM_OPTION 0x2CC8 +#define EXYNOS5_JPEG_MEM_OPTION 0x2F48 +#define EXYNOS5_GSCL_OPTION 0x4008 +#define EXYNOS5_ISP_OPTION 0x4028 +#define EXYNOS5_MFC_OPTION 0x4048 +#define EXYNOS5_G3D_OPTION 0x4068 +#define EXYNOS5_DISP1_OPTION 0x40A8 +#define EXYNOS5_MAU_OPTION 0x40C8 + +#define EXYNOS5_USE_SC_FEEDBACK (1 << 1) +#define EXYNOS5_USE_SC_COUNTER (1 << 0) + +#define EXYNOS5_SKIP_DEACTIVATE_ACEACP_IN_PWDN (1 << 7) + +#define EXYNOS5_OPTION_USE_STANDBYWFE (1 << 24) +#define EXYNOS5_OPTION_USE_STANDBYWFI (1 << 16) + +#define EXYNOS5_OPTION_USE_RETENTION (1 << 4) + +#define EXYNOS5420_SWRESET_KFC_SEL 0x3 + +/* Only for EXYNOS5420 */ +#define EXYNOS5420_ISP_ARM_OPTION 0x2488 +#define EXYNOS5420_L2RSTDISABLE_VALUE BIT(3) + +#define EXYNOS5420_LPI_MASK 0x0004 +#define EXYNOS5420_LPI_MASK1 0x0008 +#define EXYNOS5420_UFS BIT(8) +#define EXYNOS5420_ATB_KFC BIT(13) +#define EXYNOS5420_ATB_ISP_ARM BIT(19) +#define EXYNOS5420_EMULATION BIT(31) +#define ATB_ISP_ARM BIT(12) +#define ATB_KFC BIT(13) +#define ATB_NOC BIT(14) + +#define EXYNOS5420_ARM_INTR_SPREAD_ENABLE 0x0100 +#define EXYNOS5420_ARM_INTR_SPREAD_USE_STANDBYWFI 0x0104 +#define EXYNOS5420_UP_SCHEDULER 0x0120 +#define SPREAD_ENABLE 0xF +#define SPREAD_USE_STANDWFI 0xF + +#define EXYNOS5420_KFC_CORE_RESET0 BIT(8) +#define EXYNOS5420_KFC_ETM_RESET0 BIT(20) + +#define EXYNOS5420_KFC_CORE_RESET(_nr) \ + ((EXYNOS5420_KFC_CORE_RESET0 | EXYNOS5420_KFC_ETM_RESET0) << (_nr)) + +#define EXYNOS5420_BB_CON1 0x0784 +#define EXYNOS5420_BB_SEL_EN BIT(31) +#define EXYNOS5420_BB_PMOS_EN BIT(7) +#define EXYNOS5420_BB_1300X 0XF + +#define EXYNOS5420_ARM_CORE2_SYS_PWR_REG 0x1020 +#define EXYNOS5420_DIS_IRQ_ARM_CORE2_LOCAL_SYS_PWR_REG 0x1024 +#define EXYNOS5420_DIS_IRQ_ARM_CORE2_CENTRAL_SYS_PWR_REG 0x1028 +#define EXYNOS5420_ARM_CORE3_SYS_PWR_REG 0x1030 +#define EXYNOS5420_DIS_IRQ_ARM_CORE3_LOCAL_SYS_PWR_REG 0x1034 +#define EXYNOS5420_DIS_IRQ_ARM_CORE3_CENTRAL_SYS_PWR_REG 0x1038 +#define EXYNOS5420_KFC_CORE0_SYS_PWR_REG 0x1040 +#define EXYNOS5420_DIS_IRQ_KFC_CORE0_LOCAL_SYS_PWR_REG 0x1044 +#define EXYNOS5420_DIS_IRQ_KFC_CORE0_CENTRAL_SYS_PWR_REG 0x1048 +#define EXYNOS5420_KFC_CORE1_SYS_PWR_REG 0x1050 +#define EXYNOS5420_DIS_IRQ_KFC_CORE1_LOCAL_SYS_PWR_REG 0x1054 +#define EXYNOS5420_DIS_IRQ_KFC_CORE1_CENTRAL_SYS_PWR_REG 0x1058 +#define EXYNOS5420_KFC_CORE2_SYS_PWR_REG 0x1060 +#define EXYNOS5420_DIS_IRQ_KFC_CORE2_LOCAL_SYS_PWR_REG 0x1064 +#define EXYNOS5420_DIS_IRQ_KFC_CORE2_CENTRAL_SYS_PWR_REG 0x1068 +#define EXYNOS5420_KFC_CORE3_SYS_PWR_REG 0x1070 +#define EXYNOS5420_DIS_IRQ_KFC_CORE3_LOCAL_SYS_PWR_REG 0x1074 +#define EXYNOS5420_DIS_IRQ_KFC_CORE3_CENTRAL_SYS_PWR_REG 0x1078 +#define EXYNOS5420_ISP_ARM_SYS_PWR_REG 0x1090 +#define EXYNOS5420_DIS_IRQ_ISP_ARM_LOCAL_SYS_PWR_REG 0x1094 +#define EXYNOS5420_DIS_IRQ_ISP_ARM_CENTRAL_SYS_PWR_REG 0x1098 +#define EXYNOS5420_ARM_COMMON_SYS_PWR_REG 0x10A0 +#define EXYNOS5420_KFC_COMMON_SYS_PWR_REG 0x10B0 +#define EXYNOS5420_KFC_L2_SYS_PWR_REG 0x10D0 +#define EXYNOS5420_DPLL_SYSCLK_SYS_PWR_REG 0x1158 +#define EXYNOS5420_IPLL_SYSCLK_SYS_PWR_REG 0x115C +#define EXYNOS5420_KPLL_SYSCLK_SYS_PWR_REG 0x1160 +#define EXYNOS5420_RPLL_SYSCLK_SYS_PWR_REG 0x1174 +#define EXYNOS5420_SPLL_SYSCLK_SYS_PWR_REG 0x1178 +#define EXYNOS5420_INTRAM_MEM_SYS_PWR_REG 0x11B8 +#define EXYNOS5420_INTROM_MEM_SYS_PWR_REG 0x11BC +#define EXYNOS5420_ONENANDXL_MEM_SYS_PWR 0x11C0 +#define EXYNOS5420_USBDEV_MEM_SYS_PWR 0x11CC +#define EXYNOS5420_USBDEV1_MEM_SYS_PWR 0x11D0 +#define EXYNOS5420_SDMMC_MEM_SYS_PWR 0x11D4 +#define EXYNOS5420_CSSYS_MEM_SYS_PWR 0x11D8 +#define EXYNOS5420_SECSS_MEM_SYS_PWR 0x11DC +#define EXYNOS5420_ROTATOR_MEM_SYS_PWR 0x11E0 +#define EXYNOS5420_INTRAM_MEM_SYS_PWR 0x11E4 +#define EXYNOS5420_INTROM_MEM_SYS_PWR 0x11E8 +#define EXYNOS5420_PAD_RETENTION_JTAG_SYS_PWR_REG 0x1208 +#define EXYNOS5420_PAD_RETENTION_DRAM_SYS_PWR_REG 0x1210 +#define EXYNOS5420_PAD_RETENTION_UART_SYS_PWR_REG 0x1214 +#define EXYNOS5420_PAD_RETENTION_MMC0_SYS_PWR_REG 0x1218 +#define EXYNOS5420_PAD_RETENTION_MMC1_SYS_PWR_REG 0x121C +#define EXYNOS5420_PAD_RETENTION_MMC2_SYS_PWR_REG 0x1220 +#define EXYNOS5420_PAD_RETENTION_HSI_SYS_PWR_REG 0x1224 +#define EXYNOS5420_PAD_RETENTION_EBIA_SYS_PWR_REG 0x1228 +#define EXYNOS5420_PAD_RETENTION_EBIB_SYS_PWR_REG 0x122C +#define EXYNOS5420_PAD_RETENTION_SPI_SYS_PWR_REG 0x1230 +#define EXYNOS5420_PAD_RETENTION_DRAM_COREBLK_SYS_PWR_REG 0x1234 +#define EXYNOS5420_DISP1_SYS_PWR_REG 0x1410 +#define EXYNOS5420_MAU_SYS_PWR_REG 0x1414 +#define EXYNOS5420_G2D_SYS_PWR_REG 0x1418 +#define EXYNOS5420_MSC_SYS_PWR_REG 0x141C +#define EXYNOS5420_FSYS_SYS_PWR_REG 0x1420 +#define EXYNOS5420_FSYS2_SYS_PWR_REG 0x1424 +#define EXYNOS5420_PSGEN_SYS_PWR_REG 0x1428 +#define EXYNOS5420_PERIC_SYS_PWR_REG 0x142C +#define EXYNOS5420_WCORE_SYS_PWR_REG 0x1430 +#define EXYNOS5420_CMU_CLKSTOP_DISP1_SYS_PWR_REG 0x1490 +#define EXYNOS5420_CMU_CLKSTOP_MAU_SYS_PWR_REG 0x1494 +#define EXYNOS5420_CMU_CLKSTOP_G2D_SYS_PWR_REG 0x1498 +#define EXYNOS5420_CMU_CLKSTOP_MSC_SYS_PWR_REG 0x149C +#define EXYNOS5420_CMU_CLKSTOP_FSYS_SYS_PWR_REG 0x14A0 +#define EXYNOS5420_CMU_CLKSTOP_FSYS2_SYS_PWR_REG 0x14A4 +#define EXYNOS5420_CMU_CLKSTOP_PSGEN_SYS_PWR_REG 0x14A8 +#define EXYNOS5420_CMU_CLKSTOP_PERIC_SYS_PWR_REG 0x14AC +#define EXYNOS5420_CMU_CLKSTOP_WCORE_SYS_PWR_REG 0x14B0 +#define EXYNOS5420_CMU_SYSCLK_TOPPWR_SYS_PWR_REG 0x14BC +#define EXYNOS5420_CMU_SYSCLK_DISP1_SYS_PWR_REG 0x14D0 +#define EXYNOS5420_CMU_SYSCLK_MAU_SYS_PWR_REG 0x14D4 +#define EXYNOS5420_CMU_SYSCLK_G2D_SYS_PWR_REG 0x14D8 +#define EXYNOS5420_CMU_SYSCLK_MSC_SYS_PWR_REG 0x14DC +#define EXYNOS5420_CMU_SYSCLK_FSYS_SYS_PWR_REG 0x14E0 +#define EXYNOS5420_CMU_SYSCLK_FSYS2_SYS_PWR_REG 0x14E4 +#define EXYNOS5420_CMU_SYSCLK_PSGEN_SYS_PWR_REG 0x14E8 +#define EXYNOS5420_CMU_SYSCLK_PERIC_SYS_PWR_REG 0x14EC +#define EXYNOS5420_CMU_SYSCLK_WCORE_SYS_PWR_REG 0x14F0 +#define EXYNOS5420_CMU_SYSCLK_SYSMEM_TOPPWR_SYS_PWR_REG 0x14F4 +#define EXYNOS5420_CMU_RESET_FSYS2_SYS_PWR_REG 0x1570 +#define EXYNOS5420_CMU_RESET_PSGEN_SYS_PWR_REG 0x1574 +#define EXYNOS5420_CMU_RESET_PERIC_SYS_PWR_REG 0x1578 +#define EXYNOS5420_CMU_RESET_WCORE_SYS_PWR_REG 0x157C +#define EXYNOS5420_CMU_RESET_DISP1_SYS_PWR_REG 0x1590 +#define EXYNOS5420_CMU_RESET_MAU_SYS_PWR_REG 0x1594 +#define EXYNOS5420_CMU_RESET_G2D_SYS_PWR_REG 0x1598 +#define EXYNOS5420_CMU_RESET_MSC_SYS_PWR_REG 0x159C +#define EXYNOS5420_CMU_RESET_FSYS_SYS_PWR_REG 0x15A0 +#define EXYNOS5420_SFR_AXI_CGDIS1 0x15E4 +#define EXYNOS_ARM_CORE2_CONFIGURATION 0x2100 +#define EXYNOS5420_ARM_CORE2_OPTION 0x2108 +#define EXYNOS_ARM_CORE3_CONFIGURATION 0x2180 +#define EXYNOS5420_ARM_CORE3_OPTION 0x2188 +#define EXYNOS5420_ARM_COMMON_STATUS 0x2504 +#define EXYNOS5420_ARM_COMMON_OPTION 0x2508 +#define EXYNOS5420_KFC_COMMON_STATUS 0x2584 +#define EXYNOS5420_KFC_COMMON_OPTION 0x2588 +#define EXYNOS5420_LOGIC_RESET_DURATION3 0x2D1C + +#define EXYNOS5420_PAD_RET_GPIO_OPTION 0x30C8 +#define EXYNOS5420_PAD_RET_UART_OPTION 0x30E8 +#define EXYNOS5420_PAD_RET_MMCA_OPTION 0x3108 +#define EXYNOS5420_PAD_RET_MMCB_OPTION 0x3128 +#define EXYNOS5420_PAD_RET_MMCC_OPTION 0x3148 +#define EXYNOS5420_PAD_RET_HSI_OPTION 0x3168 +#define EXYNOS5420_PAD_RET_SPI_OPTION 0x31C8 +#define EXYNOS5420_PAD_RET_DRAM_COREBLK_OPTION 0x31E8 +#define EXYNOS_PAD_RET_DRAM_OPTION 0x3008 +#define EXYNOS_PAD_RET_MAUDIO_OPTION 0x3028 +#define EXYNOS_PAD_RET_JTAG_OPTION 0x3048 +#define EXYNOS_PAD_RET_GPIO_OPTION 0x3108 +#define EXYNOS_PAD_RET_UART_OPTION 0x3128 +#define EXYNOS_PAD_RET_MMCA_OPTION 0x3148 +#define EXYNOS_PAD_RET_MMCB_OPTION 0x3168 +#define EXYNOS_PAD_RET_EBIA_OPTION 0x3188 +#define EXYNOS_PAD_RET_EBIB_OPTION 0x31A8 + +#define EXYNOS_PS_HOLD_CONTROL 0x330C + +/* For SYS_PWR_REG */ +#define EXYNOS_SYS_PWR_CFG BIT(0) + +#define EXYNOS5420_MFC_CONFIGURATION 0x4060 +#define EXYNOS5420_MFC_STATUS 0x4064 +#define EXYNOS5420_MFC_OPTION 0x4068 +#define EXYNOS5420_G3D_CONFIGURATION 0x4080 +#define EXYNOS5420_G3D_STATUS 0x4084 +#define EXYNOS5420_G3D_OPTION 0x4088 +#define EXYNOS5420_DISP0_CONFIGURATION 0x40A0 +#define EXYNOS5420_DISP0_STATUS 0x40A4 +#define EXYNOS5420_DISP0_OPTION 0x40A8 +#define EXYNOS5420_DISP1_CONFIGURATION 0x40C0 +#define EXYNOS5420_DISP1_STATUS 0x40C4 +#define EXYNOS5420_DISP1_OPTION 0x40C8 +#define EXYNOS5420_MAU_CONFIGURATION 0x40E0 +#define EXYNOS5420_MAU_STATUS 0x40E4 +#define EXYNOS5420_MAU_OPTION 0x40E8 +#define EXYNOS5420_FSYS2_OPTION 0x4168 +#define EXYNOS5420_PSGEN_OPTION 0x4188 + +/* For EXYNOS_CENTRAL_SEQ_OPTION */ +#define EXYNOS5_USE_STANDBYWFI_ARM_CORE0 BIT(16) +#define EXYNOS5_USE_STANDBYWFI_ARM_CORE1 BUT(17) +#define EXYNOS5_USE_STANDBYWFE_ARM_CORE0 BIT(24) +#define EXYNOS5_USE_STANDBYWFE_ARM_CORE1 BIT(25) + +#define EXYNOS5420_ARM_USE_STANDBY_WFI0 BIT(4) +#define EXYNOS5420_ARM_USE_STANDBY_WFI1 BIT(5) +#define EXYNOS5420_ARM_USE_STANDBY_WFI2 BIT(6) +#define EXYNOS5420_ARM_USE_STANDBY_WFI3 BIT(7) +#define EXYNOS5420_KFC_USE_STANDBY_WFI0 BIT(8) +#define EXYNOS5420_KFC_USE_STANDBY_WFI1 BIT(9) +#define EXYNOS5420_KFC_USE_STANDBY_WFI2 BIT(10) +#define EXYNOS5420_KFC_USE_STANDBY_WFI3 BIT(11) +#define EXYNOS5420_ARM_USE_STANDBY_WFE0 BIT(16) +#define EXYNOS5420_ARM_USE_STANDBY_WFE1 BIT(17) +#define EXYNOS5420_ARM_USE_STANDBY_WFE2 BIT(18) +#define EXYNOS5420_ARM_USE_STANDBY_WFE3 BIT(19) +#define EXYNOS5420_KFC_USE_STANDBY_WFE0 BIT(20) +#define EXYNOS5420_KFC_USE_STANDBY_WFE1 BIT(21) +#define EXYNOS5420_KFC_USE_STANDBY_WFE2 BIT(22) +#define EXYNOS5420_KFC_USE_STANDBY_WFE3 BIT(23) + +#define DUR_WAIT_RESET 0xF + +#define EXYNOS5420_USE_STANDBY_WFI_ALL (EXYNOS5420_ARM_USE_STANDBY_WFI0 \ + | EXYNOS5420_ARM_USE_STANDBY_WFI1 \ + | EXYNOS5420_ARM_USE_STANDBY_WFI2 \ + | EXYNOS5420_ARM_USE_STANDBY_WFI3 \ + | EXYNOS5420_KFC_USE_STANDBY_WFI0 \ + | EXYNOS5420_KFC_USE_STANDBY_WFI1 \ + | EXYNOS5420_KFC_USE_STANDBY_WFI2 \ + | EXYNOS5420_KFC_USE_STANDBY_WFI3) + +#endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */ -- cgit v1.2.3 From b84106b4e2290c081cdab521fa832596cdfea246 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 25 Feb 2016 14:35:57 -0600 Subject: PCI: Disable IO/MEM decoding for devices with non-compliant BARs The PCI config header (first 64 bytes of each device's config space) is defined by the PCI spec so generic software can identify the device and manage its usage of I/O, memory, and IRQ resources. Some non-spec-compliant devices put registers other than BARs where the BARs should be. When the PCI core sizes these "BARs", the reads and writes it does may have unwanted side effects, and the "BAR" may appear to describe non-sensical address space. Add a flag bit to mark non-compliant devices so we don't touch their BARs. Turn off IO/MEM decoding to prevent the devices from consuming address space, since we can't read the BARs to find out what that address space would be. Signed-off-by: Bjorn Helgaas Tested-by: Andi Kleen CC: stable@vger.kernel.org --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..5f80661d3519 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -359,6 +359,7 @@ struct pci_dev { unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ unsigned int irq_managed:1; unsigned int has_secondary_link:1; + unsigned int non_compliant_bars:1; /* broken BARs; ignore them */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 489061bba6c655a2f98d39be17df118c0fd09d57 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:25:54 +0000 Subject: regmap: add regmap_field_force_xxx() macros Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 7d3d498fd3e8..d36ea89adc50 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -76,8 +76,12 @@ struct reg_sequence { #define regmap_field_write(field, val) \ regmap_field_update_bits_base(field, ~0, val, NULL, false, false) +#define regmap_field_force_write(field, val) \ + regmap_field_update_bits_base(field, ~0, val, NULL, false, true) #define regmap_field_update_bits(field, mask, val)\ regmap_field_update_bits_base(field, mask, val, NULL, false, false) +#define regmap_field_force_update_bits(field, mask, val) \ + regmap_field_update_bits_base(field, mask, val, NULL, false, true) #define regmap_fields_write(field, id, val) \ regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false) -- cgit v1.2.3 From e6ef243fa4660f3206137bd5f3e69b13a9b7c28a Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 15 Feb 2016 05:26:14 +0000 Subject: regmap: add regmap_fields_force_xxx() macros Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index d36ea89adc50..e0960b3ff290 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -85,8 +85,12 @@ struct reg_sequence { #define regmap_fields_write(field, id, val) \ regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false) +#define regmap_fields_force_write(field, id, val) \ + regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, true) #define regmap_fields_update_bits(field, id, mask, val)\ regmap_fields_update_bits_base(field, id, mask, val, NULL, false, false) +#define regmap_fields_force_update_bits(field, id, mask, val) \ + regmap_fields_update_bits_base(field, id, mask, val, NULL, false, true) #ifdef CONFIG_REGMAP @@ -789,8 +793,6 @@ int regmap_field_read(struct regmap_field *field, unsigned int *val); int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -int regmap_fields_force_write(struct regmap_field *field, unsigned int id, - unsigned int val); int regmap_fields_read(struct regmap_field *field, unsigned int id, unsigned int *val); int regmap_fields_update_bits_base(struct regmap_field *field, unsigned int id, -- cgit v1.2.3 From f1705ec197e705b79ea40fe7a2cc5acfa1d3bfac Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 24 Feb 2016 09:25:37 -0800 Subject: net: ipv6: Make address flushing on ifdown optional Currently, all ipv6 addresses are flushed when the interface is configured down, including global, static addresses: $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 << nothing; all addresses have been flushed>> Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the set global addresses with no expire times are not flushed on an admin down. The sysctl is per-interface or system-wide for all interfaces $ sysctl -w net.ipv6.conf.eth1.keep_addr_on_down=1 or $ sysctl -w net.ipv6.conf.all.keep_addr_on_down=1 Will keep addresses on eth1 on an admin down. $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state DOWN qlen 1000 inet6 2100:1::2/120 scope global tentative valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link tentative valid_lft forever preferred_lft forever Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4b2267e1b7c3..7edc14fb66b6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,6 +62,7 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; + __s32 keep_addr_on_down; void *sysctl; }; -- cgit v1.2.3 From 3f1ac7a700d039c61d8d8b99f28d605d489a60cf Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:57:59 -0800 Subject: net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 91 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 83 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 472d7d7b01c2..8a400a54c92e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -12,6 +12,7 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H +#include #include #include @@ -40,9 +41,6 @@ struct compat_ethtool_rxnfc { #include -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated @@ -97,13 +95,74 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) return index % n_rx_rings; } +/* number of link mode bits/ulongs handled internally by kernel */ +#define __ETHTOOL_LINK_MODE_MASK_NBITS \ + (__ETHTOOL_LINK_MODE_LAST + 1) + +/* declare a link mode bitmap */ +#define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ + DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/* drivers must ignore base.cmd and base.link_mode_masks_nwords + * fields, but they are allowed to overwrite them (will be ignored). + */ +struct ethtool_link_ksettings { + struct ethtool_link_settings base; + struct { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + } link_modes; +}; + +/** + * ethtool_link_ksettings_zero_link_mode - clear link_ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + */ +#define ethtool_link_ksettings_zero_link_mode(ptr, name) \ + bitmap_zero((ptr)->link_modes.name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/** + * ethtool_link_ksettings_add_link_mode - set bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \ + __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +/** + * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + * + * Returns true/false. + */ +#define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ + test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +extern int +__ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings); + +/* DEPRECATED, use __ethtool_get_link_ksettings */ +extern int __ethtool_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd); + /** * struct ethtool_ops - optional netdev operations - * @get_settings: Get various device settings including Ethernet link + * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Get various device settings including Ethernet link * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code or - * zero. - * @set_settings: Set various device settings including Ethernet link + * before get_settings is called. Returns a negative error code + * or zero. + * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Set various device settings including Ethernet link * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -211,6 +270,19 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. + * @get_link_ksettings: When defined, takes precedence over the + * %get_settings method. Get various device settings + * including Ethernet link settings. The %cmd and + * %link_mode_masks_nwords fields should be ignored (use + * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any + * change to them will be overwritten by kernel. Returns a + * negative error code or zero. + * @set_link_ksettings: When defined, takes precedence over the + * %set_settings method. Set various device settings including + * Ethernet link settings. The %cmd and %link_mode_masks_nwords + * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS + * instead of the latter), any change to them will be overwritten + * by kernel. Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -293,6 +365,9 @@ struct ethtool_ops { struct ethtool_coalesce *); int (*set_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); - + int (*get_link_ksettings)(struct net_device *, + struct ethtool_link_ksettings *); + int (*set_link_ksettings)(struct net_device *, + const struct ethtool_link_ksettings *); }; #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From 3237fc63a3297d472a8cec33cb914f20570cfc23 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:58:11 -0800 Subject: net: ethtool: remove unused __ethtool_get_settings replaced by __ethtool_get_link_ksettings. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 8a400a54c92e..e2b7bf27c03e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -150,10 +150,6 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); -/* DEPRECATED, use __ethtool_get_link_ksettings */ -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * struct ethtool_ops - optional netdev operations * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings -- cgit v1.2.3 From cb77659272af51e80099c93b0e65abbf43bdaad5 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin Date: Sun, 14 Feb 2016 19:13:52 -0500 Subject: staging/lustre: proper support of NFS anonymous dentries NFS can ask to encode dentries that are not connected to the root. The fix check for parent is NULL and encode a file handle accordingly. Reviewed-on: http://review.whamcloud.com/8347 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4231 Reviewed-by: Fan Yong Reviewed-by: James Simmons Reviewed-by: Jian Yu Signed-off-by: Dmitry Eremin Signed-off-by: Oleg Drokin Acked-by: Jeff Layton Signed-off-by: Greg Kroah-Hartman --- include/linux/exportfs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index fa05e04c5531..d8414502edb4 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -96,6 +96,12 @@ enum fid_type { */ FILEID_FAT_WITH_PARENT = 0x72, + /* + * 128 bit child FID (struct lu_fid) + * 128 bit parent FID (struct lu_fid) + */ + FILEID_LUSTRE = 0x97, + /* * Filesystems must not use 0xff file ID. */ -- cgit v1.2.3 From 2f9ba65d9d79311119470d9a5280b335c2fb023c Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 9 Feb 2016 19:56:11 +0100 Subject: fbdev: kill fb_rotate The fb_rotate method in struct fb_ops is never actually invoked, and it's been that way in the entire history of git (in fact, the last occurrence of the string '->fb_rotate' vanished over 10 years ago, with b4d8aea6d6, and that merely tested whether the callback existed). So remove some dead code and make struct fb_obs a little smaller. Signed-off-by: Rasmus Villemoes Signed-off-by: Tomi Valkeinen --- include/linux/fb.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 55433f86f0a3..dfe88351341f 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -296,9 +296,6 @@ struct fb_ops { /* Draws cursor */ int (*fb_cursor) (struct fb_info *info, struct fb_cursor *cursor); - /* Rotates the display */ - void (*fb_rotate)(struct fb_info *info, int angle); - /* wait for blit idle, optional */ int (*fb_sync)(struct fb_info *info); -- cgit v1.2.3 From da4e4f18afe0f3729d68f3785c5802f786d36e34 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 23 Feb 2016 18:22:39 +0000 Subject: drivers/perf: arm_pmu: implement CPU_PM notifier When a CPU is suspended (either through suspend-to-RAM or CPUidle), its PMU registers content can be lost, which means that counters registers values that were initialized on power down entry have to be reprogrammed on power-up to make sure the counters set-up is preserved (ie on power-up registers take the reset values on Cold or Warm reset, which can be architecturally UNKNOWN). To guarantee seamless profiling conditions across a core power down this patch adds a CPU PM notifier to ARM pmus, that upon CPU PM entry/exit from low-power states saves/restores the pmu registers set-up (by using the ARM perf API), so that the power-down/up cycle does not affect the perf behaviour (apart from a black-out period between power-up/down CPU PM notifications that is unavoidable). Cc: Will Deacon Cc: Sudeep Holla Cc: Daniel Lezcano Cc: Mathieu Poirier Cc: Mark Rutland Acked-by: Ashwin Chaugule Acked-by: Kevin Hilman Signed-off-by: Lorenzo Pieralisi Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 2d5eaaa90078..4196c90a3c88 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -108,6 +108,7 @@ struct arm_pmu { struct platform_device *plat_device; struct pmu_hw_events __percpu *hw_events; struct notifier_block hotplug_nb; + struct notifier_block cpu_pm_nb; }; #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) -- cgit v1.2.3 From 34b0870515aaac6b7ea1ffdc370516b0a8024c82 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 26 Feb 2016 00:22:57 +0100 Subject: cpufreq: Simplify the cpufreq_for_each_valid_entry() That macro uses an internal static inline function that is first totally unnecessary and second hard to read, so simplify it and get rid of that monster. No functional changes. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d0bf555b6bbf..4064cfcfbffd 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -504,16 +504,6 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, } #endif -static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos) -{ - while ((*pos)->frequency != CPUFREQ_TABLE_END) - if ((*pos)->frequency != CPUFREQ_ENTRY_INVALID) - return true; - else - (*pos)++; - return false; -} - /* * cpufreq_for_each_entry - iterate over a cpufreq_frequency_table * @pos: the cpufreq_frequency_table * to use as a loop cursor. @@ -530,8 +520,11 @@ static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos) * @table: the cpufreq_frequency_table * to iterate over. */ -#define cpufreq_for_each_valid_entry(pos, table) \ - for (pos = table; cpufreq_next_valid(&pos); pos++) +#define cpufreq_for_each_valid_entry(pos, table) \ + for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++) \ + if (pos->frequency == CPUFREQ_ENTRY_INVALID) \ + continue; \ + else int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); -- cgit v1.2.3 From c283e41ef32442f41e7180f9bb1c5aedf9255bfe Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Mon, 15 Feb 2016 21:57:46 +0100 Subject: dmaengine: mmp-pdma: add number of requestors The DMA chip has a fixed number of requestor lines used for flow control. This number is platform dependent. The pxa_dma dma driver will use this value to activate or not the flow control. There won't be any impact on mmp_pdma driver. Signed-off-by: Robert Jarzmik --- include/linux/platform_data/mmp_dma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmp_dma.h b/include/linux/platform_data/mmp_dma.h index 2a330ec9e2af..d1397c8ed94e 100644 --- a/include/linux/platform_data/mmp_dma.h +++ b/include/linux/platform_data/mmp_dma.h @@ -14,6 +14,7 @@ struct mmp_dma_platdata { int dma_channels; + int nb_requestors; }; #endif /* MMP_DMA_H */ -- cgit v1.2.3 From 929e7f3bc7b82fb3e72392dec6a1df334cff6313 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 19 Feb 2016 15:52:32 -0800 Subject: clk: Make of_clk_get_parent_count() return unsigned ints Russell King recently pointed out a bug in the clk-gpio code where it fails to register the clk if of_clk_get_parent_count() returns an error because the "clocks" property isn't present in the DT node. If we're trying to count parents from DT we'd like to know the count, not if there is a "clocks" property or not. Furthermore, some drivers are assigning the return value to their clk_init_data::num_parents member which is unsigned, leading to potentially large numbers of parents when the property isn't present. Let's change the API to return an unsigned int instead of an int. All the callers just want to know the count anyway, and this avoids the bug that was in the clk-gpio driver. Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index fce7f027f8a7..da95258127aa 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -716,7 +716,7 @@ void of_clk_del_provider(struct device_node *np); struct clk *of_clk_src_simple_get(struct of_phandle_args *clkspec, void *data); struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data); -int of_clk_get_parent_count(struct device_node *np); +unsigned int of_clk_get_parent_count(struct device_node *np); int of_clk_parent_fill(struct device_node *np, const char **parents, unsigned int size); const char *of_clk_get_parent_name(struct device_node *np, int index); -- cgit v1.2.3 From 9a99417acbad99ba6c6a9389b45a53a4d002bb7e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sun, 28 Feb 2016 22:22:35 -0600 Subject: objtool: Add STACK_FRAME_NON_STANDARD() macro Add a new macro, STACK_FRAME_NON_STANDARD(), which is used to denote a function which does something unusual related to its stack frame. Use of the macro prevents objtool from emitting a false positive warning. Signed-off-by: Josh Poimboeuf Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Bernd Petrovitsch Cc: Borislav Petkov Cc: Chris J Arges Cc: Jiri Slaby Cc: Linus Torvalds Cc: Michal Marek Cc: Namhyung Kim Cc: Pedro Alves Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Link: http://lkml.kernel.org/r/34487a17b23dba43c50941599d47054a9584b219.1456719558.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- include/linux/frame.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/frame.h (limited to 'include/linux') diff --git a/include/linux/frame.h b/include/linux/frame.h new file mode 100644 index 000000000000..e6baaba3f1ae --- /dev/null +++ b/include/linux/frame.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_FRAME_H +#define _LINUX_FRAME_H + +#ifdef CONFIG_STACK_VALIDATION +/* + * This macro marks the given function's stack frame as "non-standard", which + * tells objtool to ignore the function when doing stack metadata validation. + * It should only be used in special cases where you're 100% sure it won't + * affect the reliability of frame pointers and kernel stack traces. + * + * For more information, see tools/objtool/Documentation/stack-validation.txt. + */ +#define STACK_FRAME_NON_STANDARD(func) \ + static void __used __section(__func_stack_frame_non_standard) \ + *__func_stack_frame_non_standard_##func = func + +#else /* !CONFIG_STACK_VALIDATION */ + +#define STACK_FRAME_NON_STANDARD(func) + +#endif /* CONFIG_STACK_VALIDATION */ + +#endif /* _LINUX_FRAME_H */ -- cgit v1.2.3 From d3204ab9951b755d35c540836402ae2668d3158b Mon Sep 17 00:00:00 2001 From: Jaehoon Chung Date: Mon, 1 Feb 2016 21:07:35 +0900 Subject: mmc: core: remove the MMC_DATA_STREAM flag It's not set to MMC_DATA_STREAM anywhere. It seems that it had been used with CMD11/CMD20. But according to Spec, CMD11/CMD20 are obsolete command. Signed-off-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 37967b6da03c..b01e77de1a74 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -113,7 +113,6 @@ struct mmc_data { #define MMC_DATA_WRITE (1 << 8) #define MMC_DATA_READ (1 << 9) -#define MMC_DATA_STREAM (1 << 10) unsigned int bytes_xfered; -- cgit v1.2.3 From 04e24b80a3ddf4cdf85e49a99d33aec27c9432ad Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 19 Jan 2016 12:28:31 +0100 Subject: mmc: tmio: add flag to reduce delay after changing clock status The docs for RCar Gen2 & 3 I have access to, mention delays of 5ms after stop and 1ms after start. Make it possible to apply these values. Signed-off-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 24b86d538e88..05d58ee5e6a7 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -65,6 +65,10 @@ * Some controllers can support SDIO IRQ signalling. */ #define TMIO_MMC_SDIO_IRQ (1 << 2) + +/* Some controllers don't need to wait 10ms for clock changes */ +#define TMIO_MMC_FAST_CLK_CHG (1 << 3) + /* * Some controllers require waiting for the SD bus to become * idle before writing to some registers. -- cgit v1.2.3 From bf96208f0539d2009ca0b031da2ed7c430edc3a2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 19 Jan 2016 12:32:58 +0100 Subject: mmc: tmio: refactor set_clock a little Some of the indentation made the code awful to read. Fix that. Also, introduce defines instead of magic hex values. Note that this includes one change: We mask out know 0xff instead of 0x1ff. But 0x100 has always been the clock enable bit. It doesn't make any sense to set it depending on the clock calculation. Update copyright notices, too. I'll be working on those files some more in the future. Signed-off-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mmc/tmio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/tmio.h b/include/linux/mmc/tmio.h index 84d9053b5dca..5f5cd80e9765 100644 --- a/include/linux/mmc/tmio.h +++ b/include/linux/mmc/tmio.h @@ -1,6 +1,8 @@ /* * include/linux/mmc/tmio.h * + * Copyright (C) 2016 Sang Engineering, Wolfram Sang + * Copyright (C) 2015-16 Renesas Electronics Corporation * Copyright (C) 2007 Ian Molton * Copyright (C) 2004 Ian Molton * @@ -61,6 +63,9 @@ #define TMIO_STAT_CMD_BUSY 0x40000000 #define TMIO_STAT_ILL_ACCESS 0x80000000 +#define CLK_CTL_DIV_MASK 0xff +#define CLK_CTL_SCLKEN BIT(8) + #define TMIO_BBS 512 /* Boot block size */ #endif /* LINUX_MMC_TMIO_H */ -- cgit v1.2.3 From 13c3d4740216c4931fce1e764b9a76dd55c2da23 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Thu, 21 Jan 2016 16:06:14 +0800 Subject: mmc: dw_mmc: remove struct block_settings This patch removes struct block_settings since it's never used anywhere. Signed-off-by: Shawn Lin Signed-off-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 89df7abedd67..e1f90b80b77a 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -242,14 +242,6 @@ struct dw_mci_dma_ops { struct dma_pdata; -struct block_settings { - unsigned short max_segs; /* see blk_queue_max_segments */ - unsigned int max_blk_size; /* maximum size of one mmc block */ - unsigned int max_blk_count; /* maximum number of blocks in one req*/ - unsigned int max_req_size; /* maximum number of bytes in one req*/ - unsigned int max_seg_size; /* see blk_queue_max_segment_size */ -}; - /* Board platform data */ struct dw_mci_board { u32 num_slots; -- cgit v1.2.3 From e8cc37b8fc3a94d17a2689cd77a7744d70477c14 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Thu, 21 Jan 2016 14:52:52 +0800 Subject: mmc: dw_mmc: remove DW_MCI_QUIRK_BROKEN_CARD_DETECTION quirk dw_mmc already use mmc_of_parse to get "broken-cd" property, but it considered "broken-cd" to be a quirk in its driver. We don't need this quirk here, and just take what we need from mmc->caps. Signed-off-by: Shawn Lin Tested-by: Jaehoon Chung Signed-off-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index e1f90b80b77a..7b41c6db1bb6 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -235,10 +235,8 @@ struct dw_mci_dma_ops { }; /* IP Quirks/flags. */ -/* Unreliable card detection */ -#define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(0) /* Timer for broken data transfer over scheme */ -#define DW_MCI_QUIRK_BROKEN_DTO BIT(1) +#define DW_MCI_QUIRK_BROKEN_DTO BIT(0) struct dma_pdata; -- cgit v1.2.3 From 30f065bf1f05b98ac6b5620c4ce6d0e865f9dc95 Mon Sep 17 00:00:00 2001 From: Maarten ter Huurne Date: Sun, 28 Feb 2016 16:53:26 +0100 Subject: regulator: act8865: Rename platform_data field to init_data Make the field name match its type. Signed-off-by: Maarten ter Huurne Signed-off-by: Mark Brown --- include/linux/regulator/act8865.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/act8865.h b/include/linux/regulator/act8865.h index 15fa8f2d35c9..2eb386017fa5 100644 --- a/include/linux/regulator/act8865.h +++ b/include/linux/regulator/act8865.h @@ -68,12 +68,12 @@ enum { * act8865_regulator_data - regulator data * @id: regulator id * @name: regulator name - * @platform_data: regulator init data + * @init_data: regulator init data */ struct act8865_regulator_data { int id; const char *name; - struct regulator_init_data *platform_data; + struct regulator_init_data *init_data; }; /** -- cgit v1.2.3 From 0e451e883bd13ce616f439e2414b8c17fa28318a Mon Sep 17 00:00:00 2001 From: Marina Varshaver Date: Thu, 18 Feb 2016 18:31:06 +0200 Subject: IB/mlx4: Add support for the don't trap rule Add support for receiving multicast/unicast traffic with the don't trap rule. Sniffing these packets requires a flow steering rule of type NORMAL at priority 0 with flag IB_FLOW_ATTR_FLAGS_DONT_TRAP set. Choosing between multicast or unicast is done via ethernet L2 dest_mac mask and value: - If mask is all zeros - unicast and multicast are set. - If mask non zero - only mask with multicast bit 1 and rest 0 is supported, the mac value will choose if it is multicast or unicast rule. If the mask multicast bit is on and some other bits are on too, it means a request for specific multicast or unicast, this is not supported, either receive all multicast or all unicast. Only when limitations are met registered QP will receive requested type but other QPs can receive same traffic if registered for it. Otherwise, if limitations are not met, an error will be returned. Limitations: - Rule must be with priority 0. - A0 mode is not supported. - Sniffer QP cannot appear in any other flow steering rule. Signed-off-by: Marina Varshaver Reviewed-by: Matan Barak Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a0e8cc8dcc67..8541a913f6a3 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -219,6 +219,7 @@ enum { MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB = 1ULL << 31, MLX4_DEV_CAP_FLAG2_LB_SRC_CHK = 1ULL << 32, MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33, + MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER = 1ULL << 34, }; enum { @@ -1160,6 +1161,8 @@ enum mlx4_net_trans_promisc_mode { MLX4_FS_REGULAR = 1, MLX4_FS_ALL_DEFAULT, MLX4_FS_MC_DEFAULT, + MLX4_FS_MIRROR_RX_PORT, + MLX4_FS_MIRROR_SX_PORT, MLX4_FS_UC_SNIFFER, MLX4_FS_MC_SNIFFER, MLX4_FS_MODE_NUM, /* should be last */ -- cgit v1.2.3 From 4d8b229d5ea610affe672e919021e9d02cd877da Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 26 Feb 2016 17:32:49 -0800 Subject: watchdog: Add 'action' and 'data' parameters to restart handler callback The 'action' (or restart mode) and data parameters may be used by restart handlers, so they should be passed to the restart callback functions. Cc: Sylvain Lemieux Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index b585fa2507ee..0b565f2ad242 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -46,7 +46,7 @@ struct watchdog_ops { unsigned int (*status)(struct watchdog_device *); int (*set_timeout)(struct watchdog_device *, unsigned int); unsigned int (*get_timeleft)(struct watchdog_device *); - int (*restart)(struct watchdog_device *); + int (*restart)(struct watchdog_device *, unsigned long, void *); long (*ioctl)(struct watchdog_device *, unsigned int, unsigned long); }; -- cgit v1.2.3 From b54ba2772b7af82a07eb48f88c88f7cadfb33401 Mon Sep 17 00:00:00 2001 From: Meny Yossefi Date: Thu, 18 Feb 2016 18:14:59 +0200 Subject: net/mlx5_core: Add helper function to read virtual port counters Added helper function to read 64bit virtual port Infiniband traffic counters. Signed-off-by: Meny Yossefi Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 3 ++- include/linux/mlx5/vport.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..0732e6c1fe7a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3126,7 +3126,8 @@ struct mlx5_ifc_query_vport_counter_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 reserved_at_41[0xb]; + u8 port_num[0x4]; u8 vport_number[0x10]; u8 reserved_at_60[0x60]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 123771003e68..a9f2bcc98cab 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -92,5 +92,7 @@ int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev); int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev); +int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, void *out, size_t out_sz); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 1c64bf6f291cae7cbe779e407db9477378bb4e7d Mon Sep 17 00:00:00 2001 From: Meny Yossefi Date: Thu, 18 Feb 2016 18:15:00 +0200 Subject: net/mlx5_core: Add helper function to read IB error counters Added helper function to read IB standard error counters via the PPCNT register. The PPCNT register read command provides the 32-bit error counters of both IB/RoCE link layer and transport layer. Signed-off-by: Meny Yossefi Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 3 ++- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 32 ++++++++++++++++++++++++++++++++ 3 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..99e2edc93d27 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1284,7 +1284,8 @@ enum { MLX5_RFC_3635_COUNTERS_GROUP = 0x3, MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP = 0x5, MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10, - MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11 + MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11, + MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, }; static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e3006dcf35d..8edcd08853dd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -847,6 +847,8 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); +int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, + u8 port_num, void *out, size_t sz); static inline int fw_initializing(struct mlx5_core_dev *dev) { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 0732e6c1fe7a..9f404de5f99b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1208,6 +1208,36 @@ struct mlx5_ifc_phys_layer_cntrs_bits { u8 reserved_at_640[0x180]; }; +struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { + u8 symbol_error_counter[0x10]; + + u8 link_error_recovery_counter[0x8]; + + u8 link_downed_counter[0x8]; + + u8 port_rcv_errors[0x10]; + + u8 port_rcv_remote_physical_errors[0x10]; + + u8 port_rcv_switch_relay_errors[0x10]; + + u8 port_xmit_discards[0x10]; + + u8 port_xmit_constraint_errors[0x8]; + + u8 port_rcv_constraint_errors[0x8]; + + u8 reserved_at_70[0x8]; + + u8 link_overrun_errors[0x8]; + + u8 reserved_at_80[0x10]; + + u8 vl_15_dropped[0x10]; + + u8 reserved_at_a0[0xa0]; +}; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { u8 transmit_queue_high[0x20]; @@ -2618,6 +2648,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; u8 reserved_at_0[0x7c0]; }; @@ -6955,6 +6986,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_peir_reg_bits peir_reg; struct mlx5_ifc_pelc_reg_bits pelc_reg; struct mlx5_ifc_pfcc_reg_bits pfcc_reg; + struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_pifr_reg_bits pifr_reg; struct mlx5_ifc_pipg_reg_bits pipg_reg; -- cgit v1.2.3 From 3efd9a11212d500e36c2837db853178cdaa86d5a Mon Sep 17 00:00:00 2001 From: Meny Yossefi Date: Thu, 18 Feb 2016 18:15:01 +0200 Subject: IB/mlx5: Modify MAD reading counters method to use counter registers Modify mlx5_ib_process_mad to use PPCNT and query_vport commands instead of MAD_IFC, as MAD_IFC is deprecated on new firmware versions (and doesn't support RoCE anyway). Traffic counters exist in both 32-bit and 64-bit forms. Declaring support of extended coutners results in traffic counters to be read in their 64-bit form only via the query_vport command. Error counters exist only in 32-bit form and read via PPCNT command. This commit also adds counters support in RoCE. Signed-off-by: Meny Yossefi Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 99e2edc93d27..12079fd20413 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -105,6 +105,29 @@ __mlx5_mask(typ, fld)) ___t; \ }) +/* Big endian getters */ +#define MLX5_GET64_BE(typ, p, fld) (*((__be64 *)(p) +\ + __mlx5_64_off(typ, fld))) + +#define MLX5_GET_BE(type_t, typ, p, fld) ({ \ + type_t tmp; \ + switch (sizeof(tmp)) { \ + case sizeof(u8): \ + tmp = (__force type_t)MLX5_GET(typ, p, fld); \ + break; \ + case sizeof(u16): \ + tmp = (__force type_t)cpu_to_be16(MLX5_GET(typ, p, fld)); \ + break; \ + case sizeof(u32): \ + tmp = (__force type_t)cpu_to_be32(MLX5_GET(typ, p, fld)); \ + break; \ + case sizeof(u64): \ + tmp = (__force type_t)MLX5_GET64_BE(typ, p, fld); \ + break; \ + } \ + tmp; \ + }) + enum { MLX5_MAX_COMMANDS = 32, MLX5_CMD_DATA_BLOCK_SIZE = 512, -- cgit v1.2.3 From 1015c2e8ca2b94d8964f8ab30d925b6f678fd9d2 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Sun, 21 Feb 2016 16:27:16 +0200 Subject: IB/mlx5: Define interface bits for IPoIB offloads The HW can supply several offloads for UD QP, added offloads for checksumming for both TX and RX and LSO for TX. Two new bits were added in order to expose and enable these offloads: 1. HCA capability bit: declares the support for IPoIB basic offloads. 2. QPC bit which will be used in the QP creation flow, which set these abilities in the QP. Signed-off-by: Erez Shitrit Signed-off-by: Eran Ben Elisha Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9f404de5f99b..711c9dc87f63 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -736,7 +736,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; - u8 reserved_at_200[0xe]; + u8 reserved_at_200[0x3]; + u8 ipoib_basic_offloads[0x1]; + u8 reserved_at_204[0xa]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; @@ -1810,7 +1812,7 @@ struct mlx5_ifc_qpc_bits { u8 log_sq_size[0x4]; u8 reserved_at_55[0x6]; u8 rlky[0x1]; - u8 reserved_at_5c[0x4]; + u8 ulp_stateless_offload_mode[0x4]; u8 counter_set_id[0x8]; u8 uar_page[0x18]; -- cgit v1.2.3 From b11a4f9cde1c06e0073662882b60c1fb95a1d597 Mon Sep 17 00:00:00 2001 From: Haggai Eran Date: Mon, 29 Feb 2016 15:45:03 +0200 Subject: IB/mlx5: Add support for setting source QP number In order to create multiple GSI QPs, we need to set the source QP number to one on all these QPs. Add the necessary definitions and infrastructure to do that. Reviewed-by: Leon Romanovsky Signed-off-by: Haggai Eran Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 3 ++- include/linux/mlx5/qp.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 711c9dc87f63..72bba5261766 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -772,7 +772,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_22e[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_at_237[0x4]; + u8 set_deth_sqpn[0x1]; + u8 reserved_at_239[0x3]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 5b8c89ffaa58..e5bbcf06de95 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -499,7 +499,8 @@ struct mlx5_qp_context { u8 reserved2[4]; __be32 next_send_psn; __be32 cqn_send; - u8 reserved3[8]; + __be32 deth_sqpn; + u8 reserved3[4]; __be32 last_acked_psn; __be32 ssn; __be32 params2; -- cgit v1.2.3 From a606b0f6691daf861482f8b77326f672238ffbfd Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 29 Feb 2016 18:05:28 +0200 Subject: net/mlx5: Refactor mlx5_core_mr to mkey Mlx5's mkey mechanism is also used for memory windows. The current code base uses MR (memory region) naming, which is inaccurate. Changing MR to mkey in order to represent its different usages more accurately. Signed-off-by: Matan Barak Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 24 +++++++++++++----------- include/linux/mlx5/qp.h | 4 ++-- 2 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8edcd08853dd..9108904a6a56 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -338,7 +338,7 @@ struct mlx5_core_sig_ctx { u32 sigerr_count; }; -struct mlx5_core_mr { +struct mlx5_core_mkey { u64 iova; u64 size; u32 key; @@ -426,7 +426,7 @@ struct mlx5_srq_table { struct radix_tree_root tree; }; -struct mlx5_mr_table { +struct mlx5_mkey_table { /* protect radix tree */ rwlock_t lock; @@ -484,9 +484,9 @@ struct mlx5_priv { struct mlx5_cq_table cq_table; /* end: cq staff */ - /* start: mr staff */ - struct mlx5_mr_table mr_table; - /* end: mr staff */ + /* start: mkey staff */ + struct mlx5_mkey_table mkey_table; + /* end: mkey staff */ /* start: alloc staff */ /* protect buffer alocation according to numa node */ @@ -739,16 +739,18 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, struct mlx5_query_srq_mbox_out *out); int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, u16 lwm, int is_srq); -void mlx5_init_mr_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev); -int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +void mlx5_init_mkey_table(struct mlx5_core_dev *dev); +void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev); +int mlx5_core_create_mkey(struct mlx5_core_dev *dev, + struct mlx5_core_mkey *mkey, struct mlx5_create_mkey_mbox_in *in, int inlen, mlx5_cmd_cbk_t callback, void *context, struct mlx5_create_mkey_mbox_out *out); -int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr); -int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, + struct mlx5_core_mkey *mkey); +int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, struct mlx5_query_mkey_mbox_out *out, int outlen); -int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey, u32 *mkey); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index e5bbcf06de95..cf031a3f16c5 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -622,9 +622,9 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); } -static inline struct mlx5_core_mr *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) +static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) { - return radix_tree_lookup(&dev->priv.mr_table.tree, key); + return radix_tree_lookup(&dev->priv.mkey_table.tree, key); } struct mlx5_page_fault_resume_mbox_in { -- cgit v1.2.3 From d2370e0a573e5c5ea9c96373558727abb3ea71f7 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 29 Feb 2016 18:05:30 +0200 Subject: IB/mlx5: Add memory windows allocation support This patch adds user-space support for memory windows allocation and deallocation. It also exposes the supported types via query_device_caps verb. Signed-off-by: Matan Barak Reviewed-by: Yishai Hadas Tested-by: Max Gurtovoy Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 72bba5261766..3044cfa683f1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -769,7 +769,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cd[0x1]; u8 reserved_at_22c[0x1]; u8 apm[0x1]; - u8 reserved_at_22e[0x7]; + u8 reserved_at_22e[0x2]; + u8 imaicl[0x1]; + u8 reserved_at_231[0x4]; u8 qkv[0x1]; u8 pkv[0x1]; u8 set_deth_sqpn[0x1]; -- cgit v1.2.3 From 871b642adebe300be2e50aa5f65a418510f636ec Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 26 Feb 2016 10:45:37 +0100 Subject: netdev: introduce ndo_set_rx_headroom This method allows the controlling device (i.e. the bridge) to specify additional headroom to be allocated for skb head on frame reception. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e52077ffe5ed..efe7cec111fa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1093,6 +1093,12 @@ struct tc_to_netdev { * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while * sampling packet. + * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); + * This function is used to specify the headroom that the skb must + * consider when allocation skb during packet reception. Setting + * appropriate rx headroom value allows avoiding skb head copy on + * forward. Setting a negative value reset the rx headroom to the + * default value. * */ struct net_device_ops { @@ -1278,6 +1284,8 @@ struct net_device_ops { bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + void (*ndo_set_rx_headroom)(struct net_device *dev, + int needed_headroom); }; /** @@ -1315,6 +1323,8 @@ struct net_device_ops { * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured + * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external + * entity (i.e. the master device for bridged veth) */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1343,6 +1353,7 @@ enum netdev_priv_flags { IFF_L3MDEV_SLAVE = 1<<23, IFF_TEAM = 1<<24, IFF_RXFH_CONFIGURED = 1<<25, + IFF_PHONY_HEADROOM = 1<<26, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1937,6 +1948,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); +/* returns the headroom that the master device needs to take in account + * when forwarding to this dev + */ +static inline unsigned netdev_get_fwd_headroom(struct net_device *dev) +{ + return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom; +} + +static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr) +{ + if (dev->netdev_ops->ndo_set_rx_headroom) + dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr); +} + +/* set the device rx headroom to the dev's default */ +static inline void netdev_reset_rx_headroom(struct net_device *dev) +{ + netdev_set_rx_headroom(dev, -1); +} + /* * Net namespace inlines */ -- cgit v1.2.3 From f6763c29ab86c3ee27760a06e07bbeab47635b61 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:05:54 -0500 Subject: svcrdma: Do not send Write chunk XDR pad with inline content The NFS server's XDR encoders adds an XDR pad for content in the xdr_buf page list at the beginning of the xdr_buf's tail buffer. On RDMA transports, Write chunks are sent separately and without an XDR pad. If a Write chunk is being sent, strip off the pad in the tail buffer so that inline content following the Write chunk remains XDR-aligned when it is sent to the client. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=294 Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 5322fea6fe4c..40b678584041 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -224,7 +224,7 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, /* svc_rdma_sendto.c */ extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *, - struct svc_rdma_req_map *); + struct svc_rdma_req_map *, bool); extern int svc_rdma_sendto(struct svc_rqst *); extern struct rpcrdma_read_chunk * svc_rdma_get_read_chunk(struct rpcrdma_msg *); -- cgit v1.2.3 From 4500632f60fa0d85e4101c374898cdf9b7b0cfac Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:06:02 -0500 Subject: nfsd: Lower NFSv4.1 callback message size limit The maximum size of a backchannel message on RPC-over-RDMA depends on the connection's inline threshold. Today that threshold is typically 1024 bytes, making the maximum message size 996 bytes. The Linux server's CREATE_SESSION operation checks that the size of callback Calls can be as large as 1044 bytes, to accommodate RPCSEC_GSS. Thus CREATE_SESSION fails if a client advertises the true message size maximum of 996 bytes. But the server's backchannel currently does not support RPCSEC_GSS. The actual maximum size it needs is much smaller. It is safe to reduce the limit to enable NFSv4.1 on RDMA backchannel operation. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/auth.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 1ecf13e148b8..6a241a277249 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -20,11 +20,18 @@ #include #include +/* + * Maximum size of AUTH_NONE authentication information, in XDR words. + */ +#define NUL_CALLSLACK (4) +#define NUL_REPLYSLACK (2) + /* * Size of the nodename buffer. RFC1831 specifies a hard limit of 255 bytes, * but Linux hostnames are actually limited to __NEW_UTS_LEN bytes. */ #define UNX_MAXNODENAME __NEW_UTS_LEN +#define UNX_CALLSLACK (21 + XDR_QUADLEN(UNX_MAXNODENAME)) struct rpcsec_gss_info; -- cgit v1.2.3 From bf36387ad394ad4fc93ad85fdd4a95dfa583556a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:06:20 -0500 Subject: svcrdma: svc_rdma_post_recv() should close connection on error Clean up: Most svc_rdma_post_recv() call sites close the transport connection when a receive cannot be posted. Wrap that in a common helper. Signed-off-by: Chuck Lever Reviewed-by: Devesh Sharma Tested-by: Devesh Sharma Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 40b678584041..aef47dd2bd1a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -234,6 +234,7 @@ extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, enum rpcrdma_errcode); extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t); +extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); -- cgit v1.2.3 From c6db03ea577846a72dc80638f4a70b392c21962f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:06:29 -0500 Subject: rpcrdma: Add RPCRDMA_HDRLEN_ERR Error headers are shorter than either RDMA_MSG or RDMA_NOMSG. Since HDRLEN_MIN is already used in several other places that would be annoying to change, add RPCRDMA_HDRLEN_ERR for the one or two spots where the shorter length is needed. Signed-off-by: Chuck Lever Reviewed-by: Devesh Sharma Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/rpc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index f33c5a4d6fe4..8c6d23cb0cae 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -102,6 +102,7 @@ struct rpcrdma_msg { * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks */ #define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) +#define RPCRDMA_HDRLEN_ERR (sizeof(__be32) * 5) enum rpcrdma_errcode { ERR_VERS = 1, -- cgit v1.2.3 From a6081b82c533d78041acb76738716aa7dafb339a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:06:38 -0500 Subject: svcrdma: Make RDMA_ERROR messages work Fix several issues with svc_rdma_send_error(): - Post a receive buffer to replace the one that was consumed by the incoming request - Posting a send should use DMA_TO_DEVICE, not DMA_FROM_DEVICE - No need to put_page _and_ free pages in svc_rdma_put_context - Make sure the sge is set up completely in case the error path goes through svc_rdma_unmap_dma() - Replace the use of ENOSYS, which has a reserved meaning Related fixes in svc_rdma_recvfrom(): - Don't leak the ctxt associated with the incoming request - Don't close the connection after sending an error reply - Let svc_rdma_send_error() figure out the right header error code As a last clean up, move svc_rdma_send_error() to svc_rdma_sendto.c with other similar functions. There is some common logic in these functions that could someday be combined to reduce code duplication. Signed-off-by: Chuck Lever Reviewed-by: Devesh Sharma Tested-by: Devesh Sharma Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index aef47dd2bd1a..42e852230a03 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -228,11 +228,11 @@ extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *, extern int svc_rdma_sendto(struct svc_rqst *); extern struct rpcrdma_read_chunk * svc_rdma_get_read_chunk(struct rpcrdma_msg *); +extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, + int); /* svc_rdma_transport.c */ extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); -extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, - enum rpcrdma_errcode); extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t); extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); -- cgit v1.2.3 From f3ea53fb3bc3908b6e9ef39e53a75b55df7f78f8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:06:47 -0500 Subject: svcrdma: Use correct XID in error replies When constructing an error reply, svc_rdma_xdr_encode_error() needs to view the client's request message so it can get the failing request's XID. svc_rdma_xdr_decode_req() is supposed to return a pointer to the client's request header. But if it fails to decode the client's message (and thus an error reply is needed) it does not return the pointer. The server then sends a bogus XID in the error reply. Instead, unconditionally generate the pointer to the client's header in svc_rdma_recvfrom(), and pass that pointer to both functions. Signed-off-by: Chuck Lever Reviewed-by: Devesh Sharma Tested-by: Devesh Sharma Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 42e852230a03..c2b0d95602d8 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -199,7 +199,7 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, struct xdr_buf *rcvbuf); /* svc_rdma_marshal.c */ -extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *); +extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg *, struct svc_rqst *); extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *, struct rpcrdma_msg *, enum rpcrdma_errcode, __be32 *); -- cgit v1.2.3 From 8bd5ba86d9ba7169e137fc4f32c553080c056a02 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:07:13 -0500 Subject: svcrdma: Use new CQ API for RPC-over-RDMA server receive CQs Calling ib_poll_cq() to sort through WCs during a completion is a common pattern amongst RDMA consumers. Since commit 14d3a3b2498e ("IB: add a proper completion queue abstraction"), WC sorting can be handled by the IB core. By converting to this new API, svcrdma is made a better neighbor to other RDMA consumers, as it allows the core to schedule the delivery of completions more fairly amongst all active consumers. Because each ib_cqe carries a pointer to a completion method, the core can now post operations on a consumer's QP, and handle the completions itself. svcrdma receive completions no longer use the dto_tasklet. Each polled Receive WC is now handled individually in soft IRQ context. The server transport's rdma_stat_rq_poll and rdma_stat_rq_prod metrics are no longer updated. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index c2b0d95602d8..cf79ab86d3d4 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -75,6 +75,7 @@ struct svc_rdma_op_ctxt { struct svc_rdma_fastreg_mr *frmr; int hdr_count; struct xdr_buf arg; + struct ib_cqe cqe; struct list_head dto_q; enum ib_wr_opcode wr_op; enum ib_wc_status wc_status; @@ -174,7 +175,6 @@ struct svcxprt_rdma { struct work_struct sc_work; }; /* sc_flags */ -#define RDMAXPRT_RQ_PENDING 1 #define RDMAXPRT_SQ_PENDING 2 #define RDMAXPRT_CONN_PENDING 3 -- cgit v1.2.3 From be99bb11400ce02552c35a6d3bf054de393ce30e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Mar 2016 13:07:22 -0500 Subject: svcrdma: Use new CQ API for RPC-over-RDMA server send CQs Calling ib_poll_cq() to sort through WCs during a completion is a common pattern amongst RDMA consumers. Since commit 14d3a3b2498e ("IB: add a proper completion queue abstraction"), WC sorting can be handled by the IB core. By converting to this new API, svcrdma is made a better neighbor to other RDMA consumers, as it allows the core to schedule the delivery of completions more fairly amongst all active consumers. This new API also aims each completion at a function that is specific to the WR's opcode. Thus the ctxt->wr_op field and the switch in process_context is replaced by a set of methods that handle each completion type. Because each ib_cqe carries a pointer to a completion method, the core can now post operations on a consumer's QP, and handle the completions itself. The server's rdma_stat_sq_poll and rdma_stat_sq_prod metrics are no longer updated. As a clean up, the cq_event_handler, the dto_tasklet, and all associated locking is removed, as they are no longer referenced or used. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index cf79ab86d3d4..3081339968c3 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -76,8 +76,9 @@ struct svc_rdma_op_ctxt { int hdr_count; struct xdr_buf arg; struct ib_cqe cqe; + struct ib_cqe reg_cqe; + struct ib_cqe inv_cqe; struct list_head dto_q; - enum ib_wr_opcode wr_op; enum ib_wc_status wc_status; u32 byte_len; u32 position; @@ -175,7 +176,6 @@ struct svcxprt_rdma { struct work_struct sc_work; }; /* sc_flags */ -#define RDMAXPRT_SQ_PENDING 2 #define RDMAXPRT_CONN_PENDING 3 #define RPCRDMA_LISTEN_BACKLOG 10 @@ -232,6 +232,11 @@ extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, int); /* svc_rdma_transport.c */ +extern void svc_rdma_wc_send(struct ib_cq *, struct ib_wc *); +extern void svc_rdma_wc_write(struct ib_cq *, struct ib_wc *); +extern void svc_rdma_wc_reg(struct ib_cq *, struct ib_wc *); +extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *); +extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *); extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t); extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t); -- cgit v1.2.3 From 09d4d087cd4869859fcc5dfc692f0830550a1b48 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 26 Feb 2016 17:32:24 +0100 Subject: mlx4: Implement devlink interface Implement newly introduced devlink interface. Add devlink port instances for every port and set the port types accordingly. Signed-off-by: Jiri Pirko v2->v3: -add dev param to devlink_register (api change) Signed-off-by: David S. Miller --- include/linux/mlx4/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 2e8af001c5da..bd0e7075ea6d 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -33,6 +33,7 @@ #ifndef MLX4_DRIVER_H #define MLX4_DRIVER_H +#include #include struct mlx4_dev; @@ -89,6 +90,8 @@ 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); +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); + static inline u64 mlx4_mac_to_u64(u8 *addr) { u64 mac = 0; -- cgit v1.2.3 From 6b6c07bdcdc97ccac2596063bfc32a5faddfe884 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 2 Mar 2016 00:13:39 +0200 Subject: net/mlx5: Make command timeout way shorter The command timeout is terribly long, whole two hours. Make it 60s so if things do go wrong, the user gets feedback in relatively short time, so they can take corrective actions and/or investigate using tools and such. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Or Gerlitz Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a815da92d4eb..3388a43b78f6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -54,7 +54,7 @@ enum { /* one minute for the sake of bringup. Generally, commands must always * complete and we may need to increase this timeout value */ - MLX5_CMD_TIMEOUT_MSEC = 7200 * 1000, + MLX5_CMD_TIMEOUT_MSEC = 60 * 1000, MLX5_CMD_WQ_MAX_NAME = 32, }; -- cgit v1.2.3 From 0ba422410bbf7081c3c7d7b2dcc10e9eb5cb46f7 Mon Sep 17 00:00:00 2001 From: Moshe Lazer Date: Wed, 2 Mar 2016 00:13:40 +0200 Subject: net/mlx5: Fix global UAR mapping Avoid double mapping of io mapped memory, Device page may be mapped to non-cached(NC) or to write-combining(WC). The code before this fix tries to map it both to WC and NC contrary to what stated in Intel's software developer manual. Here we remove the global WC mapping of all UARS "dev->priv.bf_mapping", since UAR mapping should be decided per UAR (e.g we want different mappings for EQs, CQs vs QPs). Caller will now have to choose whether to map via write-combining API or not. mlx5e SQs will choose write-combining in order to perform BlueFlame writes. Fixes: 88a85f99e51f ('TX latency optimization to save DMA reads') Signed-off-by: Moshe Lazer Reviewed-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3388a43b78f6..bb1a880a5bc5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -460,8 +460,6 @@ struct mlx5_priv { struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); - struct io_mapping *bf_mapping; - /* pages stuff */ struct workqueue_struct *pg_wq; struct rb_root page_root; @@ -719,7 +717,8 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, + bool map_wc); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 64d4e3431e686dc37ce388ba531c4c4e866fb141 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Sat, 27 Feb 2016 20:19:54 -0800 Subject: net: remove skb_sender_cpu_clear() After commit 52bd2d62ce67 ("net: better skb->sender_cpu and skb->napi_id cohabitation") skb_sender_cpu_clear() becomes empty and can be removed. Cc: Eric Dumazet Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eab4f8fbed58..797cefb888fb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1161,10 +1161,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; -static inline void skb_sender_cpu_clear(struct sk_buff *skb) -{ -} - #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { -- cgit v1.2.3 From 4ac801b77e6f06e6b12c069fd29216a4102065fb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 28 Feb 2016 12:26:52 +0200 Subject: qed: Semantic refactoring of interrupt code Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 3d43c1d4ecef..1f7599c77cd4 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -446,6 +446,12 @@ struct qed_eth_stats { #define RX_PI 0 #define TX_PI(tc) (RX_PI + 1 + tc) +struct qed_sb_cnt_info { + int sb_cnt; + int sb_iov_cnt; + int sb_free_blk; +}; + static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) { u32 prod = 0; -- cgit v1.2.3 From 811b0d6538b9f26f3eb0f90fe4e6118f2480ec6f Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 26 Feb 2016 20:59:18 +0100 Subject: nvmem: Add flag to export NVMEM to root only Legacy AT24, AT25 EEPROMs are exported in sys so that only root can read the contents. The EEPROMs may contain sensitive information. Add a flag so the provide can indicate that NVMEM should also restrict access to root only. Signed-off-by: Andrew Lunn Acked-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0b68caff1b3c..d24fefa0c11d 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -23,6 +23,7 @@ struct nvmem_config { const struct nvmem_cell_info *cells; int ncells; bool read_only; + bool root_only; }; #if IS_ENABLED(CONFIG_NVMEM) -- cgit v1.2.3 From b6c217ab9be6895384cf0b284ace84ad79e5c53b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 26 Feb 2016 20:59:19 +0100 Subject: nvmem: Add backwards compatibility support for older EEPROM drivers. Older drivers made an 'eeprom' file available in the /sys device directory. Have the NVMEM core provide this to retain backwards compatibility. Signed-off-by: Andrew Lunn Acked-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index d24fefa0c11d..a4fcc90b0f20 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -24,6 +24,9 @@ struct nvmem_config { int ncells; bool read_only; bool root_only; + /* To be only used by old driver/misc/eeprom drivers */ + bool compat; + struct device *base_dev; }; #if IS_ENABLED(CONFIG_NVMEM) @@ -44,5 +47,4 @@ static inline int nvmem_unregister(struct nvmem_device *nvmem) } #endif /* CONFIG_NVMEM */ - #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 3ccea0e1fdf896645f8cccddcfcf60cb289fdf76 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 26 Feb 2016 20:59:21 +0100 Subject: eeprom: at25: Remove in kernel API for accessing the EEPROM The setup() callback is not used by any in kernel code. Remove it. Any new code which requires access to the eeprom can use the NVMEM API. Signed-off-by: Andrew Lunn Acked-by: Srinivas Kandagatla Acked-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/eeprom.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h index 403e007aef68..e34e169f9dcb 100644 --- a/include/linux/spi/eeprom.h +++ b/include/linux/spi/eeprom.h @@ -30,8 +30,6 @@ struct spi_eeprom { */ #define EE_INSTR_BIT3_IS_ADDR 0x0010 - /* for exporting this chip's data to other kernel code */ - void (*setup)(struct memory_accessor *mem, void *context); void *context; }; -- cgit v1.2.3 From bec3c11bad0e7ac05fb90f204d0ab6f79945822b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 26 Feb 2016 20:59:24 +0100 Subject: misc: at24: replace memory_accessor with nvmem_device_read Now that the AT24 uses the NVMEM framework, replace the memory_accessor in the setup() callback with nvmem API calls. Signed-off-by: Andrew Lunn Acked-by: Srinivas Kandagatla Tested-by: Sekhar Nori Acked-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- include/linux/davinci_emac.h | 4 ++-- include/linux/memory.h | 11 ----------- include/linux/platform_data/at24.h | 10 +++++----- 3 files changed, 7 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/davinci_emac.h b/include/linux/davinci_emac.h index 542888504994..05b97144d342 100644 --- a/include/linux/davinci_emac.h +++ b/include/linux/davinci_emac.h @@ -12,7 +12,7 @@ #define _LINUX_DAVINCI_EMAC_H #include -#include +#include struct mdio_platform_data { unsigned long bus_freq; @@ -46,5 +46,5 @@ enum { EMAC_VERSION_2, /* DM646x */ }; -void davinci_get_mac_addr(struct memory_accessor *mem_acc, void *context); +void davinci_get_mac_addr(struct nvmem_device *nvmem, void *context); #endif diff --git a/include/linux/memory.h b/include/linux/memory.h index 8b8d8d12348e..b723a686fc10 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -136,17 +136,6 @@ extern struct memory_block *find_memory_block(struct mem_section *); #define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) #endif -/* - * 'struct memory_accessor' is a generic interface to provide - * in-kernel access to persistent memory such as i2c or SPI EEPROMs - */ -struct memory_accessor { - ssize_t (*read)(struct memory_accessor *, char *buf, off_t offset, - size_t count); - ssize_t (*write)(struct memory_accessor *, const char *buf, - off_t offset, size_t count); -}; - /* * Kernel text modification mutex, used for code patching. Users of this lock * can sleep. diff --git a/include/linux/platform_data/at24.h b/include/linux/platform_data/at24.h index c42aa89d34ee..dc9a13e5acda 100644 --- a/include/linux/platform_data/at24.h +++ b/include/linux/platform_data/at24.h @@ -9,7 +9,7 @@ #define _LINUX_AT24_H #include -#include +#include /** * struct at24_platform_data - data to set up at24 (generic eeprom) driver @@ -17,7 +17,7 @@ * @page_size: number of byte which can be written in one go * @flags: tunable options, check AT24_FLAG_* defines * @setup: an optional callback invoked after eeprom is probed; enables kernel - code to access eeprom via memory_accessor, see example + code to access eeprom via nvmem, see example * @context: optional parameter passed to setup() * * If you set up a custom eeprom type, please double-check the parameters. @@ -26,13 +26,13 @@ * * An example in pseudo code for a setup() callback: * - * void get_mac_addr(struct memory_accessor *mem_acc, void *context) + * void get_mac_addr(struct mvmem_device *nvmem, void *context) * { * u8 *mac_addr = ethernet_pdata->mac_addr; * off_t offset = context; * * // Read MAC addr from EEPROM - * if (mem_acc->read(mem_acc, mac_addr, offset, ETH_ALEN) == ETH_ALEN) + * if (nvmem_device_read(nvmem, offset, ETH_ALEN, mac_addr) == ETH_ALEN) * pr_info("Read MAC addr from EEPROM: %pM\n", mac_addr); * } * @@ -48,7 +48,7 @@ struct at24_platform_data { #define AT24_FLAG_IRUGO 0x20 /* sysfs-entry will be world-readable */ #define AT24_FLAG_TAKE8ADDR 0x10 /* take always 8 addresses (24c00) */ - void (*setup)(struct memory_accessor *, void *context); + void (*setup)(struct nvmem_device *nvmem, void *context); void *context; }; -- cgit v1.2.3 From b9830d120cbe155863399f25eaef6aa8353e767f Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 26 Feb 2016 15:13:19 -0800 Subject: Drivers: hv: util: Pass the channel information during the init call Pass the channel information to the util drivers that need to defer reading the channel while they are processing a request. This would address the following issue reported by Vitaly: Commit 3cace4a61610 ("Drivers: hv: utils: run polling callback always in interrupt context") removed direct *_transaction.state = HVUTIL_READY assignments from *_handle_handshake() functions introducing the following race: if a userspace daemon connects before we get first non-negotiation request from the server hv_poll_channel() won't set transaction state to HVUTIL_READY as (!channel) condition will fail, we set it to non-NULL on the first real request from the server. Signed-off-by: K. Y. Srinivasan Reported-by: Vitaly Kuznetsov Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index d23dab0d770b..aa0fadce9308 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1251,6 +1251,7 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); struct hv_util_service { u8 *recv_buffer; + void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); void (*util_deinit)(void); -- cgit v1.2.3 From 670666b9e0aff40c65d8061a2f53e79eee238685 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 2 Mar 2016 16:24:46 +0530 Subject: regulator: core: Add support for active-discharge configuration Add support to enable/disable active discharge of regulator via machine constraints. This configuration is done when setting machine constraint during regulator register and if regulator driver implemented the callback ops. Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 3 +++ include/linux/regulator/machine.h | 12 ++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 16ac9e108806..59dbaf78a25c 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -93,6 +93,8 @@ struct regulator_linear_range { * @get_current_limit: Get the configured limit for a current-limited regulator. * @set_input_current_limit: Configure an input limit. * + * @set_active_discharge: Set active discharge enable/disable of regulators. + * * @set_mode: Set the configured operating mode for the regulator. * @get_mode: Get the configured operating mode for the regulator. * @get_status: Return actual (not as-configured) status of regulator, as a @@ -149,6 +151,7 @@ struct regulator_ops { int (*set_input_current_limit) (struct regulator_dev *, int lim_uA); int (*set_over_current_protection) (struct regulator_dev *); + int (*set_active_discharge) (struct regulator_dev *, bool enable); /* enable/disable regulator */ int (*enable) (struct regulator_dev *); diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index a1067d0b3991..5d627c83a630 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -42,6 +42,13 @@ struct regulator; #define REGULATOR_CHANGE_DRMS 0x10 #define REGULATOR_CHANGE_BYPASS 0x20 +/* Regulator active discharge flags */ +enum regulator_active_discharge { + REGULATOR_ACTIVE_DISCHARGE_DEFAULT, + REGULATOR_ACTIVE_DISCHARGE_DISABLE, + REGULATOR_ACTIVE_DISCHARGE_ENABLE, +}; + /** * struct regulator_state - regulator state during low power system states * @@ -100,6 +107,9 @@ struct regulator_state { * @initial_state: Suspend state to set by default. * @initial_mode: Mode to set at startup. * @ramp_delay: Time to settle down after voltage change (unit: uV/us) + * @active_discharge: Enable/disable active discharge. The enum + * regulator_active_discharge values are used for + * initialisation. * @enable_time: Turn-on time of the rails (unit: microseconds) */ struct regulation_constraints { @@ -140,6 +150,8 @@ struct regulation_constraints { unsigned int ramp_delay; unsigned int enable_time; + unsigned int active_discharge; + /* constraint flags */ unsigned always_on:1; /* regulator never off when system is on */ unsigned boot_on:1; /* bootloader/firmware enabled regulator */ -- cgit v1.2.3 From 354794dacc213da7596cefea4dbcd8c094368807 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 2 Mar 2016 16:24:47 +0530 Subject: regulator: helper: Add helper to configure active-discharge using regmap Add helper function to set the state of active-discharge of regulator using regmap. The HW regulator driver can directly use this by providing the necessary information in the regulator descriptor. Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 59dbaf78a25c..cd271e89a7e6 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -269,6 +269,14 @@ enum regulator_type { * @bypass_mask: Mask for control when using regmap set_bypass * @bypass_val_on: Enabling value for control when using regmap set_bypass * @bypass_val_off: Disabling value for control when using regmap set_bypass + * @active_discharge_off: Enabling value for control when using regmap + * set_active_discharge + * @active_discharge_on: Disabling value for control when using regmap + * set_active_discharge + * @active_discharge_mask: Mask for control when using regmap + * set_active_discharge + * @active_discharge_reg: Register for control when using regmap + * set_active_discharge * * @enable_time: Time taken for initial enable of regulator (in uS). * @off_on_delay: guard time (in uS), before re-enabling a regulator @@ -318,6 +326,10 @@ struct regulator_desc { unsigned int bypass_mask; unsigned int bypass_val_on; unsigned int bypass_val_off; + unsigned int active_discharge_on; + unsigned int active_discharge_off; + unsigned int active_discharge_mask; + unsigned int active_discharge_reg; unsigned int enable_time; @@ -450,6 +462,8 @@ int regulator_set_voltage_time_sel(struct regulator_dev *rdev, int regulator_set_bypass_regmap(struct regulator_dev *rdev, bool enable); int regulator_get_bypass_regmap(struct regulator_dev *rdev, bool *enable); +int regulator_set_active_discharge_regmap(struct regulator_dev *rdev, + bool enable); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); #endif -- cgit v1.2.3 From a8463d4b0e47d1f37af684d97884ffcf35de043b Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 2 Feb 2016 21:46:32 -0800 Subject: dma: Provide simple noop dma ops We are going to require dma_ops for several common drivers, even for systems that do have an identity mapping. Lets provide some minimal no-op dma_ops that can be used for that purpose. Signed-off-by: Christian Borntraeger Reviewed-by: Joerg Roedel Signed-off-by: Andy Lutomirski Signed-off-by: Michael S. Tsirkin --- include/linux/dma-mapping.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 75857cda38e9..c0b27ff2c784 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -70,6 +70,8 @@ struct dma_map_ops { int is_phys; }; +extern struct dma_map_ops dma_noop_ops; + #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) #define DMA_MASK_NONE 0x0ULL -- cgit v1.2.3 From 2a2d1382fe9dccfce6f9c60a9c9fd2f0fe5bcf2b Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 2 Feb 2016 21:46:37 -0800 Subject: virtio: Add improved queue allocation API This leaves vring_new_virtqueue alone for compatbility, but it adds two new improved APIs: vring_create_virtqueue: Creates a virtqueue backed by automatically allocated coherent memory. (Some day it this could be extended to support non-coherent memory, too, if there ends up being a platform on which it's worthwhile.) __vring_new_virtqueue: Creates a virtqueue with a manually-specified layout. This should allow mic_virtio to work much more cleanly. Signed-off-by: Andy Lutomirski Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 23 +++++++++++++++++++++-- include/linux/virtio_ring.