From b98acbff9a05b371c5f0ca6e44a3af8ce9274379 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 11 Jan 2017 15:36:20 +0000 Subject: [PATCH 001/131] regulator: twl6030: fix range comparison, allowing vsel = 59 The range min_uV > 1350000 && min_uV <= 150000 is never reachable because of a typo in the previous range check and hence vsel = 59 is never reached. Fix the previous range check to enable the vsel = 59 setting. Fixes CoverityScan CID#728454 ("Logially dead code") Signed-off-by: Colin Ian King Signed-off-by: Mark Brown --- drivers/regulator/twl6030-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c index 4864b9d742c0..716191046a70 100644 --- a/drivers/regulator/twl6030-regulator.c +++ b/drivers/regulator/twl6030-regulator.c @@ -452,7 +452,7 @@ static int twl6030smps_map_voltage(struct regulator_dev *rdev, int min_uV, vsel = 62; else if ((min_uV > 1800000) && (min_uV <= 1900000)) vsel = 61; - else if ((min_uV > 1350000) && (min_uV <= 1800000)) + else if ((min_uV > 1500000) && (min_uV <= 1800000)) vsel = 60; else if ((min_uV > 1350000) && (min_uV <= 1500000)) vsel = 59; From b5b46c4740aed1538544f0fa849c5b76c7823469 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 18 Jan 2017 14:29:21 +0100 Subject: [PATCH 002/131] objtool: Fix IRET's opcode The IRET opcode is 0xcf according to the Intel manual and also to objdump of my vmlinux: 1ea8: 48 cf iretq Fix the opcode in arch_decode_instruction(). The previous value (0xc5) seems to correspond to LDS. Signed-off-by: Jiri Slaby Acked-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170118132921.19319-1-jslaby@suse.cz Signed-off-by: Ingo Molnar --- tools/objtool/arch/x86/decode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 5e0dea2cdc01..039636ffb6c8 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -150,9 +150,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, *type = INSN_RETURN; break; - case 0xc5: /* iret */ case 0xca: /* retf */ case 0xcb: /* retf */ + case 0xcf: /* iret */ *type = INSN_CONTEXT_SWITCH; break; From 24d615a694d649aa2e167c3f97f62bdad07e3f84 Mon Sep 17 00:00:00 2001 From: Aleksander Morgado Date: Wed, 18 Jan 2017 21:31:31 +0100 Subject: [PATCH 003/131] USB: serial: qcserial: add Dell DW5570 QDL The Dell DW5570 is a re-branded Sierra Wireless MC8805 which will by default boot with vid 0x413c and pid 0x81a3. When triggered QDL download mode, the device switches to pid 0x81a6 and provides the standard TTY used for firmware upgrade. Cc: Signed-off-by: Aleksander Morgado Signed-off-by: Johan Hovold --- drivers/usb/serial/qcserial.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 1bc6089b9008..696458db7e3c 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -124,6 +124,7 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE(0x1410, 0xa021)}, /* Novatel Gobi 3000 Composite */ {USB_DEVICE(0x413c, 0x8193)}, /* Dell Gobi 3000 QDL */ {USB_DEVICE(0x413c, 0x8194)}, /* Dell Gobi 3000 Composite */ + {USB_DEVICE(0x413c, 0x81a6)}, /* Dell DW5570 QDL (MC8805) */ {USB_DEVICE(0x1199, 0x68a4)}, /* Sierra Wireless QDL */ {USB_DEVICE(0x1199, 0x68a5)}, /* Sierra Wireless Modem */ {USB_DEVICE(0x1199, 0x68a8)}, /* Sierra Wireless QDL */ From 773c7220e22d193e5667c352fcbf8d47eefc817f Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Fri, 13 Jan 2017 12:48:06 -0500 Subject: [PATCH 004/131] scsi: virtio_scsi: Reject commands when virtqueue is broken In the case of a graceful set of detaches, where the virtio-scsi-ccw disk is removed from the guest prior to the controller, the guest behaves quite normally. Specifically, the detach gets us into sd_sync_cache to issue a Synchronize Cache(10) command, which immediately fails (and is retried a couple of times) because the device has been removed. Later, the removal of the controller sees two CRWs presented, but there's no further indication of the removal from the guest viewpoint. [ 17.217458] sd 0:0:0:0: [sda] Synchronizing SCSI cache [ 17.219257] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK [ 21.449400] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2 [ 21.449406] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0 However, on s390, the SCSI disks can be removed "by surprise" when an entire controller (host) is removed and all associated disks are removed via the loop in scsi_forget_host. The same call to sd_sync_cache is made, but because the controller has already been removed, the Synchronize Cache(10) command is neither issued (and then failed) nor rejected. That the I/O isn't returned means the guest cannot have other devices added nor removed, and other tasks (such as shutdown or reboot) issued by the guest will not complete either. The virtio ring has already been marked as broken (via virtio_break_device in virtio_ccw_remove), but we still attempt to queue the command only to have it remain there. The calling sequence provides a bit of distinction for us: virtscsi_queuecommand() -> virtscsi_kick_cmd() -> virtscsi_add_cmd() -> virtqueue_add_sgs() -> virtqueue_add() if success return 0 elseif vq->broken or vring_mapping_error() return -EIO else return -ENOSPC A return of ENOSPC is generally a temporary condition, so returning "host busy" from virtscsi_queuecommand makes sense here, to have it redriven in a moment or two. But the EIO return code is more of a permanent error and so it would be wise to return the I/O itself and allow the calling thread to finish gracefully. The result is these four kernel messages in the guest (the fourth one does not occur prior to this patch): [ 22.921562] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2 [ 22.921580] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0 [ 22.921978] sd 0:0:0:0: [sda] Synchronizing SCSI cache [ 22.921993] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK I opted to fill in the same response data that is returned from the more graceful device detach, where the disk device is removed prior to the controller device. Signed-off-by: Eric Farman Reviewed-by: Fam Zheng Signed-off-by: Martin K. Petersen --- drivers/scsi/virtio_scsi.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index ec91bd07f00a..c680d7641311 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -534,7 +534,9 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi, { struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev); struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc); + unsigned long flags; int req_size; + int ret; BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize); @@ -562,8 +564,15 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi, req_size = sizeof(cmd->req.cmd); } - if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0) + ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)); + if (ret == -EIO) { + cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET; + spin_lock_irqsave(&req_vq->vq_lock, flags); + virtscsi_complete_cmd(vscsi, cmd); + spin_unlock_irqrestore(&req_vq->vq_lock, flags); + } else if (ret != 0) { return SCSI_MLQUEUE_HOST_BUSY; + } return 0; } From a5badd1e97e6caeca78ad74191f12fc923c403a8 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Sat, 14 Jan 2017 19:51:52 -0800 Subject: [PATCH 005/131] iio: health: afe4403: retrieve a valid iio_dev in suspend/resume The suspend/resume functions were using dev_to_iio_dev() to get the iio_dev. That only works on IIO dev's. Replace it with spi functions to get the correct iio_dev. Signed-off-by: Alison Schofield Acked-by: Andrew F. Davis Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/health/afe4403.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c index 9a081465c42f..6bb23a49e81e 100644 --- a/drivers/iio/health/afe4403.c +++ b/drivers/iio/health/afe4403.c @@ -422,7 +422,7 @@ MODULE_DEVICE_TABLE(of, afe4403_of_match); static int __maybe_unused afe4403_suspend(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = spi_get_drvdata(to_spi_device(dev)); struct afe4403_data *afe = iio_priv(indio_dev); int ret; @@ -443,7 +443,7 @@ static int __maybe_unused afe4403_suspend(struct device *dev) static int __maybe_unused afe4403_resume(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = spi_get_drvdata(to_spi_device(dev)); struct afe4403_data *afe = iio_priv(indio_dev); int ret; From 802ecfc113df1e15af1d028427cbbe785ae9cc4a Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Sat, 14 Jan 2017 19:52:50 -0800 Subject: [PATCH 006/131] iio: health: afe4404: retrieve a valid iio_dev in suspend/resume The suspend/resume functions were using dev_to_iio_dev() to get the iio_dev. That only works on IIO dev's. Replace it with i2c functions to get the correct iio_dev. Signed-off-by: Alison Schofield Acked-by: Andrew F. Davis Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/health/afe4404.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c index 45266404f7e3..964f5231a831 100644 --- a/drivers/iio/health/afe4404.c +++ b/drivers/iio/health/afe4404.c @@ -428,7 +428,7 @@ MODULE_DEVICE_TABLE(of, afe4404_of_match); static int __maybe_unused afe4404_suspend(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev)); struct afe4404_data *afe = iio_priv(indio_dev); int ret; @@ -449,7 +449,7 @@ static int __maybe_unused afe4404_suspend(struct device *dev) static int __maybe_unused afe4404_resume(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev)); struct afe4404_data *afe = iio_priv(indio_dev); int ret; From 828f84ee8f84710ea1818b3565add268bcb824c8 Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Mon, 16 Jan 2017 18:04:18 -0800 Subject: [PATCH 007/131] iio: health: max30100: fixed parenthesis around FIFO count check FIFO was being read every sample after the "almost full" state was reached. This was due to an incorrect placement of the parenthesis in the while condition check. Note - the fixes tag is not actually correct, but the fix in this patch would also be needed for it to function correctly so we'll go with that one. Backports should pick up both. Signed-off-by: Matt Ranostay Fixes: b74fccad7 ("iio: health: max30100: correct FIFO check condition") Cc: Stable@vger.kernel.org> Signed-off-by: Jonathan Cameron --- drivers/iio/health/max30100.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/health/max30100.c b/drivers/iio/health/max30100.c index 90ab8a2d2846..183c14329d6e 100644 --- a/drivers/iio/health/max30100.c +++ b/drivers/iio/health/max30100.c @@ -238,7 +238,7 @@ static irqreturn_t max30100_interrupt_handler(int irq, void *private) mutex_lock(&data->lock); - while (cnt || (cnt = max30100_fifo_count(data) > 0)) { + while (cnt || (cnt = max30100_fifo_count(data)) > 0) { ret = max30100_read_measurement(data); if (ret) break; From d1aaf20ee655888c227d5137b7a63551f8d15416 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 16 Jan 2017 11:27:52 -0800 Subject: [PATCH 008/131] iio: adc: palmas_gpadc: retrieve a valid iio_dev in suspend/resume The suspend/resume functions were using dev_to_iio_dev() to get the iio_dev. That only works on IIO dev's. Use dev_get_drvdata() for a platform device to get the correct iio_dev. Signed-off-by: Alison Schofield Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 2bbf0c521beb..7d61b566e148 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -775,7 +775,7 @@ static int palmas_adc_wakeup_reset(struct palmas_gpadc *adc) static int palmas_gpadc_suspend(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); int wakeup = adc->wakeup1_enable || adc->wakeup2_enable; int ret; @@ -798,7 +798,7 @@ static int palmas_gpadc_suspend(struct device *dev) static int palmas_gpadc_resume(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); int wakeup = adc->wakeup1_enable || adc->wakeup2_enable; int ret; From 5c113b5e0082e90d2e1c7b12e96a7b8cf0623e27 Mon Sep 17 00:00:00 2001 From: John Brooks Date: Wed, 18 Jan 2017 21:50:39 +0000 Subject: [PATCH 009/131] iio: dht11: Use usleep_range instead of msleep for start signal The DHT22 (AM2302) datasheet specifies that the LOW start pulse should not exceed 20ms. However, observations with an oscilloscope of an RPi Model 2B (rev 1.1) communicating with a DHT22 sensor showed that the driver was consistently sending start pulses longer than 20ms: Kernel 4.7.10-v7+ (n=132): Minimum pulse length: 20.20ms Maximum: 29.84ms Mean: 24.96ms StDev: 2.82ms Sensor response rate: 100% Read success rate: 76% On kernel 4.8, the start pulse was so long that the sensor would not even respond 97% of the time: Kernel 4.8.16-v7+ (n=100): Minimum pulse length: 30.4ms Maximum: 74.4ms Mean: 39.3ms StDev: 10.2ms Sensor response rate: 3% Read success rate: 3% The driver would return ETIMEDOUT and write log messages like this: [ 51.430987] dht11 dht11@0: Only 1 signal edges detected [ 66.311019] dht11 dht11@0: Only 0 signal edges detected Replacing msleep(18) with usleep_range(18000, 20000) made the pulse length sane again and restored responsiveness: Kernel 4.8.16-v7+ with usleep_range (n=123): Minimum pulse length: 18.16ms Maximum: 20.20ms Mean: 19.85ms StDev: 0.51ms Sensor response rate: 100% Read success rate: 84% Cc: stable@vger.kernel.org Signed-off-by: John Brooks Reviewed-by: Harald Geyer Signed-off-by: Jonathan Cameron --- drivers/iio/humidity/dht11.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/humidity/dht11.c b/drivers/iio/humidity/dht11.c index 9c47bc98f3ac..2a22ad920333 100644 --- a/drivers/iio/humidity/dht11.c +++ b/drivers/iio/humidity/dht11.c @@ -71,7 +71,8 @@ * a) select an implementation using busy loop polling on those systems * b) use the checksum to do some probabilistic decoding */ -#define DHT11_START_TRANSMISSION 18 /* ms */ +#define DHT11_START_TRANSMISSION_MIN 18000 /* us */ +#define DHT11_START_TRANSMISSION_MAX 20000 /* us */ #define DHT11_MIN_TIMERES 34000 /* ns */ #define DHT11_THRESHOLD 49000 /* ns */ #define DHT11_AMBIG_LOW 23000 /* ns */ @@ -228,7 +229,8 @@ static int dht11_read_raw(struct iio_dev *iio_dev, ret = gpio_direction_output(dht11->gpio, 0); if (ret) goto err; - msleep(DHT11_START_TRANSMISSION); + usleep_range(DHT11_START_TRANSMISSION_MIN, + DHT11_START_TRANSMISSION_MAX); ret = gpio_direction_input(dht11->gpio); if (ret) goto err; From c26665ab5c49ad3e142e0f054ca3204f259ba09c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 20 Jan 2017 21:29:40 +0100 Subject: [PATCH 010/131] x86/microcode/intel: Drop stashed AP patch pointer optimization This was meant to save us the scanning of the microcode containter in the initrd since the first AP had already done that but it can also hurt us: Imagine a single hyperthreaded CPU (Intel(R) Atom(TM) CPU N270, for example) which updates the microcode on the BSP but since the microcode engine is shared between the two threads, the update on CPU1 doesn't happen because it has already happened on CPU0 and we don't find a newer microcode revision on CPU1. Which doesn't set the intel_ucode_patch pointer and at initrd jettisoning time we don't save the microcode patch for later application. Now, when we suspend to RAM, the loaded microcode gets cleared so we need to reload but there's no patch saved in the cache. Removing the optimization fixes this issue and all is fine and dandy. Fixes: 06b8534cb728 ("x86/microcode: Rework microcode loading") Signed-off-by: Borislav Petkov Reviewed-by: Thomas Gleixner Link: http://lkml.kernel.org/r/20170120202955.4091-2-bp@alien8.de Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/microcode/intel.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 3f329b74e040..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ From 4c833368f0bf748d4147bf301b1f95bc8eccb3c0 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sun, 22 Jan 2017 16:50:23 +0800 Subject: [PATCH 011/131] x86/fpu: Set the xcomp_bv when we fake up a XSAVES area I got the following calltrace on a Apollo Lake SoC with 32-bit kernel: WARNING: CPU: 2 PID: 261 at arch/x86/include/asm/fpu/internal.h:363 fpu__restore+0x1f5/0x260 [...] Hardware name: Intel Corp. Broxton P/NOTEBOOK, BIOS APLIRVPA.X64.0138.B35.1608091058 08/09/2016 Call Trace: dump_stack() __warn() ? fpu__restore() warn_slowpath_null() fpu__restore() __fpu__restore_sig() fpu__restore_sig() restore_sigcontext.isra.9() sys_sigreturn() do_int80_syscall_32() entry_INT80_32() The reason is that a #GP occurs when executing XRSTORS. The root cause is that we forget to set the xcomp_bv when we fake up the XSAVES area in the copyin_to_xsaves() function. Signed-off-by: Kevin Hao Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Quentin Casasnovas Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/1485075023-30161-1-git-send-email-haokexin@gmail.com Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/fpu/xstate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1d7770447b3e..e287b9075527 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1070,6 +1070,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= xfeatures; + xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xsave->header.xfeatures; return 0; } From d0e287a401d9acf67b75180b26e2d62b7d482652 Mon Sep 17 00:00:00 2001 From: Rask Ingemann Lambertsen Date: Sat, 21 Jan 2017 17:11:43 +0100 Subject: [PATCH 012/131] regulator: axp20x: AXP806: Fix dcdcb being set instead of dcdce A typo or copy-paste bug means that the register access intended for regulator dcdce goes to dcdcb instead. This patch corrects it. Fixes: 2ca342d391e3 (regulator: axp20x: Support AXP806 variant) Signed-off-by: Rask Ingemann Lambertsen Acked-by: Chen-Yu Tsai Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/regulator/axp20x-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index e6a512ebeae2..a3ade9e4ef47 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -272,7 +272,7 @@ static const struct regulator_desc axp806_regulators[] = { 64, AXP806_DCDCD_V_CTRL, 0x3f, AXP806_PWR_OUT_CTRL1, BIT(3)), AXP_DESC(AXP806, DCDCE, "dcdce", "vine", 1100, 3400, 100, - AXP806_DCDCB_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(4)), + AXP806_DCDCE_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(4)), AXP_DESC(AXP806, ALDO1, "aldo1", "aldoin", 700, 3300, 100, AXP806_ALDO1_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(5)), AXP_DESC(AXP806, ALDO2, "aldo2", "aldoin", 700, 3400, 100, From af2b7fa17eb92e52b65f96604448ff7a2a89ee99 Mon Sep 17 00:00:00 2001 From: Darren Stevens Date: Mon, 23 Jan 2017 19:42:54 +0000 Subject: [PATCH 013/131] powerpc: Add missing error check to prom_find_boot_cpu() prom_init.c calls 'instance-to-package' twice, but the return is not checked during prom_find_boot_cpu(). The result is then passed to prom_getprop(), which could be PROM_ERROR. Add a return check to prevent this. This was found on a pasemi system, where CFE doesn't have a working 'instance-to package' prom call. Before Commit 5c0484e25ec0 ('powerpc: Endian safe trampoline') the area around addr 0 was mostly 0's and this doesn't cause a problem. Once the macro 'FIXUP_ENDIAN' has been added to head_64.S, the low memory area now has non-zero values, which cause the prom_getprop() call to hang. mpe: Also confirmed that under SLOF if 'instance-to-package' did fail with PROM_ERROR we would crash in SLOF. So the bug is not specific to CFE, it's just that other open firmwares don't trigger it because they have a working 'instance-to-package'. Fixes: 5c0484e25ec0 ("powerpc: Endian safe trampoline") Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Darren Stevens Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/prom_init.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ec47a939cbdd..ac83eb04a8b8 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2834,6 +2834,9 @@ static void __init prom_find_boot_cpu(void) cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + if (!PHANDLE_VALID(cpu_pkg)) + return; + prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); From dffba9a31c7769be3231c420d4b364c92ba3f1ac Mon Sep 17 00:00:00 2001 From: Yu-cheng Yu Date: Mon, 23 Jan 2017 14:54:44 -0800 Subject: [PATCH 014/131] x86/fpu/xstate: Fix xcomp_bv in XSAVES header The compacted-format XSAVES area is determined at boot time and never changed after. The field xsave.header.xcomp_bv indicates which components are in the fixed XSAVES format. In fpstate_init() we did not set xcomp_bv to reflect the XSAVES format since at the time there is no valid data. However, after we do copy_init_fpstate_to_fpregs() in fpu__clear(), as in commit: b22cbe404a9c x86/fpu: Fix invalid FPU ptrace state after execve() and when __fpu_restore_sig() does fpu__restore() for a COMPAT-mode app, a #GP occurs. This can be easily triggered by doing valgrind on a COMPAT-mode "Hello World," as reported by Joakim Tjernlund and others: https://bugzilla.kernel.org/show_bug.cgi?id=190061 Fix it by setting xcomp_bv correctly. This patch also moves the xcomp_bv initialization to the proper place, which was in copyin_to_xsaves() as of: 4c833368f0bf x86/fpu: Set the xcomp_bv when we fake up a XSAVES area which fixed the bug too, but it's more efficient and cleaner to initialize things once per boot, not for every signal handling operation. Reported-by: Kevin Hao Reported-by: Joakim Tjernlund Signed-off-by: Yu-cheng Yu Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Fenghua Yu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Ravi V. Shankar Cc: Thomas Gleixner Cc: haokexin@gmail.com Link: http://lkml.kernel.org/r/1485212084-4418-1-git-send-email-yu-cheng.yu@intel.com [ Combined it with 4c833368f0bf. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 4 +++- arch/x86/kernel/fpu/xstate.c | 1 - 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..de7234401275 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -183,7 +184,8 @@ void fpstate_init(union fpregs_state *state) * it will #GP. Make sure it is replaced after the memset(). */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; + state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index e287b9075527..1d7770447b3e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1070,7 +1070,6 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= xfeatures; - xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xsave->header.xfeatures; return 0; } From f05fea5b3574a5926c53865eea27139bb40b2f2b Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 19 Jan 2017 10:10:16 +1100 Subject: [PATCH 015/131] powerpc/eeh: Fix wrong flag passed to eeh_unfreeze_pe() In __eeh_clear_pe_frozen_state(), we should pass the flag's value instead of its address to eeh_unfreeze_pe(). The isolated flag is cleared if no error returned from __eeh_clear_pe_frozen_state(). We never observed the error from the function. So the isolated flag should have been always cleared, no real issue is caused because of the misused @flag. This fixes the code by passing the value of @flag to eeh_unfreeze_pe(). Fixes: 5cfb20b96f6 ("powerpc/eeh: Emulate EEH recovery for VFIO devices") Cc: stable@vger.kernel.org # v3.18+ Signed-off-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/eeh_driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d88573bdd090..b94887165a10 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -545,7 +545,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - bool *clear_sw_state = flag; + bool clear_sw_state = *(bool *)flag; int i, rc = 1; for (i = 0; rc && i < 3; i++) From f2574030b0e33263b8a1c28fa3c4fa9292283799 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 24 Jan 2017 21:37:20 +1100 Subject: [PATCH 016/131] powerpc: Revert the initial stack protector support Unfortunately the stack protector support we merged recently only works on some toolchains. If the toolchain is built without glibc support everything works fine, but if glibc is built then it leads to a panic at boot. The solution is not rc5 material, so revert the support for now. This reverts commits: 6533b7c16ee5 ("powerpc: Initial stack protector (-fstack-protector) support") 902e06eb86cd ("powerpc/32: Change the stack protector canary value per task") Fixes: 6533b7c16ee5 ("powerpc: Initial stack protector (-fstack-protector) support") Signed-off-by: Michael Ellerman --- arch/powerpc/Kconfig | 1 - arch/powerpc/include/asm/stackprotector.h | 40 ----------------------- arch/powerpc/kernel/Makefile | 4 --- arch/powerpc/kernel/asm-offsets.c | 3 -- arch/powerpc/kernel/entry_32.S | 6 +--- arch/powerpc/kernel/process.c | 6 ---- 6 files changed, 1 insertion(+), 59 deletions(-) delete mode 100644 arch/powerpc/include/asm/stackprotector.h diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a8ee573fe610..a46d1c0d14d3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,7 +164,6 @@ config PPC select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select HAVE_ARCH_HARDENED_USERCOPY select HAVE_KERNEL_GZIP - select HAVE_CC_STACKPROTECTOR config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h deleted file mode 100644 index 6720190eabec..000000000000 --- a/arch/powerpc/include/asm/stackprotector.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * GCC stack protector support. - * - * Stack protector works by putting predefined pattern at the start of - * the stack frame and verifying that it hasn't been overwritten when - * returning from the function. The pattern is called stack canary - * and gcc expects it to be defined by a global variable called - * "__stack_chk_guard" on PPC. This unfortunately means that on SMP - * we cannot have a different canary value per task. - */ - -#ifndef _ASM_STACKPROTECTOR_H -#define _ASM_STACKPROTECTOR_H - -#include -#include -#include - -extern unsigned long __stack_chk_guard; - -/* - * Initialize the stackprotector canary value. - * - * NOTE: this must only be called from functions that never return, - * and it must always be inlined. - */ -static __always_inline void boot_init_stack_canary(void) -{ - unsigned long canary; - - /* Try to get a semi random initial value. */ - get_random_bytes(&canary, sizeof(canary)); - canary ^= mftb(); - canary ^= LINUX_VERSION_CODE; - - current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; -} - -#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 23f8082d7bfa..f4c2b52e58b3 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,10 +19,6 @@ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) -# -fstack-protector triggers protection checks in this code, -# but it is being used too early to link to meaningful stack_chk logic. -CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) - ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0601e6a7297c..195a9fc8f81c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -91,9 +91,6 @@ int main(void) DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp)); #endif -#ifdef CONFIG_CC_STACKPROTECTOR - DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); -#endif DEFINE(KSP, offsetof(struct thread_struct, ksp)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 5742dbdbee46..3841d749a430 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -674,11 +674,7 @@ BEGIN_FTR_SECTION mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ -#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP) - lwz r0,TSK_STACK_CANARY(r2) - lis r4,__stack_chk_guard@ha - stw r0,__stack_chk_guard@l(r4) -#endif + lwz r0,_CCR(r1) mtcrf 0xFF,r0 /* r3-r12 are destroyed -- Cort */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 04885cec24df..5dd056df0baa 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -64,12 +64,6 @@ #include #include -#ifdef CONFIG_CC_STACKPROTECTOR -#include -unsigned long __stack_chk_guard __read_mostly; -EXPORT_SYMBOL(__stack_chk_guard); -#endif - /* Transactional Memory debug */ #ifdef TM_DEBUG_SW #define TM_DEBUG(x...) printk(KERN_INFO x) From 5d03a2fd2292e71936c4235885c35ccc3c94695b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Tue, 24 Jan 2017 10:31:18 +0100 Subject: [PATCH 017/131] USB: serial: option: add device ID for HP lt2523 (Novatel E371) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Yet another laptop vendor rebranded Novatel E371. Cc: stable@vger.kernel.org Signed-off-by: Bjørn Mork Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7ce31a4c7e7f..42cc72e54c05 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2007,6 +2007,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); From b5fa0f7f88edcde37df1807fdf9ff10ec787a60e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 24 Jan 2017 16:36:57 +1100 Subject: [PATCH 018/131] powerpc: Fix build failure with clang due to BUILD_BUG_ON() Anton says: In commit 4db7327194db ("powerpc: Add option to use jump label for cpu_has_feature()") and commit c12e6f24d413 ("powerpc: Add option to use jump label for mmu_has_feature()") we added: BUILD_BUG_ON(!