diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index a6aca8740883..a563b74c7aef 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -374,13 +374,13 @@ Swap: 0 kB KernelPageSize: 4 kB MMUPageSize: 4 kB -The first of these lines shows the same information as is displayed for the -mapping in /proc/PID/maps. The remaining lines show the size of the mapping, -the amount of the mapping that is currently resident in RAM, the "proportional -set size” (divide each shared page by the number of processes sharing it), the -number of clean and dirty shared pages in the mapping, and the number of clean -and dirty private pages in the mapping. The "Referenced" indicates the amount -of memory currently marked as referenced or accessed. +The first of these lines shows the same information as is displayed for the +mapping in /proc/PID/maps. The remaining lines show the size of the mapping +(size), the amount of the mapping that is currently resident in RAM (RSS), the +process' proportional share of this mapping (PSS), the number of clean and +dirty shared pages in the mapping, and the number of clean and dirty private +pages in the mapping. The "Referenced" indicates the amount of memory +currently marked as referenced or accessed. This file is only present if the CONFIG_MMU kernel configuration option is enabled. diff --git a/Documentation/misc-devices/apds990x.txt b/Documentation/misc-devices/apds990x.txt new file mode 100644 index 000000000000..d5408cade32f --- /dev/null +++ b/Documentation/misc-devices/apds990x.txt @@ -0,0 +1,111 @@ +Kernel driver apds990x +====================== + +Supported chips: +Avago APDS990X + +Data sheet: +Not freely available + +Author: +Samu Onkalo + +Description +----------- + +APDS990x is a combined ambient light and proximity sensor. ALS and proximity +functionality are highly connected. ALS measurement path must be running +while the proximity functionality is enabled. + +ALS produces raw measurement values for two channels: Clear channel +(infrared + visible light) and IR only. However, threshold comparisons happen +using clear channel only. Lux value and the threshold level on the HW +might vary quite much depending the spectrum of the light source. + +Driver makes necessary conversions to both directions so that user handles +only lux values. Lux value is calculated using information from the both +channels. HW threshold level is calculated from the given lux value to match +with current type of the lightning. Sometimes inaccuracy of the estimations +lead to false interrupt, but that doesn't harm. + +ALS contains 4 different gain steps. Driver automatically +selects suitable gain step. After each measurement, reliability of the results +is estimated and new measurement is trigged if necessary. + +Platform data can provide tuned values to the conversion formulas if +values are known. Otherwise plain sensor default values are used. + +Proximity side is little bit simpler. There is no need for complex conversions. +It produces directly usable values. + +Driver controls chip operational state using pm_runtime framework. +Voltage regulators are controlled based on chip operational state. + +SYSFS +----- + + +chip_id + RO - shows detected chip type and version + +power_state + RW - enable / disable chip. Uses counting logic + 1 enables the chip + 0 disables the chip +lux0_input + RO - measured lux value + sysfs_notify called when threshold interrupt occurs + +lux0_sensor_range + RO - lux0_input max value. Actually never reaches since sensor tends + to saturate much before that. Real max value varies depending + on the light spectrum etc. + +lux0_rate + RW - measurement rate in Hz + +lux0_rate_avail + RO - supported measurement rates + +lux0_calibscale + RW - calibration value. Set to neutral value by default. + Output results are multiplied with calibscale / calibscale_default + value. + +lux0_calibscale_default + RO - neutral calibration value + +lux0_thresh_above_value + RW - HI level threshold value. All results above the value + trigs an interrupt. 65535 (i.e. sensor_range) disables the above + interrupt. + +lux0_thresh_below_value + RW - LO level threshold value. All results below the value + trigs an interrupt. 0 disables the below interrupt. + +prox0_raw + RO - measured proximity value + sysfs_notify called when threshold interrupt occurs + +prox0_sensor_range + RO - prox0_raw max value (1023) + +prox0_raw_en + RW - enable / disable proximity - uses counting logic + 1 enables the proximity + 0 disables the proximity + +prox0_reporting_mode + RW - trigger / periodic. In "trigger" mode the driver tells two possible + values: 0 or prox0_sensor_range value. 0 means no proximity, + 1023 means proximity. This causes minimal number of interrupts. + In "periodic" mode the driver reports all values above + prox0_thresh_above. This causes more interrupts, but it can give + _rough_ estimate about the distance. + +prox0_reporting_mode_avail + RO - accepted values to prox0_reporting_mode (trigger, periodic) + +prox0_thresh_above_value + RW - threshold level which trigs proximity events. diff --git a/Documentation/misc-devices/bh1770glc.txt b/Documentation/misc-devices/bh1770glc.txt new file mode 100644 index 000000000000..7d64c014dc70 --- /dev/null +++ b/Documentation/misc-devices/bh1770glc.txt @@ -0,0 +1,116 @@ +Kernel driver bh1770glc +======================= + +Supported chips: +ROHM BH1770GLC +OSRAM SFH7770 + +Data sheet: +Not freely available + +Author: +Samu Onkalo + +Description +----------- +BH1770GLC and SFH7770 are combined ambient light and proximity sensors. +ALS and proximity parts operates on their own, but they shares common I2C +interface and interrupt logic. In principle they can run on their own, +but ALS side results are used to estimate reliability of the proximity sensor. + +ALS produces 16 bit lux values. The chip contains interrupt logic to produce +low and high threshold interrupts. + +Proximity part contains IR-led driver up to 3 IR leds. The chip measures +amount of reflected IR light and produces proximity result. Resolution is +8 bit. Driver supports only one channel. Driver uses ALS results to estimate +reliability of the proximity results. Thus ALS is always running while +proximity detection is needed. + +Driver uses threshold interrupts to avoid need for polling the values. +Proximity low interrupt doesn't exists in the chip. This is simulated +by using a delayed work. As long as there is proximity threshold above +interrupts the delayed work is pushed forward. So, when proximity level goes +below the threshold value, there is no interrupt and the delayed work will +finally run. This is handled as no proximity indication. + +Chip state is controlled via runtime pm framework when enabled in config. + +Calibscale factor is used to hide differences between the chips. By default +value set to neutral state meaning factor of 1.00. To get proper values, +calibrated source of light is needed as a reference. Calibscale factor is set +so that measurement produces about the expected lux value. + +SYSFS +----- + +chip_id + RO - shows detected chip type and version + +power_state + RW - enable / disable chip. Uses counting logic + 1 enables the chip + 0 disables the chip + +lux0_input + RO - measured lux value + sysfs_notify called when threshold interrupt occurs + +lux0_sensor_range + RO - lux0_input max value + +lux0_rate + RW - measurement rate in Hz + +lux0_rate_avail + RO - supported measurement rates + +lux0_thresh_above_value + RW - HI level threshold value. All results above the value + trigs an interrupt. 65535 (i.e. sensor_range) disables the above + interrupt. + +lux0_thresh_below_value + RW - LO level threshold value. All results below the value + trigs an interrupt. 0 disables the below interrupt. + +lux0_calibscale + RW - calibration value. Set to neutral value by default. + Output results are multiplied with calibscale / calibscale_default + value. + +lux0_calibscale_default + RO - neutral calibration value + +prox0_raw + RO - measured proximity value + sysfs_notify called when threshold interrupt occurs + +prox0_sensor_range + RO - prox0_raw max value + +prox0_raw_en + RW - enable / disable proximity - uses counting logic + 1 enables the proximity + 0 disables the proximity + +prox0_thresh_above_count + RW - number of proximity interrupts needed before triggering the event + +prox0_rate_above + RW - Measurement rate (in Hz) when the level is above threshold + i.e. when proximity on has been reported. + +prox0_rate_below + RW - Measurement rate (in Hz) when the level is below threshold + i.e. when proximity off has been reported. + +prox0_rate_avail + RO - Supported proximity measurement rates in Hz + +prox0_thresh_above0_value + RW - threshold level which trigs proximity events. + Filtered by persistence filter (prox0_thresh_above_count) + +prox0_thresh_above1_value + RW - threshold level which trigs event immediately diff --git a/Documentation/timers/hpet_example.c b/Documentation/timers/hpet_example.c index 4bfafb7bc4c5..9a3e7012c190 100644 --- a/Documentation/timers/hpet_example.c +++ b/Documentation/timers/hpet_example.c @@ -97,6 +97,33 @@ hpet_open_close(int argc, const char **argv) void hpet_info(int argc, const char **argv) { + struct hpet_info info; + int fd; + + if (argc != 1) { + fprintf(stderr, "hpet_info: device-name\n"); + return; + } + + fd = open(argv[0], O_RDONLY); + if (fd < 0) { + fprintf(stderr, "hpet_info: open of %s failed\n", argv[0]); + return; + } + + if (ioctl(fd, HPET_INFO, &info) < 0) { + fprintf(stderr, "hpet_info: failed to get info\n"); + goto out; + } + + fprintf(stderr, "hpet_info: hi_irqfreq 0x%lx hi_flags 0x%lx ", + info.hi_ireqfreq, info.hi_flags); + fprintf(stderr, "hi_hpet %d hi_timer %d\n", + info.hi_hpet, info.hi_timer); + +out: + close(fd); + return; } void diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl index 1b55146d1c8d..b3e73ddb1567 100644 --- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl +++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl @@ -46,7 +46,7 @@ use constant HIGH_KSWAPD_LATENCY => 20; use constant HIGH_KSWAPD_REWAKEUP => 21; use constant HIGH_NR_SCANNED => 22; use constant HIGH_NR_TAKEN => 23; -use constant HIGH_NR_RECLAIM => 24; +use constant HIGH_NR_RECLAIMED => 24; use constant HIGH_NR_CONTIG_DIRTY => 25; my %perprocesspid; @@ -58,11 +58,13 @@ my $opt_read_procstat; my $total_wakeup_kswapd; my ($total_direct_reclaim, $total_direct_nr_scanned); my ($total_direct_latency, $total_kswapd_latency); +my ($total_direct_nr_reclaimed); my ($total_direct_writepage_file_sync, $total_direct_writepage_file_async); my ($total_direct_writepage_anon_sync, $total_direct_writepage_anon_async); my ($total_kswapd_nr_scanned, $total_kswapd_wake); my ($total_kswapd_writepage_file_sync, $total_kswapd_writepage_file_async); my ($total_kswapd_writepage_anon_sync, $total_kswapd_writepage_anon_async); +my ($total_kswapd_nr_reclaimed); # Catch sigint and exit on request my $sigint_report = 0; @@ -104,7 +106,7 @@ my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)'; my $regex_kswapd_sleep_default = 'nid=([0-9]*)'; my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*)'; my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_taken=([0-9]*) contig_taken=([0-9]*) contig_dirty=([0-9]*) contig_failed=([0-9]*)'; -my $regex_lru_shrink_inactive_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) priority=([0-9]*)'; +my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) zid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)'; my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)'; my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)'; @@ -203,8 +205,8 @@ $regex_lru_shrink_inactive = generate_traceevent_regex( "vmscan/mm_vmscan_lru_shrink_inactive", $regex_lru_shrink_inactive_default, "nid", "zid", - "lru", - "nr_scanned", "nr_reclaimed", "priority"); + "nr_scanned", "nr_reclaimed", "priority", + "flags"); $regex_lru_shrink_active = generate_traceevent_regex( "vmscan/mm_vmscan_lru_shrink_active", $regex_lru_shrink_active_default, @@ -375,6 +377,16 @@ EVENT_PROCESS: my $nr_contig_dirty = $7; $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned; $perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty; + } elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") { + $details = $5; + if ($details !~ /$regex_lru_shrink_inactive/o) { + print "WARNING: Failed to parse mm_vmscan_lru_shrink_inactive as expected\n"; + print " $details\n"; + print " $regex_lru_shrink_inactive/o\n"; + next; + } + my $nr_reclaimed = $4; + $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED} += $nr_reclaimed; } elsif ($tracepoint eq "mm_vmscan_writepage") { $details = $5; if ($details !~ /$regex_writepage/o) { @@ -464,8 +476,8 @@ sub dump_stats { # Print out process activity printf("\n"); - printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s\n", "Process", "Direct", "Wokeup", "Pages", "Pages", "Pages", "Time"); - printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s\n", "details", "Rclms", "Kswapd", "Scanned", "Sync-IO", "ASync-IO", "Stalled"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s\n", "Process", "Direct", "Wokeup", "Pages", "Pages", "Pages", "Pages", "Time"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s\n", "details", "Rclms", "Kswapd", "Scanned", "Rclmed", "Sync-IO", "ASync-IO", "Stalled"); foreach $process_pid (keys %stats) { if (!$stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}) { @@ -475,6 +487,7 @@ sub dump_stats { $total_direct_reclaim += $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}; $total_wakeup_kswapd += $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}; $total_direct_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED}; + $total_direct_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED}; $total_direct_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}; $total_direct_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}; $total_direct_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}; @@ -489,11 +502,12 @@ sub dump_stats { $index++; } - printf("%-" . $max_strlen . "s %8d %10d %8u %8u %8u %8.3f", + printf("%-" . $max_strlen . "s %8d %10d %8u %8u %8u %8u %8.3f", $process_pid, $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}, $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}, $stats{$process_pid}->{HIGH_NR_SCANNED}, + $stats{$process_pid}->{HIGH_NR_RECLAIMED}, $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}, $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}, $this_reclaim_delay / 1000); @@ -529,8 +543,8 @@ sub dump_stats { # Print out kswapd activity printf("\n"); - printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Kswapd", "Kswapd", "Order", "Pages", "Pages", "Pages"); - printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Instance", "Wakeups", "Re-wakeup", "Scanned", "Sync-IO", "ASync-IO"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Kswapd", "Kswapd", "Order", "Pages", "Pages", "Pages", "Pages"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Instance", "Wakeups", "Re-wakeup", "Scanned", "Rclmed", "Sync-IO", "ASync-IO"); foreach $process_pid (keys %stats) { if (!$stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}) { @@ -539,16 +553,18 @@ sub dump_stats { $total_kswapd_wake += $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}; $total_kswapd_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED}; + $total_kswapd_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED}; $total_kswapd_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}; $total_kswapd_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}; $total_kswapd_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}; $total_kswapd_writepage_anon_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}; - printf("%-" . $max_strlen . "s %8d %10d %8u %8i %8u", + printf("%-" . $max_strlen . "s %8d %10d %8u %8u %8i %8u", $process_pid, $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}, $stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP}, $stats{$process_pid}->{HIGH_NR_SCANNED}, + $stats{$process_pid}->{HIGH_NR_RECLAIMED}, $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}, $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}); @@ -579,6 +595,7 @@ sub dump_stats { print "\nSummary\n"; print "Direct reclaims: $total_direct_reclaim\n"; print "Direct reclaim pages scanned: $total_direct_nr_scanned\n"; + print "Direct reclaim pages reclaimed: $total_direct_nr_reclaimed\n"; print "Direct reclaim write file sync I/O: $total_direct_writepage_file_sync\n"; print "Direct reclaim write anon sync I/O: $total_direct_writepage_anon_sync\n"; print "Direct reclaim write file async I/O: $total_direct_writepage_file_async\n"; @@ -588,6 +605,7 @@ sub dump_stats { print "\n"; print "Kswapd wakeups: $total_kswapd_wake\n"; print "Kswapd pages scanned: $total_kswapd_nr_scanned\n"; + print "Kswapd pages reclaimed: $total_kswapd_nr_reclaimed\n"; print "Kswapd reclaim write file sync I/O: $total_kswapd_writepage_file_sync\n"; print "Kswapd reclaim write anon sync I/O: $total_kswapd_writepage_anon_sync\n"; print "Kswapd reclaim write file async I/O: $total_kswapd_writepage_file_async\n"; @@ -612,6 +630,7 @@ sub aggregate_perprocesspid() { $perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD} += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}; $perprocess{$process}->{HIGH_KSWAPD_REWAKEUP} += $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP}; $perprocess{$process}->{HIGH_NR_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_SCANNED}; + $perprocess{$process}->{HIGH_NR_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED}; $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}; $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}; $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}; diff --git a/Documentation/vm/highmem.txt b/Documentation/vm/highmem.txt new file mode 100644 index 000000000000..4324d24ffacd --- /dev/null +++ b/Documentation/vm/highmem.txt @@ -0,0 +1,162 @@ + + ==================== + HIGH MEMORY HANDLING + ==================== + +By: Peter Zijlstra + +Contents: + + (*) What is high memory? + + (*) Temporary virtual mappings. + + (*) Using kmap_atomic. + + (*) Cost of temporary mappings. + + (*) i386 PAE. + + +==================== +WHAT IS HIGH MEMORY? +==================== + +High memory (highmem) is used when the size of physical memory approaches or +exceeds the maximum size of virtual memory. At that point it becomes +impossible for the kernel to keep all of the available physical memory mapped +at all times. This means the kernel needs to start using temporary mappings of +the pieces of physical memory that it wants to access. + +The part of (physical) memory not covered by a permanent mapping is what we +refer to as 'highmem'. There are various architecture dependent constraints on +where exactly that border lies. + +In the i386 arch, for example, we choose to map the kernel into every process's +VM space so that we don't have to pay the full TLB invalidation costs for +kernel entry/exit. This means the available virtual memory space (4GiB on +i386) has to be divided between user and kernel space. + +The traditional split for architectures using this approach is 3:1, 3GiB for +userspace and the top 1GiB for kernel space: + + +--------+ 0xffffffff + | Kernel | + +--------+ 0xc0000000 + | | + | User | + | | + +--------+ 0x00000000 + +This means that the kernel can at most map 1GiB of physical memory at any one +time, but because we need virtual address space for other things - including +temporary maps to access the rest of the physical memory - the actual direct +map will typically be less (usually around ~896MiB). + +Other architectures that have mm context tagged TLBs can have separate kernel +and user maps. Some hardware (like some ARMs), however, have limited virtual +space when they use mm context tags. + + +========================== +TEMPORARY VIRTUAL MAPPINGS +========================== + +The kernel contains several ways of creating temporary mappings: + + (*) vmap(). This can be used to make a long duration mapping of multiple + physical pages into a contiguous virtual space. It needs global + synchronization to unmap. + + (*) kmap(). This permits a short duration mapping of a single page. It needs + global synchronization, but is amortized somewhat. It is also prone to + deadlocks when using in a nested fashion, and so it is not recommended for + new code. + + (*) kmap_atomic(). This permits a very short duration mapping of a single + page. Since the mapping is restricted to the CPU that issued it, it + performs well, but the issuing task is therefore required to stay on that + CPU until it has finished, lest some other task displace its mappings. + + kmap_atomic() may also be used by interrupt contexts, since it is does not + sleep and the caller may not sleep until after kunmap_atomic() is called. + + It may be assumed that k[un]map_atomic() won't fail. + + +================= +USING KMAP_ATOMIC +================= + +When and where to use kmap_atomic() is straightforward. It is used when code +wants to access the contents of a page that might be allocated from high memory +(see __GFP_HIGHMEM), for example a page in the pagecache. The API has two +functions, and they can be used in a manner similar to the following: + + /* Find the page of interest. */ + struct page *page = find_get_page(mapping, offset); + + /* Gain access to the contents of that page. */ + void *vaddr = kmap_atomic(page); + + /* Do something to the contents of that page. */ + memset(vaddr, 0, PAGE_SIZE); + + /* Unmap that page. */ + kunmap_atomic(vaddr); + +Note that the kunmap_atomic() call takes the result of the kmap_atomic() call +not the argument. + +If you need to map two pages because you want to copy from one page to +another you need to keep the kmap_atomic calls strictly nested, like: + + vaddr1 = kmap_atomic(page1); + vaddr2 = kmap_atomic(page2); + + memcpy(vaddr1, vaddr2, PAGE_SIZE); + + kunmap_atomic(vaddr2); + kunmap_atomic(vaddr1); + + +========================== +COST OF TEMPORARY MAPPINGS +========================== + +The cost of creating temporary mappings can be quite high. The arch has to +manipulate the kernel's page tables, the data TLB and/or the MMU's registers. + +If CONFIG_HIGHMEM is not set, then the kernel will try and create a mapping +simply with a bit of arithmetic that will convert the page struct address into +a pointer to the page contents rather than juggling mappings about. In such a +case, the unmap operation may be a null operation. + +If CONFIG_MMU is not set, then there can be no temporary mappings and no +highmem. In such a case, the arithmetic approach will also be used. + + +======== +i386 PAE +======== + +The i386 arch, under some circumstances, will permit you to stick up to 64GiB +of RAM into your 32-bit machine. This has a number of consequences: + + (*) Linux needs a page-frame structure for each page in the system and the + pageframes need to live in the permanent mapping, which means: + + (*) you can have 896M/sizeof(struct page) page-frames at most; with struct + page being 32-bytes that would end up being something in the order of 112G + worth of pages; the kernel, however, needs to store more than just + page-frames in that memory... + + (*) PAE makes your page tables larger - which slows the system down as more + data has to be accessed to traverse in TLB fills and the like. One + advantage is that PAE has more PTE bits and can provide advanced features + like NX and PAT. + +The general recommendation is that you don't use more than 8GiB on a 32-bit +machine - although more might work for you and your workload, you're pretty +much on your own - don't expect kernel developers to really care much if things +come apart. diff --git a/MAINTAINERS b/MAINTAINERS index 146b8a068a4e..014b648f99ed 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -657,7 +657,7 @@ ARM/FARADAY FA526 PORT M: Hans Ulli Kroll L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git://git.berlios.de/gemini-board +T: git git://git.berlios.de/gemini-board F: arch/arm/mm/*-fa* ARM/FOOTBRIDGE ARCHITECTURE @@ -672,7 +672,7 @@ ARM/FREESCALE IMX / MXC ARM ARCHITECTURE M: Sascha Hauer L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git://git.pengutronix.de/git/imx/linux-2.6.git +T: git git://git.pengutronix.de/git/imx/linux-2.6.git F: arch/arm/mach-mx*/ F: arch/arm/plat-mxc/ @@ -710,8 +710,7 @@ ARM/INCOME PXA270 SUPPORT M: Marek Vasut L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -F: arch/arm/mach-pxa/income.c -F: arch/arm/mach-pxa/include/mach-pxa/income.h +F: arch/arm/mach-pxa/colibri-pxa270-income.c ARM/INTEL IOP32X ARM ARCHITECTURE M: Lennert Buytenhek @@ -758,13 +757,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-ixp4xx/ -ARM/INTEL RESEARCH IMOTE 2 MACHINE SUPPORT -M: Jonathan Cameron -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: arch/arm/mach-pxa/imote2.c - -ARM/INTEL RESEARCH STARGATE 2 MACHINE SUPPORT +ARM/INTEL RESEARCH IMOTE/STARGATE 2 MACHINE SUPPORT M: Jonathan Cameron L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -929,40 +922,20 @@ W: http://www.fluff.org/ben/linux/ S: Maintained F: arch/arm/mach-s3c2410/ -ARM/S3C2440 ARM ARCHITECTURE +ARM/S3C244x ARM ARCHITECTURE M: Ben Dooks L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.fluff.org/ben/linux/ S: Maintained F: arch/arm/mach-s3c2440/ - -ARM/S3C2442 ARM ARCHITECTURE -M: Ben Dooks -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.fluff.org/ben/linux/ -S: Maintained -F: arch/arm/mach-s3c2442/ - -ARM/S3C2443 ARM ARCHITECTURE -M: Ben Dooks -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.fluff.org/ben/linux/ -S: Maintained F: arch/arm/mach-s3c2443/ -ARM/S3C6400 ARM ARCHITECTURE +ARM/S3C64xx ARM ARCHITECTURE M: Ben Dooks L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.fluff.org/ben/linux/ S: Maintained -F: arch/arm/mach-s3c6400/ - -ARM/S3C6410 ARM ARCHITECTURE -M: Ben Dooks -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.fluff.org/ben/linux/ -S: Maintained -F: arch/arm/mach-s3c6410/ +F: arch/arm/mach-s3c64xx/ ARM/S5P ARM ARCHITECTURES M: Kukjin Kim @@ -3867,7 +3840,7 @@ F: drivers/net/wireless/mwl8k.c MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER M: Nicolas Pitre S: Odd Fixes -F: drivers/mmc/host/mvsdio.* +F: drivers/mmc/host/mvsdio.* MARVELL YUKON / SYSKONNECT DRIVER M: Mirko Lindner @@ -4958,7 +4931,7 @@ RCUTORTURE MODULE M: Josh Triplett M: "Paul E. McKenney" S: Supported -T: git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git F: Documentation/RCU/torture.txt F: kernel/rcutorture.c @@ -4983,7 +4956,7 @@ M: Dipankar Sarma M: "Paul E. McKenney" W: http://www.rdrop.com/users/paulmck/rclock/ S: Supported -T: git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git F: Documentation/RCU/ F: include/linux/rcu* F: include/linux/srcu* @@ -6141,13 +6114,6 @@ L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/serial/option.c -USB OV511 DRIVER -M: Mark McClelland -L: linux-usb@vger.kernel.org -W: http://alpha.dyndns.org/ov511/ -S: Maintained -F: drivers/media/video/ov511.* - USB PEGASUS DRIVER M: Petko Manolov L: linux-usb@vger.kernel.org @@ -6308,16 +6274,6 @@ S: Supported F: drivers/usb/host/xhci* F: drivers/usb/host/pci-quirks* -USB ZC0301 DRIVER -M: Luca Risolia -L: linux-usb@vger.kernel.org -L: linux-media@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git -W: http://www.linux-projects.org -S: Maintained -F: Documentation/video4linux/zc0301.txt -F: drivers/media/video/zc0301/ - USB ZD1201 DRIVER L: linux-wireless@vger.kernel.org W: http://linux-lc100020.sourceforge.net diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index d04ccd73af45..28f93a6c0fde 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -55,6 +55,9 @@ config ZONE_DMA bool default y +config ARCH_DMA_ADDR_T_64BIT + def_bool y + config NEED_DMA_MAP_STATE def_bool y diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h index 21ac53383b37..9f67a056b461 100644 --- a/arch/alpha/include/asm/core_mcpcia.h +++ b/arch/alpha/include/asm/core_mcpcia.h @@ -247,7 +247,7 @@ struct el_MCPCIA_uncorrected_frame_mcheck { #define vip volatile int __force * #define vuip volatile unsigned int __force * -#ifdef MCPCIA_ONE_HAE_WINDOW +#ifndef MCPCIA_ONE_HAE_WINDOW #define MCPCIA_FROB_MMIO \ if (__mcpcia_is_mmio(hose)) { \ set_hae(hose & 0xffffffff); \ diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h index 471c07292e0b..91b46801b290 100644 --- a/arch/alpha/include/asm/core_t2.h +++ b/arch/alpha/include/asm/core_t2.h @@ -1,6 +1,9 @@ #ifndef __ALPHA_T2__H__ #define __ALPHA_T2__H__ +/* Fit everything into one 128MB HAE window. */ +#define T2_ONE_HAE_WINDOW 1 + #include #include #include @@ -19,7 +22,7 @@ * */ -#define T2_MEM_R1_MASK 0x07ffffff /* Mem sparse region 1 mask is 26 bits */ +#define T2_MEM_R1_MASK 0x07ffffff /* Mem sparse region 1 mask is 27 bits */ /* GAMMA-SABLE is a SABLE with EV5-based CPUs */ /* All LYNX machines, EV4 or EV5, use the GAMMA bias also */ @@ -85,7 +88,9 @@ #define T2_DIR (IDENT_ADDR + GAMMA_BIAS + 0x38e0004a0UL) #define T2_ICE (IDENT_ADDR + GAMMA_BIAS + 0x38e0004c0UL) +#ifndef T2_ONE_HAE_WINDOW #define T2_HAE_ADDRESS T2_HAE_1 +#endif /* T2 CSRs are in the non-cachable primary IO space from 3.8000.0000 to 3.8fff.ffff @@ -429,13 +434,15 @@ extern inline void t2_outl(u32 b, unsigned long addr) * */ +#ifdef T2_ONE_HAE_WINDOW +#define t2_set_hae +#else #define t2_set_hae { \ - msb = addr >> 27; \ + unsigned long msb = addr >> 27; \ addr &= T2_MEM_R1_MASK; \ set_hae(msb); \ } - -extern raw_spinlock_t t2_hae_lock; +#endif /* * NOTE: take T2_DENSE_MEM off in each readX/writeX routine, since @@ -446,28 +453,22 @@ extern raw_spinlock_t t2_hae_lock; __EXTERN_INLINE u8 t2_readb(const volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long result, msb; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long result; t2_set_hae; result = *(vip) ((addr << 5) + T2_SPARSE_MEM + 0x00); - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); return __kernel_extbl(result, addr & 3); } __EXTERN_INLINE u16 t2_readw(const volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long result, msb; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long result; t2_set_hae; result = *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x08); - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); return __kernel_extwl(result, addr & 3); } @@ -478,59 +479,47 @@ __EXTERN_INLINE u16 t2_readw(const volatile void __iomem *xaddr) __EXTERN_INLINE u32 t2_readl(const volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long result, msb; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long result; t2_set_hae; result = *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x18); - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); return result & 0xffffffffUL; } __EXTERN_INLINE u64 t2_readq(const volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long r0, r1, work, msb; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long r0, r1, work; t2_set_hae; work = (addr << 5) + T2_SPARSE_MEM + 0x18; r0 = *(vuip)(work); r1 = *(vuip)(work + (4 << 5)); - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); return r1 << 32 | r0; } __EXTERN_INLINE void t2_writeb(u8 b, volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long msb, w; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long w; t2_set_hae; w = __kernel_insbl(b, addr & 3); *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x00) = w; - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); } __EXTERN_INLINE void t2_writew(u16 b, volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long msb, w; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long w; t2_set_hae; w = __kernel_inswl(b, addr & 3); *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x08) = w; - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); } /* @@ -540,29 +529,22 @@ __EXTERN_INLINE void t2_writew(u16 b, volatile void __iomem *xaddr) __EXTERN_INLINE void t2_writel(u32 b, volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long msb; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); t2_set_hae; *(vuip) ((addr << 5) + T2_SPARSE_MEM + 0x18) = b; - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); } __EXTERN_INLINE void t2_writeq(u64 b, volatile void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr - T2_DENSE_MEM; - unsigned long msb, work; - unsigned long flags; - raw_spin_lock_irqsave(&t2_hae_lock, flags); + unsigned long work; t2_set_hae; work = (addr << 5) + T2_SPARSE_MEM + 0x18; *(vuip)work = b; *(vuip)(work + (4 << 5)) = b >> 32; - raw_spin_unlock_irqrestore(&t2_hae_lock, flags); } __EXTERN_INLINE void __iomem *t2_ioportmap(unsigned long addr) diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 71a243294142..de98a732683d 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -318,9 +318,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address) } #define pte_offset_map(dir,addr) pte_offset_kernel((dir),(addr)) -#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir),(addr)) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) extern pgd_t swapper_pg_dir[1024]; diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c index e6d90568b65d..2f770e994289 100644 --- a/arch/alpha/kernel/core_t2.c +++ b/arch/alpha/kernel/core_t2.c @@ -74,8 +74,6 @@ # define DBG(args) #endif -DEFINE_RAW_SPINLOCK(t2_hae_lock); - static volatile unsigned int t2_mcheck_any_expected; static volatile unsigned int t2_mcheck_last_taken; @@ -406,6 +404,7 @@ void __init t2_init_arch(void) { struct pci_controller *hose; + struct resource *hae_mem; unsigned long temp; unsigned int i; @@ -433,7 +432,13 @@ t2_init_arch(void) */ pci_isa_hose = hose = alloc_pci_controller(); hose->io_space = &ioport_resource; - hose->mem_space = &iomem_resource; + hae_mem = alloc_resource(); + hae_mem->start = 0; + hae_mem->end = T2_MEM_R1_MASK; + hae_mem->name = pci_hae0_name; + if (request_resource(&iomem_resource, hae_mem) < 0) + printk(KERN_ERR "Failed to request HAE_MEM\n"); + hose->mem_space = hae_mem; hose->index = 0; hose->sparse_mem_base = T2_SPARSE_MEM - IDENT_ADDR; diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h index 512685f78097..7fa62488bd16 100644 --- a/arch/alpha/kernel/machvec_impl.h +++ b/arch/alpha/kernel/machvec_impl.h @@ -25,6 +25,9 @@ #ifdef MCPCIA_ONE_HAE_WINDOW #define MCPCIA_HAE_ADDRESS (&alpha_mv.hae_cache) #endif +#ifdef T2_ONE_HAE_WINDOW +#define T2_HAE_ADDRESS (&alpha_mv.hae_cache) +#endif /* Only a few systems don't define IACK_SC, handling all interrupts through the SRM console. But splitting out that one case from IO() below diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 5aff58126602..1fc684e70ab6 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -35,9 +35,9 @@ extern void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte); #ifdef CONFIG_HIGHMEM extern void *kmap(struct page *page); extern void kunmap(struct page *page); -extern void *kmap_atomic(struct page *page, enum km_type type); -extern void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); -extern void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); +extern void *__kmap_atomic(struct page *page); +extern void __kunmap_atomic(void *kvaddr); +extern void *kmap_atomic_pfn(unsigned long pfn); extern struct page *kmap_atomic_to_page(const void *ptr); #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index a9672e8406a3..b155414192da 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -263,17 +263,15 @@ extern struct page *empty_zero_page; #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) #define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + __pte_index(addr)) -#define pte_offset_map(dir,addr) (__pte_map(dir, KM_PTE0) + __pte_index(addr)) -#define pte_offset_map_nested(dir,addr) (__pte_map(dir, KM_PTE1) + __pte_index(addr)) -#define pte_unmap(pte) __pte_unmap(pte, KM_PTE0) -#define pte_unmap_nested(pte) __pte_unmap(pte, KM_PTE1) +#define pte_offset_map(dir,addr) (__pte_map(dir) + __pte_index(addr)) +#define pte_unmap(pte) __pte_unmap(pte) #ifndef CONFIG_HIGHPTE -#define __pte_map(dir,km) pmd_page_vaddr(*(dir)) -#define __pte_unmap(pte,km) do { } while (0) +#define __pte_map(dir) pmd_page_vaddr(*(dir)) +#define __pte_unmap(pte) do { } while (0) #else -#define __pte_map(dir,km) ((pte_t *)kmap_atomic(pmd_page(*(dir)), km) + PTRS_PER_PTE) -#define __pte_unmap(pte,km) kunmap_atomic((pte - PTRS_PER_PTE), km) +#define __pte_map(dir) ((pte_t *)kmap_atomic(pmd_page(*(dir))) + PTRS_PER_PTE) +#define __pte_unmap(pte) kunmap_atomic((pte - PTRS_PER_PTE)) #endif #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext) diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index 4566bd1c8660..ef06c66a6f16 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -358,8 +358,7 @@ static int calc_clk_div(struct clk *clk, unsigned long rate, int i, found = 0, __div = 0, __pdiv = 0; /* Don't exceed the maximum rate */ - max_rate = max(max(clk_pll1.rate / 4, clk_pll2.rate / 4), - clk_xtali.rate / 4); + max_rate = max3(clk_pll1.rate / 4, clk_pll2.rate / 4, clk_xtali.rate / 4); rate = min(rate, max_rate); /* diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 8440d952ba6d..c493d7244d3d 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -89,13 +89,13 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, * open-code the spin-locking. */ ptl = pte_lockptr(vma->vm_mm, pmd); - pte = pte_offset_map_nested(pmd, address); + pte = pte_offset_map(pmd, address); spin_lock(ptl); ret = do_adjust_pte(vma, address, pfn, pte); spin_unlock(ptl); - pte_unmap_nested(pte); + pte_unmap(pte); return ret; } diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 1fbdb55bfd1b..c00f119babbf 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -36,18 +36,17 @@ void kunmap(struct page *page) } EXPORT_SYMBOL(kunmap); -void *kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page) { unsigned int idx; unsigned long vaddr; void *kmap; + int type; pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic(type); - #ifdef CONFIG_DEBUG_HIGHMEM /* * There is no cache coherency issue when non VIVT, so force the @@ -61,6 +60,8 @@ void *kmap_atomic(struct page *page, enum km_type type) if (kmap) return kmap; + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM @@ -80,14 +81,17 @@ void *kmap_atomic(struct page *page, enum km_type type) return (void *)vaddr; } -EXPORT_SYMBOL(kmap_atomic); +EXPORT_SYMBOL(__kmap_atomic); -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - unsigned int idx = type + KM_TYPE_NR * smp_processor_id(); + int idx, type; if (kvaddr >= (void *)FIXADDR_START) { + type = kmap_atomic_idx_pop(); + idx = type + KM_TYPE_NR * smp_processor_id(); + if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM @@ -103,15 +107,16 @@ void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) } pagefault_enable(); } -EXPORT_SYMBOL(kunmap_atomic_notypecheck); +EXPORT_SYMBOL(__kunmap_atomic); -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *kmap_atomic_pfn(unsigned long pfn) { - unsigned int idx; unsigned long vaddr; + int idx, type; pagefault_disable(); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index be5f58e153bf..69bbfc6645a6 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -57,9 +57,9 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) goto no_pte; init_pmd = pmd_offset(init_pgd, 0); - init_pte = pte_offset_map_nested(init_pmd, 0); + init_pte = pte_offset_map(init_pmd, 0); set_pte_ext(new_pte, *init_pte, 0); - pte_unmap_nested(init_pte); + pte_unmap(init_pte); pte_unmap(new_pte); } diff --git a/arch/avr32/include/asm/pgtable.h b/arch/avr32/include/asm/pgtable.h index a9ae30c41e74..6fbfea61f7bb 100644 --- a/arch/avr32/include/asm/pgtable.h +++ b/arch/avr32/include/asm/pgtable.h @@ -319,9 +319,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define pte_offset_kernel(dir, address) \ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address)) #define pte_offset_map(dir, address) pte_offset_kernel(dir, address) -#define pte_offset_map_nested(dir, address) pte_offset_kernel(dir, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) struct vm_area_struct; extern void update_mmu_cache(struct vm_area_struct * vma, diff --git a/arch/blackfin/include/asm/entry.h b/arch/blackfin/include/asm/entry.h index a6886f6e4819..4104d5783e2c 100644 --- a/arch/blackfin/include/asm/entry.h +++ b/arch/blackfin/include/asm/entry.h @@ -15,14 +15,6 @@ #define LFLUSH_I_AND_D 0x00000808 #define LSIGTRAP 5 -/* process bits for task_struct.flags */ -#define PF_TRACESYS_OFF 3 -#define PF_TRACESYS_BIT 5 -#define PF_PTRACED_OFF 3 -#define PF_PTRACED_BIT 4 -#define PF_DTRACE_OFF 1 -#define PF_DTRACE_BIT 5 - /* * NOTE! The single-stepping code assumes that all interrupt handlers * start by saving SYSCFG on the stack with their first instruction. diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h index f63d6fccbc6c..9eaae217b21b 100644 --- a/arch/cris/include/asm/pgtable.h +++ b/arch/cris/include/asm/pgtable.h @@ -248,10 +248,8 @@ static inline pgd_t * pgd_offset(const struct mm_struct *mm, unsigned long addre ((pte_t *) pmd_page_vaddr(*(dir)) + __pte_offset(address)) #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) -#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #define pte_pfn(x) ((unsigned long)(__va((x).pte)) >> PAGE_SHIFT) #define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) diff --git a/arch/frv/include/asm/highmem.h b/arch/frv/include/asm/highmem.h index cb4c317eaecc..a8d6565d415d 100644 --- a/arch/frv/include/asm/highmem.h +++ b/arch/frv/include/asm/highmem.h @@ -112,12 +112,11 @@ extern struct page *kmap_atomic_to_page(void *ptr); (void *) damlr; \ }) -static inline void *kmap_atomic(struct page *page, enum km_type type) +static inline void *kmap_atomic_primary(struct page *page, enum km_type type) { unsigned long paddr; pagefault_disable(); - debug_kmap_atomic(type); paddr = page_to_phys(page); switch (type) { @@ -125,14 +124,6 @@ static inline void *kmap_atomic(struct page *page, enum km_type type) case 1: return __kmap_atomic_primary(1, paddr, 3); case 2: return __kmap_atomic_primary(2, paddr, 4); case 3: return __kmap_atomic_primary(3, paddr, 5); - case 4: return __kmap_atomic_primary(4, paddr, 6); - case 5: return __kmap_atomic_primary(5, paddr, 7); - case 6: return __kmap_atomic_primary(6, paddr, 8); - case 7: return __kmap_atomic_primary(7, paddr, 9); - case 8: return __kmap_atomic_primary(8, paddr, 10); - - case 9 ... 9 + NR_TLB_LINES - 1: - return __kmap_atomic_secondary(type - 9, paddr); default: BUG(); @@ -152,22 +143,13 @@ do { \ asm volatile("tlbpr %0,gr0,#4,#1" : : "r"(vaddr) : "memory"); \ } while(0) -static inline void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +static inline void kunmap_atomic_primary(void *kvaddr, enum km_type type) { switch (type) { case 0: __kunmap_atomic_primary(0, 2); break; case 1: __kunmap_atomic_primary(1, 3); break; case 2: __kunmap_atomic_primary(2, 4); break; case 3: __kunmap_atomic_primary(3, 5); break; - case 4: __kunmap_atomic_primary(4, 6); break; - case 5: __kunmap_atomic_primary(5, 7); break; - case 6: __kunmap_atomic_primary(6, 8); break; - case 7: __kunmap_atomic_primary(7, 9); break; - case 8: __kunmap_atomic_primary(8, 10); break; - - case 9 ... 9 + NR_TLB_LINES - 1: - __kunmap_atomic_secondary(type - 9, kvaddr); - break; default: BUG(); @@ -175,6 +157,9 @@ static inline void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) pagefault_enable(); } +void *__kmap_atomic(struct page *page); +void __kunmap_atomic(void *kvaddr); + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h index c18b0d32e636..6bc241e4b4f8 100644 --- a/arch/frv/include/asm/pgtable.h +++ b/arch/frv/include/asm/pgtable.h @@ -451,17 +451,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #if defined(CONFIG_HIGHPTE) #define pte_offset_map(dir, address) \ - ((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address)) -#define pte_offset_map_nested(dir, address) \ - ((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE1) + pte_index(address)) -#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) -#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1) + ((pte_t *)kmap_atomic(pmd_page(*(dir))) + pte_index(address)) +#define pte_unmap(pte) kunmap_atomic(pte) #else #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address)) -#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address)) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #endif /* diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c index 85d110b71cf7..41098a3803a2 100644 --- a/arch/frv/mb93090-mb00/pci-dma.c +++ b/arch/frv/mb93090-mb00/pci-dma.c @@ -61,14 +61,14 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, dampr2 = __get_DAMPR(2); for (i = 0; i < nents; i++) { - vaddr = kmap_atomic(sg_page(&sg[i]), __KM_CACHE); + vaddr = kmap_atomic_primary(sg_page(&sg[i]), __KM_CACHE); frv_dcache_writeback((unsigned long) vaddr, (unsigned long) vaddr + PAGE_SIZE); } - kunmap_atomic(vaddr, __KM_CACHE); + kunmap_atomic_primary(vaddr, __KM_CACHE); if (dampr2) { __set_DAMPR(2, dampr2); __set_IAMPR(2, dampr2); diff --git a/arch/frv/mm/cache-page.c b/arch/frv/mm/cache-page.c index 0261cbe153b5..b24ade27a0f0 100644 --- a/arch/frv/mm/cache-page.c +++ b/arch/frv/mm/cache-page.c @@ -26,11 +26,11 @@ void flush_dcache_page(struct page *page) dampr2 = __get_DAMPR(2); - vaddr = kmap_atomic(page, __KM_CACHE); + vaddr = kmap_atomic_primary(page, __KM_CACHE); frv_dcache_writeback((unsigned long) vaddr, (unsigned long) vaddr + PAGE_SIZE); - kunmap_atomic(vaddr, __KM_CACHE); + kunmap_atomic_primary(vaddr, __KM_CACHE); if (dampr2) { __set_DAMPR(2, dampr2); @@ -54,12 +54,12 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, dampr2 = __get_DAMPR(2); - vaddr = kmap_atomic(page, __KM_CACHE); + vaddr = kmap_atomic_primary(page, __KM_CACHE); start = (start & ~PAGE_MASK) | (unsigned long) vaddr; frv_cache_wback_inv(start, start + len); - kunmap_atomic(vaddr, __KM_CACHE); + kunmap_atomic_primary(vaddr, __KM_CACHE); if (dampr2) { __set_DAMPR(2, dampr2); diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c index eadd07658075..61088dcc1594 100644 --- a/arch/frv/mm/highmem.c +++ b/arch/frv/mm/highmem.c @@ -36,3 +36,53 @@ struct page *kmap_atomic_to_page(void *ptr) { return virt_to_page(ptr); } + +void *__kmap_atomic(struct page *page) +{ + unsigned long paddr; + int type; + + pagefault_disable(); + type = kmap_atomic_idx_push(); + paddr = page_to_phys(page); + + switch (type) { + /* + * The first 4 primary maps are reserved for architecture code + */ + case 0: return __kmap_atomic_primary(4, paddr, 6); + case 1: return __kmap_atomic_primary(5, paddr, 7); + case 2: return __kmap_atomic_primary(6, paddr, 8); + case 3: return __kmap_atomic_primary(7, paddr, 9); + case 4: return __kmap_atomic_primary(8, paddr, 10); + + case 5 ... 5 + NR_TLB_LINES - 1: + return __kmap_atomic_secondary(type - 5, paddr); + + default: + BUG(); + return NULL; + } +} +EXPORT_SYMBOL(__kmap_atomic); + +void __kunmap_atomic(void *kvaddr) +{ + int type = kmap_atomic_idx_pop(); + switch (type) { + case 0: __kunmap_atomic_primary(4, 6); break; + case 1: __kunmap_atomic_primary(5, 7); break; + case 2: __kunmap_atomic_primary(6, 8); break; + case 3: __kunmap_atomic_primary(7, 9); break; + case 4: __kunmap_atomic_primary(8, 10); break; + + case 5 ... 