From ad377c630864e2609c54385907493dbf68a34295 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 25 May 2011 11:34:57 +0200 Subject: arm: mxs: include asm/processor.h for cpu_relax() I get this build error as of today: arch/arm/mach-mxs/ocotp.c: In function 'mxs_get_ocotp': arch/arm/mach-mxs/ocotp.c:54: error: implicit declaration of function 'cpu_relax' make[2]: *** [arch/arm/mach-mxs/ocotp.o] Error 1 Looks like it has been indirectly included before which broke now. Include it directly. Signed-off-by: Wolfram Sang Cc: Shawn Guo Signed-off-by: Sascha Hauer --- arch/arm/mach-mxs/ocotp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/mach-mxs/ocotp.c b/arch/arm/mach-mxs/ocotp.c index 65157a35dbb..54add60f94c 100644 --- a/arch/arm/mach-mxs/ocotp.c +++ b/arch/arm/mach-mxs/ocotp.c @@ -16,6 +16,8 @@ #include #include +#include /* for cpu_relax() */ + #include #define OCOTP_WORD_OFFSET 0x20 -- cgit v1.2.3-18-g5258 From 5f85e931278ff80aa3ea7861a73a6c6ce940f2e9 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Sat, 28 May 2011 16:05:08 -0300 Subject: ARM: mx51/sdma: Check the chip revision in run-time Check the MX51 chip revision in run-time so that the correct SDMA firmware can be loaded. While at it also remove the silicon revision from the sdma_script_start_addrs structure name for MX51. All the MX51 revisions share the same SDMA start addresses. Signed-off-by: Fabio Estevam Signed-off-by: Sascha Hauer --- arch/arm/plat-mxc/devices/platform-imx-dma.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm/plat-mxc/devices/platform-imx-dma.c b/arch/arm/plat-mxc/devices/platform-imx-dma.c index 3538b85ede9..b130f60ca6b 100644 --- a/arch/arm/plat-mxc/devices/platform-imx-dma.c +++ b/arch/arm/plat-mxc/devices/platform-imx-dma.c @@ -139,7 +139,7 @@ static struct sdma_script_start_addrs addr_imx35_to2 = { #endif #ifdef CONFIG_SOC_IMX51 -static struct sdma_script_start_addrs addr_imx51_to1 = { +static struct sdma_script_start_addrs addr_imx51 = { .ap_2_ap_addr = 642, .uart_2_mcu_addr = 817, .mcu_2_app_addr = 747, @@ -196,7 +196,9 @@ static int __init imxXX_add_imx_dma(void) #if defined(CONFIG_SOC_IMX51) if (cpu_is_mx51()) { - imx51_imx_sdma_data.pdata.script_addrs = &addr_imx51_to1; + int to_version = mx51_revision() >> 4; + imx51_imx_sdma_data.pdata.to_version = to_version; + imx51_imx_sdma_data.pdata.script_addrs = &addr_imx51; ret = imx_add_imx_sdma(&imx51_imx_sdma_data); } else #endif -- cgit v1.2.3-18-g5258 From 2fdf99934c2c39848ad3633ce504a0262f21faf9 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 30 May 2011 19:44:22 +0100 Subject: ARM: 6946/1: vexpress: move v2m clock init to init_early Commit 7ff550de99141cbd3be0129d563cc4554fdde9f6 breaks vexpress booting. The v2m clock table needs to be setup in init_early before the timer initialization occurs. Signed-off-by: Rob Herring Signed-off-by: Russell King --- arch/arm/mach-vexpress/v2m.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 285edcd2da2..9e6b93b1a04 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -46,12 +46,6 @@ static struct map_desc v2m_io_desc[] __initdata = { }, }; -static void __init v2m_init_early(void) -{ - ct_desc->init_early(); - versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000); -} - static void __init v2m_timer_init(void) { u32 scctrl; @@ -365,6 +359,13 @@ static struct clk_lookup v2m_lookups[] = { }, }; +static void __init v2m_init_early(void) +{ + ct_desc->init_early(); + clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups)); + versatile_sched_clock_init(MMIO_P2V(V2M_SYS_24MHZ), 24000000); +} + static void v2m_power_off(void) { if (v2m_cfg_write(SYS_CFG_SHUTDOWN | SYS_CFG_SITE_MB, 0)) @@ -418,8 +419,6 @@ static void __init v2m_init(void) { int i; - clkdev_add_table(v2m_lookups, ARRAY_SIZE(v2m_lookups)); - platform_device_register(&v2m_pcie_i2c_device); platform_device_register(&v2m_ddc_i2c_device); platform_device_register(&v2m_flash_device); -- cgit v1.2.3-18-g5258 From 9425032b77c3a4f066a032bac7f7d08668b6cc3c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 31 May 2011 22:10:03 +0100 Subject: ARM: 6947/2: mach-u300: fix compilation error in timer The introduction of the mmio timer accidentally referenced the old clocksource struct which does not exist anymore. Fix this by using a simple string instead. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/mach-u300/timer.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c index 891cf44591e..18d7fa0603c 100644 --- a/arch/arm/mach-u300/timer.c +++ b/arch/arm/mach-u300/timer.c @@ -411,8 +411,7 @@ static void __init u300_timer_init(void) /* Use general purpose timer 2 as clock source */ if (clocksource_mmio_init(U300_TIMER_APP_VBASE + U300_TIMER_APP_GPT2CC, "GPT2", rate, 300, 32, clocksource_mmio_readl_up)) - printk(KERN_ERR "timer: failed to initialize clock " - "source %s\n", clocksource_u300_1mhz.name); + pr_err("timer: failed to initialize U300 clock source\n"); clockevents_calc_mult_shift(&clockevent_u300_1mhz, rate, APPTIMER_MIN_RANGE); -- cgit v1.2.3-18-g5258 From 9a819d8ac8197b44bbc2adad592b677fe749804d Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 31 May 2011 08:09:39 +0100 Subject: ARM: 6948/1: Fix .size directives for __arm{7,9}tdmi_proc_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gas used to accept (and ignore?) .size directives which referred to undefined symbols, as these do. In binutils 2.21 these are treated as fatal errors. The issue in proc-arm7tdmi.S was also fixed independently by Peter Chubb. Signed-off-by: Ben Hutchings Signed-off-by: Uwe Kleine-König Signed-off-by: Russell King --- arch/arm/mm/proc-arm7tdmi.S | 2 +- arch/arm/mm/proc-arm9tdmi.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index e4c165ca669..537ffcb0646 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -146,7 +146,7 @@ __arm7tdmi_proc_info: .long 0 .long 0 .long v4_cache_fns - .size __arm7tdmi_proc_info, . - __arm7dmi_proc_info + .size __arm7tdmi_proc_info, . - __arm7tdmi_proc_info .type __triscenda7_proc_info, #object __triscenda7_proc_info: diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index 7b7ebd4d096..546b54da100 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -116,7 +116,7 @@ __arm9tdmi_proc_info: .long 0 .long 0 .long v4_cache_fns - .size __arm9tdmi_proc_info, . - __arm9dmi_proc_info + .size __arm9tdmi_proc_info, . - __arm9tdmi_proc_info .type __p2001_proc_info, #object __p2001_proc_info: -- cgit v1.2.3-18-g5258 From 45f6d7e0e634d49744c1a590461ed1bb3d2201ac Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Thu, 2 Jun 2011 15:01:36 +0100 Subject: ARM: 6951/1: include .bss in memory layout information The "Virtual memory kernel layout" message at startup already prints .text and .data. Print .bss too. Signed-off-by: Rabin Vincent Signed-off-by: Russell King --- arch/arm/mm/init.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2c2cce9cd8c..b2cf9460ea6 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -635,7 +635,8 @@ void __init mem_init(void) " modules : 0x%08lx - 0x%08lx (%4ld MB)\n" " .init : 0x%p" " - 0x%p" " (%4d kB)\n" " .text : 0x%p" " - 0x%p" " (%4d kB)\n" - " .data : 0x%p" " - 0x%p" " (%4d kB)\n", + " .data : 0x%p" " - 0x%p" " (%4d kB)\n" + " .bss : 0x%p" " - 0x%p" " (%4d kB)\n", MLK(UL(CONFIG_VECTORS_BASE), UL(CONFIG_VECTORS_BASE) + (PAGE_SIZE)), @@ -657,7 +658,8 @@ void __init mem_init(void) MLK_ROUNDUP(__init_begin, __init_end), MLK_ROUNDUP(_text, _etext), - MLK_ROUNDUP(_sdata, _edata)); + MLK_ROUNDUP(_sdata, _edata), + MLK_ROUNDUP(__bss_start, __bss_stop)); #undef MLK #undef MLM -- cgit v1.2.3-18-g5258 From 9fc2552a68eb28f95f367156cf46a3da7843ff37 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 5 Jun 2011 02:24:58 +0100 Subject: ARM: 6952/1: fix lockdep warning of "unannotated irqs-off" This patch fixes the lockdep warning of "unannotated irqs-off"[1]. After entering __irq_usr, arm core will disable interrupt automatically, but __irq_usr does not annotate the irq disable, so lockdep may complain the warning if it has chance to check this in irq handler. This patch adds trace_hardirqs_off in __irq_usr before entering irq_handler to handle the irq, also calls ret_to_user_from_irq to avoid calling disable_irq again. This is also a fix for irq off tracer. [1], lockdep warning log of "unannotated irqs-off" [ 13.804687] ------------[ cut here ]------------ [ 13.809570] WARNING: at kernel/lockdep.c:3335 check_flags+0x78/0x1d0() [ 13.816467] Modules linked in: [ 13.819732] Backtrace: [ 13.822357] [] (dump_backtrace+0x0/0x100) from [] (dump_stack+0x20/0x24) [ 13.831268] r6:c07d8c2c r5:00000d07 r4:00000000 r3:00000000 [ 13.837280] [] (dump_stack+0x0/0x24) from [] (warn_slowpath_common+0x5c/0x74) [ 13.846649] [] (warn_slowpath_common+0x0/0x74) from [] (warn_slowpath_null+0x2c/0x34) [ 13.856781] r8:00000000 r7:00000000 r6:c18b8194 r5:60000093 r4:ef182000 [ 13.863708] r3:00000009 [ 13.866485] [] (warn_slowpath_null+0x0/0x34) from [] (check_flags+0x78/0x1d0) [ 13.875823] [] (check_flags+0x0/0x1d0) from [] (lock_acquire+0x4c/0x150) [ 13.884704] [] (lock_acquire+0x0/0x150) from [] (_raw_spin_lock+0x4c/0x84) [ 13.893798] [] (_raw_spin_lock+0x0/0x84) from [] (sched_ttwu_pending+0x58/0x8c) [ 13.903320] r6:ef92d040 r5:00000003 r4:c18b8180 [ 13.908233] [] (sched_ttwu_pending+0x0/0x8c) from [] (scheduler_ipi+0x18/0x1c) [ 13.917663] r6:ef183fb0 r5:00000003 r4:00000000 r3:00000001 [ 13.923645] [] (scheduler_ipi+0x0/0x1c) from [] (do_IPI+0x9c/0xfc) [ 13.932006] [] (do_IPI+0x0/0xfc) from [] (__irq_usr+0x48/0xe0) [ 13.939971] Exception stack(0xef183fb0 to 0xef183ff8) [ 13.945281] 3fa0: ffffffc3 0001500c 00000001 0001500c [ 13.953948] 3fc0: 00000050 400b45f0 400d9000 00000000 00000001 400d9600 6474e552 bea05b3c [ 13.962585] 3fe0: 400d96c0 bea059c0 400b6574 400b65d8 20000010 ffffffff [ 13.969573] r6:00000403 r5:fa240100 r4:ffffffff r3:20000010 [ 13.975585] ---[ end trace efc4896ab0fb62cb ]--- [ 13.980468] possible reason: unannotated irqs-off. [ 13.985534] irq event stamp: 1610 [ 13.989044] hardirqs last enabled at (1610): [] no_work_pending+0x8/0x2c [ 13.997131] hardirqs last disabled at (1609): [] ret_slow_syscall+0xc/0x1c [ 14.005371] softirqs last enabled at (0): [] copy_process+0x2cc/0xa24 [ 14.013183] softirqs last disabled at (0): [< (null)>] (null) Signed-off-by: Ming Lei Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 6 +++++- arch/arm/kernel/entry-common.S | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index e8d88567680..90c62cd51ca 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -435,6 +435,10 @@ __irq_usr: usr_entry kuser_cmpxchg_check +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif + get_thread_info tsk #ifdef CONFIG_PREEMPT ldr r8, [tsk, #TI_PREEMPT] @ get preempt count @@ -453,7 +457,7 @@ __irq_usr: #endif mov why, #0 - b ret_to_user + b ret_to_user_from_irq UNWIND(.fnend ) ENDPROC(__irq_usr) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 1e7b04a40a3..b2a27b6b004 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -64,6 +64,7 @@ work_resched: ENTRY(ret_to_user) ret_slow_syscall: disable_irq @ disable interrupts +ENTRY(ret_to_user_from_irq) ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK bne work_pending @@ -75,6 +76,7 @@ no_work_pending: arch_ret_to_user r1, lr restore_user_regs fast = 0, offset = 0 +ENDPROC(ret_to_user_from_irq) ENDPROC(ret_to_user) /* -- cgit v1.2.3-18-g5258 From 17ee083b7897ab27b4949c42de805889ebd2b4c5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 5 May 2011 17:23:10 +0100 Subject: ARM: 6894/1: mmci: trigger card detect IRQs on falling and rising edges Right now the card detect IRQ for MMCI is requested without any flags which will give some default machine-specified IRQ behaviour. However on the U300 rising+falling edges (such as can be expected from a simple GPIO to generate when inserting/removing a card) need to be requested explicitly. Cc: Rabin Vincent Cc: Ulf Hansson Cc: Sebastian Rasmussen Signed-off-by: Linus Walleij Signed-off-by: Russell King --- drivers/mmc/host/mmci.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 5da5bea0f9f..7721de942c6 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1144,9 +1144,17 @@ static int __devinit mmci_probe(struct amba_device *dev, else if (ret != -ENOSYS) goto err_gpio_cd; + /* + * A gpio pin that will detect cards when inserted and removed + * will most likely want to trigger on the edges if it is + * 0 when ejected and 1 when inserted (or mutatis mutandis + * for the inverted case) so we request triggers on both + * edges. + */ ret = request_any_context_irq(gpio_to_irq(plat->gpio_cd), - mmci_cd_irq, 0, - DRIVER_NAME " (cd)", host); + mmci_cd_irq, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, + DRIVER_NAME " (cd)", host); if (ret >= 0) host->gpio_cd_irq = gpio_to_irq(plat->gpio_cd); } -- cgit v1.2.3-18-g5258 From 629acb6abac0ef217ee579e14084af2ce7381dbc Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Wed, 8 Jun 2011 15:10:08 +1000 Subject: MD: no integrity register if no gendisk Don't attempt md_integrity_register if there is no gendisk struct available. When MD arrays are built via device-mapper, the gendisk structure is not available via mddev. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/md.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index aa640a85bb2..4ea02c634d3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1781,8 +1781,8 @@ int md_integrity_register(mddev_t *mddev) if (list_empty(&mddev->disks)) return 0; /* nothing to do */ - if (blk_get_integrity(mddev->gendisk)) - return 0; /* already registered */ + if (!mddev->gendisk || blk_get_integrity(mddev->gendisk)) + return 0; /* shouldn't register, or already is */ list_for_each_entry(rdev, &mddev->disks, same_set) { /* skip spares and non-functional disks */ if (test_bit(Faulty, &rdev->flags)) -- cgit v1.2.3-18-g5258 From 68866e425be2ef2664aa5c691bb3ab789736acf5 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Wed, 8 Jun 2011 15:10:08 +1000 Subject: MD: no sync IO while suspended Disallow resync I/O while the RAID array is suspended. Recovery, resync, and metadata I/O should not be allowed while a device is suspended. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/md.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 4ea02c634d3..4fa915a21d0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7045,7 +7045,6 @@ void md_do_sync(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_do_sync); - static int remove_and_add_spares(mddev_t *mddev) { mdk_rdev_t *rdev; @@ -7157,6 +7156,9 @@ static void reap_sync_thread(mddev_t *mddev) */ void md_check_recovery(mddev_t *mddev) { + if (mddev->suspended) + return; + if (mddev->bitmap) bitmap_daemon_work(mddev); -- cgit v1.2.3-18-g5258 From ac42450c7c814769bee963ae4b897c149bb0ab53 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Tue, 7 Jun 2011 17:48:35 -0500 Subject: MD: possible typo Make message a bit clearer by s/blocks/k/ I chose 'k' vs 'kiB' or 'kB' because it is what is used earlier in the message. 'k' may be a bit ambigous, but I think it's better than "blocks" which normally means 512, but means 1024 in MD. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/md.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 4fa915a21d0..3715e89dcaa 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6866,8 +6866,8 @@ void md_do_sync(mddev_t *mddev) * Tune reconstruction: */ window = 32*(PAGE_SIZE/512); - printk(KERN_INFO "md: using %dk window, over a total of %llu blocks.\n", - window/2,(unsigned long long) max_sectors/2); + printk(KERN_INFO "md: using %dk window, over a total of %lluk.\n", + window/2, (unsigned long long)max_sectors/2); atomic_set(&mddev->recovery_active, 0); last_check = 0; -- cgit v1.2.3-18-g5258 From 0fd018af37dadbb7826850883ad8abfecdb1a00b Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Tue, 7 Jun 2011 17:49:36 -0500 Subject: MD: move thread wakeups into resume Move personality and sync/recovery thread starting outside md_run. Moving the wakeup's of the personality and sync/recovery threads out of md_run and into do_md_run and mddev_resume solves two issues: 1) It allows bitmap_load to be called before the sync_thread is run and 2) when MD personalities are used by device-mapper (dm-raid.c), the start-up of the array is better alligned with device-mapper primatives (CTR/resume/suspend/DTR). I/O - in this case, recovery operations - should not happen until after a resume has taken place. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/md.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 3715e89dcaa..d5385188c44 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -351,6 +351,9 @@ void mddev_resume(mddev_t *mddev) mddev->suspended = 0; wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); + + md_wakeup_thread(mddev->thread); + md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ } EXPORT_SYMBOL_GPL(mddev_resume); @@ -4619,9 +4622,6 @@ int md_run(mddev_t *mddev) if (mddev->flags) md_update_sb(mddev, 0); - md_wakeup_thread(mddev->thread); - md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ - md_new_event(mddev); sysfs_notify_dirent_safe(mddev->sysfs_state); sysfs_notify_dirent_safe(mddev->sysfs_action); @@ -4642,6 +4642,10 @@ static int do_md_run(mddev_t *mddev) bitmap_destroy(mddev); goto out; } + + md_wakeup_thread(mddev->thread); + md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ + set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); mddev->changed = 1; -- cgit v1.2.3-18-g5258 From 1ed7242e591af7e233234d483f12d33818b189d9 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Tue, 7 Jun 2011 17:50:35 -0500 Subject: MD: raid1 changes to allow use by device mapper MD RAID1: Changes to allow RAID1 to be used by device-mapper (dm-raid.c) Added the necessary congestion function and conditionalize calls requiring an array 'queue' or 'gendisk'. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid1.c | 24 +++++++++++++++++------- drivers/md/raid1.h | 2 ++ 2 files changed, 19 insertions(+), 7 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 5d096096f95..f7431b6d844 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -497,21 +497,19 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio) return best_disk; } -static int raid1_congested(void *data, int bits) +int md_raid1_congested(mddev_t *mddev, int bits) { - mddev_t *mddev = data; conf_t *conf = mddev->private; int i, ret = 0; - if (mddev_congested(mddev, bits)) - return 1; - rcu_read_lock(); for (i = 0; i < mddev->raid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); + BUG_ON(!q); + /* Note the '|| 1' - when read_balance prefers * non-congested targets, it can be removed */ @@ -524,7 +522,15 @@ static int raid1_congested(void *data, int bits) rcu_read_unlock(); return ret; } +EXPORT_SYMBOL_GPL(md_raid1_congested); +static int raid1_congested(void *data, int bits) +{ + mddev_t *mddev = data; + + return mddev_congested(mddev, bits) || + md_raid1_congested(mddev, bits); +} static void flush_pending_writes(conf_t *conf) { @@ -1972,6 +1978,8 @@ static int run(mddev_t *mddev) return PTR_ERR(conf); list_for_each_entry(rdev, &mddev->disks, same_set) { + if (!mddev->gendisk) + continue; disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk @@ -2013,8 +2021,10 @@ static int run(mddev_t *mddev) md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); - mddev->queue->backing_dev_info.congested_fn = raid1_congested; - mddev->queue->backing_dev_info.congested_data = mddev; + if (mddev->queue) { + mddev->queue->backing_dev_info.congested_fn = raid1_congested; + mddev->queue->backing_dev_info.congested_data = mddev; + } return md_integrity_register(mddev); } diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 5fc4ca1af86..e743a64fac4 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -126,4 +126,6 @@ struct r1bio_s { */ #define R1BIO_Returned 6 +extern int md_raid1_congested(mddev_t *mddev, int bits); + #endif -- cgit v1.2.3-18-g5258 From 076f968b37f0232d883749da8f5031df5dea7ade Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Tue, 7 Jun 2011 17:51:30 -0500 Subject: MD: add sync_super to mddev_t struct Add the 'sync_super' function pointer to MD array structure (struct mddev_s) If device-mapper (dm-raid.c) is to define its own on-disk superblock and be able to load it, there must still be a way for MD to initiate superblock updates. The simplest way to make this happen is to provide a pointer in the MD array structure that can be set by device-mapper (or other module) with a function to do this. If the function has been set, it will be used; otherwise, the method with be looked up via 'super_types' as usual. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/md.c | 15 +++++++++++++-- drivers/md/md.h | 1 + 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index d5385188c44..9160463b5f6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1753,6 +1753,18 @@ static struct super_type super_types[] = { }, }; +static void sync_super(mddev_t *mddev, mdk_rdev_t *rdev) +{ + if (mddev->sync_super) { + mddev->sync_super(mddev, rdev); + return; + } + + BUG_ON(mddev->major_version >= ARRAY_SIZE(super_types)); + + super_types[mddev->major_version].sync_super(mddev, rdev); +} + static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2) { mdk_rdev_t *rdev, *rdev2; @@ -2171,8 +2183,7 @@ static void sync_sbs(mddev_t * mddev, int nospares) /* Don't update this superblock */ rdev->sb_loaded = 2; } else { - super_types[mddev->major_version]. - sync_super(mddev, rdev); + sync_super(mddev, rdev); rdev->sb_loaded = 1; } } diff --git a/drivers/md/md.h b/drivers/md/md.h index 0b1fd3f1d85..5e35535ab7c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -330,6 +330,7 @@ struct mddev_s atomic_t flush_pending; struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ + void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev); }; -- cgit v1.2.3-18-g5258 From 7416401661fad5c7ee9edb17cb54e7bff7a74dfe Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Jun 2011 11:51:43 +0200 Subject: arm: davinci: Fix fallout from generic irq chip conversion The code which does the chained handler setup was overwriting chip_data. Signed-off-by: Thomas Gleixner Tested-by: Holger Hans Peter Freyther Signed-off-by: Kevin Hilman Signed-off-by: Sekhar Nori --- arch/arm/mach-davinci/gpio.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-davinci/gpio.c b/arch/arm/mach-davinci/gpio.c index a0b838894ac..e7221398e5a 100644 --- a/arch/arm/mach-davinci/gpio.c +++ b/arch/arm/mach-davinci/gpio.c @@ -252,9 +252,11 @@ static struct irq_chip gpio_irqchip = { static void gpio_irq_handler(unsigned irq, struct irq_desc *desc) { - struct davinci_gpio_regs __iomem *g = irq2regs(irq); + struct davinci_gpio_regs __iomem *g; u32 mask = 0xffff; + g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc); + /* we only care about one bank */ if (irq & 1) mask <<= 16; @@ -422,8 +424,7 @@ static int __init davinci_gpio_irq_setup(void) /* set up all irqs in this bank */ irq_set_chained_handler(bank_irq, gpio_irq_handler); - irq_set_chip_data(bank_irq, (__force void *)g); - irq_set_handler_data(bank_irq, (void *)irq); + irq_set_handler_data(bank_irq, (__force void *)g); for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) { irq_set_chip(irq, &gpio_irqchip); -- cgit v1.2.3-18-g5258 From 7e9f1945213cdd7cd11f29346ded07a81854b5af Mon Sep 17 00:00:00 2001 From: Sekhar Nori Date: Sun, 5 Jun 2011 17:33:33 +0530 Subject: davinci: make PCM platform devices static Make the PCM device structures used in devices.c and devices-da8xx.c static as they are used only in the respective files. This was found when trying to build a single image for DaVinci and DA8x devices using runtime P2V support. Signed-off-by: Sekhar Nori --- arch/arm/mach-davinci/devices-da8xx.c | 2 +- arch/arm/mach-davinci/devices.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c index 4e66881c7ae..fc4e98ea754 100644 --- a/arch/arm/mach-davinci/devices-da8xx.c +++ b/arch/arm/mach-davinci/devices-da8xx.c @@ -494,7 +494,7 @@ static struct platform_device da850_mcasp_device = { .resource = da850_mcasp_resources, }; -struct platform_device davinci_pcm_device = { +static struct platform_device davinci_pcm_device = { .name = "davinci-pcm-audio", .id = -1, }; diff --git a/arch/arm/mach-davinci/devices.c b/arch/arm/mach-davinci/devices.c index 8f4f736aa26..806a2f02b98 100644 --- a/arch/arm/mach-davinci/devices.c +++ b/arch/arm/mach-davinci/devices.c @@ -298,7 +298,7 @@ static void davinci_init_wdt(void) /*-------------------------------------------------------------------------*/ -struct platform_device davinci_pcm_device = { +static struct platform_device davinci_pcm_device = { .name = "davinci-pcm-audio", .id = -1, }; -- cgit v1.2.3-18-g5258 From 9c81075f436f867f580c2edf2350c0898cffc9d0 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Wed, 8 Jun 2011 17:59:30 -0500 Subject: MD: support initial bitmap creation in-kernel Add bitmap support to the device-mapper specific metadata area. This patch allows the creation of the bitmap metadata area upon initial array creation via device-mapper. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++--- drivers/md/md.h | 1 + 2 files changed, 89 insertions(+), 5 deletions(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 70bd738b8b9..f0769b34d65 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -534,6 +534,82 @@ void bitmap_print_sb(struct bitmap *bitmap) kunmap_atomic(sb, KM_USER0); } +/* + * bitmap_new_disk_sb + * @bitmap + * + * This function is somewhat the reverse of bitmap_read_sb. bitmap_read_sb + * reads and verifies the on-disk bitmap superblock and populates bitmap_info. + * This function verifies 'bitmap_info' and populates the on-disk bitmap + * structure, which is to be written to disk. + * + * Returns: 0 on success, -Exxx on error + */ +static int bitmap_new_disk_sb(struct bitmap *bitmap) +{ + bitmap_super_t *sb; + unsigned long chunksize, daemon_sleep, write_behind; + int err = -EINVAL; + + bitmap->sb_page = alloc_page(GFP_KERNEL); + if (IS_ERR(bitmap->sb_page)) { + err = PTR_ERR(bitmap->sb_page); + bitmap->sb_page = NULL; + return err; + } + bitmap->sb_page->index = 0; + + sb = kmap_atomic(bitmap->sb_page, KM_USER0); + + sb->magic = cpu_to_le32(BITMAP_MAGIC); + sb->version = cpu_to_le32(BITMAP_MAJOR_HI); + + chunksize = bitmap->mddev->bitmap_info.chunksize; + BUG_ON(!chunksize); + if (!is_power_of_2(chunksize)) { + kunmap_atomic(sb, KM_USER0); + printk(KERN_ERR "bitmap chunksize not a power of 2\n"); + return -EINVAL; + } + sb->chunksize = cpu_to_le32(chunksize); + + daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep; + if (!daemon_sleep || + (daemon_sleep < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) { + printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n"); + daemon_sleep = 5 * HZ; + } + sb->daemon_sleep = cpu_to_le32(daemon_sleep); + bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; + + /* + * FIXME: write_behind for RAID1. If not specified, what + * is a good choice? We choose COUNTER_MAX / 2 arbitrarily. + */ + write_behind = bitmap->mddev->bitmap_info.max_write_behind; + if (write_behind > COUNTER_MAX) + write_behind = COUNTER_MAX / 2; + sb->write_behind = cpu_to_le32(write_behind); + bitmap->mddev->bitmap_info.max_write_behind = write_behind; + + /* keep the array size field of the bitmap superblock up to date */ + sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); + + memcpy(sb->uuid, bitmap->mddev->uuid, 16); + + bitmap->flags |= BITMAP_STALE; + sb->state |= cpu_to_le32(BITMAP_STALE); + bitmap->events_cleared = bitmap->mddev->events; + sb->events_cleared = cpu_to_le64(bitmap->mddev->events); + + bitmap->flags |= BITMAP_HOSTENDIAN; + sb->version = cpu_to_le32(BITMAP_MAJOR_HOSTENDIAN); + + kunmap_atomic(sb, KM_USER0); + + return 0; +} + /* read the superblock from the bitmap file and initialize some bitmap fields */ static int bitmap_read_sb(struct bitmap *bitmap) { @@ -1076,8 +1152,8 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) } printk(KERN_INFO "%s: bitmap initialized from disk: " - "read %lu/%lu pages, set %lu bits\n", - bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt); + "read %lu/%lu pages, set %lu of %lu bits\n", + bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, chunks); return 0; @@ -1728,9 +1804,16 @@ int bitmap_create(mddev_t *mddev) vfs_fsync(file, 1); } /* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */ - if (!mddev->bitmap_info.external) - err = bitmap_read_sb(bitmap); - else { + if (!mddev->bitmap_info.external) { + /* + * If 'MD_ARRAY_FIRST_USE' is set, then device-mapper is + * instructing us to create a new on-disk bitmap instance. + */ + if (test_and_clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags)) + err = bitmap_new_disk_sb(bitmap); + else + err = bitmap_read_sb(bitmap); + } else { err = 0; if (mddev->bitmap_info.chunksize == 0 || mddev->bitmap_info.daemon_sleep == 0) diff --git a/drivers/md/md.h b/drivers/md/md.h index 5e35535ab7c..1c26c7a08ae 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -124,6 +124,7 @@ struct mddev_s #define MD_CHANGE_DEVS 0 /* Some device status has changed */ #define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ #define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */ +#define MD_ARRAY_FIRST_USE 3 /* First use of array, needs initialization */ int suspended; atomic_t active_io; -- cgit v1.2.3-18-g5258 From d6b212f4b19da5301e6b6eca562e5c7a2a6e8c8d Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Wed, 8 Jun 2011 18:00:28 -0500 Subject: MD: raid5 do not set fullsync Add check to determine if a device needs full resync or if partial resync will do RAID 5 was assuming that if a device was not In_sync, it must undergo a full resync. We add a check to see if 'saved_raid_disk' is the same as 'raid_disk'. If it is, we can safely skip the full resync and rely on the bitmap for partial recovery instead. This is the legitimate purpose of 'saved_raid_disk', from md.h: int saved_raid_disk; /* role that device used to have in the * array and could again if we did a partial * resync from the bitmap */ Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 346e69bfdab..f9d2fbc6497 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4858,7 +4858,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) printk(KERN_INFO "md/raid:%s: device %s operational as raid" " disk %d\n", mdname(mddev), bdevname(rdev->bdev, b), raid_disk); - } else + } else if (rdev->saved_raid_disk != raid_disk) /* Cannot rely on bitmap to complete recovery */ conf->fullsync = 1; } -- cgit v1.2.3-18-g5258 From d744540cd39e93976c4c8401e140232444ef3b0b Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Wed, 8 Jun 2011 18:01:10 -0500 Subject: MD: use is_power_of_2 macro Make use of is_power_of_2 macro. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index f0769b34d65..7fc028f9701 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -651,7 +651,7 @@ static int bitmap_read_sb(struct bitmap *bitmap) reason = "unrecognized superblock version"; else if (chunksize < 512) reason = "bitmap chunksize too small"; - else if ((1 << ffz(~chunksize)) != chunksize) + else if (!is_power_of_2(chunksize)) reason = "bitmap chunksize not a power of 2"; else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT) reason = "daemon sleep period out of range"; -- cgit v1.2.3-18-g5258 From 9864c0053d3da4c5731ac8a6c4835179310bd40a Mon Sep 17 00:00:00 2001 From: 马建朋 Date: Thu, 9 Jun 2011 11:42:48 +1000 Subject: md: Using poll /proc/mdstat can monitor the events of adding a spare disks Signed-off-by: majianpeng Signed-off-by: NeilBrown --- drivers/md/md.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 9160463b5f6..734bc099639 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5274,6 +5274,8 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) if (mddev->degraded) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + if (!err) + md_new_event(mddev); md_wakeup_thread(mddev->thread); return err; } -- cgit v1.2.3-18-g5258 From 01393f3d5836b7d62e925e6f4658a7eb22b83a11 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 9 Jun 2011 11:42:54 +1000 Subject: md: check ->hot_remove_disk when removing disk Check pers->hot_remove_disk instead of pers->hot_add_disk in slot_store() during disk removal. The linear personality only has ->hot_add_disk and no ->hot_remove_disk, so that removing disk in the array resulted to following kernel bug: $ sudo mdadm --create /dev/md0 --level=linear --raid-devices=4 /dev/loop[0-3] $ echo none | sudo tee /sys/block/md0/md/dev-loop2/slot BUG: unable to handle kernel NULL pointer dereference at (null) IP: [< (null)>] (null) PGD c9f5d067 PUD 8575a067 PMD 0 Oops: 0010 [#1] SMP CPU 2 Modules linked in: linear loop bridge stp llc kvm_intel kvm asus_atk0110 sr_mod cdrom sg Pid: 10450, comm: tee Not tainted 3.0.0-rc1-leonard+ #173 System manufacturer System Product Name/P5G41TD-M PRO RIP: 0010:[<0000000000000000>] [< (null)>] (null) RSP: 0018:ffff880085757df0 EFLAGS: 00010282 RAX: ffffffffa00168e0 RBX: ffff8800d1431800 RCX: 000000000000006e RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff88008543c000 RBP: ffff880085757e48 R08: 0000000000000002 R09: 000000000000000a R10: 0000000000000000 R11: ffff88008543c2e0 R12: 00000000ffffffff R13: ffff8800b4641000 R14: 0000000000000005 R15: 0000000000000000 FS: 00007fe8c9e05700(0000) GS:ffff88011fa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 00000000b4502000 CR4: 00000000000406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process tee (pid: 10450, threadinfo ffff880085756000, task ffff8800c9f08000) Stack: ffffffff8138496a ffff8800b4641000 ffff88008543c268 0000000000000000 ffff8800b4641000 ffff88008543c000 ffff8800d1431868 ffffffff81a78a90 ffff8800b4641000 ffff88008543c000 ffff8800d1431800 ffff880085757e98 Call Trace: [] ? slot_store+0xaa/0x265 [] rdev_attr_store+0x89/0xa8 [] sysfs_write_file+0x108/0x144 [] vfs_write+0xb1/0x10d [] ? trace_hardirqs_on_caller+0x111/0x135 [] sys_write+0x4d/0x77 [] system_call_fastpath+0x16/0x1b Code: Bad RIP value. RIP [< (null)>] (null) RSP CR2: 0000000000000000 ---[ end trace ba5fc64319a826fb ]--- Signed-off-by: Namhyung Kim Cc: stable@kernel.org Signed-off-by: NeilBrown --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 734bc099639..4332fc2f25d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2476,7 +2476,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) if (rdev->raid_disk == -1) return -EEXIST; /* personality does all needed checks */ - if (rdev->mddev->pers->hot_add_disk == NULL) + if (rdev->mddev->pers->hot_remove_disk == NULL) return -EINVAL; err = rdev->mddev->pers-> hot_remove_disk(rdev->mddev, rdev->raid_disk); -- cgit v1.2.3-18-g5258 From 27d5ea04d08bea37bf651090e5f3c573d2390df8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 9 Jun 2011 11:42:57 +1000 Subject: md/bitmap: use proper accessor macro Use COUNTER()/NEEDED() macro instead of open-coding them. Signed-off-by: Namhyung Kim Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 7fc028f9701..663e6051bba 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1408,7 +1408,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect return 0; } - if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) { + if (unlikely(COUNTER(*bmc) == COUNTER_MAX)) { DEFINE_WAIT(__wait); /* note that it is safe to do the prepare_to_wait * after the test as long as we do it before dropping @@ -1480,10 +1480,10 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto sysfs_notify_dirent_safe(bitmap->sysfs_can_clear); } - if (!success && ! (*bmc & NEEDED_MASK)) + if (!success && !NEEDED(*bmc)) *bmc |= NEEDED_MASK; - if ((*bmc & COUNTER_MAX) == COUNTER_MAX) + if (COUNTER(*bmc) == COUNTER_MAX) wake_up(&bitmap->overflow_wait); (*bmc)--; -- cgit v1.2.3-18-g5258 From 97b3d4aacfbd7186faf34597fcf1f55b8579be17 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 9 Jun 2011 11:43:01 +1000 Subject: md/bitmap: remove unused fields from struct bitmap Get rid of ->syncchunk and ->counter_bits since they're never used. Also discard COUNTER_BYTE_RATIO which is unused. Signed-off-by: Namhyung Kim Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 3 --- drivers/md/bitmap.h | 10 ---------- 2 files changed, 13 deletions(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 663e6051bba..574b09afedd 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1837,9 +1837,6 @@ int bitmap_create(mddev_t *mddev) bitmap->chunks = chunks; bitmap->pages = pages; bitmap->missing_pages = pages; - bitmap->counter_bits = COUNTER_BITS; - - bitmap->syncchunk = ~0UL; #ifdef INJECT_FATAL_FAULT_1 bitmap->bp = NULL; diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index d0aeaf46d93..b2a127e891a 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -85,7 +85,6 @@ typedef __u16 bitmap_counter_t; #define COUNTER_BITS 16 #define COUNTER_BIT_SHIFT 4 -#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8) #define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3) #define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1))) @@ -196,19 +195,10 @@ struct bitmap { mddev_t *mddev; /* the md device that the bitmap is for */ - int counter_bits; /* how many bits per block counter */ - /* bitmap chunksize -- how much data does each bit represent? */ unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */ unsigned long chunks; /* total number of data chunks for the array */ - /* We hold a count on the chunk currently being synced, and drop - * it when the last block is started. If the resync is aborted - * midway, we need to be able to drop that count, so we remember - * the counted chunk.. - */ - unsigned long syncchunk; - __u64 events_cleared; int need_sync; -- cgit v1.2.3-18-g5258 From f699bf2328521cc3e20c412fcdb9ffe1255c360f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 9 Jun 2011 11:43:04 +1000 Subject: md:Documentation/md.txt - fix typo Reported-by: CoolCold Signed-off-by: NeilBrown --- Documentation/md.