__builtin_constant_p(feature)) to cpu_has_feature() and mmu_has_feature() in order to catch usage issues (such as cpu_has_feature(cpu_has_feature(X), which has happened once in the past). Unfortunately LLVM isn't smart enough to resolve this, and it errors out. I work around it in my clang/LLVM builds of the kernel, but I have just discovered that it causes a lot of issues for the bcc (eBPF) trace tool (which uses LLVM). For now just #ifdef it away for clang builds. Fixes: 4db7327194db ("powerpc: Add option to use jump label for cpu_has_feature()") Fixes: c12e6f24d413 ("powerpc: Add option to use jump label for mmu_has_feature()") Cc: stable@vger.kernel.org # v4.8+ Reported-by: Anton Blanchard Tested-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cpu_has_feature.h | 2 ++ arch/powerpc/include/asm/mmu.h | 2 ++ 2 files changed, 4 insertions(+) diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index b312b152461b..6e834caa3720 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -23,7 +23,9 @@ static __always_inline bool cpu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index a34c764ca8dd..233a7e8cc8e3 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -160,7 +160,9 @@ static __always_inline bool mmu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { From 407788b51db6f6aab499d02420082f436abf3238 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 24 Jan 2017 09:18:57 -0600 Subject: [PATCH 019/131] usb: musb: Fix host mode error -71 regression Commit 467d5c980709 ("usb: musb: Implement session bit based runtime PM for musb-core") started implementing musb generic runtime PM support by introducing devctl register session bit based state control. This caused a regression where if a USB mass storage device is connected to a USB hub, we can get: usb 1-1: reset high-speed USB device number 2 using musb-hdrc usb 1-1: device descriptor read/64, error -71 usb 1-1.1: new high-speed USB device number 4 using musb-hdrc This is because before the USB storage device is connected, musb is in OTG_STATE_A_SUSPEND. And we currently only set need_finish_resume in musb_stage0_irq() and the related code calling finish_resume_work in musb_resume() and musb_runtime_resume() never gets called. To fix the issue, we can call schedule_delayed_work() directly in musb_stage0_irq() to have finish_resume_work run. And we should no longer never get interrupts when when suspended. We have changed musb to no longer need pm_runtime_irqsafe(). The need_finish_resume flag was added in commit 9298b4aad37e ("usb: musb: fix device hotplug behind hub") and no longer applies as far as I can tell. So let's just remove the earlier code that no longer is needed. Fixes: 467d5c980709 ("usb: musb: Implement session bit based runtime PM for musb-core") Reported-by: Bin Liu Signed-off-by: Tony Lindgren Signed-off-by: Bin Liu Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_core.c | 15 ++------------- drivers/usb/musb/musb_core.h | 1 - 2 files changed, 2 insertions(+), 14 deletions(-) diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index fca288bbc800..cd40467be3c5 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -594,11 +594,11 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, | MUSB_PORT_STAT_RESUME; musb->rh_timer = jiffies + msecs_to_jiffies(USB_RESUME_TIMEOUT); - musb->need_finish_resume = 1; - musb->xceiv->otg->state = OTG_STATE_A_HOST; musb->is_active = 1; musb_host_resume_root_hub(musb); + schedule_delayed_work(&musb->finish_resume_work, + msecs_to_jiffies(USB_RESUME_TIMEOUT)); break; case OTG_STATE_B_WAIT_ACON: musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL; @@ -2710,11 +2710,6 @@ static int musb_resume(struct device *dev) mask = MUSB_DEVCTL_BDEVICE | MUSB_DEVCTL_FSDEV | MUSB_DEVCTL_LSDEV; if ((devctl & mask) != (musb->context.devctl & mask)) musb->port1_status = 0; - if (musb->need_finish_resume) { - musb->need_finish_resume = 0; - schedule_delayed_work(&musb->finish_resume_work, - msecs_to_jiffies(USB_RESUME_TIMEOUT)); - } /* * The USB HUB code expects the device to be in RPM_ACTIVE once it came @@ -2766,12 +2761,6 @@ static int musb_runtime_resume(struct device *dev) musb_restore_context(musb); - if (musb->need_finish_resume) { - musb->need_finish_resume = 0; - schedule_delayed_work(&musb->finish_resume_work, - msecs_to_jiffies(USB_RESUME_TIMEOUT)); - } - spin_lock_irqsave(&musb->lock, flags); error = musb_run_resume_work(musb); if (error) diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index ade902ea1221..ce5a18c98c6d 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -410,7 +410,6 @@ struct musb { /* is_suspended means USB B_PERIPHERAL suspend */ unsigned is_suspended:1; - unsigned need_finish_resume :1; /* may_wakeup means remote wakeup is enabled */ unsigned may_wakeup:1; From 3ba7b7795b7e8889af1377904c55c7fae9e0c775 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 24 Jan 2017 09:18:58 -0600 Subject: [PATCH 020/131] usb: musb: Fix external abort on non-linefetch for musb_irq_work() While testing musb host mode cable plugging on a BeagleBone, I came across this error: Unhandled fault: external abort on non-linefetch (0x1008) at 0xd1dcfc60 ... [] (musb_default_readb [musb_hdrc]) from [] (musb_irq_work+0x1c/0x180 [musb_hdrc]) [] (musb_irq_work [musb_hdrc]) from [] (process_one_work+0x2b4/0x808) [] (process_one_work) from [] (worker_thread+0x3c/0x550) [] (worker_thread) from [] (kthread+0x104/0x148) [] (kthread) from [] (ret_from_fork+0x14/0x24) Signed-off-by: Tony Lindgren Signed-off-by: Bin Liu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index cd40467be3c5..772f15821242 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1925,6 +1925,14 @@ static void musb_pm_runtime_check_session(struct musb *musb) static void musb_irq_work(struct work_struct *data) { struct musb *musb = container_of(data, struct musb, irq_work.work); + int error; + + error = pm_runtime_get_sync(musb->controller); + if (error < 0) { + dev_err(musb->controller, "Could not enable: %i\n", error); + + return; + } musb_pm_runtime_check_session(musb); @@ -1932,6 +1940,9 @@ static void musb_irq_work(struct work_struct *data) musb->xceiv_old_state = musb->xceiv->otg->state; sysfs_notify(&musb->controller->kobj, NULL, "mode"); } + + pm_runtime_mark_last_busy(musb->controller); + pm_runtime_put_autosuspend(musb->controller); } static void musb_recover_from_babble(struct musb *musb) From d9b2997e4a0a874e452df7cdd7de5a54502bd0aa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Lalinsk=C3=BD?= Date: Fri, 20 Jan 2017 19:46:34 +0100 Subject: [PATCH 021/131] USB: Add quirk for WORLDE easykey.25 MIDI keyboard MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a quirk for WORLDE easykey.25 MIDI keyboard (idVendor=0218, idProduct=0401). The device reports that it has config string descriptor at index 3, but when the system selects the configuration and tries to get the description, it returns a -EPROTO error, the communication restarts and this keeps repeating over and over again. Not requesting the string descriptor makes the device work correctly. Relevant info from Wireshark: [...] CONFIGURATION DESCRIPTOR bLength: 9 bDescriptorType: 0x02 (CONFIGURATION) wTotalLength: 101 bNumInterfaces: 2 bConfigurationValue: 1 iConfiguration: 3 Configuration bmAttributes: 0xc0 SELF-POWERED NO REMOTE-WAKEUP 1... .... = Must be 1: Must be 1 for USB 1.1 and higher .1.. .... = Self-Powered: This device is SELF-POWERED ..0. .... = Remote Wakeup: This device does NOT support remote wakeup bMaxPower: 50 (100mA) [...] 45 0.369104 host 2.38.0 USB 64 GET DESCRIPTOR Request STRING [...] URB setup bmRequestType: 0x80 1... .... = Direction: Device-to-host .00. .... = Type: Standard (0x00) ...0 0000 = Recipient: Device (0x00) bRequest: GET DESCRIPTOR (6) Descriptor Index: 0x03 bDescriptorType: 0x03 Language Id: English (United States) (0x0409) wLength: 255 46 0.369255 2.38.0 host USB 64 GET DESCRIPTOR Response STRING[Malformed Packet] [...] Frame 46: 64 bytes on wire (512 bits), 64 bytes captured (512 bits) on interface 0 USB URB [Source: 2.38.0] [Destination: host] URB id: 0xffff88021f62d480 URB type: URB_COMPLETE ('C') URB transfer type: URB_CONTROL (0x02) Endpoint: 0x80, Direction: IN Device: 38 URB bus id: 2 Device setup request: not relevant ('-') Data: present (0) URB sec: 1484896277 URB usec: 455031 URB status: Protocol error (-EPROTO) (-71) URB length [bytes]: 0 Data length [bytes]: 0 [Request in: 45] [Time from request: 0.000151000 seconds] Unused Setup Header Interval: 0 Start frame: 0 Copy of Transfer Flags: 0x00000200 Number of ISO descriptors: 0 [Malformed Packet: USB] [Expert Info (Error/Malformed): Malformed Packet (Exception occurred)] [Malformed Packet (Exception occurred)] [Severity level: Error] [Group: Malformed] Signed-off-by: Lukáš Lalinský Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index d2e50a27140c..24f9f98968a5 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -37,6 +37,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* CBM - Flash disk */ { USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME }, + /* WORLDE easy key (easykey.25) MIDI controller */ + { USB_DEVICE(0x0218, 0x0401), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* HP 5300/5370C scanner */ { USB_DEVICE(0x03f0, 0x0701), .driver_info = USB_QUIRK_STRING_FETCH_255 }, From b17c1bba9cec1727451b906d9a0c209774624873 Mon Sep 17 00:00:00 2001 From: Rui Miguel Silva Date: Mon, 23 Jan 2017 16:32:57 +0000 Subject: [PATCH 022/131] staging: greybus: timesync: validate platform state callback When tearingdown timesync, and not in arche platform, the state platform callback is not initialized. That will trigger the following NULL dereferencing. CallTrace: ? gb_timesync_platform_unlock_bus+0x11/0x20 [greybus] gb_timesync_teardown+0x85/0xc0 [greybus] gb_timesync_svc_remove+0xab/0x190 [greybus] gb_svc_del+0x29/0x110 [greybus] gb_hd_del+0x14/0x20 [greybus] ap_disconnect+0x24/0x60 [gb_es2] usb_unbind_interface+0x7a/0x2c0 __device_release_driver+0x96/0x150 device_release_driver+0x1e/0x30 bus_remove_device+0xe7/0x130 device_del+0x116/0x230 usb_disable_device+0x97/0x1f0 usb_disconnect+0x80/0x260 hub_event+0x5ca/0x10e0 process_one_work+0x126/0x3b0 worker_thread+0x55/0x4c0 ? process_one_work+0x3b0/0x3b0 kthread+0xc4/0xe0 ? kthread_park+0xb0/0xb0 ret_from_fork+0x22/0x30 So, fix that by adding checks before use the callback. Fixes: 970dc85bd95d ("greybus: timesync: Add timesync core driver") Cc: # 4.9.x Signed-off-by: Rui Miguel Silva Reviewed-by: Viresh Kumar Reviewed-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/timesync_platform.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/staging/greybus/timesync_platform.c b/drivers/staging/greybus/timesync_platform.c index 113f3d6c4b3a..27f75b17679b 100644 --- a/drivers/staging/greybus/timesync_platform.c +++ b/drivers/staging/greybus/timesync_platform.c @@ -45,12 +45,18 @@ u32 gb_timesync_platform_get_clock_rate(void) int gb_timesync_platform_lock_bus(struct gb_timesync_svc *pdata) { + if (!arche_platform_change_state_cb) + return 0; + return arche_platform_change_state_cb(ARCHE_PLATFORM_STATE_TIME_SYNC, pdata); } void gb_timesync_platform_unlock_bus(void) { + if (!arche_platform_change_state_cb) + return; + arche_platform_change_state_cb(ARCHE_PLATFORM_STATE_ACTIVE, NULL); } From 83e526f2a2fa4b2e82b6bd3ddbb26b70acfa8947 Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Wed, 18 Jan 2017 00:57:44 +0000 Subject: [PATCH 023/131] usb: gadget: f_fs: Assorted buffer overflow checks. OS descriptor head, when flagged as provided, is accessed without checking if it fits in provided buffer. Verify length before access. Also, there are other places where buffer length it checked after accessing offsets which are potentially past the end. Check buffer length before as well to fail cleanly. Signed-off-by: Vincent Pelletier Acked-by: Felipe Balbi Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 5490fc51638e..fd80c1b9c823 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2269,6 +2269,8 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, if (len < sizeof(*d) || h->interface >= ffs->interfaces_count) return -EINVAL; length = le32_to_cpu(d->dwSize); + if (len < length) + return -EINVAL; type = le32_to_cpu(d->dwPropertyDataType); if (type < USB_EXT_PROP_UNICODE || type > USB_EXT_PROP_UNICODE_MULTI) { @@ -2277,6 +2279,11 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, return -EINVAL; } pnl = le16_to_cpu(d->wPropertyNameLength); + if (length < 14 + pnl) { + pr_vdebug("invalid os descriptor length: %d pnl:%d (descriptor %d)\n", + length, pnl, type); + return -EINVAL; + } pdl = le32_to_cpu(*(u32 *)((u8 *)data + 10 + pnl)); if (length != 14 + pnl + pdl) { pr_vdebug("invalid os descriptor length: %d pnl:%d pdl:%d (descriptor %d)\n", @@ -2363,6 +2370,9 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, } } if (flags & (1 << i)) { + if (len < 4) { + goto error; + } os_descs_count = get_unaligned_le32(data); data += 4; len -= 4; @@ -2435,7 +2445,8 @@ static int __ffs_data_got_strings(struct ffs_data *ffs, ENTER(); - if (unlikely(get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC || + if (unlikely(len < 16 || + get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC || get_unaligned_le32(data + 4) != len)) goto error; str_count = get_unaligned_le32(data + 8); From 1372cef1c697d8aac0cc923f8aa2c37d790ec9ed Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 25 Jan 2017 19:30:09 +0000 Subject: [PATCH 024/131] regulator: fixed: Revert support for ACPI interface This reverts commit 13bed58ce874 (regulator: fixed: add support for ACPI interface). While there does appear to be a practical need to manage regulators on ACPI systems, using ad-hoc properties to describe regulators to the kernel presents a number of problems (especially should ACPI gain first class support for such things), and there are ongoing discussions as to how to manage this. Until there is a rough consensus, revert commit 13bed58ce8748d43, which hasn't been in a released kernel yet as discussed in [1] and the surrounding thread. [1] http://lkml.kernel.org/r/20170125184949.x2wkoo7kbaaajkjk@sirena.org.uk Signed-off-by: Mark Rutland Cc: Liam Girdwood Cc: Lorenzo Pieralisi Cc: Lu Baolu Cc: Mark Brown Cc: Rafael J. Wysocki Cc: linux-kernel@vger.kernel.org Signed-off-by: Mark Brown --- drivers/regulator/fixed.c | 46 --------------------------------------- 1 file changed, 46 deletions(-) diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index a43b0e8a438d..988a7472c2ab 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -30,9 +30,6 @@ #include #include #include -#include -#include -#include struct fixed_voltage_data { struct regulator_desc desc; @@ -97,44 +94,6 @@ of_get_fixed_voltage_config(struct device *dev, return config; } -/** - * acpi_get_fixed_voltage_config - extract fixed_voltage_config structure info - * @dev: device requesting for fixed_voltage_config - * @desc: regulator description - * - * Populates fixed_voltage_config structure by extracting data through ACPI - * interface, returns a pointer to the populated structure of NULL if memory - * alloc fails. - */ -static struct fixed_voltage_config * -acpi_get_fixed_voltage_config(struct device *dev, - const struct regulator_desc *desc) -{ - struct fixed_voltage_config *config; - const char *supply_name; - struct gpio_desc *gpiod; - int ret; - - config = devm_kzalloc(dev, sizeof(*config), GFP_KERNEL); - if (!config) - return ERR_PTR(-ENOMEM); - - ret = device_property_read_string(dev, "supply-name", &supply_name); - if (!ret) - config->supply_name = supply_name; - - gpiod = gpiod_get(dev, "gpio", GPIOD_ASIS); - if (IS_ERR(gpiod)) - return ERR_PTR(-ENODEV); - - config->gpio = desc_to_gpio(gpiod); - config->enable_high = device_property_read_bool(dev, - "enable-active-high"); - gpiod_put(gpiod); - - return config; -} - static struct regulator_ops fixed_voltage_ops = { }; @@ -155,11 +114,6 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) &drvdata->desc); if (IS_ERR(config)) return PTR_ERR(config); - } else if (ACPI_HANDLE(&pdev->dev)) { - config = acpi_get_fixed_voltage_config(&pdev->dev, - &drvdata->desc); - if (IS_ERR(config)) - return PTR_ERR(config); } else { config = dev_get_platdata(&pdev->dev); } From 191e885a2e130e639bb0c8ee350d7047294f2ce6 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 25 Jan 2017 10:31:52 -0800 Subject: [PATCH 025/131] firmware: fix NULL pointer dereference in __fw_load_abort() Since commit 5d47ec02c37ea6 ("firmware: Correct handling of fw_state_wait() return value") fw_load_abort() could be called twice and lead us to a kernel crash. This happens only when the firmware fallback mechanism (regular or custom) is used. The fallback mechanism exposes a sysfs interface for userspace to upload a file and notify the kernel when the file is loaded and ready, or to cancel an upload by echo'ing -1 into on the loading file: echo -n "-1" > /sys/$DEVPATH/loading This will call fw_load_abort(). Some distributions actually have a udev rule in place to *always* immediately cancel all firmware fallback mechanism requests (Debian), they have: $ cat /lib/udev/rules.d/50-firmware.rules # stub for immediately telling the kernel that userspace firmware loading # failed; necessary to avoid long timeouts with CONFIG_FW_LOADER_USER_HELPER=y SUBSYSTEM=="firmware", ACTION=="add", ATTR{loading}="-1 Distributions with this udev rule would run into this crash only if the fallback mechanism is used. Since most distributions disable by default using the fallback mechanism (CONFIG_FW_LOADER_USER_HELPER_FALLBACK), this would typicaly mean only 2 drivers which *require* the fallback mechanism could typically incur a crash: drivers/firmware/dell_rbu.c and the drivers/leds/leds-lp55xx-common.c driver. Distributions enabling CONFIG_FW_LOADER_USER_HELPER_FALLBACK by default are obviously more exposed to this crash. The crash happens because after commit 5b029624948d ("firmware: do not use fw_lock for fw_state protection") and subsequent fix commit 5d47ec02c37ea6 ("firmware: Correct handling of fw_state_wait() return value") a race can happen between this cancelation and the firmware fw_state_wait_timeout() being woken up after a state change with which fw_load_abort() as that calls swake_up(). Upon error fw_state_wait_timeout() will also again call fw_load_abort() and trigger a null reference. At first glance we could just fix this with a !buf check on fw_load_abort() before accessing buf->fw_st, however there is a logical issue in having a state machine used for the fallback mechanism and preventing access from it once we abort as its inside the buf (buf->fw_st). The firmware_class.c code is setting the buf to NULL to annotate an abort has occurred. Replace this mechanism by simply using the state check instead. All the other code in place already uses similar checks for aborting as well so no further changes are needed. An oops can be reproduced with the new fw_fallback.sh fallback mechanism cancellation test. Either cancelling the fallback mechanism or the custom fallback mechanism triggers a crash. mcgrof@piggy ~/linux-next/tools/testing/selftests/firmware (git::20170111-fw-fixes)$ sudo ./fw_fallback.sh ./fw_fallback.sh: timeout works ./fw_fallback.sh: firmware comparison works ./fw_fallback.sh: fallback mechanism works [ this then sits here when it is trying the cancellation test ] Kernel log: test_firmware: loading 'nope-test-firmware.bin' misc test_firmware: Direct firmware load for nope-test-firmware.bin failed with error -2 misc test_firmware: Falling back to user helper BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: _request_firmware+0xa27/0xad0 PGD 0 Oops: 0000 [#1] SMP Modules linked in: test_firmware(E) ... etc ... CPU: 1 PID: 1396 Comm: fw_fallback.sh Tainted: G W E 4.10.0-rc3-next-20170111+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 task: ffff9740b27f4340 task.stack: ffffbb15c0bc8000 RIP: 0010:_request_firmware+0xa27/0xad0 RSP: 0018:ffffbb15c0bcbd10 EFLAGS: 00010246 RAX: 00000000fffffffe RBX: ffff9740afe5aa80 RCX: 0000000000000000 RDX: ffff9740b27f4340 RSI: 0000000000000283 RDI: 0000000000000000 RBP: ffffbb15c0bcbd90 R08: ffffbb15c0bcbcd8 R09: 0000000000000000 R10: 0000000894a0d4b1 R11: 000000000000008c R12: ffffffffc0312480 R13: 0000000000000005 R14: ffff9740b1c32400 R15: 00000000000003e8 FS: 00007f8604422700(0000) GS:ffff9740bfc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 000000012164c000 CR4: 00000000000006e0 Call Trace: request_firmware+0x37/0x50 trigger_request_store+0x79/0xd0 [test_firmware] dev_attr_store+0x18/0x30 sysfs_kf_write+0x37/0x40 kernfs_fop_write+0x110/0x1a0 __vfs_write+0x37/0x160 ? _cond_resched+0x1a/0x50 vfs_write+0xb5/0x1a0 SyS_write+0x55/0xc0 ? trace_do_page_fault+0x37/0xd0 entry_SYSCALL_64_fastpath+0x1e/0xad RIP: 0033:0x7f8603f49620 RSP: 002b:00007fff6287b788 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000055c307b110a0 RCX: 00007f8603f49620 RDX: 0000000000000016 RSI: 000055c3084d8a90 RDI: 0000000000000001 RBP: 0000000000000016 R08: 000000000000c0ff R09: 000055c3084d6336 R10: 000055c307b108b0 R11: 0000000000000246 R12: 000055c307b13c80 R13: 000055c3084d6320 R14: 0000000000000000 R15: 00007fff6287b950 Code: 9f 64 84 e8 9c 61 fe ff b8 f4 ff ff ff e9 6b f9 ff ff 48 c7 c7 40 6b 8d 84 89 45 a8 e8 43 84 18 00 49 8b be 00 03 00 00 8b 45 a8 <83> 7f 38 02 74 08 e8 6e ec ff ff 8b 45 a8 49 c7 86 00 03 00 00 RIP: _request_firmware+0xa27/0xad0 RSP: ffffbb15c0bcbd10 CR2: 0000000000000038 ---[ end trace 6d94ac339c133e6f ]--- Fixes: 5d47ec02c37e ("firmware: Correct handling of fw_state_wait() return value") Reported-and-Tested-by: Jakub Kicinski Reported-and-Tested-by: Patrick Bruenn Reported-by: Chris Wilson CC: [3.10+] Signed-off-by: Luis R. Rodriguez Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_class.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 4497d263209f..ac350c518e0c 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -558,9 +558,6 @@ static void fw_load_abort(struct firmware_priv *fw_priv) struct firmware_buf *buf = fw_priv->buf; __fw_load_abort(buf); - - /* avoid user action after loading abort */ - fw_priv->buf = NULL; } static LIST_HEAD(pending_fw_head); @@ -713,7 +710,7 @@ static ssize_t firmware_loading_store(struct device *dev, mutex_lock(&fw_lock); fw_buf = fw_priv->buf; - if (!fw_buf) + if (fw_state_is_aborted(&fw_buf->fw_st)) goto out; switch (loading) { From 9b02c54bc951fca884ba5719f42a27e8240965bf Mon Sep 17 00:00:00 2001 From: Markus Mayer Date: Mon, 19 Dec 2016 12:10:27 -0800 Subject: [PATCH 026/131] cpufreq: brcmstb-avs-cpufreq: extend sysfs entry brcm_avs_pmap We extend the brcm_avs_pmap sysfs entry (which issues the GET_PMAP command to AVS) to include all fields from struct pmap. This means adding mode (AVS, DVS, DVFS) and state (the P-state) to the output. Signed-off-by: Markus Mayer Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/brcmstb-avs-cpufreq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 4fda623e55bb..2c6e3253ba64 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -954,9 +954,9 @@ static ssize_t show_brcm_avs_pmap(struct cpufreq_policy *policy, char *buf) brcm_avs_parse_p1(pmap.p1, &mdiv_p0, &pdiv, &ndiv); brcm_avs_parse_p2(pmap.p2, &mdiv_p1, &mdiv_p2, &mdiv_p3, &mdiv_p4); - return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u\n", + return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u %u %u\n", pmap.p1, pmap.p2, ndiv, pdiv, mdiv_p0, mdiv_p1, mdiv_p2, - mdiv_p3, mdiv_p4); + mdiv_p3, mdiv_p4, pmap.mode, pmap.state); } static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf) From 3c223c19aea85d3dda1416c187915f4a30b04b1f Mon Sep 17 00:00:00 2001 From: Markus Mayer Date: Mon, 19 Dec 2016 12:10:28 -0800 Subject: [PATCH 027/131] cpufreq: brcmstb-avs-cpufreq: properly retrieve P-state upon suspend The AVS GET_PMAP command does return a P-state along with the P-map information. However, that P-state is the initial P-state when the P-map was first downloaded to AVS. It is *not* the current P-state. Therefore, we explicitly retrieve the P-state using the GET_PSTATE command. Signed-off-by: Markus Mayer Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/brcmstb-avs-cpufreq.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 2c6e3253ba64..c94360671f41 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -784,8 +784,19 @@ static int brcm_avs_target_index(struct cpufreq_policy *policy, static int brcm_avs_suspend(struct cpufreq_policy *policy) { struct private_data *priv = policy->driver_data; + int ret; - return brcm_avs_get_pmap(priv, &priv->pmap); + ret = brcm_avs_get_pmap(priv, &priv->pmap); + if (ret) + return ret; + + /* + * We can't use the P-state returned by brcm_avs_get_pmap(), since + * that's the initial P-state from when the P-map was downloaded to the + * AVS co-processor, not necessarily the P-state we are running at now. + * So, we get the current P-state explicitly. + */ + return brcm_avs_get_pstate(priv, &priv->pmap.state); } static int brcm_avs_resume(struct cpufreq_policy *policy) From 030305d69fc6963c16003f50d7e8d74b02d0a143 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 27 Jan 2017 15:00:45 -0600 Subject: [PATCH 028/131] PCI/ASPM: Handle PCI-to-PCIe bridges as roots of PCIe hierarchies In a struct pcie_link_state, link->root points to the pcie_link_state of the root of the PCIe hierarchy. For the topmost link, this points to itself (link->root = link). For others, we copy the pointer from the parent (link->root = link->parent->root). Previously we recognized that Root Ports originated PCIe hierarchies, but we treated PCI/PCI-X to PCIe Bridges as being in the middle of the hierarchy, and when we tried to copy the pointer from link->parent->root, there was no parent, and we dereferenced a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000090 IP: [] pcie_aspm_init_link_state+0x170/0x820 Recognize that PCI/PCI-X to PCIe Bridges originate PCIe hierarchies just like Root Ports do, so link->root for these devices should also point to itself. Fixes: 51ebfc92b72b ("PCI: Enumerate switches below PCI-to-PCIe bridges") Link: https://bugzilla.kernel.org/show_bug.cgi?id=193411 Link: https://bugzilla.opensuse.org/show_bug.cgi?id=1022181 Tested-by: lists@ssl-mail.com Tested-by: Jayachandran C. Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v4.2+ --- drivers/pci/pcie/aspm.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 17ac1dce3286..3dd8bcbb3011 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -532,25 +532,32 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) return NULL; + INIT_LIST_HEAD(&link->sibling); INIT_LIST_HEAD(&link->children); INIT_LIST_HEAD(&link->link); link->pdev = pdev; - if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) { + + /* + * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe + * hierarchies. + */ + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT || + pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE) { + link->root = link; + } else { struct pcie_link_state *parent; + parent = pdev->bus->parent->self->link_state; if (!parent) { kfree(link); return NULL; } + link->parent = parent; + link->root = link->parent->root; list_add(&link->link, &parent->children); } - /* Setup a pointer to the root port link */ - if (!link->parent) - link->root = link; - else - link->root = link->parent->root; list_add(&link->sibling, &link_list); pdev->link_state = link; From bf29bddf0417a4783da3b24e8c9e017ac649326f Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 27 Jan 2017 22:25:52 +0000 Subject: [PATCH 029/131] x86/efi: Always map the first physical page into the EFI pagetables Commit: 129766708 ("x86/efi: Only map RAM into EFI page tables if in mixed-mode") stopped creating 1:1 mappings for all RAM, when running in native 64-bit mode. It turns out though that there are 64-bit EFI implementations in the wild (this particular problem has been reported on a Lenovo Yoga 710-11IKB), which still make use of the first physical page for their own private use, even though they explicitly mark it EFI_CONVENTIONAL_MEMORY in the memory map. In case there is no mapping for this particular frame in the EFI pagetables, as soon as firmware tries to make use of it, a triple fault occurs and the system reboots (in case of the Yoga 710-11IKB this is very early during bootup). Fix that by always mapping the first page of physical memory into the EFI pagetables. We're free to hand this page to the BIOS, as trim_bios_range() will reserve the first page and isolate it away from memory allocators anyway. Note that just reverting 129766708 alone is not enough on v4.9-rc1+ to fix the regression on affected hardware, as this commit: ab72a27da ("x86/efi: Consolidate region mapping logic") later made the first physical frame not to be mapped anyway. Reported-by: Hanka Pavlikova Signed-off-by: Jiri Kosina Signed-off-by: Matt Fleming Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: Borislav Petkov Cc: Laura Abbott Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vojtech Pavlik Cc: Waiman Long Cc: linux-efi@vger.kernel.org Cc: stable@kernel.org # v4.8+ Fixes: 129766708 ("x86/efi: Only map RAM into EFI page tables if in mixed-mode") Link: http://lkml.kernel.org/r/20170127222552.22336-1-matt@codeblueprint.co.uk [ Tidied up the changelog and the comment. ] Signed-off-by: Ingo Molnar --- arch/x86/platform/efi/efi_64.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 319148bd4b05..2f25a363068c 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -268,6 +268,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.use_pgd = true; + /* + * Certain firmware versions are way too sentimential and still believe + * they are exclusive and unquestionable owners of the first physical page, + * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY + * (but then write-access it later during SetVirtualAddressMap()). + * + * Create a 1:1 mapping for this page, to avoid triple faults during early + * boot with such firmware. We are free to hand this page to the BIOS, + * as trim_bios_range() will reserve the first page and isolate it away + * from memory allocators anyway. + */ + if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) { + pr_err("Failed to create 1:1 mapping for the first page!