5 + NR_TLB_LINES - 1: + __kunmap_atomic_secondary(type - 5, kvaddr); + break; + + default: + BUG(); + } + pagefault_enable(); +} +EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index c3286f42e501..1a97af31ef17 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -406,9 +406,7 @@ pgd_offset (const struct mm_struct *mm, unsigned long address) #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) #define pte_offset_kernel(dir,addr) ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) #define pte_offset_map(dir,addr) pte_offset_kernel(dir, addr) -#define pte_offset_map_nested(dir,addr) pte_offset_map(dir, addr) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) /* atomic versions of the some PTE manipulations: */ diff --git a/arch/m32r/include/asm/pgtable.h b/arch/m32r/include/asm/pgtable.h index e6359c566b50..8a28cfea2729 100644 --- a/arch/m32r/include/asm/pgtable.h +++ b/arch/m32r/include/asm/pgtable.h @@ -332,9 +332,7 @@ static inline void pmd_set(pmd_t * pmdp, pte_t * ptep) ((pte_t *)pmd_page_vaddr(*(dir)) + pte_index(address)) #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address)) -#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) /* Encode and de-code a swap entry */ #define __swp_type(x) (((x).val >> 2) & 0x1f) diff --git a/arch/m68k/include/asm/entry_mm.h b/arch/m68k/include/asm/entry_mm.h index e41fea399bfe..73b8c8fbed9c 100644 --- a/arch/m68k/include/asm/entry_mm.h +++ b/arch/m68k/include/asm/entry_mm.h @@ -50,14 +50,6 @@ LFLUSH_I_AND_D = 0x00000808 -/* process bits for task_struct.ptrace */ -PT_TRACESYS_OFF = 3 -PT_TRACESYS_BIT = 1 -PT_PTRACED_OFF = 3 -PT_PTRACED_BIT = 0 -PT_DTRACE_OFF = 3 -PT_DTRACE_BIT = 2 - #define SAVE_ALL_INT save_all_int #define SAVE_ALL_SYS save_all_sys #define RESTORE_ALL restore_all diff --git a/arch/m68k/include/asm/entry_no.h b/arch/m68k/include/asm/entry_no.h index 80e41492aa2a..26be277394f9 100644 --- a/arch/m68k/include/asm/entry_no.h +++ b/arch/m68k/include/asm/entry_no.h @@ -32,16 +32,6 @@ #ifdef __ASSEMBLY__ -/* process bits for task_struct.flags */ -PF_TRACESYS_OFF = 3 -PF_TRACESYS_BIT = 5 -PF_PTRACED_OFF = 3 -PF_PTRACED_BIT = 4 -PF_DTRACE_OFF = 1 -PF_DTRACE_BIT = 5 - -LENOSYS = 38 - #define SWITCH_STACK_SIZE (6*4+4) /* Includes return address */ /* diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index 8e9a8a754dde..45bd3f589bf0 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -221,9 +221,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmdp, unsigned long address) } #define pte_offset_map(pmdp,address) ((pte_t *)__pmd_page(*pmdp) + (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))) -#define pte_offset_map_nested(pmdp, address) pte_offset_map(pmdp, address) #define pte_unmap(pte) ((void)0) -#define pte_unmap_nested(pte) ((void)0) /* * Allocate and free page tables. The xxx_kernel() versions are diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h index f847ec732d62..cf5fad9b5250 100644 --- a/arch/m68k/include/asm/sun3_pgtable.h +++ b/arch/m68k/include/asm/sun3_pgtable.h @@ -219,9 +219,7 @@ static inline pte_t pgoff_to_pte(unsigned off) #define pte_offset_kernel(pmd, address) ((pte_t *) __pmd_page(*pmd) + pte_index(address)) /* FIXME: should we bother with kmap() here? */ #define pte_offset_map(pmd, address) ((pte_t *)kmap(pmd_page(*pmd)) + pte_index(address)) -#define pte_offset_map_nested(pmd, address) pte_offset_map(pmd, address) #define pte_unmap(pte) kunmap(pte) -#define pte_unmap_nested(pte) kunmap(pte) /* Macros to (de)construct the fake PTEs representing swap pages. */ #define __swp_type(x) ((x).val & 0x7F) diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index d4f421672d3b..cae268c22ba2 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -504,12 +504,9 @@ static inline pmd_t *pmd_offset(pgd_t *dir, unsigned long address) #define pte_offset_kernel(dir, addr) \ ((pte_t *) pmd_page_kernel(*(dir)) + pte_index(addr)) #define pte_offset_map(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir)), KM_PTE0) + pte_index(addr)) -#define pte_offset_map_nested(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir)), KM_PTE1) + pte_index(addr)) + ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) -#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) -#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1) +#define pte_unmap(pte) kunmap_atomic(pte) /* Encode and decode a nonlinear file mapping entry */ #define PTE_FILE_MAX_BITS 29 diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index 75753ca73bfd..77e644082a3b 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -45,18 +45,12 @@ extern pte_t *pkmap_page_table; extern void * kmap_high(struct page *page); extern void kunmap_high(struct page *page); -extern void *__kmap(struct page *page); -extern void __kunmap(struct page *page); -extern void *__kmap_atomic(struct page *page, enum km_type type); -extern void __kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); -extern void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); -extern struct page *__kmap_atomic_to_page(void *ptr); - -#define kmap __kmap -#define kunmap __kunmap -#define kmap_atomic __kmap_atomic -#define kunmap_atomic_notypecheck __kunmap_atomic_notypecheck -#define kmap_atomic_to_page __kmap_atomic_to_page +extern void *kmap(struct page *page); +extern void kunmap(struct page *page); +extern void *__kmap_atomic(struct page *page); +extern void __kunmap_atomic(void *kvaddr); +extern void *kmap_atomic_pfn(unsigned long pfn); +extern struct page *kmap_atomic_to_page(void *ptr); #define flush_cache_kmaps() flush_cache_all() diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index ae90412556d0..8a153d2fa62a 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -154,10 +154,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) -#define pte_offset_map_nested(dir, address) \ - ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) #define pte_unmap(pte) ((void)(pte)) -#define pte_unmap_nested(pte) ((void)(pte)) #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 1be4b0fa30da..f00896087dda 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -257,10 +257,7 @@ static inline pmd_t *pmd_offset(pud_t * pud, unsigned long address) ((pte_t *) pmd_page_vaddr(*(dir)) + __pte_offset(address)) #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) -#define pte_offset_map_nested(dir, address) \ - ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) #define pte_unmap(pte) ((void)(pte)) -#define pte_unmap_nested(pte) ((void)(pte)) /* * Initialize a new pgd / pmd table with invalid pointers. diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c index 6a2b1bf9ef11..1e69b1fb4b85 100644 --- a/arch/mips/mm/highmem.c +++ b/arch/mips/mm/highmem.c @@ -9,7 +9,7 @@ static pte_t *kmap_pte; unsigned long highstart_pfn, highend_pfn; -void *__kmap(struct page *page) +void *kmap(struct page *page) { void *addr; @@ -21,16 +21,16 @@ void *__kmap(struct page *page) return addr; } -EXPORT_SYMBOL(__kmap); +EXPORT_SYMBOL(kmap); -void __kunmap(struct page *page) +void kunmap(struct page *page) { BUG_ON(in_interrupt()); if (!PageHighMem(page)) return; kunmap_high(page); } -EXPORT_SYMBOL(__kunmap); +EXPORT_SYMBOL(kunmap); /* * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because @@ -41,17 +41,17 @@ EXPORT_SYMBOL(__kunmap); * kmaps are appropriate for short, tight code paths only. */ -void *__kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page) { - enum fixed_addresses idx; unsigned long vaddr; + int idx, type; /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic(type); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM @@ -64,43 +64,47 @@ void *__kmap_atomic(struct page *page, enum km_type type) } EXPORT_SYMBOL(__kmap_atomic); -void __kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr) { -#ifdef CONFIG_DEBUG_HIGHMEM unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); + int type; if (vaddr < FIXADDR_START) { // FIXME pagefault_enable(); return; } - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); + type = kmap_atomic_idx_pop(); +#ifdef CONFIG_DEBUG_HIGHMEM + { + int idx = type + KM_TYPE_NR * smp_processor_id(); - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); - local_flush_tlb_one(vaddr); + BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); + + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(&init_mm, vaddr, kmap_pte-idx); + local_flush_tlb_one(vaddr); + } #endif - pagefault_enable(); } -EXPORT_SYMBOL(__kunmap_atomic_notypecheck); +EXPORT_SYMBOL(__kunmap_atomic); /* * This is the same as kmap_atomic() but can map memory that doesn't * have a struct page associated with it. */ -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *kmap_atomic_pfn(unsigned long pfn) { - enum fixed_addresses idx; unsigned long vaddr; + int idx, type; pagefault_disable(); - debug_kmap_atomic(type); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); set_pte(kmap_pte-idx, pfn_pte(pfn, PAGE_KERNEL)); @@ -109,7 +113,7 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) return (void*) vaddr; } -struct page *__kmap_atomic_to_page(void *ptr) +struct page *kmap_atomic_to_page(void *ptr) { unsigned long idx, vaddr = (unsigned long)ptr; pte_t *pte; diff --git a/arch/mn10300/include/asm/highmem.h b/arch/mn10300/include/asm/highmem.h index b0b187a29b88..f577ba2268ca 100644 --- a/arch/mn10300/include/asm/highmem.h +++ b/arch/mn10300/include/asm/highmem.h @@ -70,15 +70,16 @@ static inline void kunmap(struct page *page) * be used in IRQ contexts, so in some (very limited) cases we need * it. */ -static inline unsigned long kmap_atomic(struct page *page, enum km_type type) +static inline unsigned long __kmap_atomic(struct page *page) { - enum fixed_addresses idx; unsigned long vaddr; + int idx, type; + pagefault_disable(); if (page < highmem_start_page) return page_address(page); - debug_kmap_atomic(type); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #if HIGHMEM_DEBUG @@ -91,26 +92,35 @@ static inline unsigned long kmap_atomic(struct page *page, enum km_type type) return vaddr; } -static inline void kunmap_atomic_notypecheck(unsigned long vaddr, enum km_type type) +static inline void __kunmap_atomic(unsigned long vaddr) { -#if HIGHMEM_DEBUG - enum fixed_addresses idx = type + KM_TYPE_NR * smp_processor_id(); + int type; - if (vaddr < FIXADDR_START) /* FIXME */ + if (vaddr < FIXADDR_START) { /* FIXME */ + pagefault_enable(); return; + } - if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)) - BUG(); + type = kmap_atomic_idx_pop(); - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(kmap_pte - idx); - __flush_tlb_one(vaddr); +#if HIGHMEM_DEBUG + { + unsigned int idx; + idx = type + KM_TYPE_NR * smp_processor_id(); + + if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)) + BUG(); + + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(kmap_pte - idx); + __flush_tlb_one(vaddr); + } #endif + pagefault_enable(); } - #endif /* __KERNEL__ */ #endif /* _ASM_HIGHMEM_H */ diff --git a/arch/mn10300/include/asm/pgtable.h b/arch/mn10300/include/asm/pgtable.h index 16d88577f3e0..b049a8bd1577 100644 --- a/arch/mn10300/include/asm/pgtable.h +++ b/arch/mn10300/include/asm/pgtable.h @@ -457,9 +457,7 @@ static inline int set_kernel_exec(unsigned long vaddr, int enable) #define pte_offset_map(dir, address) \ ((pte_t *) page_address(pmd_page(*(dir))) + pte_index(address)) -#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) #define pte_unmap(pte) do {} while (0) -#define pte_unmap_nested(pte) do {} while (0) /* * The MN10300 has external MMU info in the form of a TLB: this is adapted from diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 01c15035e783..865f37a8a881 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -397,9 +397,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define pte_offset_kernel(pmd, address) \ ((pte_t *) pmd_page_vaddr(*(pmd)) + pte_index(address)) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) -#define pte_offset_map_nested(pmd, address) pte_offset_kernel(pmd, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #define pte_unmap(pte) do { } while (0) #define pte_unmap_nested(pte) do { } while (0) diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index d10d64a4be38..dbc264010d0b 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -60,9 +60,8 @@ extern pte_t *pkmap_page_table; extern void *kmap_high(struct page *page); extern void kunmap_high(struct page *page); -extern void *kmap_atomic_prot(struct page *page, enum km_type type, - pgprot_t prot); -extern void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); +extern void *kmap_atomic_prot(struct page *page, pgprot_t prot); +extern void __kunmap_atomic(void *kvaddr); static inline void *kmap(struct page *page) { @@ -80,9 +79,9 @@ static inline void kunmap(struct page *page) kunmap_high(page); } -static inline void *kmap_atomic(struct page *page, enum km_type type) +static inline void *__kmap_atomic(struct page *page) { - return kmap_atomic_prot(page, type, kmap_prot); + return kmap_atomic_prot(page, kmap_prot); } static inline struct page *kmap_atomic_to_page(void *ptr) diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h index a7db96f2b5c3..47edde8c3556 100644 --- a/arch/powerpc/include/asm/pgtable-ppc32.h +++ b/arch/powerpc/include/asm/pgtable-ppc32.h @@ -308,12 +308,8 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) #define pte_offset_kernel(dir, addr) \ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) #define pte_offset_map(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir)), KM_PTE0) + pte_index(addr)) -#define pte_offset_map_nested(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir)), KM_PTE1) + pte_index(addr)) - -#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) -#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1) + ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) +#define pte_unmap(pte) kunmap_atomic(pte) /* * Encode and decode a swap entry. diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 49865045d56f..2b09cd522d33 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -193,9 +193,7 @@ (((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) -#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr)) #define pte_unmap(pte) do { } while(0) -#define pte_unmap_nested(pte) do { } while(0) /* to find an entry in a kernel page-table-directory */ /* This now only contains the vmalloc pages */ diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index d692989a4318..441d2a722f06 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -238,9 +238,7 @@ static inline void vio_cmo_dealloc(struct vio_dev *viodev, size_t size) * memory in this pool does not change. */ if (spare_needed && reserve_freed) { - tmp = min(spare_needed, min(reserve_freed, - (viodev->cmo.entitled - - VIO_CMO_MIN_ENT))); + tmp = min3(spare_needed, reserve_freed, (viodev->cmo.entitled - VIO_CMO_MIN_ENT)); vio_cmo.spare += tmp; viodev->cmo.entitled -= tmp; diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c index 857d4173f9c6..b0848b462bbc 100644 --- a/arch/powerpc/mm/highmem.c +++ b/arch/powerpc/mm/highmem.c @@ -29,17 +29,17 @@ * be used in IRQ contexts, so in some (very limited) cases we need * it. */ -void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) +void *kmap_atomic_prot(struct page *page, pgprot_t prot) { - unsigned int idx; unsigned long vaddr; + int idx, type; /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic(type); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM @@ -52,26 +52,33 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) } EXPORT_SYMBOL(kmap_atomic_prot); -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr) { -#ifdef CONFIG_DEBUG_HIGHMEM unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); + int type; if (vaddr < __fix_to_virt(FIX_KMAP_END)) { pagefault_enable(); return; } - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); + type = kmap_atomic_idx_pop(); - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); - local_flush_tlb_page(NULL, vaddr); +#ifdef CONFIG_DEBUG_HIGHMEM + { + unsigned int idx; + + idx = type + KM_TYPE_NR * smp_processor_id(); + BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); + + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(&init_mm, vaddr, kmap_pte-idx); + local_flush_tlb_page(NULL, vaddr); + } #endif pagefault_enable(); } -EXPORT_SYMBOL(kunmap_atomic_notypecheck); +EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 986dc9476c21..02ace3491c51 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1094,9 +1094,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) #define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr)) #define pte_offset_kernel(pmd, address) pte_offset(pmd,address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) -#define pte_offset_map_nested(pmd, address) pte_offset_kernel(pmd, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) /* * 31 bit swap entry format: diff --git a/arch/score/include/asm/pgtable.h b/arch/score/include/asm/pgtable.h index ccf38f06c57d..2fd469807683 100644 --- a/arch/score/include/asm/pgtable.h +++ b/arch/score/include/asm/pgtable.h @@ -88,10 +88,7 @@ static inline void pmd_clear(pmd_t *pmdp) #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) -#define pte_offset_map_nested(dir, address) \ - ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) #define pte_unmap(pte) ((void)(pte)) -#define pte_unmap_nested(pte) ((void)(pte)) /* * Bits 9(_PAGE_PRESENT) and 10(_PAGE_FILE)are taken, diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h index e172d696e52b..69fdfbf14ea5 100644 --- a/arch/sh/include/asm/pgtable_32.h +++ b/arch/sh/include/asm/pgtable_32.h @@ -429,10 +429,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define pte_offset_kernel(dir, address) \ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address)) #define pte_offset_map(dir, address) pte_offset_kernel(dir, address) -#define pte_offset_map_nested(dir, address) pte_offset_kernel(dir, address) - #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #ifdef CONFIG_X2TLB #define pte_ERROR(e) \ diff --git a/arch/sh/include/asm/pgtable_64.h b/arch/sh/include/asm/pgtable_64.h index 0ee46776dad6..10a48111226d 100644 --- a/arch/sh/include/asm/pgtable_64.h +++ b/arch/sh/include/asm/pgtable_64.h @@ -84,9 +84,7 @@ static __inline__ void set_pte(pte_t *pteptr, pte_t pteval) ((pte_t *) ((pmd_val(*(dir))) & PAGE_MASK) + pte_index((addr))) #define pte_offset_map(dir,addr) pte_offset_kernel(dir, addr) -#define pte_offset_map_nested(dir,addr) pte_offset_kernel(dir, addr) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #ifndef __ASSEMBLY__ #define IOBASE_VADDR 0xff000000 diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h index ec23b0a87b98..3d7afbb7f4bb 100644 --- a/arch/sparc/include/asm/highmem.h +++ b/arch/sparc/include/asm/highmem.h @@ -70,8 +70,8 @@ static inline void kunmap(struct page *page) kunmap_high(page); } -extern void *kmap_atomic(struct page *page, enum km_type type); -extern void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); +extern void *__kmap_atomic(struct page *page); +extern void __kunmap_atomic(void *kvaddr); extern struct page *kmap_atomic_to_page(void *vaddr); #define flush_cache_kmaps() flush_cache_all() diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index 0ece77f47753..303bd4dc8292 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -304,10 +304,7 @@ BTFIXUPDEF_CALL(pte_t *, pte_offset_kernel, pmd_t *, unsigned long) * and sun4c is guaranteed to have no highmem anyway. */ #define pte_offset_map(d, a) pte_offset_kernel(d,a) -#define pte_offset_map_nested(d, a) pte_offset_kernel(d,a) - #define pte_unmap(pte) do{}while(0) -#define pte_unmap_nested(pte) do{}while(0) /* Certain architectures need to do special things when pte's * within a page table are directly modified. Thus, the following diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index f5b5fa76c02d..f8dddb7045bb 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -652,9 +652,7 @@ static inline int pte_special(pte_t pte) ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))) #define pte_offset_kernel pte_index #define pte_offset_map pte_index -#define pte_offset_map_nested pte_index #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) /* Actual page table PTE updates. */ extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig); diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c index e139e9cbf5f7..5e50c09b7dce 100644 --- a/arch/sparc/mm/highmem.c +++ b/arch/sparc/mm/highmem.c @@ -29,17 +29,17 @@ #include #include -void *kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page) { - unsigned long idx; unsigned long vaddr; + long idx, type; /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic(type); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); @@ -63,44 +63,50 @@ void *kmap_atomic(struct page *page, enum km_type type) return (void*) vaddr; } -EXPORT_SYMBOL(kmap_atomic); +EXPORT_SYMBOL(__kmap_atomic); -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr) { -#ifdef CONFIG_DEBUG_HIGHMEM unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - unsigned long idx = type + KM_TYPE_NR*smp_processor_id(); + int type; if (vaddr < FIXADDR_START) { // FIXME pagefault_enable(); return; } - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx)); + type = kmap_atomic_idx_pop(); -/* XXX Fix - Anton */ +#ifdef CONFIG_DEBUG_HIGHMEM + { + unsigned long idx; + + idx = type + KM_TYPE_NR * smp_processor_id(); + BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx)); + + /* XXX Fix - Anton */ #if 0 - __flush_cache_one(vaddr); + __flush_cache_one(vaddr); #else - flush_cache_all(); + flush_cache_all(); #endif - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); -/* XXX Fix - Anton */ + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(&init_mm, vaddr, kmap_pte-idx); + /* XXX Fix - Anton */ #if 0 - __flush_tlb_one(vaddr); + __flush_tlb_one(vaddr); #else - flush_tlb_all(); + flush_tlb_all(); #endif + } #endif - pagefault_enable(); } -EXPORT_SYMBOL(kunmap_atomic_notypecheck); +EXPORT_SYMBOL(__kunmap_atomic); /* We may be fed a pagetable here by ptep_to_xxx and others. */ struct page *kmap_atomic_to_page(void *ptr) diff --git a/arch/tile/include/asm/highmem.h b/arch/tile/include/asm/highmem.h index d155db6fa9bd..e0f7ee186721 100644 --- a/arch/tile/include/asm/highmem.h +++ b/arch/tile/include/asm/highmem.h @@ -60,12 +60,12 @@ void *kmap_fix_kpte(struct page *page, int finished); /* This macro is used only in map_new_virtual() to map "page". */ #define kmap_prot page_to_kpgprot(page) -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); -void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); +void *__kmap_atomic(struct page *page); +void __kunmap_atomic(void *kvaddr); +void *kmap_atomic_pfn(unsigned long pfn); +void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); -void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot); -void *kmap_atomic(struct page *page, enum km_type type); +void *kmap_atomic_prot(struct page *page, pgprot_t prot); void kmap_atomic_fix_kpte(struct page *page, int finished); #define flush_cache_kmaps() do { } while (0) diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h index b3367379d537..dc4ccdd855bc 100644 --- a/arch/tile/include/asm/pgtable.h +++ b/arch/tile/include/asm/pgtable.h @@ -347,15 +347,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) extern pte_t *_pte_offset_map(pmd_t *, unsigned long address, enum km_type); #define pte_offset_map(dir, address) \ _pte_offset_map(dir, address, KM_PTE0) -#define pte_offset_map_nested(dir, address) \ - _pte_offset_map(dir, address, KM_PTE1) #define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) -#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1) #else #define pte_offset_map(dir, address) pte_offset_kernel(dir, address) -#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #endif /* Clear a non-executable kernel PTE and flush it from the TLB. */ diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c index 12ab137e7d4f..8ef6595e162c 100644 --- a/arch/tile/mm/highmem.c +++ b/arch/tile/mm/highmem.c @@ -56,50 +56,6 @@ void kunmap(struct page *page) } EXPORT_SYMBOL(kunmap); -static void debug_kmap_atomic_prot(enum km_type type) -{ -#ifdef CONFIG_DEBUG_HIGHMEM - static unsigned warn_count = 10; - - if (unlikely(warn_count == 0)) - return; - - if (unlikely(in_interrupt())) { - if (in_irq()) { - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_BIO_SRC_IRQ && - /* type != KM_BIO_DST_IRQ && */ - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } else if (!irqs_disabled()) { /* softirq */ - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 && - type != KM_SKB_SUNRPC_DATA && - type != KM_SKB_DATA_SOFTIRQ && - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } - } - - if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || - type == KM_BIO_SRC_IRQ /* || type == KM_BIO_DST_IRQ */) { - if (!irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) { - if (irq_count() == 0 && !irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } -#endif -} - /* * Describe a single atomic mapping of a page on a given cpu at a * given address, and allow it to be linked into a list. @@ -240,10 +196,10 @@ void kmap_atomic_fix_kpte(struct page *page, int finished) * When holding an atomic kmap is is not legal to sleep, so atomic * kmaps are appropriate for short, tight code paths only. */ -void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) +void *kmap_atomic_prot(struct page *page, pgprot_t prot) { - enum fixed_addresses idx; unsigned long vaddr; + int idx, type; pte_t *pte; /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ @@ -255,8 +211,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic_prot(type); - + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); pte = kmap_get_pte(vaddr); @@ -269,25 +224,31 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) } EXPORT_SYMBOL(kmap_atomic_prot); -void *kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page) { /* PAGE_NONE is a magic value that tells us to check immutability. */ return kmap_atomic_prot(page, type, PAGE_NONE); } -EXPORT_SYMBOL(kmap_atomic); +EXPORT_SYMBOL(__kmap_atomic); -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); - /* - * Force other mappings to Oops if they try to access this pte without - * first remapping it. Keeping stale mappings around is a bad idea. - */ - if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx)) { + if (vaddr >= __fix_to_virt(FIX_KMAP_END) && + vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) { pte_t *pte = kmap_get_pte(vaddr); pte_t pteval = *pte; + int idx, type; + + type = kmap_atomic_idx_pop(); + idx = type + KM_TYPE_NR*smp_processor_id(); + + /* + * Force other mappings to Oops if they try to access this pte + * without first remapping it. Keeping stale mappings around + * is a bad idea. + */ BUG_ON(!pte_present(pteval) && !pte_migrating(pteval)); kmap_atomic_unregister(pte_page(pteval), vaddr); kpte_clear_flush(pte, vaddr); @@ -300,19 +261,19 @@ void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) arch_flush_lazy_mmu_mode(); pagefault_enable(); } -EXPORT_SYMBOL(kunmap_atomic_notypecheck); +EXPORT_SYMBOL(__kunmap_atomic); /* * This API is supposed to allow us to map memory without a "struct page". * Currently we don't support this, though this may change in the future. */ -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *kmap_atomic_pfn(unsigned long pfn) { - return kmap_atomic(pfn_to_page(pfn), type); + return kmap_atomic(pfn_to_page(pfn)); } -void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) +void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { - return kmap_atomic_prot(pfn_to_page(pfn), type, prot); + return kmap_atomic_prot(pfn_to_page(pfn), prot); } struct page *kmap_atomic_to_page(void *ptr) diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um index ec2b8da1aba4..50d6aa20c353 100644 --- a/arch/um/Kconfig.um +++ b/arch/um/Kconfig.um @@ -120,6 +120,9 @@ config SMP If you don't know what to do, say N. +config GENERIC_HARDIRQS_NO__DO_IRQ + def_bool y + config NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 @@ -147,3 +150,6 @@ config KERNEL_STACK_ORDER This option determines the size of UML kernel stacks. They will be 1 << order pages. The default is OK unless you're running Valgrind on UML, in which case, set this to 3. + +config NO_DMA + def_bool y diff --git a/arch/um/defconfig b/arch/um/defconfig index 6bd456f96f90..564f3de65b4a 100644 --- a/arch/um/defconfig +++ b/arch/um/defconfig @@ -566,7 +566,6 @@ CONFIG_CRC32=m # CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set CONFIG_PLIST=y -CONFIG_HAS_DMA=y # # SCSI device support diff --git a/arch/um/include/asm/dma-mapping.h b/arch/um/include/asm/dma-mapping.h deleted file mode 100644 index 1f469e80fdd3..000000000000 --- a/arch/um/include/asm/dma-mapping.h +++ /dev/null @@ -1,112 +0,0 @@ -#ifndef _ASM_DMA_MAPPING_H -#define _ASM_DMA_MAPPING_H - -#include - -static inline int -dma_supported(struct device *dev, u64 mask) -{ - BUG(); - return(0); -} - -static inline int -dma_set_mask(struct device *dev, u64 dma_mask) -{ - BUG(); - return(0); -} - -static inline void * -dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flag) -{ - BUG(); - return((void *) 0); -} - -static inline void -dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle) -{ - BUG(); -} - -static inline dma_addr_t -dma_map_single(struct device *dev, void *cpu_addr, size_t size, - enum dma_data_direction direction) -{ - BUG(); - return(0); -} - -static inline void -dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction direction) -{ - BUG(); -} - -static inline dma_addr_t -dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - BUG(); - return(0); -} - -static inline void -dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, - enum dma_data_direction direction) -{ - BUG(); -} - -static inline int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction direction) -{ - BUG(); - return(0); -} - -static inline void -dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, - enum dma_data_direction direction) -{ - BUG(); -} - -static inline void -dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - BUG(); -} - -static inline void -dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction direction) -{ - BUG(); -} - -#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) -#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) - -static inline void -dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction direction) -{ - BUG(); -} - -static inline int -dma_mapping_error(struct device *dev, dma_addr_t dma_handle) -{ - BUG(); - return 0; -} - -#endif diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index a9f7251b4a8d..41474fb5eee7 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -338,9 +338,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address)) #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address)) -#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) struct mm_struct; extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr); diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h index 93af1cf0907d..68a90ecd1450 100644 --- a/arch/um/include/asm/system.h +++ b/arch/um/include/asm/system.h @@ -8,23 +8,38 @@ extern int set_signals(int enable); extern void block_signals(void); extern void unblock_signals(void); -#define local_save_flags(flags) do { typecheck(unsigned long, flags); \ - (flags) = get_signals(); } while(0) -#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \ - set_signals(flags); } while(0) +static inline unsigned long arch_local_save_flags(void) +{ + return get_signals(); +} -#define local_irq_save(flags) do { local_save_flags(flags); \ - local_irq_disable(); } while(0) +static inline void arch_local_irq_restore(unsigned long flags) +{ + set_signals(flags); +} -#define local_irq_enable() unblock_signals() -#define local_irq_disable() block_signals() +static inline void arch_local_irq_enable(void) +{ + unblock_signals(); +} -#define irqs_disabled() \ -({ \ - unsigned long flags; \ - local_save_flags(flags); \ - (flags == 0); \ -}) +static inline void arch_local_irq_disable(void) +{ + block_signals(); +} + +static inline unsigned long arch_local_irq_save(void) +{ + unsigned long flags; + flags = arch_local_save_flags(); + arch_local_irq_disable(); + return flags; +} + +static inline bool arch_irqs_disabled(void) +{ + return arch_local_save_flags() == 0; +} extern void *_switch_to(void *prev, void *next, void *last); #define switch_to(prev, next, last) prev = _switch_to(prev, next, last) diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index 69268014dd8e..a3cab6d3ae02 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -50,8 +50,18 @@ SECTIONS .rela.got : { *(.rela.got) } .rel.bss : { *(.rel.bss .rel.bss.* .rel.gnu.linkonce.b.*) } .rela.bss : { *(.rela.bss .rela.bss.* .rela.gnu.linkonce.b.*) } - .rel.plt : { *(.rel.plt) } - .rela.plt : { *(.rela.plt) } + .rel.plt : { + *(.rel.plt) + PROVIDE_HIDDEN(__rel_iplt_start = .); + *(.rel.iplt) + PROVIDE_HIDDEN(__rel_iplt_end = .); + } + .rela.plt : { + *(.rela.plt) + PROVIDE_HIDDEN(__rela_iplt_start = .); + *(.rela.iplt) + PROVIDE_HIDDEN(__rela_iplt_end = .); + } .init : { KEEP (*(.init)) } =0x90909090 diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index a746e3037a5b..3f0ac9e0c966 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -334,7 +334,7 @@ unsigned int do_IRQ(int irq, struct uml_pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs((struct pt_regs *)regs); irq_enter(); - __do_IRQ(irq); + generic_handle_irq(irq); irq_exit(); set_irq_regs(old_regs); return 1; @@ -391,17 +391,10 @@ void __init init_IRQ(void) { int i; - irq_desc[TIMER_IRQ].status = IRQ_DISABLED; - irq_desc[TIMER_IRQ].action = NULL; - irq_desc[TIMER_IRQ].depth = 1; - irq_desc[TIMER_IRQ].chip = &SIGVTALRM_irq_type; - enable_irq(TIMER_IRQ); + set_irq_chip_and_handler(TIMER_IRQ, &SIGVTALRM_irq_type, handle_edge_irq); + for (i = 1; i < NR_IRQS; i++) { - irq_desc[i].status = IRQ_DISABLED; - irq_desc[i].action = NULL; - irq_desc[i].depth = 1; - irq_desc[i].chip = &normal_irq_type; - enable_irq(i); + set_irq_chip_and_handler(i, &normal_irq_type, handle_edge_irq); } } diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index ec6378550671..fbd99402d4d2 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -22,7 +22,7 @@ SECTIONS _text = .; _stext = .; __init_begin = .; - INIT_TEXT_SECTION(PAGE_SIZE) + INIT_TEXT_SECTION(0) . = ALIGN(PAGE_SIZE); .text : @@ -43,6 +43,23 @@ SECTIONS __syscall_stub_end = .; } + /* + * These are needed even in a static link, even if they wind up being empty. + * Newer glibc needs these __rel{,a}_iplt_{start,end} symbols. + */ + .rel.plt : { + *(.rel.plt) + PROVIDE_HIDDEN(__rel_iplt_start = .); + *(.rel.iplt) + PROVIDE_HIDDEN(__rel_iplt_end = .); + } + .rela.plt : { + *(.rela.plt) + PROVIDE_HIDDEN(__rela_iplt_start = .); + *(.rela.iplt) + PROVIDE_HIDDEN(__rela_iplt_end = .); + } + #include "asm/common.lds.S" init.data : { INIT_DATA } diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index dec5678fc17f..6e3359d6a839 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -60,7 +60,7 @@ static inline long long timeval_to_ns(const struct timeval *tv) long long disable_timer(void) { struct itimerval time = ((struct itimerval) { { 0, 0 }, { 0, 0 } }); - int remain, max = UM_NSEC_PER_SEC / UM_HZ; + long long remain, max = UM_NSEC_PER_SEC / UM_HZ; if (setitimer(ITIMER_VIRTUAL, &time, &time) < 0) printk(UM_KERN_ERR "disable_timer - setitimer failed, " diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 8caac76ac324..3bd04022fd0c 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -59,11 +59,12 @@ extern void kunmap_high(struct page *page); void *kmap(struct page *page); void kunmap(struct page *page); -void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot); -void *kmap_atomic(struct page *page, enum km_type type); -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); -void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); + +void *kmap_atomic_prot(struct page *page, pgprot_t prot); +void *__kmap_atomic(struct page *page); +void __kunmap_atomic(void *kvaddr); +void *kmap_atomic_pfn(unsigned long pfn); +void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); #define flush_cache_kmaps() do { } while (0) diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h index c4191b3b7056..363e33eb6ec1 100644 --- a/arch/x86/include/asm/iomap.h +++ b/arch/x86/include/asm/iomap.h @@ -27,10 +27,10 @@ #include void __iomem * -iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); +iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot); void -iounmap_atomic(void __iomem *kvaddr, enum km_type type); +iounmap_atomic(void __iomem *kvaddr); int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot); diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 8abde9ec90bf..0c92113c4cb6 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -49,24 +49,14 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t); #endif #if defined(CONFIG_HIGHPTE) -#define __KM_PTE \ - (in_nmi() ? KM_NMI_PTE : \ - in_irq() ? KM_IRQ_PTE : \ - KM_PTE0) #define pte_offset_map(dir, address) \ - ((pte_t *)kmap_atomic(pmd_page(*(dir)), __KM_PTE) + \ + ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ pte_index((address))) -#define pte_offset_map_nested(dir, address) \ - ((pte_t *)kmap_atomic(pmd_page(*(dir)), KM_PTE1) + \ - pte_index((address))) -#define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE) -#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1) +#define pte_unmap(pte) kunmap_atomic((pte)) #else #define pte_offset_map(dir, address) \ ((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address))) -#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address)) #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) #endif /* Clear a kernel PTE and flush it from the TLB */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f96ac9bedf75..f86da20347f2 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -127,9 +127,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } /* x86-64 always has all page tables mapped. */ #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) -#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address)) #define pte_unmap(pte) ((void)(pte))/* NOP */ -#define pte_unmap_nested(pte) ((void)(pte)) /* NOP */ #define update_mmu_cache(vma, address, ptep) do { } while (0) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 12cd823c8d03..17ad03366211 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -327,6 +327,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3) l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13)); l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1; + l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index fe73c1844a9a..c1e8c7a51164 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -49,7 +49,6 @@ static unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n) { unsigned long offset, addr = (unsigned long)from; - int type = in_nmi() ? KM_NMI : KM_IRQ0; unsigned long size, len = 0; struct page *page; void *map; @@ -63,9 +62,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) offset = addr & (PAGE_SIZE - 1); size = min(PAGE_SIZE - offset, n - len); - map = kmap_atomic(page, type); + map = kmap_atomic(page); memcpy(to, map+offset, size); - kunmap_atomic(map, type); + kunmap_atomic(map); put_page(page); len += size; diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 67414550c3cc..d5cd13945d5a 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -61,7 +61,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!is_crashed_pfn_valid(pfn)) return -EFAULT; - vaddr = kmap_atomic_pfn(pfn, KM_PTE0); + vaddr = kmap_atomic_pfn(pfn); if (!userbuf) { memcpy(buf, (vaddr + offset), csize); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index aff0b3c27509..ae03cab4352e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -713,7 +713,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, switch (action & 0xf) { case CPU_ONLINE: - INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work); + INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work); init_completion(&work.complete); /* FIXME: add schedule_work_on() */ schedule_delayed_work_on(cpu, &work.work, 0); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6af118511b4a..6c7faecd9e4a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -747,7 +747,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; - INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle); + INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); alternatives_smp_switch(1); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 852b319edbdc..7d90ceb882a4 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -919,9 +919,9 @@ spurious_fault(unsigned long error_code, unsigned long address) int show_unhandled_signals = 1; static inline int -access_error(unsigned long error_code, int write, struct vm_area_struct *vma) +access_error(unsigned long error_code, struct vm_area_struct *vma) { - if (write) { + if (error_code & PF_WRITE) { /* write, present and write, not present: */ if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; @@ -956,8 +956,10 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) struct task_struct *tsk; unsigned long address; struct mm_struct *mm; - int write; int fault; + int write = error_code & PF_WRITE; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | + (write ? FAULT_FLAG_WRITE : 0); tsk = current; mm = tsk->mm; @@ -1068,6 +1070,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) bad_area_nosemaphore(regs, error_code, address); return; } +retry: down_read(&mm->mmap_sem); } else { /* @@ -1111,9 +1114,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) * we can handle it.. */ good_area: - write = error_code & PF_WRITE; - - if (unlikely(access_error(error_code, write, vma))) { + if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address); return; } @@ -1123,21 +1124,34 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) * make sure we exit gracefully rather than endlessly redo * the fault: */ - fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, error_code, address, fault); return; } - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, - regs, address); + /* + * Major/minor page fault accounting is only done on the + * initial attempt. If we go through a retry, it is extremely + * likely that the page will be found in page cache at that point. + */ + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) { + tsk->maj_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + regs, address); + } else { + tsk->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + regs, address); + } + if (fault & VM_FAULT_RETRY) { + /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk + * of starvation. */ + flags &= ~FAULT_FLAG_ALLOW_RETRY; + goto retry; + } } check_v8086_mode(regs, address, tsk); diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 5e8fa12ef861..d723e369003c 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -9,6 +9,7 @@ void *kmap(struct page *page) return page_address(page); return kmap_high(page); } +EXPORT_SYMBOL(kmap); void kunmap(struct page *page) { @@ -18,6 +19,7 @@ void kunmap(struct page *page) return; kunmap_high(page); } +EXPORT_SYMBOL(kunmap); /* * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because @@ -27,10 +29,10 @@ void kunmap(struct page *page) * However when holding an atomic kmap it is not legal to sleep, so atomic * kmaps are appropriate for short, tight code paths only. */ -void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) +void *kmap_atomic_prot(struct page *page, pgprot_t prot) { - enum fixed_addresses idx; unsigned long vaddr; + int idx, type; /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); @@ -38,8 +40,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic(type); - + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); @@ -47,44 +48,56 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) return (void *)vaddr; } +EXPORT_SYMBOL(kmap_atomic_prot); -void *kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page) { - return kmap_atomic_prot(page, type, kmap_prot); -} - -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) -{ - unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); - - /* - * Force other mappings to Oops if they'll try to access this pte - * without first remap it. Keeping stale mappings around is a bad idea - * also, in case the page changes cacheability attributes or becomes - * a protected page in a hypervisor. - */ - if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx)) - kpte_clear_flush(kmap_pte-idx, vaddr); - else { -#ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(vaddr < PAGE_OFFSET); - BUG_ON(vaddr >= (unsigned long)high_memory); -#endif - } - - pagefault_enable(); + return kmap_atomic_prot(page, kmap_prot); } +EXPORT_SYMBOL(__kmap_atomic); /* * This is the same as kmap_atomic() but can map memory that doesn't * have a struct page associated with it. */ -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *kmap_atomic_pfn(unsigned long pfn) { - return kmap_atomic_prot_pfn(pfn, type, kmap_prot); + return kmap_atomic_prot_pfn(pfn, kmap_prot); } -EXPORT_SYMBOL_GPL(kmap_atomic_pfn); /* temporarily in use by i915 GEM until vmap */ +EXPORT_SYMBOL_GPL(kmap_atomic_pfn); + +void __kunmap_atomic(void *kvaddr) +{ + unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; + + if (vaddr >= __fix_to_virt(FIX_KMAP_END) && + vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) { + int idx, type; + + type = kmap_atomic_idx_pop(); + idx = type + KM_TYPE_NR * smp_processor_id(); + +#ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); +#endif + /* + * Force other mappings to Oops if they'll try to access this + * pte without first remap it. Keeping stale mappings around + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ + kpte_clear_flush(kmap_pte-idx, vaddr); + } +#ifdef CONFIG_DEBUG_HIGHMEM + else { + BUG_ON(vaddr < PAGE_OFFSET); + BUG_ON(vaddr >= (unsigned long)high_memory); + } +#endif + + pagefault_enable(); +} +EXPORT_SYMBOL(__kunmap_atomic); struct page *kmap_atomic_to_page(void *ptr) { @@ -98,12 +111,6 @@ struct page *kmap_atomic_to_page(void *ptr) pte = kmap_pte - (idx - FIX_KMAP_BEGIN); return pte_page(*pte); } - -EXPORT_SYMBOL(kmap); -EXPORT_SYMBOL(kunmap); -EXPORT_SYMBOL(kmap_atomic); -EXPORT_SYMBOL(kunmap_atomic_notypecheck); -EXPORT_SYMBOL(kmap_atomic_prot); EXPORT_SYMBOL(kmap_atomic_to_page); void __init set_highmem_pages_init(void) diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 72fc70cf6184..75a3d7f24a2c 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -48,21 +48,20 @@ int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot) } EXPORT_SYMBOL_GPL(iomap_create_wc); -void -iomap_free(resource_size_t base, unsigned long size) +void iomap_free(resource_size_t base, unsigned long size) { io_free_memtype(base, base + size); } EXPORT_SYMBOL_GPL(iomap_free); -void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) +void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { - enum fixed_addresses idx; unsigned long vaddr; + int idx, type; pagefault_disable(); - debug_kmap_atomic(type); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); @@ -72,10 +71,10 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) } /* - * Map 'pfn' using fixed map 'type' and protections 'prot' + * Map 'pfn' using protections 'prot' */ void __iomem * -iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) +iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { /* * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS. @@ -86,24 +85,33 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC)) prot = PAGE_KERNEL_UC_MINUS; - return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, type, prot); + return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, prot); } EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn); void -iounmap_atomic(void __iomem *kvaddr, enum km_type type) +iounmap_atomic(void __iomem *kvaddr) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); - /* - * Force other mappings to Oops if they'll try to access this pte - * without first remap it. Keeping stale mappings around is a bad idea - * also, in case the page changes cacheability attributes or becomes - * a protected page in a hypervisor. - */ - if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx)) + if (vaddr >= __fix_to_virt(FIX_KMAP_END) && + vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) { + int idx, type; + + type = kmap_atomic_idx_pop(); + idx = type + KM_TYPE_NR * smp_processor_id(); + +#ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); +#endif + /* + * Force other mappings to Oops if they'll try to access this + * pte without first remap it. Keeping stale mappings around + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ kpte_clear_flush(kmap_pte-idx, vaddr); + } pagefault_enable(); } diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 76bf35554117..b03c043ce75b 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -324,10 +324,7 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) #define pte_offset_kernel(dir,addr) \ ((pte_t*) pmd_page_vaddr(*(dir)) + pte_index(addr)) #define pte_offset_map(dir,addr) pte_offset_kernel((dir),(addr)) -#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir),(addr)) - #define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) /* diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index 0ec1fb69d4ea..518c22bd9562 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -83,8 +83,8 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, memcpy(dest_buf, src_buf, len); - kunmap_atomic(dest_buf, KM_USER0); kunmap_atomic(src_buf, KM_USER1); + kunmap_atomic(dest_buf, KM_USER0); async_tx_sync_epilog(submit); } diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c index 90d26c91f4e9..7a7219266e3c 100644 --- a/crypto/blkcipher.c +++ b/crypto/blkcipher.c @@ -89,9 +89,9 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk, memcpy(walk->dst.virt.addr, walk->page, n); blkcipher_unmap_dst(walk); } else if (!