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/md.txt b/Documentation/md.txt index 2366b1c8cf1..f0eee83ff78 100644 --- a/Documentation/md.txt +++ b/Documentation/md.txt @@ -555,7 +555,7 @@ also have sync_min sync_max The two values, given as numbers of sectors, indicate a range - withing the array where 'check'/'repair' will operate. Must be + within the array where 'check'/'repair' will operate. Must be a multiple of chunk_size. When it reaches "sync_max" it will pause, rather than complete. You can use 'select' or 'poll' on "sync_completed" to wait for -- cgit v1.2.3-18-g5258 From 618c75e491a5a50cd3819eaf5f853fd87df3ae42 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Fri, 3 Jun 2011 12:54:14 +0200 Subject: drm: fix fbs in DRM_IOCTL_MODE_GETRESOURCES ioctl The DRM_IOCTL_MODE_GETRESOURCES ioctl just returns bogus framebuffers. That is because the framebuffers for each file are in the filp_head member of struct drm_framebuffer, not in the head member. Signed-off-by: Sascha Hauer Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_crtc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 872747c5a54..21058e6ad2b 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -1113,7 +1113,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data, if (card_res->count_fbs >= fb_count) { copied = 0; fb_id = (uint32_t __user *)(unsigned long)card_res->fb_id_ptr; - list_for_each_entry(fb, &file_priv->fbs, head) { + list_for_each_entry(fb, &file_priv->fbs, filp_head) { if (put_user(fb->base.id, fb_id + copied)) { ret = -EFAULT; goto out; -- cgit v1.2.3-18-g5258 From b20f9bef8d9ff54be266062eae365ebf4b12ca64 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 8 Jun 2011 13:01:11 -0400 Subject: drm/radeon/kms: check modes against max pixel clock Filter out modes that are higher than the max pixel clock. Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_atombios.c | 4 ++++ drivers/gpu/drm/radeon/radeon_clocks.c | 8 +++++--- drivers/gpu/drm/radeon/radeon_combios.c | 5 +++++ drivers/gpu/drm/radeon/radeon_connectors.c | 13 ++++++++++++- 5 files changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index ba643b57605..27f45579e64 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -165,6 +165,7 @@ struct radeon_clock { uint32_t default_sclk; uint32_t default_dispclk; uint32_t dp_extclk; + uint32_t max_pixel_clock; }; /* diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 90dfb2b8cf0..fa62a503ae7 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -1246,6 +1246,10 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) } *dcpll = *p1pll; + rdev->clock.max_pixel_clock = le16_to_cpu(firmware_info->info.usMaxPixelClock); + if (rdev->clock.max_pixel_clock == 0) + rdev->clock.max_pixel_clock = 40000; + return true; } diff --git a/drivers/gpu/drm/radeon/radeon_clocks.c b/drivers/gpu/drm/radeon/radeon_clocks.c index 5249af8931e..2d48e7a1474 100644 --- a/drivers/gpu/drm/radeon/radeon_clocks.c +++ b/drivers/gpu/drm/radeon/radeon_clocks.c @@ -117,7 +117,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev) p1pll->reference_div = RREG32_PLL(RADEON_PPLL_REF_DIV) & 0x3ff; if (p1pll->reference_div < 2) p1pll->reference_div = 12; - p2pll->reference_div = p1pll->reference_div; + p2pll->reference_div = p1pll->reference_div; /* These aren't in the device-tree */ if (rdev->family >= CHIP_R420) { @@ -139,6 +139,8 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev) p2pll->pll_out_min = 12500; p2pll->pll_out_max = 35000; } + /* not sure what the max should be in all cases */ + rdev->clock.max_pixel_clock = 35000; spll->reference_freq = mpll->reference_freq = p1pll->reference_freq; spll->reference_div = mpll->reference_div = @@ -151,7 +153,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev) else rdev->clock.default_sclk = radeon_legacy_get_engine_clock(rdev); - + val = of_get_property(dp, "ATY,MCLK", NULL); if (val && *val) rdev->clock.default_mclk = (*val) / 10; @@ -160,7 +162,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev) radeon_legacy_get_memory_clock(rdev); DRM_INFO("Using device-tree clock info\n"); - + return true; } #else diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 5b991f7c6e2..d1b95b70af6 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -866,6 +866,11 @@ bool radeon_combios_get_clock_info(struct drm_device *dev) rdev->clock.default_sclk = sclk; rdev->clock.default_mclk = mclk; + if (RBIOS32(pll_info + 0x16)) + rdev->clock.max_pixel_clock = RBIOS32(pll_info + 0x16); + else + rdev->clock.max_pixel_clock = 35000; /* might need something asic specific */ + return true; } return false; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index ee1dccb3fec..9c2929c7e79 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -626,8 +626,14 @@ static int radeon_vga_get_modes(struct drm_connector *connector) static int radeon_vga_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_device *dev = connector->dev; + struct radeon_device *rdev = dev->dev_private; + /* XXX check mode bandwidth */ - /* XXX verify against max DAC output frequency */ + + if ((mode->clock / 10) > rdev->clock.max_pixel_clock) + return MODE_CLOCK_HIGH; + return MODE_OK; } @@ -1015,6 +1021,11 @@ static int radeon_dvi_mode_valid(struct drm_connector *connector, } else return MODE_CLOCK_HIGH; } + + /* check against the max pixel clock */ + if ((mode->clock / 10) > rdev->clock.max_pixel_clock) + return MODE_CLOCK_HIGH; + return MODE_OK; } -- cgit v1.2.3-18-g5258 From 303c805cb4dc1f5bc1d21f1c3757da0eae1e4f84 Mon Sep 17 00:00:00 2001 From: Ilija Hadzic Date: Tue, 7 Jun 2011 14:54:48 -0400 Subject: drm/radeon: fix GUI idle IH debug statements debug statement for GUI idle interrupt is wrong and incorrectly reports CP EOP interrupt; trivial issue, but confusing for someone trying to distinguish interrupt sources while debugging ... fixed Signed-off-by: Ilija Hadzic Reviewed-by: Alex Deucher Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/evergreen.c | 2 +- drivers/gpu/drm/radeon/r600.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 98ea597bc76..86157b172c8 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2944,7 +2944,7 @@ restart_ih: radeon_fence_process(rdev); break; case 233: /* GUI IDLE */ - DRM_DEBUG("IH: CP EOP\n"); + DRM_DEBUG("IH: GUI idle\n"); rdev->pm.gui_idle = true; wake_up(&rdev->irq.idle_queue); break; diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index d74d4d71437..7dd45ca64e2 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3444,7 +3444,7 @@ restart_ih: radeon_fence_process(rdev); break; case 233: /* GUI IDLE */ - DRM_DEBUG("IH: CP EOP\n"); + DRM_DEBUG("IH: GUI idle\n"); rdev->pm.gui_idle = true; wake_up(&rdev->irq.idle_queue); break; -- cgit v1.2.3-18-g5258 From 07989b7ad63af424886ff922fd3bcca9e00ffa78 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 9 Jun 2011 10:10:27 +0100 Subject: Revert "ARM: 6943/1: mm: use TTBR1 instead of reserved context ID" This reverts commit 52af9c6cd863fe37d1103035ec7ee22ac1296458. Will Deacon reports that: In 52af9c6c ("ARM: 6943/1: mm: use TTBR1 instead of reserved context ID") I updated the ASID rollover code to use only the kernel page tables whilst updating the ASID. Unfortunately, the code to restore the user page tables was part of a later patch which isn't yet in mainline, so this leaves the code quite broken. We're also in the process of eliminating __ARCH_WANT_INTERRUPTS_ON_CTXSW from ARM, so lets revert these until we can properly sort out what we're doing with the ARM context switching. Signed-off-by: Russell King --- arch/arm/mm/context.c | 11 +++++------ arch/arm/mm/proc-v7.S | 10 ++++++---- 2 files changed, 11 insertions(+), 10 deletions(-) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 8bfae964b13..b6c776ae403 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -24,7 +24,9 @@ DEFINE_PER_CPU(struct mm_struct *, current_mm); /* * We fork()ed a process, and we need a new context for the child - * to run in. + * to run in. We reserve version 0 for initial tasks so we will + * always allocate an ASID. The ASID 0 is reserved for the TTBR + * register changing sequence. */ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -34,11 +36,8 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) static void flush_context(void) { - u32 ttb; - /* Copy TTBR1 into TTBR0 */ - asm volatile("mrc p15, 0, %0, c2, c0, 1\n" - "mcr p15, 0, %0, c2, c0, 0" - : "=r" (ttb)); + /* set the reserved ASID before flushing the TLB */ + asm("mcr p15, 0, %0, c13, c0, 1\n" : : "r" (0)); isb(); local_flush_tlb_all(); if (icache_is_vivt_asid_tagged()) { diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index b3b566ec83d..3c3867850a3 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -108,16 +108,18 @@ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_ARM_ERRATA_430973 mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB #endif - mrc p15, 0, r2, c2, c0, 1 @ load TTB 1 - mcr p15, 0, r2, c2, c0, 0 @ into TTB 0 +#ifdef CONFIG_ARM_ERRATA_754322 + dsb +#endif + mcr p15, 0, r2, c13, c0, 1 @ set reserved context ID + isb +1: mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 isb #ifdef CONFIG_ARM_ERRATA_754322 dsb #endif mcr p15, 0, r1, c13, c0, 1 @ set context ID isb - mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 - isb #endif mov pc, lr ENDPROC(cpu_v7_switch_mm) -- cgit v1.2.3-18-g5258 From a0a54d37b4b1d1f55d1e81e8ffc223bb85472fa3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 9 Jun 2011 10:12:41 +0100 Subject: Revert "ARM: 6944/1: mm: allow ASID 0 to be allocated to tasks" This reverts commit 45b95235b0ac86cef2ad4480b0618b8778847479. Will Deacon reports that: In 52af9c6c ("ARM: 6943/1: mm: use TTBR1 instead of reserved context ID") I updated the ASID rollover code to use only the kernel page tables whilst updating the ASID. Unfortunately, the code to restore the user page tables was part of a later patch which isn't yet in mainline, so this leaves the code quite broken. We're also in the process of eliminating __ARCH_WANT_INTERRUPTS_ON_CTXSW from ARM, so lets revert these until we can properly sort out what we're doing with the context switching. Signed-off-by: Russell King --- arch/arm/mm/context.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index b6c776ae403..b0ee9ba3cfa 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -93,7 +93,7 @@ static void reset_context(void *info) return; smp_rmb(); - asid = cpu_last_asid + cpu; + asid = cpu_last_asid + cpu + 1; flush_context(); set_mm_context(mm, asid); @@ -143,13 +143,13 @@ void __new_context(struct mm_struct *mm) * to start a new version and flush the TLB. */ if (unlikely((asid & ~ASID_MASK) == 0)) { - asid = cpu_last_asid + smp_processor_id(); + asid = cpu_last_asid + smp_processor_id() + 1; flush_context(); #ifdef CONFIG_SMP smp_wmb(); smp_call_function(reset_context, NULL, 1); #endif - cpu_last_asid += NR_CPUS - 1; + cpu_last_asid += NR_CPUS; } set_mm_context(mm, asid); -- cgit v1.2.3-18-g5258 From 6075e9df471e35f2ebf4c73c95c304d0473bd4b2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 7 Jun 2011 09:40:51 +0100 Subject: ARM: 6949/2: mach-u300: fix compilaton warning in IO accessors The IO accessors for U300 were using u32 rather than the nominal void __iomem * type, rectify this by properly defining the virtual base for statically mapped peripherals to be void __iomem *. Requires fixing a field in struct clk as well. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/mach-u300/clock.h | 2 +- arch/arm/mach-u300/include/mach/u300-regs.h | 22 ++++++++++------------ 2 files changed, 11 insertions(+), 13 deletions(-) diff --git a/arch/arm/mach-u300/clock.h b/arch/arm/mach-u300/clock.h index c34f3ea3017..4f50ca8f901 100644 --- a/arch/arm/mach-u300/clock.h +++ b/arch/arm/mach-u300/clock.h @@ -31,7 +31,7 @@ struct clk { bool reset; __u16 clk_val; __s8 usecount; - __u32 res_reg; + void __iomem * res_reg; __u16 res_mask; bool hw_ctrld; diff --git a/arch/arm/mach-u300/include/mach/u300-regs.h b/arch/arm/mach-u300/include/mach/u300-regs.h index 8b85df4c8d8..035fdc9dbdb 100644 --- a/arch/arm/mach-u300/include/mach/u300-regs.h +++ b/arch/arm/mach-u300/include/mach/u300-regs.h @@ -18,6 +18,12 @@ * the defines are used for setting up the I/O memory mapping. */ +#ifdef __ASSEMBLER__ +#define IOMEM(a) (a) +#else +#define IOMEM(a) (void __iomem *) a +#endif + /* NAND Flash CS0 */ #define U300_NAND_CS0_PHYS_BASE 0x80000000 @@ -47,13 +53,6 @@ #define U300_SEMI_CONFIG_BASE 0x30000000 #endif -/* - * All the following peripherals are specified at their PHYSICAL address, - * so if you need to access them (in the kernel), you MUST use the macros - * defined in to map to the IO_ADDRESS_AHB() IO_ADDRESS_FAST() - * etc. - */ - /* * AHB peripherals */ @@ -63,11 +62,11 @@ /* Vectored Interrupt Controller 0, servicing 32 interrupts */ #define U300_INTCON0_BASE (U300_AHB_PER_PHYS_BASE+0x1000) -#define U300_INTCON0_VBASE (U300_AHB_PER_VIRT_BASE+0x1000) +#define U300_INTCON0_VBASE IOMEM(U300_AHB_PER_VIRT_BASE+0x1000) /* Vectored Interrupt Controller 1, servicing 32 interrupts */ #define U300_INTCON1_BASE (U300_AHB_PER_PHYS_BASE+0x2000) -#define U300_INTCON1_VBASE (U300_AHB_PER_VIRT_BASE+0x2000) +#define U300_INTCON1_VBASE IOMEM(U300_AHB_PER_VIRT_BASE+0x2000) /* Memory Stick Pro (MSPRO) controller */ #define U300_MSPRO_BASE (U300_AHB_PER_PHYS_BASE+0x3000) @@ -115,7 +114,7 @@ /* SYSCON */ #define U300_SYSCON_BASE (U300_SLOW_PER_PHYS_BASE+0x1000) -#define U300_SYSCON_VBASE (U300_SLOW_PER_VIRT_BASE+0x1000) +#define U300_SYSCON_VBASE IOMEM(U300_SLOW_PER_VIRT_BASE+0x1000) /* Watchdog */ #define U300_WDOG_BASE (U300_SLOW_PER_PHYS_BASE+0x2000) @@ -125,7 +124,7 @@ /* APP side special timer */ #define U300_TIMER_APP_BASE (U300_SLOW_PER_PHYS_BASE+0x4000) -#define U300_TIMER_APP_VBASE (U300_SLOW_PER_VIRT_BASE+0x4000) +#define U300_TIMER_APP_VBASE IOMEM(U300_SLOW_PER_VIRT_BASE+0x4000) /* Keypad */ #define U300_KEYPAD_BASE (U300_SLOW_PER_PHYS_BASE+0x5000) @@ -181,5 +180,4 @@ * Virtual accessor macros for static devices */ - #endif -- cgit v1.2.3-18-g5258 From f506cd48a4236b7045d092c9b92709ae6b4bdaf0 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Thu, 9 Jun 2011 04:58:36 +0100 Subject: ARM: 6953/1: DT: don't try to access physical address zero If the DT physical address is zero, this is equivalent to no DT. Especially when the actual RAM physical address is not located at zero, the result of phys_to_virt() would point to la-la-land and crash the kernel, which crash is completely silent this early during boot. Signed-off-by: Nicolas Pitre Acked-by: Grant Likely Signed-off-by: Russell King --- arch/arm/kernel/devtree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index a701e4226a6..0cdd7b456cb 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -76,6 +76,9 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) unsigned long dt_root; const char *model; + if (!dt_phys) + return NULL; + devtree = phys_to_virt(dt_phys); /* check device tree validity */ -- cgit v1.2.3-18-g5258 From 720c60e1943a06cfd9472ad5a9967dec304e4394 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Thu, 9 Jun 2011 05:05:27 +0100 Subject: ARM: 6954/1: zImage: fix Thumb2 breakage Commit af3e4fd37a "ARM: 6859/1: Add writethrough dcache support for ARM926EJS processor" broke Thumb2 compilation by omitting to maintain the wide encoding for the added branch instructions which made the ARM926EJ-S record smaller than expected, breaking the record walk code. Signed-off-by: Nicolas Pitre Cc: Mark A. Greer Signed-off-by: Russell King --- arch/arm/boot/compressed/head.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index f9da41921c5..942fad97e44 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -691,9 +691,9 @@ proc_types: .word 0x41069260 @ ARM926EJ-S (v5TEJ) .word 0xff0ffff0 - b __arm926ejs_mmu_cache_on - b __armv4_mmu_cache_off - b __armv5tej_mmu_cache_flush + W(b) __arm926ejs_mmu_cache_on + W(b) __armv4_mmu_cache_off + W(b) __armv5tej_mmu_cache_flush .word 0x00007000 @ ARM7 IDs .word 0x0000f000 -- cgit v1.2.3-18-g5258 From 373ce3020b03fb6199415ab866595c7d627bbc97 Mon Sep 17 00:00:00 2001 From: Po-Yu Chuang Date: Thu, 9 Jun 2011 08:42:17 +0100 Subject: ARM: 6955/1: cmpxchg syscall should data abort if page not write If the page to cmpxchg is user mode read only (not write), we should simulate a data abort first. Signed-off-by: Po-Yu Chuang Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/kernel/traps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index d52eec268b4..c5ead3c2c61 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -563,7 +563,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) if (!pmd_present(*pmd)) goto bad_access; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!pte_present(*pte) || !pte_dirty(*pte)) { + if (!pte_present(*pte) || !pte_write(*pte) || !pte_dirty(*pte)) { pte_unmap_unlock(pte, ptl); goto bad_access; } -- cgit v1.2.3-18-g5258 From a9011580a99cd4f21546381782582bfaf9e40675 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 9 Jun 2011 23:21:11 +0100 Subject: ARM: extend Code: line by one 16-bit quantity for Thumb instructions Dump out the following 16-bit instruction to the faulting instruction in the Code: line. This allows Thumb-2 instructions to be properly encoded. Tested-by: Kevin Hilman Signed-off-by: Russell King --- arch/arm/kernel/traps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index c5ead3c2c61..6807cb1e76d 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -139,7 +139,7 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) fs = get_fs(); set_fs(KERNEL_DS); - for (i = -4; i < 1; i++) { + for (i = -4; i < 1 + !!thumb; i++) { unsigned int val, bad; if (thumb) -- cgit v1.2.3-18-g5258 From 8f4b8c7613928d5c6da43715fedc00a7b1ee53be Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 11 Jun 2011 00:43:21 +0100 Subject: ARM: initrd: disable initrds outside of memory We can't cope with initrds outside of memory, so check that the initrd is within some declared memory to the kernel before using it. Otherwise we're likely to OOPS during boot. Signed-off-by: Russell King --- arch/arm/mm/init.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index b2cf9460ea6..c19571c40a2 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -330,6 +330,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) memblock_reserve(__pa(_stext), _end - _stext); #endif #ifdef CONFIG_BLK_DEV_INITRD + if (phys_initrd_size && + !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) { + pr_err("INITRD: 0x%08lx+0x%08lx is not a memory region - disabling initrd\n", + phys_initrd_start, phys_initrd_size); + phys_initrd_start = phys_initrd_size = 0; + } if (phys_initrd_size && memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) { pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n", -- cgit v1.2.3-18-g5258 From e172dedd89a342b30fddfafd820d2ef40c039cea Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 11 Jun 2011 00:44:35 +0100 Subject: ARM: footbridge: fix debug macros More of the same of 5f2c1b30 (ARM: footbridge: fix debug macros), this time for the DC21285-based debugging code rather than the 8250- based debugging code. Signed-off-by: Russell King --- arch/arm/mach-footbridge/include/mach/debug-macro.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-footbridge/include/mach/debug-macro.S b/arch/arm/mach-footbridge/include/mach/debug-macro.S index 30b971d6581..1be2eeb7a0a 100644 --- a/arch/arm/mach-footbridge/include/mach/debug-macro.S +++ b/arch/arm/mach-footbridge/include/mach/debug-macro.S @@ -26,6 +26,7 @@ #include #else +#include /* For EBSA285 debugging */ .equ dc21285_high, ARMCSR_BASE & 0xff000000 .equ dc21285_low, ARMCSR_BASE & 0x00ffffff @@ -36,8 +37,8 @@ .else mov \rp, #0 .endif - orr \rv, \rp, #0x42000000 - orr \rp, \rp, #dc21285_high + orr \rv, \rp, #dc21285_high + orr \rp, \rp, #0x42000000 .endm .macro senduart,rd,rx -- cgit v1.2.3-18-g5258 From 7d7975a0e1da7d6e558211b6296a96f1d6bf60ce Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 11 Jun 2011 00:46:17 +0100 Subject: ARM: footbridge: fix clock event support 4e8d7637 (ARM: footbridge: convert to clockevents/clocksource) did not set the cpumask for the clock event device. This causes boot to fail. Add the necessary initialization. Signed-off-by: Russell King --- arch/arm/mach-footbridge/dc21285-timer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c index 5f1f9867fc7..121ad1d4fa3 100644 --- a/arch/arm/mach-footbridge/dc21285-timer.c +++ b/arch/arm/mach-footbridge/dc21285-timer.c @@ -103,6 +103,7 @@ static void __init footbridge_timer_init(void) clockevents_calc_mult_shift(ce, mem_fclk_21285, 5); ce->max_delta_ns = clockevent_delta2ns(0xffffff, ce); ce->min_delta_ns = clockevent_delta2ns(0x000004, ce); + ce->cpumask = cpumask_of(smp_processor_id()); clockevents_register_device(ce); } -- cgit v1.2.3-18-g5258 From 89b882a25e703b72c3e84c582357e3e864d8ccca Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 1 Jun 2011 10:59:10 -0700 Subject: MAINTAINERS: Update CPU FREQUENCY patterns Commit bb0a56ecc4ba ("[CPUFREQ] Move x86 drivers to drivers/cpufreq/") moved the files, remove the old pattern. Signed-off-by: Joe Perches Signed-off-by: Dave Jones --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 29801f760b6..55d7b8062b3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1889,7 +1889,6 @@ L: cpufreq@vger.kernel.org W: http://www.codemonkey.org.uk/projects/cpufreq/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq.git S: Maintained -F: arch/x86/kernel/cpu/cpufreq/ F: drivers/cpufreq/ F: include/linux/cpufreq.h -- cgit v1.2.3-18-g5258 From 13f067537f34456443f61c950cd6dc37d1d5f3ee Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Sun, 12 Jun 2011 16:35:28 -0400 Subject: [CPUFREQ] Remove cpufreq_stats sysfs entries on module unload. cpufreq_stats leaves behind its sysfs entries, which causes a panic when something stumbled across them. (Discovered by unloading cpufreq_stats while powertop was loaded). Signed-off-by: Dave Jones Cc: stable@kernel.org --- drivers/cpufreq/cpufreq_stats.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index b60a4c26368..853f92d23dd 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -387,6 +387,7 @@ static void __exit cpufreq_stats_exit(void) unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier); for_each_online_cpu(cpu) { cpufreq_stats_free_table(cpu); + cpufreq_stats_free_sysfs(cpu); } } -- cgit v1.2.3-18-g5258 From cd51875d53ae1459a2b09b4338166a218c0635a7 Mon Sep 17 00:00:00 2001 From: Pavel Shilovsky Date: Thu, 9 Jun 2011 12:58:53 +0400 Subject: CIFS: Fix sparse error cifs_sb_master_tlink was declared as inline, but without a definition. Remove the declaration and move the definition up. Signed-off-by: Pavel Shilovsky Reviewed-by: Jeff Layton Signed-off-by: Steve French --- fs/cifs/connect.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index bb659eb7381..9190018f97e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2149,7 +2149,10 @@ cifs_put_tlink(struct tcon_link *tlink) } static inline struct tcon_link * -cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb); +cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb) +{ + return cifs_sb->master_tlink; +} static int compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) @@ -3484,12 +3487,6 @@ out: return tcon; } -static inline struct tcon_link * -cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb) -{ - return cifs_sb->master_tlink; -} - struct cifs_tcon * cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) { -- cgit v1.2.3-18-g5258 From 7fdbaa1b8daa1009b705985b903e3d2ebccad456 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 10 Jun 2011 16:14:57 -0400 Subject: cifs: don't allow cifs_reconnect to exit with NULL socket pointer It's possible for the following set of events to happen: cifsd calls cifs_reconnect which reconnects the socket. A userspace process then calls cifs_negotiate_protocol to handle the NEGOTIATE and gets a reply. But, while processing the reply, cifsd calls cifs_reconnect again. Eventually the GlobalMid_Lock is dropped and the reply from the earlier NEGOTIATE completes and the tcpStatus is set to CifsGood. cifs_reconnect then goes through and closes the socket and sets the pointer to zero, but because the status is now CifsGood, the new socket is not created and cifs_reconnect exits with the socket pointer set to NULL. Fix this by only setting the tcpStatus to CifsGood if the tcpStatus is CifsNeedNegotiate, and by making sure that generic_ip_connect is always called at least once in cifs_reconnect. Note that this is not a perfect fix for this issue. It's still possible that the NEGOTIATE reply is handled after the socket has been closed and reconnected. In that case, the socket state will look correct but it no NEGOTIATE was performed on it be for the wrong socket. In that situation though the server should just shut down the socket on the next attempted send, rather than causing the oops that occurs today. Cc: # .38.x: fd88ce9: [CIFS] cifs: clarify the meaning of tcpStatus == CifsGood Reported-and-Tested-by: Ben Greear Signed-off-by: Jeff Layton Signed-off-by: Steve French --- fs/cifs/connect.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9190018f97e..fa73e2a51cf 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -152,7 +152,7 @@ cifs_reconnect(struct TCP_Server_Info *server) mid_entry->callback(mid_entry); } - while (server->tcpStatus == CifsNeedReconnect) { + do { try_to_freeze(); /* we should try only the port we connected to before */ @@ -167,7 +167,7 @@ cifs_reconnect(struct TCP_Server_Info *server) server->tcpStatus = CifsNeedNegotiate; spin_unlock(&GlobalMid_Lock); } - } + } while (server->tcpStatus == CifsNeedReconnect); return rc; } @@ -3374,7 +3374,7 @@ int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses) } if (rc == 0) { spin_lock(&GlobalMid_Lock); - if (server->tcpStatus != CifsExiting) + if (server->tcpStatus == CifsNeedNegotiate) server->tcpStatus = CifsGood; else rc = -EHOSTDOWN; -- cgit v1.2.3-18-g5258 From 3e715513643f0207c8f3c22010b54954cd697474 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 13 Jun 2011 11:50:41 -0400 Subject: cifs: show sec= option in /proc/mounts Signed-off-by: Jeff Layton Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 989442dcfb4..e9def996e38 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -352,6 +352,37 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server) } } +static void +cifs_show_security(struct seq_file *s, struct TCP_Server_Info *server) +{ + seq_printf(s, ",sec="); + + switch (server->secType) { + case LANMAN: + seq_printf(s, "lanman"); + break; + case NTLMv2: + seq_printf(s, "ntlmv2"); + break; + case NTLM: + seq_printf(s, "ntlm"); + break; + case Kerberos: + seq_printf(s, "krb5"); + break; + case RawNTLMSSP: + seq_printf(s, "ntlmssp"); + break; + default: + /* shouldn't ever happen */ + seq_printf(s, "unknown"); + break; + } + + if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) + seq_printf(s, "i"); +} + /* * cifs_show_options() is for displaying mount options in /proc/mounts. * Not all settable options are displayed but most of the important @@ -365,6 +396,8 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) struct sockaddr *srcaddr; srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr; + cifs_show_security(s, tcon->ses->server); + seq_printf(s, ",unc=%s", tcon->treeName); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) -- cgit v1.2.3-18-g5258 From 8d1bca328b7c17af33bcf966d799c556ecbf370f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Sat, 11 Jun 2011 21:17:10 -0400 Subject: cifs: correctly handle NULL tcon pointer in CIFSTCon Long ago (in commit 00e485b0), I added some code to handle share-level passwords in CIFSTCon. That code ignored the fact that it's legit to pass in a NULL tcon pointer when connecting to the IPC$ share on the server. This wasn't really a problem until recently as we only called CIFSTCon this way when the server returned -EREMOTE. With the introduction of commit c1508ca2 however, it gets called this way on every mount, causing an oops when share-level security is in effect. Fix this by simply treating a NULL tcon pointer as if user-level security were in effect. I'm not aware of any servers that protect the IPC$ share with a specific password anyway. Also, add a comment to the top of CIFSTCon to ensure that we don't make the same mistake again. Cc: Reported-by: Martijn Uffing Signed-off-by: Jeff Layton Signed-off-by: Steve French --- fs/cifs/connect.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index fa73e2a51cf..12cf72dd0c4 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3174,6 +3174,10 @@ out: return rc; } +/* + * Issue a TREE_CONNECT request. Note that for IPC$ shares, that the tcon + * pointer may be NULL. + */ int CIFSTCon(unsigned int xid, struct cifs_ses *ses, const char *tree, struct cifs_tcon *tcon, @@ -3208,7 +3212,7 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses, pSMB->AndXCommand = 0xFF; pSMB->Flags = cpu_to_le16(TCON_EXTENDED_SECINFO); bcc_ptr = &pSMB->Password[0]; - if ((ses->server->sec_mode) & SECMODE_USER) { + if (!tcon || (ses->server->sec_mode & SECMODE_USER)) { pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ *bcc_ptr = 0; /* password is null byte */ bcc_ptr++; /* skip password */ -- cgit v1.2.3-18-g5258 From 96bf8bd1c953c3b9d89eac9f13dfdbf5e580060f Mon Sep 17 00:00:00 2001 From: Greg Dietsche Date: Mon, 13 Jun 2011 09:40:38 -0500 Subject: savage: remove unnecessary if statement the code always returns ret regardless, so if(ret) check is unnecessary. v2: fixed up the spelling. Signed-off-by: Greg Dietsche Reviewed-by: Nicolas Kaiser Signed-off-by: Dave Airlie --- drivers/gpu/drm/savage/savage_bci.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c index bf5f83ea14f..cb1ee4e0050 100644 --- a/drivers/gpu/drm/savage/savage_bci.c +++ b/drivers/gpu/drm/savage/savage_bci.c @@ -647,9 +647,6 @@ int savage_driver_firstopen(struct drm_device *dev) ret = drm_addmap(dev, aperture_base, SAVAGE_APERTURE_SIZE, _DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING, &dev_priv->aperture); - if (ret) - return ret; - return ret; } -- cgit v1.2.3-18-g5258 From 82ba3fef67829813d0ed4c45231235084a07f081 Mon Sep 17 00:00:00 2001 From: Jay Estabrook Date: Thu, 9 Jun 2011 18:18:39 -0400 Subject: alpha/drm: Cleanup Alpha support in DRM generic code Remove an obsolete Alpha adjustment, and modify another, to go with the current Alpha architecture support. Signed-off-by: Jay Estabrook Tested-by: Matt Turner Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_bufs.c | 3 --- drivers/gpu/drm/drm_vm.c | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c index 3e257a50bf5..e1bd713d91a 100644 --- a/drivers/gpu/drm/drm_bufs.c +++ b/drivers/gpu/drm/drm_bufs.c @@ -182,9 +182,6 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset, kfree(map); return -EINVAL; } -#endif -#ifdef __alpha__ - map->offset += dev->hose->mem_space->start; #endif /* Some drivers preinitialize some maps, without the X Server * needing to be aware of it. Therefore, we just return success diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c index 2c3fcbdfd8f..5db96d45fc7 100644 --- a/drivers/gpu/drm/drm_vm.c +++ b/drivers/gpu/drm/drm_vm.c @@ -526,7 +526,7 @@ static int drm_mmap_dma(struct file *filp, struct vm_area_struct *vma) static resource_size_t drm_core_get_reg_ofs(struct drm_device *dev) { #ifdef __alpha__ - return dev->hose->dense_mem_base - dev->hose->mem_space->start; + return dev->hose->dense_mem_base; #else return 0; #endif -- cgit v1.2.3-18-g5258 From 83533c132a55aac735028f6fb9b956e8c078db1f Mon Sep 17 00:00:00 2001 From: Jay Estabrook Date: Thu, 9 Jun 2011 18:19:12 -0400 Subject: alpha, drm: Remove obsolete Alpha support in MGA DRM code Remove an obsolete Alpha adjustment in the drm for MGA on Alpha. Signed-off-by: Jay Estabrook Tested-by: Matt Turner Signed-off-by: Dave Airlie --- drivers/gpu/drm/mga/mga_drv.h | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h index 1084fa4d261..54558a01969 100644 --- a/drivers/gpu/drm/mga/mga_drv.h +++ b/drivers/gpu/drm/mga/mga_drv.h @@ -195,29 +195,10 @@ extern long mga_compat_ioctl(struct file *filp, unsigned int cmd, #define mga_flush_write_combine() DRM_WRITEMEMORYBARRIER() -#if defined(__linux__) && defined(__alpha__) -#define MGA_BASE(reg) ((unsigned long)(dev_priv->mmio->handle)) -#define MGA_ADDR(reg) (MGA_BASE(reg) + reg) - -#define MGA_DEREF(reg) (*(volatile u32 *)MGA_ADDR(reg)) -#define MGA_DEREF8(reg) (*(volatile u8 *)MGA_ADDR(reg)) - -#define MGA_READ(reg) (_MGA_READ((u32 *)MGA_ADDR(reg))) -#define MGA_READ8(reg) (_MGA_READ((u8 *)MGA_ADDR(reg))) -#define MGA_WRITE(reg, val) do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF(reg) = val; } while (0) -#define MGA_WRITE8(reg, val) do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF8(reg) = val; } while (0) - -static inline u32 _MGA_READ(u32 *addr) -{ - DRM_MEMORYBARRIER(); - return *(volatile u32 *)addr; -} -#else #define MGA_READ8(reg) DRM_READ8(dev_priv->mmio, (reg)) #define MGA_READ(reg) DRM_READ32(dev_priv->mmio, (reg)) #define MGA_WRITE8(reg, val) DRM_WRITE8(dev_priv->mmio, (reg), (val)) #define MGA_WRITE(reg, val) DRM_WRITE32(dev_priv->mmio, (reg), (val)) -#endif #define DWGREG0 0x1c00 #define DWGREG0_END 0x1dff -- cgit v1.2.3-18-g5258 From 7ad35cf288fd63a19bf50e490440a992de808b2b Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 25 May 2011 14:00:49 +1000 Subject: x86/uv/x2apic: update for change in pci bridge handling. When I added 3448a19da479b6bd1e28e2a2be9fa16c6a6feb39 I forgot about the special uv handling code for this, so this patch fixes it up. Acked-by: Jesse Barnes Acked-by: Ingo Molnar Signed-off-by: Dave Airlie --- arch/x86/kernel/apic/x2apic_uv_x.c | 8 ++++---- drivers/pci/pci.