From 0133370f93eae5ed3c0f16d9da2b7add7dda6076 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Fri, 2 Nov 2012 13:44:46 +0530 Subject: drivers: bus: ocp2scp: add pdata support ocp2scp was not having pdata support which makes *musb* fail for non-dt boot in OMAP platform. The pdata will have information about the devices that is connected to ocp2scp. ocp2scp driver will now make use of this information to create the devices that is attached to ocp2scp. This is needed to fix MUSB regression caused by commit c9e4412a (arm: omap: phy: remove unused functions from omap-phy-internal.c) Signed-off-by: Kishon Vijay Abraham I Acked-by: Felipe Balbi [tony@atomide.com: updated comments for regression info] Signed-off-by: Tony Lindgren --- include/linux/platform_data/omap_ocp2scp.h | 31 ++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/platform_data/omap_ocp2scp.h (limited to 'include') diff --git a/include/linux/platform_data/omap_ocp2scp.h b/include/linux/platform_data/omap_ocp2scp.h new file mode 100644 index 000000000000..5c6c3939355f --- /dev/null +++ b/include/linux/platform_data/omap_ocp2scp.h @@ -0,0 +1,31 @@ +/* + * omap_ocp2scp.h -- ocp2scp header file + * + * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Author: Kishon Vijay Abraham I + * + * 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 __DRIVERS_OMAP_OCP2SCP_H +#define __DRIVERS_OMAP_OCP2SCP_H + +struct omap_ocp2scp_dev { + const char *drv_name; + struct resource *res; +}; + +struct omap_ocp2scp_platform_data { + int dev_cnt; + struct omap_ocp2scp_dev **devices; +}; +#endif /* __DRIVERS_OMAP_OCP2SCP_H */ -- cgit v1.2.3 From 703fb94ec58e0e8769380c2877a8a34aeb5b6c97 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 13 Nov 2012 08:52:24 +0100 Subject: xfrm: Fix the gc threshold value for ipv4 The xfrm gc threshold value depends on ip_rt_max_size. This value was set to INT_MAX with the routing cache removal patch, so we start doing garbage collecting when we have INT_MAX/2 IPsec routes cached. Fix this by going back to the static threshold of 1024 routes. Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 2 +- net/ipv4/route.c | 2 +- net/ipv4/xfrm4_policy.c | 13 +------------ 3 files changed, 3 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6f0ba01afe73..63445ede48bb 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1351,7 +1351,7 @@ struct xfrm6_tunnel { }; extern void xfrm_init(void); -extern void xfrm4_init(int rt_hash_size); +extern void xfrm4_init(void); extern int xfrm_state_init(struct net *net); extern void xfrm_state_fini(struct net *net); extern void xfrm4_state_init(void); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a8c651216fa6..200d287e49f5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2597,7 +2597,7 @@ int __init ip_rt_init(void) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); - xfrm4_init(ip_rt_max_size); + xfrm4_init(); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05c5ab8d983c..3be0ac2c1920 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -279,19 +279,8 @@ static void __exit xfrm4_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo); } -void __init xfrm4_init(int rt_max_size) +void __init xfrm4_init(void) { - /* - * Select a default value for the gc_thresh based on the main route - * table hash size. It seems to me the worst case scenario is when - * we have ipsec operating in transport mode, in which we create a - * dst_entry per socket. The xfrm gc algorithm starts trying to remove - * entries at gc_thresh, and prevents new allocations as 2*gc_thresh - * so lets set an initial xfrm gc_thresh value at the rt_max_size/2. - * That will let us store an ipsec connection per route table entry, - * and start cleaning when were 1/2 full - */ - xfrm4_dst_ops.gc_thresh = rt_max_size/2; dst_entries_init(&xfrm4_dst_ops); xfrm4_state_init(); -- cgit v1.2.3 From 3c6bdaeab4fda6c9fdd5f3f5c610dea97bddf7d6 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 18 Sep 2012 12:19:30 -0400 Subject: [SCSI] Add a report opcode helper The REPORT SUPPORTED OPERATION CODES command can be used to query whether a given opcode is supported by a device. Add a helper function that allows us to look up commands. We only issue RSOC if the device reports compliance with SPC-3 or later. But to err on the side of caution we disable the command for ATA, FireWire and USB. Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Signed-off-by: James Bottomley --- drivers/ata/libata-scsi.c | 1 + drivers/firewire/sbp2.c | 1 + drivers/scsi/scsi.c | 45 ++++++++++++++++++++++++++++++++++++++++++ drivers/usb/storage/scsiglue.c | 3 +++ include/scsi/scsi_device.h | 3 +++ 5 files changed, 53 insertions(+) (limited to 'include') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e3bda074fa12..7c2dead60518 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1052,6 +1052,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) { sdev->use_10_for_rw = 1; sdev->use_10_for_ms = 1; + sdev->no_report_opcodes = 1; /* Schedule policy is determined by ->qc_defer() callback and * it needs to see every deferred qc. Set dev_blocked to 1 to diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 1162d6b3bf85..f82e9d4295d0 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1546,6 +1546,7 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) struct sbp2_logical_unit *lu = sdev->hostdata; sdev->use_10_for_rw = 1; + sdev->no_report_opcodes = 1; if (sbp2_param_exclusive_login) sdev->manage_start_stop = 1; diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 2936b447cae9..2c0d0ec8150b 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #include @@ -1061,6 +1062,50 @@ int scsi_get_vpd_page(struct scsi_device *sdev, u8 page, unsigned char *buf, } EXPORT_SYMBOL_GPL(scsi_get_vpd_page); +/** + * scsi_report_opcode - Find out if a given command opcode is supported + * @sdev: scsi device to query + * @buffer: scratch buffer (must be at least 20 bytes long) + * @len: length of buffer + * @opcode: opcode for command to look up + * + * Uses the REPORT SUPPORTED OPERATION CODES to look up the given + * opcode. Returns 0 if RSOC fails or if the command opcode is + * unsupported. Returns 1 if the device claims to support the command. + */ +int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, + unsigned int len, unsigned char opcode) +{ + unsigned char cmd[16]; + struct scsi_sense_hdr sshdr; + int result; + + if (sdev->no_report_opcodes || sdev->scsi_level < SCSI_SPC_3) + return 0; + + memset(cmd, 0, 16); + cmd[0] = MAINTENANCE_IN; + cmd[1] = MI_REPORT_SUPPORTED_OPERATION_CODES; + cmd[2] = 1; /* One command format */ + cmd[3] = opcode; + put_unaligned_be32(len, &cmd[6]); + memset(buffer, 