(walk->flags & BLKCIPHER_WALK_PHYS)) { - blkcipher_unmap_src(walk); if (walk->flags & BLKCIPHER_WALK_DIFF) blkcipher_unmap_dst(walk); + blkcipher_unmap_src(walk); } scatterwalk_advance(&walk->in, n); diff --git a/drivers/base/node.c b/drivers/base/node.c index ee53558b452f..ce012a9c6201 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -160,6 +160,18 @@ static ssize_t node_read_numastat(struct sys_device * dev, } static SYSDEV_ATTR(numastat, S_IRUGO, node_read_numastat, NULL); +static ssize_t node_read_vmstat(struct sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + int nid = dev->id; + return sprintf(buf, + "nr_written %lu\n" + "nr_dirtied %lu\n", + node_page_state(nid, NR_WRITTEN), + node_page_state(nid, NR_DIRTIED)); +} +static SYSDEV_ATTR(vmstat, S_IRUGO, node_read_vmstat, NULL); + static ssize_t node_read_distance(struct sys_device * dev, struct sysdev_attribute *attr, char * buf) { @@ -243,6 +255,7 @@ int register_node(struct node *node, int num, struct node *parent) sysdev_create_file(&node->sysdev, &attr_meminfo); sysdev_create_file(&node->sysdev, &attr_numastat); sysdev_create_file(&node->sysdev, &attr_distance); + sysdev_create_file(&node->sysdev, &attr_vmstat); scan_unevictable_register_node(node); @@ -267,6 +280,7 @@ void unregister_node(struct node *node) sysdev_remove_file(&node->sysdev, &attr_meminfo); sysdev_remove_file(&node->sysdev, &attr_numastat); sysdev_remove_file(&node->sysdev, &attr_distance); + sysdev_remove_file(&node->sysdev, &attr_vmstat); scan_unevictable_unregister_node(node); hugetlb_unregister_node(node); /* no-op, if memoryless node */ diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6c48b3545f84..450c958b514f 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -101,8 +101,8 @@ static int transfer_none(struct loop_device *lo, int cmd, else memcpy(raw_buf, loop_buf, size); - kunmap_atomic(raw_buf, KM_USER0); kunmap_atomic(loop_buf, KM_USER1); + kunmap_atomic(raw_buf, KM_USER0); cond_resched(); return 0; } @@ -130,8 +130,8 @@ static int transfer_xor(struct loop_device *lo, int cmd, for (i = 0; i < size; i++) *out++ = *in++ ^ key[(i & 511) % keysize]; - kunmap_atomic(raw_buf, KM_USER0); kunmap_atomic(loop_buf, KM_USER1); + kunmap_atomic(raw_buf, KM_USER0); cond_resched(); return 0; } diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index a4eee324eb1e..55b8667f739f 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -32,12 +32,12 @@ #include #include #include +#include #include +#include #include -#include #include -#include #include #include @@ -81,13 +81,13 @@ static cycle_t read_hpet(struct clocksource *cs) } static struct clocksource clocksource_hpet = { - .name = "hpet", - .rating = 250, - .read = read_hpet, - .mask = CLOCKSOURCE_MASK(64), - .mult = 0, /* to be calculated */ - .shift = 10, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .name = "hpet", + .rating = 250, + .read = read_hpet, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be calculated */ + .shift = 10, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static struct clocksource *hpet_clocksource; #endif @@ -465,6 +465,21 @@ static int hpet_ioctl_ieon(struct hpet_dev *devp) if (irq) { unsigned long irq_flags; + if (devp->hd_flags & HPET_SHARED_IRQ) { + /* + * To prevent the interrupt handler from seeing an + * unwanted interrupt status bit, program the timer + * so that it will not fire in the near future ... + */ + writel(readl(&timer->hpet_config) & ~Tn_TYPE_CNF_MASK, + &timer->hpet_config); + write_counter(read_counter(&hpet->hpet_mc), + &timer->hpet_compare); + /* ... and clear any left-over status. */ + isr = 1 << (devp - devp->hd_hpets->hp_dev); + writel(isr, &hpet->hpet_isr); + } + sprintf(devp->hd_name, "hpet%d", (int)(devp - hpetp->hp_dev)); irq_flags = devp->hd_flags & HPET_SHARED_IRQ ? IRQF_SHARED : IRQF_DISABLED; @@ -581,11 +596,10 @@ hpet_ioctl_common(struct hpet_dev *devp, int cmd, unsigned long arg, break; case HPET_INFO: { + memset(info, 0, sizeof(*info)); if (devp->hd_ireqfreq) info->hi_ireqfreq = hpet_time_div(hpetp, devp->hd_ireqfreq); - else - info->hi_ireqfreq = 0; info->hi_flags = readq(&timer->hpet_config) & Tn_PER_INT_CAP_MASK; info->hi_hpet = hpetp->hp_which; @@ -811,7 +825,7 @@ int hpet_alloc(struct hpet_data *hdp) struct hpets *hpetp; size_t siz; struct hpet __iomem *hpet; - static struct hpets *last = NULL; + static struct hpets *last; unsigned long period; unsigned long long temp; u32 remainder; @@ -1000,6 +1014,8 @@ static int hpet_acpi_add(struct acpi_device *device) return -ENODEV; if (!data.hd_address || !data.hd_nirqs) { + if (data.hd_address) + iounmap(data.hd_address); printk("%s: no address or irqs in _CRS\n", __func__); return -ENODEV; } diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index e537610d2f09..b293d57d30a7 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1665,6 +1665,17 @@ static int check_hotmod_int_op(const char *curr, const char *option, return 0; } +static struct smi_info *smi_info_alloc(void) +{ + struct smi_info *info = kzalloc(sizeof(*info), GFP_KERNEL); + + if (info) { + spin_lock_init(&info->si_lock); + spin_lock_init(&info->msg_lock); + } + return info; +} + static int hotmod_handler(const char *val, struct kernel_param *kp) { char *str = kstrdup(val, GFP_KERNEL); @@ -1779,7 +1790,7 @@ static int hotmod_handler(const char *val, struct kernel_param *kp) } if (op == HM_ADD) { - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) { rv = -ENOMEM; goto out; @@ -1844,7 +1855,7 @@ static __devinit void hardcode_find_bmc(void) if (!ports[i] && !addrs[i]) continue; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) return; @@ -2027,7 +2038,7 @@ static __devinit int try_init_spmi(struct SPMITable *spmi) return -ENODEV; } - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) { printk(KERN_ERR PFX "Could not allocate SI data (3)\n"); return -ENOMEM; @@ -2137,7 +2148,7 @@ static int __devinit ipmi_pnp_probe(struct pnp_dev *dev, if (!acpi_dev) return -ENODEV; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) return -ENOMEM; @@ -2318,7 +2329,7 @@ static __devinit void try_init_dmi(struct dmi_ipmi_data *ipmi_data) { struct smi_info *info; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) { printk(KERN_ERR PFX "Could not allocate SI data\n"); return; @@ -2425,7 +2436,7 @@ static int __devinit ipmi_pci_probe(struct pci_dev *pdev, int class_type = pdev->class & PCI_ERMC_CLASSCODE_TYPE_MASK; struct smi_info *info; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) return -ENOMEM; @@ -2566,7 +2577,7 @@ static int __devinit ipmi_of_probe(struct platform_device *dev, return -EINVAL; } - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) { dev_err(&dev->dev, @@ -3013,7 +3024,7 @@ static __devinit void default_find_bmc(void) if (check_legacy_ioport(ipmi_defaults[i].port)) continue; #endif - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = smi_info_alloc(); if (!info) return; @@ -3138,9 +3149,6 @@ static int try_smi_init(struct smi_info *new_smi) goto out_err; } - spin_lock_init(&(new_smi->si_lock)); - spin_lock_init(&(new_smi->msg_lock)); - /* Do low-level detection first. */ if (new_smi->handlers->detect(new_smi->si_sm)) { if (new_smi->addr_source) diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c index 0eac3da566ba..a84250a5dd51 100644 --- a/drivers/crypto/hifn_795x.c +++ b/drivers/crypto/hifn_795x.c @@ -1467,7 +1467,7 @@ static int ablkcipher_add(unsigned int *drestp, struct scatterlist *dst, return -EINVAL; while (size) { - copy = min(drest, min(size, dst->length)); + copy = min3(drest, size, dst->length); size -= copy; drest -= copy; @@ -1729,7 +1729,7 @@ static int ablkcipher_get(void *saddr, unsigned int *srestp, unsigned int offset return -EINVAL; while (size) { - copy = min(srest, min(dst->length, size)); + copy = min3(srest, dst->length, size); daddr = kmap_atomic(sg_page(dst), KM_IRQ0); memcpy(daddr + dst->offset + offset, saddr, copy); diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c index a2b12aa1f2b9..501866662e05 100644 --- a/drivers/gpio/pca953x.c +++ b/drivers/gpio/pca953x.c @@ -345,7 +345,7 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid) do { level = __ffs(pending); - handle_nested_irq(level + chip->irq_base); + generic_handle_irq(level + chip->irq_base); pending &= ~(1 << level); } while (pending); @@ -360,7 +360,8 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, struct pca953x_platform_data *pdata = client->dev.platform_data; int ret; - if (pdata->irq_base && (id->driver_data & PCA953X_INT)) { + if (pdata->irq_base != -1 + && (id->driver_data & PCA953X_INT)) { int lvl; ret = pca953x_read_reg(chip, PCA953X_INPUT, @@ -383,7 +384,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, set_irq_chip_data(irq, chip); set_irq_chip_and_handler(irq, &pca953x_irq_chip, handle_edge_irq); - set_irq_nested_thread(irq, 1); #ifdef CONFIG_ARM set_irq_flags(irq, IRQF_VALID); #else @@ -394,6 +394,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, ret = request_threaded_irq(client->irq, NULL, pca953x_irq_handler, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, dev_name(&client->dev), chip); if (ret) { @@ -408,13 +409,13 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, return 0; out_failed: - chip->irq_base = 0; + chip->irq_base = -1; return ret; } static void pca953x_irq_teardown(struct pca953x_chip *chip) { - if (chip->irq_base) + if (chip->irq_base != -1) free_irq(chip->client->irq, chip); } #else /* CONFIG_GPIO_PCA953X_IRQ */ @@ -424,7 +425,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, struct i2c_client *client = chip->client; struct pca953x_platform_data *pdata = client->dev.platform_data; - if (pdata->irq_base && (id->driver_data & PCA953X_INT)) + if (pdata->irq_base != -1 && (id->driver_data & PCA953X_INT)) dev_warn(&client->dev, "interrupt support not compiled in\n"); return 0; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 90b1d6753b9d..eb6c473c6d1b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -155,11 +155,11 @@ fast_shmem_read(struct page **pages, char __iomem *vaddr; int unwritten; - vaddr = kmap_atomic(pages[page_base >> PAGE_SHIFT], KM_USER0); + vaddr = kmap_atomic(pages[page_base >> PAGE_SHIFT]); if (vaddr == NULL) return -ENOMEM; unwritten = __copy_to_user_inatomic(data, vaddr + page_offset, length); - kunmap_atomic(vaddr, KM_USER0); + kunmap_atomic(vaddr); if (unwritten) return -EFAULT; @@ -509,10 +509,10 @@ fast_user_write(struct io_mapping *mapping, char *vaddr_atomic; unsigned long unwritten; - vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base, KM_USER0); + vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base); unwritten = __copy_from_user_inatomic_nocache(vaddr_atomic + page_offset, user_data, length); - io_mapping_unmap_atomic(vaddr_atomic, KM_USER0); + io_mapping_unmap_atomic(vaddr_atomic); if (unwritten) return -EFAULT; return 0; @@ -551,11 +551,11 @@ fast_shmem_write(struct page **pages, char __iomem *vaddr; unsigned long unwritten; - vaddr = kmap_atomic(pages[page_base >> PAGE_SHIFT], KM_USER0); + vaddr = kmap_atomic(pages[page_base >> PAGE_SHIFT]); if (vaddr == NULL) return -ENOMEM; unwritten = __copy_from_user_inatomic(vaddr + page_offset, data, length); - kunmap_atomic(vaddr, KM_USER0); + kunmap_atomic(vaddr); if (unwritten) return -EFAULT; @@ -3346,8 +3346,7 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj, reloc_offset = obj_priv->gtt_offset + reloc->offset; reloc_page = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, (reloc_offset & - ~(PAGE_SIZE - 1)), - KM_USER0); + ~(PAGE_SIZE - 1))); reloc_entry = (uint32_t __iomem *)(reloc_page + (reloc_offset & (PAGE_SIZE - 1))); reloc_val = target_obj_priv->gtt_offset + reloc->delta; @@ -3358,7 +3357,7 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj, readl(reloc_entry), reloc_val); #endif writel(reloc_val, reloc_entry); - io_mapping_unmap_atomic(reloc_page, KM_USER0); + io_mapping_unmap_atomic(reloc_page); /* The updated presumed offset for this entry will be * copied back out to the user. @@ -4772,11 +4771,11 @@ void i915_gem_detach_phys_object(struct drm_device *dev, page_count = obj->size / PAGE_SIZE; for (i = 0; i < page_count; i++) { - char *dst = kmap_atomic(obj_priv->pages[i], KM_USER0); + char *dst = kmap_atomic(obj_priv->pages[i]); char *src = obj_priv->phys_obj->handle->vaddr + (i * PAGE_SIZE); memcpy(dst, src, PAGE_SIZE); - kunmap_atomic(dst, KM_USER0); + kunmap_atomic(dst); } drm_clflush_pages(obj_priv->pages, page_count); drm_agp_chipset_flush(dev); @@ -4833,11 +4832,11 @@ i915_gem_attach_phys_object(struct drm_device *dev, page_count = obj->size / PAGE_SIZE; for (i = 0; i < page_count; i++) { - char *src = kmap_atomic(obj_priv->pages[i], KM_USER0); + char *src = kmap_atomic(obj_priv->pages[i]); char *dst = obj_priv->phys_obj->handle->vaddr + (i * PAGE_SIZE); memcpy(dst, src, PAGE_SIZE); - kunmap_atomic(src, KM_USER0); + kunmap_atomic(src); } i915_gem_object_put_pages(obj); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 744225ebb4b2..b80010f0c4c9 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -456,10 +456,9 @@ i915_error_object_create(struct drm_device *dev, local_irq_save(flags); s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, - reloc_offset, - KM_IRQ0); + reloc_offset); memcpy_fromio(d, s, PAGE_SIZE); - io_mapping_unmap_atomic(s, KM_IRQ0); + io_mapping_unmap_atomic(s); local_irq_restore(flags); dst->pages[page] = d; diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 1d306a458be6..3264bbd47e65 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -187,8 +187,7 @@ static struct overlay_registers *intel_overlay_map_regs_atomic(struct intel_over if (OVERLAY_NONPHYSICAL(overlay->dev)) { regs = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, - overlay->reg_bo->gtt_offset, - KM_USER0); + overlay->reg_bo->gtt_offset); if (!regs) { DRM_ERROR("failed to map overlay regs in GTT\n"); @@ -203,7 +202,7 @@ static struct overlay_registers *intel_overlay_map_regs_atomic(struct intel_over static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay) { if (OVERLAY_NONPHYSICAL(overlay->dev)) - io_mapping_unmap_atomic(overlay->virt_addr, KM_USER0); + io_mapping_unmap_atomic(overlay->virt_addr); overlay->virt_addr = NULL; diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 974b0f8ae048..8fa339600fe3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -2167,11 +2167,11 @@ peek_fb(struct drm_device *dev, struct io_mapping *fb, if (off < pci_resource_len(dev->pdev, 1)) { uint8_t __iomem *p = - io_mapping_map_atomic_wc(fb, off & PAGE_MASK, KM_USER0); + io_mapping_map_atomic_wc(fb, off & PAGE_MASK); val = ioread32(p + (off & ~PAGE_MASK)); - io_mapping_unmap_atomic(p, KM_USER0); + io_mapping_unmap_atomic(p); } return val; @@ -2183,12 +2183,12 @@ poke_fb(struct drm_device *dev, struct io_mapping *fb, { if (off < pci_resource_len(dev->pdev, 1)) { uint8_t __iomem *p = - io_mapping_map_atomic_wc(fb, off & PAGE_MASK, KM_USER0); + io_mapping_map_atomic_wc(fb, off & PAGE_MASK); iowrite32(val, p + (off & ~PAGE_MASK)); wmb(); - io_mapping_unmap_atomic(p, KM_USER0); + io_mapping_unmap_atomic(p); } } diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 3451a82adba7..e8a73e65da69 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -170,7 +170,7 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, src = (void *)((unsigned long)src + (page << PAGE_SHIFT)); #ifdef CONFIG_X86 - dst = kmap_atomic_prot(d, KM_USER0, prot); + dst = kmap_atomic_prot(d, prot); #else if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) dst = vmap(&d, 1, 0, prot); @@ -183,7 +183,7 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, memcpy_fromio(dst, src, PAGE_SIZE); #ifdef CONFIG_X86 - kunmap_atomic(dst, KM_USER0); + kunmap_atomic(dst); #else if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) vunmap(dst); @@ -206,7 +206,7 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT)); #ifdef CONFIG_X86 - src = kmap_atomic_prot(s, KM_USER0, prot); + src = kmap_atomic_prot(s, prot); #else if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) src = vmap(&s, 1, 0, prot); @@ -219,7 +219,7 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, memcpy_toio(dst, src, PAGE_SIZE); #ifdef CONFIG_X86 - kunmap_atomic(src, KM_USER0); + kunmap_atomic(src); #else if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) vunmap(src); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index b4b22576f12a..19c5d3b191f4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1409,8 +1409,7 @@ static int __init ipoib_init_module(void) ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); - ipoib_sendq_size = max(ipoib_sendq_size, max(2 * MAX_SEND_CQE, - IPOIB_MIN_QUEUE_SIZE)); + ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); #endif diff --git a/drivers/macintosh/windfarm_pm121.c b/drivers/macintosh/windfarm_pm121.c index 947d4afa25ca..30e6195e19d4 100644 --- a/drivers/macintosh/windfarm_pm121.c +++ b/drivers/macintosh/windfarm_pm121.c @@ -482,7 +482,7 @@ static s32 pm121_correct(s32 new_setpoint, new_min += correction->offset; new_min = (new_min >> 16) + min; - return max(new_setpoint, max(new_min, 0)); + return max3(new_setpoint, new_min, 0); } static s32 pm121_connect(unsigned int control_id, s32 setpoint) diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 0b61792a2780..2129cdb115dc 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, * Issue the synchronous I/O from a different thread * to avoid generic_make_request recursion. */ - INIT_WORK_ON_STACK(&req.work, do_metadata); + INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); flush_workqueue(ps->metadata_wq); diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 1f69743b12ec..5a74db75f66f 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -4,7 +4,6 @@ menuconfig MISC_DEVICES bool "Misc devices" - default y ---help--- Say Y here to get to see options for device drivers from various different categories. This option alone does not add any kernel code. @@ -24,7 +23,8 @@ config AD525X_DPOT AD5260, AD5262, AD5263, AD5290, AD5291, AD5292, AD5293, AD7376, AD8400, AD8402, AD8403, ADN2850, AD5241, AD5242, AD5243, AD5245, AD5246, AD5247, AD5248, AD5280, AD5282, - ADN2860, AD5273, AD5171, AD5170, AD5172, AD5173 + ADN2860, AD5273, AD5171, AD5170, AD5172, AD5173, AD5270, + AD5271, AD5272, AD5274 digital potentiometer chips. See Documentation/misc-devices/ad525x_dpot.txt for the @@ -284,6 +284,16 @@ config SGI_GRU_DEBUG This option enables addition debugging code for the SGI GRU driver. If you are unsure, say N. +config APDS9802ALS + tristate "Medfield Avago APDS9802 ALS Sensor module" + depends on I2C + help + If you say yes here you get support for the ALS APDS9802 ambient + light sensor. + + This driver can also be built as a module. If so, the module + will be called apds9802als. + config ISL29003 tristate "Intersil ISL29003 ambient light sensor" depends on I2C && SYSFS @@ -294,6 +304,16 @@ config ISL29003 This driver can also be built as a module. If so, the module will be called isl29003. +config ISL29020 + tristate "Intersil ISL29020 ambient light sensor" + depends on I2C + help + If you say yes here you get support for the Intersil ISL29020 + ambient light sensor. + + This driver can also be built as a module. If so, the module + will be called isl29020. + config SENSORS_TSL2550 tristate "Taos TSL2550 ambient light sensor" depends on I2C && SYSFS @@ -314,6 +334,27 @@ config SENSORS_BH1780 This driver can also be built as a module. If so, the module will be called bh1780gli. +config SENSORS_BH1770 + tristate "BH1770GLC / SFH7770 combined ALS - Proximity sensor" + depends on I2C + ---help--- + Say Y here if you want to build a driver for BH1770GLC (ROHM) or + SFH7770 (Osram) combined ambient light and proximity sensor chip. + + To compile this driver as a module, choose M here: the + module will be called bh1770glc. If unsure, say N here. + +config SENSORS_APDS990X + tristate "APDS990X combined als and proximity sensors" + depends on I2C + default n + ---help--- + Say Y here if you want to build a driver for Avago APDS990x + combined ambient light and proximity sensor chip. + + To compile this driver as a module, choose M here: the + module will be called apds990x. If unsure, say N here. + config HMC6352 tristate "Honeywell HMC6352 compass" depends on I2C diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 9f2986b4da2f..4be5c6fc5ef4 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -16,6 +16,8 @@ obj-$(CONFIG_TIFM_CORE) += tifm_core.o obj-$(CONFIG_TIFM_7XX1) += tifm_7xx1.o obj-$(CONFIG_PHANTOM) += phantom.o obj-$(CONFIG_SENSORS_BH1780) += bh1780gli.o +obj-$(CONFIG_SENSORS_BH1770) += bh1770glc.o +obj-$(CONFIG_SENSORS_APDS990X) += apds990x.o obj-$(CONFIG_SGI_IOC4) += ioc4.o obj-$(CONFIG_ENCLOSURE_SERVICES) += enclosure.o obj-$(CONFIG_KGDB_TESTS) += kgdbts.o @@ -23,7 +25,9 @@ obj-$(CONFIG_SGI_XP) += sgi-xp/ obj-$(CONFIG_SGI_GRU) += sgi-gru/ obj-$(CONFIG_CS5535_MFGPT) += cs5535-mfgpt.o obj-$(CONFIG_HP_ILO) += hpilo.o +obj-$(CONFIG_APDS9802ALS) += apds9802als.o obj-$(CONFIG_ISL29003) += isl29003.o +obj-$(CONFIG_ISL29020) += isl29020.o obj-$(CONFIG_SENSORS_TSL2550) += tsl2550.o obj-$(CONFIG_EP93XX_PWM) += ep93xx_pwm.o obj-$(CONFIG_DS1682) += ds1682.o diff --git a/drivers/misc/ad525x_dpot-i2c.c b/drivers/misc/ad525x_dpot-i2c.c index 374352af7979..4ff73c215746 100644 --- a/drivers/misc/ad525x_dpot-i2c.c +++ b/drivers/misc/ad525x_dpot-i2c.c @@ -102,6 +102,8 @@ static const struct i2c_device_id ad_dpot_id[] = { {"ad5170", AD5170_ID}, {"ad5172", AD5172_ID}, {"ad5173", AD5173_ID}, + {"ad5272", AD5272_ID}, + {"ad5274", AD5274_ID}, {} }; MODULE_DEVICE_TABLE(i2c, ad_dpot_id); diff --git a/drivers/misc/ad525x_dpot-spi.c b/drivers/misc/ad525x_dpot-spi.c index b8c6df9c8437..7f9a55afe05d 100644 --- a/drivers/misc/ad525x_dpot-spi.c +++ b/drivers/misc/ad525x_dpot-spi.c @@ -38,6 +38,8 @@ static const struct ad_dpot_id ad_dpot_spi_devlist[] = { {.name = "ad8402", .devid = AD8402_ID}, {.name = "ad8403", .devid = AD8403_ID}, {.name = "adn2850", .devid = ADN2850_ID}, + {.name = "ad5270", .devid = AD5270_ID}, + {.name = "ad5271", .devid = AD5271_ID}, {} }; @@ -53,13 +55,13 @@ static int write8(void *client, u8 val) static int write16(void *client, u8 reg, u8 val) { u8 data[2] = {reg, val}; - return spi_write(client, data, 1); + return spi_write(client, data, 2); } static int write24(void *client, u8 reg, u16 val) { u8 data[3] = {reg, val >> 8, val}; - return spi_write(client, data, 1); + return spi_write(client, data, 3); } static int read8(void *client) diff --git a/drivers/misc/ad525x_dpot.c b/drivers/misc/ad525x_dpot.c index 5e6fa8449e8b..7cb911028d09 100644 --- a/drivers/misc/ad525x_dpot.c +++ b/drivers/misc/ad525x_dpot.c @@ -29,9 +29,9 @@ * AD5262 2 256 20, 50, 200 * AD5263 4 256 20, 50, 200 * AD5290 1 256 10, 50, 100 - * AD5291 1 256 20 - * AD5292 1 1024 20 - * AD5293 1 1024 20 + * AD5291 1 256 20, 50, 100 (20-TP) + * AD5292 1 1024 20, 50, 100 (20-TP) + * AD5293 1 1024 20, 50, 100 * AD7376 1 128 10, 50, 100, 1M * AD8400 1 256 1, 10, 50, 100 * AD8402 2 256 1, 10, 50, 100 @@ -52,6 +52,10 @@ * AD5170 1 256 2.5, 10, 50, 100 (OTP) * AD5172 2 256 2.5, 10, 50, 100 (OTP) * AD5173 2 256 2.5, 10, 50, 100 (OTP) + * AD5270 1 1024 20, 50, 100 (50-TP) + * AD5271 1 256 20, 50, 100 (50-TP) + * AD5272 1 1024 20, 50, 100 (50-TP) + * AD5274 1 256 20, 50, 100 (50-TP) * * See Documentation/misc-devices/ad525x_dpot.txt for more info. * @@ -126,18 +130,38 @@ static inline int dpot_write_r8d16(struct dpot_data *dpot, u8 reg, u16 val) static s32 dpot_read_spi(struct dpot_data *dpot, u8 reg) { unsigned ctrl = 0; + int value; if (!(reg & (DPOT_ADDR_EEPROM | DPOT_ADDR_CMD))) { if (dpot->feat & F_RDACS_WONLY) return dpot->rdac_cache[reg & DPOT_RDAC_MASK]; - if (dpot->uid == DPOT_UID(AD5291_ID) || dpot->uid == DPOT_UID(AD5292_ID) || - dpot->uid == DPOT_UID(AD5293_ID)) - return dpot_read_r8d8(dpot, + dpot->uid == DPOT_UID(AD5293_ID)) { + + value = dpot_read_r8d8(dpot, DPOT_AD5291_READ_RDAC << 2); + if (dpot->uid == DPOT_UID(AD5291_ID)) + value = value >> 2; + + return value; + } else if (dpot->uid == DPOT_UID(AD5270_ID) || + dpot->uid == DPOT_UID(AD5271_ID)) { + + value = dpot_read_r8d8(dpot, + DPOT_AD5270_1_2_4_READ_RDAC << 2); + + if (value < 0) + return value; + + if (dpot->uid == DPOT_UID(AD5271_ID)) + value = value >> 2; + + return value; + } + ctrl = DPOT_SPI_READ_RDAC; } else if (reg & DPOT_ADDR_EEPROM) { ctrl = DPOT_SPI_READ_EEPROM; @@ -153,6 +177,7 @@ static s32 dpot_read_spi(struct dpot_data *dpot, u8 reg) static s32 dpot_read_i2c(struct dpot_data *dpot, u8 reg) { + int value; unsigned ctrl = 0; switch (dpot->uid) { case DPOT_UID(AD5246_ID): @@ -166,7 +191,7 @@ static s32 dpot_read_i2c(struct dpot_data *dpot, u8 reg) case DPOT_UID(AD5280_ID): case DPOT_UID(AD5282_ID): ctrl = ((reg & DPOT_RDAC_MASK) == DPOT_RDAC0) ? - 0 : DPOT_AD5291_RDAC_AB; + 0 : DPOT_AD5282_RDAC_AB; return dpot_read_r8d8(dpot, ctrl); case DPOT_UID(AD5170_ID): case DPOT_UID(AD5171_ID): @@ -175,8 +200,27 @@ static s32 dpot_read_i2c(struct dpot_data *dpot, u8 reg) case DPOT_UID(AD5172_ID): case DPOT_UID(AD5173_ID): ctrl = ((reg & DPOT_RDAC_MASK) == DPOT_RDAC0) ? - 0 : DPOT_AD5272_3_A0; + 0 : DPOT_AD5172_3_A0; return dpot_read_r8d8(dpot, ctrl); + case DPOT_UID(AD5272_ID): + case DPOT_UID(AD5274_ID): + dpot_write_r8d8(dpot, + (DPOT_AD5270_1_2_4_READ_RDAC << 2), 0); + + value = dpot_read_r8d16(dpot, + DPOT_AD5270_1_2_4_RDAC << 2); + + if (value < 0) + return value; + /* + * AD5272/AD5274 returns high byte first, however + * underling smbus expects low byte first. + */ + value = swab16(value); + + if (dpot->uid == DPOT_UID(AD5271_ID)) + value = value >> 2; + return value; default: if ((reg & DPOT_REG_TOL) || (dpot->max_pos > 256)) return dpot_read_r8d16(dpot, (reg & 0xF8) | @@ -198,7 +242,7 @@ static s32 dpot_write_spi(struct dpot_data *dpot, u8 reg, u16 value) { unsigned val = 0; - if (!(reg & (DPOT_ADDR_EEPROM | DPOT_ADDR_CMD))) { + if (!(reg & (DPOT_ADDR_EEPROM | DPOT_ADDR_CMD | DPOT_ADDR_OTP))) { if (dpot->feat & F_RDACS_WONLY) dpot->rdac_cache[reg & DPOT_RDAC_MASK] = value; @@ -219,11 +263,30 @@ static s32 dpot_write_spi(struct dpot_data *dpot, u8 reg, u16 value) } else { if (dpot->uid == DPOT_UID(AD5291_ID) || dpot->uid == DPOT_UID(AD5292_ID) || - dpot->uid == DPOT_UID(AD5293_ID)) + dpot->uid == DPOT_UID(AD5293_ID)) { + + dpot_write_r8d8(dpot, DPOT_AD5291_CTRLREG << 2, + DPOT_AD5291_UNLOCK_CMD); + + if (dpot->uid == DPOT_UID(AD5291_ID)) + value = value << 2; + return dpot_write_r8d8(dpot, (DPOT_AD5291_RDAC << 2) | (value >> 8), value & 0xFF); + } else if (dpot->uid == DPOT_UID(AD5270_ID) || + dpot->uid == DPOT_UID(AD5271_ID)) { + dpot_write_r8d8(dpot, + DPOT_AD5270_1_2_4_CTRLREG << 2, + DPOT_AD5270_1_2_4_UNLOCK_CMD); + if (dpot->uid == DPOT_UID(AD5271_ID)) + value = value << 2; + + return dpot_write_r8d8(dpot, + (DPOT_AD5270_1_2_4_RDAC << 2) | + (value >> 8), value & 0xFF); + } val = DPOT_SPI_RDAC | (reg & DPOT_RDAC_MASK); } } else if (reg & DPOT_ADDR_EEPROM) { @@ -243,6 +306,16 @@ static s32 dpot_write_spi(struct dpot_data *dpot, u8 reg, u16 value) val = DPOT_SPI_INC_ALL; break; } + } else if (reg & DPOT_ADDR_OTP) { + if (dpot->uid == DPOT_UID(AD5291_ID) || + dpot->uid == DPOT_UID(AD5292_ID)) { + return dpot_write_r8d8(dpot, + DPOT_AD5291_STORE_XTPM << 2, 0); + } else if (dpot->uid == DPOT_UID(AD5270_ID) || + dpot->uid == DPOT_UID(AD5271_ID)) { + return dpot_write_r8d8(dpot, + DPOT_AD5270_1_2_4_STORE_XTPM << 2, 0); + } } else BUG(); @@ -273,7 +346,7 @@ static s32 dpot_write_i2c(struct dpot_data *dpot, u8 reg, u16 value) case DPOT_UID(AD5280_ID): case DPOT_UID(AD5282_ID): ctrl = ((reg & DPOT_RDAC_MASK) == DPOT_RDAC0) ? - 0 : DPOT_AD5291_RDAC_AB; + 0 : DPOT_AD5282_RDAC_AB; return dpot_write_r8d8(dpot, ctrl, value); break; case DPOT_UID(AD5171_ID): @@ -289,12 +362,12 @@ static s32 dpot_write_i2c(struct dpot_data *dpot, u8 reg, u16 value) case DPOT_UID(AD5172_ID): case DPOT_UID(AD5173_ID): ctrl = ((reg & DPOT_RDAC_MASK) == DPOT_RDAC0) ? - 0 : DPOT_AD5272_3_A0; + 0 : DPOT_AD5172_3_A0; if (reg & DPOT_ADDR_OTP) { tmp = dpot_read_r8d16(dpot, ctrl); if (tmp >> 14) /* Ready to Program? */ return -EFAULT; - ctrl |= DPOT_AD5270_2_3_FUSE; + ctrl |= DPOT_AD5170_2_3_FUSE; } return dpot_write_r8d8(dpot, ctrl, value); break; @@ -303,10 +376,25 @@ static s32 dpot_write_i2c(struct dpot_data *dpot, u8 reg, u16 value) tmp = dpot_read_r8d16(dpot, tmp); if (tmp >> 14) /* Ready to Program? */ return -EFAULT; - ctrl = DPOT_AD5270_2_3_FUSE; + ctrl = DPOT_AD5170_2_3_FUSE; } return dpot_write_r8d8(dpot, ctrl, value); break; + case DPOT_UID(AD5272_ID): + case DPOT_UID(AD5274_ID): + dpot_write_r8d8(dpot, DPOT_AD5270_1_2_4_CTRLREG << 2, + DPOT_AD5270_1_2_4_UNLOCK_CMD); + + if (reg & DPOT_ADDR_OTP) + return dpot_write_r8d8(dpot, + DPOT_AD5270_1_2_4_STORE_XTPM << 2, 0); + + if (dpot->uid == DPOT_UID(AD5274_ID)) + value = value << 2; + + return dpot_write_r8d8(dpot, (DPOT_AD5270_1_2_4_RDAC << 2) | + (value >> 8), value & 0xFF); + break; default: if (reg & DPOT_ADDR_CMD) return dpot_write_d8(dpot, reg); @@ -320,7 +408,6 @@ static s32 dpot_write_i2c(struct dpot_data *dpot, u8 reg, u16 value) } } - static s32 dpot_write(struct dpot_data *dpot, u8 reg, u16 value) { if (dpot->feat & F_SPI) diff --git a/drivers/misc/ad525x_dpot.h b/drivers/misc/ad525x_dpot.h index 78b89fd2e2fd..a662f5987b68 100644 --- a/drivers/misc/ad525x_dpot.h +++ b/drivers/misc/ad525x_dpot.h @@ -47,9 +47,9 @@ enum dpot_devid { AD5258_ID = DPOT_CONF(F_RDACS_RW_TOL, BRDAC0, 6, 0), /* I2C */ AD5259_ID = DPOT_CONF(F_RDACS_RW_TOL, BRDAC0, 8, 1), AD5251_ID = DPOT_CONF(F_RDACS_RW_TOL | F_CMD_INC, - BRDAC0 | BRDAC3, 6, 2), + BRDAC1 | BRDAC3, 6, 2), AD5252_ID = DPOT_CONF(F_RDACS_RW_TOL | F_CMD_INC, - BRDAC0 | BRDAC3, 8, 3), + BRDAC1 | BRDAC3, 8, 3), AD5253_ID = DPOT_CONF(F_RDACS_RW_TOL | F_CMD_INC, BRDAC0 | BRDAC1 | BRDAC2 | BRDAC3, 6, 4), AD5254_ID = DPOT_CONF(F_RDACS_RW_TOL | F_CMD_INC, @@ -93,8 +93,10 @@ enum dpot_devid { BRDAC0 | BRDAC1 | BRDAC2 | BRDAC3, 8, 23), AD5290_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_8BIT, BRDAC0, 8, 24), - AD5291_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT, BRDAC0, 8, 25), - AD5292_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT, BRDAC0, 10, 26), + AD5291_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT | F_CMD_OTP, + BRDAC0, 8, 25), + AD5292_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT | F_CMD_OTP, + BRDAC0, 10, 26), AD5293_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT, BRDAC0, 10, 27), AD7376_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_8BIT, BRDAC0, 7, 28), @@ -122,6 +124,12 @@ enum dpot_devid { AD5170_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP, BRDAC0, 8, 45), AD5172_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP, BRDAC0 | BRDAC1, 8, 46), AD5173_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP, BRDAC0 | BRDAC1, 8, 47), + AD5270_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP | F_SPI_16BIT, + BRDAC0, 10, 48), + AD5271_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP | F_SPI_16BIT, + BRDAC0, 8, 49), + AD5272_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP, BRDAC0, 10, 50), + AD5274_ID = DPOT_CONF(F_RDACS_RW | F_CMD_OTP, BRDAC0, 8, 51), }; #define DPOT_RDAC0 0 @@ -165,15 +173,24 @@ enum dpot_devid { /* AD5291/2/3 use special commands */ #define DPOT_AD5291_RDAC 0x01 #define DPOT_AD5291_READ_RDAC 0x02 +#define DPOT_AD5291_STORE_XTPM 0x03 +#define DPOT_AD5291_CTRLREG 0x06 +#define DPOT_AD5291_UNLOCK_CMD 0x03 -/* AD524x use special commands */ -#define DPOT_AD5291_RDAC_AB 0x80 +/* AD5270/1/2/4 use special commands */ +#define DPOT_AD5270_1_2_4_RDAC 0x01 +#define DPOT_AD5270_1_2_4_READ_RDAC 0x02 +#define DPOT_AD5270_1_2_4_STORE_XTPM 0x03 +#define DPOT_AD5270_1_2_4_CTRLREG 0x07 +#define DPOT_AD5270_1_2_4_UNLOCK_CMD 0x03 + +#define DPOT_AD5282_RDAC_AB 0x80 #define DPOT_AD5273_FUSE 0x80 -#define DPOT_AD5270_2_3_FUSE 0x20 -#define DPOT_AD5270_2_3_OW 0x08 -#define DPOT_AD5272_3_A0 0x08 -#define DPOT_AD5270_2FUSE 0x80 +#define DPOT_AD5170_2_3_FUSE 0x20 +#define DPOT_AD5170_2_3_OW 0x08 +#define DPOT_AD5172_3_A0 0x08 +#define DPOT_AD5170_2FUSE 0x80 struct dpot_data; diff --git a/drivers/misc/apds9802als.c b/drivers/misc/apds9802als.c new file mode 100644 index 000000000000..f9b91ba8900c --- /dev/null +++ b/drivers/misc/apds9802als.c @@ -0,0 +1,347 @@ +/* + * apds9802als.c - apds9802 ALS Driver + * + * Copyright (C) 2009 Intel Corp + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * 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; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ALS_MIN_RANGE_VAL 1 +#define ALS_MAX_RANGE_VAL 2 +#define POWER_STA_ENABLE 1 +#define POWER_STA_DISABLE 0 + +#define DRIVER_NAME "apds9802als" + +struct als_data { + struct mutex mutex; +}; + +static ssize_t als_sensing_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + int val; + + val = i2c_smbus_read_byte_data(client, 0x81); + if (val < 0) + return val; + if (val & 1) + return sprintf(buf, "4095\n"); + else + return sprintf(buf, "65535\n"); +} + +static int als_wait_for_data_ready(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + int ret; + int retry = 10; + + do { + msleep(30); + ret = i2c_smbus_read_byte_data(client, 0x86); + } while (!(ret & 0x80) && retry--); + + if (!retry) { + dev_warn(dev, "timeout waiting for data ready\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static ssize_t als_lux0_input_data_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct als_data *data = i2c_get_clientdata(client); + int ret_val; + int temp; + + /* Protect against parallel reads */ + pm_runtime_get_sync(dev); + mutex_lock(&data->mutex); + + /* clear EOC interrupt status */ + i2c_smbus_write_byte(client, 0x40); + /* start measurement */ + temp = i2c_smbus_read_byte_data(client, 0x81); + i2c_smbus_write_byte_data(client, 0x81, temp | 0x08); + + ret_val = als_wait_for_data_ready(dev); + if (ret_val < 0) + goto failed; + + temp = i2c_smbus_read_byte_data(client, 0x8C); /* LSB data */ + if (temp < 0) { + ret_val = temp; + goto failed; + } + ret_val = i2c_smbus_read_byte_data(client, 0x8D); /* MSB data */ + if (ret_val < 0) + goto failed; + + mutex_unlock(&data->mutex); + pm_runtime_put_sync(dev); + + temp = (ret_val << 8) | temp; + return sprintf(buf, "%d\n", temp); +failed: + mutex_unlock(&data->mutex); + pm_runtime_put_sync(dev); + return ret_val; +} + +static ssize_t als_sensing_range_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct i2c_client *client = to_i2c_client(dev); + struct als_data *data = i2c_get_clientdata(client); + unsigned int ret_val; + unsigned long val; + + if (strict_strtoul(buf, 10, &val)) + return -EINVAL; + + if (val < 4096) + val = 1; + else if (val < 65536) + val = 2; + else + return -ERANGE; + + pm_runtime_get_sync(dev); + + /* Make sure nobody else reads/modifies/writes 0x81 while we + are active */ + mutex_lock(&data->mutex); + + ret_val = i2c_smbus_read_byte_data(client, 0x81); + if (ret_val < 0) + goto fail; + + /* Reset the bits before setting them */ + ret_val = ret_val & 0xFA; + + if (val == 1) /* Setting detection range up to 4k LUX */ + ret_val = (ret_val | 0x01); + else /* Setting detection range up to 64k LUX*/ + ret_val = (ret_val | 0x00); + + ret_val = i2c_smbus_write_byte_data(client, 0x81, ret_val); + + if (ret_val >= 0) { + /* All OK */ + mutex_unlock(&data->mutex); + pm_runtime_put_sync(dev); + return count; + } +fail: + mutex_unlock(&data->mutex); + pm_runtime_put_sync(dev); + return ret_val; +} + +static int als_set_power_state(struct i2c_client *client, bool on_off) +{ + int ret_val; + struct als_data *data = i2c_get_clientdata(client); + + mutex_lock(&data->mutex); + ret_val = i2c_smbus_read_byte_data(client, 0x80); + if (ret_val < 0) + goto fail; + if (on_off) + ret_val = ret_val | 0x01; + else + ret_val = ret_val & 0xFE; + ret_val = i2c_smbus_write_byte_data(client, 0x80, ret_val); +fail: + mutex_unlock(&data->mutex); + return ret_val; +} + +static DEVICE_ATTR(lux0_sensor_range, S_IRUGO | S_IWUSR, + als_sensing_range_show, als_sensing_range_store); +static DEVICE_ATTR(lux0_input, S_IRUGO, als_lux0_input_data_show, NULL); + +static struct attribute *mid_att_als[] = { + &dev_attr_lux0_sensor_range.attr, + &dev_attr_lux0_input.attr, + NULL +}; + +static struct attribute_group m_als_gr = { + .name = "apds9802als", + .attrs = mid_att_als +}; + +static int als_set_default_config(struct i2c_client *client) +{ + int ret_val; + /* Write the command and then switch on */ + ret_val = i2c_smbus_write_byte_data(client, 0x80, 0x01); + if (ret_val < 0) { + dev_err(&client->dev, "failed default switch on write\n"); + return ret_val; + } + /* detection range: 1~64K Lux, maunal measurement */ + ret_val = i2c_smbus_write_byte_data(client, 0x81, 0x08); + if (ret_val < 0) + dev_err(&client->dev, "failed default LUX on write\n"); + + /* We always get 0 for the 1st measurement after system power on, + * so make sure it is finished before user asks for data. + */ + als_wait_for_data_ready(&client->dev); + + return ret_val; +} + +static int apds9802als_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + int res; + struct als_data *data; + + data = kzalloc(sizeof(struct als_data), GFP_KERNEL); + if (data == NULL) { + dev_err(&client->dev, "Memory allocation failed\n"); + return -ENOMEM; + } + i2c_set_clientdata(client, data); + res = sysfs_create_group(&client->dev.kobj, &m_als_gr); + if (res) { + dev_err(&client->dev, "device create file failed\n"); + goto als_error1; + } + dev_info(&client->dev, "ALS chip found\n"); + als_set_default_config(client); + mutex_init(&data->mutex); + + pm_runtime_enable(&client->dev); + pm_runtime_get(&client->dev); + pm_runtime_put(&client->dev); + + return res; +als_error1: + i2c_set_clientdata(client, NULL); + kfree(data); + return res; +} + +static int apds9802als_remove(struct i2c_client *client) +{ + struct als_data *data = i2c_get_clientdata(client); + + als_set_power_state(client, false); + sysfs_remove_group(&client->dev.kobj, &m_als_gr); + kfree(data); + return 0; +} + +#ifdef CONFIG_PM +static int apds9802als_suspend(struct i2c_client *client, pm_message_t mesg) +{ + als_set_power_state(client, false); + return 0; +} + +static int apds9802als_resume(struct i2c_client *client) +{ + als_set_default_config(client); + + pm_runtime_get(&client->dev); + pm_runtime_put(&client->dev); + return 0; +} + +static int apds9802als_runtime_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + + als_set_power_state(client, false); + return 0; +} + +static int apds9802als_runtime_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + + als_set_power_state(client, true); + return 0; +} + +static const struct dev_pm_ops apds9802als_pm_ops = { + .runtime_suspend = apds9802als_runtime_suspend, + .runtime_resume = apds9802als_runtime_resume, +}; + +#define APDS9802ALS_PM_OPS (&apds9802als_pm_ops) + +#else /* CONFIG_PM */ +#define apds9802als_suspend NULL +#define apds9802als_resume NULL +#define APDS9802ALS_PM_OPS NULL +#endif /* CONFIG_PM */ + +static struct i2c_device_id apds9802als_id[] = { + { DRIVER_NAME, 0 }, + { } +}; + +MODULE_DEVICE_TABLE(i2c, apds9802als_id); + +static struct i2c_driver apds9802als_driver = { + .driver = { + .name = DRIVER_NAME, + .pm = APDS9802ALS_PM_OPS, + }, + .probe = apds9802als_probe, + .remove = apds9802als_remove, + .suspend = apds9802als_suspend, + .resume = apds9802als_resume, + .id_table = apds9802als_id, +}; + +static int __init sensor_apds9802als_init(void) +{ + return i2c_add_driver(&apds9802als_driver); +} + +static void __exit sensor_apds9802als_exit(void) +{ + i2c_del_driver(&apds9802als_driver); +} +module_init(sensor_apds9802als_init); +module_exit(sensor_apds9802als_exit); + +MODULE_AUTHOR("Anantha Narayanan + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Register map */ +#define APDS990X_ENABLE 0x00 /* Enable of states and interrupts */ +#define APDS990X_ATIME 0x01 /* ALS ADC time */ +#define APDS990X_PTIME 0x02 /* Proximity ADC time */ +#define APDS990X_WTIME 0x03 /* Wait time */ +#define APDS990X_AILTL 0x04 /* ALS interrupt low threshold low byte */ +#define APDS990X_AILTH 0x05 /* ALS interrupt low threshold hi byte */ +#define APDS990X_AIHTL 0x06 /* ALS interrupt hi threshold low byte */ +#define APDS990X_AIHTH 0x07 /* ALS interrupt hi threshold hi byte */ +#define APDS990X_PILTL 0x08 /* Proximity interrupt low threshold low byte */ +#define APDS990X_PILTH 0x09 /* Proximity interrupt low threshold hi byte */ +#define APDS990X_PIHTL 0x0a /* Proximity interrupt hi threshold low byte */ +#define APDS990X_PIHTH 0x0b /* Proximity interrupt hi threshold hi byte */ +#define APDS990X_PERS 0x0c /* Interrupt persistence filters */ +#define APDS990X_CONFIG 0x0d /* Configuration */ +#define APDS990X_PPCOUNT 0x0e /* Proximity pulse count */ +#define APDS990X_CONTROL 0x0f /* Gain control register */ +#define APDS990X_REV 0x11 /* Revision Number */ +#define APDS990X_ID 0x12 /* Device ID */ +#define APDS990X_STATUS 0x13 /* Device status */ +#define APDS990X_CDATAL 0x14 /* Clear ADC low data register */ +#define APDS990X_CDATAH 0x15 /* Clear ADC high data register */ +#define APDS990X_IRDATAL 0x16 /* IR ADC low data register */ +#define APDS990X_IRDATAH 0x17 /* IR ADC high data register */ +#define APDS990X_PDATAL 0x18 /* Proximity ADC low data register */ +#define APDS990X_PDATAH 0x19 /* Proximity ADC high data register */ + +/* Control */ +#define APDS990X_MAX_AGAIN 3 + +/* Enable register */ +#define APDS990X_EN_PIEN (0x1 << 5) +#define APDS990X_EN_AIEN (0x1 << 4) +#define APDS990X_EN_WEN (0x1 << 3) +#define APDS990X_EN_PEN (0x1 << 2) +#define APDS990X_EN_AEN (0x1 << 1) +#define APDS990X_EN_PON (0x1 << 0) +#define APDS990X_EN_DISABLE_ALL 0 + +/* Status register */ +#define APDS990X_ST_PINT (0x1 << 5) +#define APDS990X_ST_AINT (0x1 << 4) + +/* I2C access types */ +#define APDS990x_CMD_TYPE_MASK (0x03 << 5) +#define APDS990x_CMD_TYPE_RB (0x00 << 5) /* Repeated byte */ +#define APDS990x_CMD_TYPE_INC (0x01 << 5) /* Auto increment */ +#define APDS990x_CMD_TYPE_SPE (0x03 << 5) /* Special function */ + +#define APDS990x_ADDR_SHIFT 0 +#define APDS990x_CMD 0x80 + +/* Interrupt ack commands */ +#define APDS990X_INT_ACK_ALS 0x6 +#define APDS990X_INT_ACK_PS 0x5 +#define APDS990X_INT_ACK_BOTH 0x7 + +/* ptime */ +#define APDS990X_PTIME_DEFAULT 0xff /* Recommended conversion time 2.7ms*/ + +/* wtime */ +#define APDS990X_WTIME_DEFAULT 0xee /* ~50ms wait time */ + +#define APDS990X_TIME_TO_ADC 1024 /* One timetick as ADC count value */ + +/* Persistence */ +#define APDS990X_APERS_SHIFT 0 +#define APDS990X_PPERS_SHIFT 4 + +/* Supported ID:s */ +#define APDS990X_ID_0 0x0 +#define APDS990X_ID_4 0x4 +#define APDS990X_ID_29 0x29 + +/* pgain and pdiode settings */ +#define APDS_PGAIN_1X 0x0 +#define APDS_PDIODE_IR 0x2 + +#define APDS990X_LUX_OUTPUT_SCALE 10 + +/* Reverse chip factors for threshold calculation */ +struct reverse_factors { + u32 afactor; + int cf1; + int irf1; + int cf2; + int irf2; +}; + +struct apds990x_chip { + struct apds990x_platform_data *pdata; + struct i2c_client *client; + struct mutex mutex; /* avoid parallel access */ + struct regulator_bulk_data regs[2]; + wait_queue_head_t wait; + + int prox_en; + bool prox_continuous_mode; + bool lux_wait_fresh_res; + + /* Chip parameters */ + struct apds990x_chip_factors cf; + struct reverse_factors rcf; + u16 atime; /* als integration time */ + u16 arate; /* als reporting rate */ + u16 a_max_result; /* Max possible ADC value with current atime */ + u8 again_meas; /* Gain used in last measurement */ + u8 again_next; /* Next calculated gain */ + u8 pgain; + u8 pdiode; + u8 pdrive; + u8 lux_persistence; + u8 prox_persistence; + + u32 lux_raw; + u32 lux; + u16 lux_clear; + u16 lux_ir; + u16 lux_calib; + u32 lux_thres_hi; + u32 lux_thres_lo; + + u32 prox_thres; + u16 prox_data; + u16 prox_calib; + + char chipname[10]; + u8 revision; +}; + +#define APDS_CALIB_SCALER 8192 +#define APDS_LUX_NEUTRAL_CALIB_VALUE (1 * APDS_CALIB_SCALER) +#define APDS_PROX_NEUTRAL_CALIB_VALUE (1 * APDS_CALIB_SCALER) + +#define APDS_PROX_DEF_THRES 600 +#define APDS_PROX_HYSTERESIS 50 +#define APDS_LUX_DEF_THRES_HI 101 +#define APDS_LUX_DEF_THRES_LO 100 +#define APDS_DEFAULT_PROX_PERS 1 + +#define APDS_TIMEOUT 2000 +#define APDS_STARTUP_DELAY 25000 /* us */ +#define APDS_RANGE 65535 +#define APDS_PROX_RANGE 1023 +#define APDS_LUX_GAIN_LO_LIMIT 100 +#define APDS_LUX_GAIN_LO_LIMIT_STRICT 25 + +#define TIMESTEP 87 /* 2.7ms is about 87 / 32 */ +#define TIME_STEP_SCALER 32 + +#define APDS_LUX_AVERAGING_TIME 50 /* tolerates 50/60Hz ripple */ +#define APDS_LUX_DEFAULT_RATE 200 + +static const u8 again[] = {1, 8, 16, 120}; /* ALS gain steps */ +static const u8 ir_currents[] = {100, 50, 25, 12}; /* IRled currents in mA */ + +/* Following two tables must match i.e 10Hz rate means 1 as persistence value */ +static const u16 arates_hz[] = {10, 5, 2, 1}; +static const u8 apersis[] = {1, 2, 4, 5}; + +/* Regulators */ +static const char reg_vcc[] = "Vdd"; +static const char reg_vled[] = "Vled"; + +static int apds990x_read_byte(struct apds990x_chip *chip, u8 reg, u8 *data) +{ + struct i2c_client *client = chip->client; + s32 ret; + + reg &= ~APDS990x_CMD_TYPE_MASK; + reg |= APDS990x_CMD | APDS990x_CMD_TYPE_RB; + + ret = i2c_smbus_read_byte_data(client, reg); + *data = ret; + return (int)ret; +} + +static int apds990x_read_word(struct apds990x_chip *chip, u8 reg, u16 *data) +{ + struct i2c_client *client = chip->client; + s32 ret; + + reg &= ~APDS990x_CMD_TYPE_MASK; + reg |= APDS990x_CMD | APDS990x_CMD_TYPE_INC; + + ret = i2c_smbus_read_word_data(client, reg); + *data = ret; + return (int)ret; +} + +static int apds990x_write_byte(struct apds990x_chip *chip, u8 reg, u8 data) +{ + struct i2c_client *client = chip->client; + s32 ret; + + reg &= ~APDS990x_CMD_TYPE_MASK; + reg |= APDS990x_CMD | APDS990x_CMD_TYPE_RB; + + ret = i2c_smbus_write_byte_data(client, reg, data); + return (int)ret; +} + +static int apds990x_write_word(struct apds990x_chip *chip, u8 reg, u16 data) +{ + struct i2c_client *client = chip->client; + s32 ret; + + reg &= ~APDS990x_CMD_TYPE_MASK; + reg |= APDS990x_CMD | APDS990x_CMD_TYPE_INC; + + ret = i2c_smbus_write_word_data(client, reg, data); + return (int)ret; +} + +static int apds990x_mode_on(struct apds990x_chip *chip) +{ + /* ALS is mandatory, proximity optional */ + u8 reg = APDS990X_EN_AIEN | APDS990X_EN_PON | APDS990X_EN_AEN | + APDS990X_EN_WEN; + + if (chip->prox_en) + reg |= APDS990X_EN_PIEN | APDS990X_EN_PEN; + + return apds990x_write_byte(chip, APDS990X_ENABLE, reg); +} + +static u16 apds990x_lux_to_threshold(struct apds990x_chip *chip, u32 lux) +{ + u32 thres; + u32 cpl; + u32 ir; + + if (lux == 0) + return 0; + else if (lux == APDS_RANGE) + return APDS_RANGE; + + /* + * Reported LUX value is a combination of the IR and CLEAR channel + * values. However, interrupt threshold is only for clear channel. + * This function approximates needed HW threshold value for a given + * LUX value in the current lightning type. + * IR level compared to visible light varies heavily depending on the + * source of the light + * + * Calculate threshold value for the next measurement period. + * Math: threshold = lux * cpl where + * cpl = atime * again / (glass_attenuation * device_factor) + * (count-per-lux) + * + * First remove calibration. Division by four is to avoid overflow + */ + lux = lux * (APDS_CALIB_SCALER / 4) / (chip->lux_calib / 4); + + /* Multiplication by 64 is to increase accuracy */ + cpl = ((u32)chip->atime * (u32)again[chip->again_next] * + APDS_PARAM_SCALE * 64) / (chip->cf.ga * chip->cf.df); + + thres = lux * cpl / 64; + /* + * Convert IR light from the latest result to match with + * new gain step. This helps to adapt with the current + * source of light. + */ + ir = (u32)chip->lux_ir * (u32)again[chip->again_next] / + (u32)again[chip->again_meas]; + + /* + * Compensate count with IR light impact + * IAC1 > IAC2 (see apds990x_get_lux for formulas) + */ + if (chip->lux_clear * APDS_PARAM_SCALE >= + chip->rcf.afactor * chip->lux_ir) + thres = (chip->rcf.cf1 * thres + chip->rcf.irf1 * ir) / + APDS_PARAM_SCALE; + else + thres = (chip->rcf.cf2 * thres + chip->rcf.irf2 * ir) / + APDS_PARAM_SCALE; + + if (thres >= chip->a_max_result) + thres = chip->a_max_result - 1; + return thres; +} + +static inline int apds990x_set_atime(struct apds990x_chip *chip, u32 time_ms) +{ + u8 reg_value; + + chip->atime = time_ms; + /* Formula is specified in the data sheet */ + reg_value = 256 - ((time_ms * TIME_STEP_SCALER) / TIMESTEP); + /* Calculate max ADC value for given integration time */ + chip->a_max_result = (u16)(256 - reg_value) * APDS990X_TIME_TO_ADC; + return apds990x_write_byte(chip, APDS990X_ATIME, reg_value); +} + +/* Called always with mutex locked */ +static int apds990x_refresh_pthres(struct apds990x_chip *chip, int data) +{ + int ret, lo, hi; + + /* If the chip is not in use, don't try to access it */ + if (pm_runtime_suspended(&chip->client->dev)) + return 0; + + if (data < chip->prox_thres) { + lo = 0; + hi = chip->prox_thres; + } else { + lo = chip->prox_thres - APDS_PROX_HYSTERESIS; + if (chip->prox_continuous_mode) + hi = chip->prox_thres; + else + hi = APDS_RANGE; + } + + ret = apds990x_write_word(chip, APDS990X_PILTL, lo); + ret |= apds990x_write_word(chip, APDS990X_PIHTL, hi); + return ret; +} + +/* Called always with mutex locked */ +static int apds990x_refresh_athres(struct apds990x_chip *chip) +{ + int ret; + /* If the chip is not in use, don't try to access it */ + if (pm_runtime_suspended(&chip->client->dev)) + return 0; + + ret = apds990x_write_word(chip, APDS990X_AILTL, + apds990x_lux_to_threshold(chip, chip->lux_thres_lo)); + ret |= apds990x_write_word(chip, APDS990X_AIHTL, + apds990x_lux_to_threshold(chip, chip->lux_thres_hi)); + + return ret; +} + +/* Called always with mutex locked */ +static void apds990x_force_a_refresh(struct apds990x_chip *chip) +{ + /* This will force ALS interrupt after the next measurement. */ + apds990x_write_word(chip, APDS990X_AILTL, APDS_LUX_DEF_THRES_LO); + apds990x_write_word(chip, APDS990X_AIHTL, APDS_LUX_DEF_THRES_HI); +} + +/* Called always with mutex locked */ +static void apds990x_force_p_refresh(struct apds990x_chip *chip) +{ + /* This will force proximity interrupt after the next measurement. */ + apds990x_write_word(chip, APDS990X_PILTL, APDS_PROX_DEF_THRES - 1); + apds990x_write_word(chip, APDS990X_PIHTL, APDS_PROX_DEF_THRES); +} + +/* Called always with mutex locked */ +static int apds990x_calc_again(struct apds990x_chip *chip) +{ + int curr_again = chip->again_meas; + int next_again = chip->again_meas; + int ret = 0; + + /* Calculate suitable als gain */ + if (chip->lux_clear == chip->a_max_result) + next_again -= 2; /* ALS saturated. Decrease gain by 2 steps */ + else if (chip->lux_clear > chip->a_max_result / 2) + next_again--; + else if (chip->lux_clear < APDS_LUX_GAIN_LO_LIMIT_STRICT) + next_again += 2; /* Too dark. Increase gain by 2 steps */ + else if (chip->lux_clear < APDS_LUX_GAIN_LO_LIMIT) + next_again++; + + /* Limit gain to available range */ + if (next_again < 0) + next_again = 0; + else if (next_again > APDS990X_MAX_AGAIN) + next_again = APDS990X_MAX_AGAIN; + + /* Let's check can we trust the measured result */ + if (chip->lux_clear == chip->a_max_result) + /* Result can be totally garbage due to saturation */ + ret = -ERANGE; + else if (next_again != curr_again && + chip->lux_clear < APDS_LUX_GAIN_LO_LIMIT_STRICT) + /* + * Gain is changed and measurement result is very small. + * Result can be totally garbage due to underflow + */ + ret = -ERANGE; + + chip->again_next = next_again; + apds990x_write_byte(chip, APDS990X_CONTROL, + (chip->pdrive << 6) | + (chip->pdiode << 4) | + (chip->pgain << 2) | + (chip->again_next << 0)); + + /* + * Error means bad result -> re-measurement is needed. The forced + * refresh uses fastest possible persistence setting to get result + * as soon as possible. + */ + if (ret < 0) + apds990x_force_a_refresh(chip); + else + apds990x_refresh_athres(chip); + + return ret; +} + +/* Called always with mutex locked */ +static int apds990x_get_lux(struct apds990x_chip *chip, int clear, int ir) +{ + int iac, iac1, iac2; /* IR adjusted counts */ + u32 lpc; /* Lux per count */ + + /* Formulas: + * iac1 = CF1 * CLEAR_CH - IRF1 * IR_CH + * iac2 = CF2 * CLEAR_CH - IRF2 * IR_CH + */ + iac1 = (chip->cf.cf1 * clear - chip->cf.irf1 * ir) / APDS_PARAM_SCALE; + iac2 = (chip->cf.cf2 * clear - chip->cf.irf2 * ir) / APDS_PARAM_SCALE; + + iac = max(iac1, iac2); + iac = max(iac, 0); + + lpc = APDS990X_LUX_OUTPUT_SCALE * (chip->cf.df * chip->cf.ga) / + (u32)(again[chip->again_meas] * (u32)chip->atime); + + return (iac * lpc) / APDS_PARAM_SCALE; +} + +static int apds990x_ack_int(struct apds990x_chip *chip, u8 mode) +{ + struct i2c_client *client = chip->client; + s32 ret; + u8 reg = APDS990x_CMD | APDS990x_CMD_TYPE_SPE; + + switch (mode & (APDS990X_ST_AINT | APDS990X_ST_PINT)) { + case APDS990X_ST_AINT: + reg |= APDS990X_INT_ACK_ALS; + break; + case APDS990X_ST_PINT: + reg |= APDS990X_INT_ACK_PS; + break; + default: + reg |= APDS990X_INT_ACK_BOTH; + break; + } + + ret = i2c_smbus_read_byte_data(client, reg); + return (int)ret; +} + +static irqreturn_t apds990x_irq(int irq, void *data) +{ + struct apds990x_chip *chip = data; + u8 status; + + apds990x_read_byte(chip, APDS990X_STATUS, &status); + apds990x_ack_int(chip, status); + + mutex_lock(&chip->mutex); + if (!pm_runtime_suspended(&chip->client->dev)) { + if (status & APDS990X_ST_AINT) { + apds990x_read_word(chip, APDS990X_CDATAL, + &chip->lux_clear); + apds990x_read_word(chip, APDS990X_IRDATAL, + &chip->lux_ir); + /* Store used gain for calculations */ + chip->again_meas = chip->again_next; + + chip->lux_raw = apds990x_get_lux(chip, + chip->lux_clear, + chip->lux_ir); + + if (apds990x_calc_again(chip) == 0) { + /* Result is valid */ + chip->lux = chip->lux_raw; + chip->lux_wait_fresh_res = false; + wake_up(&chip->wait); + sysfs_notify(&chip->client->dev.kobj, + NULL, "lux0_input"); + } + } + + if ((status & APDS990X_ST_PINT) && chip->prox_en) { + u16 clr_ch; + + apds990x_read_word(chip, APDS990X_CDATAL, &clr_ch); + /* + * If ALS channel is saturated at min gain, + * proximity gives false posivite values. + * Just ignore them. + */ + if (chip->again_meas == 0 && + clr_ch == chip->a_max_result) + chip->prox_data = 0; + else + apds990x_read_word(chip, + APDS990X_PDATAL, + &chip->prox_data); + + apds990x_refresh_pthres(chip, chip->prox_data); + if (chip->prox_data < chip->prox_thres) + chip->prox_data = 0; + else if (!chip->prox_continuous_mode) + chip->prox_data = APDS_PROX_RANGE; + sysfs_notify(&chip->client->dev.kobj, + NULL, "prox0_raw"); + } + } + mutex_unlock(&chip->mutex); + return IRQ_HANDLED; +} + +static int apds990x_configure(struct apds990x_chip *chip) +{ + /* It is recommended to use disabled mode during these operations */ + apds990x_write_byte(chip, APDS990X_ENABLE, APDS990X_EN_DISABLE_ALL); + + /* conversion and wait times for different state machince states */ + apds990x_write_byte(chip, APDS990X_PTIME, APDS990X_PTIME_DEFAULT); + apds990x_write_byte(chip, APDS990X_WTIME, APDS990X_WTIME_DEFAULT); + apds990x_set_atime(chip, APDS_LUX_AVERAGING_TIME); + + apds990x_write_byte(chip, APDS990X_CONFIG, 0); + + /* Persistence levels */ + apds990x_write_byte(chip, APDS990X_PERS, + (chip->lux_persistence << APDS990X_APERS_SHIFT) | + (chip->prox_persistence << APDS990X_PPERS_SHIFT)); + + apds990x_write_byte(chip, APDS990X_PPCOUNT, chip->pdata->ppcount); + + /* Start with relatively small gain */ + chip->again_meas = 1; + chip->again_next = 1; + apds990x_write_byte(chip, APDS990X_CONTROL, + (chip->pdrive << 6) | + (chip->pdiode << 4) | + (chip->pgain << 2) | + (chip->again_next << 0)); + return 0; +} + +static int apds990x_detect(struct apds990x_chip *chip) +{ + struct i2c_client *client = chip->client; + int ret; + u8 id; + + ret = apds990x_read_byte(chip, APDS990X_ID, &id); + if (ret < 0) { + dev_err(&client->dev, "ID read failed\n"); + return ret; + } + + ret = apds990x_read_byte(chip, APDS990X_REV, &chip->revision); + if (ret < 0) { + dev_err(&client->dev, "REV read failed\n"); + return ret; + } + + switch (id) { + case APDS990X_ID_0: + case APDS990X_ID_4: + case APDS990X_ID_29: + snprintf(chip->chipname, sizeof(chip->chipname), "APDS-990x"); + break; + default: + ret = -ENODEV; + break; + } + return ret; +} + +static int apds990x_chip_on(struct apds990x_chip *chip) +{ + int err = regulator_bulk_enable(ARRAY_SIZE(chip->regs), + chip->regs); + if (err < 0) + return err; + + usleep_range(APDS_STARTUP_DELAY, 2 * APDS_STARTUP_DELAY); + + /* Refresh all configs in case of regulators were off */ + chip->prox_data = 0; + apds990x_configure(chip); + apds990x_mode_on(chip); + return 0; +} + +static int apds990x_chip_off(struct apds990x_chip *chip) +{ + apds990x_write_byte(chip, APDS990X_ENABLE, APDS990X_EN_DISABLE_ALL); + regulator_bulk_disable(ARRAY_SIZE(chip->regs), chip->regs); + return 0; +} + +static ssize_t apds990x_lux_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + ssize_t ret; + u32 result; + long timeout; + + if (pm_runtime_suspended(dev)) + return -EIO; + + timeout = wait_event_interruptible_timeout(chip->wait, + !chip->lux_wait_fresh_res, + msecs_to_jiffies(APDS_TIMEOUT)); + if (!timeout) + return -EIO; + + mutex_lock(&chip->mutex); + result = (chip->lux * chip->lux_calib) / APDS_CALIB_SCALER; + if (result > (APDS_RANGE * APDS990X_LUX_OUTPUT_SCALE)) + result = APDS_RANGE * APDS990X_LUX_OUTPUT_SCALE; + + ret = sprintf(buf, "%d.