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index b511a011b7d..adc66c3a1fe 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -632,14 +632,14 @@ late_initcall(uv_init_heartbeat); /* Direct Legacy VGA I/O traffic to designated IOH */ int uv_set_vga_state(struct pci_dev *pdev, bool decode, - unsigned int command_bits, bool change_bridge) + unsigned int command_bits, u32 flags) { int domain, bus, rc; - PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n", - pdev->devfn, decode, command_bits, change_bridge); + PR_DEVEL("devfn %x decode %d cmd %x flags %d\n", + pdev->devfn, decode, command_bits, flags); - if (!change_bridge) + if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) return 0; if ((command_bits & PCI_COMMAND_IO) == 0) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 56098b3e17c..5f10c23dff9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3271,11 +3271,11 @@ void __init pci_register_set_vga_state(arch_set_vga_state_t func) } static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode, - unsigned int command_bits, bool change_bridge) + unsigned int command_bits, u32 flags) { if (arch_set_vga_state) return arch_set_vga_state(dev, decode, command_bits, - change_bridge); + flags); return 0; } -- cgit v1.2.3-18-g5258 From ab21e60beaa96f2c55604f633dfe74076c531df7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 6 Jun 2011 12:53:30 -0400 Subject: drm/radeon/kms: fix mac g5 quirk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apple uses the same subsystem pci ids for lots of hardware much of which is wired up differently. In this case, the G5 imac and the G5 tower. Only apply the quirk configuration to G5 towers. Reported-by: Joachim Henke Signed-off-by: Alex Deucher Cc: Joachim Henke Cc: Michel Dänzer Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_combios.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index d1b95b70af6..797c8bcbb6a 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -1553,9 +1553,8 @@ bool radeon_get_legacy_connector_info_from_table(struct drm_device *dev) (rdev->pdev->subsystem_device == 0x4a48)) { /* Mac X800 */ rdev->mode_info.connector_table = CT_MAC_X800; - } else if ((rdev->pdev->device == 0x4150) && - (rdev->pdev->subsystem_vendor == 0x1002) && - (rdev->pdev->subsystem_device == 0x4150)) { + } else if (of_machine_is_compatible("PowerMac7,2") || + of_machine_is_compatible("PowerMac7,3")) { /* Mac G5 9600 */ rdev->mode_info.connector_table = CT_MAC_G5_9600; } else -- cgit v1.2.3-18-g5258 From a27bb4b209dd6c327fa4e7185f2487f9508a58db Mon Sep 17 00:00:00 2001 From: Marek Olšák Date: Fri, 10 Jun 2011 14:41:26 +0000 Subject: drm/radeon/kms: do bounds checking for 3D_LOAD_VBPNTR and bump array limit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To my knowledge, the limit is 16 on r300. (the docs don't say what the limit is) The lack of bounds checking can be abused to do all sorts of things (from bypassing parts of the CS checker to crashing the kernel). Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=36745 Cc: stable@kernel.org Signed-off-by: Marek Olšák Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/r100_track.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/r100_track.h b/drivers/gpu/drm/radeon/r100_track.h index 2fef9de7f36..686f9dc5d4b 100644 --- a/drivers/gpu/drm/radeon/r100_track.h +++ b/drivers/gpu/drm/radeon/r100_track.h @@ -63,7 +63,7 @@ struct r100_cs_track { unsigned num_arrays; unsigned max_indx; unsigned color_channel_mask; - struct r100_cs_track_array arrays[11]; + struct r100_cs_track_array arrays[16]; struct r100_cs_track_cb cb[R300_MAX_CB]; struct r100_cs_track_cb zb; struct r100_cs_track_cb aa; @@ -146,6 +146,12 @@ static inline int r100_packet3_load_vbpntr(struct radeon_cs_parser *p, ib = p->ib->ptr; track = (struct r100_cs_track *)p->track; c = radeon_get_ib_value(p, idx++) & 0x1F; + if (c > 16) { + DRM_ERROR("Only 16 vertex buffers are allowed %d\n", + pkt->opcode); + r100_cs_dump_packet(p, pkt); + return -EINVAL; + } track->num_arrays = c; for (i = 0; i < (c - 1); i+=2, idx+=3) { r = r100_cs_packet_next_reloc(p, &reloc); -- cgit v1.2.3-18-g5258 From b65552f06ca866f587a0a50d1f4dbdd3a00ec532 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Sun, 12 Jun 2011 20:53:44 +0000 Subject: drm/i915: Don't leak in i915_gem_shmem_pread_slow() It seems to me that we are leaking 'user_pages' in drivers/gpu/drm/i915/i915_gem.c::i915_gem_shmem_pread_slow() if read_cache_page_gfp() fails. Signed-off-by: Jesper Juhl Signed-off-by: Chris Wilson Signed-off-by: Dave Airlie --- drivers/gpu/drm/i915/i915_gem.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 12d32579b95..94c84d74410 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -465,8 +465,10 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, GFP_HIGHUSER | __GFP_RECLAIMABLE); - if (IS_ERR(page)) - return PTR_ERR(page); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto out; + } if (do_bit17_swizzling) { slow_shmem_bit17_copy(page, -- cgit v1.2.3-18-g5258 From 66aa6962ff520804f9874e57ea97995153f499d8 Mon Sep 17 00:00:00 2001 From: Tormod Volden Date: Mon, 30 May 2011 19:45:43 +0000 Subject: drm: Compare only lower 32 bits of framebuffer map offsets Drivers using multiple framebuffers got broken by commit 41c2e75e60200a860a74b7c84a6375c105e7437f which ignored the framebuffer (or register) map offset when looking for existing maps. The rationale was that the kernel-userspace ABI is fixed at a 32-bit offset, so the real offsets could not always be handed over for comparison. Instead of ignoring the offset we will compare the lower 32 bit. Drivers using multiple framebuffers should just make sure that the lower 32 bit are different. The existing drivers in question are practically limited to 32-bit systems so that should be fine for them. It is assumed that current drivers always specify a correct framebuffer map offset, even if this offset was ignored since above commit. So this patch should not change anything for drivers using only one framebuffer. Drivers needing multiple framebuffers with 64-bit map offsets will need to cook up something, for instance keeping an ID in the lower bit which is to be aligned away when it comes to using the offset. All of above applies to _DRM_REGISTERS as well. Signed-off-by: Tormod Volden Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_bufs.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c index e1bd713d91a..61e1ef90d4e 100644 --- a/drivers/gpu/drm/drm_bufs.c +++ b/drivers/gpu/drm/drm_bufs.c @@ -46,10 +46,11 @@ static struct drm_map_list *drm_find_matching_map(struct drm_device *dev, list_for_each_entry(entry, &dev->maplist, head) { /* * Because the kernel-userspace ABI is fixed at a 32-bit offset - * while PCI resources may live above that, we ignore the map - * offset for maps of type _DRM_FRAMEBUFFER or _DRM_REGISTERS. - * It is assumed that each driver will have only one resource of - * each type. + * while PCI resources may live above that, we only compare the + * lower 32 bits of the map offset for maps of type + * _DRM_FRAMEBUFFER or _DRM_REGISTERS. + * It is assumed that if a driver have more than one resource + * of each type, the lower 32 bits are different. */ if (!entry->map || map->type != entry->map->type || @@ -59,9 +60,12 @@ static struct drm_map_list *drm_find_matching_map(struct drm_device *dev, case _DRM_SHM: if (map->flags != _DRM_CONTAINS_LOCK) break; + return entry; case _DRM_REGISTERS: case _DRM_FRAME_BUFFER: - return entry; + if ((entry->map->offset & 0xffffffff) == + (map->offset & 0xffffffff)) + return entry; default: /* Make gcc happy */ ; } -- cgit v1.2.3-18-g5258 From dab104a73694b06fe4a162cb39d678716da62a67 Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Thu, 2 Jun 2011 14:09:32 +1000 Subject: m68knommu: fix linker script exported name sections The recent commit titled "module: Sort exported symbols" (f02e8a65) changed the exported symbol name sections. Bring the m68knommu linker script into line with those changes - including the sorting of the symbol names. Signed-off-by: Greg Ungerer --- arch/m68k/kernel/vmlinux.lds_no.S | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/m68k/kernel/vmlinux.lds_no.S b/arch/m68k/kernel/vmlinux.lds_no.S index f4d715cdca0..7dc4087a954 100644 --- a/arch/m68k/kernel/vmlinux.lds_no.S +++ b/arch/m68k/kernel/vmlinux.lds_no.S @@ -84,52 +84,52 @@ SECTIONS { /* Kernel symbol table: Normal symbols */ . = ALIGN(4); __start___ksymtab = .; - *(__ksymtab) + *(SORT(___ksymtab+*)) __stop___ksymtab = .; /* Kernel symbol table: GPL-only symbols */ __start___ksymtab_gpl = .; - *(__ksymtab_gpl) + *(SORT(___ksymtab_gpl+*)) __stop___ksymtab_gpl = .; /* Kernel symbol table: Normal unused symbols */ __start___ksymtab_unused = .; - *(__ksymtab_unused) + *(SORT(___ksymtab_unused+*)) __stop___ksymtab_unused = .; /* Kernel symbol table: GPL-only unused symbols */ __start___ksymtab_unused_gpl = .; - *(__ksymtab_unused_gpl) + *(SORT(___ksymtab_unused_gpl+*)) __stop___ksymtab_unused_gpl = .; /* Kernel symbol table: GPL-future symbols */ __start___ksymtab_gpl_future = .; - *(__ksymtab_gpl_future) + *(SORT(___ksymtab_gpl_future+*)) __stop___ksymtab_gpl_future = .; /* Kernel symbol table: Normal symbols */ __start___kcrctab = .; - *(__kcrctab) + *(SORT(___kcrctab+*)) __stop___kcrctab = .; /* Kernel symbol table: GPL-only symbols */ __start___kcrctab_gpl = .; - *(__kcrctab_gpl) + *(SORT(___kcrctab_gpl+*)) __stop___kcrctab_gpl = .; /* Kernel symbol table: Normal unused symbols */ __start___kcrctab_unused = .; - *(__kcrctab_unused) + *(SORT(___kcrctab_unused+*)) __stop___kcrctab_unused = .; /* Kernel symbol table: GPL-only unused symbols */ __start___kcrctab_unused_gpl = .; - *(__kcrctab_unused_gpl) + *(SORT(___kcrctab_unused_gpl+*)) __stop___kcrctab_unused_gpl = .; /* Kernel symbol table: GPL-future symbols */ __start___kcrctab_gpl_future = .; - *(__kcrctab_gpl_future) + *(SORT(___kcrctab_gpl_future+*)) __stop___kcrctab_gpl_future = .; /* Kernel symbol table: strings */ -- cgit v1.2.3-18-g5258 From 62356725987fa44bbebeb656b2a0d8c803e32ef2 Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Thu, 2 Jun 2011 15:50:48 +1000 Subject: m68knommu: create config options for CPU classes There are 3 families of CPU core types that we support in the m68knommu architecture branch. They are . traditional 68000 . CPU32 (a 68020 core derivative without MMU or bitfield instructions) . ColdFire It will be useful going forward to have a CONFIG_ option defined for each type. We already have one for ColdFire (CONFIG_COLDFIRE), so add for the other 2 families, CONFIG_M68000 and CONFIG_MCPU32. Signed-off-by: Greg Ungerer --- arch/m68k/Kconfig.nommu | 52 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 45 insertions(+), 7 deletions(-) diff --git a/arch/m68k/Kconfig.nommu b/arch/m68k/Kconfig.nommu index fc98f9b9d4d..b004dc1b171 100644 --- a/arch/m68k/Kconfig.nommu +++ b/arch/m68k/Kconfig.nommu @@ -14,6 +14,33 @@ config GENERIC_CLOCKEVENTS bool default n +config M68000 + bool + help + The Freescale (was Motorola) 68000 CPU is the first generation of + the well known M68K family of processors. The CPU core as well as + being available as a stand alone CPU was also used in many + System-On-Chip devices (eg 68328, 68302, etc). It does not contain + a paging MMU. + +config MCPU32 + bool + help + The Freescale (was then Motorola) CPU32 is a CPU core that is + based on the 68020 processor. For the most part it is used in + System-On-Chip parts, and does not contain a paging MMU. + +config COLDFIRE + bool + select GENERIC_GPIO + select ARCH_REQUIRE_GPIOLIB + help + The Freescale ColdFire family of processors is a modern derivitive + of the 68000 processor family. They are mainly targeted at embedded + applications, and are all System-On-Chip (SOC) devices, as opposed + to stand alone CPUs. They implement a subset of the original 68000 + processor instruction set. + config COLDFIRE_SW_A7 bool default n @@ -36,26 +63,31 @@ choice config M68328 bool "MC68328" + select M68000 help Motorola 68328 processor support. config M68EZ328 bool "MC68EZ328" + select M68000 help Motorola 68EX328 processor support. config M68VZ328 bool "MC68VZ328" + select M68000 help Motorola 68VZ328 processor support. config M68360 bool "MC68360" + select MCPU32 help Motorola 68360 processor support. config M5206 bool "MCF5206" + select COLDFIRE select COLDFIRE_SW_A7 select HAVE_MBAR help @@ -63,6 +95,7 @@ config M5206 config M5206e bool "MCF5206e" + select COLDFIRE select COLDFIRE_SW_A7 select HAVE_MBAR help @@ -70,6 +103,7 @@ config M5206e config M520x bool "MCF520x" + select COLDFIRE select GENERIC_CLOCKEVENTS select HAVE_CACHE_SPLIT help @@ -77,6 +111,7 @@ config M520x config M523x bool "MCF523x" + select COLDFIRE select GENERIC_CLOCKEVENTS select HAVE_CACHE_SPLIT select HAVE_IPSBAR @@ -85,6 +120,7 @@ config M523x config M5249 bool "MCF5249" + select COLDFIRE select COLDFIRE_SW_A7 select HAVE_MBAR help @@ -92,6 +128,7 @@ config M5249 config M5271 bool "MCF5271" + select COLDFIRE select HAVE_CACHE_SPLIT select HAVE_IPSBAR help @@ -99,6 +136,7 @@ config M5271 config M5272 bool "MCF5272" + select COLDFIRE select COLDFIRE_SW_A7 select HAVE_MBAR help @@ -106,6 +144,7 @@ config M5272 config M5275 bool "MCF5275" + select COLDFIRE select HAVE_CACHE_SPLIT select HAVE_IPSBAR help @@ -113,6 +152,7 @@ config M5275 config M528x bool "MCF528x" + select COLDFIRE select GENERIC_CLOCKEVENTS select HAVE_CACHE_SPLIT select HAVE_IPSBAR @@ -121,6 +161,7 @@ config M528x config M5307 bool "MCF5307" + select COLDFIRE select COLDFIRE_SW_A7 select HAVE_CACHE_CB select HAVE_MBAR @@ -129,12 +170,14 @@ config M5307 config M532x bool "MCF532x" + select COLDFIRE select HAVE_CACHE_CB help Freescale (Motorola) ColdFire 532x processor support. config M5407 bool "MCF5407" + select COLDFIRE select COLDFIRE_SW_A7 select HAVE_CACHE_CB select HAVE_MBAR @@ -143,6 +186,7 @@ config M5407 config M547x bool "MCF547x" + select COLDFIRE select HAVE_CACHE_CB select HAVE_MBAR help @@ -150,6 +194,7 @@ config M547x config M548x bool "MCF548x" + select COLDFIRE select HAVE_CACHE_CB select HAVE_MBAR help @@ -168,13 +213,6 @@ config M54xx depends on (M548x || M547x) default y -config COLDFIRE - bool - depends on (M5206 || M5206e || M520x || M523x || M5249 || M527x || M5272 || M528x || M5307 || M532x || M5407 || M54xx) - select GENERIC_GPIO - select ARCH_REQUIRE_GPIOLIB - default y - config CLOCK_SET bool "Enable setting the CPU clock frequency" default n -- cgit v1.2.3-18-g5258 From 734c3ce3bd4d51c932893b9f6d32b9ded31acdff Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Thu, 2 Jun 2011 16:07:33 +1000 Subject: m68k: use kernel processor defines for conditional optimizations Older m68k-linux compilers will include pre-defined symbols that confuse what processor it is being targeted for. For example gcc-4.1.2 will pre-define __mc68020__ even if you specify the target processor as -m68000 on the gcc command line. Newer versions of gcc have this corrected. In a few places the m68k code uses defined(__mc68020__) for optimizations that include instructions that are specific to the CPU 68020 and above. When compiling with older compilers this will be true even when we have selected to compile for the older 68000 processors. Switch to using the kernel processor defines, CONFIG_M68020 and friends. Signed-off-by: Greg Ungerer --- arch/m68k/kernel/m68k_ksyms.c | 3 +-- arch/m68k/lib/memcpy.c | 9 ++++----- arch/m68k/lib/memset.c | 9 ++++----- arch/m68k/lib/muldi3.c | 21 ++++++++++----------- 4 files changed, 19 insertions(+), 23 deletions(-) diff --git a/arch/m68k/kernel/m68k_ksyms.c b/arch/m68k/kernel/m68k_ksyms.c index 33f82769547..1b7a14d1a00 100644 --- a/arch/m68k/kernel/m68k_ksyms.c +++ b/arch/m68k/kernel/m68k_ksyms.c @@ -14,8 +14,7 @@ EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__muldi3); -#if !defined(__mc68020__) && !defined(__mc68030__) && \ - !defined(__mc68040__) && !defined(__mc68060__) && !defined(__mcpu32__) +#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE) /* * Simpler 68k and ColdFire parts also need a few other gcc functions. */ diff --git a/arch/m68k/lib/memcpy.c b/arch/m68k/lib/memcpy.c index 62182c81e91..06488931697 100644 --- a/arch/m68k/lib/memcpy.c +++ b/arch/m68k/lib/memcpy.c @@ -34,8 +34,10 @@ void *memcpy(void *to, const void *from, size_t n) if (temp) { long *lto = to; const long *lfrom = from; -#if defined(__mc68020__) || defined(__mc68030__) || \ - defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__) +#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE) + for (; temp; temp--) + *lto++ = *lfrom++; +#else asm volatile ( " movel %2,%3\n" " andw #7,%3\n" @@ -56,9 +58,6 @@ void *memcpy(void *to, const void *from, size_t n) " jpl 4b" : "=a" (lfrom), "=a" (lto), "=d" (temp), "=&d" (temp1) : "0" (lfrom), "1" (lto), "2" (temp)); -#else - for (; temp; temp--) - *lto++ = *lfrom++; #endif to = lto; from = lfrom; diff --git a/arch/m68k/lib/memset.c b/arch/m68k/lib/memset.c index f649e6a2e64..8a7639f0a2f 100644 --- a/arch/m68k/lib/memset.c +++ b/arch/m68k/lib/memset.c @@ -32,8 +32,10 @@ void *memset(void *s, int c, size_t count) temp = count >> 2; if (temp) { long *ls = s; -#if defined(__mc68020__) || defined(__mc68030__) || \ - defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__) +#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE) + for (; temp; temp--) + *ls++ = c; +#else size_t temp1; asm volatile ( " movel %1,%2\n" @@ -55,9 +57,6 @@ void *memset(void *s, int c, size_t count) " jpl 1b" : "=a" (ls), "=d" (temp), "=&d" (temp1) : "d" (c), "0" (ls), "1" (temp)); -#else - for (; temp; temp--) - *ls++ = c; #endif s = ls; } diff --git a/arch/m68k/lib/muldi3.c b/arch/m68k/lib/muldi3.c index 079bafca073..79e928a525d 100644 --- a/arch/m68k/lib/muldi3.c +++ b/arch/m68k/lib/muldi3.c @@ -19,17 +19,7 @@ along with GNU CC; see the file COPYING. If not, write to the Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -#if defined(__mc68020__) || defined(__mc68030__) || \ - defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__) - -#define umul_ppmm(w1, w0, u, v) \ - __asm__ ("mulu%.l %3,%1:%0" \ - : "=d" ((USItype)(w0)), \ - "=d" ((USItype)(w1)) \ - : "%0" ((USItype)(u)), \ - "dmi" ((USItype)(v))) - -#else +#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE) #define SI_TYPE_SIZE 32 #define __BITS4 (SI_TYPE_SIZE / 4) @@ -61,6 +51,15 @@ Boston, MA 02111-1307, USA. */ (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \ } while (0) +#else + +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("mulu%.l %3,%1:%0" \ + : "=d" ((USItype)(w0)), \ + "=d" ((USItype)(w1)) \ + : "%0" ((USItype)(u)), \ + "dmi" ((USItype)(v))) + #endif #define __umulsidi3(u, v) \ -- cgit v1.2.3-18-g5258 From 9b2dc8b665932a8e681a7ab3237f60475e75e161 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 13 Jun 2011 14:48:22 +0900 Subject: md/raid5: fix raid5_set_bi_hw_segments The @bio->bi_phys_segments consists of active stripes count in the lower 16 bits and processed stripes count in the upper 16 bits. So logical-OR operator should be bitwise one. This bug has been present since 2.6.27 and the fix is suitable for any -stable kernel since then. Fortunately the bad code is only used on error paths and is relatively unlikely to be hit. Cc: stable@kernel.org Signed-off-by: Namhyung Kim Signed-off-by: NeilBrown --- drivers/md/raid5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f9d2fbc6497..af8a9a89e4d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -129,7 +129,7 @@ static inline int raid5_dec_bi_hw_segments(struct bio *bio) static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt) { - bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16); + bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16); } /* Find first data disk in a raid6 stripe */ -- cgit v1.2.3-18-g5258 From b062962edb086011e94ec4d9eb3f6a6d814f2a8f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Jun 2011 14:20:19 +1000 Subject: md/raid5: fix FUA request handling in ops_run_io() Commit e9c7469bb4f5 ("md: implment REQ_FLUSH/FUA support") introduced R5_WantFUA flag and set rw to WRITE_FUA in that case. However remaining code still checks whether rw is exactly same as WRITE or not, so FUAed-write ends up with being treated as READ. Fix it. This bug has been present since 2.6.37 and the fix is suitable for any -stable kernel since then. It is not clear why this has not caused more problems. Cc: Tejun Heo Cc: stable@kernel.org Signed-off-by: Namhyung Kim Signed-off-by: NeilBrown --- drivers/md/raid5.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index af8a9a89e4d..b7dcc677dda 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -514,7 +514,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) bi = &sh->dev[i].req; bi->bi_rw = rw; - if (rw == WRITE) + if (rw & WRITE) bi->bi_end_io = raid5_end_write_request; else bi->bi_end_io = raid5_end_read_request; @@ -548,13 +548,13 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) bi->bi_io_vec[0].bv_offset = 0; bi->bi_size = STRIPE_SIZE; bi->bi_next = NULL; - if (rw == WRITE && + if ((rw & WRITE) && test_bit(R5_ReWrite, &sh->dev[i].flags)) atomic_add(STRIPE_SECTORS, &rdev->corrected_errors); generic_make_request(bi); } else { - if (rw == WRITE) + if (rw & WRITE) set_bit(STRIPE_DEGRADED, &sh->state); pr_debug("skip op %ld on disc %d for sector %llu\n", bi->bi_rw, i, (unsigned long long)sh->sector); -- cgit v1.2.3-18-g5258 From fcde90759a985d8bfa4391346a821cc12fc16207 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Jun 2011 14:23:57 +1000 Subject: md/raid5: remove unusual use of bio_iovec_idx() In the bio_for_each_segment loop, bvl always points current bio_vec, so the same as bio_iovec_idx(, i). Let's get rid of it. Cc: Dan Williams Signed-off-by: Namhyung Kim Signed-off-by: NeilBrown --- drivers/md/raid5.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index b7dcc677dda..b72edf35ec5 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -585,7 +585,7 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, init_async_submit(&submit, flags, tx, NULL, NULL, NULL); bio_for_each_segment(bvl, bio, i) { - int len = bio_iovec_idx(bio, i)->bv_len; + int len = bvl->bv_len; int clen; int b_offset = 0; @@ -601,8 +601,8 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, clen = len; if (clen > 0) { - b_offset += bio_iovec_idx(bio, i)->bv_offset; - bio_page = bio_iovec_idx(bio, i)->bv_page; + b_offset += bvl->bv_offset; + bio_page = bvl->bv_page; if (frombio) tx = async_memcpy(page, bio_page, page_offset, b_offset, clen, &submit); -- cgit v1.2.3-18-g5258 From 4e78c724d47e2342aa8fde61f6b8536f662f795f Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 13 Jun 2011 13:49:11 +0900 Subject: TOMOYO: Fix oops in tomoyo_mount_acl(). In tomoyo_mount_acl() since 2.6.36, kern_path() was called without checking dev_name != NULL. As a result, an unprivileged user can trigger oops by issuing mount(NULL, "/", "ext3", 0, NULL) request. Fix this by checking dev_name != NULL before calling kern_path(dev_name). Signed-off-by: Tetsuo Handa Cc: stable@kernel.org Signed-off-by: James Morris --- security/tomoyo/mount.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/tomoyo/mount.c b/security/tomoyo/mount.c index 162a864dba2..9fc2e15841c 100644 --- a/security/tomoyo/mount.c +++ b/security/tomoyo/mount.c @@ -138,7 +138,7 @@ static int tomoyo_mount_acl(struct tomoyo_request_info *r, char *dev_name, } if (need_dev) { /* Get mount point or device file. */ - if (kern_path(dev_name, LOOKUP_FOLLOW, &path)) { + if (!dev_name || kern_path(dev_name, LOOKUP_FOLLOW, &path)) { error = -ENOENT; goto out; } -- cgit v1.2.3-18-g5258 From 7bbf1d46b28455aed6aa6df772b91d51408c6c81 Mon Sep 17 00:00:00 2001 From: Hans-Christian Egtvedt Date: Wed, 1 Jun 2011 11:08:01 +0200 Subject: avr32: fix use of non-existing portnr variable in at32_map_usart() This patch fixes the use of the non-existing portnr variable in at32_map_usart() to use the provided line number instead. Typo was introduced in commit 2b348e2f82f532e3aff8e0ce9293033b3294c1e0. Signed-off-by: Hans-Christian Egtvedt --- arch/avr32/mach-at32ap/at32ap700x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index aa677e2a382..1b7ad97524b 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1044,7 +1044,7 @@ void __init at32_map_usart(unsigned int hw_id, unsigned int line, int flags) } pdata = pdev->dev.platform_data; - pdata->num = portnr; + pdata->num = line; at32_usarts[line] = pdev; } -- cgit v1.2.3-18-g5258 From 4137b31566fd112c8e2d9d4701de5e7a000bcc2d Mon Sep 17 00:00:00 2001 From: Hans-Christian Egtvedt Date: Wed, 8 Jun 2011 10:47:25 +0200 Subject: avr32/at32ap: fix mapping of platform device id for USART This patch will fix the mapping of the platform device id when mapping USART peripheral ID to UART platform device id. Not setting the platform device id will in most cases (when you map USART > 0 to UART 0) make the console not available. Signed-off-by: Hans-Christian Egtvedt --- arch/avr32/mach-at32ap/at32ap700x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index 1b7ad97524b..7fbf0dcb9af 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1043,6 +1043,7 @@ void __init at32_map_usart(unsigned int hw_id, unsigned int line, int flags) data->regs = (void __iomem *)pdev->resource[0].start; } + pdev->id = line; pdata = pdev->dev.platform_data; pdata->num = line; at32_usarts[line] = pdev; -- cgit v1.2.3-18-g5258 From a527a1453dd6dd89f07f1e5b2d24fc6559922461 Mon Sep 17 00:00:00 2001 From: Hans-Christian Egtvedt Date: Wed, 1 Jun 2011 15:10:49 +0200 Subject: avr32: set CONFIG_CC_OPTIMIZE_FOR_SIZE=y for all defconfigs This patch makes sure the kconfig option CC_OPTIMIZE_FOR_SIZE is set to yes for all default configuration files. This ensures the kernel is optimized for size, and avoids potential relocation truncated to fit problems. Signed-off-by: Hans-Christian Egtvedt --- arch/avr32/configs/atngw100_defconfig | 1 + arch/avr32/configs/atngw100_evklcd100_defconfig | 1 + arch/avr32/configs/atngw100_evklcd101_defconfig | 1 + arch/avr32/configs/atngw100_mrmt_defconfig | 1 + arch/avr32/configs/atngw100mkii_defconfig | 1 + arch/avr32/configs/atngw100mkii_evklcd100_defconfig | 1 + arch/avr32/configs/atngw100mkii_evklcd101_defconfig | 1 + arch/avr32/configs/atstk1002_defconfig | 1 + arch/avr32/configs/atstk1003_defconfig | 1 + arch/avr32/configs/atstk1004_defconfig | 1 + arch/avr32/configs/atstk1006_defconfig | 1 + arch/avr32/configs/favr-32_defconfig | 1 + arch/avr32/configs/hammerhead_defconfig | 1 + arch/avr32/configs/merisc_defconfig | 1 + arch/avr32/configs/mimc200_defconfig | 1 + 15 files changed, 15 insertions(+) diff --git a/arch/avr32/configs/atngw100_defconfig b/arch/avr32/configs/atngw100_defconfig index 6f9ca56de1f..a06bfccc284 100644 --- a/arch/avr32/configs/atngw100_defconfig +++ b/arch/avr32/configs/atngw100_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atngw100_evklcd100_defconfig b/arch/avr32/configs/atngw100_evklcd100_defconfig index 7eece0af34c..d8f1fe80d21 100644 --- a/arch/avr32/configs/atngw100_evklcd100_defconfig +++ b/arch/avr32/configs/atngw100_evklcd100_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atngw100_evklcd101_defconfig b/arch/avr32/configs/atngw100_evklcd101_defconfig index 387eb9d6e42..d4c5b19ec95 100644 --- a/arch/avr32/configs/atngw100_evklcd101_defconfig +++ b/arch/avr32/configs/atngw100_evklcd101_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atngw100_mrmt_defconfig b/arch/avr32/configs/atngw100_mrmt_defconfig index 19f6ceeeff7..6cb786c0baf 100644 --- a/arch/avr32/configs/atngw100_mrmt_defconfig +++ b/arch/avr32/configs/atngw100_mrmt_defconfig @@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_SLUB_DEBUG is not set diff --git a/arch/avr32/configs/atngw100mkii_defconfig b/arch/avr32/configs/atngw100mkii_defconfig index f0fe237133a..6e0dca4d313 100644 --- a/arch/avr32/configs/atngw100mkii_defconfig +++ b/arch/avr32/configs/atngw100mkii_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atngw100mkii_evklcd100_defconfig b/arch/avr32/configs/atngw100mkii_evklcd100_defconfig index e4a7c1dc838..7f2a344a5fa 100644 --- a/arch/avr32/configs/atngw100mkii_evklcd100_defconfig +++ b/arch/avr32/configs/atngw100mkii_evklcd100_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atngw100mkii_evklcd101_defconfig b/arch/avr32/configs/atngw100mkii_evklcd101_defconfig index 6f37f70c2c3..085eeba88f6 100644 --- a/arch/avr32/configs/atngw100mkii_evklcd101_defconfig +++ b/arch/avr32/configs/atngw100mkii_evklcd101_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atstk1002_defconfig b/arch/avr32/configs/atstk1002_defconfig index 4fb01f5ab42..d1a887e6405 100644 --- a/arch/avr32/configs/atstk1002_defconfig +++ b/arch/avr32/configs/atstk1002_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atstk1003_defconfig b/arch/avr32/configs/atstk1003_defconfig index 9faaf9b900f..956f2819ad4 100644 --- a/arch/avr32/configs/atstk1003_defconfig +++ b/arch/avr32/configs/atstk1003_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atstk1004_defconfig b/arch/avr32/configs/atstk1004_defconfig index 3d2a5d85f97..40c69f38c61 100644 --- a/arch/avr32/configs/atstk1004_defconfig +++ b/arch/avr32/configs/atstk1004_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/atstk1006_defconfig b/arch/avr32/configs/atstk1006_defconfig index 1ed8f22d4fe..511eb8af356 100644 --- a/arch/avr32/configs/atstk1006_defconfig +++ b/arch/avr32/configs/atstk1006_defconfig @@ -5,6 +5,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/favr-32_defconfig b/arch/avr32/configs/favr-32_defconfig index aeadc955db3..19973b06170 100644 --- a/arch/avr32/configs/favr-32_defconfig +++ b/arch/avr32/configs/favr-32_defconfig @@ -6,6 +6,7 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/hammerhead_defconfig b/arch/avr32/configs/hammerhead_defconfig index 1692beeb7ed..6f45681196d 100644 --- a/arch/avr32/configs/hammerhead_defconfig +++ b/arch/avr32/configs/hammerhead_defconfig @@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/avr32/configs/merisc_defconfig b/arch/avr32/configs/merisc_defconfig index 8b670a6530b..3befab96682 100644 --- a/arch/avr32/configs/merisc_defconfig +++ b/arch/avr32/configs/merisc_defconfig @@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set CONFIG_MODULES=y diff --git a/arch/avr32/configs/mimc200_defconfig b/arch/avr32/configs/mimc200_defconfig index 5a51f2e7ffb..1bee51f2215 100644 --- a/arch/avr32/configs/mimc200_defconfig +++ b/arch/avr32/configs/mimc200_defconfig @@ -7,6 +7,7 @@ CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_BASE_FULL is not set # CONFIG_COMPAT_BRK is not set -- cgit v1.2.3-18-g5258 From 3000f0077a5745918830f40826c23fe5bf934b8b Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Sun, 15 May 2011 00:23:32 +0200 Subject: avr32: add some more at91 to cpu.h definition Somme common drivers will need those at91 cpu_is_xxx() definitions. Those definitions are already in Linus' tree so if we want to use them in common drivers, we will need them in AVR32 cpu.h file. Signed-off-by: Nicolas Ferre Acked-by: Hans-Christian Egtvedt --- arch/avr32/mach-at32ap/include/mach/cpu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/avr32/mach-at32ap/include/mach/cpu.h b/arch/avr32/mach-at32ap/include/mach/cpu.h index 9c96a130f3a..8181293115e 100644 --- a/arch/avr32/mach-at32ap/include/mach/cpu.h +++ b/arch/avr32/mach-at32ap/include/mach/cpu.h @@ -31,8 +31,20 @@ #define cpu_is_at91sam9263() (0) #define cpu_is_at91sam9rl() (0) #define cpu_is_at91cap9() (0) +#define cpu_is_at91cap9_revB() (0) +#define cpu_is_at91cap9_revC() (0) #define cpu_is_at91sam9g10() (0) +#define cpu_is_at91sam9g20() (0) #define cpu_is_at91sam9g45() (0) #define cpu_is_at91sam9g45es() (0) +#define cpu_is_at91sam9m10() (0) +#define cpu_is_at91sam9g46() (0) +#define cpu_is_at91sam9m11() (0) +#define cpu_is_at91sam9x5() (0) +#define cpu_is_at91sam9g15() (0) +#define cpu_is_at91sam9g35() (0) +#define cpu_is_at91sam9x35() (0) +#define cpu_is_at91sam9g25() (0) +#define cpu_is_at91sam9x25() (0) #endif /* __ASM_ARCH_CPU_H */ -- cgit v1.2.3-18-g5258 From c162755491f7ca9853cb9f2aaa3ff3677c1bda78 Mon Sep 17 00:00:00 2001 From: Hans-Christian Egtvedt Date: Mon, 6 Jun 2011 18:19:20 +0200 Subject: avr32: make intc_resume() return void to conform to syscore_ops This patch removes the unneeded, and now wrong, return 0 from intc_resume() and lets the function return void instead. This matches the resume callback in struct syscore_ops. Signed-off-by: Hans-Christian Egtvedt --- arch/avr32/mach-at32ap/intc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/avr32/mach-at32ap/intc.c b/arch/avr32/mach-at32ap/intc.c index 3e3646186c9..c9ac2f8e8f6 100644 --- a/arch/avr32/mach-at32ap/intc.c +++ b/arch/avr32/mach-at32ap/intc.c @@ -167,14 +167,12 @@ static int intc_suspend(void) return 0; } -static int intc_resume(void) +static void intc_resume(void) { int i; for (i = 0; i < 64; i++) intc_writel(&intc0, INTPR0 + 4 * i, intc0.saved_ipr[i]); - - return 0; } #else #define intc_suspend NULL -- cgit v1.2.3-18-g5258 From ff71db2f0784cfff38fa7b55908867a24ccc3216 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 10 Jun 2011 15:09:05 +0200 Subject: avr32, exec: remove redundant set_fs(USER_DS) The address limit is already set in flush_old_exec() so this set_fs(USER_DS) is redundant. Signed-off-by: Mathias Krause Signed-off-by: Hans-Christian Egtvedt --- arch/avr32/include/asm/processor.