From 7d50207163414d38e6a706904bd915db145fb8a0 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 15 Nov 2017 17:32:37 -0800 Subject: drivers/infiniband/hw/qib/qib_init.c: use kmalloc_array_node() Now that we have a NUMA-aware version of kmalloc_array() we can use it instead of kmalloc_node() without an overflow check in the size calculation. Link: http://lkml.kernel.org/r/20170927082038.3782-4-jthumshirn@suse.de Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Lameter Cc: Mike Marciniszyn Cc: Doug Ledford Cc: Sean Hefty Cc: Hal Rosenstock Cc: Christoph Hellwig Cc: Damien Le Moal Cc: David Rientjes Cc: "David S. Miller" Cc: Jens Axboe Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Santosh Shilimkar Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/hw/qib/qib_init.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index c5a4c65636d6..6aebf4e707b9 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -1674,8 +1674,9 @@ int qib_setup_eagerbufs(struct qib_ctxtdata *rcd) } if (!rcd->rcvegrbuf_phys) { rcd->rcvegrbuf_phys = - kmalloc_node(chunk * sizeof(rcd->rcvegrbuf_phys[0]), - GFP_KERNEL, rcd->node_id); + kmalloc_array_node(chunk, + sizeof(rcd->rcvegrbuf_phys[0]), + GFP_KERNEL, rcd->node_id); if (!rcd->rcvegrbuf_phys) goto bail_rcvegrbuf; } -- cgit v1.2.3 From 3c073478414db89ec963631f2aa46c94d4bb33da Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 15 Nov 2017 17:32:41 -0800 Subject: drivers/infiniband/sw/rdmavt/qp.c: use kmalloc_array_node() Now that we have a NUMA-aware version of kmalloc_array() we can use it instead of kmalloc_node() without an overflow check in the size calculation. Link: http://lkml.kernel.org/r/20170927082038.3782-5-jthumshirn@suse.de Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Lameter Cc: Christoph Hellwig Cc: Damien Le Moal Cc: David Rientjes Cc: "David S. Miller" Cc: Doug Ledford Cc: Hal Rosenstock Cc: Jens Axboe Cc: Joonsoo Kim Cc: Mike Marciniszyn Cc: Pekka Enberg Cc: Santosh Shilimkar Cc: Sean Hefty Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/sw/rdmavt/qp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index b670cb9d2006..27a1ad79d654 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -238,7 +238,7 @@ int rvt_driver_qp_init(struct rvt_dev_info *rdi) rdi->qp_dev->qp_table_size = rdi->dparms.qp_table_size; rdi->qp_dev->qp_table_bits = ilog2(rdi->dparms.qp_table_size); rdi->qp_dev->qp_table = - kmalloc_node(rdi->qp_dev->qp_table_size * + kmalloc_array_node(rdi->qp_dev->qp_table_size, sizeof(*rdi->qp_dev->qp_table), GFP_KERNEL, rdi->dparms.node); if (!rdi->qp_dev->qp_table) -- cgit v1.2.3 From e447a0151f7ce8dd884fea48279274bd64434c29 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Wed, 15 Nov 2017 17:32:56 -0800 Subject: zram: set BDI_CAP_STABLE_WRITES once With fast swap storage, the platform wants to use swap more aggressively and swap-in is crucial to application latency. The rw_page() based synchronous devices like zram, pmem and btt are such fast storage. When I profile swapin performance with zram lz4 decompress test, S/W overhead is more than 70%. Maybe, it would be bigger in nvdimm. This patchset reduces swap-in latency by skipping swapcache if the swap device is a synchronous device like a rw_page() based device. It enhances by 45% my swapin test (5G sequential swapin, no readahead) from 2.41sec to 1.64sec. This patch (of 4): Commit 19b7ccf8651d ("block: get rid of blk_integrity_revalidate()") fixed a weird thing (i.e., reset BDI_CAP_STABLE_WRITES flag unconditionally whenever revalidat_disk is called) so zram doesn't need to reset the flag any more when revalidating the bdev. Instead, set the flag just once when the zram device is created. It shouldn't change any behavior. Link: http://lkml.kernel.org/r/1505886205-9671-2-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Ilya Dryomov Cc: Christoph Hellwig Cc: Dan Williams Cc: Ross Zwisler Cc: Jens Axboe Cc: Hugh Dickins Cc: Huang Ying Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'drivers') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f149d3e61234..d95bb8ce5092 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -122,14 +122,6 @@ static inline bool is_partial_io(struct bio_vec *bvec) } #endif -static void zram_revalidate_disk(struct zram *zram) -{ - revalidate_disk(zram->disk); - /* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */ - zram->disk->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; -} - /* * Check if request is within bounds and aligned on zram logical