%d\n", + result / APDS990X_LUX_OUTPUT_SCALE, + result % APDS990X_LUX_OUTPUT_SCALE); + mutex_unlock(&chip->mutex); + return ret; +} + +static DEVICE_ATTR(lux0_input, S_IRUGO, apds990x_lux_show, NULL); + +static ssize_t apds990x_lux_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", APDS_RANGE); +} + +static DEVICE_ATTR(lux0_sensor_range, S_IRUGO, apds990x_lux_range_show, NULL); + +static ssize_t apds990x_lux_calib_format_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", APDS_CALIB_SCALER); +} + +static DEVICE_ATTR(lux0_calibscale_default, S_IRUGO, + apds990x_lux_calib_format_show, NULL); + +static ssize_t apds990x_lux_calib_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", chip->lux_calib); +} + +static ssize_t apds990x_lux_calib_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + if (chip->lux_calib > APDS_RANGE) + return -EINVAL; + + chip->lux_calib = value; + + return len; +} + +static DEVICE_ATTR(lux0_calibscale, S_IRUGO | S_IWUSR, apds990x_lux_calib_show, + apds990x_lux_calib_store); + +static ssize_t apds990x_rate_avail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int i; + int pos = 0; + for (i = 0; i < ARRAY_SIZE(arates_hz); i++) + pos += sprintf(buf + pos, "%d ", arates_hz[i]); + sprintf(buf + pos - 1, "\n"); + return pos; +} + +static ssize_t apds990x_rate_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->arate); +} + +static int apds990x_set_arate(struct apds990x_chip *chip, int rate) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(arates_hz); i++) + if (rate >= arates_hz[i]) + break; + + if (i == ARRAY_SIZE(arates_hz)) + return -EINVAL; + + /* Pick up corresponding persistence value */ + chip->lux_persistence = apersis[i]; + chip->arate = arates_hz[i]; + + /* If the chip is not in use, don't try to access it */ + if (pm_runtime_suspended(&chip->client->dev)) + return 0; + + /* Persistence levels */ + return apds990x_write_byte(chip, APDS990X_PERS, + (chip->lux_persistence << APDS990X_APERS_SHIFT) | + (chip->prox_persistence << APDS990X_PPERS_SHIFT)); +} + +static ssize_t apds990x_rate_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + unsigned long value; + int ret; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + ret = apds990x_set_arate(chip, value); + mutex_unlock(&chip->mutex); + + if (ret < 0) + return ret; + return len; +} + +static DEVICE_ATTR(lux0_rate_avail, S_IRUGO, apds990x_rate_avail, NULL); + +static DEVICE_ATTR(lux0_rate, S_IRUGO | S_IWUSR, apds990x_rate_show, + apds990x_rate_store); + +static ssize_t apds990x_prox_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t ret; + struct apds990x_chip *chip = dev_get_drvdata(dev); + if (pm_runtime_suspended(dev) || !chip->prox_en) + return -EIO; + + mutex_lock(&chip->mutex); + ret = sprintf(buf, "%d\n", chip->prox_data); + mutex_unlock(&chip->mutex); + return ret; +} + +static DEVICE_ATTR(prox0_raw, S_IRUGO, apds990x_prox_show, NULL); + +static ssize_t apds990x_prox_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", APDS_PROX_RANGE); +} + +static DEVICE_ATTR(prox0_sensor_range, S_IRUGO, apds990x_prox_range_show, NULL); + +static ssize_t apds990x_prox_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->prox_en); +} + +static ssize_t apds990x_prox_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + + if (!chip->prox_en) + chip->prox_data = 0; + + if (value) + chip->prox_en++; + else if (chip->prox_en > 0) + chip->prox_en--; + + if (!pm_runtime_suspended(dev)) + apds990x_mode_on(chip); + mutex_unlock(&chip->mutex); + return len; +} + +static DEVICE_ATTR(prox0_raw_en, S_IRUGO | S_IWUSR, apds990x_prox_enable_show, + apds990x_prox_enable_store); + +static const char reporting_modes[][9] = {"trigger", "periodic"}; + +static ssize_t apds990x_prox_reporting_mode_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%s\n", + reporting_modes[!!chip->prox_continuous_mode]); +} + +static ssize_t apds990x_prox_reporting_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + + if (sysfs_streq(buf, reporting_modes[0])) + chip->prox_continuous_mode = 0; + else if (sysfs_streq(buf, reporting_modes[1])) + chip->prox_continuous_mode = 1; + else + return -EINVAL; + return len; +} + +static DEVICE_ATTR(prox0_reporting_mode, S_IRUGO | S_IWUSR, + apds990x_prox_reporting_mode_show, + apds990x_prox_reporting_mode_store); + +static ssize_t apds990x_prox_reporting_avail_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%s %s\n", reporting_modes[0], reporting_modes[1]); +} + +static DEVICE_ATTR(prox0_reporting_mode_avail, S_IRUGO | S_IWUSR, + apds990x_prox_reporting_avail_show, NULL); + + +static ssize_t apds990x_lux_thresh_above_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->lux_thres_hi); +} + +static ssize_t apds990x_lux_thresh_below_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->lux_thres_lo); +} + +static ssize_t apds990x_set_lux_thresh(struct apds990x_chip *chip, u32 *target, + const char *buf) +{ + int ret = 0; + unsigned long thresh; + + if (strict_strtoul(buf, 0, &thresh)) + return -EINVAL; + + if (thresh > APDS_RANGE) + return -EINVAL; + + mutex_lock(&chip->mutex); + *target = thresh; + /* + * Don't update values in HW if we are still waiting for + * first interrupt to come after device handle open call. + */ + if (!chip->lux_wait_fresh_res) + apds990x_refresh_athres(chip); + mutex_unlock(&chip->mutex); + return ret; + +} + +static ssize_t apds990x_lux_thresh_above_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + int ret = apds990x_set_lux_thresh(chip, &chip->lux_thres_hi, buf); + if (ret < 0) + return ret; + return len; +} + +static ssize_t apds990x_lux_thresh_below_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + int ret = apds990x_set_lux_thresh(chip, &chip->lux_thres_lo, buf); + if (ret < 0) + return ret; + return len; +} + +static DEVICE_ATTR(lux0_thresh_above_value, S_IRUGO | S_IWUSR, + apds990x_lux_thresh_above_show, + apds990x_lux_thresh_above_store); + +static DEVICE_ATTR(lux0_thresh_below_value, S_IRUGO | S_IWUSR, + apds990x_lux_thresh_below_show, + apds990x_lux_thresh_below_store); + +static ssize_t apds990x_prox_threshold_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->prox_thres); +} + +static ssize_t apds990x_prox_threshold_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + if ((value > APDS_RANGE) || (value == 0) || + (value < APDS_PROX_HYSTERESIS)) + return -EINVAL; + + mutex_lock(&chip->mutex); + chip->prox_thres = value; + + apds990x_force_p_refresh(chip); + mutex_unlock(&chip->mutex); + return len; +} + +static DEVICE_ATTR(prox0_thresh_above_value, S_IRUGO | S_IWUSR, + apds990x_prox_threshold_show, + apds990x_prox_threshold_store); + +static ssize_t apds990x_power_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", !pm_runtime_suspended(dev)); + return 0; +} + +static ssize_t apds990x_power_state_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + if (value) { + pm_runtime_get_sync(dev); + mutex_lock(&chip->mutex); + chip->lux_wait_fresh_res = true; + apds990x_force_a_refresh(chip); + apds990x_force_p_refresh(chip); + mutex_unlock(&chip->mutex); + } else { + if (!pm_runtime_suspended(dev)) + pm_runtime_put(dev); + } + return len; +} + +static DEVICE_ATTR(power_state, S_IRUGO | S_IWUSR, + apds990x_power_state_show, + apds990x_power_state_store); + +static ssize_t apds990x_chip_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct apds990x_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%s %d\n", chip->chipname, chip->revision); +} + +static DEVICE_ATTR(chip_id, S_IRUGO, apds990x_chip_id_show, NULL); + +static struct attribute *sysfs_attrs_ctrl[] = { + &dev_attr_lux0_calibscale.attr, + &dev_attr_lux0_calibscale_default.attr, + &dev_attr_lux0_input.attr, + &dev_attr_lux0_sensor_range.attr, + &dev_attr_lux0_rate.attr, + &dev_attr_lux0_rate_avail.attr, + &dev_attr_lux0_thresh_above_value.attr, + &dev_attr_lux0_thresh_below_value.attr, + &dev_attr_prox0_raw_en.attr, + &dev_attr_prox0_raw.attr, + &dev_attr_prox0_sensor_range.attr, + &dev_attr_prox0_thresh_above_value.attr, + &dev_attr_prox0_reporting_mode.attr, + &dev_attr_prox0_reporting_mode_avail.attr, + &dev_attr_chip_id.attr, + &dev_attr_power_state.attr, + NULL +}; + +static struct attribute_group apds990x_attribute_group[] = { + {.attrs = sysfs_attrs_ctrl }, +}; + +static int __devinit apds990x_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct apds990x_chip *chip; + int err; + + chip = kzalloc(sizeof *chip, GFP_KERNEL); + if (!chip) + return -ENOMEM; + + i2c_set_clientdata(client, chip); + chip->client = client; + + init_waitqueue_head(&chip->wait); + mutex_init(&chip->mutex); + chip->pdata = client->dev.platform_data; + + if (chip->pdata == NULL) { + dev_err(&client->dev, "platform data is mandatory\n"); + err = -EINVAL; + goto fail1; + } + + if (chip->pdata->cf.ga == 0) { + /* set uncovered sensor default parameters */ + chip->cf.ga = 1966; /* 0.48 * APDS_PARAM_SCALE */ + chip->cf.cf1 = 4096; /* 1.00 * APDS_PARAM_SCALE */ + chip->cf.irf1 = 9134; /* 2.23 * APDS_PARAM_SCALE */ + chip->cf.cf2 = 2867; /* 0.70 * APDS_PARAM_SCALE */ + chip->cf.irf2 = 5816; /* 1.42 * APDS_PARAM_SCALE */ + chip->cf.df = 52; + } else { + chip->cf = chip->pdata->cf; + } + + /* precalculate inverse chip factors for threshold control */ + chip->rcf.afactor = + (chip->cf.irf1 - chip->cf.irf2) * APDS_PARAM_SCALE / + (chip->cf.cf1 - chip->cf.cf2); + chip->rcf.cf1 = APDS_PARAM_SCALE * APDS_PARAM_SCALE / + chip->cf.cf1; + chip->rcf.irf1 = chip->cf.irf1 * APDS_PARAM_SCALE / + chip->cf.cf1; + chip->rcf.cf2 = APDS_PARAM_SCALE * APDS_PARAM_SCALE / + chip->cf.cf2; + chip->rcf.irf2 = chip->cf.irf2 * APDS_PARAM_SCALE / + chip->cf.cf2; + + /* Set something to start with */ + chip->lux_thres_hi = APDS_LUX_DEF_THRES_HI; + chip->lux_thres_lo = APDS_LUX_DEF_THRES_LO; + chip->lux_calib = APDS_LUX_NEUTRAL_CALIB_VALUE; + + chip->prox_thres = APDS_PROX_DEF_THRES; + chip->pdrive = chip->pdata->pdrive; + chip->pdiode = APDS_PDIODE_IR; + chip->pgain = APDS_PGAIN_1X; + chip->prox_calib = APDS_PROX_NEUTRAL_CALIB_VALUE; + chip->prox_persistence = APDS_DEFAULT_PROX_PERS; + chip->prox_continuous_mode = false; + + chip->regs[0].supply = reg_vcc; + chip->regs[1].supply = reg_vled; + + err = regulator_bulk_get(&client->dev, + ARRAY_SIZE(chip->regs), chip->regs); + if (err < 0) { + dev_err(&client->dev, "Cannot get regulators\n"); + goto fail1; + } + + err = regulator_bulk_enable(ARRAY_SIZE(chip->regs), chip->regs); + if (err < 0) { + dev_err(&client->dev, "Cannot enable regulators\n"); + goto fail2; + } + + usleep_range(APDS_STARTUP_DELAY, 2 * APDS_STARTUP_DELAY); + + err = apds990x_detect(chip); + if (err < 0) { + dev_err(&client->dev, "APDS990X not found\n"); + goto fail3; + } + + pm_runtime_set_active(&client->dev); + + apds990x_configure(chip); + apds990x_set_arate(chip, APDS_LUX_DEFAULT_RATE); + apds990x_mode_on(chip); + + pm_runtime_enable(&client->dev); + + if (chip->pdata->setup_resources) { + err = chip->pdata->setup_resources(); + if (err) { + err = -EINVAL; + goto fail3; + } + } + + err = sysfs_create_group(&chip->client->dev.kobj, + apds990x_attribute_group); + if (err < 0) { + dev_err(&chip->client->dev, "Sysfs registration failed\n"); + goto fail4; + } + + err = request_threaded_irq(client->irq, NULL, + apds990x_irq, + IRQF_TRIGGER_FALLING | IRQF_TRIGGER_LOW | + IRQF_ONESHOT, + "apds990x", chip); + if (err) { + dev_err(&client->dev, "could not get IRQ %d\n", + client->irq); + goto fail5; + } + return err; +fail5: + sysfs_remove_group(&chip->client->dev.kobj, + &apds990x_attribute_group[0]); +fail4: + if (chip->pdata && chip->pdata->release_resources) + chip->pdata->release_resources(); +fail3: + regulator_bulk_disable(ARRAY_SIZE(chip->regs), chip->regs); +fail2: + regulator_bulk_free(ARRAY_SIZE(chip->regs), chip->regs); +fail1: + kfree(chip); + return err; +} + +static int __devexit apds990x_remove(struct i2c_client *client) +{ + struct apds990x_chip *chip = i2c_get_clientdata(client); + + free_irq(client->irq, chip); + sysfs_remove_group(&chip->client->dev.kobj, + apds990x_attribute_group); + + if (chip->pdata && chip->pdata->release_resources) + chip->pdata->release_resources(); + + if (!pm_runtime_suspended(&client->dev)) + apds990x_chip_off(chip); + + pm_runtime_disable(&client->dev); + pm_runtime_set_suspended(&client->dev); + + regulator_bulk_free(ARRAY_SIZE(chip->regs), chip->regs); + + kfree(chip); + return 0; +} + +#ifdef CONFIG_PM +static int apds990x_suspend(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct apds990x_chip *chip = i2c_get_clientdata(client); + + apds990x_chip_off(chip); + return 0; +} + +static int apds990x_resume(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct apds990x_chip *chip = i2c_get_clientdata(client); + + /* + * If we were enabled at suspend time, it is expected + * everything works nice and smoothly. Chip_on is enough + */ + apds990x_chip_on(chip); + + return 0; +} +#else +#define apds990x_suspend NULL +#define apds990x_resume NULL +#define apds990x_shutdown NULL +#endif + +#ifdef CONFIG_PM_RUNTIME +static int apds990x_runtime_suspend(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct apds990x_chip *chip = i2c_get_clientdata(client); + + apds990x_chip_off(chip); + return 0; +} + +static int apds990x_runtime_resume(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct apds990x_chip *chip = i2c_get_clientdata(client); + + apds990x_chip_on(chip); + return 0; +} + +#endif + +static const struct i2c_device_id apds990x_id[] = { + {"apds990x", 0 }, + {} +}; + +MODULE_DEVICE_TABLE(i2c, apds990x_id); + +static const struct dev_pm_ops apds990x_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(apds990x_suspend, apds990x_resume) + SET_RUNTIME_PM_OPS(apds990x_runtime_suspend, + apds990x_runtime_resume, + NULL) +}; + +static struct i2c_driver apds990x_driver = { + .driver = { + .name = "apds990x", + .owner = THIS_MODULE, + .pm = &apds990x_pm_ops, + }, + .probe = apds990x_probe, + .remove = __devexit_p(apds990x_remove), + .id_table = apds990x_id, +}; + +static int __init apds990x_init(void) +{ + return i2c_add_driver(&apds990x_driver); +} + +static void __exit apds990x_exit(void) +{ + i2c_del_driver(&apds990x_driver); +} + +MODULE_DESCRIPTION("APDS990X combined ALS and proximity sensor"); +MODULE_AUTHOR("Samu Onkalo, Nokia Corporation"); +MODULE_LICENSE("GPL v2"); + +module_init(apds990x_init); +module_exit(apds990x_exit); diff --git a/drivers/misc/bh1770glc.c b/drivers/misc/bh1770glc.c new file mode 100644 index 000000000000..cee632e645e1 --- /dev/null +++ b/drivers/misc/bh1770glc.c @@ -0,0 +1,1413 @@ +/* + * This file is part of the ROHM BH1770GLC / OSRAM SFH7770 sensor driver. + * Chip is combined proximity and ambient light sensor. + * + * Copyright (C) 2010 Nokia Corporation and/or its subsidiary(-ies). + * + * Contact: Samu Onkalo + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define BH1770_ALS_CONTROL 0x80 /* ALS operation mode control */ +#define BH1770_PS_CONTROL 0x81 /* PS operation mode control */ +#define BH1770_I_LED 0x82 /* active LED and LED1, LED2 current */ +#define BH1770_I_LED3 0x83 /* LED3 current setting */ +#define BH1770_ALS_PS_MEAS 0x84 /* Forced mode trigger */ +#define BH1770_PS_MEAS_RATE 0x85 /* PS meas. rate at stand alone mode */ +#define BH1770_ALS_MEAS_RATE 0x86 /* ALS meas. rate at stand alone mode */ +#define BH1770_PART_ID 0x8a /* Part number and revision ID */ +#define BH1770_MANUFACT_ID 0x8b /* Manufacturerer ID */ +#define BH1770_ALS_DATA_0 0x8c /* ALS DATA low byte */ +#define BH1770_ALS_DATA_1 0x8d /* ALS DATA high byte */ +#define BH1770_ALS_PS_STATUS 0x8e /* Measurement data and int status */ +#define BH1770_PS_DATA_LED1 0x8f /* PS data from LED1 */ +#define BH1770_PS_DATA_LED2 0x90 /* PS data from LED2 */ +#define BH1770_PS_DATA_LED3 0x91 /* PS data from LED3 */ +#define BH1770_INTERRUPT 0x92 /* Interrupt setting */ +#define BH1770_PS_TH_LED1 0x93 /* PS interrupt threshold for LED1 */ +#define BH1770_PS_TH_LED2 0x94 /* PS interrupt threshold for LED2 */ +#define BH1770_PS_TH_LED3 0x95 /* PS interrupt threshold for LED3 */ +#define BH1770_ALS_TH_UP_0 0x96 /* ALS upper threshold low byte */ +#define BH1770_ALS_TH_UP_1 0x97 /* ALS upper threshold high byte */ +#define BH1770_ALS_TH_LOW_0 0x98 /* ALS lower threshold low byte */ +#define BH1770_ALS_TH_LOW_1 0x99 /* ALS lower threshold high byte */ + +/* MANUFACT_ID */ +#define BH1770_MANUFACT_ROHM 0x01 +#define BH1770_MANUFACT_OSRAM 0x03 + +/* PART_ID */ +#define BH1770_PART 0x90 +#define BH1770_PART_MASK 0xf0 +#define BH1770_REV_MASK 0x0f +#define BH1770_REV_SHIFT 0 +#define BH1770_REV_0 0x00 +#define BH1770_REV_1 0x01 + +/* Operating modes for both */ +#define BH1770_STANDBY 0x00 +#define BH1770_FORCED 0x02 +#define BH1770_STANDALONE 0x03 +#define BH1770_SWRESET (0x01 << 2) + +#define BH1770_PS_TRIG_MEAS (1 << 0) +#define BH1770_ALS_TRIG_MEAS (1 << 1) + +/* Interrupt control */ +#define BH1770_INT_OUTPUT_MODE (1 << 3) /* 0 = latched */ +#define BH1770_INT_POLARITY (1 << 2) /* 1 = active high */ +#define BH1770_INT_ALS_ENA (1 << 1) +#define BH1770_INT_PS_ENA (1 << 0) + +/* Interrupt status */ +#define BH1770_INT_LED1_DATA (1 << 0) +#define BH1770_INT_LED1_INT (1 << 1) +#define BH1770_INT_LED2_DATA (1 << 2) +#define BH1770_INT_LED2_INT (1 << 3) +#define BH1770_INT_LED3_DATA (1 << 4) +#define BH1770_INT_LED3_INT (1 << 5) +#define BH1770_INT_LEDS_INT ((1 << 1) | (1 << 3) | (1 << 5)) +#define BH1770_INT_ALS_DATA (1 << 6) +#define BH1770_INT_ALS_INT (1 << 7) + +/* Led channels */ +#define BH1770_LED1 0x00 + +#define BH1770_DISABLE 0 +#define BH1770_ENABLE 1 +#define BH1770_PROX_CHANNELS 1 + +#define BH1770_LUX_DEFAULT_RATE 1 /* Index to lux rate table */ +#define BH1770_PROX_DEFAULT_RATE 1 /* Direct HW value =~ 50Hz */ +#define BH1770_PROX_DEF_RATE_THRESH 6 /* Direct HW value =~ 5 Hz */ +#define BH1770_STARTUP_DELAY 50 +#define BH1770_RESET_TIME 10 +#define BH1770_TIMEOUT 2100 /* Timeout in 2.1 seconds */ + +#define BH1770_LUX_RANGE 65535 +#define BH1770_PROX_RANGE 255 +#define BH1770_COEF_SCALER 1024 +#define BH1770_CALIB_SCALER 8192 +#define BH1770_LUX_NEUTRAL_CALIB_VALUE (1 * BH1770_CALIB_SCALER) +#define BH1770_LUX_DEF_THRES 1000 +#define BH1770_PROX_DEF_THRES 70 +#define BH1770_PROX_DEF_ABS_THRES 100 +#define BH1770_DEFAULT_PERSISTENCE 10 +#define BH1770_PROX_MAX_PERSISTENCE 50 +#define BH1770_LUX_GA_SCALE 16384 +#define BH1770_LUX_CF_SCALE 2048 /* CF ChipFactor */ +#define BH1770_NEUTRAL_CF BH1770_LUX_CF_SCALE +#define BH1770_LUX_CORR_SCALE 4096 + +#define PROX_ABOVE_THRESHOLD 1 +#define PROX_BELOW_THRESHOLD 0 + +#define PROX_IGNORE_LUX_LIMIT 500 + +struct bh1770_chip { + struct bh1770_platform_data *pdata; + char chipname[10]; + u8 revision; + struct i2c_client *client; + struct regulator_bulk_data regs[2]; + struct mutex mutex; /* avoid parallel access */ + wait_queue_head_t wait; + + bool int_mode_prox; + bool int_mode_lux; + struct delayed_work prox_work; + u32 lux_cf; /* Chip specific factor */ + u32 lux_ga; + u32 lux_calib; + int lux_rate_index; + u32 lux_corr; + u16 lux_data_raw; + u16 lux_threshold_hi; + u16 lux_threshold_lo; + u16 lux_thres_hi_onchip; + u16 lux_thres_lo_onchip; + bool lux_wait_result; + + int prox_enable_count; + u16 prox_coef; + u16 prox_const; + int prox_rate; + int prox_rate_threshold; + u8 prox_persistence; + u8 prox_persistence_counter; + u8 prox_data; + u8 prox_threshold; + u8 prox_threshold_hw; + bool prox_force_update; + u8 prox_abs_thres; + u8 prox_led; +}; + +static const char reg_vcc[] = "Vcc"; +static const char reg_vleds[] = "Vleds"; + +/* + * Supported stand alone rates in ms from chip data sheet + * {10, 20, 30, 40, 70, 100, 200, 500, 1000, 2000}; + */ +static const s16 prox_rates_hz[] = {100, 50, 33, 25, 14, 10, 5, 2}; +static const s16 prox_rates_ms[] = {10, 20, 30, 40, 70, 100, 200, 500}; + +/* Supported IR-led currents in mA */ +static const u8 prox_curr_ma[] = {5, 10, 20, 50, 100, 150, 200}; + +/* + * Supported stand alone rates in ms from chip data sheet + * {100, 200, 500, 1000, 2000}; + */ +static const s16 lux_rates_hz[] = {10, 5, 2, 1, 0}; + +/* + * interrupt control functions are called while keeping chip->mutex + * excluding module probe / remove + */ +static inline int bh1770_lux_interrupt_control(struct bh1770_chip *chip, + int lux) +{ + chip->int_mode_lux = lux; + /* Set interrupt modes, interrupt active low, latched */ + return i2c_smbus_write_byte_data(chip->client, + BH1770_INTERRUPT, + (lux << 1) | chip->int_mode_prox); +} + +static inline int bh1770_prox_interrupt_control(struct bh1770_chip *chip, + int ps) +{ + chip->int_mode_prox = ps; + return i2c_smbus_write_byte_data(chip->client, + BH1770_INTERRUPT, + (chip->int_mode_lux << 1) | (ps << 0)); +} + +/* chip->mutex is always kept here */ +static int bh1770_lux_rate(struct bh1770_chip *chip, int rate_index) +{ + /* sysfs may call this when the chip is powered off */ + if (pm_runtime_suspended(&chip->client->dev)) + return 0; + + /* Proper proximity response needs fastest lux rate (100ms) */ + if (chip->prox_enable_count) + rate_index = 0; + + return i2c_smbus_write_byte_data(chip->client, + BH1770_ALS_MEAS_RATE, + rate_index); +} + +static int bh1770_prox_rate(struct bh1770_chip *chip, int mode) +{ + int rate; + + rate = (mode == PROX_ABOVE_THRESHOLD) ? + chip->prox_rate_threshold : chip->prox_rate; + + return i2c_smbus_write_byte_data(chip->client, + BH1770_PS_MEAS_RATE, + rate); +} + +/* InfraredLED is controlled by the chip during proximity scanning */ +static inline int bh1770_led_cfg(struct bh1770_chip *chip) +{ + /* LED cfg, current for leds 1 and 2 */ + return i2c_smbus_write_byte_data(chip->client, + BH1770_I_LED, + (BH1770_LED1 << 6) | + (BH1770_LED_5mA << 3) | + chip->prox_led); +} + +/* + * Following two functions converts raw ps values from HW to normalized + * values. Purpose is to compensate differences between different sensor + * versions and variants so that result means about the same between + * versions. + */ +static inline u8 bh1770_psraw_to_adjusted(struct bh1770_chip *chip, u8 psraw) +{ + u16 adjusted; + adjusted = (u16)(((u32)(psraw + chip->prox_const) * chip->prox_coef) / + BH1770_COEF_SCALER); + if (adjusted > BH1770_PROX_RANGE) + adjusted = BH1770_PROX_RANGE; + return adjusted; +} + +static inline u8 bh1770_psadjusted_to_raw(struct bh1770_chip *chip, u8 ps) +{ + u16 raw; + + raw = (((u32)ps * BH1770_COEF_SCALER) / chip->prox_coef); + if (raw > chip->prox_const) + raw = raw - chip->prox_const; + else + raw = 0; + return raw; +} + +/* + * Following two functions converts raw lux values from HW to normalized + * values. Purpose is to compensate differences between different sensor + * versions and variants so that result means about the same between + * versions. Chip->mutex is kept when this is called. + */ +static int bh1770_prox_set_threshold(struct bh1770_chip *chip) +{ + u8 tmp = 0; + + /* sysfs may call this when the chip is powered off */ + if (pm_runtime_suspended(&chip->client->dev)) + return 0; + + tmp = bh1770_psadjusted_to_raw(chip, chip->prox_threshold); + chip->prox_threshold_hw = tmp; + + return i2c_smbus_write_byte_data(chip->client, BH1770_PS_TH_LED1, + tmp); +} + +static inline u16 bh1770_lux_raw_to_adjusted(struct bh1770_chip *chip, u16 raw) +{ + u32 lux; + lux = ((u32)raw * chip->lux_corr) / BH1770_LUX_CORR_SCALE; + return min(lux, (u32)BH1770_LUX_RANGE); +} + +static inline u16 bh1770_lux_adjusted_to_raw(struct bh1770_chip *chip, + u16 adjusted) +{ + return (u32)adjusted * BH1770_LUX_CORR_SCALE / chip->lux_corr; +} + +/* chip->mutex is kept when this is called */ +static int bh1770_lux_update_thresholds(struct bh1770_chip *chip, + u16 threshold_hi, u16 threshold_lo) +{ + u8 data[4]; + int ret; + + /* sysfs may call this when the chip is powered off */ + if (pm_runtime_suspended(&chip->client->dev)) + return 0; + + /* + * Compensate threshold values with the correction factors if not + * set to minimum or maximum. + * Min & max values disables interrupts. + */ + if (threshold_hi != BH1770_LUX_RANGE && threshold_hi != 0) + threshold_hi = bh1770_lux_adjusted_to_raw(chip, threshold_hi); + + if (threshold_lo != BH1770_LUX_RANGE && threshold_lo != 0) + threshold_lo = bh1770_lux_adjusted_to_raw(chip, threshold_lo); + + if (chip->lux_thres_hi_onchip == threshold_hi && + chip->lux_thres_lo_onchip == threshold_lo) + return 0; + + chip->lux_thres_hi_onchip = threshold_hi; + chip->lux_thres_lo_onchip = threshold_lo; + + data[0] = threshold_hi; + data[1] = threshold_hi >> 8; + data[2] = threshold_lo; + data[3] = threshold_lo >> 8; + + ret = i2c_smbus_write_i2c_block_data(chip->client, + BH1770_ALS_TH_UP_0, + ARRAY_SIZE(data), + data); + return ret; +} + +static int bh1770_lux_get_result(struct bh1770_chip *chip) +{ + u16 data; + int ret; + + ret = i2c_smbus_read_byte_data(chip->client, BH1770_ALS_DATA_0); + if (ret < 0) + return ret; + + data = ret & 0xff; + ret = i2c_smbus_read_byte_data(chip->client, BH1770_ALS_DATA_1); + if (ret < 0) + return ret; + + chip->lux_data_raw = data | ((ret & 0xff) << 8); + + return 0; +} + +/* Calculate correction value which contains chip and device specific parts */ +static u32 bh1770_get_corr_value(struct bh1770_chip *chip) +{ + u32 tmp; + /* Impact of glass attenuation correction */ + tmp = (BH1770_LUX_CORR_SCALE * chip->lux_ga) / BH1770_LUX_GA_SCALE; + /* Impact of chip factor correction */ + tmp = (tmp * chip->lux_cf) / BH1770_LUX_CF_SCALE; + /* Impact of Device specific calibration correction */ + tmp = (tmp * chip->lux_calib) / BH1770_CALIB_SCALER; + return tmp; +} + +static int bh1770_lux_read_result(struct bh1770_chip *chip) +{ + bh1770_lux_get_result(chip); + return bh1770_lux_raw_to_adjusted(chip, chip->lux_data_raw); +} + +/* + * Chip on / off functions are called while keeping mutex except probe + * or remove phase + */ +static int bh1770_chip_on(struct bh1770_chip *chip) +{ + int ret = regulator_bulk_enable(ARRAY_SIZE(chip->regs), + chip->regs); + if (ret < 0) + return ret; + + usleep_range(BH1770_STARTUP_DELAY, BH1770_STARTUP_DELAY * 2); + + /* Reset the chip */ + i2c_smbus_write_byte_data(chip->client, BH1770_ALS_CONTROL, + BH1770_SWRESET); + usleep_range(BH1770_RESET_TIME, BH1770_RESET_TIME * 2); + + /* + * ALS is started always since proximity needs als results + * for realibility estimation. + * Let's assume dark until the first ALS measurement is ready. + */ + chip->lux_data_raw = 0; + chip->prox_data = 0; + ret = i2c_smbus_write_byte_data(chip->client, + BH1770_ALS_CONTROL, BH1770_STANDALONE); + + /* Assume reset defaults */ + chip->lux_thres_hi_onchip = BH1770_LUX_RANGE; + chip->lux_thres_lo_onchip = 0; + + return ret; +} + +static void bh1770_chip_off(struct bh1770_chip *chip) +{ + i2c_smbus_write_byte_data(chip->client, + BH1770_INTERRUPT, BH1770_DISABLE); + i2c_smbus_write_byte_data(chip->client, + BH1770_ALS_CONTROL, BH1770_STANDBY); + i2c_smbus_write_byte_data(chip->client, + BH1770_PS_CONTROL, BH1770_STANDBY); + regulator_bulk_disable(ARRAY_SIZE(chip->regs), chip->regs); +} + +/* chip->mutex is kept when this is called */ +static int bh1770_prox_mode_control(struct bh1770_chip *chip) +{ + if (chip->prox_enable_count) { + chip->prox_force_update = true; /* Force immediate update */ + + bh1770_lux_rate(chip, chip->lux_rate_index); + bh1770_prox_set_threshold(chip); + bh1770_led_cfg(chip); + bh1770_prox_rate(chip, PROX_BELOW_THRESHOLD); + bh1770_prox_interrupt_control(chip, BH1770_ENABLE); + i2c_smbus_write_byte_data(chip->client, + BH1770_PS_CONTROL, BH1770_STANDALONE); + } else { + chip->prox_data = 0; + bh1770_lux_rate(chip, chip->lux_rate_index); + bh1770_prox_interrupt_control(chip, BH1770_DISABLE); + i2c_smbus_write_byte_data(chip->client, + BH1770_PS_CONTROL, BH1770_STANDBY); + } + return 0; +} + +/* chip->mutex is kept when this is called */ +static int bh1770_prox_read_result(struct bh1770_chip *chip) +{ + int ret; + bool above; + u8 mode; + + ret = i2c_smbus_read_byte_data(chip->client, BH1770_PS_DATA_LED1); + if (ret < 0) + goto out; + + if (ret > chip->prox_threshold_hw) + above = true; + else + above = false; + + /* + * when ALS levels goes above limit, proximity result may be + * false proximity. Thus ignore the result. With real proximity + * there is a shadow causing low als levels. + */ + if (chip->lux_data_raw > PROX_IGNORE_LUX_LIMIT) + ret = 0; + + chip->prox_data = bh1770_psraw_to_adjusted(chip, ret); + + /* Strong proximity level or force mode requires immediate response */ + if (chip->prox_data >= chip->prox_abs_thres || + chip->prox_force_update) + chip->prox_persistence_counter = chip->prox_persistence; + + chip->prox_force_update = false; + + /* Persistence filttering to reduce false proximity events */ + if (likely(above)) { + if (chip->prox_persistence_counter < chip->prox_persistence) { + chip->prox_persistence_counter++; + ret = -ENODATA; + } else { + mode = PROX_ABOVE_THRESHOLD; + ret = 0; + } + } else { + chip->prox_persistence_counter = 0; + mode = PROX_BELOW_THRESHOLD; + chip->prox_data = 0; + ret = 0; + } + + /* Set proximity detection rate based on above or below value */ + if (ret == 0) { + bh1770_prox_rate(chip, mode); + sysfs_notify(&chip->client->dev.kobj, NULL, "prox0_raw"); + } +out: + return ret; +} + +static int bh1770_detect(struct bh1770_chip *chip) +{ + struct i2c_client *client = chip->client; + s32 ret; + u8 manu, part; + + ret = i2c_smbus_read_byte_data(client, BH1770_MANUFACT_ID); + if (ret < 0) + goto error; + manu = (u8)ret; + + ret = i2c_smbus_read_byte_data(client, BH1770_PART_ID); + if (ret < 0) + goto error; + part = (u8)ret; + + chip->revision = (part & BH1770_REV_MASK) >> BH1770_REV_SHIFT; + chip->prox_coef = BH1770_COEF_SCALER; + chip->prox_const = 0; + chip->lux_cf = BH1770_NEUTRAL_CF; + + if ((manu == BH1770_MANUFACT_ROHM) && + ((part & BH1770_PART_MASK) == BH1770_PART)) { + snprintf(chip->chipname, sizeof(chip->chipname), "BH1770GLC"); + return 0; + } + + if ((manu == BH1770_MANUFACT_OSRAM) && + ((part & BH1770_PART_MASK) == BH1770_PART)) { + snprintf(chip->chipname, sizeof(chip->chipname), "SFH7770"); + /* Values selected by comparing different versions */ + chip->prox_coef = 819; /* 0.8 * BH1770_COEF_SCALER */ + chip->prox_const = 40; + return 0; + } + + ret = -ENODEV; +error: + dev_dbg(&client->dev, "BH1770 or SFH7770 not found\n"); + + return ret; +} + +/* + * This work is re-scheduled at every proximity interrupt. + * If this work is running, it means that there hasn't been any + * proximity interrupt in time. Situation is handled as no-proximity. + * It would be nice to have low-threshold interrupt or interrupt + * when measurement and hi-threshold are both 0. But neither of those exists. + * This is a workaroud for missing HW feature. + */ + +static void bh1770_prox_work(struct work_struct *work) +{ + struct bh1770_chip *chip = + container_of(work, struct bh1770_chip, prox_work.work); + + mutex_lock(&chip->mutex); + bh1770_prox_read_result(chip); + mutex_unlock(&chip->mutex); +} + +/* This is threaded irq handler */ +static irqreturn_t bh1770_irq(int irq, void *data) +{ + struct bh1770_chip *chip = data; + int status; + int rate = 0; + + mutex_lock(&chip->mutex); + status = i2c_smbus_read_byte_data(chip->client, BH1770_ALS_PS_STATUS); + + /* Acknowledge interrupt by reading this register */ + i2c_smbus_read_byte_data(chip->client, BH1770_INTERRUPT); + + /* + * Check if there is fresh data available for als. + * If this is the very first data, update thresholds after that. + */ + if (status & BH1770_INT_ALS_DATA) { + bh1770_lux_get_result(chip); + if (unlikely(chip->lux_wait_result)) { + chip->lux_wait_result = false; + wake_up(&chip->wait); + bh1770_lux_update_thresholds(chip, + chip->lux_threshold_hi, + chip->lux_threshold_lo); + } + } + + /* Disable interrupt logic to guarantee acknowledgement */ + i2c_smbus_write_byte_data(chip->client, BH1770_INTERRUPT, + (0 << 1) | (0 << 0)); + + if ((status & BH1770_INT_ALS_INT)) + sysfs_notify(&chip->client->dev.kobj, NULL, "lux0_input"); + + if (chip->int_mode_prox && (status & BH1770_INT_LEDS_INT)) { + rate = prox_rates_ms[chip->prox_rate_threshold]; + bh1770_prox_read_result(chip); + } + + /* Re-enable interrupt logic */ + i2c_smbus_write_byte_data(chip->client, BH1770_INTERRUPT, + (chip->int_mode_lux << 1) | + (chip->int_mode_prox << 0)); + mutex_unlock(&chip->mutex); + + /* + * Can't cancel work while keeping mutex since the work uses the + * same mutex. + */ + if (rate) { + /* + * Simulate missing no-proximity interrupt 50ms after the + * next expected interrupt time. + */ + cancel_delayed_work_sync(&chip->prox_work); + schedule_delayed_work(&chip->prox_work, + msecs_to_jiffies(rate + 50)); + } + return IRQ_HANDLED; +} + +static ssize_t bh1770_power_state_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + size_t ret; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + if (value) { + pm_runtime_get_sync(dev); + + ret = bh1770_lux_rate(chip, chip->lux_rate_index); + ret |= bh1770_lux_interrupt_control(chip, BH1770_ENABLE); + + if (ret < 0) { + pm_runtime_put(dev); + goto leave; + } + + /* This causes interrupt after the next measurement cycle */ + bh1770_lux_update_thresholds(chip, BH1770_LUX_DEF_THRES, + BH1770_LUX_DEF_THRES); + /* Inform that we are waiting for a result from ALS */ + chip->lux_wait_result = true; + bh1770_prox_mode_control(chip); + } else if (!pm_runtime_suspended(dev)) { + pm_runtime_put(dev); + } + ret = count; +leave: + mutex_unlock(&chip->mutex); + return ret; +} + +static ssize_t bh1770_power_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", !pm_runtime_suspended(dev)); +} + +static ssize_t bh1770_lux_result_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + ssize_t ret; + long timeout; + + if (pm_runtime_suspended(dev)) + return -EIO; /* Chip is not enabled at all */ + + timeout = wait_event_interruptible_timeout(chip->wait, + !chip->lux_wait_result, + msecs_to_jiffies(BH1770_TIMEOUT)); + if (!timeout) + return -EIO; + + mutex_lock(&chip->mutex); + ret = sprintf(buf, "%d\n", bh1770_lux_read_result(chip)); + mutex_unlock(&chip->mutex); + + return ret; +} + +static ssize_t bh1770_lux_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", BH1770_LUX_RANGE); +} + +static ssize_t bh1770_prox_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + /* Assume no proximity. Sensor will tell real state soon */ + if (!chip->prox_enable_count) + chip->prox_data = 0; + + if (value) + chip->prox_enable_count++; + else if (chip->prox_enable_count > 0) + chip->prox_enable_count--; + else + goto leave; + + /* Run control only when chip is powered on */ + if (!pm_runtime_suspended(dev)) + bh1770_prox_mode_control(chip); +leave: + mutex_unlock(&chip->mutex); + return count; +} + +static ssize_t bh1770_prox_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + ssize_t len; + + mutex_lock(&chip->mutex); + len = sprintf(buf, "%d\n", chip->prox_enable_count); + mutex_unlock(&chip->mutex); + return len; +} + +static ssize_t bh1770_prox_result_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + ssize_t ret; + + mutex_lock(&chip->mutex); + if (chip->prox_enable_count && !pm_runtime_suspended(dev)) + ret = sprintf(buf, "%d\n", chip->prox_data); + else + ret = -EIO; + mutex_unlock(&chip->mutex); + return ret; +} + +static ssize_t bh1770_prox_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", BH1770_PROX_RANGE); +} + +static ssize_t bh1770_get_prox_rate_avail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int i; + int pos = 0; + for (i = 0; i < ARRAY_SIZE(prox_rates_hz); i++) + pos += sprintf(buf + pos, "%d ", prox_rates_hz[i]); + sprintf(buf + pos - 1, "\n"); + return pos; +} + +static ssize_t bh1770_get_prox_rate_above(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", prox_rates_hz[chip->prox_rate_threshold]); +} + +static ssize_t bh1770_get_prox_rate_below(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", prox_rates_hz[chip->prox_rate]); +} + +static int bh1770_prox_rate_validate(int rate) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(prox_rates_hz) - 1; i++) + if (rate >= prox_rates_hz[i]) + break; + return i; +} + +static ssize_t bh1770_set_prox_rate_above(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + chip->prox_rate_threshold = bh1770_prox_rate_validate(value); + mutex_unlock(&chip->mutex); + return count; +} + +static ssize_t bh1770_set_prox_rate_below(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + chip->prox_rate = bh1770_prox_rate_validate(value); + mutex_unlock(&chip->mutex); + return count; +} + +static ssize_t bh1770_get_prox_thres(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->prox_threshold); +} + +static ssize_t bh1770_set_prox_thres(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + int ret; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + if (value > BH1770_PROX_RANGE) + return -EINVAL; + + mutex_lock(&chip->mutex); + chip->prox_threshold = value; + ret = bh1770_prox_set_threshold(chip); + mutex_unlock(&chip->mutex); + if (ret < 0) + return ret; + return count; +} + +static ssize_t bh1770_prox_persistence_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", chip->prox_persistence); +} + +static ssize_t bh1770_prox_persistence_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + if (value > BH1770_PROX_MAX_PERSISTENCE) + return -EINVAL; + + chip->prox_persistence = value; + + return len; +} + +static ssize_t bh1770_prox_abs_thres_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%u\n", chip->prox_abs_thres); +} + +static ssize_t bh1770_prox_abs_thres_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + if (value > BH1770_PROX_RANGE) + return -EINVAL; + + chip->prox_abs_thres = value; + + return len; +} + +static ssize_t bh1770_chip_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%s rev %d\n", chip->chipname, chip->revision); +} + +static ssize_t bh1770_lux_calib_default_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", BH1770_CALIB_SCALER); +} + +static ssize_t bh1770_lux_calib_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + ssize_t len; + + mutex_lock(&chip->mutex); + len = sprintf(buf, "%u\n", chip->lux_calib); + mutex_unlock(&chip->mutex); + return len; +} + +static ssize_t bh1770_lux_calib_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long value; + u32 old_calib; + u32 new_corr; + + if (strict_strtoul(buf, 0, &value)) + return -EINVAL; + + mutex_lock(&chip->mutex); + old_calib = chip->lux_calib; + chip->lux_calib = value; + new_corr = bh1770_get_corr_value(chip); + if (new_corr == 0) { + chip->lux_calib = old_calib; + mutex_unlock(&chip->mutex); + return -EINVAL; + } + chip->lux_corr = new_corr; + /* Refresh thresholds on HW after changing correction value */ + bh1770_lux_update_thresholds(chip, chip->lux_threshold_hi, + chip->lux_threshold_lo); + + mutex_unlock(&chip->mutex); + + return len; +} + +static ssize_t bh1770_get_lux_rate_avail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int i; + int pos = 0; + for (i = 0; i < ARRAY_SIZE(lux_rates_hz); i++) + pos += sprintf(buf + pos, "%d ", lux_rates_hz[i]); + sprintf(buf + pos - 1, "\n"); + return pos; +} + +static ssize_t bh1770_get_lux_rate(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", lux_rates_hz[chip->lux_rate_index]); +} + +static ssize_t bh1770_set_lux_rate(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + unsigned long rate_hz; + int ret, i; + + if (strict_strtoul(buf, 0, &rate_hz)) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(lux_rates_hz) - 1; i++) + if (rate_hz >= lux_rates_hz[i]) + break; + + mutex_lock(&chip->mutex); + chip->lux_rate_index = i; + ret = bh1770_lux_rate(chip, i); + mutex_unlock(&chip->mutex); + + if (ret < 0) + return ret; + + return count; +} + +static ssize_t bh1770_get_lux_thresh_above(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->lux_threshold_hi); +} + +static ssize_t bh1770_get_lux_thresh_below(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + return sprintf(buf, "%d\n", chip->lux_threshold_lo); +} + +static ssize_t bh1770_set_lux_thresh(struct bh1770_chip *chip, u16 *target, + const char *buf) +{ + int ret = 0; + unsigned long thresh; + + if (strict_strtoul(buf, 0, &thresh)) + return -EINVAL; + + if (thresh > BH1770_LUX_RANGE) + return -EINVAL; + + mutex_lock(&chip->mutex); + *target = thresh; + /* + * Don't update values in HW if we are still waiting for + * first interrupt to come after device handle open call. + */ + if (!chip->lux_wait_result) + ret = bh1770_lux_update_thresholds(chip, + chip->lux_threshold_hi, + chip->lux_threshold_lo); + mutex_unlock(&chip->mutex); + return ret; + +} + +static ssize_t bh1770_set_lux_thresh_above(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + int ret = bh1770_set_lux_thresh(chip, &chip->lux_threshold_hi, buf); + if (ret < 0) + return ret; + return len; +} + +static ssize_t bh1770_set_lux_thresh_below(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct bh1770_chip *chip = dev_get_drvdata(dev); + int ret = bh1770_set_lux_thresh(chip, &chip->lux_threshold_lo, buf); + if (ret < 0) + return ret; + return len; +} + +static DEVICE_ATTR(prox0_raw_en, S_IRUGO | S_IWUSR, bh1770_prox_enable_show, + bh1770_prox_enable_store); +static DEVICE_ATTR(prox0_thresh_above1_value, S_IRUGO | S_IWUSR, + bh1770_prox_abs_thres_show, + bh1770_prox_abs_thres_store); +static DEVICE_ATTR(prox0_thresh_above0_value, S_IRUGO | S_IWUSR, + bh1770_get_prox_thres, + bh1770_set_prox_thres); +static DEVICE_ATTR(prox0_raw, S_IRUGO, bh1770_prox_result_show, NULL); +static DEVICE_ATTR(prox0_sensor_range, S_IRUGO, bh1770_prox_range_show, NULL); +static DEVICE_ATTR(prox0_thresh_above_count, S_IRUGO | S_IWUSR, + bh1770_prox_persistence_show, + bh1770_prox_persistence_store); +static DEVICE_ATTR(prox0_rate_above, S_IRUGO | S_IWUSR, + bh1770_get_prox_rate_above, + bh1770_set_prox_rate_above); +static DEVICE_ATTR(prox0_rate_below, S_IRUGO | S_IWUSR, + bh1770_get_prox_rate_below, + bh1770_set_prox_rate_below); +static DEVICE_ATTR(prox0_rate_avail, S_IRUGO, bh1770_get_prox_rate_avail, NULL); + +static DEVICE_ATTR(lux0_calibscale, S_IRUGO | S_IWUSR, bh1770_lux_calib_show, + bh1770_lux_calib_store); +static DEVICE_ATTR(lux0_calibscale_default, S_IRUGO, + bh1770_lux_calib_default_show, + NULL); +static DEVICE_ATTR(lux0_input, S_IRUGO, bh1770_lux_result_show, NULL); +static DEVICE_ATTR(lux0_sensor_range, S_IRUGO, bh1770_lux_range_show, NULL); +static DEVICE_ATTR(lux0_rate, S_IRUGO | S_IWUSR, bh1770_get_lux_rate, + bh1770_set_lux_rate); +static DEVICE_ATTR(lux0_rate_avail, S_IRUGO, bh1770_get_lux_rate_avail, NULL); +static DEVICE_ATTR(lux0_thresh_above_value, S_IRUGO | S_IWUSR, + bh1770_get_lux_thresh_above, + bh1770_set_lux_thresh_above); +static DEVICE_ATTR(lux0_thresh_below_value, S_IRUGO | S_IWUSR, + bh1770_get_lux_thresh_below, + bh1770_set_lux_thresh_below); +static DEVICE_ATTR(chip_id, S_IRUGO, bh1770_chip_id_show, NULL); +static DEVICE_ATTR(power_state, S_IRUGO | S_IWUSR, bh1770_power_state_show, + bh1770_power_state_store); + + +static struct attribute *sysfs_attrs[] = { + &dev_attr_lux0_calibscale.attr, + &dev_attr_lux0_calibscale_default.attr, + &dev_attr_lux0_input.attr, + &dev_attr_lux0_sensor_range.attr, + &dev_attr_lux0_rate.attr, + &dev_attr_lux0_rate_avail.attr, + &dev_attr_lux0_thresh_above_value.attr, + &dev_attr_lux0_thresh_below_value.attr, + &dev_attr_prox0_raw.attr, + &dev_attr_prox0_sensor_range.attr, + &dev_attr_prox0_raw_en.attr, + &dev_attr_prox0_thresh_above_count.attr, + &dev_attr_prox0_rate_above.attr, + &dev_attr_prox0_rate_below.attr, + &dev_attr_prox0_rate_avail.attr, + &dev_attr_prox0_thresh_above0_value.attr, + &dev_attr_prox0_thresh_above1_value.attr, + &dev_attr_chip_id.attr, + &dev_attr_power_state.attr, + NULL +}; + +static struct attribute_group bh1770_attribute_group = { + .attrs = sysfs_attrs +}; + +static int __devinit bh1770_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct bh1770_chip *chip; + int err; + + chip = kzalloc(sizeof *chip, GFP_KERNEL); + if (!chip) + return -ENOMEM; + + i2c_set_clientdata(client, chip); + chip->client = client; + + mutex_init(&chip->mutex); + init_waitqueue_head(&chip->wait); + INIT_DELAYED_WORK(&chip->prox_work, bh1770_prox_work); + + if (client->dev.platform_data == NULL) { + dev_err(&client->dev, "platform data is mandatory\n"); + err = -EINVAL; + goto fail1; + } + + chip->pdata = client->dev.platform_data; + chip->lux_calib = BH1770_LUX_NEUTRAL_CALIB_VALUE; + chip->lux_rate_index = BH1770_LUX_DEFAULT_RATE; + chip->lux_threshold_lo = BH1770_LUX_DEF_THRES; + chip->lux_threshold_hi = BH1770_LUX_DEF_THRES; + + if (chip->pdata->glass_attenuation == 0) + chip->lux_ga = BH1770_NEUTRAL_GA; + else + chip->lux_ga = chip->pdata->glass_attenuation; + + chip->prox_threshold = BH1770_PROX_DEF_THRES; + chip->prox_led = chip->pdata->led_def_curr; + chip->prox_abs_thres = BH1770_PROX_DEF_ABS_THRES; + chip->prox_persistence = BH1770_DEFAULT_PERSISTENCE; + chip->prox_rate_threshold = BH1770_PROX_DEF_RATE_THRESH; + chip->prox_rate = BH1770_PROX_DEFAULT_RATE; + chip->prox_data = 0; + + chip->regs[0].supply = reg_vcc; + chip->regs[1].supply = reg_vleds; + + err = regulator_bulk_get(&client->dev, + ARRAY_SIZE(chip->regs), chip->regs); + if (err < 0) { + dev_err(&client->dev, "Cannot get regulators\n"); + goto fail1; + } + + err = regulator_bulk_enable(ARRAY_SIZE(chip->regs), + chip->regs); + if (err < 0) { + dev_err(&client->dev, "Cannot enable regulators\n"); + goto fail2; + } + + usleep_range(BH1770_STARTUP_DELAY, BH1770_STARTUP_DELAY * 2); + err = bh1770_detect(chip); + if (err < 0) + goto fail3; + + /* Start chip */ + bh1770_chip_on(chip); + pm_runtime_set_active(&client->dev); + pm_runtime_enable(&client->dev); + + chip->lux_corr = bh1770_get_corr_value(chip); + if (chip->lux_corr == 0) { + dev_err(&client->dev, "Improper correction values\n"); + err = -EINVAL; + goto fail3; + } + + if (chip->pdata->setup_resources) { + err = chip->pdata->setup_resources(); + if (err) { + err = -EINVAL; + goto fail3; + } + } + + err = sysfs_create_group(&chip->client->dev.kobj, + &bh1770_attribute_group); + if (err < 0) { + dev_err(&chip->client->dev, "Sysfs registration failed\n"); + goto fail4; + } + + /* + * Chip needs level triggered interrupt to work. However, + * level triggering doesn't work always correctly with power + * management. Select both + */ + err = request_threaded_irq(client->irq, NULL, + bh1770_irq, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT | + IRQF_TRIGGER_LOW, + "bh1770", chip); + if (err) { + dev_err(&client->dev, "could not get IRQ %d\n", + client->irq); + goto fail5; + } + regulator_bulk_disable(ARRAY_SIZE(chip->regs), chip->regs); + return err; +fail5: + sysfs_remove_group(&chip->client->dev.kobj, + &bh1770_attribute_group); +fail4: + if (chip->pdata->release_resources) + chip->pdata->release_resources(); +fail3: + regulator_bulk_disable(ARRAY_SIZE(chip->regs), chip->regs); +fail2: + regulator_bulk_free(ARRAY_SIZE(chip->regs), chip->regs); +fail1: + kfree(chip); + return err; +} + +static int __devexit bh1770_remove(struct i2c_client *client) +{ + struct bh1770_chip *chip = i2c_get_clientdata(client); + + free_irq(client->irq, chip); + + sysfs_remove_group(&chip->client->dev.kobj, + &bh1770_attribute_group); + + if (chip->pdata->release_resources) + chip->pdata->release_resources(); + + cancel_delayed_work_sync(&chip->prox_work); + + if (!pm_runtime_suspended(&client->dev)) + bh1770_chip_off(chip); + + pm_runtime_disable(&client->dev); + pm_runtime_set_suspended(&client->dev); + + regulator_bulk_free(ARRAY_SIZE(chip->regs), chip->regs); + kfree(chip); + return 0; +} + +#ifdef CONFIG_PM +static int bh1770_suspend(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct bh1770_chip *chip = i2c_get_clientdata(client); + + bh1770_chip_off(chip); + + return 0; +} + +static int bh1770_resume(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct bh1770_chip *chip = i2c_get_clientdata(client); + int ret = 0; + + bh1770_chip_on(chip); + + if (!pm_runtime_suspended(dev)) { + /* + * If we were enabled at suspend time, it is expected + * everything works nice and smoothly + */ + ret = bh1770_lux_rate(chip, chip->lux_rate_index); + ret |= bh1770_lux_interrupt_control(chip, BH1770_ENABLE); + + /* This causes interrupt after the next measurement cycle */ + bh1770_lux_update_thresholds(chip, BH1770_LUX_DEF_THRES, + BH1770_LUX_DEF_THRES); + /* Inform that we are waiting for a result from ALS */ + chip->lux_wait_result = true; + bh1770_prox_mode_control(chip); + } + return ret; +} + +#else +#define bh1770_suspend NULL +#define bh1770_shutdown NULL +#define bh1770_resume NULL +#endif + +#ifdef CONFIG_PM_RUNTIME +static int bh1770_runtime_suspend(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct bh1770_chip *chip = i2c_get_clientdata(client); + + bh1770_chip_off(chip); + + return 0; +} + +static int bh1770_runtime_resume(struct device *dev) +{ + struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct bh1770_chip *chip = i2c_get_clientdata(client); + + bh1770_chip_on(chip); + + return 0; +} +#endif + +static const struct i2c_device_id bh1770_id[] = { + {"bh1770glc", 0 }, + {"sfh7770", 0 }, + {} +}; + +MODULE_DEVICE_TABLE(i2c, bh1770_id); + +static const struct dev_pm_ops bh1770_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(bh1770_suspend, bh1770_resume) + SET_RUNTIME_PM_OPS(bh1770_runtime_suspend, bh1770_runtime_resume, NULL) +}; + +static struct i2c_driver bh1770_driver = { + .driver = { + .name = "bh1770glc", + .owner = THIS_MODULE, + .pm = &bh1770_pm_ops, + }, + .probe = bh1770_probe, + .remove = __devexit_p(bh1770_remove), + .id_table = bh1770_id, +}; + +static int __init bh1770_init(void) +{ + return i2c_add_driver(&bh1770_driver); +} + +static void __exit bh1770_exit(void) +{ + i2c_del_driver(&bh1770_driver); +} + +MODULE_DESCRIPTION("BH1770GLC / SFH7770 combined ALS and proximity sensor"); +MODULE_AUTHOR("Samu Onkalo, Nokia Corporation"); +MODULE_LICENSE("GPL v2"); + +module_init(bh1770_init); +module_exit(bh1770_exit); diff --git a/drivers/misc/isl29020.c b/drivers/misc/isl29020.c new file mode 100644 index 000000000000..34fe835921c4 --- /dev/null +++ b/drivers/misc/isl29020.c @@ -0,0 +1,248 @@ +/* + * isl29020.c - Intersil ALS Driver + * + * Copyright (C) 2008 Intel Corp + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * 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; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * Data sheet at: http://www.intersil.com/data/fn/fn6505.pdf + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_MUTEX(mutex); + +static ssize_t als_sensing_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + int val; + + val = i2c_smbus_read_byte_data(client, 0x00); + + if (val < 0) + return val; + return sprintf(buf, "%d000\n", 1 << (2 * (val & 3))); + +} + +static ssize_t als_lux_input_data_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + int ret_val, val; + unsigned long int lux; + int temp; + + pm_runtime_get_sync(dev); + msleep(100); + + mutex_lock(&mutex); + temp = i2c_smbus_read_byte_data(client, 0x02); /* MSB data */ + if (temp < 0) { + pm_runtime_put_sync(dev); + mutex_unlock(&mutex); + return temp; + } + + ret_val = i2c_smbus_read_byte_data(client, 0x01); /* LSB data */ + mutex_unlock(&mutex); + + if (ret_val < 0) { + pm_runtime_put_sync(dev); + return ret_val; + } + + ret_val |= temp << 8; + val = i2c_smbus_read_byte_data(client, 0x00); + pm_runtime_put_sync(dev); + if (val < 0) + return val; + lux = ((((1 << (2 * (val & 3))))*1000) * ret_val) / 65536; + return sprintf(buf, "%ld\n", lux); +} + +static ssize_t als_sensing_range_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct i2c_client *client = to_i2c_client(dev); + unsigned int ret_val; + unsigned long val; + + if (strict_strtoul(buf, 10, &val)) + return -EINVAL; + if (val < 1 || val > 64000) + return -EINVAL; + + /* Pick the smallest sensor range that will meet our requirements */ + if (val <= 1000) + val = 1; + else if (val <= 4000) + val = 2; + else if (val <= 16000) + val = 3; + else + val = 4; + + ret_val = i2c_smbus_read_byte_data(client, 0x00); + + ret_val &= 0xFC; /*reset the bit before setting them */ + ret_val |= val - 1; + ret_val = i2c_smbus_write_byte_data(client, 0x00, ret_val); + + if (ret_val < 0) + return ret_val; + return count; +} + +static void als_set_power_state(struct i2c_client *client, int enable) +{ + int ret_val; + + ret_val = i2c_smbus_read_byte_data(client, 0x00); + if (ret_val < 0) + return; + + if (enable) + ret_val |= 0x80; + else + ret_val &= 0x7F; + + i2c_smbus_write_byte_data(client, 0x00, ret_val); +} + +static DEVICE_ATTR(lux0_sensor_range, S_IRUGO | S_IWUSR, + als_sensing_range_show, als_sensing_range_store); +static DEVICE_ATTR(lux0_input, S_IRUGO, als_lux_input_data_show, NULL); + +static struct attribute *mid_att_als[] = { + &dev_attr_lux0_sensor_range.attr, + &dev_attr_lux0_input.attr, + NULL +}; + +static struct attribute_group m_als_gr = { + .name = "isl29020", + .attrs = mid_att_als +}; + +static int als_set_default_config(struct i2c_client *client) +{ + int retval; + + retval = i2c_smbus_write_byte_data(client, 0x00, 0xc0); + if (retval < 0) { + dev_err(&client->dev, "default write failed."); + return retval; + } + return 0;; +} + +static int isl29020_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + int res; + + res = als_set_default_config(client); + if (res < 0) + return res; + + res = sysfs_create_group(&client->dev.kobj, &m_als_gr); + if (res) { + dev_err(&client->dev, "isl29020: device create file failed\n"); + return res; + } + dev_info(&client->dev, "%s isl29020: ALS chip found\n", client->name); + als_set_power_state(client, 0); + pm_runtime_enable(&client->dev); + return res; +} + +static int isl29020_remove(struct i2c_client *client) +{ + struct als_data *data = i2c_get_clientdata(client); + sysfs_remove_group(&client->dev.kobj, &m_als_gr); + kfree(data); + return 0; +} + +static struct i2c_device_id isl29020_id[] = { + { "isl29020", 0 }, + { } +}; + +MODULE_DEVICE_TABLE(i2c, isl29020_id); + +#ifdef CONFIG_PM + +static int isl29020_runtime_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + als_set_power_state(client, 0); + return 0; +} + +static int isl29020_runtime_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + als_set_power_state(client, 1); + return 0; +} + +static const struct dev_pm_ops isl29020_pm_ops = { + .runtime_suspend = isl29020_runtime_suspend, + .runtime_resume = isl29020_runtime_resume, +}; + +#define ISL29020_PM_OPS (&isl29020_pm_ops) +#else /* CONFIG_PM */ +#define ISL29020_PM_OPS NULL +#endif /* CONFIG_PM */ + +static struct i2c_driver isl29020_driver = { + .driver = { + .name = "isl29020", + .pm = ISL29020_PM_OPS, + }, + .probe = isl29020_probe, + .remove = isl29020_remove, + .id_table = isl29020_id, +}; + +static int __init sensor_isl29020_init(void) +{ + return i2c_add_driver(&isl29020_driver); +} + +static void __exit sensor_isl29020_exit(void) +{ + i2c_del_driver(&isl29020_driver); +} + +module_init(sensor_isl29020_init); +module_exit(sensor_isl29020_exit); + +MODULE_AUTHOR("Kalhan Trisal ARRAY_SIZE(cp_type)) + if (type == CT_NONE || type < 0 || type > ARRAY_SIZE(cp_type)) return "None"; return cp_type[type - 1]; @@ -220,7 +220,7 @@ static const char *cp_type_to_str(enum ctype type) static const char *cp_name_to_str(enum cname name) { - if (name == INVALID || name < 0 || name > ARRAY_SIZE(cp_name)) + if (name == CN_INVALID || name < 0 || name > ARRAY_SIZE(cp_name)) return "INVALID"; return cp_name[name - 1]; @@ -245,7 +245,7 @@ static int lkdtm_parse_commandline(void) return -EINVAL; cptype = parse_cp_type(cpoint_type, strlen(cpoint_type)); - if (cptype == NONE) + if (cptype == CT_NONE) return -EINVAL; for (i = 0; i < ARRAY_SIZE(cp_name); i++) { @@ -274,30 +274,30 @@ static int recursive_loop(int a) static void lkdtm_do_action(enum ctype which) { switch (which) { - case PANIC: + case CT_PANIC: panic("dumptest"); break; - case BUG: + case CT_BUG: BUG(); break; - case EXCEPTION: + case CT_EXCEPTION: *((int *) 0) = 0; break; - case LOOP: + case CT_LOOP: for (;;) ; break; - case OVERFLOW: + case CT_OVERFLOW: (void) recursive_loop(0); break; - case CORRUPT_STACK: { + case CT_CORRUPT_STACK: { volatile u32 data[8]; volatile u32 *p = data; p[12] = 0x12345678; break; } - case UNALIGNED_LOAD_STORE_WRITE: { + case CT_UNALIGNED_LOAD_STORE_WRITE: { static u8 data[5] __attribute__((aligned(4))) = {1, 2, 3, 4, 5}; u32 *p; @@ -309,7 +309,7 @@ static void lkdtm_do_action(enum ctype which) *p = val; break; } - case OVERWRITE_ALLOCATION: { + case CT_OVERWRITE_ALLOCATION: { size_t len = 1020; u32 *data = kmalloc(len, GFP_KERNEL); @@ -317,7 +317,7 @@ static void lkdtm_do_action(enum ctype which) kfree(data); break; } - case WRITE_AFTER_FREE: { + case CT_WRITE_AFTER_FREE: { size_t len = 1024; u32 *data = kmalloc(len, GFP_KERNEL); @@ -326,21 +326,21 @@ static void lkdtm_do_action(enum ctype which) memset(data, 0x78, len); break; } - case SOFTLOCKUP: + case CT_SOFTLOCKUP: preempt_disable(); for (;;) cpu_relax(); break; - case HARDLOCKUP: + case CT_HARDLOCKUP: local_irq_disable(); for (;;) cpu_relax(); break; - case HUNG_TASK: + case CT_HUNG_TASK: set_current_state(TASK_UNINTERRUPTIBLE); schedule(); break; - case NONE: + case CT_NONE: default: break; } @@ -363,43 +363,43 @@ static int lkdtm_register_cpoint(enum cname which) { int ret; - cpoint = INVALID; + cpoint = CN_INVALID; if (lkdtm.entry != NULL) unregister_jprobe(&lkdtm); switch (which) { - case DIRECT: + case CN_DIRECT: lkdtm_do_action(cptype); return 0; - case INT_HARDWARE_ENTRY: + case CN_INT_HARDWARE_ENTRY: lkdtm.kp.symbol_name = "do_IRQ"; lkdtm.entry = (kprobe_opcode_t*) jp_do_irq; break; - case INT_HW_IRQ_EN: + case CN_INT_HW_IRQ_EN: lkdtm.kp.symbol_name = "handle_IRQ_event"; lkdtm.entry = (kprobe_opcode_t*) jp_handle_irq_event; break; - case INT_TASKLET_ENTRY: + case CN_INT_TASKLET_ENTRY: lkdtm.kp.symbol_name = "tasklet_action"; lkdtm.entry = (kprobe_opcode_t*) jp_tasklet_action; break; - case FS_DEVRW: + case CN_FS_DEVRW: lkdtm.kp.symbol_name = "ll_rw_block"; lkdtm.entry = (kprobe_opcode_t*) jp_ll_rw_block; break; - case MEM_SWAPOUT: + case CN_MEM_SWAPOUT: lkdtm.kp.symbol_name = "shrink_inactive_list"; lkdtm.entry = (kprobe_opcode_t*) jp_shrink_inactive_list; break; - case TIMERADD: + case CN_TIMERADD: lkdtm.kp.symbol_name = "hrtimer_start"; lkdtm.entry = (kprobe_opcode_t*) jp_hrtimer_start; break; - case SCSI_DISPATCH_CMD: + case CN_SCSI_DISPATCH_CMD: lkdtm.kp.symbol_name = "scsi_dispatch_cmd"; lkdtm.entry = (kprobe_opcode_t*) jp_scsi_dispatch_cmd; break; - case IDE_CORE_CP: + case CN_IDE_CORE_CP: #ifdef CONFIG_IDE lkdtm.kp.symbol_name = "generic_ide_ioctl"; lkdtm.entry = (kprobe_opcode_t*) jp_generic_ide_ioctl; @@ -416,7 +416,7 @@ static int lkdtm_register_cpoint(enum cname which) cpoint = which; if ((ret = register_jprobe(&lkdtm)) < 0) { printk(KERN_INFO "lkdtm: Couldn't register jprobe\n"); - cpoint = INVALID; + cpoint = CN_INVALID; } return ret; @@ -445,7 +445,7 @@ static ssize_t do_register_entry(enum cname which, struct file *f, cptype = parse_cp_type(buf, count); free_page((unsigned long) buf); - if (cptype == NONE) + if (cptype == CT_NONE) return -EINVAL; err = lkdtm_register_cpoint(which); @@ -487,49 +487,49 @@ static int lkdtm_debugfs_open(struct inode *inode, struct file *file) static ssize_t int_hardware_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(INT_HARDWARE_ENTRY, f, buf, count, off); + return do_register_entry(CN_INT_HARDWARE_ENTRY, f, buf, count, off); } static ssize_t int_hw_irq_en(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(INT_HW_IRQ_EN, f, buf, count, off); + return do_register_entry(CN_INT_HW_IRQ_EN, f, buf, count, off); } static ssize_t int_tasklet_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(INT_TASKLET_ENTRY, f, buf, count, off); + return do_register_entry(CN_INT_TASKLET_ENTRY, f, buf, count, off); } static ssize_t fs_devrw_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(FS_DEVRW, f, buf, count, off); + return do_register_entry(CN_FS_DEVRW, f, buf, count, off); } static ssize_t mem_swapout_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(MEM_SWAPOUT, f, buf, count, off); + return do_register_entry(CN_MEM_SWAPOUT, f, buf, count, off); } static ssize_t timeradd_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(TIMERADD, f, buf, count, off); + return do_register_entry(CN_TIMERADD, f, buf, count, off); } static ssize_t scsi_dispatch_cmd_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(SCSI_DISPATCH_CMD, f, buf, count, off); + return do_register_entry(CN_SCSI_DISPATCH_CMD, f, buf, count, off); } static ssize_t ide_core_cp_entry(struct file *f, const char __user *buf, size_t count, loff_t *off) { - return do_register_entry(IDE_CORE_CP, f, buf, count, off); + return do_register_entry(CN_IDE_CORE_CP, f, buf, count, off); } /* Special entry to just crash directly. Available without KPROBEs */ @@ -557,7 +557,7 @@ static ssize_t direct_entry(struct file *f, const char __user *user_buf, type = parse_cp_type(buf, count); free_page((unsigned long) buf); - if (type == NONE) + if (type == CT_NONE) return -EINVAL; printk(KERN_INFO "lkdtm: Performing direct entry %s\n", @@ -649,7 +649,7 @@ static int __init lkdtm_module_init(void) goto out_err; } - if (cpoint != INVALID && cptype != NONE) { + if (cpoint != CN_INVALID && cptype != CT_NONE) { ret = lkdtm_register_cpoint(cpoint); if (ret < 0) { printk(KERN_INFO "lkdtm: Invalid crash point %d\n", diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 4197a3cb26ba..b05db55c8c8e 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -343,8 +343,10 @@ static int __devinit phantom_probe(struct pci_dev *pdev, int retval; retval = pci_enable_device(pdev); - if (retval) + if (retval) { + dev_err(&pdev->dev, "pci_enable_device failed!\n"); goto err; + } minor = phantom_get_free(); if (minor == PHANTOM_MAX_MINORS) { @@ -356,8 +358,10 @@ static int __devinit phantom_probe(struct pci_dev *pdev, phantom_devices[minor] = 1; retval = pci_request_regions(pdev, "phantom"); - if (retval) + if (retval) { + dev_err(&pdev->dev, "pci_request_regions failed!\n"); goto err_null; + } retval = -ENOMEM; pht = kzalloc(sizeof(*pht), GFP_KERNEL); diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 1f59ee2226ca..17bbacb1b4b1 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -417,6 +417,7 @@ xpc_process_activate_IRQ_rcvd_uv(void) static void xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, struct xpc_activate_mq_msghdr_uv *msg_hdr, + int part_setup, int *wakeup_hb_checker) { unsigned long irq_flags; @@ -481,6 +482,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, case XPC_ACTIVATE_MQ_MSG_CHCTL_CLOSEREQUEST_UV: { struct xpc_activate_mq_msg_chctl_closerequest_uv *msg; + if (!part_setup) + break; + msg = container_of(msg_hdr, struct xpc_activate_mq_msg_chctl_closerequest_uv, hdr); @@ -497,6 +501,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, case XPC_ACTIVATE_MQ_MSG_CHCTL_CLOSEREPLY_UV: { struct xpc_activate_mq_msg_chctl_closereply_uv *msg; + if (!part_setup) + break; + msg = container_of(msg_hdr, struct xpc_activate_mq_msg_chctl_closereply_uv, hdr); @@ -511,6 +518,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, case XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREQUEST_UV: { struct xpc_activate_mq_msg_chctl_openrequest_uv *msg; + if (!part_setup) + break; + msg = container_of(msg_hdr, struct xpc_activate_mq_msg_chctl_openrequest_uv, hdr); @@ -528,6 +538,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, case XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREPLY_UV: { struct xpc_activate_mq_msg_chctl_openreply_uv *msg; + if (!part_setup) + break; + msg = container_of(msg_hdr, struct xpc_activate_mq_msg_chctl_openreply_uv, hdr); args = &part->remote_openclose_args[msg->ch_number]; @@ -545,6 +558,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, case XPC_ACTIVATE_MQ_MSG_CHCTL_OPENCOMPLETE_UV: { struct xpc_activate_mq_msg_chctl_opencomplete_uv *msg; + if (!part_setup) + break; + msg = container_of(msg_hdr, struct xpc_activate_mq_msg_chctl_opencomplete_uv, hdr); spin_lock_irqsave(&part->chctl_lock, irq_flags); @@ -621,6 +637,7 @@ xpc_handle_activate_IRQ_uv(int irq, void *dev_id) part_referenced = xpc_part_ref(part); xpc_handle_activate_mq_msg_uv(part, msg_hdr, + part_referenced, &wakeup_hb_checker); if (part_referenced) xpc_part_deref(part); diff --git a/drivers/video/au1200fb.c b/drivers/video/au1200fb.c index e77e8e4280fb..4ea187d93768 100644 --- a/drivers/video/au1200fb.c +++ b/drivers/video/au1200fb.c @@ -1079,7 +1079,7 @@ static int au1200fb_fb_check_var(struct fb_var_screeninfo *var, * clock can only be obtain by dividing this value by an even integer. * Fallback to a slower pixel clock if necessary. */ pixclock = max((u32)(PICOS2KHZ(var->pixclock) * 1000), fbi->monspecs.dclkmin); - pixclock = min(pixclock, min(fbi->monspecs.dclkmax, (u32)AU1200_LCD_MAX_CLK/2)); + pixclock = min3(pixclock, fbi->monspecs.dclkmax, (u32)AU1200_LCD_MAX_CLK/2); if (AU1200_LCD_MAX_CLK % pixclock) { int diff = AU1200_LCD_MAX_CLK % pixclock; diff --git a/firmware/ihex2fw.c b/firmware/ihex2fw.c index 5a03ba8c8364..ba0cf0b601bb 100644 --- a/firmware/ihex2fw.c +++ b/firmware/ihex2fw.c @@ -55,6 +55,7 @@ static int output_records(int outfd); static int sort_records = 0; static int wide_records = 0; +static int include_jump = 0; static int usage(void) { @@ -63,6 +64,7 @@ static int usage(void) fprintf(stderr, "usage: ihex2fw [] \n"); fprintf(stderr, " -w: wide records (16-bit length)\n"); fprintf(stderr, " -s: sort records by address\n"); + fprintf(stderr, " -j: include records for CS:IP/EIP address\n"); return 1; } @@ -73,7 +75,7 @@ int main(int argc, char **argv) uint8_t *data; int opt; - while ((opt = getopt(argc, argv, "ws")) != -1) { + while ((opt = getopt(argc, argv, "wsj")) != -1) { switch (opt) { case 'w': wide_records = 1; @@ -81,7 +83,9 @@ int main(int argc, char **argv) case 's': sort_records = 1; break; - default: + case 'j': + include_jump = 1; + break; return usage(); } } @@ -128,6 +132,7 @@ static int process_ihex(uint8_t *data, ssize_t size) { struct ihex_binrec *record; uint32_t offset = 0; + uint32_t data32; uint8_t type, crc = 0, crcbyte = 0; int i, j; int line = 1; @@ -223,8 +228,14 @@ static int process_ihex(uint8_t *data, ssize_t size) return -EINVAL; } + memcpy(&data32, &record->data[0], sizeof(data32)); + data32 = htonl(data32); + memcpy(&record->data[0], &data32, sizeof(data32)); + /* These records contain the CS/IP or EIP where execution - * starts. Don't really know what to do with them. */ + * starts. If requested output this as a record. */ + if (include_jump) + file_record(record); goto next_record; default: diff --git a/fs/Kconfig b/fs/Kconfig index 65781de44fc0..b5e582bd769d 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -47,6 +47,9 @@ source "fs/nilfs2/Kconfig" endif # BLOCK +config EXPORTFS + tristate + config FILE_LOCKING bool "Enable POSIX file locking API" if EMBEDDED default y @@ -222,9 +225,6 @@ config LOCKD_V4 depends on FILE_LOCKING default y -config EXPORTFS - tristate - config NFS_ACL_SUPPORT tristate select FS_POSIX_ACL diff --git a/fs/afs/write.c b/fs/afs/write.c index 722743b152d8..15690bb1d3b5 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -438,7 +438,6 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb, */ int afs_writepage(struct page *page, struct writeback_control *wbc) { - struct backing_dev_info *bdi = page->mapping->backing_dev_info; struct afs_writeback *wb; int ret; @@ -455,8 +454,6 @@ int afs_writepage(struct page *page, struct writeback_control *wbc) } wbc->nr_to_write -= ret; - if (wbc->nonblocking && bdi_write_congested(bdi)) - wbc->encountered_congestion = 1; _leave(" = 0"); return 0; @@ -469,7 +466,6 @@ static int afs_writepages_region(struct address_space *mapping, struct writeback_control *wbc, pgoff_t index, pgoff_t end, pgoff_t *_next) { - struct backing_dev_info *bdi = mapping->backing_dev_info; struct afs_writeback *wb; struct page *page; int ret, n; @@ -529,11 +525,6 @@ static int afs_writepages_region(struct address_space *mapping, wbc->nr_to_write -= ret; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - break; - } - cond_resched(); } while (index < end && wbc->nr_to_write > 0); @@ -548,24 +539,16 @@ static int afs_writepages_region(struct address_space *mapping, int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct backing_dev_info *bdi = mapping->backing_dev_info; pgoff_t start, end, next; int ret; _enter(""); - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - _leave(" = 0 [congest]"); - return 0; - } - if (wbc->range_cyclic) { start = mapping->writeback_index; end = -1; ret = afs_writepages_region(mapping, wbc, start, end, &next); - if (start > 0 && wbc->nr_to_write > 0 && ret == 0 && - !(wbc->nonblocking && wbc->encountered_congestion)) + if (start > 0 && wbc->nr_to_write > 0 && ret == 0) ret = afs_writepages_region(mapping, wbc, 0, start, &next); mapping->writeback_index = next; diff --git a/fs/buffer.c b/fs/buffer.c index 7f0b9b083f77..8d595ab2aed1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -905,7 +905,6 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bh->b_state = 0; atomic_set(&bh->b_count, 0); - bh->b_private = NULL; bh->b_size = size; /* Link the buffer to its page */ @@ -1706,7 +1705,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, * and kswapd activity, but those code paths have their own * higher-level throttling. */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 51bcc5ce3230..e9c874abc9e1 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -591,7 +591,6 @@ static int ceph_writepages_start(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct backing_dev_info *bdi = mapping->backing_dev_info; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc; pgoff_t index, start, end; @@ -633,13 +632,6 @@ static int ceph_writepages_start(struct address_space *mapping, pagevec_init(&pvec, 0); - /* ?? */ - if (wbc->nonblocking && bdi_write_congested(bdi)) { - dout(" writepages congested\n"); - wbc->encountered_congestion = 1; - goto out_final; - } - /* where to start/end? */ if (wbc->range_cyclic) { start = mapping->writeback_index; /* Start from prev offset */ @@ -885,7 +877,6 @@ static int ceph_writepages_start(struct address_space *mapping, rc = 0; /* vfs expects us to return 0 */ ceph_put_snap_context(snapc); dout("writepages done, rc = %d\n", rc); -out_final: return rc; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8c81e7b14d53..45af003865d2 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1303,7 +1303,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) static int cifs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned int bytes_to_write; unsigned int bytes_written; struct cifs_sb_info *cifs_sb; @@ -1326,15 +1325,6 @@ static int cifs_writepages(struct address_space *mapping, int scanned = 0; int xid, long_op; - /* - * BB: Is this meaningful for a non-block-device file system? - * If it is, we should test it again after we do I/O - */ - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - return 0; - } - cifs_sb = CIFS_SB(mapping->host->i_sb); /* diff --git a/fs/direct-io.c b/fs/direct-io.c index 48d74c7391d1..85882f6ba5f7 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -218,7 +218,7 @@ static struct page *dio_get_page(struct dio *dio) * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static int dio_complete(struct dio *dio, loff_t offset, int ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async) { ssize_t transferred = 0; diff --git a/fs/exec.c b/fs/exec.c index 6d2b6f936858..3aa75b8888a1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include @@ -759,6 +760,10 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + if (old_mm && tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + atomic_dec(&old_mm->oom_disable_count); + atomic_inc(&tsk->mm->oom_disable_count); + } task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { diff --git a/fs/file_table.c b/fs/file_table.c index a04bdd81c11c..c3dee381f1b4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -60,7 +60,7 @@ static inline void file_free(struct file *f) /* * Return the total number of open files in the system */ -static int get_nr_files(void) +static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } @@ -68,7 +68,7 @@ static int get_nr_files(void) /* * Return the maximum number of open files in the system */ -int get_max_files(void) +unsigned long get_max_files(void) { return files_stat.max_files; } @@ -82,7 +82,7 @@ int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(ctl_table *table, int write, @@ -105,7 +105,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *get_empty_filp(void) { const struct cred *cred = current_cred(); - static int old_max; + static long old_max; struct file * f; /* @@ -140,8 +140,7 @@ struct file *get_empty_filp(void) over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { - printk(KERN_INFO "VFS: file-max limit %d reached\n", - get_max_files()); + pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } goto fail; @@ -487,7 +486,7 @@ void mark_files_ro(struct super_block *sb) void __init files_init(unsigned long mempages) { - int n; + unsigned long n; filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -498,9 +497,7 @@ void __init files_init(unsigned long mempages) */ n = (mempages * (PAGE_SIZE / 1024)) / 10; - files_stat.max_files = n; - if (files_stat.max_files < NR_FILE) - files_stat.max_files = NR_FILE; + files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); lg_lock_init(files_lglock); percpu_counter_init(&nr_files, 0); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index ab38fef1c9a1..9e46aec10d1a 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -582,7 +582,7 @@ static inline bool over_bground_thresh(void) global_dirty_limits(&background_thresh, &dirty_thresh); return (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) >= background_thresh); + global_page_state(NR_UNSTABLE_NFS) > background_thresh); } /* @@ -721,6 +721,10 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) return 0; wb->last_old_flush = jiffies; + /* + * Add in the number of potentially dirty inodes, because each inode + * write can dirty pagecache in the underlying blockdev. + */ nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) + (inodes_stat.nr_inodes - inodes_stat.nr_unused); @@ -790,7 +794,7 @@ int bdi_writeback_thread(void *data) struct backing_dev_info *bdi = wb->bdi; long pages_written; - current->flags |= PF_FLUSHER | PF_SWAPWRITE; + current->flags |= PF_SWAPWRITE; set_freezable(); wb->last_active = jiffies; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index cde755cca564..b98664275f02 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -809,11 +809,9 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, int err; struct page *page = *pagep; - if (page && zeroing && count < PAGE_SIZE) { - void *mapaddr = kmap_atomic(page, KM_USER1); - memset(mapaddr, 0, PAGE_SIZE); - kunmap_atomic(mapaddr, KM_USER1); - } + if (page && zeroing && count < PAGE_SIZE) + clear_highpage(page); + while (count) { if (cs->write && cs->pipebufs && page) { return fuse_ref_page(cs, page, offset, count); @@ -830,10 +828,10 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, } } if (page) { - void *mapaddr = kmap_atomic(page, KM_USER1); + void *mapaddr = kmap_atomic(page, KM_USER0); void *buf = mapaddr + offset; offset += fuse_copy_do(cs, &buf, &count); - kunmap_atomic(mapaddr, KM_USER1); + kunmap_atomic(mapaddr, KM_USER0); } else offset += fuse_copy_do(cs, NULL, &count); } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index f3b071f921aa..939739c7b3f9 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -55,7 +55,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb * activity, but those code paths have their own higher-level * throttling. */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index 7c232c1487ee..bf15a43016b9 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -91,7 +91,6 @@ extern int rename_file(char *from, char *to); extern int do_statfs(char *root, long *bsize_out, long long *blocks_out, long long *bfree_out, long long *bavail_out, long long *files_out, long long *ffree_out, - void *fsid_out, int fsid_size, long *namelen_out, - long *spare_out); + void *fsid_out, int fsid_size, long *namelen_out); #endif diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index f7dc9b5f9ef8..cd7c93917cc7 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -217,7 +217,7 @@ int hostfs_statfs(struct dentry *dentry, struct kstatfs *sf) err = do_statfs(dentry->d_sb->s_fs_info, &sf->f_bsize, &f_blocks, &f_bfree, &f_bavail, &f_files, &f_ffree, &sf->f_fsid, sizeof(sf->f_fsid), - &sf->f_namelen, sf->f_spare); + &sf->f_namelen); if (err) return err; sf->f_blocks = f_blocks; diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 6777aa06ce2c..d51a98384bc0 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -94,8 +94,7 @@ void *open_dir(char *path, int *err_out) dir = opendir(path); *err_out = errno; - if (dir == NULL) - return NULL; + return dir; } @@ -205,7 +204,7 @@ int set_attr(const char *file, struct hostfs_iattr *attrs, int fd) if (attrs->ia_valid & HOSTFS_ATTR_MODE) { if (fd >= 0) { if (fchmod(fd, attrs->ia_mode) != 0) - return (-errno); + return -errno; } else if (chmod(file, attrs->ia_mode) != 0) { return -errno; } @@ -364,8 +363,7 @@ int rename_file(char *from, char *to) int do_statfs(char *root, long *bsize_out, long long *blocks_out, long long *bfree_out, long long *bavail_out, long long *files_out, long long *ffree_out, - void *fsid_out, int fsid_size, long *namelen_out, - long *spare_out) + void *fsid_out, int fsid_size, long *namelen_out) { struct statfs64 buf; int err; @@ -384,10 +382,6 @@ int do_statfs(char *root, long *bsize_out, long long *blocks_out, sizeof(buf.f_fsid) > fsid_size ? fsid_size : sizeof(buf.f_fsid)); *namelen_out = buf.f_namelen; - spare_out[0] = buf.f_spare[0]; - spare_out[1] = buf.f_spare[1]; - spare_out[2] = buf.f_spare[2]; - spare_out[3] = buf.f_spare[3]; - spare_out[4] = buf.f_spare[4]; + return 0; } diff --git a/fs/locks.c b/fs/locks.c index 8b2b6ad56a09..4de3a2666810 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2109,7 +2109,7 @@ EXPORT_SYMBOL_GPL(vfs_cancel_lock); #include static void lock_get_status(struct seq_file *f, struct file_lock *fl, - int id, char *pfx) + loff_t id, char *pfx) { struct inode *inode = NULL; unsigned int fl_pid; @@ -2122,7 +2122,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, if (fl->fl_file != NULL) inode = fl->fl_file->f_path.dentry->d_inode; - seq_printf(f, "%d:%s ", id, pfx); + seq_printf(f, "%lld:%s ", id, pfx); if (IS_POSIX(fl)) { seq_printf(f, "%6s %s ", (fl->fl_flags & FL_ACCESS) ? "ACCESS" : "POSIX ", @@ -2185,24 +2185,27 @@ static int locks_show(struct seq_file *f, void *v) fl = list_entry(v, struct file_lock, fl_link); - lock_get_status(f, fl, (long)f->private, ""); + lock_get_status(f, fl, *((loff_t *)f->private), ""); list_for_each_entry(bfl, &fl->fl_block, fl_block) - lock_get_status(f, bfl, (long)f->private, " ->"); + lock_get_status(f, bfl, *((loff_t *)f->private), " ->"); - f->private++; return 0; } static void *locks_start(struct seq_file *f, loff_t *pos) { + loff_t *p = f->private; + lock_flocks(); - f->private = (void *)1; + *p = (*pos + 1); return seq_list_start(&file_lock_list, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { + loff_t *p = f->private; + ++*p; return seq_list_next(v, &file_lock_list, pos); } @@ -2220,14 +2223,14 @@ static const struct seq_operations locks_seq_operations = { static int locks_open(struct inode *inode, struct file *filp) { - return seq_open(filp, &locks_seq_operations); + return seq_open_private(filp, &locks_seq_operations, sizeof(loff_t)); } static const struct file_operations proc_locks_operations = { .open = locks_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static int __init proc_locks_init(void) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 605e292501f4..4c14c17a5276 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -290,9 +290,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); nfs_pageio_cond_complete(pgio, page->index); - ret = nfs_page_async_flush(pgio, page, - wbc->sync_mode == WB_SYNC_NONE || - wbc->nonblocking != 0); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index d926af626177..687d090cea34 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1609,7 +1609,7 @@ nilfs_copy_replace_page_buffers(struct page *page, struct list_head *out) kunmap_atomic(kaddr, KM_USER0); if (!TestSetPageWriteback(clone_page)) - inc_zone_page_state(clone_page, NR_WRITEBACK); + account_page_writeback(clone_page); unlock_page(clone_page); return 0; diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 50f8f0600f06..6a0068841d96 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -33,8 +33,8 @@ config PROC_KCORE depends on PROC_FS && MMU config PROC_VMCORE - bool "/proc/vmcore support (EXPERIMENTAL)" - depends on PROC_FS && CRASH_DUMP + bool "/proc/vmcore support" + depends on PROC_FS && CRASH_DUMP default y help Exports the dump image of crashed kernel in ELF format. diff --git a/fs/proc/base.c b/fs/proc/base.c index dc5d5f51f3fe..53dc8ad40ae6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1023,28 +1023,47 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) - return -EFAULT; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } err = strict_strtol(strstrip(buffer), 0, &oom_adjust); if (err) - return -EINVAL; + goto out; if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) && - oom_adjust != OOM_DISABLE) - return -EINVAL; + oom_adjust != OOM_DISABLE) { + err = -EINVAL; + goto out; + } task = get_proc_task(file->f_path.dentry->d_inode); - if (!task) - return -ESRCH; + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + if (!lock_task_sighand(task, &flags)) { - put_task_struct(task); - return -ESRCH; + err = -ESRCH; + goto err_task_lock; } if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) { - unlock_task_sighand(task, &flags); - put_task_struct(task); - return -EACCES; + err = -EACCES; + goto err_sighand; + } + + if (oom_adjust != task->signal->oom_adj) { + if (oom_adjust == OOM_DISABLE) + atomic_inc(&task->mm->oom_disable_count); + if (task->signal->oom_adj == OOM_DISABLE) + atomic_dec(&task->mm->oom_disable_count); } /* @@ -1065,10 +1084,13 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, else task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; +err_sighand: unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); put_task_struct(task); - - return count; +out: + return err < 0 ? err : count; } static const struct file_operations proc_oom_adjust_operations = { @@ -1109,30 +1131,49 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) - return -EFAULT; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } err = strict_strtol(strstrip(buffer), 0, &oom_score_adj); if (err) - return -EINVAL; + goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || - oom_score_adj > OOM_SCORE_ADJ_MAX) - return -EINVAL; + oom_score_adj > OOM_SCORE_ADJ_MAX) { + err = -EINVAL; + goto out; + } task = get_proc_task(file->f_path.dentry->d_inode); - if (!task) - return -ESRCH; - if (!lock_task_sighand(task, &flags)) { - put_task_struct(task); - return -ESRCH; - } - if (oom_score_adj < task->signal->oom_score_adj && - !capable(CAP_SYS_RESOURCE)) { - unlock_task_sighand(task, &flags); - put_task_struct(task); - return -EACCES; + if (!task) { + err = -ESRCH; + goto out; } + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + if (oom_score_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + if (oom_score_adj != task->signal->oom_score_adj) { + if (oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_inc(&task->mm->oom_disable_count); + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&task->mm->oom_disable_count); + } task->signal->oom_score_adj = oom_score_adj; /* * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is @@ -1143,9 +1184,13 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, else task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) / OOM_SCORE_ADJ_MAX; +err_sighand: unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); put_task_struct(task); - return count; +out: + return err < 0 ? err : count; } static const struct file_operations proc_oom_score_adj_operations = { diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index caa758377d66..c1f93896cb53 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2438,7 +2438,7 @@ static int reiserfs_write_full_page(struct page *page, /* from this point on, we know the buffer is mapped to a * real block and not a direct item */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else { if (!trylock_buffer(bh)) { diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index b552f816de15..c9af48fffcd7 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -1139,8 +1139,7 @@ xfs_vm_writepage( type = IO_DELAY; flags = BMAPI_ALLOCATE; - if (wbc->sync_mode == WB_SYNC_NONE && - wbc->nonblocking) + if (wbc->sync_mode == WB_SYNC_NONE) flags |= BMAPI_TRYLOCK; } diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f4229fb315e1..2c0fc10956ba 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -150,6 +150,7 @@ #define DATA_DATA \ *(.data) \ *(.ref.data) \ + *(.data..shared_aligned) /* percpu related */ \ DEV_KEEP(init.data) \ DEV_KEEP(exit.data) \ CPU_KEEP(init.data) \ @@ -636,7 +637,7 @@ #ifdef CONFIG_BLK_DEV_INITRD #define INIT_RAM_FS \ - . = ALIGN(PAGE_SIZE); \ + . = ALIGN(4); \ VMLINUX_SYMBOL(__initramfs_start) = .; \ *(.init.ramfs) \ VMLINUX_SYMBOL(__initramfs_end) = .; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 35b00746c712..4ce34fa937d4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -111,6 +111,7 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); extern spinlock_t bdi_lock; extern struct list_head bdi_list; +extern struct list_head bdi_pending_list; static inline int wb_has_dirty_io(struct bdi_writeback *wb) { @@ -285,7 +286,7 @@ enum { void clear_bdi_congested(struct backing_dev_info *bdi, int sync); void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); - +long wait_iff_congested(struct zone *zone, int sync, long timeout); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { diff --git a/include/linux/fs.h b/include/linux/fs.h index bb20373d0b46..4658777b41cc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,9 +34,9 @@ /* And dynamically-tunable limits and defaults: */ struct files_stat_struct { - int nr_files; /* read only */ - int nr_free_files; /* read only */ - int max_files; /* tunable */ + unsigned long nr_files; /* read only */ + unsigned long nr_free_files; /* read only */ + unsigned long max_files; /* tunable */ }; struct inodes_stat_t { @@ -402,7 +402,7 @@ extern void __init inode_init_early(void); extern void __init files_init(unsigned long); extern struct files_stat_struct files_stat; -extern int get_max_files(void); +extern unsigned long get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 975609cb8548..e8713d55360a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -9,6 +9,32 @@ struct vm_area_struct; +/* Plain integer GFP bitmasks. Do not use this directly. */ +#define ___GFP_DMA 0x01u +#define ___GFP_HIGHMEM 0x02u +#define ___GFP_DMA32 0x04u +#define ___GFP_MOVABLE 0x08u +#define ___GFP_WAIT 0x10u +#define ___GFP_HIGH 0x20u +#define ___GFP_IO 0x40u +#define ___GFP_FS 0x80u +#define ___GFP_COLD 0x100u +#define ___GFP_NOWARN 0x200u +#define ___GFP_REPEAT 0x400u +#define ___GFP_NOFAIL 0x800u +#define ___GFP_NORETRY 0x1000u +#define ___GFP_COMP 0x4000u +#define ___GFP_ZERO 0x8000u +#define ___GFP_NOMEMALLOC 0x10000u +#define ___GFP_HARDWALL 0x20000u +#define ___GFP_THISNODE 0x40000u +#define ___GFP_RECLAIMABLE 0x80000u +#ifdef CONFIG_KMEMCHECK +#define ___GFP_NOTRACK 0x200000u +#else +#define ___GFP_NOTRACK 0 +#endif + /* * GFP bitmasks.. * @@ -18,10 +44,10 @@ struct vm_area_struct; * without the underscores and use them consistently. The definitions here may * be used in bit comparisons. */ -#define __GFP_DMA ((__force gfp_t)0x01u) -#define __GFP_HIGHMEM ((__force gfp_t)0x02u) -#define __GFP_DMA32 ((__force gfp_t)0x04u) -#define __GFP_MOVABLE ((__force gfp_t)0x08u) /* Page is movable */ +#define __GFP_DMA ((__force gfp_t)___GFP_DMA) +#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) +#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) +#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* Page is movable */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) /* * Action modifiers - doesn't change the zoning @@ -38,27 +64,22 @@ struct vm_area_struct; * __GFP_MOVABLE: Flag that this page will be movable by the page migration * mechanism or reclaimed */ -#define __GFP_WAIT ((__force gfp_t)0x10u) /* Can wait and reschedule? */ -#define __GFP_HIGH ((__force gfp_t)0x20u) /* Should access emergency pools? */ -#define __GFP_IO ((__force gfp_t)0x40u) /* Can start physical IO? */ -#define __GFP_FS ((__force gfp_t)0x80u) /* Can call down to low-level FS? */ -#define __GFP_COLD ((__force gfp_t)0x100u) /* Cache-cold page required */ -#define __GFP_NOWARN ((__force gfp_t)0x200u) /* Suppress page allocation failure warning */ -#define __GFP_REPEAT ((__force gfp_t)0x400u) /* See above */ -#define __GFP_NOFAIL ((__force gfp_t)0x800u) /* See above */ -#define __GFP_NORETRY ((__force gfp_t)0x1000u)/* See above */ -#define __GFP_COMP ((__force gfp_t)0x4000u)/* Add compound page metadata */ -#define __GFP_ZERO ((__force gfp_t)0x8000u)/* Return zeroed page on success */ -#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */ -#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */ -#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */ -#define __GFP_RECLAIMABLE ((__force gfp_t)0x80000u) /* Page is reclaimable */ - -#ifdef CONFIG_KMEMCHECK -#define __GFP_NOTRACK ((__force gfp_t)0x200000u) /* Don't track with kmemcheck */ -#else -#define __GFP_NOTRACK ((__force gfp_t)0) -#endif +#define __GFP_WAIT ((__force gfp_t)___GFP_WAIT) /* Can wait and reschedule? */ +#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) /* Should access emergency pools? */ +#define __GFP_IO ((__force gfp_t)___GFP_IO) /* Can start physical IO? */ +#define __GFP_FS ((__force gfp_t)___GFP_FS) /* Can call down to low-level FS? */ +#define __GFP_COLD ((__force gfp_t)___GFP_COLD) /* Cache-cold page required */ +#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) /* Suppress page allocation failure warning */ +#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) /* See above */ +#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) /* See above */ +#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /* See above */ +#define __GFP_COMP ((__force gfp_t)___GFP_COMP) /* Add compound page metadata */ +#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Return zeroed page on success */ +#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves */ +#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */ +#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */ +#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ +#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ /* * This may seem redundant, but it's a way of annotating false positives vs. @@ -186,14 +207,14 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) #endif #define GFP_ZONE_TABLE ( \ - (ZONE_NORMAL << 0 * ZONES_SHIFT) \ - | (OPT_ZONE_DMA << __GFP_DMA * ZONES_SHIFT) \ - | (OPT_ZONE_HIGHMEM << __GFP_HIGHMEM * ZONES_SHIFT) \ - | (OPT_ZONE_DMA32 << __GFP_DMA32 * ZONES_SHIFT) \ - | (ZONE_NORMAL << __GFP_MOVABLE * ZONES_SHIFT) \ - | (OPT_ZONE_DMA << (__GFP_MOVABLE | __GFP_DMA) * ZONES_SHIFT) \ - | (ZONE_MOVABLE << (__GFP_MOVABLE | __GFP_HIGHMEM) * ZONES_SHIFT)\ - | (OPT_ZONE_DMA32 << (__GFP_MOVABLE | __GFP_DMA32) * ZONES_SHIFT)\ + (ZONE_NORMAL << 0 * ZONES_SHIFT) \ + | (OPT_ZONE_DMA << ___GFP_DMA * ZONES_SHIFT) \ + | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * ZONES_SHIFT) \ + | (OPT_ZONE_DMA32 << ___GFP_DMA32 * ZONES_SHIFT) \ + | (ZONE_NORMAL << ___GFP_MOVABLE * ZONES_SHIFT) \ + | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * ZONES_SHIFT) \ + | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * ZONES_SHIFT) \ + | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * ZONES_SHIFT) \ ) /* @@ -203,20 +224,20 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) * allowed. */ #define GFP_ZONE_BAD ( \ - 1 << (__GFP_DMA | __GFP_HIGHMEM) \ - | 1 << (__GFP_DMA | __GFP_DMA32) \ - | 1 << (__GFP_DMA32 | __GFP_HIGHMEM) \ - | 1 << (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM) \ - | 1 << (__GFP_MOVABLE | __GFP_HIGHMEM | __GFP_DMA) \ - | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_DMA) \ - | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_HIGHMEM) \ - | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_DMA | __GFP_HIGHMEM)\ + 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ + | 1 << (___GFP_DMA | ___GFP_DMA32) \ + | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ + | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ + | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ + | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ + | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ + | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; - int bit = flags & GFP_ZONEMASK; + int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) & ((1 << ZONES_SHIFT) - 1); diff --git a/include/linux/highmem.h b/include/linux/highmem.h index e3060ef85b6d..8a85ec109a3a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -28,18 +28,6 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #include -#ifdef CONFIG_DEBUG_HIGHMEM - -void debug_kmap_atomic(enum km_type type); - -#else - -static inline void debug_kmap_atomic(enum km_type type) -{ -} - -#endif - #ifdef CONFIG_HIGHMEM #include @@ -49,6 +37,27 @@ extern unsigned long totalhigh_pages; void kmap_flush_unused(void); +DECLARE_PER_CPU(int, __kmap_atomic_idx); + +static inline int kmap_atomic_idx_push(void) +{ + int idx = __get_cpu_var(__kmap_atomic_idx)++; +#ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(in_irq() && !irqs_disabled()); + BUG_ON(idx > KM_TYPE_NR); +#endif + return idx; +} + +static inline int kmap_atomic_idx_pop(void) +{ + int idx = --__get_cpu_var(__kmap_atomic_idx); +#ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(idx < 0); +#endif + return idx; +} + #else /* CONFIG_HIGHMEM */ static inline unsigned int nr_free_highpages(void) { return 0; } @@ -66,19 +75,19 @@ static inline void kunmap(struct page *page) { } -static inline void *kmap_atomic(struct page *page, enum km_type idx) +static inline void *__kmap_atomic(struct page *page) { pagefault_disable(); return page_address(page); } -#define kmap_atomic_prot(page, idx, prot) kmap_atomic(page, idx) +#define kmap_atomic_prot(page, prot) __kmap_atomic(page) -static inline void kunmap_atomic_notypecheck(void *addr, enum km_type idx) +static inline void __kunmap_atomic(void *addr) { pagefault_enable(); } -#define