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h index 49a88f5a9d2..108502bc677 100644 --- a/arch/avr32/include/asm/processor.h +++ b/arch/avr32/include/asm/processor.h @@ -131,7 +131,6 @@ struct thread_struct { */ #define start_thread(regs, new_pc, new_sp) \ do { \ - set_fs(USER_DS); \ memset(regs, 0, sizeof(*regs)); \ regs->sr = MODE_USER; \ regs->pc = new_pc & ~1; \ -- cgit v1.2.3-18-g5258 From 040d15c86747cf44fcf6b8ee19d805d4ef20caf3 Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 14 Jun 2011 15:51:18 +0000 Subject: [CIFS] trivial cleanup fscache cFYI and cERROR messages ... for uniformity and cleaner debug logs. Signed-off-by: Suresh Jayaraman Signed-off-by: Steve French --- fs/cifs/cache.c | 6 +++--- fs/cifs/fscache.c | 51 ++++++++++++++++++++++++--------------------------- 2 files changed, 27 insertions(+), 30 deletions(-) diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index dd8584d35a1..545509c3313 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -92,7 +92,7 @@ static uint16_t cifs_server_get_key(const void *cookie_netfs_data, break; default: - cERROR(1, "CIFS: Unknown network family '%d'", sa->sa_family); + cERROR(1, "Unknown network family '%d'", sa->sa_family); key_len = 0; break; } @@ -152,7 +152,7 @@ static uint16_t cifs_super_get_key(const void *cookie_netfs_data, void *buffer, sharename = extract_sharename(tcon->treeName); if (IS_ERR(sharename)) { - cFYI(1, "CIFS: couldn't extract sharename\n"); + cFYI(1, "%s: couldn't extract sharename\n", __func__); sharename = NULL; return 0; } @@ -302,7 +302,7 @@ static void cifs_fscache_inode_now_uncached(void *cookie_netfs_data) pagevec_init(&pvec, 0); first = 0; - cFYI(1, "cifs inode 0x%p now uncached", cifsi); + cFYI(1, "%s: cifs inode 0x%p now uncached", __func__, cifsi); for (;;) { nr_pages = pagevec_lookup(&pvec, diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index d368a47ba5e..816696621ec 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -28,14 +28,14 @@ void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server) server->fscache = fscache_acquire_cookie(cifs_fscache_netfs.primary_index, &cifs_fscache_server_index_def, server); - cFYI(1, "CIFS: get client cookie (0x%p/0x%p)", server, - server->fscache); + cFYI(1, "%s: (0x%p/0x%p)", __func__, server, + server->fscache); } void cifs_fscache_release_client_cookie(struct TCP_Server_Info *server) { - cFYI(1, "CIFS: release client cookie (0x%p/0x%p)", server, - server->fscache); + cFYI(1, "%s: (0x%p/0x%p)", __func__, server, + server->fscache); fscache_relinquish_cookie(server->fscache, 0); server->fscache = NULL; } @@ -47,13 +47,13 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) tcon->fscache = fscache_acquire_cookie(server->fscache, &cifs_fscache_super_index_def, tcon); - cFYI(1, "CIFS: get superblock cookie (0x%p/0x%p)", - server->fscache, tcon->fscache); + cFYI(1, "%s: (0x%p/0x%p)", __func__, server->fscache, + tcon->fscache); } void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) { - cFYI(1, "CIFS: releasing superblock cookie (0x%p)", tcon->fscache); + cFYI(1, "%s: (0x%p)", __func__, tcon->fscache); fscache_relinquish_cookie(tcon->fscache, 0); tcon->fscache = NULL; } @@ -70,8 +70,8 @@ static void cifs_fscache_enable_inode_cookie(struct inode *inode) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) { cifsi->fscache = fscache_acquire_cookie(tcon->fscache, &cifs_fscache_inode_object_def, cifsi); - cFYI(1, "CIFS: got FH cookie (0x%p/0x%p)", tcon->fscache, - cifsi->fscache); + cFYI(1, "%s: got FH cookie (0x%p/0x%p)", __func__, + tcon->fscache, cifsi->fscache); } } @@ -80,8 +80,7 @@ void cifs_fscache_release_inode_cookie(struct inode *inode) struct cifsInodeInfo *cifsi = CIFS_I(inode); if (cifsi->fscache) { - cFYI(1, "CIFS releasing inode cookie (0x%p)", - cifsi->fscache); + cFYI(1, "%s: (0x%p)", __func__, cifsi->fscache); fscache_relinquish_cookie(cifsi->fscache, 0); cifsi->fscache = NULL; } @@ -92,8 +91,7 @@ static void cifs_fscache_disable_inode_cookie(struct inode *inode) struct cifsInodeInfo *cifsi = CIFS_I(inode); if (cifsi->fscache) { - cFYI(1, "CIFS disabling inode cookie (0x%p)", - cifsi->fscache); + cFYI(1, "%s: (0x%p)", __func__, cifsi->fscache); fscache_relinquish_cookie(cifsi->fscache, 1); cifsi->fscache = NULL; } @@ -121,8 +119,8 @@ void cifs_fscache_reset_inode_cookie(struct inode *inode) cifs_sb_master_tcon(cifs_sb)->fscache, &cifs_fscache_inode_object_def, cifsi); - cFYI(1, "CIFS: new cookie 0x%p oldcookie 0x%p", - cifsi->fscache, old); + cFYI(1, "%s: new cookie 0x%p oldcookie 0x%p", + __func__, cifsi->fscache, old); } } @@ -132,8 +130,8 @@ int cifs_fscache_release_page(struct page *page, gfp_t gfp) struct inode *inode = page->mapping->host; struct cifsInodeInfo *cifsi = CIFS_I(inode); - cFYI(1, "CIFS: fscache release page (0x%p/0x%p)", - page, cifsi->fscache); + cFYI(1, "%s: (0x%p/0x%p)", __func__, page, + cifsi->fscache); if (!fscache_maybe_release_page(cifsi->fscache, page, gfp)) return 0; } @@ -144,8 +142,7 @@ int cifs_fscache_release_page(struct page *page, gfp_t gfp) static void cifs_readpage_from_fscache_complete(struct page *page, void *ctx, int error) { - cFYI(1, "CFS: readpage_from_fscache_complete (0x%p/%d)", - page, error); + cFYI(1, "%s: (0x%p/%d)", __func__, page, error); if (!error) SetPageUptodate(page); unlock_page(page); @@ -158,7 +155,7 @@ int __cifs_readpage_from_fscache(struct inode *inode, struct page *page) { int ret; - cFYI(1, "CIFS: readpage_from_fscache(fsc:%p, p:%p, i:0x%p", + cFYI(1, "%s: (fsc:%p, p:%p, i:0x%p", __func__, CIFS_I(inode)->fscache, page, inode); ret = fscache_read_or_alloc_page(CIFS_I(inode)->fscache, page, cifs_readpage_from_fscache_complete, @@ -167,11 +164,11 @@ int __cifs_readpage_from_fscache(struct inode *inode, struct page *page) switch (ret) { case 0: /* page found in fscache, read submitted */ - cFYI(1, "CIFS: readpage_from_fscache: submitted"); + cFYI(1, "%s: submitted", __func__); return ret; case -ENOBUFS: /* page won't be cached */ case -ENODATA: /* page not in cache */ - cFYI(1, "CIFS: readpage_from_fscache %d", ret); + cFYI(1, "%s: %d", __func__, ret); return 1; default: @@ -190,7 +187,7 @@ int __cifs_readpages_from_fscache(struct inode *inode, { int ret; - cFYI(1, "CIFS: __cifs_readpages_from_fscache (0x%p/%u/0x%p)", + cFYI(1, "%s: (0x%p/%u/0x%p)", __func__, CIFS_I(inode)->fscache, *nr_pages, inode); ret = fscache_read_or_alloc_pages(CIFS_I(inode)->fscache, mapping, pages, nr_pages, @@ -199,12 +196,12 @@ int __cifs_readpages_from_fscache(struct inode *inode, mapping_gfp_mask(mapping)); switch (ret) { case 0: /* read submitted to the cache for all pages */ - cFYI(1, "CIFS: readpages_from_fscache: submitted"); + cFYI(1, "%s: submitted", __func__); return ret; case -ENOBUFS: /* some pages are not cached and can't be */ case -ENODATA: /* some pages are not cached */ - cFYI(1, "CIFS: readpages_from_fscache: no page"); + cFYI(1, "%s: no page", __func__); return 1; default: @@ -218,7 +215,7 @@ void __cifs_readpage_to_fscache(struct inode *inode, struct page *page) { int ret; - cFYI(1, "CIFS: readpage_to_fscache(fsc: %p, p: %p, i: %p", + cFYI(1, "%s: (fsc: %p, p: %p, i: %p)", __func__, CIFS_I(inode)->fscache, page, inode); ret = fscache_write_page(CIFS_I(inode)->fscache, page, GFP_KERNEL); if (ret != 0) @@ -230,7 +227,7 @@ void __cifs_fscache_invalidate_page(struct page *page, struct inode *inode) struct cifsInodeInfo *cifsi = CIFS_I(inode); struct fscache_cookie *cookie = cifsi->fscache; - cFYI(1, "CIFS: fscache invalidatepage (0x%p/0x%p)", page, cookie); + cFYI(1, "%s: (0x%p/0x%p)", __func__, page, cookie); fscache_wait_on_page_write(cookie, page); fscache_uncache_page(cookie, page); } -- cgit v1.2.3-18-g5258 From 1252b3013b790c77e1c4f077a40542f86df37fb4 Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 14 Jun 2011 16:19:54 +0000 Subject: [CIFS] update cifs version to 1.73 Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 64313f778eb..0900e1658c9 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -129,5 +129,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "1.72" +#define CIFS_VERSION "1.73" #endif /* _CIFSFS_H */ -- cgit v1.2.3-18-g5258 From 60b8b1de0dd2bf246f0e074d287bb3f0bc42a755 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Tue, 14 Jun 2011 12:45:10 -0700 Subject: x86 idle: APM requires pm_idle/default_idle unconditionally when a module [ Also from Ben Hutchings and Vitaliy Ivanov ] Commit 06ae40ce073d ("x86 idle: EXPORT_SYMBOL(default_idle, pm_idle) only when APM demands it") removed the export for pm_idle/default_idle unless the apm module was modularised and CONFIG_APM_CPU_IDLE was set. But the apm module uses pm_idle/default_idle unconditionally, CONFIG_APM_CPU_IDLE only affects the bios idle threshold. Adjust the export accordingly. [ Used #ifdef instead of #if defined() as it's shorter, and what both Ben and Vitaliy used.. Andy, you're out-voted ;) - Linus ] Reported-by: Randy Dunlap Acked-by: Jiri Kosina Acked-by: Ingo Molnar Acked-by: Len Brown Signed-off-by: Andy Whitcroft Signed-off-by: Vitaliy Ivanov Signed-off-by: Ben Hutchings Signed-off-by: Linus Torvalds --- arch/x86/kernel/process.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2e4928d45a2..e1ba8cb24e4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -337,7 +337,7 @@ EXPORT_SYMBOL(boot_option_idle_override); * Powermanagement idle function, if any.. */ void (*pm_idle)(void); -#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE) +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(pm_idle); #endif @@ -399,7 +399,7 @@ void default_idle(void) cpu_relax(); } } -#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE) +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(default_idle); #endif -- cgit v1.2.3-18-g5258 From ada9c93312f7ec49514c68c211595ce2601cebae Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 14 Jun 2011 15:50:11 -0700 Subject: signal.c: fix kernel-doc notation Fix kernel-doc warnings in signal.c: Warning(kernel/signal.c:2374): No description found for parameter 'nset' Warning(kernel/signal.c:2374): Excess function parameter 'set' description in 'sys_rt_sigprocmask' Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/signal.c b/kernel/signal.c index 86c32b884f8..ff767860332 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2365,7 +2365,7 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) /** * sys_rt_sigprocmask - change the list of currently blocked signals * @how: whether to add, remove, or set signals - * @set: stores pending signals + * @nset: stores pending signals * @oset: previous value of signal mask if non-null * @sigsetsize: size of sigset_t type */ -- cgit v1.2.3-18-g5258 From 8dd0de8be31b4b966d17750a0b10df2f575c91ac Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Tue, 14 Jun 2011 18:36:24 -0400 Subject: sched: Fix need_resched() when checking peempt The RT preempt check tests the wrong task if NEED_RESCHED is set. It currently checks the local CPU task. It is supposed to check the task that is running on the runqueue we are about to wake another task on. Signed-off-by: Hillf Danton Reviewed-by: Yong Zhang Signed-off-by: Steven Rostedt Link: http://lkml.kernel.org/r/20110614223657.450239027@goodmis.org Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 88725c939e0..9b8d5dce946 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1096,7 +1096,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag * to move current somewhere else, making room for our non-migratable * task. */ - if (p->prio == rq->curr->prio && !need_resched()) + if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr)) check_preempt_equal_prio(rq, p); #endif } -- cgit v1.2.3-18-g5258 From 0da938c44921cfb690283d3b0c9c48a10375db2c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 14 Jun 2011 18:36:25 -0400 Subject: sched: Check if lowest_mask is initialized in find_lowest_rq() On system boot up, the lowest_mask is initialized with an early_initcall(). But RT tasks may wake up on other early_initcall() callers before the lowest_mask is initialized, causing a system crash. Commit "d72bce0e67 rcu: Cure load woes" was the first commit to wake up RT tasks in early init. Before this commit this bug should not happen. Reported-by: Andrew Theurer Tested-by: Andrew Theurer Tested-by: Paul E. McKenney Signed-off-by: Steven Rostedt Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110614223657.824872966@goodmis.org Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 9b8d5dce946..10d018212ba 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1239,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task) int this_cpu = smp_processor_id(); int cpu = task_cpu(task); + /* Make sure the mask is initialized first */ + if (unlikely(!lowest_mask)) + return -1; + if (task->rt.nr_cpus_allowed == 1) return -1; /* No other targets possible */ -- cgit v1.2.3-18-g5258 From f300ea499721ca208fc4714b9105bfd7e9f75be0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 15 Jun 2011 15:08:08 -0700 Subject: mm: remove khugepaged double thp vmstat update with CONFIG_NUMA=n Johannes noticed the vmstat update is already taken care of by khugepaged_alloc_hugepage() internally. The only places that are required to update the vmstat are the callers of alloc_hugepage (callers of khugepaged_alloc_hugepage aren't). Signed-off-by: Andrea Arcangeli Reported-by: Johannes Weiner Acked-by: Rik van Riel Reviewed-by: Minchan Kim Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 615d9743a3c..81532f297fd 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2234,11 +2234,8 @@ static void khugepaged_loop(void) while (likely(khugepaged_enabled())) { #ifndef CONFIG_NUMA hpage = khugepaged_alloc_hugepage(); - if (unlikely(!hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); + if (unlikely(!hpage)) break; - } - count_vm_event(THP_COLLAPSE_ALLOC); #else if (IS_ERR(hpage)) { khugepaged_alloc_sleep(); -- cgit v1.2.3-18-g5258 From 0164f69d0cf1a6abbc936851f5b72ece92187cda Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jun 2011 15:08:09 -0700 Subject: mm/memory.c: fix kernel-doc notation Fix new kernel-doc warnings in mm/memory.c: Warning(mm/memory.c:1327): No description found for parameter 'tlb' Warning(mm/memory.c:1327): Excess function parameter 'tlbp' description in 'unmap_vmas' Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 6953d3926e0..b13e7dbc399 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1296,7 +1296,7 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, /** * unmap_vmas - unmap a range of memory covered by a list of vma's - * @tlbp: address of the caller's struct mmu_gather + * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping -- cgit v1.2.3-18-g5258 From b0825ee3a8c570df4873ee397fa453e67fdad5d7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jun 2011 15:08:10 -0700 Subject: lib/bitmap.c: fix kernel-doc notation Fix new kernel-doc warnings in lib/bitmap.c: Warning(lib/bitmap.c:596): No description found for parameter 'buf' Warning(lib/bitmap.c:596): Excess function parameter 'bp' description in '__bitmap_parselist' Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/bitmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/bitmap.c b/lib/bitmap.c index 41baf02924e..3f3b68199d7 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -572,7 +572,7 @@ EXPORT_SYMBOL(bitmap_scnlistprintf); /** * __bitmap_parselist - convert list format ASCII string to bitmap - * @bp: read nul-terminated user string from this buffer + * @buf: read nul-terminated user string from this buffer * @buflen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @is_user: location of buffer, 0 indicates kernel space -- cgit v1.2.3-18-g5258 From 7f81c8890c15a10f5220bebae3b6dfae4961962a Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 15 Jun 2011 15:08:11 -0700 Subject: fs/exec.c: use BUILD_BUG_ON for VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP Commit a8bef8ff6ea1 ("mm: migration: avoid race between shift_arg_pages() and rmap_walk() during migration by not migrating temporary stacks") introduced a BUG_ON() to ensure that VM_STACK_FLAGS and VM_STACK_INCOMPLETE_SETUP do not overlap. The check is a compile time one, so BUILD_BUG_ON is more appropriate. Signed-off-by: Michal Hocko Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index 97e0d52d72f..b54f74f3cd8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -277,7 +277,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ - BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); + BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; -- cgit v1.2.3-18-g5258 From a59ec1e7ff98cc4365d5b1bff4e7102e86b5716b Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Wed, 15 Jun 2011 15:08:11 -0700 Subject: backlight: new driver for the ADP8870 backlight devices Signed-off-by: Michael Hennerich Signed-off-by: Mike Frysinger Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../testing/sysfs-class-backlight-driver-adp8870 | 56 ++ drivers/video/backlight/Kconfig | 12 + drivers/video/backlight/Makefile | 1 + drivers/video/backlight/adp8870_bl.c | 1011 ++++++++++++++++++++ include/linux/i2c/adp8870.h | 153 +++ 5 files changed, 1233 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 create mode 100644 drivers/video/backlight/adp8870_bl.c create mode 100644 include/linux/i2c/adp8870.h diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 new file mode 100644 index 00000000000..aa11dbdd794 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 @@ -0,0 +1,56 @@ +What: /sys/class/backlight//_max +What: /sys/class/backlight//l1_daylight_max +What: /sys/class/backlight//l2_bright_max +What: /sys/class/backlight//l3_office_max +What: /sys/class/backlight//l4_indoor_max +What: /sys/class/backlight//l5_dark_max +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Control the maximum brightness for + on this . Values are between 0 and 127. This file + will also show the brightness level stored for this + . + +What: /sys/class/backlight//_dim +What: /sys/class/backlight//l2_bright_dim +What: /sys/class/backlight//l3_office_dim +What: /sys/class/backlight//l4_indoor_dim +What: /sys/class/backlight//l5_dark_dim +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Control the dim brightness for + on this . Values are between 0 and 127, typically + set to 0. Full off when the backlight is disabled. + This file will also show the dim brightness level stored for + this . + +What: /sys/class/backlight//ambient_light_level +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Get conversion value of the light sensor. + This value is updated every 80 ms (when the light sensor + is enabled). Returns integer between 0 (dark) and + 8000 (max ambient brightness) + +What: /sys/class/backlight//ambient_light_zone +Date: Mai 2011 +KernelVersion: 2.6.40 +Contact: device-drivers-devel@blackfin.uclinux.org +Description: + Get/Set current ambient light zone. Reading returns + integer between 1..5 (1 = daylight, 2 = bright, ..., 5 = dark). + Writing a value between 1..5 forces the backlight controller + to enter the corresponding ambient light zone. + Writing 0 returns to normal/automatic ambient light level + operation. The ambient light sensing feature on these devices + is an extension to the API documented in + Documentation/ABI/stable/sysfs-class-backlight. + It can be enabled by writing the value stored in + /sys/class/backlight//max_brightness to + /sys/class/backlight//brightness. \ No newline at end of file diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 0c9373bedd1..2d93c8d61ad 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -302,6 +302,18 @@ config BACKLIGHT_ADP8860 To compile this driver as a module, choose M here: the module will be called adp8860_bl. +config BACKLIGHT_ADP8870 + tristate "Backlight Driver for ADP8870 using WLED" + depends on BACKLIGHT_CLASS_DEVICE && I2C + select NEW_LEDS + select LEDS_CLASS + help + If you have a LCD backlight connected to the ADP8870, + say Y here to enable this driver. + + To compile this driver as a module, choose M here: the module will + be called adp8870_bl. + config BACKLIGHT_88PM860X tristate "Backlight Driver for 88PM8606 using WLED" depends on MFD_88PM860X diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index b9ca8490df8..ee72adb8786 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_BACKLIGHT_WM831X) += wm831x_bl.o obj-$(CONFIG_BACKLIGHT_ADX) += adx_bl.o obj-$(CONFIG_BACKLIGHT_ADP5520) += adp5520_bl.o obj-$(CONFIG_BACKLIGHT_ADP8860) += adp8860_bl.o +obj-$(CONFIG_BACKLIGHT_ADP8870) += adp8870_bl.o obj-$(CONFIG_BACKLIGHT_88PM860X) += 88pm860x_bl.o obj-$(CONFIG_BACKLIGHT_PCF50633) += pcf50633-backlight.o diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c new file mode 100644 index 00000000000..e320b62576e --- /dev/null +++ b/drivers/video/backlight/adp8870_bl.c @@ -0,0 +1,1011 @@ +/* + * Backlight driver for Analog Devices ADP8870 Backlight Devices + * + * Copyright 2009-2011 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#define ADP8870_EXT_FEATURES +#define ADP8870_USE_LEDS + + +#define ADP8870_MFDVID 0x00 /* Manufacturer and device ID */ +#define ADP8870_MDCR 0x01 /* Device mode and status */ +#define ADP8870_INT_STAT 0x02 /* Interrupts status */ +#define ADP8870_INT_EN 0x03 /* Interrupts enable */ +#define ADP8870_CFGR 0x04 /* Configuration register */ +#define ADP8870_BLSEL 0x05 /* Sink enable backlight or independent */ +#define ADP8870_PWMLED 0x06 /* PWM Enable Selection Register */ +#define ADP8870_BLOFF 0x07 /* Backlight off timeout */ +#define ADP8870_BLDIM 0x08 /* Backlight dim timeout */ +#define ADP8870_BLFR 0x09 /* Backlight fade in and out rates */ +#define ADP8870_BLMX1 0x0A /* Backlight (Brightness Level 1-daylight) maximum current */ +#define ADP8870_BLDM1 0x0B /* Backlight (Brightness Level 1-daylight) dim current */ +#define ADP8870_BLMX2 0x0C /* Backlight (Brightness Level 2-bright) maximum current */ +#define ADP8870_BLDM2 0x0D /* Backlight (Brightness Level 2-bright) dim current */ +#define ADP8870_BLMX3 0x0E /* Backlight (Brightness Level 3-office) maximum current */ +#define ADP8870_BLDM3 0x0F /* Backlight (Brightness Level 3-office) dim current */ +#define ADP8870_BLMX4 0x10 /* Backlight (Brightness Level 4-indoor) maximum current */ +#define ADP8870_BLDM4 0x11 /* Backlight (Brightness Level 4-indoor) dim current */ +#define ADP8870_BLMX5 0x12 /* Backlight (Brightness Level 5-dark) maximum current */ +#define ADP8870_BLDM5 0x13 /* Backlight (Brightness Level 5-dark) dim current */ +#define ADP8870_ISCLAW 0x1A /* Independent sink current fade law register */ +#define ADP8870_ISCC 0x1B /* Independent sink current control register */ +#define ADP8870_ISCT1 0x1C /* Independent Sink Current Timer Register LED[7:5] */ +#define ADP8870_ISCT2 0x1D /* Independent Sink Current Timer Register LED[4:1] */ +#define ADP8870_ISCF 0x1E /* Independent sink current fade register */ +#define ADP8870_ISC1 0x1F /* Independent Sink Current LED1 */ +#define ADP8870_ISC2 0x20 /* Independent Sink Current LED2 */ +#define ADP8870_ISC3 0x21 /* Independent Sink Current LED3 */ +#define ADP8870_ISC4 0x22 /* Independent Sink Current LED4 */ +#define ADP8870_ISC5 0x23 /* Independent Sink Current LED5 */ +#define ADP8870_ISC6 0x24 /* Independent Sink Current LED6 */ +#define ADP8870_ISC7 0x25 /* Independent Sink Current LED7 (Brightness Level 1-daylight) */ +#define ADP8870_ISC7_L2 0x26 /* Independent Sink Current LED7 (Brightness Level 2-bright) */ +#define ADP8870_ISC7_L3 0x27 /* Independent Sink Current LED7 (Brightness Level 3-office) */ +#define ADP8870_ISC7_L4 0x28 /* Independent Sink Current LED7 (Brightness Level 4-indoor) */ +#define ADP8870_ISC7_L5 0x29 /* Independent Sink Current LED7 (Brightness Level 5-dark) */ +#define ADP8870_CMP_CTL 0x2D /* ALS Comparator Control Register */ +#define ADP8870_ALS1_EN 0x2E /* Main ALS comparator level enable */ +#define ADP8870_ALS2_EN 0x2F /* Second ALS comparator level enable */ +#define ADP8870_ALS1_STAT 0x30 /* Main ALS Comparator Status Register */ +#define ADP8870_ALS2_STAT 0x31 /* Second ALS Comparator Status Register */ +#define ADP8870_L2TRP 0x32 /* L2 comparator reference */ +#define ADP8870_L2HYS 0x33 /* L2 hysteresis */ +#define ADP8870_L3TRP 0x34 /* L3 comparator reference */ +#define ADP8870_L3HYS 0x35 /* L3 hysteresis */ +#define ADP8870_L4TRP 0x36 /* L4 comparator reference */ +#define ADP8870_L4HYS 0x37 /* L4 hysteresis */ +#define ADP8870_L5TRP 0x38 /* L5 comparator reference */ +#define ADP8870_L5HYS 0x39 /* L5 hysteresis */ +#define ADP8870_PH1LEVL 0x40 /* First phototransistor ambient light level-low byte register */ +#define ADP8870_PH1LEVH 0x41 /* First phototransistor ambient light level-high byte register */ +#define ADP8870_PH2LEVL 0x42 /* Second phototransistor ambient light level-low byte register */ +#define ADP8870_PH2LEVH 0x43 /* Second phototransistor ambient light level-high byte register */ + +#define ADP8870_MANUFID 0x3 /* Analog Devices AD8870 Manufacturer and device ID */ +#define ADP8870_DEVID(x) ((x) & 0xF) +#define ADP8870_MANID(x) ((x) >> 4) + +/* MDCR Device mode and status */ +#define D7ALSEN (1 << 7) +#define INT_CFG (1 << 6) +#define NSTBY (1 << 5) +#define DIM_EN (1 << 4) +#define GDWN_DIS (1 << 3) +#define SIS_EN (1 << 2) +#define CMP_AUTOEN (1 << 1) +#define BLEN (1 << 0) + +/* ADP8870_ALS1_EN Main ALS comparator level enable */ +#define L5_EN (1 << 3) +#define L4_EN (1 << 2) +#define L3_EN (1 << 1) +#define L2_EN (1 << 0) + +#define CFGR_BLV_SHIFT 3 +#define CFGR_BLV_MASK 0x7 +#define ADP8870_FLAG_LED_MASK 0xFF + +#define FADE_VAL(in, out) ((0xF & (in)) | ((0xF & (out)) << 4)) +#define BL_CFGR_VAL(law, blv) ((((blv) & CFGR_BLV_MASK) << CFGR_BLV_SHIFT) | ((0x3 & (law)) << 1)) +#define ALS_CMPR_CFG_VAL(filt) ((0x7 & (filt)) << 1) + +struct adp8870_bl { + struct i2c_client *client; + struct backlight_device *bl; + struct adp8870_led *led; + struct adp8870_backlight_platform_data *pdata; + struct mutex lock; + unsigned long cached_daylight_max; + int id; + int revid; + int current_brightness; +}; + +struct adp8870_led { + struct led_classdev cdev; + struct work_struct work; + struct i2c_client *client; + enum led_brightness new_brightness; + int id; + int flags; +}; + +static int adp8870_read(struct i2c_client *client, int reg, uint8_t *val) +{ + int ret; + + ret = i2c_smbus_read_byte_data(client, reg); + if (ret < 0) { + dev_err(&client->dev, "failed reading at 0x%02x\n", reg); + return ret; + } + + *val = ret; + return 0; +} + + +static int adp8870_write(struct i2c_client *client, u8 reg, u8 val) +{ + int ret = i2c_smbus_write_byte_data(client, reg, val); + if (ret) + dev_err(&client->dev, "failed to write\n"); + + return ret; +} + +static int adp8870_set_bits(struct i2c_client *client, int reg, uint8_t bit_mask) +{ + struct adp8870_bl *data = i2c_get_clientdata(client); + uint8_t reg_val; + int ret; + + mutex_lock(&data->lock); + + ret = adp8870_read(client, reg, ®_val); + + if (!ret && ((reg_val & bit_mask) == 0)) { + reg_val |= bit_mask; + ret = adp8870_write(client, reg, reg_val); + } + + mutex_unlock(&data->lock); + return ret; +} + +static int adp8870_clr_bits(struct i2c_client *client, int reg, uint8_t bit_mask) +{ + struct adp8870_bl *data = i2c_get_clientdata(client); + uint8_t reg_val; + int ret; + + mutex_lock(&data->lock); + + ret = adp8870_read(client, reg, ®_val); + + if (!ret && (reg_val & bit_mask)) { + reg_val &= ~bit_mask; + ret = adp8870_write(client, reg, reg_val); + } + + mutex_unlock(&data->lock); + return ret; +} + +/* + * Independent sink / LED + */ +#if defined(ADP8870_USE_LEDS) +static void adp8870_led_work(struct work_struct *work) +{ + struct adp8870_led *led = container_of(work, struct adp8870_led, work); + adp8870_write(led->client, ADP8870_ISC1 + led->id - 1, + led->new_brightness >> 1); +} + +static void adp8870_led_set(struct led_classdev *led_cdev, + enum led_brightness value) +{ + struct adp8870_led *led; + + led = container_of(led_cdev, struct adp8870_led, cdev); + led->new_brightness = value; + /* + * Use workqueue for IO since I2C operations can sleep. + */ + schedule_work(&led->work); +} + +static int adp8870_led_setup(struct adp8870_led *led) +{ + struct i2c_client *client = led->client; + int ret = 0; + + ret = adp8870_write(client, ADP8870_ISC1 + led->id - 1, 0); + if (ret) + return ret; + + ret = adp8870_set_bits(client, ADP8870_ISCC, 1 << (led->id - 1)); + if (ret) + return ret; + + if (led->id > 4) + ret = adp8870_set_bits(client, ADP8870_ISCT1, + (led->flags & 0x3) << ((led->id - 5) * 2)); + else + ret = adp8870_set_bits(client, ADP8870_ISCT2, + (led->flags & 0x3) << ((led->id - 1) * 2)); + + return ret; +} + +static int __devinit adp8870_led_probe(struct i2c_client *client) +{ + struct adp8870_backlight_platform_data *pdata = + client->dev.platform_data; + struct adp8870_bl *data = i2c_get_clientdata(client); + struct adp8870_led *led, *led_dat; + struct led_info *cur_led; + int ret, i; + + + led = kcalloc(pdata->num_leds, sizeof(*led), GFP_KERNEL); + if (led == NULL) { + dev_err(&client->dev, "failed to alloc memory\n"); + return -ENOMEM; + } + + ret = adp8870_write(client, ADP8870_ISCLAW, pdata->led_fade_law); + if (ret) + goto err_free; + + ret = adp8870_write(client, ADP8870_ISCT1, + (pdata->led_on_time & 0x3) << 6); + if (ret) + goto err_free; + + ret = adp8870_write(client, ADP8870_ISCF, + FADE_VAL(pdata->led_fade_in, pdata->led_fade_out)); + if (ret) + goto err_free; + + for (i = 0; i < pdata->num_leds; ++i) { + cur_led = &pdata->leds[i]; + led_dat = &led[i]; + + led_dat->id = cur_led->flags & ADP8870_FLAG_LED_MASK; + + if (led_dat->id > 7 || led_dat->id < 1) { + dev_err(&client->dev, "Invalid LED ID %d\n", + led_dat->id); + goto err; + } + + if (pdata->bl_led_assign & (1 << (led_dat->id - 1))) { + dev_err(&client->dev, "LED %d used by Backlight\n", + led_dat->id); + goto err; + } + + led_dat->cdev.name = cur_led->name; + led_dat->cdev.default_trigger = cur_led->default_trigger; + led_dat->cdev.brightness_set = adp8870_led_set; + led_dat->cdev.brightness = LED_OFF; + led_dat->flags = cur_led->flags >> FLAG_OFFT_SHIFT; + led_dat->client = client; + led_dat->new_brightness = LED_OFF; + INIT_WORK(&led_dat->work, adp8870_led_work); + + ret = led_classdev_register(&client->dev, &led_dat->cdev); + if (ret) { + dev_err(&client->dev, "failed to register LED %d\n", + led_dat->id); + goto err; + } + + ret = adp8870_led_setup(led_dat); + if (ret) { + dev_err(&client->dev, "failed to write\n"); + i++; + goto err; + } + } + + data->led = led; + + return 0; + + err: + for (i = i - 1; i >= 0; --i) { + led_classdev_unregister(&led[i].cdev); + cancel_work_sync(&led[i].work); + } + + err_free: + kfree(led); + + return ret; +} + +static int __devexit adp8870_led_remove(struct i2c_client *client) +{ + struct adp8870_backlight_platform_data *pdata = + client->dev.platform_data; + struct adp8870_bl *data = i2c_get_clientdata(client); + int i; + + for (i = 0; i < pdata->num_leds; i++) { + led_classdev_unregister(&data->led[i].cdev); + cancel_work_sync(&data->led[i].work); + } + + kfree(data->led); + return 0; +} +#else +static int __devinit adp8870_led_probe(struct i2c_client *client) +{ + return 0; +} + +static int __devexit adp8870_led_remove(struct i2c_client *client) +{ + return 0; +} +#endif + +static int adp8870_bl_set(struct backlight_device *bl, int brightness) +{ + struct adp8870_bl *data = bl_get_data(bl); + struct i2c_client *client = data->client; + int ret = 0; + + if (data->pdata->en_ambl_sens) { + if ((brightness > 0) && (brightness < ADP8870_MAX_BRIGHTNESS)) { + /* Disable Ambient Light auto adjust */ + ret = adp8870_clr_bits(client, ADP8870_MDCR, + CMP_AUTOEN); + if (ret) + return ret; + ret = adp8870_write(client, ADP8870_BLMX1, brightness); + if (ret) + return ret; + } else { + /* + * MAX_BRIGHTNESS -> Enable Ambient Light auto adjust + * restore daylight l1 sysfs brightness + */ + ret = adp8870_write(client, ADP8870_BLMX1, + data->cached_daylight_max); + if (ret) + return ret; + + ret = adp8870_set_bits(client, ADP8870_MDCR, + CMP_AUTOEN); + if (ret) + return ret; + } + } else { + ret = adp8870_write(client, ADP8870_BLMX1, brightness); + if (ret) + return ret; + } + + if (data->current_brightness && brightness == 0) + ret = adp8870_set_bits(client, + ADP8870_MDCR, DIM_EN); + else if (data->current_brightness == 0 && brightness) + ret = adp8870_clr_bits(client, + ADP8870_MDCR, DIM_EN); + + if (!ret) + data->current_brightness = brightness; + + return ret; +} + +static int adp8870_bl_update_status(struct backlight_device *bl) +{ + int brightness = bl->props.brightness; + if (bl->props.power != FB_BLANK_UNBLANK) + brightness = 0; + + if (bl->props.fb_blank != FB_BLANK_UNBLANK) + brightness = 0; + + return adp8870_bl_set(bl, brightness); +} + +static int adp8870_bl_get_brightness(struct backlight_device *bl) +{ + struct adp8870_bl *data = bl_get_data(bl); + + return data->current_brightness; +} + +static const struct backlight_ops adp8870_bl_ops = { + .update_status = adp8870_bl_update_status, + .get_brightness = adp8870_bl_get_brightness, +}; + +static int adp8870_bl_setup(struct backlight_device *bl) +{ + struct adp8870_bl *data = bl_get_data(bl); + struct i2c_client *client = data->client; + struct adp8870_backlight_platform_data *pdata = data->pdata; + int ret = 0; + + ret = adp8870_write(client, ADP8870_BLSEL, ~pdata->bl_led_assign); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_PWMLED, pdata->pwm_assign); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX1, pdata->l1_daylight_max); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLDM1, pdata->l1_daylight_dim); + if (ret) + return ret; + + if (pdata->en_ambl_sens) { + data->cached_daylight_max = pdata->l1_daylight_max; + ret = adp8870_write(client, ADP8870_BLMX2, + pdata->l2_bright_max); + if (ret) + return ret; + ret = adp8870_write(client, ADP8870_BLDM2, + pdata->l2_bright_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX3, + pdata->l3_office_max); + if (ret) + return ret; + ret = adp8870_write(client, ADP8870_BLDM3, + pdata->l3_office_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX4, + pdata->l4_indoor_max); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLDM4, + pdata->l4_indor_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLMX5, + pdata->l5_dark_max); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLDM5, + pdata->l5_dark_dim); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L2TRP, pdata->l2_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L2HYS, pdata->l2_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L3TRP, pdata->l3_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L3HYS, pdata->l3_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L4TRP, pdata->l4_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L4HYS, pdata->l4_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L5TRP, pdata->l5_trip); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_L5HYS, pdata->l5_hyst); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_ALS1_EN, L5_EN | L4_EN | + L3_EN | L2_EN); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_CMP_CTL, + ALS_CMPR_CFG_VAL(pdata->abml_filt)); + if (ret) + return ret; + } + + ret = adp8870_write(client, ADP8870_CFGR, + BL_CFGR_VAL(pdata->bl_fade_law, 0)); + if (ret) + return ret; + + ret = adp8870_write(client, ADP8870_BLFR, FADE_VAL(pdata->bl_fade_in, + pdata->bl_fade_out)); + if (ret) + return ret; + /* + * ADP8870 Rev0 requires GDWN_DIS bit set + */ + + ret = adp8870_set_bits(client, ADP8870_MDCR, BLEN | DIM_EN | NSTBY | + (data->revid == 0 ? GDWN_DIS : 0)); + + return ret; +} + +static ssize_t adp8870_show(struct device *dev, char *buf, int reg) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int error; + uint8_t reg_val; + + mutex_lock(&data->lock); + error = adp8870_read(data->client, reg, ®_val); + mutex_unlock(&data->lock); + + if (error < 0) + return error; + + return sprintf(buf, "%u\n", reg_val); +} + +static ssize_t adp8870_store(struct device *dev, const char *buf, + size_t count, int reg) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + unsigned long val; + int ret; + + ret = strict_strtoul(buf, 10, &val); + if (ret) + return ret; + + mutex_lock(&data->lock); + adp8870_write(data->client, reg, val); + mutex_unlock(&data->lock); + + return count; +} + +static ssize_t adp8870_bl_l5_dark_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX5); +} + +static ssize_t adp8870_bl_l5_dark_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX5); +} +static DEVICE_ATTR(l5_dark_max, 0664, adp8870_bl_l5_dark_max_show, + adp8870_bl_l5_dark_max_store); + + +static ssize_t adp8870_bl_l4_indoor_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX4); +} + +static ssize_t adp8870_bl_l4_indoor_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX4); +} +static DEVICE_ATTR(l4_indoor_max, 0664, adp8870_bl_l4_indoor_max_show, + adp8870_bl_l4_indoor_max_store); + + +static ssize_t adp8870_bl_l3_office_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX3); +} + +static ssize_t adp8870_bl_l3_office_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX3); +} + +static DEVICE_ATTR(l3_office_max, 0664, adp8870_bl_l3_office_max_show, + adp8870_bl_l3_office_max_store); + +static ssize_t adp8870_bl_l2_bright_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX2); +} + +static ssize_t adp8870_bl_l2_bright_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLMX2); +} +static DEVICE_ATTR(l2_bright_max, 0664, adp8870_bl_l2_bright_max_show, + adp8870_bl_l2_bright_max_store); + +static ssize_t adp8870_bl_l1_daylight_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLMX1); +} + +static ssize_t adp8870_bl_l1_daylight_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int ret = strict_strtoul(buf, 10, &data->cached_daylight_max); + if (ret) + return ret; + + return adp8870_store(dev, buf, count, ADP8870_BLMX1); +} +static DEVICE_ATTR(l1_daylight_max, 0664, adp8870_bl_l1_daylight_max_show, + adp8870_bl_l1_daylight_max_store); + +static ssize_t adp8870_bl_l5_dark_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM5); +} + +static ssize_t adp8870_bl_l5_dark_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM5); +} +static DEVICE_ATTR(l5_dark_dim, 0664, adp8870_bl_l5_dark_dim_show, + adp8870_bl_l5_dark_dim_store); + +static ssize_t adp8870_bl_l4_indoor_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM4); +} + +static ssize_t adp8870_bl_l4_indoor_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM4); +} +static DEVICE_ATTR(l4_indoor_dim, 0664, adp8870_bl_l4_indoor_dim_show, + adp8870_bl_l4_indoor_dim_store); + + +static ssize_t adp8870_bl_l3_office_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM3); +} + +static ssize_t adp8870_bl_l3_office_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM3); +} +static DEVICE_ATTR(l3_office_dim, 0664, adp8870_bl_l3_office_dim_show, + adp8870_bl_l3_office_dim_store); + +static ssize_t adp8870_bl_l2_bright_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM2); +} + +static ssize_t adp8870_bl_l2_bright_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM2); +} +static DEVICE_ATTR(l2_bright_dim, 0664, adp8870_bl_l2_bright_dim_show, + adp8870_bl_l2_bright_dim_store); + +static ssize_t adp8870_bl_l1_daylight_dim_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return adp8870_show(dev, buf, ADP8870_BLDM1); +} + +static ssize_t adp8870_bl_l1_daylight_dim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return adp8870_store(dev, buf, count, ADP8870_BLDM1); +} +static DEVICE_ATTR(l1_daylight_dim, 0664, adp8870_bl_l1_daylight_dim_show, + adp8870_bl_l1_daylight_dim_store); + +#ifdef ADP8870_EXT_FEATURES +static ssize_t adp8870_bl_ambient_light_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int error; + uint8_t reg_val; + uint16_t ret_val; + + mutex_lock(&data->lock); + error = adp8870_read(data->client, ADP8870_PH1LEVL, ®_val); + if (error < 0) { + mutex_unlock(&data->lock); + return error; + } + ret_val = reg_val; + error = adp8870_read(data->client, ADP8870_PH1LEVH, ®_val); + mutex_unlock(&data->lock); + + if (error < 0) + return error; + + /* Return 13-bit conversion value for the first light sensor */ + ret_val += (reg_val & 0x1F) << 8; + + return sprintf(buf, "%u\n", ret_val); +} +static DEVICE_ATTR(ambient_light_level, 0444, + adp8870_bl_ambient_light_level_show, NULL); + +static ssize_t adp8870_bl_ambient_light_zone_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + int error; + uint8_t reg_val; + + mutex_lock(&data->lock); + error = adp8870_read(data->client, ADP8870_CFGR, ®_val); + mutex_unlock(&data->lock); + + if (error < 0) + return error; + + return sprintf(buf, "%u\n", + ((reg_val >> CFGR_BLV_SHIFT) & CFGR_BLV_MASK) + 1); +} + +static ssize_t adp8870_bl_ambient_light_zone_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct adp8870_bl *data = dev_get_drvdata(dev); + unsigned long val; + uint8_t reg_val; + int ret; + + ret = strict_strtoul(buf, 10, &val); + if (ret) + return ret; + + if (val == 0) { + /* Enable automatic ambient light sensing */ + adp8870_set_bits(data->client, ADP8870_MDCR, CMP_AUTOEN); + } else if ((val > 0) && (val < 6)) { + /* Disable automatic ambient light sensing */ + adp8870_clr_bits(data->client, ADP8870_MDCR, CMP_AUTOEN); + + /* Set user supplied ambient light zone */ + mutex_lock(&data->lock); + adp8870_read(data->client, ADP8870_CFGR, ®_val); + reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT); + reg_val |= (val - 1) << CFGR_BLV_SHIFT; + adp8870_write(data->client, ADP8870_CFGR, reg_val); + mutex_unlock(&data->lock); + } + + return count; +} +static DEVICE_ATTR(ambient_light_zone, 0664, + adp8870_bl_ambient_light_zone_show, + adp8870_bl_ambient_light_zone_store); +#endif + +static struct attribute *adp8870_bl_attributes[] = { + &dev_attr_l5_dark_max.attr, + &dev_attr_l5_dark_dim.attr, + &dev_attr_l4_indoor_max.attr, + &dev_attr_l4_indoor_dim.attr, + &dev_attr_l3_office_max.attr, + &dev_attr_l3_office_dim.attr, + &dev_attr_l2_bright_max.attr, + &dev_attr_l2_bright_dim.attr, + &dev_attr_l1_daylight_max.attr, + &dev_attr_l1_daylight_dim.attr, +#ifdef ADP8870_EXT_FEATURES + &dev_attr_ambient_light_level.attr, + &dev_attr_ambient_light_zone.attr, +#endif + NULL +}; + +static const struct attribute_group adp8870_bl_attr_group = { + .attrs = adp8870_bl_attributes, +}; + +static int __devinit adp8870_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct backlight_properties props; + struct backlight_device *bl; + struct adp8870_bl *data; + struct adp8870_backlight_platform_data *pdata = + client->dev.platform_data; + uint8_t reg_val; + int ret; + + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_BYTE_DATA)) { + dev_err(&client->dev, "SMBUS Byte Data not Supported\n"); + return -EIO; + } + + if (!pdata) { + dev_err(&client->dev, "no platform data?