\n"); + return 1; + } + /* * When making calls to the firmware everything needs to be 1:1 * mapped and addressable with 32-bit pointers. Map the kernel From a0615a16f7d0ceb5804d295203c302d496d8ee91 Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Wed, 25 Jan 2017 09:54:33 -0600 Subject: [PATCH 030/131] powerpc/mm: Use the correct pointer when setting a 2MB pte When setting a 2MB pte, radix__map_kernel_page() is using the address ptep = (pte_t *)pudp; Fix this conversion to use pmdp instead. Use pmdp_ptep() to do this instead of casting the pointer. Fixes: 2bfd65e45e87 ("powerpc/mm/radix: Add radix callbacks for early init routines") Cc: stable@vger.kernel.org # v4.7+ Reviewed-by: Aneesh Kumar K.V Signed-off-by: Reza Arbab Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..34f1a0dbc898 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -65,7 +65,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, if (!pmdp) return -ENOMEM; if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } ptep = pte_alloc_kernel(pmdp, ea); @@ -90,7 +90,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, } pmdp = pmd_offset(pudp, ea); if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } if (!pmd_present(*pmdp)) { From 24c2503255d35c269b67162c397a1a1c1e02f6ce Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 Jan 2017 21:00:48 +0100 Subject: [PATCH 031/131] x86/microcode: Do not access the initrd after it has been freed When we look for microcode blobs, we first try builtin and if that doesn't succeed, we fallback to the initrd supplied to the kernel. However, at some point doing boot, that initrd gets jettisoned and we shouldn't access it anymore. But we do, as the below KASAN report shows. That's because find_microcode_in_initrd() doesn't check whether the initrd is still valid or not. So do that. ================================================================== BUG: KASAN: use-after-free in find_cpio_data Read of size 1 by task swapper/1/0 page:ffffea0000db9d40 count:0 mapcount:0 mapping: (null) index:0x1 flags: 0x100000000000000() raw: 0100000000000000 0000000000000000 0000000000000001 00000000ffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: kasan: bad access detected CPU: 1 PID: 0 Comm: swapper/1 Tainted: G W 4.10.0-rc5-debug-00075-g2dbde22 #3 Hardware name: Dell Inc. XPS 13 9360/0839Y6, BIOS 1.2.3 12/01/2016 Call Trace: dump_stack ? _atomic_dec_and_lock ? __dump_page kasan_report_error ? pointer ? find_cpio_data __asan_report_load1_noabort ? find_cpio_data find_cpio_data ? vsprintf ? dump_stack ? get_ucode_user ? print_usage_bug find_microcode_in_initrd __load_ucode_intel ? collect_cpu_info_early ? debug_check_no_locks_freed load_ucode_intel_ap ? collect_cpu_info ? trace_hardirqs_on ? flat_send_IPI_mask_allbutself load_ucode_ap ? get_builtin_firmware ? flush_tlb_func ? do_raw_spin_trylock ? cpumask_weight cpu_init ? trace_hardirqs_off ? play_dead_common ? native_play_dead ? hlt_play_dead ? syscall_init ? arch_cpu_idle_dead ? do_idle start_secondary start_cpu Memory state around the buggy address: ffff880036e74f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff880036e74f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff880036e75000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff880036e75080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff880036e75100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== Reported-by: Andrey Ryabinin Tested-by: Andrey Ryabinin Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170126165833.evjemhbqzaepirxo@pd.tnic Signed-off-by: Ingo Molnar --- arch/x86/include/asm/microcode.h | 1 + arch/x86/kernel/cpu/microcode/amd.c | 5 +++-- arch/x86/kernel/cpu/microcode/core.c | 22 +++++++++++++++++----- 3 files changed, 21 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 38711df3bcb5..2266f864b747 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -140,6 +140,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); +extern bool initrd_gone; #else static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..079e81733a58 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -384,8 +384,9 @@ void load_ucode_amd_ap(unsigned int family) reget: if (!get_builtin_microcode(&cp, family)) { #ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); + if (!initrd_gone) + cp = find_cpio_data(ucode_path, (void *)initrd_start, + initrd_end - initrd_start, NULL); #endif if (!(cp.data && cp.size)) { /* diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..73102d932760 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -190,21 +192,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + ret = save_microcode_in_initrd_amd(c->x86); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +252,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ From 4e5b54f127426c82dc2816340c26d951a5bb3429 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Sun, 18 Dec 2016 14:35:45 +0100 Subject: [PATCH 032/131] drm: prevent double-(un)registration for connectors If we're unlucky then the registration from a hotplugged connector might race with the final registration step on driver load. And since MST topology discover is asynchronous that's even somewhat likely. v2: Also update the kerneldoc for @registered! v3: Review from Chris: - Improve kerneldoc for late_register/early_unregister callbacks. - Use mutex_destroy. Reviewed-by: Chris Wilson Cc: Chris Wilson Reviewed-by: Sean Paul Reported-by: Chris Wilson Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20161218133545.2106-1-daniel.vetter@ffwll.ch (cherry picked from commit e73ab00e9a0f1731f34d0620a9c55f5c30c4ad4e) --- drivers/gpu/drm/drm_connector.c | 20 +++++++++++++++----- include/drm/drm_connector.h | 16 +++++++++++++++- 2 files changed, 30 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 5a4526289392..8be60a4576b3 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -225,6 +225,7 @@ int drm_connector_init(struct drm_device *dev, INIT_LIST_HEAD(&connector->probed_modes); INIT_LIST_HEAD(&connector->modes); + mutex_init(&connector->mutex); connector->edid_blob_ptr = NULL; connector->status = connector_status_unknown; @@ -359,6 +360,8 @@ void drm_connector_cleanup(struct drm_connector *connector) connector->funcs->atomic_destroy_state(connector, connector->state); + mutex_destroy(&connector->mutex); + memset(connector, 0, sizeof(*connector)); } EXPORT_SYMBOL(drm_connector_cleanup); @@ -374,14 +377,15 @@ EXPORT_SYMBOL(drm_connector_cleanup); */ int drm_connector_register(struct drm_connector *connector) { - int ret; + int ret = 0; + mutex_lock(&connector->mutex); if (connector->registered) - return 0; + goto unlock; ret = drm_sysfs_connector_add(connector); if (ret) - return ret; + goto unlock; ret = drm_debugfs_connector_add(connector); if (ret) { @@ -397,12 +401,14 @@ int drm_connector_register(struct drm_connector *connector) drm_mode_object_register(connector->dev, &connector->base); connector->registered = true; - return 0; + goto unlock; err_debugfs: drm_debugfs_connector_remove(connector); err_sysfs: drm_sysfs_connector_remove(connector); +unlock: + mutex_unlock(&connector->mutex); return ret; } EXPORT_SYMBOL(drm_connector_register); @@ -415,8 +421,11 @@ EXPORT_SYMBOL(drm_connector_register); */ void drm_connector_unregister(struct drm_connector *connector) { - if (!connector->registered) + mutex_lock(&connector->mutex); + if (!connector->registered) { + mutex_unlock(&connector->mutex); return; + } if (connector->funcs->early_unregister) connector->funcs->early_unregister(connector); @@ -425,6 +434,7 @@ void drm_connector_unregister(struct drm_connector *connector) drm_debugfs_connector_remove(connector); connector->registered = false; + mutex_unlock(&connector->mutex); } EXPORT_SYMBOL(drm_connector_unregister); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index a9b95246e26e..045a97cbeba2 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -381,6 +381,8 @@ struct drm_connector_funcs { * core drm connector interfaces. Everything added from this callback * should be unregistered in the early_unregister callback. * + * This is called while holding drm_connector->mutex. + * * Returns: * * 0 on success, or a negative error code on failure. @@ -395,6 +397,8 @@ struct drm_connector_funcs { * late_register(). It is called from drm_connector_unregister(), * early in the driver unload sequence to disable userspace access * before data structures are torndown. + * + * This is called while holding drm_connector->mutex. */ void (*early_unregister)(struct drm_connector *connector); @@ -559,7 +563,6 @@ struct drm_cmdline_mode { * @interlace_allowed: can this connector handle interlaced modes? * @doublescan_allowed: can this connector handle doublescan? * @stereo_allowed: can this connector handle stereo modes? - * @registered: is this connector exposed (registered) with userspace? * @modes: modes available on this connector (from fill_modes() + user) * @status: one of the drm_connector_status enums (connected, not, or unknown) * @probed_modes: list of modes derived directly from the display @@ -607,6 +610,13 @@ struct drm_connector { char *name; + /** + * @mutex: Lock for general connector state, but currently only protects + * @registered. Most of the connector state is still protected by the + * mutex in &drm_mode_config. + */ + struct mutex mutex; + /** * @index: Compacted connector index, which matches the position inside * the mode_config.list for drivers not supporting hot-add/removing. Can @@ -620,6 +630,10 @@ struct drm_connector { bool interlace_allowed; bool doublescan_allowed; bool stereo_allowed; + /** + * @registered: Is this connector exposed (registered) with userspace? + * Protected by @mutex. + */ bool registered; struct list_head modes; /* list of modes on this connector */ From e6e7b48b295afa5a5ab440de0a94d9ad8b3ce2d0 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 12 Jan 2017 17:15:56 +0100 Subject: [PATCH 033/131] drm: Don't race connector registration I was under the misconception that the sysfs dev stuff can be fully set up, and then registered all in one step with device_add. That's true for properties and property groups, but not for parents and child devices. Those must be fully registered before you can register a child. Add a bit of tracking to make sure that asynchronous mst connector hotplugging gets this right. For consistency we rely upon the implicit barriers of the connector->mutex, which is taken anyway, to ensure that at least either the connector or device registration call will work out. Mildly tested since I can't reliably reproduce this on my mst box here. Reported-by: Dave Hansen Cc: Dave Hansen Acked-by: Chris Wilson Cc: Chris Wilson Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1484237756-2720-1-git-send-email-daniel.vetter@ffwll.ch --- drivers/gpu/drm/drm_connector.c | 3 +++ drivers/gpu/drm/drm_drv.c | 4 ++++ include/drm/drmP.h | 1 + 3 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 8be60a4576b3..7a7019ac9388 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -379,6 +379,9 @@ int drm_connector_register(struct drm_connector *connector) { int ret = 0; + if (!connector->dev->registered) + return 0; + mutex_lock(&connector->mutex); if (connector->registered) goto unlock; diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index a525751b4559..6594b4088f11 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -745,6 +745,8 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) if (ret) goto err_minors; + dev->registered = true; + if (dev->driver->load) { ret = dev->driver->load(dev, flags); if (ret) @@ -785,6 +787,8 @@ void drm_dev_unregister(struct drm_device *dev) drm_lastclose(dev); + dev->registered = false; + if (drm_core_check_feature(dev, DRIVER_MODESET)) drm_modeset_unregister_all(dev); diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 192016e2b518..9c4ee144b5f6 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -517,6 +517,7 @@ struct drm_device { struct drm_minor *control; /**< Control node */ struct drm_minor *primary; /**< Primary node */ struct drm_minor *render; /**< Render node */ + bool registered; /* currently active master for this device. Protected by master_mutex */ struct drm_master *master; From a76a82a3e38c8d3fb6499e3dfaeb0949241ab588 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 Jan 2017 16:39:55 +0100 Subject: [PATCH 034/131] perf/core: Fix use-after-free bug Dmitry reported a KASAN use-after-free on event->group_leader. It turns out there's a hole in perf_remove_from_context() due to event_function_call() not calling its function when the task associated with the event is already dead. In this case the event will have been detached from the task, but the grouping will have been retained, such that group operations might still work properly while there are live child events etc. This does however mean that we can miss a perf_group_detach() call when the group decomposes, this in turn can then lead to use-after-free. Fix it by explicitly doing the group detach if its still required. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org # v4.5+ Cc: syzkaller Fixes: 63b6da39bb38 ("perf: Fix perf_event_exit_task() race") Link: http://lkml.kernel.org/r/20170126153955.GD6515@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/events/core.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 110b38a58493..4e1f4c0070ce 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1469,7 +1469,6 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { - lockdep_assert_held(&ctx->lock); WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); @@ -1624,6 +1623,8 @@ static void perf_group_attach(struct perf_event *event) { struct perf_event *group_leader = event->group_leader, *pos; + lockdep_assert_held(&event->ctx->lock); + /* * We can have double attach due to group movement in perf_event_open. */ @@ -1697,6 +1698,8 @@ static void perf_group_detach(struct perf_event *event) struct perf_event *sibling, *tmp; struct list_head *list = NULL; + lockdep_assert_held(&event->ctx->lock); + /* * We can have double detach due to exit/hot-unplug + close. */ @@ -1895,9 +1898,29 @@ __perf_remove_from_context(struct perf_event *event, */ static void perf_remove_from_context(struct perf_event *event, unsigned long flags) { - lockdep_assert_held(&event->ctx->mutex); + struct perf_event_context *ctx = event->ctx; + + lockdep_assert_held(&ctx->mutex); event_function_call(event, __perf_remove_from_context, (void *)flags); + + /* + * The above event_function_call() can NO-OP when it hits + * TASK_TOMBSTONE. In that case we must already have been detached + * from the context (by perf_event_exit_event()) but the grouping + * might still be in-tact. + */ + WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); + if ((flags & DETACH_GROUP) && + (event->attach_state & PERF_ATTACH_GROUP)) { + /* + * Since in that case we cannot possibly be scheduled, simply + * detach now. + */ + raw_spin_lock_irq(&ctx->lock); + perf_group_detach(event); + raw_spin_unlock_irq(&ctx->lock); + } } /* From 0b3589be9b98994ce3d5aeca52445d1f5627c4ba Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 Jan 2017 23:15:08 +0100 Subject: [PATCH 035/131] perf/core: Fix PERF_RECORD_MMAP2 prot/flags for anonymous memory Andres reported that MMAP2 records for anonymous memory always have their protection field 0. Turns out, someone daft put the prot/flags generation code in the file branch, leaving them unset for anonymous memory. Reported-by: Andres Freund Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Don Zickus Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Stephane Eranian Cc: Thomas Gleixner Cc: acme@kernel.org Cc: anton@ozlabs.org Cc: namhyung@kernel.org Cc: stable@vger.kernel.org # v3.16+ Fixes: f972eb63b100 ("perf: Pass protection and flags bits through mmap2 interface") Link: http://lkml.kernel.org/r/20170126221508.GF6536@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/events/core.c | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 4e1f4c0070ce..e5aaa806702d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6632,6 +6632,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) char *buf = NULL; char *name; + if (vma->vm_flags & VM_READ) + prot |= PROT_READ; + if (vma->vm_flags & VM_WRITE) + prot |= PROT_WRITE; + if (vma->vm_flags & VM_EXEC) + prot |= PROT_EXEC; + + if (vma->vm_flags & VM_MAYSHARE) + flags = MAP_SHARED; + else + flags = MAP_PRIVATE; + + if (vma->vm_flags & VM_DENYWRITE) + flags |= MAP_DENYWRITE; + if (vma->vm_flags & VM_MAYEXEC) + flags |= MAP_EXECUTABLE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + if (vma->vm_flags & VM_HUGETLB) + flags |= MAP_HUGETLB; + if (file) { struct inode *inode; dev_t dev; @@ -6658,27 +6679,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) maj = MAJOR(dev); min = MINOR(dev); - if (vma->vm_flags & VM_READ) - prot |= PROT_READ; - if (vma->vm_flags & VM_WRITE) - prot |= PROT_WRITE; - if (vma->vm_flags & VM_EXEC) - prot |= PROT_EXEC; - - if (vma->vm_flags & VM_MAYSHARE) - flags = MAP_SHARED; - else - flags = MAP_PRIVATE; - - if (vma->vm_flags & VM_DENYWRITE) - flags |= MAP_DENYWRITE; - if (vma->vm_flags & VM_MAYEXEC) - flags |= MAP_EXECUTABLE; - if (vma->vm_flags & VM_LOCKED) - flags |= MAP_LOCKED; - if (vma->vm_flags & VM_HUGETLB) - flags |= MAP_HUGETLB; - goto got_name; } else { if (vma->vm_ops && vma->vm_ops->name) { From ed72b81bb7a49e8bfaa8dd6ab0b0e103ff0771ae Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 2 Jan 2017 09:41:40 -0200 Subject: [PATCH 036/131] [media] cec rst: remove "This API is not yet finalized" notice The API is now finalized, so this notice should be dropped. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/cec/cec-func-close.rst | 5 ----- Documentation/media/uapi/cec/cec-func-ioctl.rst | 5 ----- Documentation/media/uapi/cec/cec-func-open.rst | 5 ----- Documentation/media/uapi/cec/cec-func-poll.rst | 5 ----- Documentation/media/uapi/cec/cec-intro.rst | 5 ----- Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst | 5 ----- Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst | 5 ----- Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst | 5 ----- Documentation/media/uapi/cec/cec-ioc-dqevent.rst | 5 ----- Documentation/media/uapi/cec/cec-ioc-g-mode.rst | 5 ----- Documentation/media/uapi/cec/cec-ioc-receive.rst | 5 ----- 11 files changed, 55 deletions(-) diff --git a/Documentation/media/uapi/cec/cec-func-close.rst b/Documentation/media/uapi/cec/cec-func-close.rst index 8267c31b317d..895d9c2d1c04 100644 --- a/Documentation/media/uapi/cec/cec-func-close.rst +++ b/Documentation/media/uapi/cec/cec-func-close.rst @@ -33,11 +33,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - Closes the cec device. Resources associated with the file descriptor are freed. The device configuration remain unchanged. diff --git a/Documentation/media/uapi/cec/cec-func-ioctl.rst b/Documentation/media/uapi/cec/cec-func-ioctl.rst index 9e8dbb118d6a..7dcfd178fb24 100644 --- a/Documentation/media/uapi/cec/cec-func-ioctl.rst +++ b/Documentation/media/uapi/cec/cec-func-ioctl.rst @@ -39,11 +39,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - The :c:func:`ioctl()` function manipulates cec device parameters. The argument ``fd`` must be an open file descriptor. diff --git a/Documentation/media/uapi/cec/cec-func-open.rst b/Documentation/media/uapi/cec/cec-func-open.rst index af3f5b5c24c6..0304388cd159 100644 --- a/Documentation/media/uapi/cec/cec-func-open.rst +++ b/Documentation/media/uapi/cec/cec-func-open.rst @@ -46,11 +46,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To open a cec device applications call :c:func:`open()` with the desired device name. The function has no side effects; the device configuration remain unchanged. diff --git a/Documentation/media/uapi/cec/cec-func-poll.rst b/Documentation/media/uapi/cec/cec-func-poll.rst index cfb73e6027a5..6a863cfda6e0 100644 --- a/Documentation/media/uapi/cec/cec-func-poll.rst +++ b/Documentation/media/uapi/cec/cec-func-poll.rst @@ -39,11 +39,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - With the :c:func:`poll()` function applications can wait for CEC events. diff --git a/Documentation/media/uapi/cec/cec-intro.rst b/Documentation/media/uapi/cec/cec-intro.rst index 4a19ea5323a9..7d31d37b0642 100644 --- a/Documentation/media/uapi/cec/cec-intro.rst +++ b/Documentation/media/uapi/cec/cec-intro.rst @@ -3,11 +3,6 @@ Introduction ============ -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - HDMI connectors provide a single pin for use by the Consumer Electronics Control protocol. This protocol allows different devices connected by an HDMI cable to communicate. The protocol for CEC version 1.4 is defined diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst index 2b0ddb14b280..a0e961f11017 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst @@ -29,11 +29,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - All cec devices must support :ref:`ioctl CEC_ADAP_G_CAPS `. To query device information, applications call the ioctl with a pointer to a struct :c:type:`cec_caps`. The driver fills the structure and diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst index b878637e91b3..09f09bbe28d4 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst @@ -35,11 +35,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To query the current CEC logical addresses, applications call :ref:`ioctl CEC_ADAP_G_LOG_ADDRS ` with a pointer to a struct :c:type:`cec_log_addrs` where the driver stores the logical addresses. diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst index 3357deb43c85..a3cdc75cec3e 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst @@ -35,11 +35,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To query the current physical address applications call :ref:`ioctl CEC_ADAP_G_PHYS_ADDR ` with a pointer to a __u16 where the driver stores the physical address. diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst index e256c6605de7..6e589a1fae17 100644 --- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst +++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst @@ -30,11 +30,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - CEC devices can send asynchronous events. These can be retrieved by calling :c:func:`CEC_DQEVENT`. If the file descriptor is in non-blocking mode and no event is pending, then it will return -1 and diff --git a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst index 4f5818b9d277..e4ded9df0a84 100644 --- a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst +++ b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst @@ -31,11 +31,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - By default any filehandle can use :ref:`CEC_TRANSMIT`, but in order to prevent applications from stepping on each others toes it must be possible to obtain exclusive access to the CEC adapter. This ioctl sets the diff --git a/Documentation/media/uapi/cec/cec-ioc-receive.rst b/Documentation/media/uapi/cec/cec-ioc-receive.rst index bdf015b1d1dc..dc2adb391c0a 100644 --- a/Documentation/media/uapi/cec/cec-ioc-receive.rst +++ b/Documentation/media/uapi/cec/cec-ioc-receive.rst @@ -34,11 +34,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To receive a CEC message the application has to fill in the ``timeout`` field of struct :c:type:`cec_msg` and pass it to :ref:`ioctl CEC_RECEIVE `. From 8015d6b83cadc8f9f94c7bc8430255090ddf43d4 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 2 Jan 2017 09:54:24 -0200 Subject: [PATCH 037/131] [media] cec-intro.rst: mention the v4l-utils package and CEC utilities Mention where to find the CEC utilities. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/cec/cec-intro.rst | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/Documentation/media/uapi/cec/cec-intro.rst b/Documentation/media/uapi/cec/cec-intro.rst index 7d31d37b0642..07ee2b8f89d6 100644 --- a/Documentation/media/uapi/cec/cec-intro.rst +++ b/Documentation/media/uapi/cec/cec-intro.rst @@ -26,3 +26,15 @@ control just the CEC pin. Drivers that support CEC will create a CEC device node (/dev/cecX) to give userspace access to the CEC adapter. The :ref:`CEC_ADAP_G_CAPS` ioctl will tell userspace what it is allowed to do. + +In order to check the support and test it, it is suggested to download +the `v4l-utils `_ package. It +provides three tools to handle CEC: + +- cec-ctl: the Swiss army knife of CEC. Allows you to configure, transmit + and monitor CEC messages. + +- cec-compliance: does a CEC compliance test of a remote CEC device to + determine how compliant the CEC implementation is. + +- cec-follower: emulates a CEC follower. From f9f96fc10c09ca16e336854c08bc1563eed97985 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 10 Jan 2017 09:44:54 -0200 Subject: [PATCH 038/131] [media] cec: fix wrong last_la determination Due to an incorrect condition the last_la used for the initial attempt at claiming a logical address could be wrong. The last_la wasn't converted to a mask when ANDing with type2mask, so that test was broken. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/cec-adap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index ebb5e391b800..87a6b65ed3af 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -1206,7 +1206,7 @@ static int cec_config_thread_func(void *arg) las->log_addr[i] = CEC_LOG_ADDR_INVALID; if (last_la == CEC_LOG_ADDR_INVALID || last_la == CEC_LOG_ADDR_UNREGISTERED || - !(last_la & type2mask[type])) + !((1 << last_la) & type2mask[type])) last_la = la_list[0]; err = cec_config_log_addr(adap, i, last_la); From 08d85f3ea99f1eeafc4e8507936190e86a16ee8c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 17 Jan 2017 16:00:48 +0000 Subject: [PATCH 039/131] irqdomain: Avoid activating interrupts more than once Since commit f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early"), we can end-up activating a PCI/MSI twice (once at allocation time, and once at startup time). This is normally of no consequences, except that there is some HW out there that may misbehave if activate is used more than once (the GICv3 ITS, for example, uses the activate callback to issue the MAPVI command, and the architecture spec says that "If there is an existing mapping for the EventID-DeviceID combination, behavior is UNPREDICTABLE"). While this could be worked around in each individual driver, it may make more sense to tackle the issue at the core level. In order to avoid getting in that situation, let's have a per-interrupt flag to remember if we have already activated that interrupt or not. Fixes: f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early") Reported-and-tested-by: Andre Przywara Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1484668848-24361-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 17 ++++++++++++++++ kernel/irq/irqdomain.c | 44 ++++++++++++++++++++++++++++-------------- 2 files changed, 47 insertions(+), 14 deletions(-) diff --git a/include/linux/irq.h b/include/linux/irq.h index e79875574b39..39e3254e5769 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -184,6 +184,7 @@ struct irq_data { * * IRQD_TRIGGER_MASK - Mask for the trigger type bits * IRQD_SETAFFINITY_PENDING - Affinity setting is pending + * IRQD_ACTIVATED - Interrupt has already been activated * IRQD_NO_BALANCING - Balancing disabled for this IRQ * IRQD_PER_CPU - Interrupt is per cpu * IRQD_AFFINITY_SET - Interrupt affinity was set @@ -202,6 +203,7 @@ struct irq_data { enum { IRQD_TRIGGER_MASK = 0xf, IRQD_SETAFFINITY_PENDING = (1 << 8), + IRQD_ACTIVATED = (1 << 9), IRQD_NO_BALANCING = (1 << 10), IRQD_PER_CPU = (1 << 11), IRQD_AFFINITY_SET = (1 << 12), @@ -312,6 +314,21 @@ static inline bool irqd_affinity_is_managed(struct irq_data *d) return __irqd_to_state(d) & IRQD_AFFINITY_MANAGED; } +static inline bool irqd_is_activated(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_ACTIVATED; +} + +static inline void irqd_set_activated(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_ACTIVATED; +} + +static inline void irqd_clr_activated(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_ACTIVATED; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8c0a0ae43521..b59e6768c5e9 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1346,6 +1346,30 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, } EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); +static void __irq_domain_activate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (irq_data->parent_data) + __irq_domain_activate_irq(irq_data->parent_data); + if (domain->ops->activate) + domain->ops->activate(domain, irq_data); + } +} + +static void __irq_domain_deactivate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (domain->ops->deactivate) + domain->ops->deactivate(domain, irq_data); + if (irq_data->parent_data) + __irq_domain_deactivate_irq(irq_data->parent_data); + } +} + /** * irq_domain_activate_irq - Call domain_ops->activate recursively to activate * interrupt @@ -1356,13 +1380,9 @@ EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); */ void irq_domain_activate_irq(struct irq_data *irq_data) { - if (irq_data && irq_data->domain) { - struct irq_domain *domain = irq_data->domain; - - if (irq_data->parent_data) - irq_domain_activate_irq(irq_data->parent_data); - if (domain->ops->activate) - domain->ops->activate(domain, irq_data); + if (!irqd_is_activated(irq_data)) { + __irq_domain_activate_irq(irq_data); + irqd_set_activated(irq_data); } } @@ -1376,13 +1396,9 @@ void irq_domain_activate_irq(struct irq_data *irq_data) */ void irq_domain_deactivate_irq(struct irq_data *irq_data) { - if (irq_data && irq_data->domain) { - struct irq_domain *domain = irq_data->domain; - - if (domain->ops->deactivate) - domain->ops->deactivate(domain, irq_data); - if (irq_data->parent_data) - irq_domain_deactivate_irq(irq_data->parent_data); + if (irqd_is_activated(irq_data)) { + __irq_domain_deactivate_irq(irq_data); + irqd_clr_activated(irq_data); } } From 52f5631a4c056ad01682393be56d2be237e81610 Mon Sep 17 00:00:00 2001 From: Jurij Smakov Date: Mon, 30 Jan 2017 15:41:36 -0600 Subject: [PATCH 040/131] rtlwifi: rtl8192ce: Fix loading of incorrect firmware In commit cf4747d7535a ("rtlwifi: Fix regression caused by commit d86e64768859, an error in the edit results in the wrong firmware being loaded for some models of the RTL8188/8192CE. In this condition, the connection suffered from high ping latency, slow transfer rates, and required higher signal strengths to work at all See https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=853073, https://bugzilla.opensuse.org/show_bug.cgi?id=1017471, and https://github.com/lwfinger/rtlwifi_new/issues/203 for descriptions of the problems. This patch fixes all of those problems. Fixes: cf4747d7535a ("rtlwifi: Fix regression caused by commit d86e64768859") Signed-off-by: Jurij Smakov Signed-off-by: Larry Finger Cc: Stable # 4.9+ Signed-off-by: Kalle Valo --- drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c index 691ddef1ae28..a33a06d58a9a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c @@ -92,7 +92,7 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); - char *fw_name = "rtlwifi/rtl8192cfwU.bin"; + char *fw_name; rtl8192ce_bt_reg_init(hw); @@ -164,8 +164,13 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw) } /* request fw */ - if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version)) + if (IS_VENDOR_UMC_A_CUT(rtlhal->version) && + !IS_92C_SERIAL(rtlhal->version)) + fw_name = "rtlwifi/rtl8192cfwU.bin"; + else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version)) fw_name = "rtlwifi/rtl8192cfwU_B.bin"; + else + fw_name = "rtlwifi/rtl8192cfw.bin"; rtlpriv->max_fw_size = 0x4000; pr_info("Using firmware %s\n", fw_name); From 433e19cf33d34bb6751c874a9c00980552fe508c Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sat, 28 Jan 2017 11:46:02 -0700 Subject: [PATCH 041/131] Drivers: hv: vmbus: finally fix hv_need_to_signal_on_read() Commit a389fcfd2cb5 ("Drivers: hv: vmbus: Fix signaling logic in hv_need_to_signal_on_read()") added the proper mb(), but removed the test "prev_write_sz < pending_sz" when making the signal decision. As a result, the guest can signal the host unnecessarily, and then the host can throttle the guest because the host thinks the guest is buggy or malicious; finally the user running stress test can perceive intermittent freeze of the guest. This patch brings back the test, and properly handles the in-place consumption APIs used by NetVSC (see get_next_pkt_raw(), put_pkt_raw() and commit_rd_index()). Fixes: a389fcfd2cb5 ("Drivers: hv: vmbus: Fix signaling logic in hv_need_to_signal_on_read()") Signed-off-by: Dexuan Cui Reported-by: Rolf Neugebauer Tested-by: Rolf Neugebauer Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/ring_buffer.c | 1 + drivers/net/hyperv/netvsc.c | 6 ++++++ include/linux/hyperv.h | 32 ++++++++++++++++++++++++++++++-- 3 files changed, 37 insertions(+), 2 deletions(-) diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index cd49cb17eb7f..308dbda700eb 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -383,6 +383,7 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, return ret; } + init_cached_read_index(channel); next_read_location = hv_get_next_read_location(inring_info); next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc, sizeof(desc), diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 5a1cc089acb7..86e5749226ef 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1295,6 +1295,9 @@ void netvsc_channel_cb(void *context) ndev = hv_get_drvdata(device); buffer = get_per_channel_state(channel); + /* commit_rd_index() -> hv_signal_on_read() needs this. */ + init_cached_read_index(channel); + do { desc = get_next_pkt_raw(channel); if (desc != NULL) { @@ -1347,6 +1350,9 @@ void netvsc_channel_cb(void *context) bufferlen = bytes_recvd; } + + init_cached_read_index(channel); + } while (1); if (bufferlen > NETVSC_PACKET_SIZE) diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 42fe43fb0c80..183efde54269 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -128,6 +128,7 @@ struct hv_ring_buffer_info { u32 ring_data_startoffset; u32 priv_write_index; u32 priv_read_index; + u32 cached_read_index; }; /* @@ -180,6 +181,19 @@ static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi) return write; } +static inline u32 hv_get_cached_bytes_to_write( + const struct hv_ring_buffer_info *rbi) +{ + u32 read_loc, write_loc, dsize, write; + + dsize = rbi->ring_datasize; + read_loc = rbi->cached_read_index; + write_loc = rbi->ring_buffer->write_index; + + write = write_loc >= read_loc ? dsize - (write_loc - read_loc) : + read_loc - write_loc; + return write; +} /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. @@ -1488,7 +1502,7 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info) static inline void hv_signal_on_read(struct vmbus_channel *channel) { - u32 cur_write_sz; + u32 cur_write_sz, cached_write_sz; u32 pending_sz; struct hv_ring_buffer_info *rbi = &channel->inbound; @@ -1512,12 +1526,24 @@ static inline void hv_signal_on_read(struct vmbus_channel *channel) cur_write_sz = hv_get_bytes_to_write(rbi); - if (cur_write_sz >= pending_sz) + if (cur_write_sz < pending_sz) + return; + + cached_write_sz = hv_get_cached_bytes_to_write(rbi); + if (cached_write_sz < pending_sz) vmbus_setevent(channel); return; } +static inline void +init_cached_read_index(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + + rbi->cached_read_index = rbi->ring_buffer->read_index; +} + /* * An API to support in-place processing of incoming VMBUS packets. */ @@ -1569,6 +1595,8 @@ static inline void put_pkt_raw(struct vmbus_channel *channel, * This call commits the read index and potentially signals the host. * Here is the pattern for using the "in-place" consumption APIs: * + * init_cached_read_index(); + * * while (get_next_pkt_raw() { * process the packet "in-place"; * put_pkt_raw(); From 96692b097ba76d0c637ae8af47b29c73da33c9d0 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Wed, 14 Dec 2016 09:52:39 +1000 Subject: [PATCH 042/131] drm/nouveau/fence/g84-: protect against concurrent access to semaphore buffers Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_fence.h | 1 + drivers/gpu/drm/nouveau/nv84_fence.