diff options
38 files changed, 405 insertions, 182 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index b959659c5df4..b3f35e5f9c95 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -603,3 +603,19 @@ Why: The adm9240, w83792d and w83793 hardware monitoring drivers have Who: Jean Delvare <khali@linux-fr.org> ---------------------------- + +What: noswapaccount kernel command line parameter +When: 2.6.40 +Why: The original implementation of memsw feature enabled by + CONFIG_CGROUP_MEM_RES_CTLR_SWAP could be disabled by the noswapaccount + kernel parameter (introduced in 2.6.29-rc1). Later on, this decision + turned out to be not ideal because we cannot have the feature compiled + in and disabled by default and let only interested to enable it + (e.g. general distribution kernels might need it). Therefore we have + added swapaccount[=0|1] parameter (introduced in 2.6.37) which provides + the both possibilities. If we remove noswapaccount we will have + less command line parameters with the same functionality and we + can also cleanup the parameter handling a bit (). +Who: Michal Hocko <mhocko@suse.cz> + +---------------------------- diff --git a/Documentation/scheduler/sched-stats.txt b/Documentation/scheduler/sched-stats.txt index 01e69404ee5e..1cd5d51bc761 100644 --- a/Documentation/scheduler/sched-stats.txt +++ b/Documentation/scheduler/sched-stats.txt @@ -1,3 +1,7 @@ +Version 15 of schedstats dropped counters for some sched_yield: +yld_exp_empty, yld_act_empty and yld_both_empty. Otherwise, it is +identical to version 14. + Version 14 of schedstats includes support for sched_domains, which hit the mainline kernel in 2.6.20 although it is identical to the stats from version 12 which was in the kernel from 2.6.13-2.6.19 (version 13 never saw a kernel @@ -28,32 +32,25 @@ to write their own scripts, the fields are described here. CPU statistics -------------- -cpu<N> 1 2 3 4 5 6 7 8 9 10 11 12 - -NOTE: In the sched_yield() statistics, the active queue is considered empty - if it has only one process in it, since obviously the process calling - sched_yield() is that process. +cpu<N> 1 2 3 4 5 6 7 8 9 -First four fields are sched_yield() statistics: - 1) # of times both the active and the expired queue were empty - 2) # of times just the active queue was empty - 3) # of times just the expired queue was empty - 4) # of times sched_yield() was called +First field is a sched_yield() statistic: + 1) # of times sched_yield() was called Next three are schedule() statistics: - 5) # of times we switched to the expired queue and reused it - 6) # of times schedule() was called - 7) # of times schedule() left the processor idle + 2) # of times we switched to the expired queue and reused it + 3) # of times schedule() was called + 4) # of times schedule() left the processor idle Next two are try_to_wake_up() statistics: - 8) # of times try_to_wake_up() was called - 9) # of times try_to_wake_up() was called to wake up the local cpu + 5) # of times try_to_wake_up() was called + 6) # of times try_to_wake_up() was called to wake up the local cpu Next three are statistics describing scheduling latency: - 10) sum of all time spent running by tasks on this processor (in jiffies) - 11) sum of all time spent waiting to run by tasks on this processor (in + 7) sum of all time spent running by tasks on this processor (in jiffies) + 8) sum of all time spent waiting to run by tasks on this processor (in jiffies) - 12) # of timeslices run on this cpu + 9) # of timeslices run on this cpu Domain statistics diff --git a/MAINTAINERS b/MAINTAINERS index 445537d46e7a..9511bff301c9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -978,6 +978,8 @@ S: Maintained F: arch/arm/plat-samsung/ F: arch/arm/plat-s3c24xx/ F: arch/arm/plat-s5p/ +F: drivers/*/*s3c2410* +F: drivers/*/*/*s3c2410* ARM/S3C2410 ARM ARCHITECTURE M: Ben Dooks <ben-linux@fluff.org> @@ -5614,18 +5616,20 @@ F: include/linux/sfi*.h SIMTEC EB110ATX (Chalice CATS) P: Ben Dooks -M: Vincent Sanders <support@simtec.co.uk> +P: Vincent Sanders <vince@simtec.co.uk> +M: Simtec Linux Team <linux@simtec.co.uk> W: http://www.simtec.co.uk/products/EB110ATX/ S: Supported SIMTEC EB2410ITX (BAST) P: Ben Dooks -M: Vincent Sanders <support@simtec.co.uk> +P: Vincent Sanders <vince@simtec.co.uk> +M: Simtec Linux Team <linux@simtec.co.uk> W: http://www.simtec.co.uk/products/EB2410ITX/ S: Supported -F: arch/arm/mach-s3c2410/ -F: drivers/*/*s3c2410* -F: drivers/*/*/*s3c2410* +F: arch/arm/mach-s3c2410/mach-bast.c +F: arch/arm/mach-s3c2410/bast-ide.c +F: arch/arm/mach-s3c2410/bast-irq.c TI DAVINCI MACHINE SUPPORT M: Kevin Hilman <khilman@deeprootsystems.com> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ff19efdf6fef..636bcb81d068 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -406,7 +406,7 @@ config QDIO If unsure, say Y. config CHSC_SCH - def_tristate y + def_tristate m prompt "Support for CHSC subchannels" help This driver allows usage of CHSC subchannels. A CHSC subchannel diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h index 405cc97c6249..7e1f77620624 100644 --- a/arch/s390/include/asm/cacheflush.h +++ b/arch/s390/include/asm/cacheflush.h @@ -1,29 +1,8 @@ #ifndef _S390_CACHEFLUSH_H #define _S390_CACHEFLUSH_H -/* Keep includes the same across arches. */ -#include <linux/mm.h> - /* Caches aren't brain-dead on the s390. */ -#define flush_cache_all() do { } while (0) -#define flush_cache_mm(mm) do { } while (0) -#define flush_cache_dup_mm(mm) do { } while (0) -#define flush_cache_range(vma, start, end) do { } while (0) -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define flush_dcache_page(page) do { } while (0) -#define flush_dcache_mmap_lock(mapping) do { } while (0) -#define flush_dcache_mmap_unlock(mapping) do { } while (0) -#define flush_icache_range(start, end) do { } while (0) -#define