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 8f4d4bfa6d46..d5eb5479a425 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -75,8 +75,27 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *vq); bool virtqueue_is_broken(struct virtqueue *vq); -void *virtqueue_get_avail(struct virtqueue *vq); -void *virtqueue_get_used(struct virtqueue *vq); +const struct vring *virtqueue_get_vring(struct virtqueue *vq); +dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); +dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); +dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); + +/* + * Legacy accessors -- in almost all cases, these are the wrong functions + * to use. + */ +static inline void *virtqueue_get_desc(struct virtqueue *vq) +{ + return virtqueue_get_vring(vq)->desc; +} +static inline void *virtqueue_get_avail(struct virtqueue *vq) +{ + return virtqueue_get_vring(vq)->avail; +} +static inline void *virtqueue_get_used(struct virtqueue *vq) +{ + return virtqueue_get_vring(vq)->used; +} /** * virtio_device - representation of a device using virtio diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index a156e2b6ccfe..e8d36938f09a 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -59,6 +59,35 @@ static inline void virtio_store_mb(bool weak_barriers, struct virtio_device; struct virtqueue; +/* + * Creates a virtqueue and allocates the descriptor ring. If + * may_reduce_num is set, then this may allocate a smaller ring than + * expected. The caller should query virtqueue_get_ring_size to learn + * the actual size of the ring. + */ +struct virtqueue *vring_create_virtqueue(unsigned int index, + unsigned int num, + unsigned int vring_align, + struct virtio_device *vdev, + bool weak_barriers, + bool may_reduce_num, + bool (*notify)(struct virtqueue *vq), + void (*callback)(struct virtqueue *vq), + const char *name); + +/* Creates a virtqueue with a custom layout. */ +struct virtqueue *__vring_new_virtqueue(unsigned int index, + struct vring vring, + struct virtio_device *vdev, + bool weak_barriers, + bool (*notify)(struct virtqueue *), + void (*callback)(struct virtqueue *), + const char *name); + +/* + * Creates a virtqueue with a standard layout but a caller-allocated + * ring. + */ struct virtqueue *vring_new_virtqueue(unsigned int index, unsigned int num, unsigned int vring_align, @@ -68,7 +97,13 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, bool (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), const char *name); + +/* + * Destroys a virtqueue. If created with vring_create_virtqueue, this + * also frees the ring. + */ void vring_del_virtqueue(struct virtqueue *vq); + /* Filter out transport-specific feature bits. */ void vring_transport_features(struct virtio_device *vdev); -- cgit v1.2.3 From 77a8f0ad38844b5d4163424c4feb8abbbbb55af0 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 17 Jan 2016 10:18:12 -0800 Subject: Input: rotary_encoder - convert to use gpiod API Instead of using old GPIO API, let's switch to GPIOD API, which automatically handles polarity. Signed-off-by: Dmitry Torokhov --- include/linux/rotary_encoder.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rotary_encoder.h b/include/linux/rotary_encoder.h index fe3dc64e5aeb..4536c813a1e9 100644 --- a/include/linux/rotary_encoder.h +++ b/include/linux/rotary_encoder.h @@ -4,10 +4,6 @@ struct rotary_encoder_platform_data { unsigned int steps; unsigned int axis; - unsigned int gpio_a; - unsigned int gpio_b; - unsigned int inverted_a; - unsigned int inverted_b; unsigned int steps_per_period; bool relative_axis; bool rollover; -- cgit v1.2.3 From a67dd266adf42a24df31380e9da78390bb4d65ef Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 25 Feb 2016 10:08:35 +0100 Subject: netfilter: xtables: prepare for on-demand hook register This change prepares for upcoming on-demand xtables hook registration. We change the protoypes of the register/unregister functions. A followup patch will then add nf_hook_register/unregister calls to the iptables one. Once a hook is registered packets will be picked up, so all assignments of the form net->ipv4.iptable_$table = new_table have to be moved to ip(6)t_register_table, else we can see NULL net->ipv4.iptable_$table later. This patch doesn't change functionality; without this the actual change simply gets too big. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_arp/arp_tables.h | 9 +++++---- include/linux/netfilter_ipv4/ip_tables.h | 9 +++++---- include/linux/netfilter_ipv6/ip6_tables.h | 9 +++++---- 3 files changed, 15 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 6f074db2f23d..029b95e8924e 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -48,10 +48,11 @@ struct arpt_error { } extern void *arpt_alloc_initial_table(const struct xt_table *); -extern struct xt_table *arpt_register_table(struct net *net, - const struct xt_table *table, - const struct arpt_replace *repl); -extern void arpt_unregister_table(struct xt_table *table); +int arpt_register_table(struct net *net, const struct xt_table *table, + const struct arpt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void arpt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index aa598f942c01..7bfc5893ec31 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -24,10 +24,11 @@ extern void ipt_init(void) __init; -extern struct xt_table *ipt_register_table(struct net *net, - const struct xt_table *table, - const struct ipt_replace *repl); -extern void ipt_unregister_table(struct net *net, struct xt_table *table); +int ipt_register_table(struct net *net, const struct xt_table *table, + const struct ipt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void ipt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); /* Standard entry. */ struct ipt_standard { diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 0f76e5c674f9..b21c392d6012 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -25,10 +25,11 @@ extern void ip6t_init(void) __init; extern void *ip6t_alloc_initial_table(const struct xt_table *); -extern struct xt_table *ip6t_register_table(struct net *net, - const struct xt_table *table, - const struct ip6t_replace *repl); -extern void ip6t_unregister_table(struct net *net, struct xt_table *table); +int ip6t_register_table(struct net *net, const struct xt_table *table, + const struct ip6t_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void ip6t_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); -- cgit v1.2.3 From b9e69e127397187b70c813a4397cce7afb5e8cb1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 25 Feb 2016 10:08:36 +0100 Subject: netfilter: xtables: don't hook tables by default delay hook registration until the table is being requested inside a namespace. Historically, a particular table (iptables mangle, ip6tables filter, etc) was registered on module load. When netns support was added to iptables only the ip/ip6tables ruleset was made namespace aware, not the actual hook points. This means f.e. that when ipt_filter table/module is loaded on a system, then each namespace on that system has an (empty) iptables filter ruleset. In other words, if a namespace sends a packet, such skb is 'caught' by netfilter machinery and fed to hooking points for that table (i.e. INPUT, FORWARD, etc). Thanks to Eric Biederman, hooks are no longer global, but per namespace. This means that we can avoid allocation of empty ruleset in a namespace and defer hook registration until we need the functionality. We register a tables hook entry points ONLY in the initial namespace. When an iptables get/setockopt is issued inside a given namespace, we check if the table is found in the per-namespace list. If not, we attempt to find it in the initial namespace, and, if found, create an empty default table in the requesting namespace and register the needed hooks. Hook points are destroyed only once namespace is deleted, there is no 'usage count' (it makes no sense since there is no 'remove table' operation in xtables api). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c5577410c25d..80a305b85323 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -200,6 +200,9 @@ struct xt_table { u_int8_t af; /* address/protocol family */ int priority; /* hook order */ + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); + /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; @@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) return cnt; } -struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *); -void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *); +struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); #ifdef CONFIG_COMPAT #include -- cgit v1.2.3 From af4610c39589d839551da104f7da342d86f23ea0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 25 Feb 2016 10:08:38 +0100 Subject: netfilter: don't call hooks unless needed With the previous patches in place, a netns nf_hook_list might be empty, even if e.g. init_net performs filtering. Thus change nf_hook_thresh to check the hook_list as well before initializing hook_state and calling nf_hook_slow(). We still make use of static keys; if no netfilter modules are loaded list is guaranteed to be empty. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0ad556726181..9230f9aee896 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - -static inline bool nf_hook_list_active(struct list_head *hook_list, - u_int8_t pf, unsigned int hook) -{ - if (__builtin_constant_p(pf) && - __builtin_constant_p(hook)) - return static_key_false(&nf_hooks_needed[pf][hook]); - - return !list_empty(hook_list); -} -#else -static inline bool nf_hook_list_active(struct list_head *hook_list, - u_int8_t pf, unsigned int hook) -{ - return !list_empty(hook_list); -} #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); @@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { - struct list_head *hook_list = &net->nf.hooks[pf][hook]; + struct list_head *hook_list; + +#ifdef HAVE_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return 1; +#endif + + hook_list = &net->nf.hooks[pf][hook]; - if (nf_hook_list_active(hook_list, pf, hook)) { + if (!list_empty(hook_list)) { struct nf_hook_state state; nf_hook_state_init(&state, hook_list, hook, thresh, -- cgit v1.2.3 From afea03656add70a0e00f5b0039f87288c7af8b9f Mon Sep 17 00:00:00 2001 From: Giuseppe Cavallaro Date: Mon, 29 Feb 2016 14:27:28 +0100 Subject: stmmac: rework DMA bus setting and introduce new platform AXI structure This patch restructures the DMA bus settings and this is done by introducing a new platform structure used for programming the AXI Bus Mode Register inside the DMA module. This structure can be populated from device-tree as documented in the binding txt file. After initializing the DMA, the AXI register can be optionally tuned for platform drivers based. This patch also reworks some parameters to make coherent the DMA configuration now that AXI register is introduced. For example, the burst_len is managed by using the mentioned axi support above; so the snps,burst-len parameter has been removed. It makes sense to provide the AAL parameter from DT to Address-Aligned Beats inside the Register0 and review the PBL settings when initialize the engine. For PCI glue, rebuilding the story of this setting, it was added to align a configuration so not for fixing some known problem. No issue raised after this patch. It is safe to use the default burst length instead of tuning it to the maximum value Signed-off-by: Giuseppe Cavallaro Signed-off-by: Alexandre TORGUE Signed-off-by: David S. Miller --- include/linux/stmmac.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index eead8ab93c0a..6e53fa8942a4 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -90,7 +90,21 @@ struct stmmac_dma_cfg { int pbl; int fixed_burst; int mixed_burst; - int burst_len; + bool aal; +}; + +#define AXI_BLEN 7 +struct stmmac_axi { + bool axi_lpi_en; + bool axi_xit_frm; + u32 axi_wr_osr_lmt; + u32 axi_rd_osr_lmt; + bool axi_kbbe; + bool axi_axi_all; + u32 axi_blen[AXI_BLEN]; + bool axi_fb; + bool axi_mb; + bool axi_rb; }; struct plat_stmmacenet_data { @@ -122,5 +136,6 @@ struct plat_stmmacenet_data { int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); void *bsp_priv; + struct stmmac_axi *axi; }; #endif -- cgit v1.2.3 From a9e340dce3c3bceeb42f6b6d33b7858822d76cb6 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 17 Jan 2016 10:57:09 -0800 Subject: Input: rotary_encoder - move away from platform data structure Drop support for platform data passed via a C-structure and switch to device properties instead, which should make the driver compatible with all platforms: OF, ACPI and static boards. Static boards should use property sets to communicate device parameters to the driver. Signed-off-by: Dmitry Torokhov --- include/linux/rotary_encoder.h | 13 ------------- 1 file changed, 13 deletions(-) delete mode 100644 include/linux/rotary_encoder.h (limited to 'include/linux') diff --git a/include/linux/rotary_encoder.h b/include/linux/rotary_encoder.h deleted file mode 100644 index 4536c813a1e9..000000000000 --- a/include/linux/rotary_encoder.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef __ROTARY_ENCODER_H__ -#define __ROTARY_ENCODER_H__ - -struct rotary_encoder_platform_data { - unsigned int steps; - unsigned int axis; - unsigned int steps_per_period; - bool relative_axis; - bool rollover; - bool wakeup_source; -}; - -#endif /* __ROTARY_ENCODER_H__ */ -- cgit v1.2.3 From ff20c2e0acc5ad7e27c68592ade135efee399549 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 1 Mar 2016 09:45:14 +0530 Subject: mm: Some arch may want to use HPAGE_PMD related values as variables With next generation power processor, we are having a new mmu model [1] that require us to maintain a different linux page table format. Inorder to support both current and future ppc64 systems with a single kernel we need to make sure kernel can select between different page table format at runtime. With the new MMU (radix MMU) added, we will have two different pmd hugepage size 16MB for hash model and 2MB for Radix model. Hence make HPAGE_PMD related values as a variable. Actual conversion of HPAGE_PMD to a variable for ppc64 happens in a followup patch. [1] http://ibm.biz/power-isa3 (Needs registration). Signed-off-by: Kirill A. Shutemov Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- include/linux/bug.h | 9 +++++++++ include/linux/huge_mm.h | 3 --- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bug.h b/include/linux/bug.h index 7f4818673c41..e51b0709e78d 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -20,6 +20,7 @@ struct pt_regs; #define BUILD_BUG_ON_MSG(cond, msg) (0) #define BUILD_BUG_ON(condition) (0) #define BUILD_BUG() (0) +#define MAYBE_BUILD_BUG_ON(cond) (0) #else /* __CHECKER__ */ /* Force a compilation error if a constant expression is not a power of 2 */ @@ -83,6 +84,14 @@ struct pt_regs; */ #define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") +#define MAYBE_BUILD_BUG_ON(cond) \ + do { \ + if (__builtin_constant_p((cond))) \ + BUILD_BUG_ON(cond); \ + else \ + BUG_ON(cond); \ + } while (0) + #endif /* __CHECKER__ */ #ifdef CONFIG_GENERIC_BUG diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 459fd25b378e..f12513a20a06 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -111,9 +111,6 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, __split_huge_pmd(__vma, __pmd, __address); \ } while (0) -#if HPAGE_PMD_ORDER >= MAX_ORDER -#error "hugepages can't be allocated by the buddy allocator" -#endif extern int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); extern void vma_adjust_trans_huge(struct vm_area_struct *vma, -- cgit v1.2.3 From 88cb04b96a1934ecbfd1d324e7cde55890c1a576 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:58 -0500 Subject: cgroup: explicitly track whether a cgroup_subsys_state is visible to userland Currently, whether a css (cgroup_subsys_state) has its interface files created is not tracked and assumed to change together with the owning cgroup's lifecycle. cgroup directory and interface creation is being separated out from internal object creation to help refactoring and eventually allow cgroups which are not visible through cgroupfs. This patch adds CSS_VISIBLE to track whether a css has its interface files created and perform management operations only when necessary which helps decoupling interface file handling from internal object lifecycle. After this patch, all css interface file management functions can be called regardless of the current state and will achieve the expected result. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- include/linux/cgroup-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8fc3f0452289..7593c1a46786 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -45,6 +45,7 @@ enum { CSS_NO_REF = (1 << 0), /* no reference counting for this css */ CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ + CSS_VISIBLE = (1 << 3), /* css is visible to userland */ }; /* bits in struct cgroup flags field */ -- cgit v1.2.3 From 15a27c362d54378f17ec078579b2f6af88495a3f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:59 -0500 Subject: cgroup: introduce cgroup_{save|propagate|restore}_control() While controllers are being enabled and disabled in cgroup_subtree_control_write(), the original subsystem masks are stashed in local variables so that they can be restored if the operation fails in the middle. This patch adds dedicated fields to struct cgroup to be used instead of the local variables and implements functions to stash the current values, propagate the changes and restore them recursively. Combined with the previous changes, this makes subsystem management operations fully recursive and modularlized. This will be used to expand cgroup core functionalities. While at it, remove now unused @css_enable and @css_disable from cgroup_subtree_control_write(). Signed-off-by: Tejun Heo Acked-by: Zefan Li --- include/linux/cgroup-defs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7593c1a46786..aae8c94de4b3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -260,6 +260,8 @@ struct cgroup { */ u16 subtree_control; u16 subtree_ss_mask; + u16 old_subtree_control; + u16 old_subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; -- cgit v1.2.3 From d5bdec8ddb9f5fac3b351bed463a7132f6ba907b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Fri, 19 Feb 2016 13:56:58 +0100 Subject: lightnvm: fold get bb tbl when using dual/quad plane mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the media manager runs in dual or quad plane mode, lightnvm abstracts away plane specific commands. This poses a problem for get bad block table, as it reports bad blocks per plane, making the table either two or four times bigger than expected. Fold the bad block list before returning. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index d6750111e48e..7fa1838f7356 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -92,9 +92,9 @@ enum { NVM_ADDRMODE_CHANNEL = 1, /* Plane programming mode for LUN */ - NVM_PLANE_SINGLE = 0, - NVM_PLANE_DOUBLE = 1, - NVM_PLANE_QUAD = 2, + NVM_PLANE_SINGLE = 1, + NVM_PLANE_DOUBLE = 2, + NVM_PLANE_QUAD = 4, /* Status codes */ NVM_RSP_SUCCESS = 0x0, -- cgit v1.2.3 From 4ece44af733ff63a7cd12aaa8c85afb6d9fdc664 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Sat, 20 Feb 2016 08:52:41 +0100 Subject: lightnvm: rename ->nr_pages to ->nr_sects MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The struct rrpc->nr_pages can easily be interpreted as the number of flash pages allocated to rrpc, while it is the nr_sects. Make sure that this is reflected from the variable name. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 7fa1838f7356..8f8a74328f20 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -337,8 +337,8 @@ struct nvm_dev { int lps_per_blk; int *lptbl; - unsigned long total_pages; unsigned long total_blocks; + unsigned long total_secs; int nr_luns; unsigned max_pages_per_blk; -- cgit v1.2.3 From fe99c707fc7bb0baba75b26ed585ee3464612dbe Mon Sep 17 00:00:00 2001 From: David Rivshin Date: Wed, 2 Mar 2016 16:35:51 -0500 Subject: of: add 'const' for of_property_*_string*() parameter '*np' The of_property_{read,count,match}_string* family of functions never modify the struct device_node pointer that is passed in, so there is no reason for it to be non-const. Equivalent functions for all other types already take a 'const struct device_node *np'. Signed-off-by: David Rivshin Signed-off-by: Rob Herring --- include/linux/of.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index dd10626a615f..588fdd5d21ad 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -296,13 +296,13 @@ extern int of_property_read_u64_array(const struct device_node *np, u64 *out_values, size_t sz); -extern int of_property_read_string(struct device_node *np, +extern int of_property_read_string(const struct device_node *np, const char *propname, const char **out_string); -extern int of_property_match_string(struct device_node *np, +extern int of_property_match_string(const struct device_node *np, const char *propname, const char *string); -extern int of_property_read_string_helper(struct device_node *np, +extern int of_property_read_string_helper(const struct device_node *np, const char *propname, const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, @@ -538,14 +538,14 @@ static inline int of_property_read_u64_array(const struct device_node *np, return -ENOSYS; } -static inline int of_property_read_string(struct device_node *np, +static inline int of_property_read_string(const struct device_node *np, const char *propname, const char **out_string) { return -ENOSYS; } -static inline int of_property_read_string_helper(struct device_node *np, +static inline int of_property_read_string_helper(const struct device_node *np, const char *propname, const char **out_strs, size_t sz, int index) { @@ -571,7 +571,7 @@ static inline int of_property_read_u64(const struct device_node *np, return -ENOSYS; } -static inline int of_property_match_string(struct device_node *np, +static inline int of_property_match_string(const struct device_node *np, const char *propname, const char *string) { @@ -773,7 +773,7 @@ static inline int of_property_count_u64_elems(const struct device_node *np, * * If @out_strs is NULL, the number of strings in the property is returned. */ -static inline int of_property_read_string_array(struct device_node *np, +static inline int of_property_read_string_array(const struct device_node *np, const char *propname, const char **out_strs, size_t sz) { @@ -792,7 +792,7 @@ static inline int of_property_read_string_array(struct device_node *np, * does not have a value, and -EILSEQ if the string is not null-terminated * within the length of the property data. */ -static inline int of_property_count_strings(struct device_node *np, +static inline int of_property_count_strings(const struct device_node *np, const char *propname) { return of_property_read_string_helper(np, propname, NULL, 0, 0); @@ -816,7 +816,7 @@ static inline int of_property_count_strings(struct device_node *np, * * The out_string pointer is modified only if a valid string can be decoded. */ -static inline int of_property_read_string_index(struct device_node *np, +static inline int of_property_read_string_index(const struct device_node *np, const char *propname, int index, const char **output) { -- cgit v1.2.3 From 1ca1b6a65ba7771ab8d16971b5fc40f9ba7a0e53 Mon Sep 17 00:00:00 2001 From: John Youn Date: Fri, 5 Feb 2016 17:05:26 -0800 Subject: usb: gadget: Add gadget_is_superspeed_plus() Add a function to check for SuperSpeedPlus capable gadgets. Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index d82d0068872b..d6a1bdaf11c1 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -728,6 +728,16 @@ static inline int gadget_is_superspeed(struct usb_gadget *g) return g->max_speed >= USB_SPEED_SUPER; } +/** + * gadget_is_superspeed_plus() - return true if the hardware handles + * superspeed plus + * @g: controller that might support superspeed plus + */ +static inline int gadget_is_superspeed_plus(struct usb_gadget *g) +{ + return g->max_speed >= USB_SPEED_SUPER_PLUS; +} + /** * gadget_is_otg - return true iff the hardware is OTG-ready * @g: controller that might have a Mini-AB connector -- cgit v1.2.3 From eaef50c760576bca70b87fdc26eb87a3660529f8 Mon Sep 17 00:00:00 2001 From: John Youn Date: Fri, 5 Feb 2016 17:06:07 -0800 Subject: usb: gadget: Update usb_assign_descriptors for SuperSpeedPlus Add the 'ssp_descriptors' parameter to the usb_assign_descriptors() function. This allows a function driver to add descriptors for SuperSpeedPlus speeds if it supports it. Also update all uses of this function in the gadget subsystem so that they pass NULL for the ssp_descriptors parameters. Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index d6a1bdaf11c1..42527297f218 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -1204,7 +1204,8 @@ struct usb_function; int usb_assign_descriptors(struct usb_function *f, struct usb_descriptor_header **fs, struct usb_descriptor_header **hs, - struct usb_descriptor_header **ss); + struct usb_descriptor_header **ss, + struct usb_descriptor_header **ssp); void usb_free_all_descriptors(struct usb_function *f); struct usb_descriptor_header *usb_otg_descriptor_alloc( -- cgit v1.2.3 From f5c61225cf29c4f97e544ad7bd088256303acf97 Mon Sep 17 00:00:00 2001 From: John Youn Date: Fri, 5 Feb 2016 17:06:21 -0800 Subject: usb: gadget: Update function for SuperSpeedPlus Add a ssp_descriptors member to struct usb_function and handle the initialization and cleanup of it. This holds the SuperSpeedPlus descriptors for a function that supports SuperSpeedPlus. This is added by usb_assign_descriptors(). Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 1074b8921a5d..9ff1e465d307 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -126,6 +126,10 @@ struct usb_os_desc_table { * string identifiers assigned during @bind(). If this * pointer is null after initiation, the function will not * be available at super speed. + * @ssp_descriptors: Table of super speed plus descriptors, using + * interface and string identifiers assigned during @bind(). If + * this pointer is null after initiation, the function will not + * be available at super speed plus. * @config: assigned when @usb_add_function() is called; this is the * configuration with which this function is associated. * @os_desc_table: Table of (interface id, os descriptors) pairs. The function @@ -186,6 +190,7 @@ struct usb_function { struct usb_descriptor_header **fs_descriptors; struct usb_descriptor_header **hs_descriptors; struct usb_descriptor_header **ss_descriptors; + struct usb_descriptor_header **ssp_descriptors; struct usb_configuration *config; -- cgit v1.2.3 From 554eead5436401ae3cfdb7d79fca24c14ebab143 Mon Sep 17 00:00:00 2001 From: John Youn Date: Fri, 5 Feb 2016 17:06:35 -0800 Subject: usb: gadget: Update config for SuperSpeedPlus When a function is added to a configuration with usb_add_function(), the configuration speed flags are updated. These flags indicate for which speeds the configuration is valid for. This patch adds a flag in the configuration for SuperSpeedPlus and also updates this based on the existence of ssp_descriptors. Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 9ff1e465d307..2b81b24eb5aa 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -322,6 +322,7 @@ struct usb_configuration { unsigned superspeed:1; unsigned highspeed:1; unsigned fullspeed:1; + unsigned superspeed_plus:1; struct usb_function *interface[MAX_CONFIG_INTERFACES]; }; -- cgit v1.2.3 From de18757e272d0e948bfa3e083a1771887f719c05 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 7 Jan 2016 18:18:13 +0900 Subject: usb: renesas_usbhs: add R-Car Gen3 power control Since the usb2 phy driver for gen3 (phy-rcar-gen3-usb2) cannot access LPSTS and UGCTRL2 registers in the HSUSB module, this driver have to initialize the registers. So, this patch adds such handling code into rcar3.c. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- include/linux/usb/renesas_usbhs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 4db191fe8c2c..00a47d058d83 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -184,6 +184,7 @@ struct renesas_usbhs_driver_param { }; #define USBHS_TYPE_RCAR_GEN2 1 +#define USBHS_TYPE_RCAR_GEN3 2 /* * option: -- cgit v1.2.3 From 175f712119c57c0f2a9b553211d3edcfc460b484 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 18 Feb 2016 11:34:43 +0100 Subject: usb: gadget: provide interface for legacy gadgets to get UDC name Since commit 855ed04a3758b205e84b269f92d26ab36ed8e2f7 ("usb: gadget: udc-core: independent registration of gadgets and gadget drivers") gadget drivers can not assume that UDC drivers are already available on their initialization. This broke the HACK, which was used in gadgetfs driver, to get UDC controller name. This patch removes this hack and replaces it by additional function in the UDC core (which is usefully only for legacy drivers, please don't use it in the new code). Reported-by: Vegard Nossum Signed-off-by: Marek Szyprowski Tested-by: Vegard Nossum Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 42527297f218..dd7c53279e6a 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -1136,6 +1136,7 @@ extern int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, void (*release)(struct device *dev)); extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget); extern void usb_del_gadget_udc(struct usb_gadget *gadget); +extern char *usb_get_gadget_udc_name(void); /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From 75a9c82ab9638c13ce0964ed8d89d910597f03b4 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Fri, 19 Feb 2016 10:04:40 +0800 Subject: usb: gadget: add hnp_polling_support and host_request_flag in usb_gadget Add 2 flags for USB OTG HNP polling, hnp_polling_support is to indicate if the gadget can support HNP polling, host_request_flag is used for gadget to store host request information from application, which can be used to respond to HNP polling from host. Acked-by: Peter Chen Signed-off-by: Li Jun Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index dd7c53279e6a..5d4e151c49bf 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -595,6 +595,10 @@ struct usb_gadget_ops { * only supports HNP on a different root port. * @b_hnp_enable: OTG device feature flag, indicating that the A-Host * enabled HNP support. + * @hnp_polling_support: OTG device feature flag, indicating if the OTG device + * in peripheral mode can support HNP polling. + * @host_request_flag: OTG device feature flag, indicating if A-Peripheral + * or B-Peripheral wants to take host role. * @quirk_ep_out_aligned_size: epout requires buffer size to be aligned to * MaxPacketSize. * @is_selfpowered: if the gadget is self-powered. @@ -642,6 +646,8 @@ struct usb_gadget { unsigned b_hnp_enable:1; unsigned a_hnp_support:1; unsigned a_alt_hnp_support:1; + unsigned hnp_polling_support:1; + unsigned host_request_flag:1; unsigned quirk_ep_out_aligned_size:1; unsigned quirk_altset_not_supp:1; unsigned quirk_stall_not_supp:1; -- cgit v1.2.3 From ae57e97a95211397b46a40f8cb0a23966c054bc5 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Fri, 19 Feb 2016 10:04:42 +0800 Subject: usb: common: otg-fsm: add HNP polling support Adds HNP polling timer when transits to host state, the OTG status request will be sent to peripheral after timeout, if host request flag is set, it will switch to peripheral state, otherwise it will repeat HNP polling every 1.5s and maintain the current session. Acked-by: Peter Chen Signed-off-by: Li Jun Signed-off-by: Felipe Balbi --- include/linux/usb/otg-fsm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index f728f1854829..3059a9599f53 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -40,6 +40,18 @@ #define PROTO_HOST (1) #define PROTO_GADGET (2) +#define OTG_STS_SELECTOR 0xF000 /* OTG status selector, according to + * OTG and EH 2.0 Chapter 6.2.3 + * Table:6-4 + */ + +#define HOST_REQUEST_FLAG 1 /* Host request flag, according to + * OTG and EH 2.0 Charpter 6.2.3 + * Table:6-5 + */ + +#define T_HOST_REQ_POLL (1500) /* 1500ms, HNP polling interval */ + enum otg_fsm_timer { /* Standard OTG timers */ A_WAIT_VRISE, @@ -119,6 +131,8 @@ struct otg_fsm { /* Current usb protocol used: 0:undefine; 1:host; 2:client */ int protocol; struct mutex lock; + u8 *host_req_flag; + struct delayed_work hnp_polling_work; }; struct otg_fsm_ops { -- cgit v1.2.3 From 9c527f49a7312450923222941ff50e5940004e97 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Fri, 19 Feb 2016 10:04:48 +0800 Subject: usb: otg-fsm: add B_AIDL_BDIS timer Add A-idle to B-disconnect timer, B-device detects that bus is idle for more than TB_AIDL_BDIS min and begins HNP by turning off pullup on D+. This allows the bus to discharge to the SE0 state. Acked-by: Peter Chen Signed-off-by: Li Jun Signed-off-by: Felipe Balbi --- include/linux/usb/otg-fsm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index 3059a9599f53..24198e16f849 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -60,6 +60,7 @@ enum otg_fsm_timer { A_AIDL_BDIS, B_ASE0_BRST, A_BIDL_ADIS, + B_AIDL_BDIS, /* Auxiliary timers */ B_SE0_SRP, -- cgit v1.2.3 From ead22caf8507c0533aab6b89e26776414b477b6f Mon Sep 17 00:00:00 2001 From: Petr Kulhavy Date: Wed, 24 Feb 2016 16:27:16 +0100 Subject: usb: musb: core: added missing const qualifier to musb_hdrc_platform_data::config The musb_hdrc_platform_data::config was defined as a non-const pointer. However some drivers (e.g. the ux500) set up this pointer to point to a static structure, which is potentially dangerous. Since the musb core uses the pointer in a read-only manner the const qualifier was added to protect the content of the config. Signed-off-by: Petr Kulhavy Acked-by: Sergei Shtylyov Signed-off-by: Bin Liu Signed-off-by: Felipe Balbi --- include/linux/usb/musb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 96ddfb7ab018..0b3da40a525e 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -124,7 +124,7 @@ struct musb_hdrc_platform_data { int (*set_power)(int state); /* MUSB configuration-specific details */ - struct musb_hdrc_config *config; + const struct musb_hdrc_config *config; /* Architecture specific board data */ void *board_data; -- cgit v1.2.3 From 793b80ef14af56d20c998265287648ad34239b6f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Mar 2016 16:03:58 +0100 Subject: vfs: pass a flags argument to vfs_readv/vfs_writev This way we can set kiocb flags also from the sync read/write path for the read_iter/write_iter operations. For now there is no way to pass flags to plain read/write operations as there is no real need for that, and all flags passed are explicitly rejected for these files. Signed-off-by: Milosz Tanski [hch: rebased on top of my kiocb changes] Signed-off-by: Christoph Hellwig Reviewed-by: Stephen Bates Tested-by: Stephen Bates Acked-by: Jeff Moyer Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a2046275cdf..6ec87964644f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1712,9 +1712,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *) extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *); + unsigned long, loff_t *, int); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *); + unsigned long, loff_t *, int); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From f17d8b35452cab31a70d224964cd583fb2845449 Mon Sep 17 00:00:00 2001 From: Milosz Tanski Date: Thu, 3 Mar 2016 16:03:59 +0100 Subject: vfs: vfs: Define new syscalls preadv2,pwritev2 New syscalls that take an flag argument. No flags are added yet in this patch. Signed-off-by: Milosz Tanski [hch: rebased on top of my kiocb changes] Signed-off-by: Christoph Hellwig Reviewed-by: Stephen Bates Tested-by: Stephen Bates Acked-by: Jeff Moyer Signed-off-by: Al Viro --- include/linux/compat.h | 6 ++++++ include/linux/syscalls.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index a76c9172b2eb..fe4ccd0c748a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -340,6 +340,12 @@ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); +asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); +asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 185815c96433..d795472c54d8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -575,8 +575,14 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); +asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + int flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); +asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + int flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); asmlinkage long sys_chdir(const char __user *filename); -- cgit v1.2.3 From 97be7ebe53915af504fb491fb99f064c7cf3cb09 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Mar 2016 16:04:01 +0100 Subject: vfs: add the RWF_HIPRI flag for preadv2/pwritev2 This adds a flag that tells the file system that this is a high priority request for which it's worth to poll the hardware. The flag is purely advisory and can be ignored if not supported. Signed-off-by: Christoph Hellwig Reviewed-by: Stephen Bates Tested-by: Stephen Bates Acked-by: Jeff Moyer Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6ec87964644f..337de88ff50f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -320,6 +320,7 @@ struct writeback_control; #define IOCB_EVENTFD (1 << 0) #define IOCB_APPEND (1 << 1) #define IOCB_DIRECT (1 << 2) +#define IOCB_HIPRI (1 << 3) struct kiocb { struct file *ki_filp; -- cgit v1.2.3 From 8e0b60b96ba06d826a2b26e23b1986853a4e5291 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Mar 2016 16:04:03 +0100 Subject: blk-mq: enable polling support by default Now that applications need to explicitly ask for polling we can enable it by default in blk-mq drivers. Note that this will only have an affect on driver that supply a poll function, which currently only includes nvme. Signed-off-by: Christoph Hellwig Reviewed-by: Stephen Bates Tested-by: Stephen Bates Reviewed-by: Jeff Moyer Signed-off-by: Al Viro --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 29189aeace19..ff33a1ab58c9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -499,7 +499,8 @@ struct request_queue { #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_POLL)) static inline void queue_lockdep_assert_held(struct request_queue *q) { -- cgit v1.2.3 From b5d3755a22e0cc4c369c0985aef0c52c2477c1e7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 4 Mar 2016 11:52:16 +0100 Subject: uapi: define DIV_ROUND_UP for userland DIV_ROUND_UP is defined in linux/kernel.h only for the kernel. When ethtool.h is included by a userland app, we got the following error: include/linux/ethtool.h:1218:8: error: variably modified 'queue_mask' at file scope __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; ^ Let's add a common definition in uapi and use it everywhere. Fixes: ac2c7ad0e5d6 ("net/ethtool: introduce a new ioctl for per queue setting") CC: Kan Liang Suggested-by: Ben Hutchings Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..ac1923957236 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,7 +64,7 @@ #define round_down(x, y) ((x) & ~__round_mask(x, y)) #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) +#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_UP_ULL(ll,d) \ ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) -- cgit v1.2.3 From b821957a5ae76994eebf9eed3247be0ba5775c30 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 3 Mar 2016 00:48:30 +0000 Subject: regmap: replace regmap_write_bits() commit 23b92e4cf5fd ("regmap: remove regmap_write_bits()") removed regmap_write_bits(), but MFD driver was using it. So, commit e30fccd6771d ("regmap: Keep regmap_write_bits()") turns out it, but it is using original style. This patch uses regmap_update_bits_base() for regmap_write_bits() Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e0960b3ff290..0744c9fea24c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -74,6 +74,9 @@ struct reg_sequence { #define regmap_update_bits_check_async(map, reg, mask, val, change)\ regmap_update_bits_base(map, reg, mask, val, change, true, false) +#define regmap_write_bits(map, reg, mask, val) \ + regmap_update_bits_base(map, reg, mask, val, NULL, false, true) + #define regmap_field_write(field, val) \ regmap_field_update_bits_base(field, ~0, val, NULL, false, false) #define regmap_field_force_write(field, val) \ @@ -721,8 +724,6 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool async, bool force); -int regmap_write_bits(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val); int regmap_get_val_bytes(struct regmap *map); int regmap_get_max_register(struct regmap *map); int regmap_get_reg_stride(struct regmap *map); @@ -961,13 +962,6 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, return -EINVAL; } -static inline int regmap_write_bits(struct regmap *map, unsigned int reg, - unsigned int mask, unsigned int val) -{ - WARN_ONCE(1, "regmap API is disabled"); - return -EINVAL; -} - static inline int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force) -- cgit v1.2.3 From 045b98480cbe9d8dfe80983013591769f8a112cc Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 10 Feb 2016 14:29:50 +0530 Subject: regmap: irq: add devm apis for regmap_{add,del}_irq_chip Add device managed APIs for regmap_add_irq_chip() and regmap_del_irq_chip() so that it can be managed by device framework for freeing it. This helps on following: 1. Maintaining the sequence of resource allocation and deallocation regmap_add_irq_chip(&d); devm_requested_threaded_irq(virq) On free path: regmap_del_irq_chip(d); and then removing the irq registration. On this case, regmap irq is deleted before the irq is free. This force to use normal irq registration. By using devm apis, the sequence can be maintain properly: devm_regmap_add_irq_chip(&d); devm_requested_threaded_irq(virq); and resource deallocation will be done in reverse order by device framework. 2. No need to delete the regmap_irq_chip in error path or remove callback and hence there is less code on this path. Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 18394343f489..de428962bfe6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -868,6 +868,14 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); + +int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq, + int irq_flags, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); +void devm_regmap_del_irq_chip(struct device *dev, int irq, + struct regmap_irq_chip_data *data); + int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data); int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq); struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data); -- cgit v1.2.3 From d17799f9c10e283cccd4d598d3416e6fac336ab9 Mon Sep 17 00:00:00 2001 From: chenhui zhao Date: Fri, 20 Nov 2015 17:13:59 +0800 Subject: powerpc/rcpm: add RCPM driver There is a RCPM (Run Control/Power Management) in Freescale QorIQ series processors. The device performs tasks associated with device run control and power management. The driver implements some features: mask/unmask irq, enter/exit low power states, freeze time base, etc. Signed-off-by: Chenhui Zhao Signed-off-by: Tang Yuantian [scottwood: remove __KERNEL__ ifdef] Signed-off-by: Scott Wood --- include/linux/fsl/guts.h | 105 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h index 84d971ff3fba..649e9171a9b3 100644 --- a/include/linux/fsl/guts.h +++ b/include/linux/fsl/guts.h @@ -189,4 +189,109 @@ static inline void guts_set_pmuxcr_dma(struct ccsr_guts __iomem *guts, #endif +struct ccsr_rcpm_v1 { + u8 res0000[4]; + __be32 cdozsr; /* 0x0004 Core Doze Status Register */ + u8 res0008[4]; + __be32 cdozcr; /* 0x000c Core Doze Control Register */ + u8 res0010[4]; + __be32 cnapsr; /* 0x0014 Core Nap Status Register */ + u8 res0018[4]; + __be32 cnapcr; /* 0x001c Core Nap Control Register */ + u8 res0020[4]; + __be32 cdozpsr; /* 0x0024 Core Doze Previous Status Register */ + u8 res0028[4]; + __be32 cnappsr; /* 0x002c Core Nap Previous Status Register */ + u8 res0030[4]; + __be32 cwaitsr; /* 0x0034 Core Wait Status Register */ + u8 res0038[4]; + __be32 cwdtdsr; /* 0x003c Core Watchdog Detect Status Register */ + __be32 powmgtcsr; /* 0x0040 PM Control&Status Register */ +#define RCPM_POWMGTCSR_SLP 0x00020000 + u8 res0044[12]; + __be32 ippdexpcr; /* 0x0050 IP Powerdown Exception Control Register */ + u8 res0054[16]; + __be32 cpmimr; /* 0x0064 Core PM IRQ Mask Register */ + u8 res0068[4]; + __be32 cpmcimr; /* 0x006c Core PM Critical IRQ Mask Register */ + u8 res0070[4]; + __be32 cpmmcmr; /* 0x0074 Core PM Machine Check Mask Register */ + u8 res0078[4]; + __be32 cpmnmimr; /* 0x007c Core PM NMI Mask Register */ + u8 res0080[4]; + __be32 ctbenr; /* 0x0084 Core Time Base Enable Register */ + u8 res0088[4]; + __be32 ctbckselr; /* 0x008c Core Time Base Clock Select Register */ + u8 res0090[4]; + __be32 ctbhltcr; /* 0x0094 Core Time Base Halt Control Register */ + u8 res0098[4]; + __be32 cmcpmaskcr; /* 0x00a4 Core Machine Check Mask Register */ +}; + +struct ccsr_rcpm_v2 { + u8 res_00[12]; + __be32 tph10sr0; /* Thread PH10 Status Register */ + u8 res_10[12]; + __be32 tph10setr0; /* Thread PH10 Set Control Register */ + u8 res_20[12]; + __be32 tph10clrr0; /* Thread PH10 Clear Control Register */ + u8 res_30[12]; + __be32 tph10psr0; /* Thread PH10 Previous Status Register */ + u8 res_40[12]; + __be32 twaitsr0; /* Thread Wait Status Register */ + u8 res_50[96]; + __be32 pcph15sr; /* Physical Core PH15 Status Register */ + __be32 pcph15setr; /* Physical Core PH15 Set Control Register */ + __be32 pcph15clrr; /* Physical Core PH15 Clear Control Register */ + __be32 pcph15psr; /* Physical Core PH15 Prev Status Register */ + u8 res_c0[16]; + __be32 pcph20sr; /* Physical Core PH20 Status Register */ + __be32 pcph20setr; /* Physical Core PH20 Set Control Register */ + __be32 pcph20clrr; /* Physical Core PH20 Clear Control Register */ + __be32 pcph20psr; /* Physical Core PH20 Prev Status Register */ + __be32 pcpw20sr; /* Physical Core PW20 Status Register */ + u8 res_e0[12]; + __be32 pcph30sr; /* Physical Core PH30 Status Register */ + __be32 pcph30setr; /* Physical Core PH30 Set Control Register */ + __be32 pcph30clrr; /* Physical Core PH30 Clear Control Register */ + __be32 pcph30psr; /* Physical Core PH30 Prev Status Register */ + u8 res_100[32]; + __be32 ippwrgatecr; /* IP Power Gating Control Register */ + u8 res_124[12]; + __be32 powmgtcsr; /* Power Management Control & Status Reg */ +#define RCPM_POWMGTCSR_LPM20_RQ 0x00100000 +#define RCPM_POWMGTCSR_LPM20_ST 0x00000200 +#define RCPM_POWMGTCSR_P_LPM20_ST 0x00000100 + u8 res_134[12]; + __be32 ippdexpcr[4]; /* IP Powerdown Exception Control Reg */ + u8 res_150[12]; + __be32 tpmimr0; /* Thread PM Interrupt Mask Reg */ + u8 res_160[12]; + __be32 tpmcimr0; /* Thread PM Crit Interrupt Mask Reg */ + u8 res_170[12]; + __be32 tpmmcmr0; /* Thread PM Machine Check Interrupt Mask Reg */ + u8 res_180[12]; + __be32 tpmnmimr0; /* Thread PM NMI Mask Reg */ + u8 res_190[12]; + __be32 tmcpmaskcr0; /* Thread Machine Check Mask Control Reg */ + __be32 pctbenr; /* Physical Core Time Base Enable Reg */ + __be32 pctbclkselr; /* Physical Core Time Base Clock Select */ + __be32 tbclkdivr; /* Time Base Clock Divider Register */ + u8 res_1ac[4]; + __be32 ttbhltcr[4]; /* Thread Time Base Halt Control Register */ + __be32 clpcl10sr; /* Cluster PCL10 Status Register */ + __be32 clpcl10setr; /* Cluster PCL30 Set Control Register */ + __be32 clpcl10clrr; /* Cluster PCL30 Clear Control Register */ + __be32 clpcl10psr; /* Cluster PCL30 Prev Status Register */ + __be32 cddslpsetr; /* Core Domain Deep Sleep Set Register */ + __be32 cddslpclrr; /* Core Domain Deep Sleep Clear Register */ + __be32 cdpwroksetr; /* Core Domain Power OK Set Register */ + __be32 cdpwrokclrr; /* Core Domain Power OK Clear Register */ + __be32 cdpwrensr; /* Core Domain Power Enable Status Register */ + __be32 cddslsr; /* Core Domain Deep Sleep Status Register */ + u8 res_1e8[8]; + __be32 dslpcntcr[8]; /* Deep Sleep Counter Cfg Register */ + u8 res_300[3568]; +}; + #endif -- cgit v1.2.3 From 54ce3a0d801142c96935122736a46c08d15d83b5 Mon Sep 17 00:00:00 2001 From: Joseph McNally Date: Sun, 28 Feb 2016 22:31:23 +0000 Subject: hwmon: (ntc_thermistor) Add support for ncpXXxh103 This patch adds support for the Murata NCP15XH103 thermistor series. Signed-off-by: Joseph McNally Signed-off-by: Guenter Roeck --- include/linux/platform_data/ntc_thermistor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h index aed170588b74..698d0d59db76 100644 --- a/include/linux/platform_data/ntc_thermistor.h +++ b/include/linux/platform_data/ntc_thermistor.h @@ -28,6 +28,7 @@ enum ntc_thermistor_type { TYPE_NCPXXWL333, TYPE_B57330V2103, TYPE_NCPXXWF104, + TYPE_NCPXXXH103, }; struct ntc_thermistor_platform_data { -- cgit v1.2.3 From 69bec725985324e79b1c47ea287815ac4ddb0521 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Fri, 19 Feb 2016 17:26:15 +0800 Subject: USB: core: let USB device know device node Although most of USB devices are hot-plug's, there are still some devices are hard wired on the board, eg, for HSIC and SSIC interface USB devices. If these kinds of USB devices are multiple functions, and they can supply other interfaces like i2c, gpios for other devices, we may need to describe these at device tree. In this commit, it uses "reg" in dts as physical port number to match the phyiscal port number decided by USB core, if they are the same, then the device node is for the device we are creating for USB core. Signed-off-by: Peter Chen Acked-by: Philipp Zabel Acked-by: Alan Stern Acked-by: Rob Herring Acked-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/of.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 974bce93aa28..de3237fce6b2 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -16,6 +16,8 @@ enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np); bool of_usb_host_tpl_support(struct device_node *np); int of_usb_update_otg_caps(struct device_node *np, struct usb_otg_caps *otg_caps); +struct device_node *usb_of_get_child_node(struct device_node *parent, + int portnum); #else static inline enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np) @@ -31,6 +33,11 @@ static inline int of_usb_update_otg_caps(struct device_node *np, { return 0; } +static inline struct device_node *usb_of_get_child_node + (struct device_node *parent, int portnum) +{ + return NULL; +} #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT) -- cgit v1.2.3 From aef25338226660cdd4df908c2eff1abdcfca65e5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 12 Feb 2016 17:01:11 -0800 Subject: libnvdimm, nfit: centralize command status translation The return value from an 'ndctl_fn' reports the command execution status, i.e. was the command properly formatted and was it successfully submitted to the bus provider. The new 'cmd_rc' parameter allows the bus provider to communicate command specific results, translated into common error codes. Convert the ARS commands to this scheme to: 1/ Consolidate status reporting 2/ Prepare for for expanding ars unit test cases 3/ Make the implementation more generic Cc: Vishal Verma Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 141ffdd59960..f398953270d1 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -48,7 +48,7 @@ struct nvdimm; struct nvdimm_bus_descriptor; typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, - unsigned int buf_len); + unsigned int buf_len, int *cmd_rc); struct nd_namespace_label; struct nvdimm_drvdata; -- cgit v1.2.3 From 719994660c249a086a7493205c7f1562e30c38cb Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Feb 2016 10:29:49 -0800 Subject: libnvdimm: async notification support In preparation for asynchronous address range scrub support add an ability for the pmem driver to dynamically consume address range scrub results. Signed-off-by: Dan Williams --- include/linux/nd.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nd.h b/include/linux/nd.h index 507e47c86737..5489ab756d1a 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -16,11 +16,16 @@ #include #include +enum nvdimm_event { + NVDIMM_REVALIDATE_POISON, +}; + struct nd_device_driver { struct device_driver drv; unsigned long type; int (*probe)(struct device *dev); int (*remove)(struct device *dev); + void (*notify)(struct device *dev, enum nvdimm_event event); }; static inline struct nd_device_driver *to_nd_device_driver( @@ -144,6 +149,8 @@ static inline int nvdimm_write_bytes(struct nd_namespace_common *ndns, MODULE_ALIAS("nd:t" __stringify(type) "*") #define ND_DEVICE_MODALIAS_FMT "nd:t%d" +struct nd_region; +void nvdimm_region_notify(struct nd_region *nd_region, enum nvdimm_event event); int __must_check __nd_driver_register(struct nd_device_driver *nd_drv, struct module *module, const char *mod_name); #define nd_driver_register(driver) \ -- cgit v1.2.3 From 7ae0fa439faff000744b234d04cb470bfd83593b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 19 Feb 2016 12:16:34 -0800 Subject: nfit, libnvdimm: async region scrub workqueue Introduce a workqueue that will be used to run address range scrub asynchronously with the rest of nvdimm device probing. Userspace still wants notification when probing operations complete, so introduce a new callback to flush this workqueue when userspace is awaiting probe completion. Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f398953270d1..2299f8742f7f 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -71,6 +71,7 @@ struct nvdimm_bus_descriptor { unsigned long dsm_mask; char *provider_name; ndctl_fn ndctl; + int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); }; struct nd_cmd_desc { -- cgit v1.2.3 From 87bf572e19a092cc9cc77d5a00d543a2b628c142 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 22 Feb 2016 21:50:31 -0800 Subject: nfit: disable userspace initiated ars during scrub While the nfit driver is issuing address range scrub commands and reaping the results do not permit an ars_start command issued from userspace. The scrub thread assumes that all ars completions are for scrubs initiated by platform firmware at boot, or by the nfit driver. Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 2299f8742f7f..833867b9ddc2 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -72,6 +72,8 @@ struct nvdimm_bus_descriptor { char *provider_name; ndctl_fn ndctl; int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); + int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc, + struct nvdimm *nvdimm, unsigned int cmd); }; struct nd_cmd_desc { -- cgit v1.2.3 From 1ae1602de028acaa42a0f6ff18d19756f8e825c6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Feb 2016 11:02:14 +0100 Subject: configfs: switch ->default groups to a linked list Replace the current NULL-terminated array of default groups with a linked list. This gets rid of lots of nasty code to size and/or dynamically allocate the array. While we're at it also provide a conveniant helper to remove the default groups. Signed-off-by: Christoph Hellwig Acked-by: Felipe Balbi [drivers/usb/gadget] Acked-by: Joel Becker Acked-by: Nicholas Bellinger Reviewed-by: Sagi Grimberg --- include/linux/configfs.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index f8165c129ccb..485fe5519448 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -96,7 +96,8 @@ struct config_group { struct config_item cg_item; struct list_head cg_children; struct configfs_subsystem *cg_subsys; - struct config_group **default_groups; + struct list_head default_groups; + struct list_head group_entry; }; extern void config_group_init(struct config_group *group); @@ -123,6 +124,12 @@ extern struct config_item *config_group_find_item(struct config_group *, const char *); +static inline void configfs_add_default_group(struct config_group *new_group, + struct config_group *group) +{ + list_add_tail(&new_group->group_entry, &group->default_groups); +} + struct configfs_attribute { const char *ca_name; struct module *ca_owner; @@ -251,6 +258,8 @@ int configfs_register_group(struct config_group *parent_group, struct config_group *group); void configfs_unregister_group(struct config_group *group); +void configfs_remove_default_groups(struct config_group *group); + struct config_group * configfs_register_default_group(struct config_group *parent_group, const char *name, -- cgit v1.2.3 From 335e073faacc9d90bee1527fa2550d6df045df63 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Sun, 6 Mar 2016 22:20:25 +0100 Subject: klp: remove CONFIG_LIVEPATCH dependency from klp headers There is no need for livepatch.h (generic and arch-specific) to depend on CONFIG_LIVEPATCH. Remove that superfluous dependency. Reported-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index a8828652f794..c05679701e10 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -24,8 +24,6 @@ #include #include -#if IS_ENABLED(CONFIG_LIVEPATCH) - #include enum klp_state { @@ -134,6 +132,4 @@ int klp_unregister_patch(struct klp_patch *); int klp_enable_patch(struct klp_patch *); int klp_disable_patch(struct klp_patch *); -#endif /* CONFIG_LIVEPATCH */ - #endif /* _LINUX_LIVEPATCH_H_ */ -- cgit v1.2.3 From 4d7928959832ea41f7f91456b76da19cad01bd09 Mon Sep 17 00:00:00 2001 From: Hante Meuleman Date: Wed, 17 Feb 2016 11:27:07 +0100 Subject: brcmfmac: switch to new platform data Platform data is only available for sdio. With this patch a new platform data structure is being used which allows for platform data for any device and configurable per device. This patch only switches to the new structure and adds support for SDIO devices. Reviewed-by: Arend Van Spriel Reviewed-by: Franky (Zhenhui) Lin Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/platform_data/brcmfmac-sdio.h | 135 -------------------- include/linux/platform_data/brcmfmac.h | 185 ++++++++++++++++++++++++++++ 2 files changed, 185 insertions(+), 135 deletions(-) delete mode 100644 include/linux/platform_data/brcmfmac-sdio.h create mode 100644 include/linux/platform_data/brcmfmac.h (limited to 'include/linux') diff --git a/include/linux/platform_data/brcmfmac-sdio.h b/include/linux/platform_data/brcmfmac-sdio.h deleted file mode 100644 index e75dcbf2b230..000000000000 --- a/include/linux/platform_data/brcmfmac-sdio.h +++ /dev/null @@ -1,135 +0,0 @@ -/* - * Copyright (c) 2013 Broadcom Corporation - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY - * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION - * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN - * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -#ifndef _LINUX_BRCMFMAC_PLATFORM_H -#define _LINUX_BRCMFMAC_PLATFORM_H - -/* - * Platform specific driver functions and data. Through the platform specific - * device data functions can be provided to help the brcmfmac driver to - * operate with the device in combination with the used platform. - * - * Use the platform data in the following (similar) way: - * - * -#include - - -static void brcmfmac_power_on(void) -{ -} - -static void brcmfmac_power_off(void) -{ -} - -static void brcmfmac_reset(void) -{ -} - -static struct brcmfmac_sdio_platform_data brcmfmac_sdio_pdata = { - .power_on = brcmfmac_power_on, - .power_off = brcmfmac_power_off, - .reset = brcmfmac_reset -}; - -static struct platform_device brcmfmac_device = { - .name = BRCMFMAC_SDIO_PDATA_NAME, - .id = PLATFORM_DEVID_NONE, - .dev.platform_data = &brcmfmac_sdio_pdata -}; - -void __init brcmfmac_init_pdata(void) -{ - brcmfmac_sdio_pdata.oob_irq_supported = true; - brcmfmac_sdio_pdata.oob_irq_nr = gpio_to_irq(GPIO_BRCMF_SDIO_OOB); - brcmfmac_sdio_pdata.oob_irq_flags = IORESOURCE_IRQ | - IORESOURCE_IRQ_HIGHLEVEL; - platform_device_register(&brcmfmac_device); -} - * - * - * Note: the brcmfmac can be loaded as module or be statically built-in into - * the kernel. If built-in then do note that it uses module_init (and - * module_exit) routines which equal device_initcall. So if you intend to - * create a module with the platform specific data for the brcmfmac and have - * it built-in to the kernel then use a higher initcall then device_initcall - * (see init.h). If this is not done then brcmfmac will load without problems - * but will not pickup the platform data. - * - * When the driver does not "detect" platform driver data then it will continue - * without reporting anything and just assume there is no data needed. Which is - * probably true for most platforms. - * - * Explanation of the platform_data fields: - * - * drive_strength: is the preferred drive_strength to be used for the SDIO - * pins. If 0 then a default value will be used. This is the target drive - * strength, the exact drive strength which will be used depends on the - * capabilities of the device. - * - * oob_irq_supported: does the board have support for OOB interrupts. SDIO - * in-band interrupts are relatively slow and for having less overhead on - * interrupt processing an out of band interrupt can be used. If the HW - * supports this then enable this by setting this field to true and configure - * the oob related fields. - * - * oob_irq_nr, oob_irq_flags: the OOB interrupt information. The values are - * used for registering the irq using request_irq function. - * - * broken_sg_support: flag for broken sg list support of SDIO host controller. - * Set this to true if the SDIO host controller has higher align requirement - * than 32 bytes for each scatterlist item. - * - * sd_head_align: alignment requirement for start of data buffer - * - * sd_sgentry_align: length alignment requirement for each sg entry - * - * power_on: This function is called by the brcmfmac when the module gets - * loaded. This can be particularly useful for low power devices. The platform - * spcific routine may for example decide to power up the complete device. - * If there is no use-case for this function then provide NULL. - * - * power_off: This function is called by the brcmfmac when the module gets - * unloaded. At this point the device can be powered down or otherwise be reset. - * So if an actual power_off is not supported but reset is then reset the device - * when this function gets called. This can be particularly useful for low power - * devices. If there is no use-case for this function (either power-down or - * reset) then provide NULL. - * - * reset: This function can get called if the device communication broke down. - * This functionality is particularly useful in case of SDIO type devices. It is - * possible to reset a dongle via sdio data interface, but it requires that - * this is fully functional. This function is chip/module specific and this - * function should return only after the complete reset has completed. - */ - -#define BRCMFMAC_SDIO_PDATA_NAME "brcmfmac_sdio" - -struct brcmfmac_sdio_platform_data { - unsigned int drive_strength; - bool oob_irq_supported; - unsigned int oob_irq_nr; - unsigned long oob_irq_flags; - bool broken_sg_support; - unsigned short sd_head_align; - unsigned short sd_sgentry_align; - void (*power_on)(void); - void (*power_off)(void); - void (*reset)(void); -}; - -#endif /* _LINUX_BRCMFMAC_PLATFORM_H */ diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h new file mode 100644 index 000000000000..1d30bf278231 --- /dev/null +++ b/include/linux/platform_data/brcmfmac.h @@ -0,0 +1,185 @@ +/* + * Copyright (c) 201 Broadcom Corporation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef _LINUX_BRCMFMAC_PLATFORM_H +#define _LINUX_BRCMFMAC_PLATFORM_H + + +#define BRCMFMAC_PDATA_NAME "brcmfmac" + +#define BRCMFMAC_COUNTRY_BUF_SZ 4 + + +/* + * Platform specific driver functions and data. Through the platform specific + * device data functions and data can be provided to help the brcmfmac driver to + * operate with the device in combination with the used platform. + */ + + +/** + * Note: the brcmfmac can be loaded as module or be statically built-in into + * the kernel. If built-in then do note that it uses module_init (and + * module_exit) routines which equal device_initcall. So if you intend to + * create a module with the platform specific data for the brcmfmac and have + * it built-in to the kernel then use a higher initcall then device_initcall + * (see init.h). If this is not done then brcmfmac will load without problems + * but will not pickup the platform data. + * + * When the driver does not "detect" platform driver data then it will continue + * without reporting anything and just assume there is no data needed. Which is + * probably true for most platforms. + */ + +/** + * enum brcmf_bus_type - Bus type identifier. Currently SDIO, USB and PCIE are + * supported. + */ +enum brcmf_bus_type { + BRCMF_BUSTYPE_SDIO, + BRCMF_BUSTYPE_USB, + BRCMF_BUSTYPE_PCIE +}; + + +/** + * struct brcmfmac_sdio_pd - SDIO Device specific platform data. + * + * @txglomsz: SDIO txglom size. Use 0 if default of driver is to be + * used. + * @drive_strength: is the preferred drive_strength to be used for the SDIO + * pins. If 0 then a default value will be used. This is + * the target drive strength, the exact drive strength + * which will be used depends on the capabilities of the + * device. + * @oob_irq_supported: does the board have support for OOB interrupts. SDIO + * in-band interrupts are relatively slow and for having + * less overhead on interrupt processing an out of band + * interrupt can be used. If the HW supports this then + * enable this by setting this field to true and configure + * the oob related fields. + * @oob_irq_nr, + * @oob_irq_flags: the OOB interrupt information. The values are used for + * registering the irq using request_irq function. + * @broken_sg_support: flag for broken sg list support of SDIO host controller. + * Set this to true if the SDIO host controller has higher + * align requirement than 32 bytes for each scatterlist + * item. + * @sd_head_align: alignment requirement for start of data buffer. + * @sd_sgentry_align: length alignment requirement for each sg entry. + * @reset: This function can get called if the device communication + * broke down. This functionality is particularly useful in + * case of SDIO type devices. It is possible to reset a + * dongle via sdio data interface, but it requires that + * this is fully functional. This function is chip/module + * specific and this function should return only after the + * complete reset has completed. + */ +struct brcmfmac_sdio_pd { + int txglomsz; + unsigned int drive_strength; + bool oob_irq_supported; + unsigned int oob_irq_nr; + unsigned long oob_irq_flags; + bool broken_sg_support; + unsigned short sd_head_align; + unsigned short sd_sgentry_align; + void (*reset)(void); +}; + +/** + * struct brcmfmac_pd_cc_entry - Struct for translating user space country code + * (iso3166) to firmware country code and + * revision. + * + * @iso3166: iso3166 alpha 2 country code string. + * @cc: firmware country code string. + * @rev: firmware country code revision. + */ +struct brcmfmac_pd_cc_entry { + char iso3166[BRCMFMAC_COUNTRY_BUF_SZ]; + char cc[BRCMFMAC_COUNTRY_BUF_SZ]; + s32 rev; +}; + +/** + * struct brcmfmac_pd_cc - Struct for translating country codes as set by user + * space to a country code and rev which can be used by + * firmware. + * + * @table_size: number of entries in table (> 0) + * @table: array of 1 or more elements with translation information. + */ +struct brcmfmac_pd_cc { + int table_size; + struct brcmfmac_pd_cc_entry table[0]; +}; + +/** + * struct brcmfmac_pd_device - Device specific platform data. (id/rev/bus_type) + * is the unique identifier of the device. + * + * @id: ID of the device for which this data is. In case of SDIO + * or PCIE this is the chipid as identified by chip.c In + * case of USB this is the chipid as identified by the + * device query. + * @rev: chip revision, see id. + * @bus_type: The type of bus. Some chipid/rev exist for different bus + * types. Each bus type has its own set of settings. + * @feature_disable: Bitmask of features to disable (override), See feature.c + * in brcmfmac for details. + * @country_codes: If available, pointer to struct for translating country + * codes. + * @bus: Bus specific (union) device settings. Currently only + * SDIO. + */ +struct brcmfmac_pd_device { + unsigned int id; + unsigned int rev; + enum brcmf_bus_type bus_type; + unsigned int feature_disable; + struct brcmfmac_pd_cc *country_codes; + union { + struct brcmfmac_sdio_pd sdio; + } bus; +}; + +/** + * struct brcmfmac_platform_data - BRCMFMAC specific platform data. + * + * @power_on: This function is called by the brcmfmac driver when the module + * gets loaded. This can be particularly useful for low power + * devices. The platform spcific routine may for example decide to + * power up the complete device. If there is no use-case for this + * function then provide NULL. + * @power_off: This function is called by the brcmfmac when the module gets + * unloaded. At this point the devices can be powered down or + * otherwise be reset. So if an actual power_off is not supported + * but reset is supported by the devices then reset the devices + * when this function gets called. This can be particularly useful + * for low power devices. If there is no use-case for this + * function then provide NULL. + */ +struct brcmfmac_platform_data { + void (*power_on)(void); + void (*power_off)(void); + char *fw_alternative_path; + int device_count; + struct brcmfmac_pd_device devices[0]; +}; + + +#endif /* _LINUX_BRCMFMAC_PLATFORM_H */ -- cgit v1.2.3 From 2e62f9b2a41e4ade1a0bb3c1bbda4defe4c67243 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 12 Feb 2016 10:15:43 +0100 Subject: bcma: drop unneeded fields from bcma_pflash struct MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most of info stored in this struct wasn't really used anywhere as we put all that data in platform data & resource as well. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 700d0c6f7480..16eaaad9dda5 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -579,9 +579,6 @@ struct bcma_chipcommon_pmu { #ifdef CONFIG_BCMA_DRIVER_MIPS struct bcma_pflash { bool present; - u8 buswidth; - u32 window; - u32 window_size; }; #ifdef CONFIG_BCMA_SFLASH -- cgit v1.2.3 From d6a3b51ada68c2bd3e184f4729ce626a1721cf74 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 12 Feb 2016 10:15:44 +0100 Subject: bcma: move parallel flash support to separated file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This follows the way of handling other flashes and cleans code a bit. As next task we will want to move flash code to ChipCommon driver as: 1) Flash controllers are accesible using ChipCommon registers 2) This code isn't MIPS specific This change prepares bcma for that. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 16eaaad9dda5..846513c73606 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -576,10 +576,11 @@ struct bcma_chipcommon_pmu { u32 crystalfreq; /* The active crystal frequency (in kHz) */ }; -#ifdef CONFIG_BCMA_DRIVER_MIPS +#ifdef CONFIG_BCMA_PFLASH struct bcma_pflash { bool present; }; +#endif #ifdef CONFIG_BCMA_SFLASH struct mtd_info; @@ -603,6 +604,7 @@ struct bcma_nflash { }; #endif +#ifdef CONFIG_BCMA_DRIVER_MIPS struct bcma_serial_port { void *regs; unsigned long clockspeed; @@ -622,8 +624,9 @@ struct bcma_drv_cc { /* Fast Powerup Delay constant */ u16 fast_pwrup_delay; struct bcma_chipcommon_pmu pmu; -#ifdef CONFIG_BCMA_DRIVER_MIPS +#ifdef CONFIG_BCMA_PFLASH struct bcma_pflash pflash; +#endif #ifdef CONFIG_BCMA_SFLASH struct bcma_sflash sflash; #endif @@ -631,6 +634,7 @@ struct bcma_drv_cc { struct bcma_nflash nflash; #endif +#ifdef CONFIG_BCMA_DRIVER_MIPS int nr_serial_ports; struct bcma_serial_port serial_ports[4]; #endif /* CONFIG_BCMA_DRIVER_MIPS */ -- cgit v1.2.3 From bc4b024a8b8bd7dceb2697299aad2bda57d065e0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Mar 2016 10:40:02 -0600 Subject: PCI: Move pci_dma_* helpers to common code For a long time all architectures implement the pci_dma_* functions using the generic DMA API, and they all use the same header to do so. Move this header, pci-dma-compat.h, to include/linux and include it from the generic pci.h instead of having each arch duplicate this include. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma-compat.h | 118 +++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 4 ++ 2 files changed, 122 insertions(+) create mode 100644 include/linux/pci-dma-compat.h (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h new file mode 100644 index 000000000000..eafce7b6f052 --- /dev/null +++ b/include/linux/pci-dma-compat.h @@ -0,0 +1,118 @@ +/* include this file if the platform implements the dma_ DMA Mapping API + * and wants to provide the pci_ DMA Mapping API in terms of it */ + +#ifndef _ASM_GENERIC_PCI_DMA_COMPAT_H +#define _ASM_GENERIC_PCI_DMA_COMPAT_H + +#include + +static inline void * +pci_alloc_consistent(struct pci_dev *hwdev, size_t size, + dma_addr_t *dma_handle) +{ + return dma_alloc_coherent(hwdev == NULL ? NULL : &hwdev->dev, size, dma_handle, GFP_ATOMIC); +} + +static inline void * +pci_zalloc_consistent(struct pci_dev *hwdev, size_t size, + dma_addr_t *dma_handle) +{ + return dma_zalloc_coherent(hwdev == NULL ? NULL : &hwdev->dev, + size, dma_handle, GFP_ATOMIC); +} + +static inline void +pci_free_consistent(struct pci_dev *hwdev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + dma_free_coherent(hwdev == NULL ? NULL : &hwdev->dev, size, vaddr, dma_handle); +} + +static inline dma_addr_t +pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction) +{ + return dma_map_single(hwdev == NULL ? NULL : &hwdev->dev, ptr, size, (enum dma_data_direction)direction); +} + +static inline void +pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, + size_t size, int direction) +{ + dma_unmap_single(hwdev == NULL ? NULL : &hwdev->dev, dma_addr, size, (enum dma_data_direction)direction); +} + +static inline dma_addr_t +pci_map_page(struct pci_dev *hwdev, struct page *page, + unsigned long offset, size_t size, int direction) +{ + return dma_map_page(hwdev == NULL ? NULL : &hwdev->dev, page, offset, size, (enum dma_data_direction)direction); +} + +static inline void +pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address, + size_t size, int direction) +{ + dma_unmap_page(hwdev == NULL ? NULL : &hwdev->dev, dma_address, size, (enum dma_data_direction)direction); +} + +static inline int +pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, + int nents, int direction) +{ + return dma_map_sg(hwdev == NULL ? NULL : &hwdev->dev, sg, nents, (enum dma_data_direction)direction); +} + +static inline void +pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, + int nents, int direction) +{ + dma_unmap_sg(hwdev == NULL ? NULL : &hwdev->dev, sg, nents, (enum dma_data_direction)direction); +} + +static inline void +pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, + size_t size, int direction) +{ + dma_sync_single_for_cpu(hwdev == NULL ? NULL : &hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); +} + +static inline void +pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, + size_t size, int direction) +{ + dma_sync_single_for_device(hwdev == NULL ? NULL : &hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); +} + +static inline void +pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, + int nelems, int direction) +{ + dma_sync_sg_for_cpu(hwdev == NULL ? NULL : &hwdev->dev, sg, nelems, (enum dma_data_direction)direction); +} + +static inline void +pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, + int nelems, int direction) +{ + dma_sync_sg_for_device(hwdev == NULL ? NULL : &hwdev->dev, sg, nelems, (enum dma_data_direction)direction); +} + +static inline int +pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr) +{ + return dma_mapping_error(&pdev->dev, dma_addr); +} + +#ifdef CONFIG_PCI +static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) +{ + return dma_set_mask(&dev->dev, mask); +} + +static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) +{ + return dma_set_coherent_mask(&dev->dev, mask); +} +#endif + +#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 3d371c150753..5db6e0ce9504 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2011,4 +2011,8 @@ static inline bool pci_ari_enabled(struct pci_bus *bus) { return bus->self && bus->self->ari_enabled; } + +/* provide the legacy pci_dma_* API */ +#include + #endif /* LINUX_PCI_H */ -- cgit v1.2.3 From fe537670eab767157eecc50538bd28e8d9b0ce9f Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 7 Mar 2016 11:39:16 -0600 Subject: PCI: Consolidate PCI DMA constants and interfaces in linux/pci-dma-compat.h Christoph added a generic include/linux/pci-dma-compat.h, so now there's one place with most of the PCI DMA interfaces. Move more PCI DMA-related things there: - The PCI_DMA_* direction constants from linux/pci.h - The pci_set_dma_max_seg_size() and pci_set_dma_seg_boundary() CONFIG_PCI implementations from drivers/pci/pci.c - The pci_set_dma_max_seg_size() and pci_set_dma_seg_boundary() !CONFIG_PCI stubs from linux/pci.h - The pci_set_dma_mask() and pci_set_consistent_dma_mask() !CONFIG_PCI stubs from linux/pci.h Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma-compat.h | 29 +++++++++++++++++++++++++++++ include/linux/pci.h | 19 +------------------ 2 files changed, 30 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index eafce7b6f052..39726caef5b1 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -6,6 +6,12 @@ #include +/* This defines the direction arg to the DMA mapping routines. */ +#define PCI_DMA_BIDIRECTIONAL 0 +#define PCI_DMA_TODEVICE 1 +#define PCI_DMA_FROMDEVICE 2 +#define PCI_DMA_NONE 3 + static inline void * pci_alloc_consistent(struct pci_dev *hwdev, size_t size, dma_addr_t *dma_handle) @@ -113,6 +119,29 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return dma_set_coherent_mask(&dev->dev, mask); } + +static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, + unsigned int size) +{ + return dma_set_max_seg_size(&dev->dev, size); +} + +static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, + unsigned long mask) +{ + return dma_set_seg_boundary(&dev->dev, mask); +} +#else +static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) +{ return -EIO; } +static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) +{ return -EIO; } +static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, + unsigned int size) +{ return -EIO; } +static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, + unsigned long mask) +{ return -EIO; } #endif #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 5db6e0ce9504..5049bd60ba90 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -70,12 +70,6 @@ enum pci_mmap_state { pci_mmap_mem }; -/* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL 0 -#define PCI_DMA_TODEVICE 1 -#define PCI_DMA_FROMDEVICE 2 -#define PCI_DMA_NONE 3 - /* * For PCI devices, the region numbers are assigned this way: */ @@ -1038,8 +1032,6 @@ void pci_intx(struct pci_dev *dev, int enable); bool pci_intx_mask_supported(struct pci_dev *dev); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); -int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size); -int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask); int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask); int pci_wait_for_pending_transaction(struct pci_dev *dev); int pcix_get_max_mmrbc(struct pci_dev *dev); @@ -1255,6 +1247,7 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); + /* kmem_cache style wrapper around pci_alloc_consistent() */ #include @@ -1466,16 +1459,6 @@ static inline struct pci_dev *pci_get_class(unsigned int class, static inline void pci_set_master(struct pci_dev *dev) { } static inline int pci_enable_device(struct pci_dev *dev) { return -EIO; } static inline void pci_disable_device(struct pci_dev *dev) { } -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ return -EIO; } -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ return -EIO; } static inline int pci_assign_resource(struct pci_dev *dev, int i) { return -EBUSY; } static inline int __pci_register_driver(struct pci_driver *drv, -- cgit v1.2.3 From 088c86183012495b53ecc1c734909e5712a40b66 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Fri, 4 Mar 2016 12:35:05 -0500 Subject: qed/qede: Add infrastructure support for hardware GRO This patch adds mainly structures and APIs prototype changes in order to give support for qede slowpath/fastpath support for the same. Signed-off-by: Yuval Mintz Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index e53b0ca49e41..e1d69834a11f 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -39,6 +39,14 @@ struct qed_update_vport_params { struct qed_update_vport_rss_params rss_params; }; +struct qed_start_vport_params { + bool remove_inner_vlan; + bool gro_enable; + bool drop_ttl0; + u8 vport_id; + u16 mtu; +}; + struct qed_stop_rxq_params { u8 rss_id; u8 rx_queue_id; @@ -118,9 +126,7 @@ struct qed_eth_ops { void *cookie); int (*vport_start)(struct qed_dev *cdev, - u8 vport_id, u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg); + struct qed_start_vport_params *params); int (*vport_stop)(struct qed_dev *cdev, u8 vport_id); -- cgit v1.2.3 From 2958ccee3690717f711431b546d7f194d8fa4f8b Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Mon, 22 Feb 2016 15:18:55 +0100 Subject: tty/serial: at91: fix bad offset for UART timeout register With SAMA5D2, the UART has hw timeout but the offset of the register to define this value is not the same as the one for USART. When using the new UART, the value of this register was 0 so we never get timeout irqs. It involves that when using DMA, we were stuck until the execution of the dma callback which happens when a buffer is full (so after receiving 2048 bytes). Signed-off-by: Ludovic Desroches Acked-by: Nicolas Ferre Signed-off-by: Greg Kroah-Hartman --- include/linux/atmel_serial.