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index ccdce1b4eec4..d5e58a38f160 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -99,6 +99,7 @@ struct nv84_fence_priv { struct nouveau_bo *bo; struct nouveau_bo *bo_gart; u32 *suspend; + struct mutex mutex; }; int nv84_fence_context_new(struct nouveau_channel *); diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c index 52b87ae83e7b..f0b322bec7df 100644 --- a/drivers/gpu/drm/nouveau/nv84_fence.c +++ b/drivers/gpu/drm/nouveau/nv84_fence.c @@ -107,8 +107,10 @@ nv84_fence_context_del(struct nouveau_channel *chan) struct nv84_fence_chan *fctx = chan->fence; nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence); + mutex_lock(&priv->mutex); nouveau_bo_vma_del(priv->bo, &fctx->vma_gart); nouveau_bo_vma_del(priv->bo, &fctx->vma); + mutex_unlock(&priv->mutex); nouveau_fence_context_del(&fctx->base); chan->fence = NULL; nouveau_fence_context_free(&fctx->base); @@ -134,11 +136,13 @@ nv84_fence_context_new(struct nouveau_channel *chan) fctx->base.sync32 = nv84_fence_sync32; fctx->base.sequence = nv84_fence_read(chan); + mutex_lock(&priv->mutex); ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma); if (ret == 0) { ret = nouveau_bo_vma_add(priv->bo_gart, cli->vm, &fctx->vma_gart); } + mutex_unlock(&priv->mutex); if (ret) nv84_fence_context_del(chan); @@ -212,6 +216,8 @@ nv84_fence_create(struct nouveau_drm *drm) priv->base.context_base = dma_fence_context_alloc(priv->base.contexts); priv->base.uevent = true; + mutex_init(&priv->mutex); + /* Use VRAM if there is any ; otherwise fallback to system memory */ domain = drm->device.info.ram_size != 0 ? TTM_PL_FLAG_VRAM : /* From c966b6279f610a24ac1d42dcbe30e10fa61220b2 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Wed, 25 May 2016 17:11:40 +1000 Subject: [PATCH 043/131] drm/nouveau: prevent userspace from deleting client object Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_usif.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c index 08f9c6fa0f7f..1fba38622744 100644 --- a/drivers/gpu/drm/nouveau/nouveau_usif.c +++ b/drivers/gpu/drm/nouveau/nouveau_usif.c @@ -313,7 +313,8 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc) if (!(ret = nvif_unpack(-ENOSYS, &data, &size, argv->v0, 0, 0, true))) { /* block access to objects not created via this interface */ owner = argv->v0.owner; - if (argv->v0.object == 0ULL) + if (argv->v0.object == 0ULL && + argv->v0.type != NVIF_IOCTL_V0_DEL) argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */ else argv->v0.owner = NVDRM_OBJECT_USIF; From 7dfee6827780d4228148263545af936d0cae8930 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Mon, 9 Jan 2017 10:22:15 +1000 Subject: [PATCH 044/131] drm/nouveau/disp/mcp7x: disable dptmds workaround The workaround appears to cause regressions on these boards, and from inspection of RM traces, NVIDIA don't appear to do it on them either. Signed-off-by: Ben Skeggs Tested-by: Roy Spliet --- drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c index 567466f93cd5..0db8efbf1c2e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c @@ -433,8 +433,6 @@ nv50_disp_dptmds_war(struct nvkm_device *device) case 0x94: case 0x96: case 0x98: - case 0xaa: - case 0xac: return true; default: break; From d72498ca2cbcf15e5038b184a95f061bca21e820 Mon Sep 17 00:00:00 2001 From: Martin Peres Date: Wed, 7 Dec 2016 06:30:15 +0200 Subject: [PATCH 045/131] drm/nouveau/nouveau/led: prevent compiling the led-code if nouveau=y and leds=m The proper fix would have been to select LEDS_CLASS but this can lead to a circular dependency, as found out by Arnd. This patch implements Arnd's suggestion instead, at the cost of some auto-magic for a fringe feature. Reported-by: Arnd Bergmann Reported-by: Intel's 0-DAY Fixes: 8d021d71b324 ("drm/nouveau/drm/nouveau: add a LED driver for the NVIDIA logo") Signed-off-by: Martin Peres Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_led.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_led.h b/drivers/gpu/drm/nouveau/nouveau_led.h index 187ecdb82002..21a5775028cc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_led.h +++ b/drivers/gpu/drm/nouveau/nouveau_led.h @@ -42,7 +42,7 @@ nouveau_led(struct drm_device *dev) } /* nouveau_led.c */ -#if IS_ENABLED(CONFIG_LEDS_CLASS) +#if IS_REACHABLE(CONFIG_LEDS_CLASS) int nouveau_led_init(struct drm_device *dev); void nouveau_led_suspend(struct drm_device *dev); void nouveau_led_resume(struct drm_device *dev); From d347583a39e2df609a9e40c835f72d3614665b53 Mon Sep 17 00:00:00 2001 From: Alastair Bridgewater Date: Wed, 11 Jan 2017 15:47:18 -0500 Subject: [PATCH 046/131] drm/nouveau/disp/gt215: Fix HDA ELD handling (thus, HDMI audio) on gt215 Store the ELD correctly, not just enough copies of the first byte to pad out the given ELD size. Signed-off-by: Alastair Bridgewater Fixes: 120b0c39c756 ("drm/nv50-/disp: audit and version SOR_HDA_ELD method") Cc: stable@vger.kernel.org # v3.17+ Reviewed-by: Ilia Mirkin Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c index 6f0436df0219..f8f2f16c22a2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c @@ -59,7 +59,7 @@ gt215_hda_eld(NV50_DISP_MTHD_V1) ); } for (i = 0; i < size; i++) - nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[0]); + nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[i]); for (; i < 0x60; i++) nvkm_wr32(device, 0x61c440 + soff, (i << 8)); nvkm_mask(device, 0x61c448 + soff, 0x80000003, 0x80000003); From 24bf7ae359b8cca165bb30742d2b1c03a1eb23af Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Thu, 19 Jan 2017 22:56:30 -0500 Subject: [PATCH 047/131] drm/nouveau/nv1a,nv1f/disp: fix memory clock rate retrieval Based on the xf86-video-nv code, NFORCE (NV1A) and NFORCE2 (NV1F) have a different way of retrieving clocks. See the nv_hw.c:nForceUpdateArbitrationSettings function in the original code for how these clocks were accessed. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=54587 Cc: stable@vger.kernel.org Signed-off-by: Ilia Mirkin Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/dispnv04/hw.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index 74856a8b8f35..e64f52464ecf 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -222,6 +222,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype) uint32_t mpllP; pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP); + mpllP = (mpllP >> 8) & 0xf; if (!mpllP) mpllP = 4; @@ -232,7 +233,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype) uint32_t clock; pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock); - return clock; + return clock / 1000; } ret = nouveau_hw_get_pllvals(dev, plltype, &pllvals); From 2b5078937355c0d662ecef54b7d4d04f48da4fa9 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Tue, 24 Jan 2017 09:32:26 +1000 Subject: [PATCH 048/131] drm/nouveau/kms/nv50: request vblank events for commits that send completion events This somehow fixes an issue where sync-to-vblank longer works correctly after resume from suspend. From a HW perspective, we don't need the IRQs turned on to be able to detect flip completion, so it's assumed that this is required for the voodoo in the core DRM vblank core. Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nv50_display.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 2c2c64507661..32097fd615fd 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -4052,6 +4052,11 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) } } + for_each_crtc_in_state(state, crtc, crtc_state, i) { + if (crtc->state->event) + drm_crtc_vblank_get(crtc); + } + /* Update plane(s). */ for_each_plane_in_state(state, plane, plane_state, i) { struct nv50_wndw_atom *asyw = nv50_wndw_atom(plane->state); @@ -4101,6 +4106,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) drm_crtc_send_vblank_event(crtc, crtc->state->event); spin_unlock_irqrestore(&crtc->dev->event_lock, flags); crtc->state->event = NULL; + drm_crtc_vblank_put(crtc); } } From 161e6d44a5e2d3f85365cb717d60e363171b39e6 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 16 Jan 2017 12:23:42 -0200 Subject: [PATCH 049/131] mmc: sdhci: Ignore unexpected CARD_INT interrupts One of our kernelCI boxes hanged at boot because a faulty eSDHC device was triggering spurious CARD_INT interrupts for SD cards, causing CMD52 reads, which are not allowed for SD devices. This adds a sanity check to the interruption path, preventing that illegal command from getting sent if the CARD_INT interruption should be disabled. This quirk allows that particular machine to resume boot despite the faulty hardware, instead of getting hung dealing with thousands of mishandled interrupts. Suggested-by: Adrian Hunter Signed-off-by: Gabriel Krisman Bertazi Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson Cc: --- drivers/mmc/host/sdhci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 23909804ffb8..0def99590d16 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2733,7 +2733,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) if (intmask & SDHCI_INT_RETUNE) mmc_retune_needed(host->mmc); - if (intmask & SDHCI_INT_CARD_INT) { + if ((intmask & SDHCI_INT_CARD_INT) && + (host->ier & SDHCI_INT_CARD_INT)) { sdhci_enable_sdio_irq_nolock(host, false); host->thread_isr |= SDHCI_INT_CARD_INT; result = IRQ_WAKE_THREAD; From 92c715fca907686f5298220ece53423e38ba3aed Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 31 Jan 2017 10:25:25 +0100 Subject: [PATCH 050/131] drm/atomic: Fix double free in drm_atomic_state_default_clear drm_atomic_helper_page_flip and drm_atomic_ioctl set their own events in crtc_state->event. But when it's set the event is freed in 2 places. Solve this by only freeing the event in the atomic ioctl when it allocated its own event. This has been broken twice. The first time when the code was introduced, but only in the corner case when an event is allocated, but more crtc's were included by atomic check and then failing. This can mostly happen when you do an atomic modeset in i915 and the display clock is changed, which forces all crtc's to be included to the state. This has been broken worse by adding in-fences support, which caused the double free to be done unconditionally. [IGT] kms_rotation_crc: starting subtest primary-rotation-180 ============================================================================= BUG kmalloc-128 (Tainted: G U ): Object already free ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Allocated in drm_atomic_helper_setup_commit+0x285/0x2f0 [drm_kms_helper] age=0 cpu=3 pid=1529 ___slab_alloc+0x308/0x3b0 __slab_alloc+0xd/0x20 kmem_cache_alloc_trace+0x92/0x1c0 drm_atomic_helper_setup_commit+0x285/0x2f0 [drm_kms_helper] intel_atomic_commit+0x35/0x4f0 [i915] drm_atomic_commit+0x46/0x50 [drm] drm_mode_atomic_ioctl+0x7d4/0xab0 [drm] drm_ioctl+0x2b3/0x490 [drm] do_vfs_ioctl+0x69c/0x700 SyS_ioctl+0x4e/0x80 entry_SYSCALL_64_fastpath+0x13/0x94 INFO: Freed in drm_event_cancel_free+0xa3/0xb0 [drm] age=0 cpu=3 pid=1529 __slab_free+0x48/0x2e0 kfree+0x159/0x1a0 drm_event_cancel_free+0xa3/0xb0 [drm] drm_mode_atomic_ioctl+0x86d/0xab0 [drm] drm_ioctl+0x2b3/0x490 [drm] do_vfs_ioctl+0x69c/0x700 SyS_ioctl+0x4e/0x80 entry_SYSCALL_64_fastpath+0x13/0x94 INFO: Slab 0xffffde1f0997b080 objects=17 used=2 fp=0xffff92fb65ec2578 flags=0x200000000008101 INFO: Object 0xffff92fb65ec2578 @offset=1400 fp=0xffff92fb65ec2ae8 Redzone ffff92fb65ec2570: bb bb bb bb bb bb bb bb ........ Object ffff92fb65ec2578: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec2588: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec2598: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec25a8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec25b8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec25c8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec25d8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff92fb65ec25e8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5 kkkkkkkkkkkkkkk. Redzone ffff92fb65ec25f8: bb bb bb bb bb bb bb bb ........ Padding ffff92fb65ec2738: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ CPU: 3 PID: 180 Comm: kworker/3:2 Tainted: G BU 4.10.0-rc6-patser+ #5039 Hardware name: /NUC5PPYB, BIOS PYBSWCEL.86A.0031.2015.0601.1712 06/01/2015 Workqueue: events intel_atomic_helper_free_state [i915] Call Trace: dump_stack+0x4d/0x6d print_trailer+0x20c/0x220 free_debug_processing+0x1c6/0x330 ? drm_atomic_state_default_clear+0xf7/0x1c0 [drm] __slab_free+0x48/0x2e0 ? drm_atomic_state_default_clear+0xf7/0x1c0 [drm] kfree+0x159/0x1a0 drm_atomic_state_default_clear+0xf7/0x1c0 [drm] ? drm_atomic_state_clear+0x30/0x30 [drm] intel_atomic_state_clear+0xd/0x20 [i915] drm_atomic_state_clear+0x1a/0x30 [drm] __drm_atomic_state_free+0x13/0x60 [drm] intel_atomic_helper_free_state+0x5d/0x70 [i915] process_one_work+0x260/0x4a0 worker_thread+0x2d1/0x4f0 kthread+0x127/0x130 ? process_one_work+0x4a0/0x4a0 ? kthread_stop+0x120/0x120 ret_from_fork+0x29/0x40 FIX kmalloc-128: Object at 0xffff92fb65ec2578 not freed Fixes: 3b24f7d67581 ("drm/atomic: Add struct drm_crtc_commit to track async updates") Fixes: 9626014258a5 ("drm/fence: add in-fences support") Cc: # v4.8+ Cc: Daniel Vetter Signed-off-by: Maarten Lankhorst Reviewed-by: Daniel Vetter Reviewed-by: Gustavo Padovan Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1485854725-27640-1-git-send-email-maarten.lankhorst@linux.intel.com --- drivers/gpu/drm/drm_atomic.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 50f5cf7b69d1..fdfb1ec17e66 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -2032,13 +2032,16 @@ static void complete_crtc_signaling(struct drm_device *dev, } for_each_crtc_in_state(state, crtc, crtc_state, i) { + struct drm_pending_vblank_event *event = crtc_state->event; /* - * TEST_ONLY and PAGE_FLIP_EVENT are mutually - * exclusive, if they weren't, this code should be - * called on success for TEST_ONLY too. + * Free the allocated event. drm_atomic_helper_setup_commit + * can allocate an event too, so only free it if it's ours + * to prevent a double free in drm_atomic_state_clear. */ - if (crtc_state->event) - drm_event_cancel_free(dev, &crtc_state->event->base); + if (event && (event->base.fence || event->base.file_priv)) { + drm_event_cancel_free(dev, &event->base); + crtc_state->event = NULL; + } } if (!fence_state) From d07830db1bdb254e4b50d366010b219286b8c937 Mon Sep 17 00:00:00 2001 From: "Marcel J.E. Mol" Date: Mon, 30 Jan 2017 19:26:40 +0100 Subject: [PATCH 051/131] USB: serial: pl2303: add ATEN device ID Seems that ATEN serial-to-usb devices using pl2303 exist with different device ids. This patch adds a missing device ID so it is recognised by the driver. Signed-off-by: Marcel J.E. Mol Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/pl2303.c | 1 + drivers/usb/serial/pl2303.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 46fca6b75846..1db4b61bdf7b 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -49,6 +49,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, + { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID2) }, { USB_DEVICE(ATEN_VENDOR_ID2, ATEN_PRODUCT_ID) }, { USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID) }, { USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID_UCSGT) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index e3b7af8adfb7..09d9be88209e 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -27,6 +27,7 @@ #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 #define ATEN_PRODUCT_ID 0x2008 +#define ATEN_PRODUCT_ID2 0x2118 #define IODATA_VENDOR_ID 0x04bb #define IODATA_PRODUCT_ID 0x0a03 From d19fb70dd68c4e960e2ac09b0b9c79dfdeefa726 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Wed, 18 Jan 2017 19:04:42 +0800 Subject: [PATCH 052/131] NFSD: Fix a null reference case in find_or_create_lock_stateid() nfsd assigns the nfs4_free_lock_stateid to .sc_free in init_lock_stateid(). If nfsd doesn't go through init_lock_stateid() and put stateid at end, there is a NULL reference to .sc_free when calling nfs4_put_stid(ns). This patch let the nfs4_stid.sc_free assignment to nfs4_alloc_stid(). Cc: stable@vger.kernel.org Fixes: 356a95ece7aa "nfsd: clean up races in lock stateid searching..." Signed-off-by: Kinglong Mee Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4layouts.c | 5 +++-- fs/nfsd/nfs4state.c | 19 ++++++++----------- fs/nfsd/state.h | 4 ++-- 3 files changed, 13 insertions(+), 15 deletions(-) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 596205d939a1..1fc07a9c70e9 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -223,10 +223,11 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, struct nfs4_layout_stateid *ls; struct nfs4_stid *stp; - stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache); + stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache, + nfsd4_free_layout_stateid); if (!stp) return NULL; - stp->sc_free = nfsd4_free_layout_stateid; + get_nfs4_file(fp); stp->sc_file = fp; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4b4beaaa4eaa..a0dee8ae9f97 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -633,8 +633,8 @@ out: return co; } -struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, - struct kmem_cache *slab) +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, + void (*sc_free)(struct nfs4_stid *)) { struct nfs4_stid *stid; int new_id; @@ -650,6 +650,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, idr_preload_end(); if (new_id < 0) goto out_free; + + stid->sc_free = sc_free; stid->sc_client = cl; stid->sc_stateid.si_opaque.so_id = new_id; stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; @@ -675,15 +677,12 @@ out_free: static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) { struct nfs4_stid *stid; - struct nfs4_ol_stateid *stp; - stid = nfs4_alloc_stid(clp, stateid_slab); + stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid); if (!stid) return NULL; - stp = openlockstateid(stid); - stp->st_stid.sc_free = nfs4_free_ol_stateid; - return stp; + return openlockstateid(stid); } static void nfs4_free_deleg(struct nfs4_stid *stid) @@ -781,11 +780,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh, goto out_dec; if (delegation_blocked(¤t_fh->fh_handle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); + dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); if (dp == NULL) goto out_dec; - dp->dl_stid.sc_free = nfs4_free_deleg; /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid @@ -5580,7 +5578,6 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; - stp->st_stid.sc_free = nfs4_free_lock_stateid; stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; @@ -5623,7 +5620,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, lst = find_lock_stateid(lo, fi); if (lst == NULL) { spin_unlock(&clp->cl_lock); - ns = nfs4_alloc_stid(clp, stateid_slab); + ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); if (ns == NULL) return NULL; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index c9399366f9df..4516e8b7d776 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -603,8 +603,8 @@ extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); -struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, - struct kmem_cache *slab); +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, + void (*sc_free)(struct nfs4_stid *)); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); From 41f53350a0f36a7b8e31bec0d0ca907e028ab4cd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Jan 2017 09:22:41 +0100 Subject: [PATCH 053/131] nfsd: special case truncates some more Both the NFS protocols and the Linux VFS use a setattr operation with a bitmap of attributs to set to set various file attributes including the file size and the uid/gid. The Linux syscalls never mixes size updates with unrelated updates like the uid/gid, and some file systems like XFS and GFS2 rely on the fact that truncates might not update random other attributes, and many other file systems handle the case but do not update the different attributes in the same transaction. NFSD on the other hand passes the attributes it gets on the wire more or less directly through to the VFS, leading to updates the file systems don't expect. XFS at least has an assert on the allowed attributes, which caught an unusual NFS client setting the size and group at the same time. To handle this issue properly this switches nfsd to call vfs_truncate for size changes, and then handle all other attributes through notify_change. As a side effect this also means less boilerplace code around the size change as we can now reuse the VFS code. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 97 ++++++++++++++++++++------------------------------- 1 file changed, 37 insertions(+), 60 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 26c6fdb4bf67..ca13236dbb1f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -332,37 +332,6 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) } } -static __be32 -nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct iattr *iap) -{ - struct inode *inode = d_inode(fhp->fh_dentry); - int host_err; - - if (iap->ia_size < inode->i_size) { - __be32 err; - - err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, - NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); - if (err) - return err; - } - - host_err = get_write_access(inode); - if (host_err) - goto out_nfserrno; - - host_err = locks_verify_truncate(inode, NULL, iap->ia_size); - if (host_err) - goto out_put_write_access; - return 0; - -out_put_write_access: - put_write_access(inode); -out_nfserrno: - return nfserrno(host_err); -} - /* * Set various file attributes. After this call fhp needs an fh_put. */ @@ -377,7 +346,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, __be32 err; int host_err; bool get_write_count; - int size_change = 0; if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; @@ -390,11 +358,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, /* Get inode */ err = fh_verify(rqstp, fhp, ftype, accmode); if (err) - goto out; + return err; if (get_write_count) { host_err = fh_want_write(fhp); if (host_err) - return nfserrno(host_err); + goto out_host_err; } dentry = fhp->fh_dentry; @@ -405,50 +373,59 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, iap->ia_valid &= ~ATTR_MODE; if (!iap->ia_valid) - goto out; + return 0; nfsd_sanitize_attrs(inode, iap); + if (check_guard && guardtime != inode->i_ctime.tv_sec) + return nfserr_notsync; + /* * The size case is special, it changes the file in addition to the - * attributes. + * attributes, and file systems don't expect it to be mixed with + * "random" attribute changes. We thus split out the size change + * into a separate call for vfs_truncate, and do the rest as a + * a separate setattr call. */ if (iap->ia_valid & ATTR_SIZE) { - err = nfsd_get_write_access(rqstp, fhp, iap); - if (err) - goto out; - size_change = 1; + struct path path = { + .mnt = fhp->fh_export->ex_path.mnt, + .dentry = dentry, + }; + bool implicit_mtime = false; /* - * RFC5661, Section 18.30.4: - * Changing the size of a file with SETATTR indirectly - * changes the time_modify and change attributes. - * - * (and similar for the older RFCs) + * vfs_truncate implicity updates the mtime IFF the file size + * actually changes. Avoid the additional seattr call below if + * the only other attribute that the client sends is the mtime. */ - if (iap->ia_size != i_size_read(inode)) - iap->ia_valid |= ATTR_MTIME; + if (iap->ia_size != i_size_read(inode) && + ((iap->ia_valid & ~(ATTR_SIZE | ATTR_MTIME)) == 0)) + implicit_mtime = true; + + host_err = vfs_truncate(&path, iap->ia_size); + if (host_err) + goto out_host_err; + + iap->ia_valid &= ~ATTR_SIZE; + if (implicit_mtime) + iap->ia_valid &= ~ATTR_MTIME; + if (!iap->ia_valid) + goto done; } iap->ia_valid |= ATTR_CTIME; - if (check_guard && guardtime != inode->i_ctime.tv_sec) { - err = nfserr_notsync; - goto out_put_write_access; - } - fh_lock(fhp); host_err = notify_change(dentry, iap, NULL); fh_unlock(fhp); - err = nfserrno(host_err); + if (host_err) + goto out_host_err; -out_put_write_access: - if (size_change) - put_write_access(inode); - if (!err) - err = nfserrno(commit_metadata(fhp)); -out: - return err; +done: + host_err = commit_metadata(fhp); +out_host_err: + return nfserrno(host_err); } #if defined(CONFIG_NFSD_V4) From 034dd34ff4916ec1f8f74e39ca3efb04eab2f791 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 31 Jan 2017 11:37:50 -0500 Subject: [PATCH 054/131] svcrpc: fix oops in absence of krb5 module Olga Kornievskaia says: "I ran into this oops in the nfsd (below) (4.10-rc3 kernel). To trigger this I had a client (unsuccessfully) try to mount the server with krb5 where the server doesn't have the rpcsec_gss_krb5 module built." The problem is that rsci.cred is copied from a svc_cred structure that gss_proxy didn't properly initialize. Fix that. [120408.542387] general protection fault: 0000 [#1] SMP ... [120408.565724] CPU: 0 PID: 3601 Comm: nfsd Not tainted 4.10.0-rc3+ #16 [120408.567037] Hardware name: VMware, Inc. VMware Virtual = Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [120408.569225] task: ffff8800776f95c0 task.stack: ffffc90003d58000 [120408.570483] RIP: 0010:gss_mech_put+0xb/0x20 [auth_rpcgss] ... [120408.584946] ? rsc_free+0x55/0x90 [auth_rpcgss] [120408.585901] gss_proxy_save_rsc+0xb2/0x2a0 [auth_rpcgss] [120408.587017] svcauth_gss_proxy_init+0x3cc/0x520 [auth_rpcgss] [120408.588257] ? __enqueue_entity+0x6c/0x70 [120408.589101] svcauth_gss_accept+0x391/0xb90 [auth_rpcgss] [120408.590212] ? try_to_wake_up+0x4a/0x360 [120408.591036] ? wake_up_process+0x15/0x20 [120408.592093] ? svc_xprt_do_enqueue+0x12e/0x2d0 [sunrpc] [120408.593177] svc_authenticate+0xe1/0x100 [sunrpc] [120408.594168] svc_process_common+0x203/0x710 [sunrpc] [120408.595220] svc_process+0x105/0x1c0 [sunrpc] [120408.596278] nfsd+0xe9/0x160 [nfsd] [120408.597060] kthread+0x101/0x140 [120408.597734] ? nfsd_destroy+0x60/0x60 [nfsd] [120408.598626] ? kthread_park+0x90/0x90 [120408.599448] ret_from_fork+0x22/0x30 Fixes: 1d658336b05f "SUNRPC: Add RPC based upcall mechanism for RPCGSS auth" Cc: stable@vger.kernel.org Cc: Simo Sorce Reported-by: Olga Kornievskaia Tested-by: Olga Kornievskaia Signed-off-by: J. Bruce Fields --- net/sunrpc/auth_gss/gss_rpc_xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index dc6fb79a361f..25d9a9cf7b66 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -260,7 +260,7 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, if (!oa->data) return -ENOMEM; - creds = kmalloc(sizeof(struct svc_cred), GFP_KERNEL); + creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL); if (!creds) { kfree(oa->data); return -ENOMEM; From