0, len); + + result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buffer, len, + &sshdr, 30 * HZ, 3, NULL); + + if (result && scsi_sense_valid(&sshdr) && + sshdr.sense_key == ILLEGAL_REQUEST && + (sshdr.asc == 0x20 || sshdr.asc == 0x24) && sshdr.ascq == 0x00) + return 0; + + if ((buffer[1] & 3) == 3) /* Command supported */ + return 1; + + return 0; +} +EXPORT_SYMBOL(scsi_report_opcode); + /** * scsi_device_get - get an additional reference to a scsi_device * @sdev: device to get a reference to diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index a3d54366afcc..6ab376a7c501 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -186,6 +186,9 @@ static int slave_configure(struct scsi_device *sdev) /* Some devices don't handle VPD pages correctly */ sdev->skip_vpd_pages = 1; + /* Do not attempt to use REPORT SUPPORTED OPERATION CODES */ + sdev->no_report_opcodes = 1; + /* Some disks return the total number of blocks in response * to READ CAPACITY rather than the highest block number. * If this device makes that mistake, tell the sd driver. */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 88fae8d20154..379d465e8070 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -135,6 +135,7 @@ struct scsi_device { * because we did a bus reset. */ unsigned use_10_for_rw:1; /* first try 10-byte read / write */ unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */ + unsigned no_report_opcodes:1; /* no REPORT SUPPORTED OPERATION CODES */ unsigned skip_ms_page_8:1; /* do not use MODE SENSE page 0x08 */ unsigned skip_ms_page_3f:1; /* do not use MODE SENSE page 0x3f */ unsigned skip_vpd_pages:1; /* do not read VPD pages */ @@ -362,6 +363,8 @@ extern int scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries, struct scsi_sense_hdr *sshdr); extern int scsi_get_vpd_page(struct scsi_device *, u8 page, unsigned char *buf, int buf_len); +extern int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, + unsigned int len, unsigned char opcode); extern int scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state); extern struct scsi_event *sdev_evt_alloc(enum scsi_device_event evt_type, -- cgit v1.2.3 From 5db44863b6ebbb400c5e61d56ebe8f21ef48b1bd Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 18 Sep 2012 12:19:32 -0400 Subject: [SCSI] sd: Implement support for WRITE SAME Implement support for WRITE SAME(10) and WRITE SAME(16) in the SCSI disk driver. - We set the default maximum to 0xFFFF because there are several devices out there that only support two-byte block counts even with WRITE SAME(16). We only enable transfers bigger than 0xFFFF if the device explicitly reports MAXIMUM WRITE SAME LENGTH in the BLOCK LIMITS VPD. - max_write_same_blocks can be overriden per-device basis in sysfs. - The UNMAP discovery heuristics remain unchanged but the discard limits are tweaked to match the "real" WRITE SAME commands. - In the error handling logic we now distinguish between WRITE SAME with and without UNMAP set. The discovery process heuristics are: - If the device reports a SCSI level of SPC-3 or greater we'll issue READ SUPPORTED OPERATION CODES to find out whether WRITE SAME(16) is supported. If that's the case we will use it. - If the device supports the block limits VPD and reports a MAXIMUM WRITE SAME LENGTH bigger than 0xFFFF we will use WRITE SAME(16). - Otherwise we will use WRITE SAME(10) unless the target LBA is beyond 0xFFFFFFFF or the block count exceeds 0xFFFF. - no_write_same is set for ATA, FireWire and USB. Signed-off-by: Martin K. Petersen Reviewed-by: Mike Snitzer Reviewed-by: Jeff Garzik Signed-off-by: James Bottomley --- drivers/ata/libata-scsi.c | 1 + drivers/firewire/sbp2.c | 1 + drivers/scsi/scsi_lib.c | 22 ++++-- drivers/scsi/sd.c | 172 ++++++++++++++++++++++++++++++++++++++--- drivers/scsi/sd.h | 7 ++ drivers/usb/storage/scsiglue.c | 3 + include/scsi/scsi_device.h | 1 + 7 files changed, 191 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7c2dead60518..a6df6a351d6e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1053,6 +1053,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) sdev->use_10_for_rw = 1; sdev->use_10_for_ms = 1; sdev->no_report_opcodes = 1; + sdev->no_write_same = 1; /* Schedule policy is determined by ->qc_defer() callback and * it needs to see every deferred qc. Set dev_blocked to 1 to diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index f82e9d4295d0..bb1b392f5cda 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1547,6 +1547,7 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->use_10_for_rw = 1; sdev->no_report_opcodes = 1; + sdev->no_write_same = 1; if (sbp2_param_exclusive_login) sdev->manage_start_stop = 1; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index da36a3a81a9e..9032e910bca3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -900,11 +900,23 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) action = ACTION_FAIL; error = -EILSEQ; /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */ - } else if ((sshdr.asc == 0x20 || sshdr.asc == 0x24) && - (cmd->cmnd[0] == UNMAP || - cmd->cmnd[0] == WRITE_SAME_16 || - cmd->cmnd[0] == WRITE_SAME)) { - description = "Discard failure"; + } else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) { + switch (cmd->cmnd[0]) { + case UNMAP: + description = "Discard failure"; + break; + case WRITE_SAME: + case WRITE_SAME_16: + if (cmd->cmnd[1] & 0x8) + description = "Discard failure"; + else + description = + "Write same failure"; + break; + default: + description = "Invalid command failure"; + break; + } action = ACTION_FAIL; error = -EREMOTEIO; } else diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index c6af4c1a9ca3..352bc77b7c88 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -99,6 +99,7 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); #endif static void sd_config_discard(struct scsi_disk *, unsigned int); +static void sd_config_write_same(struct scsi_disk *); static int sd_revalidate_disk(struct gendisk *); static void sd_unlock_native_capacity(struct gendisk *disk); static int sd_probe(struct device *); @@ -395,6 +396,45 @@ sd_store_max_medium_access_timeouts(struct device *dev, return err ? err : count; } +static ssize_t +sd_show_write_same_blocks(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->max_ws_blocks); +} + +static ssize_t +sd_store_write_same_blocks(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + unsigned long max; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (sdp->type != TYPE_DISK) + return -EINVAL; + + err = kstrtoul(buf, 10, &max); + + if (err) + return err; + + if (max == 0) + sdp->no_write_same = 1; + else if (max <= SD_MAX_WS16_BLOCKS) + sdkp->max_ws_blocks = max; + + sd_config_write_same(sdkp); + + return count; +} + static struct device_attribute sd_disk_attrs[] = { __ATTR(cache_type, S_IRUGO|S_IWUSR, sd_show_cache_type, sd_store_cache_type), @@ -410,6 +450,8 @@ static struct device_attribute sd_disk_attrs[] = { __ATTR(thin_provisioning, S_IRUGO, sd_show_thin_provisioning, NULL), __ATTR(provisioning_mode, S_IRUGO|S_IWUSR, sd_show_provisioning_mode, sd_store_provisioning_mode), + __ATTR(max_write_same_blocks, S_IRUGO|S_IWUSR, + sd_show_write_same_blocks, sd_store_write_same_blocks), __ATTR(max_medium_access_timeouts, S_IRUGO|S_IWUSR, sd_show_max_medium_access_timeouts, sd_store_max_medium_access_timeouts), @@ -561,19 +603,23 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) return; case SD_LBP_UNMAP: - max_blocks = min_not_zero(sdkp->max_unmap_blocks, 0xffffffff); + max_blocks = min_not_zero(sdkp->max_unmap_blocks, + (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS16: - max_blocks = min_not_zero(sdkp->max_ws_blocks, 0xffffffff); + max_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS10: - max_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)0xffff); + max_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: - max_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)0xffff); + max_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS10_BLOCKS); q->limits.discard_zeroes_data = 1; break; } @@ -667,6 +713,83 @@ out: return ret; } +static void sd_config_write_same(struct scsi_disk *sdkp) +{ + struct request_queue *q = sdkp->disk->queue; + unsigned int logical_block_size = sdkp->device->sector_size; + unsigned int blocks = 0; + + if (sdkp->device->no_write_same) { + sdkp->max_ws_blocks = 0; + goto out; + } + + /* Some devices can not handle block counts above 0xffff despite + * supporting WRITE SAME(16). Consequently we default to 64k + * blocks per I/O unless the device explicitly advertises a + * bigger limit. + */ + if (sdkp->max_ws_blocks == 0) + sdkp->max_ws_blocks = SD_MAX_WS10_BLOCKS; + + if (sdkp->ws16 || sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS) + blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS16_BLOCKS); + else + blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS10_BLOCKS); + +out: + blk_queue_max_write_same_sectors(q, blocks * (logical_block_size >> 9)); +} + +/** + * sd_setup_write_same_cmnd - write the same data to multiple blocks + * @sdp: scsi device to operate one + * @rq: Request to prepare + * + * Will issue either WRITE SAME(10) or WRITE SAME(16) depending on + * preference indicated by target device. + **/ +static int sd_setup_write_same_cmnd(struct scsi_device *sdp, struct request *rq) +{ + struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct bio *bio = rq->bio; + sector_t sector = blk_rq_pos(rq); + unsigned int nr_sectors = blk_rq_sectors(rq); + unsigned int nr_bytes = blk_rq_bytes(rq); + int ret; + + if (sdkp->device->no_write_same) + return BLKPREP_KILL; + + BUG_ON(bio_offset(bio) || bio_iovec(bio)->bv_len != sdp->sector_size); + + sector >>= ilog2(sdp->sector_size) - 9; + nr_sectors >>= ilog2(sdp->sector_size) - 9; + + rq->__data_len = sdp->sector_size; + rq->timeout = SD_WRITE_SAME_TIMEOUT; + memset(rq->cmd, 0, rq->cmd_len); + + if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff) { + rq->cmd_len = 16; + rq->cmd[0] = WRITE_SAME_16; + put_unaligned_be64(sector, &rq->cmd[2]); + put_unaligned_be32(nr_sectors, &rq->cmd[10]); + } else { + rq->cmd_len = 10; + rq->cmd[0] = WRITE_SAME; + put_unaligned_be32(sector, &rq->cmd[2]); + put_unaligned_be16(nr_sectors, &rq->cmd[7]); + } + + ret = scsi_setup_blk_pc_cmnd(sdp, rq); + rq->__data_len = nr_bytes; + + return ret; +} + static int scsi_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq) { rq->timeout = SD_FLUSH_TIMEOUT; @@ -712,6 +835,9 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) if (rq->cmd_flags & REQ_DISCARD) { ret = sd_setup_discard_cmnd(sdp, rq); goto out; + } else if (rq->cmd_flags & REQ_WRITE_SAME) { + ret = sd_setup_write_same_cmnd(sdp, rq); + goto out; } else if (rq->cmd_flags & REQ_FLUSH) { ret = scsi_setup_flush_cmnd(sdp, rq); goto out; @@ -1484,8 +1610,9 @@ static int sd_done(struct scsi_cmnd *SCpnt) int sense_valid = 0; int sense_deferred = 0; unsigned char op = SCpnt->cmnd[0]; + unsigned char unmap = SCpnt->cmnd[1] & 8; - if (req->cmd_flags & REQ_DISCARD) { + if (req->cmd_flags & REQ_DISCARD || req->cmd_flags & REQ_WRITE_SAME) { if (!result) { good_bytes = blk_rq_bytes(req); scsi_set_resid(SCpnt, 0); @@ -1542,9 +1669,25 @@ static int sd_done(struct scsi_cmnd *SCpnt) if (sshdr.asc == 0x10) /* DIX: Host detected corruption */ good_bytes = sd_completed_bytes(SCpnt); /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */ - if ((sshdr.asc == 0x20 || sshdr.asc == 0x24) && - (op == UNMAP || op == WRITE_SAME_16 || op == WRITE_SAME)) - sd_config_discard(sdkp, SD_LBP_DISABLE); + if (sshdr.asc == 0x20 || sshdr.asc == 0x24) { + switch (op) { + case UNMAP: + sd_config_discard(sdkp, SD_LBP_DISABLE); + break; + case WRITE_SAME_16: + case WRITE_SAME: + if (unmap) + sd_config_discard(sdkp, SD_LBP_DISABLE); + else { + sdkp->device->no_write_same = 1; + sd_config_write_same(sdkp); + + good_bytes = 0; + req->__data_len = blk_rq_bytes(req); + req->cmd_flags |= REQ_QUIET; + } + } + } break; default: break; @@ -2380,9 +2523,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) if (buffer[3] == 0x3c) { unsigned int lba_count, desc_count; - sdkp->max_ws_blocks = - (u32) min_not_zero(get_unaligned_be64(&buffer[36]), - (u64)0xffffffff); + sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]); if (!sdkp->lbpme) goto out; @@ -2475,6 +2616,13 @@ static void sd_read_block_provisioning(struct scsi_disk *sdkp) kfree(buffer); } +static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) +{ + if (scsi_report_opcode(sdkp->device, buffer, SD_BUF_SIZE, + WRITE_SAME_16)) + sdkp->ws16 = 1; +} + static int sd_try_extended_inquiry(struct scsi_device *sdp) { /* @@ -2534,6 +2682,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_write_protect_flag(sdkp, buffer); sd_read_cache_type(sdkp, buffer); sd_read_app_tag_own(sdkp, buffer); + sd_read_write_same(sdkp, buffer); } sdkp->first_scan = 0; @@ -2551,6 +2700,7 @@ static int sd_revalidate_disk(struct gendisk *disk) blk_queue_flush(sdkp->disk->queue, flush); set_capacity(disk, sdkp->capacity); + sd_config_write_same(sdkp); kfree(buffer); out: diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 47c52a6d733c..74a1e4ca5401 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -14,6 +14,7 @@ #define SD_TIMEOUT (30 * HZ) #define