blocks. */ @@ -1373,7 +1365,8 @@ static ssize_t disksize_store(struct device *dev, zram->comp = comp; zram->disksize = disksize; set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); - zram_revalidate_disk(zram); + + revalidate_disk(zram->disk); up_write(&zram->init_lock); return len; @@ -1420,7 +1413,7 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - zram_revalidate_disk(zram); + revalidate_disk(zram->disk); bdput(bdev); mutex_lock(&bdev->bd_mutex); @@ -1539,6 +1532,7 @@ static int zram_add(void) /* zram devices sort of resembles non-rotational disks */ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue); + /* * To ensure that we always get PAGE_SIZE aligned * and n*PAGE_SIZED sized I/O requests. @@ -1563,6 +1557,8 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); + zram->disk->queue->backing_dev_info->capabilities |= + BDI_CAP_STABLE_WRITES; add_disk(zram->disk); ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj, -- cgit v1.2.3 From 23c47d2ada9f96731492a67b28c0072715075baa Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Wed, 15 Nov 2017 17:33:00 -0800 Subject: bdi: introduce BDI_CAP_SYNCHRONOUS_IO As discussed at https://lkml.kernel.org/r/<20170728165604.10455-1-ross.zwisler@linux.intel.com> someday we will remove rw_page(). If so, we need something to detect such super-fast storage on which synchronous IO operations like the current rw_page are always a win. Introduces BDI_CAP_SYNCHRONOUS_IO to indicate such devices. With it, we could use various optimization techniques. Link: http://lkml.kernel.org/r/1505886205-9671-3-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim Cc: Christoph Hellwig Cc: Dan Williams Cc: Ross Zwisler Cc: Hugh Dickins Cc: Ilya Dryomov Cc: Jens Axboe Cc: Sergey Senozhatsky Cc: Huang Ying Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/brd.c | 2 ++ drivers/block/zram/zram_drv.c | 2 +- drivers/nvdimm/btt.c | 3 +++ drivers/nvdimm/pmem.c | 2 ++ 4 files changed, 8 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/block/brd.c b/drivers/block/brd.c index c1cf87718c2e..588360d79fca 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_BLK_DEV_RAM_DAX #include #include @@ -448,6 +449,7 @@ static struct brd_device *brd_alloc(int i) disk->flags = GENHD_FL_EXT_DEVT; sprintf(disk->disk_name, "ram%d", i); set_capacity(disk, rd_size * 2); + disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; #ifdef CONFIG_BLK_DEV_RAM_DAX queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d95bb8ce5092..88564222f473 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1558,7 +1558,7 @@ static int zram_add(void) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); zram->disk->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; + (BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO); add_disk(zram->disk); ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj, diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index d5612bd1cc81..e949e3302af4 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "btt.h" #include "nd.h" @@ -1402,6 +1403,8 @@ static int btt_blk_init(struct btt *btt) btt->btt_disk->private_data = btt; btt->btt_disk->queue = btt->btt_queue; btt->btt_disk->flags = GENHD_FL_EXT_DEVT; + btt->btt_disk->queue->backing_dev_info->capabilities |= + BDI_CAP_SYNCHRONOUS_IO; blk_queue_make_request(btt->btt_queue, btt_make_request); blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 39dfd7affa31..7fbc5c5dc8e1 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "pmem.h" #include "pfn.h" #include "nd.h" @@ -394,6 +395,7 @@ static int pmem_attach_disk(struct device *dev, disk->fops = &pmem_fops; disk->queue = q; disk->flags = GENHD_FL_EXT_DEVT; + disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) / 512); -- cgit v1.2.3 From 5ef3a8b12556d7fcba81edc74e9d85b029615ae0 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 15 Nov 2017 17:33:49 -0800 Subject: zram: add zstd to the supported algorithms list Add ZSTD to the list of supported compression algorithms. ZRAM fio perf test: LZO DEFLATE ZSTD #jobs1 WRITE: (2180MB/s) (77.2MB/s) (1429MB/s) WRITE: (1617MB/s) (77.7MB/s) (1202MB/s) READ: (426MB/s) (595MB/s) (1181MB/s) READ: (422MB/s) (572MB/s) (1020MB/s) READ: (318MB/s) (67.8MB/s) (563MB/s) WRITE: (318MB/s) (67.9MB/s) (564MB/s) READ: (336MB/s) (68.3MB/s) (583MB/s) WRITE: (335MB/s) (68.2MB/s) (582MB/s) #jobs2 WRITE: (3441MB/s) (152MB/s) (2141MB/s) WRITE: (2507MB/s) (147MB/s) (1888MB/s) READ: (801MB/s) (1146MB/s) (1890MB/s) READ: (767MB/s) (1096MB/s) (2073MB/s) READ: (621MB/s) (126MB/s) (1009MB/s) WRITE: (621MB/s) (126MB/s) (1009MB/s) READ: (656MB/s) (125MB/s) (1075MB/s) WRITE: (657MB/s) (126MB/s) (1077MB/s) #jobs3 WRITE: (4772MB/s) (225MB/s) (3394MB/s) WRITE: (3905MB/s) (211MB/s) (2939MB/s) READ: (1216MB/s) (1608MB/s) (3218MB/s) READ: (1159MB/s) (1431MB/s) (2981MB/s) READ: (906MB/s) (156MB/s) (1457MB/s) WRITE: (907MB/s) (156MB/s) (1458MB/s) READ: (953MB/s) (158MB/s) (1595MB/s) WRITE: (952MB/s) (157MB/s) (1593MB/s) #jobs4 WRITE: (6036MB/s) (265MB/s) (4469MB/s) WRITE: (5059MB/s) (263MB/s) (3951MB/s) READ: (1618MB/s) (2066MB/s) (4276MB/s) READ: (1573MB/s) (1942MB/s) (3830MB/s) READ: (1202MB/s) (227MB/s) (1971MB/s) WRITE: (1200MB/s) (227MB/s) (1968MB/s) READ: (1265MB/s) (226MB/s) (2116MB/s) WRITE: (1264MB/s) (226MB/s) (2114MB/s) #jobs5 WRITE: (5339MB/s) (233MB/s) (3781MB/s) WRITE: (4298MB/s) (234MB/s) (3276MB/s) READ: (1626MB/s) (2048MB/s) (4081MB/s) READ: (1567MB/s) (1929MB/s) (3758MB/s) READ: (1174MB/s) (205MB/s) (1747MB/s) WRITE: (1173MB/s) (204MB/s) (1746MB/s) READ: (1214MB/s) (208MB/s) (1890MB/s) WRITE: (1215MB/s) (208MB/s) (1892MB/s) #jobs6 WRITE: (5666MB/s) (270MB/s) (4338MB/s) WRITE: (4828MB/s) (267MB/s) (3772MB/s) READ: (1803MB/s) (2058MB/s) (4946MB/s) READ: (1805MB/s) (2156MB/s) (4711MB/s) READ: (1334MB/s) (235MB/s) (2135MB/s) WRITE: (1335MB/s) (235MB/s) (2137MB/s) READ: (1364MB/s) (236MB/s) (2268MB/s) WRITE: (1365MB/s) (237MB/s) (2270MB/s) #jobs7 WRITE: (5474MB/s) (270MB/s) (4300MB/s) WRITE: (4666MB/s) (266MB/s) (3817MB/s) READ: (2022MB/s) (2319MB/s) (5472MB/s) READ: (1924MB/s) (2260MB/s) (5031MB/s) READ: (1369MB/s) (242MB/s) (2153MB/s) WRITE: (1370MB/s) (242MB/s) (2155MB/s) READ: (1499MB/s) (246MB/s) (2310MB/s) WRITE: (1497MB/s) (246MB/s) (2307MB/s) #jobs8 WRITE: (5558MB/s) (273MB/s) (4439MB/s) WRITE: (4763MB/s) (271MB/s) (3918MB/s) READ: (2201MB/s) (2599MB/s) (6062MB/s) READ: (2105MB/s) (2463MB/s) (5413MB/s) READ: (1490MB/s) (252MB/s) (2238MB/s) WRITE: (1488MB/s) (252MB/s) (2236MB/s) READ: (1566MB/s) (254MB/s) (2434MB/s) WRITE: (1568MB/s) (254MB/s) (2437MB/s) #jobs9 WRITE: (5120MB/s) (264MB/s) (4035MB/s) WRITE: (4531MB/s) (267MB/s) (3740MB/s) READ: (1940MB/s) (2258MB/s) (4986MB/s) READ: (2024MB/s) (2387MB/s) (4871MB/s) READ: (1343MB/s) (246MB/s) (2038MB/s) WRITE: (1342MB/s) (246MB/s) (2037MB/s) READ: (1553MB/s) (238MB/s) (2243MB/s) WRITE: (1552MB/s) (238MB/s) (2242MB/s) #jobs10 WRITE: (5345MB/s) (271MB/s) (3988MB/s) WRITE: (4750MB/s) (254MB/s) (3668MB/s) READ: (1876MB/s) (2363MB/s) (5150MB/s) READ: (1990MB/s) (2256MB/s) (5080MB/s) READ: (1355MB/s) (250MB/s) (2019MB/s) WRITE: (1356MB/s) (251MB/s) (2020MB/s) READ: (1490MB/s) (252MB/s) (2202MB/s) WRITE: (1488MB/s) (252MB/s) (2199MB/s) jobs1 perfstat instructions 52,065,555,710 ( 0.79) 855,731,114,587 ( 2.64) 54,280,709,944 ( 1.40) branches 14,020,427,116 ( 725.847) 101,733,449,582 (1074.521) 11,170,591,067 ( 992.869) branch-misses 22,626,174 ( 0.16%) 274,197,885 ( 0.27%) 25,915,805 ( 0.23%) jobs2 perfstat instructions 103,633,110,402 ( 0.75) 1,710,822,100,914 ( 2.59) 107,879,874,104 ( 1.28) branches 27,931,237,282 ( 679.203) 203,298,267,479 (1037.326) 22,185,350,842 ( 884.427) branch-misses 46,103,811 ( 0.17%) 533,747,204 ( 0.26%) 49,682,483 ( 0.22%) jobs3 perfstat instructions 154,857,283,657 ( 0.76) 2,565,748,974,197 ( 2.57) 161,515,435,813 ( 1.31) branches 41,759,490,355 ( 670.529) 304,905,605,277 ( 978.765) 33,215,805,907 ( 888.003) branch-misses 74,263,293 ( 0.18%) 759,746,240 ( 0.25%) 76,841,196 ( 0.23%) jobs4 perfstat instructions 206,215,849,076 ( 0.75) 3,420,169,460,897 ( 2.60) 215,003,061,664 ( 1.31) branches 55,632,141,739 ( 666.501) 406,394,977,433 ( 927.241) 44,214,322,251 ( 883.532) branch-misses 102,287,788 ( 0.18%) 1,098,617,314 ( 0.27%) 103,891,040 ( 0.23%) jobs5 perfstat instructions 258,711,315,588 ( 0.67) 4,275,657,533,244 ( 2.23) 269,332,235,685 ( 1.08) branches 69,802,821,166 ( 588.823) 507,996,211,252 ( 797.036) 55,450,846,129 ( 735.095) branch-misses 129,217,214 ( 0.19%) 1,243,284,991 ( 0.24%) 173,512,278 ( 0.31%) jobs6 perfstat instructions 312,796,166,008 ( 0.61) 5,133,896,344,660 ( 2.02) 323,658,769,588 ( 1.04) branches 84,372,488,583 ( 520.541) 610,310,494,402 ( 697.642) 66,683,292,992 ( 693.939) branch-misses 159,438,978 ( 0.19%) 1,396,368,563 ( 0.23%) 174,406,934 ( 0.26%) jobs7 perfstat instructions 363,211,372,930 ( 0.56) 5,988,205,600,879 ( 1.75) 377,824,674,156 ( 0.93) branches 98,057,013,765 ( 463.117) 711,841,255,974 ( 598.762) 77,879,009,954 ( 600.443) branch-misses 199,513,153 ( 0.20%) 1,507,651,077 ( 0.21%) 248,203,369 ( 0.32%) jobs8 perfstat instructions 413,960,354,615 ( 0.52) 6,842,918,558,378 ( 1.45) 431,938,486,581 ( 0.83) branches 111,812,574,884 ( 414.224) 813,299,084,518 ( 491.173) 89,062,699,827 ( 517.795) branch-misses 233,584,845 ( 0.21%) 1,531,593,921 ( 0.19%) 286,818,489 ( 0.32%) jobs9 perfstat instructions 465,976,220,300 ( 0.53) 7,698,467,237,372 ( 1.47) 486,352,600,321 ( 0.84) branches 125,931,456,162 ( 424.063) 915,207,005,715 ( 498.192) 100,370,404,090 ( 517.439) branch-misses 256,992,445 ( 0.20%) 1,782,809,816 ( 0.19%) 345,239,380 ( 0.34%) jobs10 perfstat instructions 517,406,372,715 ( 0.53) 8,553,527,312,900 ( 1.48) 540,732,653,094 ( 0.84) branches 139,839,780,676 ( 427.732) 1,016,737,699,389 ( 503.172) 111,696,557,638 ( 516.750) branch-misses 259,595,561 ( 0.19%) 1,952,570,279 ( 0.19%) 357,818,661 ( 0.32%) seconds elapsed 20.630411534 96.084546565 12.743373571 seconds elapsed 22.292627625 100.984155001 14.407413560 seconds elapsed 22.396016966 110.344880848 14.032201392 seconds elapsed 22.517330949 113.351459170 14.243074935 seconds elapsed 28.548305104 156.515193765 19.159286861 seconds elapsed 30.453538116 164.559937678 19.362492717 seconds elapsed 33.467108086 188.486827481 21.492612173 seconds elapsed 35.617727591 209.602677783 23.256422492 seconds elapsed 42.584239509 243.959902566 28.458540338 seconds elapsed 47.683632526 269.635248851 31.542404137 Over all, ZSTD has slower WRITE, but much faster READ (perhaps a static compression buffer used during the test helped ZSTD a lot), which results in faster test results. Memory consumption (zram mm_stat file): zram LZO mm_stat mm_stat (jobs1): 2147483648 23068672 33558528 0 33558528 0 0 mm_stat (jobs2): 2147483648 23068672 33558528 0 33558528 0 0 mm_stat (jobs3): 2147483648 23068672 33558528 0 33562624 0 0 mm_stat (jobs4): 2147483648 23068672 33558528 0 33558528 0 0 mm_stat (jobs5): 2147483648 23068672 33558528 0 33558528 0 0 mm_stat (jobs6): 2147483648 23068672 33558528 0 33562624 0 0 mm_stat (jobs7): 2147483648 23068672 33558528 0 33566720 0 0 mm_stat (jobs8): 2147483648 23068672 33558528 0 33558528 0 0 mm_stat (jobs9): 2147483648 23068672 33558528 0 33558528 0 0 mm_stat (jobs10): 2147483648 23068672 33558528 0 33562624 0 0 zram DEFLATE mm_stat mm_stat (jobs1): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs2): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs3): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs4): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs5): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs6): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs7): 2147483648 16252928 25178112 0 25190400 0 0 mm_stat (jobs8): 2147483648 16252928 25178112 0 25190400 0 0 mm_stat (jobs9): 2147483648 16252928 25178112 0 25178112 0 0 mm_stat (jobs10): 2147483648 16252928 25178112 0 25178112 0 0 zram ZSTD mm_stat mm_stat (jobs1): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs2): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs3): 2147483648 11010048 16781312 0 16785408 0 0 mm_stat (jobs4): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs5): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs6): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs7): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs8): 2147483648 11010048 16781312 0 16781312 0 0 mm_stat (jobs9): 2147483648 11010048 16781312 0 16785408 0 0 mm_stat (jobs10): 2147483648 11010048 16781312 0 16781312 0 0 ================================================================================== Official benchmarks [1]: Compressor name Ratio Compression Decompress. zstd 1.1.3 -1 2.877 430 MB/s 1110 MB/s zlib 1.2.8 -1 2.743 110 MB/s 400 MB/s brotli 0.5.2 -0 2.708 400 MB/s 430 MB/s quicklz 1.5.0 -1 2.238 550 MB/s 710 MB/s lzo1x 2.09 -1 2.108 650 MB/s 830 MB/s lz4 1.7.5 2.101 720 MB/s 3600 MB/s snappy 1.1.3 2.091 500 MB/s 1650 MB/s lzf 3.6 -1 2.077 400 MB/s 860 MB/s Minchan said: : I did test with my sample data and compared zstd with deflate. zstd's : compress ratio is lower a little bit but compression speed is much faster : 3 times more and decompress speed is too 2 times more. With different : data, it is different but overall, zstd would be better for speed at the : cost of a little lower compress ratio(about 5%) so I believe it's worth to : replace deflate. [1] https://github.com/facebook/zstd Link: http://lkml.kernel.org/r/20170912050005.3247-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Tested-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zcomp.