aaaec6fc755447a1d056765b11b24d8ff2b81366 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Jan 2017 19:03:21 +0100 Subject: [PATCH 055/131] x86/irq: Make irq activate operations symmetric The recent commit which prevents double activation of interrupts unearthed interesting code in x86. The code (ab)uses irq_domain_activate_irq() to reconfigure an already activated interrupt. That trips over the prevention code now. Fix it by deactivating the interrupt before activating the new configuration. Fixes: 08d85f3ea99f1 "irqdomain: Avoid activating interrupts more than once" Reported-and-tested-by: Mike Galbraith Reported-and-tested-by: Borislav Petkov Signed-off-by: Thomas Gleixner Cc: Andrey Ryabinin Cc: Marc Zyngier Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1701311901580.3457@nanos --- arch/x86/kernel/apic/io_apic.c | 2 ++ arch/x86/kernel/hpet.c | 1 + 2 files changed, 3 insertions(+) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1e35dd06b090..52f352b063fd 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2117,6 +2117,7 @@ static inline void __init check_timer(void) if (idx != -1 && irq_trigger(idx)) unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2138,6 +2139,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 85e87b46c318..dc6ba5bda9fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); From 0becc0ae5b42828785b589f686725ff5bc3b9b25 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Jan 2017 09:37:34 +0100 Subject: [PATCH 056/131] x86/mce: Make timer handling more robust Erik reported that on a preproduction hardware a CMCI storm triggers the BUG_ON in add_timer_on(). The reason is that the per CPU MCE timer is started by the CMCI logic before the MCE CPU hotplug callback starts the timer with add_timer_on(). So the timer is already queued which triggers the BUG. Using add_timer_on() is pretty pointless in this code because the timer is strictlty per CPU, initialized as pinned and all operations which arm the timer happen on the CPU to which the timer belongs. Simplify the whole machinery by using mod_timer() instead of add_timer_on() which avoids the problem because mod_timer() can handle already queued timers. Use __start_timer() everywhere so the earliest armed expiry time is preserved. Reported-by: Erik Veijola Tested-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Tony Luck Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1701310936080.3457@nanos Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/mcheck/mce.c | 31 ++++++++++++------------------- 1 file changed, 12 insertions(+), 19 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..537c6647d84c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1373,20 +1373,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1416,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1427,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1774,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1799,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2566,7 +2559,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2570,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); From 970d14e3989160ee9e97c7d75ecbc893fd29dab9 Mon Sep 17 00:00:00 2001 From: Bhumika Goyal Date: Wed, 25 Jan 2017 00:54:07 +0530 Subject: [PATCH 057/131] nvdimm: constify device_type structures Declare device_type structure as const as it is only stored in the type field of a device structure. This field is of type const, so add const to declaration of device_type structure. File size before: text data bss dec hex filename 19278 3199 16 22493 57dd nvdimm/namespace_devs.o File size after: text data bss dec hex filename 19929 3160 16 23105 5a41 nvdimm/namespace_devs.o Signed-off-by: Bhumika Goyal Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index a518cb1b59d4..eda027db0918 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -52,17 +52,17 @@ static void namespace_blk_release(struct device *dev) kfree(nsblk); } -static struct device_type namespace_io_device_type = { +static const struct device_type namespace_io_device_type = { .name = "nd_namespace_io", .release = namespace_io_release, }; -static struct device_type namespace_pmem_device_type = { +static const struct device_type namespace_pmem_device_type = { .name = "nd_namespace_pmem", .release = namespace_pmem_release, }; -static struct device_type namespace_blk_device_type = { +static const struct device_type namespace_blk_device_type = { .name = "nd_namespace_blk", .release = namespace_blk_release, }; From 9d032f4201d39e5cf43a8709a047e481f5723fdc Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 25 Jan 2017 00:54:07 +0530 Subject: [PATCH 058/131] libnvdimm, namespace: do not delete namespace-id 0 Given that the naming of pmem devices changes from the pmemX form to the pmemX.Y form when namespace id is greater than 0, arrange for namespaces with id-0 to be exempt from deletion. Otherwise a simple reconfiguration of an existing namespace to a new mode results in a name change of the resulting block device: # ndctl list --namespace=namespace1.0 { "dev":"namespace1.0", "mode":"raw", "size":2147483648, "uuid":"3dadf3dc-89b9-4b24-b20e-abc8a4707ce3", "blockdev":"pmem1" } # ndctl create-namespace --reconfig=namespace1.0 --mode=memory --force { "dev":"namespace1.1", "mode":"memory", "size":2111832064, "uuid":"7b4a6341-7318-4219-a02c-fb57c0bbf613", "blockdev":"pmem1.1" } This change does require tooling changes to explicitly look for namespaceX.0 if the seed has already advanced to another namespace. Cc: Fixes: 98a29c39dc68 ("libnvdimm, namespace: allow creation of multiple pmem-namespaces per region") Reviewed-by: Johannes Thumshirn Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index eda027db0918..ce3e8dfa10ad 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -962,8 +962,8 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) struct nvdimm_drvdata *ndd; struct nd_label_id label_id; u32 flags = 0, remainder; + int rc, i, id = -1; u8 *uuid = NULL; - int rc, i; if (dev->driver || ndns->claim) return -EBUSY; @@ -972,11 +972,13 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); uuid = nspm->uuid; + id = nspm->id; } else if (is_namespace_blk(dev)) { struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); uuid = nsblk->uuid; flags = NSLABEL_FLAG_LOCAL; + id = nsblk->id; } /* @@ -1039,10 +1041,11 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) /* * Try to delete the namespace if we deleted all of its - * allocation, this is not the seed device for the region, and - * it is not actively claimed by a btt instance. + * allocation, this is not the seed or 0th device for the + * region, and it is not actively claimed by a btt, pfn, or dax + * instance. */ - if (val == 0 && nd_region->ns_seed != dev && !ndns->claim) + if (val == 0 && id != 0 && nd_region->ns_seed != dev && !ndns->claim) nd_device_unregister(dev, ND_ASYNC); return rc; From 4b3e6f2ef3722f1a6a97b6034ed492c1a21fd4ae Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 31 Jan 2017 18:35:37 -0800 Subject: [PATCH 059/131] xtensa: fix noMMU build on cores with MMU Commit bf15f86b343ed8 ("xtensa: initialize MMU before jumping to reset vector") calls MMU management functions even when CONFIG_MMU is not selected. That breaks noMMU build on cores with MMU. Don't manage MMU when CONFIG_MMU is not selected. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov --- arch/xtensa/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 88a044af7504..32cdc2c52e98 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -540,7 +540,7 @@ subsys_initcall(topology_init); void cpu_reset(void) { -#if XCHAL_HAVE_PTP_MMU +#if XCHAL_HAVE_PTP_MMU && IS_ENABLED(CONFIG_MMU) local_irq_disable(); /* * We have full MMU: all autoload ways, ways 7, 8 and 9 of DTLB must From dd86e373e09fb16b83e8adf5c48c421a4ca76468 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Jan 2017 23:58:38 +0100 Subject: [PATCH 060/131] perf/x86/intel/rapl: Make package handling more robust The package management code in RAPL relies on package mapping being available before a CPU is started. This changed with: 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust") because the ACPI/BIOS information turned out to be unreliable, but that left RAPL in broken state. This was not noticed because on a regular boot all CPUs are online before RAPL is initialized. A possible fix would be to reintroduce the mess which allocates a package data structure in CPU prepare and when it turns out to already exist in starting throw it away later in the CPU online callback. But that's a horrible hack and not required at all because RAPL becomes functional for perf only in the CPU online callback. That's correct because user space is not yet informed about the CPU being onlined, so nothing caan rely on RAPL being available on that particular CPU. Move the allocation to the CPU online callback and simplify the hotplug handling. At this point the package mapping is established and correct. This also adds a missing check for available package data in the event_init() function. Reported-by: Yasuaki Ishimatsu Signed-off-by: Thomas Gleixner Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Stephane Eranian Cc: Vince Weaver Fixes: 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust") Link: http://lkml.kernel.org/r/20170131230141.212593966@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/events/intel/rapl.c | 60 ++++++++++++++++-------------------- include/linux/cpuhotplug.h | 1 - 2 files changed, 26 insertions(+), 35 deletions(-) diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 17c3564d087a..22ef4f72cf32 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -161,7 +161,13 @@ static u64 rapl_timer_ms; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - return rapl_pmus->pmus[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) @@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event) /* must be done before validate_group */ pmu = cpu_to_rapl_pmu(event->cpu); + if (!pmu) + return -EINVAL; event->cpu = pmu->cpu; event->pmu_private = pmu; event->hw.event_base = msr; @@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu) struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; + if (!pmu) { + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -ENOMEM; + + raw_spin_lock_init(&pmu->lock); + INIT_LIST_HEAD(&pmu->active_list); + pmu->pmu = &rapl_pmus->pmu; + pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + rapl_hrtimer_init(pmu); + + rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; + } + /* * Check if there is an online cpu in the package which collects rapl * events already. @@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu) return 0; } -static int rapl_cpu_prepare(unsigned int cpu) -{ - struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); - - if (pmu) - return 0; - - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); - if (!pmu) - return -ENOMEM; - - raw_spin_lock_init(&pmu->lock); - INIT_LIST_HEAD(&pmu->active_list); - pmu->pmu = &rapl_pmus->pmu; - pmu->timer_interval = ms_to_ktime(rapl_timer_ms); - pmu->cpu = -1; - rapl_hrtimer_init(pmu); - rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; - return 0; -} - static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -803,29 +804,21 @@ static int __init rapl_pmu_init(void) /* * Install callbacks. Core will call them for each online cpu. */ - - ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare", - rapl_cpu_prepare, NULL); - if (ret) - goto out; - ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) - goto out1; + goto out; ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); if (ret) - goto out2; + goto out1; rapl_advertise(); return 0; -out2: - cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out1: - cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(); @@ -836,7 +829,6 @@ module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP); perf_pmu_unregister(&rapl_pmus->pmu); cleanup_rapl_pmus(); } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d936a0021839..8329f3dc592c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -10,7 +10,6 @@ enum cpuhp_state { CPUHP_PERF_X86_PREPARE, CPUHP_PERF_X86_UNCORE_PREP, CPUHP_PERF_X86_AMD_UNCORE_PREP, - CPUHP_PERF_X86_RAPL_PREP, CPUHP_PERF_BFIN, CPUHP_PERF_POWER, CPUHP_PERF_SUPERH, From 1aa6cfd33df492939b0be15ebdbcff1f8ae5ddb6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Jan 2017 23:58:39 +0100 Subject: [PATCH 061/131] perf/x86/intel/uncore: Clean up hotplug conversion fallout The recent conversion to the hotplug state machine kept two mechanisms from the original code: 1) The first_init logic which adds the number of online CPUs in a package to the refcount. That's wrong because the callbacks are executed for all online CPUs. Remove it so the refcounting is correct. 2) The on_each_cpu() call to undo box->init() in the error handling path. That's bogus because when the prepare callback fails no box has been initialized yet. Remove it. Signed-off-by: Thomas Gleixner Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Stephane Eranian Cc: Vince Weaver Cc: Yasuaki Ishimatsu Fixes: 1a246b9f58c6 ("perf/x86/intel/uncore: Convert to hotplug state machine") Link: http://lkml.kernel.org/r/20170131230141.298032324@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore.c | 44 ++++------------------------------ 1 file changed, 4 insertions(+), 40 deletions(-) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 8c4ccdc3a3f3..56c5235dcc29 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -764,30 +764,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) -{ - struct intel_uncore_pmu *pmu = type->pmus; - struct intel_uncore_box *box; - int i, pkg; - - if (pmu) { - pkg = topology_physical_package_id(cpu); - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box) - uncore_box_exit(box); - } - } -} - -static void uncore_exit_boxes(void *dummy) -{ - struct intel_uncore_type **types; - - for (types = uncore_msr_uncores; *types; types++) - __uncore_exit_boxes(*types++, smp_processor_id()); -} - static void uncore_free_boxes(struct intel_uncore_pmu *pmu) { int pkg; @@ -1078,22 +1054,12 @@ static int uncore_cpu_dying(unsigned int cpu) return 0; } -static int first_init; - static int uncore_cpu_starting(unsigned int cpu) { struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, pkg, ncpus = 1; - - if (first_init) { - /* - * On init we get the number of online cpus in the package - * and set refcount for all of them. - */ - ncpus = cpumask_weight(topology_core_cpumask(cpu)); - } + int i, pkg; pkg = topology_logical_package_id(cpu); for (; *types; types++) { @@ -1104,7 +1070,7 @@ static int uncore_cpu_starting(unsigned int cpu) if (!box) continue; /* The first cpu on a package activates the box */ - if (atomic_add_return(ncpus, &box->refcnt) == ncpus) + if (atomic_inc_return(&box->refcnt) == 1) uncore_box_init(box); } } @@ -1408,19 +1374,17 @@ static int __init intel_uncore_init(void) "perf/x86/intel/uncore:prepare", uncore_cpu_prepare, NULL); } - first_init = 1; + cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING, "perf/x86/uncore:starting", uncore_cpu_starting, uncore_cpu_dying); - first_init = 0; + cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, "perf/x86/uncore:online", uncore_event_cpu_online, uncore_event_cpu_offline); return 0; err: - /* Undo box->init_box() */ - on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); return ret; From fff4b87e594ad3d2e4f51e8d3d86a6f9d3d8b654 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Jan 2017 23:58:40 +0100 Subject: [PATCH 062/131] perf/x86/intel/uncore: Make package handling more robust The package management code in uncore relies on package mapping being available before a CPU is started. This changed with: 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust") because the ACPI/BIOS information turned out to be unreliable, but that left uncore in broken state. This was not noticed because on a regular boot all CPUs are online before uncore is initialized. Move the allocation to the CPU online callback and simplify the hotplug handling. At this point the package mapping is established and correct. Signed-off-by: Thomas Gleixner Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Stephane Eranian Cc: Vince Weaver Cc: Yasuaki Ishimatsu Fixes: 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust") Link: http://lkml.kernel.org/r/20170131230141.377156255@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore.c | 196 +++++++++++++++------------------ include/linux/cpuhotplug.h | 2 - 2 files changed, 91 insertions(+), 107 deletions(-) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 56c5235dcc29..1ab45976474d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj, struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - return pmu->boxes[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < max_packages ? pmu->boxes[pkgid] : NULL; } u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) @@ -1034,76 +1040,6 @@ static void uncore_pci_exit(void) } } -static int uncore_cpu_dying(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box && atomic_dec_return(&box->refcnt) == 0) - uncore_box_exit(box); - } - } - return 0; -} - -static int uncore_cpu_starting(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (!box) - continue; - /* The first cpu on a package activates the box */ - if (atomic_inc_return(&box->refcnt) == 1) - uncore_box_init(box); - } - } - - return 0; -} - -static int uncore_cpu_prepare(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - if (pmu->boxes[pkg]) - continue; - /* First cpu of a package allocates the box */ - box = uncore_alloc_box(type, cpu_to_node(cpu)); - if (!box) - return -ENOMEM; - box->pmu = pmu; - box->pkgid = pkg; - pmu->boxes[pkg] = box; - } - } - return 0; -} - static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu, int new_cpu) { @@ -1143,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores, static int uncore_event_cpu_offline(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, pkg, target; /* Check if exiting cpu is used for collecting uncore events */ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) - return 0; - + goto unref; /* Find a new cpu to collect uncore events */ target = cpumask_any_but(topology_core_cpumask(cpu), cpu); @@ -1160,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu) uncore_change_context(uncore_msr_uncores, cpu, target); uncore_change_context(uncore_pci_uncores, cpu, target); + +unref: + /* Clear the references */ + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); + } + } return 0; } +static int allocate_boxes(struct intel_uncore_type **types, + unsigned int pkg, unsigned int cpu) +{ + struct intel_uncore_box *box, *tmp; + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + LIST_HEAD(allocated); + int i; + + /* Try to allocate all required boxes */ + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[pkg]) + continue; + box = uncore_alloc_box(type, cpu_to_node(cpu)); + if (!box) + goto cleanup; + box->pmu = pmu; + box->pkgid = pkg; + list_add(&box->active_list, &allocated); + } + } + /* Install them in the pmus */ + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + box->pmu->boxes[pkg] = box; + } + return 0; + +cleanup: + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + kfree(box); + } + return -ENOMEM; +} + static int uncore_event_cpu_online(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, ret, pkg, target; + + pkg = topology_logical_package_id(cpu); + ret = allocate_boxes(types, pkg, cpu); + if (ret) + return ret; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box && atomic_inc_return(&box->refcnt) == 1) + uncore_box_init(box); + } + } /* * Check if there is an online cpu in the package @@ -1355,33 +1363,13 @@ static int __init intel_uncore_init(void) if (cret && pret) return -ENODEV; - /* - * Install callbacks. Core will call them for each online cpu. - * - * The first online cpu of each package allocates and takes - * the refcounts for all other online cpus in that package. - * If msrs are not enabled no allocation is required and - * uncore_cpu_prepare() is not called for each online cpu. - */ - if (!cret) { - ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - if (ret) - goto err; - } else { - cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - } - - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING, - "perf/x86/uncore:starting", - uncore_cpu_starting, uncore_cpu_dying); - - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, - "perf/x86/uncore:online", - uncore_event_cpu_online, uncore_event_cpu_offline); + /* Install hotplug callbacks to setup the targets for each package */ + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, + "perf/x86/intel/uncore:online", + uncore_event_cpu_online, + uncore_event_cpu_offline); + if (ret) + goto err; return 0; err: @@ -1393,9 +1381,7 @@ module_init(intel_uncore_init); static void __exit intel_uncore_exit(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8329f3dc592c..921acaaa1601 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -8,7 +8,6 @@ enum cpuhp_state { CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, - CPUHP_PERF_X86_UNCORE_PREP, CPUHP_PERF_X86_AMD_UNCORE_PREP, CPUHP_PERF_BFIN, CPUHP_PERF_POWER, @@ -85,7 +84,6 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, - CPUHP_AP_PERF_X86_UNCORE_STARTING, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_PERF_X86_AMD_IBS_STARTING, From eeee74a4f6625b77c3e8db0693c2d4546507ba0d Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 31 Jan 2017 10:21:30 +0100 Subject: [PATCH 063/131] drm/atomic: Unconditionally call prepare_fb. Atomic drivers may set properties like rotation on the same fb, which may require a call to prepare_fb even when framebuffer stays identical. Instead of handling all the special cases in the core, let the driver decide when prepare_fb and cleanup_fb are noops. This is a revert of: commit fcc60b413d14dd06ddbd79ec50e83c4fb2a097ba Author: Keith Packard Date: Sat Jun 4 01:16:22 2016 -0700 drm: Don't prepare or cleanup unchanging frame buffers [v3] The original commit mentions that this prevents waiting in i915 on all previous rendering during cursor updates, but there are better ways to fix this. Signed-off-by: Maarten Lankhorst Acked-by: Laurent Pinchart Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/6d82f9b6-9d16-91d1-d176-4a37b09afc44@linux.intel.com (cherry picked from commit 0532be078a207d7dd6ad26ebd0834e258acc4ee7) Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1485854491-27389-2-git-send-email-maarten.lankhorst@linux.intel.com --- drivers/gpu/drm/drm_atomic_helper.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 34f757bcabae..4594477dee00 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1666,9 +1666,6 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev, funcs = plane->helper_private; - if (!drm_atomic_helper_framebuffer_changed(dev, state, plane_state->crtc)) - continue; - if (funcs->prepare_fb) { ret = funcs->prepare_fb(plane, plane_state); if (ret) @@ -1685,9 +1682,6 @@ fail: if (j >= i) continue; - if (!drm_atomic_helper_framebuffer_changed(dev, state, plane_state->crtc)) - continue; - funcs = plane->helper_private; if (funcs->cleanup_fb) @@ -1954,9 +1948,6 @@ void drm_atomic_helper_cleanup_planes(struct drm_device *dev, for_each_plane_in_state(old_state, plane, plane_state, i) { const struct drm_plane_helper_funcs *funcs; - if (!drm_atomic_helper_framebuffer_changed(dev, old_state, plane_state->crtc)) - continue; - funcs = plane->helper_private; if (funcs->cleanup_fb) From e8fe4f4b2b7b93048729538321c681c0cff33b39 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 31 Jan 2017 10:21:31 +0100 Subject: [PATCH 064/131] drm/i915: Track pinned vma in intel_plane_state With atomic plane states we are able to track an allocation right from preparation, during use and through to the final free after being swapped out for a new plane. We can couple the VMA we pin for the framebuffer (and its rotation) to this lifetime and avoid all the clumsy lookups in between. v2: Remove residual vma on plane cleanup (Chris) v3: Add a description for the vma destruction in intel_plane_destroy_state (Maarten) References: https://bugs.freedesktop.org/show_bug.cgi?id=98829 Signed-off-by: Chris Wilson Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/20170116152131.18089-1-chris@chris-wilson.co.uk Acked-by: Joonas Lahtinen (cherry picked from commit be1e341513ca23b0668b7b0f26fa6e2ffc46ba20) Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1485854491-27389-3-git-send-email-maarten.lankhorst@linux.intel.com --- drivers/gpu/drm/i915/i915_drv.h | 16 +-- drivers/gpu/drm/i915/intel_atomic_plane.c | 20 ++++ drivers/gpu/drm/i915/intel_display.c | 125 ++++++++-------------- drivers/gpu/drm/i915/intel_drv.h | 9 +- drivers/gpu/drm/i915/intel_fbc.c | 52 ++++----- drivers/gpu/drm/i915/intel_fbdev.c | 4 +- drivers/gpu/drm/i915/intel_sprite.c | 8 +- 7 files changed, 99 insertions(+), 135 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 69bc3b0c4390..8493e19b563a 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1012,6 +1012,8 @@ struct intel_fbc { struct work_struct underrun_work; struct intel_fbc_state_cache { + struct i915_vma *vma; + struct { unsigned int mode_flags; uint32_t hsw_bdw_pixel_rate; @@ -1025,15 +1027,14 @@ struct intel_fbc { } plane; struct { - u64 ilk_ggtt_offset; uint32_t pixel_format; unsigned int stride; - int fence_reg; - unsigned int tiling_mode; } fb; } state_cache; struct intel_fbc_reg_params { + struct i915_vma *vma; + struct { enum pipe pipe; enum plane plane; @@ -1041,10 +1042,8 @@ struct intel_fbc { } crtc; struct { - u64 ggtt_offset; uint32_t pixel_format; unsigned int stride; - int fence_reg; } fb; int cfb_size; @@ -3168,13 +3167,6 @@ i915_gem_object_to_ggtt(struct drm_i915_gem_object *obj, return i915_gem_obj_to_vma(obj, &to_i915(obj->base.dev)->ggtt.base, view); } -static inline unsigned long -i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o, - const struct i915_ggtt_view *view) -{ - return i915_ggtt_offset(i915_gem_object_to_ggtt(o, view)); -} - /* i915_gem_fence_reg.c */ int __must_check i915_vma_get_fence(struct i915_vma *vma); int __must_check i915_vma_put_fence(struct i915_vma *vma); diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c index dbe9fb41ae53..8d3e515f27ba 100644 --- a/drivers/gpu/drm/i915/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/intel_atomic_plane.c @@ -85,6 +85,8 @@ intel_plane_duplicate_state(struct drm_plane *plane) __drm_atomic_helper_plane_duplicate_state(plane, state); + intel_state->vma = NULL; + return state; } @@ -100,6 +102,24 @@ void intel_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *state) { + struct i915_vma *vma; + + vma = fetch_and_zero(&to_intel_plane_state(state)->vma); + + /* + * FIXME: Normally intel_cleanup_plane_fb handles destruction of vma. + * We currently don't clear all planes during driver unload, so we have + * to be able to unpin vma here for now. + * + * Normally this can only happen during unload when kmscon is disabled + * and userspace doesn't attempt to set a framebuffer at all. + */ + if (vma) { + mutex_lock(&plane->dev->struct_mutex); + intel_unpin_fb_vma(vma); + mutex_unlock(&plane->dev->struct_mutex); + } + drm_atomic_helper_plane_destroy_state(plane, state); } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index f0b9aa7a0483..f1e4a21d4664 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2235,27 +2235,22 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation) i915_vma_pin_fence(vma); } + i915_vma_get(vma); err: intel_runtime_pm_put(dev_priv); return vma; } -void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation) +void intel_unpin_fb_vma(struct i915_vma *vma) { - struct drm_i915_gem_object *obj = intel_fb_obj(fb); - struct i915_ggtt_view view; - struct i915_vma *vma; - - WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex)); - - intel_fill_fb_ggtt_view(&view, fb, rotation); - vma = i915_gem_object_to_ggtt(obj, &view); + lockdep_assert_held(&vma->vm->dev->struct_mutex); if (WARN_ON_ONCE(!vma)) return; i915_vma_unpin_fence(vma); i915_gem_object_unpin_from_display_plane(vma); + i915_vma_put(vma); } static int intel_fb_pitch(const struct drm_framebuffer *fb, int plane, @@ -2750,7 +2745,6 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, struct drm_device *dev = intel_crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); struct drm_crtc *c; - struct intel_crtc *i; struct drm_i915_gem_object *obj; struct drm_plane *primary = intel_crtc->base.primary; struct drm_plane_state *plane_state = primary->state; @@ -2775,20 +2769,20 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, * an fb with another CRTC instead */ for_each_crtc(dev, c) { - i = to_intel_crtc(c); + struct intel_plane_state *state; if (c == &intel_crtc->base) continue; - if (!i->active) + if (!to_intel_crtc(c)->active) continue; - fb = c->primary->fb; - if (!fb) + state = to_intel_plane_state(c->primary->state); + if (!state->vma) continue; - obj = intel_fb_obj(fb); - if (i915_gem_object_ggtt_offset(obj, NULL) == plane_config->base) { + if (intel_plane_ggtt_offset(state) == plane_config->base) { + fb = c->primary->fb; drm_framebuffer_reference(fb); goto valid_fb; } @@ -2809,6 +2803,19 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, return; valid_fb: + mutex_lock(&dev->struct_mutex); + intel_state->vma = + intel_pin_and_fence_fb_obj(fb, primary->state->rotation); + mutex_unlock(&dev->struct_mutex); + if (IS_ERR(intel_state->vma)) { + DRM_ERROR("failed to pin boot fb on pipe %d: %li\n", + intel_crtc->pipe, PTR_ERR(intel_state->vma)); + + intel_state->vma = NULL; + drm_framebuffer_unreference(fb); + return; + } + plane_state->src_x = 0; plane_state->src_y = 0; plane_state->src_w = fb->width << 16; @@ -3104,13 +3111,13 @@ static void i9xx_update_primary_plane(struct drm_plane *primary, I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); if (INTEL_GEN(dev_priv) >= 4) { I915_WRITE(DSPSURF(plane), - intel_fb_gtt_offset(fb, rotation) + + intel_plane_ggtt_offset(plane_state) + intel_crtc->dspaddr_offset); I915_WRITE(DSPTILEOFF(plane), (y << 16) | x); I915_WRITE(DSPLINOFF(plane), linear_offset); } else { I915_WRITE(DSPADDR(plane), - intel_fb_gtt_offset(fb, rotation) + + intel_plane_ggtt_offset(plane_state) + intel_crtc->dspaddr_offset); } POSTING_READ(reg); @@ -3207,7 +3214,7 @@ static void