SD_MOD_TIMEOUT (75 * HZ) #define SD_FLUSH_TIMEOUT (60 * HZ) +#define SD_WRITE_SAME_TIMEOUT (120 * HZ) /* * Number of allowed retries @@ -38,6 +39,11 @@ enum { SD_MEMPOOL_SIZE = 2, /* CDB pool size */ }; +enum { + SD_MAX_WS10_BLOCKS = 0xffff, + SD_MAX_WS16_BLOCKS = 0x7fffff, +}; + enum { SD_LBP_FULL = 0, /* Full logical block provisioning */ SD_LBP_UNMAP, /* Use UNMAP command */ @@ -77,6 +83,7 @@ struct scsi_disk { unsigned lbpws : 1; unsigned lbpws10 : 1; unsigned lbpvpd : 1; + unsigned ws16 : 1; }; #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 6ab376a7c501..92f35abee92d 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -189,6 +189,9 @@ static int slave_configure(struct scsi_device *sdev) /* Do not attempt to use REPORT SUPPORTED OPERATION CODES */ sdev->no_report_opcodes = 1; + /* Do not attempt to use WRITE SAME */ + sdev->no_write_same = 1; + /* Some disks return the total number of blocks in response * to READ CAPACITY rather than the highest block number. * If this device makes that mistake, tell the sd driver. */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 379d465e8070..55367b04dc94 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -136,6 +136,7 @@ struct scsi_device { unsigned use_10_for_rw:1; /* first try 10-byte read / write */ unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */ unsigned no_report_opcodes:1; /* no REPORT SUPPORTED OPERATION CODES */ + unsigned no_write_same:1; /* no WRITE SAME command */ unsigned skip_ms_page_8:1; /* do not use MODE SENSE page 0x08 */ unsigned skip_ms_page_3f:1; /* do not use MODE SENSE page 0x3f */ unsigned skip_vpd_pages:1; /* do not read VPD pages */ -- cgit v1.2.3 From 9aadd70aed60b47e367e7a1a6b9068daba04fe05 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Tue, 6 Nov 2012 16:31:32 +0000 Subject: Revert "ARM: OMAP: convert I2C driver to PM QoS for MPU latency constraints" This reverts commit 3db11feffc1ad2ab9dea27789e6b5b3032827adc (ARM: OMAP: convert I2C driver to PM QoS for MPU latency constraints). This commit causes I2C timeouts to appear on several OMAP3430/3530-based boards: http://marc.info/?l=linux-arm-kernel&m=135071372426971&w=2 http://marc.info/?l=linux-arm-kernel&m=135067558415214&w=2 http://marc.info/?l=linux-arm-kernel&m=135216013608196&w=2 and appears to have been sent for merging before one of its prerequisites was merged: http://marc.info/?l=linux-arm-kernel&m=135219411617621&w=2 Signed-off-by: Paul Walmsley Acked-by: Jean Pihet Signed-off-by: Wolfram Sang --- arch/arm/plat-omap/i2c.c | 21 +++++++++++++++++++++ drivers/i2c/busses/i2c-omap.c | 32 ++++++++++++++------------------ include/linux/i2c-omap.h | 1 + 3 files changed, 36 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/arch/arm/plat-omap/i2c.c b/arch/arm/plat-omap/i2c.c index a5683a84c6ee..6013831a043e 100644 --- a/arch/arm/plat-omap/i2c.c +++ b/arch/arm/plat-omap/i2c.c @@ -26,12 +26,14 @@ #include #include #include +#include #include #include #include #include #include +#include #include #define OMAP_I2C_SIZE 0x3f @@ -127,6 +129,16 @@ static inline int omap1_i2c_add_bus(int bus_id) #ifdef CONFIG_ARCH_OMAP2PLUS +/* + * XXX This function is a temporary compatibility wrapper - only + * needed until the I2C driver can be converted to call + * omap_pm_set_max_dev_wakeup_lat() and handle a return code. + */ +static void omap_pm_set_max_mpu_wakeup_lat_compat(struct device *dev, long t) +{ + omap_pm_set_max_mpu_wakeup_lat(dev, t); +} + static inline int omap2_i2c_add_bus(int bus_id) { int l; @@ -158,6 +170,15 @@ static inline int omap2_i2c_add_bus(int bus_id) dev_attr = (struct omap_i2c_dev_attr *)oh->dev_attr; pdata->flags = dev_attr->flags; + /* + * When waiting for completion of a i2c transfer, we need to + * set a wake up latency constraint for the MPU. This is to + * ensure quick enough wakeup from idle, when transfer + * completes. + * Only omap3 has support for constraints + */ + if (cpu_is_omap34xx()) + pdata->set_mpu_wkup_lat = omap_pm_set_max_mpu_wakeup_lat_compat; pdev = omap_device_build(name, bus_id, oh, pdata, sizeof(struct omap_i2c_bus_platform_data), NULL, 0, 0); diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index db31eaed6ea5..0b0254312d21 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -43,7 +43,6 @@ #include #include #include -#include /* I2C controller revisions */ #define OMAP_I2C_OMAP1_REV_2 0x20 @@ -187,8 +186,9 @@ struct omap_i2c_dev { int reg_shift; /* bit shift for I2C register addresses */ struct completion cmd_complete; struct resource *ioarea; - u32 latency; /* maximum MPU wkup latency */ - struct pm_qos_request pm_qos_request; + u32 latency; /* maximum mpu wkup latency */ + void (*set_mpu_wkup_lat)(struct device *dev, + long latency); u32 speed; /* Speed of bus in kHz */ u32 dtrev; /* extra revision from DT */ u32 flags; @@ -494,7 +494,9 @@ static void omap_i2c_resize_fifo(struct omap_i2c_dev *dev, u8 size, bool is_rx) dev->b_hw = 1; /* Enable hardware fixes */ /* calculate wakeup latency constraint for MPU */ - dev->latency = (1000000 * dev->threshold) / (1000 * dev->speed / 8); + if (dev->set_mpu_wkup_lat != NULL) + dev->latency = (1000000 * dev->threshold) / + (1000 * dev->speed / 8); } /* @@ -629,16 +631,8 @@ omap_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) if (r < 0) goto out; - /* - * When waiting for completion of a i2c transfer, we need to - * set a wake up latency constraint for the MPU. This is to - * ensure quick enough wakeup from idle, when transfer - * completes. - */ - if (dev->latency) - pm_qos_add_request(&dev->pm_qos_request, - PM_QOS_CPU_DMA_LATENCY, - dev->latency); + if (dev->set_mpu_wkup_lat != NULL) + dev->set_mpu_wkup_lat(dev->dev, dev->latency); for (i = 0; i < num; i++) { r = omap_i2c_xfer_msg(adap, &msgs[i], (i == (num - 1))); @@ -646,8 +640,8 @@ omap_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) break; } - if (dev->latency) - pm_qos_remove_request(&dev->pm_qos_request); + if (dev->set_mpu_wkup_lat != NULL) + dev->set_mpu_wkup_lat(dev->dev, -1); if (r == 0) r = num; @@ -1104,6 +1098,7 @@ omap_i2c_probe(struct platform_device *pdev) } else if (pdata != NULL) { dev->speed = pdata->clkrate; dev->flags = pdata->flags; + dev->set_mpu_wkup_lat = pdata->set_mpu_wkup_lat; dev->dtrev = pdata->rev; } @@ -1159,8 +1154,9 @@ omap_i2c_probe(struct platform_device *pdev) dev->b_hw = 1; /* Enable hardware fixes */ /* calculate wakeup latency constraint for MPU */ - dev->latency = (1000000 * dev->fifo_size) / - (1000 * dev->speed / 8); + if (dev->set_mpu_wkup_lat != NULL) + dev->latency = (1000000 * dev->fifo_size) / + (1000 * dev->speed / 8); } /* reset ASAP, clearing any IRQs */ diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h index df804ba73e0b..92a0dc75bc74 100644 --- a/include/linux/i2c-omap.h +++ b/include/linux/i2c-omap.h @@ -34,6 +34,7 @@ struct omap_i2c_bus_platform_data { u32 clkrate; u32 rev; u32 flags; + void (*set_mpu_wkup_lat)(struct device *dev, long set); }; #endif -- cgit v1.2.3 From 93532c8a4890871aa0d84dd91b80dad9f58542e0 Mon Sep 17 00:00:00 2001 From: Igor Mazanov Date: Thu, 15 Nov 2012 21:07:00 +0400 Subject: clk: remove inline usage from clk-provider.