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atmel_serial.h b/include/linux/atmel_serial.h index ee696d7e8a43..5a4d664af87a 100644 --- a/include/linux/atmel_serial.h +++ b/include/linux/atmel_serial.h @@ -119,7 +119,8 @@ #define ATMEL_US_BRGR 0x20 /* Baud Rate Generator Register */ #define ATMEL_US_CD GENMASK(15, 0) /* Clock Divider */ -#define ATMEL_US_RTOR 0x24 /* Receiver Time-out Register */ +#define ATMEL_US_RTOR 0x24 /* Receiver Time-out Register for USART */ +#define ATMEL_UA_RTOR 0x28 /* Receiver Time-out Register for UART */ #define ATMEL_US_TO GENMASK(15, 0) /* Time-out Value */ #define ATMEL_US_TTGR 0x28 /* Transmitter Timeguard Register */ -- cgit v1.2.3 From 0607616d9311096bfd1c325c36ffbfa71ccd40ab Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 25 Feb 2016 15:33:46 +0100 Subject: serial: sa1100: make sa1100_register_uart_fns a function Calling sa1100_register_uart_fns() leaves the port structure unused when CONFIG_SERIAL_SA1100 is disabled, and we get a compiler warning about that: arch/arm/mach-sa1100/badge4.c:317:31: warning: 'badge4_port_fns' defined but not used [-Wunused-variable] static struct sa1100_port_fns badge4_port_fns __initdata = { This turns the two empty macros into empty inline functions, which has the same effect, but lets the compiler know that the variables are intentionally unused. Signed-off-by: Arnd Bergmann Acked-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/sa11x0-serial.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/sa11x0-serial.h b/include/linux/platform_data/sa11x0-serial.h index 4504d5d592f0..009e1d83fe39 100644 --- a/include/linux/platform_data/sa11x0-serial.h +++ b/include/linux/platform_data/sa11x0-serial.h @@ -26,8 +26,12 @@ struct sa1100_port_fns { void sa1100_register_uart_fns(struct sa1100_port_fns *fns); void sa1100_register_uart(int idx, int port); #else -#define sa1100_register_uart_fns(fns) do { } while (0) -#define sa1100_register_uart(idx,port) do { } while (0) +static inline void sa1100_register_uart_fns(struct sa1100_port_fns *fns) +{ +} +static inline void sa1100_register_uart(int idx, int port) +{ +} #endif #endif -- cgit v1.2.3 From f5b8aa78ef086248145363bf1ffe5ca4348b6a98 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Mar 2016 10:46:51 +0100 Subject: mtd: kill the ecclayout->oobavail field ecclayout->oobavail is just redundant with the mtd->oobavail field. Moreover, it prevents static const definition of ecc layouts since the NAND framework is calculating this value based on the ecclayout->oobfree field. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/mtd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index cc84923011c0..9cf13c4bccc8 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -105,7 +105,6 @@ struct mtd_oob_ops { struct nand_ecclayout { __u32 eccbytes; __u32 eccpos[MTD_MAX_ECCPOS_ENTRIES_LARGE]; - __u32 oobavail; struct nand_oobfree oobfree[MTD_MAX_OOBFREE_ENTRIES_LARGE]; }; -- cgit v1.2.3 From 29f1058a90b319b01c4cf469720e0350212d5c9c Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Mar 2016 10:46:52 +0100 Subject: mtd: create an mtd_oobavail() helper and make use of it Currently, all MTD drivers/sublayers exposing an OOB area are doing the same kind of test to extract the available OOB size based on the mtd_info and mtd_oob_ops structures. Move this common logic into an inline function and make use of it. Signed-off-by: Boris Brezillon Suggested-by: Priit Laes Signed-off-by: Brian Norris --- include/linux/mtd/mtd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 9cf13c4bccc8..771272187316 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -264,6 +264,11 @@ static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd) return mtd->dev.of_node; } +static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops) +{ + return ops->mode == MTD_OPS_AUTO_OOB ? mtd->oobavail : mtd->oobsize; +} + int mtd_erase(struct mtd_info *mtd, struct erase_info *instr); int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, void **virt, resource_size_t *phys); -- cgit v1.2.3 From a8c65d504e0b2256f7672506ae6ea68d88ef020a Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 7 Mar 2016 10:46:54 +0100 Subject: mtd: nand: simplify nand_bch_init() usage nand_bch_init() requires several arguments which could directly be deduced from the mtd device. Get rid of those useless parameters. nand_bch_init() is also requiring the caller to provide a proper eccbytes value, while this value could be deduced from the ecc.size and ecc.strength value. Fallback to eccbytes calculation when it is set to 0. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand_bch.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h index fb0bc3420a10..98f20ef05d60 100644 --- a/include/linux/mtd/nand_bch.h +++ b/include/linux/mtd/nand_bch.h @@ -32,9 +32,7 @@ int nand_bch_correct_data(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, /* * Initialize BCH encoder/decoder */ -struct nand_bch_control * -nand_bch_init(struct mtd_info *mtd, unsigned int eccsize, - unsigned int eccbytes, struct nand_ecclayout **ecclayout); +struct nand_bch_control *nand_bch_init(struct mtd_info *mtd); /* * Release BCH encoder/decoder resources */ @@ -58,9 +56,7 @@ nand_bch_correct_data(struct mtd_info *mtd, unsigned char *buf, return -ENOTSUPP; } -static inline struct nand_bch_control * -nand_bch_init(struct mtd_info *mtd, unsigned int eccsize, - unsigned int eccbytes, struct nand_ecclayout **ecclayout) +static inline struct nand_bch_control *nand_bch_init(struct mtd_info *mtd) { return NULL; } -- cgit v1.2.3 From 3dd8012a8eeb3702fa17450ec1a16a3f38af138d Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 29 Jan 2016 11:25:36 -0800 Subject: mtd: spi-nor: add TB (Top/Bottom) protect support Some flash support a bit in the status register that inverts protection so that it applies to the bottom of the flash, not the top. This yields additions to the protection range table, as noted in the comments. Because this feature is not universal to all flash that support lock/unlock, control it via a new flag. Signed-off-by: Brian Norris Tested-by: Ezequiel Garcia --- include/linux/mtd/spi-nor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 62356d50815b..3c36113a88e1 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -85,6 +85,7 @@ #define SR_BP0 BIT(2) /* Block protect 0 */ #define SR_BP1 BIT(3) /* Block protect 1 */ #define SR_BP2 BIT(4) /* Block protect 2 */ +#define SR_TB BIT(5) /* Top/Bottom protect */ #define SR_SRWD BIT(7) /* SR write protect */ #define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ @@ -116,6 +117,7 @@ enum spi_nor_ops { enum spi_nor_option_flags { SNOR_F_USE_FSR = BIT(0), + SNOR_F_HAS_SR_TB = BIT(1), }; /** -- cgit v1.2.3 From c4a5923055c9e0c87dfc0387f7cda5ee2bbac3c1 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:45 -0600 Subject: tracing: Add event record param to trigger_ops.func() Some triggers may need access to the trace event, so pass it in. Also fix up the existing trigger funcs and their callers. Link: http://lkml.kernel.org/r/543e31e9fc445ef61077421ab219033401c39846.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/trace_events.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 925730bc9fc1..0d6930e941e8 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -430,7 +430,8 @@ extern int call_filter_check_discard(struct trace_event_call *call, void *rec, extern enum event_trigger_type event_triggers_call(struct trace_event_file *file, void *rec); extern void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt); + enum event_trigger_type tt, + void *rec); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); @@ -517,7 +518,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) - event_triggers_post_call(file, tt); + event_triggers_post_call(file, tt, entry); } /** @@ -550,7 +551,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file, irq_flags, pc, regs); if (tt) - event_triggers_post_call(file, tt); + event_triggers_post_call(file, tt, entry); } #ifdef CONFIG_BPF_EVENTS -- cgit v1.2.3 From e4857982f49d21c05a84351b56724bf353022355 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:26 -0500 Subject: cgroup: use css_set->mg_dst_cgrp for the migration target cgroup Migration can be multi-target on the default hierarchy when a controller is enabled - processes belonging to each child cgroup have to be moved to the child cgroup itself to refresh css association. This isn't a problem for cgroup_migrate_add_src() as each source css_set still maps to single source and target cgroups; however, cgroup_migrate_prepare_dst() is called once after all source css_sets are added and thus might not have a single destination cgroup. This is currently worked around by specifying NULL for @dst_cgrp and using the source's default cgroup as destination as the only multi-target migration in use is self-targetting. While this works, it's subtle and clunky. As all taget cgroups are already specified while preparing the source css_sets, this clunkiness can easily be removed by recording the target cgroup in each source css_set. This patch adds css_set->mg_dst_cgrp which is recorded on cgroup_migrate_src() and used by cgroup_migrate_prepare_dst(). This also makes migration code ready for arbitrary multi-target migration. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index aae8c94de4b3..590291d56049 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -191,12 +191,13 @@ struct css_set { /* * If this cset is acting as the source of migration the following - * two fields are set. mg_src_cgrp is the source cgroup of the - * on-going migration and mg_dst_cset is the destination cset the - * target tasks on this cset should be migrated to. Protected by - * cgroup_mutex. + * two fields are set. mg_src_cgrp and mg_dst_cgrp are + * respectively the source and destination cgroups of the on-going + * migration. mg_dst_cset is the destination cset the target tasks + * on this cset should be migrated to. Protected by cgroup_mutex. */ struct cgroup *mg_src_cgrp; + struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; /* -- cgit v1.2.3 From f6d635ad341d5cc0b9c7ab46adfbf3bf5886cee4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:26 -0500 Subject: cgroup: implement cgroup_subsys->implicit_on_dfl Some controllers, perf_event for now and possibly freezer in the future, don't really make sense to control explicitly through "cgroup.subtree_control". For example, the primary role of perf_event is identifying the cgroups of tasks; however, because the controller also keeps a small amount of state per cgroup, it can't be replaced with simple cgroup membership tests. This patch implements cgroup_subsys->implicit_on_dfl flag. When set, the controller is implicitly enabled on all cgroups on the v2 hierarchy so that utility type controllers such as perf_event can be enabled and function transparently. An implicit controller doesn't show up in "cgroup.controllers" or "cgroup.subtree_control", is exempt from no internal process rule and can be stolen from the default hierarchy even if there are non-root csses. v2: Reimplemented on top of the recent updates to css handling and subsystem rebinding. Rebinding implicit subsystems is now a simple matter of exempting it from the busy subsystem check. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 590291d56049..34b42f03fcd8 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -450,6 +450,19 @@ struct cgroup_subsys { bool early_init:1; + /* + * If %true, the controller, on the default hierarchy, doesn't show + * up in "cgroup.controllers" or "cgroup.subtree_control", is + * implicitly enabled on all cgroups on the default hierarchy, and + * bypasses the "no internal process" constraint. This is for + * utility type controllers which is transparent to userland. + * + * An implicit controller can be stolen from the default hierarchy + * anytime and thus must be okay with offline csses from previous + * hierarchies coexisting with csses for the current one. + */ + bool implicit_on_dfl:1; + /* * If %false, this subsystem is properly hierarchical - * configuration, resource accounting and restriction on a parent -- cgit v1.2.3 From 0c0e0736acad4e76e718456c75d78ad95eea0011 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 1 Mar 2016 11:38:46 -0600 Subject: PCI: Set ROM shadow location in arch code, not in PCI core IORESOURCE_ROM_SHADOW means there is a copy of a device's option ROM in RAM. The existence of such a copy and its location are arch-specific. Previously the IORESOURCE_ROM_SHADOW flag was set in arch code, but the 0xC0000-0xDFFFF location was hard-coded into the PCI core. If we're using a shadow copy in RAM, disable the ROM BAR and release the address space it was consuming. Move the location information from the PCI core to the arch code that sets IORESOURCE_ROM_SHADOW. Save the location of the RAM copy in the struct resource for PCI_ROM_RESOURCE. After this change, pci_map_rom() will call pci_assign_resource() and pci_enable_rom() for these IORESOURCE_ROM_SHADOW resources, which we did not do before. This is safe because: - pci_assign_resource() will do nothing because the resource is marked IORESOURCE_PCI_FIXED, which means we can't move it, and - pci_enable_rom() will not turn on the ROM BAR's enable bit because the resource is marked IORESOURCE_ROM_SHADOW, which means it is in RAM rather than in PCI memory space. Storing the location in the struct resource means "lspci" will show the shadow location, not the value from the ROM BAR. Signed-off-by: Bjorn Helgaas --- include/linux/ioport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 24bea087e7af..2cf16673f17a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -98,7 +98,7 @@ struct resource { /* PCI ROM control bits (IORESOURCE_BITS) */ #define IORESOURCE_ROM_ENABLE (1<<0) /* ROM is enabled, same as PCI_ROM_ADDRESS_ENABLE */ -#define IORESOURCE_ROM_SHADOW (1<<1) /* ROM is copy at C000:0 */ +#define IORESOURCE_ROM_SHADOW (1<<1) /* Use RAM image, not ROM BAR */ #define IORESOURCE_ROM_COPY (1<<2) /* ROM is alloc'd copy, resource field overlaid */ #define IORESOURCE_ROM_BIOS_COPY (1<<3) /* ROM is BIOS copy, resource field overlaid */ -- cgit v1.2.3 From 4774f400935fbb44a25f5e8fd5c5583431e28ac1 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Tue, 8 Mar 2016 10:34:04 -0800 Subject: Input: ad7879 - move header to platform_data directory The header file is used by the SPI and I2C variant of the driver. Therefore, move it to a more generic place under platform_data. Signed-off-by: Stefan Agner Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/ad7879.h | 41 ++++++++++++++++++++++++++++++++++++ include/linux/spi/ad7879.h | 41 ------------------------------------ 2 files changed, 41 insertions(+), 41 deletions(-) create mode 100644 include/linux/platform_data/ad7879.h delete mode 100644 include/linux/spi/ad7879.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ad7879.h b/include/linux/platform_data/ad7879.h new file mode 100644 index 000000000000..69e2e1fd2bc8 --- /dev/null +++ b/include/linux/platform_data/ad7879.h @@ -0,0 +1,41 @@ +/* linux/platform_data/ad7879.h */ + +/* Touchscreen characteristics vary between boards and models. The + * platform_data for the device's "struct device" holds this information. + * + * It's OK if the min/max values are zero. + */ +struct ad7879_platform_data { + u16 model; /* 7879 */ + u16 x_plate_ohms; + u16 x_min, x_max; + u16 y_min, y_max; + u16 pressure_min, pressure_max; + + bool swap_xy; /* swap x and y axes */ + + /* [0..255] 0=OFF Starts at 1=550us and goes + * all the way to 9.440ms in steps of 35us. + */ + u8 pen_down_acc_interval; + /* [0..15] Starts at 0=128us and goes all the + * way to 4.096ms in steps of 128us. + */ + u8 first_conversion_delay; + /* [0..3] 0 = 2us, 1 = 4us, 2 = 8us, 3 = 16us */ + u8 acquisition_time; + /* [0..3] Average X middle samples 0 = 2, 1 = 4, 2 = 8, 3 = 16 */ + u8 averaging; + /* [0..3] Perform X measurements 0 = OFF, + * 1 = 4, 2 = 8, 3 = 16 (median > averaging) + */ + u8 median; + /* 1 = AUX/VBAT/GPIO export GPIO to gpiolib + * requires CONFIG_GPIOLIB + */ + bool gpio_export; + /* identifies the first GPIO number handled by this chip; + * or, if negative, requests dynamic ID allocation. + */ + s32 gpio_base; +}; diff --git a/include/linux/spi/ad7879.h b/include/linux/spi/ad7879.h deleted file mode 100644 index 58368be0b4c0..000000000000 --- a/include/linux/spi/ad7879.h +++ /dev/null @@ -1,41 +0,0 @@ -/* linux/spi/ad7879.h */ - -/* Touchscreen characteristics vary between boards and models. The - * platform_data for the device's "struct device" holds this information. - * - * It's OK if the min/max values are zero. - */ -struct ad7879_platform_data { - u16 model; /* 7879 */ - u16 x_plate_ohms; - u16 x_min, x_max; - u16 y_min, y_max; - u16 pressure_min, pressure_max; - - bool swap_xy; /* swap x and y axes */ - - /* [0..255] 0=OFF Starts at 1=550us and goes - * all the way to 9.440ms in steps of 35us. - */ - u8 pen_down_acc_interval; - /* [0..15] Starts at 0=128us and goes all the - * way to 4.096ms in steps of 128us. - */ - u8 first_conversion_delay; - /* [0..3] 0 = 2us, 1 = 4us, 2 = 8us, 3 = 16us */ - u8 acquisition_time; - /* [0..3] Average X middle samples 0 = 2, 1 = 4, 2 = 8, 3 = 16 */ - u8 averaging; - /* [0..3] Perform X measurements 0 = OFF, - * 1 = 4, 2 = 8, 3 = 16 (median > averaging) - */ - u8 median; - /* 1 = AUX/VBAT/GPIO export GPIO to gpiolib - * requires CONFIG_GPIOLIB - */ - bool gpio_export; - /* identifies the first GPIO number handled by this chip; - * or, if negative, requests dynamic ID allocation. - */ - s32 gpio_base; -}; -- cgit v1.2.3 From b121d1e74d1f24654bdc3165d3db1ca149501356 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:13 -0800 Subject: bpf: prevent kprobe+bpf deadlocks if kprobe is placed within update or delete hash map helpers that hold bucket spin lock and triggered bpf program is trying to grab the spinlock for the same bucket on the same cpu, it will deadlock. Fix it by extending existing recursion prevention mechanism. Note, map_lookup and other tracing helpers don't have this problem, since they don't hold any locks and don't modify global data. bpf_trace_printk has its own recursive check and ok as well. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 51e498e5470e..4b070827200d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,6 +10,7 @@ #include #include #include +#include struct bpf_map; @@ -163,6 +164,8 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f const struct bpf_func_proto *bpf_get_trace_printk_proto(void); #ifdef CONFIG_BPF_SYSCALL +DECLARE_PER_CPU(int, bpf_prog_active); + void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); -- cgit v1.2.3 From 6c90598174322b8888029e40dd84a4eb01f56afe Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:15 -0800 Subject: bpf: pre-allocate hash map elements If kprobe is placed on spin_unlock then calling kmalloc/kfree from bpf programs is not safe, since the following dead lock is possible: kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe-> bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock) and deadlocks. The following solutions were considered and some implemented, but eventually discarded - kmem_cache_create for every map - add recursion check to slow-path of slub - use reserved memory in bpf_map_update for in_irq or in preempt_disabled - kmalloc via irq_work At the end pre-allocation of all map elements turned out to be the simplest solution and since the user is charged upfront for all the memory, such pre-allocation doesn't affect the user space visible behavior. Since it's impossible to tell whether kprobe is triggered in a safe location from kmalloc point of view, use pre-allocation by default and introduce new BPF_F_NO_PREALLOC flag. While testing of per-cpu hash maps it was discovered that alloc_percpu(GFP_ATOMIC) has odd corner cases and often fails to allocate memory even when 90% of it is free. The pre-allocation of per-cpu hash elements solves this problem as well. Turned out that bpf_map_update() quickly followed by bpf_map_lookup()+bpf_map_delete() is very common pattern used in many of iovisor/bcc/tools, so there is additional benefit of pre-allocation, since such use cases are must faster. Since all hash map elements are now pre-allocated we can remove atomic increment of htab->count and save few more cycles. Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid large malloc/free done by users who don't have sufficient limits. Pre-allocation is done with vmalloc and alloc/free is done via percpu_freelist. Here are performance numbers for different pre-allocation algorithms that were implemented, but discarded in favor of percpu_freelist: 1 cpu: pcpu_ida 2.1M pcpu_ida nolock 2.3M bt 2.4M kmalloc 1.8M hlist+spinlock 2.3M pcpu_freelist 2.6M 4 cpu: pcpu_ida 1.5M pcpu_ida nolock 1.8M bt w/smp_align 1.7M bt no/smp_align 1.1M kmalloc 0.7M hlist+spinlock 0.2M pcpu_freelist 2.0M 8 cpu: pcpu_ida 0.7M bt w/smp_align 0.8M kmalloc 0.4M pcpu_freelist 1.5M 32 cpu: kmalloc 0.13M pcpu_freelist 0.49M pcpu_ida nolock is a modified percpu_ida algorithm without percpu_ida_cpu locks and without cross-cpu tag stealing. It's faster than existing percpu_ida, but not as fast as pcpu_freelist. bt is a variant of block/blk-mq-tag.c simlified and customized for bpf use case. bt w/smp_align is using cache line for every 'long' (similar to blk-mq-tag). bt no/smp_align allocates 'long' bitmasks continuously to save memory. It's comparable to percpu_ida and in some cases faster, but slower than percpu_freelist hlist+spinlock is the simplest free list with single spinlock. As expeceted it has very bad scaling in SMP. kmalloc is existing implementation which is still available via BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist, but saves memory, so in cases where map->max_entries can be large and number of map update/delete per second is low, it may make sense to use it. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4b070827200d..efd1d4ca95c6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,7 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 map_flags; u32 pages; struct user_struct *user; const struct bpf_map_ops *ops; @@ -178,6 +179,7 @@ struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); +int bpf_map_precharge_memlock(u32 pages); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 557c0c6e7df8e14a46bd7560d193fa5bbc00a858 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:17 -0800 Subject: bpf: convert stackmap to pre-allocation It was observed that calling bpf_get_stackid() from a kprobe inside slub or from spin_unlock causes similar deadlock as with hashmap, therefore convert stackmap to use pre-allocated memory. The call_rcu is no longer feasible mechanism, since delayed freeing causes bpf_get_stackid() to fail unpredictably when number of actual stacks is significantly less than user requested max_entries. Since elements are no longer freed into slub, we can push elements into freelist immediately and let them be recycled. However the very unlikley race between user space map_lookup() and program-side recycling is possible: cpu0 cpu1 ---- ---- user does lookup(stackidX) starts copying ips into buffer delete(stackidX) calls bpf_get_stackid() which recyles the element and overwrites with new stack trace To avoid user space seeing a partial stack trace consisting of two merged stack traces, do bucket = xchg(, NULL); copy; xchg(,bucket); to preserve consistent stack trace delivery to user space. Now we can move memset(,0) of left-over element value from critical path of bpf_get_stackid() into slow-path of user space lookup. Also disallow lookup() from bpf program, since it's useless and program shouldn't be messing with collected stack trace. Note that similar race between user space lookup and kernel side updates is also present in hashmap, but it's not a new race. bpf programs were always allowed to modify hash and array map elements while user space is copying them. Fixes: d5a3b1f69186 ("bpf: introduce BPF_MAP_TYPE_STACK_TRACE") Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index efd1d4ca95c6..21ee41b92e8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -195,6 +195,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. -- cgit v1.2.3 From 057bd2e0528ec68b3d0481ede0b26a31a9e5d2f1 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Tue, 9 Feb 2016 15:30:47 +0100 Subject: PCI: Add pci_ops.{add,remove}_bus() callbacks Add pci_ops.{add,remove}_bus() callbacks, which will be called on every newly created bus and when a bus is being removed, respectively. This can be used by drivers to implement driver-specific initialization and teardown of the bus, in addition to the architecture-specifics implemented by the pcibios_add_bus() and the pcibios_remove_bus() functions. Signed-off-by: Thierry Reding Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..0f7ef14c4d10 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -578,6 +578,8 @@ static inline int pcibios_err_to_errno(int err) /* Low-level architecture-dependent routines */ struct pci_ops { + int (*add_bus)(struct pci_bus *bus); + void (*remove_bus)(struct pci_bus *bus); void __iomem *(*map_bus)(struct pci_bus *bus, unsigned int devfn, int where); int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val); int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val); -- cgit v1.2.3 From c194f7ea7f68f2690533832ec22f0d7ed4f2d74d Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Fri, 4 Mar 2016 10:53:03 +1100 Subject: PCI/IOV: Rename and export virtfn_{add, remove} During EEH recovery, hotplug is applied to the devices which don't have drivers or their drivers don't support EEH. However, the hotplug, which was implemented based on PCI bus, can't be applied to VF directly. Instead, we unplug and plug individual PCI devices (VFs). This renames virtn_{add,remove}() and exports them so they can be used in PCI hotplug during EEH recovery. Signed-off-by: Wei Yang Reviewed-by: Gavin Shan Acked-by: Bjorn Helgaas Signed-off-by: Michael Ellerman --- include/linux/pci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..3db5e30e8ede 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1738,6 +1738,8 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); +int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset); +void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset); int pci_num_vf(struct pci_dev *dev); int pci_vfs_assigned(struct pci_dev *dev); int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); @@ -1754,6 +1756,12 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) } static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } +static inline int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset) +{ + return -ENOSYS; +} +static inline void pci_iov_remove_virtfn(struct pci_dev *dev, + int id, int reset) { } static inline void pci_disable_sriov(struct pci_dev *dev) { } static inline int pci_num_vf(struct pci_dev *dev) { return 0; } static inline int pci_vfs_assigned(struct pci_dev *dev) -- cgit v1.2.3 From 7b77061f8d03cdaf71d91ea356835131d651b103 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Fri, 4 Mar 2016 10:53:04 +1100 Subject: PCI: Add pcibios_bus_add_device() weak function This adds weak function pcibios_bus_add_device() for arch dependent code could do proper setup. For example, powerpc could setup EEH related resources for SRIOV VFs. Signed-off-by: Wei Yang Reviewed-by: Gavin Shan Acked-by: Bjorn Helgaas Signed-off-by: Michael Ellerman --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 3db5e30e8ede..bc435d6293d2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -770,6 +770,7 @@ extern struct list_head pci_root_buses; /* list of all known PCI buses */ int no_pci_devices(void); void pcibios_resource_survey_bus(struct pci_bus *bus); +void pcibios_bus_add_device(struct pci_dev *pdev); void pcibios_add_bus(struct pci_bus *bus); void pcibios_remove_bus(struct pci_bus *bus); void pcibios_fixup_bus(struct pci_bus *); -- cgit v1.2.3 From e237a5518425155faa508a087f28269f58074b92 Mon Sep 17 00:00:00 2001 From: Chen Fan Date: Mon, 15 Feb 2016 12:52:01 +0800 Subject: x86/ACPI/PCI: Recognize that Interrupt Line 255 means "not connected" Per the x86-specific footnote to PCI spec r3.0, sec 6.2.4, the value 255 in the Interrupt Line register means "unknown" or "no connection." Previously, when we couldn't derive an IRQ from the _PRT, we fell back to using the value from Interrupt Line as an IRQ. It's questionable whether we should do that at all, but the spec clearly suggests we shouldn't do it for the value 255 on x86. Calling request_irq() with IRQ 255 may succeed, but the driver won't receive any interrupts. Or, if IRQ 255 is shared with another device, it may succeed, and the driver's ISR will be called at random times when the *other* device interrupts. Or it may fail if another device is using IRQ 255 with incompatible flags. What we *want* is for request_irq() to fail predictably so the driver can fall back to polling. On x86, assume 255 in the Interrupt Line means the INTx line is not connected. In that case, set dev->irq to IRQ_NOTCONNECTED so request_irq() will fail gracefully with -ENOTCONN. We found this problem on a system where Secure Boot firmware assigned Interrupt Line 255 to an i801_smbus device and another device was already using MSI-X IRQ 255. This was in v3.10, where i801_probe() fails if request_irq() fails: i801_smbus 0000:00:1f.3: enabling device (0140 -> 0143) i801_smbus 0000:00:1f.3: can't derive routing for PCI INT C i801_smbus 0000:00:1f.3: PCI INT C: no GSI genirq: Flags mismatch irq 255. 00000080 (i801_smbus) vs. 00000000 (megasa) CPU: 0 PID: 2487 Comm: kworker/0:1 Not tainted 3.10.0-229.el7.x86_64 #1 Hardware name: FUJITSU PRIMEQUEST 2800E2/D3736, BIOS PRIMEQUEST 2000 Serie5 Call Trace: dump_stack+0x19/0x1b __setup_irq+0x54a/0x570 request_threaded_irq+0xcc/0x170 i801_probe+0x32f/0x508 [i2c_i801] local_pci_probe+0x45/0xa0 i801_smbus 0000:00:1f.3: Failed to allocate irq 255: -16 i801_smbus: probe of 0000:00:1f.3 failed with error -16 After aeb8a3d16ae0 ("i2c: i801: Check if interrupts are disabled"), i801_probe() will fall back to polling if request_irq() fails. But we still need this patch because request_irq() may succeed or fail depending on other devices in the system. If request_irq() fails, i801_smbus will work by falling back to polling, but if it succeeds, i801_smbus won't work because it expects interrupts that it may not receive. Signed-off-by: Chen Fan Acked-by: Thomas Gleixner Acked-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- include/linux/interrupt.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0e95fcc75b2a..358076eda364 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -125,6 +125,16 @@ struct irqaction { extern irqreturn_t no_action(int cpl, void *dev_id); +/* + * If a (PCI) device interrupt is not connected we set dev->irq to + * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we + * can distingiush that case from other error returns. + * + * 0x80000000 is guaranteed to be outside the available range of interrupts + * and easy to distinguish from other possible incorrect values. + */ +#define IRQ_NOTCONNECTED (1U << 31) + extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, -- cgit v1.2.3 From 3fab91ea284a3b795327dda915a3c150a49e4be2 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Mon, 29 Feb 2016 21:08:19 +0800 Subject: gpio: lp3943: Drop pin_used and lp3943_gpio_request/lp3943_gpio_free The implementation of lp3943_gpio_request/lp3943_gpio_free test pin_used for tracing the pin usage. However, gpiolib already checks FLAG_REQUESTED flag for the same purpose. So remove the redundant implementation. Signed-off-by: Axel Lin Signed-off-by: Linus Walleij --- include/linux/mfd/lp3943.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/lp3943.h b/include/linux/mfd/lp3943.h index 3490db782988..d3a738118b27 100644 --- a/include/linux/mfd/lp3943.h +++ b/include/linux/mfd/lp3943.h @@ -94,18 +94,12 @@ struct lp3943_reg_cfg { * @regmap: Used for I2C communication on accessing registers * @pdata: LP3943 platform specific data * @mux_cfg: Register configuration for pin MUX - * @pin_used: Bit mask for output pin used. - * This bitmask is used for pin assignment management. - * 1 = pin used, 0 = available. - * Only LSB 16 bits are used, but it is unsigned long type - * for atomic bitwise operations. */ struct lp3943 { struct device *dev; struct regmap *regmap; struct lp3943_platform_data *pdata; const struct lp3943_reg_cfg *mux_cfg; - unsigned long pin_used; }; int lp3943_read_byte(struct lp3943 *lp3943, u8 reg, u8 *read); -- cgit v1.2.3 From caf02abf9bd00b4c23745a055c4f4c243eecd392 Mon Sep 17 00:00:00 2001 From: "Robin H. Johnson" Date: Sun, 6 Mar 2016 22:02:30 +0000 Subject: PCI: Add QEMU top-level IDs for (sub)vendor & device Introduce PCI_VENDOR/PCI_SUBVENDOR/PCI_SUBDEVICE defines to replace the constants scattered in the kernel already used to detect QEMU. They are defined in the QEMU codebase per docs/specs/pci-ids.txt. Signed-off-by: Robin H. Johnson Signed-off-by: Bjorn Helgaas Reviewed-by: Takashi Iwai Reviewed-by: Gerd Hoffmann Acked-by: Michael S. Tsirkin Acked-by: Daniel Vetter --- include/linux/pci_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 37f05cb1dfd6..6d249d32c8b8 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2506,6 +2506,10 @@ #define PCI_VENDOR_ID_AZWAVE 0x1a3b +#define PCI_VENDOR_ID_REDHAT_QUMRANET 0x1af4 +#define PCI_SUBVENDOR_ID_REDHAT_QUMRANET 0x1af4 +#define PCI_SUBDEVICE_ID_QEMU 0x1100 + #define PCI_VENDOR_ID_ASMEDIA 0x1b21 #define PCI_VENDOR_ID_CIRCUITCO 0x1cc8 -- cgit v1.2.3 From 34e2c555f3e13c90e9284e23d00f03be8a6e06c5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 15 Feb 2016 20:20:42 +0100 Subject: cpufreq: Add mechanism for registering utilization update callbacks Introduce a mechanism by which parts of the cpufreq subsystem ("setpolicy" drivers or the core) can register callbacks to be executed from cpufreq_update_util() which is invoked by the scheduler's update_load_avg() on CPU utilization changes. This allows the "setpolicy" drivers to dispense with their timers and do all of the computations they need and frequency/voltage adjustments in the update_load_avg() code path, among other things. The update_load_avg() changes were suggested by Peter Zijlstra. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- include/linux/cpufreq.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d0bf555b6bbf..704d85bf7242 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -151,6 +151,36 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) extern struct kobject *cpufreq_global_kobject; #ifdef CONFIG_CPU_FREQ +void cpufreq_update_util(u64 time, unsigned long util, unsigned long max); + +/** + * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. + * @time: Current time. + * + * The way cpufreq is currently arranged requires it to evaluate the CPU + * performance state (frequency/voltage) on a regular basis to prevent it from + * being stuck in a completely inadequate performance level for too long. + * That is not guaranteed to happen if the updates are only triggered from CFS, + * though, because they may not be coming in if RT or deadline tasks are active + * all the time (or there are RT and DL tasks only). + * + * As a workaround for that issue, this function is called by the RT and DL + * sched classes to trigger extra cpufreq updates to prevent it from stalling, + * but that really is a band-aid. Going forward it should be replaced with + * solutions targeted more specifically at RT and DL tasks. + */ +static inline void cpufreq_trigger_update(u64 time) +{ + cpufreq_update_util(time, ULONG_MAX, 0); +} + +struct update_util_data { + void (*func)(struct update_util_data *data, + u64 time, unsigned long util, unsigned long max); +}; + +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); + unsigned int cpufreq_get(unsigned int cpu); unsigned int cpufreq_quick_get(unsigned int cpu); unsigned int cpufreq_quick_get_max(unsigned int cpu); @@ -162,6 +192,10 @@ int cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); #else +static inline void cpufreq_update_util(u64 time, unsigned long util, + unsigned long max) {} +static inline void cpufreq_trigger_update(u64 time) {} + static inline unsigned int cpufreq_get(unsigned int cpu) { return 0; -- cgit v1.2.3 From 68e80dae09033d778b98dc88e5bfe8fdade188e5 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 9 Feb 2016 09:01:35 +0530 Subject: Revert "cpufreq: Drop rwsem lock around CPUFREQ_GOV_POLICY_EXIT" Earlier, when the struct freq-attr was used to represent governor attributes, the standard cpufreq show/store sysfs attribute callbacks were applied to the governor tunable attributes and they always acquire the policy->rwsem lock before carrying out the operation. That could have resulted in an ABBA deadlock if governor tunable attributes are removed under policy->rwsem while one of them is being accessed concurrently (if sysfs attributes removal wins the race, it will wait for the access to complete with policy->rwsem held while the attribute callback will block on policy->rwsem indefinitely). We attempted to address this issue by dropping policy->rwsem around governor tunable attributes removal (that is, around invocations of the ->governor callback with the event arg equal to CPUFREQ_GOV_POLICY_EXIT) in cpufreq_set_policy(), but that opened up race conditions that had not been possible with policy->rwsem held all the time. The previous commit, "cpufreq: governor: New sysfs show/store callbacks for governor tunables", fixed the original ABBA deadlock by adding new governor specific show/store callbacks. We don't have to drop rwsem around invocations of governor event CPUFREQ_GOV_POLICY_EXIT anymore, and original fix can be reverted now. Fixes: 955ef4833574 (cpufreq: Drop rwsem lock around CPUFREQ_GOV_POLICY_EXIT) Signed-off-by: Viresh Kumar Reported-by: Juri Lelli Tested-by: Juri Lelli Tested-by: Shilpasri G Bhat Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 704d85bf7242..cac3d1ba8200 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -100,10 +100,6 @@ struct cpufreq_policy { * - Any routine that will write to the policy structure and/or may take away * the policy altogether (eg. CPU hotplug), will hold this lock in write * mode before doing so. - * - * Additional rules: - * - Lock should not be held across - * __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT); */ struct rw_semaphore rwsem; -- cgit v1.2.3 From 242aa883a64d8c54cfeee47f3603b21bc705e081 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 22 Feb 2016 16:36:44 +0530 Subject: cpufreq: Remove 'policy->governor_enabled' The entire sequence of events (like INIT/START or STOP/EXIT) for which cpufreq_governor() is called, is guaranteed to be protected by policy->rwsem now. The additional checks that were added earlier (as we were forced to drop policy->rwsem before calling cpufreq_governor() for EXIT event), aren't required anymore. Over that, they weren't sufficient really. They just take care of START/STOP events, but not INIT/EXIT and the state machine was never maintained properly by them. Kill the unnecessary checks and policy->governor_enabled field. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index cac3d1ba8200..a50c5b2e3bf2 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -80,7 +80,6 @@ struct cpufreq_policy { unsigned int last_policy; /* policy before unplug */ struct cpufreq_governor *governor; /* see below */ void *governor_data; - bool governor_enabled; /* governor start/stop flag */ char last_governor[CPUFREQ_NAME_LEN]; /* last governor used */ struct work_struct update; /* if update_policy() needs to be -- cgit v1.2.3 From 70aba44b6cade8dc63261c4f97d5e83b0c02d07a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 9 Mar 2016 22:00:27 +0700 Subject: Revert "gpio: lp3943: Drop pin_used and lp3943_gpio_request/lp3943_gpio_free" This reverts commit 3fab91ea284a3b795327dda915a3c150a49e4be2. --- include/linux/mfd/lp3943.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/lp3943.h b/include/linux/mfd/lp3943.h index d3a738118b27..3490db782988 100644 --- a/include/linux/mfd/lp3943.h +++ b/include/linux/mfd/lp3943.h @@ -94,12 +94,18 @@ struct lp3943_reg_cfg { * @regmap: Used for I2C communication on accessing registers * @pdata: LP3943 platform specific data * @mux_cfg: Register configuration for pin MUX + * @pin_used: Bit mask for output pin used. + * This bitmask is used for pin assignment management. + * 1 = pin used, 0 = available. + * Only LSB 16 bits are used, but it is unsigned long type + * for atomic bitwise operations. */ struct lp3943 { struct device *dev; struct regmap *regmap; struct lp3943_platform_data *pdata; const struct lp3943_reg_cfg *mux_cfg; + unsigned long pin_used; }; int lp3943_read_byte(struct lp3943 *lp3943, u8 reg, u8 *read); -- cgit v1.2.3 From e498b4984db82b4ba3ceea7dba813222a31e9c2e Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 9 Mar 2016 18:40:06 +0530 Subject: thermal: of-thermal: Add devm version of thermal_zone_of_sensor_register Add resource managed version of thermal_zone_of_sensor_register() and thermal_zone_of_sensor_unregister(). This helps in reducing the code size in error path, remove of driver remove callbacks and making proper sequence for deallocations. Signed-off-by: Laxman Dewangan Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index e13a1ace50e9..9c481991fdc7 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -362,6 +362,11 @@ thermal_zone_of_sensor_register(struct device *dev, int id, void *data, const struct thermal_zone_of_device_ops *ops); void thermal_zone_of_sensor_unregister(struct device *dev, struct thermal_zone_device *tz); +struct thermal_zone_device *devm_thermal_zone_of_sensor_register( + struct device *dev, int id, void *data, + const struct thermal_zone_of_device_ops *ops); +void devm_thermal_zone_of_sensor_unregister(struct device *dev, + struct thermal_zone_device *tz); #else static inline struct thermal_zone_device * thermal_zone_of_sensor_register(struct device *dev, int id, void *data, @@ -376,6 +381,19 @@ void thermal_zone_of_sensor_unregister(struct device *dev, { } +static inline struct thermal_zone_device *devm_thermal_zone_of_sensor_register( + struct device *dev, int id, void *data, + const struct thermal_zone_of_device_ops *ops) +{ + return ERR_PTR(-ENODEV); +} + +static inline +void devm_thermal_zone_of_sensor_unregister(struct device *dev, + struct thermal_zone_device *tz) +{ +} + #endif #if IS_ENABLED(CONFIG_THERMAL) -- cgit v1.2.3 From ff3cc952d3f009e6c376cc40651b87187ce364a6 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 9 Mar 2016 12:47:04 -0700 Subject: resource: Add remove_resource interface insert_resource() and insert_resource_conflict() are called by resource producers to insert a new resource. When there is any conflict, they move conflicting resources down to the children of the new resource. There is no destructor of these interfaces, however. Add remove_resource(), which removes a resource previously inserted by insert_resource() or insert_resource_conflict(), and moves the children up to where they were before. __release_resource() is changed to have @release_child, so that this function can be used for remove_resource() as well. Also add comments to clarify that these functions are intended for producers of resources to avoid any confusion with request/release_resource() for consumers. Signed-off-by: Toshi Kani Cc: Ingo Molnar Cc: Borislav Petkov Cc: Andrew Morton Cc: Dan Williams Signed-off-by: Dan Williams --- include/linux/ioport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index afb45597fb5f..8017b8bf45fa 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -174,6 +174,7 @@ extern void reserve_region_with_split(struct resource *root, extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); +extern int remove_resource(struct resource *old); extern void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, -- cgit v1.2.3 From ff3c44e675054533403909ecb76e78c1d4efbd26 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:00 -0800 Subject: rcu: Add list_next_or_null_rcu This is a convenience function that returns the next entry in an RCU list or NULL if at the end of the list. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/rculist.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 14ec1652daf4..17d4f849c65e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -318,6 +318,27 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) +/** + * list_next_or_null_rcu - get the first element from a list + * @head: the head for the list. + * @ptr: the list head to take the next element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the ptr is at the end of the list, NULL is returned. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). + */ +#define list_next_or_null_rcu(head, ptr, type, member) \ +({ \ + struct list_head *__head = (head); \ + struct list_head *__ptr = (ptr); \ + struct list_head *__next = READ_ONCE(__ptr->next); \ + likely(__next != __head) ? list_entry_rcu(__next, type, \ + member) : NULL; \ +}) + /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. -- cgit v1.2.3 From f4a00aacdb5f6784d46e8c999b6bb52ece4b306b Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:01 -0800 Subject: net: Make sock_alloc exportable Export it for cases where we want to create sockets by hand. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 0b4ac7da583a..49175e4ced11 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -215,6 +215,7 @@ int __sock_create(struct net *net, int family, int type, int proto, int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); +struct socket *sock_alloc(void); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, -- cgit v1.2.3 From f092276d85b82504e8a07498f4e9e0c51f06745c Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:03 -0800 Subject: net: Add MSG_BATCH flag Add a new msg flag called MSG_BATCH. This flag is used in sendmsg to indicate that more messages will follow (i.e. a batch of messages is being sent). This is similar to MSG_MORE except that the following messages are not merged into one packet, they are sent individually. sendmmsg is updated so that each contained message except for the last one is marked as MSG_BATCH. MSG_BATCH is a performance optimization in cases where a socket implementation can benefit by transmitting packets in a batch. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 5bf59c8493b7..d834af22a460 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -274,6 +274,7 @@ struct ucred { #define MSG_MORE 0x8000 /* Sender will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ +#define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ -- cgit v1.2.3 From ab7ac4eb9832e32a09f4e8042705484d2fb0aad3 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:06 -0800 Subject: kcm: Kernel Connection Multiplexor module This module implements the Kernel Connection Multiplexor. Kernel Connection Multiplexor (KCM) is a facility that provides a message based interface over TCP for generic application protocols. With KCM an application can efficiently send and receive application protocol messages over TCP using datagram sockets. For more information see the included Documentation/networking/kcm.txt Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/socket.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index d834af22a460..73bf6c6a833b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -200,7 +200,9 @@ struct ucred { #define AF_ALG 38 /* Algorithm sockets */ #define AF_NFC 39 /* NFC sockets */ #define AF_VSOCK 40 /* vSockets */ -#define AF_MAX 41 /* For now.. */ +#define AF_KCM 41 /* Kernel Connection Multiplexor*/ + +#define AF_MAX 42 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -246,6 +248,7 @@ struct ucred { #define PF_ALG AF_ALG #define PF_NFC AF_NFC #define PF_VSOCK AF_VSOCK +#define PF_KCM AF_KCM #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -323,6 +326,7 @@ struct ucred { #define SOL_CAIF 278 #define SOL_ALG 279 #define SOL_NFC 280 +#define SOL_KCM 281 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From 87aca73737e379f079993802d2c43606f7c5d26c Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 21 Jan 2016 09:20:12 +0100 Subject: NFC: microread: Drop platform data header file Originally I only wanted to drop the unneeded inclusion of , but then noticed that struct microread_nfc_platform_data isn't actually used, and MICROREAD_DRIVER_NAME is redefined in the only file where it is used, so we can get rid of the header file and dead code altogether. Signed-off-by: Jean Delvare Cc: Lauro Ramos Venancio Cc: Aloisio Almeida Jr Signed-off-by: Samuel Ortiz --- include/linux/platform_data/microread.h | 35 --------------------------------- 1 file changed, 35 deletions(-) delete mode 100644 include/linux/platform_data/microread.h (limited to 'include/linux') diff --git a/include/linux/platform_data/microread.h b/include/linux/platform_data/microread.h deleted file mode 100644 index ca13992089b8..000000000000 --- a/include/linux/platform_data/microread.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Driver include for the Inside Secure microread NFC Chip. - * - * Copyright (C) 2011 Tieto Poland - * Copyright (C) 2012 Intel Corporation. All rights reserved. - * - * 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. - * - * 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _MICROREAD_H -#define _MICROREAD_H - -#include - -#define MICROREAD_DRIVER_NAME "microread" - -/* board config platform data for microread */ -struct microread_nfc_platform_data { - unsigned int rst_gpio; - unsigned int irq_gpio; - unsigned int ioh_gpio; -}; - -#endif /* _MICROREAD_H */ -- cgit v1.2.3 From 59e6473980f321c16299e12db69d1fabc2644a6f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Mar 2016 07:16:07 -0800 Subject: libnvdimm, pmem: clear poison on write If a write is directed at a known bad block perform the following: 1/ write the data 2/ send a clear poison command 3/ invalidate the poison out of the cache hierarchy Cc: Cc: Ross Zwisler Reviewed-by: Vishal Verma Signed-off-by: Dan Williams --- include/linux/pmem.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pmem.h b/include/linux/pmem.h index 7c3d11a6b4ad..3ec5309e29f3 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -58,6 +58,11 @@ static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size) { BUG(); } + +static inline void arch_invalidate_pmem(void __pmem *addr, size_t size) +{ + BUG(); +} #endif /* @@ -185,6 +190,20 @@ static inline void clear_pmem(void __pmem *addr, size_t size) default_clear_pmem(addr, size); } +/** + * invalidate_pmem - flush a pmem range from the cache hierarchy + * @addr: virtual start address + * @size: bytes to invalidate (internally aligned to cache line size) + * + * For platforms that support clearing poison this flushes any poisoned + * ranges out of the cache + */ +static inline void invalidate_pmem(void __pmem *addr, size_t size) +{ + if (arch_has_pmem_api()) + arch_invalidate_pmem(addr, size); +} + /** * wb_cache_pmem - write back processor cache for PMEM memory range * @addr: virtual start address -- cgit v1.2.3 From 2793a23aacbd754dbbb5cb75093deb7e4103bace Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 9 Mar 2016 21:58:32 -0500 Subject: net: validate variable length ll headers Netdevice parameter hard_header_len is variously interpreted both as an upper and lower bound on link layer header length. The field is used as upper bound when reserving room at allocation, as lower bound when validating user input in PF_PACKET. Clarify the definition to be maximum header length. For validation of untrusted headers, add an optional validate member to header_ops. Allow bypassing of validation by passing CAP_SYS_RAWIO, for instance for deliberate testing of corrupt input. In this case, pad trailing bytes, as some device drivers expect completely initialized headers. See also http://comments.gmane.org/gmane.linux.network/401064 Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index efe7cec111fa..fd30cb545c45 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -268,6 +268,7 @@ struct header_ops { void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); + bool (*validate)(const char *ll_header, unsigned int len); }; /* These flag bits are private to the generic network queueing @@ -1459,8 +1460,7 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length, which means that this is the - * minimum size of a packet. + * @hard_header_len: Maximum hardware header length. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -2687,6 +2687,24 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +/* ll_header must have at least hard_header_len allocated */ +static inline bool dev_validate_header(const struct net_device *dev, + char *ll_header, int len) +{ + if (likely(len >= dev->hard_header_len)) + return true; + + if (capable(CAP_SYS_RAWIO)) { + memset(ll_header + len, 0, dev->hard_header_len - len); + return true; + } + + if (dev->header_ops && dev->header_ops->validate) + return dev->header_ops->validate(ll_header, len); + + return false; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) -- cgit v1.2.3 From 153fefbf34e5079c2dd69490f5f23373758d2e9c Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 7 Mar 2016 18:51:45 +0200 Subject: net/mlx5_core: Create anchor of last flow table Create an empty flow table in the end of NIC rx namesapce. Adding this flow table simplify the implementation of "forward to next prio" rules. Signed-off-by: Maor Gottlieb Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8230caa3fb6e..72adf53fdcba 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -52,6 +52,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, + MLX5_FLOW_NAMESPACE_ANCHOR, MLX5_FLOW_NAMESPACE_FDB, }; -- cgit v1.2.3 From b3638e1a76648dbd482cc5a8f27eb6948cc3bc86 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 7 Mar 2016 18:51:46 +0200 Subject: net/mlx5_core: Introduce forward to next priority action Add support to create flow rule that forward packets to the first flow table in the next priority (next priority could be the first priority in the next namespace or the next priority in the same namespace). This feature could be used for DONT_TRAP rules or rules that only want to mark the packet with flow tag. In order to do it optimally, each flow table has list of all rules that point to this flow table, when a flow table is destroyed/created, we update the list head correspondingly. This kind of rule is created when destination is NULL and action is MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO. Signed-off-by: Maor Gottlieb Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- include/linux/mlx5/fs.h | 4 ++++ include/linux/mlx5/mlx5_ifc.h | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 72adf53fdcba..8dec5508d93d 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -38,6 +38,10 @@ #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 +enum { + MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, +}; + #define LEFTOVERS_RULE_NUM 2 static inline void build_leftovers_ft_param(int *priority, int *n_ent, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..5f70f36af3cd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -458,7 +458,8 @@ struct mlx5_ifc_ads_bits { }; struct mlx5_ifc_flow_table_nic_cap_bits { - u8 reserved_at_0[0x200]; + u8 nic_rx_multi_path_tirs[0x1]; + u8 reserved_at_1[0x1ff]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; -- cgit v1.2.3 From 35d1901134e97cf95c0ab6ef70f5aead6cb34e9e Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 7 Mar 2016 18:51:47 +0200 Subject: IB/mlx5: Add support for don't trap rules Each bypass flow steering priority will be split into two priorities: 1. Priority for don't trap rules. 2. Priority for normal rules. When user creates a flow using IB_FLOW_ATTR_FLAGS_DONT_TRAP flag, the driver creates two flow rules, one used for receiving the traffic and the other one for forwarding the packet to continue matching in lower or equal priorities. Signed-off-by: Maor Gottlieb Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..2bf222e65e6b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1294,6 +1294,11 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } -#define MLX5_BY_PASS_NUM_PRIOS 9 +#define MLX5_BY_PASS_NUM_REGULAR_PRIOS 8 +#define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 8 +#define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1 +#define MLX5_BY_PASS_NUM_PRIOS (MLX5_BY_PASS_NUM_REGULAR_PRIOS +\ + MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS +\ + MLX5_BY_PASS_NUM_MULTICAST_PRIOS) #endif /* MLX5_DEVICE_H */ -- cgit v1.2.3 From 764fd639d794a1c0b0d203b19d1bef0451c23fb1 Mon Sep 17 00:00:00 2001 From: "Wiebe, Wladislav (Nokia - DE/Ulm)" Date: Fri, 13 Nov 2015 12:10:05 +0000 Subject: pstore: Add support for 64 Bit address space Some architectures have their reserved RAM in 64 Bit address space. Therefore convert mem_address module parameter to ullong. Signed-off-by: Wladislav Wiebe Acked-by: Kees Cook Signed-off-by: Tony Luck --- include/linux/pstore_ram.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9c9d6c154c8e..4660aaa3195e 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -76,7 +76,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, struct ramoops_platform_data { unsigned long mem_size; - unsigned long mem_address; + phys_addr_t mem_address; unsigned int mem_type; unsigned long record_size; unsigned long console_size; -- cgit v1.2.3 From 9f3e04297b08212ef43fce4f167e01f40a98d243 Mon Sep 17 00:00:00 2001 From: Archit Taneja Date: Wed, 3 Feb 2016 14:29:49 +0530 Subject: mtd: nand: don't select chip in nand_chip's block_bad op One of the arguments passed to struct nand_chip's block_bad op is 'getchip', which, if true, is supposed to get and select the nand device, and later unselect and release the device. This op is intended to be replaceable by drivers. The drivers shouldn't be responsible for selecting/unselecting chip. Like other ops, the chip should already be selected before the block_bad op is called. Remove the getchip argument from the block_bad op and nand_block_checkbad. Move the chip selection to nand_block_isbad, since it is the only caller to nand_block_checkbad which requires chip selection. Modify nand_block_bad (the default function for the op) such that it doesn't select the chip. Remove the getchip argument from the bad_block funcs in cafe_nand, diskonchip and docg4 drivers. Reviewed-by: Boris Brezillon Signed-off-by: Archit Taneja Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 7604f4be3386..56574ba36555 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -672,7 +672,7 @@ struct nand_chip { void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); void (*select_chip)(struct mtd_info *mtd, int chip); - int (*block_bad)(struct mtd_info *mtd, loff_t ofs, int getchip); + int (*block_bad)(struct mtd_info *mtd, loff_t ofs); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); int (*dev_ready)(struct mtd_info *mtd); -- cgit v1.2.3 From adaf9fcd136970e480d7ca834c0cf25ce922ea74 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Mar 2016 20:44:47 +0100 Subject: cpufreq: Move scheduler-related code to the sched directory Create cpufreq.c under kernel/sched/ and move the cpufreq code related to the scheduler to that file and to sched.h. Redefine cpufreq_update_util() as a static inline function to avoid function calls at its call sites in the scheduler code (as suggested by Peter Zijlstra). Also move the definition of struct update_util_data and declaration of cpufreq_set_update_util_data() from include/linux/cpufreq.h to include/linux/sched.h. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- include/linux/cpufreq.h | 34 ---------------------------------- include/linux/sched.h | 9 +++++++++ 2 files changed, 9 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a50c5b2e3bf2..a5ea52f793f3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -146,36 +146,6 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) extern struct kobject *cpufreq_global_kobject; #ifdef CONFIG_CPU_FREQ -void cpufreq_update_util(u64 time, unsigned long util, unsigned long max); - -/** - * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. - * @time: Current time. - * - * The way cpufreq is currently arranged requires it to evaluate the CPU - * performance state (frequency/voltage) on a regular basis to prevent it from - * being stuck in a completely inadequate performance level for too long. - * That is not guaranteed to happen if the updates are only triggered from CFS, - * though, because they may not be coming in if RT or deadline tasks are active - * all the time (or there are RT and DL tasks only). - * - * As a workaround for that issue, this function is called by the RT and DL - * sched classes to trigger extra cpufreq updates to prevent it from stalling, - * but that really is a band-aid. Going forward it should be replaced with - * solutions targeted more specifically at RT and DL tasks. - */ -static inline void cpufreq_trigger_update(u64 time) -{ - cpufreq_update_util(time, ULONG_MAX, 0); -} - -struct update_util_data { - void (*func)(struct update_util_data *data, - u64 time, unsigned long util, unsigned long max); -}; - -void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); - unsigned int cpufreq_get(unsigned int cpu); unsigned int cpufreq_quick_get(unsigned int cpu); unsigned int cpufreq_quick_get_max(unsigned int cpu); @@ -187,10 +157,6 @@ int cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); #else -static inline void cpufreq_update_util(u64 time, unsigned long util, - unsigned long max) {} -static inline void cpufreq_trigger_update(u64 time) {} - static inline unsigned int cpufreq_get(unsigned int cpu) { return 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index a10494a94cc3..913e755ef7b8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3207,4 +3207,13 @@ static inline unsigned long rlimit_max(unsigned int limit) return task_rlimit_max(current, limit); } +#ifdef CONFIG_CPU_FREQ +struct update_util_data { + void (*func)(struct update_util_data *data, + u64 time, unsigned long util, unsigned long max); +}; + +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); +#endif /* CONFIG_CPU_FREQ */ + #endif -- cgit v1.2.3 From 5b33f48842fa1e13e9c0ea8cc59c1d0df19042db Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 8 Mar 2016 12:42:29 +0200 Subject: net/flower: Introduce hardware offload support This patch is based on a patch made by John Fastabend. It adds support for offloading cls_flower. when NETIF_F_HW_TC is on: flags = 0 => Rule will be processed twice - by hardware, and if still relevant, by software. flags = SKIP_HW => Rull will be processed by software only If hardware fail/not capabale to apply the rule, operation will NOT fail. Filter will be processed by SW only. Acked-by: Jiri Pirko Suggested-by: John Fastabend Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd30cb545c45..41df0b450757 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -786,6 +786,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, enum { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, + TC_SETUP_CLSFLOWER, }; struct tc_cls_u32_offload; @@ -795,6 +796,7 @@ struct tc_to_netdev { union { u8 tc; struct tc_cls_u32_offload *cls_u32; + struct tc_cls_flower_offload *cls_flower; }; }; -- cgit v1.2.3 From 4df2bf466a9c9c92f40d27c4aa9120f4e8227bfc Mon Sep 17 00:00:00 2001 From: DingXiang Date: Tue, 2 Feb 2016 12:29:18 +0800 Subject: dm snapshot: disallow the COW and origin devices from being identical Otherwise loading a "snapshot" table using the same device for the origin and COW devices, e.g.: echo "0 20971520 snapshot 253:3 253:3 P 8" | dmsetup create snap will trigger: BUG: unable to handle kernel NULL pointer dereference at 0000000000000098 [ 1958.979934] IP: [] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1958.989655] PGD 0 [ 1958.991903] Oops: 0000 [#1] SMP ... [ 1959.059647] CPU: 9 PID: 3556 Comm: dmsetup Tainted: G IO 4.5.0-rc5.snitm+ #150 ... [ 1959.083517] task: ffff8800b9660c80 ti: ffff88032a954000 task.ti: ffff88032a954000 [ 1959.091865] RIP: 0010:[] [] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.104295] RSP: 0018:ffff88032a957b30 EFLAGS: 00010246 [ 1959.110219] RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000001 [ 1959.118180] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff880329334a00 [ 1959.126141] RBP: ffff88032a957b50 R08: 0000000000000000 R09: 0000000000000001 [ 1959.134102] R10: 000000000000000a R11: f000000000000000 R12: ffff880330884d80 [ 1959.142061] R13: 0000000000000008 R14: ffffc90001c13088 R15: ffff880330884d80 [ 1959.150021] FS: 00007f8926ba3840(0000) GS:ffff880333440000(0000) knlGS:0000000000000000 [ 1959.159047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1959.165456] CR2: 0000000000000098 CR3: 000000032f48b000 CR4: 00000000000006e0 [ 1959.173415] Stack: [ 1959.175656] ffffc90001c13040 ffff880329334a00 ffff880330884ed0 ffff88032a957bdc [ 1959.183946] ffff88032a957bb8 ffffffffa040f225 ffff880329334a30 ffff880300000000 [ 1959.192233] ffffffffa04133e0 ffff880329334b30 0000000830884d58 00000000569c58cf [ 1959.200521] Call Trace: [ 1959.203248] [] dm_exception_store_create+0x1d5/0x240 [dm_snapshot] [ 1959.211986] [] snapshot_ctr+0x140/0x630 [dm_snapshot] [ 1959.219469] [] ? dm_split_args+0x64/0x150 [dm_mod] [ 1959.226656] [] dm_table_add_target+0x177/0x440 [dm_mod] [ 1959.234328] [] table_load+0x143/0x370 [dm_mod] [ 1959.241129] [] ? retrieve_status+0x1b0/0x1b0 [dm_mod] [ 1959.248607] [] ctl_ioctl+0x255/0x4d0 [dm_mod] [ 1959.255307] [] ? memzero_explicit+0x12/0x20 [ 1959.261816] [] dm_ctl_ioctl+0x13/0x20 [dm_mod] [ 1959.268615] [] do_vfs_ioctl+0xa6/0x5c0 [ 1959.274637] [] ? __audit_syscall_entry+0xaf/0x100 [ 1959.281726] [] ? do_audit_syscall_entry+0x66/0x70 [ 1959.288814] [] SyS_ioctl+0x79/0x90 [ 1959.294450] [] entry_SYSCALL_64_fastpath+0x12/0x71 ... [ 1959.323277] RIP [] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.333090] RSP [ 1959.336978] CR2: 0000000000000098 [ 1959.344121] ---[ end trace b049991ccad1169e ]--- Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1195899 Cc: stable@vger.kernel.org Signed-off-by: Ding Xiang Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 82ae3b5e2c45..0830c9e86f0d 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -124,6 +124,8 @@ struct dm_dev { char name[16]; }; +dev_t dm_get_dev_t(const char *path); + /* * Constructors should call these functions to ensure destination devices * are opened/closed correctly. -- cgit v1.2.3 From 2b6a321da9a2d8725a1d3dbb0b2e96a7618ebe56 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Thu, 10 Mar 2016 15:35:49 -0800 Subject: Input: synaptics-rmi4 - add support for Synaptics RMI4 devices Synaptics uses the Register Mapped Interface (RMI) protocol as a communications interface for their devices. This driver adds the core functionality needed to interface with RMI4 devices. RMI devices can be connected to the host via several transport protocols and can supports a wide variety of functionality defined by RMI functions. Support for transport protocols and RMI functions are implemented in individual drivers. The RMI4 core driver uses a bus architecture to facilitate the various combinations of transport and function drivers needed by a particular device. Signed-off-by: Andrew Duggan Signed-off-by: Christopher Heiny Tested-by: Benjamin Tissoires Tested-by: Linus Walleij Tested-by: Bjorn Andersson Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 209 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 209 insertions(+) create mode 100644 include/linux/rmi.h (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h new file mode 100644 index 000000000000..c748fa302067 --- /dev/null +++ b/include/linux/rmi.h @@ -0,0 +1,209 @@ +/* + * Copyright (c) 2011-2016 Synaptics Incorporated + * Copyright (c) 2011 Unixphere + * + * 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 _RMI_H +#define _RMI_H +#include +#include +#include +#include +#include +#include +#include + +#define NAME_BUFFER_SIZE 256 + +/** + * struct rmi_f01_power - override default power management settings. + * + */ +enum rmi_f01_nosleep { + RMI_F01_NOSLEEP_DEFAULT = 0, + RMI_F01_NOSLEEP_OFF = 1, + RMI_F01_NOSLEEP_ON = 2 +}; + +/** + * struct rmi_f01_power_management -When non-zero, these values will be written + * to the touch sensor to override the default firmware settigns. For a + * detailed explanation of what each field does, see the corresponding + * documention in the RMI4 specification. + * + * @nosleep - specifies whether the device is permitted to sleep or doze (that + * is, enter a temporary low power state) when no fingers are touching the + * sensor. + * @wakeup_threshold - controls the capacitance threshold at which the touch + * sensor will decide to wake up from that low power state. + * @doze_holdoff - controls how long the touch sensor waits after the last + * finger lifts before entering the doze state, in units of 100ms. + * @doze_interval - controls the interval between checks for finger presence + * when the touch sensor is in doze mode, in units of 10ms. + */ +struct rmi_f01_power_management { + enum rmi_f01_nosleep nosleep; + u8 wakeup_threshold; + u8 doze_holdoff; + u8 doze_interval; +}; + +/** + * struct rmi_device_platform_data - system specific configuration info. + * + * @reset_delay_ms - after issuing a reset command to the touch sensor, the + * driver waits a few milliseconds to give the firmware a chance to + * to re-initialize. You can override the default wait period here. + */ +struct rmi_device_platform_data { + int reset_delay_ms; + + /* function handler pdata */ + struct rmi_f01_power_management power_management; +}; + +/** + * struct rmi_function_descriptor - RMI function base addresses + * + * @query_base_addr: The RMI Query base address + * @command_base_addr: The RMI Command base address + * @control_base_addr: The RMI Control base address + * @data_base_addr: The RMI Data base address + * @interrupt_source_count: The number of irqs this RMI function needs + * @function_number: The RMI function number + * + * This struct is used when iterating the Page Description Table. The addresses + * are 16-bit values to include the current page address. + * + */ +struct rmi_function_descriptor { + u16 query_base_addr; + u16 command_base_addr; + u16 control_base_addr; + u16 data_base_addr; + u8 interrupt_source_count; + u8 function_number; + u8 function_version; +}; + +struct rmi_device; + +/** + * struct rmi_transport_dev - represent an RMI transport device + * + * @dev: Pointer to the communication device, e.g. i2c or spi + * @rmi_dev: Pointer to the RMI device + * @proto_name: name of the transport protocol (SPI, i2c, etc) + * @ops: pointer to transport operations implementation + * + * The RMI transport device implements the glue between different communication + * buses such as I2C and SPI. + * + */ +struct rmi_transport_dev { + struct device *dev; + struct rmi_device *rmi_dev; + + const char *proto_name; + const struct rmi_transport_ops *ops; + + struct rmi_device_platform_data pdata; + + struct input_dev *input; + + void *attn_data; + int attn_size; +}; + +/** + * struct rmi_transport_ops - defines transport protocol operations. + * + * @write_block: Writing a block of data to the specified address + * @read_block: Read a block of data from the specified address. + */ +struct rmi_transport_ops { + int (*write_block)(struct rmi_transport_dev *xport, u16 addr, + const void *buf, size_t len); + int (*read_block)(struct rmi_transport_dev *xport, u16 addr, + void *buf, size_t len); + int (*reset)(struct rmi_transport_dev *xport, u16 reset_addr); +}; + +/** + * struct rmi_driver - driver for an RMI4 sensor on the RMI bus. + * + * @driver: Device driver model driver + * @reset_handler: Called when a reset is detected. + * @clear_irq_bits: Clear the specified bits in the current interrupt mask. + * @set_irq_bist: Set the specified bits in the current interrupt mask. + * @store_productid: Callback for cache product id from function 01 + * @data: Private data pointer + * + */ +struct rmi_driver { + struct device_driver driver; + + int (*reset_handler)(struct rmi_device *rmi_dev); + int (*clear_irq_bits)(struct rmi_device *rmi_dev, unsigned long *mask); + int (*set_irq_bits)(struct rmi_device *rmi_dev, unsigned long *mask); + int (*store_productid)(struct rmi_device *rmi_dev); + int (*set_input_params)(struct rmi_device *rmi_dev, + struct input_dev *input); + void *data; +}; + +/** + * struct rmi_device - represents an RMI4 sensor device on the RMI bus. + * + * @dev: The device created for the RMI bus + * @number: Unique number for the device on the bus. + * @driver: Pointer to associated driver + * @xport: Pointer to the transport interface + * + */ +struct rmi_device { + struct device dev; + int number; + + struct rmi_driver *driver; + struct rmi_transport_dev *xport; + +}; + +struct rmi_driver_data { + struct list_head function_list; + + struct rmi_device *rmi_dev; + + struct rmi_function *f01_container; + bool f01_bootloader_mode; + + u32 attn_count; + int num_of_irq_regs; + int irq_count; + unsigned long *irq_status; + unsigned long *fn_irq_bits; + unsigned long *current_irq_mask; + unsigned long *new_irq_mask; + struct mutex irq_mutex; + struct input_dev *input; + + u8 pdt_props; + u8 bsr; + + bool enabled; + + void *data; +}; + +int rmi_register_transport_device(struct rmi_transport_dev *xport); +void rmi_unregister_transport_device(struct rmi_transport_dev *xport); +int rmi_process_interrupt_requests(struct rmi_device *rmi_dev); + +int rmi_driver_suspend(struct rmi_device *rmi_dev); +int rmi_driver_resume(struct rmi_device *rmi_dev); +#endif -- cgit v1.2.3 From ff8f83708b3e36c050dc3fd7e2f04ea7f1752599 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Thu, 10 Mar 2016 15:47:28 -0800 Subject: Input: synaptics-rmi4 - add support for 2D sensors and F11 RMI4 currently defines two functions for reporting data for 2D sensors (F11 and F12). This patch adds the common functionality which is shared by devices with 2D reporting along with implementing functionality for F11. Signed-off-by: Andrew Duggan Signed-off-by: Christopher Heiny Tested-by: Benjamin Tissoires Tested-by: Linus Walleij Tested-by: Bjorn Andersson Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 83 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index c748fa302067..b527064bac47 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -19,6 +19,88 @@ #define NAME_BUFFER_SIZE 256 +/** + * struct rmi_2d_axis_alignment - target axis alignment + * @swap_axes: set to TRUE if desired to swap x- and y-axis + * @flip_x: set to TRUE if desired to flip direction on x-axis + * @flip_y: set to TRUE if desired to flip direction on y-axis + * @clip_x_low - reported X coordinates below this setting will be clipped to + * the specified value + * @clip_x_high - reported X coordinates above this setting will be clipped to + * the specified value + * @clip_y_low - reported Y coordinates below this setting will be clipped to + * the specified value + * @clip_y_high - reported Y coordinates above this setting will be clipped to + * the specified value + * @offset_x - this value will be added to all reported X coordinates + * @offset_y - this value will be added to all reported Y coordinates + * @rel_report_enabled - if set to true, the relative reporting will be + * automatically enabled for this sensor. + */ +struct rmi_2d_axis_alignment { + bool swap_axes; + bool flip_x; + bool flip_y; + u16 clip_x_low; + u16 clip_y_low; + u16 clip_x_high; + u16 clip_y_high; + u16 offset_x; + u16 offset_y; + u8 delta_x_threshold; + u8 delta_y_threshold; +}; + +/** This is used to override any hints an F11 2D sensor might have provided + * as to what type of sensor it is. + * + * @rmi_f11_sensor_default - do not override, determine from F11_2D_QUERY14 if + * available. + * @rmi_f11_sensor_touchscreen - treat the sensor as a touchscreen (direct + * pointing). + * @rmi_f11_sensor_touchpad - thread the sensor as a touchpad (indirect + * pointing). + */ +enum rmi_sensor_type { + rmi_sensor_default = 0, + rmi_sensor_touchscreen, + rmi_sensor_touchpad +}; + +#define RMI_F11_DISABLE_ABS_REPORT BIT(0) + +/** + * struct rmi_2d_sensor_data - overrides defaults for a 2D sensor. + * @axis_align - provides axis alignment overrides (see above). + * @sensor_type - Forces the driver to treat the sensor as an indirect + * pointing device (touchpad) rather than a direct pointing device + * (touchscreen). This is useful when F11_2D_QUERY14 register is not + * available. + * @disable_report_mask - Force data to not be reported even if it is supported + * by the firware. + * @topbuttonpad - Used with the "5 buttons touchpads" found on the Lenovo 40 + * series + * @kernel_tracking - most moderns RMI f11 firmwares implement Multifinger + * Type B protocol. However, there are some corner cases where the user + * triggers some jumps by tapping with two fingers on the touchpad. + * Use this setting and dmax to filter out these jumps. + * Also, when using an old sensor using MF Type A behavior, set to true to + * report an actual MT protocol B. + * @dmax - the maximum distance (in sensor units) the kernel tracking allows two + * distincts fingers to be considered the same. + */ +struct rmi_2d_sensor_platform_data { + struct rmi_2d_axis_alignment axis_align; + enum rmi_sensor_type sensor_type; + int x_mm; + int y_mm; + int disable_report_mask; + u16 rezero_wait; + bool topbuttonpad; + bool kernel_tracking; + int dmax; +}; + /** * struct rmi_f01_power - override default power management settings. * @@ -63,6 +145,7 @@ struct rmi_device_platform_data { int reset_delay_ms; /* function handler pdata */ + struct rmi_2d_sensor_platform_data *sensor_pdata; struct rmi_f01_power_management power_management; }; -- cgit v1.2.3 From 562b42d3ee305472e1b2ea31574c59925e95fd7e Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Thu, 10 Mar 2016 15:56:58 -0800 Subject: Input: synaptics-rmi4 - add support for F30 RMI4 F30 supports input from clickpad buttons and controls LEDs located on the touchpad PCB. This patch adds support of the clickpad buttons and defers supporting LEDs for the future. Signed-off-by: Andrew Duggan Signed-off-by: Benjamin Tissoires Tested-by: Benjamin Tissoires Tested-by: Linus Walleij Tested-by: Bjorn Andersson Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index b527064bac47..ac89d1e731dc 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -101,6 +101,21 @@ struct rmi_2d_sensor_platform_data { int dmax; }; +/** + * struct rmi_f30_data - overrides defaults for a single F30 GPIOs/LED chip. + * @buttonpad - the touchpad is a buttonpad, so enable only the first actual + * button that is found. + * @trackstick_buttons - Set when the function 30 is handling the physical + * buttons of the trackstick (as a PD/2 passthrough device. + * @disable - the touchpad incorrectly reports F30 and it should be ignored. + * This is a special case which is due to misconfigured firmware. + */ +struct rmi_f30_data { + bool buttonpad; + bool trackstick_buttons; + bool disable; +}; + /** * struct rmi_f01_power - override default power management settings. * @@ -147,6 +162,7 @@ struct rmi_device_platform_data { /* function handler pdata */ struct rmi_2d_sensor_platform_data *sensor_pdata; struct rmi_f01_power_management power_management; + struct rmi_f30_data *f30_data; }; /** -- cgit v1.2.3 From 8d99758dee31ff4a72bfc35d3a7a51fe66b7bb91 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Thu, 10 Mar 2016 15:58:12 -0800 Subject: Input: synaptics-rmi4 - add SPI transport driver Add the transport driver for devices using RMI4 over SPI. Signed-off-by: Andrew Duggan Tested-by: Benjamin Tissoires Tested-by: Linus Walleij Tested-by: Bjorn Andersson Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index ac89d1e731dc..e0aca1476001 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -149,6 +149,55 @@ struct rmi_f01_power_management { u8 doze_interval; }; +/** + * struct rmi_device_platform_data_spi - provides parameters used in SPI + * communications. All Synaptics SPI products support a standard SPI + * interface; some also support what is called SPI V2 mode, depending on + * firmware and/or ASIC limitations. In V2 mode, the touch sensor can + * support shorter delays during certain operations, and these are specified + * separately from the standard mode delays. + * + * @block_delay - for standard SPI transactions consisting of both a read and + * write operation, the delay (in microseconds) between the read and write + * operations. + * @split_read_block_delay_us - for V2 SPI transactions consisting of both a + * read and write operation, the delay (in microseconds) between the read and + * write operations. + * @read_delay_us - the delay between each byte of a read operation in normal + * SPI mode. + * @write_delay_us - the delay between each byte of a write operation in normal + * SPI mode. + * @split_read_byte_delay_us - the delay between each byte of a read operation + * in V2 mode. + * @pre_delay_us - the delay before the start of a SPI transaction. This is + * typically useful in conjunction with custom chip select assertions (see + * below). + * @post_delay_us - the delay after the completion of an SPI transaction. This + * is typically useful in conjunction with custom chip select assertions (see + * below). + * @cs_assert - For systems where the SPI subsystem does not control the CS/SSB + * line, or where such control is broken, you can provide a custom routine to + * handle a GPIO as CS/SSB. This routine will be called at the beginning and + * end of each SPI transaction. The RMI SPI implementation will wait + * pre_delay_us after this routine returns before starting the SPI transfer; + * and post_delay_us after completion of the SPI transfer(s) before calling it + * with assert==FALSE. + */ +struct rmi_device_platform_data_spi { + u32 block_delay_us; + u32 split_read_block_delay_us; + u32 read_delay_us; + u32 write_delay_us; + u32 split_read_byte_delay_us; + u32 pre_delay_us; + u32 post_delay_us; + u8 bits_per_word; + u16 mode; + + void *cs_assert_data; + int (*cs_assert)(const void *cs_assert_data, const bool assert); +}; + /** * struct rmi_device_platform_data - system specific configuration info. * @@ -159,6 +208,8 @@ struct rmi_f01_power_management { struct rmi_device_platform_data { int reset_delay_ms; + struct rmi_device_platform_data_spi spi_data; + /* function handler pdata */ struct rmi_2d_sensor_platform_data *sensor_pdata; struct rmi_f01_power_management power_management; -- cgit v1.2.3 From c76d9ae415f1a80489a76ea41620c3f17383b7fb Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Thu, 10 Mar 2016 15:01:13 -0300 Subject: spi: Fix htmldocs build error due struct spi_replaced_transfers The kernel-doc has to be just before the structure definition but the one for struct spi_replaced_transfers was before a structure declaration and that confuses kernel-doc which complains with the following build error: .