ironlake_update_primary_plane(struct drm_plane *primary, I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); I915_WRITE(DSPSURF(plane), - intel_fb_gtt_offset(fb, rotation) + + intel_plane_ggtt_offset(plane_state) + intel_crtc->dspaddr_offset); if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { I915_WRITE(DSPOFFSET(plane), (y << 16) | x); @@ -3230,23 +3237,6 @@ u32 intel_fb_stride_alignment(const struct drm_i915_private *dev_priv, } } -u32 intel_fb_gtt_offset(struct drm_framebuffer *fb, - unsigned int rotation) -{ - struct drm_i915_gem_object *obj = intel_fb_obj(fb); - struct i915_ggtt_view view; - struct i915_vma *vma; - - intel_fill_fb_ggtt_view(&view, fb, rotation); - - vma = i915_gem_object_to_ggtt(obj, &view); - if (WARN(!vma, "ggtt vma for display object not found! (view=%u)\n", - view.type)) - return -1; - - return i915_ggtt_offset(vma); -} - static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id) { struct drm_device *dev = intel_crtc->base.dev; @@ -3441,7 +3431,7 @@ static void skylake_update_primary_plane(struct drm_plane *plane, } I915_WRITE(PLANE_SURF(pipe, 0), - intel_fb_gtt_offset(fb, rotation) + surf_addr); + intel_plane_ggtt_offset(plane_state) + surf_addr); POSTING_READ(PLANE_SURF(pipe, 0)); } @@ -11536,7 +11526,7 @@ static void intel_unpin_work_fn(struct work_struct *__work) flush_work(&work->mmio_work); mutex_lock(&dev->struct_mutex); - intel_unpin_fb_obj(work->old_fb, primary->state->rotation); + intel_unpin_fb_vma(work->old_vma); i915_gem_object_put(work->pending_flip_obj); mutex_unlock(&dev->struct_mutex); @@ -12246,8 +12236,10 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, goto cleanup_pending; } - work->gtt_offset = intel_fb_gtt_offset(fb, primary->state->rotation); - work->gtt_offset += intel_crtc->dspaddr_offset; + work->old_vma = to_intel_plane_state(primary->state)->vma; + to_intel_plane_state(primary->state)->vma = vma; + + work->gtt_offset = i915_ggtt_offset(vma) + intel_crtc->dspaddr_offset; work->rotation = crtc->primary->state->rotation; /* @@ -12301,7 +12293,8 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, cleanup_request: i915_add_request_no_flush(request); cleanup_unpin: - intel_unpin_fb_obj(fb, crtc->primary->state->rotation); + to_intel_plane_state(primary->state)->vma = work->old_vma; + intel_unpin_fb_vma(vma); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); unlock: @@ -14794,6 +14787,8 @@ intel_prepare_plane_fb(struct drm_plane *plane, DRM_DEBUG_KMS("failed to pin object\n"); return PTR_ERR(vma); } + + to_intel_plane_state(new_state)->vma = vma; } return 0; @@ -14812,19 +14807,12 @@ void intel_cleanup_plane_fb(struct drm_plane *plane, struct drm_plane_state *old_state) { - struct drm_i915_private *dev_priv = to_i915(plane->dev); - struct intel_plane_state *old_intel_state; - struct drm_i915_gem_object *old_obj = intel_fb_obj(old_state->fb); - struct drm_i915_gem_object *obj = intel_fb_obj(plane->state->fb); + struct i915_vma *vma; - old_intel_state = to_intel_plane_state(old_state); - - if (!obj && !old_obj) - return; - - if (old_obj && (plane->type != DRM_PLANE_TYPE_CURSOR || - !INTEL_INFO(dev_priv)->cursor_needs_physical)) - intel_unpin_fb_obj(old_state->fb, old_state->rotation); + /* Should only be called after a successful intel_prepare_plane_fb()! */ + vma = fetch_and_zero(&to_intel_plane_state(old_state)->vma); + if (vma) + intel_unpin_fb_vma(vma); } int @@ -15166,7 +15154,7 @@ intel_update_cursor_plane(struct drm_plane *plane, if (!obj) addr = 0; else if (!INTEL_INFO(dev_priv)->cursor_needs_physical) - addr = i915_gem_object_ggtt_offset(obj, NULL); + addr = intel_plane_ggtt_offset(state); else addr = obj->phys_handle->busaddr; @@ -17066,41 +17054,12 @@ void intel_display_resume(struct drm_device *dev) void intel_modeset_gem_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); - struct drm_crtc *c; - struct drm_i915_gem_object *obj; intel_init_gt_powersave(dev_priv); intel_modeset_init_hw(dev); intel_setup_overlay(dev_priv); - - /* - * Make sure any fbs we allocated at startup are properly - * pinned & fenced. When we do the allocation it's too early - * for this. - */ - for_each_crtc(dev, c) { - struct i915_vma *vma; - - obj = intel_fb_obj(c->primary->fb); - if (obj == NULL) - continue; - - mutex_lock(&dev->struct_mutex); - vma = intel_pin_and_fence_fb_obj(c->primary->fb, - c->primary->state->rotation); - mutex_unlock(&dev->struct_mutex); - if (IS_ERR(vma)) { - DRM_ERROR("failed to pin boot fb on pipe %d\n", - to_intel_crtc(c)->pipe); - drm_framebuffer_unreference(c->primary->fb); - c->primary->fb = NULL; - c->primary->crtc = c->primary->state->crtc = NULL; - update_state_fb(c->primary); - c->state->plane_mask &= ~(1 << drm_plane_index(c->primary)); - } - } } int intel_connector_register(struct drm_connector *connector) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index cd72ae171eeb..03a2112004f9 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -377,6 +377,7 @@ struct intel_atomic_state { struct intel_plane_state { struct drm_plane_state base; struct drm_rect clip; + struct i915_vma *vma; struct { u32 offset; @@ -1046,6 +1047,7 @@ struct intel_flip_work { struct work_struct mmio_work; struct drm_crtc *crtc; + struct i915_vma *old_vma; struct drm_framebuffer *old_fb; struct drm_i915_gem_object *pending_flip_obj; struct drm_pending_vblank_event *event; @@ -1273,7 +1275,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector, struct drm_modeset_acquire_ctx *ctx); struct i915_vma * intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation); -void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation); +void intel_unpin_fb_vma(struct i915_vma *vma); struct drm_framebuffer * __intel_framebuffer_create(struct drm_device *dev, struct drm_mode_fb_cmd2 *mode_cmd, @@ -1362,7 +1364,10 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode, int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state); int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); -u32 intel_fb_gtt_offset(struct drm_framebuffer *fb, unsigned int rotation); +static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *state) +{ + return i915_ggtt_offset(state->vma); +} u32 skl_plane_ctl_format(uint32_t pixel_format); u32 skl_plane_ctl_tiling(uint64_t fb_modifier); diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 62f215b12eb5..f3a1d6a5cabe 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -173,7 +173,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv) if (IS_I945GM(dev_priv)) fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */ fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT; - fbc_ctl |= params->fb.fence_reg; + fbc_ctl |= params->vma->fence->id; I915_WRITE(FBC_CONTROL, fbc_ctl); } @@ -193,8 +193,8 @@ static void g4x_fbc_activate(struct drm_i915_private *dev_priv) else dpfc_ctl |= DPFC_CTL_LIMIT_1X; - if (params->fb.fence_reg != I915_FENCE_REG_NONE) { - dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fb.fence_reg; + if (params->vma->fence) { + dpfc_ctl |= DPFC_CTL_FENCE_EN | params->vma->fence->id; I915_WRITE(DPFC_FENCE_YOFF, params->crtc.fence_y_offset); } else { I915_WRITE(DPFC_FENCE_YOFF, 0); @@ -251,13 +251,14 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv) break; } - if (params->fb.fence_reg != I915_FENCE_REG_NONE) { + if (params->vma->fence) { dpfc_ctl |= DPFC_CTL_FENCE_EN; if (IS_GEN5(dev_priv)) - dpfc_ctl |= params->fb.fence_reg; + dpfc_ctl |= params->vma->fence->id; if (IS_GEN6(dev_priv)) { I915_WRITE(SNB_DPFC_CTL_SA, - SNB_CPU_FENCE_ENABLE | params->fb.fence_reg); + SNB_CPU_FENCE_ENABLE | + params->vma->fence->id); I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset); } @@ -269,7 +270,8 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv) } I915_WRITE(ILK_DPFC_FENCE_YOFF, params->crtc.fence_y_offset); - I915_WRITE(ILK_FBC_RT_BASE, params->fb.ggtt_offset | ILK_FBC_RT_VALID); + I915_WRITE(ILK_FBC_RT_BASE, + i915_ggtt_offset(params->vma) | ILK_FBC_RT_VALID); /* enable it... */ I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); @@ -319,10 +321,11 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv) break; } - if (params->fb.fence_reg != I915_FENCE_REG_NONE) { + if (params->vma->fence) { dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN; I915_WRITE(SNB_DPFC_CTL_SA, - SNB_CPU_FENCE_ENABLE | params->fb.fence_reg); + SNB_CPU_FENCE_ENABLE | + params->vma->fence->id); I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset); } else { I915_WRITE(SNB_DPFC_CTL_SA,0); @@ -727,14 +730,6 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) return effective_w <= max_w && effective_h <= max_h; } -/* XXX replace me when we have VMA tracking for intel_plane_state */ -static int get_fence_id(struct drm_framebuffer *fb) -{ - struct i915_vma *vma = i915_gem_object_to_ggtt(intel_fb_obj(fb), NULL); - - return vma && vma->fence ? vma->fence->id : I915_FENCE_REG_NONE; -} - static void intel_fbc_update_state_cache(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state) @@ -743,7 +738,8 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc, struct intel_fbc *fbc = &dev_priv->fbc; struct intel_fbc_state_cache *cache = &fbc->state_cache; struct drm_framebuffer *fb = plane_state->base.fb; - struct drm_i915_gem_object *obj; + + cache->vma = NULL; cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags; if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) @@ -758,16 +754,10 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc, if (!cache->plane.visible) return; - obj = intel_fb_obj(fb); - - /* FIXME: We lack the proper locking here, so only run this on the - * platforms that need. */ - if (IS_GEN(dev_priv, 5, 6)) - cache->fb.ilk_ggtt_offset = i915_gem_object_ggtt_offset(obj, NULL); cache->fb.pixel_format = fb->pixel_format; cache->fb.stride = fb->pitches[0]; - cache->fb.fence_reg = get_fence_id(fb); - cache->fb.tiling_mode = i915_gem_object_get_tiling(obj); + + cache->vma = plane_state->vma; } static bool intel_fbc_can_activate(struct intel_crtc *crtc) @@ -784,7 +774,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) return false; } - if (!cache->plane.visible) { + if (!cache->vma) { fbc->no_fbc_reason = "primary plane not visible"; return false; } @@ -807,8 +797,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) * so have no fence associated with it) due to aperture constaints * at the time of pinning. */ - if (cache->fb.tiling_mode != I915_TILING_X || - cache->fb.fence_reg == I915_FENCE_REG_NONE) { + if (!cache->vma->fence) { fbc->no_fbc_reason = "framebuffer not tiled or fenced"; return false; } @@ -888,17 +877,16 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc, * zero. */ memset(params, 0, sizeof(*params)); + params->vma = cache->vma; + params->crtc.pipe = crtc->pipe; params->crtc.plane = crtc->plane; params->crtc.fence_y_offset = get_crtc_fence_y_offset(crtc); params->fb.pixel_format = cache->fb.pixel_format; params->fb.stride = cache->fb.stride; - params->fb.fence_reg = cache->fb.fence_reg; params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache); - - params->fb.ggtt_offset = cache->fb.ilk_ggtt_offset; } static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1, diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 8cf2d80f2254..f4a8c4fc57c4 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -284,7 +284,7 @@ static int intelfb_create(struct drm_fb_helper *helper, out_destroy_fbi: drm_fb_helper_release_fbi(helper); out_unpin: - intel_unpin_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0); + intel_unpin_fb_vma(vma); out_unlock: mutex_unlock(&dev->struct_mutex); return ret; @@ -549,7 +549,7 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev) if (ifbdev->fb) { mutex_lock(&ifbdev->helper.dev->struct_mutex); - intel_unpin_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0); + intel_unpin_fb_vma(ifbdev->vma); mutex_unlock(&ifbdev->helper.dev->struct_mutex); drm_framebuffer_remove(&ifbdev->fb->base); diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 8f131a08d440..242a73e66d82 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -273,7 +273,7 @@ skl_update_plane(struct drm_plane *drm_plane, I915_WRITE(PLANE_CTL(pipe, plane), plane_ctl); I915_WRITE(PLANE_SURF(pipe, plane), - intel_fb_gtt_offset(fb, rotation) + surf_addr); + intel_plane_ggtt_offset(plane_state) + surf_addr); POSTING_READ(PLANE_SURF(pipe, plane)); } @@ -458,7 +458,7 @@ vlv_update_plane(struct drm_plane *dplane, I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w); I915_WRITE(SPCNTR(pipe, plane), sprctl); I915_WRITE(SPSURF(pipe, plane), - intel_fb_gtt_offset(fb, rotation) + sprsurf_offset); + intel_plane_ggtt_offset(plane_state) + sprsurf_offset); POSTING_READ(SPSURF(pipe, plane)); } @@ -594,7 +594,7 @@ ivb_update_plane(struct drm_plane *plane, I915_WRITE(SPRSCALE(pipe), sprscale); I915_WRITE(SPRCTL(pipe), sprctl); I915_WRITE(SPRSURF(pipe), - intel_fb_gtt_offset(fb, rotation) + sprsurf_offset); + intel_plane_ggtt_offset(plane_state) + sprsurf_offset); POSTING_READ(SPRSURF(pipe)); } @@ -721,7 +721,7 @@ ilk_update_plane(struct drm_plane *plane, I915_WRITE(DVSSCALE(pipe), dvsscale); I915_WRITE(DVSCNTR(pipe), dvscntr); I915_WRITE(DVSSURF(pipe), - intel_fb_gtt_offset(fb, rotation) + dvssurf_offset); + intel_plane_ggtt_offset(plane_state) + dvssurf_offset); POSTING_READ(DVSSURF(pipe)); } From 2da64d20a0b20046d688e44f4033efd09157e29d Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Wed, 1 Feb 2017 14:26:16 +1100 Subject: [PATCH 065/131] vfio/spapr: Fix missing mutex unlock when creating a window Commit d9c728949ddc ("vfio/spapr: Postpone default window creation") added an additional exit to the VFIO_IOMMU_SPAPR_TCE_CREATE case and made it possible to return from tce_iommu_ioctl() without unlocking container->lock; this fixes the issue. Fixes: d9c728949ddc ("vfio/spapr: Postpone default window creation") Signed-off-by: Alexey Kardashevskiy Reviewed-by: David Gibson Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_spapr_tce.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 128d10282d16..7690e5bf3cf1 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -1123,12 +1123,11 @@ static long tce_iommu_ioctl(void *iommu_data, mutex_lock(&container->lock); ret = tce_iommu_create_default_window(container); - if (ret) - return ret; - - ret = tce_iommu_create_window(container, create.page_shift, - create.window_size, create.levels, - &create.start_addr); + if (!ret) + ret = tce_iommu_create_window(container, + create.page_shift, + create.window_size, create.levels, + &create.start_addr); mutex_unlock(&container->lock); From c8f325a59cfc718d13a50fbc746ed9b415c25e92 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 1 Feb 2017 17:45:02 +0000 Subject: [PATCH 066/131] efi/fdt: Avoid FDT manipulation after ExitBootServices() Some AArch64 UEFI implementations disable the MMU in ExitBootServices(), after which unaligned accesses to RAM are no longer supported. Commit: abfb7b686a3e ("efi/libstub/arm*: Pass latest memory map to the kernel") fixed an issue in the memory map handling of the stub FDT code, but inadvertently created an issue with such firmware, by moving some of the FDT manipulation to after the invocation of ExitBootServices(). Given that the stub's libfdt implementation uses the ordinary, accelerated string functions, which rely on hardware handling of unaligned accesses, manipulating the FDT with the MMU off may result in alignment faults. So fix the situation by moving the update_fdt_memmap() call into the callback function invoked by efi_exit_boot_services() right before it calls the ExitBootServices() UEFI service (which is arguably a better place for it anyway) Note that disabling the MMU in ExitBootServices() is not compliant with the UEFI spec, and carries great risk due to the fact that switching from cached to uncached memory accesses halfway through compiler generated code (i.e., involving a stack) can never be done in a way that is architecturally safe. Fixes: abfb7b686a3e ("efi/libstub/arm*: Pass latest memory map to the kernel") Signed-off-by: Ard Biesheuvel Tested-by: Riku Voipio Cc: Cc: mark.rutland@arm.com Cc: linux-efi@vger.kernel.org Cc: matt@codeblueprint.co.uk Cc: leif.lindholm@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1485971102-23330-2-git-send-email-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- drivers/firmware/efi/libstub/fdt.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 921dfa047202..260c4b4b492e 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -187,6 +187,7 @@ static efi_status_t update_fdt_memmap(void *fdt, struct efi_boot_memmap *map) struct exit_boot_struct { efi_memory_desc_t *runtime_map; int *runtime_entry_count; + void *new_fdt_addr; }; static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, @@ -202,7 +203,7 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, efi_get_virtmap(*map->map, *map->map_size, *map->desc_size, p->runtime_map, p->runtime_entry_count); - return EFI_SUCCESS; + return update_fdt_memmap(p->new_fdt_addr, map); } /* @@ -300,22 +301,13 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, priv.runtime_map = runtime_map; priv.runtime_entry_count = &runtime_entry_count; + priv.new_fdt_addr = (void *)*new_fdt_addr; status = efi_exit_boot_services(sys_table, handle, &map, &priv, exit_boot_func); if (status == EFI_SUCCESS) { efi_set_virtual_address_map_t *svam; - status = update_fdt_memmap((void *)*new_fdt_addr, &map); - if (status != EFI_SUCCESS) { - /* - * The kernel won't get far without the memory map, but - * may still be able to print something meaningful so - * return success here. - */ - return EFI_SUCCESS; - } - /* Install the new virtual address map */ svam = sys_table->runtime->set_virtual_address_map; status = svam(runtime_entry_count * desc_size, desc_size, From 3484ecbe0e9deb94afb0b9b6172d77e98eb72b94 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Thu, 22 Dec 2016 15:00:12 +0000 Subject: [PATCH 067/131] crypto: qat - fix bar discovery for c62x Some accelerators of the c62x series have only two bars. This patch skips BAR0 if the accelerator does not have it. Cc: Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- drivers/crypto/qat/qat_c62x/adf_drv.c | 2 +- drivers/crypto/qat/qat_common/adf_accel_devices.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c index bc5cbc193aae..5b2d78a5b5aa 100644 --- a/drivers/crypto/qat/qat_c62x/adf_drv.c +++ b/drivers/crypto/qat/qat_c62x/adf_drv.c @@ -233,7 +233,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) &hw_data->accel_capabilities_mask); /* Find and map all the device's BARS */ - i = 0; + i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, ADF_PCI_MAX_BARS * 2) { diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h index e8822536530b..33f0a6251e38 100644 --- a/drivers/crypto/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h @@ -69,6 +69,7 @@ #define ADF_ERRSOU5 (0x3A000 + 0xD8) #define ADF_DEVICE_FUSECTL_OFFSET 0x40 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C +#define ADF_DEVICE_FUSECTL_MASK 0x80000000 #define ADF_PCI_MAX_BARS 3 #define ADF_DEVICE_NAME_LENGTH 32 #define ADF_ETR_MAX_RINGS_PER_BANK 16 From 685ce0626840e2673fe64ea8807684f7324fec5f Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Thu, 22 Dec 2016 15:00:24 +0000 Subject: [PATCH 068/131] crypto: qat - zero esram only for DH85x devices Zero embedded ram in DH85x devices. This is not needed for newer generations as it is done by HW. Cc: Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- drivers/crypto/qat/qat_common/qat_hal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c index 1e480f140663..8c4fd255a601 100644 --- a/drivers/crypto/qat/qat_common/qat_hal.c +++ b/drivers/crypto/qat/qat_common/qat_hal.c @@ -456,7 +456,7 @@ static int qat_hal_init_esram(struct icp_qat_fw_loader_handle *handle) unsigned int csr_val; int times = 30; - if (handle->pci_dev->device == ADF_C3XXX_PCI_DEVICE_ID) + if (handle->pci_dev->device != ADF_DH895XCC_PCI_DEVICE_ID) return 0; csr_val = ADF_CSR_RD(csr_addr, 0); @@ -716,7 +716,7 @@ int qat_hal_init(struct adf_accel_dev *accel_dev) (void __iomem *)((uintptr_t)handle->hal_cap_ae_xfer_csr_addr_v + LOCAL_TO_XFER_REG_OFFSET); handle->pci_dev = pci_info->pci_dev; - if (handle->pci_dev->device != ADF_C3XXX_PCI_DEVICE_ID) { + if (handle->pci_dev->device == ADF_DH895XCC_PCI_DEVICE_ID) { sram_bar = &pci_info->pci_bars[hw_data->get_sram_bar_id(hw_data)]; handle->hal_sram_addr_v = sram_bar->virt_addr; From 26a346f23c5291d1d9521e72763103daf2c6f0d1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 1 Feb 2017 17:57:56 +0100 Subject: [PATCH 069/131] tracing/kprobes: Fix __init annotation clang complains about "__init" being attached to a struct name: kernel/trace/trace_kprobe.c:1375:15: error: '__section__' attribute only applies to functions and global variables The intention must have been to mark the function as __init instead of the type, so move the attribute there. Link: http://lkml.kernel.org/r/20170201165826.2625888-1-arnd@arndb.de Fixes: f18f97ac43d7 ("tracing/kprobes: Add a helper method to return number of probe hits") Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_kprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index a133ecd741e4..7ad9e53ad174 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1372,7 +1372,7 @@ kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6) return a1 + a2 + a3 + a4 + a5 + a6; } -static struct __init trace_event_file * +static __init struct trace_event_file * find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr) { struct trace_event_file *file; From 57bcd0a6364cd4eaa362d7ff1777e88ddf501602 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 27 Jan 2017 10:31:52 -0500 Subject: [PATCH 070/131] drm/amdgpu/si: fix crash on headless asics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Missing check for crtcs present. Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=193341 https://bugs.freedesktop.org/show_bug.cgi?id=99387 Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index e2b0b1646f99..0635829b18cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -254,6 +254,9 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev) } WREG32(mmHDP_REG_COHERENCY_FLUSH_CNTL, 0); + if (adev->mode_info.num_crtc) + amdgpu_display_set_vga_render_state(adev, false); + gmc_v6_0_mc_stop(adev, &save); if (gmc_v6_0_wait_for_idle((void *)adev)) { @@ -283,7 +286,6 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev) dev_warn(adev->dev, "Wait for MC idle timedout !\n"); } gmc_v6_0_mc_resume(adev, &save); - amdgpu_display_set_vga_render_state(adev, false); } static int gmc_v6_0_mc_init(struct amdgpu_device *adev) From 51964e9e12d0a054002a1a0d1dec4f661c7aaf28 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Mon, 30 Jan 2017 12:06:35 +0900 Subject: [PATCH 071/131] drm/radeon: Fix vram_size/visible values in DRM_RADEON_GEM_INFO ioctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vram_size is supposed to be the total amount of VRAM that can be used by userspace, which corresponds to the TTM VRAM manager size (which is normally the full amount of VRAM, but can be just the visible VRAM when DMA can't be used for BO migration for some reason). The above was incorrectly used for vram_visible before, resulting in generally too large values being reported. Reviewed-by: Christian König Reviewed-by: Nicolai Hähnle Reviewed-by: Alex Deucher Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_drv.c | 3 ++- drivers/gpu/drm/radeon/radeon_gem.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index e0c143b865f3..30bd4a6a9d46 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -97,9 +97,10 @@ * 2.46.0 - Add PFP_SYNC_ME support on evergreen * 2.47.0 - Add UVD_NO_OP register support * 2.48.0 - TA_CS_BC_BASE_ADDR allowed on SI + * 2.49.0 - DRM_RADEON_GEM_INFO ioctl returns correct vram_size/visible values */ #define KMS_DRIVER_MAJOR 2 -#define KMS_DRIVER_MINOR 48 +#define KMS_DRIVER_MINOR 49 #define KMS_DRIVER_PATCHLEVEL 0 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags); int radeon_driver_unload_kms(struct drm_device *dev); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 0bcffd8a7bd3..96683f5b2b1b 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -220,8 +220,8 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data, man = &rdev->mman.bdev.man[TTM_PL_VRAM]; - args->vram_size = rdev->mc.real_vram_size; - args->vram_visible = (u64)man->size << PAGE_SHIFT; + args->vram_size = (u64)man->size << PAGE_SHIFT; + args->vram_visible = rdev->mc.visible_vram_size; args->vram_visible -= rdev->vram_pin_size; args->gart_size = rdev->mc.gtt_size; args->gart_size -= rdev->gart_pin_size; From f32b20e89e82c9ff1825fc5c5d69753ff5558ccd Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 31 Jan 2017 22:35:32 -0800 Subject: [PATCH 072/131] mlx4: Fix memory leak after mlx4_en_update_priv() In mlx4_en_update_priv(), dst->tx_ring[t] and dst->tx_cq[t] are over-written by src->tx_ring[t] and src->tx_cq[t] without first calling kfree. One of the reproducible code paths is by doing 'ethtool -L'. The fix is to do the kfree in mlx4_en_free_resources(). Here is the kmemleak report: unreferenced object 0xffff880841211800 (size 2048): comm "ethtool", pid 3096, jiffies 4294716940 (age 528.353s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmemleak_alloc+0x28/0x50 [] kmem_cache_alloc_trace+0x103/0x260 [] mlx4_en_try_alloc_resources+0x118/0x1a0 [] mlx4_en_set_ringparam+0x169/0x210 [] dev_ethtool+0xae5/0x2190 [] dev_ioctl+0x168/0x6f0 [] sock_do_ioctl+0x42/0x50 [] sock_ioctl+0x21b/0x2d0 [] do_vfs_ioctl+0x93/0x6a0 [] SyS_ioctl+0x79/0x90 [] entry_SYSCALL_64_fastpath+0x18/0xad [] 0xffffffffffffffff unreferenced object 0xffff880841213000 (size 2048): comm "ethtool", pid 3096, jiffies 4294716940 (age 528.353s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmemleak_alloc+0x28/0x50 [] kmem_cache_alloc_trace+0x103/0x260 [] mlx4_en_try_alloc_resources+0x13b/0x1a0 [] mlx4_en_set_ringparam+0x169/0x210 [] dev_ethtool+0xae5/0x2190 [] dev_ioctl+0x168/0x6f0 [] sock_do_ioctl+0x42/0x50 [] sock_ioctl+0x21b/0x2d0 [] do_vfs_ioctl+0x93/0x6a0 [] SyS_ioctl+0x79/0x90 [] entry_SYSCALL_64_fastpath+0x18/0xad [] 0xffffffffffffffff (gdb) list *mlx4_en_try_alloc_resources+0x118 0xffffffff8170e0a8 is in mlx4_en_try_alloc_resources (drivers/net/ethernet/mellanox/mlx4/en_netdev.c:2145). 2140 if (!dst->tx_ring_num[t]) 2141 continue; 2142 2143 dst->tx_ring[t] = kzalloc(sizeof(struct mlx4_en_tx_ring *) * 2144 MAX_TX_RINGS, GFP_KERNEL); 2145 if (!dst->tx_ring[t]) 2146 goto err_free_tx; 2147 2148 dst->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) * 2149 MAX_TX_RINGS, GFP_KERNEL); (gdb) list *mlx4_en_try_alloc_resources+0x13b 0xffffffff8170e0cb is in mlx4_en_try_alloc_resources (drivers/net/ethernet/mellanox/mlx4/en_netdev.c:2150). 