kmap_atomic_pfn(pfn, idx) kmap_atomic(pfn_to_page(pfn), (idx)) +#define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) #define kmap_atomic_to_page(ptr) virt_to_page(ptr) #define kmap_flush_unused() do {} while(0) @@ -86,12 +95,20 @@ static inline void kunmap_atomic_notypecheck(void *addr, enum km_type idx) #endif /* CONFIG_HIGHMEM */ -/* Prevent people trying to call kunmap_atomic() as if it were kunmap() */ -/* kunmap_atomic() should get the return value of kmap_atomic, not the page. */ -#define kunmap_atomic(addr, idx) do { \ - BUILD_BUG_ON(__same_type((addr), struct page *)); \ - kunmap_atomic_notypecheck((addr), (idx)); \ - } while (0) +/* + * Make both: kmap_atomic(page, idx) and kmap_atomic(page) work. + */ +#define kmap_atomic(page, args...) __kmap_atomic(page) + +/* + * Prevent people trying to call kunmap_atomic() as if it were kunmap() + * kunmap_atomic() should get the return value of kmap_atomic, not the page. + */ +#define kunmap_atomic(addr, args...) \ +do { \ + BUILD_BUG_ON(__same_type((addr), struct page *)); \ + __kunmap_atomic(addr); \ +} while (0) /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage @@ -201,8 +218,8 @@ static inline void copy_user_highpage(struct page *to, struct page *from, vfrom = kmap_atomic(from, KM_USER0); vto = kmap_atomic(to, KM_USER1); copy_user_page(vto, vfrom, vaddr, to); - kunmap_atomic(vfrom, KM_USER0); kunmap_atomic(vto, KM_USER1); + kunmap_atomic(vfrom, KM_USER0); } #endif @@ -214,8 +231,8 @@ static inline void copy_highpage(struct page *to, struct page *from) vfrom = kmap_atomic(from, KM_USER0); vto = kmap_atomic(to, KM_USER1); copy_page(vto, vfrom); - kunmap_atomic(vfrom, KM_USER0); kunmap_atomic(vto, KM_USER1); + kunmap_atomic(vfrom, KM_USER0); } #endif /* _LINUX_HIGHMEM_H */ diff --git a/include/linux/i2c/apds990x.h b/include/linux/i2c/apds990x.h new file mode 100644 index 000000000000..d186fcc5d257 --- /dev/null +++ b/include/linux/i2c/apds990x.h @@ -0,0 +1,79 @@ +/* + * This file is part of the APDS990x sensor driver. + * Chip is combined proximity and ambient light sensor. + * + * Copyright (C) 2010 Nokia Corporation and/or its subsidiary(-ies). + * + * Contact: Samu Onkalo + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#ifndef __APDS990X_H__ +#define __APDS990X_H__ + + +#define APDS_IRLED_CURR_12mA 0x3 +#define APDS_IRLED_CURR_25mA 0x2 +#define APDS_IRLED_CURR_50mA 0x1 +#define APDS_IRLED_CURR_100mA 0x0 + +/** + * struct apds990x_chip_factors - defines effect of the cover window + * @ga: Total glass attenuation + * @cf1: clear channel factor 1 for raw to lux conversion + * @irf1: IR channel factor 1 for raw to lux conversion + * @cf2: clear channel factor 2 for raw to lux conversion + * @irf2: IR channel factor 2 for raw to lux conversion + * @df: device factor for conversion formulas + * + * Structure for tuning ALS calculation to match with environment. + * Values depend on the material above the sensor and the sensor + * itself. If the GA is zero, driver will use uncovered sensor default values + * format: decimal value * APDS_PARAM_SCALE except df which is plain integer. + */ +#define APDS_PARAM_SCALE 4096 +struct apds990x_chip_factors { + int ga; + int cf1; + int irf1; + int cf2; + int irf2; + int df; +}; + +/** + * struct apds990x_platform_data - platform data for apsd990x.c driver + * @cf: chip factor data + * @pddrive: IR-led driving current + * @ppcount: number of IR pulses used for proximity estimation + * @setup_resources: interrupt line setup call back function + * @release_resources: interrupt line release call back function + * + * Proximity detection result depends heavily on correct ppcount, pdrive + * and cover window. + * + */ + +struct apds990x_platform_data { + struct apds990x_chip_factors cf; + u8 pdrive; + u8 ppcount; + int (*setup_resources)(void); + int (*release_resources)(void); +}; + +#endif diff --git a/include/linux/i2c/bh1770glc.h b/include/linux/i2c/bh1770glc.h new file mode 100644 index 000000000000..8b5e2df36c72 --- /dev/null +++ b/include/linux/i2c/bh1770glc.h @@ -0,0 +1,53 @@ +/* + * This file is part of the ROHM BH1770GLC / OSRAM SFH7770 sensor driver. + * Chip is combined proximity and ambient light sensor. + * + * Copyright (C) 2010 Nokia Corporation and/or its subsidiary(-ies). + * + * Contact: Samu Onkalo + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#ifndef __BH1770_H__ +#define __BH1770_H__ + +/** + * struct bh1770_platform_data - platform data for bh1770glc driver + * @led_def_curr: IR led driving current. + * @glass_attenuation: Attenuation factor for covering window. + * @setup_resources: Call back for interrupt line setup function + * @release_resources: Call back for interrupte line release function + * + * Example of glass attenuation: 16384 * 385 / 100 means attenuation factor + * of 3.85. i.e. light_above_sensor = light_above_cover_window / 3.85 + */ + +struct bh1770_platform_data { +#define BH1770_LED_5mA 0 +#define BH1770_LED_10mA 1 +#define BH1770_LED_20mA 2 +#define BH1770_LED_50mA 3 +#define BH1770_LED_100mA 4 +#define BH1770_LED_150mA 5 +#define BH1770_LED_200mA 6 + __u8 led_def_curr; +#define BH1770_NEUTRAL_GA 16384 /* 16384 / 16384 = 1 */ + __u32 glass_attenuation; + int (*setup_resources)(void); + int (*release_resources)(void); +}; +#endif diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 7fb592793738..8cdcc2a199ad 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -81,8 +81,7 @@ io_mapping_free(struct io_mapping *mapping) /* Atomic map/unmap */ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, - unsigned long offset, - int slot) + unsigned long offset) { resource_size_t phys_addr; unsigned long pfn; @@ -90,13 +89,13 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; pfn = (unsigned long) (phys_addr >> PAGE_SHIFT); - return iomap_atomic_prot_pfn(pfn, slot, mapping->prot); + return iomap_atomic_prot_pfn(pfn, mapping->prot); } static inline void -io_mapping_unmap_atomic(void __iomem *vaddr, int slot) +io_mapping_unmap_atomic(void __iomem *vaddr) { - iounmap_atomic(vaddr, slot); + iounmap_atomic(vaddr); } static inline void __iomem * @@ -137,14 +136,13 @@ io_mapping_free(struct io_mapping *mapping) /* Atomic map/unmap */ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, - unsigned long offset, - int slot) + unsigned long offset) { return ((char __force __iomem *) mapping) + offset; } static inline void -io_mapping_unmap_atomic(void __iomem *vaddr, int slot) +io_mapping_unmap_atomic(void __iomem *vaddr) { } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index edef168a0406..450092c1e35f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -173,6 +173,11 @@ extern int _cond_resched(void); (__x < 0) ? -__x : __x; \ }) +#define abs64(x) ({ \ + s64 __x = (x); \ + (__x < 0) ? -__x : __x; \ + }) + #ifdef CONFIG_PROVE_LOCKING void might_fault(void); #else @@ -203,10 +208,10 @@ extern unsigned long simple_strtoul(const char *,char **,unsigned int); extern long simple_strtol(const char *,char **,unsigned int); extern unsigned long long simple_strtoull(const char *,char **,unsigned int); extern long long simple_strtoll(const char *,char **,unsigned int); -extern int strict_strtoul(const char *, unsigned int, unsigned long *); -extern int strict_strtol(const char *, unsigned int, long *); -extern int strict_strtoull(const char *, unsigned int, unsigned long long *); -extern int strict_strtoll(const char *, unsigned int, long long *); +extern int __must_check strict_strtoul(const char *, unsigned int, unsigned long *); +extern int __must_check strict_strtol(const char *, unsigned int, long *); +extern int __must_check strict_strtoull(const char *, unsigned int, unsigned long long *); +extern int __must_check strict_strtoll(const char *, unsigned int, long long *); extern int sprintf(char * buf, const char * fmt, ...) __attribute__ ((format (printf, 2, 3))); extern int vsprintf(char *buf, const char *, va_list) @@ -277,6 +282,11 @@ asmlinkage int vprintk(const char *fmt, va_list args) asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; +/* + * Please don't use printk_ratelimit(), because it shares ratelimiting state + * with all other unrelated printk_ratelimit() callsites. Instead use + * printk_ratelimited() or plain old __ratelimit(). + */ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, @@ -651,6 +661,24 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } (void) (&_max1 == &_max2); \ _max1 > _max2 ? _max1 : _max2; }) +#define min3(x, y, z) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + typeof(z) _min3 = (z); \ + (void) (&_min1 == &_min2); \ + (void) (&_min1 == &_min3); \ + _min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \ + (_min2 < _min3 ? _min2 : _min3); }) + +#define max3(x, y, z) ({ \ + typeof(x) _max1 = (x); \ + typeof(y) _max2 = (y); \ + typeof(z) _max3 = (z); \ + (void) (&_max1 == &_max2); \ + (void) (&_max1 == &_max3); \ + _max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \ + (_max2 > _max3 ? _max2 : _max3); }) + /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero * @x: value1 diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 62dbee554f60..c238ad2f82ea 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -171,11 +171,8 @@ struct kfifo_rec_ptr_2 __STRUCT_KFIFO_PTR(unsigned char, 2, void); } -static inline unsigned int __must_check -__kfifo_must_check_helper(unsigned int val) -{ - return val; -} +/* __kfifo_must_check_helper() is temporarily disabled because it was faulty */ +#define __kfifo_must_check_helper(x) (x) /** * kfifo_initialized - Check if the fifo is initialized diff --git a/include/linux/math64.h b/include/linux/math64.h index c87f1528703a..23fcdfcba81b 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -35,6 +35,14 @@ static inline u64 div64_u64(u64 dividend, u64 divisor) return dividend / divisor; } +/** + * div64_s64 - signed 64bit divide with 64bit divisor + */ +static inline s64 div64_s64(s64 dividend, s64 divisor) +{ + return dividend / divisor; +} + #elif BITS_PER_LONG == 32 #ifndef div_u64_rem @@ -53,6 +61,10 @@ extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); extern u64 div64_u64(u64 dividend, u64 divisor); #endif +#ifndef div64_s64 +extern s64 div64_s64(s64 dividend, s64 divisor); +#endif + #endif /* BITS_PER_LONG */ /** diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 864035fb8f8a..4307231bd22f 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -70,6 +70,10 @@ extern void online_page(struct page *page); extern int online_pages(unsigned long, unsigned long); extern void __offline_isolated_pages(unsigned long, unsigned long); +#ifdef CONFIG_MEMORY_HOTREMOVE +extern bool is_pageblock_removable_nolock(struct page *page); +#endif /* CONFIG_MEMORY_HOTREMOVE */ + /* reasonably generic interface to expand the physical pages in a zone */ extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); diff --git a/include/linux/mm.h b/include/linux/mm.h index a4c66846fb8f..721f451c3029 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -144,6 +144,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ +#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is @@ -497,8 +498,8 @@ static inline void set_compound_order(struct page *page, unsigned long order) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) -/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */ -#ifdef NODE_NOT_IN_PAGEFLAGS +/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ +#ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) @@ -723,6 +724,7 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ +#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ @@ -868,6 +870,7 @@ int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_dirtied(struct page *page, struct address_space *mapping); +void account_page_writeback(struct page *page); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); @@ -1031,7 +1034,15 @@ extern void unregister_shrinker(struct shrinker *); int vma_wants_writenotify(struct vm_area_struct *vma); -extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); +extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl); +static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) +{ + pte_t *ptep; + __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); + return ptep; +} #ifdef __PAGETABLE_PUD_FOLDED static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cb57d657ce4d..bb7288a782fd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -310,6 +310,8 @@ struct mm_struct { #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_mm *mmu_notifier_mm; #endif + /* How many tasks sharing this mm are OOM_DISABLE */ + atomic_t oom_disable_count; }; /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3984c4eb41fd..39c24ebe9cfd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -104,6 +104,8 @@ enum zone_stat_item { NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ + NR_DIRTIED, /* page dirtyings since bootup */ + NR_WRITTEN, /* page writings since bootup */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -421,6 +423,9 @@ struct zone { typedef enum { ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */ + ZONE_CONGESTED, /* zone has many dirty pages backed by + * a congested BDI + */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -438,6 +443,11 @@ static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag) clear_bit(flag, &zone->flags); } +static inline int zone_is_reclaim_congested(const struct zone *zone) +{ + return test_bit(ZONE_CONGESTED, &zone->flags); +} + static inline int zone_is_reclaim_locked(const struct zone *zone) { return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 9d2f1837b3d8..112adf8bd47d 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -21,8 +21,8 @@ #define __module_cat(a,b) ___module_cat(a,b) #define __MODULE_INFO(tag, name, info) \ static const char __module_cat(name,__LINE__)[] \ - __used \ - __attribute__((section(".modinfo"),unused)) = __stringify(tag) "=" info + __used __attribute__((section(".modinfo"), unused, aligned(1))) \ + = __stringify(tag) "=" info #else /* !MODULE */ #define __MODULE_INFO(tag, name, info) #endif diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index e8c06122be36..19ef95d293ae 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -67,7 +67,8 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, #define get_pageblock_flags(page) \ get_pageblock_flags_group(page, 0, NR_PAGEBLOCK_BITS-1) -#define set_pageblock_flags(page) \ - set_pageblock_flags_group(page, 0, NR_PAGEBLOCK_BITS-1) +#define set_pageblock_flags(page, flags) \ + set_pageblock_flags_group(page, flags, \ + 0, NR_PAGEBLOCK_BITS-1) #endif /* PAGEBLOCK_FLAGS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e12cdc6d79ee..2d1ffe3cf1ee 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -299,6 +299,8 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); extern void __lock_page_nosync(struct page *page); +extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, + unsigned int flags); extern void unlock_page(struct page *page); static inline void __set_page_locked(struct page *page) @@ -350,6 +352,17 @@ static inline void lock_page_nosync(struct page *page) __lock_page_nosync(page); } +/* + * lock_page_or_retry - Lock the page, unless this would block and the + * caller indicated that it can handle a retry. + */ +static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, + unsigned int flags) +{ + might_sleep(); + return trylock_page(page) || __lock_page_or_retry(page, mm, flags); +} + /* * This is exported only for wait_on_page_locked/wait_on_page_writeback. * Never use this directly! diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 8f69d09a41a5..03ff67b0cdf5 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -36,6 +36,8 @@ static inline void ratelimit_state_init(struct ratelimit_state *rs, rs->begin = 0; } +extern struct ratelimit_state printk_ratelimit_state; + extern int ___ratelimit(struct ratelimit_state *rs, const char *func); #define __ratelimit(state) ___ratelimit(state, __func__) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 31b2fd75dcba..bb83c0da2071 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -25,8 +25,8 @@ * pointing to this anon_vma once its vma list is empty. */ struct anon_vma { - spinlock_t lock; /* Serialize access to vma list */ struct anon_vma *root; /* Root of this anon_vma tree */ + spinlock_t lock; /* Serialize access to vma list */ #if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION) /* @@ -205,9 +205,20 @@ int try_to_unmap_one(struct page *, struct vm_area_struct *, /* * Called from mm/filemap_xip.c to unmap empty zero page */ -pte_t *page_check_address(struct page *, struct mm_struct *, +pte_t *__page_check_address(struct page *, struct mm_struct *, unsigned long, spinlock_t **, int); +static inline pte_t *page_check_address(struct page *page, struct mm_struct *mm, + unsigned long address, + spinlock_t **ptlp, int sync) +{ + pte_t *ptep; + + __cond_lock(*ptlp, ptep = __page_check_address(page, mm, address, + ptlp, sync)); + return ptep; +} + /* * Used by swapoff to help locate where page is expected in vma. */ @@ -230,7 +241,20 @@ int try_to_munlock(struct page *); /* * Called by memory-failure.c to kill processes. */ -struct anon_vma *page_lock_anon_vma(struct page *page); +struct anon_vma *__page_lock_anon_vma(struct page *page); + +static inline struct anon_vma *page_lock_anon_vma(struct page *page) +{ + struct anon_vma *anon_vma; + + __cond_lock(RCU, anon_vma = __page_lock_anon_vma(page)); + + /* (void) is needed to make gcc happy */ + (void) __cond_lock(&anon_vma->root->lock, anon_vma); + + return anon_vma; +} + void page_unlock_anon_vma(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); diff --git a/include/linux/sched.h b/include/linux/sched.h index 56154bbb8da9..393ce94e54b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1706,7 +1706,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_DUMPCORE 0x00000200 /* dumped core */ #define PF_SIGNALED 0x00000400 /* killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory */ -#define PF_FLUSHER 0x00001000 /* responsible for disk writeback */ #define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */ #define PF_FREEZING 0x00004000 /* freeze in progress. do not account to load */ #define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 7cdd63366f88..eba53e71d2cc 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -271,8 +271,18 @@ extern void scan_mapping_unevictable_pages(struct address_space *); extern unsigned long scan_unevictable_pages; extern int scan_unevictable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +#ifdef CONFIG_NUMA extern int scan_unevictable_register_node(struct node *node); extern void scan_unevictable_unregister_node(struct node *node); +#else +static inline int scan_unevictable_register_node(struct node *node) +{ + return 0; +} +static inline void scan_unevictable_unregister_node(struct node *node) +{ +} +#endif extern int kswapd_run(int nid); extern void kswapd_stop(int nid); diff --git a/include/linux/types.h b/include/linux/types.h index 357dbc19606f..c2a9eb44f2fa 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -121,15 +121,7 @@ typedef __u64 u_int64_t; typedef __s64 int64_t; #endif -/* - * aligned_u64 should be used in defining kernel<->userspace ABIs to avoid - * common 32/64-bit compat problems. - * 64-bit values align to 4-byte boundaries on x86_32 (and possibly other - * architectures) and to 8-byte boundaries on 64-bit architetures. The new - * aligned_64 type enforces 8-byte alignment so that structs containing - * aligned_64 values have the same alignment on 32-bit and 64-bit architectures. - * No conversions are necessary between 32-bit user-space and a 64-bit kernel. - */ +/* this is a special 64bit data type that is 8-byte aligned */ #define aligned_u64 __u64 __attribute__((aligned(8))) #define aligned_be64 __be64 __attribute__((aligned(8))) #define aligned_le64 __le64 __attribute__((aligned(8))) @@ -186,7 +178,15 @@ typedef __u64 __bitwise __be64; typedef __u16 __bitwise __sum16; typedef __u32 __bitwise __wsum; -/* this is a special 64bit data type that is 8-byte aligned */ +/* + * aligned_u64 should be used in defining kernel<->userspace ABIs to avoid + * common 32/64-bit compat problems. + * 64-bit values align to 4-byte boundaries on x86_32 (and possibly other + * architectures) and to 8-byte boundaries on 64-bit architetures. The new + * aligned_64 type enforces 8-byte alignment so that structs containing + * aligned_64 values have the same alignment on 32-bit and 64-bit architectures. + * No conversions are necessary between 32-bit user-space and a 64-bit kernel. + */ #define __aligned_u64 __u64 __attribute__((aligned(8))) #define __aligned_be64 __be64 __attribute__((aligned(8))) #define __aligned_le64 __le64 __attribute__((aligned(8))) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 63a4fe6d51bd..a03dcf62ca9d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -53,8 +53,10 @@ static inline void vmalloc_init(void) #endif extern void *vmalloc(unsigned long size); +extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); +extern void *vzalloc_node(unsigned long size, int node); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 070bb7a88936..0c0771f06bfa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -190,7 +190,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } __INIT_WORK((_work), (_func), 0); \ } while (0) -#define INIT_WORK_ON_STACK(_work, _func) \ +#define INIT_WORK_ONSTACK(_work, _func) \ do { \ __INIT_WORK((_work), (_func), 1); \ } while (0) @@ -201,9 +201,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } init_timer(&(_work)->timer); \ } while (0) -#define INIT_DELAYED_WORK_ON_STACK(_work, _func) \ +#define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ do { \ - INIT_WORK_ON_STACK(&(_work)->work, (_func)); \ + INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ init_timer_on_stack(&(_work)->timer); \ } while (0) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 72a5d647a5f2..c7299d2ace6b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -149,6 +149,8 @@ int write_cache_pages(struct address_space *mapping, int do_writepages(struct address_space *mapping, struct writeback_control *wbc); void set_page_dirty_balance(struct page *page, int page_mkwrite); void writeback_set_ratelimit(void); +void tag_pages_for_writeback(struct address_space *mapping, + pgoff_t start, pgoff_t end); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 01e9e0076a92..6bcb00645de4 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -242,18 +242,20 @@ TRACE_EVENT(ext4_da_writepages, __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; - __entry->nonblocking = wbc->nonblocking; __entry->for_kupdate = wbc->for_kupdate; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d writeback_index %lu", + TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld " + "range_start %llu range_end %llu " + "for_kupdate %d for_reclaim %d " + "range_cyclic %d writeback_index %lu", jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, - __entry->range_end, __entry->nonblocking, + __entry->range_end, __entry->for_kupdate, __entry->for_reclaim, __entry->range_cyclic, (unsigned long) __entry->writeback_index) diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 370aa5a87322..c255fcc587bf 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -10,6 +10,7 @@ #define RECLAIM_WB_ANON 0x0001u #define RECLAIM_WB_FILE 0x0002u +#define RECLAIM_WB_MIXED 0x0010u #define RECLAIM_WB_SYNC 0x0004u #define RECLAIM_WB_ASYNC 0x0008u @@ -17,13 +18,20 @@ (flags) ? __print_flags(flags, "|", \ {RECLAIM_WB_ANON, "RECLAIM_WB_ANON"}, \ {RECLAIM_WB_FILE, "RECLAIM_WB_FILE"}, \ + {RECLAIM_WB_MIXED, "RECLAIM_WB_MIXED"}, \ {RECLAIM_WB_SYNC, "RECLAIM_WB_SYNC"}, \ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" #define trace_reclaim_flags(page, sync) ( \ (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ - (sync == PAGEOUT_IO_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + (sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + ) + +#define trace_shrink_flags(file, sync) ( \ + (sync == LUMPY_MODE_SYNC ? RECLAIM_WB_MIXED : \ + (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) | \ + (sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ ) TRACE_EVENT(mm_vmscan_kswapd_sleep, @@ -269,6 +277,40 @@ TRACE_EVENT(mm_vmscan_writepage, show_reclaim_flags(__entry->reclaim_flags)) ); +TRACE_EVENT(mm_vmscan_lru_shrink_inactive, + + TP_PROTO(int nid, int zid, + unsigned long nr_scanned, unsigned long nr_reclaimed, + int priority, int reclaim_flags), + + TP_ARGS(nid, zid, nr_scanned, nr_reclaimed, priority, reclaim_flags), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, zid) + __field(unsigned long, nr_scanned) + __field(unsigned long, nr_reclaimed) + __field(int, priority) + __field(int, reclaim_flags) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->zid = zid; + __entry->nr_scanned = nr_scanned; + __entry->nr_reclaimed = nr_reclaimed; + __entry->priority = priority; + __entry->reclaim_flags = reclaim_flags; + ), + + TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s", + __entry->nid, __entry->zid, + __entry->nr_scanned, __entry->nr_reclaimed, + __entry->priority, + show_reclaim_flags(__entry->reclaim_flags)) +); + + #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index f345f66ae9d1..89a2b2db4375 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -96,8 +96,6 @@ DECLARE_EVENT_CLASS(wbc_class, __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) - __field(int, nonblocking) - __field(int, encountered_congestion) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) @@ -153,6 +151,41 @@ DEFINE_WBC_EVENT(wbc_balance_dirty_written); DEFINE_WBC_EVENT(wbc_balance_dirty_wait); DEFINE_WBC_EVENT(wbc_writepage); +DECLARE_EVENT_CLASS(writeback_congest_waited_template, + + TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), + + TP_ARGS(usec_timeout, usec_delayed), + + TP_STRUCT__entry( + __field( unsigned int, usec_timeout ) + __field( unsigned int, usec_delayed ) + ), + + TP_fast_assign( + __entry->usec_timeout = usec_timeout; + __entry->usec_delayed = usec_delayed; + ), + + TP_printk("usec_timeout=%u usec_delayed=%u", + __entry->usec_timeout, + __entry->usec_delayed) +); + +DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, + + TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), + + TP_ARGS(usec_timeout, usec_delayed) +); + +DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, + + TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), + + TP_ARGS(usec_timeout, usec_delayed) +); + #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ diff --git a/init/do_mounts.c b/init/do_mounts.c index 62a47eafa8e9..830aaec9c7d5 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -291,7 +291,7 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data) if (err) return err; - sys_chdir("/root"); + sys_chdir((const char __user __force *)"/root"); ROOT_DEV = current->fs->pwd.mnt->mnt_sb->s_dev; printk("VFS: Mounted root (%s filesystem)%s on device %u:%u.\n", current->fs->pwd.mnt->mnt_sb->s_type->name, @@ -488,5 +488,5 @@ void __init prepare_namespace(void) out: devtmpfs_mount("dev"); sys_mount(".", "/", NULL, MS_MOVE, NULL); - sys_chroot("."); + sys_chroot((const char __user __force *)"."); } diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 69aebbf8fd2d..32c4799b8c91 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -283,7 +283,7 @@ static void __init autodetect_raid(void) wait_for_device_probe(); - fd = sys_open("/dev/md0", 0, 0); + fd = sys_open((const char __user __force *) "/dev/md0", 0, 0); if (fd >= 0) { sys_ioctl(fd, RAID_AUTORUN, raid_autopart); sys_close(fd); diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index bf3ef667bf36..6e1ee6987c78 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -168,7 +168,7 @@ int __init rd_load_image(char *from) char rotator[4] = { '|' , '/' , '-' , '\\' }; #endif - out_fd = sys_open("/dev/ram", O_RDWR, 0); + out_fd = sys_open((const char __user __force *) "/dev/ram", O_RDWR, 0); if (out_fd < 0) goto out; @@ -267,7 +267,7 @@ int __init rd_load_image(char *from) sys_close(out_fd); out: kfree(buf); - sys_unlink("/dev/ram"); + sys_unlink((const char __user __force *) "/dev/ram"); return res; } diff --git a/init/initramfs.c b/init/initramfs.c index 4b9c20205092..d9c6e782ff53 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -528,7 +528,7 @@ static void __init clean_rootfs(void) struct linux_dirent64 *dirp; int num; - fd = sys_open("/", O_RDONLY, 0); + fd = sys_open((const char __user __force *) "/", O_RDONLY, 0); WARN_ON(fd < 0); if (fd < 0) return; @@ -590,7 +590,8 @@ static int __init populate_rootfs(void) } printk(KERN_INFO "rootfs image is not initramfs (%s)" "; looks like an initrd\n", err); - fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 0700); + fd = sys_open((const char __user __force *) "/initrd.image", + O_WRONLY|O_CREAT, 0700); if (fd >= 0) { sys_write(fd, (char *)initrd_start, initrd_end - initrd_start); diff --git a/init/noinitramfs.c b/init/noinitramfs.c index f4c1a3a1b8c5..267739d85179 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -29,17 +29,17 @@ static int __init default_rootfs(void) { int err; - err = sys_mkdir("/dev", 0755); + err = sys_mkdir((const char __user __force *) "/dev", 0755); if (err < 0) goto out; - err = sys_mknod((const char __user *) "/dev/console", + err = sys_mknod((const char __user __force *) "/dev/console", S_IFCHR | S_IRUSR | S_IWUSR, new_encode_dev(MKDEV(5, 1))); if (err < 0) goto out; - err = sys_mkdir("/root", 0700); + err = sys_mkdir((const char __user __force *) "/root", 0700); if (err < 0) goto out; diff --git a/kernel/exit.c b/kernel/exit.c index e2bdf37f9fde..894179a32ec1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -687,6 +688,8 @@ static void exit_mm(struct task_struct * tsk) enter_lazy_tlb(mm, current); /* We don't want this task to be frozen prematurely */ clear_freeze_flag(tsk); + if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&mm->oom_disable_count); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); diff --git a/kernel/fork.c b/kernel/fork.c index c445f8cc408d..e87aaaaf5131 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include @@ -488,6 +489,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); + atomic_set(&mm->oom_disable_count, 0); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; @@ -741,6 +743,8 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) /* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; + if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_inc(&mm->oom_disable_count); tsk->mm = mm; tsk->active_mm = mm; @@ -1299,8 +1303,13 @@ static struct task_struct *copy_process(unsigned long clone_flags, bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: - if (p->mm) + if (p->mm) { + task_lock(p); + if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&p->mm->oom_disable_count); + task_unlock(p); mmput(p->mm); + } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); @@ -1693,6 +1702,10 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) active_mm = current->active_mm; current->mm = new_mm; current->active_mm = new_mm; + if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + atomic_dec(&mm->oom_disable_count); + atomic_inc(&new_mm->oom_disable_count); + } activate_mm(active_mm, new_mm); new_mm = mm; } diff --git a/kernel/kexec.c b/kernel/kexec.c index c0613f7d6730..b55045bc7563 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -816,7 +816,7 @@ static int kimage_load_normal_segment(struct kimage *image, ptr = kmap(page); /* Start with a clear page */ - memset(ptr, 0, PAGE_SIZE); + clear_page(ptr); ptr += maddr & ~PAGE_MASK; mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK); if (mchunk > mbytes) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ac7eb109f196..0dac75ea4456 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -984,8 +984,8 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) src = kmap_atomic(s_page, KM_USER0); dst = kmap_atomic(d_page, KM_USER1); do_copy_page(dst, src); - kunmap_atomic(src, KM_USER0); kunmap_atomic(dst, KM_USER1); + kunmap_atomic(src, KM_USER0); } else { if (PageHighMem(d_page)) { /* Page pointed to by src may contain some kernel @@ -993,7 +993,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) */ safe_copy_page(buffer, s_page); dst = kmap_atomic(d_page, KM_USER0); - memcpy(dst, buffer, PAGE_SIZE); + copy_page(dst, buffer); kunmap_atomic(dst, KM_USER0); } else { safe_copy_page(page_address(d_page), s_page); @@ -1687,7 +1687,7 @@ int snapshot_read_next(struct snapshot_handle *handle) memory_bm_position_reset(&orig_bm); memory_bm_position_reset(©_bm); } else if (handle->cur <= nr_meta_pages) { - memset(buffer, 0, PAGE_SIZE); + clear_page(buffer); pack_pfns(buffer, &orig_bm); } else { struct page *page; @@ -1701,7 +1701,7 @@ int snapshot_read_next(struct snapshot_handle *handle) void *kaddr; kaddr = kmap_atomic(page, KM_USER0); - memcpy(buffer, kaddr, PAGE_SIZE); + copy_page(buffer, kaddr); kunmap_atomic(kaddr, KM_USER0); handle->buffer = buffer; } else { @@ -1984,7 +1984,7 @@ static void copy_last_highmem_page(void) void *dst; dst = kmap_atomic(last_highmem_page, KM_USER0); - memcpy(dst, buffer, PAGE_SIZE); + copy_page(dst, buffer); kunmap_atomic(dst, KM_USER0); last_highmem_page = NULL; } @@ -2270,11 +2270,11 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf) kaddr1 = kmap_atomic(p1, KM_USER0); kaddr2 = kmap_atomic(p2, KM_USER1); - memcpy(buf, kaddr1, PAGE_SIZE); - memcpy(kaddr1, kaddr2, PAGE_SIZE); - memcpy(kaddr2, buf, PAGE_SIZE); - kunmap_atomic(kaddr1, KM_USER0); + copy_page(buf, kaddr1); + copy_page(kaddr1, kaddr2); + copy_page(kaddr2, buf); kunmap_atomic(kaddr2, KM_USER1); + kunmap_atomic(kaddr1, KM_USER0); } /** diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 916eaa790399..a0e4a86ccf94 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -251,7 +251,7 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain) if (bio_chain) { src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); if (src) { - memcpy(src, buf, PAGE_SIZE); + copy_page(src, buf); } else { WARN_ON_ONCE(1); bio_chain = NULL; /* Go synchronous */ @@ -325,7 +325,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf, error = write_page(handle->cur, handle->cur_swap, NULL); if (error) goto out; - memset(handle->cur, 0, PAGE_SIZE); + clear_page(handle->cur); handle->cur_swap = offset; handle->k = 0; } @@ -910,7 +910,7 @@ int swsusp_check(void) hib_resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); - memset(swsusp_header, 0, PAGE_SIZE); + clear_page(swsusp_header); error = hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL); if (error) diff --git a/kernel/printk.c b/kernel/printk.c index 2531017795f6..b2ebaee8c377 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -210,7 +210,7 @@ __setup("log_buf_len=", log_buf_len_setup); #ifdef CONFIG_BOOT_PRINTK_DELAY -static unsigned int boot_delay; /* msecs delay after each printk during bootup */ +static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) @@ -647,6 +647,7 @@ static inline int can_use_console(unsigned int cpu) * released but interrupts still disabled. */ static int acquire_console_semaphore_for_printk(unsigned int cpu) + __releases(&logbuf_lock) { int retval = 0; @@ -1511,7 +1512,7 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper) } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); -static const char const *kmsg_reasons[] = { +static const char * const kmsg_reasons[] = { [KMSG_DUMP_OOPS] = "oops", [KMSG_DUMP_PANIC] = "panic", [KMSG_DUMP_KEXEC] = "kexec", diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 090c28812ce1..2df820b03beb 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -262,7 +262,7 @@ static int cpu_stopper_thread(void *data) cpu_stop_fn_t fn = work->fn; void *arg = work->arg; struct cpu_stop_done *done = work->done; - char ksym_buf[KSYM_NAME_LEN]; + char ksym_buf[KSYM_NAME_LEN] __maybe_unused; __set_current_state(TASK_RUNNING); @@ -304,7 +304,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, p = kthread_create(cpu_stopper_thread, stopper, "migration/%d", cpu); if (IS_ERR(p)) - return NOTIFY_BAD; + return notifier_from_errno(PTR_ERR(p)); get_task_struct(p); kthread_bind(p, cpu); sched_set_stop_task(cpu, p); @@ -372,7 +372,7 @@ static int __init cpu_stop_init(void) /* start one for the boot cpu */ err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE, bcpu); - BUG_ON(err == NOTIFY_BAD); + BUG_ON(err != NOTIFY_OK); cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu); register_cpu_notifier(&cpu_stop_cpu_notifier); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3a45c224770f..48d9d689498f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -161,8 +161,6 @@ extern int no_unaligned_warning; extern int unaligned_dump_stack; #endif -extern struct ratelimit_state printk_ratelimit_state; - #ifdef CONFIG_PROC_SYSCTL static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -1352,16 +1350,16 @@ static struct ctl_table fs_table[] = { { .procname = "file-nr", .data = &files_stat, - .maxlen = 3*sizeof(int), + .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, - .maxlen = sizeof(int), + .maxlen = sizeof(files_stat.max_files), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "nr_open", diff --git a/kernel/user.c b/kernel/user.c index 7e72614b736d..2c7d8d5914b1 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -91,6 +91,7 @@ static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) + __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e5ff2cbaadc2..90db1bd1a978 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2064,7 +2064,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * checks and call back into the fixup functions where we * might deadlock. */ - INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); + INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 69a32664c289..95bda87a3e84 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -317,6 +317,14 @@ config DEBUG_OBJECTS_RCU_HEAD help Enable this to turn on debugging of RCU list heads (call_rcu() usage). +config DEBUG_OBJECTS_PERCPU_COUNTER + bool "Debug percpu counter objects" + depends on DEBUG_OBJECTS + help + If you say Y here, additional code will be inserted into the + percpu counter routines to track the life time of percpu counter + objects and validate the percpu counter operations. + config DEBUG_OBJECTS_ENABLE_DEFAULT int "debug_objects bootup default value (0-1)" range 0 1 @@ -740,6 +748,15 @@ config DEBUG_LIST If unsure, say N. +config TEST_LIST_SORT + bool "Linked list sorting test" + depends on DEBUG_KERNEL + help + Enable this to turn on 'list_sort()' function test. This test is + executed only once during system boot, so affects only boot time. + + If unsure, say N. + config DEBUG_SG bool "Debug SG table operations" depends on DEBUG_KERNEL diff --git a/lib/bitmap.c b/lib/bitmap.c index ffb78c916ccd..741fae905ae3 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -359,7 +359,6 @@ EXPORT_SYMBOL(bitmap_find_next_zero_area); #define CHUNKSZ 32 #define nbits_to_hold_value(val) fls(val) -#define unhex(c) (isdigit(c) ? (c - '0') : (toupper(c) - 'A' + 10)) #define BASEDEC 10 /* fancier cpuset lists input in decimal */ /** @@ -466,7 +465,7 @@ int __bitmap_parse(const char *buf, unsigned int buflen, if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1)) return -EOVERFLOW; - chunk = (chunk << 4) | unhex(c); + chunk = (chunk << 4) | hex_to_bin(c); ndigits++; totaldigits++; } if (ndigits == 0) diff --git a/lib/div64.c b/lib/div64.c index a111eb8de9cf..5b4919191778 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -77,26 +77,58 @@ s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) EXPORT_SYMBOL(div_s64_rem); #endif -/* 64bit divisor, dividend and result. dynamic precision */ +/** + * div64_u64 - unsigned 64bit divide with 64bit divisor + * @dividend: 64bit dividend + * @divisor: 64bit divisor + * + * This implementation is a modified version of the algorithm proposed + * by the book 'Hacker's Delight'. The original source and full proof + * can be found here and is available for use without restriction. + * + * 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c' + */ #ifndef div64_u64 u64 div64_u64(u64 dividend, u64 divisor) { - u32 high, d; + u32 high = divisor >> 32; + u64 quot; - high = divisor >> 32; - if (high) { - unsigned int shift = fls(high); + if (high == 0) { + quot = div_u64(dividend, divisor); + } else { + int n = 1 + fls(high); + quot = div_u64(dividend >> n, divisor >> n); - d = divisor >> shift; - dividend >>= shift; - } else - d = divisor; + if (quot != 0) + quot--; + if ((dividend - quot * divisor) >= divisor) + quot++; + } - return div_u64(dividend, d); + return quot; } EXPORT_SYMBOL(div64_u64); #endif +/** + * div64_s64 - signed 64bit divide with 64bit divisor + * @dividend: 64bit dividend + * @divisor: 64bit divisor + */ +#ifndef div64_s64 +s64 div64_s64(s64 dividend, s64 divisor) +{ + s64 quot, t; + + quot = div64_u64(abs64(dividend), abs64(divisor)); + t = (dividend ^ divisor) >> 63; + + return (quot ^ t) - t; +} +EXPORT_SYMBOL(div64_s64); +#endif + #endif /* BITS_PER_LONG == 32 */ /* diff --git a/lib/idr.c b/lib/idr.c index 5e0966be0f7c..e35850d3004a 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -110,9 +110,10 @@ static void idr_mark_full(struct idr_layer **pa, int id) * @idp: idr handle * @gfp_mask: memory allocation flags * - * This function should be called prior to locking and calling the - * idr_get_new* functions. It preallocates enough memory to satisfy - * the worst possible allocation. + * This function should be called prior to calling the idr_get_new* functions. + * It preallocates enough memory to satisfy the worst possible allocation. The + * caller should pass in GFP_KERNEL if possible. This of course requires that + * no spinning locks be held. * * If the system is REALLY out of memory this function returns 0, * otherwise 1. @@ -290,9 +291,11 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id) * This is the allocate id function. It should be called with any * required locks. * - * If memory is required, it will return -EAGAIN, you should unlock - * and go back to the idr_pre_get() call. If the idr is full, it will - * return -ENOSPC. + * If allocation from IDR's private freelist fails, idr_get_new_above() will + * return -EAGAIN. The caller should retry the idr_pre_get() call to refill + * IDR's preallocation and then retry the idr_get_new_above() call. + * + * If the idr is full idr_get_new_above() will return -ENOSPC. * * @id returns a value in the range @starting_id ... 0x7fffffff */ @@ -318,12 +321,11 @@ EXPORT_SYMBOL(idr_get_new_above); * @ptr: pointer you want associated with the id * @id: pointer to the allocated handle * - * This is the allocate id function. It should be called with any - * required locks. + * If allocation from IDR's private freelist fails, idr_get_new_above() will + * return -EAGAIN. The caller should retry the idr_pre_get() call to refill + * IDR's preallocation and then retry the idr_get_new_above() call. * - * If memory is required, it will return -EAGAIN, you should unlock - * and go back to the idr_pre_get() call. If the idr is full, it will - * return -ENOSPC. + * If the idr is full idr_get_new_above() will return -ENOSPC. * * @id returns a value in the range 0 ... 0x7fffffff */ diff --git a/lib/list_sort.c b/lib/list_sort.c index a7616fa3162e..d7325c6b103f 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -141,77 +141,151 @@ void list_sort(void *priv, struct list_head *head, } EXPORT_SYMBOL(list_sort); -#ifdef DEBUG_LIST_SORT -struct debug_el { - struct list_head l_h; - int value; - unsigned serial; -}; +#ifdef CONFIG_TEST_LIST_SORT -static int cmp(void *priv, struct list_head *a, struct list_head *b) -{ - return container_of(a, struct debug_el, l_h)->value - - container_of(b, struct debug_el, l_h)->value; -} +#include /* * The pattern of set bits in the list length determines which cases * are hit in list_sort(). */ -#define LIST_SORT_TEST_LENGTH (512+128+2) /* not including head */ +#define TEST_LIST_LEN (512+128+2) /* not including head */ -static int __init list_sort_test(void) +#define TEST_POISON1 0xDEADBEEF +#define TEST_POISON2 0xA324354C + +struct debug_el { + unsigned int poison1; + struct list_head list; + unsigned int poison2; + int value; + unsigned serial; +}; + +/* Array, containing pointers to all elements in the test list */ +static struct debug_el **elts __initdata; + +static int __init check(struct debug_el *ela, struct debug_el *elb) { - int i, r = 1, count; - struct list_head *head = kmalloc(sizeof(*head), GFP_KERNEL); - struct list_head *cur; - - printk(KERN_WARNING "testing list_sort()\n"); - - cur = head; - for (i = 0; i < LIST_SORT_TEST_LENGTH; i++) { - struct debug_el *el = kmalloc(sizeof(*el), GFP_KERNEL); - BUG_ON(!el); - /* force some equivalencies */ - el->value = (r = (r * 725861) % 6599) % (LIST_SORT_TEST_LENGTH/3); - el->serial = i; - - el->l_h.prev = cur; - cur->next = &el->l_h; - cur = cur->next; + if (ela->serial >= TEST_LIST_LEN) { + printk(KERN_ERR "list_sort_test: error: incorrect serial %d\n", + ela->serial); + return -EINVAL; } - head->prev = cur; - - list_sort(NULL, head, cmp); - - count = 1; - for (cur = head->next; cur->next != head; cur = cur->next) { - struct debug_el *el = container_of(cur, struct debug_el, l_h); - int cmp_result = cmp(NULL, cur, cur->next); - if (cur->next->prev != cur) { - printk(KERN_EMERG "list_sort() returned " - "a corrupted list!\n"); - return 1; - } else if (cmp_result > 0) { - printk(KERN_EMERG "list_sort() failed to sort!\n"); - return 1; - } else if (cmp_result == 0 && - el->serial >= container_of(cur->next, - struct debug_el, l_h)->serial) { - printk(KERN_EMERG "list_sort() failed to preserve order" - " of equivalent elements!\n"); - return 1; - } - kfree(cur->prev); - count++; + if (elb->serial >= TEST_LIST_LEN) { + printk(KERN_ERR "list_sort_test: error: incorrect serial %d\n", + elb->serial); + return -EINVAL; } - kfree(cur); - if (count != LIST_SORT_TEST_LENGTH) { - printk(KERN_EMERG "list_sort() returned list of" - "different length!