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers') diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 5b8992beffec..cc66daec7bbc 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -31,6 +31,9 @@ static const char * const backends[] = { #endif #if IS_ENABLED(CONFIG_CRYPTO_842) "842", +#endif +#if IS_ENABLED(CONFIG_CRYPTO_ZSTD) + "zstd", #endif NULL }; -- cgit v1.2.3 From 0b07ff3972061a5e06e168378dd578801ae3e88e Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 15 Nov 2017 17:33:53 -0800 Subject: zram: remove zlib from the list of recommended algorithms ZSTD tends to outperform deflate/inflate, thus we remove zlib from the list of recommended algorithms and recommend zstd instead. Link: http://lkml.kernel.org/r/20170912050005.3247-2-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky Suggested-by: Minchan Kim Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zcomp.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'drivers') diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index cc66daec7bbc..4ed0a78fdc09 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -23,9 +23,6 @@ static const char * const backends[] = { #if IS_ENABLED(CONFIG_CRYPTO_LZ4) "lz4", #endif -#if IS_ENABLED(CONFIG_CRYPTO_DEFLATE) - "deflate", -#endif #if IS_ENABLED(CONFIG_CRYPTO_LZ4HC) "lz4hc", #endif -- cgit v1.2.3 From 4950276672fce5c241857540f8561c440663673d Mon Sep 17 00:00:00 2001 From: "Levin, Alexander (Sasha Levin)" Date: Wed, 15 Nov 2017 17:35:51 -0800 Subject: kmemcheck: remove annotations Patch series "kmemcheck: kill kmemcheck", v2. As discussed at LSF/MM, kill kmemcheck. KASan is a replacement that is able to work without the limitation of kmemcheck (single CPU, slow). KASan is already upstream. We are also not aware of any users of kmemcheck (or users who don't consider KASan as a suitable replacement). The only objection was that since KASAN wasn't supported by all GCC versions provided by distros at that time we should hold off for 2 years, and try again. Now that 2 years have passed, and all distros provide gcc that supports KASAN, kill kmemcheck again for the very same reasons. This patch (of 4): Remove kmemcheck annotations, and calls to kmemcheck from the kernel. [alexander.levin@verizon.com: correctly remove kmemcheck call from dma_map_sg_attrs] Link: http://lkml.kernel.org/r/20171012192151.26531-1-alexander.levin@verizon.com Link: http://lkml.kernel.org/r/20171007030159.22241-2-alexander.levin@verizon.com Signed-off-by: Sasha Levin Cc: Alexander Potapenko Cc: Eric W. Biederman Cc: Michal Hocko Cc: Pekka Enberg Cc: Steven Rostedt Cc: Tim Hansen Cc: Vegard Nossum Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/random.c | 1 - drivers/misc/c2port/core.c | 2 -- 2 files changed, 3 deletions(-) (limited to 'drivers') diff --git a/drivers/char/random.c b/drivers/char/random.c index 6c7ccac2679e..ec42c8bb9b0d 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -259,7 +259,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/misc/c2port/core.c b/drivers/misc/c2port/core.c index 1922cb8f6b88..1c5b7aec13d4 100644 --- a/drivers/misc/c2port/core.c +++ b/drivers/misc/c2port/core.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -904,7 +903,6 @@ struct c2port_device *c2port_device_register(char *name, return ERR_PTR(-EINVAL); c2dev = kmalloc(sizeof(struct c2port_device), GFP_KERNEL); - kmemcheck_annotate_bitfield(c2dev, flags); if (unlikely(!c2dev)) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From 384bc41fc064bd8b12b7081aa3e81d26f3407045 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 15 Nov 2017 17:37:08 -0800 Subject: drivers/block/zram/zram_drv.c: make zram_page_end_io() static zram_page_end_io() is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warning: symbol 'zram_page_end_io' was not declared. Should it be static? Link: http://lkml.kernel.org/r/20171016173336.20320-1-colin.king@canonical.com Signed-off-by: Colin Ian King Reviewed-by: Sergey Senozhatsky Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 88564222f473..d70eba30003a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -428,7 +428,7 @@ static void put_entry_bdev(struct zram *zram, unsigned long entry) WARN_ON_ONCE(!was_set); } -void zram_page_end_io(struct bio *bio) +static void zram_page_end_io(struct bio *bio) { struct page *page = bio->bi_io_vec[0].bv_page; -- cgit v1.2.3 From 8667982014d6048e0b5e286b6247ff24f48d4cc6 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 