flush_icache_page(vma,pg) do { } while (0) -#define flush_icache_user_range(vma,pg,adr,len) do { } while (0) -#define flush_cache_vmap(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) do { } while (0) - -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) +#include <asm-generic/cacheflush.h> #ifdef CONFIG_DEBUG_PAGEALLOC void kernel_map_pages(struct page *page, int numpages, int enable); diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index f1f644f2240a..9074a54c4d10 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -22,6 +22,7 @@ */ #include <linux/mm.h> +#include <linux/pagemap.h> #include <linux/swap.h> #include <asm/processor.h> #include <asm/pgalloc.h> diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index 07deaeee14c8..a6c4f7ed24a4 100644 --- a/arch/s390/lib/uaccess_std.c +++ b/arch/s390/lib/uaccess_std.c @@ -125,9 +125,9 @@ static size_t copy_in_user_std(size_t size, void __user *to, unsigned long tmp1; asm volatile( + " sacf 256\n" " "AHI" %0,-1\n" " jo 5f\n" - " sacf 256\n" " bras %3,3f\n" "0:"AHI" %0,257\n" "1: mvc 0(1,%1),0(%2)\n" @@ -142,9 +142,8 @@ static size_t copy_in_user_std(size_t size, void __user *to, "3:"AHI" %0,-256\n" " jnm 2b\n" "4: ex %0,1b-0b(%3)\n" - " sacf 0\n" "5: "SLR" %0,%0\n" - "6:\n" + "6: sacf 0\n" EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b) : "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1) : : "cc", "memory"); @@ -156,9 +155,9 @@ static size_t clear_user_std(size_t size, void __user *to) unsigned long tmp1, tmp2; asm volatile( + " sacf 256\n" " "AHI" %0,-1\n" " jo 5f\n" - " sacf 256\n" " bras %3,3f\n" " xc 0(1,%1),0(%1)\n" "0:"AHI" %0,257\n" @@ -178,9 +177,8 @@ static size_t clear_user_std(size_t size, void __user *to) "3:"AHI" %0,-256\n" " jnm 2b\n" "4: ex %0,0(%3)\n" - " sacf 0\n" "5: "SLR" %0,%0\n" - "6:\n" + "6: sacf 0\n" EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b) : "+a" (size), "+a" (to), "=a" (tmp1), "=a" (tmp2) : : "cc", "memory"); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 0c719c61972e..e1850c28cd68 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -336,7 +336,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) page->flags ^= bits; if (page->flags & FRAG_MASK) { /* Page now has some free pgtable fragments. */ - list_move(&page->lru, &mm->context.pgtable_list); + if (!list_empty(&page->lru)) + list_move(&page->lru, &mm->context.pgtable_list); page = NULL; } else /* All fragments of the 4K page have been freed. */ diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index e56b9bfbabd1..f7a0993c1e7c 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -682,7 +682,7 @@ static int p4_validate_raw_event(struct perf_event *event) * if an event is shared accross the logical threads * the user needs special permissions to be able to use it */ - if (p4_event_bind_map[v].shared) { + if (p4_ht_active() && p4_event_bind_map[v].shared) { if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return -EACCES; } @@ -727,7 +727,8 @@ static int p4_hw_config(struct perf_event *event) event->hw.config = p4_set_ht_bit(event->hw.config); if (event->attr.type == PERF_TYPE_RAW) { - + struct p4_event_bind *bind; + unsigned int esel; /* * Clear bits we reserve to be managed by kernel itself * and never allowed from a user space @@ -743,6 +744,13 @@ static int p4_hw_config(struct perf_event *event) * bits since we keep additional info here (for cache events and etc) */ event->hw.config |= event->attr.config; + bind = p4_config_get_bind(event->attr.config); + if (!bind) { + rc = -EINVAL; + goto out; + } + esel = P4_OPCODE_ESEL(bind->opcode); + event->hw.config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel)); } rc = x86_setup_perfctr(event); diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c index f011c5d9dea1..1c5cc65ea1e1 100644 --- a/drivers/media/rc/ir-lirc-codec.c +++ b/drivers/media/rc/ir-lirc-codec.c @@ -1,4 +1,4 @@ -/* ir-lirc-codec.c - ir-core to classic lirc interface bridge +/* ir-lirc-codec.c - rc-core to classic lirc interface bridge * * Copyright (C) 2010 by Jarod Wilson <jarod@redhat.com> * @@ -47,6 +47,7 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) /* Carrier reports */ if (ev.carrier_report) { sample = LIRC_FREQUENCY(ev.carrier); + IR_dprintk(2, "carrier report (freq: %d)\n", sample); /* Packet end */ } else if (ev.timeout) { @@ -62,6 +63,7 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) return 0; sample = LIRC_TIMEOUT(ev.duration / 1000); + IR_dprintk(2, "timeout report (duration: %d)\n", sample); /* Normal sample */ } else { @@ -85,6 +87,8 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) sample = ev.pulse ? LIRC_PULSE(ev.duration / 1000) : LIRC_SPACE(ev.duration / 1000); + IR_dprintk(2, "delivering %uus %s to lirc_dev\n", + TO_US(ev.duration), TO_STR(ev.pulse)); } lirc_buffer_write(dev->raw->lirc.drv->rbuf, diff --git a/drivers/media/rc/keymaps/rc-rc6-mce.c b/drivers/media/rc/keymaps/rc-rc6-mce.c index 3bf3337875d1..2f5dc0622b94 100644 --- a/drivers/media/rc/keymaps/rc-rc6-mce.c +++ b/drivers/media/rc/keymaps/rc-rc6-mce.c @@ -3,6 +3,9 @@ * * Copyright (c) 2010 by Jarod Wilson <jarod@redhat.com> * + * See http://mediacenterguides.com/book/export/html/31 for details on + * key mappings. + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or @@ -60,6 +63,9 @@ static struct rc_map_table rc6_mce[] = { { 0x800f0426, KEY_EPG }, /* Guide */ { 0x800f0427, KEY_ZOOM }, /* Aspect */ + { 0x800f0432, KEY_MODE }, /* Visualization */ + { 0x800f0433, KEY_PRESENTATION }, /* Slide Show */ + { 0x800f0434, KEY_EJECTCD }, { 0x800f043a, KEY_BRIGHTNESSUP }, { 0x800f0446, KEY_TV }, diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index 079353e5d558..6df0a4980645 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -816,7 +816,7 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index) switch (ir->buf_in[index]) { /* 