\n"); - return 1; + if (elts[ela->serial] != ela || elts[elb->serial] != elb) { + printk(KERN_ERR "list_sort_test: error: phantom element\n"); + return -EINVAL; + } + if (ela->poison1 != TEST_POISON1 || ela->poison2 != TEST_POISON2) { + printk(KERN_ERR "list_sort_test: error: bad poison: %#x/%#x\n", + ela->poison1, ela->poison2); + return -EINVAL; + } + if (elb->poison1 != TEST_POISON1 || elb->poison2 != TEST_POISON2) { + printk(KERN_ERR "list_sort_test: error: bad poison: %#x/%#x\n", + elb->poison1, elb->poison2); + return -EINVAL; } return 0; } + +static int __init cmp(void *priv, struct list_head *a, struct list_head *b) +{ + struct debug_el *ela, *elb; + + ela = container_of(a, struct debug_el, list); + elb = container_of(b, struct debug_el, list); + + check(ela, elb); + return ela->value - elb->value; +} + +static int __init list_sort_test(void) +{ + int i, count = 1, err = -EINVAL; + struct debug_el *el; + struct list_head *cur, *tmp; + LIST_HEAD(head); + + printk(KERN_DEBUG "list_sort_test: start testing list_sort()\n"); + + elts = kmalloc(sizeof(void *) * TEST_LIST_LEN, GFP_KERNEL); + if (!elts) { + printk(KERN_ERR "list_sort_test: error: cannot allocate " + "memory\n"); + goto exit; + } + + for (i = 0; i < TEST_LIST_LEN; i++) { + el = kmalloc(sizeof(*el), GFP_KERNEL); + if (!el) { + printk(KERN_ERR "list_sort_test: error: cannot " + "allocate memory\n"); + goto exit; + } + /* force some equivalencies */ + el->value = random32() % (TEST_LIST_LEN/3); + el->serial = i; + el->poison1 = TEST_POISON1; + el->poison2 = TEST_POISON2; + elts[i] = el; + list_add_tail(&el->list, &head); + } + + list_sort(NULL, &head, cmp); + + for (cur = head.next; cur->next != &head; cur = cur->next) { + struct debug_el *el1; + int cmp_result; + + if (cur->next->prev != cur) { + printk(KERN_ERR "list_sort_test: error: list is " + "corrupted\n"); + goto exit; + } + + cmp_result = cmp(NULL, cur, cur->next); + if (cmp_result > 0) { + printk(KERN_ERR "list_sort_test: error: list is not " + "sorted\n"); + goto exit; + } + + el = container_of(cur, struct debug_el, list); + el1 = container_of(cur->next, struct debug_el, list); + if (cmp_result == 0 && el->serial >= el1->serial) { + printk(KERN_ERR "list_sort_test: error: order of " + "equivalent elements not preserved\n"); + goto exit; + } + + if (check(el, el1)) { + printk(KERN_ERR "list_sort_test: error: element check " + "failed\n"); + goto exit; + } + count++; + } + + if (count != TEST_LIST_LEN) { + printk(KERN_ERR "list_sort_test: error: bad list length %d", + count); + goto exit; + } + + err = 0; +exit: + kfree(elts); + list_for_each_safe(cur, tmp, &head) { + list_del(cur); + kfree(container_of(cur, struct debug_el, list)); + } + return err; +} module_init(list_sort_test); -#endif +#endif /* CONFIG_TEST_LIST_SORT */ diff --git a/lib/parser.c b/lib/parser.c index fb34977246bb..6e89eca5cca0 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -128,12 +128,13 @@ static int match_number(substring_t *s, int *result, int base) char *endp; char *buf; int ret; + size_t len = s->to - s->from; - buf = kmalloc(s->to - s->from + 1, GFP_KERNEL); + buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; - memcpy(buf, s->from, s->to - s->from); - buf[s->to - s->from] = '\0'; + memcpy(buf, s->from, len); + buf[len] = '\0'; *result = simple_strtol(buf, &endp, base); ret = 0; if (endp == buf) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index ec9048e74f44..604678d7d06d 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -8,10 +8,53 @@ #include #include #include +#include static LIST_HEAD(percpu_counters); static DEFINE_MUTEX(percpu_counters_lock); +#ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER + +static struct debug_obj_descr percpu_counter_debug_descr; + +static int percpu_counter_fixup_free(void *addr, enum debug_obj_state state) +{ + struct percpu_counter *fbc = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + percpu_counter_destroy(fbc); + debug_object_free(fbc, &percpu_counter_debug_descr); + return 1; + default: + return 0; + } +} + +static struct debug_obj_descr percpu_counter_debug_descr = { + .name = "percpu_counter", + .fixup_free = percpu_counter_fixup_free, +}; + +static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) +{ + debug_object_init(fbc, &percpu_counter_debug_descr); + debug_object_activate(fbc, &percpu_counter_debug_descr); +} + +static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) +{ + debug_object_deactivate(fbc, &percpu_counter_debug_descr); + debug_object_free(fbc, &percpu_counter_debug_descr); +} + +#else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ +static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) +{ } +static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) +{ } +#endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ + void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; @@ -30,9 +73,9 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; s32 *pcount; - int cpu = get_cpu(); - pcount = per_cpu_ptr(fbc->counters, cpu); + preempt_disable(); + pcount = this_cpu_ptr(fbc->counters); count = *pcount + amount; if (count >= batch || count <= -batch) { spin_lock(&fbc->lock); @@ -42,7 +85,7 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) } else { *pcount = count; } - put_cpu(); + preempt_enable(); } EXPORT_SYMBOL(__percpu_counter_add); @@ -75,7 +118,11 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, fbc->counters = alloc_percpu(s32); if (!fbc->counters) return -ENOMEM; + + debug_percpu_counter_activate(fbc); + #ifdef CONFIG_HOTPLUG_CPU + INIT_LIST_HEAD(&fbc->list); mutex_lock(&percpu_counters_lock); list_add(&fbc->list, &percpu_counters); mutex_unlock(&percpu_counters_lock); @@ -89,6 +136,8 @@ void percpu_counter_destroy(struct percpu_counter *fbc) if (!fbc->counters) return; + debug_percpu_counter_deactivate(fbc); + #ifdef CONFIG_HOTPLUG_CPU mutex_lock(&percpu_counters_lock); list_del(&fbc->list); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 7af9d841c43b..c150d3dafff4 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -988,8 +988,15 @@ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { - if (!ptr) + if (!ptr) { + /* + * Print (null) with the same width as a pointer so it makes + * tabular output look nice. + */ + if (spec.field_width == -1) + spec.field_width = 2 * sizeof(void *); return string(buf, end, "(null)", spec); + } switch (*fmt) { case 'F': @@ -1031,7 +1038,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, } spec.flags |= SMALL; if (spec.field_width == -1) { - spec.field_width = 2*sizeof(void *); + spec.field_width = 2 * sizeof(void *); spec.flags |= ZEROPAD; } spec.base = 16; @@ -1497,7 +1504,7 @@ EXPORT_SYMBOL(snprintf); * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including - * the trailing '\0'. If @size is <= 0 the function returns 0. + * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) @@ -1509,7 +1516,11 @@ int scnprintf(char *buf, size_t size, const char *fmt, ...) i = vsnprintf(buf, size, fmt, args); va_end(args); - return (i >= size) ? (size - 1) : i; + if (likely(i < size)) + return i; + if (size != 0) + return size - 1; + return 0; } EXPORT_SYMBOL(scnprintf); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 65d420499a61..f2eb27884ffa 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -362,7 +362,7 @@ static int bdi_forker_thread(void *ptr) { struct bdi_writeback *me = ptr; - current->flags |= PF_FLUSHER | PF_SWAPWRITE; + current->flags |= PF_SWAPWRITE; set_freezable(); /* @@ -729,6 +729,7 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; +static atomic_t nr_bdi_congested[2]; void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { @@ -736,7 +737,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync) wait_queue_head_t *wqh = &congestion_wqh[sync]; bit = sync ? BDI_sync_congested : BDI_async_congested; - clear_bit(bit, &bdi->state); + if (test_and_clear_bit(bit, &bdi->state)) + atomic_dec(&nr_bdi_congested[sync]); smp_mb__after_clear_bit(); if (waitqueue_active(wqh)) wake_up(wqh); @@ -748,7 +750,8 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync) enum bdi_state bit; bit = sync ? BDI_sync_congested : BDI_async_congested; - set_bit(bit, &bdi->state); + if (!test_and_set_bit(bit, &bdi->state)) + atomic_inc(&nr_bdi_congested[sync]); } EXPORT_SYMBOL(set_bdi_congested); @@ -764,13 +767,72 @@ EXPORT_SYMBOL(set_bdi_congested); long congestion_wait(int sync, long timeout) { long ret; + unsigned long start = jiffies; DEFINE_WAIT(wait); wait_queue_head_t *wqh = &congestion_wqh[sync]; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = io_schedule_timeout(timeout); finish_wait(wqh, &wait); + + trace_writeback_congestion_wait(jiffies_to_usecs(timeout), + jiffies_to_usecs(jiffies - start)); + return ret; } EXPORT_SYMBOL(congestion_wait); +/** + * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes + * @zone: A zone to check if it is heavily congested + * @sync: SYNC or ASYNC IO + * @timeout: timeout in jiffies + * + * In the event of a congested backing_dev (any backing_dev) and the given + * @zone has experienced recent congestion, this waits for up to @timeout + * jiffies for either a BDI to exit congestion of the given @sync queue + * or a write to complete. + * + * In the absense of zone congestion, cond_resched() is called to yield + * the processor if necessary but otherwise does not sleep. + * + * The return value is 0 if the sleep is for the full timeout. Otherwise, + * it is the number of jiffies that were still remaining when the function + * returned. return_value == timeout implies the function did not sleep. + */ +long wait_iff_congested(struct zone *zone, int sync, long timeout) +{ + long ret; + unsigned long start = jiffies; + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = &congestion_wqh[sync]; + + /* + * If there is no congestion, or heavy congestion is not being + * encountered in the current zone, yield if necessary instead + * of sleeping on the congestion queue + */ + if (atomic_read(&nr_bdi_congested[sync]) == 0 || + !zone_is_reclaim_congested(zone)) { + cond_resched(); + + /* In case we scheduled, work out time remaining */ + ret = timeout - (jiffies - start); + if (ret < 0) + ret = 0; + + goto out; + } + + /* Sleep until uncongested or a write happens */ + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = io_schedule_timeout(timeout); + finish_wait(wqh, &wait); + +out: + trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), + jiffies_to_usecs(jiffies - start)); + + return ret; +} +EXPORT_SYMBOL(wait_iff_congested); diff --git a/mm/dmapool.c b/mm/dmapool.c index 3df063706f53..4df2de77e069 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -311,6 +311,8 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, size_t offset; void *retval; + might_sleep_if(mem_flags & __GFP_WAIT); + spin_lock_irqsave(&pool->lock, flags); restart: list_for_each_entry(page, &pool->page_list, page_list) { diff --git a/mm/filemap.c b/mm/filemap.c index 3d4df44e4221..75572b5f2374 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -612,6 +612,19 @@ void __lock_page_nosync(struct page *page) TASK_UNINTERRUPTIBLE); } +int __lock_page_or_retry(struct page *page, struct mm_struct *mm, + unsigned int flags) +{ + if (!(flags & FAULT_FLAG_ALLOW_RETRY)) { + __lock_page(page); + return 1; + } else { + up_read(&mm->mmap_sem); + wait_on_page_locked(page); + return 0; + } +} + /** * find_get_page - find and get a page reference * @mapping: the address_space to search @@ -1539,25 +1552,28 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) * waiting for the lock. */ do_async_mmap_readahead(vma, ra, file, page, offset); - lock_page(page); - - /* Did it get truncated? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); - goto no_cached_page; - } } else { /* No page in the page cache at all */ do_sync_mmap_readahead(vma, ra, file, offset); count_vm_event(PGMAJFAULT); ret = VM_FAULT_MAJOR; retry_find: - page = find_lock_page(mapping, offset); + page = find_get_page(mapping, offset); if (!page) goto no_cached_page; } + if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) + return ret | VM_FAULT_RETRY; + + /* Did it get truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + put_page(page); + goto retry_find; + } + VM_BUG_ON(page->index != offset); + /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. @@ -2177,12 +2193,12 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, } if (written > 0) { - loff_t end = pos + written; - if (end > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { - i_size_write(inode, end); + pos += written; + if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { + i_size_write(inode, pos); mark_inode_dirty(inode); } - *ppos = end; + *ppos = pos; } out: return written; diff --git a/mm/highmem.c b/mm/highmem.c index 7a0aa1be4993..781e754a75ac 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -42,6 +42,10 @@ unsigned long totalhigh_pages __read_mostly; EXPORT_SYMBOL(totalhigh_pages); + +DEFINE_PER_CPU(int, __kmap_atomic_idx); +EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); + unsigned int nr_free_highpages (void) { pg_data_t *pgdat; @@ -422,61 +426,3 @@ void __init page_address_init(void) } #endif /* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */ - -#ifdef CONFIG_DEBUG_HIGHMEM - -void debug_kmap_atomic(enum km_type type) -{ - static int warn_count = 10; - - if (unlikely(warn_count < 0)) - return; - - if (unlikely(in_interrupt())) { - if (in_nmi()) { - if (type != KM_NMI && type != KM_NMI_PTE) { - WARN_ON(1); - warn_count--; - } - } else if (in_irq()) { - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ && - type != KM_BOUNCE_READ && type != KM_IRQ_PTE) { - WARN_ON(1); - warn_count--; - } - } else if (!irqs_disabled()) { /* softirq */ - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 && - type != KM_SKB_SUNRPC_DATA && - type != KM_SKB_DATA_SOFTIRQ && - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } - } - - if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || - type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ || - type == KM_IRQ_PTE || type == KM_NMI || - type == KM_NMI_PTE ) { - if (!irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) { - if (irq_count() == 0 && !irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } -#ifdef CONFIG_KGDB_KDB - if (unlikely(type == KM_KDB && atomic_read(&kgdb_active) == -1)) { - WARN_ON(1); - warn_count--; - } -#endif /* CONFIG_KGDB_KDB */ -} - -#endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 96991ded82fe..c4a3558589ab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2448,8 +2448,11 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, * When the original hugepage is shared one, it does not have * anon_vma prepared. */ - if (unlikely(anon_vma_prepare(vma))) + if (unlikely(anon_vma_prepare(vma))) { + /* Caller expects lock to be held */ + spin_lock(&mm->page_table_lock); return VM_FAULT_OOM; + } copy_user_huge_page(new_page, old_page, address, vma); __SetPageUptodate(new_page); diff --git a/mm/internal.h b/mm/internal.h index 6a697bb97fc5..dedb0aff673f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -62,7 +62,7 @@ extern bool is_free_buddy_page(struct page *page); */ static inline unsigned long page_order(struct page *page) { - VM_BUG_ON(!PageBuddy(page)); + /* PageBuddy() must be checked by the caller */ return page_private(page); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 44a8cefeae6e..124324134ff6 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1292,6 +1292,7 @@ static int soft_offline_huge_page(struct page *page, int flags) list_add(&hpage->lru, &pagelist); ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0); if (ret) { + putback_lru_pages(&pagelist); pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) diff --git a/mm/memory.c b/mm/memory.c index af82741caaa4..02e48aa0ed13 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -736,7 +736,7 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) return -ENOMEM; - src_pte = pte_offset_map_nested(src_pmd, addr); + src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; @@ -767,7 +767,7 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); - pte_unmap_nested(orig_src_pte); + pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); @@ -1591,7 +1591,7 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ -pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, +pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pgd_t * pgd = pgd_offset(mm, addr); @@ -2080,7 +2080,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) - memset(kaddr, 0, PAGE_SIZE); + clear_page(kaddr); kunmap_atomic(kaddr, KM_USER0); flush_dcache_page(dst); } else @@ -2108,6 +2108,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte) + __releases(ptl) { struct page *old_page, *new_page; pte_t entry; @@ -2627,6 +2628,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, *swapcache = NULL; swp_entry_t entry; pte_t pte; + int locked; struct mem_cgroup *ptr = NULL; int exclusive = 0; int ret = 0; @@ -2677,8 +2679,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_release; } - lock_page(page); + locked = lock_page_or_retry(page, mm, flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + if (!locked) { + ret |= VM_FAULT_RETRY; + goto out_release; + } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not @@ -2927,7 +2933,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, vmf.page = NULL; ret = vma->vm_ops->fault(vma, &vmf); - if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | + VM_FAULT_RETRY))) return ret; if (unlikely(PageHWPoison(vmf.page))) { @@ -3344,7 +3351,7 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ -static int follow_pte(struct mm_struct *mm, unsigned long address, +static int __follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; @@ -3381,6 +3388,17 @@ static int follow_pte(struct mm_struct *mm, unsigned long address, return -EINVAL; } +static inline int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) +{ + int res; + + /* (void) is needed to make gcc happy */ + (void) __cond_lock(*ptlp, + !(res = __follow_pte(mm, address, ptepp, ptlp))); + return res; +} + /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index d4e940a26945..9260314a221e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -602,27 +602,14 @@ static struct page *next_active_pageblock(struct page *page) /* Checks if this range of memory is likely to be hot-removable. */ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { - int type; struct page *page = pfn_to_page(start_pfn); struct page *end_page = page + nr_pages; /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { - type = get_pageblock_migratetype(page); - - /* - * A pageblock containing MOVABLE or free pages is considered - * removable - */ - if (type != MIGRATE_MOVABLE && !pageblock_free(page)) - return 0; - - /* - * A pageblock starting with a PageReserved page is not - * considered removable. - */ - if (PageReserved(page)) + if (!is_pageblock_removable_nolock(page)) return 0; + cond_resched(); } /* All pageblocks in the memory block are likely to be hot-removable */ @@ -659,7 +646,7 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) * Scanning pfn is much easier than scanning lru list. * Scan pfn from start to end and Find LRU page. */ -int scan_lru_pages(unsigned long start, unsigned long end) +static unsigned long scan_lru_pages(unsigned long start, unsigned long end) { unsigned long pfn; struct page *page; @@ -709,29 +696,30 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) page_is_file_cache(page)); } else { - /* Becasue we don't have big zone->lock. we should - check this again here. */ - if (page_count(page)) - not_managed++; #ifdef CONFIG_DEBUG_VM printk(KERN_ALERT "removing pfn %lx from LRU failed\n", pfn); dump_page(page); #endif + /* Becasue we don't have big zone->lock. we should + check this again here. */ + if (page_count(page)) { + not_managed++; + ret = -EBUSY; + break; + } } } - ret = -EBUSY; - if (not_managed) { - if (!list_empty(&source)) + if (!list_empty(&source)) { + if (not_managed) { + putback_lru_pages(&source); + goto out; + } + /* this function returns # of failed pages */ + ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1); + if (ret) putback_lru_pages(&source); - goto out; } - ret = 0; - if (list_empty(&source)) - goto out; - /* this function returns # of failed pages */ - ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1); - out: return ret; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f969da5dd8a2..81a127643aea 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -924,15 +924,21 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; + struct vm_area_struct *vma; nodes_clear(nmask); node_set(source, nmask); - check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, + vma = check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); + if (IS_ERR(vma)) + return PTR_ERR(vma); - if (!list_empty(&pagelist)) + if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_node_page, dest, 0); + if (err) + putback_lru_pages(&pagelist); + } return err; } @@ -1147,9 +1153,12 @@ static long do_mbind(unsigned long start, unsigned long len, err = mbind_range(mm, start, end, new); - if (!list_empty(&pagelist)) + if (!list_empty(&pagelist)) { nr_failed = migrate_pages(&pagelist, new_vma_page, (unsigned long)vma, 0); + if (nr_failed) + putback_lru_pages(&pagelist); + } if (!err && nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; diff --git a/mm/migrate.c b/mm/migrate.c index f8c9bccf2520..fe5a3c6a5426 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -497,7 +497,6 @@ static int writeout(struct address_space *mapping, struct page *page) .nr_to_write = 1, .range_start = 0, .range_end = LLONG_MAX, - .nonblocking = 1, .for_reclaim = 1 }; int rc; @@ -884,8 +883,9 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * * The function returns after 10 attempts or if no pages * are movable anymore because to has become empty - * or no retryable pages exist anymore. All pages will be - * returned to the LRU or freed. + * or no retryable pages exist anymore. + * Caller should call putback_lru_pages to return pages to the LRU + * or free list. * * Return: Number of pages not migrated or error code. */ @@ -932,8 +932,6 @@ int migrate_pages(struct list_head *from, if (!swapwrite) current->flags &= ~PF_SWAPWRITE; - putback_lru_pages(from); - if (rc) return rc; @@ -1039,7 +1037,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm, err = -EFAULT; vma = find_vma(mm, pp->addr); - if (!vma || !vma_migratable(vma)) + if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma)) goto set_status; page = follow_page(vma, pp->addr, FOLL_GET); @@ -1088,9 +1086,12 @@ static int do_move_page_to_node_array(struct mm_struct *mm, } err = 0; - if (!list_empty(&pagelist)) + if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, (unsigned long)pm, 0); + if (err) + putback_lru_pages(&pagelist); + } up_read(&mm->mmap_sem); return err; @@ -1203,7 +1204,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, int err = -EFAULT; vma = find_vma(mm, addr); - if (!vma) + if (!vma || addr < vma->vm_start) goto set_status; page = follow_page(vma, addr, 0); diff --git a/mm/mremap.c b/mm/mremap.c index cde56ee51ef7..563fbdd6293a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -101,7 +101,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, * pte locks because exclusive mmap_sem prevents deadlock. */ old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); - new_pte = pte_offset_map_nested(new_pmd, new_addr); + new_pte = pte_offset_map(new_pmd, new_addr); new_ptl = pte_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); @@ -119,7 +119,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, arch_leave_lazy_mmu_mode(); if (new_ptl != old_ptl) spin_unlock(new_ptl); - pte_unmap_nested(new_pte - 1); + pte_unmap(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) spin_unlock(&mapping->i_mmap_lock); diff --git a/mm/nommu.c b/mm/nommu.c index 88ff091eb07a..30b5c20eec15 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -293,11 +293,58 @@ void *vmalloc(unsigned long size) } EXPORT_SYMBOL(vmalloc); +/* + * vzalloc - allocate virtually continguos memory with zero fill + * + * @size: allocation size + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into continguos kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vzalloc(unsigned long size) +{ + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + PAGE_KERNEL); +} +EXPORT_SYMBOL(vzalloc); + +/** + * vmalloc_node - allocate memory on a specific node + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ void *vmalloc_node(unsigned long size, int node) { return vmalloc(size); } -EXPORT_SYMBOL(vmalloc_node); + +/** + * vzalloc_node - allocate memory on a specific node with zero fill + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vzalloc_node(unsigned long size, int node) +{ + return vzalloc(size); +} +EXPORT_SYMBOL(vzalloc_node); #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 4029583a1024..7dcca55ede7c 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -162,10 +162,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, return 0; /* - * Shortcut check for OOM_SCORE_ADJ_MIN so the entire heuristic doesn't - * need to be executed for something that cannot be killed. + * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN + * so the entire heuristic doesn't need to be executed for something + * that cannot be killed. */ - if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + if (atomic_read(&p->mm->oom_disable_count)) { task_unlock(p); return 0; } @@ -403,16 +404,40 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, #define K(x) ((x) << (PAGE_SHIFT-10)) static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) { + struct task_struct *q; + struct mm_struct *mm; + p = find_lock_task_mm(p); if (!p) return 1; + /* mm cannot be safely dereferenced after task_unlock(p) */ + mm = p->mm; + pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(p), p->comm, K(p->mm->total_vm), K(get_mm_counter(p->mm, MM_ANONPAGES)), K(get_mm_counter(p->mm, MM_FILEPAGES))); task_unlock(p); + /* + * Kill all processes sharing p->mm in other thread groups, if any. + * They don't get access to memory reserves or a higher scheduler + * priority, though, to avoid depletion of all memory or task + * starvation. This prevents mm->mmap_sem livelock when an oom killed + * task cannot exit because it requires the semaphore and its contended + * by another thread trying to allocate memory itself. That thread will + * now get access to memory reserves since it has a pending fatal + * signal. + */ + for_each_process(q) + if (q->mm == mm && !same_thread_group(q, p)) { + task_lock(q); /* Protect ->comm from prctl() */ + pr_err("Kill process %d (%s) sharing same memory\n", + task_pid_nr(q), q->comm); + task_unlock(q); + force_sig(SIGKILL, q); + } set_tsk_thread_flag(p, TIF_MEMDIE); force_sig(SIGKILL, p); @@ -680,7 +705,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, read_lock(&tasklist_lock); if (sysctl_oom_kill_allocating_task && !oom_unkillable_task(current, NULL, nodemask) && - (current->signal->oom_adj != OOM_DISABLE)) { + current->mm && !atomic_read(¤t->mm->oom_disable_count)) { /* * oom_kill_process() needs tasklist_lock held. If it returns * non-zero, current could not be killed so we must fallback to diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e3bccac1f025..b840afa89761 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -415,14 +415,8 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); - else { - int dirty_ratio; - - dirty_ratio = vm_dirty_ratio; - if (dirty_ratio < 5) - dirty_ratio = 5; - dirty = (dirty_ratio * available_memory) / 100; - } + else + dirty = (vm_dirty_ratio * available_memory) / 100; if (dirty_background_bytes) background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE); @@ -510,7 +504,7 @@ static void balance_dirty_pages(struct address_space *mapping, * catch-up. This avoids (excessively) small writeouts * when the bdi limits are ramping up. */ - if (nr_reclaimable + nr_writeback < + if (nr_reclaimable + nr_writeback <= (background_thresh + dirty_thresh) / 2) break; @@ -542,8 +536,8 @@ static void balance_dirty_pages(struct address_space *mapping, * the last resort safeguard. */ dirty_exceeded = - (bdi_nr_reclaimable + bdi_nr_writeback >= bdi_thresh) - || (nr_reclaimable + nr_writeback >= dirty_thresh); + (bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh) + || (nr_reclaimable + nr_writeback > dirty_thresh); if (!dirty_exceeded) break; @@ -1121,6 +1115,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) { if (mapping_cap_account_dirty(mapping)) { __inc_zone_page_state(page, NR_FILE_DIRTY); + __inc_zone_page_state(page, NR_DIRTIED); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); task_dirty_inc(current); task_io_account_write(PAGE_CACHE_SIZE); @@ -1128,6 +1123,18 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) } EXPORT_SYMBOL(account_page_dirtied); +/* + * Helper function for set_page_writeback family. + * NOTE: Unlike account_page_dirtied this does not rely on being atomic + * wrt interrupts. + */ +void account_page_writeback(struct page *page) +{ + inc_zone_page_state(page, NR_WRITEBACK); + inc_zone_page_state(page, NR_WRITTEN); +} +EXPORT_SYMBOL(account_page_writeback); + /* * For address_spaces which do not use buffers. Just tag the page as dirty in * its radix tree. @@ -1366,7 +1373,7 @@ int test_set_page_writeback(struct page *page) ret = TestSetPageWriteback(page); } if (!ret) - inc_zone_page_state(page, NR_WRITEBACK); + account_page_writeback(page); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2a362c52fdf4..07a654486f75 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -531,7 +531,7 @@ static inline void __free_one_page(struct page *page, * so it's less likely to be used soon and more likely to be merged * as a higher order page */ - if ((order < MAX_ORDER-1) && pfn_valid_within(page_to_pfn(buddy))) { + if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) { struct page *higher_page, *higher_buddy; combined_idx = __find_combined_index(page_idx, order); higher_page = page + combined_idx - page_idx; @@ -1907,7 +1907,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) - congestion_wait(BLK_RW_ASYNC, HZ/50); + wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); } while (!page && (gfp_mask & __GFP_NOFAIL)); return page; @@ -1932,7 +1932,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) const gfp_t wait = gfp_mask & __GFP_WAIT; /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ - BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH); + BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); /* * The caller may dip into page reserves a bit more if the caller @@ -1940,7 +1940,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). */ - alloc_flags |= (gfp_mask & __GFP_HIGH); + alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); if (!wait) { alloc_flags |= ALLOC_HARDER; @@ -2095,7 +2095,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { /* Wait for some write requests to complete then retry */ - congestion_wait(BLK_RW_ASYNC, HZ/50); + wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); goto rebalance; } @@ -5297,12 +5297,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, * page allocater never alloc memory from ISOLATE block. */ +static int +__count_immobile_pages(struct zone *zone, struct page *page, int count) +{ + unsigned long pfn, iter, found; + /* + * For avoiding noise data, lru_add_drain_all() should be called + * If ZONE_MOVABLE, the zone never contains immobile pages + */ + if (zone_idx(zone) == ZONE_MOVABLE) + return true; + + if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE) + return true; + + pfn = page_to_pfn(page); + for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { + unsigned long check = pfn + iter; + + if (!pfn_valid_within(check)) { + iter++; + continue; + } + page = pfn_to_page(check); + if (!page_count(page)) { + if (PageBuddy(page)) + iter += (1 << page_order(page)) - 1; + continue; + } + if (!PageLRU(page)) + found++; + /* + * If there are RECLAIMABLE pages, we need to check it. + * But now, memory offline itself doesn't call shrink_slab() + * and it still to be fixed. + */ + /* + * If the page is not RAM, page_count()should be 0. + * we don't need more check. This is an _used_ not-movable page. + * + * The problematic thing here is PG_reserved pages. PG_reserved + * is set to both of a memory hole page and a _used_ kernel + * page at boot. + */ + if (found > count) + return false; + } + return true; +} + +bool is_pageblock_removable_nolock(struct page *page) +{ + struct zone *zone = page_zone(page); + return __count_immobile_pages(zone, page, 0); +} + int set_migratetype_isolate(struct page *page) { struct zone *zone; - struct page *curr_page; - unsigned long flags, pfn, iter; - unsigned long immobile = 0; + unsigned long flags, pfn; struct memory_isolate_notify arg; int notifier_ret; int ret = -EBUSY; @@ -5312,11 +5365,6 @@ int set_migratetype_isolate(struct page *page) zone_idx = zone_idx(zone); spin_lock_irqsave(&zone->lock, flags); - if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE || - zone_idx == ZONE_MOVABLE) { - ret = 0; - goto out; - } pfn = page_to_pfn(page); arg.start_pfn = pfn; @@ -5336,23 +5384,20 @@ int set_migratetype_isolate(struct page *page) */ notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg); notifier_ret = notifier_to_errno(notifier_ret); - if (notifier_ret || !arg.pages_found) + if (notifier_ret) goto out; - - for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) { - if (!pfn_valid_within(pfn)) - continue; - - curr_page = pfn_to_page(iter); - if (!page_count(curr_page) || PageLRU(curr_page)) - continue; - - immobile++; - } - - if (arg.pages_found == immobile) + /* + * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. + * We just check MOVABLE pages. + */ + if (__count_immobile_pages(zone, page, arg.pages_found)) ret = 0; + /* + * immobile means "not-on-lru" paes. If immobile is larger than + * removable-by-driver pages reported by notifier, we'll fail. + */ + out: if (!ret) { set_pageblock_migratetype(page, MIGRATE_ISOLATE); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 5e0ffd967452..4ae42bb40892 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -86,7 +86,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) * all pages in [start_pfn...end_pfn) must be in the same zone. * zone->lock must be held before call this. * - * Returns 0 if all pages in the range is isolated. + * Returns 1 if all pages in the range is isolated. */ static int __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn) @@ -119,7 +119,6 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn) struct zone *zone; int ret; - pfn = start_pfn; /* * Note: pageblock_nr_page != MAX_ORDER. Then, chunks of free page * is not aligned to pageblock_nr_pages. diff --git a/mm/rmap.c b/mm/rmap.c index f5ad996a4a8f..1a8bf76bfd03 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -80,7 +80,7 @@ static inline struct anon_vma_chain *anon_vma_chain_alloc(void) return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL); } -void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) +static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } @@ -314,7 +314,7 @@ void __init anon_vma_init(void) * Getting a lock on a stable anon_vma from a page off the LRU is * tricky: page_lock_anon_vma rely on RCU to guard against the races. */ -struct anon_vma *page_lock_anon_vma(struct page *page) +struct anon_vma *__page_lock_anon_vma(struct page *page) { struct anon_vma *anon_vma, *root_anon_vma; unsigned long anon_mapping; @@ -348,6 +348,8 @@ struct anon_vma *page_lock_anon_vma(struct page *page) } void page_unlock_anon_vma(struct anon_vma *anon_vma) + __releases(&anon_vma->root->lock) + __releases(RCU) { anon_vma_unlock(anon_vma); rcu_read_unlock(); @@ -407,7 +409,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) * * On success returns with pte mapped and locked. */ -pte_t *page_check_address(struct page *page, struct mm_struct *mm, +pte_t *__page_check_address(struct page *page, struct mm_struct *mm, unsigned long address, spinlock_t **ptlp, int sync) { pgd_t *pgd; diff --git a/mm/slab.c b/mm/slab.c index fcae9815d3b3..b1e40dafbab3 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -901,7 +901,7 @@ static int transfer_objects(struct array_cache *to, struct array_cache *from, unsigned int max) { /* Figure out how many entries to transfer */ - int nr = min(min(from->avail, max), to->limit - to->avail); + int nr = min3(from->avail, max, to->limit - to->avail); if (!nr) return 0; diff --git a/mm/swapfile.c b/mm/swapfile.c index 9fc7bac7db0c..67ddaaf98c74 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -58,6 +59,10 @@ static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); +static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); +/* Activity counter to indicate that a swapon or swapoff has occurred */ +static atomic_t proc_poll_event = ATOMIC_INIT(0); + static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ @@ -1680,6 +1685,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) } filp_close(swap_file, NULL); err = 0; + atomic_inc(&proc_poll_event); + wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); @@ -1688,6 +1695,25 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) } #ifdef CONFIG_PROC_FS +struct proc_swaps { + struct seq_file seq; + int event; +}; + +static unsigned swaps_poll(struct file *file, poll_table *wait) +{ + struct proc_swaps *s = file->private_data; + + poll_wait(file, &proc_poll_wait, wait); + + if (s->event != atomic_read(&proc_poll_event)) { + s->event = atomic_read(&proc_poll_event); + return POLLIN | POLLRDNORM | POLLERR | POLLPRI; + } + + return POLLIN | POLLRDNORM; +} + /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { @@ -1771,7 +1797,24 @@ static const struct seq_operations swaps_op = { static int swaps_open(struct inode *inode, struct file *file) { - return seq_open(file, &swaps_op); + struct proc_swaps *s; + int ret; + + s = kmalloc(sizeof(struct proc_swaps), GFP_KERNEL); + if (!s) + return -ENOMEM; + + file->private_data = s; + + ret = seq_open(file, &swaps_op); + if (ret) { + kfree(s); + return ret; + } + + s->seq.private = s; + s->event = atomic_read(&proc_poll_event); + return ret; } static const struct file_operations proc_swaps_operations = { @@ -1779,6 +1822,7 @@ static const struct file_operations proc_swaps_operations = { .read = seq_read, .llseek = seq_lseek, .release = seq_release, + .poll = swaps_poll, }; static int __init procswaps_init(void) @@ -2084,6 +2128,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) swap_info[prev]->next = type; spin_unlock(&swap_lock); mutex_unlock(&swapon_mutex); + atomic_inc(&proc_poll_event); + wake_up_interruptible(&proc_poll_wait); + error = 0; goto out; bad_swap: diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9f909622a25e..a3d66b3dc5cb 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -293,13 +293,13 @@ static void __insert_vmap_area(struct vmap_area *va) struct rb_node *tmp; while (*p) { - struct vmap_area *tmp; + struct vmap_area *tmp_va; parent = *p; - tmp = rb_entry(parent, struct vmap_area, rb_node); - if (va->va_start < tmp->va_end) + tmp_va = rb_entry(parent, struct vmap_area, rb_node); + if (va->va_start < tmp_va->va_end) p = &(*p)->rb_left; - else if (va->va_end > tmp->va_start) + else if (va->va_end > tmp_va->va_start) p = &(*p)->rb_right; else BUG(); @@ -1596,6 +1596,13 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) } EXPORT_SYMBOL(__vmalloc); +static inline void *__vmalloc_node_flags(unsigned long size, + int node, gfp_t flags) +{ + return __vmalloc_node(size, 1, flags, PAGE_KERNEL, + node, __builtin_return_address(0)); +} + /** * vmalloc - allocate virtually contiguous memory * @size: allocation size @@ -1607,11 +1614,27 @@ EXPORT_SYMBOL(__vmalloc); */ void *vmalloc(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, - -1, __builtin_return_address(0)); + return __vmalloc_node_flags(size, -1, GFP_KERNEL | __GFP_HIGHMEM); } EXPORT_SYMBOL(vmalloc); +/** + * vzalloc - allocate virtually contiguous memory with zero fill + * @size: allocation size + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vzalloc(unsigned long size) +{ + return __vmalloc_node_flags(size, -1, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); +} +EXPORT_SYMBOL(vzalloc); + /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size @@ -1653,6 +1676,25 @@ void *vmalloc_node(unsigned long size, int node) } EXPORT_SYMBOL(vmalloc_node); +/** + * vzalloc_node - allocate memory on a specific node with zero fill + * @size: allocation size + * @node: numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * The memory allocated is set to zero. + * + * For tight control over page level allocator and protection flags + * use __vmalloc_node() instead. + */ +void *vzalloc_node(unsigned long size, int node) +{ + return __vmalloc_node_flags(size, node, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); +} +EXPORT_SYMBOL(vzalloc_node); + #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif @@ -2350,6 +2392,7 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) + __acquires(&vmlist_lock) { loff_t n = *pos; struct vm_struct *v; @@ -2376,6 +2419,7 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos) } static void s_stop(struct seq_file *m, void *p) + __releases(&vmlist_lock) { read_unlock(&vmlist_lock); } diff --git a/mm/vmscan.c b/mm/vmscan.c index b94c9464f262..b8a6fdc21312 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -51,6 +51,12 @@ #define CREATE_TRACE_POINTS #include +enum lumpy_mode { + LUMPY_MODE_NONE, + LUMPY_MODE_ASYNC, + LUMPY_MODE_SYNC, +}; + struct scan_control { /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; @@ -82,7 +88,7 @@ struct scan_control { * Intend to reclaim enough continuous memory rather than reclaim * enough amount of memory. i.e, mode for high order allocation. */ - bool lumpy_reclaim_mode; + enum lumpy_mode lumpy_reclaim_mode; /* Which cgroup do we reclaim from */ struct mem_cgroup *mem_cgroup; @@ -265,6 +271,36 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, return ret; } +static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc, + bool sync) +{ + enum lumpy_mode mode = sync ? LUMPY_MODE_SYNC : LUMPY_MODE_ASYNC; + + /* + * Some reclaim have alredy been failed. No worth to try synchronous + * lumpy reclaim. + */ + if (sync && sc->lumpy_reclaim_mode == LUMPY_MODE_NONE) + return; + + /* + * If we need a large contiguous chunk of memory, or have + * trouble getting a small set of contiguous pages, we + * will reclaim both active and inactive pages. + */ + if (sc->order > PAGE_ALLOC_COSTLY_ORDER) + sc->lumpy_reclaim_mode = mode; + else if (sc->order && priority < DEF_PRIORITY - 2) + sc->lumpy_reclaim_mode = mode; + else + sc->lumpy_reclaim_mode = LUMPY_MODE_NONE; +} + +static void disable_lumpy_reclaim_mode(struct scan_control *sc) +{ + sc->lumpy_reclaim_mode = LUMPY_MODE_NONE; +} + static inline int is_page_cache_freeable(struct page *page) { /* @@ -275,7 +311,8 @@ static inline int is_page_cache_freeable(struct page *page) return page_count(page) - page_has_private(page) == 2; } -static int may_write_to_queue(struct backing_dev_info *bdi) +static int may_write_to_queue(struct backing_dev_info *bdi, + struct scan_control *sc) { if (current->flags & PF_SWAPWRITE) return 1; @@ -283,6 +320,10 @@ static int may_write_to_queue(struct backing_dev_info *bdi) return 1; if (bdi == current->backing_dev_info) return 1; + + /* lumpy reclaim for hugepage often need a lot of write */ + if (sc->order > PAGE_ALLOC_COSTLY_ORDER) + return 1; return 0; } @@ -307,12 +348,6 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } -/* Request for sync pageout. */ -enum pageout_io { - PAGEOUT_IO_ASYNC, - PAGEOUT_IO_SYNC, -}; - /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ @@ -330,7 +365,7 @@ typedef enum { * Calls ->writepage(). */ static pageout_t pageout(struct page *page, struct address_space *mapping, - enum pageout_io sync_writeback) + struct scan_control *sc) { /* * If the page is dirty, only perform writeback if that write @@ -366,7 +401,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_queue(mapping->backing_dev_info)) + if (!may_write_to_queue(mapping->backing_dev_info, sc)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { @@ -376,7 +411,6 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, - .nonblocking = 1, .for_reclaim = 1, }; @@ -394,7 +428,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * direct reclaiming a large contiguous area and the * first attempt to free a range of pages fails. */ - if (PageWriteback(page) && sync_writeback == PAGEOUT_IO_SYNC) + if (PageWriteback(page) && + sc->lumpy_reclaim_mode == LUMPY_MODE_SYNC) wait_on_page_writeback(page); if (!PageWriteback(page)) { @@ -402,7 +437,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, ClearPageReclaim(page); } trace_mm_vmscan_writepage(page, - trace_reclaim_flags(page, sync_writeback)); + trace_reclaim_flags(page, sc->lumpy_reclaim_mode)); inc_zone_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } @@ -580,7 +615,7 @@ static enum page_references page_check_references(struct page *page, referenced_page = TestClearPageReferenced(page); /* Lumpy reclaim - ignore references */ - if (sc->lumpy_reclaim_mode) + if (sc->lumpy_reclaim_mode != LUMPY_MODE_NONE) return PAGEREF_RECLAIM; /* @@ -616,7 +651,7 @@ static enum page_references page_check_references(struct page *page, } /* Reclaim if clean, defer dirty pages to writeback */ - if (referenced_page) + if (referenced_page && !PageSwapBacked(page)) return PAGEREF_RECLAIM_CLEAN; return PAGEREF_RECLAIM; @@ -644,12 +679,14 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages) * shrink_page_list() returns the number of reclaimed pages */ static unsigned long shrink_page_list(struct list_head *page_list, - struct scan_control *sc, - enum pageout_io sync_writeback) + struct zone *zone, + struct scan_control *sc) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); int pgactivate = 0; + unsigned long nr_dirty = 0; + unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; cond_resched(); @@ -669,6 +706,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep; VM_BUG_ON(PageActive(page)); + VM_BUG_ON(page_zone(page) != zone); sc->nr_scanned++; @@ -694,10 +732,13 @@ static unsigned long shrink_page_list(struct list_head *page_list, * for any page for which writeback has already * started. */ - if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs) + if (sc->lumpy_reclaim_mode == LUMPY_MODE_SYNC && + may_enter_fs) wait_on_page_writeback(page); - else - goto keep_locked; + else { + unlock_page(page); + goto keep_lumpy; + } } references = page_check_references(page, sc); @@ -743,6 +784,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, } if (PageDirty(page)) { + nr_dirty++; + if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) @@ -751,14 +794,18 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep_locked; /* Page is dirty, try to write it out here */ - switch (pageout(page, mapping, sync_writeback)) { + switch (pageout(page, mapping, sc)) { case PAGE_KEEP: + nr_congested++; goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: - if (PageWriteback(page) || PageDirty(page)) + if (PageWriteback(page)) + goto keep_lumpy; + if (PageDirty(page)) goto keep; + /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the page. @@ -841,6 +888,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, try_to_free_swap(page); unlock_page(page); putback_lru_page(page); + disable_lumpy_reclaim_mode(sc); continue; activate_locked: @@ -853,10 +901,21 @@ static unsigned long shrink_page_list(struct list_head *page_list, keep_locked: unlock_page(page); keep: + disable_lumpy_reclaim_mode(sc); +keep_lumpy: list_add(&page->lru, &ret_pages); VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); } + /* + * Tag a zone as congested if all the dirty pages encountered were + * backed by a congested BDI. In this case, reclaimers should just + * back off and wait for congestion to clear because further reclaim + * will encounter the same problem + */ + if (nr_dirty == nr_congested) + zone_set_flag(zone, ZONE_CONGESTED); + free_page_list(&free_pages); list_splice(&ret_pages, page_list); @@ -1006,7 +1065,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, /* Check that we have not crossed a zone boundary. */ if (unlikely(page_zone_id(cursor_page) != zone_id)) - continue; + break; /* * If we don't have enough swap space, reclaiming of @@ -1014,8 +1073,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, * pointless. */ if (nr_swap_pages <= 0 && PageAnon(cursor_page) && - !PageSwapCache(cursor_page)) - continue; + !PageSwapCache(cursor_page)) + break; if (__isolate_lru_page(cursor_page, mode, file) == 0) { list_move(&cursor_page->lru, dst); @@ -1026,11 +1085,16 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, nr_lumpy_dirty++; scan++; } else { - if (mode == ISOLATE_BOTH && - page_count(cursor_page)) - nr_lumpy_failed++; + /* the page is freed already. */ + if (!page_count(cursor_page)) + continue; + break; } } + + /* If we break out of the loop above, lumpy reclaim failed */ + if (pfn < end_pfn) + nr_lumpy_failed++; } *scanned = scan; @@ -1253,7 +1317,7 @@ static inline bool should_reclaim_stall(unsigned long nr_taken, return false; /* Only stall on lumpy reclaim */ - if (!sc->lumpy_reclaim_mode) + if (sc->lumpy_reclaim_mode == LUMPY_MODE_NONE) return false; /* If we have relaimed everything on the isolated list, no stall */ @@ -1286,7 +1350,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, unsigned long nr_scanned; unsigned long nr_reclaimed = 0; unsigned long nr_taken; - unsigned long nr_active; unsigned long nr_anon; unsigned long nr_file; @@ -1298,15 +1361,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, return SWAP_CLUSTER_MAX; } - + set_lumpy_reclaim_mode(priority, sc, false); lru_add_drain(); spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { nr_taken = isolate_pages_global(nr_to_scan, &page_list, &nr_scanned, sc->order, - sc->lumpy_reclaim_mode ? - ISOLATE_BOTH : ISOLATE_INACTIVE, + sc->lumpy_reclaim_mode == LUMPY_MODE_NONE ? + ISOLATE_INACTIVE : ISOLATE_BOTH, zone, 0, file); zone->pages_scanned += nr_scanned; if (current_is_kswapd()) @@ -1318,8 +1381,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, } else { nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list, &nr_scanned, sc->order, - sc->lumpy_reclaim_mode ? - ISOLATE_BOTH : ISOLATE_INACTIVE, + sc->lumpy_reclaim_mode == LUMPY_MODE_NONE ? + ISOLATE_INACTIVE : ISOLATE_BOTH, zone, sc->mem_cgroup, 0, file); /* @@ -1337,20 +1400,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, spin_unlock_irq(&zone->lru_lock); - nr_reclaimed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC); + nr_reclaimed = shrink_page_list(&page_list, zone, sc); /* Check if we should syncronously wait for writeback */ if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) { - congestion_wait(BLK_RW_ASYNC, HZ/10); - - /* - * The attempt at page out may have made some - * of the pages active, mark them inactive again. - */ - nr_active = clear_active_flags(&page_list, NULL); - count_vm_events(PGDEACTIVATE, nr_active); - - nr_reclaimed += shrink_page_list(&page_list, sc, PAGEOUT_IO_SYNC); + set_lumpy_reclaim_mode(priority, sc, true); + nr_reclaimed += shrink_page_list(&page_list, zone, sc); } local_irq_disable(); @@ -1359,6 +1414,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed); putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list); + + trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, + zone_idx(zone), + nr_scanned, nr_reclaimed, + priority, + trace_shrink_flags(file, sc->lumpy_reclaim_mode)); return nr_reclaimed; } @@ -1506,6 +1567,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, spin_unlock_irq(&zone->lru_lock); } +#ifdef CONFIG_SWAP static int inactive_anon_is_low_global(struct zone *zone) { unsigned long active, inactive; @@ -1531,12 +1593,26 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc) { int low; + /* + * If we don't have swap space, anonymous page deactivation + * is pointless. + */ + if (!total_swap_pages) + return 0; + if (scanning_global_lru(sc)) low = inactive_anon_is_low_global(zone); else low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup); return low; } +#else +static inline int inactive_anon_is_low(struct zone *zone, + struct scan_control *sc) +{ + return 0; +} +#endif static int inactive_file_is_low_global(struct zone *zone) { @@ -1721,21 +1797,6 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, } } -static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc) -{ - /* - * If we need a large contiguous chunk of memory, or have - * trouble getting a small set of contiguous pages, we - * will reclaim both active and inactive pages. - */ - if (sc->order > PAGE_ALLOC_COSTLY_ORDER) - sc->lumpy_reclaim_mode = 1; - else if (sc->order && priority < DEF_PRIORITY - 2) - sc->lumpy_reclaim_mode = 1; - else - sc->lumpy_reclaim_mode = 0; -} - /* * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. */ @@ -1750,8 +1811,6 @@ static void shrink_zone(int priority, struct zone *zone, get_scan_count(zone, sc, nr, priority); - set_lumpy_reclaim_mode(priority, sc); - while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { for_each_evictable_lru(l) { @@ -1782,7 +1841,7 @@ static void shrink_zone(int priority, struct zone *zone, * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0) + if (inactive_anon_is_low(zone, sc)) shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0); throttle_vm_writeout(sc->gfp_mask); @@ -1937,21 +1996,16 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, /* Take a nap, wait for some writeback to complete */ if (!sc->hibernation_mode && sc->nr_scanned && - priority < DEF_PRIORITY - 2) - congestion_wait(BLK_RW_ASYNC, HZ/10); + priority < DEF_PRIORITY - 2) { + struct zone *preferred_zone; + + first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask), + NULL, &preferred_zone); + wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10); + } } out: - /* - * Now that we've scanned all the zones at this priority level, note - * that level within the zone so that the next thread which performs - * scanning of this zone will immediately start out at this priority - * level. This affects only the decision whether or not to bring - * mapped pages onto the inactive list. - */ - if (priority < 0) - priority = 0; - delayacct_freepages_end(); put_mems_allowed(); @@ -2247,6 +2301,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) if (!zone_watermark_ok(zone, order, min_wmark_pages(zone), end_zone, 0)) has_under_min_watermark_zone = 1; + } else { + /* + * If a zone reaches its high watermark, + * consider it to be no longer congested. It's + * possible there are dirty pages backed by + * congested BDIs but as pressure is relieved, + * spectulatively avoid congestion waits + */ + zone_clear_flag(zone, ZONE_CONGESTED); } } @@ -2987,6 +3050,7 @@ int scan_unevictable_handler(struct ctl_table *table, int write, return 0; } +#ifdef CONFIG_NUMA /* * per node 'scan_unevictable_pages' attribute. On demand re-scan of * a specified node's per zone unevictable lists for evictable pages. @@ -3033,4 +3097,4 @@ void scan_unevictable_unregister_node(struct node *node) { sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages); } - +#endif diff --git a/mm/vmstat.c b/mm/vmstat.c index 355a9e669aaa..cd2e42be7b68 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -17,6 +17,8 @@ #include #include #include +#include +#include #ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; @@ -394,6 +396,7 @@ void zone_statistics(struct zone *preferred_zone, struct zone *z) #endif #ifdef CONFIG_COMPACTION + struct contig_page_info { unsigned long free_pages; unsigned long free_blocks_total; @@ -745,6 +748,11 @@ static const char * const vmstat_text[] = { "nr_isolated_anon", "nr_isolated_file", "nr_shmem", + "nr_dirtied", + "nr_written", + "nr_dirty_threshold", + "nr_dirty_background_threshold", + #ifdef CONFIG_NUMA "numa_hit", "numa_miss", @@ -904,36 +912,44 @@ static const struct file_operations proc_zoneinfo_file_operations = { .release = seq_release, }; +enum writeback_stat_item { + NR_DIRTY_THRESHOLD, + NR_DIRTY_BG_THRESHOLD, + NR_VM_WRITEBACK_STAT_ITEMS, +}; + static void *vmstat_start(struct seq_file *m, loff_t *pos) { unsigned long *v; -#ifdef CONFIG_VM_EVENT_COUNTERS - unsigned long *e; -#endif - int i; + int i, stat_items_size; if (*pos >= ARRAY_SIZE(vmstat_text)) return NULL; + stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) + + NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long); #ifdef CONFIG_VM_EVENT_COUNTERS - v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) - + sizeof(struct vm_event_state), GFP_KERNEL); -#else - v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long), - GFP_KERNEL); + stat_items_size += sizeof(struct vm_event_state); #endif + + v = kmalloc(stat_items_size, GFP_KERNEL); m->private = v; if (!v) return ERR_PTR(-ENOMEM); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) v[i] = global_page_state(i); + v += NR_VM_ZONE_STAT_ITEMS; + + global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, + v + NR_DIRTY_THRESHOLD); + v += NR_VM_WRITEBACK_STAT_ITEMS; + #ifdef CONFIG_VM_EVENT_COUNTERS - e = v + NR_VM_ZONE_STAT_ITEMS; - all_vm_events(e); - e[PGPGIN] /= 2; /* sectors -> kbytes */ - e[PGPGOUT] /= 2; + all_vm_events(v); + v[PGPGIN] /= 2; /* sectors -> kbytes */ + v[PGPGOUT] /= 2; #endif - return v + *pos; + return m->private + *pos; } static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0ebc777a6660..3c95304a0817 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,7 +117,7 @@ static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; static DEFINE_SPINLOCK(unix_table_lock); -static atomic_t unix_nr_socks = ATOMIC_INIT(0); +static atomic_long_t unix_nr_socks; #define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) @@ -360,13 +360,13 @@ static void unix_sock_destructor(struct sock *sk) if (u->addr) unix_release_addr(u->addr); - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); #ifdef UNIX_REFCNT_DEBUG - printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk, - atomic_read(&unix_nr_socks)); + printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk, + atomic_long_read(&unix_nr_socks)); #endif } @@ -606,8 +606,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) struct sock *sk = NULL; struct unix_sock *u; - atomic_inc(&unix_nr_socks); - if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) + atomic_long_inc(&unix_nr_socks); + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) goto out; sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto); @@ -632,7 +632,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) unix_insert_socket(unix_sockets_unbound, sk); out: if (sk == NULL) - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); else { local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 2039acdf5122..90b54d4697fd 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -2,7 +2,7 @@ # (c) 2001, Dave Jones. (the file handling bit) # (c) 2005, Joel Schopp (the ugly bit) # (c) 2007,2008, Andy Whitcroft (new conditions, test suite) -# (c) 2008,2009, Andy Whitcroft +# (c) 2008-2010 Andy Whitcroft # Licensed under the terms of the GNU GPL License version 2 use strict; @@ -10,7 +10,7 @@ use strict; my $P = $0; $P =~ s@.