2145 if (!dst->tx_ring[t]) 2146 goto err_free_tx; 2147 2148 dst->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) * 2149 MAX_TX_RINGS, GFP_KERNEL); 2150 if (!dst->tx_cq[t]) { 2151 kfree(dst->tx_ring[t]); 2152 goto err_free_tx; 2153 } 2154 } Fixes: ec25bc04ed8e ("net/mlx4_en: Add resilience in low memory systems") Cc: Eugenia Emantayev Cc: Saeed Mahameed Cc: Tariq Toukan Signed-off-by: Martin KaFai Lau Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 761f8b12399c..3abcead208d2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2042,6 +2042,8 @@ static void mlx4_en_free_resources(struct mlx4_en_priv *priv) if (priv->tx_cq[t] && priv->tx_cq[t][i]) mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]); } + kfree(priv->tx_ring[t]); + kfree(priv->tx_cq[t]); } for (i = 0; i < priv->rx_ring_num; i++) { @@ -2214,7 +2216,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - int t; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2248,11 +2249,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mlx4_en_free_resources(priv); mutex_unlock(&mdev->state_lock); - for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { - kfree(priv->tx_ring[t]); - kfree(priv->tx_cq[t]); - } - free_netdev(dev); } From 770f82253dbd7e6892a88018f2f6cd395f48d214 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 31 Jan 2017 22:35:33 -0800 Subject: [PATCH 073/131] mlx4: xdp_prog becomes inactive after ethtool '-L' or '-G' After calling mlx4_en_try_alloc_resources (e.g. by changing the number of rx-queues with ethtool -L), the existing xdp_prog becomes inactive. The bug is that the xdp_prog ptr has not been carried over from the old rx-queues to the new rx-queues Fixes: 47a38e155037 ("net/mlx4_en: add support for fast rx drop bpf program") Cc: Brenden Blanco Cc: Saeed Mahameed Cc: Tariq Toukan Signed-off-by: Martin KaFai Lau Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx4/en_ethtool.c | 4 +-- .../net/ethernet/mellanox/mlx4/en_netdev.c | 27 ++++++++++++++++--- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 ++- 3 files changed, 27 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d5a9372ed84d..9aa422691954 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1099,7 +1099,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev, memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); new_prof.tx_ring_size = tx_size; new_prof.rx_ring_size = rx_size; - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; @@ -1774,7 +1774,7 @@ static int mlx4_en_set_channels(struct net_device *dev, new_prof.tx_ring_num[TX_XDP] = xdp_count; new_prof.rx_ring_num = channel->rx_count; - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 3abcead208d2..3b4961a8e8e4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2186,9 +2186,11 @@ static void mlx4_en_update_priv(struct mlx4_en_priv *dst, int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, struct mlx4_en_priv *tmp, - struct mlx4_en_port_profile *prof) + struct mlx4_en_port_profile *prof, + bool carry_xdp_prog) { - int t; + struct bpf_prog *xdp_prog; + int i, t; mlx4_en_copy_priv(tmp, priv, prof); @@ -2202,6 +2204,23 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, } return -ENOMEM; } + + /* All rx_rings has the same xdp_prog. Pick the first one. */ + xdp_prog = rcu_dereference_protected( + priv->rx_ring[0]->xdp_prog, + lockdep_is_held(&priv->mdev->state_lock)); + + if (xdp_prog && carry_xdp_prog) { + xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num); + if (IS_ERR(xdp_prog)) { + mlx4_en_free_resources(tmp); + return PTR_ERR(xdp_prog); + } + for (i = 0; i < tmp->rx_ring_num; i++) + rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog, + xdp_prog); + } + return 0; } @@ -2751,7 +2770,7 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n"); } - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, false); if (err) { if (prog) bpf_prog_sub(prog, priv->rx_ring_num - 1); @@ -3495,7 +3514,7 @@ int mlx4_en_reset_config(struct net_device *dev, memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config)); - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index ba1c6cd0cc79..cec59bc264c9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -679,7 +679,8 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, struct mlx4_en_priv *tmp, - struct mlx4_en_port_profile *prof); + struct mlx4_en_port_profile *prof, + bool carry_xdp_prog); void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, struct mlx4_en_priv *tmp); From cafe8df8b9bc9aa3dffa827c1a6757c6cd36f657 Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Tue, 31 Jan 2017 18:46:43 -0800 Subject: [PATCH 074/131] net: phy: Fix lack of reference count on PHY driver There is currently no reference count being held on the PHY driver, which makes it possible to remove the PHY driver module while the PHY state machine is running and polling the PHY. This could cause crashes similar to this one to show up: [ 43.361162] BUG: unable to handle kernel NULL pointer dereference at 0000000000000140 [ 43.361162] IP: phy_state_machine+0x32/0x490 [ 43.361162] PGD 59dc067 [ 43.361162] PUD 0 [ 43.361162] [ 43.361162] Oops: 0000 [#1] SMP [ 43.361162] Modules linked in: dsa_loop [last unloaded: broadcom] [ 43.361162] CPU: 0 PID: 1299 Comm: kworker/0:3 Not tainted 4.10.0-rc5+ #415 [ 43.361162] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu2 04/01/2014 [ 43.361162] Workqueue: events_power_efficient phy_state_machine [ 43.361162] task: ffff880006782b80 task.stack: ffffc90000184000 [ 43.361162] RIP: 0010:phy_state_machine+0x32/0x490 [ 43.361162] RSP: 0018:ffffc90000187e18 EFLAGS: 00000246 [ 43.361162] RAX: 0000000000000000 RBX: ffff8800059e53c0 RCX: ffff880006a15c60 [ 43.361162] RDX: ffff880006782b80 RSI: 0000000000000000 RDI: ffff8800059e5428 [ 43.361162] RBP: ffffc90000187e48 R08: ffff880006a15c40 R09: 0000000000000000 [ 43.361162] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800059e5428 [ 43.361162] R13: ffff8800059e5000 R14: 0000000000000000 R15: ffff880006a15c40 [ 43.361162] FS: 0000000000000000(0000) GS:ffff880006a00000(0000) knlGS:0000000000000000 [ 43.361162] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 43.361162] CR2: 0000000000000140 CR3: 0000000005979000 CR4: 00000000000006f0 [ 43.361162] Call Trace: [ 43.361162] process_one_work+0x1b4/0x3e0 [ 43.361162] worker_thread+0x43/0x4d0 [ 43.361162] ? __schedule+0x17f/0x4e0 [ 43.361162] kthread+0xf7/0x130 [ 43.361162] ? process_one_work+0x3e0/0x3e0 [ 43.361162] ? kthread_create_on_node+0x40/0x40 [ 43.361162] ret_from_fork+0x29/0x40 [ 43.361162] Code: 56 41 55 41 54 4c 8d 67 68 53 4c 8d af 40 fc ff ff 48 89 fb 4c 89 e7 48 83 ec 08 e8 c9 9d 27 00 48 8b 83 60 ff ff ff 44 8b 73 98 <48> 8b 90 40 01 00 00 44 89 f0 48 85 d2 74 08 4c 89 ef ff d2 8b Keep references on the PHY driver module right before we are going to utilize it in phy_attach_direct(), and conversely when we don't use it anymore in phy_detach(). Signed-off-by: Mao Wenan [florian: rebase, rework commit message] Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 92b08383cafa..0d8f4d3847f6 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -920,6 +920,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, return -EIO; } + if (!try_module_get(d->driver->owner)) { + dev_err(&dev->dev, "failed to get the device driver module\n"); + return -EIO; + } + get_device(d); /* Assume that if there is no driver, that it doesn't @@ -977,6 +982,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, error: phy_detach(phydev); put_device(d); + module_put(d->driver->owner); if (ndev_owner != bus->owner) module_put(bus->owner); return err; @@ -1059,6 +1065,7 @@ void phy_detach(struct phy_device *phydev) bus = phydev->mdio.bus; put_device(&phydev->mdio.dev); + module_put(phydev->mdio.dev.driver->owner); if (ndev_owner != bus->owner) module_put(bus->owner); } From 94e1dab1c94715e18bb0bada503de3f3d7593076 Mon Sep 17 00:00:00 2001 From: Harsh Jain Date: Tue, 24 Jan 2017 10:34:32 +0530 Subject: [PATCH 075/131] crypto: chcr - Fix panic on dma_unmap_sg Save DMA mapped sg list addresses to request context buffer. Signed-off-by: Atul Gupta Signed-off-by: Herbert Xu --- drivers/crypto/chelsio/chcr_algo.c | 49 +++++++++++++++------------- drivers/crypto/chelsio/chcr_crypto.h | 3 ++ 2 files changed, 29 insertions(+), 23 deletions(-) diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index 2ed1e24b44a8..d29c2b45d3ab 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -158,7 +158,7 @@ int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input, case CRYPTO_ALG_TYPE_AEAD: ctx_req.req.aead_req = (struct aead_request *)req; ctx_req.ctx.reqctx = aead_request_ctx(ctx_req.req.aead_req); - dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.req.aead_req->dst, + dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.ctx.reqctx->dst, ctx_req.ctx.reqctx->dst_nents, DMA_FROM_DEVICE); if (ctx_req.ctx.reqctx->skb) { kfree_skb(ctx_req.ctx.reqctx->skb); @@ -1362,8 +1362,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, struct chcr_wr *chcr_req; struct cpl_rx_phys_dsgl *phys_cpl; struct phys_sge_parm sg_param; - struct scatterlist *src, *dst; - struct scatterlist src_sg[2], dst_sg[2]; + struct scatterlist *src; unsigned int frags = 0, transhdr_len; unsigned int ivsize = crypto_aead_ivsize(tfm), dst_size = 0; unsigned int kctx_len = 0; @@ -1383,19 +1382,21 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0) goto err; - src = scatterwalk_ffwd(src_sg, req->src, req->assoclen); - dst = src; + src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen); + reqctx->dst = src; + if (req->src != req->dst) { err = chcr_copy_assoc(req, aeadctx); if (err) return ERR_PTR(err); - dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen); + reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst, + req->assoclen); } if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_NULL) { null = 1; assoclen = 0; } - reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen + + reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen + (op_type ? -authsize : authsize)); if (reqctx->dst_nents <= 0) { pr_err("AUTHENC:Invalid Destination sg entries\n"); @@ -1460,7 +1461,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; sg_param.align = 0; - if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst, + if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst, &sg_param)) goto dstmap_fail; @@ -1711,8 +1712,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, struct chcr_wr *chcr_req; struct cpl_rx_phys_dsgl *phys_cpl; struct phys_sge_parm sg_param; - struct scatterlist *src, *dst; - struct scatterlist src_sg[2], dst_sg[2]; + struct scatterlist *src; unsigned int frags = 0, transhdr_len, ivsize = AES_BLOCK_SIZE; unsigned int dst_size = 0, kctx_len; unsigned int sub_type; @@ -1728,17 +1728,19 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0) goto err; sub_type = get_aead_subtype(tfm); - src = scatterwalk_ffwd(src_sg, req->src, req->assoclen); - dst = src; + src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen); + reqctx->dst = src; + if (req->src != req->dst) { err = chcr_copy_assoc(req, aeadctx); if (err) { pr_err("AAD copy to destination buffer fails\n"); return ERR_PTR(err); } - dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen); + reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst, + req->assoclen); } - reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen + + reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen + (op_type ? -authsize : authsize)); if (reqctx->dst_nents <= 0) { pr_err("CCM:Invalid Destination sg entries\n"); @@ -1777,7 +1779,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; sg_param.align = 0; - if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst, + if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst, &sg_param)) goto dstmap_fail; @@ -1809,8 +1811,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, struct chcr_wr *chcr_req; struct cpl_rx_phys_dsgl *phys_cpl; struct phys_sge_parm sg_param; - struct scatterlist *src, *dst; - struct scatterlist src_sg[2], dst_sg[2]; + struct scatterlist *src; unsigned int frags = 0, transhdr_len; unsigned int ivsize = AES_BLOCK_SIZE; unsigned int dst_size = 0, kctx_len; @@ -1832,13 +1833,14 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0) goto err; - src = scatterwalk_ffwd(src_sg, req->src, req->assoclen); - dst = src; + src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen); + reqctx->dst = src; if (req->src != req->dst) { err = chcr_copy_assoc(req, aeadctx); if (err) return ERR_PTR(err); - dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen); + reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst, + req->assoclen); } if (!req->cryptlen) @@ -1848,7 +1850,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, crypt_len = AES_BLOCK_SIZE; else crypt_len = req->cryptlen; - reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen + + reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen + (op_type ? -authsize : authsize)); if (reqctx->dst_nents <= 0) { pr_err("GCM:Invalid Destination sg entries\n"); @@ -1923,7 +1925,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; sg_param.align = 0; - if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst, + if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst, &sg_param)) goto dstmap_fail; @@ -1937,7 +1939,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, write_sg_to_skb(skb, &frags, src, req->cryptlen); } else { aes_gcm_empty_pld_pad(req->dst, authsize - 1); - write_sg_to_skb(skb, &frags, dst, crypt_len); + write_sg_to_skb(skb, &frags, reqctx->dst, crypt_len); + } create_wreq(ctx, chcr_req, req, skb, kctx_len, size, 1, diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index d5af7d64a763..7ec0a8f12475 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -158,6 +158,9 @@ struct ablk_ctx { }; struct chcr_aead_reqctx { struct sk_buff *skb; + struct scatterlist *dst; + struct scatterlist srcffwd[2]; + struct scatterlist dstffwd[2]; short int dst_nents; u16 verify; u8 iv[CHCR_MAX_CRYPTO_IV_LEN]; From f5f7bebc91ab378dea5aad5277c4d283e46472d9 Mon Sep 17 00:00:00 2001 From: Harsh Jain Date: Tue, 24 Jan 2017 10:34:33 +0530 Subject: [PATCH 076/131] crypto: chcr - Check device is allocated before use Ensure dev is allocated for crypto uld context before using the device for crypto operations. Cc: Signed-off-by: Atul Gupta Signed-off-by: Herbert Xu --- drivers/crypto/chelsio/chcr_core.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c index 918da8e6e2d8..1c65f07e1cc9 100644 --- a/drivers/crypto/chelsio/chcr_core.c +++ b/drivers/crypto/chelsio/chcr_core.c @@ -52,6 +52,7 @@ static struct cxgb4_uld_info chcr_uld_info = { int assign_chcr_device(struct chcr_dev **dev) { struct uld_ctx *u_ctx; + int ret = -ENXIO; /* * Which device to use if multiple devices are available TODO @@ -59,15 +60,14 @@ int assign_chcr_device(struct chcr_dev **dev) * must go to the same device to maintain the ordering. */ mutex_lock(&dev_mutex); /* TODO ? */ - u_ctx = list_first_entry(&uld_ctx_list, struct uld_ctx, entry); - if (!u_ctx) { - mutex_unlock(&dev_mutex); - return -ENXIO; + list_for_each_entry(u_ctx, &uld_ctx_list, entry) + if (u_ctx && u_ctx->dev) { + *dev = u_ctx->dev; + ret = 0; + break; } - - *dev = u_ctx->dev; mutex_unlock(&dev_mutex); - return 0; + return ret; } static int chcr_dev_add(struct uld_ctx *u_ctx) @@ -202,10 +202,8 @@ static int chcr_uld_state_change(void *handle, enum cxgb4_state state) static int __init chcr_crypto_init(void) { - if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) { + if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) pr_err("ULD register fail: No chcr crypto support in cxgb4"); - return -1; - } return 0; } From 500c0106e638e08c2c661c305ed57d6b67e10908 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Fri, 27 Jan 2017 15:28:45 -0600 Subject: [PATCH 077/131] crypto: ccp - Fix DMA operations when IOMMU is enabled An I/O page fault occurs when the IOMMU is enabled on a system that supports the v5 CCP. DMA operations use a Request ID value that does not match what is expected by the IOMMU, resulting in the I/O page fault. Setting the Request ID value to 0 corrects this issue. Cc: Signed-off-by: Gary R Hook Signed-off-by: Herbert Xu --- drivers/crypto/ccp/ccp-dev-v5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c index e2ce8190ecc9..612898b4aaad 100644 --- a/drivers/crypto/ccp/ccp-dev-v5.c +++ b/drivers/crypto/ccp/ccp-dev-v5.c @@ -959,7 +959,7 @@ static irqreturn_t ccp5_irq_handler(int irq, void *data) static void ccp5_config(struct ccp_device *ccp) { /* Public side */ - iowrite32(0x00001249, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET); + iowrite32(0x0, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET); } static void ccp5other_config(struct ccp_device *ccp) From e5da5c5667381d2772374ee6a2967b3576c9483d Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Fri, 27 Jan 2017 17:09:04 -0600 Subject: [PATCH 078/131] crypto: ccp - Fix double add when creating new DMA command Eliminate a double-add by creating a new list to manage command descriptors when created; move the descriptor to the pending list when the command is submitted. Cc: Signed-off-by: Gary R Hook Signed-off-by: Herbert Xu --- drivers/crypto/ccp/ccp-dev.h | 1 + drivers/crypto/ccp/ccp-dmaengine.c | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h index 830f35e6005f..649e5610a5ce 100644 --- a/drivers/crypto/ccp/ccp-dev.h +++ b/drivers/crypto/ccp/ccp-dev.h @@ -238,6 +238,7 @@ struct ccp_dma_chan { struct ccp_device *ccp; spinlock_t lock; + struct list_head created; struct list_head pending; struct list_head active; struct list_head complete; diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index 6553912804f7..e5d9278f4019 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -63,6 +63,7 @@ static void ccp_free_chan_resources(struct dma_chan *dma_chan) ccp_free_desc_resources(chan->ccp, &chan->complete); ccp_free_desc_resources(chan->ccp, &chan->active); ccp_free_desc_resources(chan->ccp, &chan->pending); + ccp_free_desc_resources(chan->ccp, &chan->created); spin_unlock_irqrestore(&chan->lock, flags); } @@ -273,6 +274,7 @@ static dma_cookie_t ccp_tx_submit(struct dma_async_tx_descriptor *tx_desc) spin_lock_irqsave(&chan->lock, flags); cookie = dma_cookie_assign(tx_desc); + list_del(&desc->entry); list_add_tail(&desc->entry, &chan->pending); spin_unlock_irqrestore(&chan->lock, flags); @@ -426,7 +428,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan, spin_lock_irqsave(&chan->lock, sflags); - list_add_tail(&desc->entry, &chan->pending); + list_add_tail(&desc->entry, &chan->created); spin_unlock_irqrestore(&chan->lock, sflags); @@ -610,6 +612,7 @@ static int ccp_terminate_all(struct dma_chan *dma_chan) /*TODO: Purge the complete list? */ ccp_free_desc_resources(chan->ccp, &chan->active); ccp_free_desc_resources(chan->ccp, &chan->pending); + ccp_free_desc_resources(chan->ccp, &chan->created); spin_unlock_irqrestore(&chan->lock, flags); @@ -679,6 +682,7 @@ int ccp_dmaengine_register(struct ccp_device *ccp) chan->ccp = ccp; spin_lock_init(&chan->lock); + INIT_LIST_HEAD(&chan->created); INIT_LIST_HEAD(&chan->pending); INIT_LIST_HEAD(&chan->active); INIT_LIST_HEAD(&chan->complete); From c26819900036f5b91608051a0fc7c76f6b4ffc7b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 1 Feb 2017 22:17:39 +0800 Subject: [PATCH 079/131] crypto: aesni - Fix failure when pcbc module is absent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When aesni is built as a module together with pcbc, the pcbc module must be present for aesni to load. However, the pcbc module may not be present for reasons such as its absence on initramfs. This patch allows the aesni to function even if the pcbc module is enabled but not present. Reported-by: Arkadiusz Miśkiewicz Signed-off-by: Herbert Xu --- arch/x86/crypto/aesni-intel_glue.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 6ef688a1ef3e..7ff1b0c86a8e 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1085,9 +1085,9 @@ static void aesni_free_simds(void) aesni_simd_skciphers[i]; i++) simd_skcipher_free(aesni_simd_skciphers[i]); - for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) && - aesni_simd_skciphers2[i].simd; i++) - simd_skcipher_free(aesni_simd_skciphers2[i].simd); + for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++) + if (aesni_simd_skciphers2[i].simd) + simd_skcipher_free(aesni_simd_skciphers2[i].simd); } static int __init aesni_init(void) @@ -1168,7 +1168,7 @@ static int __init aesni_init(void) simd = simd_skcipher_create_compat(algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) - goto unregister_simds; + continue; aesni_simd_skciphers2[i].simd = simd; } From 0b529f143e8baad441a5aac9ad55ec2434d8fb46 Mon Sep 17 00:00:00 2001 From: Harsh Jain Date: Wed, 1 Feb 2017 21:10:28 +0530 Subject: [PATCH 080/131] crypto: algif_aead - Fix kernel panic on list_del MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Kernel panics when userspace program try to access AEAD interface. Remove node from Linked List before freeing its memory. Cc: Signed-off-by: Harsh Jain Reviewed-by: Stephan Müller Signed-off-by: Herbert Xu --- crypto/algif_aead.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index f849311e9fd4..533265f110e0 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -661,9 +661,9 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) unlock: list_for_each_entry_safe(rsgl, tmp, &ctx->list, list) { af_alg_free_sg(&rsgl->sgl); + list_del(&rsgl->list); if (rsgl != &ctx->first_rsgl) sock_kfree_s(sk, rsgl, sizeof(*rsgl)); - list_del(&rsgl->list); } INIT_LIST_HEAD(&ctx->list); aead_wmem_wakeup(sk); From 7c2cf1c4615cc2f576d0604406cdf0065f00b83b Mon Sep 17 00:00:00 2001 From: Harsh Jain Date: Fri, 27 Jan 2017 16:09:06 +0530 Subject: [PATCH 081/131] crypto: chcr - Fix key length for RFC4106 Check keylen before copying salt to avoid wrap around of Integer. Signed-off-by: Harsh Jain Signed-off-by: Herbert Xu --- drivers/crypto/chelsio/chcr_algo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index d29c2b45d3ab..b4b78b37f8a6 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -2192,8 +2192,8 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key, unsigned int ck_size; int ret = 0, key_ctx_size = 0; - if (get_aead_subtype(aead) == - CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) { + if (get_aead_subtype(aead) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 && + keylen > 3) { keylen -= 4; /* nonce/salt is present in the last 4 bytes */ memcpy(aeadctx->salt, key + keylen, 4); } From d19a55ccad15a486ffe03030570744e5d5bd9f8e Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 6 Jan 2017 15:33:14 -0500 Subject: [PATCH 082/131] dm mpath: cleanup -Wbool-operation warning in choose_pgpath() Reported-by: David Binderman Signed-off-by: Mike Snitzer --- drivers/md/dm-mpath.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 6400cffb986d..3570bcb7a4a4 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -427,7 +427,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) unsigned long flags; struct priority_group *pg; struct pgpath *pgpath; - bool bypassed = true; + unsigned bypassed = 1; if (!atomic_read(&m->nr_valid_paths)) { clear_bit(MPATHF_QUEUE_IO, &m->flags); @@ -466,7 +466,7 @@ check_current_pg: */ do { list_for_each_entry(pg, &m->priority_groups, list) { - if (pg->bypassed == bypassed) + if (pg->bypassed == !!bypassed) continue; pgpath = choose_path_in_pg(m, pg, nr_bytes); if (!IS_ERR_OR_NULL(pgpath)) { From 4087a1fffe38106e10646606a27f10d40451862d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 25 Jan 2017 16:24:52 +0100 Subject: [PATCH 083/131] dm rq: cope with DM device destruction while in dm_old_request_fn() Fixes a crash in dm_table_find_target() due to a NULL struct dm_table being passed from dm_old_request_fn() that races with DM device destruction. Reported-by: artem@flashgrid.io Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/dm-rq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 9d7275fb541a..6e702fc69a83 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -779,6 +779,10 @@ static void dm_old_request_fn(struct request_queue *q) int srcu_idx; struct dm_table *map = dm_get_live_table(md, &srcu_idx); + if (unlikely(!map)) { + dm_put_live_table(md, srcu_idx); + return; + } ti = dm_table_find_target(map, pos); dm_put_live_table(md, srcu_idx); } From f5b0cba8f23915e92932f11eb063e37d70556a89 Mon Sep 17 00:00:00 2001 From: Ondrej Kozina Date: Tue, 31 Jan 2017 15:47:11 +0100 Subject: [PATCH 084/131] dm crypt: replace RCU read-side section with rwsem The lockdep splat below hints at a bug in RCU usage in dm-crypt that was introduced with commit c538f6ec9f56 ("dm crypt: add ability to use keys from the kernel key retention service"). The kernel keyring function user_key_payload() is in fact a wrapper for rcu_dereference_protected() which must not be called with only rcu_read_lock() section mark. Unfortunately the kernel keyring subsystem doesn't currently provide an interface that allows the use of an RCU read-side section. So for now we must drop RCU in favour of rwsem until a proper function is made available in the kernel keyring subsystem. =============================== [ INFO: suspicious RCU usage. ] 4.10.0-rc5 #2 Not tainted ------------------------------- ./include/keys/user-type.h:53 suspicious rcu_dereference_protected() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by cryptsetup/6464: #0: (&md->type_lock){+.+.+.}, at: [] dm_lock_md_type+0x12/0x20 [dm_mod] #1: (rcu_read_lock){......}, at: [] crypt_set_key+0x1d8/0x4b0 [dm_crypt] stack backtrace: CPU: 1 PID: 6464 Comm: cryptsetup Not tainted 4.10.0-rc5 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.1-1.fc24 04/01/2014 Call Trace: dump_stack+0x67/0x92 lockdep_rcu_suspicious+0xc5/0x100 crypt_set_key+0x351/0x4b0 [dm_crypt] ? crypt_set_key+0x1d8/0x4b0 [dm_crypt] crypt_ctr+0x341/0xa53 [dm_crypt] dm_table_add_target+0x147/0x330 [dm_mod] table_load+0x111/0x350 [dm_mod] ? retrieve_status+0x1c0/0x1c0 [dm_mod] ctl_ioctl+0x1f5/0x510 [dm_mod] dm_ctl_ioctl+0xe/0x20 [dm_mod] do_vfs_ioctl+0x8e/0x690 ? ____fput+0x9/0x10 ? task_work_run+0x7e/0xa0 ? trace_hardirqs_on_caller+0x122/0x1b0 SyS_ioctl+0x3c/0x70 entry_SYSCALL_64_fastpath+0x18/0xad RIP: 0033:0x7f392c9a4ec7 RSP: 002b:00007ffef6383378 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffef63830a0 RCX: 00007f392c9a4ec7 RDX: 000000000124fcc0 RSI: 00000000c138fd09 RDI: 0000000000000005 RBP: 00007ffef6383090 R08: 00000000ffffffff R09: 00000000012482b0 R10: 2a28205d34383336 R11: 0000000000000246 R12: 00007f392d803a08 R13: 00007ffef63831e0 R14: 0000000000000000 R15: 00007f392d803a0b Fixes: c538f6ec9f56 ("dm crypt: add ability to use keys from the kernel key retention service") Reported-by: Milan Broz Signed-off-by: Ondrej Kozina Reviewed-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-crypt.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 7c6c57216bf2..8a9f742d8ed7 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1534,18 +1534,18 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string return PTR_ERR(key); } - rcu_read_lock(); + down_read(&key->sem); ukp = user_key_payload(key); if (!ukp) { - rcu_read_unlock(); + up_read(&key->sem); key_put(key); kzfree(new_key_string); return -EKEYREVOKED; } if (cc->key_size != ukp->datalen) { - rcu_read_unlock(); + up_read(&key->sem); key_put(key); kzfree(new_key_string); return -EINVAL; @@ -1553,7 +1553,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string memcpy(cc->key, ukp->data, cc->key_size); - rcu_read_unlock(); + up_read(&key->sem); key_put(key); /* clear the flag since following operations may invalidate previously valid key */ From 013e8167899d389075160412a8c0c5e0581e1f13 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Thu, 2 Feb 2017 11:29:38 +0100 Subject: [PATCH 085/131] ipv6: sr: remove cleanup flag and fix HMAC computation In the latest version of the IPv6 Segment Routing IETF draft [1] the cleanup flag is removed and the flags field length is shrunk from 16 bits to 8 bits. As a consequence, the input of the HMAC computation is modified in a non-backward compatible way by covering the whole octet of flags instead of only the cleanup bit. As such, if an implementation compatible with the latest draft computes the HMAC of an SRH who has other flags set to 1, then the HMAC result would differ from the current implementation. This patch carries those modifications to prevent conflict with other implementations of IPv6 SR. [1] https://tools.ietf.org/html/draft-ietf-6man-segment-routing-header-05 Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/uapi/linux/seg6.h | 9 +++------ net/ipv6/exthdrs.c | 31 +++---------------------------- net/ipv6/seg6_hmac.c | 8 ++++---- 3 files changed, 10 insertions(+), 38 deletions(-) diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h index c396a8052f73..052799e4d751 100644 --- a/include/uapi/linux/seg6.h +++ b/include/uapi/linux/seg6.h @@ -23,14 +23,12 @@ struct ipv6_sr_hdr { __u8 type; __u8 segments_left; __u8 first_segment; - __u8 flag_1; - __u8 flag_2; - __u8 reserved; + __u8 flags; + __u16 reserved; struct in6_addr segments[0]; }; -#define SR6_FLAG1_CLEANUP (1 << 7) #define SR6_FLAG1_PROTECTED (1 << 6) #define SR6_FLAG1_OAM (1 << 5) #define SR6_FLAG1_ALERT (1 << 4) @@ -42,8 +40,7 @@ struct ipv6_sr_hdr { #define SR6_TLV_PADDING 4 #define SR6_TLV_HMAC 5 -#define sr_has_cleanup(srh) ((srh)->flag_1 & SR6_FLAG1_CLEANUP) -#define sr_has_hmac(srh) ((srh)->flag_1 & SR6_FLAG1_HMAC) +#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC) struct sr6_tlv { __u8 type; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index e4198502fd98..275cac628a95 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -327,7 +327,6 @@ static int ipv6_srh_rcv(struct sk_buff *skb) struct ipv6_sr_hdr *hdr; struct inet6_dev *idev; struct in6_addr *addr; - bool cleanup = false; int accept_seg6; hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); @@ -351,11 +350,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb) #endif looped_back: - if (hdr->segments_left > 0) { - if (hdr->nexthdr != NEXTHDR_IPV6 && hdr->segments_left == 1 && - sr_has_cleanup(hdr)) - cleanup = true; - } else { + if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6) { int offset = (hdr->hdrlen + 1) << 3; @@ -418,21 +413,6 @@ looped_back: ipv6_hdr(skb)->daddr = *addr; - if (cleanup) { - int srhlen = (hdr->hdrlen + 1) << 3; - int nh = hdr->nexthdr; - - skb_pull_rcsum(skb, sizeof(struct ipv6hdr) + srhlen); - memmove(skb_network_header(skb) + srhlen, - skb_network_header(skb), - (unsigned char *)hdr - skb_network_header(skb)); - skb->network_header += srhlen; - ipv6_hdr(skb)->nexthdr = nh; - ipv6_hdr(skb)->payload_len = htons(skb->len - - sizeof(struct ipv6hdr)); - skb_push_rcsum(skb, sizeof(struct ipv6hdr)); - } - skb_dst_drop(skb); ip6_route_input(skb); @@ -453,13 +433,8 @@ looped_back: } ipv6_hdr(skb)->hop_limit--; - /* be sure that srh is still present before reinjecting */ - if (!cleanup) { - skb_pull(skb, sizeof(struct ipv6hdr)); - goto looped_back; - } - skb_set_transport_header(skb, sizeof(struct ipv6hdr)); - IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); + skb_pull(skb, sizeof(struct ipv6hdr)); + goto looped_back; } dst_input(skb); diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 03a064803626..6ef3dfb6e811 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -174,7 +174,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr, * hash function (RadioGatun) with up to 1216 bits */ - /* saddr(16) + first_seg(1) + cleanup(1) + keyid(4) + seglist(16n) */ + /* saddr(16) + first_seg(1) + flags(1) + keyid(4) + seglist(16n) */ plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16; /* this limit allows for 14 segments */ @@ -186,7 +186,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr, * * 1. Source IPv6 address (128 bits) * 2. first_segment value (8 bits) - * 3. cleanup flag (8 bits: highest bit is cleanup value, others are 0) + * 3. Flags (8 bits) * 4. HMAC Key ID (32 bits) * 5. All segments in the segments list (n * 128 bits) */ @@ -202,8 +202,8 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr, /* first_segment value */ *off++ = hdr->first_segment; - /* cleanup flag */ - *off++ = !!(sr_has_cleanup(hdr)) << 7; + /* flags */ + *off++ = hdr->flags; /* HMAC Key ID */ memcpy(off, &hmackeyid, 4); From 3808d34838184fd29088d6b3a364ba2f1c018fb6 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 2 Feb 2017 13:32:10 +0100 Subject: [PATCH 086/131] ethtool: do not vzalloc(0) on registers dump If ->get_regs_len() callback return 0, we allocate 0 bytes of memory, what print ugly warning in dmesg, which can be found further below. This happen on mac80211 devices where ieee80211_get_regs_len() just return 0 and driver only fills ethtool_regs structure and actually do not provide any dump. However I assume this can happen on other drivers i.e. when for some devices driver provide regs dump and for others do not. Hence preventing to to print warning in ethtool code seems to be reasonable. ethtool: vmalloc: allocation failure: 0 bytes, mode:0x24080c2(GFP_KERNEL|__GFP_HIGHMEM|__GFP_ZERO) Call Trace: [] dump_stack+0x63/0x8c [] warn_alloc+0x13f/0x170 [] __vmalloc_node_range+0x1e6/0x2c0 [] vzalloc+0x54/0x60 [] dev_ethtool+0xb4c/0x1b30 [] dev_ioctl+0x181/0x520 [] sock_do_ioctl+0x42/0x50 Mem-Info: active_anon:435809 inactive_anon:173951 isolated_anon:0 active_file:835822 inactive_file:196932 isolated_file:0 unevictable:0 dirty:8 writeback:0 unstable:0 slab_reclaimable:157732 slab_unreclaimable:10022 mapped:83042 shmem:306356 pagetables:9507 bounce:0 free:130041 free_pcp:1080 free_cma:0 Node 0 active_anon:1743236kB inactive_anon:695804kB active_file:3343288kB inactive_file:787728kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:332168kB dirty:32kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 1225424kB writeback_tmp:0kB unstable:0kB pages_scanned:0 all_unreclaimable? no Node 0 DMA free:15900kB min:136kB low:168kB high:200kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:15984kB managed:15900kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB lowmem_reserve[]: 0 3187 7643 7643 Node 0 DMA32 free:419732kB min:28124kB low:35152kB high:42180kB active_anon:541180kB inactive_anon:248988kB active_file:1466388kB inactive_file:389632kB unevictable:0kB writepending:0kB present:3370280kB managed:3290932kB mlocked:0kB slab_reclaimable:217184kB slab_unreclaimable:4180kB kernel_stack:160kB pagetables:984kB bounce:0kB free_pcp:2236kB local_pcp:660kB free_cma:0kB lowmem_reserve[]: 0 0 4456 4456 Signed-off-by: Stanislaw Gruszka Signed-off-by: David S. Miller --- net/core/ethtool.