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Users of GCC 4.7 have reported compiler errors due to having inline applied to function declarations in clk-provider.h. The definitions exist in drivers/clk/clk.c. An example error: In file included from arch/arm/mach-omap2/clockdomain.c:25:0: arch/arm/mach-omap2/clockdomain.c: In function ‘clkdm_clk_disable’: include/linux/clk-provider.h:338:12: error: inlining failed in call to always_inline ‘__clk_get_enable_count’: function body not available arch/arm/mach-omap2/clockdomain.c:1001:28: error: called from here make[1]: *** [arch/arm/mach-omap2/clockdomain.o] Error 1 make: *** [arch/arm/mach-omap2] Error 2 This patch removes the use of inline from include/linux/clk-provider.h but keeps the function definitions in drivers/clk/clk.c as inlined since they are one-liners. Signed-off-by: Igor Mazanov Acked-by: Paul Walmsley Signed-off-by: Mike Turquette [mturquette@linaro.org: improved subject, added changelog] --- include/linux/clk-provider.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c12731582920..f9f5e9eeb9dd 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -335,8 +335,8 @@ const char *__clk_get_name(struct clk *clk); struct clk_hw *__clk_get_hw(struct clk *clk); u8 __clk_get_num_parents(struct clk *clk); struct clk *__clk_get_parent(struct clk *clk); -inline int __clk_get_enable_count(struct clk *clk); -inline int __clk_get_prepare_count(struct clk *clk); +int __clk_get_enable_count(struct clk *clk); +int __clk_get_prepare_count(struct clk *clk); unsigned long __clk_get_rate(struct clk *clk); unsigned long __clk_get_flags(struct clk *clk); int __clk_is_enabled(struct clk *clk); -- cgit v1.2.3 From fa0cbbf145aabbf29c6f28f8a11935c0b0fd86fc Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 12 Nov 2012 17:53:04 -0800 Subject: mm, oom: reintroduce /proc/pid/oom_adj This is mostly a revert of 01dc52ebdf47 ("oom: remove deprecated oom_adj") from Davidlohr Bueso. It reintroduces /proc/pid/oom_adj for backwards compatibility with earlier kernels. It simply scales the value linearly when /proc/pid/oom_score_adj is written. The major difference is that its scheduled removal is no longer included in Documentation/feature-removal-schedule.txt. We do warn users with a single printk, though, to suggest the more powerful and supported /proc/pid/oom_score_adj interface. Reported-by: Artem S. Tashkinov Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 16 ++++-- fs/proc/base.c | 109 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/oom.h | 9 +++ 3 files changed, 130 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index a1793d670cd0..3844d21d6ca3 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -33,7 +33,7 @@ Table of Contents 2 Modifying System Parameters 3 Per-Process Parameters - 3.1 /proc//oom_score_adj - Adjust the oom-killer + 3.1 /proc//oom_adj & /proc//oom_score_adj - Adjust the oom-killer score 3.2 /proc//oom_score - Display current oom-killer score 3.3 /proc//io - Display the IO accounting fields @@ -1320,10 +1320,10 @@ of the kernel. CHAPTER 3: PER-PROCESS PARAMETERS ------------------------------------------------------------------------------ -3.1 /proc//oom_score_adj- Adjust the oom-killer score +3.1 /proc//oom_adj & /proc//oom_score_adj- Adjust the oom-killer score -------------------------------------------------------------------------------- -This file can be used to adjust the badness heuristic used to select which +These file can be used to adjust the badness heuristic used to select which process gets killed in out of memory conditions. The badness heuristic assigns a value to each candidate task ranging from 0 @@ -1361,6 +1361,12 @@ same system, cpuset, mempolicy, or memory controller resources to use at least equivalent to discounting 50% of the task's allowed memory from being considered as scoring against the task. +For backwards compatibility with previous kernels, /proc//oom_adj may also +be used to tune the badness score. Its acceptable values range from -16 +(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 +(OOM_DISABLE) to disable oom killing entirely for that task. Its value is +scaled linearly with /proc//oom_score_adj. + The value of /proc//oom_score_adj may be reduced no lower than the last value set by a CAP_SYS_RESOURCE process. To reduce the value any lower requires CAP_SYS_RESOURCE. @@ -1375,7 +1381,9 @@ minimal amount of work. ------------------------------------------------------------- This file can be used to check the current score used by the oom-killer is for -any given . +any given . Use it together with /proc//oom_score_adj to tune which +process should be killed in an out-of-memory situation. + 3.3 /proc//io - Display the IO accounting fields ------------------------------------------------------- diff --git a/fs/proc/base.c b/fs/proc/base.c index 144a96732dd7..3c231adf8450 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = { .release = mem_release, }; +static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); + char buffer[PROC_NUMBUF]; + int oom_adj = OOM_ADJUST_MIN; + size_t len; + unsigned long flags; + + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) + oom_adj = OOM_ADJUST_MAX; + else + oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / + OOM_SCORE_ADJ_MAX; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t oom_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + int oom_adj; + unsigned long flags; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_adj); + if (err) + goto out; + if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && + oom_adj != OOM_DISABLE) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + /* + * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum + * value is always attainable. + */ + if (oom_adj == OOM_ADJUST_MAX) + oom_adj = OOM_SCORE_ADJ_MAX; + else + oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + + if (oom_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + /* + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use + * /proc/pid/oom_score_adj instead. + */ + printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + current->comm, task_pid_nr(current), task_pid_nr(task), + task_pid_nr(task)); + + task->signal->oom_score_adj = oom_adj; + trace_oom_score_adj_update(task); +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_adj_operations = { + .read = oom_adj_read, + .write = oom_adj_write, + .llseek = generic_file_llseek, +}; + static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -2598,6 +2705,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), @@ -2964,6 +3072,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), diff --git a/include/uapi/linux/oom.h b/include/uapi/linux/oom.h index a49c4afc7060..b29272d621ce 100644 --- a/include/uapi/linux/oom.h +++ b/include/uapi/linux/oom.h @@ -8,4 +8,13 @@ #define OOM_SCORE_ADJ_MIN (-1000) #define OOM_SCORE_ADJ_MAX 1000 +/* + * /proc//oom_adj set to -17 protects from the oom killer for legacy + * purposes. + */ +#define OOM_DISABLE (-17) +/* inclusive */ +#define OOM_ADJUST_MIN (-16) +#define OOM_ADJUST_MAX 15 + #endif /* _UAPI__INCLUDE_LINUX_OOM_H */ -- cgit v1.2.3 From bea8c150a7efbc0f204e709b7274fe273f55e0d3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 16 Nov 2012 14:14:54 -0800 Subject: memcg: fix hotplugged memory zone oops When MEMCG is configured on (even when it's disabled by boot option), when adding or removing a page to/from its lru list, the zone pointer used for stats updates is nowadays taken from the struct lruvec. (On many configurations, calculating zone from page is slower.) But we have no code to update all the lruvecs (per zone, per memcg) when a memory node is hotadded. Here's an extract from the oops which results when running numactl to bind a program to a newly onlined node: BUG: unable to handle kernel NULL pointer dereference at 0000000000000f60 IP: __mod_zone_page_state+0x9/0x60 Pid: 1219, comm: numactl Not tainted 3.6.0-rc5+ #180 Bochs Bochs Process numactl (pid: 1219, threadinfo ffff880039abc000, task ffff8800383c4ce0) Call Trace: __pagevec_lru_add_fn+0xdf/0x140 pagevec_lru_move_fn+0xb1/0x100 __pagevec_lru_add+0x1c/0x30 lru_add_drain_cpu+0xa3/0x130 lru_add_drain+0x2f/0x40 ... The natural solution might be to use a memcg callback whenever memory is hotadded; but that solution has not been scoped out, and it happens that we do have an easy location at which to update lruvec->zone. The lruvec pointer is discovered either by mem_cgroup_zone_lruvec() or by mem_cgroup_page_lruvec(), and both of those do know the right zone. So check and set lruvec->zone in those; and remove the inadequate attempt to set lruvec->zone from lruvec_init(), which is called before NODE_DATA(node) has been allocated in such cases. Ah, there was one exceptionr. For no particularly good reason, mem_cgroup_force_empty_list() has its own code for deciding lruvec. Change it to use the standard mem_cgroup_zone_lruvec() and mem_cgroup_get_lru_size() too. In fact it was already safe against such an oops (the lru lists in danger could only be empty), but we're better proofed against future changes this way. I've marked this for stable (3.6) since we introduced the problem in 3.5 (now closed to stable); but I have no idea if this is the only fix needed to get memory hotadd working with memcg in 3.6, and received no answer when I enquired twice before. Reported-by: Tang Chen Signed-off-by: Hugh Dickins Acked-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Cc: Konstantin Khlebnikov Cc: Wen Congyang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- mm/memcontrol.c | 46 +++++++++++++++++++++++++++++++++++----------- mm/mmzone.c | 6 +----- mm/page_alloc.c | 2 +- 4 files changed, 38 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 50aaca81f63d..a23923ba8263 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -752,7 +752,7 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size, enum memmap_context context); -extern void lruvec_init(struct lruvec *lruvec, struct zone *zone); +extern void lruvec_init(struct lruvec *lruvec); static inline struct zone *lruvec_zone(struct lruvec *lruvec) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 93a7e36ded89..dd39ba000b31 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1055,12 +1055,24 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, struct mem_cgroup *memcg) { struct mem_cgroup_per_zone *mz; + struct lruvec *lruvec; - if (mem_cgroup_disabled()) - return &zone->lruvec; + if (mem_cgroup_disabled()) { + lruvec = &zone->lruvec; + goto out; + } mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone)); - return &mz->lruvec; + lruvec = &mz->lruvec; +out: + /* + * Since a node can be onlined after the mem_cgroup was created, + * we have to be prepared to initialize lruvec->zone here; + * and if offlined then reonlined, we need to reinitialize it. + */ + if (unlikely(lruvec->zone != zone)) + lruvec->zone = zone; + return lruvec; } /* @@ -1087,9 +1099,12 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) struct mem_cgroup_per_zone *mz; struct mem_cgroup *memcg; struct page_cgroup *pc; + struct lruvec *lruvec; - if (mem_cgroup_disabled()) - return &zone->lruvec; + if (mem_cgroup_disabled()) { + lruvec = &zone->lruvec; + goto out; + } pc = lookup_page_cgroup(page); memcg = pc->mem_cgroup; @@ -1107,7 +1122,16 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) pc->mem_cgroup = memcg = root_mem_cgroup; mz = page_cgroup_zoneinfo(memcg, page); - return &mz->lruvec; + lruvec = &mz->lruvec; +out: + /* + * Since a node can be onlined after the mem_cgroup was created, + * we have to be prepared to initialize lruvec->zone here; + * and if offlined then reonlined, we need to reinitialize it. + */ + if (unlikely(lruvec->zone != zone)) + lruvec->zone = zone; + return lruvec; } /** @@ -3697,17 +3721,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg, int node, int zid, enum lru_list lru) { - struct mem_cgroup_per_zone *mz; + struct lruvec *lruvec; unsigned long flags, loop; struct list_head *list; struct page *busy; struct zone *zone; zone = &NODE_DATA(node)->node_zones[zid]; - mz = mem_cgroup_zoneinfo(memcg, node, zid); - list = &mz->lruvec.lists[lru]; + lruvec = mem_cgroup_zone_lruvec(zone, memcg); + list = &lruvec->lists[lru]; - loop = mz->lru_size[lru]; + loop = mem_cgroup_get_lru_size(lruvec, lru); /* give some margin against EBUSY etc...