2-byte return value commands */ case MCE_CMD_S_TIMEOUT: - ir->rc->timeout = MS_TO_NS((hi << 8 | lo) / 2); + ir->rc->timeout = US_TO_NS((hi << 8 | lo) / 2); break; /* 1-byte return value commands */ @@ -855,9 +855,10 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) break; case PARSE_IRDATA: ir->rem--; + init_ir_raw_event(&rawir); rawir.pulse = ((ir->buf_in[i] & MCE_PULSE_BIT) != 0); rawir.duration = (ir->buf_in[i] & MCE_PULSE_MASK) - * MS_TO_US(MCE_TIME_UNIT); + * US_TO_NS(MCE_TIME_UNIT); dev_dbg(ir->dev, "Storing %s with duration %d\n", rawir.pulse ? "pulse" : "space", @@ -883,6 +884,8 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) i, ir->rem + 1, false); if (ir->rem) ir->parser_state = PARSE_IRDATA; + else + ir_raw_event_reset(ir->rc); break; } @@ -1060,7 +1063,7 @@ static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir) rc->priv = ir; rc->driver_type = RC_DRIVER_IR_RAW; rc->allowed_protos = RC_TYPE_ALL; - rc->timeout = MS_TO_NS(1000); + rc->timeout = US_TO_NS(1000); if (!ir->flags.no_tx) { rc->s_tx_mask = mceusb_set_tx_mask; rc->s_tx_carrier = mceusb_set_tx_carrier; diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c index dd4caf8ef80b..273d9d674792 100644 --- a/drivers/media/rc/nuvoton-cir.c +++ b/drivers/media/rc/nuvoton-cir.c @@ -460,7 +460,7 @@ static u32 nvt_rx_carrier_detect(struct nvt_dev *nvt) return 0; } - carrier = (count * 1000000) / duration; + carrier = MS_TO_NS(count) / duration; if ((carrier > MAX_CARRIER) || (carrier < MIN_CARRIER)) nvt_dbg("WTF? Carrier frequency out of range!"); @@ -612,8 +612,8 @@ static void nvt_process_rx_ir_data(struct nvt_dev *nvt) sample = nvt->buf[i]; rawir.pulse = ((sample & BUF_PULSE_BIT) != 0); - rawir.duration = (sample & BUF_LEN_MASK) - * SAMPLE_PERIOD * 1000; + rawir.duration = US_TO_NS((sample & BUF_LEN_MASK) + * SAMPLE_PERIOD); if ((sample & BUF_LEN_MASK) == BUF_LEN_MASK) { if (nvt->rawir.pulse == rawir.pulse) diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c index 6e2911c2abfb..e435d94c0776 100644 --- a/drivers/media/rc/streamzap.c +++ b/drivers/media/rc/streamzap.c @@ -164,7 +164,7 @@ static void sz_push_full_pulse(struct streamzap_ir *sz, sz->signal_start.tv_usec - sz->signal_last.tv_usec); rawir.duration -= sz->sum; - rawir.duration *= 1000; + rawir.duration = US_TO_NS(rawir.duration); rawir.duration &= IR_MAX_DURATION; } sz_push(sz, rawir); @@ -177,7 +177,7 @@ static void sz_push_full_pulse(struct streamzap_ir *sz, rawir.duration = ((int) value) * SZ_RESOLUTION; rawir.duration += SZ_RESOLUTION / 2; sz->sum += rawir.duration; - rawir.duration *= 1000; + rawir.duration = US_TO_NS(rawir.duration); rawir.duration &= IR_MAX_DURATION; sz_push(sz, rawir); } @@ -197,7 +197,7 @@ static void sz_push_full_space(struct streamzap_ir *sz, rawir.duration = ((int) value) * SZ_RESOLUTION; rawir.duration += SZ_RESOLUTION / 2; sz->sum += rawir.duration; - rawir.duration *= 1000; + rawir.duration = US_TO_NS(rawir.duration); sz_push(sz, rawir); } @@ -273,6 +273,7 @@ static void streamzap_callback(struct urb *urb) if (sz->timeout_enabled) sz_push(sz, rawir); ir_raw_event_handle(sz->rdev); + ir_raw_event_reset(sz->rdev); } else { sz_push_full_space(sz, sz->buf_in[i]); } @@ -290,6 +291,7 @@ static void streamzap_callback(struct urb *urb) } } + ir_raw_event_handle(sz->rdev); usb_submit_urb(urb, GFP_ATOMIC); return; @@ -430,13 +432,13 @@ static int __devinit streamzap_probe(struct usb_interface *intf, sz->decoder_state = PulseSpace; /* FIXME: don't yet have a way to set this */ sz->timeout_enabled = true; - sz->rdev->timeout = (((SZ_TIMEOUT * SZ_RESOLUTION * 1000) & + sz->rdev->timeout = ((US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION) & IR_MAX_DURATION) | 0x03000000); #if 0 /* not yet supported, depends on patches from maxim */ /* see also: LIRC_GET_REC_RESOLUTION and LIRC_SET_REC_TIMEOUT */ - sz->min_timeout = SZ_TIMEOUT * SZ_RESOLUTION * 1000; - sz->max_timeout = SZ_TIMEOUT * SZ_RESOLUTION * 1000; + sz->min_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION); + sz->max_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION); #endif do_gettimeofday(&sz->signal_start); diff --git a/drivers/media/video/gspca/zc3xx.c b/drivers/media/video/gspca/zc3xx.c index 865216e9362c..47236a58bf33 100644 --- a/drivers/media/video/gspca/zc3xx.c +++ b/drivers/media/video/gspca/zc3xx.c @@ -5793,7 +5793,7 @@ static void usb_exchange(struct gspca_dev *gspca_dev, break; default: /* case 0xdd: * delay */ - msleep(action->val / 64 + 10); + msleep(action->idx); break; } action++; @@ -5830,7 +5830,7 @@ static void setmatrix(struct gspca_dev *gspca_dev) [SENSOR_GC0305] = gc0305_matrix, [SENSOR_HDCS2020b] = NULL, [SENSOR_HV7131B] = NULL, - [SENSOR_HV7131R] = NULL, + [SENSOR_HV7131R] = po2030_matrix, [SENSOR_ICM105A] = po2030_matrix, [SENSOR_MC501CB] = NULL, [SENSOR_MT9V111_1] = gc0305_matrix, @@ -5936,6 +5936,7 @@ static void setquality(struct gspca_dev *gspca_dev) case SENSOR_ADCM2700: case SENSOR_GC0305: case SENSOR_HV7131B: + case SENSOR_HV7131R: case SENSOR_OV7620: case SENSOR_PAS202B: case SENSOR_PO2030: @@ -6108,11 +6109,13 @@ static void send_unknown(struct gspca_dev *gspca_dev, int sensor) reg_w(gspca_dev, 0x02, 0x003b); reg_w(gspca_dev, 0x00, 0x0038); break; + case SENSOR_HV7131R: case SENSOR_PAS202B: reg_w(gspca_dev, 0x03, 0x003b); reg_w(gspca_dev, 0x0c, 0x003a); reg_w(gspca_dev, 0x0b, 0x0039); - reg_w(gspca_dev, 0x0b, 0x0038); + if (sensor == SENSOR_PAS202B) + reg_w(gspca_dev, 0x0b, 0x0038); break; } } @@ -6704,10 +6707,13 @@ static int sd_start(struct gspca_dev *gspca_dev) reg_w(gspca_dev, 0x02, 0x003b); reg_w(gspca_dev, 0x00, 0x0038); break; + case SENSOR_HV7131R: case SENSOR_PAS202B: reg_w(gspca_dev, 0x03, 0x003b); reg_w(gspca_dev, 0x0c, 0x003a); reg_w(gspca_dev, 0x0b, 0x0039); + if (sd->sensor == SENSOR_HV7131R) + reg_w(gspca_dev, 0x50, ZC3XX_R11D_GLOBALGAIN); break; } @@ -6720,6 +6726,7 @@ static int sd_start(struct gspca_dev *gspca_dev) break; case SENSOR_PAS202B: case SENSOR_GC0305: + case SENSOR_HV7131R: case SENSOR_TAS5130C: reg_r(gspca_dev, 0x0008); /* fall thru */ @@ -6760,6 +6767,12 @@ static int sd_start(struct gspca_dev *gspca_dev) /* ms-win + */ reg_w(gspca_dev, 0x40, 0x0117); break; + case SENSOR_HV7131R: + i2c_write(gspca_dev, 0x25, 0x04, 0x00); /* exposure */ + i2c_write(gspca_dev, 0x26, 0x93, 0x00); + i2c_write(gspca_dev, 0x27, 0xe0, 0x00); + reg_w(gspca_dev, 0x00, ZC3XX_R1A7_CALCGLOBALMEAN); + break; case SENSOR_GC0305: case SENSOR_TAS5130C: reg_w(gspca_dev, 0x09, 0x01ad); /* (from win traces) */ @@ -6808,9 +6821,17 @@ static void sd_pkt_scan(struct gspca_dev *gspca_dev, { struct sd *sd = (struct sd *) gspca_dev; - if (data[0] == 0xff && data[1] == 0xd8) { /* start of frame */ + /* check the JPEG end of frame */ + if (len >= 3 + && data[len - 3] == 0xff && data[len - 2] == 0xd9) { +/*fixme: what does the last byte mean?*/ gspca_frame_add(gspca_dev, LAST_PACKET, - NULL, 0); + data, len - 1); + return; + } + + /* check the JPEG start of a frame */ + if (data[0] == 0xff && data[1] == 0xd8) { /* put the JPEG header in the new frame */ gspca_frame_add(gspca_dev, FIRST_PACKET, sd->jpeg_hdr, JPEG_HDR_SZ); diff --git a/drivers/media/video/hdpvr/hdpvr-core.c b/drivers/media/video/hdpvr/hdpvr-core.c index a6572e5ae369..a27d93b503a5 100644 --- a/drivers/media/video/hdpvr/hdpvr-core.c +++ b/drivers/media/video/hdpvr/hdpvr-core.c @@ -283,6 +283,7 @@ static int hdpvr_probe(struct usb_interface *interface, struct hdpvr_device *dev; struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *endpoint; + struct i2c_client *client; size_t buffer_size; int i; int retval = -ENOMEM; @@ -381,13 +382,21 @@ static int hdpvr_probe(struct usb_interface *interface, #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) retval = hdpvr_register_i2c_adapter(dev); if (retval < 0) { - v4l2_err(&dev->v4l2_dev, "registering i2c adapter failed\n"); + v4l2_err(&dev->v4l2_dev, "i2c adapter register failed\n"); goto error; } - retval = hdpvr_register_i2c_ir(dev); - if (retval < 0) - v4l2_err(&dev->v4l2_dev, "registering i2c IR devices failed\n"); + client = hdpvr_register_ir_rx_i2c(dev); + if (!client) { + v4l2_err(&dev->v4l2_dev, "i2c IR RX device register failed\n"); + goto reg_fail; + } + + client = hdpvr_register_ir_tx_i2c(dev); + if (!client) { + v4l2_err(&dev->v4l2_dev, "i2c IR TX device register failed\n"); + goto reg_fail; + } #endif /* let the user know what node this device is now attached to */ @@ -395,6 +404,10 @@ static int hdpvr_probe(struct usb_interface *interface, video_device_node_name(dev->video_dev)); return 0; +reg_fail: +#if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) + i2c_del_adapter(&dev->i2c_adapter); +#endif error: if (dev) { /* Destroy single thread */ @@ -424,6 +437,9 @@ static void hdpvr_disconnect(struct usb_interface *interface) mutex_lock(&dev->io_mutex); hdpvr_cancel_queue(dev); mutex_unlock(&dev->io_mutex); +#if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) + i2c_del_adapter(&dev->i2c_adapter); +#endif video_unregister_device(dev->video_dev); atomic_dec(&dev_nr); } diff --git a/drivers/media/video/hdpvr/hdpvr-i2c.c b/drivers/media/video/hdpvr/hdpvr-i2c.c index 89b71faeaac2..e53fa55d56a1 100644 --- a/drivers/media/video/hdpvr/hdpvr-i2c.c +++ b/drivers/media/video/hdpvr/hdpvr-i2c.c @@ -31,26 +31,34 @@ #define Z8F0811_IR_RX_I2C_ADDR 0x71 -static struct i2c_board_info hdpvr_i2c_board_info = { - I2C_BOARD_INFO("ir_tx_z8f0811_hdpvr", Z8F0811_IR_TX_I2C_ADDR), - I2C_BOARD_INFO("ir_rx_z8f0811_hdpvr", Z8F0811_IR_RX_I2C_ADDR), -}; +struct i2c_client *hdpvr_register_ir_tx_i2c(struct hdpvr_device *dev) +{ + struct IR_i2c_init_data *init_data = &dev->ir_i2c_init_data; + struct i2c_board_info hdpvr_ir_tx_i2c_board_info = { + I2C_BOARD_INFO("ir_tx_z8f0811_hdpvr", Z8F0811_IR_TX_I2C_ADDR), + }; + + init_data->name = "HD-PVR"; + hdpvr_ir_tx_i2c_board_info.platform_data = init_data; -int hdpvr_register_i2c_ir(struct hdpvr_device *dev) + return i2c_new_device(&dev->i2c_adapter, &hdpvr_ir_tx_i2c_board_info); +} + +struct i2c_client *hdpvr_register_ir_rx_i2c(struct hdpvr_device *dev) { - struct i2c_client *c; struct IR_i2c_init_data *init_data = &dev->ir_i2c_init_data; + struct i2c_board_info hdpvr_ir_rx_i2c_board_info = { + I2C_BOARD_INFO("ir_rx_z8f0811_hdpvr", Z8F0811_IR_RX_I2C_ADDR), + }; /* Our default information for ir-kbd-i2c.c to use */ init_data->ir_codes = RC_MAP_HAUPPAUGE_NEW; init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR; init_data->type = RC_TYPE_RC5; - init_data->name = "HD PVR"; - hdpvr_i2c_board_info.platform_data = init_data; - - c = i2c_new_device(&dev->i2c_adapter, &hdpvr_i2c_board_info); + init_data->name = "HD-PVR"; + hdpvr_ir_rx_i2c_board_info.platform_data = init_data; - return (c == NULL) ? -ENODEV : 0; + return i2c_new_device(&dev->i2c_adapter, &hdpvr_ir_rx_i2c_board_info); } static int hdpvr_i2c_read(struct hdpvr_device *dev, int bus, diff --git a/drivers/media/video/hdpvr/hdpvr.h b/drivers/media/video/hdpvr/hdpvr.h index ee74e3be9a6a..072f23c570f3 100644 --- a/drivers/media/video/hdpvr/hdpvr.h +++ b/drivers/media/video/hdpvr/hdpvr.h @@ -313,7 +313,8 @@ int hdpvr_cancel_queue(struct hdpvr_device *dev); /* i2c adapter registration */ int hdpvr_register_i2c_adapter(struct hdpvr_device *dev); -int hdpvr_register_i2c_ir(struct hdpvr_device *dev); +struct i2c_client *hdpvr_register_ir_rx_i2c(struct hdpvr_device *dev); +struct i2c_client *hdpvr_register_ir_tx_i2c(struct hdpvr_device *dev); /*========================================================================*/ /* buffer management */ diff --git a/drivers/media/video/ir-kbd-i2c.c b/drivers/media/video/ir-kbd-i2c.c index d2b20ad383a3..a221ad68b330 100644 --- a/drivers/media/video/ir-kbd-i2c.c +++ b/drivers/media/video/ir-kbd-i2c.c @@ -128,6 +128,19 @@ static int get_key_haup(struct IR_i2c *ir, u32 *ir_key, u32 *ir_raw) static int get_key_haup_xvr(struct IR_i2c *ir, u32 *ir_key, u32 *ir_raw) { + int ret; + unsigned char buf[1] = { 0 }; + + /* + * This is the same apparent "are you ready?" poll command observed + * watching Windows driver traffic and implemented in lirc_zilog. With + * this added, we get far saner remote behavior with z8 chips on usb + * connected devices, even with the default polling interval of 100ms. + */ + ret = i2c_master_send(ir->c, buf, 1); + if (ret != 1) + return (ret < 0) ? ret : -EINVAL; + return get_key_haup_common (ir, ir_key, ir_raw, 6, 3); } diff --git a/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c b/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c index ccc884948f34..451ecd485f97 100644 --- a/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c +++ b/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c @@ -597,7 +597,6 @@ static void pvr2_i2c_register_ir(struct pvr2_hdw *hdw) init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR; init_data->type = RC_TYPE_RC5; init_data->name = hdw->hdw_desc->description; - init_data->polling_interval = 260; /* ms From lirc_zilog */ /* IR Receiver */ info.addr = 0x71; info.platform_data = init_data; diff --git a/drivers/media/video/saa7115.c b/drivers/media/video/saa7115.c index f35459d1f42f..0db90922ee93 100644 --- a/drivers/media/video/saa7115.c +++ b/drivers/media/video/saa7115.c @@ -1565,7 +1565,7 @@ static int saa711x_probe(struct i2c_client *client, chip_id = name[5]; /* Check whether this chip is part of the saa711x series */ - if (memcmp(name, "1f711", 5)) { + if (memcmp(name + 1, "f711", 4)) { v4l_dbg(1, debug, client, "chip found @ 0x%x (ID %s) does not match a known saa711x chip.\n", client->addr << 1, name); return -ENODEV; diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 4155805dcdff..2b771f18d1ad 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -319,6 +319,9 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) private = (struct dasd_eckd_private *) device->private; lcu = private->lcu; + /* nothing to do if already disconnected */ + if (!lcu) + return; device->discipline->get_uid(device, &uid); spin_lock_irqsave(&lcu->lock, flags); list_del_init(&device->alias_list); @@ -680,6 +683,9 @@ int dasd_alias_remove_device(struct dasd_device *device) private = (struct dasd_eckd_private *) device->private; lcu = private->lcu; + /* nothing to do if already removed */ + if (!lcu) + return 0; spin_lock_irqsave(&lcu->lock, flags); _remove_device_from_lcu(lcu, device); spin_unlock_irqrestore(&lcu->lock, flags); diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index e9fff2b9bce2..5640c89cd9de 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -476,7 +476,7 @@ static inline void inbound_primed(struct qdio_q *q, int count) static int get_inbound_buffer_frontier(struct qdio_q *q) { int count, stop; - unsigned char state; + unsigned char state = 0; /* * Don't check 128 buffers, as otherwise qdio_inbound_q_moved @@ -643,7 +643,7 @@ void qdio_inbound_processing(unsigned long data) static int get_outbound_buffer_frontier(struct qdio_q *q) { int count, stop; - unsigned char state; + unsigned char state = 0; if (need_siga_sync(q)) if (((queue_type(q) != QDIO_IQDIO_QFMT) && diff --git a/drivers/staging/lirc/lirc_zilog.c b/drivers/staging/lirc/lirc_zilog.c index 3fe5f4160194..0aad0d7a74a3 100644 --- a/drivers/staging/lirc/lirc_zilog.c +++ b/drivers/staging/lirc/lirc_zilog.c @@ -495,7 +495,7 @@ static int send_data_block(struct IR_tx *tx, unsigned char *data_block) /* send boot data to the IR TX device */ static int send_boot_data(struct IR_tx *tx) { - int ret; + int ret, i; unsigned char buf[4]; /* send the boot block */ @@ -503,7 +503,7 @@ static int send_boot_data(struct IR_tx *tx) if (ret != 0) return ret; - /* kick it off? */ + /* Hit the go button to activate the new boot data */ buf[0] = 0x00; buf[1] = 0x20; ret = i2c_master_send(tx->c, buf, 2); @@ -511,7 +511,19 @@ static int send_boot_data(struct IR_tx *tx) zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; } - ret = i2c_master_send(tx->c, buf, 1); + + /* + * Wait for zilog to settle after hitting go post boot block upload. + * Without this delay, the HD-PVR and HVR-1950 both return an -EIO + * upon attempting to get firmware revision, and tx probe thus fails. + */ + for (i = 0; i < 10; i++) { + ret = i2c_master_send(tx->c, buf, 1); + if (ret == 1) + break; + udelay(100); + } + if (ret != 1) { zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; @@ -523,8 +535,8 @@ static int send_boot_data(struct IR_tx *tx) zilog_error("i2c_master_recv failed with %d\n", ret); return 0; } - if (buf[0] != 0x80) { - zilog_error("unexpected IR TX response: %02x\n", buf[0]); + if ((buf[0] != 0x80) && (buf[0] != 0xa0)) { + zilog_error("unexpected IR TX init response: %02x\n", buf[0]); return 0; } zilog_notify("Zilog/Hauppauge IR blaster firmware version " @@ -827,7 +839,15 @@ static int send_code(struct IR_tx *tx, unsigned int code, unsigned int key) zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; } - ret = i2c_master_send(tx->c, buf, 1); + + /* Give the z8 a moment to process data block */ + for (i = 0; i < 10; i++) { + ret = i2c_master_send(tx->c, buf, 1); + if (ret == 1) + break; + udelay(100); + } + if (ret != 1) { zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cc8a9b7d6064..267d0ada4541 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1114,6 +1114,17 @@ static int ep_send_events(struct eventpoll *ep, return ep_scan_ready_list(ep, ep_send_events_proc, &esed); } +static inline struct timespec ep_set_mstimeout(long ms) +{ + struct timespec now, ts = { + .tv_sec = ms / MSEC_PER_SEC, + .