\n"); + return -EINVAL; + } + + ret = adp8870_read(client, ADP8870_MFDVID, ®_val); + if (ret < 0) + return -EIO; + + if (ADP8870_MANID(reg_val) != ADP8870_MANUFID) { + dev_err(&client->dev, "failed to probe\n"); + return -ENODEV; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + data->revid = ADP8870_DEVID(reg_val); + data->client = client; + data->pdata = pdata; + data->id = id->driver_data; + data->current_brightness = 0; + i2c_set_clientdata(client, data); + + mutex_init(&data->lock); + + memset(&props, 0, sizeof(props)); + props.max_brightness = props.brightness = ADP8870_MAX_BRIGHTNESS; + bl = backlight_device_register(dev_driver_string(&client->dev), + &client->dev, data, &adp8870_bl_ops, &props); + if (IS_ERR(bl)) { + dev_err(&client->dev, "failed to register backlight\n"); + ret = PTR_ERR(bl); + goto out2; + } + + data->bl = bl; + + if (pdata->en_ambl_sens) + ret = sysfs_create_group(&bl->dev.kobj, + &adp8870_bl_attr_group); + + if (ret) { + dev_err(&client->dev, "failed to register sysfs\n"); + goto out1; + } + + ret = adp8870_bl_setup(bl); + if (ret) { + ret = -EIO; + goto out; + } + + backlight_update_status(bl); + + dev_info(&client->dev, "Rev.%d Backlight\n", data->revid); + + if (pdata->num_leds) + adp8870_led_probe(client); + + return 0; + +out: + if (data->pdata->en_ambl_sens) + sysfs_remove_group(&data->bl->dev.kobj, + &adp8870_bl_attr_group); +out1: + backlight_device_unregister(bl); +out2: + i2c_set_clientdata(client, NULL); + kfree(data); + + return ret; +} + +static int __devexit adp8870_remove(struct i2c_client *client) +{ + struct adp8870_bl *data = i2c_get_clientdata(client); + + adp8870_clr_bits(client, ADP8870_MDCR, NSTBY); + + if (data->led) + adp8870_led_remove(client); + + if (data->pdata->en_ambl_sens) + sysfs_remove_group(&data->bl->dev.kobj, + &adp8870_bl_attr_group); + + backlight_device_unregister(data->bl); + i2c_set_clientdata(client, NULL); + kfree(data); + + return 0; +} + +#ifdef CONFIG_PM +static int adp8870_i2c_suspend(struct i2c_client *client, pm_message_t message) +{ + adp8870_clr_bits(client, ADP8870_MDCR, NSTBY); + + return 0; +} + +static int adp8870_i2c_resume(struct i2c_client *client) +{ + adp8870_set_bits(client, ADP8870_MDCR, NSTBY); + + return 0; +} +#else +#define adp8870_i2c_suspend NULL +#define adp8870_i2c_resume NULL +#endif + +static const struct i2c_device_id adp8870_id[] = { + { "adp8870", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, adp8870_id); + +static struct i2c_driver adp8870_driver = { + .driver = { + .name = KBUILD_MODNAME, + }, + .probe = adp8870_probe, + .remove = __devexit_p(adp8870_remove), + .suspend = adp8870_i2c_suspend, + .resume = adp8870_i2c_resume, + .id_table = adp8870_id, +}; + +static int __init adp8870_init(void) +{ + return i2c_add_driver(&adp8870_driver); +} +module_init(adp8870_init); + +static void __exit adp8870_exit(void) +{ + i2c_del_driver(&adp8870_driver); +} +module_exit(adp8870_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Michael Hennerich "); +MODULE_DESCRIPTION("ADP8870 Backlight driver"); +MODULE_ALIAS("platform:adp8870-backlight"); diff --git a/include/linux/i2c/adp8870.h b/include/linux/i2c/adp8870.h new file mode 100644 index 00000000000..624dceccbd5 --- /dev/null +++ b/include/linux/i2c/adp8870.h @@ -0,0 +1,153 @@ +/* + * Definitions and platform data for Analog Devices + * Backlight drivers ADP8870 + * + * Copyright 2009-2010 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#ifndef __LINUX_I2C_ADP8870_H +#define __LINUX_I2C_ADP8870_H + +#define ID_ADP8870 8870 + +#define ADP8870_MAX_BRIGHTNESS 0x7F +#define FLAG_OFFT_SHIFT 8 + +/* + * LEDs subdevice platform data + */ + +#define ADP8870_LED_DIS_BLINK (0 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_600ms (1 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_1200ms (2 << FLAG_OFFT_SHIFT) +#define ADP8870_LED_OFFT_1800ms (3 << FLAG_OFFT_SHIFT) + +#define ADP8870_LED_ONT_200ms 0 +#define ADP8870_LED_ONT_600ms 1 +#define ADP8870_LED_ONT_800ms 2 +#define ADP8870_LED_ONT_1200ms 3 + +#define ADP8870_LED_D7 (7) +#define ADP8870_LED_D6 (6) +#define ADP8870_LED_D5 (5) +#define ADP8870_LED_D4 (4) +#define ADP8870_LED_D3 (3) +#define ADP8870_LED_D2 (2) +#define ADP8870_LED_D1 (1) + +/* + * Backlight subdevice platform data + */ + +#define ADP8870_BL_D7 (1 << 6) +#define ADP8870_BL_D6 (1 << 5) +#define ADP8870_BL_D5 (1 << 4) +#define ADP8870_BL_D4 (1 << 3) +#define ADP8870_BL_D3 (1 << 2) +#define ADP8870_BL_D2 (1 << 1) +#define ADP8870_BL_D1 (1 << 0) + +#define ADP8870_FADE_T_DIS 0 /* Fade Timer Disabled */ +#define ADP8870_FADE_T_300ms 1 /* 0.3 Sec */ +#define ADP8870_FADE_T_600ms 2 +#define ADP8870_FADE_T_900ms 3 +#define ADP8870_FADE_T_1200ms 4 +#define ADP8870_FADE_T_1500ms 5 +#define ADP8870_FADE_T_1800ms 6 +#define ADP8870_FADE_T_2100ms 7 +#define ADP8870_FADE_T_2400ms 8 +#define ADP8870_FADE_T_2700ms 9 +#define ADP8870_FADE_T_3000ms 10 +#define ADP8870_FADE_T_3500ms 11 +#define ADP8870_FADE_T_4000ms 12 +#define ADP8870_FADE_T_4500ms 13 +#define ADP8870_FADE_T_5000ms 14 +#define ADP8870_FADE_T_5500ms 15 /* 5.5 Sec */ + +#define ADP8870_FADE_LAW_LINEAR 0 +#define ADP8870_FADE_LAW_SQUARE 1 +#define ADP8870_FADE_LAW_CUBIC1 2 +#define ADP8870_FADE_LAW_CUBIC2 3 + +#define ADP8870_BL_AMBL_FILT_80ms 0 /* Light sensor filter time */ +#define ADP8870_BL_AMBL_FILT_160ms 1 +#define ADP8870_BL_AMBL_FILT_320ms 2 +#define ADP8870_BL_AMBL_FILT_640ms 3 +#define ADP8870_BL_AMBL_FILT_1280ms 4 +#define ADP8870_BL_AMBL_FILT_2560ms 5 +#define ADP8870_BL_AMBL_FILT_5120ms 6 +#define ADP8870_BL_AMBL_FILT_10240ms 7 /* 10.24 sec */ + +/* + * Blacklight current 0..30mA + */ +#define ADP8870_BL_CUR_mA(I) ((I * 127) / 30) + +/* + * L2 comparator current 0..1106uA + */ +#define ADP8870_L2_COMP_CURR_uA(I) ((I * 255) / 1106) + +/* + * L3 comparator current 0..551uA + */ +#define ADP8870_L3_COMP_CURR_uA(I) ((I * 255) / 551) + +/* + * L4 comparator current 0..275uA + */ +#define ADP8870_L4_COMP_CURR_uA(I) ((I * 255) / 275) + +/* + * L5 comparator current 0..138uA + */ +#define ADP8870_L5_COMP_CURR_uA(I) ((I * 255) / 138) + +struct adp8870_backlight_platform_data { + u8 bl_led_assign; /* 1 = Backlight 0 = Individual LED */ + u8 pwm_assign; /* 1 = Enables PWM mode */ + + u8 bl_fade_in; /* Backlight Fade-In Timer */ + u8 bl_fade_out; /* Backlight Fade-Out Timer */ + u8 bl_fade_law; /* fade-on/fade-off transfer characteristic */ + + u8 en_ambl_sens; /* 1 = enable ambient light sensor */ + u8 abml_filt; /* Light sensor filter time */ + + u8 l1_daylight_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l1_daylight_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_bright_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_bright_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_office_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_office_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l4_indoor_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l4_indor_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l5_dark_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l5_dark_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + + u8 l2_trip; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l2_hyst; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l3_trip; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l3_hyst; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l4_trip; /* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */ + u8 l4_hyst; /* use L4_COMP_CURR_uA(I) 0 <= I <= 275 uA */ + u8 l5_trip; /* use L5_COMP_CURR_uA(I) 0 <= I <= 138 uA */ + u8 l5_hyst; /* use L6_COMP_CURR_uA(I) 0 <= I <= 138 uA */ + + /** + * Independent Current Sinks / LEDS + * Sinks not assigned to the Backlight can be exposed to + * user space using the LEDS CLASS interface + */ + + int num_leds; + struct led_info *leds; + u8 led_fade_in; /* LED Fade-In Timer */ + u8 led_fade_out; /* LED Fade-Out Timer */ + u8 led_fade_law; /* fade-on/fade-off transfer characteristic */ + u8 led_on_time; +}; + +#endif /* __LINUX_I2C_ADP8870_H */ -- cgit v1.2.3-18-g5258 From e1bbd19bc4afef7adb80cca163800391c4f5773d Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 15 Jun 2011 15:08:12 -0700 Subject: drivers/video/backlight/adp8870_bl.c: add missed props.type conversion Cc: Michael Hennerich Cc: Mike Frysinger Cc: Matthew Garrett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/video/backlight/adp8870_bl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c index e320b62576e..05a8832bb3e 100644 --- a/drivers/video/backlight/adp8870_bl.c +++ b/drivers/video/backlight/adp8870_bl.c @@ -889,6 +889,7 @@ static int __devinit adp8870_probe(struct i2c_client *client, mutex_init(&data->lock); memset(&props, 0, sizeof(props)); + props.type = BACKLIGHT_RAW; props.max_brightness = props.brightness = ADP8870_MAX_BRIGHTNESS; bl = backlight_device_register(dev_driver_string(&client->dev), &client->dev, data, &adp8870_bl_ops, &props); -- cgit v1.2.3-18-g5258 From a433658c30974fc87ba3ff52d7e4e6299762aa3d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 15 Jun 2011 15:08:13 -0700 Subject: vmscan,memcg: memcg aware swap token Currently, memcg reclaim can disable swap token even if the swap token mm doesn't belong in its memory cgroup. It's slightly risky. If an admin creates very small mem-cgroup and silly guy runs contentious heavy memory pressure workload, every tasks are going to lose swap token and then system may become unresponsive. That's bad. This patch adds 'memcg' parameter into disable_swap_token(). and if the parameter doesn't match swap token, VM doesn't disable it. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++ include/linux/swap.h | 8 ++--- mm/memcontrol.c | 16 ++++----- mm/thrash.c | 87 ++++++++++++++++++++++++++++++++++++---------- mm/vmscan.c | 4 +-- 5 files changed, 85 insertions(+), 36 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9724a38ee69..50940da6adf 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -84,6 +84,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) @@ -246,6 +247,11 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) return NULL; } +static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +{ + return NULL; +} + static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem) { return 1; diff --git a/include/linux/swap.h b/include/linux/swap.h index 384eb5fe530..e7056464703 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -358,6 +358,7 @@ struct backing_dev_info; extern struct mm_struct *swap_token_mm; extern void grab_swap_token(struct mm_struct *); extern void __put_swap_token(struct mm_struct *); +extern void disable_swap_token(struct mem_cgroup *memcg); static inline int has_swap_token(struct mm_struct *mm) { @@ -370,11 +371,6 @@ static inline void put_swap_token(struct mm_struct *mm) __put_swap_token(mm); } -static inline void disable_swap_token(void) -{ - put_swap_token(swap_token_mm); -} - #ifdef CONFIG_CGROUP_MEM_RES_CTLR extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); @@ -500,7 +496,7 @@ static inline int has_swap_token(struct mm_struct *mm) return 0; } -static inline void disable_swap_token(void) +static inline void disable_swap_token(struct mem_cgroup *memcg) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bd9052a5d3a..e37c44d88d4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -735,7 +735,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) struct mem_cgroup, css); } -static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) +struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *mem = NULL; @@ -5414,18 +5414,16 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *old_cont, struct task_struct *p) { - struct mm_struct *mm; + struct mm_struct *mm = get_task_mm(p); - if (!mc.to) - /* no need to move charge */ - return; - - mm = get_task_mm(p); if (mm) { - mem_cgroup_move_charge(mm); + if (mc.to) + mem_cgroup_move_charge(mm); + put_swap_token(mm); mmput(mm); } - mem_cgroup_clear_mc(); + if (mc.to) + mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, diff --git a/mm/thrash.c b/mm/thrash.c index 2372d4ed5dd..6cdf8651138 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -21,11 +21,31 @@ #include #include #include +#include static DEFINE_SPINLOCK(swap_token_lock); struct mm_struct *swap_token_mm; +struct mem_cgroup *swap_token_memcg; static unsigned int global_faults; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) +{ + struct mem_cgroup *memcg; + + memcg = try_get_mem_cgroup_from_mm(mm); + if (memcg) + css_put(mem_cgroup_css(memcg)); + + return memcg; +} +#else +static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) +{ + return NULL; +} +#endif + void grab_swap_token(struct mm_struct *mm) { int current_interval; @@ -38,40 +58,69 @@ void grab_swap_token(struct mm_struct *mm) return; /* First come first served */ - if (swap_token_mm == NULL) { - mm->token_priority = mm->token_priority + 2; - swap_token_mm = mm; + if (!swap_token_mm) + goto replace_token; + + if (mm == swap_token_mm) { + mm->token_priority += 2; goto out; } - if (mm != swap_token_mm) { - if (current_interval < mm->last_interval) - mm->token_priority++; - else { - if (likely(mm->token_priority > 0)) - mm->token_priority--; - } - /* Check if we deserve the token */ - if (mm->token_priority > swap_token_mm->token_priority) { - mm->token_priority += 2; - swap_token_mm = mm; - } - } else { - /* Token holder came in again! */ - mm->token_priority += 2; + if (current_interval < mm->last_interval) + mm->token_priority++; + else { + if (likely(mm->token_priority > 0)) + mm->token_priority--; } + /* Check if we deserve the token */ + if (mm->token_priority > swap_token_mm->token_priority) + goto replace_token; + out: mm->faultstamp = global_faults; mm->last_interval = current_interval; spin_unlock(&swap_token_lock); + return; + +replace_token: + mm->token_priority += 2; + swap_token_mm = mm; + swap_token_memcg = swap_token_memcg_from_mm(mm); + goto out; } /* Called on process exit. */ void __put_swap_token(struct mm_struct *mm) { spin_lock(&swap_token_lock); - if (likely(mm == swap_token_mm)) + if (likely(mm == swap_token_mm)) { swap_token_mm = NULL; + swap_token_memcg = NULL; + } spin_unlock(&swap_token_lock); } + +static bool match_memcg(struct mem_cgroup *a, struct mem_cgroup *b) +{ + if (!a) + return true; + if (!b) + return true; + if (a == b) + return true; + return false; +} + +void disable_swap_token(struct mem_cgroup *memcg) +{ + /* memcg reclaim don't disable unrelated mm token. */ + if (match_memcg(memcg, swap_token_memcg)) { + spin_lock(&swap_token_lock); + if (match_memcg(memcg, swap_token_memcg)) { + swap_token_mm = NULL; + swap_token_memcg = NULL; + } + spin_unlock(&swap_token_lock); + } +} diff --git a/mm/vmscan.c b/mm/vmscan.c index faa0a088f9c..dbe6ea321df 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2081,7 +2081,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, for (priority = DEF_PRIORITY; priority >= 0; priority--) { sc->nr_scanned = 0; if (!priority) - disable_swap_token(); + disable_swap_token(sc->mem_cgroup); total_scanned += shrink_zones(priority, zonelist, sc); /* * Don't shrink slabs when reclaiming memory from @@ -2407,7 +2407,7 @@ loop_again: /* The swap token gets in the way of swapout... */ if (!priority) - disable_swap_token(); + disable_swap_token(NULL); all_zones_ok = 1; balanced = 0; -- cgit v1.2.3-18-g5258 From 83cd81a34357a632509f7491eec81e62e71d65f7 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 15 Jun 2011 15:08:14 -0700 Subject: vmscan: implement swap token trace This is useful for observing swap token activity. example output: zsh-1845 [000] 598.962716: update_swap_token_priority: mm=ffff88015eaf7700 old_prio=1 new_prio=0 memtoy-1830 [001] 602.033900: update_swap_token_priority: mm=ffff880037a45880 old_prio=947 new_prio=949 memtoy-1830 [000] 602.041509: update_swap_token_priority: mm=ffff880037a45880 old_prio=949 new_prio=951 memtoy-1830 [000] 602.051959: update_swap_token_priority: mm=ffff880037a45880 old_prio=951 new_prio=953 memtoy-1830 [000] 602.052188: update_swap_token_priority: mm=ffff880037a45880 old_prio=953 new_prio=955 memtoy-1830 [001] 602.427184: put_swap_token: token_mm=ffff880037a45880 zsh-1789 [000] 602.427281: replace_swap_token: old_token_mm= (null) old_prio=0 new_token_mm=ffff88015eaf7018 new_prio=2 zsh-1789 [001] 602.433456: update_swap_token_priority: mm=ffff88015eaf7018 old_prio=2 new_prio=4 zsh-1789 [000] 602.437613: update_swap_token_priority: mm=ffff88015eaf7018 old_prio=4 new_prio=6 zsh-1789 [000] 602.443924: update_swap_token_priority: mm=ffff88015eaf7018 old_prio=6 new_prio=8 zsh-1789 [000] 602.451873: update_swap_token_priority: mm=ffff88015eaf7018 old_prio=8 new_prio=10 zsh-1789 [001] 602.462639: update_swap_token_priority: mm=ffff88015eaf7018 old_prio=10 new_prio=12 Signed-off-by: KOSAKI Motohiro Acked-by: Rik van Riel Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 77 +++++++++++++++++++++++++++++++++++++++++++ mm/thrash.c | 11 ++++++- 2 files changed, 87 insertions(+), 1 deletion(-) diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index ea422aaa23e..1798e0cee2a 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -6,6 +6,8 @@ #include #include +#include +#include #include "gfpflags.h" #define RECLAIM_WB_ANON 0x0001u @@ -310,6 +312,81 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, show_reclaim_flags(__entry->reclaim_flags)) ); +TRACE_EVENT(replace_swap_token, + TP_PROTO(struct mm_struct *old_mm, + struct mm_struct *new_mm), + + TP_ARGS(old_mm, new_mm), + + TP_STRUCT__entry( + __field(struct mm_struct*, old_mm) + __field(unsigned int, old_prio) + __field(struct mm_struct*, new_mm) + __field(unsigned int, new_prio) + ), + + TP_fast_assign( + __entry->old_mm = old_mm; + __entry->old_prio = old_mm ? old_mm->token_priority : 0; + __entry->new_mm = new_mm; + __entry->new_prio = new_mm->token_priority; + ), + + TP_printk("old_token_mm=%p old_prio=%u new_token_mm=%p new_prio=%u", + __entry->old_mm, __entry->old_prio, + __entry->new_mm, __entry->new_prio) +); + +DECLARE_EVENT_CLASS(put_swap_token_template, + TP_PROTO(struct mm_struct *swap_token_mm), + + TP_ARGS(swap_token_mm), + + TP_STRUCT__entry( + __field(struct mm_struct*, swap_token_mm) + ), + + TP_fast_assign( + __entry->swap_token_mm = swap_token_mm; + ), + + TP_printk("token_mm=%p", __entry->swap_token_mm) +); + +DEFINE_EVENT(put_swap_token_template, put_swap_token, + TP_PROTO(struct mm_struct *swap_token_mm), + TP_ARGS(swap_token_mm) +); + +DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token, + TP_PROTO(struct mm_struct *swap_token_mm), + TP_ARGS(swap_token_mm), + TP_CONDITION(swap_token_mm != NULL) +); + +TRACE_EVENT_CONDITION(update_swap_token_priority, + TP_PROTO(struct mm_struct *mm, + unsigned int old_prio), + + TP_ARGS(mm, old_prio), + + TP_CONDITION(mm->token_priority != old_prio), + + TP_STRUCT__entry( + __field(struct mm_struct*, mm) + __field(unsigned int, old_prio) + __field(unsigned int, new_prio) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->old_prio = old_prio; + __entry->new_prio = mm->token_priority; + ), + + TP_printk("mm=%p old_prio=%u new_prio=%u", + __entry->mm, __entry->old_prio, __entry->new_prio) +); #endif /* _TRACE_VMSCAN_H */ diff --git a/mm/thrash.c b/mm/thrash.c index 6cdf8651138..17d9e29e4c9 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -23,6 +23,8 @@ #include #include +#include + static DEFINE_SPINLOCK(swap_token_lock); struct mm_struct *swap_token_mm; struct mem_cgroup *swap_token_memcg; @@ -49,6 +51,7 @@ static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) void grab_swap_token(struct mm_struct *mm) { int current_interval; + unsigned int old_prio = mm->token_priority; global_faults++; @@ -63,7 +66,7 @@ void grab_swap_token(struct mm_struct *mm) if (mm == swap_token_mm) { mm->token_priority += 2; - goto out; + goto update_priority; } if (current_interval < mm->last_interval) @@ -77,6 +80,9 @@ void grab_swap_token(struct mm_struct *mm) if (mm->token_priority > swap_token_mm->token_priority) goto replace_token; +update_priority: + trace_update_swap_token_priority(mm, old_prio); + out: mm->faultstamp = global_faults; mm->last_interval = current_interval; @@ -85,6 +91,7 @@ out: replace_token: mm->token_priority += 2; + trace_replace_swap_token(swap_token_mm, mm); swap_token_mm = mm; swap_token_memcg = swap_token_memcg_from_mm(mm); goto out; @@ -95,6 +102,7 @@ void __put_swap_token(struct mm_struct *mm) { spin_lock(&swap_token_lock); if (likely(mm == swap_token_mm)) { + trace_put_swap_token(swap_token_mm); swap_token_mm = NULL; swap_token_memcg = NULL; } @@ -118,6 +126,7 @@ void disable_swap_token(struct mem_cgroup *memcg) if (match_memcg(memcg, swap_token_memcg)) { spin_lock(&swap_token_lock); if (match_memcg(memcg, swap_token_memcg)) { + trace_disable_swap_token(swap_token_mm); swap_token_mm = NULL; swap_token_memcg = NULL; } -- cgit v1.2.3-18-g5258 From d7911ef30cb7bec52234c2b7a5c275ac8f07905a Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 15 Jun 2011 15:08:15 -0700 Subject: vmscan: implement swap token priority aging While testing for memcg aware swap token, I observed a swap token was often grabbed an intermittent running process (eg init, auditd) and they never release a token. Why? Some processes (eg init, auditd, audispd) wake up when a process exiting. And swap token can be get first page-in process when a process exiting makes no swap token owner. Thus such above intermittent running process often get a token. And currently, swap token priority is only decreased at page fault path. Then, if the process sleep immediately after to grab swap token, the swap token priority never be decreased. That's obviously undesirable. This patch implement very poor (and lightweight) priority aging. It only be affect to the above corner case and doesn't change swap tendency workload performance (eg multi process qsbench load) Signed-off-by: KOSAKI Motohiro Reviewed-by: Rik van Riel Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 20 +++++++++++++------- mm/thrash.c | 11 ++++++++++- 2 files changed, 23 insertions(+), 8 deletions(-) diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 1798e0cee2a..b2c33bd955f 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -366,9 +366,10 @@ DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token, TRACE_EVENT_CONDITION(update_swap_token_priority, TP_PROTO(struct mm_struct *mm, - unsigned int old_prio), + unsigned int old_prio, + struct mm_struct *swap_token_mm), - TP_ARGS(mm, old_prio), + TP_ARGS(mm, old_prio, swap_token_mm), TP_CONDITION(mm->token_priority != old_prio), @@ -376,16 +377,21 @@ TRACE_EVENT_CONDITION(update_swap_token_priority, __field(struct mm_struct*, mm) __field(unsigned int, old_prio) __field(unsigned int, new_prio) + __field(struct mm_struct*, swap_token_mm) + __field(unsigned int, swap_token_prio) ), TP_fast_assign( - __entry->mm = mm; - __entry->old_prio = old_prio; - __entry->new_prio = mm->token_priority; + __entry->mm = mm; + __entry->old_prio = old_prio; + __entry->new_prio = mm->token_priority; + __entry->swap_token_mm = swap_token_mm; + __entry->swap_token_prio = swap_token_mm ? swap_token_mm->token_priority : 0; ), - TP_printk("mm=%p old_prio=%u new_prio=%u", - __entry->mm, __entry->old_prio, __entry->new_prio) + TP_printk("mm=%p old_prio=%u new_prio=%u swap_token_mm=%p token_prio=%u", + __entry->mm, __entry->old_prio, __entry->new_prio, + __entry->swap_token_mm, __entry->swap_token_prio) ); #endif /* _TRACE_VMSCAN_H */ diff --git a/mm/thrash.c b/mm/thrash.c index 17d9e29e4c9..fabf2d0f516 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -25,10 +25,13 @@ #include +#define TOKEN_AGING_INTERVAL (0xFF) + static DEFINE_SPINLOCK(swap_token_lock); struct mm_struct *swap_token_mm; struct mem_cgroup *swap_token_memcg; static unsigned int global_faults; +static unsigned int last_aging; #ifdef CONFIG_CGROUP_MEM_RES_CTLR static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) @@ -64,6 +67,11 @@ void grab_swap_token(struct mm_struct *mm) if (!swap_token_mm) goto replace_token; + if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) { + swap_token_mm->token_priority /= 2; + last_aging = global_faults; + } + if (mm == swap_token_mm) { mm->token_priority += 2; goto update_priority; @@ -81,7 +89,7 @@ void grab_swap_token(struct mm_struct *mm) goto replace_token; update_priority: - trace_update_swap_token_priority(mm, old_prio); + trace_update_swap_token_priority(mm, old_prio, swap_token_mm); out: mm->faultstamp = global_faults; @@ -94,6 +102,7 @@ replace_token: trace_replace_swap_token(swap_token_mm, mm); swap_token_mm = mm; swap_token_memcg = swap_token_memcg_from_mm(mm); + last_aging = global_faults; goto out; } -- cgit v1.2.3-18-g5258 From 50c35e5ba255fd8428cef8ff076da8d23bfd4909 Mon Sep 17 00:00:00 2001 From: Ying Han Date: Wed, 15 Jun 2011 15:08:16 -0700 Subject: memcg: add documentation for the memory.numastat API [akpm@linux-foundation.org: rework text, fit it into 80-cols] Signed-off-by: Ying Han Reviewed-by: KOSAKI Motohiro Acked-by: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memory.txt | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 7c163477fcd..510d64570d6 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -70,6 +70,7 @@ Brief summary of control files. (See sysctl's vm.swappiness) memory.move_charge_at_immigrate # set/show controls of moving charges memory.oom_control # set/show oom controls. + memory.numa_stat # show the number of memory usage per numa node 1. History @@ -464,6 +465,24 @@ value for efficient access. (Of course, when necessary, it's synchronized.) If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP) value in memory.stat(see 5.2). +5.6 numa_stat + +This is similar to numa_maps but operates on a per-memcg basis. This is +useful for providing visibility into the numa locality information within +an memcg since the pages are allowed to be allocated from any physical +node. One of the usecases is evaluating application performance by +combining this information with the application's cpu allocation. + +We export "total", "file", "anon" and "unevictable" pages per-node for +each memcg. The ouput format of memory.numa_stat is: + +total= N0= N1= ... +file= N0= N1= ... +anon= N0= N1= ... +unevictable= N0= N1= ... + +And we have total = file + anon + unevictable. + 6. Hierarchy support The memory controller supports a deep hierarchy and hierarchical accounting. -- cgit v1.2.3-18-g5258 From ac5622418bbff9cd3dc607aa57dfb4f62a7f2043 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jun 2011 15:08:17 -0700 Subject: kmsg_dump.h: fix build when CONFIG_PRINTK is disabled Fix when CONFIG_PRINTK is not enabled: include/linux/kmsg_dump.h:56: error: 'EINVAL' undeclared (first use in this function) include/linux/kmsg_dump.h:61: error: 'EINVAL' undeclared (first use in this function) Looks like commit 595dd3d8bf95 ("kmsg_dump: fix build for CONFIG_PRINTK=n") uses EINVAL without having the needed header file(s), but I'm sure that I build tested that patch also. oh well. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmsg_dump.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 2a0d7d651dc..ee0c952188d 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -12,6 +12,7 @@ #ifndef _LINUX_KMSG_DUMP_H #define _LINUX_KMSG_DUMP_H +#include #include enum kmsg_dump_reason { -- cgit v1.2.3-18-g5258 From 17441227f6258fc379c6ebfe21c3eec43b6f0de3 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 15 Jun 2011 15:08:17 -0700 Subject: checkpatch: add warning for uses of printk_ratelimit Warn about uses of printk_ratelimit() because it uses a global state and can hide subsequent useful messages. Signed-off-by: Joe Perches Cc: Andy Whitcroft Cc: Richard Weinberger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkpatch.pl | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 8657f99bfb2..b0aa2c68059 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -1943,6 +1943,11 @@ sub process { WARN("LINUX_VERSION_CODE should be avoided, code should be for the version to which it is merged\n" . $herecurr); } +# check for uses of printk_ratelimit + if ($line =~ /\bprintk_ratelimit\s*\(/) { + WARN("Prefer printk_ratelimited or pr__ratelimited to printk_ratelimit\n" . $herecurr); + } + # printk should use KERN_* levels. Note that follow on printk's on the # same line do not need a level, so we use the current block context # to try and find and validate the current printk. In summary the current -- cgit v1.2.3-18-g5258 From 32e45ff43eaf5c17f5a82c9ad358d515622c2562 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 15 Jun 2011 15:08:20 -0700 Subject: mm: increase RECLAIM_DISTANCE to 30 Recently, Robert Mueller reported (http://lkml.org/lkml/2010/9/12/236) that zone_reclaim_mode doesn't work properly on his new NUMA server (Dual Xeon E5520 + Intel S5520UR MB). He is using Cyrus IMAPd and it's built on a very traditional single-process model. * a master process which reads config files and manages the other process * multiple imapd processes, one per connection * multiple pop3d processes, one per connection * multiple lmtpd processes, one per connection * periodical "cleanup" processes. There are thousands of independent processes. The problem is, recent Intel motherboard turn on zone_reclaim_mode by default and traditional prefork model software don't work well on it. Unfortunatelly, such models are still typical even in the 21st century. We can't ignore them. This patch raises the zone_reclaim_mode threshold to 30. 