*/ loop += 256; busy = NULL; @@ -4745,7 +4769,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; - lruvec_init(&mz->lruvec, &NODE_DATA(node)->node_zones[zone]); + lruvec_init(&mz->lruvec); mz->usage_in_excess = 0; mz->on_tree = false; mz->memcg = memcg; diff --git a/mm/mmzone.c b/mm/mmzone.c index 3cef80f6ac79..4596d81b89b1 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -87,7 +87,7 @@ int memmap_valid_within(unsigned long pfn, } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ -void lruvec_init(struct lruvec *lruvec, struct zone *zone) +void lruvec_init(struct lruvec *lruvec) { enum lru_list lru; @@ -95,8 +95,4 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone) for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); - -#ifdef CONFIG_MEMCG - lruvec->zone = zone; -#endif } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5b74de6702e0..c91598b1b4c0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4505,7 +4505,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone->zone_pgdat = pgdat; zone_pcp_init(zone); - lruvec_init(&zone->lruvec, zone); + lruvec_init(&zone->lruvec); if (!size) continue; -- cgit v1.2.3 From 2ca3cb50edc351875df13d083524f524cdeb3054 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 16 Nov 2012 14:14:56 -0800 Subject: rapidio: fix kernel-doc warnings Fix rapidio kernel-doc warnings: Warning(drivers/rapidio/rio.c:415): No description found for parameter 'local' Warning(drivers/rapidio/rio.c:415): Excess function parameter 'lstart' description in 'rio_map_inb_region' Warning(include/linux/rio.h:290): No description found for parameter 'switches' Warning(include/linux/rio.h:290): No description found for parameter 'destid_table' Signed-off-by: Randy Dunlap Cc: Matt Porter Acked-by: Alexandre Bounine Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rapidio/rio.c | 2 +- include/linux/rio.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index c17ae22567e0..0c6fcb461faf 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -401,7 +401,7 @@ EXPORT_SYMBOL_GPL(rio_release_inb_pwrite); /** * rio_map_inb_region -- Map inbound memory region. * @mport: Master port. - * @lstart: physical address of memory region to be mapped + * @local: physical address of memory region to be mapped * @rbase: RIO base address assigned to this window * @size: Size of the memory region * @rflags: Flags for mapping. diff --git a/include/linux/rio.h b/include/linux/rio.h index 4187da511006..a3e784278667 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -275,9 +275,11 @@ struct rio_id_table { * struct rio_net - RIO network info * @node: Node in global list of RIO networks * @devices: List of devices in this network + * @switches: List of switches in this netowrk * @mports: List of master ports accessing this network * @hport: Default port for accessing this network * @id: RIO network ID + * @destid_table: destID allocation table */ struct rio_net { struct list_head node; /* node in list of networks */ -- cgit v1.2.3 From 5576646f3c1abd60d72d19829de6f5d8c2ca8ecf Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 16 Nov 2012 14:15:06 -0800 Subject: revert "mm: fix-up zone present pages" Revert commit 7f1290f2f2a4 ("mm: fix-up zone present pages") That patch tried to fix a issue when calculating zone->present_pages, but it caused a regression on 32bit systems with HIGHMEM. With that change, reset_zone_present_pages() resets all zone->present_pages to zero, and fixup_zone_present_pages() is called to recalculate zone->present_pages when the boot allocator frees core memory pages into buddy allocator. Because highmem pages are not freed by bootmem allocator, all highmem zones' present_pages becomes zero. Various options for improving the situation are being discussed but for now, let's return to the 3.6 code. Cc: Jianguo Wu Cc: Jiang Liu Cc: Petr Tesarik Cc: "Luck, Tony" Cc: Mel Gorman Cc: Yinghai Lu Cc: Minchan Kim Cc: Johannes Weiner Acked-by: David Rientjes Tested-by: Chris Clayton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 1 - include/linux/mm.h | 4 ---- mm/bootmem.c | 10 +--------- mm/memory_hotplug.c | 7 ------- mm/nobootmem.c | 3 --- mm/page_alloc.c | 34 ---------------------------------- 6 files changed, 1 insertion(+), 58 deletions(-) (limited to 'include') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index acd5b68e8871..082e383c1b6f 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -637,7 +637,6 @@ mem_init (void) high_memory = __va(max_low_pfn * PAGE_SIZE); - reset_zone_present_pages(); for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) totalram_pages += free_all_bootmem_node(pgdat); diff --git a/include/linux/mm.h b/include/linux/mm.h index fa0680402738..bcaab4e6fe91 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1684,9 +1684,5 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool page_is_guard(struct page *page) { return false; } #endif /* CONFIG_DEBUG_PAGEALLOC */ -extern void reset_zone_present_pages(void); -extern void fixup_zone_present_pages(int nid, unsigned long start_pfn, - unsigned long end_pfn); - #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/bootmem.c b/mm/bootmem.c index 434be4ae7a04..f468185b3b28 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -198,8 +198,6 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) int order = ilog2(BITS_PER_LONG); __free_pages_bootmem(pfn_to_page(start), order); - fixup_zone_present_pages(page_to_nid(pfn_to_page(start)), - start, start + BITS_PER_LONG); count += BITS_PER_LONG; start += BITS_PER_LONG; } else { @@ -210,9 +208,6 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) if (vec & 1) { page = pfn_to_page(start + off); __free_pages_bootmem(page, 0); - fixup_zone_present_pages( - page_to_nid(page), - start + off, start + off + 1); count++; } vec >>= 1; @@ -226,11 +221,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) pages = bdata->node_low_pfn - bdata->node_min_pfn; pages = bootmem_bootmap_pages(pages); count += pages; - while (pages--) { - fixup_zone_present_pages(page_to_nid(page), - page_to_pfn(page), page_to_pfn(page) + 1); + while (pages--) __free_pages_bootmem(page++, 0); - } bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 56b758ae57d2..e4eeacae2b91 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -106,7 +106,6 @@ static void get_page_bootmem(unsigned long info, struct page *page, void __ref put_page_bootmem(struct page *page) { unsigned long type; - struct zone *zone; type = (unsigned long) page->lru.next; BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || @@ -117,12 +116,6 @@ void __ref put_page_bootmem(struct page *page) set_page_private(page, 0); INIT_LIST_HEAD(&page->lru); __free_pages_bootmem(page, 0); - - zone = page_zone(page); - zone_span_writelock(zone); - zone->present_pages++; - zone_span_writeunlock(zone); - totalram_pages++; } } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 714d5d650470..bd82f6b31411 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -116,8 +116,6 @@ static unsigned long __init __free_memory_core(phys_addr_t start, return 