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC), + }; + + ktime_get_ts(&now); + return timespec_add_safe(now, ts); +} + static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, long timeout) { @@ -1121,12 +1132,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, unsigned long flags; long slack; wait_queue_t wait; - struct timespec end_time; ktime_t expires, *to = NULL; if (timeout > 0) { - ktime_get_ts(&end_time); - timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC); + struct timespec end_time = ep_set_mstimeout(timeout); + slack = select_estimate_accuracy(&end_time); to = &expires; *to = timespec_to_ktime(end_time); diff --git a/fs/exec.c b/fs/exec.c index c62efcb959c7..52a447d9b6ab 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -120,7 +120,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) goto out; file = do_filp_open(AT_FDCWD, tmp, - O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, + O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0, MAY_READ | MAY_EXEC | MAY_OPEN); putname(tmp); error = PTR_ERR(file); @@ -723,7 +723,7 @@ struct file *open_exec(const char *name) int err; file = do_filp_open(AT_FDCWD, name, - O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, + O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0, MAY_EXEC | MAY_OPEN); if (IS_ERR(file)) goto out; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 42685424817b..a7555238c41a 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1030,7 +1030,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data)); } - inode->i_mapping->backing_dev_info = sb->s_bdi; if (S_ISREG(inode->i_mode)) { inode->i_op = &exofs_file_inode_operations; inode->i_fop = &exofs_file_operations; @@ -1131,7 +1130,6 @@ struct inode *exofs_new_inode(struct inode *dir, int mode) sbi = sb->s_fs_info; - inode->i_mapping->backing_dev_info = sb->s_bdi; sb->s_dirt = 1; inode_init_owner(inode, dir, mode); inode->i_ino = sbi->s_nextid++; diff --git a/fs/fcntl.c b/fs/fcntl.c index ecc8b3954ed6..cb1026181bdc 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -815,7 +815,7 @@ static int __init fcntl_init(void) __O_SYNC | O_DSYNC | FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - FMODE_EXEC + __FMODE_EXEC )); fasync_cache = kmem_cache_create("fasync_cache", diff --git a/fs/ioctl.c b/fs/ioctl.c index a59635e295fa..1eebeb72b202 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -273,6 +273,13 @@ int __generic_block_fiemap(struct inode *inode, len = isize; } + /* + * Some filesystems can't deal with being asked to map less than + * blocksize, so make sure our len is at least block length. + */ + if (logical_to_blk(inode, len) == 0) + len = blk_to_logical(inode, 1); + start_blk = logical_to_blk(inode, start); last_blk = logical_to_blk(inode, start + len - 1); diff --git a/include/linux/fs.h b/include/linux/fs.h index 32b38cd829d3..bd3215940c37 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2555,9 +2555,12 @@ int proc_nr_inodes(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); +#define __FMODE_EXEC ((__force int) FMODE_EXEC) +#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) + #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & FMODE_NONOTIFY))) + (flag & __FMODE_NONOTIFY))) #endif /* __KERNEL__ */ #endif /* _LINUX_FS_H */ diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index fcb9884df618..a5930cb66145 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -182,6 +182,26 @@ static inline bool res_counter_check_under_limit(struct res_counter *cnt) return ret; } +/** + * res_counter_check_margin - check if the counter allows charging + * @cnt: the resource counter to check + * @bytes: the number of bytes to check the remaining space against + * + * Returns a boolean value on whether the counter can be charged + * @bytes or whether this would exceed the limit. + */ +static inline bool res_counter_check_margin(struct res_counter *cnt, + unsigned long bytes) +{ + bool ret; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + ret = cnt->limit - cnt->usage >= bytes; + spin_unlock_irqrestore(&cnt->lock, flags); + return ret; +} + static inline bool res_counter_check_under_soft_limit(struct res_counter *cnt) { bool ret; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 126a302c481c..999835b6112b 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1901,11 +1901,12 @@ static void __perf_event_read(void *info) return; raw_spin_lock(&ctx->lock); - update_context_time(ctx); + if (ctx->is_active) + update_context_time(ctx); update_event_times(event); + if (event->state == PERF_EVENT_STATE_ACTIVE) + event->pmu->read(event); raw_spin_unlock(&ctx->lock); - - event->pmu->read(event); } static inline u64 perf_event_count(struct perf_event *event) @@ -1999,8 +2000,7 @@ static int alloc_callchain_buffers(void) * accessed from NMI. Use a temporary manual per cpu allocation * until that gets sorted out. */ - size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) * - num_possible_cpus(); + size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]); entries = kzalloc(size, GFP_KERNEL); if (!entries) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index c914ec747ca6..ad6267714c84 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -625,7 +625,7 @@ static void update_curr_rt(struct rq *rq) struct rt_rq *rt_rq = rt_rq_of_se(rt_se); u64 delta_exec; - if (!task_has_rt_policy(curr)) + if (curr->sched_class != &rt_sched_class) return; delta_exec = rq->clock_task - curr->se.exec_start; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d7ebdf4cea98..f37f974aa81b 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -27,7 +27,7 @@ #include <asm/irq_regs.h> #include <linux/perf_event.h> -int watchdog_enabled; +int watchdog_enabled = 1; int __read_mostly softlockup_thresh = 60; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif -static int no_watchdog; - - /* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: @@ -58,7 +55,7 @@ static