//include/linux/spi/spi.h:933: error: Cannot parse struct or union! Signed-off-by: Javier Martinez Canillas Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 3c02b4d06268..1fc33db4347f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -898,6 +898,10 @@ spi_max_transfer_size(struct spi_device *spi) /* SPI transfer replacement methods which make use of spi_res */ +struct spi_replaced_transfers; +typedef void (*spi_replaced_release_t)(struct spi_master *master, + struct spi_message *msg, + struct spi_replaced_transfers *res); /** * struct spi_replaced_transfers - structure describing the spi_transfer * replacements that have occurred @@ -917,10 +921,6 @@ spi_max_transfer_size(struct spi_device *spi) * if some extra allocation is requested, so alignment will be the same * as for spi_transfers */ -struct spi_replaced_transfers; -typedef void (*spi_replaced_release_t)(struct spi_master *master, - struct spi_message *msg, - struct spi_replaced_transfers *res); struct spi_replaced_transfers { spi_replaced_release_t release; void *extradata; -- cgit v1.2.3 From c7019c4d739e79d7baaa13c86dcaaedec8113d70 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 1 Mar 2016 13:49:15 -0600 Subject: crypto: ccp - CCP versioning support Future hardware may introduce new algorithms wherein the driver will need to manage resources for different versions of the cryptographic coprocessor. This precursor patch determines the version of the available device, and marks and registers algorithms accordingly. A structure is added which manages the version-specific data. Signed-off-by: Gary R Hook Acked-by: Tom Lendacky Signed-off-by: Herbert Xu --- include/linux/ccp.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ccp.h b/include/linux/ccp.h index 7f437036baa4..915af3095b39 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -33,6 +33,18 @@ struct ccp_cmd; */ int ccp_present(void); +#define CCP_VSIZE 16 +#define CCP_VMASK ((unsigned int)((1 << CCP_VSIZE) - 1)) +#define CCP_VERSION(v, r) ((unsigned int)((v << CCP_VSIZE) \ + | (r & CCP_VMASK))) + +/** + * ccp_version - get the version of the CCP + * + * Returns a positive version number, or zero if no CCP + */ +unsigned int ccp_version(void); + /** * ccp_enqueue_cmd - queue an operation for processing by the CCP * @@ -65,6 +77,11 @@ static inline int ccp_present(void) return -ENODEV; } +static inline unsigned int ccp_version(void) +{ + return 0; +} + static inline int ccp_enqueue_cmd(struct ccp_cmd *cmd) { return -ENODEV; -- cgit v1.2.3 From 4c656c13b254d598e83e586b7b4d36a2043dad85 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 8 Mar 2016 12:59:35 -0800 Subject: bridge: allow zero ageing time This fixes a regression in the bridge ageing time caused by: commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev") There are users of Linux bridge which use the feature that if ageing time is set to 0 it causes entries to never expire. See: https://www.linuxfoundation.org/collaborate/workgroups/networking/bridge For a pure software bridge, it is unnecessary for the code to have arbitrary restrictions on what values are allowable. Signed-off-by: Stephen Hemminger Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index a338a688ee4a..dcb89e3515db 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,10 +46,6 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) -/* values as per ieee8021QBridgeFdbAgingTime */ -#define BR_MIN_AGEING_TIME (10 * HZ) -#define BR_MAX_AGEING_TIME (1000000 * HZ) - #define BR_DEFAULT_AGEING_TIME (300 * HZ) extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -- cgit v1.2.3 From d9c8bea179a6906a74ea42a2a162c4d1c6d9a16b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 2 Mar 2016 21:46:50 -0600 Subject: PCI: Remove unused IORESOURCE_ROM_COPY and IORESOURCE_ROM_BIOS_COPY The IORESOURCE_ROM_COPY and IORESOURCE_ROM_BIOS_COPY bits are unused. Remove them and code that depends on them. Signed-off-by: Bjorn Helgaas --- include/linux/ioport.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 2cf16673f17a..29a6deb9f054 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -99,8 +99,6 @@ struct resource { /* PCI ROM control bits (IORESOURCE_BITS) */ #define IORESOURCE_ROM_ENABLE (1<<0) /* ROM is enabled, same as PCI_ROM_ADDRESS_ENABLE */ #define IORESOURCE_ROM_SHADOW (1<<1) /* Use RAM image, not ROM BAR */ -#define IORESOURCE_ROM_COPY (1<<2) /* ROM is alloc'd copy, resource field overlaid */ -#define IORESOURCE_ROM_BIOS_COPY (1<<3) /* ROM is BIOS copy, resource field overlaid */ /* PCI control bits. Shares IORESOURCE_BITS with above PCI ROM. */ #define IORESOURCE_PCI_FIXED (1<<4) /* Do not move resource */ -- cgit v1.2.3 From 470c3822d2ab7fadcbb1ac317ef27b31caac370e Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 10 Mar 2016 13:58:58 +0100 Subject: phy: remove documentation of removed members of phy_device structure Commit e5a03bfd873c ("phy: Add an mdio_device structure") removed addr, bus and dev member of the phy_device structure. This patch remove the documentation about those members. Signed-off-by: LABBE Corentin Reviewed-by: Andrew Lunn Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d6f3641e7933..2abd7918f64f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -327,8 +327,6 @@ struct phy_c45_device_ids { /* phy_device: An instance of a PHY * * drv: Pointer to the driver for this PHY instance - * bus: Pointer to the bus this PHY is on - * dev: driver model device structure for this PHY * phy_id: UID for this device found during discovery * c45_ids: 802.3-c45 Device Identifers if is_c45. * is_c45: Set to true if this phy uses clause 45 addressing. @@ -338,7 +336,6 @@ struct phy_c45_device_ids { * suspended: Set to true if this phy has been suspended successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. - * addr: Bus address of PHY * link_timeout: The number of timer firings to wait before the * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) -- cgit v1.2.3 From 3c17578473b9be5a6e7680a45ea97e1d56e13249 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 11 Mar 2016 18:07:32 +0100 Subject: net: add MACsec netdevice priv_flags and helper Signed-off-by: Sabrina Dubroca Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 41df0b450757..be693b34662f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1328,6 +1328,7 @@ struct net_device_ops { * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) + * @IFF_MACSEC: device is a MACsec device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1357,6 +1358,7 @@ enum netdev_priv_flags { IFF_TEAM = 1<<24, IFF_RXFH_CONFIGURED = 1<<25, IFF_PHONY_HEADROOM = 1<<26, + IFF_MACSEC = 1<<27, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1385,6 +1387,7 @@ enum netdev_priv_flags { #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED +#define IFF_MACSEC IFF_MACSEC /** * struct net_device - The DEVICE structure. @@ -4045,6 +4048,11 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, skb->mac_len = mac_len; } +static inline bool netif_is_macsec(const struct net_device *dev) +{ + return dev->priv_flags & IFF_MACSEC; +} + static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; -- cgit v1.2.3 From 949a852e46dda07caaa0ff02e181f55d24e3ebf8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 6 Mar 2016 14:20:52 -0500 Subject: namei: teach lookup_slow() to skip revalidate ... and make mountpoint_last() use it. That makes all candidates for lookup with parent locked shared go through lookup_slow(). Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index d0f25d81b46a..77d01700daf7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -31,6 +31,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 #define LOOKUP_RCU 0x0040 +#define LOOKUP_NO_REVAL 0x0080 /* * Intent data -- cgit v1.2.3 From 9d95afd5971918b1aa8db1960ba24532c2d6ec89 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 1 Mar 2016 15:35:06 -0500 Subject: kill dentry_unhash() the last user is gone Signed-off-by: Al Viro --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ae681002100a..c577923cd400 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1539,11 +1539,6 @@ extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); -/* - * VFS dentry helper functions. - */ -extern void dentry_unhash(struct dentry *dentry); - /* * VFS file helper functions. */ -- cgit v1.2.3 From 668d0cd56ef7bc71be6dd8c081007221e09d9a86 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 8 Mar 2016 12:44:17 -0500 Subject: replace d_add_unique() with saner primitive new primitive: d_exact_alias(dentry, inode). If there is an unhashed dentry with the same name/parent and given inode, rehash, grab and return it. Otherwise, return NULL. The only caller of d_add_unique() switched to d_exact_alias() + d_splice_alias(). Signed-off-by: Al Viro --- include/linux/dcache.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c4b5f4b3f8f8..bda4ec53886b 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -246,6 +246,7 @@ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); +extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); @@ -288,23 +289,6 @@ static inline void d_add(struct dentry *entry, struct inode *inode) d_rehash(entry); } -/** - * d_add_unique - add dentry to hash queues without aliasing - * @entry: dentry to add - * @inode: The inode to attach to this dentry - * - * This adds the entry to the hash queues and initializes @inode. - * The entry was actually filled in earlier during d_alloc(). - */ -static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *inode) -{ - struct dentry *res; - - res = d_instantiate_unique(entry, inode); - d_rehash(res != NULL ? res : entry); - return res; -} - extern void dentry_update_name_case(struct dentry *, struct qstr *); /* used for rename() and baskets */ -- cgit v1.2.3 From 34d0d19dc0929ccc326448737f05a8fae3d47b8a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 8 Mar 2016 21:01:03 -0500 Subject: uninline d_add() Signed-off-by: Al Viro --- include/linux/dcache.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bda4ec53886b..1c51d2d84a32 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -273,21 +273,8 @@ extern int have_submounts(struct dentry *); * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); - -/** - * d_add - add dentry to hash queues - * @entry: dentry to add - * @inode: The inode to attach to this dentry - * - * This adds the entry to the hash queues and initializes @inode. - * The entry was actually filled in earlier during d_alloc(). - */ -static inline void d_add(struct dentry *entry, struct inode *inode) -{ - d_instantiate(entry, inode); - d_rehash(entry); -} +extern void d_add(struct dentry *, struct inode *); extern void dentry_update_name_case(struct dentry *, struct qstr *); -- cgit v1.2.3 From 27f203f655a2e1dab66598a5b19afb637c587f0b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 9 Mar 2016 17:58:49 -0500 Subject: untangle fsnotify_d_instantiate() a bit First of all, don't bother calling it if inode is NULL - that makes inode argument unused. Moreover, do it *before* dropping ->d_lock, not right after that (and don't bother grabbing ->d_lock in it, of course). Signed-off-by: Al Viro --- include/linux/fsnotify.h | 9 --------- include/linux/fsnotify_backend.h | 9 ++------- 2 files changed, 2 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 7ee1774edee5..0141f257d67b 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -16,15 +16,6 @@ #include #include -/* - * fsnotify_d_instantiate - instantiate a dentry for inode - */ -static inline void fsnotify_d_instantiate(struct dentry *dentry, - struct inode *inode) -{ - __fsnotify_d_instantiate(dentry, inode); -} - /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) { diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 6b7e89f45aa4..827b249259f7 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -293,14 +293,9 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) /* * fsnotify_d_instantiate - instantiate a dentry for inode */ -static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode) +static inline void __fsnotify_d_instantiate(struct dentry *dentry) { - if (!inode) - return; - - spin_lock(&dentry->d_lock); __fsnotify_update_dcache_flags(dentry); - spin_unlock(&dentry->d_lock); } /* called from fsnotify listeners, such as fanotify or dnotify */ @@ -399,7 +394,7 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) {} -static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode) +static inline void __fsnotify_d_instantiate(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) -- cgit v1.2.3 From 70b2563b35b3edcf67819b99e560f3f0f6ce4a9f Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 21 Jan 2016 23:11:25 +0100 Subject: leds: core: fix misleading comment after workqueue removal from drivers Now that workqueues have been removed from individual drivers and were replaced with a core-internal workqueue we shouldn't encourage people to add new workqueues to drivers. Signed-off-by: Heiner Kallweit Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index bc1476fda96e..e3470e732ede 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -49,8 +49,10 @@ struct led_classdev { #define LED_SYSFS_DISABLE (1 << 22) #define LED_DEV_CAP_FLASH (1 << 23) - /* Set LED brightness level */ - /* Must not sleep, use a workqueue if needed */ + /* Set LED brightness level + * Must not sleep. Use brightness_set_blocking for drivers + * that can sleep while setting brightness. + */ void (*brightness_set)(struct led_classdev *led_cdev, enum led_brightness brightness); /* -- cgit v1.2.3 From d84d80f38f0ff4eb4becf1a3569c8e7b2c463b61 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 22 Jan 2016 21:43:48 +0100 Subject: leds: core: avoid error message when a USB LED device is unplugged When a USB LED device is unplugged the remove call chain calls led_classdev_unregister which tries to switch the LED off. As the device has been removed already this results in a ENODEV error message in dmesg. Avoid this error message by ignoring ENODEV in calls from led_classdev_unregister if the LED device is flagged as pluggable. Therefore a new flag LED_HW_PLUGGABLE was introduced which should be set by all LED drivers handling pluggable LED devices (mainly USB LED devices). Signed-off-by: Heiner Kallweit Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index e3470e732ede..f203a8f89d30 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -39,6 +39,7 @@ struct led_classdev { /* Lower 16 bits reflect status */ #define LED_SUSPENDED (1 << 0) +#define LED_UNREGISTERING (1 << 1) /* Upper 16 bits reflect control information */ #define LED_CORE_SUSPENDRESUME (1 << 16) #define LED_BLINK_ONESHOT (1 << 17) @@ -48,6 +49,7 @@ struct led_classdev { #define LED_BLINK_DISABLE (1 << 21) #define LED_SYSFS_DISABLE (1 << 22) #define LED_DEV_CAP_FLASH (1 << 23) +#define LED_HW_PLUGGABLE (1 << 24) /* Set LED brightness level * Must not sleep. Use brightness_set_blocking for drivers -- cgit v1.2.3 From c988cabe2534b6efbf0cfab6d69e18855dc3409e Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 25 Feb 2016 09:56:04 -0800 Subject: iscsi_ibft: Add prefix-len attr and display netmask The iBFT table only specifies a prefix length, not a netmask. And the netmask is pretty much pointless for IPv6. So introduce a new attribute 'prefix-len'. Some older user-space code might rely on the netmask attribute being present, so we should always display it. Changes from v1: - Combined two patches into one Changes from v2: - Cleaned up/corrected wording for patch description v3: [Put Hannes back as author] Signed-off-by: Hannes Reinecke Signed-off-by: Lee Duncan Reviewed-by: Mike Christie Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/iscsi_boot_sysfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iscsi_boot_sysfs.h b/include/linux/iscsi_boot_sysfs.h index 2a8b1659bf35..548d55395488 100644 --- a/include/linux/iscsi_boot_sysfs.h +++ b/include/linux/iscsi_boot_sysfs.h @@ -23,6 +23,7 @@ enum iscsi_boot_eth_properties_enum { ISCSI_BOOT_ETH_INDEX, ISCSI_BOOT_ETH_FLAGS, ISCSI_BOOT_ETH_IP_ADDR, + ISCSI_BOOT_ETH_PREFIX_LEN, ISCSI_BOOT_ETH_SUBNET_MASK, ISCSI_BOOT_ETH_ORIGIN, ISCSI_BOOT_ETH_GATEWAY, -- cgit v1.2.3 From f3937549a975fadec9b517b059616f08f9cb7653 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 9 Feb 2016 22:56:34 +0530 Subject: rtc: max77686: move initialisation of rtc regmap, irq chip locally To make RTC block of MAX77686/MAX77802 as independent driver, move the registration of i2c device, regmap for register access and irq_chip for interrupt support inside the RTC driver. Removed the same initialisation from MFD driver. Having this change will allow to reuse this driver for different PMIC/devices from Maxim Semiconductor if they kept same RTC IP on different PMIC. Some of examples as PMIC MAX77620, MAX20024 where same RTC IP used and hence driver for these chips will use this driver only for RTC support. Suggested-by: Krzysztof Kozlowski Signed-off-by: Laxman Dewangan Tested-by: Javier Martinez Canillas Reviewed-by: Javier Martinez Canillas Acked-by: Lee Jones Tested-by: Krzysztof Kozlowski Reviewed-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- include/linux/mfd/max77686-private.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index f5043490d67c..643dae777b43 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -437,14 +437,11 @@ enum max77686_irq { struct max77686_dev { struct device *dev; struct i2c_client *i2c; /* 0xcc / PMIC, Battery Control, and FLASH */ - struct i2c_client *rtc; /* slave addr 0x0c */ unsigned long type; struct regmap *regmap; /* regmap for mfd */ - struct regmap *rtc_regmap; /* regmap for rtc */ struct regmap_irq_chip_data *irq_data; - struct regmap_irq_chip_data *rtc_irq_data; int irq; struct mutex irqlock; -- cgit v1.2.3 From b3967067c273359c7462f4be9a887c3d1a515f49 Mon Sep 17 00:00:00 2001 From: Joshua Clayton Date: Fri, 5 Feb 2016 12:41:11 -0800 Subject: rtc: Add functions to set and read rtc offset A number of rtc devices, such as the NXP pcf2123 include a facility to adjust the clock in order to compensate for temperature or a crystal, capacitor, etc, that results in the rtc clock not running at exactly 32.768 kHz. Data sheets I have seen refer to this as a clock offset, and measure it in parts per million, however they often reference ppm to 2 digits of precision, which makes integer ppm less than ideal. We use parts per billion, which more than covers the precision needed and works nicely within 32 bits Signed-off-by: Joshua Clayton Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 3359f0422c6b..b693adac853b 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -89,6 +89,8 @@ struct rtc_class_ops { int (*set_mmss)(struct device *, unsigned long secs); int (*read_callback)(struct device *, int data); int (*alarm_irq_enable)(struct device *, unsigned int enabled); + int (*read_offset)(struct device *, long *offset); + int (*set_offset)(struct device *, long offset); }; #define RTC_DEVICE_NAME_SIZE 20 @@ -208,6 +210,8 @@ void rtc_timer_init(struct rtc_timer *timer, void (*f)(void *p), void *data); int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer, ktime_t expires, ktime_t period); void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer); +int rtc_read_offset(struct rtc_device *rtc, long *offset); +int rtc_set_offset(struct rtc_device *rtc, long offset); void rtc_timer_do_work(struct work_struct *work); static inline bool is_leap_year(unsigned int year) -- cgit v1.2.3 From f2900acea8018c4525ddaa86c7f7cd8afd3f0cc4 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Mon, 14 Mar 2016 09:39:02 +0100 Subject: bus: mvebu-mbus: provide api for obtaining IO and DRAM window information This commit enables finding appropriate mbus window and obtaining its target id and attribute for given physical address in two separate routines, both for IO and DRAM windows. This functionality is needed for Armada XP/38x Network Controller's Buffer Manager and PnC configuration. [gregory.clement@free-electrons.com: Fix size test for mvebu_mbus_get_dram_win_info] Signed-off-by: Marcin Wojtas [DRAM window information reference in LKv3.10] Signed-off-by: Evan Wang Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- include/linux/mbus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 1f7bc630d225..ea34a867caa0 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -69,6 +69,9 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(vo int mvebu_mbus_save_cpu_target(u32 *store_addr); void mvebu_mbus_get_pcie_mem_aperture(struct resource *res); void mvebu_mbus_get_pcie_io_aperture(struct resource *res); +int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr); +int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, u8 *target, + u8 *attr); int mvebu_mbus_add_window_remap_by_id(unsigned int target, unsigned int attribute, phys_addr_t base, size_t size, -- cgit v1.2.3 From a44d6eacdaf56f74fad699af7f4925a5f5ac0e7f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 14 Mar 2016 10:52:15 -0700 Subject: tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In Per RFC4898, they count segments sent/received containing a positive length data segment (that includes retransmission segments carrying data). Unlike tcpi_segs_out/in, tcpi_data_segs_out/in excludes segments carrying no data (e.g. pure ack). The patch also updates the segs_in in tcp_fastopen_add_skb() so that segs_in >= data_segs_in property is kept. Together with retransmission data, tcpi_data_segs_out gives a better signal on the rxmit rate. v6: Rebase on the latest net-next v5: Eric pointed out that checking skb->len is still needed in tcp_fastopen_add_skb() because skb can carry a FIN without data. Hence, instead of open coding segs_in and data_segs_in, tcp_segs_in() helper is used. Comment is added to the fastopen case to explain why segs_in has to be reset and tcp_segs_in() has to be called before __skb_pull(). v4: Add comment to the changes in tcp_fastopen_add_skb() and also add remark on this case in the commit message. v3: Add const modifier to the skb parameter in tcp_segs_in() v2: Rework based on recent fix by Eric: commit a9d99ce28ed3 ("tcp: fix tcpi_segs_in after connection establishment") Signed-off-by: Martin KaFai Lau Cc: Chris Rapier Cc: Eric Dumazet Cc: Marcelo Ricardo Leitner Cc: Neal Cardwell Cc: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bcbf51da4e1e..7be9b1242354 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -158,6 +158,9 @@ struct tcp_sock { u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn * total number of segments in. */ + u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. + */ u32 rcv_nxt; /* What we want to receive next */ u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ @@ -165,6 +168,9 @@ struct tcp_sock { u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut * The total number of segments sent. */ + u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. -- cgit v1.2.3 From 66cede527924543e0ff9414e6be65a923cbce10a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 Mar 2016 11:27:26 -0500 Subject: xprtrdma: Clean up unused RPCRDMA_INLINE_PAD_THRESH macro Fixes: b3221d6a53c4 ('xprtrdma: Remove logic that constructs...') Signed-off-by: Chuck Lever Reviewed-by: Sagi Grimberg Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprtrdma.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h index b7b279b54504..767190b01363 100644 --- a/include/linux/sunrpc/xprtrdma.h +++ b/include/linux/sunrpc/xprtrdma.h @@ -54,8 +54,6 @@ #define RPCRDMA_DEF_INLINE (1024) /* default inline max */ -#define RPCRDMA_INLINE_PAD_THRESH (512)/* payload threshold to pad (bytes) */ - /* Memory registration strategies, by number. * This is part of a kernel / user space API. Do not remove. */ enum rpcrdma_memreg { -- cgit v1.2.3 From d8647f2d3c381a6f543358710eb07dafa7070854 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 Mar 2016 11:28:09 -0500 Subject: rpcrdma: Add RPCRDMA_HDRLEN_ERR Error headers are shorter than either RDMA_MSG or RDMA_NOMSG. Since HDRLEN_MIN is already used in several other places that would be annoying to change, add RPCRDMA_HDRLEN_ERR for the one or two spots where the shorter length is needed. Signed-off-by: Chuck Lever Reviewed-by: Devesh Sharma Reviewed-by: Sagi Grimberg Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index f33c5a4d6fe4..8c6d23cb0cae 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -102,6 +102,7 @@ struct rpcrdma_msg { * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks */ #define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) +#define RPCRDMA_HDRLEN_ERR (sizeof(__be32) * 5) enum rpcrdma_errcode { ERR_VERS = 1, -- cgit v1.2.3 From 59aa1f9a3cce388b4d7d842d6963df11d92a407e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 Mar 2016 11:28:18 -0500 Subject: xprtrdma: Properly handle RDMA_ERROR replies These are shorter than RPCRDMA_HDRLEN_MIN, and they need to complete the waiting RPC. Signed-off-by: Chuck Lever Reviewed-by: Sagi Grimberg Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 8c6d23cb0cae..3b1ff38f0c37 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -93,6 +93,12 @@ struct rpcrdma_msg { __be32 rm_pempty[3]; /* 3 empty chunk lists */ } rm_padded; + struct { + __be32 rm_err; + __be32 rm_vers_low; + __be32 rm_vers_high; + } rm_error; + __be32 rm_chunks[0]; /* read, write and reply chunks */ } rm_body; @@ -109,11 +115,6 @@ enum rpcrdma_errcode { ERR_CHUNK = 2 }; -struct rpcrdma_err_vers { - uint32_t rdma_vers_low; /* Version range supported by peer */ - uint32_t rdma_vers_high; -}; - enum rpcrdma_proc { RDMA_MSG = 0, /* An RPC call or reply msg */ RDMA_NOMSG = 1, /* An RPC call or reply msg - separate body */ -- cgit v1.2.3 From 5bcbe0f35fb13e31fdd0b2dc9695f19ab0208207 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 12 Mar 2016 00:01:40 +0100 Subject: phy: fixed: Fix removal of phys. The fixed phys delete function simply removed the fixed phy from the internal linked list and freed the memory. It however did not unregister the associated phy device. This meant it was still possible to find the phy device on the mdio bus. Make fixed_phy_del() an internal function and add a fixed_phy_unregister() to unregisters the phy device and then uses fixed_phy_del() to free resources. Modify DSA to use this new API function, so we don't leak phys. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy_fixed.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 2400d2ea4f34..1d41ec44e39d 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -19,7 +19,7 @@ extern struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, int link_gpio, struct device_node *np); -extern void fixed_phy_del(int phy_addr); +extern void fixed_phy_unregister(struct phy_device *phydev); extern int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, struct fixed_phy_status *)); @@ -40,9 +40,8 @@ static inline struct phy_device *fixed_phy_register(unsigned int irq, { return ERR_PTR(-ENODEV); } -static inline int fixed_phy_del(int phy_addr) +static inline void fixed_phy_unregister(struct phy_device *phydev) { - return -ENODEV; } static inline int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, -- cgit v1.2.3 From 7b78f48a0443eceae435870b14e86d586f8c2a3e Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Tue, 15 Mar 2016 14:06:00 +0200 Subject: PCI: Add PCI_CLASS_SERIAL_USB_DEVICE definition PCI-SIG has defined Interface FEh for Base Class 0Ch, Sub-Class 03h as "USB Device (not host controller)". It is already being used in various USB device controller drivers for matching, so add PCI_CLASS_SERIAL_USB_DEVICE and use it. Signed-off-by: Heikki Krogerus Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 6d249d32c8b8..247da8c95860 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -110,6 +110,7 @@ #define PCI_CLASS_SERIAL_USB_OHCI 0x0c0310 #define PCI_CLASS_SERIAL_USB_EHCI 0x0c0320 #define PCI_CLASS_SERIAL_USB_XHCI 0x0c0330 +#define PCI_CLASS_SERIAL_USB_DEVICE 0x0c03fe #define PCI_CLASS_SERIAL_FIBER 0x0c04 #define PCI_CLASS_SERIAL_SMBUS 0x0c05 -- cgit v1.2.3 From fab9963a69dbd71304357dbfe4ec5345f14cebdd Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 15 Mar 2016 14:53:38 -0700 Subject: mm: fault-inject take over bootstrap kmem_cache check Remove the SLAB specific function slab_should_failslab(), by moving the check against fault-injection for the bootstrap slab, into the shared function should_failslab() (used by both SLAB and SLUB). This is a step towards sharing alloc_hook's between SLUB and SLAB. This bootstrap slab "kmem_cache" is used for allocating struct kmem_cache objects to the allocator itself. Signed-off-by: Jesper Dangaard Brouer Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 3159a7dba034..9f4956d8601c 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -62,10 +62,9 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, #endif /* CONFIG_FAULT_INJECTION */ #ifdef CONFIG_FAILSLAB -extern bool should_failslab(size_t size, gfp_t gfpflags, unsigned long flags); +extern bool should_failslab(struct kmem_cache *s, gfp_t gfpflags); #else -static inline bool should_failslab(size_t size, gfp_t gfpflags, - unsigned long flags) +static inline bool should_failslab(struct kmem_cache *s, gfp_t gfpflags) { return false; } -- cgit v1.2.3 From ca257195511d536308700548de008b51729221eb Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 15 Mar 2016 14:54:00 -0700 Subject: mm: new API kfree_bulk() for SLAB+SLUB allocators This patch introduce a new API call kfree_bulk() for bulk freeing memory objects not bound to a single kmem_cache. Christoph pointed out that it is possible to implement freeing of objects, without knowing the kmem_cache pointer as that information is available from the object's page->slab_cache. Proposing to remove the kmem_cache argument from the bulk free API. Jesper demonstrated that these extra steps per object comes at a performance cost. It is only in the case CONFIG_MEMCG_KMEM is compiled in and activated runtime that these steps are done anyhow. The extra cost is most visible for SLAB allocator, because the SLUB allocator does the page lookup (virt_to_head_page()) anyhow. Thus, the conclusion was to keep the kmem_cache free bulk API with a kmem_cache pointer, but we can still implement a kfree_bulk() API fairly easily. Simply by handling if kmem_cache_free_bulk() gets called with a kmem_cache NULL pointer. This does increase the code size a bit, but implementing a separate kfree_bulk() call would likely increase code size even more. Below benchmarks cost of alloc+free (obj size 256 bytes) on CPU i7-4790K @ 4.00GHz, no PREEMPT and CONFIG_MEMCG_KMEM=y. Code size increase for SLAB: add/remove: 0/0 grow/shrink: 1/0 up/down: 74/0 (74) function old new delta kmem_cache_free_bulk 660 734 +74 SLAB fastpath: 87 cycles(tsc) 21.814 sz - fallback - kmem_cache_free_bulk - kfree_bulk 1 - 103 cycles 25.878 ns - 41 cycles 10.498 ns - 81 cycles 20.312 ns 2 - 94 cycles 23.673 ns - 26 cycles 6.682 ns - 42 cycles 10.649 ns 3 - 92 cycles 23.181 ns - 21 cycles 5.325 ns - 39 cycles 9.950 ns 4 - 90 cycles 22.727 ns - 18 cycles 4.673 ns - 26 cycles 6.693 ns 8 - 89 cycles 22.270 ns - 14 cycles 3.664 ns - 23 cycles 5.835 ns 16 - 88 cycles 22.038 ns - 14 cycles 3.503 ns - 22 cycles 5.543 ns 30 - 89 cycles 22.284 ns - 13 cycles 3.310 ns - 20 cycles 5.197 ns 32 - 88 cycles 22.249 ns - 13 cycles 3.420 ns - 20 cycles 5.166 ns 34 - 88 cycles 22.224 ns - 14 cycles 3.643 ns - 20 cycles 5.170 ns 48 - 88 cycles 22.088 ns - 14 cycles 3.507 ns - 20 cycles 5.203 ns 64 - 88 cycles 22.063 ns - 13 cycles 3.428 ns - 20 cycles 5.152 ns 128 - 89 cycles 22.483 ns - 15 cycles 3.891 ns - 23 cycles 5.885 ns 158 - 89 cycles 22.381 ns - 15 cycles 3.779 ns - 22 cycles 5.548 ns 250 - 91 cycles 22.798 ns - 16 cycles 4.152 ns - 23 cycles 5.967 ns SLAB when enabling MEMCG_KMEM runtime: - kmemcg fastpath: 130 cycles(tsc) 32.684 ns (step:0) 1 - 148 cycles 37.220 ns - 66 cycles 16.622 ns - 66 cycles 16.583 ns 2 - 141 cycles 35.510 ns - 51 cycles 12.820 ns - 58 cycles 14.625 ns 3 - 140 cycles 35.017 ns - 37 cycles 9.326 ns - 33 cycles 8.474 ns 4 - 137 cycles 34.507 ns - 31 cycles 7.888 ns - 33 cycles 8.300 ns 8 - 140 cycles 35.069 ns - 25 cycles 6.461 ns - 25 cycles 6.436 ns 16 - 138 cycles 34.542 ns - 23 cycles 5.945 ns - 22 cycles 5.670 ns 30 - 136 cycles 34.227 ns - 22 cycles 5.502 ns - 22 cycles 5.587 ns 32 - 136 cycles 34.253 ns - 21 cycles 5.475 ns - 21 cycles 5.324 ns 34 - 136 cycles 34.254 ns - 21 cycles 5.448 ns - 20 cycles 5.194 ns 48 - 136 cycles 34.075 ns - 21 cycles 5.458 ns - 21 cycles 5.367 ns 64 - 135 cycles 33.994 ns - 21 cycles 5.350 ns - 21 cycles 5.259 ns 128 - 137 cycles 34.446 ns - 23 cycles 5.816 ns - 22 cycles 5.688 ns 158 - 137 cycles 34.379 ns - 22 cycles 5.727 ns - 22 cycles 5.602 ns 250 - 138 cycles 34.755 ns - 24 cycles 6.093 ns - 23 cycles 5.986 ns Code size increase for SLUB: function old new delta kmem_cache_free_bulk 717 799 +82 SLUB benchmark: SLUB fastpath: 46 cycles(tsc) 11.691 ns (step:0) sz - fallback - kmem_cache_free_bulk - kfree_bulk 1 - 61 cycles 15.486 ns - 53 cycles 13.364 ns - 57 cycles 14.464 ns 2 - 54 cycles 13.703 ns - 32 cycles 8.110 ns - 33 cycles 8.482 ns 3 - 53 cycles 13.272 ns - 25 cycles 6.362 ns - 27 cycles 6.947 ns 4 - 51 cycles 12.994 ns - 24 cycles 6.087 ns - 24 cycles 6.078 ns 8 - 50 cycles 12.576 ns - 21 cycles 5.354 ns - 22 cycles 5.513 ns 16 - 49 cycles 12.368 ns - 20 cycles 5.054 ns - 20 cycles 5.042 ns 30 - 49 cycles 12.273 ns - 18 cycles 4.748 ns - 19 cycles 4.758 ns 32 - 49 cycles 12.401 ns - 19 cycles 4.821 ns - 19 cycles 4.810 ns 34 - 98 cycles 24.519 ns - 24 cycles 6.154 ns - 24 cycles 6.157 ns 48 - 83 cycles 20.833 ns - 21 cycles 5.446 ns - 21 cycles 5.429 ns 64 - 75 cycles 18.891 ns - 20 cycles 5.247 ns - 20 cycles 5.238 ns 128 - 93 cycles 23.271 ns - 27 cycles 6.856 ns - 27 cycles 6.823 ns 158 - 102 cycles 25.581 ns - 30 cycles 7.714 ns - 30 cycles 7.695 ns 250 - 107 cycles 26.917 ns - 38 cycles 9.514 ns - 38 cycles 9.506 ns SLUB when enabling MEMCG_KMEM runtime: - kmemcg fastpath: 71 cycles(tsc) 17.897 ns (step:0) 1 - 85 cycles 21.484 ns - 78 cycles 19.569 ns - 75 cycles 18.938 ns 2 - 81 cycles 20.363 ns - 45 cycles 11.258 ns - 44 cycles 11.076 ns 3 - 78 cycles 19.709 ns - 33 cycles 8.354 ns - 32 cycles 8.044 ns 4 - 77 cycles 19.430 ns - 28 cycles 7.216 ns - 28 cycles 7.003 ns 8 - 101 cycles 25.288 ns - 23 cycles 5.849 ns - 23 cycles 5.787 ns 16 - 76 cycles 19.148 ns - 20 cycles 5.162 ns - 20 cycles 5.081 ns 30 - 76 cycles 19.067 ns - 19 cycles 4.868 ns - 19 cycles 4.821 ns 32 - 76 cycles 19.052 ns - 19 cycles 4.857 ns - 19 cycles 4.815 ns 34 - 121 cycles 30.291 ns - 25 cycles 6.333 ns - 25 cycles 6.268 ns 48 - 108 cycles 27.111 ns - 21 cycles 5.498 ns - 21 cycles 5.458 ns 64 - 100 cycles 25.164 ns - 20 cycles 5.242 ns - 20 cycles 5.229 ns 128 - 155 cycles 38.976 ns - 27 cycles 6.886 ns - 27 cycles 6.892 ns 158 - 132 cycles 33.034 ns - 30 cycles 7.711 ns - 30 cycles 7.728 ns 250 - 130 cycles 32.612 ns - 38 cycles 9.560 ns - 38 cycles 9.549 ns Signed-off-by: Jesper Dangaard Brouer Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 3627d5c1bc47..9d9a5bdb9b00 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -323,6 +323,15 @@ void kmem_cache_free(struct kmem_cache *, void *); void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); +/* + * Caller must not use kfree_bulk() on memory not originally allocated + * by kmalloc(), because the SLOB allocator cannot handle this. + */ +static __always_inline void kfree_bulk(size_t size, void **p) +{ + kmem_cache_free_bulk(NULL, size, p); +} + #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment; -- cgit v1.2.3 From 9f706d6820d3ea776d6b3fc0c1de9f81eb0d021b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 15 Mar 2016 14:54:03 -0700 Subject: mm: fix some spelling Fix up trivial spelling errors, noticed while reading the code. Signed-off-by: Jesper Dangaard Brouer Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- include/linux/slab.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 792c8981e633..30b02e79610e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -765,7 +765,7 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge(struct page *page, int order); /* - * helper for acessing a memcg's index. It will be used as an index in the + * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function * will return -1 when this is not a kmem-limited memcg. */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 9d9a5bdb9b00..5d49f0c60dcb 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -314,7 +314,7 @@ void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment void kmem_cache_free(struct kmem_cache *, void *); /* - * Bulk allocation and freeing operations. These are accellerated in an + * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * -- cgit v1.2.3 From 40b44137971c2e5865a78f9f7de274449983ccb5 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 15 Mar 2016 14:54:21 -0700 Subject: mm/slab: clean up DEBUG_PAGEALLOC processing code Currently, open code for checking DEBUG_PAGEALLOC cache is spread to some sites. It makes code unreadable and hard to change. This patch cleans up this code. The following patch will change the criteria for DEBUG_PAGEALLOC cache so this clean-up will help it, too. [akpm@linux-foundation.org: fix build with CONFIG_DEBUG_PAGEALLOC=n] Signed-off-by: Joonsoo Kim Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2b6e22782699..69fd6bbb8cce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2195,14 +2195,18 @@ kernel_map_pages(struct page *page, int numpages, int enable) } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); -#endif /* CONFIG_HIBERNATION */ -#else +#endif /* CONFIG_HIBERNATION */ +#else /* CONFIG_DEBUG_PAGEALLOC */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } -#endif /* CONFIG_HIBERNATION */ -#endif +#endif /* CONFIG_HIBERNATION */ +static inline bool debug_pagealloc_enabled(void) +{ + return false; +} +#endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); -- cgit v1.2.3 From d31676dfde257cb2b3e52d4e657d8ad2251e4d49 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 15 Mar 2016 14:54:24 -0700 Subject: mm/slab: alternative implementation for DEBUG_SLAB_LEAK DEBUG_SLAB_LEAK is a debug option. It's current implementation requires status buffer so we need more memory to use it. And, it cause kmem_cache initialization step more complex. To remove this extra memory usage and to simplify initialization step, this patch implement this feature with another way. When user requests to get slab object owner information, it marks that getting information is started. And then, all free objects in caches are flushed to corresponding slab page. Now, we can distinguish all freed object so we can know all allocated objects, too. After collecting slab object owner information on allocated objects, mark is checked that there is no free during the processing. If true, we can be sure that our information is correct so information is returned to user. Although this way is rather complex, it has two important benefits mentioned above. So, I think it is worth changing. There is one drawback that it takes more time to get slab object owner information but it is just a debug option so it doesn't matter at all. To help review, this patch implements new way only. Following patch will remove useless code. Signed-off-by: Joonsoo Kim Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab_def.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index cf139d3fa513..e878ba35ae91 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -60,6 +60,9 @@ struct kmem_cache { atomic_t allocmiss; atomic_t freehit; atomic_t freemiss; +#ifdef CONFIG_DEBUG_SLAB_LEAK + atomic_t store_user_clean; +#endif /* * If debugging is enabled, then the allocator can add additional -- cgit v1.2.3 From becfda68abca673d61d5cc953e8e099816db99d9 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 15 Mar 2016 14:55:06 -0700 Subject: slub: convert SLAB_DEBUG_FREE to SLAB_CONSISTENCY_CHECKS SLAB_DEBUG_FREE allows expensive consistency checks at free to be turned on or off. Expand its use to be able to turn off all consistency checks. This gives a nice speed up if you only want features such as poisoning or tracing. Credit to Mathias Krause for the original work which inspired this series Signed-off-by: Laura Abbott Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Kees Cook Cc: Mathias Krause Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 5d49f0c60dcb..e4b568738ca3 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -20,7 +20,7 @@ * Flags to pass to kmem_cache_create(). * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set. */ -#define SLAB_DEBUG_FREE 0x00000100UL /* DEBUG: Perform (expensive) checks on free */ +#define SLAB_CONSISTENCY_CHECKS 0x00000100UL /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_RED_ZONE 0x00000400UL /* DEBUG: Red zone objs in a cache */ #define SLAB_POISON 0x00000800UL /* DEBUG: Poison objects */ #define SLAB_HWCACHE_ALIGN 0x00002000UL /* Align objs on cache lines */ -- cgit v1.2.3 From d86bd1bece6fc41d59253002db5441fe960a37f6 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 15 Mar 2016 14:55:12 -0700 Subject: mm/slub: support left redzone SLUB already has a redzone debugging feature. But it is only positioned at the end of object (aka right redzone) so it cannot catch left oob. Although current object's right redzone acts as left redzone of next object, first object in a slab cannot take advantage of this effect. This patch explicitly adds a left red zone to each object to detect left oob more precisely. Background: Someone complained to me that left OOB doesn't catch even if KASAN is enabled which does page allocation debugging. That page is out of our control so it would be allocated when left OOB happens and, in this case, we can't find OOB. Moreover, SLUB debugging feature can be enabled without page allocator debugging and, in this case, we will miss that OOB. Before trying to implement, I expected that changes would be too complex, but, it doesn't look that complex to me now. Almost changes are applied to debug specific functions so I feel okay. Signed-off-by: Joonsoo Kim Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index b7e57927f521..ac5143f95ee6 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -81,6 +81,7 @@ struct kmem_cache { int reserved; /* Reserved bytes at the end of slabs */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ + int red_left_pad; /* Left redzone padding size */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ #endif -- cgit v1.2.3 From 20f6e03a40ba536dfc7c6f83dd894d994aeb39f3 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:55:42 -0700 Subject: tracepoints: move trace_print_flags definitions to tracepoint-defs.h The following patch will need to declare array of struct trace_print_flags in a header. To prevent this header from pulling in all of RCU through trace_events.h, move the struct trace_print_flags{_64} definitions to the new lightweight tracepoint-defs.h header. Signed-off-by: Vlastimil Babka Acked-by: David Rientjes Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Rasmus Villemoes Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/trace_events.h | 10 ---------- include/linux/tracepoint-defs.h | 14 ++++++++++++-- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 925730bc9fc1..705df7db4482 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -15,16 +15,6 @@ struct tracer; struct dentry; struct bpf_prog; -struct trace_print_flags { - unsigned long mask; - const char *name; -}; - -struct trace_print_flags_u64 { - unsigned long long mask; - const char *name; -}; - const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, const struct trace_print_flags *flag_array); diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index e1ee97c713bf..4ac89acb6136 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -3,13 +3,23 @@ /* * File can be included directly by headers who only want to access - * tracepoint->key to guard out of line trace calls. Otherwise - * linux/tracepoint.h should be used. + * tracepoint->key to guard out of line trace calls, or the definition of + * trace_print_flags{_u64}. Otherwise linux/tracepoint.h should be used. */ #include #include +struct trace_print_flags { + unsigned long mask; + const char *name; +}; + +struct trace_print_flags_u64 { + unsigned long long mask; + const char *name; +}; + struct tracepoint_func { void *func; void *data; -- cgit v1.2.3 From 1f7866b4aebd19e2525775083279e171b36783a4 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:55:45 -0700 Subject: mm, tracing: make show_gfp_flags() up to date The show_gfp_flags() macro provides human-friendly printing of gfp flags in tracepoints. However, it is somewhat out of date and missing several flags. This patches fills in the missing flags, and distinguishes properly between GFP_ATOMIC and __GFP_ATOMIC which were both translated to "GFP_ATOMIC". More generally, all __GFP_X flags which were previously printed as GFP_X, are now printed as __GFP_X, since ommiting the underscores results in output that doesn't actually match the source code, and can only lead to confusion. Where both variants are defined equal (e.g. _DMA and _DMA32), the variant without underscores are preferred. Also add a note in gfp.h so hopefully future changes will be synced better. __GFP_MOVABLE is defined twice in include/linux/gfp.h with different comments. Leave just the newer one, which was intended to replace the old one. Signed-off-by: Vlastimil Babka Reviewed-by: Michal Hocko Acked-by: David Rientjes Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Rasmus Villemoes Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index af1f2b24bbe4..bbe5e7fae337 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -9,6 +9,11 @@ struct vm_area_struct; +/* + * In case of changes, please don't forget to update + * include/trace/events/gfpflags.h + */ + /* Plain integer GFP bitmasks. Do not use this directly. */ #define ___GFP_DMA 0x01u #define ___GFP_HIGHMEM 0x02u @@ -48,7 +53,6 @@ struct vm_area_struct; #define __GFP_DMA ((__force gfp_t)___GFP_DMA) #define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) #define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) -#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* Page is movable */ #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) -- cgit v1.2.3 From 14e0a214d62d284ff40b1fd7d687cb66fca9fc67 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:55:49 -0700 Subject: tools, perf: make gfp_compact_table up to date When updating tracing's show_gfp_flags() I have noticed that perf's gfp_compact_table is also outdated. Fill in the missing flags and place a note in gfp.h to increase chance that future updates are synced. Convert the __GFP_X flags from "GFP_X" to "__GFP_X" strings in line with the previous patch. Signed-off-by: Vlastimil Babka Acked-by: David Rientjes Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Rasmus Villemoes Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index bbe5e7fae337..3d6d878c00f5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -11,7 +11,7 @@ struct vm_area_struct; /* * In case of changes, please don't forget to update - * include/trace/events/gfpflags.h + * include/trace/events/gfpflags.h and tools/perf/builtin-kmem.c */ /* Plain integer GFP bitmasks. Do not use this directly. */ -- cgit v1.2.3 From 420adbe9fc1a45187cfa74df9dbfd72272c4e2fa Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:55:52 -0700 Subject: mm, tracing: unify mm flags handling in tracepoints and printk In tracepoints, it's possible to print gfp flags in a human-friendly format through a macro show_gfp_flags(), which defines a translation array and passes is to __print_flags(). Since the following patch will introduce support for gfp flags printing in printk(), it would be nice to reuse the array. This is not straightforward, since __print_flags() can't simply reference an array defined in a .c file such as mm/debug.c - it has to be a macro to allow the macro magic to communicate the format to userspace tools such as trace-cmd. The solution is to create a macro __def_gfpflag_names which is used both in show_gfp_flags(), and to define the gfpflag_names[] array in mm/debug.c. On the other hand, mm/debug.c also defines translation tables for page flags and vma flags, and desire was expressed (but not implemented in this series) to use these also from tracepoints. Thus, this patch also renames the events/gfpflags.h file to events/mmflags.h and moves the table definitions there, using the same macro approach as for gfpflags. This allows translating all three kinds of mm-specific flags both in tracepoints and printk. Signed-off-by: Vlastimil Babka Reviewed-by: Michal Hocko Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Rasmus Villemoes Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 3d6d878c00f5..06546b36eb6a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -11,7 +11,7 @@ struct vm_area_struct; /* * In case of changes, please don't forget to update - * include/trace/events/gfpflags.h and tools/perf/builtin-kmem.c + * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c */ /* Plain integer GFP bitmasks. Do not use this directly. */ -- cgit v1.2.3 From 60f30350fd69a3e4d5f0f45937d3274c22565134 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:56:08 -0700 Subject: mm, page_owner: print migratetype of page and pageblock, symbolic flags The information in /sys/kernel/debug/page_owner includes the migratetype of the pageblock the page belongs to. This is also checked against the page's migratetype (as declared by gfp_flags during its allocation), and the page is reported as Fallback if its migratetype differs from the pageblock's one. t This is somewhat misleading because in fact fallback allocation is not the only reason why these two can differ. It also doesn't direcly provide the page's migratetype, although it's possible to derive that from the gfp_flags. It's arguably better to print both page and pageblock's migratetype and leave the interpretation to the consumer than to suggest fallback allocation as the only possible reason. While at it, we can print the migratetypes as string the same way as /proc/pagetypeinfo does, as some of the numeric values depend on kernel configuration. For that, this patch moves the migratetype_names array from #ifdef CONFIG_PROC_FS part of mm/vmstat.c to mm/page_alloc.c and exports it. With the new format strings for flags, we can now also provide symbolic page and gfp flags in the /sys/kernel/debug/page_owner file. This replaces the positional printing of page flags as single letters, which might have looked nicer, but was limited to a subset of flags, and required the user to remember the letters. Example page_owner entry after the patch: Page allocated via order 0, mask 0x24213ca(GFP_HIGHUSER_MOVABLE|__GFP_COLD|__GFP_NOWARN|__GFP_NORETRY) PFN 520 type Movable Block 1 type Movable Flags 0xfffff8001006c(referenced|uptodate|lru|active|mappedtodisk) [] __alloc_pages_nodemask+0x134/0x230 [] alloc_pages_current+0x88/0x120 [] __page_cache_alloc+0xe6/0x120 [] __do_page_cache_readahead+0xdc/0x240 [] ondemand_readahead+0x135/0x260 [] page_cache_sync_readahead+0x31/0x50 [] generic_file_read_iter+0x453/0x760 [] __vfs_read+0xa7/0xd0 Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7b6c2cfee390..9fc23ab550a7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -63,6 +63,9 @@ enum { MIGRATE_TYPES }; +/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ +extern char * const migratetype_names[MIGRATE_TYPES]; + #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) #else -- cgit v1.2.3 From 7dd80b8af0bcd705a9ef2fa272c082882616a499 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:56:12 -0700 Subject: mm, page_owner: convert page_owner_inited to static key CONFIG_PAGE_OWNER attempts to impose negligible runtime overhead when enabled during compilation, but not actually enabled during runtime by boot param page_owner=on. This overhead can be further reduced using the static key mechanism, which this patch does. Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index cacaabea8a09..8e2eb153c7b9 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -1,8 +1,10 @@ #ifndef __LINUX_PAGE_OWNER_H #define __LINUX_PAGE_OWNER_H +#include + #ifdef CONFIG_PAGE_OWNER -extern bool page_owner_inited; +extern struct static_key_false page_owner_inited; extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); @@ -12,27 +14,23 @@ extern gfp_t __get_page_owner_gfp(struct page *page); static inline void reset_page_owner(struct page *page, unsigned int order) { - if (likely(!page_owner_inited)) - return; - - __reset_page_owner(page, order); + if (static_branch_unlikely(&page_owner_inited)) + __reset_page_owner(page, order); } static inline void set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { - if (likely(!page_owner_inited)) - return; - - __set_page_owner(page, order, gfp_mask); + if (static_branch_unlikely(&page_owner_inited)) + __set_page_owner(page, order, gfp_mask); } static inline gfp_t get_page_owner_gfp(struct page *page) { - if (likely(!page_owner_inited)) + if (static_branch_unlikely(&page_owner_inited)) + return __get_page_owner_gfp(page); + else return 0; - - return __get_page_owner_gfp(page); } #else static inline void reset_page_owner(struct page *page, unsigned int order) -- cgit v1.2.3 From d435edca928805074dae005ab9a42d9fa60fc702 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:56:15 -0700 Subject: mm, page_owner: copy page owner info during migration The page_owner mechanism stores gfp_flags of an allocation and stack trace that lead to it. During page migration, the original information is practically replaced by the allocation of free page as the migration target. Arguably this is less useful and might lead to all the page_owner info for migratable pages gradually converge towards compaction or numa balancing migrations. It has also lead to inaccuracies such as one fixed by commit e2cfc91120fa ("mm/page_owner: set correct gfp_mask on page_owner"). This patch thus introduces copying the page_owner info during migration. However, since the fact that the page has been migrated from its original place might be useful for debugging, the next patch will introduce a way to track that information as well. Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 8e2eb153c7b9..6440daab4ef8 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -11,6 +11,7 @@ extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); extern gfp_t __get_page_owner_gfp(struct page *page); +extern void __copy_page_owner(struct page *oldpage, struct page *newpage); static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -32,6 +33,11 @@ static inline gfp_t get_page_owner_gfp(struct page *page) else return 0; } +static inline void copy_page_owner(struct page *oldpage, struct page *newpage) +{ + if (static_branch_unlikely(&page_owner_inited)) + __copy_page_owner(oldpage, newpage); +} #else static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -44,6 +50,8 @@ static inline gfp_t get_page_owner_gfp(struct page *page) { return 0; } - +static inline void copy_page_owner(struct page *oldpage, struct page *newpage) +{ +} #endif /* CONFIG_PAGE_OWNER */ #endif /* __LINUX_PAGE_OWNER_H */ -- cgit v1.2.3 From 7cd12b4abfd2f8f42414c520bbd051a5b7dc7a8c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:56:18 -0700 Subject: mm, page_owner: track and print last migrate reason During migration, page_owner info is now copied with the rest of the page, so the stacktrace leading to free page allocation during migration is overwritten. For debugging purposes, it might be however useful to know that the page has been migrated since its initial allocation. This might happen many times during the lifetime for different reasons and fully tracking this, especially with stacktraces would incur extra memory costs. As a compromise, store and print the migrate_reason of the last migration that occurred to the page. This is enough to distinguish compaction, numa balancing etc. Example page_owner entry after the patch: Page allocated via order 0, mask 0x24200ca(GFP_HIGHUSER_MOVABLE) PFN 628753 type Movable Block 1228 type Movable Flags 0x1fffff80040030(dirty|lru|swapbacked) [] __alloc_pages_nodemask+0x134/0x230 [] alloc_pages_vma+0xb5/0x250 [] shmem_alloc_page+0x61/0x90 [] shmem_getpage_gfp+0x678/0x960 [] shmem_fallocate+0x329/0x440 [] vfs_fallocate+0x140/0x230 [] SyS_fallocate+0x44/0x70 [] entry_SYSCALL_64_fastpath+0x12/0x71 Page has been migrated, last migrate reason: compaction Signed-off-by: Vlastimil Babka Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Michal Hocko Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 6 +++++- include/linux/page_ext.h | 1 + include/linux/page_owner.h | 9 +++++++++ 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index cac1c0904d5f..9b50325e4ddf 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -23,9 +23,13 @@ enum migrate_reason { MR_SYSCALL, /* also applies to cpusets */ MR_MEMPOLICY_MBIND, MR_NUMA_MISPLACED, - MR_CMA + MR_CMA, + MR_TYPES }; +/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ +extern char *migrate_reason_names[MR_TYPES]; + #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 17f118a82854..e1fe7cf5bddf 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -45,6 +45,7 @@ struct page_ext { unsigned int order; gfp_t gfp_mask; unsigned int nr_entries; + int last_migrate_reason; unsigned long trace_entries[8]; #endif }; diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 6440daab4ef8..555893bf13d7 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -12,6 +12,7 @@ extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); extern gfp_t __get_page_owner_gfp(struct page *page); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); +extern void __set_page_owner_migrate_reason(struct page *page, int reason); static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -38,6 +39,11 @@ static inline void copy_page_owner(struct page *oldpage, struct page *newpage) if (static_branch_unlikely(&page_owner_inited)) __copy_page_owner(oldpage, newpage); } +static inline void set_page_owner_migrate_reason(struct page *page, int reason) +{ + if (static_branch_unlikely(&page_owner_inited)) + __set_page_owner_migrate_reason(page, reason); +} #else static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -53,5 +59,8 @@ static inline gfp_t get_page_owner_gfp(struct page *page) static inline void copy_page_owner(struct page *oldpage, struct page *newpage) { } +static inline void set_page_owner_migrate_reason(struct page *page, int reason) +{ +} #endif /* CONFIG_PAGE_OWNER */ #endif /* __LINUX_PAGE_OWNER_H */ -- cgit v1.2.3 From 4e462112e98f9ad6dd62e160f8b14c7df5fed2fc Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:56:21 -0700 Subject: mm, page_owner: dump page owner info from dump_page() The page_owner mechanism is useful for dealing with memory leaks. By reading /sys/kernel/debug/page_owner one can determine the stack traces leading to allocations of all pages, and find e.g. a buggy driver. This information might be also potentially useful for debugging, such as the VM_BUG_ON_PAGE() calls to dump_page(). So let's print the stored info from dump_page(). Example output: page:ffffea000292f1c0 count:1 mapcount:0 mapping:ffff8800b2f6cc18 index:0x91d flags: 0x1fffff8001002c(referenced|uptodate|lru|mappedtodisk) page dumped because: VM_BUG_ON_PAGE(1) page->mem_cgroup:ffff8801392c5000 page allocated via order 0, migratetype Movable, gfp_mask 0x24213ca(GFP_HIGHUSER_MOVABLE|__GFP_COLD|__GFP_NOWARN|__GFP_NORETRY) [] __alloc_pages_nodemask+0x134/0x230 [] alloc_pages_current+0x88/0x120 [] __page_cache_alloc+0xe6/0x120 [] __do_page_cache_readahead+0xdc/0x240 [] ondemand_readahead+0x135/0x260 [] page_cache_async_readahead+0x6c/0x70 [] generic_file_read_iter+0x3f2/0x760 [] __vfs_read+0xa7/0xd0 page has been migrated, last migrate reason: compaction Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 555893bf13d7..46f1b939948c 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -13,6 +13,7 @@ extern void __set_page_owner(struct page *page, extern gfp_t __get_page_owner_gfp(struct page *page); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); +extern void __dump_page_owner(struct page *page); static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -44,6 +45,11 @@ static inline void set_page_owner_migrate_reason(struct page *page, int reason) if (static_branch_unlikely(&page_owner_inited)) __set_page_owner_migrate_reason(page, reason); } +static inline void dump_page_owner(struct page *page) +{ + if (static_branch_unlikely(&page_owner_inited)) + __dump_page_owner(page); +} #else static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -62,5 +68,8 @@ static inline void copy_page_owner(struct page *oldpage, struct page *newpage) static inline void set_page_owner_migrate_reason(struct page *page, int reason) { } +static inline void dump_page_owner(struct page *page) +{ +} #endif /* CONFIG_PAGE_OWNER */ #endif /* __LINUX_PAGE_OWNER_H */ -- cgit v1.2.3 From ff8e81163889ac4c7f59e7f7db6377d0c5d8d69c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Mar 2016 14:56:24 -0700 Subject: mm, debug: move bad flags printing to bad_page() Since bad_page() is the only user of the badflags parameter of dump_page_badflags(), we can move the code to bad_page() and simplify a bit. The dump_page_badflags() function is renamed to __dump_page() and can still be called separately from dump_page() for temporary debug prints where page_owner info is not desired. The only user-visible change is that page->mem_cgroup is printed before the bad flags. Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Sasha Levin Cc: "Kirill A. Shutemov" Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmdebug.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 053824b0a412..de7be78c6f0e 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -9,8 +9,7 @@ struct vm_area_struct; struct mm_struct; extern void dump_page(struct page *page, const char *reason); -extern void dump_page_badflags(struct page *page, const char *reason, - unsigned long badflags); +extern void __dump_page(struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); -- cgit v1.2.3 From 8823b1dbc05fab1a8bec275eeae4709257c2661d Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 15 Mar 2016 14:56:27 -0700 Subject: mm/page_poison.c: enable PAGE_POISONING as a separate option Page poisoning is currently set up as a feature if architectures don't have architecture debug page_alloc to allow unmapping of pages. It has uses apart from that though. Clearing of the pages on free provides an increase in security as it helps to limit the risk of information leaks. Allow page poisoning to be enabled as a separate option independent of kernel_map pages since the two features do separate work. Because of how hiberanation is implemented, the checks on alloc cannot occur if hibernation is enabled. The runtime alloc checks can also be enabled with an option when !HIBERNATION. Credit to Grsecurity/PaX team for inspiring this work Signed-off-by: Laura Abbott Cc: Rafael J. Wysocki Cc: "Kirill A. Shutemov" Cc: Vlastimil Babka Cc: Michal Hocko Cc: Kees Cook Cc: Mathias Krause Cc: Dave Hansen Cc: Jianyu Zhan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 69fd6bbb8cce..99dcc8f36e28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2176,6 +2176,15 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); +#ifdef CONFIG_PAGE_POISONING +extern bool page_poisoning_enabled(void); +extern void kernel_poison_pages(struct page *page, int numpages, int enable); +#else +static inline bool page_poisoning_enabled(void) { return false; } +static inline void kernel_poison_pages(struct page *page, int numpages, + int enable) { } +#endif + #ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; extern void __kernel_map_pages(struct page *page, int numpages, int enable); -- cgit v1.2.3 From 1414c7f4f7d72d138fff35f00151d15749b5beda Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 15 Mar 2016 14:56:30 -0700 Subject: mm/page_poisoning.c: allow for zero poisoning By default, page poisoning uses a poison value (0xaa) on free. If this is changed to 0, the page is not only sanitized but zeroing on alloc with __GFP_ZERO can be skipped as well. The tradeoff is that detecting corruption from the poisoning is harder to detect. This feature also cannot be used with hibernation since pages are not guaranteed to be zeroed after hibernation. Credit to Grsecurity/PaX team for inspiring this work Signed-off-by: Laura Abbott Acked-by: Rafael J. Wysocki Cc: "Kirill A. Shutemov" Cc: Vlastimil Babka Cc: Michal Hocko Cc: Kees Cook Cc: Mathias Krause Cc: Dave Hansen Cc: Jianyu Zhan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/poison.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 99dcc8f36e28..b97243d6aa49 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2179,10 +2179,12 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); +extern bool page_is_poisoned(struct page *page); #else static inline bool page_poisoning_enabled(void) { return false; } static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } +static inline bool page_is_poisoned(struct page *page) { return false; } #endif #ifdef CONFIG_DEBUG_PAGEALLOC diff --git a/include/linux/poison.h b/include/linux/poison.h index 4a27153574e2..51334edec506 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -30,7 +30,11 @@ #define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) /********** mm/debug-pagealloc.c **********/ +#ifdef CONFIG_PAGE_POISONING_ZERO +#define PAGE_POISON 0x00 +#else #define PAGE_POISON 0xaa +#endif /********** mm/page_alloc.c ************/ -- cgit v1.2.3 From 31bc3858ea3ebcc3157b3f5f0e624c5962f5a7a6 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 15 Mar 2016 14:56:48 -0700 Subject: memory-hotplug: add automatic onlining policy for the newly added memory Currently, all newly added memory blocks remain in 'offline' state unless someone onlines them, some linux distributions carry special udev rules like: SUBSYSTEM=="memory", ACTION=="add", ATTR{state}=="offline", ATTR{state}="online" to make this happen automatically. This is not a great solution for virtual machines where memory hotplug is being used to address high memory pressure situations as such onlining is slow and a userspace process doing this (udev) has a chance of being killed by the OOM killer as it will probably require to allocate some memory. Introduce default policy for the newly added memory blocks in /sys/devices/system/memory/auto_online_blocks file with two possible values: "offline" which preserves the current behavior and "online" which causes all newly added memory blocks to go online as soon as they're added. The default is "offline". Signed-off-by: Vitaly Kuznetsov Reviewed-by: Daniel Kiper Cc: Jonathan Corbet Cc: Greg Kroah-Hartman Cc: Daniel Kiper Cc: Dan Williams Cc: Tang Chen Cc: David Vrabel Acked-by: David Rientjes Cc: Naoya Horiguchi Cc: Xishi Qiu Cc: Mel Gorman Cc: "K. Y. Srinivasan" Cc: Igor Mammedov Cc: Kay Sievers Cc: Konrad Rzeszutek Wilk Cc: Boris Ostrovsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 3 +++ include/linux/memory_hotplug.h | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 8b8d8d12348e..82730adba950 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -109,6 +109,9 @@ extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); extern int register_new_memory(int, struct mem_section *); +extern int memory_block_change_state(struct memory_block *mem, + unsigned long to_state, + unsigned long from_state_req); #ifdef CONFIG_MEMORY_HOTREMOVE extern int unregister_memory_section(struct mem_section *); #endif diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 43405992d027..769d76870550 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -99,6 +99,8 @@ extern void __online_page_free(struct page *page); extern int try_online_node(int nid); +extern bool memhp_auto_online; + #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); extern int arch_remove_memory(u64 start, u64 size); @@ -267,7 +269,7 @@ static inline void remove_memory(int nid, u64 start, u64 size) {} extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); -extern int add_memory_resource(int nid, struct resource *resource); +extern int add_memory_resource(int nid, struct resource *resource, bool online); extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default, bool for_device); extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device); -- cgit v1.2.3 From 81f8c3a461d16f0355ced3d56d6d1bb5923207a1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 15 Mar 2016 14:57:04 -0700 Subject: mm: memcontrol: generalize locking for the page->mem_cgroup binding These patches tag the page cache radix tree eviction entries with the memcg an evicted page belonged to, thus making per-cgroup LRU reclaim work properly and be as adaptive to new cache workingsets as global reclaim already is. This should have been part of the original thrash detection patch series, but was deferred due to the complexity of those patches. This patch (of 5): So far the only sites that needed to exclude charge migration to stabilize page->mem_cgroup have been per-cgroup page statistics, hence the name mem_cgroup_begin_page_stat(). But per-cgroup thrash detection will add another site that needs to ensure page->mem_cgroup lifetime. Rename these locking functions to the more generic lock_page_memcg() and unlock_page_memcg(). Since charge migration is a cgroup1 feature only, we might be able to delete it at some point, and these now easy to identify locking sites along with it. Signed-off-by: Johannes Weiner Suggested-by: Vladimir Davydov Acked-by: Vladimir Davydov Cc: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 30b02e79610e..8502fd4144eb 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -429,8 +429,8 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); +struct mem_cgroup *lock_page_memcg(struct page *page); +void unlock_page_memcg(struct mem_cgroup *memcg); /** * mem_cgroup_update_page_stat - update page state statistics @@ -438,7 +438,13 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); * @idx: page state item to account * @val: number of pages (positive or negative) * - * See mem_cgroup_begin_page_stat() for locking requirements. + * Callers must use lock_page_memcg() to prevent double accounting + * when the page is concurrently being moved to another memcg: + * + * memcg = lock_page_memcg(page); + * if (TestClearPageState(page)) + * mem_cgroup_update_page_stat(memcg, state, -1); + * unlock_page_memcg(memcg); */ static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val) @@ -613,12 +619,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) +static inline struct mem_cgroup *lock_page_memcg(struct page *page) { return NULL; } -static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) +static inline void unlock_page_memcg(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 23047a96d7cfcfca1a6d026ecaec526ea4803e9e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 15 Mar 2016 14:57:16 -0700 Subject: mm: workingset: per-cgroup cache thrash detection Cache thrash detection (see a528910e12ec "mm: thrash detection-based file cache sizing" for details) currently only works on the system level, not inside cgroups. Worse, as the refaults are compared to the global number of active cache, cgroups might wrongfully get all their refaults activated when their pages are hotter than those of others. Move the refault machinery from the zone to the lruvec, and then tag eviction entries with the memcg ID. This makes the thrash detection work correctly inside cgroups. [sergey.senozhatsky@gmail.com: do not return from workingset_activation() with locked rcu and page] Signed-off-by: Johannes Weiner Signed-off-by: Sergey Senozhatsky Reviewed-by: Vladimir Davydov Cc: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 56 ++++++++++++++++++++++++++++++++++++++++------ include/linux/mmzone.h | 13 ++++++----- 2 files changed, 56 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8502fd4144eb..09b449849369 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -89,6 +89,10 @@ enum mem_cgroup_events_target { }; #ifdef CONFIG_MEMCG + +#define MEM_CGROUP_ID_SHIFT 16 +#define MEM_CGROUP_ID_MAX USHRT_MAX + struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; unsigned long events[MEMCG_NR_EVENTS]; @@ -265,6 +269,11 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; +static inline bool mem_cgroup_disabled(void) +{ + return !cgroup_subsys_enabled(memory_cgrp_subsys); +} + /** * mem_cgroup_events - count memory events against a cgroup * @memcg: the memory cgroup @@ -312,6 +321,28 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled()) + return 0; + + return memcg->css.id; +} + +/** + * mem_cgroup_from_id - look up a memcg from an id + * @id: the id to look up + * + * Caller must hold rcu_read_lock() and use css_tryget() as necessary. + */ +static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + struct cgroup_subsys_state *css; + + css = css_from_id(id, &memory_cgrp_subsys); + return mem_cgroup_from_css(css); +} + /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find @@ -353,11 +384,6 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); ino_t page_cgroup_ino(struct page *page); -static inline bool mem_cgroup_disabled(void) -{ - return !cgroup_subsys_enabled(memory_cgrp_subsys); -} - static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) @@ -502,8 +528,17 @@ void mem_cgroup_split_huge_fixup(struct page *head); #endif #else /* CONFIG_MEMCG */ + +#define MEM_CGROUP_ID_SHIFT 0 +#define MEM_CGROUP_ID_MAX 0 + struct mem_cgroup; +static inline bool mem_cgroup_disabled(void) +{ + return true; +} + static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, unsigned int nr) @@ -586,9 +621,16 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root, { } -static inline bool mem_cgroup_disabled(void) +static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { - return true; + return 0; +} + +static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(id); + /* XXX: This should always return root_mem_cgroup */ + return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9fc23ab550a7..03cbdd906f55 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -212,10 +212,12 @@ struct zone_reclaim_stat { }; struct lruvec { - struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; + struct list_head lists[NR_LRU_LISTS]; + struct zone_reclaim_stat reclaim_stat; + /* Evictions & activations on the inactive file list */ + atomic_long_t inactive_age; #ifdef CONFIG_MEMCG - struct zone *zone; + struct zone *zone; #endif }; @@ -490,9 +492,6 @@ struct zone { spinlock_t lru_lock; struct lruvec lruvec; - /* Evictions & activations on the inactive file list */ - atomic_long_t inactive_age; - /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter @@ -761,6 +760,8 @@ static inline struct zone *lruvec_zone(struct lruvec *lruvec) #endif } +extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru); + #ifdef CONFIG_HAVE_MEMORY_PRESENT void memory_present(int nid, unsigned long start, unsigned long end); #else -- cgit v1.2.3 From 6a93ca8fde3cfce0f00f02281139a377c83e8d8c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 15 Mar 2016 14:57:19 -0700 Subject: mm: migrate: do not touch page->mem_cgroup of live pages Changing a page's memcg association complicates dealing with the page, so we want to limit this as much as possible. Page migration e.g. does not have to do that. Just like page cache replacement, it can forcibly charge a replacement page, and then uncharge the old page when it gets freed. Temporarily overcharging the cgroup by a single page is not an issue in practice, and charging is so cheap nowadays that this is much preferrable to the headache of messing with live pages. The only place that still changes the page->mem_cgroup binding of live pages is when pages move along with a task to another cgroup. But that path isolates the page from the LRU, takes the page lock, and the move lock (lock_page_memcg()). That means page->mem_cgroup is always stable in callers that have the page isolated from the LRU or locked. Lighter unlocked paths, like writeback accounting, can use lock_page_memcg(). [akpm@linux-foundation.org: fix build] [vdavydov@virtuozzo.com: fix lockdep splat] Signed-off-by: Johannes Weiner Acked-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- include/linux/mm.h | 9 --------- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 09b449849369..c45ab3fb6e04 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -300,7 +300,7 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); -void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage); +void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); @@ -580,7 +580,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -static inline void mem_cgroup_replace_page(struct page *old, struct page *new) +static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } diff --git a/include/linux/mm.h b/include/linux/mm.h index b97243d6aa49..6b471d1fc8df 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -905,20 +905,11 @@ static inline struct mem_cgroup *page_memcg(struct page *page) { return page->mem_cgroup; } - -static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) -{ - page->mem_cgroup = memcg; -} #else static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } - -static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) -{ -} #endif /* -- cgit v1.2.3 From 62cccb8c8e7a3ca233f49d5e7dcb1557d25465cd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 15 Mar 2016 14:57:22 -0700 Subject: mm: simplify lock_page_memcg() Now that migration doesn't clear page->mem_cgroup of live pages anymore, it's safe to make lock_page_memcg() and the memcg stat functions take pages, and spare the callers from memcg objects. [akpm@linux-foundation.org: fix warnings] Signed-off-by: Johannes Weiner Suggested-by: Vladimir Davydov Acked-by: Vladimir Davydov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 35 +++++++++++++++++------------------ include/linux/mm.h | 5 ++--- include/linux/pagemap.h | 3 +-- 3 files changed, 20 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c45ab3fb6e04..d560c9a3cadf 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -455,42 +455,42 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -struct mem_cgroup *lock_page_memcg(struct page *page); -void unlock_page_memcg(struct mem_cgroup *memcg); +void lock_page_memcg(struct page *page); +void unlock_page_memcg(struct page *page); /** * mem_cgroup_update_page_stat - update page state statistics - * @memcg: memcg to account against + * @page: the page * @idx: page state item to account * @val: number of pages (positive or negative) * * Callers must use lock_page_memcg() to prevent double accounting * when the page is concurrently being moved to another memcg: * - * memcg = lock_page_memcg(page); + * lock_page_memcg(page); * if (TestClearPageState(page)) - * mem_cgroup_update_page_stat(memcg, state, -1); - * unlock_page_memcg(memcg); + * mem_cgroup_update_page_stat(page, state, -1); + * unlock_page_memcg(page); */ -static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, +static inline void mem_cgroup_update_page_stat(struct page *page, enum mem_cgroup_stat_index idx, int val) { VM_BUG_ON(!rcu_read_lock_held()); - if (memcg) - this_cpu_add(memcg->stat->count[idx], val); + if (page->mem_cgroup) + this_cpu_add(page->mem_cgroup->stat->count[idx], val); } -static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, +static inline void mem_cgroup_inc_page_stat(struct page *page, enum mem_cgroup_stat_index idx) { - mem_cgroup_update_page_stat(memcg, idx, 1); + mem_cgroup_update_page_stat(page, idx, 1); } -static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg, +static inline void mem_cgroup_dec_page_stat(struct page *page, enum mem_cgroup_stat_index idx) { - mem_cgroup_update_page_stat(memcg, idx, -1); + mem_cgroup_update_page_stat(page, idx, -1); } unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, @@ -661,12 +661,11 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline struct mem_cgroup *lock_page_memcg(struct page *page) +static inline void lock_page_memcg(struct page *page) { - return NULL; } -static inline void unlock_page_memcg(struct mem_cgroup *memcg) +static inline void unlock_page_memcg(struct page *page) { } @@ -692,12 +691,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) return false; } -static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, +static inline void mem_cgroup_inc_page_stat(struct page *page, enum mem_cgroup_stat_index idx) { } -static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg, +static inline void mem_cgroup_dec_page_stat(struct page *page, enum mem_cgroup_stat_index idx) { } diff --git a/include/linux/mm.h b/include/linux/mm.h index 6b471d1fc8df..a862b4f0ac24 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1291,10 +1291,9 @@ int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_dirtied(struct page *page, struct address_space *mapping, - struct mem_cgroup *memcg); +void account_page_dirtied(struct page *page, struct address_space *mapping); void account_page_cleaned(struct page *page, struct address_space *mapping, - struct mem_cgroup *memcg, struct bdi_writeback *wb); + struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); void cancel_dirty_page(struct page *page); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 92395a0a7dc5..183b15ea052b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -663,8 +663,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow, - struct mem_cgroup *memcg); +extern void __delete_from_page_cache(struct page *page, void *shadow); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* -- cgit v1.2.3 From fdf1cdb91b6ab7a8a91df68c384f36b8a0909cab Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 15 Mar 2016 14:57:25 -0700 Subject: mm: remove unnecessary uses of lock_page_memcg() There are several users that nest lock_page_memcg() inside lock_page() to prevent page->mem_cgroup from changing. But the page lock prevents pages from moving between cgroups, so that is unnecessary overhead. Remove lock_page_memcg() in contexts with locked contexts and fix the debug code in the page stat functions to be okay with the page lock. Signed-off-by: Johannes Weiner Acked-by: Vladimir Davydov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d560c9a3cadf..f0c4bec6565b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -28,6 +28,7 @@ #include #include #include +#include struct mem_cgroup; struct page; @@ -464,18 +465,19 @@ void unlock_page_memcg(struct page *page); * @idx: page state item to account * @val: number of pages (positive or negative) * - * Callers must use lock_page_memcg() to prevent double accounting - * when the page is concurrently being moved to another memcg: + * The @page must be locked or the caller must use lock_page_memcg() + * to prevent double accounting when the page is concurrently being + * moved to another memcg: * - * lock_page_memcg(page); + * lock_page(page) or lock_page_memcg(page) * if (TestClearPageState(page)) * mem_cgroup_update_page_stat(page, state, -1); - * unlock_page_memcg(page); + * unlock_page(page) or unlock_page_memcg(page) */ static inline void mem_cgroup_update_page_stat(struct page *page, enum mem_cgroup_stat_index idx, int val) { - VM_BUG_ON(!rcu_read_lock_held()); + VM_BUG_ON(!