0; __free_pages_memory(start_pfn, end_pfn); - fixup_zone_present_pages(pfn_to_nid(start >> PAGE_SHIFT), - start_pfn, end_pfn); return end_pfn - start_pfn; } @@ -128,7 +126,6 @@ unsigned long __init free_low_memory_core_early(int nodeid) phys_addr_t start, end, size; u64 i; - reset_zone_present_pages(); for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) count += __free_memory_core(start, end); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c91598b1b4c0..7bb35ac0964a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6098,37 +6098,3 @@ void dump_page(struct page *page) dump_page_flags(page->flags); mem_cgroup_print_bad_page(page); } - -/* reset zone->present_pages */ -void reset_zone_present_pages(void) -{ - struct zone *z; - int i, nid; - - for_each_node_state(nid, N_HIGH_MEMORY) { - for (i = 0; i < MAX_NR_ZONES; i++) { - z = NODE_DATA(nid)->node_zones + i; - z->present_pages = 0; - } - } -} - -/* calculate zone's present pages in buddy system */ -void fixup_zone_present_pages(int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - struct zone *z; - unsigned long zone_start_pfn, zone_end_pfn; - int i; - - for (i = 0; i < MAX_NR_ZONES; i++) { - z = NODE_DATA(nid)->node_zones + i; - zone_start_pfn = z->zone_start_pfn; - zone_end_pfn = zone_start_pfn + z->spanned_pages; - - /* if the two regions intersect */ - if (!(zone_start_pfn >= end_pfn || zone_end_pfn <= start_pfn)) - z->present_pages += min(end_pfn, zone_end_pfn) - - max(start_pfn, zone_start_pfn); - } -} -- cgit v1.2.3 From c4f4925439f13a243aecfb36c693613603c0bfbd Mon Sep 17 00:00:00 2001 From: Igor Grinberg Date: Tue, 20 Nov 2012 23:00:10 -0800 Subject: Input: ads7846 - enable pendown GPIO debounce time setting Some platforms need the pendown GPIO debounce time setting programmed. Since the pendown GPIO is handled by the driver, the debounce time should also be handled along with the pendown GPIO request. Signed-off-by: Igor Grinberg Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/ads7846.c | 6 +++++- include/linux/spi/ads7846.h | 5 +++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index f02028ec3db6..78e5d9ab0ba7 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -955,7 +955,8 @@ static int ads7846_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(ads7846_pm, ads7846_suspend, ads7846_resume); -static int __devinit ads7846_setup_pendown(struct spi_device *spi, struct ads7846 *ts) +static int __devinit ads7846_setup_pendown(struct spi_device *spi, + struct ads7846 *ts) { struct ads7846_platform_data *pdata = spi->dev.platform_data; int err; @@ -981,6 +982,9 @@ static int __devinit ads7846_setup_pendown(struct spi_device *spi, struct ads784 ts->gpio_pendown = pdata->gpio_pendown; + if (pdata->gpio_pendown_debounce) + gpio_set_debounce(pdata->gpio_pendown, + pdata->gpio_pendown_debounce); } else { dev_err(&spi->dev, "no get_pendown_state nor gpio_pendown?\n"); return -EINVAL; diff --git a/include/linux/spi/ads7846.h b/include/linux/spi/ads7846.h index c64de9dd7631..2f694f3846a9 100644 --- a/include/linux/spi/ads7846.h +++ b/include/linux/spi/ads7846.h @@ -46,8 +46,9 @@ struct ads7846_platform_data { u16 debounce_rep; /* additional consecutive good readings * required after the first two */ int gpio_pendown; /* the GPIO used to decide the pendown - * state if get_pendown_state == NULL - */ + * state if get_pendown_state == NULL */ + int gpio_pendown_debounce; /* platform specific debounce time for + * the gpio_pendown */ int (*get_pendown_state)(void); int (*filter_init) (const struct ads7846_platform_data *pdata, void **filter_data); -- cgit v1.2.3 From 0181bd5dea2ed0696f84591a92da0b6a1f1a2e62 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 21 Nov 2012 18:37:38 -0500 Subject: drm/radeon: add new SI pci id Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- include/drm/drm_pciids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index af1cbaf535ed..c5c35e629426 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -210,6 +210,7 @@ {0x1002, 0x6798, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6799, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ {0x1002, 0x679A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x679B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ {0x1002, 0x679E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ {0x1002, 0x679F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6800, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ -- cgit v1.2.3 From 0e622d39197f0b64b9e043fe75ac3634bf9f3a05 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Fri, 23 Nov 2012 12:24:09 +0100 Subject: of/address: sparc: Declare of_iomap as an extern function for sparc again This bug-fix makes sure that of_iomap is defined extern for sparc so that the sparc-specific implementation of_iomap is once again used when including include/linux/of_address.h in a sparc context. OF_GPIO that is now available for sparc relies on this. The bug was inadvertently introduced in a850a75, "of/address: add empty static inlines for !CONFIG_OF", that added a static dummy inline for of_iomap when !CONFIG_OF_ADDRESS. However, CONFIG_OF_ADDRESS is never defined for sparc, but there is a sparc-specific implementation /arch/sparc/kernel/of_device_common.c. This fix takes the same approach as 0bce04b that solved the equivalent problem for of_address_to_resource. Signed-off-by: Andreas Larsson Acked-by: David Miller Signed-off-by: Grant Likely --- arch/sparc/include/asm/prom.h | 5 ++++- include/linux/of_address.h | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h index f93003123bce..67c62578d170 100644 --- a/arch/sparc/include/asm/prom.h +++ b/arch/sparc/include/asm/prom.h @@ -63,10 +63,13 @@ extern char *of_console_options; extern void irq_trans_init(struct device_node *dp); extern char *build_path_component(struct device_node *dp); -/* SPARC has a local implementation */ +/* SPARC has local implementations */ extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); #define of_address_to_resource of_address_to_resource +void __iomem *of_iomap(struct device_node *node, int index); +#define of_iomap of_iomap + #endif /* __KERNEL__ */ #endif /* _SPARC_PROM_H */ diff --git a/include/linux/of_address.h b/include/linux/of_address.h index e20e3af68fb6..0506eb53519b 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -42,10 +42,12 @@ static inline struct device_node *of_find_matching_node_by_address( { return NULL; } +#ifndef of_iomap static inline void __iomem *of_iomap(struct device_node *device, int index) { return NULL; } +#endif static inline const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { -- cgit v1.2.3