int __init hardlockup_panic_setup(char *str) if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "0", 1)) - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -77,7 +74,7 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); @@ -85,7 +82,7 @@ __setup("nowatchdog", nowatchdog_setup); /* deprecated */ static int __init nosoftlockup_setup(char *str) { - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); @@ -432,9 +429,6 @@ static int watchdog_enable(int cpu) wake_up_process(p); } - /* if any cpu succeeds, watchdog is considered enabled for the system */ - watchdog_enabled = 1; - return 0; } @@ -462,12 +456,16 @@ static void watchdog_disable(int cpu) static void watchdog_enable_all_cpus(void) { int cpu; - int result = 0; + + watchdog_enabled = 0; for_each_online_cpu(cpu) - result += watchdog_enable(cpu); + if (!watchdog_enable(cpu)) + /* if any cpu succeeds, watchdog is considered + enabled for the system */ + watchdog_enabled = 1; - if (result) + if (!watchdog_enabled) printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); } @@ -476,9 +474,6 @@ static void watchdog_disable_all_cpus(void) { int cpu; - if (no_watchdog) - return; - for_each_online_cpu(cpu) watchdog_disable(cpu); @@ -498,10 +493,12 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write, { proc_dointvec(table, write, buffer, length, ppos); - if (watchdog_enabled) - watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); + if (write) { + if (watchdog_enabled) + watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + } return 0; } @@ -530,7 +527,8 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - err = watchdog_enable(hotcpu); + if (watchdog_enabled) + err = watchdog_enable(hotcpu); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: @@ -555,9 +553,6 @@ void __init lockup_detector_init(void) void *cpu = (void *)(long)smp_processor_id(); int err; - if (no_watchdog) - return; - err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); WARN_ON(notifier_to_errno(err)); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e187454d82f6..b6c1ce3c53b5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1162,7 +1162,12 @@ static void __split_huge_page_refcount(struct page *page) /* after clearing PageTail the gup refcount can be released */ smp_mb(); - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + /* + * retain hwpoison flag of the poisoned tail page: + * fix for the unsuitable process killed on Guest Machine(KVM) + * by the memory-failure. + */ + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; page_tail->flags |= (page->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3878cfe399dc..da53a252b259 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -612,8 +612,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]); - else + else { __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]); + nr_pages = -nr_pages; /* for event */ + } __this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages); @@ -1111,6 +1113,23 @@ static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) return false; } +/** + * mem_cgroup_check_margin - check if the memory cgroup allows charging + * @mem: memory cgroup to check + * @bytes: the number of bytes the caller intends to charge + * + * Returns a boolean value on whether @mem can be charged @bytes or + * whether this would exceed the limit. + */ +static bool mem_cgroup_check_margin(struct mem_cgroup *mem, unsigned long bytes) +{ + if (!res_counter_check_margin(&mem->res, bytes)) + return false; + if (do_swap_account && !res_counter_check_margin(&mem->memsw, bytes)) + return false; + return true; +} + static unsigned int get_swappiness(struct mem_cgroup *memcg) { struct cgroup *cgrp = memcg->css.cgroup; @@ -1837,23 +1856,34 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, flags |= MEM_CGROUP_RECLAIM_NOSWAP; } else mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); - - if (csize > PAGE_SIZE) /* change csize and retry */ + /* + * csize can be either a huge page (HPAGE_SIZE), a batch of + * regular pages (CHARGE_SIZE), or a single regular page + * (PAGE_SIZE). + * + * Never reclaim on behalf of optional batching, retry with a + * single page instead. + */ + if (csize == CHARGE_SIZE) return CHARGE_RETRY; if (!(gfp_mask & __GFP_WAIT)) return CHARGE_WOULDBLOCK; ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, - gfp_mask, flags); + gfp_mask, flags); + if (mem_cgroup_check_margin(mem_over_limit, csize)) + return CHARGE_RETRY; /* - * try_to_free_mem_cgroup_pages() might not give us a full - * picture of reclaim. Some pages are reclaimed and might be - * moved to swap cache or just unmapped from the cgroup. - * Check the limit again to see if the reclaim reduced the - * current usage of the cgroup before giving up + * Even though the limit is exceeded at this point, reclaim + * may have been able to free some pages. Retry the charge + * before killing the task. + * + * Only for regular pages, though: huge pages are rather + * unlikely to succeed so close to the limit, and we fall back + * to regular pages anyway in case of failure. */ - if (ret || mem_cgroup_check_under_limit(mem_over_limit)) + if (csize == PAGE_SIZE && ret) return CHARGE_RETRY; /* @@ -2323,13 +2353,19 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, enum charge_type ctype) { struct mem_cgroup *mem = NULL; + int page_size = PAGE_SIZE; struct page_cgroup *pc; + bool oom = true; int ret; - int page_size = PAGE_SIZE; if (PageTransHuge(page)) { page_size <<= compound_order(page); VM_BUG_ON(!PageTransHuge(page)); + /* + * Never OOM-kill a process for a huge page. The + * fault handler will fall back to regular pages. + */ + oom = false; } pc = lookup_page_cgroup(page); @@ -2338,7 +2374,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, return 0; prefetchw(pc); - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page_size); + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size); if (ret || !mem) return ret; @@ -5024,9 +5060,9 @@ struct cgroup_subsys mem_cgroup_subsys = { static int __init enable_swap_account(char *s) { /* consider enabled if no parameter or 1 is given */ - if (!s || !strcmp(s, "1")) + if (!