(rcu_read_lock_held() || PageLocked(page))); if (page->mem_cgroup) this_cpu_add(page->mem_cgroup->stat->count[idx], val); -- cgit v1.2.3 From 7cf91a98e607c2f935dbcc177d70011e95b8faff Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 15 Mar 2016 14:57:51 -0700 Subject: mm/compaction: speed up pageblock_pfn_to_page() when zone is contiguous There is a performance drop report due to hugepage allocation and in there half of cpu time are spent on pageblock_pfn_to_page() in compaction [1]. In that workload, compaction is triggered to make hugepage but most of pageblocks are un-available for compaction due to pageblock type and skip bit so compaction usually fails. Most costly operations in this case is to find valid pageblock while scanning whole zone range. To check if pageblock is valid to compact, valid pfn within pageblock is required and we can obtain it by calling pageblock_pfn_to_page(). This function checks whether pageblock is in a single zone and return valid pfn if possible. Problem is that we need to check it every time before scanning pageblock even if we re-visit it and this turns out to be very expensive in this workload. Although we have no way to skip this pageblock check in the system where hole exists at arbitrary position, we can use cached value for zone continuity and just do pfn_to_page() in the system where hole doesn't exist. This optimization considerably speeds up in above workload. Before vs After Max: 1096 MB/s vs 1325 MB/s Min: 635 MB/s 1015 MB/s Avg: 899 MB/s 1194 MB/s Avg is improved by roughly 30% [2]. [1]: http://www.spinics.net/lists/linux-mm/msg97378.html [2]: https://lkml.org/lkml/2015/12/9/23 [akpm@linux-foundation.org: don't forget to restore zone->contiguous on error path, per Vlastimil] Signed-off-by: Joonsoo Kim Reported-by: Aaron Lu Acked-by: Vlastimil Babka Tested-by: Aaron Lu Cc: Mel Gorman Cc: Rik van Riel Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 6 ------ include/linux/memory_hotplug.h | 3 +++ include/linux/mmzone.h | 2 ++ 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 06546b36eb6a..bb16dfeb917e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -519,13 +519,7 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT void page_alloc_init_late(void); -#else -static inline void page_alloc_init_late(void) -{ -} -#endif /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 769d76870550..adbef586e696 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -198,6 +198,9 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); +extern void set_zone_contiguous(struct zone *zone); +extern void clear_zone_contiguous(struct zone *zone); + #else /* ! CONFIG_MEMORY_HOTPLUG */ /* * Stub functions for when hotplug is off diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 03cbdd906f55..6de02ac378a0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -522,6 +522,8 @@ struct zone { bool compact_blockskip_flush; #endif + bool contiguous; + ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; -- cgit v1.2.3 From e9a7c2f1a548f34bcaa7640094201e8b29247940 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Tue, 15 Mar 2016 14:58:25 -0700 Subject: autofs4: coding style fixes Try and make the coding style completely consistent throughtout the autofs module and inline with kernel coding style recommendations. Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_dev-ioctl.h | 1 - include/linux/auto_fs.h | 10 +++------- 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/auto_dev-ioctl.h b/include/linux/auto_dev-ioctl.h index 850f39b33e74..642781612062 100644 --- a/include/linux/auto_dev-ioctl.h +++ b/include/linux/auto_dev-ioctl.h @@ -125,7 +125,6 @@ static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; in->size = sizeof(struct autofs_dev_ioctl); in->ioctlfd = -1; - return; } /* diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h index fcd704d354c4..b4066bb89083 100644 --- a/include/linux/auto_fs.h +++ b/include/linux/auto_fs.h @@ -1,14 +1,10 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * linux/include/linux/auto_fs.h - * - * Copyright 1997 Transmeta Corporation - All Rights Reserved +/* + * Copyright 1997 Transmeta Corporation - All Rights Reserved * * This file is part of the Linux kernel and is made available under * the terms of the GNU General Public License, version 2, or at your * option, any later version, incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ + */ #ifndef _LINUX_AUTO_FS_H #define _LINUX_AUTO_FS_H -- cgit v1.2.3 From 63c06227a22b098a3849c5c99e836aea161ca0d7 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Tue, 15 Mar 2016 14:58:47 -0700 Subject: autofs4: fix string.h include in auto_dev-ioctl.h Since including linux/string.h will now do the right thing remove the conditional check. Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_dev-ioctl.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/auto_dev-ioctl.h b/include/linux/auto_dev-ioctl.h index 642781612062..7caaf298f539 100644 --- a/include/linux/auto_dev-ioctl.h +++ b/include/linux/auto_dev-ioctl.h @@ -11,12 +11,7 @@ #define _LINUX_AUTO_DEV_IOCTL_H #include - -#ifdef __KERNEL__ #include -#else -#include -#endif /* __KERNEL__ */ #define AUTOFS_DEVICE_NAME "autofs" -- cgit v1.2.3 From 09c32427c9e9e861e5aeaf9e08ba0b4a3cfca917 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 8 Mar 2016 09:42:07 +0900 Subject: clk: renesas: Rename header file renesas.h This is part of an ongoing process to migrate from ARCH_SHMOBILE to ARCH_RENESAS the motivation for which being that RENESAS seems to be a more appropriate name than SHMOBILE for the majority of Renesas ARM based SoCs. Along with the above mentioned Kconfig changes it seems appropriate to also rename files. Signed-off-by: Simon Horman Acked-by: Geert Uytterhoeven Signed-off-by: Stephen Boyd --- include/linux/clk/renesas.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/clk/shmobile.h | 35 ----------------------------------- 2 files changed, 35 insertions(+), 35 deletions(-) create mode 100644 include/linux/clk/renesas.h delete mode 100644 include/linux/clk/shmobile.h (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h new file mode 100644 index 000000000000..7adfd80fbf55 --- /dev/null +++ b/include/linux/clk/renesas.h @@ -0,0 +1,35 @@ +/* + * Copyright 2013 Ideas On Board SPRL + * Copyright 2013, 2014 Horms Solutions Ltd. + * + * Contact: Laurent Pinchart + * Contact: Simon Horman + * + * 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. + */ + +#ifndef __LINUX_CLK_RENESAS_H_ +#define __LINUX_CLK_RENESAS_H_ + +#include + +struct device; +struct device_node; +struct generic_pm_domain; + +void r8a7778_clocks_init(u32 mode); +void r8a7779_clocks_init(u32 mode); +void rcar_gen2_clocks_init(u32 mode); + +#ifdef CONFIG_PM_GENERIC_DOMAINS_OF +void cpg_mstp_add_clk_domain(struct device_node *np); +int cpg_mstp_attach_dev(struct generic_pm_domain *domain, struct device *dev); +void cpg_mstp_detach_dev(struct generic_pm_domain *domain, struct device *dev); +#else +static inline void cpg_mstp_add_clk_domain(struct device_node *np) {} +#endif + +#endif diff --git a/include/linux/clk/shmobile.h b/include/linux/clk/shmobile.h deleted file mode 100644 index cb19cc1865ca..000000000000 --- a/include/linux/clk/shmobile.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Copyright 2013 Ideas On Board SPRL - * Copyright 2013, 2014 Horms Solutions Ltd. - * - * Contact: Laurent Pinchart - * Contact: Simon Horman - * - * 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. - */ - -#ifndef __LINUX_CLK_SHMOBILE_H_ -#define __LINUX_CLK_SHMOBILE_H_ - -#include - -struct device; -struct device_node; -struct generic_pm_domain; - -void r8a7778_clocks_init(u32 mode); -void r8a7779_clocks_init(u32 mode); -void rcar_gen2_clocks_init(u32 mode); - -#ifdef CONFIG_PM_GENERIC_DOMAINS_OF -void cpg_mstp_add_clk_domain(struct device_node *np); -int cpg_mstp_attach_dev(struct generic_pm_domain *domain, struct device *dev); -void cpg_mstp_detach_dev(struct generic_pm_domain *domain, struct device *dev); -#else -static inline void cpg_mstp_add_clk_domain(struct device_node *np) {} -#endif - -#endif -- cgit v1.2.3 From b45b719ee03162eb54772c30a6474d57b41b6b54 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 25 Jan 2016 09:50:11 -0600 Subject: mfd: tps65086: Add driver for the TPS65086 PMIC Add support for the TPS65912 device. It provides communication through I2C and contains the following components: - Regulators - Load switches - GPO controller Signed-off-by: Andrew F. Davis Signed-off-by: Lee Jones --- include/linux/mfd/tps65086.h | 117 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 117 insertions(+) create mode 100644 include/linux/mfd/tps65086.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps65086.h b/include/linux/mfd/tps65086.h new file mode 100644 index 000000000000..a228ae4c88d9 --- /dev/null +++ b/include/linux/mfd/tps65086.h @@ -0,0 +1,117 @@ +/* + * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis + * + * 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. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether expressed or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License version 2 for more details. + * + * Based on the TPS65912 driver + */ + +#ifndef __LINUX_MFD_TPS65086_H +#define __LINUX_MFD_TPS65086_H + +#include +#include + +/* List of registers for TPS65086 */ +#define TPS65086_DEVICEID 0x01 +#define TPS65086_IRQ 0x02 +#define TPS65086_IRQ_MASK 0x03 +#define TPS65086_PMICSTAT 0x04 +#define TPS65086_SHUTDNSRC 0x05 +#define TPS65086_BUCK1CTRL 0x20 +#define TPS65086_BUCK2CTRL 0x21 +#define TPS65086_BUCK3DECAY 0x22 +#define TPS65086_BUCK3VID 0x23 +#define TPS65086_BUCK3SLPCTRL 0x24 +#define TPS65086_BUCK4CTRL 0x25 +#define TPS65086_BUCK5CTRL 0x26 +#define TPS65086_BUCK6CTRL 0x27 +#define TPS65086_LDOA2CTRL 0x28 +#define TPS65086_LDOA3CTRL 0x29 +#define TPS65086_DISCHCTRL1 0x40 +#define TPS65086_DISCHCTRL2 0x41 +#define TPS65086_DISCHCTRL3 0x42 +#define TPS65086_PG_DELAY1 0x43 +#define TPS65086_FORCESHUTDN 0x91 +#define TPS65086_BUCK1SLPCTRL 0x92 +#define TPS65086_BUCK2SLPCTRL 0x93 +#define TPS65086_BUCK4VID 0x94 +#define TPS65086_BUCK4SLPVID 0x95 +#define TPS65086_BUCK5VID 0x96 +#define TPS65086_BUCK5SLPVID 0x97 +#define TPS65086_BUCK6VID 0x98 +#define TPS65086_BUCK6SLPVID 0x99 +#define TPS65086_LDOA2VID 0x9A +#define TPS65086_LDOA3VID 0x9B +#define TPS65086_BUCK123CTRL 0x9C +#define TPS65086_PG_DELAY2 0x9D +#define TPS65086_PIN_EN_MASK1 0x9E +#define TPS65086_PIN_EN_MASK2 0x9F +#define TPS65086_SWVTT_EN 0x9F +#define TPS65086_PIN_EN_OVR1 0xA0 +#define TPS65086_PIN_EN_OVR2 0xA1 +#define TPS65086_GPOCTRL 0xA1 +#define TPS65086_PWR_FAULT_MASK1 0xA2 +#define TPS65086_PWR_FAULT_MASK2 0xA3 +#define TPS65086_GPO1PG_CTRL1 0xA4 +#define TPS65086_GPO1PG_CTRL2 0xA5 +#define TPS65086_GPO4PG_CTRL1 0xA6 +#define TPS65086_GPO4PG_CTRL2 0xA7 +#define TPS65086_GPO2PG_CTRL1 0xA8 +#define TPS65086_GPO2PG_CTRL2 0xA9 +#define TPS65086_GPO3PG_CTRL1 0xAA +#define TPS65086_GPO3PG_CTRL2 0xAB +#define TPS65086_LDOA1CTRL 0xAE +#define TPS65086_PG_STATUS1 0xB0 +#define TPS65086_PG_STATUS2 0xB1 +#define TPS65086_PWR_FAULT_STATUS1 0xB2 +#define TPS65086_PWR_FAULT_STATUS2 0xB3 +#define TPS65086_TEMPCRIT 0xB4 +#define TPS65086_TEMPHOT 0xB5 +#define TPS65086_OC_STATUS 0xB6 + +/* IRQ Register field definitions */ +#define TPS65086_IRQ_DIETEMP_MASK BIT(0) +#define TPS65086_IRQ_SHUTDN_MASK BIT(3) +#define TPS65086_IRQ_FAULT_MASK BIT(7) + +/* DEVICEID Register field definitions */ +#define TPS65086_DEVICEID_PART_MASK GENMASK(3, 0) +#define TPS65086_DEVICEID_OTP_MASK GENMASK(5, 4) +#define TPS65086_DEVICEID_REV_MASK GENMASK(7, 6) + +/* VID Masks */ +#define BUCK_VID_MASK GENMASK(7, 1) +#define VDOA1_VID_MASK GENMASK(4, 1) +#define VDOA23_VID_MASK GENMASK(3, 0) + +/* Define the TPS65086 IRQ numbers */ +enum tps65086_irqs { + TPS65086_IRQ_DIETEMP, + TPS65086_IRQ_SHUTDN, + TPS65086_IRQ_FAULT, +}; + +/** + * struct tps65086 - state holder for the tps65086 driver + * + * Device data may be used to access the TPS65086 chip + */ +struct tps65086 { + struct device *dev; + struct regmap *regmap; + + /* IRQ Data */ + int irq; + struct regmap_irq_chip_data *irq_data; +}; + +#endif /* __LINUX_MFD_TPS65086_H */ -- cgit v1.2.3 From f4bcf5a29d57fe515b8eb6c612090376086b5f79 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 5 Feb 2016 14:32:56 +0100 Subject: mfd: cros_ec: Small kerneldoc fix s/cros_ec_register/cros_ec_query_all Signed-off-by: Tomeu Vizoso Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 494682ce4bf3..a677c2bd485c 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -245,7 +245,7 @@ int cros_ec_remove(struct cros_ec_device *ec_dev); int cros_ec_register(struct cros_ec_device *ec_dev); /** - * cros_ec_register - Query the protocol version supported by the ChromeOS EC + * cros_ec_query_all - Query the protocol version supported by the ChromeOS EC * * @ec_dev: Device to register * @return 0 if ok, -ve on error -- cgit v1.2.3 From feec4799ac4d214abd62e2bdfccb3ca9c5801d2f Mon Sep 17 00:00:00 2001 From: John Crispin Date: Wed, 27 Jan 2016 12:47:36 +0100 Subject: mfd: mt6397: int_con and int_status may vary in location MT6323 has the INT_CON and INT_STATUS located at a different position. Make the registers locations configurable. Signed-off-by: John Crispin Signed-off-by: Lee Jones --- include/linux/mfd/mt6397/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index 45b8e8aa1fbf..d678f526e498 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -60,6 +60,8 @@ struct mt6397_chip { u16 wake_mask[2]; u16 irq_masks_cur[2]; u16 irq_masks_cache[2]; + u16 int_con[2]; + u16 int_status[2]; }; #endif /* __MFD_MT6397_CORE_H__ */ -- cgit v1.2.3 From 44760cf3bf0a29da8f5cc271698c8772b8f79673 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Wed, 27 Jan 2016 12:47:38 +0100 Subject: mfd: mt6397: Add MT6323 support to MT6397 driver Signed-off-by: John Crispin Signed-off-by: Lee Jones --- include/linux/mfd/mt6323/core.h | 36 ++++ include/linux/mfd/mt6323/registers.h | 408 +++++++++++++++++++++++++++++++++++ 2 files changed, 444 insertions(+) create mode 100644 include/linux/mfd/mt6323/core.h create mode 100644 include/linux/mfd/mt6323/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6323/core.h b/include/linux/mfd/mt6323/core.h new file mode 100644 index 000000000000..06d0ec3b1f8f --- /dev/null +++ b/include/linux/mfd/mt6323/core.h @@ -0,0 +1,36 @@ +/* + * Copyright (c) 2016 Chen Zhong + * + * 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 __MFD_MT6323_CORE_H__ +#define __MFD_MT6323_CORE_H__ + +enum MT6323_IRQ_STATUS_numbers { + MT6323_IRQ_STATUS_SPKL_AB = 0, + MT6323_IRQ_STATUS_SPKL, + MT6323_IRQ_STATUS_BAT_L, + MT6323_IRQ_STATUS_BAT_H, + MT6323_IRQ_STATUS_WATCHDOG, + MT6323_IRQ_STATUS_PWRKEY, + MT6323_IRQ_STATUS_THR_L, + MT6323_IRQ_STATUS_THR_H, + MT6323_IRQ_STATUS_VBATON_UNDET, + MT6323_IRQ_STATUS_BVALID_DET, + MT6323_IRQ_STATUS_CHRDET, + MT6323_IRQ_STATUS_OV, + MT6323_IRQ_STATUS_LDO = 16, + MT6323_IRQ_STATUS_FCHRKEY, + MT6323_IRQ_STATUS_ACCDET, + MT6323_IRQ_STATUS_AUDIO, + MT6323_IRQ_STATUS_RTC, + MT6323_IRQ_STATUS_VPROC, + MT6323_IRQ_STATUS_VSYS, + MT6323_IRQ_STATUS_VPA, + MT6323_IRQ_STATUS_NR, +}; + +#endif /* __MFD_MT6323_CORE_H__ */ diff --git a/include/linux/mfd/mt6323/registers.h b/include/linux/mfd/mt6323/registers.h new file mode 100644 index 000000000000..160f3c0e2589 --- /dev/null +++ b/include/linux/mfd/mt6323/registers.h @@ -0,0 +1,408 @@ +/* + * Copyright (c) 2016 Chen Zhong + * + * 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 __MFD_MT6323_REGISTERS_H__ +#define __MFD_MT6323_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6323_CHR_CON0 0x0000 +#define MT6323_CHR_CON1 0x0002 +#define MT6323_CHR_CON2 0x0004 +#define MT6323_CHR_CON3 0x0006 +#define MT6323_CHR_CON4 0x0008 +#define MT6323_CHR_CON5 0x000A +#define MT6323_CHR_CON6 0x000C +#define MT6323_CHR_CON7 0x000E +#define MT6323_CHR_CON8 0x0010 +#define MT6323_CHR_CON9 0x0012 +#define MT6323_CHR_CON10 0x0014 +#define MT6323_CHR_CON11 0x0016 +#define MT6323_CHR_CON12 0x0018 +#define MT6323_CHR_CON13 0x001A +#define MT6323_CHR_CON14 0x001C +#define MT6323_CHR_CON15 0x001E +#define MT6323_CHR_CON16 0x0020 +#define MT6323_CHR_CON17 0x0022 +#define MT6323_CHR_CON18 0x0024 +#define MT6323_CHR_CON19 0x0026 +#define MT6323_CHR_CON20 0x0028 +#define MT6323_CHR_CON21 0x002A +#define MT6323_CHR_CON22 0x002C +#define MT6323_CHR_CON23 0x002E +#define MT6323_CHR_CON24 0x0030 +#define MT6323_CHR_CON25 0x0032 +#define MT6323_CHR_CON26 0x0034 +#define MT6323_CHR_CON27 0x0036 +#define MT6323_CHR_CON28 0x0038 +#define MT6323_CHR_CON29 0x003A +#define MT6323_STRUP_CON0 0x003C +#define MT6323_STRUP_CON2 0x003E +#define MT6323_STRUP_CON3 0x0040 +#define MT6323_STRUP_CON4 0x0042 +#define MT6323_STRUP_CON5 0x0044 +#define MT6323_STRUP_CON6 0x0046 +#define MT6323_STRUP_CON7 0x0048 +#define MT6323_STRUP_CON8 0x004A +#define MT6323_STRUP_CON9 0x004C +#define MT6323_STRUP_CON10 0x004E +#define MT6323_STRUP_CON11 0x0050 +#define MT6323_SPK_CON0 0x0052 +#define MT6323_SPK_CON1 0x0054 +#define MT6323_SPK_CON2 0x0056 +#define MT6323_SPK_CON6 0x005E +#define MT6323_SPK_CON7 0x0060 +#define MT6323_SPK_CON8 0x0062 +#define MT6323_SPK_CON9 0x0064 +#define MT6323_SPK_CON10 0x0066 +#define MT6323_SPK_CON11 0x0068 +#define MT6323_SPK_CON12 0x006A +#define MT6323_CID 0x0100 +#define MT6323_TOP_CKPDN0 0x0102 +#define MT6323_TOP_CKPDN0_SET 0x0104 +#define MT6323_TOP_CKPDN0_CLR 0x0106 +#define MT6323_TOP_CKPDN1 0x0108 +#define MT6323_TOP_CKPDN1_SET 0x010A +#define MT6323_TOP_CKPDN1_CLR 0x010C +#define MT6323_TOP_CKPDN2 0x010E +#define MT6323_TOP_CKPDN2_SET 0x0110 +#define MT6323_TOP_CKPDN2_CLR 0x0112 +#define MT6323_TOP_RST_CON 0x0114 +#define MT6323_TOP_RST_CON_SET 0x0116 +#define MT6323_TOP_RST_CON_CLR 0x0118 +#define MT6323_TOP_RST_MISC 0x011A +#define MT6323_TOP_RST_MISC_SET 0x011C +#define MT6323_TOP_RST_MISC_CLR 0x011E +#define MT6323_TOP_CKCON0 0x0120 +#define MT6323_TOP_CKCON0_SET 0x0122 +#define MT6323_TOP_CKCON0_CLR 0x0124 +#define MT6323_TOP_CKCON1 0x0126 +#define MT6323_TOP_CKCON1_SET 0x0128 +#define MT6323_TOP_CKCON1_CLR 0x012A +#define MT6323_TOP_CKTST0 0x012C +#define MT6323_TOP_CKTST1 0x012E +#define MT6323_TOP_CKTST2 0x0130 +#define MT6323_TEST_OUT 0x0132 +#define MT6323_TEST_CON0 0x0134 +#define MT6323_TEST_CON1 0x0136 +#define MT6323_EN_STATUS0 0x0138 +#define MT6323_EN_STATUS1 0x013A +#define MT6323_OCSTATUS0 0x013C +#define MT6323_OCSTATUS1 0x013E +#define MT6323_PGSTATUS 0x0140 +#define MT6323_CHRSTATUS 0x0142 +#define MT6323_TDSEL_CON 0x0144 +#define MT6323_RDSEL_CON 0x0146 +#define MT6323_SMT_CON0 0x0148 +#define MT6323_SMT_CON1 0x014A +#define MT6323_SMT_CON2 0x014C +#define MT6323_SMT_CON3 0x014E +#define MT6323_SMT_CON4 0x0150 +#define MT6323_DRV_CON0 0x0152 +#define MT6323_DRV_CON1 0x0154 +#define MT6323_DRV_CON2 0x0156 +#define MT6323_DRV_CON3 0x0158 +#define MT6323_DRV_CON4 0x015A +#define MT6323_SIMLS1_CON 0x015C +#define MT6323_SIMLS2_CON 0x015E +#define MT6323_INT_CON0 0x0160 +#define MT6323_INT_CON0_SET 0x0162 +#define MT6323_INT_CON0_CLR 0x0164 +#define MT6323_INT_CON1 0x0166 +#define MT6323_INT_CON1_SET 0x0168 +#define MT6323_INT_CON1_CLR 0x016A +#define MT6323_INT_MISC_CON 0x016C +#define MT6323_INT_MISC_CON_SET 0x016E +#define MT6323_INT_MISC_CON_CLR 0x0170 +#define MT6323_INT_STATUS0 0x0172 +#define MT6323_INT_STATUS1 0x0174 +#define MT6323_OC_GEAR_0 0x0176 +#define MT6323_OC_GEAR_1 0x0178 +#define MT6323_OC_GEAR_2 0x017A +#define MT6323_OC_CTL_VPROC 0x017C +#define MT6323_OC_CTL_VSYS 0x017E +#define MT6323_OC_CTL_VPA 0x0180 +#define MT6323_FQMTR_CON0 0x0182 +#define MT6323_FQMTR_CON1 0x0184 +#define MT6323_FQMTR_CON2 0x0186 +#define MT6323_RG_SPI_CON 0x0188 +#define MT6323_DEW_DIO_EN 0x018A +#define MT6323_DEW_READ_TEST 0x018C +#define MT6323_DEW_WRITE_TEST 0x018E +#define MT6323_DEW_CRC_SWRST 0x0190 +#define MT6323_DEW_CRC_EN 0x0192 +#define MT6323_DEW_CRC_VAL 0x0194 +#define MT6323_DEW_DBG_MON_SEL 0x0196 +#define MT6323_DEW_CIPHER_KEY_SEL 0x0198 +#define MT6323_DEW_CIPHER_IV_SEL 0x019A +#define MT6323_DEW_CIPHER_EN 0x019C +#define MT6323_DEW_CIPHER_RDY 0x019E +#define MT6323_DEW_CIPHER_MODE 0x01A0 +#define MT6323_DEW_CIPHER_SWRST 0x01A2 +#define MT6323_DEW_RDDMY_NO 0x01A4 +#define MT6323_DEW_RDATA_DLY_SEL 0x01A6 +#define MT6323_BUCK_CON0 0x0200 +#define MT6323_BUCK_CON1 0x0202 +#define MT6323_BUCK_CON2 0x0204 +#define MT6323_BUCK_CON3 0x0206 +#define MT6323_BUCK_CON4 0x0208 +#define MT6323_BUCK_CON5 0x020A +#define MT6323_VPROC_CON0 0x020C +#define MT6323_VPROC_CON1 0x020E +#define MT6323_VPROC_CON2 0x0210 +#define MT6323_VPROC_CON3 0x0212 +#define MT6323_VPROC_CON4 0x0214 +#define MT6323_VPROC_CON5 0x0216 +#define MT6323_VPROC_CON7 0x021A +#define MT6323_VPROC_CON8 0x021C +#define MT6323_VPROC_CON9 0x021E +#define MT6323_VPROC_CON10 0x0220 +#define MT6323_VPROC_CON11 0x0222 +#define MT6323_VPROC_CON12 0x0224 +#define MT6323_VPROC_CON13 0x0226 +#define MT6323_VPROC_CON14 0x0228 +#define MT6323_VPROC_CON15 0x022A +#define MT6323_VPROC_CON18 0x0230 +#define MT6323_VSYS_CON0 0x0232 +#define MT6323_VSYS_CON1 0x0234 +#define MT6323_VSYS_CON2 0x0236 +#define MT6323_VSYS_CON3 0x0238 +#define MT6323_VSYS_CON4 0x023A +#define MT6323_VSYS_CON5 0x023C +#define MT6323_VSYS_CON7 0x0240 +#define MT6323_VSYS_CON8 0x0242 +#define MT6323_VSYS_CON9 0x0244 +#define MT6323_VSYS_CON10 0x0246 +#define MT6323_VSYS_CON11 0x0248 +#define MT6323_VSYS_CON12 0x024A +#define MT6323_VSYS_CON13 0x024C +#define MT6323_VSYS_CON14 0x024E +#define MT6323_VSYS_CON15 0x0250 +#define MT6323_VSYS_CON18 0x0256 +#define MT6323_VPA_CON0 0x0300 +#define MT6323_VPA_CON1 0x0302 +#define MT6323_VPA_CON2 0x0304 +#define MT6323_VPA_CON3 0x0306 +#define MT6323_VPA_CON4 0x0308 +#define MT6323_VPA_CON5 0x030A +#define MT6323_VPA_CON7 0x030E +#define MT6323_VPA_CON8 0x0310 +#define MT6323_VPA_CON9 0x0312 +#define MT6323_VPA_CON10 0x0314 +#define MT6323_VPA_CON11 0x0316 +#define MT6323_VPA_CON12 0x0318 +#define MT6323_VPA_CON14 0x031C +#define MT6323_VPA_CON16 0x0320 +#define MT6323_VPA_CON17 0x0322 +#define MT6323_VPA_CON18 0x0324 +#define MT6323_VPA_CON19 0x0326 +#define MT6323_VPA_CON20 0x0328 +#define MT6323_BUCK_K_CON0 0x032A +#define MT6323_BUCK_K_CON1 0x032C +#define MT6323_BUCK_K_CON2 0x032E +#define MT6323_ISINK0_CON0 0x0330 +#define MT6323_ISINK0_CON1 0x0332 +#define MT6323_ISINK0_CON2 0x0334 +#define MT6323_ISINK0_CON3 0x0336 +#define MT6323_ISINK1_CON0 0x0338 +#define MT6323_ISINK1_CON1 0x033A +#define MT6323_ISINK1_CON2 0x033C +#define MT6323_ISINK1_CON3 0x033E +#define MT6323_ISINK2_CON0 0x0340 +#define MT6323_ISINK2_CON1 0x0342 +#define MT6323_ISINK2_CON2 0x0344 +#define MT6323_ISINK2_CON3 0x0346 +#define MT6323_ISINK3_CON0 0x0348 +#define MT6323_ISINK3_CON1 0x034A +#define MT6323_ISINK3_CON2 0x034C +#define MT6323_ISINK3_CON3 0x034E +#define MT6323_ISINK_ANA0 0x0350 +#define MT6323_ISINK_ANA1 0x0352 +#define MT6323_ISINK_PHASE_DLY 0x0354 +#define MT6323_ISINK_EN_CTRL 0x0356 +#define MT6323_ANALDO_CON0 0x0400 +#define MT6323_ANALDO_CON1 0x0402 +#define MT6323_ANALDO_CON2 0x0404 +#define MT6323_ANALDO_CON3 0x0406 +#define MT6323_ANALDO_CON4 0x0408 +#define MT6323_ANALDO_CON5 0x040A +#define MT6323_ANALDO_CON6 0x040C +#define MT6323_ANALDO_CON7 0x040E +#define MT6323_ANALDO_CON8 0x0410 +#define MT6323_ANALDO_CON10 0x0412 +#define MT6323_ANALDO_CON15 0x0414 +#define MT6323_ANALDO_CON16 0x0416 +#define MT6323_ANALDO_CON17 0x0418 +#define MT6323_ANALDO_CON18 0x041A +#define MT6323_ANALDO_CON19 0x041C +#define MT6323_ANALDO_CON20 0x041E +#define MT6323_ANALDO_CON21 0x0420 +#define MT6323_DIGLDO_CON0 0x0500 +#define MT6323_DIGLDO_CON2 0x0502 +#define MT6323_DIGLDO_CON3 0x0504 +#define MT6323_DIGLDO_CON5 0x0506 +#define MT6323_DIGLDO_CON6 0x0508 +#define MT6323_DIGLDO_CON7 0x050A +#define MT6323_DIGLDO_CON8 0x050C +#define MT6323_DIGLDO_CON9 0x050E +#define MT6323_DIGLDO_CON10 0x0510 +#define MT6323_DIGLDO_CON11 0x0512 +#define MT6323_DIGLDO_CON12 0x0514 +#define MT6323_DIGLDO_CON13 0x0516 +#define MT6323_DIGLDO_CON14 0x0518 +#define MT6323_DIGLDO_CON15 0x051A +#define MT6323_DIGLDO_CON16 0x051C +#define MT6323_DIGLDO_CON17 0x051E +#define MT6323_DIGLDO_CON18 0x0520 +#define MT6323_DIGLDO_CON19 0x0522 +#define MT6323_DIGLDO_CON20 0x0524 +#define MT6323_DIGLDO_CON21 0x0526 +#define MT6323_DIGLDO_CON23 0x0528 +#define MT6323_DIGLDO_CON24 0x052A +#define MT6323_DIGLDO_CON26 0x052C +#define MT6323_DIGLDO_CON27 0x052E +#define MT6323_DIGLDO_CON28 0x0530 +#define MT6323_DIGLDO_CON29 0x0532 +#define MT6323_DIGLDO_CON30 0x0534 +#define MT6323_DIGLDO_CON31 0x0536 +#define MT6323_DIGLDO_CON32 0x0538 +#define MT6323_DIGLDO_CON33 0x053A +#define MT6323_DIGLDO_CON34 0x053C +#define MT6323_DIGLDO_CON35 0x053E +#define MT6323_DIGLDO_CON36 0x0540 +#define MT6323_DIGLDO_CON39 0x0542 +#define MT6323_DIGLDO_CON40 0x0544 +#define MT6323_DIGLDO_CON41 0x0546 +#define MT6323_DIGLDO_CON42 0x0548 +#define MT6323_DIGLDO_CON43 0x054A +#define MT6323_DIGLDO_CON44 0x054C +#define MT6323_DIGLDO_CON45 0x054E +#define MT6323_DIGLDO_CON46 0x0550 +#define MT6323_DIGLDO_CON47 0x0552 +#define MT6323_DIGLDO_CON48 0x0554 +#define MT6323_DIGLDO_CON49 0x0556 +#define MT6323_DIGLDO_CON50 0x0558 +#define MT6323_DIGLDO_CON51 0x055A +#define MT6323_DIGLDO_CON52 0x055C +#define MT6323_DIGLDO_CON53 0x055E +#define MT6323_DIGLDO_CON54 0x0560 +#define MT6323_EFUSE_CON0 0x0600 +#define MT6323_EFUSE_CON1 0x0602 +#define MT6323_EFUSE_CON2 0x0604 +#define MT6323_EFUSE_CON3 0x0606 +#define MT6323_EFUSE_CON4 0x0608 +#define MT6323_EFUSE_CON5 0x060A +#define MT6323_EFUSE_CON6 0x060C +#define MT6323_EFUSE_VAL_0_15 0x060E +#define MT6323_EFUSE_VAL_16_31 0x0610 +#define MT6323_EFUSE_VAL_32_47 0x0612 +#define MT6323_EFUSE_VAL_48_63 0x0614 +#define MT6323_EFUSE_VAL_64_79 0x0616 +#define MT6323_EFUSE_VAL_80_95 0x0618 +#define MT6323_EFUSE_VAL_96_111 0x061A +#define MT6323_EFUSE_VAL_112_127 0x061C +#define MT6323_EFUSE_VAL_128_143 0x061E +#define MT6323_EFUSE_VAL_144_159 0x0620 +#define MT6323_EFUSE_VAL_160_175 0x0622 +#define MT6323_EFUSE_VAL_176_191 0x0624 +#define MT6323_EFUSE_DOUT_0_15 0x0626 +#define MT6323_EFUSE_DOUT_16_31 0x0628 +#define MT6323_EFUSE_DOUT_32_47 0x062A +#define MT6323_EFUSE_DOUT_48_63 0x062C +#define MT6323_EFUSE_DOUT_64_79 0x062E +#define MT6323_EFUSE_DOUT_80_95 0x0630 +#define MT6323_EFUSE_DOUT_96_111 0x0632 +#define MT6323_EFUSE_DOUT_112_127 0x0634 +#define MT6323_EFUSE_DOUT_128_143 0x0636 +#define MT6323_EFUSE_DOUT_144_159 0x0638 +#define MT6323_EFUSE_DOUT_160_175 0x063A +#define MT6323_EFUSE_DOUT_176_191 0x063C +#define MT6323_EFUSE_CON7 0x063E +#define MT6323_EFUSE_CON8 0x0640 +#define MT6323_EFUSE_CON9 0x0642 +#define MT6323_RTC_MIX_CON0 0x0644 +#define MT6323_RTC_MIX_CON1 0x0646 +#define MT6323_AUDTOP_CON0 0x0700 +#define MT6323_AUDTOP_CON1 0x0702 +#define MT6323_AUDTOP_CON2 0x0704 +#define MT6323_AUDTOP_CON3 0x0706 +#define MT6323_AUDTOP_CON4 0x0708 +#define MT6323_AUDTOP_CON5 0x070A +#define MT6323_AUDTOP_CON6 0x070C +#define MT6323_AUDTOP_CON7 0x070E +#define MT6323_AUDTOP_CON8 0x0710 +#define MT6323_AUDTOP_CON9 0x0712 +#define MT6323_AUXADC_ADC0 0x0714 +#define MT6323_AUXADC_ADC1 0x0716 +#define MT6323_AUXADC_ADC2 0x0718 +#define MT6323_AUXADC_ADC3 0x071A +#define MT6323_AUXADC_ADC4 0x071C +#define MT6323_AUXADC_ADC5 0x071E +#define MT6323_AUXADC_ADC6 0x0720 +#define MT6323_AUXADC_ADC7 0x0722 +#define MT6323_AUXADC_ADC8 0x0724 +#define MT6323_AUXADC_ADC9 0x0726 +#define MT6323_AUXADC_ADC10 0x0728 +#define MT6323_AUXADC_ADC11 0x072A +#define MT6323_AUXADC_ADC12 0x072C +#define MT6323_AUXADC_ADC13 0x072E +#define MT6323_AUXADC_ADC14 0x0730 +#define MT6323_AUXADC_ADC15 0x0732 +#define MT6323_AUXADC_ADC16 0x0734 +#define MT6323_AUXADC_ADC17 0x0736 +#define MT6323_AUXADC_ADC18 0x0738 +#define MT6323_AUXADC_ADC19 0x073A +#define MT6323_AUXADC_ADC20 0x073C +#define MT6323_AUXADC_RSV1 0x073E +#define MT6323_AUXADC_RSV2 0x0740 +#define MT6323_AUXADC_CON0 0x0742 +#define MT6323_AUXADC_CON1 0x0744 +#define MT6323_AUXADC_CON2 0x0746 +#define MT6323_AUXADC_CON3 0x0748 +#define MT6323_AUXADC_CON4 0x074A +#define MT6323_AUXADC_CON5 0x074C +#define MT6323_AUXADC_CON6 0x074E +#define MT6323_AUXADC_CON7 0x0750 +#define MT6323_AUXADC_CON8 0x0752 +#define MT6323_AUXADC_CON9 0x0754 +#define MT6323_AUXADC_CON10 0x0756 +#define MT6323_AUXADC_CON11 0x0758 +#define MT6323_AUXADC_CON12 0x075A +#define MT6323_AUXADC_CON13 0x075C +#define MT6323_AUXADC_CON14 0x075E +#define MT6323_AUXADC_CON15 0x0760 +#define MT6323_AUXADC_CON16 0x0762 +#define MT6323_AUXADC_CON17 0x0764 +#define MT6323_AUXADC_CON18 0x0766 +#define MT6323_AUXADC_CON19 0x0768 +#define MT6323_AUXADC_CON20 0x076A +#define MT6323_AUXADC_CON21 0x076C +#define MT6323_AUXADC_CON22 0x076E +#define MT6323_AUXADC_CON23 0x0770 +#define MT6323_AUXADC_CON24 0x0772 +#define MT6323_AUXADC_CON25 0x0774 +#define MT6323_AUXADC_CON26 0x0776 +#define MT6323_AUXADC_CON27 0x0778 +#define MT6323_ACCDET_CON0 0x077A +#define MT6323_ACCDET_CON1 0x077C +#define MT6323_ACCDET_CON2 0x077E +#define MT6323_ACCDET_CON3 0x0780 +#define MT6323_ACCDET_CON4 0x0782 +#define MT6323_ACCDET_CON5 0x0784 +#define MT6323_ACCDET_CON6 0x0786 +#define MT6323_ACCDET_CON7 0x0788 +#define MT6323_ACCDET_CON8 0x078A +#define MT6323_ACCDET_CON9 0x078C +#define MT6323_ACCDET_CON10 0x078E +#define MT6323_ACCDET_CON11 0x0790 +#define MT6323_ACCDET_CON12 0x0792 +#define MT6323_ACCDET_CON13 0x0794 +#define MT6323_ACCDET_CON14 0x0796 +#define MT6323_ACCDET_CON15 0x0798 +#define MT6323_ACCDET_CON16 0x079A + +#endif /* __MFD_MT6323_REGISTERS_H__ */ -- cgit v1.2.3 From a862dc3ea793256a1364991f52e68198a2c5f27d Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Sun, 31 Jan 2016 22:58:41 +0100 Subject: mfd: rc5t583: Set regmap config reg counts properly Regmap config max_register field should contain number of device last register, however num_reg_defaults_raw field should be set to register count instead (usually one register more than max_register). rc5t583 driver had both of these fields set to the same value, fix this by introducing separate defines for max register number and total count of registers. Signed-off-by: Maciej S. Szmigiero Signed-off-by: Lee Jones --- include/linux/mfd/rc5t583.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rc5t583.h b/include/linux/mfd/rc5t583.h index fd413ccab915..8d0a392e0a7f 100644 --- a/include/linux/mfd/rc5t583.h +++ b/include/linux/mfd/rc5t583.h @@ -28,8 +28,6 @@ #include #include -#define RC5T583_MAX_REGS 0xF8 - /* Maximum number of main interrupts */ #define MAX_MAIN_INTERRUPT 5 #define RC5T583_MAX_GPEDGE_REG 2 @@ -169,6 +167,9 @@ #define RC5T583_RTC_AY_MONTH 0xF3 #define RC5T583_RTC_AY_YEAR 0xF4 +#define RC5T583_MAX_REG 0xF7 +#define RC5T583_NUM_REGS (RC5T583_MAX_REG + 1) + /* RICOH_RC5T583 IRQ definitions */ enum { RC5T583_IRQ_ONKEY, -- cgit v1.2.3 From e9b7ba7954fa8df6e021ee4bef084ed10eba2c2b Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Sun, 31 Jan 2016 22:56:59 +0100 Subject: mfd: as3711: Set regmap config reg counts properly Regmap config max_register field should contain number of device last register, however num_reg_defaults_raw field should be set to register count instead (usually one register more than max_register). as3711 driver had both of these fields set to the same value, fix this by introducing separate defines for max register number and total count of registers. Signed-off-by: Maciej S. Szmigiero Signed-off-by: Lee Jones --- include/linux/mfd/as3711.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/as3711.h b/include/linux/mfd/as3711.h index 38452ce1e892..34cc85864be5 100644 --- a/include/linux/mfd/as3711.h +++ b/include/linux/mfd/as3711.h @@ -51,7 +51,8 @@ #define AS3711_ASIC_ID_1 0x90 #define AS3711_ASIC_ID_2 0x91 -#define AS3711_MAX_REGS 0x92 +#define AS3711_MAX_REG AS3711_ASIC_ID_2 +#define AS3711_NUM_REGS (AS3711_MAX_REG + 1) /* Regulators */ enum { -- cgit v1.2.3 From 8c037e0c8eaa7dcb3a190b9be841ee81edb865ff Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 29 Jan 2016 09:42:19 +0100 Subject: mfd: syscon: Return ENOTSUPP instead of ENOSYS when disabled When CONFIG_MFD_SYSCON is disabled, have the function stubs return ENOTSUPP to indicate the syscon functionality is not available. There are currently no callers that depend on the ENOSYS return value. This patchfixes a checkpatch warning: WARNING: ENOSYS means 'invalid syscall nr' and nothing else Signed-off-by: Philipp Zabel Signed-off-by: Lee Jones --- include/linux/mfd/syscon.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 75e543b78f53..1088149be0c9 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -29,24 +29,24 @@ extern struct regmap *syscon_regmap_lookup_by_phandle( #else static inline struct regmap *syscon_node_to_regmap(struct device_node *np) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-ENOTSUPP); } static inline struct regmap *syscon_regmap_lookup_by_compatible(const char *s) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-ENOTSUPP); } static inline struct regmap *syscon_regmap_lookup_by_pdevname(const char *s) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-ENOTSUPP); } static inline struct regmap *syscon_regmap_lookup_by_phandle( struct device_node *np, const char *property) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-ENOTSUPP); } #endif -- cgit v1.2.3 From 5c1488906f852473b4d7837c3e33e411e0eb6910 Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Sun, 31 Jan 2016 23:00:06 +0100 Subject: mfd: tps65090: Set regmap config reg counts properly Regmap config max_register field should contain number of device last register, however num_reg_defaults_raw field should be set to register count instead (usually one register more than max_register). tps65090 driver had both of these fields set to the same value, fix this by introducing separate defines for max register number and total count of registers. Signed-off-by: Maciej S. Szmigiero Signed-off-by: Lee Jones --- include/linux/mfd/tps65090.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h index 0bf2708df150..67d144b3b8f9 100644 --- a/include/linux/mfd/tps65090.h +++ b/include/linux/mfd/tps65090.h @@ -77,6 +77,11 @@ enum { #define TPS65090_REG_CG_CTRL5 0x09 #define TPS65090_REG_CG_STATUS1 0x0a #define TPS65090_REG_CG_STATUS2 0x0b +#define TPS65090_REG_AD_OUT1 0x17 +#define TPS65090_REG_AD_OUT2 0x18 + +#define TPS65090_MAX_REG TPS65090_REG_AD_OUT2 +#define TPS65090_NUM_REGS (TPS65090_MAX_REG + 1) struct tps65090 { struct device *dev; -- cgit v1.2.3 From 2609e4daaaff930548e35793d46ae079d39fb722 Mon Sep 17 00:00:00 2001 From: Christoph Fritz Date: Thu, 25 Feb 2016 15:47:48 +0100 Subject: mfd: imx6sx: Add PCIe register definitions for iomuxc gpr This patch adds macros to define masks and bits for imx6sx PCIe registers. This is based on a patch by Richard Zhu. Signed-off-by: Christoph Fritz Signed-off-by: Lee Jones --- include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h index 558a485d03ab..238c8db953eb 100644 --- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h +++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h @@ -422,6 +422,7 @@ #define IMX6SX_GPR5_VADC_TO_CSI_CAPTURE_EN_MASK (0x1 << 26) #define IMX6SX_GPR5_VADC_TO_CSI_CAPTURE_EN_ENABLE (0x1 << 26) #define IMX6SX_GPR5_VADC_TO_CSI_CAPTURE_EN_DISABLE (0x0 << 26) +#define IMX6SX_GPR5_PCIE_BTNRST_RESET BIT(19) #define IMX6SX_GPR5_CSI1_MUX_CTRL_MASK (0x3 << 4) #define IMX6SX_GPR5_CSI1_MUX_CTRL_EXT_PIN (0x0 << 4) #define IMX6SX_GPR5_CSI1_MUX_CTRL_CVD (0x1 << 4) @@ -435,6 +436,10 @@ #define IMX6SX_GPR5_DISP_MUX_DCIC1_LVDS (0x1 << 1) #define IMX6SX_GPR5_DISP_MUX_DCIC1_MASK (0x1 << 1) +#define IMX6SX_GPR12_PCIE_TEST_POWERDOWN BIT(30) +#define IMX6SX_GPR12_PCIE_RX_EQ_MASK (0x7 << 0) +#define IMX6SX_GPR12_PCIE_RX_EQ_2 (0x2 << 0) + /* For imx6ul iomux gpr register field define */ #define IMX6UL_GPR1_ENET1_CLK_DIR (0x1 << 17) #define IMX6UL_GPR1_ENET2_CLK_DIR (0x1 << 18) -- cgit v1.2.3 From 664a39236e718f9f03fa73fc01006da9ced04efc Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 28 Feb 2016 13:12:15 -0800 Subject: watchdog: Introduce hardware maximum heartbeat in watchdog core Introduce an optional hardware maximum heartbeat in the watchdog core. The hardware maximum heartbeat can be lower than the maximum timeout. Drivers can set the maximum hardware heartbeat value in the watchdog data structure. If the configured timeout exceeds the maximum hardware heartbeat, the watchdog core enables a timer function to assist sending keepalive requests to the watchdog driver. Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 0b565f2ad242..8e82daecb7d3 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -10,8 +10,9 @@ #include -#include #include +#include +#include #include #include @@ -61,14 +62,19 @@ struct watchdog_ops { * @bootstatus: Status of the watchdog device at boot. * @timeout: The watchdog devices timeout value (in seconds). * @min_timeout:The watchdog devices minimum timeout value (in seconds). - * @max_timeout:The watchdog devices maximum timeout value (in seconds). + * @max_timeout:The watchdog devices maximum timeout value (in seconds) + * as configurable from user space. Only relevant if + * max_hw_heartbeat_ms is not provided. + * @max_hw_heartbeat_ms: + * Hardware limit for maximum timeout, in milli-seconds. + * Replaces max_timeout if specified. * @reboot_nb: The notifier block to stop watchdog on reboot. * @restart_nb: The notifier block to register a restart function. * @driver_data:Pointer to the drivers private data. * @wd_data: Pointer to watchdog core internal data. * @status: Field that contains the devices internal status bits. - * @deferred: entry in wtd_deferred_reg_list which is used to - * register early initialized watchdogs. + * @deferred: Entry in wtd_deferred_reg_list which is used to + * register early initialized watchdogs. * * The watchdog_device structure contains all information about a * watchdog timer device. @@ -89,6 +95,7 @@ struct watchdog_device { unsigned int timeout; unsigned int min_timeout; unsigned int max_timeout; + unsigned int max_hw_heartbeat_ms; struct notifier_block reboot_nb; struct notifier_block restart_nb; void *driver_data; @@ -128,13 +135,18 @@ static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigne { /* * The timeout is invalid if + * - the requested value is larger than UINT_MAX / 1000 + * (since internal calculations are done in milli-seconds), + * or * - the requested value is smaller than the configured minimum timeout, * or - * - a maximum timeout is configured, and the requested value is larger - * than the maximum timeout. + * - a maximum hardware timeout is not configured, a maximum timeout + * is configured, and the requested value is larger than the + * configured maximum timeout. */ - return t < wdd->min_timeout || - (wdd->max_timeout && t > wdd->max_timeout); + return t > UINT_MAX / 1000 || t < wdd->min_timeout || + (!wdd->max_hw_heartbeat_ms && wdd->max_timeout && + t > wdd->max_timeout); } /* Use the following functions to manipulate watchdog driver specific data */ -- cgit v1.2.3 From ee142889e32f564f9b5e57b68b06693ec5473074 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 28 Feb 2016 13:12:16 -0800 Subject: watchdog: Introduce WDOG_HW_RUNNING flag The WDOG_HW_RUNNING flag is expected to be set by watchdog drivers if the hardware watchdog is running. If the flag is set, the watchdog subsystem will ping the watchdog even if the watchdog device is closed. The watchdog driver stop function is now optional and may be omitted if the watchdog can not be stopped. If stopping the watchdog is not possible but the driver implements a stop function, it is responsible to set the WDOG_HW_RUNNING flag in its stop function. Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 8e82daecb7d3..e2f45549b243 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -105,6 +105,7 @@ struct watchdog_device { #define WDOG_ACTIVE 0 /* Is the watchdog running/active */ #define WDOG_NO_WAY_OUT 1 /* Is 'nowayout' feature set ? */ #define WDOG_STOP_ON_REBOOT 2 /* Should be stopped on reboot */ +#define WDOG_HW_RUNNING 3 /* True if HW watchdog running */ struct list_head deferred; }; @@ -117,6 +118,15 @@ static inline bool watchdog_active(struct watchdog_device *wdd) return test_bit(WDOG_ACTIVE, &wdd->status); } +/* + * Use the following function to check whether or not the hardware watchdog + * is running + */ +static inline bool watchdog_hw_running(struct watchdog_device *wdd) +{ + return test_bit(WDOG_HW_RUNNING, &wdd->status); +} + /* Use the following function to set the nowayout feature */ static inline void watchdog_set_nowayout(struct watchdog_device *wdd, bool nowayout) { -- cgit v1.2.3 From 15013ad813f6544be8e79afc23672745950d59bc Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 28 Feb 2016 13:12:18 -0800 Subject: watchdog: Add support for minimum time between heartbeats Some watchdogs require a minimum time between heartbeats. Examples are the watchdogs in DA9062 and AT91SAM9x. Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index e2f45549b243..51732d6c9555 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -65,6 +65,8 @@ struct watchdog_ops { * @max_timeout:The watchdog devices maximum timeout value (in seconds) * as configurable from user space. Only relevant if * max_hw_heartbeat_ms is not provided. + * @min_hw_heartbeat_ms: + * Minimum time between heartbeats, in milli-seconds. * @max_hw_heartbeat_ms: * Hardware limit for maximum timeout, in milli-seconds. * Replaces max_timeout if specified. @@ -95,6 +97,7 @@ struct watchdog_device { unsigned int timeout; unsigned int min_timeout; unsigned int max_timeout; + unsigned int min_hw_heartbeat_ms; unsigned int max_hw_heartbeat_ms; struct notifier_block reboot_nb; struct notifier_block restart_nb; -- cgit v1.2.3 From 2b021cbf3cb6208f0d40fd2f1869f237934340ed Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 15 Mar 2016 20:43:04 -0400 Subject: cgroup: ignore css_sets associated with dead cgroups during migration Before 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups"), all dead tasks were associated with init_css_set. If a zombie task is requested for migration, while migration prep operations would still be performed on init_css_set, the actual migration would ignore zombie tasks. As init_css_set is always valid, this worked fine. However, after 2e91fa7f6d45, zombie tasks stay with the css_set it was associated with at the time of death. Let's say a task T associated with cgroup A on hierarchy H-1 and cgroup B on hiearchy H-2. After T becomes a zombie, it would still remain associated with A and B. If A only contains zombie tasks, it can be removed. On removal, A gets marked offline but stays pinned until all zombies are drained. At this point, if migration is initiated on T to a cgroup C on hierarchy H-2, migration path would try to prepare T's css_set for migration and trigger the following. WARNING: CPU: 0 PID: 1576 at kernel/cgroup.c:474 cgroup_get+0x121/0x160() CPU: 0 PID: 1576 Comm: bash Not tainted 4.4.0-work+ #289 ... Call Trace: [] dump_stack+0x4e/0x82 [] warn_slowpath_common+0x78/0xb0 [] warn_slowpath_null+0x15/0x20 [] cgroup_get+0x121/0x160 [] link_css_set+0x7b/0x90 [] find_css_set+0x3bc/0x5e0 [] cgroup_migrate_prepare_dst+0x89/0x1f0 [] cgroup_attach_task+0x157/0x230 [] __cgroup_procs_write+0x2b7/0x470 [] cgroup_tasks_write+0xc/0x10 [] cgroup_file_write+0x30/0x1b0 [] kernfs_fop_write+0x13c/0x180 [] __vfs_write+0x23/0xe0 [] vfs_write+0xa4/0x1a0 [] SyS_write+0x44/0xa0 [] entry_SYSCALL_64_fastpath+0x12/0x6f It doesn't make sense to prepare migration for css_sets pointing to dead cgroups as they are guaranteed to contain only zombies which are ignored later during migration. This patch makes cgroup destruction path mark all affected css_sets as dead and updates the migration path to ignore them during preparation. Signed-off-by: Tejun Heo Fixes: 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups") Cc: stable@vger.kernel.org # v4.4+ --- include/linux/cgroup-defs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 34b42f03fcd8..3e39ae5bc799 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -212,6 +212,9 @@ struct css_set { /* all css_task_iters currently walking this cset */ struct list_head task_iters; + /* dead and being drained, ignore for migration */ + bool dead; + /* For RCU-protected deletion */ struct rcu_head rcu_head; }; -- cgit v1.2.3 From 02113ba93ea414b7113d64e42b87dc0720e3e578 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 15 Mar 2016 11:33:40 +0000 Subject: PM / clk: Add support for obtaining clocks from device-tree The PM clocks framework requires clients to pass either a con-id or a valid clk pointer in order to add a clock to a device. Add a new function of_pm_clk_add_clks() to allows device clocks to be retrieved from device-tree and populated for a given device. Note that it is not necessary to make the compilation of this new function dependent upon CONFIG_OF because there are stubs functions for the device-tree APIs used. In order to handle errors encountered when adding clocks from device-tree, add a function pm_clk_remove_clk() to remove any clocks (using a pointer to the clk structure) that have been added successfully before the error occurred. Signed-off-by: Jon Hunter Acked-by: Geert Uytterhoeven Signed-off-by: Rafael J. Wysocki --- include/linux/pm_clock.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h index 25266c600021..308d6044f153 100644 --- a/include/linux/pm_clock.h +++ b/include/linux/pm_clock.h @@ -42,7 +42,9 @@ extern int pm_clk_create(struct device *dev); extern void pm_clk_destroy(struct device *dev); extern int pm_clk_add(struct device *dev, const char *con_id); extern int pm_clk_add_clk(struct device *dev, struct clk *clk); +extern int of_pm_clk_add_clks(struct device *dev); extern void pm_clk_remove(struct device *dev, const char *con_id); +extern void pm_clk_remove_clk(struct device *dev, struct clk *clk); extern int pm_clk_suspend(struct device *dev); extern int pm_clk_resume(struct device *dev); #else @@ -69,11 +71,18 @@ static inline int pm_clk_add_clk(struct device *dev, struct clk *clk) { return -EINVAL; } +static inline int of_pm_clk_add_clks(struct device *dev) +{ + return -EINVAL; +} static inline void pm_clk_remove(struct device *dev, const char *con_id) { } #define pm_clk_suspend NULL #define pm_clk_resume NULL +static inline void pm_clk_remove_clk(struct device *dev, struct clk *clk) +{ +} #endif #ifdef CONFIG_HAVE_CLK -- cgit v1.2.3 From 7e545d6eca20ce8ef7f66a63146cbff82b2ba760 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 16 Mar 2016 20:55:39 -0400 Subject: livepatch/module: remove livepatch module notifier Remove the livepatch module notifier in favor of directly enabling and disabling patches to modules in the module loader. Hard-coding the function calls ensures that ftrace_module_enable() is run before klp_module_coming() during module load, and that klp_module_going() is run before ftrace_release_mod() during module unload. This way, ftrace and livepatch code is run in the correct order during the module load/unload sequence without dependence on the module notifier call chain. Signed-off-by: Jessica Yu Reviewed-by: Petr Mladek Acked-by: Josh Poimboeuf Acked-by: Rusty Russell Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index c05679701e10..bd830d590465 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -24,6 +24,8 @@ #include #include +#if IS_ENABLED(CONFIG_LIVEPATCH) + #include enum klp_state { @@ -132,4 +134,15 @@ int klp_unregister_patch(struct klp_patch *); int klp_enable_patch(struct klp_patch *); int klp_disable_patch(struct klp_patch *); +/* Called from the module loader during module coming/going states */ +int klp_module_coming(struct module *mod); +void klp_module_going(struct module *mod); + +#else /* !CONFIG_LIVEPATCH */ + +static inline int klp_module_coming(struct module *mod) { return 0; } +static inline void klp_module_going(struct module *mod) { } + +#endif /* CONFIG_LIVEPATCH */ + #endif /* _LINUX_LIVEPATCH_H_ */ -- cgit v1.2.3 From 40cf446b9482bd2c681b60062b34cc47c78342f8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Mar 2016 20:46:14 +0100 Subject: nfs4.h: add SCSI layout definitions Based on draft-ietf-nfsv4-scsi-layout-05 after the WG last call. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index d6f9b4e6006d..011433478a14 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -529,6 +529,7 @@ enum pnfs_layouttype { LAYOUT_OSD2_OBJECTS = 2, LAYOUT_BLOCK_VOLUME = 3, LAYOUT_FLEX_FILES = 4, + LAYOUT_SCSI = 5, LAYOUT_TYPE_MAX }; @@ -555,6 +556,7 @@ enum pnfs_block_volume_type { PNFS_BLOCK_VOLUME_SLICE = 1, PNFS_BLOCK_VOLUME_CONCAT = 2, PNFS_BLOCK_VOLUME_STRIPE = 3, + PNFS_BLOCK_VOLUME_SCSI = 4, }; enum pnfs_block_extent_state { @@ -568,6 +570,23 @@ enum pnfs_block_extent_state { #define PNFS_BLOCK_EXTENT_SIZE \ (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE) +/* on the wire size of a scsi commit range */ +#define PNFS_SCSI_RANGE_SIZE \ + (4 * sizeof(__be32)) + +enum scsi_code_set { + PS_CODE_SET_BINARY = 1, + PS_CODE_SET_ASCII = 2, + PS_CODE_SET_UTF8 = 3 +}; + +enum scsi_designator_type { + PS_DESIGNATOR_T10 = 1, + PS_DESIGNATOR_EUI64 = 2, + PS_DESIGNATOR_NAA = 3, + PS_DESIGNATOR_NAME = 8 +}; + #define NFL4_UFLG_MASK 0x0000003F #define NFL4_UFLG_DENSE 0x00000001 #define NFL4_UFLG_COMMIT_THRU_MDS 0x00000002 -- cgit v1.2.3 From 27ee57c93ff00b8a2d6c6dd6b0b3dddda7b43b77 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 17 Mar 2016 14:17:35 -0700 Subject: mm: memcontrol: report slab usage in cgroup2 memory.stat Show how much memory is used for storing reclaimable and unreclaimable in-kernel data structures allocated from slab caches. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f0c4bec6565b..e7af4834ffea 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,6 +53,8 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, + MEMCG_SLAB_RECLAIMABLE, + MEMCG_SLAB_UNRECLAIMABLE, MEMCG_NR_STAT, }; @@ -883,6 +885,20 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep) if (memcg_kmem_enabled()) __memcg_kmem_put_cache(cachep); } + +/** + * memcg_kmem_update_page_stat - update kmem page state statistics + * @page: the page + * @idx: page state item to account + * @val: number of pages (positive or negative) + */ +static inline void memcg_kmem_update_page_stat(struct page *page, + enum mem_cgroup_stat_index idx, int val) +{ + if (memcg_kmem_enabled() && page->mem_cgroup) + this_cpu_add(page->mem_cgroup->stat->count[idx], val); +} + #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) @@ -928,6 +944,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) static inline void memcg_kmem_put_cache(struct kmem_cache *cachep) { } + +static inline void memcg_kmem_update_page_stat(struct page *page, + enum mem_cgroup_stat_index idx, int val) +{ +} #endif /* CONFIG_MEMCG && !CONFIG_SLOB */ #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From 12580e4b54ba8a1b22ec977c200be0174ca42348 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 17 Mar 2016 14:17:38 -0700 Subject: mm: memcontrol: report kernel stack usage in cgroup2 memory.stat Show how much memory is allocated to kernel stacks. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e7af4834ffea..d6300313b298 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,9 +52,10 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, + MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS, MEMCG_SLAB_RECLAIMABLE, MEMCG_SLAB_UNRECLAIMABLE, + MEMCG_SOCK, MEMCG_NR_STAT, }; -- cgit v1.2.3 From 832fc1de01aea28255cb11d270679b7f1273f0d7 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 17 Mar 2016 14:17:41 -0700 Subject: /proc/kpageflags: return KPF_BUDDY for "tail" buddy pages Currently /proc/kpageflags returns nothing for "tail" buddy pages, which is inconvenient when grasping how free pages are distributed. This patch sets KPF_BUDDY for such pages. With this patch: $ grep MemFree /proc/meminfo ; tools/vm/page-types -b buddy MemFree: 3134992 kB flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000400 779272 3044 __________B_______________________________ buddy 0x0000000000000c00 4385 17 __________BM______________________________ buddy,mmap total 783657 3061 783657 pages is 3134628 kB (roughly consistent with the global counter,) so it's OK. [akpm@linux-foundation.org: update comment, per Naoya] Signed-off-by: Naoya Horiguchi Reviewed-by: Vladimir Davydov > Cc: Konstantin Khlebnikov Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 19724e6ebd26..597695523679 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -593,6 +593,8 @@ static inline void __ClearPageBuddy(struct page *page) atomic_set(&page->_mapcount, -1); } +extern bool is_free_buddy_page(struct page *page); + #define PAGE_BALLOON_MAPCOUNT_VALUE (-256) static inline int PageBalloon(struct page *page) -- cgit v1.2.3 From 698b1b30642f1ff0ea10ef1de9745ab633031377 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 17 Mar 2016 14:18:08 -0700 Subject: mm, compaction: introduce kcompactd Memory compaction can be currently performed in several contexts: - kswapd balancing a zone after a high-order allocation failure - direct compaction to satisfy a high-order allocation, including THP page fault attemps - khugepaged trying to collapse a hugepage - manually from /proc The purpose of compaction is two-fold. The obvious purpose is to satisfy a (pending or future) high-order allocation, and is easy to evaluate. The other purpose is to keep overal memory fragmentation low and help the anti-fragmentation mechanism. The success wrt the latter purpose is more The current situation wrt the purposes has a few drawbacks: - compaction is invoked only when a high-order page or hugepage is not available (or manually). This might be too late for the purposes of keeping memory fragmentation low. - direct compaction increases latency of allocations. Again, it would be better if compaction was performed asynchronously to keep fragmentation low, before the allocation itself comes. - (a special case of the previous) the cost of compaction during THP page faults can easily offset the benefits of THP. - kswapd compaction appears to be complex, fragile and not working in some scenarios. It could also end up compacting for a high-order allocation request when it should be reclaiming memory for a later order-0 request. To improve the situation, we should be able to benefit from an equivalent of kswapd, but for compaction - i.e. a background thread which responds to fragmentation and the need for high-order allocations (including hugepages) somewhat proactively. One possibility is to extend the responsibilities of kswapd, which could however complicate its design too much. It should be better to let kswapd handle reclaim, as order-0 allocations are often more critical than high-order ones. Another possibility is to extend khugepaged, but this kthread is a single instance and tied to THP configs. This patch goes with the option of a new set of per-node kthreads called kcompactd, and lays the foundations, without introducing any new tunables. The lifecycle mimics kswapd kthreads, including the memory hotplug hooks. For compaction, kcompactd uses the standard compaction_suitable() and ompact_finished() criteria and the deferred compaction functionality. Unlike direct compaction, it uses only sync compaction, as there's no allocation latency to minimize. This patch doesn't yet add a call to wakeup_kcompactd. The kswapd compact/reclaim loop for high-order pages will be replaced by waking up kcompactd in the next patch with the description of what's wrong with the old approach. Waking up of the kcompactd threads is also tied to kswapd activity and follows these rules: - we don't want to affect any fastpaths, so wake up kcompactd only from the slowpath, as it's done for kswapd - if kswapd is doing reclaim, it's more important than compaction, so don't invoke kcompactd until kswapd goes to sleep - the target order used for kswapd is passed to kcompactd Future possible future uses for kcompactd include the ability to wake up kcompactd on demand in special situations, such as when hugepages are not available (currently not done due to __GFP_NO_KSWAPD) or when a fragmentation event (i.e. __rmqueue_fallback()) occurs. It's also possible to perform periodic compaction with kcompactd. [arnd@arndb.de: fix build errors with kcompactd] [paul.gortmaker@windriver.com: don't use modular references for non modular code] Signed-off-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Rik van Riel Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Arnd Bergmann Signed-off-by: Paul Gortmaker Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 16 ++++++++++++++++ include/linux/mmzone.h | 6 ++++++ include/linux/vm_event_item.h | 1 + 3 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4cd4ddf64cc7..d7c8de583a23 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -52,6 +52,10 @@ extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); extern bool compaction_restarting(struct zone *zone, int order); +extern int kcompactd_run(int nid); +extern void kcompactd_stop(int nid); +extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); + #else static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, int alloc_flags, @@ -84,6 +88,18 @@ static inline bool compaction_deferred(struct zone *zone, int order) return true; } +static inline int kcompactd_run(int nid) +{ + return 0; +} +static inline void kcompactd_stop(int nid) +{ +} + +static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) +{ +} + #endif /* CONFIG_COMPACTION */ #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6de02ac378a0..bdd9a270a813 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -668,6 +668,12 @@ typedef struct pglist_data { mem_hotplug_begin/end() */ int kswapd_max_order; enum zone_type classzone_idx; +#ifdef CONFIG_COMPACTION + int kcompactd_max_order; + enum zone_type kcompactd_classzone_idx; + wait_queue_head_t kcompactd_wait; + struct task_struct *kcompactd; +#endif #ifdef CONFIG_NUMA_BALANCING /* Lock serializing the migrate rate limiting window */ spinlock_t numabalancing_migrate_lock; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 67c1dbd19c6d..58ecc056ee45 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -53,6 +53,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED, COMPACTISOLATED, COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS, + KCOMPACTD_WAKE, #endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, -- cgit v1.2.3 From ee91ef6173e81819f5ff610c2485802081635657 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Thu, 17 Mar 2016 14:18:21 -0700 Subject: bufferhead: force inlining of buffer head flag operations With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, set_buffer_foo(), clear_buffer_foo() and similar functions get deinlined about 60 times. Examples of disassembly: (14 copies, 43 calls): 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 80 0f 20 lock orb $0x20,(%rdi) 5d pop %rbp c3 retq (3 copies, 34 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 c1 e8 05 shr $0x5,%rax 83 e0 01 and $0x1,%eax 5d pop %rbp c3 retq (5 copies, 13 calls): 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 80 0f 40 lock orb $0x40,(%rdi) 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. This decreases vmlinux by about 3 kbytes. text data bss dec hex filename 88200439 19905208 36421632 144527279 89d4faf vmlinux2 88197239 19905240 36421632 144524111 89d434f vmlinux Signed-off-by: Denys Vlasenko Cc: Ingo Molnar Cc: Thomas Graf Cc: Peter Zijlstra Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 89d9aa9e79bf..c67f052cc5e5 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -82,15 +82,15 @@ struct buffer_head { * and buffer_foo() functions. */ #define BUFFER_FNS(bit, name) \ -static inline void set_buffer_##name(struct buffer_head *bh) \ +static __always_inline void set_buffer_##name(struct buffer_head *bh) \ { \ set_bit(BH_##bit, &(bh)->b_state); \ } \ -static inline void clear_buffer_##name(struct buffer_head *bh) \ +static __always_inline void clear_buffer_##name(struct buffer_head *bh) \ { \ clear_bit(BH_##bit, &(bh)->b_state); \ } \ -static inline int buffer_##name(const struct buffer_head *bh) \ +static __always_inline int buffer_##name(const struct buffer_head *bh) \ { \ return test_bit(BH_##bit, &(bh)->b_state); \ } @@ -99,11 +99,11 @@ static inline int buffer_##name(const struct buffer_head *bh) \ * test_set_buffer_foo() and test_clear_buffer_foo() */ #define TAS_BUFFER_FNS(bit, name) \ -static inline int test_set_buffer_##name(struct buffer_head *bh) \ +static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \ { \ return test_and_set_bit(BH_##bit, &(bh)->b_state); \ } \ -static inline int test_clear_buffer_##name(struct buffer_head *bh) \ +static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ { \ return test_and_clear_bit(BH_##bit, &(bh)->b_state); \ } \ -- cgit v1.2.3 From 4b0f326163f09e6d67f09dd5e1a70093cee710fc Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Thu, 17 Mar 2016 14:18:24 -0700 Subject: include/linux/page-flags.h: force inlining of selected page flag modifications Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: (43 copies, 141 calls): 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 80 0f 08 lock orb $0x8,(%rdi) 5d pop %rbp c3 retq (10 copies, 134 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 c1 e8 0b shr $0xb,%rax 83 e0 01 and $0x1,%eax 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. Code size decrease after the patch is ~7k: text data bss dec hex filename 92125002 20826048 36417536 149368586 8e72f0a vmlinux 92118087 20826112 36417536 149361735 8e71447 vmlinux7_pageops_after Signed-off-by: Denys Vlasenko Cc: Ingo Molnar Cc: Thomas Graf Cc: Peter Zijlstra Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 597695523679..f4ed4f1b0c77 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -144,12 +144,12 @@ static inline struct page *compound_head(struct page *page) return page; } -static inline int PageTail(struct page *page) +static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; } -static inline int PageCompound(struct page *page) +static __always_inline int PageCompound(struct page *page) { return test_bit(PG_head, &page->flags) || PageTail(page); } @@ -184,31 +184,31 @@ static inline int PageCompound(struct page *page) * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname, policy) \ -static inline int Page##uname(struct page *page) \ +static __always_inline int Page##uname(struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ -static inline void SetPage##uname(struct page *page) \ +static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ -static inline void ClearPage##uname(struct page *page) \ +static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ -static inline void __SetPage##uname(struct page *page) \ +static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ -static inline void __ClearPage##uname(struct page *page) \ +static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ -static inline int TestSetPage##uname(struct page *page) \ +static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ -static inline int TestClearPage##uname(struct page *page) \ +static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ @@ -371,7 +371,7 @@ PAGEFLAG(Idle, idle, PF_ANY) #define PAGE_MAPPING_KSM 2 #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) -static inline int PageAnon(struct page *page) +static __always_inline int PageAnon(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; @@ -384,7 +384,7 @@ static inline int PageAnon(struct page *page) * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ -static inline int PageKsm(struct page *page) +static __always_inline int PageKsm(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == @@ -415,14 +415,14 @@ static inline int PageUptodate(struct page *page) return ret; } -static inline void __SetPageUptodate(struct page *page) +static __always_inline void __SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); __set_bit(PG_uptodate, &page->flags); } -static inline void SetPageUptodate(struct page *page) +static __always_inline void SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); /* @@ -456,12 +456,12 @@ static inline void set_page_writeback_keepwrite(struct page *page) __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) -static inline void set_compound_head(struct page *page, struct page *head) +static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } -static inline void clear_compound_head(struct page *page) +static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } -- cgit v1.2.3 From b6ecd2dea4435a771a99c497a6ac5df6d3618c5a Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 17 Mar 2016 14:18:33 -0700 Subject: mm: memcontrol: zap memcg_kmem_online helper As kmem accounting is now either enabled for all cgroups or disabled system-wide, there's no point in having memcg_kmem_online() helper - instead one can use memcg_kmem_enabled() and mem_cgroup_online(), as shrink_slab() now does. There are only two places left where this helper is used - __memcg_kmem_charge() and memcg_create_kmem_cache(). The former can only be called if memcg_kmem_enabled() returned true. Since the cgroup it operates on is online, mem_cgroup_is_root() check will be enough. memcg_create_kmem_cache() can't use mem_cgroup_online() helper instead of memcg_kmem_online(), because it relies on the fact that in memcg_offline_kmem() memcg->kmem_state is changed before memcg_deactivate_kmem_caches() is called, but there we can just open-code the check. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d6300313b298..bc8e4e22f58f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -795,11 +795,6 @@ static inline bool memcg_kmem_enabled(void) return static_branch_unlikely(&memcg_kmem_enabled_key); } -static inline bool memcg_kmem_online(struct mem_cgroup *memcg) -{ - return memcg->kmem_state == KMEM_ONLINE; -} - /* * In general, we'll do everything in our power to not incur in any overhead * for non-memcg users for the kmem functions. Not even a function call, if we @@ -909,11 +904,6 @@ static inline bool memcg_kmem_enabled(void) return false; } -static inline bool memcg_kmem_online(struct mem_cgroup *memcg) -{ - return false; -} - static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { return 0; -- cgit v1.2.3 From 0a6b76dd23fa08c5fd7b68acdb55018a37afd4aa Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 17 Mar 2016 14:18:42 -0700 Subject: mm: workingset: make shadow node shrinker memcg aware Workingset code was recently made memcg aware, but shadow node shrinker is still global. As a result, one small cgroup can consume all memory available for shadow nodes, possibly hurting other cgroups by reclaiming their shadow nodes, even though reclaim distances stored in its shadow nodes have no effect. To avoid this, we need to make shadow node shrinker memcg aware. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bc8e4e22f58f..1191d79aa495 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -403,6 +403,9 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int nr_pages); +unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, unsigned int lru_mask); + static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { @@ -661,6 +664,13 @@ mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, { } +static inline unsigned long +mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, unsigned int lru_mask) +{ + return 0; +} + static inline void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { -- cgit v1.2.3 From f9719a03de51e13526d614e79d002f838770b2d6 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:18:45 -0700 Subject: thp, vmstats: count deferred split events Count how many times we put a THP in split queue. Currently, it happens on partial unmap of a THP. Rapidly growing value can indicate that an application behaves unfriendly wrt THP: often fault in huge page and then unmap part of it. This leads to unnecessary memory fragmentation and the application may require tuning. The event also can help with debugging kernel [mis-]behaviour. Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 58ecc056ee45..ec084321fe09 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -72,6 +72,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_COLLAPSE_ALLOC_FAILED, THP_SPLIT_PAGE, THP_SPLIT_PAGE_FAILED, + THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, -- cgit v1.2.3 From ea606cf5d8df370e7932460dfd960b21f20e7c6d Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 17 Mar 2016 14:18:48 -0700 Subject: mm: move max_map_count bits into mm.h max_map_count sysctl unrelated to scheduler. Move its bits from include/linux/sched/sysctl.h to include/linux/mm.h. Signed-off-by: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++++++++++++++++++ include/linux/sched/sysctl.h | 21 --------------------- 2 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dbf1eddab964..6922adf41938 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -82,6 +82,27 @@ extern int mmap_rnd_compat_bits __read_mostly; #define mm_forbids_zeropage(X) (0) #endif +/* + * Default maximum number of active map areas, this limits the number of vmas + * per mm struct. Users can overwrite this number by sysctl but there is a + * problem. + * + * When a program's coredump is generated as ELF format, a section is created + * per a vma. In ELF, the number of sections is represented in unsigned short. + * This means the number of sections should be smaller than 65535 at coredump. + * Because the kernel adds some informative sections to a image of program at + * generating coredump, we need some margin. The number of extra sections is + * 1-3 now and depends on arch. We use "5" as safe margin, here. + * + * ELF extended numbering allows more than 65535 sections, so 16-bit bound is + * not a hard limit any more. Although some userspace tools can be surprised by + * that. + */ +#define MAPCOUNT_ELF_CORE_MARGIN (5) +#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) + +extern int sysctl_max_map_count; + extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4f080ab4f2cd..22db1e63707e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -14,27 +14,6 @@ extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, enum { sysctl_hung_task_timeout_secs = 0 }; #endif -/* - * Default maximum number of active map areas, this limits the number of vmas - * per mm struct. Users can overwrite this number by sysctl but there is a - * problem. - * - * When a program's coredump is generated as ELF format, a section is created - * per a vma. In ELF, the number of sections is represented in unsigned short. - * This means the number of sections should be smaller than 65535 at coredump. - * Because the kernel adds some informative sections to a image of program at - * generating coredump, we need some margin. The number of extra sections is - * 1-3 now and depends on arch. We use "5" as safe margin, here. - * - * ELF extended numbering allows more than 65535 sections, so 16-bit bound is - * not a hard limit any more. Although some userspace tools can be surprised by - * that. - */ -#define MAPCOUNT_ELF_CORE_MARGIN (5) -#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) - -extern int sysctl_max_map_count; - extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; -- cgit v1.2.3 From bcf6691797f425b301f629bb783b7ff2d0bcfa5a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:18:53 -0700 Subject: mm, tracing: refresh __def_vmaflag_names Get list of VMA flags up-to-date and sort it to match VM_* definition order. [vbabka@suse.cz: add a note above vmaflag definitions to update the names when changing] Signed-off-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Signed-off-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6922adf41938..b3202612bb95 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -143,6 +143,7 @@ extern unsigned int kobjsize(const void *objp); /* * vm_flags in vm_area_struct, see mm_types.h. + * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 -- cgit v1.2.3 From d02bd27bd33dd7e8d22594cd568b81be0cb584cd Mon Sep 17 00:00:00 2001 From: Igor Redko Date: Thu, 17 Mar 2016 14:19:05 -0700 Subject: mm/page_alloc.c: calculate 'available' memory in a separate function Add a new field, VIRTIO_BALLOON_S_AVAIL, to virtio_balloon memory statistics protocol, corresponding to 'Available' in /proc/meminfo. It indicates to the hypervisor how big the balloon can be inflated without pushing the guest system to swap. This metric would be very useful in VM orchestration software to improve memory management of different VMs under overcommit. This patch (of 2): Factor out calculation of the available memory counter into a separate exportable function, in order to be able to use it in other parts of the kernel. In particular, it appears a relevant metric to report to the hypervisor via virtio-balloon statistics interface (in a followup patch). Signed-off-by: Igor Redko Signed-off-by: Denis V. Lunev Reviewed-by: Roman Kagan Cc: Michael S. Tsirkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b3202612bb95..db9df3f78de1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1875,6 +1875,7 @@ extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(unsigned int flags); +extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -- cgit v1.2.3 From 3ed3a4f0ddffece942bb2661924d87be4ce63cb7 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:19:11 -0700 Subject: mm: cleanup *pte_alloc* interfaces There are few things about *pte_alloc*() helpers worth cleaning up: - 'vma' argument is unused, let's drop it; - most __pte_alloc() callers do speculative check for pmd_none(), before taking ptl: let's introduce pte_alloc() macro which does the check. The only direct user of __pte_alloc left is userfaultfd, which has different expectation about atomicity wrt pmd. - pte_alloc_map() and pte_alloc_map_lock() are redefined using pte_alloc(). [sudeep.holla@arm.com: fix build for arm64 hugetlbpage] [sfr@canb.auug.org.au: fix arch/arm/mm/mmu.c some more] Signed-off-by: Kirill A. Shutemov Cc: Dave Hansen Signed-off-by: Sudeep Holla Acked-by: Kirill A. Shutemov Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index db9df3f78de1..75d1907b9009 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1545,8 +1545,7 @@ static inline void mm_dec_nr_pmds(struct mm_struct *mm) } #endif -int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, - pmd_t *pmd, unsigned long address); +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address); int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); /* @@ -1672,15 +1671,15 @@ static inline void pgtable_page_dtor(struct page *page) pte_unmap(pte); \ } while (0) -#define pte_alloc_map(mm, vma, pmd, address) \ - ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma, \ - pmd, address))? \ - NULL: pte_offset_map(pmd, address)) +#define pte_alloc(mm, pmd, address) \ + (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd, address)) + +#define pte_alloc_map(mm, pmd, address) \ + (pte_alloc(mm, pmd, address) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ - ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL, \ - pmd, address))? \ - NULL: pte_offset_map_lock(mm, pmd, address, ptlp)) + (pte_alloc(mm, pmd, address) ? \ + NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ -- cgit v1.2.3 From 795ae7a0de6b834a0cc202aa55c190ef81496665 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 17 Mar 2016 14:19:14 -0700 Subject: mm: scale kswapd watermarks in proportion to memory In machines with 140G of memory and enterprise flash storage, we have seen read and write bursts routinely exceed the kswapd watermarks and cause thundering herds in direct reclaim. Unfortunately, the only way to tune kswapd aggressiveness is through adjusting min_free_kbytes - the system's emergency reserves - which is entirely unrelated to the system's latency requirements. In order to get kswapd to maintain a 250M buffer of free memory, the emergency reserves need to be set to 1G. That is a lot of memory wasted for no good reason. On the other hand, it's reasonable to assume that allocation bursts and overall allocation concurrency scale with memory capacity, so it makes sense to make kswapd aggressiveness a function of that as well. Change the kswapd watermark scale factor from the currently fixed 25% of the tunable emergency reserve to a tunable 0.1% of memory. Beyond 1G of memory, this will produce bigger watermark steps than the current formula in default settings. Ensure that the new formula never chooses steps smaller than that, i.e. 25% of the emergency reserve. On a 140G machine, this raises the default watermark steps - the distance between min and low, and low and high - from 16M to 143M. Signed-off-by: Johannes Weiner Acked-by: Mel Gorman Acked-by: Rik van Riel Acked-by: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/linux/mmzone.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 75d1907b9009..f7fd64227d3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1889,6 +1889,7 @@ extern void zone_pcp_reset(struct zone *zone); /* page_alloc.c */ extern int min_free_kbytes; +extern int watermark_scale_factor; /* nommu.c */ extern atomic_long_t mmap_pages_allocated; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bdd9a270a813..c60df9257cc7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -841,6 +841,8 @@ static inline int is_highmem(struct zone *zone) struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -- cgit v1.2.3 From b14a1ef58e8acb7fa64c1c8f745b21fd8a577aba Mon Sep 17 00:00:00 2001 From: Satoru Takeuchi Date: Thu, 17 Mar 2016 14:19:17 -0700 Subject: mm: remove unnecessary description about a non-exist gfp flag Since __GFP_NOACCOUNT was removed by commit 20b5c3039863 ("Revert 'gfp: add __GFP_NOACCOUNT'"), its description is not necessary. Signed-off-by: Satoru Takeuchi Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index bb16dfeb917e..c083d0820a87 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -105,8 +105,6 @@ struct vm_area_struct; * * __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the __GFP_MEMALLOC flag if both are set. - * - * __GFP_NOACCOUNT ignores the accounting for kmemcg limit enforcement. */ #define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) -- cgit v1.2.3 From 444eb2a449ef36fe115431ed7b71467c4563c7f1 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 17 Mar 2016 14:19:23 -0700 Subject: mm: thp: set THP defrag by default to madvise and add a stall-free defrag option THP defrag is enabled by default to direct reclaim/compact but not wake kswapd in the event of a THP allocation failure. The problem is that THP allocation requests potentially enter reclaim/compaction. This potentially incurs a severe stall that is not guaranteed to be offset by reduced TLB misses. While there has been considerable effort to reduce the impact of reclaim/compaction, it is still a high cost and workloads that should fit in memory fail to do so. Specifically, a simple anon/file streaming workload will enter direct reclaim on NUMA at least even though the working set size is 80% of RAM. It's been years and it's time to throw in the towel. First, this patch defines THP defrag as follows; madvise: A failed allocation will direct reclaim/compact if the application requests it never: Neither reclaim/compact nor wake kswapd defer: A failed allocation will wake kswapd/kcompactd always: A failed allocation will direct reclaim/compact (historical behaviour) khugepaged defrag will enter direct/reclaim but not wake kswapd. Next it sets the default defrag option to be "madvise" to only enter direct reclaim/compaction for applications that specifically requested it. Lastly, it removes a check from the page allocator slowpath that is related to __GFP_THISNODE to allow "defer" to work. The callers that really cares are slub/slab and they are updated accordingly. The slab one may be surprising because it also corrects a comment as kswapd was never woken up by that path. This means that a THP fault will no longer stall for most applications by default and the ideal for most users that get THP if they are immediately available. There are still options for users that prefer a stall at startup of a new application by either restoring historical behaviour with "always" or pick a half-way point with "defer" where kswapd does some of the work in the background and wakes kcompactd if necessary. THP defrag for khugepaged remains enabled and will enter direct/reclaim but no wakeup kswapd or kcompactd. After this patch a THP allocation failure will quickly fallback and rely on khugepaged to recover the situation at some time in the future. In some cases, this will reduce THP usage but the benefit of THP is hard to measure and not a universal win where as a stall to reclaim/compaction is definitely measurable and can be painful. The first test for this is using "usemem" to read a large file and write a large anonymous mapping (to avoid the zero page) multiple times. The total size of the mappings is 80% of RAM and the benchmark simply measures how long it takes to complete. It uses multiple threads to see if that is a factor. On UMA, the performance is almost identical so is not reported but on NUMA, we see this usemem 4.4.0 4.4.0 kcompactd-v1r1 nodefrag-v1r3 Amean System-1 102.86 ( 0.00%) 46.81 ( 54.50%) Amean System-4 37.85 ( 0.00%) 34.02 ( 10.12%) Amean System-7 48.12 ( 0.00%) 46.89 ( 2.56%) Amean System-12 51.98 ( 0.00%) 56.96 ( -9.57%) Amean System-21 80.16 ( 0.00%) 79.05 ( 1.39%) Amean System-30 110.71 ( 0.00%) 107.17 ( 3.20%) Amean System-48 127.98 ( 0.00%) 124.83 ( 2.46%) Amean Elapsd-1 185.84 ( 0.00%) 105.51 ( 43.23%) Amean Elapsd-4 26.19 ( 0.00%) 25.58 ( 2.33%) Amean Elapsd-7 21.65 ( 0.00%) 21.62 ( 0.16%) Amean Elapsd-12 18.58 ( 0.00%) 17.94 ( 3.43%) Amean Elapsd-21 17.53 ( 0.00%) 16.60 ( 5.33%) Amean Elapsd-30 17.45 ( 0.00%) 17.13 ( 1.84%) Amean Elapsd-48 15.40 ( 0.00%) 15.27 ( 0.82%) For a single thread, the benchmark completes 43.23% faster with this patch applied with smaller benefits as the thread increases. Similar, notice the large reduction in most cases in system CPU usage. The overall CPU time is 4.4.0 4.4.0 kcompactd-v1r1 nodefrag-v1r3 User 10357.65 10438.33 System 3988.88 3543.94 Elapsed 2203.01 1634.41 Which is substantial. Now, the reclaim figures 4.4.0 4.4.0 kcompactd-v1r1nodefrag-v1r3 Minor Faults 128458477 278352931 Major Faults 2174976 225 Swap Ins 16904701 0 Swap Outs 17359627 0 Allocation stalls 43611 0 DMA allocs 0 0 DMA32 allocs 19832646 19448017 Normal allocs 614488453 580941839 Movable allocs 0 0 Direct pages scanned 24163800 0 Kswapd pages scanned 0 0 Kswapd pages reclaimed 0 0 Direct pages reclaimed 20691346 0 Compaction stalls 42263 0 Compaction success 938 0 Compaction failures 41325 0 This patch eliminates almost all swapping and direct reclaim activity. There is still overhead but it's from NUMA balancing which does not identify that it's pointless trying to do anything with this workload. I also tried the thpscale benchmark which forces a corner case where compaction can be used heavily and measures the latency of whether base or huge pages were used thpscale Fault Latencies 4.4.0 4.4.0 kcompactd-v1r1 nodefrag-v1r3 Amean fault-base-1 5288.84 ( 0.00%) 2817.12 ( 46.73%) Amean fault-base-3 6365.53 ( 0.00%) 3499.11 ( 45.03%) Amean fault-base-5 6526.19 ( 0.00%) 4363.06 ( 33.15%) Amean fault-base-7 7142.25 ( 0.00%) 4858.08 ( 31.98%) Amean fault-base-12 13827.64 ( 0.00%) 10292.11 ( 25.57%) Amean fault-base-18 18235.07 ( 0.00%) 13788.84 ( 24.38%) Amean fault-base-24 21597.80 ( 0.00%) 24388.03 (-12.92%) Amean fault-base-30 26754.15 ( 0.00%) 19700.55 ( 26.36%) Amean fault-base-32 26784.94 ( 0.00%) 19513.57 ( 27.15%) Amean fault-huge-1 4223.96 ( 0.00%) 2178.57 ( 48.42%) Amean fault-huge-3 2194.77 ( 0.00%) 2149.74 ( 2.05%) Amean fault-huge-5 2569.60 ( 0.00%) 2346.95 ( 8.66%) Amean fault-huge-7 3612.69 ( 0.00%) 2997.70 ( 17.02%) Amean fault-huge-12 3301.75 ( 0.00%) 6727.02 (-103.74%) Amean fault-huge-18 6696.47 ( 0.00%) 6685.72 ( 0.16%) Amean fault-huge-24 8000.72 ( 0.00%) 9311.43 (-16.38%) Amean fault-huge-30 13305.55 ( 0.00%) 9750.45 ( 26.72%) Amean fault-huge-32 9981.71 ( 0.00%) 10316.06 ( -3.35%) The average time to fault pages is substantially reduced in the majority of caseds but with the obvious caveat that fewer THPs are actually used in this adverse workload 4.4.0 4.4.0 kcompactd-v1r1 nodefrag-v1r3 Percentage huge-1 0.71 ( 0.00%) 14.04 (1865.22%) Percentage huge-3 10.77 ( 0.00%) 33.05 (206.85%) Percentage huge-5 60.39 ( 0.00%) 38.51 (-36.23%) Percentage huge-7 45.97 ( 0.00%) 34.57 (-24.79%) Percentage huge-12 68.12 ( 0.00%) 40.07 (-41.17%) Percentage huge-18 64.93 ( 0.00%) 47.82 (-26.35%) Percentage huge-24 62.69 ( 0.00%) 44.23 (-29.44%) Percentage huge-30 43.49 ( 0.00%) 55.38 ( 27.34%) Percentage huge-32 50.72 ( 0.00%) 51.90 ( 2.35%) 4.4.0 4.4.0 kcompactd-v1r1nodefrag-v1r3 Minor Faults 37429143 47564000 Major Faults 1916 1558 Swap Ins 1466 1079 Swap Outs 2936863 149626 Allocation stalls 62510 3 DMA allocs 0 0 DMA32 allocs 6566458 6401314 Normal allocs 216361697 216538171 Movable allocs 0 0 Direct pages scanned 25977580 17998 Kswapd pages scanned 0 3638931 Kswapd pages reclaimed 0 207236 Direct pages reclaimed 8833714 88 Compaction stalls 103349 5 Compaction success 270 4 Compaction failures 103079 1 Note again that while this does swap as it's an aggressive workload, the direct relcim activity and allocation stalls is substantially reduced. There is some kswapd activity but ftrace showed that the kswapd activity was due to normal wakeups from 4K pages being allocated. Compaction-related stalls and activity are almost eliminated. I also tried the stutter benchmark. For this, I do not have figures for NUMA but it's something that does impact UMA so I'll report what is available stutter 4.4.0 4.4.0 kcompactd-v1r1 nodefrag-v1r3 Min mmap 7.3571 ( 0.00%) 7.3438 ( 0.18%) 1st-qrtle mmap 7.5278 ( 0.00%) 17.9200 (-138.05%) 2nd-qrtle mmap 7.6818 ( 0.00%) 21.6055 (-181.25%) 3rd-qrtle mmap 11.0889 ( 0.00%) 21.8881 (-97.39%) Max-90% mmap 27.8978 ( 0.00%) 22.1632 ( 20.56%) Max-93% mmap 28.3202 ( 0.00%) 22.3044 ( 21.24%) Max-95% mmap 28.5600 ( 0.00%) 22.4580 ( 21.37%) Max-99% mmap 29.6032 ( 0.00%) 25.5216 ( 13.79%) Max mmap 4109.7289 ( 0.00%) 4813.9832 (-17.14%) Mean mmap 12.4474 ( 0.00%) 19.3027 (-55.07%) This benchmark is trying to fault an anonymous mapping while there is a heavy IO load -- a scenario that desktop users used to complain about frequently. This shows a mix because the ideal case of mapping with THP is not hit as often. However, note that 99% of the mappings complete 13.79% faster. The CPU usage here is particularly interesting 4.4.0 4.4.0 kcompactd-v1r1nodefrag-v1r3 User 67.50 0.99 System 1327.88 91.30 Elapsed 2079.00 2128.98 And once again we look at the reclaim figures 4.4.0 4.4.0 kcompactd-v1r1nodefrag-v1r3 Minor Faults 335241922 1314582827 Major Faults 715 819 Swap Ins 0 0 Swap Outs 0 0 Allocation stalls 532723 0 DMA allocs 0 0 DMA32 allocs 1822364341 1177950222 Normal allocs 1815640808 1517844854 Movable allocs 0 0 Direct pages scanned 21892772 0 Kswapd pages scanned 20015890 41879484 Kswapd pages reclaimed 19961986 41822072 Direct pages reclaimed 21892741 0 Compaction stalls 1065755 0 Compaction success 514 0 Compaction failures 1065241 0 Allocation stalls and all direct reclaim activity is eliminated as well as compaction-related stalls. THP gives impressive gains in some cases but only if they are quickly available. We're not going to reach the point where they are completely free so lets take the costs out of the fast paths finally and defer the cost to kswapd, kcompactd and khugepaged where it belongs. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- include/linux/huge_mm.h | 9 ++------- 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c083d0820a87..11d56c6e7ef2 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -257,7 +257,7 @@ struct vm_area_struct; #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) #define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \ - ~__GFP_KSWAPD_RECLAIM) + ~__GFP_RECLAIM) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 459fd25b378e..a4cecb4801ec 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -41,7 +41,8 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, - TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, @@ -71,12 +72,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); ((__vma)->vm_flags & VM_HUGEPAGE))) && \ !((__vma)->vm_flags & VM_NOHUGEPAGE) && \ !is_vma_temporary_stack(__vma)) -#define transparent_hugepage_defrag(__vma) \ - ((transparent_hugepage_flags & \ - (1<vm_flags & VM_HUGEPAGE)) #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1< Date: Thu, 17 Mar 2016 14:19:26 -0700 Subject: mm: introduce page reference manipulation functions The success of CMA allocation largely depends on the success of migration and key factor of it is page reference count. Until now, page reference is manipulated by direct calling atomic functions so we cannot follow up who and where manipulate it. Then, it is hard to find actual reason of CMA allocation failure. CMA allocation should be guaranteed to succeed so finding offending place is really important. In this patch, call sites where page reference is manipulated are converted to introduced wrapper function. This is preparation step to add tracepoint to each page reference manipulation function. With this facility, we can easily find reason of CMA allocation failure. There is no functional change in this patch. In addition, this patch also converts reference read sites. It will help a second step that renames page._count to something else and prevents later attempt to direct access to it (Suggested by Andrew). Signed-off-by: Joonsoo Kim Acked-by: Michal Nazarewicz Acked-by: Vlastimil Babka Cc: Minchan Kim Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: Sergey Senozhatsky Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 25 ++++---------- include/linux/page_ref.h | 85 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pagemap.h | 19 ++--------- 3 files changed, 94 insertions(+), 35 deletions(-) create mode 100644 include/linux/page_ref.h (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f7fd64227d3a..997fc2e5d9d8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -22,6 +22,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -386,8 +387,8 @@ static inline int pmd_devmap(pmd_t pmd) */ static inline int put_page_testzero(struct page *page) { - VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0, page); - return atomic_dec_and_test(&page->_count); + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + return page_ref_dec_and_test(page); } /* @@ -398,7 +399,7 @@ static inline int put_page_testzero(struct page *page) */ static inline int get_page_unless_zero(struct page *page) { - return atomic_inc_not_zero(&page->_count); + return page_ref_add_unless(page, 1, 0); } extern int page_is_ram(unsigned long pfn); @@ -486,11 +487,6 @@ static inline int total_mapcount(struct page *page) } #endif -static inline int page_count(struct page *page) -{ - return atomic_read(&compound_head(page)->_count); -} - static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); @@ -498,15 +494,6 @@ static inline struct page *virt_to_head_page(const void *x) return compound_head(page); } -/* - * Setup the page count before being freed into the page allocator for - * the first time (boot or memory hotplug) - */ -static inline void init_page_count(struct page *page) -{ - atomic_set(&page->_count, 1); -} - void __put_page(struct page *page); void put_pages_list(struct list_head *pages); @@ -716,8 +703,8 @@ static inline void get_page(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); - atomic_inc(&page->_count); + VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); + page_ref_inc(page); if (unlikely(is_zone_device_page(page))) get_zone_device_page(page); diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h new file mode 100644 index 000000000000..30f5817f6b8e --- /dev/null +++ b/include/linux/page_ref.h @@ -0,0 +1,85 @@ +#ifndef _LINUX_PAGE_REF_H +#define _LINUX_PAGE_REF_H + +#include +#include +#include + +static inline int page_ref_count(struct page *page) +{ + return atomic_read(&page->_count); +} + +static inline int page_count(struct page *page) +{ + return atomic_read(&compound_head(page)->_count); +} + +static inline void set_page_count(struct page *page, int v) +{ + atomic_set(&page->_count, v); +} + +/* + * Setup the page count before being freed into the page allocator for + * the first time (boot or memory hotplug) + */ +static inline void init_page_count(struct page *page) +{ + set_page_count(page, 1); +} + +static inline void page_ref_add(struct page *page, int nr) +{ + atomic_add(nr, &page->_count); +} + +static inline void page_ref_sub(struct page *page, int nr) +{ + atomic_sub(nr, &page->_count); +} + +static inline void page_ref_inc(struct page *page) +{ + atomic_inc(&page->_count); +} + +static inline void page_ref_dec(struct page *page) +{ + atomic_dec(&page->_count); +} + +static inline int page_ref_sub_and_test(struct page *page, int nr) +{ + return atomic_sub_and_test(nr, &page->_count); +} + +static inline int page_ref_dec_and_test(struct page *page) +{ + return atomic_dec_and_test(&page->_count); +} + +static inline int page_ref_dec_return(struct page *page) +{ + return atomic_dec_return(&page->_count); +} + +static inline int page_ref_add_unless(struct page *page, int nr, int u) +{ + return atomic_add_unless(&page->_count, nr, u); +} + +static inline int page_ref_freeze(struct page *page, int count) +{ + return likely(atomic_cmpxchg(&page->_count, count, 0) == count); +} + +static inline void page_ref_unfreeze(struct page *page, int count) +{ + VM_BUG_ON_PAGE(page_count(page) != 0, page); + VM_BUG_ON(count == 0); + + atomic_set(&page->_count, count); +} + +#endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 183b15ea052b..1ebd65c91422 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -165,7 +165,7 @@ static inline int page_cache_get_speculative(struct page *page) * SMP requires. */ VM_BUG_ON_PAGE(page_count(page) == 0, page); - atomic_inc(&page->_count); + page_ref_inc(page); #else if (unlikely(!get_page_unless_zero(page))) { @@ -194,10 +194,10 @@ static inline int page_cache_add_speculative(struct page *page, int count) VM_BUG_ON(!in_atomic()); # endif VM_BUG_ON_PAGE(page_count(page) == 0, page); - atomic_add(count, &page->_count); + page_ref_add(page, count); #else - if (unlikely(!atomic_add_unless(&page->_count, count, 0))) + if (unlikely(!page_ref_add_unless(page, count, 0))) return 0; #endif VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page); @@ -205,19 +205,6 @@ static inline int page_cache_add_speculative(struct page *page, int count) return 1; } -static inline int page_freeze_refs(struct page *page, int count) -{ - return likely(atomic_cmpxchg(&page->_count, count, 0) == count); -} - -static inline void page_unfreeze_refs(struct page *page, int count) -{ - VM_BUG_ON_PAGE(page_count(page) != 0, page); - VM_BUG_ON(count == 0); - - atomic_set(&page->_count, count); -} - #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else -- cgit v1.2.3 From 95813b8faa0cd315f61a8b9d9c523792370b693e Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Thu, 17 Mar 2016 14:19:29 -0700 Subject: mm/page_ref: add tracepoint to track down page reference manipulation CMA allocation should be guaranteed to succeed by definition, but, unfortunately, it would be failed sometimes. It is hard to track down the problem, because it is related to page reference manipulation and we don't have any facility to analyze it. This patch adds tracepoints to track down page reference manipulation. With it, we can find exact reason of failure and can fix the problem. Following is an example of tracepoint output. (note: this example is stale version that printing flags as the number. Recent version will print it as human readable string.) <...>-9018 [004] 92.678375: page_ref_set: pfn=0x17ac9 flags=0x0 count=1 mapcount=0 mapping=(nil) mt=4 val=1 <...>-9018 [004] 92.678378: kernel_stack: => get_page_from_freelist (ffffffff81176659) => __alloc_pages_nodemask (ffffffff81176d22) => alloc_pages_vma (ffffffff811bf675) => handle_mm_fault (ffffffff8119e693) => __do_page_fault (ffffffff810631ea) => trace_do_page_fault (ffffffff81063543) => do_async_page_fault (ffffffff8105c40a) => async_page_fault (ffffffff817581d8) [snip] <...>-9018 [004] 92.678379: page_ref_mod: pfn=0x17ac9 flags=0x40048 count=2 mapcount=1 mapping=0xffff880015a78dc1 mt=4 val=1 [snip] ... ... <...>-9131 [001] 93.174468: test_pages_isolated: start_pfn=0x17800 end_pfn=0x17c00 fin_pfn=0x17ac9 ret=fail [snip] <...>-9018 [004] 93.174843: page_ref_mod_and_test: pfn=0x17ac9 flags=0x40068 count=0 mapcount=0 mapping=0xffff880015a78dc1 mt=4 val=-1 ret=1 => release_pages (ffffffff8117c9e4) => free_pages_and_swap_cache (ffffffff811b0697) => tlb_flush_mmu_free (ffffffff81199616) => tlb_finish_mmu (ffffffff8119a62c) => exit_mmap (ffffffff811a53f7) => mmput (ffffffff81073f47) => do_exit (ffffffff810794e9) => do_group_exit (ffffffff81079def) => SyS_exit_group (ffffffff81079e74) => entry_SYSCALL_64_fastpath (ffffffff817560b6) This output shows that problem comes from exit path. In exit path, to improve performance, pages are not freed immediately. They are gathered and processed by batch. During this process, migration cannot be possible and CMA allocation is failed. This problem is hard to find without this page reference tracepoint facility. Enabling this feature bloat kernel text 30 KB in my configuration. text data bss dec hex filename 12127327 2243616 1507328 15878271 f2487f vmlinux_disabled 12157208 2258880 1507328 15923416 f2f8d8 vmlinux_enabled Note that, due to header file dependency problem between mm.h and tracepoint.h, this feature has to open code the static key functions for tracepoints. Proposed by Steven Rostedt in following link. https://lkml.org/lkml/2015/12/9/699 [arnd@arndb.de: crypto/async_pq: use __free_page() instead of put_page()] [iamjoonsoo.kim@lge.com: fix build failure for xtensa] [akpm@linux-foundation.org: tweak Kconfig text, per Vlastimil] Signed-off-by: Joonsoo Kim Acked-by: Michal Nazarewicz Acked-by: Vlastimil Babka Cc: Minchan Kim Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: Sergey Senozhatsky Acked-by: Steven Rostedt Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ref.h | 98 +++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 93 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 30f5817f6b8e..e596d5d9540e 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -4,6 +4,62 @@ #include #include #include +#include + +extern struct tracepoint __tracepoint_page_ref_set; +extern struct tracepoint __tracepoint_page_ref_mod; +extern struct tracepoint __tracepoint_page_ref_mod_and_test; +extern struct tracepoint __tracepoint_page_ref_mod_and_return; +extern struct tracepoint __tracepoint_page_ref_mod_unless; +extern struct tracepoint __tracepoint_page_ref_freeze; +extern struct tracepoint __tracepoint_page_ref_unfreeze; + +#ifdef CONFIG_DEBUG_PAGE_REF + +/* + * Ideally we would want to use the trace__enabled() helper + * functions. But due to include header file issues, that is not + * feasible. Instead we have to open code the static key functions. + * + * See trace_##name##_enabled(void) in include/linux/tracepoint.h + */ +#define page_ref_tracepoint_active(t) static_key_false(&(t).key) + +extern void __page_ref_set(struct page *page, int v); +extern void __page_ref_mod(struct page *page, int v); +extern void __page_ref_mod_and_test(struct page *page, int v, int ret); +extern void __page_ref_mod_and_return(struct page *page, int v, int ret); +extern void __page_ref_mod_unless(struct page *page, int v, int u); +extern void __page_ref_freeze(struct page *page, int v, int ret); +extern void __page_ref_unfreeze(struct page *page, int v); + +#else + +#define page_ref_tracepoint_active(t) false + +static inline void __page_ref_set(struct page *page, int v) +{ +} +static inline void __page_ref_mod(struct page *page, int v) +{ +} +static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) +{ +} +static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) +{ +} +static inline void __page_ref_mod_unless(struct page *page, int v, int u) +{ +} +static inline void __page_ref_freeze(struct page *page, int v, int ret) +{ +} +static inline void __page_ref_unfreeze(struct page *page, int v) +{ +} + +#endif static inline int page_ref_count(struct page *page) { @@ -18,6 +74,8 @@ static inline int page_count(struct page *page) static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_count, v); + if (page_ref_tracepoint_active(__tracepoint_page_ref_set)) + __page_ref_set(page, v); } /* @@ -32,46 +90,74 @@ static inline void init_page_count(struct page *page) static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_count); + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + __page_ref_mod(page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_count); + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + __page_ref_mod(page, -nr); } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_count); + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + __page_ref_mod(page, 1); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_count); + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + __page_ref_mod(page, -1); } static inline int page_ref_sub_and_test(struct page *page, int nr) { - return atomic_sub_and_test(nr, &page->_count); + int ret = atomic_sub_and_test(nr, &page->_count); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) + __page_ref_mod_and_test(page, -nr, ret); + return ret; } static inline int page_ref_dec_and_test(struct page *page) { - return atomic_dec_and_test(&page->_count); + int ret = atomic_dec_and_test(&page->_count); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) + __page_ref_mod_and_test(page, -1, ret); + return ret; } static inline int page_ref_dec_return(struct page *page) { - return atomic_dec_return(&page->_count); + int ret = atomic_dec_return(&page->_count); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + __page_ref_mod_and_return(page, -1, ret); + return ret; } static inline int page_ref_add_unless(struct page *page, int nr, int u) { - return atomic_add_unless(&page->_count, nr, u); + int ret = atomic_add_unless(&page->_count, nr, u); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless)) + __page_ref_mod_unless(page, nr, ret); + return ret; } static inline int page_ref_freeze(struct page *page, int count) { - return likely(atomic_cmpxchg(&page->_count, count, 0) == count); + int ret = likely(atomic_cmpxchg(&page->_count, count, 0) == count); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze)) + __page_ref_freeze(page, count, ret); + return ret; } static inline void page_ref_unfreeze(struct page *page, int count) @@ -80,6 +166,8 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON(count == 0); atomic_set(&page->_count, count); + if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) + __page_ref_unfreeze(page, count); } #endif -- cgit v1.2.3 From b11a7b94100cba5ec926a181894c2897a22651b9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 17 Mar 2016 14:19:41 -0700 Subject: mm: exclude ZONE_DEVICE from GFP_ZONE_TABLE ZONE_DEVICE (merged in 4.3) and ZONE_CMA (proposed) are examples of new mm zones that are bumping up against the current maximum limit of 4 zones, i.e. 2 bits in page->flags for the GFP_ZONE_TABLE. The GFP_ZONE_TABLE poses an interesting constraint since include/linux/gfp.h gets included by the 32-bit portion of a 64-bit build. We need to be careful to only build the table for zones that have a corresponding gfp_t flag. GFP_ZONES_SHIFT is introduced for this purpose. This patch does not attempt to solve the problem of adding a new zone that also has a corresponding GFP_ flag. Vlastimil points out that ZONE_DEVICE, by depending on x86_64 and SPARSEMEM_VMEMMAP implies that SECTIONS_WIDTH is zero. In other words even though ZONE_DEVICE does not fit in GFP_ZONE_TABLE it is free to consume another bit in page->flags (expand ZONES_WIDTH) with room to spare. Link: https://bugzilla.kernel.org/show_bug.cgi?id=110931 Fixes: 033fbae988fc ("mm: ZONE_DEVICE for "device memory"") Signed-off-by: Dan Williams Reported-by: Mark Reported-by: Vlastimil Babka Cc: Mel Gorman Cc: Rik van Riel Cc: Joonsoo Kim Cc: Dave Hansen Cc: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 33 ++++++++++++++++++++------------- include/linux/page-flags-layout.h | 2 ++ 2 files changed, 22 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 11d56c6e7ef2..570383a41853 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -331,22 +331,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * - * ZONES_SHIFT must be <= 2 on 32 bit platforms. + * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ -#if 16 * ZONES_SHIFT > BITS_PER_LONG -#error ZONES_SHIFT too large to create GFP_ZONE_TABLE integer +#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 +/* ZONE_DEVICE is not a valid GFP zone specifier */ +#define GFP_ZONES_SHIFT 2 +#else +#define GFP_ZONES_SHIFT ZONES_SHIFT +#endif + +#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG +#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ - (ZONE_NORMAL << 0 * ZONES_SHIFT) \ - | (OPT_ZONE_DMA << ___GFP_DMA * ZONES_SHIFT) \ - | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * ZONES_SHIFT) \ - | (OPT_ZONE_DMA32 << ___GFP_DMA32 * ZONES_SHIFT) \ - | (ZONE_NORMAL << ___GFP_MOVABLE * ZONES_SHIFT) \ - | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * ZONES_SHIFT) \ - | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * ZONES_SHIFT) \ - | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * ZONES_SHIFT) \ + (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ + | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ + | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ + | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ + | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ + | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ + | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ + | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* @@ -371,8 +378,8 @@ static inline enum zone_type gfp_zone(gfp_t flags) enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); - z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) & - ((1 << ZONES_SHIFT) - 1); + z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & + ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index da523661500a..77b078c103b2 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -17,6 +17,8 @@ #define ZONES_SHIFT 1 #elif MAX_NR_ZONES <= 4 #define ZONES_SHIFT 2 +#elif MAX_NR_ZONES <= 8 +#define ZONES_SHIFT 3 #else #error ZONES_SHIFT -- too many zones configured adjust calculation #endif -- cgit v1.2.3 From 0e8fb9312fbaf1a687dd731b04d8ab3121c4ff5a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 17 Mar 2016 14:19:55 -0700 Subject: mm: remove VM_FAULT_MINOR The define has a comment from Nick Piggin from 2007: /* For backwards compat. Remove me quickly. */ I guess 9 years should not be too hurried sense of 'quickly' even for kernel measures. Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 997fc2e5d9d8..7d42501c8bb4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1052,8 +1052,6 @@ static inline void clear_page_pfmemalloc(struct page *page) * just gets major/minor fault counters bumped up. */ -#define VM_FAULT_MINOR 0 /* For backwards compat. Remove me quickly. */ - #define VM_FAULT_OOM 0x0001 #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 -- cgit v1.2.3 From b97731992d00f09456726bfc5ab6641c07773038 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:20:01 -0700 Subject: rmap: introduce rmap_walk_locked() This patchset rewrites freeze_page() and unfreeze_page() using try_to_unmap() and remove_migration_ptes(). Result is much simpler, but somewhat slower. Migration 8GiB worth of PMD-mapped THP: Baseline 20.21 +/- 0.393 Patched 20.73 +/- 0.082 Slowdown 1.03x It's 3% slower, comparing to 14% in v1. I don't it should be a stopper. Splitting of PTE-mapped pages slowed more. But this is not a common case. Migration 8GiB worth of PMD-mapped THP: Baseline 20.39 +/- 0.225 Patched 22.43 +/- 0.496 Slowdown 1.10x rmap_walk_locked() is the same as rmap_walk(), but the caller takes care of the relevant rmap lock. This is preparation for switching THP splitting from custom rmap walk in freeze_page()/unfreeze_page() to the generic one. There is no support for KSM pages for now: not clear which lock is implied. Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a07f42bedda3..a5875e9b4a27 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -266,6 +266,7 @@ struct rmap_walk_control { }; int rmap_walk(struct page *page, struct rmap_walk_control *rwc); +int rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From 2a52bcbcc688eecead2953143f7ef695b8e44575 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:20:04 -0700 Subject: rmap: extend try_to_unmap() to be usable by split_huge_page() Add support for two ttu_flags: - TTU_SPLIT_HUGE_PMD would split PMD if it's there, before trying to unmap page; - TTU_RMAP_LOCKED indicates that caller holds relevant rmap lock; Also, change rwc->done to !page_mapcount() instead of !page_mapped(). try_to_unmap() works on pte level, so we are really interested in the mappedness of this small page rather than of the compound page it's a part of. Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 7 +++++++ include/linux/rmap.h | 3 +++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a4cecb4801ec..01ad22e938b0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -106,6 +106,9 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, __split_huge_pmd(__vma, __pmd, __address); \ } while (0) + +void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address); + #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif @@ -173,6 +176,10 @@ static inline int split_huge_page(struct page *page) static inline void deferred_split_huge_page(struct page *page) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) + +static inline void split_huge_pmd_address(struct vm_area_struct *vma, + unsigned long address) {} + static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a5875e9b4a27..3d975e2252d4 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -86,6 +86,7 @@ enum ttu_flags { TTU_MIGRATION = 2, /* migration mode */ TTU_MUNLOCK = 4, /* munlock mode */ TTU_LZFREE = 8, /* lazy free mode */ + TTU_SPLIT_HUGE_PMD = 16, /* split huge PMD if any */ TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ @@ -93,6 +94,8 @@ enum ttu_flags { TTU_BATCH_FLUSH = (1 << 11), /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ + TTU_RMAP_LOCKED = (1 << 12) /* do not grab rmap lock: + * caller holds it */ }; #ifdef CONFIG_MMU -- cgit v1.2.3 From e388466de4a2a1a50c43bfaeacc0c8254d9e7cb2 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:20:07 -0700 Subject: mm: make remove_migration_ptes() beyond mm/migration.c Make remove_migration_ptes() available to be used in split_huge_page(). New parameter 'locked' added: as with try_to_umap() we need a way to indicate that caller holds rmap lock. We also shouldn't try to mlock() pte-mapped huge pages: pte-mapeed THP pages are never mlocked. Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 3d975e2252d4..49eb4f8ebac9 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -243,6 +243,8 @@ int page_mkclean(struct page *); */ int try_to_munlock(struct page *); +void remove_migration_ptes(struct page *old, struct page *new, bool locked); + /* * Called by memory-failure.c to kill processes. */ -- cgit v1.2.3 From fec89c109f3a7737fe3a7bf0f40d1fb7709d353b Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 17 Mar 2016 14:20:10 -0700 Subject: thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers freeze_page() and unfreeze_page() helpers evolved in rather complex beasts. It would be nice to cut complexity of this code. This patch rewrites freeze_page() using standard try_to_unmap(). unfreeze_page() is rewritten with remove_migration_ptes(). The result is much simpler. But the new variant is somewhat slower for PTE-mapped THPs. Current helpers iterates over VMAs the compound page is mapped to, and then over ptes within this VMA. New helpers iterates over small page, then over VMA the small page mapped to, and only then find relevant pte. We have short cut for PMD-mapped THP: we directly install migration entries on PMD split. I don't think the slowdown is critical, considering how much simpler result is and that split_huge_page() is quite rare nowadays. It only happens due memory pressure or migration. Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 01ad22e938b0..5307dfb3f8ec 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,18 +96,20 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address); + unsigned long address, bool freeze); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ - __split_huge_pmd(__vma, __pmd, __address); \ + __split_huge_pmd(__vma, __pmd, __address, \ + false); \ } while (0) -void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address); +void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, + bool freeze, struct page *page); #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" @@ -178,7 +180,7 @@ static inline void deferred_split_huge_page(struct page *page) {} do { } while (0) static inline void split_huge_pmd_address(struct vm_area_struct *vma, - unsigned long address) {} + unsigned long address, bool freeze, struct page *page) {} static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) -- cgit v1.2.3 From da8b44d5a9f8bf26da637b7336508ca534d6b319 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 17 Mar 2016 14:20:51 -0700 Subject: timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc//timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc//timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz Cc: Arjan van de Ven Cc: Thomas Gleixner Cc: Oren Laadan Cc: Ruchi Kandoi Cc: Rom Lemarchand Cc: Kees Cook Cc: Android Kernel Team Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/freezer.h | 2 +- include/linux/hrtimer.h | 12 +++++++----- include/linux/poll.h | 2 +- include/linux/sched.h | 4 ++-- 4 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 6b7fd9cf5ea2..dd03e837ebb7 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -231,7 +231,7 @@ static inline long freezable_schedule_timeout_killable_unsafe(long timeout) * call this with locks held. */ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode) + u64 delta, const enum hrtimer_mode mode) { int __retval; freezer_do_not_count(); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2ead22dd74a0..c98c6539e2c2 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -220,7 +220,7 @@ static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time timer->node.expires = ktime_add_safe(time, delta); } -static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) +static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); @@ -378,7 +378,7 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long range_ns, const enum hrtimer_mode mode); + u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer on the current CPU @@ -399,7 +399,7 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { - unsigned long delta; + u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); @@ -477,10 +477,12 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); -extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, +extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode, int clock); + u64 delta, + const enum hrtimer_mode mode, + int clock); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ diff --git a/include/linux/poll.h b/include/linux/poll.h index c08386fb3e08..9fb4f40d9a26 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -96,7 +96,7 @@ extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack); -extern long select_estimate_accuracy(struct timespec *tv); +extern u64 select_estimate_accuracy(struct timespec *tv); static inline int poll_schedule(struct poll_wqueues *pwq, int state) diff --git a/include/linux/sched.h b/include/linux/sched.h index eb7f2f84009b..3284d07edec7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1792,8 +1792,8 @@ struct task_struct { * time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ - unsigned long timer_slack_ns; - unsigned long default_timer_slack_ns; + u64 timer_slack_ns; + u64 default_timer_slack_ns; #ifdef CONFIG_KASAN unsigned int kasan_depth; -- cgit v1.2.3 From 93e205a728e6cb8d7d11f6836e289798a1de25e2 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 17 Mar 2016 14:21:15 -0700 Subject: fix Christoph's email addresses There are various email addresses for me throughout the kernel. Use the one that will always be valid. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quicklist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quicklist.h b/include/linux/quicklist.h index bd466439c588..3bdfa70bc642 100644 --- a/include/linux/quicklist.h +++ b/include/linux/quicklist.h @@ -5,7 +5,7 @@ * as needed after allocation when they are freed. Per cpu lists of pages * are kept that only contain node local pages. * - * (C) 2007, SGI. Christoph Lameter + * (C) 2007, SGI. Christoph Lameter */ #include #include -- cgit v1.2.3 From 26a247fd9f8d2df1965b7f22c9be2fb3a48603f3 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 17 Mar 2016 14:21:35 -0700 Subject: include/linux/list_bl.h: use bool instead of int for boolean functions hlist_bl_unhashed() and hlist_bl_empty() are all boolean functions, so return bool instead of int. Signed-off-by: Chen Gang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_bl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index ee7229a6c06a..cb483305e1f5 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -48,7 +48,7 @@ static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) -static inline int hlist_bl_unhashed(const struct hlist_bl_node *h) +static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } @@ -68,7 +68,7 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h, h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } -static inline int hlist_bl_empty(const struct hlist_bl_head *h) +static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } -- cgit v1.2.3 From f67c07f07fca95a7f330b8bb928eabaf9fcce75d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 17 Mar 2016 14:21:42 -0700 Subject: radix-tree: add an explicit include of bitops.h The radix-tree header uses the __ffs() function, which is defined in bitops.h. The current kernel headers implicitly include bitops.h, but the userspace test harness does not. Signed-off-by: Matthew Wilcox Cc: Johannes Weiner Cc: Matthew Wilcox Cc: "Kirill A. Shutemov" Cc: Ross Zwisler Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index f54be7082207..39598b9cf1d9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -21,6 +21,7 @@ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H +#include #include #include #include -- cgit v1.2.3 From e61452365372570253b2b1de84bab0cdb2e62c64 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 17 Mar 2016 14:21:54 -0700 Subject: radix_tree: add support for multi-order entries With huge pages, it is convenient to have the radix tree be able to return an entry that covers multiple indices. Previous attempts to deal with the problem have involved inserting N duplicate entries, which is a waste of memory and leads to problems trying to handle aliased tags, or probing the tree multiple times to find alternative entries which might cover the requested index. This approach inserts one canonical entry into the tree for a given range of indices, and may also insert other entries in order to ensure that lookups find the canonical entry. This solution only tolerates inserting powers of two that are greater than the fanout of the tree. If we wish to expand the radix tree's abilities to support large-ish pages that is less than the fanout at the penultimate level of the tree, then we would need to add one more step in lookup to ensure that any sibling nodes in the final level of the tree are dereferenced and we return the canonical entry that they reference. Signed-off-by: Matthew Wilcox Cc: Johannes Weiner Cc: Matthew Wilcox Cc: "Kirill A. Shutemov" Cc: Ross Zwisler Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 39598b9cf1d9..b211f145c811 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -271,8 +271,15 @@ static inline void radix_tree_replace_slot(void **pslot, void *item) } int __radix_tree_create(struct radix_tree_root *root, unsigned long index, - struct radix_tree_node **nodep, void ***slotp); -int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); + unsigned order, struct radix_tree_node **nodep, + void ***slotp); +int __radix_tree_insert(struct radix_tree_root *, unsigned long index, + unsigned order, void *); +static inline int radix_tree_insert(struct radix_tree_root *root, + unsigned long index, void *entry) +{ + return __radix_tree_insert(root, index, 0, entry); +} void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void ***slotp); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); -- cgit v1.2.3 From 7165092fe5ca70bae722ac6cd78421cfd0eec18d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 17 Mar 2016 14:22:06 -0700 Subject: radix-tree,shmem: introduce radix_tree_iter_next() shmem likes to occasionally drop the lock, schedule, then reacqire the lock and continue with the iteration from the last place it left off. This is currently done with a pretty ugly goto. Introduce radix_tree_iter_next() and use it throughout shmem.c. [koct9i@gmail.com: fix bug in radix_tree_iter_next() for tagged iteration] Signed-off-by: Matthew Wilcox Cc: Hugh Dickins Signed-off-by: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b211f145c811..51a97ac8bfbf 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -402,6 +402,22 @@ void **radix_tree_iter_retry(struct radix_tree_iter *iter) return NULL; } +/** + * radix_tree_iter_next - resume iterating when the chunk may be invalid + * @iter: iterator state + * + * If the iterator needs to release then reacquire a lock, the chunk may + * have been invalidated by an insertion or deletion. Call this function + * to continue the iteration from the next index. + */ +static inline __must_check +void **radix_tree_iter_next(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index + 1; + iter->tags = 0; + return NULL; +} + /** * radix_tree_chunk_size - get current chunk size * -- cgit v1.2.3 From 56b060814e2d87d6646a85a2f4609c73587399ca Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 17 Mar 2016 14:22:14 -0700 Subject: lib/string: introduce match_string() helper Occasionally we have to search for an occurrence of a string in an array of strings. Make a simple helper for that purpose. Signed-off-by: Andy Shevchenko Cc: "David S. Miller" Cc: Bartlomiej Zolnierkiewicz Cc: David Airlie Cc: David Woodhouse Cc: Dmitry Eremin-Solenikov Cc: Greg Kroah-Hartman Cc: Heikki Krogerus Cc: Linus Walleij Cc: Mika Westerberg Cc: Rafael J. Wysocki Cc: Sebastian Reichel Cc: Tejun Heo Cc: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 9eebc66d957a..0f235e80d355 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -130,6 +130,8 @@ extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); extern int strtobool(const char *s, bool *res); +int match_string(const char * const *array, size_t n, const char *string); + #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); -- cgit v1.2.3 From e3bde9568d992c5f985e6e30731a5f9f9bef7b13 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Thu, 17 Mar 2016 14:22:47 -0700 Subject: include/linux/unaligned: force inlining of byteswap operations Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: (24 copies, 108 calls): 66 8b 07 mov (%rdi),%ax 55 push %rbp 48 89 e5 mov %rsp,%rbp 86 e0 xchg %ah,%al 5d pop %rbp c3 retq (25 copies, 181 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 5d pop %rbp c3 retq (23 copies, 94 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 0f c8 bswap %rax 5d pop %rbp c3 retq (2 copies, 11 calls): 89 f8 mov %edi,%eax 55 push %rbp c1 ef 08 shr $0x8,%edi c1 e0 08 shl $0x8,%eax 09 c7 or %eax,%edi 48 89 e5 mov %rsp,%rbp 66 89 3e mov %di,(%rsi) (8 copies, 43 calls): 55 push %rbp 0f cf bswap %edi 89 3e mov %edi,(%rsi) 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq (26 copies, 157 calls): 55 push %rbp 48 0f cf bswap %rdi 48 89 3e mov %rdi,(%rsi) 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. It only affects arches with efficient unaligned access insns, such as x86. (arched which lack such ops do not include linux/unaligned/access_ok.h) Code size decrease after the patch is ~8.5k: text data bss dec hex filename 92197848 20826112 36417536 149441496 8e84bd8 vmlinux 92189231 20826144 36417536 149432911 8e82a4f vmlinux6_unaligned_be_after Signed-off-by: Denys Vlasenko Acked-by: Ingo Molnar Cc: Thomas Graf Cc: Peter Zijlstra Cc: David Rientjes Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unaligned/access_ok.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unaligned/access_ok.h b/include/linux/unaligned/access_ok.h index 99c1b4d20b0f..33383ca23837 100644 --- a/include/linux/unaligned/access_ok.h +++ b/include/linux/unaligned/access_ok.h @@ -4,62 +4,62 @@ #include #include -static inline u16 get_unaligned_le16(const void *p) +static __always_inline u16 get_unaligned_le16(const void *p) { return le16_to_cpup((__le16 *)p); } -static inline u32 get_unaligned_le32(const void *p) +static __always_inline u32 get_unaligned_le32(const void *p) { return le32_to_cpup((__le32 *)p); } -static inline u64 get_unaligned_le64(const void *p) +static __always_inline u64 get_unaligned_le64(const void *p) { return le64_to_cpup((__le64 *)p); } -static inline u16 get_unaligned_be16(const void *p) +static __always_inline u16 get_unaligned_be16(const void *p) { return be16_to_cpup((__be16 *)p); } -static inline u32 get_unaligned_be32(const void *p) +static __always_inline u32 get_unaligned_be32(const void *p) { return be32_to_cpup((__be32 *)p); } -static inline u64 get_unaligned_be64(const void *p) +static __always_inline u64 get_unaligned_be64(const void *p) { return be64_to_cpup((__be64 *)p); } -static inline void put_unaligned_le16(u16 val, void *p) +static __always_inline void put_unaligned_le16(u16 val, void *p) { *((__le16 *)p) = cpu_to_le16(val); } -static inline void put_unaligned_le32(u32 val, void *p) +static __always_inline void put_unaligned_le32(u32 val, void *p) { *((__le32 *)p) = cpu_to_le32(val); } -static inline void put_unaligned_le64(u64 val, void *p) +static __always_inline void put_unaligned_le64(u64 val, void *p) { *((__le64 *)p) = cpu_to_le64(val); } -static inline void put_unaligned_be16(u16 val, void *p) +static __always_inline void put_unaligned_be16(u16 val, void *p) { *((__be16 *)p) = cpu_to_be16(val); } -static inline void put_unaligned_be32(u32 val, void *p) +static __always_inline void put_unaligned_be32(u32 val, void *p) { *((__be32 *)p) = cpu_to_be32(val); } -static inline void put_unaligned_be64(u64 val, void *p) +static __always_inline void put_unaligned_be64(u64 val, void *p) { *((__be64 *)p) = cpu_to_be64(val); } -- cgit v1.2.3 From ef951599074ba4fad2d0efa0a977129b41e6d203 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Mar 2016 14:22:50 -0700 Subject: lib: move strtobool() to kstrtobool() Create the kstrtobool_from_user() helper and move strtobool() logic into the new kstrtobool() (matching all the other kstrto* functions). Provides an inline wrapper for existing strtobool() callers. Signed-off-by: Kees Cook Cc: Joe Perches Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Daniel Borkmann Cc: Amitkumar Karwar Cc: Nishant Sarmukadam Cc: Kalle Valo Cc: Steve French Cc: Michael Ellerman Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ include/linux/string.h | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..f4fa2b29c38c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -357,6 +357,7 @@ int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); +int __must_check kstrtobool(const char *s, bool *res); int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); @@ -368,6 +369,7 @@ int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigne int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); +int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) { diff --git a/include/linux/string.h b/include/linux/string.h index 0f235e80d355..d3993a79a325 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -128,7 +128,11 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); -extern int strtobool(const char *s, bool *res); +extern int kstrtobool(const char *s, bool *res); +static inline int strtobool(const char *s, bool *res) +{ + return kstrtobool(s, res); +} int match_string(const char * const *array, size_t n, const char *string); -- cgit v1.2.3 From 4cc7ecb7f2a60e8deb783b8fbf7c1ae467acb920 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Mar 2016 14:23:00 -0700 Subject: param: convert some "on"/"off" users to strtobool This changes several users of manual "on"/"off" parsing to use strtobool. Some side-effects: - these uses will now parse y/n/1/0 meaningfully too - the early_param uses will now bubble up parse errors Signed-off-by: Kees Cook Acked-by: Heiko Carstens Acked-by: Michael Ellerman Cc: Amitkumar Karwar Cc: Andy Shevchenko Cc: Daniel Borkmann Cc: Joe Perches Cc: Kalle Valo Cc: Martin Schwidefsky Cc: Nishant Sarmukadam Cc: Rasmus Villemoes Cc: Steve French Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 21f73649a4dc..62be0786d6d0 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -111,7 +111,7 @@ enum tick_dep_bits { #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) #ifdef CONFIG_NO_HZ_COMMON -extern int tick_nohz_enabled; +extern bool tick_nohz_enabled; extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); -- cgit v1.2.3 From 0b81d0779072696371822e5ed9e7c6292e547024 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 15 May 2015 16:26:10 -0700 Subject: fs crypto: move per-file encryption from f2fs tree to fs/crypto This patch adds the renamed functions moved from the f2fs crypto files. 1. definitions for per-file encryption used by ext4 and f2fs. 2. crypto.c for encrypt/decrypt functions a. IO preparation: - fscrypt_get_ctx / fscrypt_release_ctx b. before IOs: - fscrypt_encrypt_page - fscrypt_decrypt_page - fscrypt_zeroout_range c. after IOs: - fscrypt_decrypt_bio_pages - fscrypt_pullback_bio_page - fscrypt_restore_control_page 3. policy.c supporting context management. a. For ioctls: - fscrypt_process_policy - fscrypt_get_policy b. For context permission - fscrypt_has_permitted_context - fscrypt_inherit_context 4. keyinfo.c to handle permissions - fscrypt_get_encryption_info - fscrypt_free_encryption_info 5. fname.c to support filename encryption a. general wrapper functions - fscrypt_fname_disk_to_usr - fscrypt_fname_usr_to_disk - fscrypt_setup_filename - fscrypt_free_filename b. specific filename handling functions - fscrypt_fname_alloc_buffer - fscrypt_fname_free_buffer 6. Makefile and Kconfig Cc: Al Viro Signed-off-by: Michael Halcrow Signed-off-by: Ildar Muslukhov Signed-off-by: Uday Savagaonkar Signed-off-by: Theodore Ts'o Signed-off-by: Arnd Bergmann Signed-off-by: Jaegeuk Kim --- include/linux/dcache.h | 2 + include/linux/fs.h | 8 + include/linux/fscrypto.h | 433 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 443 insertions(+) create mode 100644 include/linux/fscrypto.h (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 7781ce110503..c7bdfc54cec5 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -228,6 +228,8 @@ struct dentry_operations { #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ #define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ +#define DCACHE_ENCRYPTED_WITH_KEY 0x04000000 /* dir is encrypted with a valid key */ + extern seqlock_t rename_lock; /* diff --git a/include/linux/fs.h b/include/linux/fs.h index ae681002100a..28fc12189997 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -53,6 +53,8 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; +struct fscrypt_info; +struct fscrypt_operations; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -678,6 +680,10 @@ struct inode { struct hlist_head i_fsnotify_marks; #endif +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + struct fscrypt_info *i_crypt_info; +#endif + void *i_private; /* fs or device private pointer */ }; @@ -1323,6 +1329,8 @@ struct super_block { #endif const struct xattr_handler **s_xattr; + const struct fscrypt_operations *s_cop; + struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h new file mode 100644 index 000000000000..895cdac4fcdd --- /dev/null +++ b/include/linux/fscrypto.h @@ -0,0 +1,433 @@ +/* + * General per-file encryption definition + * + * Copyright (C) 2015, Google, Inc. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ + +#ifndef _LINUX_FSCRYPTO_H +#define _LINUX_FSCRYPTO_H + +#include +#include +#include +#include +#include +#include + +#define FS_KEY_DERIVATION_NONCE_SIZE 16 +#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1 + +#define FS_POLICY_FLAGS_PAD_4 0x00 +#define FS_POLICY_FLAGS_PAD_8 0x01 +#define FS_POLICY_FLAGS_PAD_16 0x02 +#define FS_POLICY_FLAGS_PAD_32 0x03 +#define FS_POLICY_FLAGS_PAD_MASK 0x03 +#define FS_POLICY_FLAGS_VALID 0x03 + +/* Encryption algorithms */ +#define FS_ENCRYPTION_MODE_INVALID 0 +#define FS_ENCRYPTION_MODE_AES_256_XTS 1 +#define FS_ENCRYPTION_MODE_AES_256_GCM 2 +#define FS_ENCRYPTION_MODE_AES_256_CBC 3 +#define FS_ENCRYPTION_MODE_AES_256_CTS 4 + +/** + * Encryption context for inode + * + * Protector format: + * 1 byte: Protector format (1 = this version) + * 1 byte: File contents encryption mode + * 1 byte: File names encryption mode + * 1 byte: Flags + * 8 bytes: Master Key descriptor + * 16 bytes: Encryption Key derivation nonce + */ +struct fscrypt_context { + u8 format; + u8 contents_encryption_mode; + u8 filenames_encryption_mode; + u8 flags; + u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; +} __packed; + +/* Encryption parameters */ +#define FS_XTS_TWEAK_SIZE 16 +#define FS_AES_128_ECB_KEY_SIZE 16 +#define FS_AES_256_GCM_KEY_SIZE 32 +#define FS_AES_256_CBC_KEY_SIZE 32 +#define FS_AES_256_CTS_KEY_SIZE 32 +#define FS_AES_256_XTS_KEY_SIZE 64 +#define FS_MAX_KEY_SIZE 64 + +#define FS_KEY_DESC_PREFIX "fscrypt:" +#define FS_KEY_DESC_PREFIX_SIZE 8 + +/* This is passed in from userspace into the kernel keyring */ +struct fscrypt_key { + u32 mode; + u8 raw[FS_MAX_KEY_SIZE]; + u32 size; +} __packed; + +struct fscrypt_info { + u8 ci_data_mode; + u8 ci_filename_mode; + u8 ci_flags; + struct crypto_ablkcipher *ci_ctfm; + struct key *ci_keyring_key; + u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; +}; + +#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 +#define FS_WRITE_PATH_FL 0x00000002 + +struct fscrypt_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + u8 flags; /* Flags */ + u8 mode; /* Encryption mode for tfm */ +}; + +struct fscrypt_completion_result { + struct completion completion; + int res; +}; + +#define DECLARE_FS_COMPLETION_RESULT(ecr) \ + struct fscrypt_completion_result ecr = { \ + COMPLETION_INITIALIZER((ecr).completion), 0 } + +static inline int fscrypt_key_size(int mode) +{ + switch (mode) { + case FS_ENCRYPTION_MODE_AES_256_XTS: + return FS_AES_256_XTS_KEY_SIZE; + case FS_ENCRYPTION_MODE_AES_256_GCM: + return FS_AES_256_GCM_KEY_SIZE; + case FS_ENCRYPTION_MODE_AES_256_CBC: + return FS_AES_256_CBC_KEY_SIZE; + case FS_ENCRYPTION_MODE_AES_256_CTS: + return FS_AES_256_CTS_KEY_SIZE; + default: + BUG(); + } + return 0; +} + +#define FS_FNAME_NUM_SCATTER_ENTRIES 4 +#define FS_CRYPTO_BLOCK_SIZE 16 +#define FS_FNAME_CRYPTO_DIGEST_SIZE 32 + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct fscrypt_symlink_data { + __le16 len; + char encrypted_path[1]; +} __packed; + +/** + * This function is used to calculate the disk space required to + * store a filename of length l in encrypted symlink format. + */ +static inline u32 fscrypt_symlink_data_len(u32 l) +{ + if (l < FS_CRYPTO_BLOCK_SIZE) + l = FS_CRYPTO_BLOCK_SIZE; + return (l + sizeof(struct fscrypt_symlink_data) - 1); +} + +struct fscrypt_str { + unsigned char *name; + u32 len; +}; + +struct fscrypt_name { + const struct qstr *usr_fname; + struct fscrypt_str disk_name; + u32 hash; + u32 minor_hash; + struct fscrypt_str crypto_buf; +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + +/* + * crypto opertions for filesystems + */ +struct fscrypt_operations { + int (*get_context)(struct inode *, void *, size_t); + int (*prepare_context)(struct inode *); + int (*set_context)(struct inode *, const void *, size_t, void *); + int (*dummy_context)(struct inode *); + bool (*is_encrypted)(struct inode *); + bool (*empty_dir)(struct inode *); + unsigned (*max_namelen)(struct inode *); +}; + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + if (inode->i_sb->s_cop->dummy_context && + inode->i_sb->s_cop->dummy_context(inode)) + return true; + return false; +} + +static inline bool fscrypt_valid_contents_enc_mode(u32 mode) +{ + return (mode == FS_ENCRYPTION_MODE_AES_256_XTS); +} + +static inline bool fscrypt_valid_filenames_enc_mode(u32 mode) +{ + return (mode == FS_ENCRYPTION_MODE_AES_256_CTS); +} + +static inline u32 fscrypt_validate_encryption_key_size(u32 mode, u32 size) +{ + if (size == fscrypt_key_size(mode)) + return size; + return 0; +} + +static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) +{ + if (str->len == 1 && str->name[0] == '.') + return true; + + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; +} + +static inline struct page *fscrypt_control_page(struct page *page) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return ((struct fscrypt_ctx *)page_private(page))->w.control_page; +#else + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +#endif +} + +static inline int fscrypt_has_encryption_key(struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return (inode->i_crypt_info != NULL); +#else + return 0; +#endif +} + +static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + spin_unlock(&dentry->d_lock); +#endif +} + +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +extern const struct dentry_operations fscrypt_d_ops; +#endif + +static inline void fscrypt_set_d_op(struct dentry *dentry) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + d_set_d_op(dentry, &fscrypt_d_ops); +#endif +} + +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +/* crypto.c */ +extern struct kmem_cache *fscrypt_info_cachep; +int fscrypt_initialize(void); + +extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *); +extern void fscrypt_release_ctx(struct fscrypt_ctx *); +extern struct page *fscrypt_encrypt_page(struct inode *, struct page *); +extern int fscrypt_decrypt_page(struct page *); +extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); +extern void fscrypt_pullback_bio_page(struct page **, bool); +extern void fscrypt_restore_control_page(struct page *); +extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t, + unsigned int); +/* policy.c */ +extern int fscrypt_process_policy(struct inode *, + const struct fscrypt_policy *); +extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *); +extern int fscrypt_has_permitted_context(struct inode *, struct inode *); +extern int fscrypt_inherit_context(struct inode *, struct inode *, + void *, bool); +/* keyinfo.c */ +extern int get_crypt_info(struct inode *); +extern int fscrypt_get_encryption_info(struct inode *); +extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); + +/* fname.c */ +extern int fscrypt_setup_filename(struct inode *, const struct qstr *, + int lookup, struct fscrypt_name *); +extern void fscrypt_free_filename(struct fscrypt_name *); +extern u32 fscrypt_fname_encrypted_size(struct inode *, u32); +extern int fscrypt_fname_alloc_buffer(struct inode *, u32, + struct fscrypt_str *); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, + const struct fscrypt_str *, struct fscrypt_str *); +extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, + struct fscrypt_str *); +#endif + +/* crypto.c */ +static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c) +{ + return; +} + +static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i, + struct page *p) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int fscrypt_notsupp_decrypt_page(struct page *p) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_notsupp_decrypt_bio_pages(struct fscrypt_ctx *c, + struct bio *b) +{ + return; +} + +static inline void fscrypt_notsupp_pullback_bio_page(struct page **p, bool b) +{ + return; +} + +static inline void fscrypt_notsupp_restore_control_page(struct page *p) +{ + return; +} + +static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p, + sector_t s, unsigned int f) +{ + return -EOPNOTSUPP; +} + +/* policy.c */ +static inline int fscrypt_notsupp_process_policy(struct inode *i, + const struct fscrypt_policy *p) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_notsupp_get_policy(struct inode *i, + struct fscrypt_policy *p) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_notsupp_has_permitted_context(struct inode *p, + struct inode *i) +{ + return 0; +} + +static inline int fscrypt_notsupp_inherit_context(struct inode *p, + struct inode *i, void *v, bool b) +{ + return -EOPNOTSUPP; +} + +/* keyinfo.c */ +static inline int fscrypt_notsupp_get_encryption_info(struct inode *i) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_notsupp_put_encryption_info(struct inode *i, + struct fscrypt_info *f) +{ + return; +} + + /* fname.c */ +static inline int fscrypt_notsupp_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct fscrypt_name *fname) +{ + if (dir->i_sb->s_cop->is_encrypted(dir)) + return -EOPNOTSUPP; + + memset(fname, 0, sizeof(struct fscrypt_name)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname) +{ + return; +} + +static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s) +{ + /* never happens */ + WARN_ON(1); + return 0; +} + +static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode, + u32 ilen, struct fscrypt_str *crypto_str) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c) +{ + return; +} + +static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} +#endif /* _LINUX_FSCRYPTO_H */ -- cgit v1.2.3 From 81ad4276b505e987dd8ebbdf63605f92cd172b52 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 18 Mar 2016 10:03:24 +0800 Subject: Thermal: Ignore invalid trip points In some cases, platform thermal driver may report invalid trip points, thermal core should not take any action for these trip points. This fixed a regression that bogus trip point starts to screw up thermal control on some Lenovo laptops, after commit bb431ba26c5cd0a17c941ca6c3a195a3a6d5d461 Author: Zhang Rui Date: Fri Oct 30 16:31:47 2015 +0800 Thermal: initialize thermal zone device correctly After thermal zone device registered, as we have not read any temperature before, thus tz->temperature should not be 0, which actually means 0C, and thermal trend is not available. In this case, we need specially handling for the first thermal_zone_device_update(). Both thermal core framework and step_wise governor is enhanced to handle this. And since the step_wise governor is the only one that uses trends, so it's the only thermal governor that needs to be updated. Tested-by: Manuel Krause Tested-by: szegad Tested-by: prash Tested-by: amish Tested-by: Matthias Reviewed-by: Javi Merino Signed-off-by: Zhang Rui Signed-off-by: Chen Yu CC: #3.18+ Link: https://bugzilla.redhat.com/show_bug.cgi?id=1317190 Link: https://bugzilla.kernel.org/show_bug.cgi?id=114551 Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 9c481991fdc7..a55d0523f75d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -156,6 +156,7 @@ struct thermal_attr { * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports + * @trips_disabled; bitmap for disabled trips * @passive_delay: number of milliseconds to wait between polls when * performing passive cooling. * @polling_delay: number of milliseconds to wait between polls when @@ -191,6 +192,7 @@ struct thermal_zone_device { struct thermal_attr *trip_hyst_attrs; void *devdata; int trips; + unsigned long trips_disabled; /* bitmap for disabled trips */ int passive_delay; int polling_delay; int temperature; -- cgit v1.2.3 From 4c9dacb82d5aa36aa2568df60d897f2eb3d8819b Mon Sep 17 00:00:00 2001 From: Wenwei Tao Date: Thu, 3 Mar 2016 15:06:37 +0100 Subject: lightnvm: specify target's logical address area MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We can create more than one target on a lightnvm device by specifying its begin lun and end lun. But only specify the physical address area is not enough, we need to get the corresponding non- intersection logical address area division from the backend device's logcial address space. Otherwise the targets on the device might use the same logical addresses cause incorrect information in the device's l2p table. Signed-off-by: Wenwei Tao Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index c3c43184a787..b466bd9f2cf8 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -355,6 +355,7 @@ struct nvm_dev { char name[DISK_NAME_LEN]; struct mutex mlock; + spinlock_t lock; }; static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, @@ -467,6 +468,9 @@ typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); +typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); +typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t); + struct nvmm_type { const char *name; unsigned int version[3]; @@ -491,6 +495,10 @@ struct nvmm_type { /* Statistics */ nvmm_lun_info_print_fn *lun_info_print; + + nvmm_get_area_fn *get_area; + nvmm_put_area_fn *put_area; + struct list_head list; }; -- cgit v1.2.3 From da1e284919b0b99c5bf0618b6c98cbaf2c17e62e Mon Sep 17 00:00:00 2001 From: Wenwei Tao Date: Thu, 3 Mar 2016 15:06:38 +0100 Subject: lightnvm: add a bitmap of luns MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a bitmap of luns to indicate the status of luns: inuse/available. When create targets do the necessary check to avoid allocating luns that are already allocated. Signed-off-by: Wenwei Tao Freed dev->lun_map if nvm_core_init later failed in the init process. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index b466bd9f2cf8..0ee2c2c78ffd 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -346,6 +346,7 @@ struct nvm_dev { int nr_luns; unsigned max_pages_per_blk; + unsigned long *lun_map; void *ppalist_pool; struct nvm_id identity; @@ -466,6 +467,8 @@ typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, unsigned long); typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); +typedef int (nvmm_reserve_lun)(struct nvm_dev *, int); +typedef void (nvmm_release_lun)(struct nvm_dev *, int); typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); @@ -492,6 +495,8 @@ struct nvmm_type { /* Configuration management */ nvmm_get_lun_fn *get_lun; + nvmm_reserve_lun *reserve_lun; + nvmm_release_lun *release_lun; /* Statistics */ nvmm_lun_info_print_fn *lun_info_print; -- cgit v1.2.3 From 9f867268436d799549909437e627e7cf279e1127 Mon Sep 17 00:00:00 2001 From: Matias Bjorling Date: Thu, 3 Mar 2016 15:06:39 +0100 Subject: nvme: lightnvm: return ppa completion status MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PPAs sent to device is separately acknowledge in a 64bit status variable. The status is stored in DW0 and DW1 of the completion queue entry. Store this status inside the nvm_rq for further processing. This can later be used to implement retry techniques for failed writes and reads. Reviewed-by: Christoph Hellwig Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 0ee2c2c78ffd..cdcb2ccbefa8 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -242,6 +242,7 @@ struct nvm_rq { uint16_t nr_pages; uint16_t flags; + u64 ppa_status; /* ppa media status */ int error; }; -- cgit v1.2.3 From 18b862dcd57a3e23e34c8cd1e939f68548c1209a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 18 Mar 2016 20:02:39 +0000 Subject: dma-buf, drm, ion: Propagate error code from dma_buf_start_cpu_access() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers, especially i915.ko, can fail during the initial migration of a dma-buf for CPU access. However, the error code from the driver was not being propagated back to ioctl and so userspace was blissfully ignorant of the failure. Rendering corruption ensues. Whilst fixing the ioctl to return the error code from dma_buf_start_cpu_access(), also do the same for dma_buf_end_cpu_access(). For most drivers, dma_buf_end_cpu_access() cannot fail. i915.ko however, as most drivers would, wants to avoid being uninterruptible (as would be required to guarrantee no failure when flushing the buffer to the device). As userspace already has to handle errors from the SYNC_IOCTL, take advantage of this to be able to restart the syscall across signals. This fixes a coherency issue for i915.ko as well as reducing the uninterruptible hold upon its BKL, the struct_mutex. Fixes commit c11e391da2a8fe973c3c2398452000bed505851e Author: Daniel Vetter Date: Thu Feb 11 20:04:51 2016 -0200 dma-buf: Add ioctls to allow userspace to flush Testcase: igt/gem_concurrent_blit/*dmabuf*interruptible Testcase: igt/prime_mmap_coherency/ioctl-errors Signed-off-by: Chris Wilson Cc: Tiago Vignatti Cc: Stéphane Marchesin Cc: David Herrmann Cc: Sumit Semwal Cc: Daniel Vetter CC: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Cc: intel-gfx@lists.freedesktop.org Cc: devel@driverdev.osuosl.org Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1458331359-2634-1-git-send-email-chris@chris-wilson.co.uk --- include/linux/dma-buf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 532108ea0c1c..3fe90d494edb 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -94,7 +94,7 @@ struct dma_buf_ops { void (*release)(struct dma_buf *); int (*begin_cpu_access)(struct dma_buf *, enum dma_data_direction); - void (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); + int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); void *(*kmap_atomic)(struct dma_buf *, unsigned long); void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*kmap)(struct dma_buf *, unsigned long); @@ -224,8 +224,8 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *, enum dma_data_direction); int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void dma_buf_end_cpu_access(struct dma_buf *dma_buf, - enum dma_data_direction dir); +int dma_buf_end_cpu_access(struct dma_buf *dma_buf, + enum dma_data_direction dir); void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); void *dma_buf_kmap(struct dma_buf *, unsigned long); -- cgit v1.2.3 From 897bb0c7f1ea82d7cc882b19790b5e1df00ffc29 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 19 Mar 2016 11:30:33 +0100 Subject: blk-mq: Use proper cpumask iterator queue_for_each_ctx() iterates over per_cpu variables under the assumption that the possible cpu mask cannot have holes. That's wrong as all cpumasks can have holes. In case there are holes the iteration ends up accessing uninitialized memory and crashing as a result. Replace the macro by a proper for_each_possible_cpu() loop and drop the unused macro blk_ctx_sum() which references queue_for_each_ctx(). Reported-by: Xiong Zhou Signed-off-by: Thomas Gleixner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 15a73d49fd1d..9ac9799b702b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -263,22 +263,8 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) for ((i) = 0; (i) < (q)->nr_hw_queues && \ ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) -#define queue_for_each_ctx(q, ctx, i) \ - for ((i) = 0; (i) < (q)->nr_queues && \ - ({ ctx = per_cpu_ptr((q)->queue_ctx, (i)); 1; }); (i)++) - #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) -#define blk_ctx_sum(q, sum) \ -({ \ - struct blk_mq_ctx *__x; \ - unsigned int __ret = 0, __i; \ - \ - queue_for_each_ctx((q), __x, __i) \ - __ret += sum; \ - __ret; \ -}) - #endif -- cgit v1.2.3 From fac8e0f579695a3ecbc4d3cac369139d7f819971 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Sat, 19 Mar 2016 09:32:01 -0700 Subject: tunnels: Don't apply GRO to multiple layers of encapsulation. When drivers express support for TSO of encapsulated packets, they only mean that they can do it for one layer of encapsulation. Supporting additional levels would mean updating, at a minimum, more IP length fields and they are unaware of this. No encapsulation device expresses support for handling offloaded encapsulated packets, so we won't generate these types of frames in the transmit path. However, GRO doesn't have a check for multiple levels of encapsulation and will attempt to build them. UDP tunnel GRO actually does prevent this situation but it only handles multiple UDP tunnels stacked on top of each other. This generalizes that solution to prevent any kind of tunnel stacking that would cause problems. Fixes: bf5a755f ("net-gre-gro: Add GRE support to the GRO stack") Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be693b34662f..f9eebd518545 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2096,8 +2096,8 @@ struct napi_gro_cb { /* This is non-zero if the packet may be of the same flow. */ u8 same_flow:1; - /* Used in udp_gro_receive */ - u8 udp_mark:1; + /* Used in tunnel GRO receive */ + u8 encap_mark:1; /* GRO checksum is valid */ u8 csum_valid:1; -- cgit v1.2.3 From ebf918cf9922748b9d4d9bf6a2620530cdc5a1d0 Mon Sep 17 00:00:00 2001 From: Tina Ruchandani Date: Sat, 19 Mar 2016 11:21:14 -0700 Subject: isdn: Use ktime_t instead of 'struct timeval' 'struct timeval' uses 32-bit representation for seconds which will overflow in year 2038 and beyond. mISDN/clock.c needs to compute and store elapsed time in intervals of 125 microseconds. This patch replaces the usage of 'struct timeval' with 64-bit ktime_t which is y2038 safe. The patch also replaces do_gettimeofday() (wall-clock time) with ktime_get() (monotonic time) since we only care about elapsed time here. Signed-off-by: Tina Ruchandani Suggested-by: Arnd Bergmnann Suggested-by: David Miller Signed-off-by: David S. Miller --- include/linux/mISDNif.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h index 246a3529ecf6..ac02c54520e9 100644 --- a/include/linux/mISDNif.h +++ b/include/linux/mISDNif.h @@ -596,7 +596,7 @@ static inline struct mISDNdevice *dev_to_mISDN(struct device *dev) } extern void set_channel_address(struct mISDNchannel *, u_int, u_int); -extern void mISDN_clock_update(struct mISDNclock *, int, struct timeval *); +extern void mISDN_clock_update(struct mISDNclock *, int, ktime_t *); extern unsigned short mISDN_clock_get(void); extern const char *mISDNDevName4ch(struct mISDNchannel *); -- cgit v1.2.3 From b47bcb93bbf201e9c5af698945755efeb60c0bc8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 29 Feb 2016 10:53:11 -0500 Subject: dma-buf/fence: fix fence_is_later v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A fence is never later than itself. This caused a bunch of overhead for AMDGPU. v2: simplify check as suggested by Michel. Signed-off-by: Christian König Reviewed-by: Michel Dänzer Reviewed-by: Alex Deucher Reviewed-by: Gustavo Padovan Reviewed-by: Maarten Lankhorst Signed-off-by: Alex Deucher Signed-off-by: Sumit Semwal Signed-off-by: Daniel Vetter --- include/linux/fence.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index bb522011383b..5aa95eb886f7 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -292,7 +292,7 @@ static inline bool fence_is_later(struct fence *f1, struct fence *f2) if (WARN_ON(f1->context != f2->context)) return false; - return f1->seqno - f2->seqno < INT_MAX; + return (int)(f1->seqno - f2->seqno) > 0; } /** -- cgit v1.2.3 From aace66b170ce7feda2d1860a81eefff37fa9d1d2 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Wed, 16 Mar 2016 19:23:14 -0500 Subject: mailbox: Introduce TI message manager driver Support for TI Message Manager Module. This hardware block manages a bunch of hardware queues meant for communication between processor entities. Clients sitting on top of this would manage the required protocol for communicating with the counterpart entities. For more details on TI Message Manager hardware block, see documentation that will is available here: http://www.ti.com/lit/ug/spruhy8/spruhy8.pdf Chapter 8.1(Message Manager) Signed-off-by: Nishanth Menon Signed-off-by: Jassi Brar --- include/linux/soc/ti/ti-msgmgr.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/soc/ti/ti-msgmgr.h (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h new file mode 100644 index 000000000000..eac8e0c6fe11 --- /dev/null +++ b/include/linux/soc/ti/ti-msgmgr.h @@ -0,0 +1,35 @@ +/* + * Texas Instruments' Message Manager + * + * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/ + * Nishanth Menon + * + * 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. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef TI_MSGMGR_H +#define TI_MSGMGR_H + +/** + * struct ti_msgmgr_message - Message Manager structure + * @len: Length of data in the Buffer + * @buf: Buffer pointer + * + * This is the structure for data used in mbox_send_message + * the length of data buffer used depends on the SoC integration + * parameters - each message may be 64, 128 bytes long depending + * on SoC. Client is supposed to be aware of this. + */ +struct ti_msgmgr_message { + size_t len; + u8 *buf; +}; + +#endif /* TI_MSGMGR_H */ -- cgit v1.2.3 From b06e7de8a9d8d1d540ec122bbdf2face2a211634 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 23 Feb 2016 10:25:22 +0200 Subject: net/mlx5_core: Refactor device capability function Device capability function was called similar in all places. It was called twice for every queried parameter, while the difference between calls was in HCA capability mode only. The change proposed unify these calls into one function. Signed-off-by: Leon Romanovsky Reviewed-by: Saeed Mahameed Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9108904a6a56..406b27ec1d42 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -706,8 +706,7 @@ void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr); int mlx5_cmd_status_to_err_v2(void *ptr); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, - enum mlx5_cap_mode cap_mode); +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, -- cgit v1.2.3 From 3f0393a57509c200aeecc5e3984bf1a47bffc578 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 23 Feb 2016 10:25:23 +0200 Subject: net/mlx5_core: Introduce offload arithmetic hardware capabilities Define the necessary hardware structures for the offload arithmetic capabilities and read/cache them on driver load. Signed-off-by: Sagi Grimberg Signed-off-by: Leon Romanovsky Reviewed-by: Saeed Mahameed Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 6 ++++++ include/linux/mlx5/mlx5_ifc.h | 31 ++++++++++++++++++++++++++++++- 2 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 9566b3b3b2c5..4b531c44b3c7 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1219,6 +1219,8 @@ enum mlx5_cap_type { MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, + MLX5_CAP_RESERVED, + MLX5_CAP_VECTOR_CALC, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1281,6 +1283,10 @@ enum mlx5_cap_type { #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) +#define MLX5_CAP_VECTOR_CALC(mdev, cap) \ + MLX5_GET(vector_calc_cap, \ + mdev->hca_caps_cur[MLX5_CAP_VECTOR_CALC], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a3cacab22849..ad0a44b1592c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -616,6 +616,33 @@ struct mlx5_ifc_odp_cap_bits { u8 reserved_at_e0[0x720]; }; +struct mlx5_ifc_calc_op { + u8 reserved_at_0[0x10]; + u8 reserved_at_10[0x9]; + u8 op_swap_endianness[0x1]; + u8 op_min[0x1]; + u8 op_xor[0x1]; + u8 op_or[0x1]; + u8 op_and[0x1]; + u8 op_max[0x1]; + u8 op_add[0x1]; +}; + +struct mlx5_ifc_vector_calc_cap_bits { + u8 calc_matrix[0x1]; + u8 reserved_at_1[0x1f]; + u8 reserved_at_20[0x8]; + u8 max_vec_count[0x8]; + u8 reserved_at_30[0xd]; + u8 max_chunk_size[0x3]; + struct mlx5_ifc_calc_op calc0; + struct mlx5_ifc_calc_op calc1; + struct mlx5_ifc_calc_op calc2; + struct mlx5_ifc_calc_op calc3; + + u8 reserved_at_e0[0x720]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -770,7 +797,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cd[0x1]; u8 reserved_at_22c[0x1]; u8 apm[0x1]; - u8 reserved_at_22e[0x2]; + u8 vector_calc[0x1]; + u8 reserved_at_22f[0x1]; u8 imaicl[0x1]; u8 reserved_at_231[0x4]; u8 qkv[0x1]; @@ -1940,6 +1968,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; + struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; u8 reserved_at_0[0x8000]; }; -- cgit v1.2.3 From cc8e27cc97318471b7e707932d5b93b0d5f70830 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 11 Mar 2016 22:58:34 +0200 Subject: net/core: Add support for configuring VF GUIDs Add two new NLAs to support configuration of Infiniband node or port GUIDs. New applications can choose to use this interface to configure GUIDs with iproute2 with commands such as: ip link set dev ib0 vf 0 node_guid 00:02:c9:03:00:21:6e:70 ip link set dev ib0 vf 0 port_guid 00:02:c9:03:00:21:6e:78 A new ndo, ndo_sef_vf_guid is introduced to notify the net device of the request to change the GUID. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Doug Ledford --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5440b7b705eb..7b4ae218b90b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1147,6 +1147,9 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_set_vf_guid)(struct net_device *dev, + int vf, u64 guid, + int guid_type); int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); -- cgit v1.2.3 From 2a4826fe746e01712ca53902ee75c1a1f6c0a4aa Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 11 Mar 2016 22:58:40 +0200 Subject: net/mlx5_core: Add VF param when querying vport counter Add a vf parameter to mlx5_core_query_vport_counter so we can call it to query counters of virtual functions. Also update current users of the API. PFs may call mlx5_core_query_vport_counter with other_vport set to indicate that they are querying a virtual function. The virtual function to be queried is given by the vf parameter. Virtual function numbering is zero based so the first VF is 0 and so on. When a PF queries its own function, the other_vport parameter is cleared. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Doug Ledford --- include/linux/mlx5/vport.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index a9f2bcc98cab..aafb3e48b5f8 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -93,6 +93,7 @@ int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev); int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev); int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, - u8 port_num, void *out, size_t out_sz); + int vf, u8 port_num, void *out, + size_t out_sz); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 1f324bff9ba3db276f074169d5b4af9e9c117ba1 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 11 Mar 2016 22:58:41 +0200 Subject: net/mlx5_core: Implement modify HCA vport command Implement the modify HCA vport commands used to modify the parameters of virtual HCA's ports. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Doug Ledford --- include/linux/mlx5/vport.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index aafb3e48b5f8..bd93e6323603 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -95,5 +95,9 @@ int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev); int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, int vf, u8 port_num, void *out, size_t out_sz); +int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, + u8 other_vport, u8 port_num, + int vf, + struct mlx5_hca_vport_context *req); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From eff901d30e6cebd940072637f112ce4d0090ac12 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 11 Mar 2016 22:58:42 +0200 Subject: IB/mlx5: Implement callbacks for manipulating VFs Implement the IB defined callbacks used to manipulate the policy for the link state, set GUIDs or get statistics information. This functionality is added into a new file that will be used to add any SRIOV related functionality to the mlx5 IB layer. The following callbacks have been added: mlx5_ib_get_vf_config mlx5_ib_set_vf_link_state mlx5_ib_get_vf_stats mlx5_ib_set_vf_guid In addition, publish whether this device is based on a virtual function. In mlx5 supported devices, virtual functions are implemented as vHCAs. vHCAs have their own QP number space so it is possible that two vHCAs will use a QP with the same number at the same time. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 5 ++++- include/linux/mlx5/mlx5_ifc.h | 6 ++++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 406b27ec1d42..e1d987fb49b2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -613,7 +613,10 @@ struct mlx5_pas { }; enum port_state_policy { - MLX5_AAA_000 + MLX5_POLICY_DOWN = 0, + MLX5_POLICY_UP = 1, + MLX5_POLICY_FOLLOW = 2, + MLX5_POLICY_INVALID = 0xffffffff }; enum phy_port_state { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ad0a44b1592c..bb9e07ca6534 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3696,6 +3696,12 @@ struct mlx5_ifc_query_hca_vport_pkey_in_bits { u8 pkey_index[0x10]; }; +enum { + MLX5_HCA_VPORT_SEL_PORT_GUID = 1 << 0, + MLX5_HCA_VPORT_SEL_NODE_GUID = 1 << 1, + MLX5_HCA_VPORT_SEL_STATE_POLICY = 1 << 2, +}; + struct mlx5_ifc_query_hca_vport_gid_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit v1.2.3 From afc54992296a5e7f7d2e41456ed90789b01a4e7b Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Mon, 21 Mar 2016 04:53:13 -0400 Subject: NTB: Make _addr functions optional in the API The functions ntb_peer_db_addr and ntb_peer_spad_addr were required by the api. The functions already support returning an error, so any existing calling code should already check for it. Any existing code using drivers that implement the functions will not be affected. Signed-off-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index f798e2afba88..6f47562d477b 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -284,7 +284,7 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->db_read_mask && */ ops->db_set_mask && ops->db_clear_mask && - ops->peer_db_addr && + /* ops->peer_db_addr && */ /* ops->peer_db_read && */ ops->peer_db_set && /* ops->peer_db_clear && */ @@ -295,7 +295,7 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) ops->spad_count && ops->spad_read && ops->spad_write && - ops->peer_spad_addr && + /* ops->peer_spad_addr && */ /* ops->peer_spad_read && */ ops->peer_spad_write && 1; @@ -757,6 +757,9 @@ static inline int ntb_peer_db_addr(struct ntb_dev *ntb, phys_addr_t *db_addr, resource_size_t *db_size) { + if (!ntb->ops->peer_db_addr) + return -EINVAL; + return ntb->ops->peer_db_addr(ntb, db_addr, db_size); } @@ -948,6 +951,9 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, phys_addr_t *spad_addr) { + if (!ntb->ops->peer_spad_addr) + return -EINVAL; + return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); } -- cgit v1.2.3 From 6d0e24cd07f7e97015d958299fda535e459d2c99 Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Mon, 21 Mar 2016 20:58:28 +0000 Subject: net: add missing descriptions in net_device_priv_flags The flags IFF_XMIT_DST_RELEASE_PERM, IFF_IPVLAN_MASTER and IFF_IPVLAN_SLAVE are missing descriptions for the Documentation. Adding them. Signed-off-by: Luis de Bethencourt Suggested-by: Benjamin Poirier Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f9eebd518545..fd07734fb277 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1320,6 +1320,10 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account + * underlying stacked devices + * @IFF_IPVLAN_MASTER: IPvlan master device + * @IFF_IPVLAN_SLAVE: IPvlan slave device * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master -- cgit v1.2.3 From 62d885fe73e0032004e756b25101ac6c9ebf85dd Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Mon, 21 Mar 2016 14:08:28 -0700 Subject: net: Add missing kernel-doc for netdev ptype lists .//include/linux/netdevice.h:1826: warning: No description found for parameter 'ptype_all' .//include/linux/netdevice.h:1826: warning: No description found for parameter 'ptype_specific' Introduced by commit 7866a621043f ("dev: add per net_device packet type chains") Cc: Salam Noureddine Signed-off-by: Benjamin Poirier Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd07734fb277..3f6385d27b81 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1418,6 +1418,8 @@ enum netdev_priv_flags { * @unreg_list: List entry, that is used, when we are unregistering the * device, see the function unregister_netdev * @close_list: List entry, that is used, when we are closing the device + * @ptype_all: Device-specific packet handlers for all protocols + * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding * @all_adj_list: All linked devices, *including* neighbours -- cgit v1.2.3 From 3debb0a9ddb16526de8b456491b7db60114f7b5e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 22 Mar 2016 17:30:58 -0400 Subject: tracing: Fix trace_printk() to print when not using bprintk() The trace_printk() code will allocate extra buffers if the compile detects that a trace_printk() is used. To do this, the format of the trace_printk() is saved to the __trace_printk_fmt section, and if that section is bigger than zero, the buffers are allocated (along with a message that this has happened). If trace_printk() uses a format that is not a constant, and thus something not guaranteed to be around when the print happens, the compiler optimizes the fmt out, as it is not used, and the __trace_printk_fmt section is not filled. This means the kernel will not allocate the special buffers needed for the trace_printk() and the trace_printk() will not write anything to the tracing buffer. Adding a "__used" to the variable in the __trace_printk_fmt section will keep it around, even though it is set to NULL. This will keep the string from being printed in the debugfs/tracing/printk_formats section as it is not needed. Reported-by: Vlastimil Babka Fixes: 07d777fe8c398 "tracing: Add percpu buffers for trace_printk()" Cc: stable@vger.kernel.org # v3.5+ Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..95452f72349a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -635,7 +635,7 @@ do { \ #define do_trace_printk(fmt, args...) \ do { \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ @@ -679,7 +679,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); */ #define trace_puts(str) ({ \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(str) ? str : NULL; \ \ @@ -701,7 +701,7 @@ extern void trace_dump_stack(int skip); #define ftrace_vprintk(fmt, vargs) \ do { \ if (__builtin_constant_p(fmt)) { \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ -- cgit v1.2.3 From 5180e3e24fd3e8e7ea46fbe21e10f5ea3fb1edaa Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 22 Mar 2016 14:24:43 -0700 Subject: compat: add in_compat_syscall to ask whether we're in a compat syscall A lot of code currently abuses is_compat_task to determine this. Signed-off-by: Andy Lutomirski Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: Clemens Ladisch Cc: David Airlie Cc: David Herrmann Cc: David Miller Cc: Dmitry Torokhov Cc: Eric Paris Cc: Herbert Xu Cc: Ingo Molnar Acked-by: Jiri Kosina Cc: Matt Fleming Cc: Neil Horman Cc: Oded Gabbay Cc: Oleg Drokin Cc: Oleg Nesterov Cc: Paul Moore Cc: Sam Ravnborg Cc: Steffen Klassert Cc: Thomas Gleixner Cc: Vlad Yasevich Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index fe4ccd0c748a..f964ef79e0ad 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -5,6 +5,8 @@ * syscall compatibility layer. */ +#include + #ifdef CONFIG_COMPAT #include @@ -719,9 +721,22 @@ asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, int, const char __user *); + +/* + * For most but not all architectures, "am I in a compat syscall?" and + * "am I a compat task?" are the same question. For architectures on which + * they aren't the same question, arch code can override in_compat_syscall. + */ + +#ifndef in_compat_syscall +static inline bool in_compat_syscall(void) { return is_compat_task(); } +#endif + #else #define is_compat_task() (0) +static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ + #endif /* _LINUX_COMPAT_H */ -- cgit v1.2.3 From 378c6520e7d29280f400ef2ceaf155c86f05a71a Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 22 Mar 2016 14:25:36 -0700 Subject: fs/coredump: prevent fsuid=0 dumps into user-controlled directories This commit fixes the following security hole affecting systems where all of the following conditions are fulfilled: - The fs.suid_dumpable sysctl is set to 2. - The kernel.core_pattern sysctl's value starts with "/". (Systems where kernel.core_pattern starts with "|/" are not affected.) - Unprivileged user namespace creation is permitted. (This is true on Linux >=3.8, but some distributions disallow it by default using a distro patch.) Under these conditions, if a program executes under secure exec rules, causing it to run with the SUID_DUMP_ROOT flag, then unshares its user namespace, changes its root directory and crashes, the coredump will be written using fsuid=0 and a path derived from kernel.core_pattern - but this path is interpreted relative to the root directory of the process, allowing the attacker to control where a coredump will be written with root privileges. To fix the security issue, always interpret core_pattern for dumps that are written under SUID_DUMP_ROOT relative to the root directory of init. Signed-off-by: Jann Horn Acked-by: Kees Cook Cc: Al Viro Cc: "Eric W. Biederman" Cc: Andy Lutomirski Cc: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 35d99266ca9a..14a97194b34b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2263,7 +2263,7 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags, extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, - const char *, int); + const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); -- cgit v1.2.3 From 95f27356e4a8982257ecae6bc44c650772d77659 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 22 Mar 2016 14:25:39 -0700 Subject: cpumask: remove incorrect information from comment Since commit cdfdef75e795 ("cpumask: only allocate nr_cpumask_bits."), this comment above cpumask_size() is no longer relevant. Signed-off-by: Eric Biggers Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index fc14275ff34e..40cee6b77a93 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -607,8 +607,6 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) /** * cpumask_size - size to allocate for a 'struct cpumask' in bytes - * - * This will eventually be a runtime variable, depending on nr_cpu_ids. */ static inline size_t cpumask_size(void) { -- cgit v1.2.3 From 8b189fdbc5f68f3f43e67004de25f75c1a5b4e51 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:00 -0700 Subject: rapidio: add query_mport operation Add mport query operation to report master port RapidIO capabilities and run time configuration to upper level drivers. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/rio_regs.h | 3 +++ 2 files changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index cde976e86b48..8996a629a321 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -314,6 +314,50 @@ struct rio_net { struct rio_id_table destid_table; /* destID allocation table */ }; +enum rio_link_speed { + RIO_LINK_DOWN = 0, /* SRIO Link not initialized */ + RIO_LINK_125 = 1, /* 1.25 GBaud */ + RIO_LINK_250 = 2, /* 2.5 GBaud */ + RIO_LINK_312 = 3, /* 3.125 GBaud */ + RIO_LINK_500 = 4, /* 5.0 GBaud */ + RIO_LINK_625 = 5 /* 6.25 GBaud */ +}; + +enum rio_link_width { + RIO_LINK_1X = 0, + RIO_LINK_1XR = 1, + RIO_LINK_2X = 3, + RIO_LINK_4X = 2, + RIO_LINK_8X = 4, + RIO_LINK_16X = 5 +}; + +enum rio_mport_flags { + RIO_MPORT_DMA = (1 << 0), /* supports DMA data transfers */ + RIO_MPORT_DMA_SG = (1 << 1), /* DMA supports HW SG mode */ + RIO_MPORT_IBSG = (1 << 2), /* inbound mapping supports SG */ +}; + +/** + * struct rio_mport_attr - RIO mport device attributes + * @flags: mport device capability flags + * @link_speed: SRIO link speed value (as defined by RapidIO specification) + * @link_width: SRIO link width value (as defined by RapidIO specification) + * @dma_max_sge: number of SG list entries that can be handled by DMA channel(s) + * @dma_max_size: max number of bytes in single DMA transfer (SG entry) + * @dma_align: alignment shift for DMA operations (as for other DMA operations) + */ +struct rio_mport_attr { + int flags; + int link_speed; + int link_width; + + /* DMA capability info: valid only if RIO_MPORT_DMA flag is set */ + int dma_max_sge; + int dma_max_size; + int dma_align; +}; + /* Low-level architecture-dependent routines */ /** @@ -333,6 +377,7 @@ struct rio_net { * @get_inb_message: Callback to get a message from an inbound mailbox queue. * @map_inb: Callback to map RapidIO address region into local memory space. * @unmap_inb: Callback to unmap RapidIO address region mapped with map_inb(). + * @query_mport: Callback to query mport device attributes. */ struct rio_ops { int (*lcread) (struct rio_mport *mport, int index, u32 offset, int len, @@ -358,6 +403,8 @@ struct rio_ops { int (*map_inb)(struct rio_mport *mport, dma_addr_t lstart, u64 rstart, u32 size, u32 flags); void (*unmap_inb)(struct rio_mport *mport, dma_addr_t lstart); + int (*query_mport)(struct rio_mport *mport, + struct rio_mport_attr *attr); }; #define RIO_RESOURCE_MEM 0x00000100 @@ -481,5 +528,7 @@ extern int rio_open_inb_mbox(struct rio_mport *, void *, int, int); extern void rio_close_inb_mbox(struct rio_mport *, int); extern int rio_open_outb_mbox(struct rio_mport *, void *, int, int); extern void rio_close_outb_mbox(struct rio_mport *, int); +extern int rio_query_mport(struct rio_mport *port, + struct rio_mport_attr *mport_attr); #endif /* LINUX_RIO_H */ diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index 218168a2b5e9..1063ae382bc2 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -238,6 +238,8 @@ #define RIO_PORT_N_ACK_INBOUND 0x3f000000 #define RIO_PORT_N_ACK_OUTSTAND 0x00003f00 #define RIO_PORT_N_ACK_OUTBOUND 0x0000003f +#define RIO_PORT_N_CTL2_CSR(x) (0x0054 + x*0x20) +#define RIO_PORT_N_CTL2_SEL_BAUD 0xf0000000 #define RIO_PORT_N_ERR_STS_CSR(x) (0x0058 + x*0x20) #define RIO_PORT_N_ERR_STS_PW_OUT_ES 0x00010000 /* Output Error-stopped */ #define RIO_PORT_N_ERR_STS_PW_INP_ES 0x00000100 /* Input Error-stopped */ @@ -249,6 +251,7 @@ #define RIO_PORT_N_CTL_PWIDTH 0xc0000000 #define RIO_PORT_N_CTL_PWIDTH_1 0x00000000 #define RIO_PORT_N_CTL_PWIDTH_4 0x40000000 +#define RIO_PORT_N_CTL_IPW 0x38000000 /* Initialized Port Width */ #define RIO_PORT_N_CTL_P_TYP_SER 0x00000001 #define RIO_PORT_N_CTL_LOCKOUT 0x00000002 #define RIO_PORT_N_CTL_EN_RX_SER 0x00200000 -- cgit v1.2.3 From 83dc2cbc1136108068637d5c98636647f7b82461 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:05 -0700 Subject: rapidio: add shutdown notification for RapidIO devices Add bus-specific callback to stop RapidIO devices during a system shutdown. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 8996a629a321..c64a0baf37c8 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -423,6 +423,7 @@ struct rio_ops { * @id_table: RIO device ids to be associated with this driver * @probe: RIO device inserted * @remove: RIO device removed + * @shutdown: shutdown notification callback * @suspend: RIO device suspended * @resume: RIO device awakened * @enable_wake: RIO device enable wake event @@ -437,6 +438,7 @@ struct rio_driver { const struct rio_device_id *id_table; int (*probe) (struct rio_dev * dev, const struct rio_device_id * id); void (*remove) (struct rio_dev * dev); + void (*shutdown)(struct rio_dev *dev); int (*suspend) (struct rio_dev * dev, u32 state); int (*resume) (struct rio_dev * dev); int (*enable_wake) (struct rio_dev * dev, u32 state, int enable); -- cgit v1.2.3 From e6b585ca6e81badeb3d42db3cc408174f2826034 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:17 -0700 Subject: rapidio: move net allocation into core code Make net allocation/release routines available to all components of RapidIO subsystem by moving code from rio-scan enumerator. Make destination ID allocation method private to existing enumerator because other enumeration methods can use their own algorithm. Setup net device object as a parent of all RapidIO devices residing in it and register net as a child of active mport device. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index c64a0baf37c8..36086bf7e6f9 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -202,6 +202,7 @@ struct rio_dev { #define to_rio_dev(n) container_of(n, struct rio_dev, dev) #define sw_to_rio_dev(n) container_of(n, struct rio_dev, rswitch[0]) #define to_rio_mport(n) container_of(n, struct rio_mport, dev) +#define to_rio_net(n) container_of(n, struct rio_net, dev) /** * struct rio_msg - RIO message event @@ -237,6 +238,7 @@ enum rio_phy_type { * @dbells: List of doorbell events * @node: Node in global list of master ports * @nnode: Node in network list of master ports + * @net: RIO net this mport is attached to * @iores: I/O mem resource that this master port interface owns * @riores: RIO resources that this master port interfaces owns * @inb_msg: RIO inbound message event descriptors @@ -258,6 +260,7 @@ struct rio_mport { struct list_head dbells; /* list of doorbell events */ struct list_head node; /* node in global list of ports */ struct list_head nnode; /* node in net list of ports */ + struct rio_net *net; /* RIO net this mport is attached to */ struct resource iores; struct resource riores[RIO_MAX_MPORT_RESOURCES]; struct rio_msg inb_msg[RIO_MAX_MBOX]; @@ -287,13 +290,6 @@ struct rio_mport { */ #define RIO_SCAN_ENUM_NO_WAIT 0x00000001 /* Do not wait for enum completed */ -struct rio_id_table { - u16 start; /* logical minimal id */ - u32 max; /* max number of IDs in table */ - spinlock_t lock; - unsigned long *table; -}; - /** * struct rio_net - RIO network info * @node: Node in global list of RIO networks @@ -302,7 +298,9 @@ struct rio_id_table { * @mports: List of master ports accessing this network * @hport: Default port for accessing this network * @id: RIO network ID - * @destid_table: destID allocation table + * @dev: Device object + * @enum_data: private data specific to a network enumerator + * @release: enumerator-specific release callback */ struct rio_net { struct list_head node; /* node in list of networks */ @@ -311,7 +309,9 @@ struct rio_net { struct list_head mports; /* list of ports accessing net */ struct rio_mport *hport; /* primary port for accessing net */ unsigned char id; /* RIO network ID */ - struct rio_id_table destid_table; /* destID allocation table */ + struct device dev; + void *enum_data; /* private data for enumerator of the network */ + void (*release)(struct rio_net *net); }; enum rio_link_speed { -- cgit v1.2.3 From b77a2030dface6ea6b0d900bd8496ef41a9f3323 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:20 -0700 Subject: rapidio: add core mport removal support Add common mport removal support functions into the RapidIO subsystem core. Changes to the existing mport registration process have been made to avoid race conditions with active subsystem interfaces immediately after mport device registration: part of initialization code from rio_register_mport() have been moved into separate function rio_mport_initialize() to allow to perform mport registration as the final step of setup process. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 36086bf7e6f9..f833773cdc68 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -137,6 +137,13 @@ struct rio_switch_ops { int (*em_handle) (struct rio_dev *dev, u8 swport); }; +enum rio_device_state { + RIO_DEVICE_INITIALIZING, + RIO_DEVICE_RUNNING, + RIO_DEVICE_GONE, + RIO_DEVICE_SHUTDOWN, +}; + /** * struct rio_dev - RIO device info * @global_list: Node in list of all RIO devices @@ -165,6 +172,7 @@ struct rio_switch_ops { * @destid: Network destination ID (or associated destid for switch) * @hopcount: Hopcount to this device * @prev: Previous RIO device connected to the current one + * @state: device state * @rswitch: struct rio_switch (if valid for this device) */ struct rio_dev { @@ -194,6 +202,7 @@ struct rio_dev { u16 destid; u8 hopcount; struct rio_dev *prev; + atomic_t state; struct rio_switch rswitch[0]; /* RIO switch info */ }; @@ -255,6 +264,7 @@ enum rio_phy_type { * @priv: Master port private data * @dma: DMA device associated with mport * @nscan: RapidIO network enumeration/discovery operations + * @state: mport device state */ struct rio_mport { struct list_head dbells; /* list of doorbell events */ @@ -283,8 +293,14 @@ struct rio_mport { struct dma_device dma; #endif struct rio_scan *nscan; + atomic_t state; }; +static inline int rio_mport_is_running(struct rio_mport *mport) +{ + return atomic_read(&mport->state) == RIO_DEVICE_RUNNING; +} + /* * Enumeration/discovery control flags */ @@ -525,7 +541,9 @@ struct rio_scan_node { }; /* Architecture and hardware-specific functions */ +extern int rio_mport_initialize(struct rio_mport *); extern int rio_register_mport(struct rio_mport *); +extern int rio_unregister_mport(struct rio_mport *); extern int rio_open_inb_mbox(struct rio_mport *, void *, int, int); extern void rio_close_inb_mbox(struct rio_mport *, int); extern int rio_open_outb_mbox(struct rio_mport *, void *, int, int); -- cgit v1.2.3 From a7b4c636d83034f0e89d58651ef2e9b96564489a Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:35 -0700 Subject: rapidio: add lock protection for doorbell list Add lock protection around doorbell list handling to prevent list corruption on SMP platforms. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index f833773cdc68..948f60550ae5 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -248,6 +248,7 @@ enum rio_phy_type { * @node: Node in global list of master ports * @nnode: Node in network list of master ports * @net: RIO net this mport is attached to + * @lock: lock to synchronize lists manipulations * @iores: I/O mem resource that this master port interface owns * @riores: RIO resources that this master port interfaces owns * @inb_msg: RIO inbound message event descriptors @@ -271,6 +272,7 @@ struct rio_mport { struct list_head node; /* node in global list of ports */ struct list_head nnode; /* node in net list of ports */ struct rio_net *net; /* RIO net this mport is attached to */ + struct mutex lock; struct resource iores; struct resource riores[RIO_MAX_MPORT_RESOURCES]; struct rio_msg inb_msg[RIO_MAX_MBOX]; -- cgit v1.2.3 From 5024622f583eb242ed8040d0b9d1e0d2458d1db8 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:38 -0700 Subject: rapidio: move rio_local_set_device_id function to the common core Make function rio_local_set_device_id() common for all components of RapidIO subsystem. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio_drv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index 9fc2f213e74f..341b3bf78333 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -435,6 +435,7 @@ static inline void rio_set_drvdata(struct rio_dev *rdev, void *data) /* Misc driver helpers */ extern u16 rio_local_get_device_id(struct rio_mport *port); +extern void rio_local_set_device_id(struct rio_mport *port, u16 did); extern struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from); extern struct rio_dev *rio_get_asm(u16 vid, u16 did, u16 asm_vid, u16 asm_did, struct rio_dev *from); -- cgit v1.2.3 From b6cb95e8eb97e51a1a1b5609b59df859cc6dc2f2 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:41 -0700 Subject: rapidio: move rio_pw_enable into core code Make rio_pw_enable() routine available to other RapidIO drivers. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 2 ++ include/linux/rio_drv.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 948f60550ae5..cb3c47543bb0 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -266,6 +266,7 @@ enum rio_phy_type { * @dma: DMA device associated with mport * @nscan: RapidIO network enumeration/discovery operations * @state: mport device state + * @pwe_refcnt: port-write enable ref counter to track enable/disable requests */ struct rio_mport { struct list_head dbells; /* list of doorbell events */ @@ -296,6 +297,7 @@ struct rio_mport { #endif struct rio_scan *nscan; atomic_t state; + unsigned int pwe_refcnt; }; static inline int rio_mport_is_running(struct rio_mport *mport) diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index 341b3bf78333..9fb2bcd0a987 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -375,6 +375,7 @@ extern int rio_request_inb_pwrite(struct rio_dev *, int (*)(struct rio_dev *, union rio_pw_msg*, int)); extern int rio_release_inb_pwrite(struct rio_dev *); extern int rio_inb_pwrite_handler(union rio_pw_msg *pw_msg); +extern void rio_pw_enable(struct rio_mport *mport, int enable); /* LDM support */ int rio_register_driver(struct rio_driver *); -- cgit v1.2.3 From 9a0b062742e7e039273c0c2ba4b96ad9ec7e7d8f Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:44 -0700 Subject: rapidio: add global inbound port write interfaces Add new Port Write handler registration interfaces that attach PW handlers to local mport device objects. This is different from old interface that attaches PW callback to individual RapidIO device. The new interfaces are intended for use for common event handling (e.g. hot-plug notifications) while the old interface is available for individual device drivers. This patch is based on patch proposed by Andre van Herk but preserves existing per-device interface and adds lock protection for list handling. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 2 ++ include/linux/rio_drv.h | 9 ++++++++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index cb3c47543bb0..44f3da512c15 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -245,6 +245,7 @@ enum rio_phy_type { /** * struct rio_mport - RIO master port info * @dbells: List of doorbell events + * @pwrites: List of portwrite events * @node: Node in global list of master ports * @nnode: Node in network list of master ports * @net: RIO net this mport is attached to @@ -270,6 +271,7 @@ enum rio_phy_type { */ struct rio_mport { struct list_head dbells; /* list of doorbell events */ + struct list_head pwrites; /* list of portwrite events */ struct list_head node; /* node in global list of ports */ struct list_head nnode; /* node in net list of ports */ struct rio_net *net; /* RIO net this mport is attached to */ diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index 9fb2bcd0a987..5dff9a4cb675 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -374,7 +374,14 @@ extern void rio_unmap_inb_region(struct rio_mport *mport, dma_addr_t lstart); extern int rio_request_inb_pwrite(struct rio_dev *, int (*)(struct rio_dev *, union rio_pw_msg*, int)); extern int rio_release_inb_pwrite(struct rio_dev *); -extern int rio_inb_pwrite_handler(union rio_pw_msg *pw_msg); +extern int rio_add_mport_pw_handler(struct rio_mport *mport, void *dev_id, + int (*pwcback)(struct rio_mport *mport, void *dev_id, + union rio_pw_msg *msg, int step)); +extern int rio_del_mport_pw_handler(struct rio_mport *mport, void *dev_id, + int (*pwcback)(struct rio_mport *mport, void *dev_id, + union rio_pw_msg *msg, int step)); +extern int rio_inb_pwrite_handler(struct rio_mport *mport, + union rio_pw_msg *pw_msg); extern void rio_pw_enable(struct rio_mport *mport, int enable); /* LDM support */ -- cgit v1.2.3 From 93bdaca5018c02ba838f8fe2178fab261e2c1e68 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:26:50 -0700 Subject: rapidio: add outbound window support Add RapidIO controller (mport) outbound window configuration operations. This patch is a part of the original patch submitted by Li Yang: https://lists.ozlabs.org/pipermail/linuxppc-dev/2009-April/071210.html For some reason the original part was not applied to mainline code tree. The inbound window mapping part has been applied later during tsi721 mport driver submission. Now goes the second part with corresponding HW support. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Aurelien Jacquiot Cc: Andre van Herk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 5 +++++ include/linux/rio_drv.h | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 44f3da512c15..aa2323893e8d 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -400,6 +400,8 @@ struct rio_mport_attr { * @map_inb: Callback to map RapidIO address region into local memory space. * @unmap_inb: Callback to unmap RapidIO address region mapped with map_inb(). * @query_mport: Callback to query mport device attributes. + * @map_outb: Callback to map outbound address region into local memory space. + * @unmap_outb: Callback to unmap outbound RapidIO address region. */ struct rio_ops { int (*lcread) (struct rio_mport *mport, int index, u32 offset, int len, @@ -427,6 +429,9 @@ struct rio_ops { void (*unmap_inb)(struct rio_mport *mport, dma_addr_t lstart); int (*query_mport)(struct rio_mport *mport, struct rio_mport_attr *attr); + int (*map_outb)(struct rio_mport *mport, u16 destid, u64 rstart, + u32 size, u32 flags, dma_addr_t *laddr); + void (*unmap_outb)(struct rio_mport *mport, u16 destid, u64 rstart); }; #define RIO_RESOURCE_MEM 0x00000100 diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index 5dff9a4cb675..0834264fb7f2 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -369,6 +369,10 @@ void rio_release_region(struct rio_dev *, int); extern int rio_map_inb_region(struct rio_mport *mport, dma_addr_t local, u64 rbase, u32 size, u32 rflags); extern void rio_unmap_inb_region(struct rio_mport *mport, dma_addr_t lstart); +extern int rio_map_outb_region(struct rio_mport *mport, u16 destid, u64 rbase, + u32 size, u32 rflags, dma_addr_t *local); +extern void rio_unmap_outb_region(struct rio_mport *mport, + u16 destid, u64 rstart); /* Port-Write management */ extern int rio_request_inb_pwrite(struct rio_dev *, -- cgit v1.2.3 From e8de370188d098bb49483c287b44925957c3c9b6 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 22 Mar 2016 14:27:08 -0700 Subject: rapidio: add mport char device driver Add mport character device driver to provide user space interface to basic RapidIO subsystem operations. See included Documentation/rapidio/mport_cdev.txt for more details. [akpm@linux-foundation.org: fix printk warning on i386] [dan.carpenter@oracle.com: mport_cdev: fix some error codes] Signed-off-by: Alexandre Bounine Signed-off-by: Dan Carpenter Tested-by: Barry Wood Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Cc: Barry Wood Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio_mport_cdev.h | 271 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 271 insertions(+) create mode 100644 include/linux/rio_mport_cdev.h (limited to 'include/linux') diff --git a/include/linux/rio_mport_cdev.h b/include/linux/rio_mport_cdev.h new file mode 100644 index 000000000000..b65d19df76d2 --- /dev/null +++ b/include/linux/rio_mport_cdev.h @@ -0,0 +1,271 @@ +/* + * Copyright (c) 2015-2016, Integrated Device Technology Inc. + * Copyright (c) 2015, Prodrive Technologies + * Copyright (c) 2015, Texas Instruments Incorporated + * Copyright (c) 2015, RapidIO Trade Association + * All rights reserved. + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License(GPL) Version 2, or the BSD-3 Clause license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * 2. Redistributions in binary form must reproduce the above copyright notice, + * this list of conditions and the following disclaimer in the documentation + * and/or other materials provided with the distribution. + * + * 3. Neither the name of the copyright holder nor the names of its contributors + * may be used to endorse or promote products derived from this software without + * specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, + * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; + * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _RIO_MPORT_CDEV_H_ +#define _RIO_MPORT_CDEV_H_ + +#ifndef __user +#define __user +#endif + +struct rio_mport_maint_io { + uint32_t rioid; /* destID of remote device */ + uint32_t hopcount; /* hopcount to remote device */ + uint32_t offset; /* offset in register space */ + size_t length; /* length in bytes */ + void __user *buffer; /* data buffer */ +}; + +/* + * Definitions for RapidIO data transfers: + * - memory mapped (MAPPED) + * - packet generation from memory (TRANSFER) + */ +#define RIO_TRANSFER_MODE_MAPPED (1 << 0) +#define RIO_TRANSFER_MODE_TRANSFER (1 << 1) +#define RIO_CAP_DBL_SEND (1 << 2) +#define RIO_CAP_DBL_RECV (1 << 3) +#define RIO_CAP_PW_SEND (1 << 4) +#define RIO_CAP_PW_RECV (1 << 5) +#define RIO_CAP_MAP_OUTB (1 << 6) +#define RIO_CAP_MAP_INB (1 << 7) + +struct rio_mport_properties { + uint16_t hdid; + uint8_t id; /* Physical port ID */ + uint8_t index; + uint32_t flags; + uint32_t sys_size; /* Default addressing size */ + uint8_t port_ok; + uint8_t link_speed; + uint8_t link_width; + uint32_t dma_max_sge; + uint32_t dma_max_size; + uint32_t dma_align; + uint32_t transfer_mode; /* Default transfer mode */ + uint32_t cap_sys_size; /* Capable system sizes */ + uint32_t cap_addr_size; /* Capable addressing sizes */ + uint32_t cap_transfer_mode; /* Capable transfer modes */ + uint32_t cap_mport; /* Mport capabilities */ +}; + +/* + * Definitions for RapidIO events; + * - incoming port-writes + * - incoming doorbells + */ +#define RIO_DOORBELL (1 << 0) +#define RIO_PORTWRITE (1 << 1) + +struct rio_doorbell { + uint32_t rioid; + uint16_t payload; +}; + +struct rio_doorbell_filter { + uint32_t rioid; /* 0xffffffff to match all ids */ + uint16_t low; + uint16_t high; +}; + + +struct rio_portwrite { + uint32_t payload[16]; +}; + +struct rio_pw_filter { + uint32_t mask; + uint32_t low; + uint32_t high; +}; + +/* RapidIO base address for inbound requests set to value defined below + * indicates that no specific RIO-to-local address translation is requested + * and driver should use direct (one-to-one) address mapping. +*/ +#define RIO_MAP_ANY_ADDR (uint64_t)(~((uint64_t) 0)) + +struct rio_mmap { + uint32_t rioid; + uint64_t rio_addr; + uint64_t length; + uint64_t handle; + void *address; +}; + +struct rio_dma_mem { + uint64_t length; /* length of DMA memory */ + uint64_t dma_handle; /* handle associated with this memory */ + void *buffer; /* pointer to this memory */ +}; + + +struct rio_event { + unsigned int header; /* event type RIO_DOORBELL or RIO_PORTWRITE */ + union { + struct rio_doorbell doorbell; /* header for RIO_DOORBELL */ + struct rio_portwrite portwrite; /* header for RIO_PORTWRITE */ + } u; +}; + +enum rio_transfer_sync { + RIO_TRANSFER_SYNC, /* synchronous transfer */ + RIO_TRANSFER_ASYNC, /* asynchronous transfer */ + RIO_TRANSFER_FAF, /* fire-and-forget transfer */ +}; + +enum rio_transfer_dir { + RIO_TRANSFER_DIR_READ, /* Read operation */ + RIO_TRANSFER_DIR_WRITE, /* Write operation */ +}; + +/* + * RapidIO data exchange transactions are lists of individual transfers. Each + * transfer exchanges data between two RapidIO devices by remote direct memory + * access and has its own completion code. + * + * The RapidIO specification defines four types of data exchange requests: + * NREAD, NWRITE, SWRITE and NWRITE_R. The RapidIO DMA channel interface allows + * to specify the required type of write operation or combination of them when + * only the last data packet requires response. + * + * NREAD: read up to 256 bytes from remote device memory into local memory + * NWRITE: write up to 256 bytes from local memory to remote device memory + * without confirmation + * SWRITE: as NWRITE, but all addresses and payloads must be 64-bit aligned + * NWRITE_R: as NWRITE, but expect acknowledgment from remote device. + * + * The default exchange is chosen from NREAD and any of the WRITE modes as the + * driver sees fit. For write requests the user can explicitly choose between + * any of the write modes for each transaction. + */ +enum rio_exchange { + RIO_EXCHANGE_DEFAULT, /* Default method */ + RIO_EXCHANGE_NWRITE, /* All packets using NWRITE */ + RIO_EXCHANGE_SWRITE, /* All packets using SWRITE */ + RIO_EXCHANGE_NWRITE_R, /* Last packet NWRITE_R, others NWRITE */ + RIO_EXCHANGE_SWRITE_R, /* Last packet NWRITE_R, others SWRITE */ + RIO_EXCHANGE_NWRITE_R_ALL, /* All packets using NWRITE_R */ +}; + +struct rio_transfer_io { + uint32_t rioid; /* Target destID */ + uint64_t rio_addr; /* Address in target's RIO mem space */ + enum rio_exchange method; /* Data exchange method */ + void __user *loc_addr; + uint64_t handle; + uint64_t offset; /* Offset in buffer */ + uint64_t length; /* Length in bytes */ + uint32_t completion_code; /* Completion code for this transfer */ +}; + +struct rio_transaction { + uint32_t transfer_mode; /* Data transfer mode */ + enum rio_transfer_sync sync; /* Synchronization method */ + enum rio_transfer_dir dir; /* Transfer direction */ + size_t count; /* Number of transfers */ + struct rio_transfer_io __user *block; /* Array of transfers */ +}; + +struct rio_async_tx_wait { + uint32_t token; /* DMA transaction ID token */ + uint32_t timeout; /* Wait timeout in msec, if 0 use default TO */ +}; + +#define RIO_MAX_DEVNAME_SZ 20 + +struct rio_rdev_info { + uint32_t destid; + uint8_t hopcount; + uint32_t comptag; + char name[RIO_MAX_DEVNAME_SZ + 1]; +}; + +/* Driver IOCTL codes */ +#define RIO_MPORT_DRV_MAGIC 'm' + +#define RIO_MPORT_MAINT_HDID_SET \ + _IOW(RIO_MPORT_DRV_MAGIC, 1, uint16_t) +#define RIO_MPORT_MAINT_COMPTAG_SET \ + _IOW(RIO_MPORT_DRV_MAGIC, 2, uint32_t) +#define RIO_MPORT_MAINT_PORT_IDX_GET \ + _IOR(RIO_MPORT_DRV_MAGIC, 3, uint32_t) +#define RIO_MPORT_GET_PROPERTIES \ + _IOR(RIO_MPORT_DRV_MAGIC, 4, struct rio_mport_properties) +#define RIO_MPORT_MAINT_READ_LOCAL \ + _IOR(RIO_MPORT_DRV_MAGIC, 5, struct rio_mport_maint_io) +#define RIO_MPORT_MAINT_WRITE_LOCAL \ + _IOW(RIO_MPORT_DRV_MAGIC, 6, struct rio_mport_maint_io) +#define RIO_MPORT_MAINT_READ_REMOTE \ + _IOR(RIO_MPORT_DRV_MAGIC, 7, struct rio_mport_maint_io) +#define RIO_MPORT_MAINT_WRITE_REMOTE \ + _IOW(RIO_MPORT_DRV_MAGIC, 8, struct rio_mport_maint_io) +#define RIO_ENABLE_DOORBELL_RANGE \ + _IOW(RIO_MPORT_DRV_MAGIC, 9, struct rio_doorbell_filter) +#define RIO_DISABLE_DOORBELL_RANGE \ + _IOW(RIO_MPORT_DRV_MAGIC, 10, struct rio_doorbell_filter) +#define RIO_ENABLE_PORTWRITE_RANGE \ + _IOW(RIO_MPORT_DRV_MAGIC, 11, struct rio_pw_filter) +#define RIO_DISABLE_PORTWRITE_RANGE \ + _IOW(RIO_MPORT_DRV_MAGIC, 12, struct rio_pw_filter) +#define RIO_SET_EVENT_MASK \ + _IOW(RIO_MPORT_DRV_MAGIC, 13, unsigned int) +#define RIO_GET_EVENT_MASK \ + _IOR(RIO_MPORT_DRV_MAGIC, 14, unsigned int) +#define RIO_MAP_OUTBOUND \ + _IOWR(RIO_MPORT_DRV_MAGIC, 15, struct rio_mmap) +#define RIO_UNMAP_OUTBOUND \ + _IOW(RIO_MPORT_DRV_MAGIC, 16, struct rio_mmap) +#define RIO_MAP_INBOUND \ + _IOWR(RIO_MPORT_DRV_MAGIC, 17, struct rio_mmap) +#define RIO_UNMAP_INBOUND \ + _IOW(RIO_MPORT_DRV_MAGIC, 18, uint64_t) +#define RIO_ALLOC_DMA \ + _IOWR(RIO_MPORT_DRV_MAGIC, 19, struct rio_dma_mem) +#define RIO_FREE_DMA \ + _IOW(RIO_MPORT_DRV_MAGIC, 20, uint64_t) +#define RIO_TRANSFER \ + _IOWR(RIO_MPORT_DRV_MAGIC, 21, struct rio_transaction) +#define RIO_WAIT_FOR_ASYNC \ + _IOW(RIO_MPORT_DRV_MAGIC, 22, struct rio_async_tx_wait) +#define RIO_DEV_ADD \ + _IOW(RIO_MPORT_DRV_MAGIC, 23, struct rio_rdev_info) +#define RIO_DEV_DEL \ + _IOW(RIO_MPORT_DRV_MAGIC, 24, struct rio_rdev_info) + +#endif /* _RIO_MPORT_CDEV_H_ */ -- cgit v1.2.3 From 0335695dfa4df01edff5bb102b9a82a0668ee51e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 22 Mar 2016 14:27:11 -0700 Subject: cred/userns: define current_user_ns() as a function The current_user_ns() macro currently returns &init_user_ns when user namespaces are disabled, and that causes several warnings when building with gcc-6.0 in code that compares the result of the macro to &init_user_ns itself: fs/xfs/xfs_ioctl.c: In function 'xfs_ioctl_setattr_check_projid': fs/xfs/xfs_ioctl.c:1249:22: error: self-comparison always evaluates to true [-Werror=tautological-compare] if (current_user_ns() == &init_user_ns) This is a legitimate warning in principle, but here it isn't really helpful, so I'm reprasing the definition in a way that shuts up the warning. Apparently gcc only warns when comparing identical literals, but it can figure out that the result of an inline function can be identical to a constant expression in order to optimize a condition yet not warn about the fact that the condition is known at compile time. This is exactly what we want here, and it looks reasonable because we generally prefer inline functions over macros anyway. Signed-off-by: Arnd Bergmann Acked-by: Serge Hallyn Cc: David Howells Cc: Yaowei Bai Cc: James Morris Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/capability.h | 2 -- include/linux/cred.h | 5 ++++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index f314275d4e3f..00690ff92edf 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -40,8 +40,6 @@ struct inode; struct dentry; struct user_namespace; -struct user_namespace *current_user_ns(void); - extern const kernel_cap_t __cap_empty_set; extern const kernel_cap_t __cap_init_eff_set; diff --git a/include/linux/cred.h b/include/linux/cred.h index 8d70e1361ecd..257db64562e5 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -377,7 +377,10 @@ extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else -#define current_user_ns() (&init_user_ns) +static inline struct user_namespace *current_user_ns(void) +{ + return &init_user_ns; +} #endif -- cgit v1.2.3 From ebc41f20d77f6ad91f1f2d2af5147dc9bb6b5eea Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Tue, 22 Mar 2016 14:27:17 -0700 Subject: panic: change nmi_panic from macro to function Commit 1717f2096b54 ("panic, x86: Fix re-entrance problem due to panic on NMI") and commit 58c5661f2144 ("panic, x86: Allow CPUs to save registers even if looping in NMI context") introduced nmi_panic() which prevents concurrent/recursive execution of panic(). It also saves registers for the crash dump on x86. However, there are some cases where NMI handlers still use panic(). This patch set partially replaces them with nmi_panic() in those cases. Even this patchset is applied, some NMI or similar handlers (e.g. MCE handler) continue to use panic(). This is because I can't test them well and actual problems won't happen. For example, the possibility that normal panic and panic on MCE happen simultaneously is very low. This patch (of 3): Convert nmi_panic() to a proper function and export it instead of exporting internal implementation details to modules, for obvious reasons. Signed-off-by: Hidehiro Kawai Acked-by: Borislav Petkov Acked-by: Michal Nazarewicz Cc: Michal Hocko Cc: Rasmus Villemoes Cc: Nicolas Iooss Cc: Javi Merino Cc: Gobinda Charan Maji Cc: "Steven Rostedt (Red Hat)" Cc: Thomas Gleixner Cc: Vitaly Kuznetsov Cc: HATAYAMA Daisuke Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b82646ee70eb..a13c52ccd8ac 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -255,7 +255,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; -void nmi_panic_self_stop(struct pt_regs *); +void nmi_panic(struct pt_regs *regs, const char *msg); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); @@ -456,25 +456,6 @@ extern bool crash_kexec_post_notifiers; extern atomic_t panic_cpu; #define PANIC_CPU_INVALID -1 -/* - * A variant of panic() called from NMI context. We return if we've already - * panicked on this CPU. If another CPU already panicked, loop in - * nmi_panic_self_stop() which can provide architecture dependent code such - * as saving register state for crash dump. - */ -#define nmi_panic(regs, fmt, ...) \ -do { \ - int old_cpu, cpu; \ - \ - cpu = raw_smp_processor_id(); \ - old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \ - \ - if (old_cpu == PANIC_CPU_INVALID) \ - panic(fmt, ##__VA_ARGS__); \ - else if (old_cpu != cpu) \ - nmi_panic_self_stop(regs); \ -} while (0) - /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. -- cgit v1.2.3 From 5c9a8750a6409c63a0f01d51a9024861022f6593 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Tue, 22 Mar 2016 14:27:30 -0700 Subject: kernel: add kcov code coverage kcov provides code coverage collection for coverage-guided fuzzing (randomized testing). Coverage-guided fuzzing is a testing technique that uses coverage feedback to determine new interesting inputs to a system. A notable user-space example is AFL (http://lcamtuf.coredump.cx/afl/). However, this technique is not widely used for kernel testing due to missing compiler and kernel support. kcov does not aim to collect as much coverage as possible. It aims to collect more or less stable coverage that is function of syscall inputs. To achieve this goal it does not collect coverage in soft/hard interrupts and instrumentation of some inherently non-deterministic or non-interesting parts of kernel is disbled (e.g. scheduler, locking). Currently there is a single coverage collection mode (tracing), but the API anticipates additional collection modes. Initially I also implemented a second mode which exposes coverage in a fixed-size hash table of counters (what Quentin used in his original patch). I've dropped the second mode for simplicity. This patch adds the necessary support on kernel side. The complimentary compiler support was added in gcc revision 231296. We've used this support to build syzkaller system call fuzzer, which has found 90 kernel bugs in just 2 months: https://github.com/google/syzkaller/wiki/Found-Bugs We've also found 30+ bugs in our internal systems with syzkaller. Another (yet unexplored) direction where kcov coverage would greatly help is more traditional "blob mutation". For example, mounting a random blob as a filesystem, or receiving a random blob over wire. Why not gcov. Typical fuzzing loop looks as follows: (1) reset coverage, (2) execute a bit of code, (3) collect coverage, repeat. A typical coverage can be just a dozen of basic blocks (e.g. an invalid input). In such context gcov becomes prohibitively expensive as reset/collect coverage steps depend on total number of basic blocks/edges in program (in case of kernel it is about 2M). Cost of kcov depends only on number of executed basic blocks/edges. On top of that, kernel requires per-thread coverage because there are always background threads and unrelated processes that also produce coverage. With inlined gcov instrumentation per-thread coverage is not possible. kcov exposes kernel PCs and control flow to user-space which is insecure. But debugfs should not be mapped as user accessible. Based on a patch by Quentin Casasnovas. [akpm@linux-foundation.org: make task_struct.kcov_mode have type `enum kcov_mode'] [akpm@linux-foundation.org: unbreak allmodconfig] [akpm@linux-foundation.org: follow x86 Makefile layout standards] Signed-off-by: Dmitry Vyukov Reviewed-by: Kees Cook Cc: syzkaller Cc: Vegard Nossum Cc: Catalin Marinas Cc: Tavis Ormandy Cc: Will Deacon Cc: Quentin Casasnovas Cc: Kostya Serebryany Cc: Eric Dumazet Cc: Alexander Potapenko Cc: Kees Cook Cc: Bjorn Helgaas Cc: Sasha Levin Cc: David Drysdale Cc: Ard Biesheuvel Cc: Andrey Ryabinin Cc: Kirill A. Shutemov Cc: Jiri Slaby Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kcov.h | 29 +++++++++++++++++++++++++++++ include/linux/sched.h | 11 +++++++++++ 2 files changed, 40 insertions(+) create mode 100644 include/linux/kcov.h (limited to 'include/linux') diff --git a/include/linux/kcov.h b/include/linux/kcov.h new file mode 100644 index 000000000000..2883ac98c280 --- /dev/null +++ b/include/linux/kcov.h @@ -0,0 +1,29 @@ +#ifndef _LINUX_KCOV_H +#define _LINUX_KCOV_H + +#include + +struct task_struct; + +#ifdef CONFIG_KCOV + +void kcov_task_init(struct task_struct *t); +void kcov_task_exit(struct task_struct *t); + +enum kcov_mode { + /* Coverage collection is not enabled yet. */ + KCOV_MODE_DISABLED = 0, + /* + * Tracing coverage collection mode. + * Covered PCs are collected in a per-task buffer. + */ + KCOV_MODE_TRACE = 1, +}; + +#else + +static inline void kcov_task_init(struct task_struct *t) {} +static inline void kcov_task_exit(struct task_struct *t) {} + +#endif /* CONFIG_KCOV */ +#endif /* _LINUX_KCOV_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 084ed9fba620..34495d2d2d7b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -51,6 +51,7 @@ struct sched_param { #include #include #include +#include #include #include #include @@ -1818,6 +1819,16 @@ struct task_struct { /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ +#ifdef CONFIG_KCOV + /* Coverage collection mode enabled for this task (0 if disabled). */ + enum kcov_mode kcov_mode; + /* Size of the kcov_area. */ + unsigned kcov_size; + /* Buffer for coverage collection. */ + void *kcov_area; + /* kcov desciptor wired with this task or NULL. */ + struct kcov *kcov; +#endif #ifdef CONFIG_MEMCG struct mem_cgroup *memcg_in_oom; gfp_t memcg_oom_gfp_mask; -- cgit v1.2.3 From 21b2f44315d735345f02356239a819debdd89462 Mon Sep 17 00:00:00 2001 From: Stefani Seibold Date: Tue, 22 Mar 2016 14:27:42 -0700 Subject: kfifo: fix sparse complaints This patch fix complaints by the sparse tool when using kfifo_put() with non scalar types like structures (i.e. drivers/iio/industrialio-event.c). Casting a pointer to the value and read this pointer instead of directly casting the value will fix this. The generated code is equal. Signed-off-by: Stefani Seibold Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 473b43678ad1..41eb6fdf87a8 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -401,7 +401,7 @@ __kfifo_int_must_check_helper( \ ((typeof(__tmp->type))__kfifo->data) : \ (__tmp->buf) \ )[__kfifo->in & __tmp->kfifo.mask] = \ - (typeof(*__tmp->type))__val; \ + *(typeof(__tmp->type))&__val; \ smp_wmb(); \ __kfifo->in++; \ } \ -- cgit v1.2.3 From c907e0eb43a522de60fb651c011c553f87273222 Mon Sep 17 00:00:00 2001 From: Brian Starkey Date: Tue, 22 Mar 2016 14:28:00 -0700 Subject: memremap: add MEMREMAP_WC flag Add a flag to memremap() for writecombine mappings. Mappings satisfied by this flag will not be cached, however writes may be delayed or combined into more efficient bursts. This is most suitable for buffers written sequentially by the CPU for use by other DMA devices. Signed-off-by: Brian Starkey Reviewed-by: Catalin Marinas Cc: Dan Williams Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 32403b5716e5..e2c8419278c1 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -135,6 +135,7 @@ enum { /* See memremap() kernel-doc for usage description... */ MEMREMAP_WB = 1 << 0, MEMREMAP_WT = 1 << 1, + MEMREMAP_WC = 1 << 2, }; void *memremap(resource_size_t offset, size_t size, unsigned long flags); -- cgit v1.2.3 From f09e3f4fe42caad0c0f59c1489d2b3f512c070b5 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Wed, 23 Mar 2016 09:40:09 +0800 Subject: x86/apic: Remove declaration of unused hw_nmi_is_cpu_stuck Commit 10f9014912 ("x86: Cleanup hw_nmi.c cruft") removed unused code in the hw_nmi.c file because of the redesign of the hardlockup watchdog but left declaration of hw_nmi_is_cpu_stuck in linux/nmi.h, so remvoe it. Signed-off-by: Yaowei Bai Link: http://lkml.kernel.org/r/1458697210-3027-1-git-send-email-baiyaowei@cmss.chinamobile.com Signed-off-by: Thomas Gleixner --- include/linux/nmi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 7ec5b86735f3..4630eeae18e0 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -65,7 +65,6 @@ static inline bool trigger_allbutself_cpu_backtrace(void) #endif #ifdef CONFIG_LOCKUP_DETECTOR -int hw_nmi_is_cpu_stuck(struct pt_regs *); u64 hw_nmi_get_sample_period(int watchdog_thresh); extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; -- cgit v1.2.3 From 6c31da3464b4d28825d1827ee41a3a217b2dcf0e Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 19 Mar 2016 17:54:10 +0100 Subject: parisc,metag: Implement CONFIG_DEBUG_STACK_USAGE option On parisc and metag the stack grows upwards, so for those we need to scan the stack downwards in order to calculate how much stack a process has used. Tested on a 64bit parisc kernel. Signed-off-by: Helge Deller --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 34495d2d2d7b..589c4780b077 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2870,10 +2870,18 @@ static inline unsigned long stack_not_used(struct task_struct *p) unsigned long *n = end_of_stack(p); do { /* Skip over canary */ +# ifdef CONFIG_STACK_GROWSUP + n--; +# else n++; +# endif } while (!*n); +# ifdef CONFIG_STACK_GROWSUP + return (unsigned long)end_of_stack(p) - (unsigned long)n; +# else return (unsigned long)n - (unsigned long)end_of_stack(p); +# endif } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); -- cgit v1.2.3 From 5e82b4b2a0015ed0a659b22ef2ee3409a3c39e54 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 23 Mar 2016 13:47:23 -0500 Subject: net: Fix typos and whitespace. Fix typos. Capitalize CPU, NAPI, RCU consistently. Align structure indentation. No functional change intended; only comment and whitespace changes. Signed-off-by: Bjorn Helgaas Signed-off-by: David S. Miller --- include/linux/netdevice.h | 215 +++++++++++++++++++++++----------------------- 1 file changed, 106 insertions(+), 109 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3f6385d27b81..a675205df0f1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -81,8 +81,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, * function. Real network devices commonly used with qdiscs should only return * the driver transmit return codes though - when qdiscs are used, the actual * transmission happens asynchronously, so the value is not propagated to - * higher layers. Virtual network devices transmit synchronously, in this case - * the driver transmit return codes are consumed by dev_queue_xmit(), all + * higher layers. Virtual network devices transmit synchronously; in this case + * the driver transmit return codes are consumed by dev_queue_xmit(), and all * others are propagated to higher layers. */ @@ -129,7 +129,7 @@ static inline bool dev_xmit_complete(int rc) } /* - * Compute the worst case header length according to the protocols + * Compute the worst-case header length according to the protocols * used. */ @@ -246,7 +246,7 @@ struct hh_cache { unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; }; -/* Reserve HH_DATA_MOD byte aligned hard_header_len, but at least that much. +/* Reserve HH_DATA_MOD byte-aligned hard_header_len, but at least that much. * Alternative is: * dev->hard_header_len ? (dev->hard_header_len + * (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0 @@ -272,7 +272,7 @@ struct header_ops { }; /* These flag bits are private to the generic network queueing - * layer, they may not be explicitly referenced by any other + * layer; they may not be explicitly referenced by any other * code. */ @@ -286,7 +286,7 @@ enum netdev_state_t { /* - * This structure holds at boot time configured netdevice settings. They + * This structure holds boot-time configured netdevice settings. They * are then used in the device probing. */ struct netdev_boot_setup { @@ -304,7 +304,7 @@ struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct - * to the per-cpu poll_list, and whoever clears that bit + * to the per-CPU poll_list, and whoever clears that bit * can remove from the list right before clearing the bit. */ struct list_head poll_list; @@ -350,7 +350,7 @@ typedef enum gro_result gro_result_t; * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in * case skb->dev was changed by rx_handler. * @RX_HANDLER_EXACT: Force exact delivery, no wildcard. - * @RX_HANDLER_PASS: Do nothing, passe the skb as if no rx_handler was called. + * @RX_HANDLER_PASS: Do nothing, pass the skb as if no rx_handler was called. * * rx_handlers are functions called from inside __netif_receive_skb(), to do * special processing of the skb, prior to delivery to protocol handlers. @@ -365,19 +365,19 @@ typedef enum gro_result gro_result_t; * Upon return, rx_handler is expected to tell __netif_receive_skb() what to * do with the skb. * - * If the rx_handler consumed to skb in some way, it should return + * If the rx_handler consumed the skb in some way, it should return * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for - * the skb to be delivered in some other ways. + * the skb to be delivered in some other way. * * If the rx_handler changed skb->dev, to divert the skb to another * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the * new device will be called if it exists. * - * If the rx_handler consider the skb should be ignored, it should return + * If the rx_handler decides the skb should be ignored, it should return * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that * are registered on exact device (ptype->dev == skb->dev). * - * If the rx_handler didn't changed skb->dev, but want the skb to be normally + * If the rx_handler didn't change skb->dev, but wants the skb to be normally * delivered, it should return RX_HANDLER_PASS. * * A device without a registered rx_handler will behave as if rx_handler @@ -402,11 +402,11 @@ static inline bool napi_disable_pending(struct napi_struct *n) } /** - * napi_schedule_prep - check if napi can be scheduled - * @n: napi context + * napi_schedule_prep - check if NAPI can be scheduled + * @n: NAPI context * * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable + * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ @@ -418,7 +418,7 @@ static inline bool napi_schedule_prep(struct napi_struct *n) /** * napi_schedule - schedule NAPI poll - * @n: napi context + * @n: NAPI context * * Schedule NAPI poll routine to be called if it is not already * running. @@ -431,7 +431,7 @@ static inline void napi_schedule(struct napi_struct *n) /** * napi_schedule_irqoff - schedule NAPI poll - * @n: napi context + * @n: NAPI context * * Variant of napi_schedule(), assuming hard irqs are masked. */ @@ -455,7 +455,7 @@ void __napi_complete(struct napi_struct *n); void napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete - * @n: napi context + * @n: NAPI context * * Mark NAPI processing as complete. * Consider using napi_complete_done() instead. @@ -467,32 +467,32 @@ static inline void napi_complete(struct napi_struct *n) /** * napi_hash_add - add a NAPI to global hashtable - * @napi: napi context + * @napi: NAPI context * - * generate a new napi_id and store a @napi under it in napi_hash - * Used for busy polling (CONFIG_NET_RX_BUSY_POLL) + * Generate a new napi_id and store a @napi under it in napi_hash. + * Used for busy polling (CONFIG_NET_RX_BUSY_POLL). * Note: This is normally automatically done from netif_napi_add(), - * so might disappear in a future linux version. + * so might disappear in a future Linux version. */ void napi_hash_add(struct napi_struct *napi); /** * napi_hash_del - remove a NAPI from global table - * @napi: napi context + * @napi: NAPI context * - * Warning: caller must observe rcu grace period + * Warning: caller must observe RCU grace period * before freeing memory containing @napi, if * this function returns true. * Note: core networking stack automatically calls it - * from netif_napi_del() + * from netif_napi_del(). * Drivers might want to call this helper to combine all - * the needed rcu grace periods into a single one. + * the needed RCU grace periods into a single one. */ bool napi_hash_del(struct napi_struct *napi); /** * napi_disable - prevent NAPI from scheduling - * @n: napi context + * @n: NAPI context * * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. @@ -501,7 +501,7 @@ void napi_disable(struct napi_struct *n); /** * napi_enable - enable NAPI scheduling - * @n: napi context + * @n: NAPI context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. @@ -516,7 +516,7 @@ static inline void napi_enable(struct napi_struct *n) /** * napi_synchronize - wait until NAPI is not running - * @n: napi context + * @n: NAPI context * * Wait until NAPI is done being scheduled on this context. * Waits till any outstanding processing completes but @@ -559,7 +559,7 @@ enum netdev_queue_state_t { struct netdev_queue { /* - * read mostly part + * read-mostly part */ struct net_device *dev; struct Qdisc __rcu *qdisc; @@ -571,7 +571,7 @@ struct netdev_queue { int numa_node; #endif /* - * write mostly part + * write-mostly part */ spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; @@ -648,11 +648,11 @@ struct rps_dev_flow_table { /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). - * Each entry is a 32bit value. Upper part is the high order bits - * of flow hash, lower part is cpu number. + * Each entry is a 32bit value. Upper part is the high-order bits + * of flow hash, lower part is CPU number. * rps_cpu_mask is used to partition the space, depending on number of - * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 - * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f, + * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { @@ -674,7 +674,7 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, unsigned int index = hash & table->mask; u32 val = hash & ~rps_cpu_mask; - /* We only give a hint, preemption can change cpu under us */ + /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); if (table->ents[index] != val) @@ -807,21 +807,21 @@ struct tc_to_netdev { * optional and can be filled with a null pointer. * * int (*ndo_init)(struct net_device *dev); - * This function is called once when network device is registered. - * The network device can use this to any late stage initializaton - * or semantic validattion. It can fail with an error code which will - * be propogated back to register_netdev + * This function is called once when a network device is registered. + * The network device can use this for any late stage initialization + * or semantic validation. It can fail with an error code which will + * be propagated back to register_netdev. * * void (*ndo_uninit)(struct net_device *dev); * This function is called when device is unregistered or when registration * fails. It is not called if init fails. * * int (*ndo_open)(struct net_device *dev); - * This function is called when network device transistions to the up + * This function is called when a network device transitions to the up * state. * * int (*ndo_stop)(struct net_device *dev); - * This function is called when network device transistions to the down + * This function is called when a network device transitions to the down * state. * * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, @@ -832,7 +832,7 @@ struct tc_to_netdev { * corner cases, but the stack really does a non-trivial amount * of useless work if you return NETDEV_TX_BUSY. * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) - * Required can not be NULL. + * Required; cannot be NULL. * * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); @@ -842,34 +842,34 @@ struct tc_to_netdev { * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * void *accel_priv, select_queue_fallback_t fallback); - * Called to decide which queue to when device supports multiple + * Called to decide which queue to use when device supports multiple * transmit queues. * * void (*ndo_change_rx_flags)(struct net_device *dev, int flags); * This function is called to allow device receiver to make - * changes to configuration when multicast or promiscious is enabled. + * changes to configuration when multicast or promiscuous is enabled. * * void (*ndo_set_rx_mode)(struct net_device *dev); * This function is called device changes address list filtering. * If driver handles unicast address filtering, it should set - * IFF_UNICAST_FLT to its priv_flags. + * IFF_UNICAST_FLT in its priv_flags. * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address * needs to be changed. If this interface is not defined, the - * mac address can not be changed. + * MAC address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); - * Called when a user request an ioctl which can't be handled by - * the generic interface code. If not defined ioctl's return + * Called when a user requests an ioctl which can't be handled by + * the generic interface code. If not defined ioctls return * not supported error code. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface - * is retained for legacy reason, new devices should use the bus + * is retained for legacy reasons; new devices should use the bus * interface (PCI) for low level management. * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); @@ -878,7 +878,7 @@ struct tc_to_netdev { * will return an error. * * void (*ndo_tx_timeout)(struct net_device *dev); - * Callback uses when the transmitter has not made any progress + * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, @@ -896,11 +896,11 @@ struct tc_to_netdev { * neither operation. * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); - * If device support VLAN filtering this function is called when a + * If device supports VLAN filtering this function is called when a * VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); - * If device support VLAN filtering this function is called when a + * If device supports VLAN filtering this function is called when a * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); @@ -920,7 +920,7 @@ struct tc_to_netdev { * * Enable or disable the VF ability to query its RSS Redirection Table and * Hash Key. This is needed since on some devices VF share this information - * with PF and querying it may adduce a theoretical security risk. + * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) @@ -1030,20 +1030,20 @@ struct tc_to_netdev { * * void (*ndo_add_vxlan_port)(struct net_device *dev, * sa_family_t sa_family, __be16 port); - * Called by vxlan to notiy a driver about the UDP port and socket - * address family that vxlan is listnening to. It is called only when + * Called by vxlan to notify a driver about the UDP port and socket + * address family that vxlan is listening to. It is called only when * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * * void (*ndo_add_geneve_port)(struct net_device *dev, - * sa_family_t sa_family, __be16 port); + * sa_family_t sa_family, __be16 port); * Called by geneve to notify a driver about the UDP port and socket * address family that geneve is listnening to. It is called only when * a new port starts listening. The operation is protected by the * geneve_net->sock_lock. * * void (*ndo_del_geneve_port)(struct net_device *dev, - * sa_family_t sa_family, __be16 port); + * sa_family_t sa_family, __be16 port); * Called by geneve to notify the driver about a UDP port and socket * address family that geneve is not listening to anymore. The operation * is protected by the geneve_net->sock_lock. @@ -1072,9 +1072,9 @@ struct tc_to_netdev { * Callback to use for xmit over the accelerated station. This * is used in place of ndo_start_xmit on accelerated net * devices. - * netdev_features_t (*ndo_features_check) (struct sk_buff *skb, - * struct net_device *dev - * netdev_features_t features); + * netdev_features_t (*ndo_features_check)(struct sk_buff *skb, + * struct net_device *dev + * netdev_features_t features); * Called by core transmit path to determine if device is capable of * performing offload operations on a given packet. This is to give * the device an opportunity to implement any restrictions that cannot @@ -1088,7 +1088,7 @@ struct tc_to_netdev { * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. * void (*ndo_change_proto_down)(struct net_device *dev, - * bool proto_down); + * bool proto_down); * This function is used to pass protocol port error state information * to the switch driver. The switch driver can react to the proto_down * by doing a phys down on the associated switch port. @@ -1100,7 +1100,7 @@ struct tc_to_netdev { * This function is used to specify the headroom that the skb must * consider when allocation skb during packet reception. Setting * appropriate rx headroom value allows avoiding skb head copy on - * forward. Setting a negative value reset the rx headroom to the + * forward. Setting a negative value resets the rx headroom to the * default value. * */ @@ -1296,7 +1296,7 @@ struct net_device_ops { * * These are the &struct net_device, they are only set internally * by drivers and used in the kernel. These flags are invisible to - * userspace, this means that the order of these flags can change + * userspace; this means that the order of these flags can change * during any kernel release. * * You should have a pretty good reason to be extending these flags. @@ -1414,10 +1414,10 @@ enum netdev_priv_flags { * * @state: Generic network queuing layer state, see netdev_state_t * @dev_list: The global list of network devices - * @napi_list: List entry, that is used for polling napi devices - * @unreg_list: List entry, that is used, when we are unregistering the - * device, see the function unregister_netdev - * @close_list: List entry, that is used, when we are closing the device + * @napi_list: List entry used for polling NAPI devices + * @unreg_list: List entry when we are unregistering the + * device; see the function unregister_netdev + * @close_list: List entry used when we are closing the device * @ptype_all: Device-specific packet handlers for all protocols * @ptype_specific: Device-specific, protocol-specific packet handlers * @@ -1437,7 +1437,7 @@ enum netdev_priv_flags { * @mpls_features: Mask of features inheritable by MPLS * * @ifindex: interface index - * @group: The group, that the device belongs to + * @group: The group the device belongs to * * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead @@ -1491,7 +1491,7 @@ enum netdev_priv_flags { * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one - * @uc_promisc: Counter, that indicates, that promiscuous mode + * @uc_promisc: Counter that indicates promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that * does not implement ndo_set_rx_mode() @@ -1499,9 +1499,9 @@ enum netdev_priv_flags { * @mc: multicast mac addresses * @dev_addrs: list of device hw addresses * @queues_kset: Group of all Kobjects in the Tx and RX queues - * @promiscuity: Number of times, the NIC is told to work in - * Promiscuous mode, if it becomes 0 the NIC will - * exit from working in Promiscuous mode + * @promiscuity: Number of times the NIC is told to work in + * promiscuous mode; if it becomes 0 the NIC will + * exit promiscuous mode * @allmulti: Counter, enables or disables allmulticast mode * * @vlan_info: VLAN info @@ -1547,7 +1547,7 @@ enum netdev_priv_flags { * * @trans_start: Time (in jiffies) of last Tx * @watchdog_timeo: Represents the timeout that is used by - * the watchdog ( see dev_watchdog() ) + * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * * @pcpu_refcnt: Number of references to this device @@ -1664,8 +1664,8 @@ struct net_device { atomic_long_t rx_nohandler; #ifdef CONFIG_WIRELESS_EXT - const struct iw_handler_def * wireless_handlers; - struct iw_public_data * wireless_data; + const struct iw_handler_def *wireless_handlers; + struct iw_public_data *wireless_data; #endif const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; @@ -1718,7 +1718,7 @@ struct net_device { unsigned int allmulti; - /* Protocol specific pointers */ + /* Protocol-specific pointers */ #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; @@ -1748,13 +1748,11 @@ struct net_device { /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; - #ifdef CONFIG_SYSFS struct netdev_rx_queue *_rx; unsigned int num_rx_queues; unsigned int real_num_rx_queues; - #endif unsigned long gro_flush_timeout; @@ -1846,7 +1844,7 @@ struct net_device { struct garp_port __rcu *garp_port; struct mrp_port __rcu *mrp_port; - struct device dev; + struct device dev; const struct attribute_group *sysfs_groups[4]; const struct attribute_group *sysfs_rx_queue_group; @@ -1861,9 +1859,9 @@ struct net_device { #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - u8 num_tc; - struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; - u8 prio_tc_map[TC_BITMASK + 1]; + u8 num_tc; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; + u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) unsigned int fcoe_ddp_xid; @@ -1871,9 +1869,9 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif - struct phy_device *phydev; - struct lock_class_key *qdisc_tx_busylock; - bool proto_down; + struct phy_device *phydev; + struct lock_class_key *qdisc_tx_busylock; + bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2021,7 +2019,7 @@ static inline void *netdev_priv(const struct net_device *dev) /* Set the sysfs device type for the network logical device to allow * fine-grained identification of different network device types. For - * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc. + * example Ethernet, Wireless LAN, Bluetooth, WiMAX etc. */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) @@ -2031,22 +2029,22 @@ static inline void *netdev_priv(const struct net_device *dev) #define NAPI_POLL_WEIGHT 64 /** - * netif_napi_add - initialize a napi context + * netif_napi_add - initialize a NAPI context * @dev: network device - * @napi: napi context + * @napi: NAPI context * @poll: polling function * @weight: default weight * - * netif_napi_add() must be used to initialize a napi context prior to calling - * *any* of the other napi related functions. + * netif_napi_add() must be used to initialize a NAPI context prior to calling + * *any* of the other NAPI-related functions. */ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); /** - * netif_tx_napi_add - initialize a napi context + * netif_tx_napi_add - initialize a NAPI context * @dev: network device - * @napi: napi context + * @napi: NAPI context * @poll: polling function * @weight: default weight * @@ -2064,22 +2062,22 @@ static inline void netif_tx_napi_add(struct net_device *dev, } /** - * netif_napi_del - remove a napi context - * @napi: napi context + * netif_napi_del - remove a NAPI context + * @napi: NAPI context * - * netif_napi_del() removes a napi context from the network device napi list + * netif_napi_del() removes a NAPI context from the network device NAPI list */ void netif_napi_del(struct napi_struct *napi); struct napi_gro_cb { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; + void *frag0; /* Length of frag0. */ unsigned int frag0_len; /* This indicates where we are processing relative to skb->data. */ - int data_offset; + int data_offset; /* This is non-zero if the packet cannot be merged with the new skb. */ u16 flush; @@ -2175,7 +2173,7 @@ struct udp_offload { struct udp_offload_callbacks callbacks; }; -/* often modified stats are per cpu, other are shared (netdev->stats) */ +/* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { u64 rx_packets; u64 rx_bytes; @@ -2272,7 +2270,7 @@ struct netdev_notifier_changeupper_info { struct netdev_notifier_info info; /* must be first */ struct net_device *upper_dev; /* new upper dev */ bool master; /* is upper dev master */ - bool linking; /* is the nofication for link or unlink */ + bool linking; /* is the notification for link or unlink */ void *upper_info; /* upper dev info */ }; @@ -2737,7 +2735,7 @@ extern int netdev_flow_limit_table_len; #endif /* CONFIG_NET_FLOW_LIMIT */ /* - * Incoming packets are placed on per-cpu queues + * Incoming packets are placed on per-CPU queues */ struct softnet_data { struct list_head poll_list; @@ -2907,7 +2905,7 @@ netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their ndo_start_xmit(), - * to give appropriate hint to the cpu. + * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue) { @@ -2921,7 +2919,7 @@ static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_que * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their TX completion path, - * to give appropriate hint to the cpu. + * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue) { @@ -3060,7 +3058,7 @@ static inline bool netif_running(const struct net_device *dev) } /* - * Routines to manage the subqueues on a device. We only need start + * Routines to manage the subqueues on a device. We only need start, * stop, and a check if it's stopped. All other device management is * done at the overall netdevice level. * Also test the device if we're multiqueue. @@ -3344,7 +3342,6 @@ void netif_carrier_off(struct net_device *dev); * in a "pending" state, waiting for some external event. For "on- * demand" interfaces, this new state identifies the situation where the * interface is waiting for events to place it in the up state. - * */ static inline void netif_dormant_on(struct net_device *dev) { @@ -3679,7 +3676,7 @@ void dev_uc_init(struct net_device *dev); * * Add newly added addresses to the interface, and release * addresses that have been deleted. - **/ + */ static inline int __dev_uc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), @@ -3695,7 +3692,7 @@ static inline int __dev_uc_sync(struct net_device *dev, * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_uc_sync(). - **/ + */ static inline void __dev_uc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) @@ -3723,7 +3720,7 @@ void dev_mc_init(struct net_device *dev); * * Add newly added addresses to the interface, and release * addresses that have been deleted. - **/ + */ static inline int __dev_mc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), @@ -3739,7 +3736,7 @@ static inline int __dev_mc_sync(struct net_device *dev, * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_mc_sync(). - **/ + */ static inline void __dev_mc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) -- cgit v1.2.3 From 4cef191d05871fbc8bb3b812880e1997e855a3b9 Mon Sep 17 00:00:00 2001 From: Jaedon Shin Date: Fri, 25 Mar 2016 12:46:54 +0900 Subject: net: phy: bcm7xxx: Add entries for Broadcom BCM7346 and BCM7362 Add PHY entries for the Broadcom BCM7346 and BCM7362 chips, these are 40nm generation Ethernet PHY. Fixes: 815717d1473e ("net: phy: bcm7xxx: Remove wildcard entries") Signed-off-by: Jaedon Shin Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index f0ba9c2ec639..e3354b74286c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -24,6 +24,8 @@ #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 +#define PHY_ID_BCM7346 0x600d8650 +#define PHY_ID_BCM7362 0x600d84b0 #define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7435 0x600d8750 -- cgit v1.2.3 From 82dcabad750a36a2b749889bc89c5a3188775b2e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 Jan 2016 16:19:06 +0100 Subject: libceph: revamp subs code, switch to SUBSCRIBE2 protocol It is currently hard-coded in the mon_client that mdsmap and monmap subs are continuous, while osdmap sub is always "onetime". To better handle full clusters/pools in the osd_client, we need to be able to issue continuous osdmap subs. Revamp subs code to allow us to specify for each sub whether it should be continuous or not. Although not strictly required for the above, switch to SUBSCRIBE2 protocol while at it, eliminating the ambiguity between a request for "every map since X" and a request for "just the latest" when we don't have a map yet (i.e. have epoch 0). SUBSCRIBE2 feature bit is now required - it's been supported since pre-argonaut (2010). Move "got mdsmap" call to the end of ceph_mdsc_handle_map() - calling in before we validate the epoch and successfully install the new map can mess up mon_client sub state. Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_features.h | 2 ++ include/linux/ceph/ceph_fs.h | 4 ++-- include/linux/ceph/mon_client.h | 28 ++++++++++++++++++++-------- 3 files changed, 24 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 15151f3c4120..ae2f66833762 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -105,6 +105,7 @@ static inline u64 ceph_sanitize_features(u64 features) */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_SUBSCRIBE2 | \ CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ @@ -127,6 +128,7 @@ static inline u64 ceph_sanitize_features(u64 features) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_SUBSCRIBE2 | \ CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index d7d072a25c27..bf74005eedec 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -198,8 +198,8 @@ struct ceph_client_mount { #define CEPH_SUBSCRIBE_ONETIME 1 /* i want only 1 update after have */ struct ceph_mon_subscribe_item { - __le64 have_version; __le64 have; - __u8 onetime; + __le64 start; + __u8 flags; } __attribute__ ((packed)); struct ceph_mon_subscribe_ack { diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index 81810dc21f06..8b2d2f0b659e 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -68,7 +68,8 @@ struct ceph_mon_client { bool hunting; int cur_mon; /* last monitor i contacted */ - unsigned long sub_sent, sub_renew_after; + unsigned long sub_renew_after; + unsigned long sub_renew_sent; struct ceph_connection con; /* pending generic requests */ @@ -76,10 +77,12 @@ struct ceph_mon_client { int num_generic_requests; u64 last_tid; - /* mds/osd map */ - int want_mdsmap; - int want_next_osdmap; /* 1 = want, 2 = want+asked */ - u32 have_osdmap, have_mdsmap; + /* subs, indexed with CEPH_SUB_* */ + struct { + struct ceph_mon_subscribe_item item; + bool want; + u32 have; /* epoch */ + } subs[3]; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_file; @@ -93,14 +96,23 @@ extern int ceph_monmap_contains(struct ceph_monmap *m, extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl); extern void ceph_monc_stop(struct ceph_mon_client *monc); +enum { + CEPH_SUB_MDSMAP = 0, + CEPH_SUB_MONMAP, + CEPH_SUB_OSDMAP, +}; + +extern const char *ceph_sub_str[]; + /* * The model here is to indicate that we need a new map of at least - * epoch @want, and also call in when we receive a map. We will + * epoch @epoch, and also call in when we receive a map. We will * periodically rerequest the map from the monitor cluster until we * get what we want. */ -extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have); -extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have); +bool ceph_monc_want_map(struct ceph_mon_client *monc, int sub, u32 epoch, + bool continuous); +void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch); extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc); extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch, -- cgit v1.2.3 From 58d81b1294f02262a141687cd62529c1ec8e6484 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 21 Jan 2016 16:33:15 +0100 Subject: libceph: monc ping rate is 10s Split ping interval and ping timeout: ping interval is 10s; keepalive timeout is 30s. Make monc_ping_timeout a constant while at it - it's not actually exported as a mount option (and the rest of tick-related settings won't be either), so it's got no place in ceph_options. Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 3e3799cdc6e6..f5466273b9a3 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -47,7 +47,6 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ - unsigned long monc_ping_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -68,7 +67,9 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) -#define CEPH_MONC_PING_TIMEOUT_DEFAULT msecs_to_jiffies(30 * 1000) + +#define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) +#define CEPH_MONC_PING_TIMEOUT msecs_to_jiffies(30 * 1000) #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) -- cgit v1.2.3 From 168b9090c739c4b5556023a3f08789b349ca7339 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 21 Jan 2016 16:33:19 +0100 Subject: libceph: monc hunt rate is 3s with backoff up to 30s Unless we are in the process of setting up a client (i.e. connecting to the monitor cluster for the first time), apply a backoff: every time we want to reopen a session, increase our timeout by a multiple (currently 2); when we complete the connection, reduce that multipler by 50%. Mirrors ceph.git commit 794c86fd289bd62a35ed14368fa096c46736e9a2. Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 3 +++ include/linux/ceph/mon_client.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index f5466273b9a3..e7975e4681e1 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -68,8 +68,11 @@ struct ceph_options { #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) #define CEPH_MONC_PING_TIMEOUT msecs_to_jiffies(30 * 1000) +#define CEPH_MONC_HUNT_BACKOFF 2 +#define CEPH_MONC_HUNT_MAX_MULT 10 #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index 8b2d2f0b659e..e230e7ed60d3 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -72,6 +72,9 @@ struct ceph_mon_client { unsigned long sub_renew_sent; struct ceph_connection con; + bool had_a_connection; + int hunt_mult; /* [1..CEPH_MONC_HUNT_MAX_MULT] */ + /* pending generic requests */ struct rb_root generic_request_tree; int num_generic_requests; -- cgit v1.2.3 From de2aa102ea464a54dba14b9588e0bc188bd94707 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 8 Feb 2016 13:39:46 +0100 Subject: libceph: rename ceph_osd_req_op::payload_len to indata_len Follow userspace nomenclature on this - the next commit adds outdata_len. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 7506b485bb6d..35c8b006916f 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -77,7 +77,7 @@ struct ceph_osd_data { struct ceph_osd_req_op { u16 op; /* CEPH_OSD_OP_* */ u32 flags; /* CEPH_OSD_OP_FLAG_* */ - u32 payload_len; + u32 indata_len; /* request */ union { struct ceph_osd_data raw_data_in; struct { -- cgit v1.2.3 From 7665d85b7307fa0218881bc2009de067c42dc52e Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 7 Jan 2016 16:48:57 +0800 Subject: libceph: move r_reply_op_{len,result} into struct ceph_osd_req_op This avoids defining large array of r_reply_op_{len,result} in in struct ceph_osd_request. Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 35c8b006916f..c6d1d603bacf 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -78,6 +78,9 @@ struct ceph_osd_req_op { u16 op; /* CEPH_OSD_OP_* */ u32 flags; /* CEPH_OSD_OP_FLAG_* */ u32 indata_len; /* request */ + u32 outdata_len; /* reply */ + s32 rval; + union { struct ceph_osd_data raw_data_in; struct { @@ -148,8 +151,6 @@ struct ceph_osd_request { struct ceph_eversion *r_request_reassert_version; int r_result; - int r_reply_op_len[CEPH_OSD_MAX_OP]; - s32 r_reply_op_result[CEPH_OSD_MAX_OP]; int r_got_reply; int r_linger; -- cgit v1.2.3 From 3f1af42ad0fad8a12242233dd0d9fc42f5e83415 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 9 Feb 2016 17:50:15 +0100 Subject: libceph: enable large, variable-sized OSD requests Turn r_ops into a flexible array member to enable large, consisting of up to 16 ops, OSD requests. The use case is scattered writeback in cephfs and, as far as the kernel client is concerned, 16 is just a made up number. r_ops had size 3 for copyup+hint+write, but copyup is really a special case - it can only happen once. ceph_osd_request_cache is therefore stuffed with num_ops=2 requests, anything bigger than that is allocated with kmalloc(). req_mempool is backed by ceph_osd_request_cache, which means either num_ops=1 or num_ops=2 for use_mempool=true - all existing users (ceph_writepages_start(), ceph_osdc_writepages()) are fine with that. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index c6d1d603bacf..aada6a1383a4 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -43,7 +43,8 @@ struct ceph_osd { }; -#define CEPH_OSD_MAX_OP 3 +#define CEPH_OSD_SLAB_OPS 2 +#define CEPH_OSD_MAX_OPS 16 enum ceph_osd_data_type { CEPH_OSD_DATA_TYPE_NONE = 0, @@ -139,7 +140,6 @@ struct ceph_osd_request { /* request osd ops array */ unsigned int r_num_ops; - struct ceph_osd_req_op r_ops[CEPH_OSD_MAX_OP]; /* these are updated on each send */ __le32 *r_request_osdmap_epoch; @@ -175,6 +175,8 @@ struct ceph_osd_request { unsigned long r_stamp; /* send OR check time */ struct ceph_snap_context *r_snapc; /* snap context for writes */ + + struct ceph_osd_req_op r_ops[]; }; struct ceph_request_redirect { -- cgit v1.2.3 From 2c63f49a724a10bb71cc0fd34f8e5acce78525d5 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 7 Jan 2016 17:32:54 +0800 Subject: libceph: add helper that duplicates last extent operation This helper duplicates last extent operation in OSD request, then adjusts the new extent operation's offset and length. The helper is for scatterd page writeback, which adds nonconsecutive dirty pages to single OSD request. Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index aada6a1383a4..4343df806710 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -266,6 +266,8 @@ extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, u64 truncate_size, u32 truncate_seq); extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, unsigned int which, u64 length); +extern void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req, + unsigned int which, u64 offset_inc); extern struct ceph_osd_data *osd_req_op_extent_osd_data( struct ceph_osd_request *osd_req, -- cgit v1.2.3 From 315f24088048a51eed341c53be66ea477a3c7d16 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 7 Mar 2016 10:34:50 +0800 Subject: ceph: fix security xattr deadlock When security is enabled, security module can call filesystem's getxattr/setxattr callbacks during d_instantiate(). For cephfs, d_instantiate() is usually called by MDS' dispatch thread, while handling MDS reply. If the MDS reply does not include xattrs and corresponding caps, getxattr/setxattr need to send a new request to MDS and waits for the reply. This makes MDS' dispatch sleep, nobody handles later MDS replies. The fix is make sure lookup/atomic_open reply include xattrs and corresponding caps. So getxattr can be handled by cached xattrs. This requires some modification to both MDS and request message. (Client tells MDS what caps it wants; MDS encodes proper caps in the reply) Smack security module may call setxattr during d_instantiate(). Unlike getxattr, we can't force MDS to issue CEPH_CAP_XATTR_EXCL to us. So just make setxattr return error when called by MDS' dispatch thread. Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index bf74005eedec..37f28bf55ce4 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -376,7 +376,8 @@ union ceph_mds_request_args { __le32 stripe_count; /* ... */ __le32 object_size; __le32 file_replication; - __le32 unused; /* used to be preferred osd */ + __le32 mask; /* CEPH_CAP_* */ + __le32 old_size; } __attribute__ ((packed)) open; struct { __le32 flags; -- cgit v1.2.3 From 96c22a3293512ba684e73a981196430f524689da Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Wed, 23 Mar 2016 14:14:48 +0200 Subject: configfs: fix CONFIGFS_BIN_ATTR_[RW]O definitions The type should be struct configfs_bin_attribute and not struct configfs_attribute. Signed-off-by: Octavian Purdila Signed-off-by: Christoph Hellwig --- include/linux/configfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 485fe5519448..d9d6a9d77489 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -188,7 +188,7 @@ static struct configfs_bin_attribute _pfx##attr_##_name = { \ } #define CONFIGFS_BIN_ATTR_RO(_pfx, _name, _priv, _maxsz) \ -static struct configfs_attribute _pfx##attr_##_name = { \ +static struct configfs_bin_attribute _pfx##attr_##_name = { \ .cb_attr = { \ .ca_name = __stringify(_name), \ .ca_mode = S_IRUGO, \ @@ -200,7 +200,7 @@ static struct configfs_attribute _pfx##attr_##_name = { \ } #define CONFIGFS_BIN_ATTR_WO(_pfx, _name, _priv, _maxsz) \ -static struct configfs_attribute _pfx##attr_##_name = { \ +static struct configfs_bin_attribute _pfx##attr_##_name = { \ .cb_attr = { \ .ca_name = __stringify(_name), \ .ca_mode = S_IWUSR, \ -- cgit v1.2.3 From 69b27baf00fa9b7b14b3263c105390d1683425b2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 25 Mar 2016 14:20:21 -0700 Subject: sched: add schedule_timeout_idle() This will be needed in the patch "mm, oom: introduce oom reaper". Acked-by: Michal Hocko Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 589c4780b077..478b41de7f7d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -426,6 +426,7 @@ extern signed long schedule_timeout(signed long timeout); extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); +extern signed long schedule_timeout_idle(signed long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); -- cgit v1.2.3 From aac453635549699c13a84ea1456d5b0e574ef855 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:24 -0700 Subject: mm, oom: introduce oom reaper This patch (of 5): This is based on the idea from Mel Gorman discussed during LSFMM 2015 and independently brought up by Oleg Nesterov. The OOM killer currently allows to kill only a single task in a good hope that the task will terminate in a reasonable time and frees up its memory. Such a task (oom victim) will get an access to memory reserves via mark_oom_victim to allow a forward progress should there be a need for additional memory during exit path. It has been shown (e.g. by Tetsuo Handa) that it is not that hard to construct workloads which break the core assumption mentioned above and the OOM victim might take unbounded amount of time to exit because it might be blocked in the uninterruptible state waiting for an event (e.g. lock) which is blocked by another task looping in the page allocator. This patch reduces the probability of such a lockup by introducing a specialized kernel thread (oom_reaper) which tries to reclaim additional memory by preemptively reaping the anonymous or swapped out memory owned by the oom victim under an assumption that such a memory won't be needed when its owner is killed and kicked from the userspace anyway. There is one notable exception to this, though, if the OOM victim was in the process of coredumping the result would be incomplete. This is considered a reasonable constrain because the overall system health is more important than debugability of a particular application. A kernel thread has been chosen because we need a reliable way of invocation so workqueue context is not appropriate because all the workers might be busy (e.g. allocating memory). Kswapd which sounds like another good fit is not appropriate as well because it might get blocked on locks during reclaim as well. oom_reaper has to take mmap_sem on the target task for reading so the solution is not 100% because the semaphore might be held or blocked for write but the probability is reduced considerably wrt. basically any lock blocking forward progress as described above. In order to prevent from blocking on the lock without any forward progress we are using only a trylock and retry 10 times with a short sleep in between. Users of mmap_sem which need it for write should be carefully reviewed to use _killable waiting as much as possible and reduce allocations requests done with the lock held to absolute minimum to reduce the risk even further. The API between oom killer and oom reaper is quite trivial. wake_oom_reaper updates mm_to_reap with cmpxchg to guarantee only NULL->mm transition and oom_reaper clear this atomically once it is done with the work. This means that only a single mm_struct can be reaped at the time. As the operation is potentially disruptive we are trying to limit it to the ncessary minimum and the reaper blocks any updates while it operates on an mm. mm_struct is pinned by mm_count to allow parallel exit_mmap and a race is detected by atomic_inc_not_zero(mm_users). Signed-off-by: Michal Hocko Suggested-by: Oleg Nesterov Suggested-by: Mel Gorman Acked-by: Mel Gorman Acked-by: David Rientjes Cc: Mel Gorman Cc: Tetsuo Handa Cc: Oleg Nesterov Cc: Hugh Dickins Cc: Andrea Argangeli Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 450fc977ed02..ed6407d1b7b5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1132,6 +1132,8 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ + bool ignore_dirty; /* Ignore dirty pages */ + bool check_swap_entries; /* Check also swap entries */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From 36324a990cf578b57828c04cd85ac62cd25cf5a4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:27 -0700 Subject: oom: clear TIF_MEMDIE after oom_reaper managed to unmap the address space When oom_reaper manages to unmap all the eligible vmas there shouldn't be much of the freable memory held by the oom victim left anymore so it makes sense to clear the TIF_MEMDIE flag for the victim and allow the OOM killer to select another task. The lack of TIF_MEMDIE also means that the victim cannot access memory reserves anymore but that shouldn't be a problem because it would get the access again if it needs to allocate and hits the OOM killer again due to the fatal_signal_pending resp. PF_EXITING check. We can safely hide the task from the OOM killer because it is clearly not a good candidate anymore as everyhing reclaimable has been torn down already. This patch will allow to cap the time an OOM victim can keep TIF_MEMDIE and thus hold off further global OOM killer actions granted the oom reaper is able to take mmap_sem for the associated mm struct. This is not guaranteed now but further steps should make sure that mmap_sem for write should be blocked killable which will help to reduce such a lock contention. This is not done by this patch. Note that exit_oom_victim might be called on a remote task from __oom_reap_task now so we have to check and clear the flag atomically otherwise we might race and underflow oom_victims or wake up waiters too early. Signed-off-by: Michal Hocko Suggested-by: Johannes Weiner Suggested-by: Tetsuo Handa Cc: Andrea Argangeli Cc: David Rientjes Cc: Hugh Dickins Cc: Mel Gorman Cc: Oleg Nesterov Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 03e6257321f0..45993b840ed6 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -91,7 +91,7 @@ extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, extern bool out_of_memory(struct oom_control *oc); -extern void exit_oom_victim(void); +extern void exit_oom_victim(struct task_struct *tsk); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 03049269de433cb5fe2859be9ae4469ceb1163ed Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:33 -0700 Subject: mm, oom_reaper: implement OOM victims queuing wake_oom_reaper has allowed only 1 oom victim to be queued. The main reason for that was the simplicity as other solutions would require some way of queuing. The current approach is racy and that was deemed sufficient as the oom_reaper is considered a best effort approach to help with oom handling when the OOM victim cannot terminate in a reasonable time. The race could lead to missing an oom victim which can get stuck out_of_memory wake_oom_reaper cmpxchg // OK oom_reaper oom_reap_task __oom_reap_task oom_victim terminates atomic_inc_not_zero // fail out_of_memory wake_oom_reaper cmpxchg // fails task_to_reap = NULL This race requires 2 OOM invocations in a short time period which is not very likely but certainly not impossible. E.g. the original victim might have not released a lot of memory for some reason. The situation would improve considerably if wake_oom_reaper used a more robust queuing. This is what this patch implements. This means adding oom_reaper_list list_head into task_struct (eat a hole before embeded thread_struct for that purpose) and a oom_reaper_lock spinlock for queuing synchronization. wake_oom_reaper will then add the task on the queue and oom_reaper will dequeue it. Signed-off-by: Michal Hocko Cc: Vladimir Davydov Cc: Andrea Argangeli Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Mel Gorman Cc: Oleg Nesterov Cc: Rik van Riel Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 478b41de7f7d..788f223f8f8f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1849,6 +1849,9 @@ struct task_struct { unsigned long task_state_change; #endif int pagefault_disabled; +#ifdef CONFIG_MMU + struct list_head oom_reaper_list; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* -- cgit v1.2.3 From 855b018325737f7691f9b7d86339df40aa4e47c3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:36 -0700 Subject: oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task Tetsuo has reported that oom_kill_allocating_task=1 will cause oom_reaper_list corruption because oom_kill_process doesn't follow standard OOM exclusion (aka ignores TIF_MEMDIE) and allows to enqueue the same task multiple times - e.g. by sacrificing the same child multiple times. This patch fixes the issue by introducing a new MMF_OOM_KILLED mm flag which is set in oom_kill_process atomically and oom reaper is disabled if the flag was already set. Signed-off-by: Michal Hocko Reported-by: Tetsuo Handa Cc: David Rientjes Cc: Mel Gorman Cc: Oleg Nesterov Cc: Hugh Dickins Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 788f223f8f8f..c2d2d7c5d463 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -512,6 +512,8 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_KILLED 21 /* OOM killer has chosen this mm */ + #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) struct sighand_struct { -- cgit v1.2.3 From 29c696e1c6eceb5db6b21f0c89495fcfcd40c0eb Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Fri, 25 Mar 2016 14:20:39 -0700 Subject: oom: make oom_reaper_list single linked Entries are only added/removed from oom_reaper_list at head so we can use a single linked list and hence save a word in task_struct. Signed-off-by: Vladimir Davydov Signed-off-by: Michal Hocko Cc: Tetsuo Handa Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c2d2d7c5d463..49b1febcf7c3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1852,7 +1852,7 @@ struct task_struct { #endif int pagefault_disabled; #ifdef CONFIG_MMU - struct list_head oom_reaper_list; + struct task_struct *oom_reaper_list; #endif /* CPU-specific state of this task */ struct thread_struct thread; -- cgit v1.2.3 From bb29902a7515208846114b3b36a4281a9bbf766a Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 25 Mar 2016 14:20:44 -0700 Subject: oom, oom_reaper: protect oom_reaper_list using simpler way "oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task" tried to protect oom_reaper_list using MMF_OOM_KILLED flag. But we can do it by simply checking tsk->oom_reaper_list != NULL. Signed-off-by: Tetsuo Handa Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 49b1febcf7c3..60bba7e032dc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -512,8 +512,6 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_KILLED 21 /* OOM killer has chosen this mm */ - #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) struct sighand_struct { -- cgit v1.2.3 From aaf4fb712b8311d8b950e89937479d61e9c25ba8 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 25 Mar 2016 14:21:53 -0700 Subject: include/linux/oom.h: remove undefined oom_kills_count()/note_oom_kill() A leftover from commit c32b3cbe0d06 ("oom, PM: make OOM detection in the freezer path raceless"). Signed-off-by: Tetsuo Handa Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 45993b840ed6..628a43242a34 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -76,8 +76,6 @@ extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); -extern int oom_kills_count(void); -extern void note_oom_kill(void); extern void oom_kill_process(struct oom_control *oc, struct task_struct *p, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, const char *message); -- cgit v1.2.3 From 7ed2f9e663854db313f177a511145630e398b402 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 25 Mar 2016 14:21:59 -0700 Subject: mm, kasan: SLAB support Add KASAN hooks to SLAB allocator. This patch is based on the "mm: kasan: unified support for SLUB and SLAB allocators" patch originally prepared by Dmitry Chernenkov. Signed-off-by: Alexander Potapenko Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Steven Rostedt Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 12 ++++++++++++ include/linux/slab.h | 6 ++++++ include/linux/slab_def.h | 14 ++++++++++++++ include/linux/slub_def.h | 11 +++++++++++ 4 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 0fdc798e3ff7..839f2007a0f9 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -48,6 +48,9 @@ void kasan_unpoison_task_stack(struct task_struct *task); void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); +void kasan_cache_create(struct kmem_cache *cache, size_t *size, + unsigned long *flags); + void kasan_poison_slab(struct page *page); void kasan_unpoison_object_data(struct kmem_cache *cache, void *object); void kasan_poison_object_data(struct kmem_cache *cache, void *object); @@ -61,6 +64,11 @@ void kasan_krealloc(const void *object, size_t new_size); void kasan_slab_alloc(struct kmem_cache *s, void *object); void kasan_slab_free(struct kmem_cache *s, void *object); +struct kasan_cache { + int alloc_meta_offset; + int free_meta_offset; +}; + int kasan_module_alloc(void *addr, size_t size); void kasan_free_shadow(const struct vm_struct *vm); @@ -76,6 +84,10 @@ static inline void kasan_disable_current(void) {} static inline void kasan_alloc_pages(struct page *page, unsigned int order) {} static inline void kasan_free_pages(struct page *page, unsigned int order) {} +static inline void kasan_cache_create(struct kmem_cache *cache, + size_t *size, + unsigned long *flags) {} + static inline void kasan_poison_slab(struct page *page) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} diff --git a/include/linux/slab.h b/include/linux/slab.h index e4b568738ca3..aa61595a1482 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -92,6 +92,12 @@ # define SLAB_ACCOUNT 0x00000000UL #endif +#ifdef CONFIG_KASAN +#define SLAB_KASAN 0x08000000UL +#else +#define SLAB_KASAN 0x00000000UL +#endif + /* The following flags affect the page allocator grouping pages by mobility */ #define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e878ba35ae91..9edbbf352340 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -76,8 +76,22 @@ struct kmem_cache { #ifdef CONFIG_MEMCG struct memcg_cache_params memcg_params; #endif +#ifdef CONFIG_KASAN + struct kasan_cache kasan_info; +#endif struct kmem_cache_node *node[MAX_NUMNODES]; }; +static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, + void *x) { + void *object = x - (x - page->s_mem) % cache->size; + void *last_object = page->s_mem + (cache->num - 1) * cache->size; + + if (unlikely(object > last_object)) + return last_object; + else + return object; +} + #endif /* _LINUX_SLAB_DEF_H */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index ac5143f95ee6..665cd0cd18b8 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -130,4 +130,15 @@ static inline void *virt_to_obj(struct kmem_cache *s, void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason); +static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, + void *x) { + void *object = x - (x - page_address(page)) % cache->size; + void *last_object = page_address(page) + + (page->objects - 1) * cache->size; + if (unlikely(object > last_object)) + return last_object; + else + return object; +} + #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 505f5dcb1c419e55a9621a01f83eb5745d8d7398 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 25 Mar 2016 14:22:02 -0700 Subject: mm, kasan: add GFP flags to KASAN API Add GFP flags to KASAN hooks for future patches to use. This patch is based on the "mm: kasan: unified support for SLUB and SLAB allocators" patch originally prepared by Dmitry Chernenkov. Signed-off-by: Alexander Potapenko Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Steven Rostedt Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 19 +++++++++++-------- include/linux/slab.h | 4 ++-- 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 839f2007a0f9..737371b56044 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -55,13 +55,14 @@ void kasan_poison_slab(struct page *page); void kasan_unpoison_object_data(struct kmem_cache *cache, void *object); void kasan_poison_object_data(struct kmem_cache *cache, void *object); -void kasan_kmalloc_large(const void *ptr, size_t size); +void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); void kasan_kfree_large(const void *ptr); void kasan_kfree(void *ptr); -void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size); -void kasan_krealloc(const void *object, size_t new_size); +void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, + gfp_t flags); +void kasan_krealloc(const void *object, size_t new_size, gfp_t flags); -void kasan_slab_alloc(struct kmem_cache *s, void *object); +void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); void kasan_slab_free(struct kmem_cache *s, void *object); struct kasan_cache { @@ -94,14 +95,16 @@ static inline void kasan_unpoison_object_data(struct kmem_cache *cache, static inline void kasan_poison_object_data(struct kmem_cache *cache, void *object) {} -static inline void kasan_kmalloc_large(void *ptr, size_t size) {} +static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {} static inline void kasan_kfree_large(const void *ptr) {} static inline void kasan_kfree(void *ptr) {} static inline void kasan_kmalloc(struct kmem_cache *s, const void *object, - size_t size) {} -static inline void kasan_krealloc(const void *object, size_t new_size) {} + size_t size, gfp_t flags) {} +static inline void kasan_krealloc(const void *object, size_t new_size, + gfp_t flags) {} -static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {} +static inline void kasan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags) {} static inline void kasan_slab_free(struct kmem_cache *s, void *object) {} static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } diff --git a/include/linux/slab.h b/include/linux/slab.h index aa61595a1482..508bd827e6dc 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -376,7 +376,7 @@ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, { void *ret = kmem_cache_alloc(s, flags); - kasan_kmalloc(s, ret, size); + kasan_kmalloc(s, ret, size, flags); return ret; } @@ -387,7 +387,7 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, { void *ret = kmem_cache_alloc_node(s, gfpflags, node); - kasan_kmalloc(s, ret, size); + kasan_kmalloc(s, ret, size, gfpflags); return ret; } #endif /* CONFIG_TRACING */ -- cgit v1.2.3 From be7635e7287e0e8013af3c89a6354a9e0182594c Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 25 Mar 2016 14:22:05 -0700 Subject: arch, ftrace: for KASAN put hard/soft IRQ entries into separate sections KASAN needs to know whether the allocation happens in an IRQ handler. This lets us strip everything below the IRQ entry point to reduce the number of unique stack traces needed to be stored. Move the definition of __irq_entry to so that the users don't need to pull in . Also introduce the __softirq_entry macro which is similar to __irq_entry, but puts the corresponding functions to the .softirqentry.text section. Signed-off-by: Alexander Potapenko Acked-by: Steven Rostedt Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ftrace.h | 11 ----------- include/linux/interrupt.h | 20 ++++++++++++++++++++ 2 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6d9df3f7e334..dea12a6e413b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -811,16 +811,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, */ #define __notrace_funcgraph notrace -/* - * We want to which function is an entrypoint of a hardirq. - * That will help us to put a signal on output. - */ -#define __irq_entry __attribute__((__section__(".irqentry.text"))) - -/* Limits of hardirq entrypoints */ -extern char __irqentry_text_start[]; -extern char __irqentry_text_end[]; - #define FTRACE_NOTRACE_DEPTH 65536 #define FTRACE_RETFUNC_DEPTH 50 #define FTRACE_RETSTACK_ALLOC_SIZE 32 @@ -857,7 +847,6 @@ static inline void unpause_graph_tracing(void) #else /* !CONFIG_FUNCTION_GRAPH_TRACER */ #define __notrace_funcgraph -#define __irq_entry #define INIT_FTRACE_GRAPH static inline void ftrace_graph_init_task(struct task_struct *t) { } diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 358076eda364..9fcabeb07787 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -683,4 +683,24 @@ extern int early_irq_init(void); extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +/* + * We want to know which function is an entrypoint of a hardirq or a softirq. + */ +#define __irq_entry __attribute__((__section__(".irqentry.text"))) +#define __softirq_entry \ + __attribute__((__section__(".softirqentry.text"))) + +/* Limits of hardirq entrypoints */ +extern char __irqentry_text_start[]; +extern char __irqentry_text_end[]; +/* Limits of softirq entrypoints */ +extern char __softirqentry_text_start[]; +extern char __softirqentry_text_end[]; + +#else +#define __irq_entry +#define __softirq_entry +#endif + #endif -- cgit v1.2.3 From cd11016e5f5212c13c0cec7384a525edc93b4921 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 25 Mar 2016 14:22:08 -0700 Subject: mm, kasan: stackdepot implementation. Enable stackdepot for SLAB Implement the stack depot and provide CONFIG_STACKDEPOT. Stack depot will allow KASAN store allocation/deallocation stack traces for memory chunks. The stack traces are stored in a hash table and referenced by handles which reside in the kasan_alloc_meta and kasan_free_meta structures in the allocated memory chunks. IRQ stack traces are cut below the IRQ entry point to avoid unnecessary duplication. Right now stackdepot support is only enabled in SLAB allocator. Once KASAN features in SLAB are on par with those in SLUB we can switch SLUB to stackdepot as well, thus removing the dependency on SLUB stack bookkeeping, which wastes a lot of memory. This patch is based on the "mm: kasan: stack depots" patch originally prepared by Dmitry Chernenkov. Joonsoo has said that he plans to reuse the stackdepot code for the mm/page_owner.c debugging facility. [akpm@linux-foundation.org: s/depot_stack_handle/depot_stack_handle_t] [aryabinin@virtuozzo.com: comment style fixes] Signed-off-by: Alexander Potapenko Signed-off-by: Andrey Ryabinin Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Steven Rostedt Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/stackdepot.h (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h new file mode 100644 index 000000000000..7978b3e2c1e1 --- /dev/null +++ b/include/linux/stackdepot.h @@ -0,0 +1,32 @@ +/* + * A generic stack depot implementation + * + * Author: Alexander Potapenko + * Copyright (C) 2016 Google, Inc. + * + * Based on code by Dmitry Chernenkov. + * + * 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. + * + */ + +#ifndef _LINUX_STACKDEPOT_H +#define _LINUX_STACKDEPOT_H + +typedef u32 depot_stack_handle_t; + +struct stack_trace; + +depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags); + +void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace); + +#endif -- cgit v1.2.3 From d101a125954eae1d397adda94ca6319485a50493 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 26 Mar 2016 16:14:37 -0400 Subject: fs: add file_dentry() This series fixes bugs in nfs and ext4 due to 4bacc9c9234c ("overlayfs: Make f_path always point to the overlay and f_inode to the underlay"). Regular files opened on overlayfs will result in the file being opened on the underlying filesystem, while f_path points to the overlayfs mount/dentry. This confuses filesystems which get the dentry from struct file and assume it's theirs. Add a new helper, file_dentry() [*], to get the filesystem's own dentry from the file. This checks file->f_path.dentry->d_flags against DCACHE_OP_REAL, and returns file->f_path.dentry if DCACHE_OP_REAL is not set (this is the common, non-overlayfs case). In the uncommon case it will call into overlayfs's ->d_real() to get the underlying dentry, matching file_inode(file). The reason we need to check against the inode is that if the file is copied up while being open, d_real() would return the upper dentry, while the open file comes from the lower dentry. [*] If possible, it's better simply to use file_inode() instead. Signed-off-by: Miklos Szeredi Signed-off-by: Theodore Ts'o Tested-by: Goldwyn Rodrigues Reviewed-by: Trond Myklebust Cc: # v4.2 Cc: David Howells Cc: Al Viro Cc: Daniel Axtens --- include/linux/dcache.h | 10 ++++++++++ include/linux/fs.h | 10 ++++++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 7cb043d8f4e8..4bb4de8d95ea 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -161,6 +161,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); struct inode *(*d_select_inode)(struct dentry *, unsigned); + struct dentry *(*d_real)(struct dentry *, struct inode *); } ____cacheline_aligned; /* @@ -229,6 +230,7 @@ struct dentry_operations { #define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ #define DCACHE_ENCRYPTED_WITH_KEY 0x04000000 /* dir is encrypted with a valid key */ +#define DCACHE_OP_REAL 0x08000000 extern seqlock_t rename_lock; @@ -555,4 +557,12 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } +static inline struct dentry *d_real(struct dentry *dentry) +{ + if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) + return dentry->d_op->d_real(dentry, NULL); + else + return dentry; +} + #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 35d99266ca9a..b2ed2311b021 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1241,6 +1241,16 @@ static inline struct inode *file_inode(const struct file *f) return f->f_inode; } +static inline struct dentry *file_dentry(const struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; + + if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) + return dentry->d_op->d_real(dentry, file_inode(file)); + else + return dentry; +} + static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); -- cgit v1.2.3 From 596cf3fe5854fe2b1703b0466ed6bf9cfb83c91e Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Wed, 16 Mar 2016 21:49:00 +0100 Subject: netfilter: ipset: fix race condition in ipset save, swap and delete This fix adds a new reference counter (ref_netlink) for the struct ip_set. The other reference counter (ref) can be swapped out by ip_set_swap and we need a separate counter to keep track of references for netlink events like dump. Using the same ref counter for dump causes a race condition which can be demonstrated by the following script: ipset create hash_ip1 hash:ip family inet hashsize 1024 maxelem 500000 \ counters ipset create hash_ip2 hash:ip family inet hashsize 300000 maxelem 500000 \ counters ipset create hash_ip3 hash:ip family inet hashsize 1024 maxelem 500000 \ counters ipset save & ipset swap hash_ip3 hash_ip2 ipset destroy hash_ip3 /* will crash the machine */ Swap will exchange the values of ref so destroy will see ref = 0 instead of ref = 1. With this fix in place swap will not succeed because ipset save still has ref_netlink on the set (ip_set_swap doesn't swap ref_netlink). Both delete and swap will error out if ref_netlink != 0 on the set. Note: The changes to *_head functions is because previously we would increment ref whenever we called these functions, we don't do that anymore. Reviewed-by: Joshua Hunt Signed-off-by: Vishwanath Pai Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 0e1f433cc4b7..f48b8a664b0f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -234,6 +234,10 @@ struct ip_set { spinlock_t lock; /* References to the set */ u32 ref; + /* References to the set for netlink events like dump, + * ref can be swapped out by ip_set_swap + */ + u32 ref_netlink; /* The core set type */ struct ip_set_type *type; /* The type variant doing the real job */ -- cgit v1.2.3 From fc0c2028135c7f75fce36b90e44efb8003a9173b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Mar 2016 10:30:19 -0800 Subject: x86, pmem: use memcpy_mcsafe() for memcpy_from_pmem() Update the definition of memcpy_from_pmem() to return 0 or a negative error code. Implement x86/arch_memcpy_from_pmem() with memcpy_mcsafe(). Cc: Borislav Petkov Cc: Tony Luck Cc: Thomas Gleixner Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Acked-by: Ingo Molnar Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- include/linux/pmem.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pmem.h b/include/linux/pmem.h index 3ec5309e29f3..ac6d872ce067 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -42,6 +42,13 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, BUG(); } +static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src, + size_t n) +{ + BUG(); + return -EFAULT; +} + static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, struct iov_iter *i) { @@ -66,14 +73,17 @@ static inline void arch_invalidate_pmem(void __pmem *addr, size_t size) #endif /* - * Architectures that define ARCH_HAS_PMEM_API must provide - * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(), - * arch_copy_from_iter_pmem(), arch_clear_pmem(), arch_wb_cache_pmem() - * and arch_has_wmb_pmem(). + * memcpy_from_pmem - read from persistent memory with error handling + * @dst: destination buffer + * @src: source buffer + * @size: transfer length + * + * Returns 0 on success negative error code on failure. */ -static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size) +static inline int memcpy_from_pmem(void *dst, void __pmem const *src, + size_t size) { - memcpy(dst, (void __force const *) src, size); + return arch_memcpy_from_pmem(dst, src, size); } static inline bool arch_has_pmem_api(void) -- cgit v1.2.3 From 5acba71e18833b9d06686b3751598bfa263a3ac3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:37:59 +0100 Subject: locking/atomic: Introduce atomic_fetch_or() This is deemed to replace the type generic fetch_or() which brings a lot of issues such as macro induced block variable aliasing and sloppy types. Not to mention fetch_or() doesn't refer to any namespace, adding even more confusion. So lets provide an atomic_t version. Current and next users of fetch_or() are thus encouraged to use atomic_t. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index df4f369254c0..3d64c0852164 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -558,6 +558,27 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif +/** + * atomic_fetch_or - perform *p |= mask and return old value of *p + * @p: pointer to atomic_t + * @mask: mask to OR on the atomic_t + */ +#ifndef atomic_fetch_or +static inline int atomic_fetch_or(atomic_t *p, int mask) +{ + int old, val = atomic_read(p); + + for (;;) { + old = atomic_cmpxchg(p, val, val | mask); + if (old == val) + break; + val = old; + } + + return old; +} +#endif + /** * fetch_or - perform *ptr |= mask and return old value of *ptr * @ptr: pointer to value -- cgit v1.2.3 From f009a7a767e792d5ab0b46c08d46236ea5271dd9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:38:00 +0100 Subject: timers/nohz: Convert tick dependency mask to atomic_t The tick dependency mask was intially unsigned long because this is the type on which clear_bit() operates on and fetch_or() accepts it. But now that we have atomic_fetch_or(), we can instead use atomic_andnot() to clear the bit. This consolidates the type of our tick dependency mask, reduce its size on structures and benefit from possible architecture optimizations on atomic_t operations. Suggested-by: Linus Torvalds Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 60bba7e032dc..52c4847b05e2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -720,7 +720,7 @@ struct signal_struct { struct task_cputime cputime_expires; #ifdef CONFIG_NO_HZ_FULL - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; #endif struct list_head cpu_timers[3]; @@ -1549,7 +1549,7 @@ struct task_struct { #endif #ifdef CONFIG_NO_HZ_FULL - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; #endif unsigned long nvcsw, nivcsw; /* context switch counts */ u64 start_time; /* monotonic time in nsec */ -- cgit v1.2.3 From 5529578a27288d11d4d15635c258c6dde0f0fb10 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:38:01 +0100 Subject: locking/atomic, sched: Unexport fetch_or() This patch functionally reverts: 5fd7a09cfb8c ("atomic: Export fetch_or()") During the merge Linus observed that the generic version of fetch_or() was messy: " This makes the ugly "fetch_or()" macro that the scheduler used internally a new generic helper, and does a bad job at it. " e23604edac2a Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Now that we have introduced atomic_fetch_or(), fetch_or() is only used by the scheduler in order to deal with thread_info flags which type can vary across architectures. Lets confine fetch_or() back to the scheduler so that we encourage future users to use the more robust and well typed atomic_t version instead. While at it, fetch_or() gets robustified, pasting improvements from a previous patch by Ingo Molnar that avoids needless expression re-evaluations in the loop. Reported-by: Linus Torvalds Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3d64c0852164..506c3531832e 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -579,27 +579,6 @@ static inline int atomic_fetch_or(atomic_t *p, int mask) } #endif -/** - * fetch_or - perform *ptr |= mask and return old value of *ptr - * @ptr: pointer to value - * @mask: mask to OR on the value - * - * cmpxchg based fetch_or, macro so it works for different integer types - */ -#ifndef fetch_or -#define fetch_or(ptr, mask) \ -({ typeof(*(ptr)) __old, __val = *(ptr); \ - for (;;) { \ - __old = cmpxchg((ptr), __val, __val | (mask)); \ - if (__old == __val) \ - break; \ - __val = __old; \ - } \ - __old; \ -}) -#endif - - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif -- cgit v1.2.3 From 5a5abb1fa3b05dd6aa821525832644c1e7d2905f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 31 Mar 2016 02:13:18 +0200 Subject: tun, bpf: fix suspicious RCU usage in tun_{attach, detach}_filter Sasha Levin reported a suspicious rcu_dereference_protected() warning found while fuzzing with trinity that is similar to this one: [ 52.765684] net/core/filter.c:2262 suspicious rcu_dereference_protected() usage! [ 52.765688] other info that might help us debug this: [ 52.765695] rcu_scheduler_active = 1, debug_locks = 1 [ 52.765701] 1 lock held by a.out/1525: [ 52.765704] #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x17/0x20 [ 52.765721] stack backtrace: [ 52.765728] CPU: 1 PID: 1525 Comm: a.out Not tainted 4.5.0+ #264 [...] [ 52.765768] Call Trace: [ 52.765775] [] dump_stack+0x85/0xc8 [ 52.765784] [] lockdep_rcu_suspicious+0xd5/0x110 [ 52.765792] [] sk_detach_filter+0x82/0x90 [ 52.765801] [] tun_detach_filter+0x35/0x90 [tun] [ 52.765810] [] __tun_chr_ioctl+0x354/0x1130 [tun] [ 52.765818] [] ? selinux_file_ioctl+0x130/0x210 [ 52.765827] [] tun_chr_ioctl+0x13/0x20 [tun] [ 52.765834] [] do_vfs_ioctl+0x96/0x690 [ 52.765843] [] ? security_file_ioctl+0x43/0x60 [ 52.765850] [] SyS_ioctl+0x79/0x90 [ 52.765858] [] do_syscall_64+0x62/0x140 [ 52.765866] [] entry_SYSCALL64_slow_path+0x25/0x25 Same can be triggered with PROVE_RCU (+ PROVE_RCU_REPEATEDLY) enabled from tun_attach_filter() when user space calls ioctl(tun_fd, TUN{ATTACH, DETACH}FILTER, ...) for adding/removing a BPF filter on tap devices. Since the fix in f91ff5b9ff52 ("net: sk_{detach|attach}_filter() rcu fixes") sk_attach_filter()/sk_detach_filter() now dereferences the filter with rcu_dereference_protected(), checking whether socket lock is held in control path. Since its introduction in 994051625981 ("tun: socket filter support"), tap filters are managed under RTNL lock from __tun_chr_ioctl(). Thus the sock_owned_by_user(sk) doesn't apply in this specific case and therefore triggers the false positive. Extend the BPF API with __sk_attach_filter()/__sk_detach_filter() pair that is used by tap filters and pass in lockdep_rtnl_is_held() for the rcu_dereference_protected() checks instead. Reported-by: Sasha Levin Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 43aa1f8855c7..a51a5361695f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -465,10 +465,14 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); +int __sk_detach_filter(struct sock *sk, bool locked); + int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); -- cgit v1.2.3 From d7e944c8ddc0983640a9a32868fb217485d12ca2 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Fri, 1 Apr 2016 09:07:15 +0200 Subject: Revert "stmmac: Fix 'eth0: No PHY found' regression" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 88f8b1bb41c6208f81b6a480244533ded7b59493. due to problems on GeekBox and Banana Pi M1 board when connected to a real transceiver instead of a switch via fixed-link. Signed-off-by: Giuseppe Cavallaro Cc: Gabriel Fernandez Cc: Andreas Färber Cc: Frank Schäfer Cc: Dinh Nguyen Cc: David S. Miller Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 4bcf5a61aada..6e53fa8942a4 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -114,7 +114,6 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; - struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; -- cgit v1.2.3 From a7657f128c279ae5796ab2ca7d04a7819f4259f0 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Fri, 1 Apr 2016 09:07:16 +0200 Subject: stmmac: fix MDIO settings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Initially the phy_bus_name was added to manipulate the driver name but it was recently just used to manage the fixed-link and then to take some decision at run-time. So the patch uses the is_pseudo_fixed_link and removes the phy_bus_name variable not necessary anymore. The driver can manage the mdio registration by using phy-handle, dwmac-mdio and own parameter e.g. snps,phy-addr. This patch takes care about all these possible configurations and fixes the mdio registration in case of there is a real transceiver or a switch (that needs to be managed by using fixed-link). Signed-off-by: Giuseppe Cavallaro Reviewed-by: Andreas Färber Tested-by: Frank Schäfer Cc: Gabriel Fernandez Cc: Dinh Nguyen Cc: David S. Miller Cc: Phil Reid Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 6e53fa8942a4..e6bc30a42a74 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -108,12 +108,12 @@ struct stmmac_axi { }; struct plat_stmmacenet_data { - char *phy_bus_name; int bus_id; int phy_addr; int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; -- cgit v1.2.3 From 969e8d7e47f93ef693028667480558de8f70523f Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Fri, 1 Apr 2016 14:31:17 -0700 Subject: include/linux/huge_mm.h: return NULL instead of false for pmd_trans_huge_lock() The return value of pmd_trans_huge_lock() is a pointer, not a boolean value, so use NULL instead of false as the return value. Signed-off-by: Chen Gang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 79b0ef6aaa14..7008623e24b1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -127,7 +127,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else - return false; + return NULL; } static inline int hpage_nr_pages(struct page *page) { -- cgit v1.2.3 From 09cbfeaf1a5a67bfb3201e0c83c810cecb2efa5a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 1 Apr 2016 15:29:47 +0300 Subject: mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/bio.h | 2 +- include/linux/blkdev.h | 2 +- include/linux/buffer_head.h | 4 ++-- include/linux/ceph/libceph.h | 4 ++-- include/linux/f2fs_fs.h | 4 ++-- include/linux/fs.h | 4 ++-- include/linux/nfs_page.h | 2 +- include/linux/pagemap.h | 14 +++++++------- include/linux/swap.h | 2 +- 9 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 88bc64f00bb5..6b7481f62218 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -41,7 +41,7 @@ #endif #define BIO_MAX_PAGES 256 -#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_CACHE_SHIFT) +#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_SHIFT) #define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e5d7e018bea..669e419d6234 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1372,7 +1372,7 @@ unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *); static inline void put_dev_sector(Sector p) { - page_cache_release(p.v); + put_page(p.v); } static inline bool __bvec_gap_to_prev(struct request_queue *q, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index c67f052cc5e5..d48daa3f6f20 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -43,7 +43,7 @@ enum bh_state_bits { */ }; -#define MAX_BUF_PER_PAGE (PAGE_CACHE_SIZE / 512) +#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; @@ -263,7 +263,7 @@ void buffer_init(void); static inline void attach_page_buffers(struct page *page, struct buffer_head *head) { - page_cache_get(page); + get_page(page); SetPagePrivate(page); set_page_private(page, (unsigned long)head); } diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index e7975e4681e1..db92a8d4926e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -176,8 +176,8 @@ extern void ceph_put_snap_context(struct ceph_snap_context *sc); */ static inline int calc_pages_for(u64 off, u64 len) { - return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) - - (off >> PAGE_CACHE_SHIFT); + return ((off+len+PAGE_SIZE-1) >> PAGE_SHIFT) - + (off >> PAGE_SHIFT); } extern struct kmem_cache *ceph_inode_cachep; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 9eb215a155e0..b90e9bdbd1dd 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -262,7 +262,7 @@ struct f2fs_node { /* * For NAT entries */ -#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry)) +#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ @@ -282,7 +282,7 @@ struct f2fs_nat_block { * Not allow to change this. */ #define SIT_VBLOCK_MAP_SIZE 64 -#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry)) +#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry)) /* * Note that f2fs_sit_entry->vblocks has the following bit-field information. diff --git a/include/linux/fs.h b/include/linux/fs.h index 14a97194b34b..304991a80e23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -929,7 +929,7 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) #endif @@ -2067,7 +2067,7 @@ extern int generic_update_time(struct inode *, struct timespec *, int); /* /sys/fs */ extern struct kobject *fs_kobj; -#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) +#define MAX_RW_COUNT (INT_MAX & PAGE_MASK) #ifdef CONFIG_MANDATORY_FILE_LOCKING extern int locks_mandatory_locked(struct file *); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index f2f650f136ee..efada239205e 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -184,7 +184,7 @@ nfs_list_entry(struct list_head *head) static inline loff_t req_offset(struct nfs_page *req) { - return (((loff_t)req->wb_index) << PAGE_CACHE_SHIFT) + req->wb_offset; + return (((loff_t)req->wb_index) << PAGE_SHIFT) + req->wb_offset; } #endif /* _LINUX_NFS_PAGE_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1ebd65c91422..f396ccb900cc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -390,13 +390,13 @@ static inline pgoff_t page_to_pgoff(struct page *page) return page->index << compound_order(page); if (likely(!PageTransTail(page))) - return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + return page->index; /* * We don't initialize ->index for tail pages: calculate based on * head page */ - pgoff = compound_head(page)->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = compound_head(page)->index; pgoff += page - compound_head(page); return pgoff; } @@ -406,12 +406,12 @@ static inline pgoff_t page_to_pgoff(struct page *page) */ static inline loff_t page_offset(struct page *page) { - return ((loff_t)page->index) << PAGE_CACHE_SHIFT; + return ((loff_t)page->index) << PAGE_SHIFT; } static inline loff_t page_file_offset(struct page *page) { - return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT; + return ((loff_t)page_file_index(page)) << PAGE_SHIFT; } extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, @@ -425,7 +425,7 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; - return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT); + return pgoff; } extern void __lock_page(struct page *page); @@ -671,8 +671,8 @@ static inline int add_to_page_cache(struct page *page, static inline unsigned long dir_pages(struct inode *inode) { - return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> + PAGE_SHIFT; } #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index d18b65c53dbb..3d980ea1c946 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -435,7 +435,7 @@ struct backing_dev_info; /* only sparc can not include linux/pagemap.h in this file * so leave page_cache_release and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ - page_cache_release(page) + put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr), false); -- cgit v1.2.3 From ea1754a084760e68886f5b725c8eaada9cc57155 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 1 Apr 2016 15:29:48 +0300 Subject: mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage Mostly direct substitution with occasional adjustment or removing outdated comments. Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 2 +- include/linux/mm.h | 2 +- include/linux/mm_types.h | 2 +- include/linux/nfs_page.h | 4 ++-- include/linux/nilfs2_fs.h | 4 ++-- include/linux/pagemap.h | 3 +-- include/linux/sunrpc/svc.h | 2 +- include/linux/swap.h | 2 +- 8 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 1b4d69f68c33..3f103076d0bf 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -135,7 +135,7 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; - unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ + unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned int capabilities; /* Device capabilities */ congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ diff --git a/include/linux/mm.h b/include/linux/mm.h index ed6407d1b7b5..ffcff53e3b2b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -623,7 +623,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, - * in units of PAGE_CACHE_SIZE. + * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 944b2b37313b..c2d75b4fa86c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct vm_area_struct { /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE - units, *not* PAGE_CACHE_SIZE */ + units */ struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index efada239205e..957049f72290 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -41,8 +41,8 @@ struct nfs_page { struct page *wb_page; /* page to read in/write out */ struct nfs_open_context *wb_context; /* File state context info */ struct nfs_lock_context *wb_lock_context; /* lock context info */ - pgoff_t wb_index; /* Offset >> PAGE_CACHE_SHIFT */ - unsigned int wb_offset, /* Offset & ~PAGE_CACHE_MASK */ + pgoff_t wb_index; /* Offset >> PAGE_SHIFT */ + unsigned int wb_offset, /* Offset & ~PAGE_MASK */ wb_pgbase, /* Start of page data */ wb_bytes; /* Length of request */ struct kref wb_kref; /* reference count */ diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 9abb763e4b86..e9fcf90b270d 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -331,7 +331,7 @@ static inline unsigned nilfs_rec_len_from_disk(__le16 dlen) { unsigned len = le16_to_cpu(dlen); -#if !defined(__KERNEL__) || (PAGE_CACHE_SIZE >= 65536) +#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536) if (len == NILFS_MAX_REC_LEN) return 1 << 16; #endif @@ -340,7 +340,7 @@ static inline unsigned nilfs_rec_len_from_disk(__le16 dlen) static inline __le16 nilfs_rec_len_to_disk(unsigned len) { -#if !defined(__KERNEL__) || (PAGE_CACHE_SIZE >= 65536) +#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536) if (len == (1 << 16)) return cpu_to_le16(NILFS_MAX_REC_LEN); else if (len > (1 << 16)) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index f396ccb900cc..b3fc0370c14f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -535,8 +535,7 @@ extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); /* * Fault a userspace page into pagetables. Return non-zero on a fault. * - * This assumes that two userspace pages are always sufficient. That's - * not true if PAGE_CACHE_SIZE > PAGE_SIZE. + * This assumes that two userspace pages are always sufficient. */ static inline int fault_in_pages_writeable(char __user *uaddr, int size) { diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index cc0fc712bb82..7ca44fb5b675 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -129,7 +129,7 @@ static inline void svc_get(struct svc_serv *serv) * * These happen to all be powers of 2, which is not strictly * necessary but helps enforce the real limitation, which is - * that they should be multiples of PAGE_CACHE_SIZE. + * that they should be multiples of PAGE_SIZE. * * For UDP transports, a block plus NFS,RPC, and UDP headers * has to fit into the IP datagram limit of 64K. The largest diff --git a/include/linux/swap.h b/include/linux/swap.h index 3d980ea1c946..2b83359c19ca 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -433,7 +433,7 @@ struct backing_dev_info; #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file - * so leave page_cache_release and release_pages undeclared... */ + * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ -- cgit v1.2.3 From 1fa64f198b9f8d6ec0f7aec7c18dc94684391140 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 1 Apr 2016 15:29:49 +0300 Subject: mm: drop PAGE_CACHE_* and page_cache_{get,release} definition All users gone. We can remove these macros. Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b3fc0370c14f..7e1ab155c67c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -86,21 +86,6 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) (__force unsigned long)mask; } -/* - * The page cache can be done in larger chunks than - * one page, because it allows for more efficient - * throughput (it can then be mapped into user - * space in smaller chunks for same flexibility). - * - * Or rather, it _will_ be done in larger chunks. - */ -#define PAGE_CACHE_SHIFT PAGE_SHIFT -#define PAGE_CACHE_SIZE PAGE_SIZE -#define PAGE_CACHE_MASK PAGE_MASK -#define PAGE_CACHE_ALIGN(addr) (((addr)+PAGE_CACHE_SIZE-1)&PAGE_CACHE_MASK) - -#define page_cache_get(page) get_page(page) -#define page_cache_release(page) put_page(page) void release_pages(struct page **pages, int nr, bool cold); /* -- cgit v1.2.3 From b70bb984489363aadd5ccc94d919629d9e264d36 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 15 Mar 2016 22:37:17 +0100 Subject: iommu: provide of_xlate pointer unconditionally iommu drivers that support the standard DT bindings use a of_xlate callback pointer, but that is only part of struct iommu_ops when CONFIG_OF_IOMMU is enabled, leading to build errors in randconfig builds when that is not provided: drivers/iommu/mtk_iommu.c:497:2: error: unknown field 'of_xlate' specified in initializer .of_xlate = mtk_iommu_of_xlate, ^ drivers/iommu/mtk_iommu.c:497:14: error: initialization from incompatible pointer type [-Werror=incompatible-pointer-types] .of_xlate = mtk_iommu_of_xlate, ^~~~~~~~~~~~~~~~~~ drivers/iommu/mtk_iommu.c:497:14: note: (near initialization for 'mtk_iommu_ops.domain_get_attr') We can work around it by adding more #ifdefs in each driver, but it seems nicer to just allow setting the pointer even if it is unused. This makes the driver code look nicer, and it gives better compile-time coverage when test building on other architectures. Signed-off-by: Arnd Bergmann Fixes: 0df4fabe208d ("iommu/mediatek: Add mt8173 IOMMU driver") Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a5c539fa5d2b..ef7a6ecd8584 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -195,9 +195,7 @@ struct iommu_ops { /* Get the number of windows per domain */ u32 (*domain_get_windows)(struct iommu_domain *domain); -#ifdef CONFIG_OF_IOMMU int (*of_xlate)(struct device *dev, struct of_phandle_args *args); -#endif unsigned long pgsize_bitmap; void *priv; -- cgit v1.2.3 From 95272c29378ee7dc15f43fa2758cb28a5913a06d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 31 Mar 2016 09:38:51 +0200 Subject: compiler-gcc: disable -ftracer for __noclone functions -ftracer can duplicate asm blocks causing compilation to fail in noclone functions. For example, KVM declares a global variable in an asm like asm("2: ... \n .pushsection data \n .global vmx_return \n vmx_return: .long 2b"); and -ftracer causes a double declaration. Cc: Andrew Morton Cc: Michal Marek Cc: stable@vger.kernel.org Cc: kvm@vger.kernel.org Reported-by: Linda Walsh Signed-off-by: Paolo Bonzini --- include/linux/compiler-gcc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 22ab246feed3..eeae401a2412 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -199,7 +199,7 @@ #define unreachable() __builtin_unreachable() /* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) +#define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) #endif /* GCC_VERSION >= 40500 */ -- cgit v1.2.3 From a0ca153f98db8cf25298565a09e11fe9d82846ad Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 5 Apr 2016 09:13:39 -0700 Subject: GRE: Disable segmentation offloads w/ CSUM and we are encapsulated via FOU This patch fixes an issue I found in which we were dropping frames if we had enabled checksums on GRE headers that were encapsulated by either FOU or GUE. Without this patch I was barely able to get 1 Gb/s of throughput. With this patch applied I am now at least getting around 6 Gb/s. The issue is due to the fact that with FOU or GUE applied we do not provide a transport offset pointing to the GRE header, nor do we offload it in software as the GRE header is completely skipped by GSO and treated like a VXLAN or GENEVE type header. As such we need to prevent the stack from generating it and also prevent GRE from generating it via any interface we create. Fixes: c3483384ee511 ("gro: Allow tunnel stacking in the case of FOU/GUE") Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cb0d5d09c2e4..8395308a2445 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2120,7 +2120,10 @@ struct napi_gro_cb { /* Used in foo-over-udp, set in udp[46]_gro_receive */ u8 is_ipv6:1; - /* 7 bit hole */ + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; + + /* 6 bit hole */ /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; -- cgit v1.2.3