30 doesn't have any specific meaning. but 20 means that one-hop QPI/Hypertransport and such relatively cheap 2-4 socket machine are often used for traditional servers as above. The intention is that these machines don't use zone_reclaim_mode. Note: ia64 and Power have arch specific RECLAIM_DISTANCE definitions. This patch doesn't change such high-end NUMA machine behavior. Dave Hansen said: : I know specifically of pieces of x86 hardware that set the information : in the BIOS to '21' *specifically* so they'll get the zone_reclaim_mode : behavior which that implies. : : They've done performance testing and run very large and scary benchmarks : to make sure that they _want_ this turned on. What this means for them : is that they'll probably be de-optimized, at least on newer versions of : the kernel. : : If you want to do this for particular systems, maybe _that_'s what we : should do. Have a list of specific configurations that need the : defaults overridden either because they're buggy, or they have an : unusual hardware configuration not really reflected in the distance : table. And later said: : The original change in the hardware tables was for the benefit of a : benchmark. Said benchmark isn't going to get run on mainline until the : next batch of enterprise distros drops, at which point the hardware where : this was done will be irrelevant for the benchmark. I'm sure any new : hardware will just set this distance to another yet arbitrary value to : make the kernel do what it wants. :) : : Also, when the hardware got _set_ to this initially, I complained. So, I : guess I'm getting my way now, with this patch. I'm cool with it. Reported-by: Robert Mueller Signed-off-by: KOSAKI Motohiro Acked-by: Christoph Lameter Acked-by: David Rientjes Reviewed-by: KAMEZAWA Hiroyuki Cc: Benjamin Herrenschmidt Cc: "Luck, Tony" Acked-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/topology.h b/include/linux/topology.h index b91a40e847d..fc839bfa793 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -60,7 +60,7 @@ int arch_update_cpu_topology(void); * (in whatever arch specific measurement units returned by node_distance()) * then switch on zone reclaim on boot. */ -#define RECLAIM_DISTANCE 20 +#define RECLAIM_DISTANCE 30 #endif #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) -- cgit v1.2.3-18-g5258 From 5a1e6f75831bf1f8e596d642cd8a2512f11548fc Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 15 Jun 2011 15:08:21 -0700 Subject: drivers/misc/spear13xx_pcie_gadget.c: fix a memory leak in spear_pcie_gadget_probe error path In the case of goto err_kzalloc, we should kfree target. Signed-off-by: Axel Lin Acked-by: Pratyush Anand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/misc/spear13xx_pcie_gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/spear13xx_pcie_gadget.c b/drivers/misc/spear13xx_pcie_gadget.c index 7aded90f9da..cfbddbef11d 100644 --- a/drivers/misc/spear13xx_pcie_gadget.c +++ b/drivers/misc/spear13xx_pcie_gadget.c @@ -845,7 +845,7 @@ err_iounmap: err_iounmap_app: iounmap(config->va_app_base); err_kzalloc: - kfree(config); + kfree(target); err_rel_res: release_mem_region(res1->start, resource_size(res1)); err_rel_res0: -- cgit v1.2.3-18-g5258 From 4bbd61fb9726808e72ab2aa440401f6e5e1aa8f7 Mon Sep 17 00:00:00 2001 From: Christian Gmeiner Date: Wed, 15 Jun 2011 15:08:22 -0700 Subject: drivers/misc/cs5535-mfgpt.c: fix wrong if condition Fix the wrong `if' condition for the check if the requested timer is available. The bitmap avail is used to store if a timer is used already. test_bit() is used to check if the requested timer is available. If a bit in the avail bitmap is set it means that the timer is available. The runtime effect would be that allocating a specific timer always fails (versus telling cs5535_mfgpt_alloc_timer to allocate the first available timer, which works). Signed-off-by: Christian Gmeiner Acked-by: Andres Salomon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/misc/cs5535-mfgpt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/cs5535-mfgpt.c b/drivers/misc/cs5535-mfgpt.c index e01e08c8c88..bc685bfc4c3 100644 --- a/drivers/misc/cs5535-mfgpt.c +++ b/drivers/misc/cs5535-mfgpt.c @@ -174,7 +174,7 @@ struct cs5535_mfgpt_timer *cs5535_mfgpt_alloc_timer(int timer_nr, int domain) timer_nr = t < max ? (int) t : -1; } else { /* check if the requested timer's available */ - if (test_bit(timer_nr, mfgpt->avail)) + if (!test_bit(timer_nr, mfgpt->avail)) timer_nr = -1; } -- cgit v1.2.3-18-g5258 From 5f1a19070b16c20cdc71ed0e981bfa19f8f6a4ee Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 15 Jun 2011 15:08:23 -0700 Subject: mm: fix wrong kunmap_atomic() pointer Running a ktest.pl test, I hit the following bug on x86_32: ------------[ cut here ]------------ WARNING: at arch/x86/mm/highmem_32.c:81 __kunmap_atomic+0x64/0xc1() Hardware name: Modules linked in: Pid: 93, comm: sh Not tainted 2.6.39-test+ #1 Call Trace: [] warn_slowpath_common+0x7c/0x91 [] ? __kunmap_atomic+0x64/0xc1 [] ? __kunmap_atomic+0x64/0xc1^M [] warn_slowpath_null+0x22/0x24 [] __kunmap_atomic+0x64/0xc1 [] unmap_vmas+0x43a/0x4e0 [] exit_mmap+0x91/0xd2 [] mmput+0x43/0xad [] exit_mm+0x111/0x119 [] do_exit+0x1ff/0x5fa [] ? set_current_blocked+0x3c/0x40 [] ? sigprocmask+0x7e/0x8e [] do_group_exit+0x65/0x88 [] sys_exit_group+0x18/0x1c [] sysenter_do_call+0x12/0x38 ---[ end trace 8055f74ea3c0eb62 ]--- Running a ktest.pl git bisect, found the culprit: commit e303297e6c3a ("mm: extended batches for generic mmu_gather") But although this was the commit triggering the bug, it was not the one originally responsible for the bug. That was commit d16dfc550f53 ("mm: mmu_gather rework"). The code in zap_pte_range() has something that looks like the following: pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { [...] } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap_unlock(pte - 1, ptl); The pte starts off pointing at the first element in the page table directory that was returned by the pte_offset_map_lock(). When it's done with the page, pte will be pointing to anything between the next entry and the first entry of the next page inclusive. By doing a pte - 1, this puts the pte back onto the original page, which is all that pte_unmap_unlock() needs. In most archs (64 bit), this is not an issue as the pte is ignored in the pte_unmap_unlock(). But on 32 bit archs, where things may be kmapped, it is essential that the pte passed to pte_unmap_unlock() resides on the same page that was given by pte_offest_map_lock(). The problem came in d16dfc55 ("mm: mmu_gather rework") where it introduced a "break;" from the while loop. This alone did not seem to easily trigger the bug. But the modifications made by e303297e6 caused that "break;" to be hit on the first iteration, before the pte++. The pte not being incremented will now cause pte_unmap_unlock(pte - 1) to be pointing to the previous page. This will cause the wrong page to be unmapped, and also trigger the warning above. The simple solution is to just save the pointer given by pte_offset_map_lock() and use it in the unlock. Signed-off-by: Steven Rostedt Cc: Peter Zijlstra Cc: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index b13e7dbc399..87d935333f0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1112,11 +1112,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; + pte_t *start_pte; pte_t *pte; again: init_rss_vec(rss); - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = start_pte; arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; @@ -1196,7 +1198,7 @@ again: add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(start_pte, ptl); /* * mmu_gather ran out of room to batch pages, we break out of -- cgit v1.2.3-18-g5258 From 3957c7768e5ea02fd3345176ddd340f820e5d285 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 15 Jun 2011 15:08:25 -0700 Subject: mm: compaction: fix special case -1 order checks Commit 56de7263fcf3 ("mm: compaction: direct compact when a high-order allocation fails") introduced a check for cc->order == -1 in compact_finished. We should continue compacting in that case because the request came from userspace and there is no particular order to compact for. Similar check has been added by 82478fb7 (mm: compaction: prevent division-by-zero during user-requested compaction) for compaction_suitable. The check is, however, done after zone_watermark_ok which uses order as a right hand argument for shifts. Not only watermark check is pointless if we can break out without it but it also uses 1 << -1 which is not well defined (at least from C standard). Let's move the -1 check above zone_watermark_ok. [minchan.kim@gmail.com> - caught compaction_suitable] Signed-off-by: Michal Hocko Cc: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 021a2960ef9..94bdbe1f7ca 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -420,13 +420,6 @@ static int compact_finished(struct zone *zone, if (cc->free_pfn <= cc->migrate_pfn) return COMPACT_COMPLETE; - /* Compaction run is not finished if the watermark is not met */ - watermark = low_wmark_pages(zone); - watermark += (1 << cc->order); - - if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) - return COMPACT_CONTINUE; - /* * order == -1 is expected when compacting via * /proc/sys/vm/compact_memory @@ -434,6 +427,13 @@ static int compact_finished(struct zone *zone, if (cc->order == -1) return COMPACT_CONTINUE; + /* Compaction run is not finished if the watermark is not met */ + watermark = low_wmark_pages(zone); + watermark += (1 << cc->order); + + if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) + return COMPACT_CONTINUE; + /* Direct compactor: Is a suitable page free? */ for (order = cc->order; order < MAX_ORDER; order++) { /* Job done if page is free of the right migratetype */ @@ -460,6 +460,13 @@ unsigned long compaction_suitable(struct zone *zone, int order) int fragindex; unsigned long watermark; + /* + * order == -1 is expected when compacting via + * /proc/sys/vm/compact_memory + */ + if (order == -1) + return COMPACT_CONTINUE; + /* * Watermarks for order-0 must be met for compaction. Note the 2UL. * This is because during migration, copies of pages need to be @@ -469,13 +476,6 @@ unsigned long compaction_suitable(struct zone *zone, int order) if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) return COMPACT_SKIPPED; - /* - * order == -1 is expected when compacting via - * /proc/sys/vm/compact_memory - */ - if (order == -1) - return COMPACT_CONTINUE; - /* * fragmentation index determines if allocation failures are due to * low memory or external fragmentation -- cgit v1.2.3-18-g5258 From ca39599c633fb02aceac31a7e67563612e4fe347 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Wed, 15 Jun 2011 15:08:27 -0700 Subject: BUILD_BUG_ON_ZERO: fix sparse breakage BUILD_BUG_ON_ZERO and BUILD_BUG_ON_NULL must return values, even in the CHECKER case otherwise various users of it become syntactically invalid. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fb0e7329fee..953352a8833 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -671,8 +671,8 @@ struct sysinfo { #ifdef __CHECKER__ #define BUILD_BUG_ON_NOT_POWER_OF_2(n) -#define BUILD_BUG_ON_ZERO(e) -#define BUILD_BUG_ON_NULL(e) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void*)0) #define BUILD_BUG_ON(condition) #else /* __CHECKER__ */ -- cgit v1.2.3-18-g5258 From bd5dc17be87b3a3073d50b23802647db3ae3fa8e Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Wed, 15 Jun 2011 15:08:28 -0700 Subject: uts: make default hostname configurable, rather than always using "(none)" The "hostname" tool falls back to setting the hostname to "localhost" if /etc/hostname does not exist. Distribution init scripts have the same fallback. However, if userspace never calls sethostname, such as when booting with init=/bin/sh, or otherwise booting a minimal system without the usual init scripts, the default hostname of "(none)" remains, unhelpfully appearing in various places such as prompts ("root@(none):~#") and logs. Furthermore, "(none)" doesn't typically resolve to anything useful. Make the default hostname configurable. This removes the need for the standard fallback, provides a useful default for systems that never call sethostname, and makes minimal systems that much more useful with less configuration. Distributions could choose to use "localhost" here to avoid the fallback, while embedded systems may wish to use a specific target hostname. Signed-off-by: Josh Triplett Acked-by: Linus Torvalds Acked-by: David Miller Cc: Serge Hallyn Cc: Kel Modderman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uts.h | 2 +- init/Kconfig | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/linux/uts.h b/include/linux/uts.h index 73eb1ed36ec..6ddbd86377d 100644 --- a/include/linux/uts.h +++ b/include/linux/uts.h @@ -9,7 +9,7 @@ #endif #ifndef UTS_NODENAME -#define UTS_NODENAME "(none)" /* set by sethostname() */ +#define UTS_NODENAME CONFIG_DEFAULT_HOSTNAME /* set by sethostname() */ #endif #ifndef UTS_DOMAINNAME diff --git a/init/Kconfig b/init/Kconfig index ebafac4231e..e0a22e42d39 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -204,6 +204,15 @@ config KERNEL_LZO endchoice +config DEFAULT_HOSTNAME + string "Default hostname" + default "(none)" + help + This option determines the default system hostname before userspace + calls sethostname(2). The kernel traditionally uses "(none)" here, + but you may wish to use a different default here to make a minimal + system more usable with less configuration. + config SWAP bool "Support for paging of anonymous memory (swap)" depends on MMU && BLOCK -- cgit v1.2.3-18-g5258 From 185e595f770219f2329e590a6be69e6e89e152af Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 15 Jun 2011 15:08:30 -0700 Subject: MAINTAINERS: Balbir has moved Update my email address. Email will start to the old address bouncing soon Signed-off-by: Balbir Singh Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2cc3a943050..88c016d209f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4144,7 +4144,7 @@ F: include/linux/mm.h F: mm/ MEMORY RESOURCE CONTROLLER -M: Balbir Singh +M: Balbir Singh M: Daisuke Nishimura M: KAMEZAWA Hiroyuki L: linux-mm@kvack.org @@ -4889,7 +4889,7 @@ F: mm/percpu*.c F: arch/*/include/asm/percpu.h PER-TASK DELAY ACCOUNTING -M: Balbir Singh +M: Balbir Singh S: Maintained F: include/linux/delayacct.h F: kernel/delayacct.c @@ -6097,7 +6097,7 @@ F: include/target/ F: Documentation/target/ TASKSTATS STATISTICS INTERFACE -M: Balbir Singh +M: Balbir Singh S: Maintained F: Documentation/accounting/taskstats* F: include/linux/taskstats* -- cgit v1.2.3-18-g5258 From 9d8f776bfb812dd23fcdbb698e9ac4298fc3c624 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 15 Jun 2011 15:08:31 -0700 Subject: drivers/leds/leds-asic3: make LEDS_ASIC3 depend on LEDS_CLASS We call led_classdev_unregister/led_classdev_register in asic3_led_remove/asic3_led_probe, thus make LEDS_ASIC3 depend on LEDS_CLASS. This patch fixes below build error if LEDS_CLASS is not configured. LD .tmp_vmlinux1 drivers/built-in.o: In function `asic3_led_remove': clkdev.c:(.devexit.text+0x1860): undefined reference to `led_classdev_unregister' drivers/built-in.o: In function `asic3_led_probe': clkdev.c:(.devinit.text+0xcee8): undefined reference to `led_classdev_register' make: *** [.tmp_vmlinux1] Error 1 Signed-off-by: Axel Lin Cc: Paul Parsons Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/leds/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 23f0d5e99f3..883813d7843 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -391,6 +391,7 @@ config LEDS_NETXBIG config LEDS_ASIC3 bool "LED support for the HTC ASIC3" + depends on LEDS_CLASS depends on MFD_ASIC3 default y help -- cgit v1.2.3-18-g5258 From be5ce2f1c93295711be4ae5565f9194ed9776ea7 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Wed, 15 Jun 2011 15:08:31 -0700 Subject: leds: move LEDS_GPIO_REGISTER out of menuconfig NEW_LEDS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 4440673a95e6 ("leds: provide helper to register "leds-gpio" devices") broke the display of the NEW_LEDS menu as it didn't depend on NEW_LEDS and so made "LED drivers" and "LED Triggers" appear at the same level as "LED Support" instead of below it as it was before 4440673a. Moving LEDS_GPIO_REGISTER out of the menuconfig NEW_LEDS fixes this unintended side effect. Reported-by: Axel Lin Signed-off-by: Uwe Kleine-König Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/leds/Kconfig | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 883813d7843..1032730cd17 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -1,3 +1,10 @@ +config LEDS_GPIO_REGISTER + bool + help + This option provides the function gpio_led_register_device. + As this function is used by arch code it must not be compiled as a + module. + menuconfig NEW_LEDS bool "LED Support" help @@ -14,13 +21,6 @@ config LEDS_CLASS This option enables the led sysfs class in /sys/class/leds. You'll need this to do anything useful with LEDs. If unsure, say N. -config LEDS_GPIO_REGISTER - bool - help - This option provides the function gpio_led_register_device. - As this function is used by arch code it must not be compiled as a - module. - if NEW_LEDS comment "LED drivers" -- cgit v1.2.3-18-g5258 From 9e6f343852cb16ea961ba5be2ca8dde609aa6f23 Mon Sep 17 00:00:00 2001 From: Pawel Osciak Date: Wed, 15 Jun 2011 15:08:32 -0700 Subject: MAINTAINERS: add videobuf2 maintainers Add maintainers for the videobuf2 V4L2 driver framework. Signed-off-by: Pawel Osciak Acked-by: Marek Szyprowski Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 88c016d209f..518442ab25a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6716,6 +6716,14 @@ S: Maintained F: Documentation/filesystems/vfat.txt F: fs/fat/ +VIDEOBUF2 FRAMEWORK +M: Pawel Osciak +M: Marek Szyprowski +L: linux-media@vger.kernel.org +S: Maintained +F: drivers/media/video/videobuf2-* +F: include/media/videobuf2-* + VIRTIO CONSOLE DRIVER M: Amit Shah L: virtualization@lists.linux-foundation.org -- cgit v1.2.3-18-g5258 From 49b24d6b41c576ba43153fc94695f871cce139a5 Mon Sep 17 00:00:00 2001 From: Nicolas Kaiser Date: Wed, 15 Jun 2011 15:08:34 -0700 Subject: include/asm-generic/pgtable.h: fix unbalanced parenthesis Signed-off-by: Nicolas Kaiser Reviewed-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index e9b8e5926be..76bff2bff15 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -88,7 +88,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, pmd_t pmd = *pmdp; pmd_clear(mm, address, pmdp); return pmd; -}) +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -- cgit v1.2.3-18-g5258 From 26575f9544530127757297d4de8fb2f2c75f1f69 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 15 Jun 2011 15:08:35 -0700 Subject: w1: W1_MASTER_DS1WM should depend on GENERIC_HARDIRQS On m68k (which doesn't support generic hardirqs yet): drivers/w1/masters/ds1wm.c: In function `ds1wm_probe': drivers/w1/masters/ds1wm.c: error: implicit declaration of function `irq_set_irq_type' Signed-off-by: Geert Uytterhoeven Cc: Evgeniy Polyakov Cc: Jean-Franois Dagenais Cc: Matt Reimer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/w1/masters/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig index 00d615d7aa2..979d6eed9a0 100644 --- a/drivers/w1/masters/Kconfig +++ b/drivers/w1/masters/Kconfig @@ -42,7 +42,7 @@ config W1_MASTER_MXC config W1_MASTER_DS1WM tristate "Maxim DS1WM 1-wire busmaster" - depends on W1 + depends on W1 && GENERIC_HARDIRQS help Say Y here to enable the DS1WM 1-wire driver, such as that in HP iPAQ devices like h5xxx, h2200, and ASIC3-based like -- cgit v1.2.3-18-g5258 From de695e159e3fd679594eb45449d2638d54434c32 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 15 Jun 2011 15:08:37 -0700 Subject: init/calibrate.c: remove annoying printk Remove calibrate_delay_direct()'s KERN_DEBUG printk related to bogomips calculation as it appears when booting every core on setups with 'ignore_loglevel' which dmesg people scan for possible issues. As the message doesn't show very useful information to the widest audience of kernel boot message gazers, it should be removed. Introduced by commit d2b463135f84 ("init/calibrate.c: fix for critical bogoMIPS intermittent calculation failure"). Signed-off-by: Borislav Petkov Cc: Andrew Worsley Cc: Phil Carmody Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/calibrate.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/init/calibrate.c b/init/calibrate.c index cfd7000c9d7..2568d22a304 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -93,9 +93,6 @@ static unsigned long __cpuinit calibrate_delay_direct(void) * If the upper limit and lower limit of the timer_rate is * >= 12.5% apart, redo calibration. */ - printk(KERN_DEBUG "calibrate_delay_direct() timer_rate_max=%lu " - "timer_rate_min=%lu pre_start=%lu pre_end=%lu\n", - timer_rate_max, timer_rate_min, pre_start, pre_end); if (start >= post_end) printk(KERN_NOTICE "calibrate_delay_direct() ignoring " "timer_rate as we had a TSC wrap around" -- cgit v1.2.3-18-g5258 From 959ecc48fc7506b9d7825ea70e40d92d9b308033 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:38 -0700 Subject: mm/memory_hotplug.c: fix building of node hotplug zonelist During memory hotplug we refresh zonelists when we online a page in a new zone. It means that the node's zonelist is not initialized until pages are onlined. So for example, "nid" passed by MEM_GOING_ONLINE notifier will point to NODE_DATA(nid) which has no zone fallback list. Moreover, if we hot-add cpu-only nodes, alloc_pages() will do no fallback. This patch makes a zonelist when a new pgdata is available. Note: in production, at fujitsu, memory should be onlined before cpu and our server didn't have any memory-less nodes and had no problems. But recent changes in MEM_GOING_ONLINE+page_cgroup will access not initialized zonelist of node. Anyway, there are memory-less node and we need some care. Signed-off-by: KAMEZAWA Hiroyuki Cc: Mel Gorman Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9f646374e32..02159c75513 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -494,6 +494,12 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) /* init node's zones as empty zones, we don't have any present pages.*/ free_area_init_node(nid, zones_size, start_pfn, zholes_size); + /* + * The node we allocated has no zone fallback lists. For avoiding + * to access not-initialized zonelist, build here. + */ + build_all_zonelists(NULL); + return pgdat; } -- cgit v1.2.3-18-g5258 From b0320c7b7d1ac1bd5c2d9dff3258524ab39bad32 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Wed, 15 Jun 2011 15:08:39 -0700 Subject: mm: fix negative commitlimit when gigantic hugepages are allocated When 1GB hugepages are allocated on a system, free(1) reports less available memory than what really is installed in the box. Also, if the total size of hugepages allocated on a system is over half of the total memory size, CommitLimit becomes a negative number. The problem is that gigantic hugepages (order > MAX_ORDER) can only be allocated at boot with bootmem, thus its frames are not accounted to 'totalram_pages'. However, they are accounted to hugetlb_total_pages() What happens to turn CommitLimit into a negative number is this calculation, in fs/proc/meminfo.c: allowed = ((totalram_pages - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100) + total_swap_pages; A similar calculation occurs in __vm_enough_memory() in mm/mmap.c. Also, every vm statistic which depends on 'totalram_pages' will render confusing values, as if system were 'missing' some part of its memory. Impact of this bug: When gigantic hugepages are allocated and sysctl_overcommit_memory == OVERCOMMIT_NEVER. In a such situation, __vm_enough_memory() goes through the mentioned 'allowed' calculation and might end up mistakenly returning -ENOMEM, thus forcing the system to start reclaiming pages earlier than it would be ususal, and this could cause detrimental impact to overall system's performance, depending on the workload. Besides the aforementioned scenario, I can only think of this causing annoyances with memory reports from /proc/meminfo and free(1). [akpm@linux-foundation.org: standardize comment layout] Reported-by: Russ Anderson Signed-off-by: Rafael Aquini Acked-by: Russ Anderson Cc: Andrea Arcangeli Cc: Christoph Lameter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6402458fee3..bfcf153bc82 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1111,6 +1111,14 @@ static void __init gather_bootmem_prealloc(void) WARN_ON(page_count(page) != 1); prep_compound_huge_page(page, h->order); prep_new_huge_page(h, page, page_to_nid(page)); + /* + * If we had gigantic hugepages allocated at boot time, we need + * to restore the 'stolen' pages to totalram_pages in order to + * fix confusing memory reports from free(1) and another + * side-effects, like CommitLimit going negative. + */ + if (h->order > (MAX_ORDER - 1)) + totalram_pages += 1 << h->order; } } -- cgit v1.2.3-18-g5258 From 45d16f09ddd66597e561876f5652c05bf986360a Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Wed, 15 Jun 2011 15:08:40 -0700 Subject: leds: fix the incorrect display in menuconfig Seems when a config option does not have a dependency of the menuconfig, it messes the display of the rest configs, even if it's a hidden one. Signed-off-by: Eric Miao Cc: Richard Purdie Cc: Valdis Kletnieks Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/leds/Kconfig | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 1032730cd17..713d43b4e56 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -14,15 +14,14 @@ menuconfig NEW_LEDS This is not related to standard keyboard LEDs which are controlled via the input system. +if NEW_LEDS + config LEDS_CLASS bool "LED Class Support" - depends on NEW_LEDS help This option enables the led sysfs class in /sys/class/leds. You'll need this to do anything useful with LEDs. If unsure, say N. -if NEW_LEDS - comment "LED drivers" config LEDS_88PM860X -- cgit v1.2.3-18-g5258 From 8957712710e045044e3c44375c6a87d7ffa17d51 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:41 -0700 Subject: mm: memory.numa_stat: fix file permission Commit 406eb0c9ba76 ("memcg: add memory.numastat api for numa statistics") adds memory.numa_stat file for memory cgroup. But the file permissions are wrong. [kamezawa@bluextal linux-2.6]$ ls -l /cgroup/memory/A/memory.numa_stat ---------- 1 root root 0 Jun 9 18:36 /cgroup/memory/A/memory.numa_stat This patch fixes the permission as [root@bluextal kamezawa]# ls -l /cgroup/memory/A/memory.numa_stat -r--r--r-- 1 root root 0 Jun 10 16:49 /cgroup/memory/A/memory.numa_stat Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e37c44d88d4..02a7947608a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4640,6 +4640,7 @@ static struct cftype mem_cgroup_files[] = { { .name = "numa_stat", .open = mem_control_numa_stat_open, + .mode = S_IRUGO, }, #endif }; -- cgit v1.2.3-18-g5258 From 37573e8c718277103f61f03741bdc5606d31b07e Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:42 -0700 Subject: memcg: fix init_page_cgroup nid with sparsemem Commit 21a3c9646873 ("memcg: allocate memory cgroup structures in local nodes") makes page_cgroup allocation as NUMA aware. But that caused a problem https://bugzilla.kernel.org/show_bug.cgi?id=36192. The problem was getting a NID from invalid struct pages, which was not initialized because it was out-of-node, out of [node_start_pfn, node_end_pfn) Now, with sparsemem, page_cgroup_init scans pfn from 0 to max_pfn. But this may scan a pfn which is not on any node and can access memmap which is not initialized. This makes page_cgroup_init() for SPARSEMEM node aware and remove a code to get nid from page->flags. (Then, we'll use valid NID always.) [akpm@linux-foundation.org: try to fix up comments] Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_cgroup.c | 71 ++++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 53 insertions(+), 18 deletions(-) diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 74ccff61d1b..53bffc6c293 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -162,13 +162,13 @@ static void free_page_cgroup(void *addr) } #endif -static int __meminit init_section_page_cgroup(unsigned long pfn) +static int __meminit init_section_page_cgroup(unsigned long pfn, int nid) { struct page_cgroup *base, *pc; struct mem_section *section; unsigned long table_size; unsigned long nr; - int nid, index; + int index; nr = pfn_to_section_nr(pfn); section = __nr_to_section(nr); @@ -176,7 +176,6 @@ static int __meminit init_section_page_cgroup(unsigned long pfn) if (section->page_cgroup) return 0; - nid = page_to_nid(pfn_to_page(pfn)); table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; base = alloc_page_cgroup(table_size, nid); @@ -196,7 +195,11 @@ static int __meminit init_section_page_cgroup(unsigned long pfn) pc = base + index; init_page_cgroup(pc, nr); } - + /* + * The passed "pfn" may not be aligned to SECTION. For the calculation + * we need to apply a mask. + */ + pfn &= PAGE_SECTION_MASK; section->page_cgroup = base - pfn; total_usage += table_size; return 0; @@ -225,10 +228,20 @@ int __meminit online_page_cgroup(unsigned long start_pfn, start = start_pfn & ~(PAGES_PER_SECTION - 1); end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION); + if (nid == -1) { + /* + * In this case, "nid" already exists and contains valid memory. + * "start_pfn" passed to us is a pfn which is an arg for + * online__pages(), and start_pfn should exist. + */ + nid = pfn_to_nid(start_pfn); + VM_BUG_ON(!node_state(nid, N_ONLINE)); + } + for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) { if (!pfn_present(pfn)) continue; - fail = init_section_page_cgroup(pfn); + fail = init_section_page_cgroup(pfn, nid); } if (!fail) return 0; @@ -284,25 +297,47 @@ static int __meminit page_cgroup_callback(struct notifier_block *self, void __init page_cgroup_init(void) { unsigned long pfn; - int fail = 0; + int nid; if (mem_cgroup_disabled()) return; - for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) { - if (!pfn_present(pfn)) - continue; - fail = init_section_page_cgroup(pfn); - } - if (fail) { - printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n"); - panic("Out of memory"); - } else { - hotplug_memory_notifier(page_cgroup_callback, 0); + for_each_node_state(nid, N_HIGH_MEMORY) { + unsigned long start_pfn, end_pfn; + + start_pfn = node_start_pfn(nid); + end_pfn = node_end_pfn(nid); + /* + * start_pfn and end_pfn may not be aligned to SECTION and the + * page->flags of out of node pages are not initialized. So we + * scan [start_pfn, the biggest section's pfn < end_pfn) here. + */ + for (pfn = start_pfn; + pfn < end_pfn; + pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { + + if (!pfn_valid(pfn)) + continue; + /* + * Nodes's pfns can be overlapping. + * We know some arch can have a nodes layout such as + * -------------pfn--------------> + * N0 | N1 | N2 | N0 | N1 | N2|.... + */ + if (pfn_to_nid(pfn) != nid) + continue; + if (init_section_page_cgroup(pfn, nid)) + goto oom; + } } + hotplug_memory_notifier(page_cgroup_callback, 0); printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage); - printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't" - " want memory cgroups\n"); + printk(KERN_INFO "please try 'cgroup_disable=memory' option if you " + "don't want memory cgroups\n"); + return; +oom: + printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n"); + panic("Out of memory"); } void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) -- cgit v1.2.3-18-g5258 From 733eda7ac316cd4e550fa096e4ed42356dc546e7 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:43 -0700 Subject: memcg: clear mm->owner when last possible owner leaves The following crash was reported: > Call Trace: > [] mem_cgroup_from_task+0x15/0x17 > [] __mem_cgroup_try_charge+0x148/0x4b4 > [] ? need_resched+0x23/0x2d > [] ? preempt_schedule+0x46/0x4f > [] mem_cgroup_charge_common+0x9a/0xce > [] mem_cgroup_newpage_charge+0x5d/0x5f > [] khugepaged+0x5da/0xfaf > [] ? __init_waitqueue_head+0x4b/0x4b > [] ? add_mm_counter.constprop.5+0x13/0x13 > [] kthread+0xa8/0xb0 > [] ? sub_preempt_count+0xa1/0xb4 > [] kernel_thread_helper+0x4/0x10 > [] ? retint_restore_args+0x13/0x13 > [] ? __init_kthread_worker+0x5a/0x5a What happens is that khugepaged tries to charge a huge page against an mm whose last possible owner has already exited, and the memory controller crashes when the stale mm->owner is used to look up the cgroup to charge. mm->owner has never been set to NULL with the last owner going away, but nobody cared until khugepaged came along. Even then it wasn't a problem because the final mmput() on an mm was forced to acquire and release mmap_sem in write-mode, preventing an exiting owner to go away while the mmap_sem was held, and until "692e0b3 mm: thp: optimize memcg charge in khugepaged", the memory cgroup charge was protected by mmap_sem in read-mode. Instead of going back to relying on the mmap_sem to enforce lifetime of a task, this patch ensures that mm->owner is properly set to NULL when the last possible owner is exiting, which the memory controller can handle just fine. [akpm@linux-foundation.org: tweak comments] Signed-off-by: Hugh Dickins Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Johannes Weiner Reported-by: Hugh Dickins Reported-by: Dave Jones Reviewed-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 20a40647152..f2b321bae44 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -561,29 +561,28 @@ void exit_files(struct task_struct *tsk) #ifdef CONFIG_MM_OWNER /* - * Task p is exiting and it owned mm, lets find a new owner for it + * A task is exiting. If it owned this mm, find a new owner for the mm. */ -static inline int -mm_need_new_owner(struct mm_struct *mm, struct task_struct *p) -{ - /* - * If there are other users of the mm and the owner (us) is exiting - * we need to find a new owner to take on the responsibility. - */ - if (atomic_read(&mm->mm_users) <= 1) - return 0; - if (mm->owner != p) - return 0; - return 1; -} - void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: - if (!mm_need_new_owner(mm, p)) + /* + * If the exiting or execing task is not the owner, it's + * someone else's problem. + */ + if (mm->owner != p) return; + /* + * The current owner is exiting/execing and there are no other + * candidates. Do not leave the mm pointing to a possibly + * freed task structure. + */ + if (atomic_read(&mm->mm_users) <= 1) { + mm->owner = NULL; + return; + } read_lock(&tasklist_lock); /* -- cgit v1.2.3-18-g5258 From 7ae534d074e01e54d5cfbc9734b73fdfc855501f Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:44 -0700 Subject: memcg: fix wrong check of noswap with softlimit Hierarchical reclaim doesn't swap out if memsw and resource limits are thye same (memsw_is_minimum == true) because we would hit mem+swap limit anyway (during hard limit reclaim). If it comes to the soft limit we shouldn't consider memsw_is_minimum at all because it doesn't make much sense. Either the soft limit is bellow the hard limit and then we cannot hit mem+swap limit or the direct reclaim takes a precedence. Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Michal Hocko Acked-by: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 02a7947608a..0b1a32cbd74 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1663,7 +1663,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT; /* If memsw_is_minimum==1, swap-out is of-no-use. */ - if (root_mem->memsw_is_minimum) + if (!check_soft && root_mem->memsw_is_minimum) noswap = true; while (1) { -- cgit v1.2.3-18-g5258 From 26fe616844491a41a1abc02e29f7a9d1ec2f8ddb Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:45 -0700 Subject: memcg: fix percpu cached charge draining frequency For performance, memory cgroup caches some "charge" from res_counter into per cpu cache. This works well but because it's cache, it needs to be flushed in some cases. Typical cases are 1. when someone hit limit. 