(*s) || !strcmp(s, "=1")) really_do_swap_account = 1; - else if (!strcmp(s, "0")) + else if (!strcmp(s, "=0")) really_do_swap_account = 0; return 1; } @@ -5034,7 +5070,8 @@ __setup("swapaccount", enable_swap_account); static int __init disable_swap_account(char *s) { - enable_swap_account("0"); + printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n"); + enable_swap_account("=0"); return 1; } __setup("noswapaccount", disable_swap_account); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 548fbd70f026..0207c2f6f8bd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -233,8 +233,8 @@ void shake_page(struct page *p, int access) } /* - * Only all shrink_slab here (which would also - * shrink other caches) if access is not potentially fatal. + * Only call shrink_slab here (which would also shrink other caches) if + * access is not potentially fatal. */ if (access) { int nr; @@ -386,8 +386,6 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct task_struct *tsk; struct anon_vma *av; - if (!PageHuge(page) && unlikely(split_huge_page(page))) - return; read_lock(&tasklist_lock); av = page_lock_anon_vma(page); if (av == NULL) /* Not actually mapped anymore */ @@ -856,6 +854,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, int ret; int kill = 1; struct page *hpage = compound_head(p); + struct page *ppage; if (PageReserved(p) || PageSlab(p)) return SWAP_SUCCESS; @@ -897,6 +896,44 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, } /* + * ppage: poisoned page + * if p is regular page(4k page) + * ppage == real poisoned page; + * else p is hugetlb or THP, ppage == head page. + */ + ppage = hpage; + + if (PageTransHuge(hpage)) { + /* + * Verify that this isn't a hugetlbfs head page, the check for + * PageAnon is just for avoid tripping a split_huge_page + * internal debug check, as split_huge_page refuses to deal with + * anything that isn't an anon page. PageAnon can't go away fro + * under us because we hold a refcount on the hpage, without a + * refcount on the hpage. split_huge_page can't be safely called + * in the first place, having a refcount on the tail isn't + * enough * to be safe. + */ + if (!PageHuge(hpage) && PageAnon(hpage)) { + if (unlikely(split_huge_page(hpage))) { + /* + * FIXME: if splitting THP is failed, it is + * better to stop the following operation rather + * than causing panic by unmapping. System might + * survive if the page is freed later. + */ + printk(KERN_INFO + "MCE %#lx: failed to split THP\n", pfn); + + BUG_ON(!PageHWPoison(p)); + return SWAP_FAIL; + } + /* THP is split, so ppage should be the real poisoned page. */ + ppage = p; + } + } + + /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. @@ -905,12 +942,18 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(hpage, &tokill); + collect_procs(ppage, &tokill); + + if (hpage != ppage) + lock_page_nosync(ppage); - ret = try_to_unmap(hpage, ttu); + ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(ppage)); + + if (hpage != ppage) + unlock_page(ppage); /* * Now that the dirty bit has been propagated to the @@ -921,7 +964,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs_ao(&tokill, !!PageDirty(hpage), trapno, + kill_procs_ao(&tokill, !!PageDirty(ppage), trapno, ret != SWAP_SUCCESS, p, pfn); return ret; @@ -1022,19 +1065,22 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - if (!PageLRU(p) && !PageHuge(p)) - shake_page(p, 0); - if (!PageLRU(p) && !PageHuge(p)) { - /* - * shake_page could have turned it free. - */ - if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy, 2nd try", DELAYED); - return 0; + if (!PageHuge(p) && !PageTransCompound(p)) { + if (!PageLRU(p)) + shake_page(p, 0); + if (!PageLRU(p)) { + /* + * shake_page could have turned it free. + */ + if (is_free_buddy_page(p)) { + action_result(pfn, "free buddy, 2nd try", + DELAYED); + return 0; + } + action_result(pfn, "non LRU", IGNORED); + put_page(p); + return -EBUSY; } - action_result(pfn, "non LRU", IGNORED); - put_page(p); - return -EBUSY; } /* @@ -1064,7 +1110,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * For error on the tail page, we should set PG_hwpoison * on the head page to show that the hugepage is hwpoisoned */ - if (PageTail(p) && TestSetPageHWPoison(hpage)) { + if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { action_result(pfn, "hugepage already hardware poisoned", IGNORED); unlock_page(hpage); @@ -1295,7 +1341,10 @@ static int soft_offline_huge_page(struct page *page, int flags) ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, true); if (ret) { - putback_lru_pages(&pagelist); + struct page *page1, *page2; + list_for_each_entry_safe(page1, page2, &pagelist, lru) + put_page(page1); + pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) @@ -1419,6 +1468,7 @@ int soft_offline_page(struct page *page, int flags) ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, true); if (ret) { + putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) diff --git a/mm/migrate.c b/mm/migrate.c index 9f29a3b7aac2..766115253807 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -772,6 +772,7 @@ uncharge: unlock: unlock_page(page); +move_newpage: if (rc != -EAGAIN) { /* * A page that has been migrated has all references @@ -785,8 +786,6 @@ unlock: putback_lru_page(page); } -move_newpage: - /* * Move the new page to the LRU. If migration was not successful * then this will free the page. @@ -981,10 +980,6 @@ int migrate_huge_pages(struct list_head *from, } rc = 0; out: - - list_for_each_entry_safe(page, page2, from, lru) - put_page(page); - if (rc) return rc; |