*/@@g; -my $V = '0.30'; +my $V = '0.31'; use Getopt::Long qw(:config no_auto_abbrev); @@ -103,6 +103,8 @@ for my $key (keys %debug) { die "$@" if ($@); } +my $rpt_cleaners = 0; + if ($terse) { $emacs = 1; $quiet++; @@ -150,6 +152,20 @@ our $Sparse = qr{ # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check our $Attribute = qr{ const| + __percpu| + __nocast| + __safe| + __bitwise__| + __packed__| + __packed2__| + __naked| + __maybe_unused| + __always_unused| + __noreturn| + __used| + __cold| + __noclone| + __deprecated| __read_mostly| __kprobes| __(?:mem|cpu|dev|)(?:initdata|initconst|init\b)| @@ -675,15 +691,15 @@ sub ctx_block_get { $blk .= $rawlines[$line]; # Handle nested #if/#else. - if ($rawlines[$line] =~ /^.\s*#\s*(?:ifndef|ifdef|if)\s/) { + if ($lines[$line] =~ /^.\s*#\s*(?:ifndef|ifdef|if)\s/) { push(@stack, $level); - } elsif ($rawlines[$line] =~ /^.\s*#\s*(?:else|elif)\b/) { + } elsif ($lines[$line] =~ /^.\s*#\s*(?:else|elif)\b/) { $level = $stack[$#stack - 1]; - } elsif ($rawlines[$line] =~ /^.\s*#\s*endif\b/) { + } elsif ($lines[$line] =~ /^.\s*#\s*endif\b/) { $level = pop(@stack); } - foreach my $c (split(//, $rawlines[$line])) { + foreach my $c (split(//, $lines[$line])) { ##print "C<$c>L<$level><$open$close>O<$off>\n"; if ($off > 0) { $off--; @@ -843,7 +859,12 @@ sub annotate_values { $av_preprocessor = 0; } - } elsif ($cur =~ /^($Type)\s*(?:$Ident|,|\)|\()/) { + } elsif ($cur =~ /^(\(\s*$Type\s*)\)/) { + print "CAST($1)\n" if ($dbg_values > 1); + push(@av_paren_type, $type); + $type = 'C'; + + } elsif ($cur =~ /^($Type)\s*(?:$Ident|,|\)|\(|\s*$)/) { print "DECLARE($1)\n" if ($dbg_values > 1); $type = 'T'; @@ -1308,7 +1329,11 @@ sub process { $here = "#$realline: " if ($file); # extract the filename as it passes - if ($line=~/^\+\+\+\s+(\S+)/) { + if ($line =~ /^diff --git.*?(\S+)$/) { + $realfile = $1; + $realfile =~ s@^([^/]*)/@@; + + } elsif ($line =~ /^\+\+\+\s+(\S+)/) { $realfile = $1; $realfile =~ s@^([^/]*)/@@; @@ -1332,6 +1357,14 @@ sub process { $cnt_lines++ if ($realcnt != 0); +# Check for incorrect file permissions + if ($line =~ /^new (file )?mode.*[7531]\d{0,2}$/) { + my $permhere = $here . "FILE: $realfile\n"; + if ($realfile =~ /(Makefile|Kconfig|\.c|\.h|\.S|\.tmpl)$/) { + ERROR("do not set execute permissions for source files\n" . $permhere); + } + } + #check the patch for a signoff: if ($line =~ /^\s*signed-off-by:/i) { # This is a signoff, if ugly, so do not double report. @@ -1389,21 +1422,38 @@ sub process { } elsif ($rawline =~ /^\+.*\S\s+$/ || $rawline =~ /^\+\s+$/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; ERROR("trailing whitespace\n" . $herevet); + $rpt_cleaners = 1; } # check for Kconfig help text having a real description +# Only applies when adding the entry originally, after that we do not have +# sufficient context to determine whether it is indeed long enough. if ($realfile =~ /Kconfig/ && - $line =~ /\+?\s*(---)?help(---)?$/) { + $line =~ /\+\s*(?:---)?help(?:---)?$/) { my $length = 0; - for (my $l = $linenr; defined($lines[$l]); $l++) { - my $f = $lines[$l]; + my $cnt = $realcnt; + my $ln = $linenr + 1; + my $f; + my $is_end = 0; + while ($cnt > 0 && defined $lines[$ln - 1]) { + $f = $lines[$ln - 1]; + $cnt-- if ($lines[$ln - 1] !~ /^-/); + $is_end = $lines[$ln - 1] =~ /^\+/; + $ln++; + + next if ($f =~ /^-/); + $f =~ s/^.//; $f =~ s/#.*//; $f =~ s/^\s+//; next if ($f =~ /^$/); - last if ($f =~ /^\s*config\s/); + if ($f =~ /^\s*config\s/) { + $is_end = 1; + last; + } $length++; } - WARN("please write a paragraph that describes the config symbol fully\n" . $herecurr) if ($length < 4); + WARN("please write a paragraph that describes the config symbol fully\n" . $herecurr) if ($is_end && $length < 4); + #print "is_end<$is_end> length<$length>\n"; } # check we are in a valid source file if not then ignore this hunk @@ -1450,6 +1500,7 @@ sub process { $rawline =~ /^\+\s* \s*/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; ERROR("code indent should use tabs where possible\n" . $herevet); + $rpt_cleaners = 1; } # check for space before tabs. @@ -1459,10 +1510,13 @@ sub process { } # check for spaces at the beginning of a line. - if ($rawline =~ /^\+ / && $rawline !~ /\+ +\*/) { +# Exceptions: +# 1) within comments +# 2) indented preprocessor commands +# 3) hanging labels + if ($rawline =~ /^\+ / && $line !~ /\+ *(?:$;|#|$Ident:)/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; - WARN("please, no space for starting a line, \ - excluding comments\n" . $herevet); + WARN("please, no spaces at the start of a line\n" . $herevet); } # check we are in a valid C source file if not then ignore this hunk @@ -1598,7 +1652,7 @@ sub process { if ($ctx !~ /{\s*/ && defined($lines[$ctx_ln -1]) && $lines[$ctx_ln - 1] =~ /^\+\s*{/) { ERROR("that open brace { should be on the previous line\n" . - "$here\n$ctx\n$lines[$ctx_ln - 1]\n"); + "$here\n$ctx\n$rawlines[$ctx_ln - 1]\n"); } if ($level == 0 && $pre_ctx !~ /}\s*while\s*\($/ && $ctx =~ /\)\s*\;\s*$/ && @@ -1607,7 +1661,7 @@ sub process { my ($nlength, $nindent) = line_stats($lines[$ctx_ln - 1]); if ($nindent > $indent) { WARN("trailing semicolon indicates no statements, indent implies otherwise\n" . - "$here\n$ctx\n$lines[$ctx_ln - 1]\n"); + "$here\n$ctx\n$rawlines[$ctx_ln - 1]\n"); } } } @@ -1768,8 +1822,17 @@ sub process { !defined $suppress_export{$realline_next} && ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/ || $lines[$realline_next - 1] =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + # Handle definitions which produce identifiers with + # a prefix: + # XXX(foo); + # EXPORT_SYMBOL(something_foo); my $name = $1; - if ($stat !~ /(?: + if ($stat =~ /^.([A-Z_]+)\s*\(\s*($Ident)/ && + $name =~ /^${Ident}_$2/) { +#print "FOO C name<$name>\n"; + $suppress_export{$realline_next} = 1; + + } elsif ($stat !~ /(?: \n.}\s*$| ^.DEFINE_$Ident\(\Q$name\E\)| ^.DECLARE_$Ident\(\Q$name\E\)| @@ -1806,6 +1869,23 @@ sub process { $herecurr); } +# check for static const char * arrays. + if ($line =~ /\bstatic\s+const\s+char\s*\*\s*(\w+)\s*\[\s*\]\s*=\s*/) { + WARN("static const char * array should probably be static const char * const\n" . + $herecurr); + } + +# check for static char foo[] = "bar" declarations. + if ($line =~ /\bstatic\s+char\s+(\w+)\s*\[\s*\]\s*=\s*"/) { + WARN("static char array declaration should probably be static const char\n" . + $herecurr); + } + +# check for declarations of struct pci_device_id + if ($line =~ /\bstruct\s+pci_device_id\s+\w+\s*\[\s*\]\s*\=\s*\{/) { + WARN("Use DEFINE_PCI_DEVICE_TABLE for struct pci_device_id\n" . $herecurr); + } + # check for new typedefs, only function parameters and sparse annotations # make sense. if ($line =~ /\btypedef\s/ && @@ -1899,6 +1979,11 @@ sub process { ERROR("open brace '{' following $1 go on the same line\n" . $hereprev); } +# missing space after union, struct or enum definition + if ($line =~ /^.\s*(?:typedef\s+)?(enum|union|struct)(?:\s+$Ident)?(?:\s+$Ident)?[=\{]/) { + WARN("missing space after $1 definition\n" . $herecurr); + } + # check for spacing round square brackets; allowed: # 1. with a type on the left -- int [] a; # 2. at the beginning of a line for slice initialisers -- [0...10] = 5, @@ -2176,21 +2261,29 @@ sub process { my $value = $2; # Flatten any parentheses - $value =~ s/\)\(/\) \(/g; + $value =~ s/\(/ \(/g; + $value =~ s/\)/\) /g; while ($value =~ s/\[[^\{\}]*\]/1/ || $value !~ /(?:$Ident|-?$Constant)\s* $Compare\s* (?:$Ident|-?$Constant)/x && $value =~ s/\([^\(\)]*\)/1/) { } - - if ($value =~ /^(?:$Ident|-?$Constant)$/) { +#print "value<$value>\n"; + if ($value =~ /^\s*(?:$Ident|-?$Constant)\s*$/) { ERROR("return is not a function, parentheses are not required\n" . $herecurr); } elsif ($spacing !~ /\s+/) { ERROR("space required before the open parenthesis '('\n" . $herecurr); } } +# Return of what appears to be an errno should normally be -'ve + if ($line =~ /^.\s*return\s*(E[A-Z]*)\s*;/) { + my $name = $1; + if ($name ne 'EOF' && $name ne 'ERROR') { + WARN("return of an errno should typically be -ve (return -$1)\n" . $herecurr); + } + } # Need a space before open parenthesis after if, while etc if ($line=~/\b(if|while|for|switch)\(/) { @@ -2409,8 +2502,8 @@ sub process { \.$Ident\s*=\s*| ^\"|\"$ }x; - #print "REST<$rest> dstat<$dstat>\n"; - if ($rest ne '') { + #print "REST<$rest> dstat<$dstat> ctx<$ctx>\n"; + if ($rest ne '' && $rest ne ',') { if ($rest !~ /while\s*\(/ && $dstat !~ /$exceptions/) { @@ -2839,6 +2932,15 @@ sub process { print "\n" if ($quiet == 0); } + if ($quiet == 0) { + # If there were whitespace errors which cleanpatch can fix + # then suggest that. + if ($rpt_cleaners) { + print "NOTE: whitespace errors detected, you may wish to use scripts/cleanpatch or\n"; + print " scripts/cleanfile\n\n"; + } + } + if ($clean == 1 && $quiet == 0) { print "$vname has no obvious style problems and is ready for submission.\n" } diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index b2281982f52f..d21ec3a89603 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.24'; +my $V = '0.26-beta6'; use Getopt::Long qw(:config no_auto_abbrev); @@ -24,15 +24,19 @@ my $email_maintainer = 1; my $email_list = 1; my $email_subscriber_list = 0; my $email_git_penguin_chiefs = 0; -my $email_git = 1; +my $email_git = 0; my $email_git_all_signature_types = 0; my $email_git_blame = 0; +my $email_git_blame_signatures = 1; +my $email_git_fallback = 1; my $email_git_min_signatures = 1; my $email_git_max_maintainers = 5; my $email_git_min_percent = 5; my $email_git_since = "1-year-ago"; my $email_hg_since = "-365"; +my $interactive = 0; my $email_remove_duplicates = 1; +my $email_use_mailmap = 1; my $output_multiline = 1; my $output_separator = ", "; my $output_roles = 0; @@ -49,8 +53,13 @@ my $pattern_depth = 0; my $version = 0; my $help = 0; +my $vcs_used = 0; + my $exit = 0; +my %commit_author_hash; +my %commit_signer_hash; + my @penguin_chief = (); push(@penguin_chief, "Linus Torvalds:torvalds\@linux-foundation.org"); #Andrew wants in on most everything - 2009/01/14 @@ -73,7 +82,6 @@ my @signature_tags = (); push(@signature_tags, "Signed-off-by:"); push(@signature_tags, "Reviewed-by:"); push(@signature_tags, "Acked-by:"); -my $signaturePattern = "\(" . join("|", @signature_tags) . "\)"; # rfc822 email address - preloaded methods go here. my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; @@ -86,31 +94,70 @@ my %VCS_cmds; my %VCS_cmds_git = ( "execute_cmd" => \&git_execute_cmd, "available" => '(which("git") ne "") && (-d ".git")', - "find_signers_cmd" => "git log --no-color --since=\$email_git_since -- \$file", - "find_commit_signers_cmd" => "git log --no-color -1 \$commit", + "find_signers_cmd" => + "git log --no-color --since=\$email_git_since " . + '--format="GitCommit: %H%n' . + 'GitAuthor: %an <%ae>%n' . + 'GitDate: %aD%n' . + 'GitSubject: %s%n' . + '%b%n"' . + " -- \$file", + "find_commit_signers_cmd" => + "git log --no-color " . + '--format="GitCommit: %H%n' . + 'GitAuthor: %an <%ae>%n' . + 'GitDate: %aD%n' . + 'GitSubject: %s%n' . + '%b%n"' . + " -1 \$commit", + "find_commit_author_cmd" => + "git log --no-color " . + '--format="GitCommit: %H%n' . + 'GitAuthor: %an <%ae>%n' . + 'GitDate: %aD%n' . + 'GitSubject: %s%n"' . + " -1 \$commit", "blame_range_cmd" => "git blame -l -L \$diff_start,+\$diff_length \$file", "blame_file_cmd" => "git blame -l \$file", - "commit_pattern" => "^commit [0-9a-f]{40,40}", - "blame_commit_pattern" => "^([0-9a-f]+) " + "commit_pattern" => "^GitCommit: ([0-9a-f]{40,40})", + "blame_commit_pattern" => "^([0-9a-f]+) ", + "author_pattern" => "^GitAuthor: (.*)", + "subject_pattern" => "^GitSubject: (.*)", ); my %VCS_cmds_hg = ( "execute_cmd" => \&hg_execute_cmd, "available" => '(which("hg") ne "") && (-d ".hg")', "find_signers_cmd" => - "hg log --date=\$email_hg_since" . - " --template='commit {node}\\n{desc}\\n' -- \$file", - "find_commit_signers_cmd" => "hg log --template='{desc}\\n' -r \$commit", + "hg log --date=\$email_hg_since " . + "--template='HgCommit: {node}\\n" . + "HgAuthor: {author}\\n" . + "HgSubject: {desc}\\n'" . + " -- \$file", + "find_commit_signers_cmd" => + "hg log " . + "--template='HgSubject: {desc}\\n'" . + " -r \$commit", + "find_commit_author_cmd" => + "hg log " . + "--template='HgCommit: {node}\\n" . + "HgAuthor: {author}\\n" . + "HgSubject: {desc|firstline}\\n'" . + " -r \$commit", "blame_range_cmd" => "", # not supported - "blame_file_cmd" => "hg blame -c \$file", - "commit_pattern" => "^commit [0-9a-f]{40,40}", - "blame_commit_pattern" => "^([0-9a-f]+):" + "blame_file_cmd" => "hg blame -n \$file", + "commit_pattern" => "^HgCommit: ([0-9a-f]{40,40})", + "blame_commit_pattern" => "^([ 0-9a-f]+):", + "author_pattern" => "^HgAuthor: (.*)", + "subject_pattern" => "^HgSubject: (.*)", ); -if (-f "${lk_path}.get_maintainer.conf") { +my $conf = which_conf(".get_maintainer.conf"); +if (-f $conf) { my @conf_args; - open(my $conffile, '<', "${lk_path}.get_maintainer.conf") - or warn "$P: Can't open .get_maintainer.conf: $!\n"; + open(my $conffile, '<', "$conf") + or warn "$P: Can't find a readable .get_maintainer.conf file $!\n"; + while (<$conffile>) { my $line = $_; @@ -136,13 +183,17 @@ if (!GetOptions( 'git!' => \$email_git, 'git-all-signature-types!' => \$email_git_all_signature_types, 'git-blame!' => \$email_git_blame, + 'git-blame-signatures!' => \$email_git_blame_signatures, + 'git-fallback!' => \$email_git_fallback, 'git-chief-penguins!' => \$email_git_penguin_chiefs, 'git-min-signatures=i' => \$email_git_min_signatures, 'git-max-maintainers=i' => \$email_git_max_maintainers, 'git-min-percent=i' => \$email_git_min_percent, 'git-since=s' => \$email_git_since, 'hg-since=s' => \$email_hg_since, + 'i|interactive!' => \$interactive, 'remove-duplicates!' => \$email_remove_duplicates, + 'mailmap!' => \$email_use_mailmap, 'm!' => \$email_maintainer, 'n!' => \$email_usename, 'l!' => \$email_list, @@ -181,13 +232,9 @@ if (-t STDIN && !@ARGV) { die "$P: missing patchfile or -f file - use --help if necessary\n"; } -if ($output_separator ne ", ") { - $output_multiline = 0; -} - -if ($output_rolestats) { - $output_roles = 1; -} +$output_multiline = 0 if ($output_separator ne ", "); +$output_rolestats = 1 if ($interactive); +$output_roles = 1 if ($output_rolestats); if ($sections) { $email = 0; @@ -197,6 +244,7 @@ if ($sections) { $subsystem = 0; $web = 0; $keywords = 0; + $interactive = 0; } else { my $selections = $email + $scm + $status + $subsystem + $web; if ($selections == 0) { @@ -215,10 +263,6 @@ if (!top_of_kernel_tree($lk_path)) { . "a linux kernel source tree.\n"; } -if ($email_git_all_signature_types) { - $signaturePattern = "(.+?)[Bb][Yy]:"; -} - ## Read MAINTAINERS for type/value pairs my @typevalue = (); @@ -253,31 +297,82 @@ while (<$maint>) { } close($maint); -my %mailmap; -if ($email_remove_duplicates) { - open(my $mailmap, '<', "${lk_path}.mailmap") +# +# Read mail address map +# + +my $mailmap; + +read_mailmap(); + +sub read_mailmap { + $mailmap = { + names => {}, + addresses => {} + }; + + return if (!$email_use_mailmap || !(-f "${lk_path}.mailmap")); + + open(my $mailmap_file, '<', "${lk_path}.mailmap") or warn "$P: Can't open .mailmap: $!\n"; - while (<$mailmap>) { - my $line = $_; - next if ($line =~ m/^\s*#/); - next if ($line =~ m/^\s*$/); + while (<$mailmap_file>) { + s/#.*$//; #strip comments + s/^\s+|\s+$//g; #trim - my ($name, $address) = parse_email($line); - $line = format_email($name, $address, $email_usename); + next if (/^\s*$/); #skip empty lines + #entries have one of the following formats: + # name1 + # + # name1 + # name1 name2 + # (see man git-shortlog) + if (/^(.+)<(.+)>$/) { + my $real_name = $1; + my $address = $2; - next if ($line =~ m/^\s*$/); + $real_name =~ s/\s+$//; + ($real_name, $address) = parse_email("$real_name <$address>"); + $mailmap->{names}->{$address} = $real_name; - if (exists($mailmap{$name})) { - my $obj = $mailmap{$name}; - push(@$obj, $address); - } else { - my @arr = ($address); - $mailmap{$name} = \@arr; + } elsif (/^<([^\s]+)>\s*<([^\s]+)>$/) { + my $real_address = $1; + my $wrong_address = $2; + + $mailmap->{addresses}->{$wrong_address} = $real_address; + + } elsif (/^(.+)<([^\s]+)>\s*<([^\s]+)>$/) { + my $real_name = $1; + my $real_address = $2; + my $wrong_address = $3; + + $real_name =~ s/\s+$//; + ($real_name, $real_address) = + parse_email("$real_name <$real_address>"); + $mailmap->{names}->{$wrong_address} = $real_name; + $mailmap->{addresses}->{$wrong_address} = $real_address; + + } elsif (/^(.+)<([^\s]+)>\s*([^\s].*)<([^\s]+)>$/) { + my $real_name = $1; + my $real_address = $2; + my $wrong_name = $3; + my $wrong_address = $4; + + $real_name =~ s/\s+$//; + ($real_name, $real_address) = + parse_email("$real_name <$real_address>"); + + $wrong_name =~ s/\s+$//; + ($wrong_name, $wrong_address) = + parse_email("$wrong_name <$wrong_address>"); + + my $wrong_email = format_email($wrong_name, $wrong_address, 1); + $mailmap->{names}->{$wrong_email} = $real_name; + $mailmap->{addresses}->{$wrong_email} = $real_address; } } - close($mailmap); + close($mailmap_file); } ## use the filenames on the command line or find the filenames in the patchfiles @@ -302,7 +397,7 @@ foreach my $file (@ARGV) { } if ($from_filename) { push(@files, $file); - if (-f $file && ($keywords || $file_emails)) { + if ($file ne "MAINTAINERS" && -f $file && ($keywords || $file_emails)) { open(my $f, '<', $file) or die "$P: Can't open $file: $!\n"; my $text = do { local($/) ; <$f> }; @@ -357,134 +452,24 @@ foreach my $file (@ARGV) { @file_emails = uniq(@file_emails); +my %email_hash_name; +my %email_hash_address; my @email_to = (); +my %hash_list_to; my @list_to = (); my @scm = (); my @web = (); my @subsystem = (); my @status = (); +my %deduplicate_name_hash = (); +my %deduplicate_address_hash = (); +my $signature_pattern; -# Find responsible parties +my @maintainers = get_maintainers(); -foreach my $file (@files) { - - my %hash; - my $tvi = find_first_section(); - while ($tvi < @typevalue) { - my $start = find_starting_index($tvi); - my $end = find_ending_index($tvi); - my $exclude = 0; - my $i; - - #Do not match excluded file patterns - - for ($i = $start; $i < $end; $i++) { - my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { - my $type = $1; - my $value = $2; - if ($type eq 'X') { - if (file_match_pattern($file, $value)) { - $exclude = 1; - last; - } - } - } - } - - if (!$exclude) { - for ($i = $start; $i < $end; $i++) { - my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { - my $type = $1; - my $value = $2; - if ($type eq 'F') { - if (file_match_pattern($file, $value)) { - my $value_pd = ($value =~ tr@/@@); - my $file_pd = ($file =~ tr@/@@); - $value_pd++ if (substr($value,-1,1) ne "/"); - if ($pattern_depth == 0 || - (($file_pd - $value_pd) < $pattern_depth)) { - $hash{$tvi} = $value_pd; - } - } - } - } - } - } - - $tvi = $end + 1; - } - - foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) { - add_categories($line); - if ($sections) { - my $i; - my $start = find_starting_index($line); - my $end = find_ending_index($line); - for ($i = $start; $i < $end; $i++) { - my $line = $typevalue[$i]; - if ($line =~ /^[FX]:/) { ##Restore file patterns - $line =~ s/([^\\])\.([^\*])/$1\?$2/g; - $line =~ s/([^\\])\.$/$1\?/g; ##Convert . back to ? - $line =~ s/\\\./\./g; ##Convert \. to . - $line =~ s/\.\*/\*/g; ##Convert .* to * - } - $line =~ s/^([A-Z]):/$1:\t/g; - print("$line\n"); - } - print("\n"); - } - } - - if ($email && $email_git) { - vcs_file_signoffs($file); - } - - if ($email && $email_git_blame) { - vcs_file_blame($file); - } -} - -if ($keywords) { - @keyword_tvi = sort_and_uniq(@keyword_tvi); - foreach my $line (@keyword_tvi) { - add_categories($line); - } -} - -if ($email) { - foreach my $chief (@penguin_chief) { - if ($chief =~ m/^(.*):(.*)/) { - my $email_address; - - $email_address = format_email($1, $2, $email_usename); - if ($email_git_penguin_chiefs) { - push(@email_to, [$email_address, 'chief penguin']); - } else { - @email_to = grep($_->[0] !~ /${email_address}/, @email_to); - } - } - } - - foreach my $email (@file_emails) { - my ($name, $address) = parse_email($email); - - my $tmp_email = format_email($name, $address, $email_usename); - push_email_address($tmp_email, ''); - add_role($tmp_email, 'in file'); - } -} - -if ($email || $email_list) { - my @to = (); - if ($email) { - @to = (@to, @email_to); - } - if ($email_list) { - @to = (@to, @list_to); - } - output(merge_email(@to)); +if (@maintainers) { + @maintainers = merge_email(@maintainers); + output(@maintainers); } if ($scm) { @@ -509,6 +494,167 @@ if ($web) { exit($exit); +sub get_maintainers { + %email_hash_name = (); + %email_hash_address = (); + %commit_author_hash = (); + %commit_signer_hash = (); + @email_to = (); + %hash_list_to = (); + @list_to = (); + @scm = (); + @web = (); + @subsystem = (); + @status = (); + %deduplicate_name_hash = (); + %deduplicate_address_hash = (); + if ($email_git_all_signature_types) { + $signature_pattern = "(.+?)[Bb][Yy]:"; + } else { + $signature_pattern = "\(" . join("|", @signature_tags) . "\)"; + } + + # Find responsible parties + + my %exact_pattern_match_hash = (); + + foreach my $file (@files) { + + my %hash; + my $tvi = find_first_section(); + while ($tvi < @typevalue) { + my $start = find_starting_index($tvi); + my $end = find_ending_index($tvi); + my $exclude = 0; + my $i; + + #Do not match excluded file patterns + + for ($i = $start; $i < $end; $i++) { + my $line = $typevalue[$i]; + if ($line =~ m/^(\C):\s*(.*)/) { + my $type = $1; + my $value = $2; + if ($type eq 'X') { + if (file_match_pattern($file, $value)) { + $exclude = 1; + last; + } + } + } + } + + if (!$exclude) { + for ($i = $start; $i < $end; $i++) { + my $line = $typevalue[$i]; + if ($line =~ m/^(\C):\s*(.*)/) { + my $type = $1; + my $value = $2; + if ($type eq 'F') { + if (file_match_pattern($file, $value)) { + my $value_pd = ($value =~ tr@/@@); + my $file_pd = ($file =~ tr@/@@); + $value_pd++ if (substr($value,-1,1) ne "/"); + $value_pd = -1 if ($value =~ /^\.\*/); + if ($value_pd >= $file_pd) { + $exact_pattern_match_hash{$file} = 1; + } + if ($pattern_depth == 0 || + (($file_pd - $value_pd) < $pattern_depth)) { + $hash{$tvi} = $value_pd; + } + } + } + } + } + } + $tvi = $end + 1; + } + + foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) { + add_categories($line); + if ($sections) { + my $i; + my $start = find_starting_index($line); + my $end = find_ending_index($line); + for ($i = $start; $i < $end; $i++) { + my $line = $typevalue[$i]; + if ($line =~ /^[FX]:/) { ##Restore file patterns + $line =~ s/([^\\])\.([^\*])/$1\?$2/g; + $line =~ s/([^\\])\.$/$1\?/g; ##Convert . back to ? + $line =~ s/\\\./\./g; ##Convert \. to . + $line =~ s/\.\*/\*/g; ##Convert .* to * + } + $line =~ s/^([A-Z]):/$1:\t/g; + print("$line\n"); + } + print("\n"); + } + } + } + + if ($keywords) { + @keyword_tvi = sort_and_uniq(@keyword_tvi); + foreach my $line (@keyword_tvi) { + add_categories($line); + } + } + + foreach my $email (@email_to, @list_to) { + $email->[0] = deduplicate_email($email->[0]); + } + + foreach my $file (@files) { + if ($email && + ($email_git || ($email_git_fallback && + !$exact_pattern_match_hash{$file}))) { + vcs_file_signoffs($file); + } + if ($email && $email_git_blame) { + vcs_file_blame($file); + } + } + + if ($email) { + foreach my $chief (@penguin_chief) { + if ($chief =~ m/^(.*):(.*)/) { + my $email_address; + + $email_address = format_email($1, $2, $email_usename); + if ($email_git_penguin_chiefs) { + push(@email_to, [$email_address, 'chief penguin']); + } else { + @email_to = grep($_->[0] !~ /${email_address}/, @email_to); + } + } + } + + foreach my $email (@file_emails) { + my ($name, $address) = parse_email($email); + + my $tmp_email = format_email($name, $address, $email_usename); + push_email_address($tmp_email, ''); + add_role($tmp_email, 'in file'); + } + } + + my @to = (); + if ($email || $email_list) { + if ($email) { + @to = (@to, @email_to); + } + if ($email_list) { + @to = (@to, @list_to); + } + } + + if ($interactive) { + @to = interactive_get_maintainers(\@to); + } + + return @to; +} + sub file_match_pattern { my ($file, $pattern) = @_; if (substr($pattern, -1) eq "/") { @@ -537,7 +683,8 @@ MAINTAINER field selection options: --email => print email address(es) if any --git => include recent git \*-by: signers --git-all-signature-types => include signers regardless of signature type - or use only ${signaturePattern} signers (default: $email_git_all_signature_types) + or use only ${signature_pattern} signers (default: $email_git_all_signature_types) + --git-fallback => use git when no exact MAINTAINERS pattern (default: $email_git_fallback) --git-chief-penguins => include ${penguin_chiefs} --git-min-signatures => number of signatures required (default: $email_git_min_signatures) --git-max-maintainers => maximum maintainers to add (default: $email_git_max_maintainers) @@ -545,6 +692,7 @@ MAINTAINER field selection options: --git-blame => use git blame to find modified commits for patch or file --git-since => git history to use (default: $email_git_since) --hg-since => hg history to use (default: $email_hg_since) + --interactive => display a menu (mostly useful if used with the --git option) --m => include maintainer(s) if any --n => include name 'Full Name ' --l => include list(s) if any @@ -565,8 +713,9 @@ Output type options: Other options: --pattern-depth => Number of pattern directory traversals (default: 0 (all)) - --keywords => scan patch for keywords (default: 1 (on)) - --sections => print the entire subsystem sections with pattern matches + --keywords => scan patch for keywords (default: $keywords) + --sections => print all of the subsystem sections with pattern matches + --mailmap => use .mailmap file (default: $email_use_mailmap) --version => show version --help => show this help information @@ -606,30 +755,30 @@ EOT } sub top_of_kernel_tree { - my ($lk_path) = @_; + my ($lk_path) = @_; - if ($lk_path ne "" && substr($lk_path,length($lk_path)-1,1) ne "/") { - $lk_path .= "/"; - } - if ( (-f "${lk_path}COPYING") - && (-f "${lk_path}CREDITS") - && (-f "${lk_path}Kbuild") - && (-f "${lk_path}MAINTAINERS") - && (-f "${lk_path}Makefile") - && (-f "${lk_path}README") - && (-d "${lk_path}Documentation") - && (-d "${lk_path}arch") - && (-d "${lk_path}include") - && (-d "${lk_path}drivers") - && (-d "${lk_path}fs") - && (-d "${lk_path}init") - && (-d "${lk_path}ipc") - && (-d "${lk_path}kernel") - && (-d "${lk_path}lib") - && (-d "${lk_path}scripts")) { - return 1; - } - return 0; + if ($lk_path ne "" && substr($lk_path,length($lk_path)-1,1) ne "/") { + $lk_path .= "/"; + } + if ( (-f "${lk_path}COPYING") + && (-f "${lk_path}CREDITS") + && (-f "${lk_path}Kbuild") + && (-f "${lk_path}MAINTAINERS") + && (-f "${lk_path}Makefile") + && (-f "${lk_path}README") + && (-d "${lk_path}Documentation") + && (-d "${lk_path}arch") + && (-d "${lk_path}include") + && (-d "${lk_path}drivers") + && (-d "${lk_path}fs") + && (-d "${lk_path}init") + && (-d "${lk_path}ipc") + && (-d "${lk_path}kernel") + && (-d "${lk_path}lib") + && (-d "${lk_path}scripts")) { + return 1; + } + return 0; } sub parse_email { @@ -821,11 +970,19 @@ sub add_categories { } if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - push(@list_to, [$list_address, "subscriber list${list_role}"]); + if (!$hash_list_to{lc($list_address)}) { + $hash_list_to{lc($list_address)} = 1; + push(@list_to, [$list_address, + "subscriber list${list_role}"]); + } } } else { if ($email_list) { - push(@list_to, [$list_address, "open list${list_role}"]); + if (!$hash_list_to{lc($list_address)}) { + $hash_list_to{lc($list_address)} = 1; + push(@list_to, [$list_address, + "open list${list_role}"]); + } } } } elsif ($ptype eq "M") { @@ -856,15 +1013,12 @@ sub add_categories { } } -my %email_hash_name; -my %email_hash_address; - sub email_inuse { my ($name, $address) = @_; return 1 if (($name eq "") && ($address eq "")); - return 1 if (($name ne "") && exists($email_hash_name{$name})); - return 1 if (($address ne "") && exists($email_hash_address{$address})); + return 1 if (($name ne "") && exists($email_hash_name{lc($name)})); + return 1 if (($address ne "") && exists($email_hash_address{lc($address)})); return 0; } @@ -882,8 +1036,8 @@ sub push_email_address { push(@email_to, [format_email($name, $address, $email_usename), $role]); } elsif (!email_inuse($name, $address)) { push(@email_to, [format_email($name, $address, $email_usename), $role]); - $email_hash_name{$name}++; - $email_hash_address{$address}++; + $email_hash_name{lc($name)}++ if ($name ne ""); + $email_hash_address{lc($address)}++; } return 1; @@ -952,30 +1106,69 @@ sub which { return ""; } -sub mailmap { - my (@lines) = @_; - my %hash; +sub which_conf { + my ($conf) = @_; - foreach my $line (@lines) { - my ($name, $address) = parse_email($line); - if (!exists($hash{$name})) { - $hash{$name} = $address; - } elsif ($address ne $hash{$name}) { - $address = $hash{$name}; - $line = format_email($name, $address, $email_usename); - } - if (exists($mailmap{$name})) { - my $obj = $mailmap{$name}; - foreach my $map_address (@$obj) { - if (($map_address eq $address) && - ($map_address ne $hash{$name})) { - $line = format_email($name, $hash{$name}, $email_usename); - } - } + foreach my $path (split(/:/, ".:$ENV{HOME}:.scripts")) { + if (-e "$path/$conf") { + return "$path/$conf"; } } - return @lines; + return ""; +} + +sub mailmap_email { + my ($line) = @_; + + my ($name, $address) = parse_email($line); + my $email = format_email($name, $address, 1); + my $real_name = $name; + my $real_address = $address; + + if (exists $mailmap->{names}->{$email} || + exists $mailmap->{addresses}->{$email}) { + if (exists $mailmap->{names}->{$email}) { + $real_name = $mailmap->{names}->{$email}; + } + if (exists $mailmap->{addresses}->{$email}) { + $real_address = $mailmap->{addresses}->{$email}; + } + } else { + if (exists $mailmap->{names}->{$address}) { + $real_name = $mailmap->{names}->{$address}; + } + if (exists $mailmap->{addresses}->{$address}) { + $real_address = $mailmap->{addresses}->{$address}; + } + } + return format_email($real_name, $real_address, 1); +} + +sub mailmap { + my (@addresses) = @_; + + my @mapped_emails = (); + foreach my $line (@addresses) { + push(@mapped_emails, mailmap_email($line)); + } + merge_by_realname(@mapped_emails) if ($email_use_mailmap); + return @mapped_emails; +} + +sub merge_by_realname { + my %address_map; + my (@emails) = @_; + + foreach my $email (@emails) { + my ($name, $address) = parse_email($email); + if (exists $address_map{$name}) { + $address = $address_map{$name}; + $email = format_email($name, $address, 1); + } else { + $address_map{$name} = $address; + } + } } sub git_execute_cmd { @@ -999,10 +1192,30 @@ sub hg_execute_cmd { return @lines; } +sub extract_formatted_signatures { + my (@signature_lines) = @_; + + my @type = @signature_lines; + + s/\s*(.*):.*/$1/ for (@type); + + # cut -f2- -d":" + s/\s*.*:\s*(.+)\s*/$1/ for (@signature_lines); + +## Reformat email addresses (with names) to avoid badly written signatures + + foreach my $signer (@signature_lines) { + $signer = deduplicate_email($signer); + } + + return (\@type, \@signature_lines); +} + sub vcs_find_signers { my ($cmd) = @_; - my @lines = (); my $commits; + my @lines = (); + my @signatures = (); @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); @@ -1010,21 +1223,48 @@ sub vcs_find_signers { $commits = grep(/$pattern/, @lines); # of commits - @lines = grep(/^[ \t]*${signaturePattern}.*\@.*$/, @lines); + @signatures = grep(/^[ \t]*${signature_pattern}.*\@.*$/, @lines); + + return (0, @signatures) if !@signatures; + + save_commits_by_author(@lines) if ($interactive); + save_commits_by_signer(@lines) if ($interactive); + + if (!$email_git_penguin_chiefs) { + @signatures = grep(!/${penguin_chiefs}/i, @signatures); + } + + my ($types_ref, $signers_ref) = extract_formatted_signatures(@signatures); + + return ($commits, @$signers_ref); +} + +sub vcs_find_author { + my ($cmd) = @_; + my @lines = (); + + @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); + if (!$email_git_penguin_chiefs) { @lines = grep(!/${penguin_chiefs}/i, @lines); } - # cut -f2- -d":" - s/.*:\s*(.+)\s*/$1/ for (@lines); -## Reformat email addresses (with names) to avoid badly written signatures + return @lines if !@lines; + my @authors = (); foreach my $line (@lines) { - my ($name, $address) = parse_email($line); - $line = format_email($name, $address, 1); + if ($line =~ m/$VCS_cmds{"author_pattern"}/) { + my $author = $1; + my ($name, $address) = parse_email($author); + $author = format_email($name, $address, 1); + push(@authors, $author); + } } - return ($commits, @lines); + save_commits_by_author(@lines) if ($interactive); + save_commits_by_signer(@lines) if ($interactive); + + return @authors; } sub vcs_save_commits { @@ -1084,6 +1324,10 @@ sub vcs_blame { @commits = vcs_save_commits($cmd); } + foreach my $commit (@commits) { + $commit =~ s/^\^//g; + } + return @commits; } @@ -1092,7 +1336,7 @@ sub vcs_exists { %VCS_cmds = %VCS_cmds_git; return 1 if eval $VCS_cmds{"available"}; %VCS_cmds = %VCS_cmds_hg; - return 1 if eval $VCS_cmds{"available"}; + return 2 if eval $VCS_cmds{"available"}; %VCS_cmds = (); if (!$printed_novcs) { warn("$P: No supported VCS found. Add --nogit to options?\n"); @@ -1104,6 +1348,405 @@ sub vcs_exists { return 0; } +sub vcs_is_git { + vcs_exists(); + return $vcs_used == 1; +} + +sub vcs_is_hg { + return $vcs_used == 2; +} + +sub interactive_get_maintainers { + my ($list_ref) = @_; + my @list = @$list_ref; + + vcs_exists(); + + my %selected; + my %authored; + my %signed; + my $count = 0; + my $maintained = 0; + foreach my $entry (@list) { + $maintained = 1 if ($entry->[1] =~ /^(maintainer|supporter)/i); + $selected{$count} = 1; + $authored{$count} = 0; + $signed{$count} = 0; + $count++; + } + + #menu loop + my $done = 0; + my $print_options = 0; + my $redraw = 1; + while (!$done) { + $count = 0; + if ($redraw) { + printf STDERR "\n%1s %2s %-65s", + "*", "#", "email/list and role:stats"; + if ($email_git || + ($email_git_fallback && !$maintained) || + $email_git_blame) { + print STDERR "auth sign"; + } + print STDERR "\n"; + foreach my $entry (@list) { + my $email = $entry->[0]; + my $role = $entry->[1]; + my $sel = ""; + $sel = "*" if ($selected{$count}); + my $commit_author = $commit_author_hash{$email}; + my $commit_signer = $commit_signer_hash{$email}; + my $authored = 0; + my $signed = 0; + $authored++ for (@{$commit_author}); + $signed++ for (@{$commit_signer}); + printf STDERR "%1s %2d %-65s", $sel, $count + 1, $email; + printf STDERR "%4d %4d", $authored, $signed + if ($authored > 0 || $signed > 0); + printf STDERR "\n %s\n", $role; + if ($authored{$count}) { + my $commit_author = $commit_author_hash{$email}; + foreach my $ref (@{$commit_author}) { + print STDERR " Author: @{$ref}[1]\n"; + } + } + if ($signed{$count}) { + my $commit_signer = $commit_signer_hash{$email}; + foreach my $ref (@{$commit_signer}) { + print STDERR " @{$ref}[2]: @{$ref}[1]\n"; + } + } + + $count++; + } + } + my $date_ref = \$email_git_since; + $date_ref = \$email_hg_since if (vcs_is_hg()); + if ($print_options) { + $print_options = 0; + if (vcs_exists()) { + print STDERR <; + chomp($input); + + $redraw = 1; + my $rerun = 0; + my @wish = split(/[, ]+/, $input); + foreach my $nr (@wish) { + $nr = lc($nr); + my $sel = substr($nr, 0, 1); + my $str = substr($nr, 1); + my $val = 0; + $val = $1 if $str =~ /^(\d+)$/; + + if ($sel eq "y") { + $interactive = 0; + $done = 1; + $output_rolestats = 0; + $output_roles = 0; + last; + } elsif ($nr =~ /^\d+$/ && $nr > 0 && $nr <= $count) { + $selected{$nr - 1} = !$selected{$nr - 1}; + } elsif ($sel eq "*" || $sel eq '^') { + my $toggle = 0; + $toggle = 1 if ($sel eq '*'); + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = $toggle; + } + } elsif ($sel eq "0") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i}; + } + } elsif ($sel eq "t") { + if (lc($str) eq "m") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(maintainer|supporter)/i); + } + } elsif (lc($str) eq "g") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(author|commit|signer)/i); + } + } elsif (lc($str) eq "l") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(open list)/i); + } + } elsif (lc($str) eq "s") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(subscriber list)/i); + } + } + } elsif ($sel eq "a") { + if ($val > 0 && $val <= $count) { + $authored{$val - 1} = !$authored{$val - 1}; + } elsif ($str eq '*' || $str eq '^') { + my $toggle = 0; + $toggle = 1 if ($str eq '*'); + for (my $i = 0; $i < $count; $i++) { + $authored{$i} = $toggle; + } + } + } elsif ($sel eq "s") { + if ($val > 0 && $val <= $count) { + $signed{$val - 1} = !$signed{$val - 1}; + } elsif ($str eq '*' || $str eq '^') { + my $toggle = 0; + $toggle = 1 if ($str eq '*'); + for (my $i = 0; $i < $count; $i++) { + $signed{$i} = $toggle; + } + } + } elsif ($sel eq "o") { + $print_options = 1; + $redraw = 1; + } elsif ($sel eq "g") { + if ($str eq "f") { + bool_invert(\$email_git_fallback); + } else { + bool_invert(\$email_git); + } + $rerun = 1; + } elsif ($sel eq "b") { + if ($str eq "s") { + bool_invert(\$email_git_blame_signatures); + } else { + bool_invert(\$email_git_blame); + } + $rerun = 1; + } elsif ($sel eq "c") { + if ($val > 0) { + $email_git_min_signatures = $val; + $rerun = 1; + } + } elsif ($sel eq "x") { + if ($val > 0) { + $email_git_max_maintainers = $val; + $rerun = 1; + } + } elsif ($sel eq "%") { + if ($str ne "" && $val >= 0) { + $email_git_min_percent = $val; + $rerun = 1; + } + } elsif ($sel eq "d") { + if (vcs_is_git()) { + $email_git_since = $str; + } elsif (vcs_is_hg()) { + $email_hg_since = $str; + } + $rerun = 1; + } elsif ($sel eq "t") { + bool_invert(\$email_git_all_signature_types); + $rerun = 1; + } elsif ($sel eq "f") { + bool_invert(\$file_emails); + $rerun = 1; + } elsif ($sel eq "r") { + bool_invert(\$email_remove_duplicates); + $rerun = 1; + } elsif ($sel eq "m") { + bool_invert(\$email_use_mailmap); + read_mailmap(); + $rerun = 1; + } elsif ($sel eq "k") { + bool_invert(\$keywords); + $rerun = 1; + } elsif ($sel eq "p") { + if ($str ne "" && $val >= 0) { + $pattern_depth = $val; + $rerun = 1; + } + } elsif ($sel eq "h" || $sel eq "?") { + print STDERR <[0]; + $address = $deduplicate_name_hash{lc($name)}->[1]; + $matched = 1; + } elsif ($deduplicate_address_hash{lc($address)}) { + $name = $deduplicate_address_hash{lc($address)}->[0]; + $address = $deduplicate_address_hash{lc($address)}->[1]; + $matched = 1; + } + if (!$matched) { + $deduplicate_name_hash{lc($name)} = [ $name, $address ]; + $deduplicate_address_hash{lc($address)} = [ $name, $address ]; + } + $email = format_email($name, $address, 1); + $email = mailmap_email($email); + return $email; +} + +sub save_commits_by_author { + my (@lines) = @_; + + my @authors = (); + my @commits = (); + my @subjects = (); + + foreach my $line (@lines) { + if ($line =~ m/$VCS_cmds{"author_pattern"}/) { + my $author = $1; + $author = deduplicate_email($author); + push(@authors, $author); + } + push(@commits, $1) if ($line =~ m/$VCS_cmds{"commit_pattern"}/); + push(@subjects, $1) if ($line =~ m/$VCS_cmds{"subject_pattern"}/); + } + + for (my $i = 0; $i < @authors; $i++) { + my $exists = 0; + foreach my $ref(@{$commit_author_hash{$authors[$i]}}) { + if (@{$ref}[0] eq $commits[$i] && + @{$ref}[1] eq $subjects[$i]) { + $exists = 1; + last; + } + } + if (!$exists) { + push(@{$commit_author_hash{$authors[$i]}}, + [ ($commits[$i], $subjects[$i]) ]); + } + } +} + +sub save_commits_by_signer { + my (@lines) = @_; + + my $commit = ""; + my $subject = ""; + + foreach my $line (@lines) { + $commit = $1 if ($line =~ m/$VCS_cmds{"commit_pattern"}/); + $subject = $1 if ($line =~ m/$VCS_cmds{"subject_pattern"}/); + if ($line =~ /^[ \t]*${signature_pattern}.*\@.*$/) { + my @signatures = ($line); + my ($types_ref, $signers_ref) = extract_formatted_signatures(@signatures); + my @types = @$types_ref; + my @signers = @$signers_ref; + + my $type = $types[0]; + my $signer = $signers[0]; + + $signer = deduplicate_email($signer); + + my $exists = 0; + foreach my $ref(@{$commit_signer_hash{$signer}}) { + if (@{$ref}[0] eq $commit && + @{$ref}[1] eq $subject && + @{$ref}[2] eq $type) { + $exists = 1; + last; + } + } + if (!$exists) { + push(@{$commit_signer_hash{$signer}}, + [ ($commit, $subject, $type) ]); + } + } + } +} + sub vcs_assign { my ($role, $divisor, @lines) = @_; @@ -1117,9 +1760,9 @@ sub vcs_assign { $divisor = 1; } - if ($email_remove_duplicates) { - @lines = mailmap(@lines); - } + @lines = mailmap(@lines); + + return if (@lines <= 0); @lines = sort(@lines); @@ -1152,12 +1795,18 @@ sub vcs_file_signoffs { my @signers = (); my $commits; - return if (!vcs_exists()); + $vcs_used = vcs_exists(); + return if (!$vcs_used); my $cmd = $VCS_cmds{"find_signers_cmd"}; $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd ($commits, @signers) = vcs_find_signers($cmd); + + foreach my $signer (@signers) { + $signer = deduplicate_email($signer); + } + vcs_assign("commit_signer", $commits, @signers); } @@ -1165,29 +1814,114 @@ sub vcs_file_blame { my ($file) = @_; my @signers = (); + my @all_commits = (); my @commits = (); my $total_commits; + my $total_lines; - return if (!vcs_exists()); + $vcs_used = vcs_exists(); + return if (!$vcs_used); - @commits = vcs_blame($file); - @commits = uniq(@commits); + @all_commits = vcs_blame($file); + @commits = uniq(@all_commits); $total_commits = @commits; + $total_lines = @all_commits; - foreach my $commit (@commits) { - my $commit_count; - my @commit_signers = (); + if ($email_git_blame_signatures) { + if (vcs_is_hg()) { + my $commit_count; + my @commit_signers = (); + my $commit = join(" -r ", @commits); + my $cmd; - my $cmd = $VCS_cmds{"find_commit_signers_cmd"}; - $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + $cmd = $VCS_cmds{"find_commit_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd - ($commit_count, @commit_signers) = vcs_find_signers($cmd); - push(@signers, @commit_signers); + ($commit_count, @commit_signers) = vcs_find_signers($cmd); + + push(@signers, @commit_signers); + } else { + foreach my $commit (@commits) { + my $commit_count; + my @commit_signers = (); + my $cmd; + + $cmd = $VCS_cmds{"find_commit_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd + + ($commit_count, @commit_signers) = vcs_find_signers($cmd); + + push(@signers, @commit_signers); + } + } } if ($from_filename) { + if ($output_rolestats) { + my @blame_signers; + if (vcs_is_hg()) {{ # Double brace for last exit + my $commit_count; + my @commit_signers = (); + @commits = uniq(@commits); + @commits = sort(@commits); + my $commit = join(" -r ", @commits); + my $cmd; + + $cmd = $VCS_cmds{"find_commit_author_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd + + my @lines = (); + + @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); + + if (!$email_git_penguin_chiefs) { + @lines = grep(!/${penguin_chiefs}/i, @lines); + } + + last if !@lines; + + my @authors = (); + foreach my $line (@lines) { + if ($line =~ m/$VCS_cmds{"author_pattern"}/) { + my $author = $1; + $author = deduplicate_email($author); + push(@authors, $author); + } + } + + save_commits_by_author(@lines) if ($interactive); + save_commits_by_signer(@lines) if ($interactive); + + push(@signers, @authors); + }} + else { + foreach my $commit (@commits) { + my $i; + my $cmd = $VCS_cmds{"find_commit_author_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + my @author = vcs_find_author($cmd); + next if !@author; + + my $formatted_author = deduplicate_email($author[0]); + + my $count = grep(/$commit/, @all_commits); + for ($i = 0; $i < $count ; $i++) { + push(@blame_signers, $formatted_author); + } + } + } + if (@blame_signers) { + vcs_assign("authored lines", $total_lines, @blame_signers); + } + } + foreach my $signer (@signers) { + $signer = deduplicate_email($signer); + } vcs_assign("commits", $total_commits, @signers); } else { + foreach my $signer (@signers) { + $signer = deduplicate_email($signer); + } vcs_assign("modified commits", $total_commits, @signers); } }