2. when rmdir() is called and need to charges to be 0. But "1" has problem. Recently, with large SMP machines, we see many kworker runs because of flushing memcg's cache. Bad things in implementation are that even if a cpu contains a cache for memcg not related to a memcg which hits limit, drain code is called. This patch does A) check percpu cache contains a useful data or not. B) check other asynchronous percpu draining doesn't run. C) don't call local cpu callback. (*)This patch avoid changing the calling condition with hard-limit. When I run "cat 1Gfile > /dev/null" under 300M limit memcg, [Before] 13767 kamezawa 20 0 98.6m 424 416 D 10.0 0.0 0:00.61 cat 58 root 20 0 0 0 0 S 0.6 0.0 0:00.09 kworker/2:1 60 root 20 0 0 0 0 S 0.6 0.0 0:00.08 kworker/4:1 4 root 20 0 0 0 0 S 0.3 0.0 0:00.02 kworker/0:0 57 root 20 0 0 0 0 S 0.3 0.0 0:00.05 kworker/1:1 61 root 20 0 0 0 0 S 0.3 0.0 0:00.05 kworker/5:1 62 root 20 0 0 0 0 S 0.3 0.0 0:00.05 kworker/6:1 63 root 20 0 0 0 0 S 0.3 0.0 0:00.05 kworker/7:1 [After] 2676 root 20 0 98.6m 416 416 D 9.3 0.0 0:00.87 cat 2626 kamezawa 20 0 15192 1312 920 R 0.3 0.0 0:00.28 top 1 root 20 0 19384 1496 1204 S 0.0 0.0 0:00.66 init 2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd 3 root 20 0 0 0 0 S 0.0 0.0 0:00.00 ksoftirqd/0 4 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kworker/0:0 [akpm@linux-foundation.org: make percpu_charge_mutex static, tweak comments] Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Daisuke Nishimura Reviewed-by: Michal Hocko Tested-by: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 54 ++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 16 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0b1a32cbd74..c39a177bb64 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -359,7 +359,7 @@ enum charge_type { static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); -static void drain_all_stock_async(void); +static void drain_all_stock_async(struct mem_cgroup *mem); static struct mem_cgroup_per_zone * mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) @@ -1671,7 +1671,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, if (victim == root_mem) { loop++; if (loop >= 1) - drain_all_stock_async(); + drain_all_stock_async(root_mem); if (loop >= 2) { /* * If we have not been able to reclaim @@ -1934,9 +1934,11 @@ struct memcg_stock_pcp { struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; struct work_struct work; + unsigned long flags; +#define FLUSHING_CACHED_CHARGE (0) }; static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); -static atomic_t memcg_drain_count; +static DEFINE_MUTEX(percpu_charge_mutex); /* * Try to consume stocked charge on this cpu. If success, one page is consumed @@ -1984,6 +1986,7 @@ static void drain_local_stock(struct work_struct *dummy) { struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); drain_stock(stock); + clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } /* @@ -2008,26 +2011,45 @@ static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages) * expects some charges will be back to res_counter later but cannot wait for * it. */ -static void drain_all_stock_async(void) +static void drain_all_stock_async(struct mem_cgroup *root_mem) { - int cpu; - /* This function is for scheduling "drain" in asynchronous way. - * The result of "drain" is not directly handled by callers. Then, - * if someone is calling drain, we don't have to call drain more. - * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if - * there is a race. We just do loose check here. + int cpu, curcpu; + /* + * If someone calls draining, avoid adding more kworker runs. */ - if (atomic_read(&memcg_drain_count)) + if (!mutex_trylock(&percpu_charge_mutex)) return; /* Notify other cpus that system-wide "drain" is running */ - atomic_inc(&memcg_drain_count); get_online_cpus(); + /* + * Get a hint for avoiding draining charges on the current cpu, + * which must be exhausted by our charging. It is not required that + * this be a precise check, so we use raw_smp_processor_id() instead of + * getcpu()/putcpu(). + */ + curcpu = raw_smp_processor_id(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); - schedule_work_on(cpu, &stock->work); + struct mem_cgroup *mem; + + if (cpu == curcpu) + continue; + + mem = stock->cached; + if (!mem) + continue; + if (mem != root_mem) { + if (!root_mem->use_hierarchy) + continue; + /* check whether "mem" is under tree of "root_mem" */ + if (!css_is_ancestor(&mem->css, &root_mem->css)) + continue; + } + if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) + schedule_work_on(cpu, &stock->work); } put_online_cpus(); - atomic_dec(&memcg_drain_count); + mutex_unlock(&percpu_charge_mutex); /* We don't wait for flush_work */ } @@ -2035,9 +2057,9 @@ static void drain_all_stock_async(void) static void drain_all_stock_sync(void) { /* called when force_empty is called */ - atomic_inc(&memcg_drain_count); + mutex_lock(&percpu_charge_mutex); schedule_on_each_cpu(drain_local_stock); - atomic_dec(&memcg_drain_count); + mutex_unlock(&percpu_charge_mutex); } /* -- cgit v1.2.3-18-g5258 From fbc29a25e484be073e7d762c9f7f1d4bf8aecc48 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 15 Jun 2011 15:08:46 -0700 Subject: memcg: avoid percpu cached charge draining at softlimit Based on Michal Hocko's comment. We are not draining per cpu cached charges during soft limit reclaim because background reclaim doesn't care about charges. It tries to free some memory and charges will not give any. Cached charges might influence only selection of the biggest soft limit offender but as the call is done only after the selection has been already done it makes no change. Signed-off-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c39a177bb64..cf7d027a884 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1670,7 +1670,13 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, victim = mem_cgroup_select_victim(root_mem); if (victim == root_mem) { loop++; - if (loop >= 1) + /* + * We are not draining per cpu cached charges during + * soft limit reclaim because global reclaim doesn't + * care about charges. It tries to free some memory and + * charges will not give any. + */ + if (!check_soft && loop >= 1) drain_all_stock_async(root_mem); if (loop >= 2) { /* -- cgit v1.2.3-18-g5258 From b0461a44a2f1fc052fc949ae19c3a5d684627b09 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 15 Jun 2011 15:08:46 -0700 Subject: MAINTAINERS: add entry for legacy eeprom driver I shall maintain the legacy eeprom driver, until we finally get rid of it. Signed-off-by: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 518442ab25a..6c59eb90fdf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3819,6 +3819,12 @@ S: Maintained F: drivers/leds/ F: include/linux/leds.h +LEGACY EEPROM DRIVER +M: Jean Delvare +S: Maintained +F: Documentation/misc-devices/eeprom +F: drivers/misc/eeprom/eeprom.c + LEGO USB Tower driver M: Juergen Stuber L: legousb-devel@lists.sourceforge.net -- cgit v1.2.3-18-g5258 From d2c32258798f813dc2be6cbc32f78aa5ac5cb205 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Wed, 15 Jun 2011 15:08:47 -0700 Subject: gcov: disable CONFIG_CONSTRUCTORS when not needed by CONFIG_GCOV_KERNEL CONFIG_CONSTRUCTORS controls support for running constructor functions at kernel init time. According to commit b99b87f70c7785ab ("kernel: constructor support"), gcov (CONFIG_GCOV_KERNEL) needs this. However, CONFIG_CONSTRUCTORS currently defaults to y, with no option to disable it, and CONFIG_GCOV_KERNEL depends on it. Instead, default it to n and have CONFIG_GCOV_KERNEL select it, so that the normal case of CONFIG_GCOV_KERNEL=n will result in CONFIG_CONSTRUCTORS=n. Observed in the short list of =y values in a minimal kernel configuration. Signed-off-by: Josh Triplett Acked-by: WANG Cong Acked-by: Peter Oberparleiter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 1 - kernel/gcov/Kconfig | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index e0a22e42d39..412c21b00d5 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -19,7 +19,6 @@ config DEFCONFIG_LIST config CONSTRUCTORS bool depends on !UML - default y config HAVE_IRQ_WORK bool diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index b8cadf70b1f..5bf924d80b5 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -2,7 +2,8 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" - depends on DEBUG_FS && CONSTRUCTORS + depends on DEBUG_FS + select CONSTRUCTORS default n ---help--- This option enables gcov-based code profiling (e.g. for code coverage -- cgit v1.2.3-18-g5258 From 5db8a73a8d7cc6a66afbf25ed7fda338caa8f5f9 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Wed, 15 Jun 2011 15:08:48 -0700 Subject: mm/memory-failure.c: fix page isolated count mismatch Pages isolated for migration are accounted with the vmstat counters NR_ISOLATE_[ANON|FILE]. Callers of migrate_pages() are expected to increment these counters when pages are isolated from the LRU. Once the pages have been migrated, they are put back on the LRU or freed and the isolated count is decremented. Memory failure is not properly accounting for pages it isolates causing the NR_ISOLATED counters to be negative. On SMP builds, this goes unnoticed as negative counters are treated as 0 due to expected per-cpu drift. On UP builds, the counter is treated by too_many_isolated() as a large value causing processes to enter D state during page reclaim or compaction. This patch accounts for pages isolated by memory failure correctly. [mel@csn.ul.ie: rewrote changelog] Reviewed-by: Andrea Arcangeli Signed-off-by: Minchan Kim Cc: Andi Kleen Acked-by: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5c8f7e08928..eac0ba56149 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -52,6 +52,7 @@ #include #include #include +#include #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1468,7 +1469,8 @@ int soft_offline_page(struct page *page, int flags) put_page(page); if (!ret) { LIST_HEAD(pagelist); - + inc_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, true); -- cgit v1.2.3-18-g5258 From a582a738c763e106f47eab24b8146c698a9c700b Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 15 Jun 2011 15:08:49 -0700 Subject: compaction: checks correct fragmentation index fragmentation_index() returns -1000 when the allocation might succeed This doesn't match the comment and code in compaction_suitable(). I thought compaction_suitable should return COMPACT_PARTIAL in -1000 case, because in this case allocation could succeed depending on watermarks. The impact of this is that compaction starts and compact_finished() is called which rechecks the watermarks and the free lists. It should have the same result in that compaction should not start but is more expensive. Acked-by: Mel Gorman Signed-off-by: Shaohua Li Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 94bdbe1f7ca..cf7086c6dc0 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -480,7 +480,8 @@ unsigned long compaction_suitable(struct zone *zone, int order) * fragmentation index determines if allocation failures are due to * low memory or external fragmentation * - * index of -1 implies allocations might succeed dependingon watermarks + * index of -1000 implies allocations might succeed depending on + * watermarks * index towards 0 implies failure is due to lack of memory * index towards 1000 implies failure is due to fragmentation * @@ -490,7 +491,8 @@ unsigned long compaction_suitable(struct zone *zone, int order) if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) return COMPACT_SKIPPED; - if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) + if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark, + 0, 0)) return COMPACT_PARTIAL; return COMPACT_CONTINUE; -- cgit v1.2.3-18-g5258 From 7454f4ba40b419eb999a3c61a99da662bf1a2bb8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 15 Jun 2011 15:08:50 -0700 Subject: mm: compaction: ensure that the compaction free scanner does not move to the next zone Compaction works with two scanners, a migration and a free scanner. When the scanners crossover, migration within the zone is complete. The location of the scanner is recorded on each cycle to avoid excesive scanning. When a zone is small and mostly reserved, it's very easy for the migration scanner to be close to the end of the zone. Then the following situation can occurs o migration scanner isolates some pages near the end of the zone o free scanner starts at the end of the zone but finds that the migration scanner is already there o free scanner gets reinitialised for the next cycle as cc->migrate_pfn + pageblock_nr_pages moving the free scanner into the next zone o migration scanner moves into the next zone When this happens, NR_ISOLATED accounting goes haywire because some of the accounting happens against the wrong zone. One zones counter remains positive while the other goes negative even though the overall global count is accurate. This was reported on X86-32 with !SMP because !SMP allows the negative counters to be visible. The fact that it is the bug should theoritically be possible there. Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/mm/compaction.c b/mm/compaction.c index cf7086c6dc0..9b94eaf537e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -144,9 +144,20 @@ static void isolate_freepages(struct zone *zone, int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; + /* + * Initialise the free scanner. The starting point is where we last + * scanned from (or the end of the zone if starting). The low point + * is the end of the pageblock the migration scanner is using. + */ pfn = cc->free_pfn; low_pfn = cc->migrate_pfn + pageblock_nr_pages; - high_pfn = low_pfn; + + /* + * Take care that if the migration scanner is at the end of the zone + * that the free scanner does not accidentally move to the next zone + * in the next isolation cycle. + */ + high_pfn = min(low_pfn, pfn); /* * Isolate free pages until enough are available to migrate the -- cgit v1.2.3-18-g5258 From d179e84ba5da1d0024087d1759a2938817a00f3f Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 15 Jun 2011 15:08:51 -0700 Subject: mm: vmscan: do not use page_count without a page pin It is unsafe to run page_count during the physical pfn scan because compound_head could trip on a dangling pointer when reading page->first_page if the compound page is being freed by another CPU. [mgorman@suse.de: split out patch] Signed-off-by: Andrea Arcangeli Signed-off-by: Mel Gorman Reviewed-by: Michal Hocko Reviewed-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index dbe6ea321df..8ff834e19c2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1124,8 +1124,20 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, nr_lumpy_dirty++; scan++; } else { - /* the page is freed already. */ - if (!page_count(cursor_page)) + /* + * Check if the page is freed already. + * + * We can't use page_count() as that + * requires compound_head and we don't + * have a pin on the page here. If a + * page is tail, we may or may not + * have isolated the head, so assume + * it's not free, it'd be tricky to + * track the head status without a + * page pin. + */ + if (!PageTail(cursor_page) && + !atomic_read(&cursor_page->_count)) continue; break; } -- cgit v1.2.3-18-g5258 From f9e35b3b41f47c4e17d8132edbcab305a6aaa4b0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 15 Jun 2011 15:08:52 -0700 Subject: mm: compaction: abort compaction if too many pages are isolated and caller is asynchronous V2 Asynchronous compaction is used when promoting to huge pages. This is all very nice but if there are a number of processes in compacting memory, a large number of pages can be isolated. An "asynchronous" process can stall for long periods of time as a result with a user reporting that firefox can stall for 10s of seconds. This patch aborts asynchronous compaction if too many pages are isolated as it's better to fail a hugepage promotion than stall a process. [minchan.kim@gmail.com: return COMPACT_PARTIAL for abort] Reported-and-tested-by: Ury Stankevich Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 9b94eaf537e..6cc604bd564 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -251,11 +251,18 @@ static bool too_many_isolated(struct zone *zone) return isolated > (inactive + active) / 2; } +/* possible outcome of isolate_migratepages */ +typedef enum { + ISOLATE_ABORT, /* Abort compaction now */ + ISOLATE_NONE, /* No pages isolated, continue scanning */ + ISOLATE_SUCCESS, /* Pages isolated, migrate */ +} isolate_migrate_t; + /* * Isolate all pages that can be migrated from the block pointed to by * the migrate scanner within compact_control. */ -static unsigned long isolate_migratepages(struct zone *zone, +static isolate_migrate_t isolate_migratepages(struct zone *zone, struct compact_control *cc) { unsigned long low_pfn, end_pfn; @@ -272,7 +279,7 @@ static unsigned long isolate_migratepages(struct zone *zone, /* Do not cross the free scanner or scan within a memory hole */ if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { cc->migrate_pfn = end_pfn; - return 0; + return ISOLATE_NONE; } /* @@ -281,10 +288,14 @@ static unsigned long isolate_migratepages(struct zone *zone, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(zone))) { + /* async migration should just abort */ + if (!cc->sync) + return ISOLATE_ABORT; + congestion_wait(BLK_RW_ASYNC, HZ/10); if (fatal_signal_pending(current)) - return 0; + return ISOLATE_ABORT; } /* Time to isolate some pages for migration */ @@ -369,7 +380,7 @@ static unsigned long isolate_migratepages(struct zone *zone, trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); - return cc->nr_migratepages; + return ISOLATE_SUCCESS; } /* @@ -535,8 +546,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) unsigned long nr_migrate, nr_remaining; int err; - if (!isolate_migratepages(zone, cc)) + switch (isolate_migratepages(zone, cc)) { + case ISOLATE_ABORT: + ret = COMPACT_PARTIAL; + goto out; + case ISOLATE_NONE: continue; + case ISOLATE_SUCCESS: + ; + } nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, @@ -560,6 +578,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } +out: /* Release free pages and check accounting */ cc->nr_freepages -= release_freepages(&cc->freepages); VM_BUG_ON(cc->nr_freepages != 0); -- cgit v1.2.3-18-g5258 From 31b5f8eeece4c0d70b649bfac7759cf7e3f915dd Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Wed, 15 Jun 2011 15:08:52 -0700 Subject: Documentation/feature-removal-schedule.txt: remove ns_cgroup from feature-removal-schedule.txt Commit a77aea92010acf ("cgroup: remove the ns_cgroup") removed the ns_cgroup but it forgot to remove the related doc in feature-removal-schedule.txt. Signed-off-by: WANG Cong Cc: Daniel Lezcano Cc: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/feature-removal-schedule.txt | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 1a9446b5915..72e238465b0 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -481,23 +481,6 @@ Who: FUJITA Tomonori ---------------------------- -What: namespace cgroup (ns_cgroup) -When: 2.6.38 -Why: The ns_cgroup leads to some problems: - * cgroup creation is out-of-control - * cgroup name can conflict when pids are looping - * it is not possible to have a single process handling - a lot of namespaces without falling in a exponential creation time - * we may want to create a namespace without creating a cgroup - - The ns_cgroup is replaced by a compatibility flag 'clone_children', - where a newly created cgroup will copy the parent cgroup values. - The userspace has to manually create a cgroup and add a task to - the 'tasks' file. -Who: Daniel Lezcano - ----------------------------- - What: iwlwifi disable_hw_scan module parameters When: 2.6.40 Why: Hareware scan is the prefer method for iwlwifi devices for -- cgit v1.2.3-18-g5258 From 273ef9509b7903e50f36aaf9f1d5dc9087fca506 Mon Sep 17 00:00:00 2001 From: Nils Carlson Date: Wed, 15 Jun 2011 15:08:54 -0700 Subject: drivers/char/hpet.c: fix periodic-emulation for delayed interrupts When interrupts are delayed due to interrupt masking or due to other interrupts being serviced the HPET periodic-emuation would fail. This happened because given an interval t and a time for the current interrupt m we would compute the next time as t + m. This works until we are delayed for > t, in which case we would be writing a new value which is in fact in the past. This can be solved by computing the next time instead as (k * t) + m where k is large enough to be in the future. The exact computation of k is described in a comment to the code. More detail: Assuming an interval of 5 between each expected interrupt we have a normal case of t0: interrupt, read t0 from comparator, set next interrupt t0 + 5 t5: interrupt, read t5 from comparator, set next interrupt t5 + 5 t10: interrupt, read t10 from comparator, set next interrupt t10 + 5 ... So, what happens when the interrupt is serviced too late? t0: interrupt, read t0 from comparator, set next interrupt t0 + 5 t11: delayed interrupt serviced, read t5 from comparator, set next interrupt t5 + 5, which is in the past! ... counter loops ... t10: Much much later, get the next interrupt. This can happen either because we have interrupts masked for too long (some stupid driver goes on a printk rampage) or just because we are pushing the limits of the interval (too small a period), or both most probably. My solution is to read the main counter as well and set the next interrupt to occur at the right interval, for example: t0: interrupt, read t0 from comparator, set next interrupt t0 + 5 t11: delayed interrupt serviced, read t5 from comparator, set next interrupt t15 as t10 has been missed. t15: back on track. Signed-off-by: Nils Carlson Cc: John Stultz Cc: Thomas Gleixner Cc: Clemens Ladisch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/hpet.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 051474c65b7..34d6a1cab8d 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -163,11 +163,32 @@ static irqreturn_t hpet_interrupt(int irq, void *data) * This has the effect of treating non-periodic like periodic. */ if ((devp->hd_flags & (HPET_IE | HPET_PERIODIC)) == HPET_IE) { - unsigned long m, t; + unsigned long m, t, mc, base, k; + struct hpet __iomem *hpet = devp->hd_hpet; + struct hpets *hpetp = devp->hd_hpets; t = devp->hd_ireqfreq; m = read_counter(&devp->hd_timer->hpet_compare); - write_counter(t + m, &devp->hd_timer->hpet_compare); + mc = read_counter(&hpet->hpet_mc); + /* The time for the next interrupt would logically be t + m, + * however, if we are very unlucky and the interrupt is delayed + * for longer than t then we will completely miss the next + * interrupt if we set t + m and an application will hang. + * Therefore we need to make a more complex computation assuming + * that there exists a k for which the following is true: + * k * t + base < mc + delta + * (k + 1) * t + base > mc + delta + * where t is the interval in hpet ticks for the given freq, + * base is the theoretical start value 0 < base < t, + * mc is the main counter value at the time of the interrupt, + * delta is the time it takes to write the a value to the + * comparator. + * k may then be computed as (mc - base + delta) / t . + */ + base = mc % t; + k = (mc - base + hpetp->hp_delta) / t; + write_counter(t * (k + 1) + base, + &devp->hd_timer->hpet_compare); } if (devp->hd_flags & HPET_SHARED_IRQ) -- cgit v1.2.3-18-g5258 From fb139dfeef9558a12ffdbf9e26951fd1a9304f3b Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Wed, 15 Jun 2011 15:08:55 -0700 Subject: drivers/tty/serial/pch_uart.c: don't oops if dmi_get_system_info returns NULL If dmi_get_system_info() returns NULL, pch_uart_init_port() will dereferencea a zero pointer. This oops was observed on an Atom based board which has no BIOS, but a bootloder which doesn't provide DMI data. Signed-off-by: Alexander Stein Cc: Greg KH Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/tty/serial/pch_uart.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index f2cb7503fcb..46521093089 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -1397,6 +1397,7 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, int fifosize, base_baud; int port_type; struct pch_uart_driver_data *board; + const char *board_name; board = &drv_dat[id->driver_data]; port_type = board->port_type; @@ -1412,7 +1413,8 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, base_baud = 1843200; /* 1.8432MHz */ /* quirk for CM-iTC board */ - if (strstr(dmi_get_system_info(DMI_BOARD_NAME), "CM-iTC")) + board_name = dmi_get_system_info(DMI_BOARD_NAME); + if (board_name && strstr(board_name, "CM-iTC")) base_baud = 192000000; /* 192.0MHz */ switch (port_type) { -- cgit v1.2.3-18-g5258 From c7cbb02222eccb82bfd42696b01abceddae663f2 Mon Sep 17 00:00:00 2001 From: Wanlong Gao Date: Wed, 15 Jun 2011 15:08:56 -0700 Subject: rtc: fix build warnings in defconfigs RTC_CLASS is changed to bool, so 'm' is invalid. Signed-off-by: Wanlong Gao Acked-by: Mike Frysinger Acked-by: Wolfram Sang Acked-by: Hans-Christian Egtvedt Acked-by: Benjamin Herrenschmidt Cc: Guan Xuetao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/configs/davinci_all_defconfig | 2 +- arch/arm/configs/netx_defconfig | 2 +- arch/arm/configs/viper_defconfig | 2 +- arch/arm/configs/xcep_defconfig | 2 +- arch/arm/configs/zeus_defconfig | 2 +- arch/avr32/configs/atngw100_mrmt_defconfig | 2 +- arch/blackfin/configs/CM-BF548_defconfig | 2 +- arch/mips/configs/mtx1_defconfig | 2 +- arch/powerpc/configs/52xx/pcm030_defconfig | 2 +- arch/powerpc/configs/ps3_defconfig | 2 +- arch/sh/configs/titan_defconfig | 2 +- 11 files changed, 11 insertions(+), 11 deletions(-) diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index 889922ad229..67b5abb6f85 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -157,7 +157,7 @@ CONFIG_LEDS_GPIO=m CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=m CONFIG_LEDS_TRIGGER_HEARTBEAT=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y CONFIG_XFS_FS=m diff --git a/arch/arm/configs/netx_defconfig b/arch/arm/configs/netx_defconfig index 316af5479d9..9c0ad799398 100644 --- a/arch/arm/configs/netx_defconfig +++ b/arch/arm/configs/netx_defconfig @@ -60,7 +60,7 @@ CONFIG_FB_ARMCLCD=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_INOTIFY=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig index 8b0c717378f..1d01ddd3312 100644 --- a/arch/arm/configs/viper_defconfig +++ b/arch/arm/configs/viper_defconfig @@ -142,7 +142,7 @@ CONFIG_USB_GADGETFS=m CONFIG_USB_FILE_STORAGE=m CONFIG_USB_G_SERIAL=m CONFIG_USB_G_PRINTER=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=m CONFIG_RTC_DRV_SA1100=m CONFIG_EXT2_FS=m diff --git a/arch/arm/configs/xcep_defconfig b/arch/arm/configs/xcep_defconfig index 5b550414364..721832ffe2d 100644 --- a/arch/arm/configs/xcep_defconfig +++ b/arch/arm/configs/xcep_defconfig @@ -73,7 +73,7 @@ CONFIG_SENSORS_MAX6650=m # CONFIG_VGA_CONSOLE is not set # CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_SA1100=m CONFIG_DMADEVICES=y # CONFIG_DNOTIFY is not set diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig index 960f65514d8..59577ad3f4e 100644 --- a/arch/arm/configs/zeus_defconfig +++ b/arch/arm/configs/zeus_defconfig @@ -158,7 +158,7 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=m CONFIG_LEDS_TRIGGER_BACKLIGHT=m CONFIG_LEDS_TRIGGER_GPIO=m CONFIG_LEDS_TRIGGER_DEFAULT_ON=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_ISL1208=m CONFIG_RTC_DRV_PXA=m CONFIG_EXT2_FS=y diff --git a/arch/avr32/configs/atngw100_mrmt_defconfig b/arch/avr32/configs/atngw100_mrmt_defconfig index 6cb786c0baf..77ca4f905d2 100644 --- a/arch/avr32/configs/atngw100_mrmt_defconfig +++ b/arch/avr32/configs/atngw100_mrmt_defconfig @@ -110,7 +110,7 @@ CONFIG_LEDS_GPIO=y CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_S35390A=m CONFIG_RTC_DRV_AT32AP700X=m CONFIG_DMADEVICES=y diff --git a/arch/blackfin/configs/CM-BF548_defconfig b/arch/blackfin/configs/CM-BF548_defconfig index 31d954216c0..9f1d08401fc 100644 --- a/arch/blackfin/configs/CM-BF548_defconfig +++ b/arch/blackfin/configs/CM-BF548_defconfig @@ -112,7 +112,7 @@ CONFIG_USB_G_SERIAL=m CONFIG_USB_G_PRINTER=m CONFIG_MMC=m CONFIG_SDH_BFIN=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_BFIN=m CONFIG_EXT2_FS=m # CONFIG_DNOTIFY is not set diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 37862b2ce36..807c97eed8a 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -678,7 +678,7 @@ CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_INTF_DEV_UIE_EMUL=y CONFIG_RTC_DRV_TEST=m CONFIG_RTC_DRV_DS1307=m diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig index 7f7e4a87860..22e719575c6 100644 --- a/arch/powerpc/configs/52xx/pcm030_defconfig +++ b/arch/powerpc/configs/52xx/pcm030_defconfig @@ -85,7 +85,7 @@ CONFIG_USB_OHCI_HCD=m CONFIG_USB_OHCI_HCD_PPC_OF_BE=y # CONFIG_USB_OHCI_HCD_PCI is not set CONFIG_USB_STORAGE=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PCF8563=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 6472322bf13..185c292b0f1 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -141,7 +141,7 @@ CONFIG_USB_EHCI_TT_NEWSCHED=y # CONFIG_USB_EHCI_HCD_PPC_OF is not set CONFIG_USB_OHCI_HCD=m CONFIG_USB_STORAGE=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PS3=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig index 0f558914e76..e2cbd92d520 100644 --- a/arch/sh/configs/titan_defconfig +++ b/arch/sh/configs/titan_defconfig @@ -227,7 +227,7 @@ CONFIG_USB_SERIAL=m CONFIG_USB_SERIAL_GENERIC=y CONFIG_USB_SERIAL_ARK3116=m CONFIG_USB_SERIAL_PL2303=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_SH=m CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y -- cgit v1.2.3-18-g5258 From 2b472611a32a72f4a118c069c2d62a1a3f087afd Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 15 Jun 2011 15:08:58 -0700 Subject: ksm: fix NULL pointer dereference in scan_get_next_rmap_item() Andrea Righi reported a case where an exiting task can race against ksmd::scan_get_next_rmap_item (http://lkml.org/lkml/2011/6/1/742) easily triggering a NULL pointer dereference in ksmd. ksm_scan.mm_slot == &ksm_mm_head with only one registered mm CPU 1 (__ksm_exit) CPU 2 (scan_get_next_rmap_item) list_empty() is false lock slot == &ksm_mm_head list_del(slot->mm_list) (list now empty) unlock lock slot = list_entry(slot->mm_list.next) (list is empty, so slot is still ksm_mm_head) unlock slot->mm == NULL ... Oops Close this race by revalidating that the new slot is not simply the list head again. Andrea's test case: #include #include #include #include #define BUFSIZE getpagesize() int main(int argc, char **argv) { void *ptr; if (posix_memalign(&ptr, getpagesize(), BUFSIZE) < 0) { perror("posix_memalign"); exit(1); } if (madvise(ptr, BUFSIZE, MADV_MERGEABLE) < 0) { perror("madvise"); exit(1); } *(char *)NULL = 0; return 0; } Reported-by: Andrea Righi Tested-by: Andrea Righi Cc: Andrea Arcangeli Signed-off-by: Hugh Dickins Signed-off-by: Chris Wright Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ksm.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/mm/ksm.c b/mm/ksm.c index d708b3ef226..9a68b0cf0a1 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1302,6 +1302,12 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list); ksm_scan.mm_slot = slot; spin_unlock(&ksm_mmlist_lock); + /* + * Although we tested list_empty() above, a racing __ksm_exit + * of the last mm on the list may have removed it since then. + */ + if (slot == &ksm_mm_head) + return NULL; next_mm: ksm_scan.address = 0; ksm_scan.rmap_list = &slot->rmap_list; -- cgit v1.2.3-18-g5258 From ec8f9ceacef719a844ca269d654502af6a00a273 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 15 Jun 2011 15:08:59 -0700 Subject: drivers/misc/apds990x.c: apds990x_chip_on() should depend on CONFIG_PM || CONFIG_PM_RUNTIME Fixes this warning: drivers/misc/apds990x.c: At top level: drivers/misc/apds990x.c:613: warning: `apds990x_chip_on' defined but not used Signed-off-by: Geert Uytterhoeven Cc: Samu Onkalo Cc: Jonathan Cameron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/misc/apds990x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/misc/apds990x.c b/drivers/misc/apds990x.c index 200311fea36..e2a52e5cf44 100644 --- a/drivers/misc/apds990x.c +++ b/drivers/misc/apds990x.c @@ -609,6 +609,7 @@ static int apds990x_detect(struct apds990x_chip *chip) return ret; } +#if defined(CONFIG_PM) || defined(CONFIG_PM_RUNTIME) static int apds990x_chip_on(struct apds990x_chip *chip) { int err = regulator_bulk_enable(ARRAY_SIZE(chip->regs), @@ -624,6 +625,7 @@ static int apds990x_chip_on(struct apds990x_chip *chip) apds990x_mode_on(chip); return 0; } +#endif static int apds990x_chip_off(struct apds990x_chip *chip) { -- cgit v1.2.3-18-g5258 From 21c5977a836e399fc710ff2c5367845ed5c2527f Mon Sep 17 00:00:00 2001 From: Dan Rosenberg Date: Wed, 15 Jun 2011 15:09:01 -0700 Subject: alpha: fix several security issues Fix several security issues in Alpha-specific syscalls. Untested, but mostly trivial. 1. Signedness issue in osf_getdomainname allows copying out-of-bounds kernel memory to userland. 2. Signedness issue in osf_sysinfo allows copying large amounts of kernel memory to userland. 3. Typo (?) in osf_getsysinfo bounds minimum instead of maximum copy size, allowing copying large amounts of kernel memory to userland. 4. Usage of user pointer in osf_wait4 while under KERNEL_DS allows privilege escalation via writing return value of sys_wait4 to kernel memory. Signed-off-by: Dan Rosenberg Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/osf_sys.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 376f2213079..326f0a2d56e 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -409,7 +409,7 @@ SYSCALL_DEFINE2(osf_getdomainname, char __user *, name, int, namelen) return -EFAULT; len = namelen; - if (namelen > 32) + if (len > 32) len = 32; down_read(&uts_sem); @@ -594,7 +594,7 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) down_read(&uts_sem); res = sysinfo_table[offset]; len = strlen(res)+1; - if (len > count) + if ((unsigned long)len > (unsigned long)count) len = count; if (copy_to_user(buf, res, len)) err = -EFAULT; @@ -649,7 +649,7 @@ SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer, return 1; case GSI_GET_HWRPB: - if (nbytes < sizeof(*hwrpb)) + if (nbytes > sizeof(*hwrpb)) return -EINVAL; if (copy_to_user(buffer, hwrpb, nbytes) != 0) return -EFAULT; @@ -1008,6 +1008,7 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, { struct rusage r; long ret, err; + unsigned int status = 0; mm_segment_t old_fs; if (!ur) @@ -1016,13 +1017,15 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, old_fs = get_fs(); set_fs (KERNEL_DS); - ret = sys_wait4(pid, ustatus, options, (struct rusage __user *) &r); + ret = sys_wait4(pid, (unsigned int __user *) &status, options, + (struct rusage __user *) &r); set_fs (old_fs); if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur))) return -EFAULT; err = 0; + err |= put_user(status, ustatus); err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec); err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec); err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec); -- cgit v1.2.3-18-g5258 From 04c55715cbd5de526046745bca3d3b6ffa6641c6 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Wed, 15 Jun 2011 12:57:09 -0700 Subject: Documentation: update printk-formats.txt This patch updates the incomplete documentation concerning the printk extended format specifiers. Signed-off-by: Andrew Murray Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- Documentation/printk-formats.txt | 119 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 117 insertions(+), 2 deletions(-) diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index 1b5a5ddbc3e..5df176ed59b 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -9,7 +9,121 @@ If variable is of Type, use printk format specifier: size_t %zu or %zx ssize_t %zd or %zx -Raw pointer value SHOULD be printed with %p. +Raw pointer value SHOULD be printed with %p. The kernel supports +the following extended format specifiers for pointer types: + +Symbols/Function Pointers: + + %pF versatile_init+0x0/0x110 + %pf versatile_init + %pS versatile_init+0x0/0x110 + %ps versatile_init + %pB prev_fn_of_versatile_init+0x88/0x88 + + For printing symbols and function pointers. The 'S' and 's' specifiers + result in the symbol name with ('S') or without ('s') offsets. Where + this is used on a kernel without KALLSYMS - the symbol address is + printed instead. + + The 'B' specifier results in the symbol name with offsets and should be + used when printing stack backtraces. The specifier takes into + consideration the effect of compiler optimisations which may occur + when tail-call's are used and marked with the noreturn GCC attribute. + + On ia64, ppc64 and parisc64 architectures function pointers are + actually function descriptors which must first be resolved. The 'F' and + 'f' specifiers perform this resolution and then provide the same + functionality as the 'S' and 's' specifiers. + +Kernel Pointers: + + %pK 0x01234567 or 0x0123456789abcdef + + For printing kernel pointers which should be hidden from unprivileged + users. The behaviour of %pK depends on the kptr_restrict sysctl - see + Documentation/sysctl/kernel.txt for more details. + +Struct Resources: + + %pr [mem 0x60000000-0x6fffffff flags 0x2200] or + [mem 0x0000000060000000-0x000000006fffffff flags 0x2200] + %pR [mem 0x60000000-0x6fffffff pref] or + [mem 0x0000000060000000-0x000000006fffffff pref] + + For printing struct resources. The 'R' and 'r' specifiers result in a + printed resource with ('R') or without ('r') a decoded flags member. + +MAC/FDDI addresses: + + %pM 00:01:02:03:04:05 + %pMF 00-01-02-03-04-05 + %pm 000102030405 + + For printing 6-byte MAC/FDDI addresses in hex notation. The 'M' and 'm' + specifiers result in a printed address with ('M') or without ('m') byte + separators. The default byte separator is the colon (':'). + + Where FDDI addresses are concerned the 'F' specifier can be used after + the 'M' specifier to use dash ('-') separators instead of the default + separator. + +IPv4 addresses: + + %pI4 1.2.3.4 + %pi4 001.002.003.004 + %p[Ii][hnbl] + + For printing IPv4 dot-separated decimal addresses. The 'I4' and 'i4' + specifiers result in a printed address with ('i4') or without ('I4') + leading zeros. + + The additional 'h', 'n', 'b', and 'l' specifiers are used to specify + host, network, big or little endian order addresses respectively. Where + no specifier is provided the default network/big endian order is used. + +IPv6 addresses: + + %pI6 0001:0002:0003:0004:0005:0006:0007:0008 + %pi6 00010002000300040005000600070008 + %pI6c 1:2:3:4:5:6:7:8 + + For printing IPv6 network-order 16-bit hex addresses. The 'I6' and 'i6' + specifiers result in a printed address with ('I6') or without ('i6') + colon-separators. Leading zeros are always used. + + The additional 'c' specifier can be used with the 'I' specifier to + print a compressed IPv6 address as described by + http://tools.ietf.org/html/rfc5952 + +UUID/GUID addresses: + + %pUb 00010203-0405-0607-0809-0a0b0c0d0e0f + %pUB 00010203-0405-0607-0809-0A0B0C0D0E0F + %pUl 03020100-0504-0706-0809-0a0b0c0e0e0f + %pUL 03020100-0504-0706-0809-0A0B0C0E0E0F + + For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L', + 'b' and 'B' specifiers are used to specify a little endian order in + lower ('l') or upper case ('L') hex characters - and big endian order + in lower ('b') or upper case ('B') hex characters. + + Where no additional specifiers are used the default little endian + order with lower case hex characters will be printed. + +struct va_format: + + %pV + + For printing struct va_format structures. These contain a format string + and va_list as follows: + + struct va_format { + const char *fmt; + va_list *va; + }; + + Do not use this feature without some mechanism to verify the + correctness of the format string and va_list arguments. u64 SHOULD be printed with %llu/%llx, (unsigned long long): @@ -32,4 +146,5 @@ Reminder: sizeof() result is of type size_t. Thank you for your cooperation and attention. -By Randy Dunlap +By Randy Dunlap and +Andrew Murray -- cgit v1.2.3-18-g5258 From 06a2c45d6b4a7586eba7cd20dd656b08d8b63c2f Mon Sep 17 00:00:00 2001 From: "Maxin B. John" Date: Wed, 15 Jun 2011 12:58:29 -0700 Subject: Documentation: update kmemleak supported archs Instead of listing the architectures that are supported by kmemleak in Documentation/kmemleak.txt, just refer people to the list of supported architecutures in lib/Kconfig.debug so that Documentation/kmemleak.txt does not need more updates for this. Signed-off-by: Maxin B. John Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- Documentation/kmemleak.