15 Nov 2017 17:37:52 -0800 Subject: mm, pagevec: remove cold parameter for pagevecs Every pagevec_init user claims the pages being released are hot even in cases where it is unlikely the pages are hot. As no one cares about the hotness of pages being released to the allocator, just ditch the parameter. No performance impact is expected as the overhead is marginal. The parameter is removed simply because it is a bit stupid to have a useless parameter copied everywhere. Link: http://lkml.kernel.org/r/20171018075952.10627-6-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andi Kleen Cc: Dave Chinner Cc: Dave Hansen Cc: Jan Kara Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index ad524cb0f6fc..7982ad817c11 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1859,7 +1859,7 @@ static void i915_address_space_init(struct i915_address_space *vm, INIT_LIST_HEAD(&vm->unbound_list); list_add_tail(&vm->global_link, &dev_priv->vm_list); - pagevec_init(&vm->free_pages, false); + pagevec_init(&vm->free_pages); } static void i915_address_space_fini(struct i915_address_space *vm) -- cgit v1.2.3 From c6f92f9fbe7dbcc8903a67229aa88b4077ae4422 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 15 Nov 2017 17:37:55 -0800 Subject: mm: remove cold parameter for release_pages All callers of release_pages claim the pages being released are cache hot. As no one cares about the hotness of pages being released to the allocator, just ditch the parameter. No performance impact is expected as the overhead is marginal. The parameter is removed simply because it is a bit stupid to have a useless parameter copied everywhere. Link: http://lkml.kernel.org/r/20171018075952.10627-7-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andi Kleen Cc: Dave Chinner Cc: Dave Hansen Cc: Jan Kara Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 ++---- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 6 +++--- drivers/gpu/drm/i915/i915_gem_userptr.c | 4 ++-- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- 6 files changed, 10 insertions(+), 12 deletions(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 60d8bedb694d..cd664832f9e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -553,8 +553,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, * invalidated it. Free it and try again */ release_pages(e->user_pages, - e->robj->tbo.ttm->num_pages, - false); + e->robj->tbo.ttm->num_pages); kvfree(e->user_pages); e->user_pages = NULL; } @@ -691,8 +690,7 @@ error_free_pages: continue; release_pages(e->user_pages, - e->robj->tbo.ttm->num_pages, - false); + e->robj->tbo.ttm->num_pages); kvfree(e->user_pages); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 6149a47fe63d..0bda8f2a188a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -347,7 +347,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, return 0; free_pages: - release_pages(bo->tbo.ttm->pages, bo->tbo.ttm->num_pages, false); + release_pages(bo->tbo.ttm->pages, bo->tbo.ttm->num_pages); unlock_mmap_sem: up_read(¤t->mm->mmap_sem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index bc746131987f..d792959fac43 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -659,7 +659,7 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages) return 0; release_pages: - release_pages(pages, pinned, 0); + release_pages(pages, pinned); return r; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 57881167ccd2..bcc8c2d7c7c9 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -779,7 +779,7 @@ static struct page **etnaviv_gem_userptr_do_get_pages( up_read(&mm->mmap_sem); if (ret < 0) { - release_pages(pvec, pinned, 0); + release_pages(pvec, pinned); kvfree(pvec); return ERR_PTR(ret); } @@ -852,7 +852,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) } } - release_pages(pvec, pinned, 0); + release_pages(pvec, pinned); kvfree(pvec); work = kmalloc(sizeof(*work), GFP_KERNEL); @@ -886,7 +886,7 @@ static void etnaviv_gem_userptr_release(struct etnaviv_gem_object *etnaviv_obj) if (etnaviv_obj->pages) { int npages = etnaviv_obj->base.size >> PAGE_SHIFT; - release_pages(etnaviv_obj->pages, npages, 0); + release_pages(etnaviv_obj->pages, npages); kvfree(etnaviv_obj->pages); } put_task_struct(etnaviv_obj->userptr.task); diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 709efe2357ea..aa22361bd5a1 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -554,7 +554,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) } mutex_unlock(&obj->mm.lock); - release_pages(pvec, pinned, 