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt index 090e6ee0453..51063e681ca 100644 --- a/Documentation/kmemleak.txt +++ b/Documentation/kmemleak.txt @@ -11,7 +11,9 @@ with the difference that the orphan objects are not freed but only reported via /sys/kernel/debug/kmemleak. A similar method is used by the Valgrind tool (memcheck --leak-check) to detect the memory leaks in user-space applications. -Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze and tile. + +Please check DEBUG_KMEMLEAK dependencies in lib/Kconfig.debug for supported +architectures. Usage ----- -- cgit v1.2.3-18-g5258 From f6e07d38078e82a6aeaae00bb134591ef5ac1167 Mon Sep 17 00:00:00 2001 From: Jörg Sommer Date: Wed, 15 Jun 2011 12:59:45 -0700 Subject: Documentation: update cgroupfs mount point MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to commit 676db4af0430 ("cgroupfs: create /sys/fs/cgroup to mount cgroupfs on") the canonical mountpoint for the cgroup filesystem is /sys/fs/cgroup. Hence, this should be used in the documentation. Signed-off-by: Jörg Sommer Acked-by: Paul Menage Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- Documentation/accounting/cgroupstats.txt | 4 +- Documentation/cgroups/blkio-controller.txt | 29 +++++++------- Documentation/cgroups/cgroups.txt | 58 +++++++++++++++++----------- Documentation/cgroups/cpuacct.txt | 21 +++++----- Documentation/cgroups/cpusets.txt | 28 +++++++------- Documentation/cgroups/devices.txt | 6 +-- Documentation/cgroups/freezer-subsystem.txt | 20 +++++----- Documentation/cgroups/memory.txt | 17 ++++---- Documentation/scheduler/sched-design-CFS.txt | 7 ++-- Documentation/scheduler/sched-rt-group.txt | 7 ++-- Documentation/vm/hwpoison.txt | 6 +-- 11 files changed, 109 insertions(+), 94 deletions(-) diff --git a/Documentation/accounting/cgroupstats.txt b/Documentation/accounting/cgroupstats.txt index eda40fd39ca..d16a9849e60 100644 --- a/Documentation/accounting/cgroupstats.txt +++ b/Documentation/accounting/cgroupstats.txt @@ -21,7 +21,7 @@ information will not be available. To extract cgroup statistics a utility very similar to getdelays.c has been developed, the sample output of the utility is shown below -~/balbir/cgroupstats # ./getdelays -C "/cgroup/a" +~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup/a" sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0 -~/balbir/cgroupstats # ./getdelays -C "/cgroup" +~/balbir/cgroupstats # ./getdelays -C "/sys/fs/cgroup" sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2 diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 465351d4cf8..b1b1bfadc9c 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -28,16 +28,19 @@ cgroups. Here is what you can do. - Enable group scheduling in CFQ CONFIG_CFQ_GROUP_IOSCHED=y -- Compile and boot into kernel and mount IO controller (blkio). +- Compile and boot into kernel and mount IO controller (blkio); see + cgroups.txt, Why are cgroups needed?. - mount -t cgroup -o blkio none /cgroup + mount -t tmpfs cgroup_root /sys/fs/cgroup + mkdir /sys/fs/cgroup/blkio + mount -t cgroup -o blkio none /sys/fs/cgroup/blkio - Create two cgroups - mkdir -p /cgroup/test1/ /cgroup/test2 + mkdir -p /sys/fs/cgroup/blkio/test1/ /sys/fs/cgroup/blkio/test2 - Set weights of group test1 and test2 - echo 1000 > /cgroup/test1/blkio.weight - echo 500 > /cgroup/test2/blkio.weight + echo 1000 > /sys/fs/cgroup/blkio/test1/blkio.weight + echo 500 > /sys/fs/cgroup/blkio/test2/blkio.weight - Create two same size files (say 512MB each) on same disk (file1, file2) and launch two dd threads in different cgroup to read those files. @@ -46,12 +49,12 @@ cgroups. Here is what you can do. echo 3 > /proc/sys/vm/drop_caches dd if=/mnt/sdb/zerofile1 of=/dev/null & - echo $! > /cgroup/test1/tasks - cat /cgroup/test1/tasks + echo $! > /sys/fs/cgroup/blkio/test1/tasks + cat /sys/fs/cgroup/blkio/test1/tasks dd if=/mnt/sdb/zerofile2 of=/dev/null & - echo $! > /cgroup/test2/tasks - cat /cgroup/test2/tasks + echo $! > /sys/fs/cgroup/blkio/test2/tasks + cat /sys/fs/cgroup/blkio/test2/tasks - At macro level, first dd should finish first. To get more precise data, keep on looking at (with the help of script), at blkio.disk_time and @@ -68,13 +71,13 @@ Throttling/Upper Limit policy - Enable throttling in block layer CONFIG_BLK_DEV_THROTTLING=y -- Mount blkio controller - mount -t cgroup -o blkio none /cgroup/blkio +- Mount blkio controller (see cgroups.txt, Why are cgroups needed?) + mount -t cgroup -o blkio none /sys/fs/cgroup/blkio - Specify a bandwidth rate on particular device for root group. The format for policy is ": ". - echo "8:16 1048576" > /cgroup/blkio/blkio.read_bps_device + echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.read_bps_device Above will put a limit of 1MB/second on reads happening for root group on device having major/minor number 8:16. @@ -149,7 +152,7 @@ Proportional weight policy files Following is the format. - #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device + # echo dev_maj:dev_minor weight > blkio.weight_device Configure weight=300 on /dev/sdb (8:16) in this cgroup # echo 8:16 300 > blkio.weight_device # cat blkio.weight_device diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 0ed99f08f1f..15bca101ff6 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -138,7 +138,7 @@ With the ability to classify tasks differently for different resources the admin can easily set up a script which receives exec notifications and depending on who is launching the browser he can - # echo browser_pid > /mnt///tasks + # echo browser_pid > /sys/fs/cgroup///tasks With only a single hierarchy, he now would potentially have to create a separate cgroup for every browser launched and associate it with @@ -153,9 +153,9 @@ apps enhanced CPU power, With ability to write pids directly to resource classes, it's just a matter of : - # echo pid > /mnt/network//tasks + # echo pid > /sys/fs/cgroup/network//tasks (after some time) - # echo pid > /mnt/network//tasks + # echo pid > /sys/fs/cgroup/network//tasks Without this ability, he would have to split the cgroup into multiple separate ones and then associate the new cgroups with the @@ -310,21 +310,24 @@ subsystem, this is the case for the cpuset. To start a new job that is to be contained within a cgroup, using the "cpuset" cgroup subsystem, the steps are something like: - 1) mkdir /dev/cgroup - 2) mount -t cgroup -ocpuset cpuset /dev/cgroup - 3) Create the new cgroup by doing mkdir's and write's (or echo's) in - the /dev/cgroup virtual file system. - 4) Start a task that will be the "founding father" of the new job. - 5) Attach that task to the new cgroup by writing its pid to the - /dev/cgroup tasks file for that cgroup. - 6) fork, exec or clone the job tasks from this founding father task. + 1) mount -t tmpfs cgroup_root /sys/fs/cgroup + 2) mkdir /sys/fs/cgroup/cpuset + 3) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset + 4) Create the new cgroup by doing mkdir's and write's (or echo's) in + the /sys/fs/cgroup virtual file system. + 5) Start a task that will be the "founding father" of the new job. + 6) Attach that task to the new cgroup by writing its pid to the + /sys/fs/cgroup/cpuset/tasks file for that cgroup. + 7) fork, exec or clone the job tasks from this founding father task. For example, the following sequence of commands will setup a cgroup named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, and then start a subshell 'sh' in that cgroup: - mount -t cgroup cpuset -ocpuset /dev/cgroup - cd /dev/cgroup + mount -t tmpfs cgroup_root /sys/fs/cgroup + mkdir /sys/fs/cgroup/cpuset + mount -t cgroup cpuset -ocpuset /sys/fs/cgroup/cpuset + cd /sys/fs/cgroup/cpuset mkdir Charlie cd Charlie /bin/echo 2-3 > cpuset.cpus @@ -345,7 +348,7 @@ Creating, modifying, using the cgroups can be done through the cgroup virtual filesystem. To mount a cgroup hierarchy with all available subsystems, type: -# mount -t cgroup xxx /dev/cgroup +# mount -t cgroup xxx /sys/fs/cgroup The "xxx" is not interpreted by the cgroup code, but will appear in /proc/mounts so may be any useful identifying string that you like. @@ -354,23 +357,32 @@ Note: Some subsystems do not work without some user input first. For instance, if cpusets are enabled the user will have to populate the cpus and mems files for each new cgroup created before that group can be used. +As explained in section `1.2 Why are cgroups needed?' you should create +different hierarchies of cgroups for each single resource or group of +resources you want to control. Therefore, you should mount a tmpfs on +/sys/fs/cgroup and create directories for each cgroup resource or resource +group. + +# mount -t tmpfs cgroup_root /sys/fs/cgroup +# mkdir /sys/fs/cgroup/rg1 + To mount a cgroup hierarchy with just the cpuset and memory subsystems, type: -# mount -t cgroup -o cpuset,memory hier1 /dev/cgroup +# mount -t cgroup -o cpuset,memory hier1 /sys/fs/cgroup/rg1 To change the set of subsystems bound to a mounted hierarchy, just remount with different options: -# mount -o remount,cpuset,blkio hier1 /dev/cgroup +# mount -o remount,cpuset,blkio hier1 /sys/fs/cgroup/rg1 Now memory is removed from the hierarchy and blkio is added. Note this will add blkio to the hierarchy but won't remove memory or cpuset, because the new options are appended to the old ones: -# mount -o remount,blkio /dev/cgroup +# mount -o remount,blkio /sys/fs/cgroup/rg1 To Specify a hierarchy's release_agent: # mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \ - xxx /dev/cgroup + xxx /sys/fs/cgroup/rg1 Note that specifying 'release_agent' more than once will return failure. @@ -379,17 +391,17 @@ when the hierarchy consists of a single (root) cgroup. Supporting the ability to arbitrarily bind/unbind subsystems from an existing cgroup hierarchy is intended to be implemented in the future. -Then under /dev/cgroup you can find a tree that corresponds to the -tree of the cgroups in the system. For instance, /dev/cgroup +Then under /sys/fs/cgroup/rg1 you can find a tree that corresponds to the +tree of the cgroups in the system. For instance, /sys/fs/cgroup/rg1 is the cgroup that holds the whole system. If you want to change the value of release_agent: -# echo "/sbin/new_release_agent" > /dev/cgroup/release_agent +# echo "/sbin/new_release_agent" > /sys/fs/cgroup/rg1/release_agent It can also be changed via remount. -If you want to create a new cgroup under /dev/cgroup: -# cd /dev/cgroup +If you want to create a new cgroup under /sys/fs/cgroup/rg1: +# cd /sys/fs/cgroup/rg1 # mkdir my_cgroup Now you want to do something with this cgroup. diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt index 8b930946c52..9ad85df4b98 100644 --- a/Documentation/cgroups/cpuacct.txt +++ b/Documentation/cgroups/cpuacct.txt @@ -10,26 +10,25 @@ directly present in its group. Accounting groups can be created by first mounting the cgroup filesystem. -# mkdir /cgroups -# mount -t cgroup -ocpuacct none /cgroups - -With the above step, the initial or the parent accounting group -becomes visible at /cgroups. At bootup, this group includes all the -tasks in the system. /cgroups/tasks lists the tasks in this cgroup. -/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by -this group which is essentially the CPU time obtained by all the tasks +# mount -t cgroup -ocpuacct none /sys/fs/cgroup + +With the above step, the initial or the parent accounting group becomes +visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in +the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup. +/sys/fs/cgroup/cpuacct.usage gives the CPU time (in nanoseconds) obtained +by this group which is essentially the CPU time obtained by all the tasks in the system. -New accounting groups can be created under the parent group /cgroups. +New accounting groups can be created under the parent group /sys/fs/cgroup. -# cd /cgroups +# cd /sys/fs/cgroup # mkdir g1 # echo $$ > g1 The above steps create a new group g1 and move the current shell process (bash) into it. CPU time consumed by this bash and its children can be obtained from g1/cpuacct.usage and the same is accumulated in -/cgroups/cpuacct.usage also. +/sys/fs/cgroup/cpuacct.usage also. cpuacct.stat file lists a few statistics which further divide the CPU time obtained by the cgroup into user and system times. Currently diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 98a30829af7..5b0d78e55cc 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -661,21 +661,21 @@ than stress the kernel. To start a new job that is to be contained within a cpuset, the steps are: - 1) mkdir /dev/cpuset - 2) mount -t cgroup -ocpuset cpuset /dev/cpuset + 1) mkdir /sys/fs/cgroup/cpuset + 2) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset 3) Create the new cpuset by doing mkdir's and write's (or echo's) in - the /dev/cpuset virtual file system. + the /sys/fs/cgroup/cpuset virtual file system. 4) Start a task that will be the "founding father" of the new job. 5) Attach that task to the new cpuset by writing its pid to the - /dev/cpuset tasks file for that cpuset. + /sys/fs/cgroup/cpuset tasks file for that cpuset. 6) fork, exec or clone the job tasks from this founding father task. For example, the following sequence of commands will setup a cpuset named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, and then start a subshell 'sh' in that cpuset: - mount -t cgroup -ocpuset cpuset /dev/cpuset - cd /dev/cpuset + mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset + cd /sys/fs/cgroup/cpuset mkdir Charlie cd Charlie /bin/echo 2-3 > cpuset.cpus @@ -710,14 +710,14 @@ Creating, modifying, using the cpusets can be done through the cpuset virtual filesystem. To mount it, type: -# mount -t cgroup -o cpuset cpuset /dev/cpuset +# mount -t cgroup -o cpuset cpuset /sys/fs/cgroup/cpuset -Then under /dev/cpuset you can find a tree that corresponds to the -tree of the cpusets in the system. For instance, /dev/cpuset +Then under /sys/fs/cgroup/cpuset you can find a tree that corresponds to the +tree of the cpusets in the system. For instance, /sys/fs/cgroup/cpuset is the cpuset that holds the whole system. -If you want to create a new cpuset under /dev/cpuset: -# cd /dev/cpuset +If you want to create a new cpuset under /sys/fs/cgroup/cpuset: +# cd /sys/fs/cgroup/cpuset # mkdir my_cpuset Now you want to do something with this cpuset. @@ -765,12 +765,12 @@ wrapper around the cgroup filesystem. The command -mount -t cpuset X /dev/cpuset +mount -t cpuset X /sys/fs/cgroup/cpuset is equivalent to -mount -t cgroup -ocpuset,noprefix X /dev/cpuset -echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent +mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset +echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent 2.2 Adding/removing cpus ------------------------ diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt index 57ca4c89fe5..16624a7f822 100644 --- a/Documentation/cgroups/devices.txt +++ b/Documentation/cgroups/devices.txt @@ -22,16 +22,16 @@ removed from the child(ren). An entry is added using devices.allow, and removed using devices.deny. For instance - echo 'c 1:3 mr' > /cgroups/1/devices.allow + echo 'c 1:3 mr' > /sys/fs/cgroup/1/devices.allow allows cgroup 1 to read and mknod the device usually known as /dev/null. Doing - echo a > /cgroups/1/devices.deny + echo a > /sys/fs/cgroup/1/devices.deny will remove the default 'a *:* rwm' entry. Doing - echo a > /cgroups/1/devices.allow + echo a > /sys/fs/cgroup/1/devices.allow will add the 'a *:* rwm' entry to the whitelist. diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroups/freezer-subsystem.txt index 41f37fea127..c21d77742a0 100644 --- a/Documentation/cgroups/freezer-subsystem.txt +++ b/Documentation/cgroups/freezer-subsystem.txt @@ -59,28 +59,28 @@ is non-freezable. * Examples of usage : - # mkdir /containers - # mount -t cgroup -ofreezer freezer /containers - # mkdir /containers/0 - # echo $some_pid > /containers/0/tasks + # mkdir /sys/fs/cgroup/freezer + # mount -t cgroup -ofreezer freezer /sys/fs/cgroup/freezer + # mkdir /sys/fs/cgroup/freezer/0 + # echo $some_pid > /sys/fs/cgroup/freezer/0/tasks to get status of the freezer subsystem : - # cat /containers/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state THAWED to freeze all tasks in the container : - # echo FROZEN > /containers/0/freezer.state - # cat /containers/0/freezer.state + # echo FROZEN > /sys/fs/cgroup/freezer/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state FREEZING - # cat /containers/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state FROZEN to unfreeze all tasks in the container : - # echo THAWED > /containers/0/freezer.state - # cat /containers/0/freezer.state + # echo THAWED > /sys/fs/cgroup/freezer/0/freezer.state + # cat /sys/fs/cgroup/freezer/0/freezer.state THAWED This is the basic mechanism which should do the right thing for user space task diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 510d64570d6..ffec2416aa7 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -264,16 +264,17 @@ b. Enable CONFIG_RESOURCE_COUNTERS c. Enable CONFIG_CGROUP_MEM_RES_CTLR d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension) -1. Prepare the cgroups -# mkdir -p /cgroups -# mount -t cgroup none /cgroups -o memory +1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?) +# mount -t tmpfs none /sys/fs/cgroup +# mkdir /sys/fs/cgroup/memory +# mount -t cgroup none /sys/fs/cgroup/memory -o memory 2. Make the new group and move bash into it -# mkdir /cgroups/0 -# echo $$ > /cgroups/0/tasks +# mkdir /sys/fs/cgroup/memory/0 +# echo $$ > /sys/fs/cgroup/memory/0/tasks Since now we're in the 0 cgroup, we can alter the memory limit: -# echo 4M > /cgroups/0/memory.limit_in_bytes +# echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo, mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.) @@ -281,11 +282,11 @@ mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.) NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited). NOTE: We cannot set limits on the root cgroup any more. -# cat /cgroups/0/memory.limit_in_bytes +# cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes 4194304 We can check the usage: -# cat /cgroups/0/memory.usage_in_bytes +# cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes 1216512 A successful write to this file does not guarantee a successful set of diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt index 99961993257..91ecff07ced 100644 --- a/Documentation/scheduler/sched-design-CFS.txt +++ b/Documentation/scheduler/sched-design-CFS.txt @@ -223,9 +223,10 @@ When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each group created using the pseudo filesystem. See example steps below to create task groups and modify their CPU share using the "cgroups" pseudo filesystem. - # mkdir /dev/cpuctl - # mount -t cgroup -ocpu none /dev/cpuctl - # cd /dev/cpuctl + # mount -t tmpfs cgroup_root /sys/fs/cgroup + # mkdir /sys/fs/cgroup/cpu + # mount -t cgroup -ocpu none /sys/fs/cgroup/cpu + # cd /sys/fs/cgroup/cpu # mkdir multimedia # create "multimedia" group of tasks # mkdir browser # create "browser" group of tasks diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 605b0d40329..71b54d54998 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -129,9 +129,8 @@ priority! Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real CPU bandwidth to task groups. -This uses the /cgroup virtual file system and -"/cgroup//cpu.rt_runtime_us" to control the CPU time reserved for each -control group. +This uses the cgroup virtual file system and "/cpu.rt_runtime_us" +to control the CPU time reserved for each control group. For more information on working with control groups, you should read Documentation/cgroups/cgroups.txt as well. @@ -150,7 +149,7 @@ For now, this can be simplified to just the following (but see Future plans): =============== There is work in progress to make the scheduling period for each group -("/cgroup//cpu.rt_period_us") configurable as well. +("/cpu.rt_period_us") configurable as well. The constraint on the period is that a subgroup must have a smaller or equal period to its parent. But realistically its not very useful _yet_ diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt index 12f9ba20ccb..55006846660 100644 --- a/Documentation/vm/hwpoison.txt +++ b/Documentation/vm/hwpoison.txt @@ -129,12 +129,12 @@ Limit injection to pages owned by memgroup. Specified by inode number of the memcg. Example: - mkdir /cgroup/hwpoison + mkdir /sys/fs/cgroup/mem/hwpoison usemem -m 100 -s 1000 & - echo `jobs -p` > /cgroup/hwpoison/tasks + echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks - memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ') + memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ') echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg page-types -p `pidof init` --hwpoison # shall do nothing -- cgit v1.2.3-18-g5258 From 67de0162fbb78713fcb23cb2502b380faa8bde73 Mon Sep 17 00:00:00 2001 From: Jörg Sommer Date: Wed, 15 Jun 2011 13:00:47 -0700 Subject: Documentation: fix cgroup typos and formatting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix format and spelling. Signed-off-by: Jörg Sommer Acked-by: Paul Menage Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- Documentation/cgroups/blkio-controller.txt | 2 +- Documentation/cgroups/cgroups.txt | 2 +- Documentation/cgroups/memory.txt | 22 +++++++++++----------- 3 files changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index b1b1bfadc9c..cd45c8ea746 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -111,7 +111,7 @@ Hierarchical Cgroups CFQ and throttling will practically treat all groups at same level. pivot - / | \ \ + / / \ \ root test1 test2 test3 Down the line we can implement hierarchical accounting/control support diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 15bca101ff6..cd67e90003c 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -142,7 +142,7 @@ and depending on who is launching the browser he can With only a single hierarchy, he now would potentially have to create a separate cgroup for every browser launched and associate it with -approp network and other resource class. This may lead to +appropriate network and other resource class. This may lead to proliferation of such cgroups. Also lets say that the administrator would like to give enhanced network diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index ffec2416aa7..06eb6d957c8 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -1,8 +1,8 @@ Memory Resource Controller -NOTE: The Memory Resource Controller has been generically been referred - to as the memory controller in this document. Do not confuse memory - controller used here with the memory controller that is used in hardware. +NOTE: The Memory Resource Controller has generically been referred to as the + memory controller in this document. Do not confuse memory controller + used here with the memory controller that is used in hardware. (For editors) In this document: @@ -182,7 +182,7 @@ behind this approach is that a cgroup that aggressively uses a shared page will eventually get charged for it (once it is uncharged from the cgroup that brought it in -- this will happen on memory pressure). -Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.. +Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used. When you do swapoff and make swapped-out pages of shmem(tmpfs) to be backed into memory in force, charges for pages are accounted against the caller of swapoff rather than the users of shmem. @@ -214,7 +214,7 @@ affecting global LRU, memory+swap limit is better than just limiting swap from OS point of view. * What happens when a cgroup hits memory.memsw.limit_in_bytes -When a cgroup his memory.memsw.limit_in_bytes, it's useless to do swap-out +When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out in this cgroup. Then, swap-out will not be done by cgroup routine and file caches are dropped. But as mentioned above, global LRU can do swapout memory from it for sanity of the system's memory management state. You can't forbid @@ -491,13 +491,13 @@ The hierarchy is created by creating the appropriate cgroups in the cgroup filesystem. Consider for example, the following cgroup filesystem hierarchy - root + root / | \ - / | \ - a b c - | \ - | \ - d e + / | \ + a b c + | \ + | \ + d e In the diagram above, with hierarchical accounting enabled, all memory usage of e, is accounted to its ancestors up until the root (i.e, c and root), -- cgit v1.2.3-18-g5258 From 13fca640bb8ab611a50e0ba120b186faa2994d6c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 15 Jun 2011 21:53:52 -0700 Subject: Revert "fs/exec.c: use BUILD_BUG_ON for VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP" This reverts commit 7f81c8890c15a10f5220bebae3b6dfae4961962a. It turns out that it's not actually a build-time check on x86-64 UML, which does some seriously crazy stuff with VM_STACK_FLAGS. The VM_STACK_FLAGS define depends on the arch-supplied VM_STACK_DEFAULT_FLAGS value, and on x86-64 UML we have arch/um/sys-x86_64/shared/sysdep/vm-flags.h: #define VM_STACK_DEFAULT_FLAGS \ (test_thread_flag(TIF_IA32) ? vm_stack_flags32 : vm_stack_flags) #define VM_STACK_DEFAULT_FLAGS vm_stack_flags (yes, seriously: two different #define's for that thing, with the first one being inside an "#ifdef TIF_IA32") It's possible that it is UML that should just be fixed in this area, but for now let's just undo the (very small) optimization. Reported-by: Randy Dunlap Acked-by: Andrew Morton Cc: Michal Hocko Cc: Richard Weinberger Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index b54f74f3cd8..97e0d52d72f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -277,7 +277,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ - BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); + BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; -- cgit v1.2.3-18-g5258 From c4e0dd7835d12d9765a372b586a5020ac29cc706 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 16 Jun 2011 05:08:09 +0000 Subject: dmaengine: shdma: add to_sh_dev define This patch adds "to_sh_dev" macro, and clean up codes. Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 13 ++++--------- drivers/dma/shdma.h | 2 ++ 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 2a638f9f09a..d2fb16d31bb 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -130,8 +130,7 @@ static bool dmae_is_busy(struct sh_dmae_chan *sh_chan) static unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan, u32 chcr) { - struct sh_dmae_device *shdev = container_of(sh_chan->common.device, - struct sh_dmae_device, common); + struct sh_dmae_device *shdev = to_sh_dev(sh_chan); struct sh_dmae_pdata *pdata = shdev->pdata; int cnt = ((chcr & pdata->ts_low_mask) >> pdata->ts_low_shift) | ((chcr & pdata->ts_high_mask) >> pdata->ts_high_shift); @@ -144,8 +143,7 @@ static unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan, u32 chcr) static u32 log2size_to_chcr(struct sh_dmae_chan *sh_chan, int l2size) { - struct sh_dmae_device *shdev = container_of(sh_chan->common.device, - struct sh_dmae_device, common); + struct sh_dmae_device *shdev = to_sh_dev(sh_chan); struct sh_dmae_pdata *pdata = shdev->pdata; int i; @@ -209,8 +207,7 @@ static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val) static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val) { - struct sh_dmae_device *shdev = container_of(sh_chan->common.device, - struct sh_dmae_device, common); + struct sh_dmae_device *shdev = to_sh_dev(sh_chan); struct sh_dmae_pdata *pdata = shdev->pdata; const struct sh_dmae_channel *chan_pdata = &pdata->channel[sh_chan->id]; u16 __iomem *addr = shdev->dmars; @@ -296,9 +293,7 @@ static struct sh_desc *sh_dmae_get_desc(struct sh_dmae_chan *sh_chan) static const struct sh_dmae_slave_config *sh_dmae_find_slave( struct sh_dmae_chan *sh_chan, struct sh_dmae_slave *param) { - struct dma_device *dma_dev = sh_chan->common.device; - struct sh_dmae_device *shdev = container_of(dma_dev, - struct sh_dmae_device, common); + struct sh_dmae_device *shdev = to_sh_dev(sh_chan); struct sh_dmae_pdata *pdata = shdev->pdata; int i; diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h index 5ae9fc51218..6c73b654a5c 100644 --- a/drivers/dma/shdma.h +++ b/drivers/dma/shdma.h @@ -52,5 +52,7 @@ struct sh_dmae_device { #define to_sh_chan(chan) container_of(chan, struct sh_dmae_chan, common) #define to_sh_desc(lh) container_of(lh, struct sh_desc, node) #define tx_to_sh_desc(tx) container_of(tx, struct sh_desc, async_tx) +#define to_sh_dev(chan) container_of(chan->common.device,\ + struct sh_dmae_device, common) #endif /* __DMA_SHDMA_H */ -- cgit v1.2.3-18-g5258 From 1d2c0980262e70f5643df34493ffd7e608282c16 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 16 Jun 2011 05:08:18 +0000 Subject: dmaengine: shdma: tidyup spin_unlock_bh on sh_chan_xfer_ld_queue It is not readable that there is any spin_unlock_bh on same function. Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index d2fb16d31bb..3d22eb82289 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -766,10 +766,8 @@ static void sh_chan_xfer_ld_queue(struct sh_dmae_chan *sh_chan) spin_lock_bh(&sh_chan->desc_lock); /* DMA work check */ - if (dmae_is_busy(sh_chan)) { - spin_unlock_bh(&sh_chan->desc_lock); - return; - } + if (dmae_is_busy(sh_chan)) + goto sh_chan_xfer_ld_queue_end; /* Find the first not transferred descriptor */ list_for_each_entry(desc, &sh_chan->ld_queue, node) @@ -783,6 +781,7 @@ static void sh_chan_xfer_ld_queue(struct sh_dmae_chan *sh_chan) break; } +sh_chan_xfer_ld_queue_end: spin_unlock_bh(&sh_chan->desc_lock); } -- cgit v1.2.3-18-g5258 From 090b91805a97f58a7deff0f2b40aad1cc2f1b7e0 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 16 Jun 2011 05:08:28 +0000 Subject: dmaengine: shdma: fixup parameter definition on dmae_set_dmars chan_pdata->dmars_bit is unsigned int Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 3d22eb82289..41a21b32296 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -211,7 +211,7 @@ static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val) struct sh_dmae_pdata *pdata = shdev->pdata; const struct sh_dmae_channel *chan_pdata = &pdata->channel[sh_chan->id]; u16 __iomem *addr = shdev->dmars; - int shift = chan_pdata->dmars_bit; + unsigned int shift = chan_pdata->dmars_bit; if (dmae_is_busy(sh_chan)) return -EBUSY; -- cgit v1.2.3-18-g5258 From fb2e73947461d55a3166f94a8a545b78d6635262 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Wed, 15 Jun 2011 06:08:18 +0000 Subject: sh: ecovec: Add renesas_usbhs support Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- arch/sh/boards/mach-ecovec24/setup.c | 48 ++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 3a32741cc0a..513cb1a2e6c 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -232,6 +233,52 @@ static struct platform_device usb1_common_device = { .resource = usb1_common_resources, }; +/* + * USBHS + */ +static int usbhs_get_id(struct platform_device *pdev) +{ + return gpio_get_value(GPIO_PTB3); +} + +static struct renesas_usbhs_platform_info usbhs_info = { + .platform_callback = { + .get_id = usbhs_get_id, + }, + .driver_param = { + .buswait_bwait = 4, + .detection_delay = 5, + }, +}; + +static struct resource usbhs_resources[] = { + [0] = { + .start = 0xa4d90000, + .end = 0xa4d90124 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = 66, + .end = 66, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usbhs_device = { + .name = "renesas_usbhs", + .id = 1, + .dev = { + .dma_mask = NULL, /* not use dma */ + .coherent_dma_mask = 0xffffffff, + .platform_data = &usbhs_info, + }, + .num_resources = ARRAY_SIZE(usbhs_resources), + .resource = usbhs_resources, + .archdata = { + .hwblk_id = HWBLK_USB1, + }, +}; + /* LCDC */ const static struct fb_videomode ecovec_lcd_modes[] = { { @@ -897,6 +944,7 @@ static struct platform_device *ecovec_devices[] __initdata = { &sh_eth_device, &usb0_host_device, &usb1_common_device, + &usbhs_device, &lcdc_device, &ceu0_device, &ceu1_device, -- cgit v1.2.3-18-g5258 From 261a9af671a79b750cb170bac620601d686535c1 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Wed, 15 Jun 2011 06:08:28 +0000 Subject: sh: sh7724: Add USBHS DMAEngine support Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- arch/sh/include/cpu-sh4/cpu/sh7724.h | 8 +++++++ arch/sh/kernel/cpu/sh4a/setup-sh7724.c | 40 ++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h index 3daef8ecbc6..cbc47e6bcab 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7724.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h @@ -298,6 +298,14 @@ enum { SHDMA_SLAVE_SCIF4_RX, SHDMA_SLAVE_SCIF5_TX, SHDMA_SLAVE_SCIF5_RX, + SHDMA_SLAVE_USB0D0_TX, + SHDMA_SLAVE_USB0D0_RX, + SHDMA_SLAVE_USB0D1_TX, + SHDMA_SLAVE_USB0D1_RX, + SHDMA_SLAVE_USB1D0_TX, + SHDMA_SLAVE_USB1D0_RX, + SHDMA_SLAVE_USB1D1_TX, + SHDMA_SLAVE_USB1D1_RX, SHDMA_SLAVE_SDHI0_TX, SHDMA_SLAVE_SDHI0_RX, SHDMA_SLAVE_SDHI1_TX, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c index 0333fe9e388..134a397b191 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c @@ -92,6 +92,46 @@ static const struct sh_dmae_slave_config sh7724_dmae_slaves[] = { .addr = 0xa4e50024, .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x36, + }, { + .slave_id = SHDMA_SLAVE_USB0D0_TX, + .addr = 0xA4D80100, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x73, + }, { + .slave_id = SHDMA_SLAVE_USB0D0_RX, + .addr = 0xA4D80100, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x73, + }, { + .slave_id = SHDMA_SLAVE_USB0D1_TX, + .addr = 0xA4D80120, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x77, + }, { + .slave_id = SHDMA_SLAVE_USB0D1_RX, + .addr = 0xA4D80120, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0x77, + }, { + .slave_id = SHDMA_SLAVE_USB1D0_TX, + .addr = 0xA4D90100, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xab, + }, { + .slave_id = SHDMA_SLAVE_USB1D0_RX, + .addr = 0xA4D90100, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xab, + }, { + .slave_id = SHDMA_SLAVE_USB1D1_TX, + .addr = 0xA4D90120, + .chcr = DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xaf, + }, { + .slave_id = SHDMA_SLAVE_USB1D1_RX, + .addr = 0xA4D90120, + .chcr = DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT), + .mid_rid = 0xaf, }, { .slave_id = SHDMA_SLAVE_SDHI0_TX, .addr = 0x04ce0030, -- cgit v1.2.3-18-g5258