0); + release_pages(pvec, pinned); kvfree(pvec); i915_gem_object_put(obj); @@ -668,7 +668,7 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) __i915_gem_userptr_set_active(obj, true); if (IS_ERR(pages)) - release_pages(pvec, pinned, 0); + release_pages(pvec, pinned); kvfree(pvec); return pages; diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index bf69bf9086bf..1fdfc7a46072 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -597,7 +597,7 @@ release_sg: kfree(ttm->sg); release_pages: - release_pages(ttm->pages, pinned, 0); + release_pages(ttm->pages, pinned); return r; } -- cgit v1.2.3 From 453f85d43fa9ee243f0fc3ac4e1be45615301e3f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 15 Nov 2017 17:38:03 -0800 Subject: mm: remove __GFP_COLD As the page free path makes no distinction between cache hot and cold pages, there is no real useful ordering of pages in the free list that allocation requests can take advantage of. Juding from the users of __GFP_COLD, it is likely that a number of them are the result of copying other sites instead of actually measuring the impact. Remove the __GFP_COLD parameter which simplifies a number of paths in the page allocator. This is potentially controversial but bear in mind that the size of the per-cpu pagelists versus modern cache sizes means that the whole per-cpu list can often fit in the L3 cache. Hence, there is only a potential benefit for microbenchmarks that alloc/free pages in a tight loop. It's even worse when THP is taken into account which has little or no chance of getting a cache-hot page as the per-cpu list is bypassed and the zeroing of multiple pages will thrash the cache anyway. The truncate microbenchmarks are not shown as this patch affects the allocation path and not the free path. A page fault microbenchmark was tested but it showed no sigificant difference which is not surprising given that the __GFP_COLD branches are a miniscule percentage of the fault path. Link: http://lkml.kernel.org/r/20171018075952.10627-9-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andi Kleen Cc: Dave Chinner Cc: Dave Hansen Cc: Jan Kara Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe-desc.c | 2 +- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 +-- drivers/net/ethernet/cavium/liquidio/octeon_network.h | 2 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 5 ++--- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 ++-- drivers/net/ethernet/qlogic/qlge/qlge_main.c | 3 +-- drivers/net/ethernet/sfc/falcon/rx.c | 2 +- drivers/net/ethernet/sfc/rx.c | 2 +- drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c | 2 +- drivers/net/ethernet/ti/netcp_core.c | 2 +- drivers/net/virtio_net.c | 1 - drivers/staging/lustre/lustre/mdc/mdc_request.c | 2 +- 13 files changed, 14 insertions(+), 18 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index c6bd5e24005d..fbbbd8b3eb45 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -517,7 +517,7 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) rc = ena_alloc_rx_page(rx_ring, rx_info, - __GFP_COLD | GFP_ATOMIC | __GFP_COMP); + GFP_ATOMIC | __GFP_COMP); if (unlikely(rc < 0)) { netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev, "failed to alloc buffer for rx queue %d\n", diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c index 45d92304068e..cc1e4f820e64 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c @@ -295,7 +295,7 @@ again: order = alloc_order; /* Try to obtain pages, decreasing order if necessary */ - gfp = GFP_ATOMIC | __GFP_COLD | __GFP_COMP | __GFP_NOWARN; + gfp = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN; while (order >= 0) { pages = alloc_pages_node(node, gfp, order); if (pages) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 0654e0c76bc2..519ca6534b85 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -304,8 +304,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self) buff->flags = 0U; buff->len = AQ_CFG_RX_FRAME_MAX; - buff->page = alloc_pages(GFP_ATOMIC | __GFP_COLD | - __GFP_COMP, pages_order); + buff->page = alloc_pages(GFP_ATOMIC | __GFP_COMP, pages_order); if (!buff->page) { err = -ENOMEM; goto err_exit; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index 9e36319cead6..57853eead4b5 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -195,7 +195,7 @@ static inline void struct sk_buff *skb; struct octeon_skb_page_info *skb_pg_info; - page = alloc_page(GFP_ATOMIC | __GFP_COLD); + page = alloc_page(GFP_ATOMIC); if (unlikely(!page)) return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b97a55c827eb..ffead38cf5da 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -193,7 +193,7 @@ static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv) if (mlx4_en_prepare_rx_desc(priv, ring, ring->actual_size, - GFP_KERNEL | __GFP_COLD)) { + GFP_KERNEL)) { if (ring->actual_size < MLX4_EN_MIN_RX_SIZE) { en_err(priv, "Failed to allocate enough rx buffers\n"); return -ENOMEM; @@ -552,8 +552,7 @@ static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv, do { if (mlx4_en_prepare_rx_desc(priv, ring, ring->prod & ring->size_mask, - GFP_ATOMIC | __GFP_COLD | - __GFP_MEMALLOC)) + GFP_ATOMIC | __GFP_MEMALLOC)) break; ring->prod++; } while (likely(--missing)); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index e118b5f23996..ffb12dc13a5a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1185,7 +1185,7 @@ static void *nfp_net_rx_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr) } else { struct page *page; - page = alloc_page(GFP_KERNEL | __GFP_COLD); + page = alloc_page(GFP_KERNEL); frag = page ? page_address(page) : NULL; } if (!frag) { @@ -1212,7 +1212,7 @@ static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr) } else { struct page *page; - page = alloc_page(GFP_ATOMIC | __GFP_COLD); + page = alloc_page(GFP_ATOMIC); frag = page ? page_address(page) : NULL; } if (!frag) { diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 29fea74bff2e..7b97a9969046 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -1092,8 +1092,7 @@ static int ql_get_next_chunk(struct ql_adapter *qdev, struct rx_ring *rx_ring, { if (!rx_ring->pg_chunk.page) { u64 map; - rx_ring->pg_chunk.page = alloc_pages(__GFP_COLD | __GFP_COMP | - GFP_ATOMIC, + rx_ring->pg_chunk.page = alloc_pages(__GFP_COMP | GFP_ATOMIC, qdev->lbq_buf_order); if (unlikely(!rx_ring->pg_chunk.page)) { netif_err(qdev, drv, qdev->ndev, diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c index 6a8406dc0c2b..91097aea6c41 100644 --- a/drivers/net/ethernet/sfc/falcon/rx.c +++ b/drivers/net/ethernet/sfc/falcon/rx.c @@ -163,7 +163,7 @@ static int ef4_init_rx_buffers(struct ef4_rx_queue *rx_queue, bool atomic) do { page = ef4_reuse_page(rx_queue); if (page == NULL) { - page = alloc_pages(__GFP_COLD | __GFP_COMP | + page = alloc_pages(__GFP_COMP | (atomic ? GFP_ATOMIC : GFP_KERNEL), efx->rx_buffer_order); if (unlikely(page == NULL)) diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 42443f434569..0004c50d3c83 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -163,7 +163,7 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic) do { page = efx_reuse_page(rx_queue); if (page == NULL) { - page = alloc_pages(__GFP_COLD | __GFP_COMP | + page = alloc_pages(__GFP_COMP | (atomic ? GFP_ATOMIC : GFP_KERNEL), efx->rx_buffer_order); if (unlikely(page == NULL)) diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c index e9672b1f9968..031cf9c3435a 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c @@ -335,7 +335,7 @@ static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata, dma_addr_t pages_dma; /* Try to obtain pages, decreasing order if necessary */ - gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN; while (order >= 0) { pages = alloc_pages(gfp, order); if (pages) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 437d36289786..50d2b76771b5 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -906,7 +906,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) sw_data[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ - page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD); + page = alloc_page(GFP_ATOMIC | GFP_DMA); if (unlikely(!page)) { dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n"); goto fail; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 511f8339fa96..5eec09d63fc0 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -988,7 +988,6 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, int err; bool oom; - gfp |= __GFP_COLD; do { if (vi->mergeable_rx_bufs) err = add_recvbuf_mergeable(vi, rq, gfp); diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c index 9e538a59f09d..03e55bca4ada 100644 --- a/drivers/staging/lustre/lustre/mdc/mdc_request.c +++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c @@ -1152,7 +1152,7 @@ static int mdc_read_page_remote(void *data, struct page *page0) } for (npages = 1; npages < max_pages; npages++) { - page = page_cache_alloc_cold(inode->i_mapping); + page = page_cache_alloc(inode->i_mapping); if (!page) break; page_pool[npages] = page; -- cgit v1.2.3