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 236a21e3c878..d92de0a1f0a4 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1405,9 +1405,12 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = vzalloc(reglen); - if (reglen && !regbuf) - return -ENOMEM; + regbuf = NULL; + if (reglen) { + regbuf = vzalloc(reglen); + if (!regbuf) + return -ENOMEM; + } ops->get_regs(dev, ®s, regbuf); From 56067812d5b0e737ac2063e94a50f76b810d6ca3 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 3 Feb 2017 09:54:05 +0000 Subject: [PATCH 087/131] kbuild: modversions: add infrastructure for emitting relative CRCs This add the kbuild infrastructure that will allow architectures to emit vmlinux symbol CRCs as 32-bit offsets to another location in the kernel where the actual value is stored. This works around problems with CRCs being mistaken for relocatable symbols on kernels that self relocate at runtime (i.e., powerpc with CONFIG_RELOCATABLE=y) For the kbuild side of things, this comes down to the following: - introducing a Kconfig symbol MODULE_REL_CRCS - adding a -R switch to genksyms to instruct it to emit the CRC symbols as references into the .rodata section - making modpost distinguish such references from absolute CRC symbols by the section index (SHN_ABS) - making kallsyms disregard non-absolute symbols with a __crc_ prefix Signed-off-by: Ard Biesheuvel Signed-off-by: Linus Torvalds --- init/Kconfig | 4 ++++ scripts/Makefile.build | 2 ++ scripts/genksyms/genksyms.c | 19 ++++++++++++++----- scripts/kallsyms.c | 12 ++++++++++++ scripts/mod/modpost.c | 10 ++++++++++ 5 files changed, 42 insertions(+), 5 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index e1a937348a3e..4dd8bd232a1d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1987,6 +1987,10 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +config MODULE_REL_CRCS + bool + depends on MODVERSIONS + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help diff --git a/scripts/Makefile.build b/scripts/Makefile.build index eadcd4d359d9..d883116ebaa4 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -164,6 +164,7 @@ cmd_gensymtypes_c = \ $(CPP) -D__GENKSYMS__ $(c_flags) $< | \ $(GENKSYMS) $(if $(1), -T $(2)) \ $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \ + $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS)) \ $(if $(KBUILD_PRESERVE),-p) \ -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null)) @@ -337,6 +338,7 @@ cmd_gensymtypes_S = \ $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | \ $(GENKSYMS) $(if $(1), -T $(2)) \ $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \ + $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS)) \ $(if $(KBUILD_PRESERVE),-p) \ -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null)) diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 06121ce524a7..c9235d8340f1 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -44,7 +44,7 @@ char *cur_filename, *source_file; int in_source_file; static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types, - flag_preserve, flag_warnings; + flag_preserve, flag_warnings, flag_rel_crcs; static const char *mod_prefix = ""; static int errors; @@ -693,7 +693,10 @@ void export_symbol(const char *name) fputs(">\n", debugfile); /* Used as a linker script. */ - printf("%s__crc_%s = 0x%08lx ;\n", mod_prefix, name, crc); + printf(!flag_rel_crcs ? "%s__crc_%s = 0x%08lx;\n" : + "SECTIONS { .rodata : ALIGN(4) { " + "%s__crc_%s = .; LONG(0x%08lx); } }\n", + mod_prefix, name, crc); } } @@ -730,7 +733,7 @@ void error_with_pos(const char *fmt, ...) static void genksyms_usage(void) { - fputs("Usage:\n" "genksyms [-adDTwqhV] > /path/to/.tmp_obj.ver\n" "\n" + fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n" #ifdef __GNU_LIBRARY__ " -s, --symbol-prefix Select symbol prefix\n" " -d, --debug Increment the debug level (repeatable)\n" @@ -742,6 +745,7 @@ static void genksyms_usage(void) " -q, --quiet Disable warnings (default)\n" " -h, --help Print this message\n" " -V, --version Print the release version\n" + " -R, --relative-crc Emit section relative symbol CRCs\n" #else /* __GNU_LIBRARY__ */ " -s Select symbol prefix\n" " -d Increment the debug level (repeatable)\n" @@ -753,6 +757,7 @@ static void genksyms_usage(void) " -q Disable warnings (default)\n" " -h Print this message\n" " -V Print the release version\n" + " -R Emit section relative symbol CRCs\n" #endif /* __GNU_LIBRARY__ */ , stderr); } @@ -774,13 +779,14 @@ int main(int argc, char **argv) {"preserve", 0, 0, 'p'}, {"version", 0, 0, 'V'}, {"help", 0, 0, 'h'}, + {"relative-crc", 0, 0, 'R'}, {0, 0, 0, 0} }; - while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph", + while ((o = getopt_long(argc, argv, "s:dwqVDr:T:phR", &long_opts[0], NULL)) != EOF) #else /* __GNU_LIBRARY__ */ - while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF) + while ((o = getopt(argc, argv, "s:dwqVDr:T:phR")) != EOF) #endif /* __GNU_LIBRARY__ */ switch (o) { case 's': @@ -823,6 +829,9 @@ int main(int argc, char **argv) case 'h': genksyms_usage(); return 0; + case 'R': + flag_rel_crcs = 1; + break; default: genksyms_usage(); return 1; diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 299b92ca1ae0..5d554419170b 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -219,6 +219,10 @@ static int symbol_valid(struct sym_entry *s) "_SDA2_BASE_", /* ppc */ NULL }; + static char *special_prefixes[] = { + "__crc_", /* modversions */ + NULL }; + static char *special_suffixes[] = { "_veneer", /* arm */ "_from_arm", /* arm */ @@ -259,6 +263,14 @@ static int symbol_valid(struct sym_entry *s) if (strcmp(sym_name, special_symbols[i]) == 0) return 0; + for (i = 0; special_prefixes[i]; i++) { + int l = strlen(special_prefixes[i]); + + if (l <= strlen(sym_name) && + strncmp(sym_name, special_prefixes[i], l) == 0) + return 0; + } + for (i = 0; special_suffixes[i]; i++) { int l = strlen(sym_name) - strlen(special_suffixes[i]); diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 29c89a6bad3d..4dedd0d3d3a7 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -621,6 +621,16 @@ static void handle_modversions(struct module *mod, struct elf_info *info, if (strncmp(symname, CRC_PFX, strlen(CRC_PFX)) == 0) { is_crc = true; crc = (unsigned int) sym->st_value; + if (sym->st_shndx != SHN_UNDEF && sym->st_shndx != SHN_ABS) { + unsigned int *crcp; + + /* symbol points to the CRC in the ELF object */ + crcp = (void *)info->hdr + sym->st_value + + info->sechdrs[sym->st_shndx].sh_offset - + (info->hdr->e_type != ET_REL ? + info->sechdrs[sym->st_shndx].sh_addr : 0); + crc = *crcp; + } sym_update_crc(symname + strlen(CRC_PFX), mod, crc, export); } From 71810db27c1c853b335675bee335d893bc3d324b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 3 Feb 2017 09:54:06 +0000 Subject: [PATCH 088/131] modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R__RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell Signed-off-by: Ard Biesheuvel Signed-off-by: Linus Torvalds --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/module.h | 4 --- arch/powerpc/kernel/module_64.c | 8 ----- include/asm-generic/export.h | 11 ++++--- include/linux/export.h | 14 ++++++++ include/linux/module.h | 14 ++++---- kernel/module.c | 53 +++++++++++++++---------------- 7 files changed, 53 insertions(+), 52 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a8ee573fe610..db8a1ef6bfaf 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -484,6 +484,7 @@ config RELOCATABLE bool "Build a relocatable kernel" depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE)) select NONSTATIC_KERNEL + select MODULE_REL_CRCS if MODVERSIONS help This builds a kernel image that is capable of running at the location the kernel is loaded at. For ppc32, there is no any diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index cc12c61ef315..53885512b8d3 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -90,9 +90,5 @@ static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sec } #endif -#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64) -#define ARCH_RELOCATES_KCRCTAB -#define reloc_start PHYSICAL_START -#endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MODULE_H */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index bb1807184bad..0b0f89685b67 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -286,14 +286,6 @@ static void dedotify_versions(struct modversion_info *vers, for (end = (void *)vers + size; vers < end; vers++) if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); -#ifdef ARCH_RELOCATES_KCRCTAB - /* The TOC symbol has no CRC computed. To avoid CRC - * check failing, we must force it to the expected - * value (see CRC check in module.c). - */ - if (!strcmp(vers->name, "TOC.")) - vers->crc = -(unsigned long)reloc_start; -#endif } } diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index 63554e9f6e0c..719db1968d81 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -9,18 +9,15 @@ #ifndef KSYM_ALIGN #define KSYM_ALIGN 8 #endif -#ifndef KCRC_ALIGN -#define KCRC_ALIGN 8 -#endif #else #define __put .long #ifndef KSYM_ALIGN #define KSYM_ALIGN 4 #endif +#endif #ifndef KCRC_ALIGN #define KCRC_ALIGN 4 #endif -#endif #ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX #define KSYM(name) _##name @@ -52,7 +49,11 @@ KSYM(__kstrtab_\name): .section ___kcrctab\sec+\name,"a" .balign KCRC_ALIGN KSYM(__kcrctab_\name): - __put KSYM(__crc_\name) +#if defined(CONFIG_MODULE_REL_CRCS) + .long KSYM(__crc_\name) - . +#else + .long KSYM(__crc_\name) +#endif .weak KSYM(__crc_\name) .previous #endif diff --git a/include/linux/export.h b/include/linux/export.h index 2a0f61fbc731..7473fba6a60c 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -43,6 +43,13 @@ extern struct module __this_module; #ifdef CONFIG_MODVERSIONS /* Mark the CRC weak since genksyms apparently decides not to * generate a checksums for some symbols */ +#if defined(CONFIG_MODULE_REL_CRCS) +#define __CRC_SYMBOL(sym, sec) \ + asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ + " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ + " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " - . \n" \ + " .previous \n"); +#elif !defined(CONFIG_64BIT) #define __CRC_SYMBOL(sym, sec) \ extern __visible void *__crc_##sym __attribute__((weak)); \ static const unsigned long __kcrctab_##sym \ @@ -50,6 +57,13 @@ extern struct module __this_module; __attribute__((section("___kcrctab" sec "+" #sym), used)) \ = (unsigned long) &__crc_##sym; #else +#define __CRC_SYMBOL(sym, sec) \ + asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ + " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ + " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ + " .previous \n"); +#endif +#else #define __CRC_SYMBOL(sym, sec) #endif diff --git a/include/linux/module.h b/include/linux/module.h index 7c84273d60b9..cc7cba219b20 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -346,7 +346,7 @@ struct module { /* Exported symbols */ const struct kernel_symbol *syms; - const unsigned long *crcs; + const s32 *crcs; unsigned int num_syms; /* Kernel parameters. */ @@ -359,18 +359,18 @@ struct module { /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; - const unsigned long *gpl_crcs; + const s32 *gpl_crcs; #ifdef CONFIG_UNUSED_SYMBOLS /* unused exported symbols. */ const struct kernel_symbol *unused_syms; - const unsigned long *unused_crcs; + const s32 *unused_crcs; unsigned int num_unused_syms; /* GPL-only, unused exported symbols. */ unsigned int num_unused_gpl_syms; const struct kernel_symbol *unused_gpl_syms; - const unsigned long *unused_gpl_crcs; + const s32 *unused_gpl_crcs; #endif #ifdef CONFIG_MODULE_SIG @@ -382,7 +382,7 @@ struct module { /* symbols that will be GPL-only in the near future. */ const struct kernel_symbol *gpl_future_syms; - const unsigned long *gpl_future_crcs; + const s32 *gpl_future_crcs; unsigned int num_gpl_future_syms; /* Exception table */ @@ -523,7 +523,7 @@ struct module *find_module(const char *name); struct symsearch { const struct kernel_symbol *start, *stop; - const unsigned long *crcs; + const s32 *crcs; enum { NOT_GPL_ONLY, GPL_ONLY, @@ -539,7 +539,7 @@ struct symsearch { */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, - const unsigned long **crc, + const s32 **crc, bool gplok, bool warn); diff --git a/kernel/module.c b/kernel/module.c index 38d4270925d4..3d8f126208e3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -389,16 +389,16 @@ extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const struct kernel_symbol __start___ksymtab_gpl_future[]; extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; -extern const unsigned long __start___kcrctab[]; -extern const unsigned long __start___kcrctab_gpl[]; -extern const unsigned long __start___kcrctab_gpl_future[]; +extern const s32 __start___kcrctab[]; +extern const s32 __start___kcrctab_gpl[]; +extern const s32 __start___kcrctab_gpl_future[]; #ifdef CONFIG_UNUSED_SYMBOLS extern const struct kernel_symbol __start___ksymtab_unused[]; extern const struct kernel_symbol __stop___ksymtab_unused[]; extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; -extern const unsigned long __start___kcrctab_unused[]; -extern const unsigned long __start___kcrctab_unused_gpl[]; +extern const s32 __start___kcrctab_unused[]; +extern const s32 __start___kcrctab_unused_gpl[]; #endif #ifndef CONFIG_MODVERSIONS @@ -497,7 +497,7 @@ struct find_symbol_arg { /* Output */ struct module *owner; - const unsigned long *crc; + const s32 *crc; const struct kernel_symbol *sym; }; @@ -563,7 +563,7 @@ static bool find_symbol_in_section(const struct symsearch *syms, * (optional) module which owns it. Needs preempt disabled or module_mutex. */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, - const unsigned long **crc, + const s32 **crc, bool gplok, bool warn) { @@ -1249,23 +1249,17 @@ static int try_to_force_load(struct module *mod, const char *reason) } #ifdef CONFIG_MODVERSIONS -/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */ -static unsigned long maybe_relocated(unsigned long crc, - const struct module *crc_owner) + +static u32 resolve_rel_crc(const s32 *crc) { -#ifdef ARCH_RELOCATES_KCRCTAB - if (crc_owner == NULL) - return crc - (unsigned long)reloc_start; -#endif - return crc; + return *(u32 *)((void *)crc + *crc); } static int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc, - const struct module *crc_owner) + const s32 *crc) { unsigned int i, num_versions; struct modversion_info *versions; @@ -1283,13 +1277,19 @@ static int check_version(Elf_Shdr *sechdrs, / sizeof(struct modversion_info); for (i = 0; i < num_versions; i++) { + u32 crcval; + if (strcmp(versions[i].name, symname) != 0) continue; - if (versions[i].crc == maybe_relocated(*crc, crc_owner)) + if (IS_ENABLED(CONFIG_MODULE_REL_CRCS)) + crcval = resolve_rel_crc(crc); + else + crcval = *crc; + if (versions[i].crc == crcval) return 1; - pr_debug("Found checksum %lX vs module %lX\n", - maybe_relocated(*crc, crc_owner), versions[i].crc); + pr_debug("Found checksum %X vs module %lX\n", + crcval, versions[i].crc); goto bad_version; } @@ -1307,7 +1307,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, unsigned int versindex, struct module *mod) { - const unsigned long *crc; + const s32 *crc; /* * Since this should be found in kernel (which can't be removed), no @@ -1321,8 +1321,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, } preempt_enable(); return check_version(sechdrs, versindex, - VMLINUX_SYMBOL_STR(module_layout), mod, crc, - NULL); + VMLINUX_SYMBOL_STR(module_layout), mod, crc); } /* First part is kernel version, which we ignore if module has crcs. */ @@ -1340,8 +1339,7 @@ static inline int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc, - const struct module *crc_owner) + const s32 *crc) { return 1; } @@ -1368,7 +1366,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, { struct module *owner; const struct kernel_symbol *sym; - const unsigned long *crc; + const s32 *crc; int err; /* @@ -1383,8 +1381,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, if (!sym) goto unlock; - if (!check_version(info->sechdrs, info->index.vers, name, mod, crc, - owner)) { + if (!check_version(info->sechdrs, info->index.vers, name, mod, crc)) { sym = ERR_PTR(-EINVAL); goto getname; } From 4b9eee96fcb361a5e16a8d2619825e8a048f81f7 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 3 Feb 2017 09:54:07 +0000 Subject: [PATCH 089/131] module: unify absolute krctab definitions for 32-bit and 64-bit The previous patch introduced a separate inline asm version of the krcrctab declaration template for use with 64-bit architectures, which cannot refer to ELF symbols using 32-bit quantities. This declaration should be equivalent to the C one for 32-bit architectures, but just in case - unify them in a separate patch, which can simply be dropped if it turns out to break anything. Signed-off-by: Ard Biesheuvel Signed-off-by: Linus Torvalds --- include/linux/export.h | 7 ------- 1 file changed, 7 deletions(-) diff --git a/include/linux/export.h b/include/linux/export.h index 7473fba6a60c..1a1dfdb2a5c6 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -49,13 +49,6 @@ extern struct module __this_module; " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " - . \n" \ " .previous \n"); -#elif !defined(CONFIG_64BIT) -#define __CRC_SYMBOL(sym, sec) \ - extern __visible void *__crc_##sym __attribute__((weak)); \ - static const unsigned long __kcrctab_##sym \ - __used \ - __attribute__((section("___kcrctab" sec "+" #sym), used)) \ - = (unsigned long) &__crc_##sym; #else #define __CRC_SYMBOL(sym, sec) \ asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ From 00c87e9a70a17b355b81c36adedf05e84f54e10d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Wed, 1 Feb 2017 14:19:53 +0100 Subject: [PATCH 090/131] KVM: x86: do not save guest-unsupported XSAVE state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Saving unsupported state prevents migration when the new host does not support a XSAVE feature of the original host, even if the feature is not exposed to the guest. We've masked host features with guest-visible features before, with 4344ee981e21 ("KVM: x86: only copy XSAVE state for the supported features") and dropped it when implementing XSAVES. Do it again. Fixes: df1daba7d1cb ("KVM: x86: support XSAVES usage in the host") Cc: stable@vger.kernel.org Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d153be8929a6..e52c9088660f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3182,6 +3182,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* From 29905b52fad0854351f57bab867647e4982285bf Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 2 Feb 2017 18:05:26 +0000 Subject: [PATCH 091/131] log2: make order_base_2() behave correctly on const input value zero The function order_base_2() is defined (according to the comment block) as returning zero on input zero, but subsequently passes the input into roundup_pow_of_two(), which is explicitly undefined for input zero. This has gone unnoticed until now, but optimization passes in GCC 7 may produce constant folded function instances where a constant value of zero is passed into order_base_2(), resulting in link errors against the deliberately undefined '____ilog2_NaN'. So update order_base_2() to adhere to its own documented interface. [ See http://marc.info/?l=linux-kernel&m=147672952517795&w=2 and follow-up discussion for more background. The gcc "optimization pass" is really just broken, but now the GCC trunk problem seems to have escaped out of just specially built daily images, so we need to work around it in mainline. - Linus ] Signed-off-by: Ard Biesheuvel Signed-off-by: Linus Torvalds --- include/linux/log2.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/include/linux/log2.h b/include/linux/log2.h index fd7ff3d91e6a..ef3d4f67118c 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -203,6 +203,17 @@ unsigned long __rounddown_pow_of_two(unsigned long n) * ... and so on. */ -#define order_base_2(n) ilog2(roundup_pow_of_two(n)) +static inline __attribute_const__ +int __order_base_2(unsigned long n) +{ + return n > 1 ? ilog2(n - 1) + 1 : 0; +} +#define order_base_2(n) \ +( \ + __builtin_constant_p(n) ? ( \ + ((n) == 0 || (n) == 1) ? 0 : \ + ilog2((n) - 1) + 1) : \ + __order_base_2(n) \ +) #endif /* _LINUX_LOG2_H */ From e471486c13b82b1338d49c798f78bb62b1ed0a9e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 2 Feb 2017 10:31:00 -0800 Subject: [PATCH 092/131] acpi, nfit: fix acpi_nfit_flush_probe() crash We queue an on-stack work item to 'nfit_wq' and wait for it to complete as part of a 'flush_probe' request. However, if the user cancels the wait we need to make sure the item is flushed from the queue otherwise we are leaving an out-of-scope stack address on the work list. BUG: unable to handle kernel paging request at ffffbcb3c72f7cd0 IP: [] __list_add+0x1b/0xb0 [..] RIP: 0010:[] [] __list_add+0x1b/0xb0 RSP: 0018:ffffbcb3c7ba7c00 EFLAGS: 00010046 [..] Call Trace: [] insert_work+0x3a/0xc0 [] ? seq_open+0x5a/0xa0 [] __queue_work+0x16a/0x460 [] queue_work_on+0x38/0x40 [] acpi_nfit_flush_probe+0x95/0xc0 [nfit] [] ? nfit_visible+0x40/0x40 [nfit] [] wait_probe_show+0x25/0x60 [] dev_attr_show+0x20/0x50 Fixes: 7ae0fa439faf ("nfit, libnvdimm: async region scrub workqueue") Cc: Reviewed-by: Vishal Verma Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 2f82b8eba360..7361d00818e2 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2704,6 +2704,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); struct device *dev = acpi_desc->dev; struct acpi_nfit_flush_work flush; + int rc; /* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */ device_lock(dev); @@ -2716,7 +2717,10 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) INIT_WORK_ONSTACK(&flush.work, flush_probe); COMPLETION_INITIALIZER_ONSTACK(flush.cmp); queue_work(nfit_wq, &flush.work); - return wait_for_completion_interruptible(&flush.cmp); + + rc = wait_for_completion_interruptible(&flush.cmp); + cancel_work_sync(&flush.work); + return rc; } static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, From 5fa8bbda38c668e56b0c6cdecced2eac2fe36dec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 2 Feb 2017 10:31:35 -0800 Subject: [PATCH 093/131] net: use a work queue to defer net_disable_timestamp() work Dmitry reported a warning [1] showing that we were calling net_disable_timestamp() -> static_key_slow_dec() from a non process context. Grabbing a mutex while holding a spinlock or rcu_read_lock() is not allowed. As Cong suggested, we now use a work queue. It is possible netstamp_clear() exits while netstamp_needed_deferred is not zero, but it is probably not worth trying to do better than that. netstamp_needed_deferred atomic tracks the exact number of deferred decrements. [1] [ INFO: suspicious RCU usage. ] 4.10.0-rc5+ #192 Not tainted ------------------------------- ./include/linux/rcupdate.h:561 Illegal context switch in RCU read-side critical section! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 0 2 locks held by syz-executor14/23111: #0: (sk_lock-AF_INET6){+.+.+.}, at: [] lock_sock include/net/sock.h:1454 [inline] #0: (sk_lock-AF_INET6){+.+.+.}, at: [] rawv6_sendmsg+0x1e65/0x3ec0 net/ipv6/raw.c:919 #1: (rcu_read_lock){......}, at: [] nf_hook include/linux/netfilter.h:201 [inline] #1: (rcu_read_lock){......}, at: [] __ip6_local_out+0x258/0x840 net/ipv6/output_core.c:160 stack backtrace: CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:15 [inline] dump_stack+0x2ee/0x3ef lib/dump_stack.c:51 lockdep_rcu_suspicious+0x139/0x180 kernel/locking/lockdep.c:4452 rcu_preempt_sleep_check include/linux/rcupdate.h:560 [inline] ___might_sleep+0x560/0x650 kernel/sched/core.c:7748 __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739 mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752 atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060 __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149 static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174 net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728 sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403 __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441 sk_destruct+0x47/0x80 net/core/sock.c:1460 __sk_free+0x57/0x230 net/core/sock.c:1468 sock_wfree+0xae/0x120 net/core/sock.c:1645 skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655 skb_release_all+0x15/0x60 net/core/skbuff.c:668 __kfree_skb+0x15/0x20 net/core/skbuff.c:684 kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304 inet_frag_put include/net/inet_frag.h:133 [inline] nf_ct_frag6_gather+0x1106/0x3840 net/ipv6/netfilter/nf_conntrack_reasm.c:617 ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68 nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline] nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310 nf_hook include/linux/netfilter.h:212 [inline] __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742 rawv6_push_pending_frames net/ipv6/raw.c:613 [inline] rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744 sock_sendmsg_nosec net/socket.c:635 [inline] sock_sendmsg+0xca/0x110 net/socket.c:645 sock_write_iter+0x326/0x600 net/socket.c:848 do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695 do_readv_writev+0x42c/0x9b0 fs/read_write.c:872 vfs_writev+0x87/0xc0 fs/read_write.c:911 do_writev+0x110/0x2c0 fs/read_write.c:944 SYSC_writev fs/read_write.c:1017 [inline] SyS_writev+0x27/0x30 fs/read_write.c:1014 entry_SYSCALL_64_fastpath+0x1f/0xc2 RIP: 0033:0x445559 RSP: 002b:00007f6f46fceb58 EFLAGS: 00000292 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 0000000000445559 RDX: 0000000000000001 RSI: 0000000020f1eff0 RDI: 0000000000000005 RBP: 00000000006e19c0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000292 R12: 0000000000700000 R13: 0000000020f59000 R14: 0000000000000015 R15: 0000000000020400 BUG: sleeping function called from invalid context at kernel/locking/mutex.c:752 in_atomic(): 1, irqs_disabled(): 0, pid: 23111, name: syz-executor14 INFO: lockdep is turned off. CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:15 [inline] dump_stack+0x2ee/0x3ef lib/dump_stack.c:51 ___might_sleep+0x47e/0x650 kernel/sched/core.c:7780 __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739 mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752 atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060 __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149 static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174 net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728 sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403 __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441 sk_destruct+0x47/0x80 net/core/sock.c:1460 __sk_free+0x57/0x230 net/core/sock.c:1468 sock_wfree+0xae/0x120 net/core/sock.c:1645 skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655 skb_release_all+0x15/0x60 net/core/skbuff.c:668 __kfree_skb+0x15/0x20 net/core/skbuff.c:684 kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304 inet_frag_put include/net/inet_frag.h:133 [inline] nf_ct_frag6_gather+0x1106/0x3840 net/ipv6/netfilter/nf_conntrack_reasm.c:617 ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68 nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline] nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310 nf_hook include/linux/netfilter.h:212 [inline] __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742 rawv6_push_pending_frames net/ipv6/raw.c:613 [inline] rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744 sock_sendmsg_nosec net/socket.c:635 [inline] sock_sendmsg+0xca/0x110 net/socket.c:645 sock_write_iter+0x326/0x600 net/socket.c:848 do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695 do_readv_writev+0x42c/0x9b0 fs/read_write.c:872 vfs_writev+0x87/0xc0 fs/read_write.c:911 do_writev+0x110/0x2c0 fs/read_write.c:944 SYSC_writev fs/read_write.c:1017 [inline] SyS_writev+0x27/0x30 fs/read_write.c:1014 entry_SYSCALL_64_fastpath+0x1f/0xc2 RIP: 0033:0x445559 Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context") Suggested-by: Cong Wang Reported-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 31 +++++++++++++------------------ 1 file changed, 13 insertions(+), 18 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 7f218e095361..29101c98399f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1695,24 +1695,19 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL -/* We are not allowed to call static_key_slow_dec() from irq context - * If net_disable_timestamp() is called from irq context, defer the - * static_key_slow_dec() calls. - */ static atomic_t netstamp_needed_deferred; +static void netstamp_clear(struct work_struct *work) +{ + int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + + while (deferred--) + static_key_slow_dec(&netstamp_needed); +} +static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { -#ifdef HAVE_JUMP_LABEL - int deferred = atomic_xchg(&netstamp_needed_deferred, 0); - - if (deferred) { - while (--deferred) - static_key_slow_dec(&netstamp_needed); - return; - } -#endif static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); @@ -1720,12 +1715,12 @@ EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - if (in_interrupt()) { - atomic_inc(&netstamp_needed_deferred); - return; - } -#endif + /* net_disable_timestamp() can be called from non process context */ + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_dec(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_disable_timestamp); From 0d5415b489f68b58e1983a53793d25d53098ed4b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 3 Feb 2017 05:43:52 +0200 Subject: [PATCH 094/131] Revert "vring: Force use of DMA API for ARM-based systems with legacy devices" This reverts commit c7070619f3408d9a0dffbed9149e6f00479cf43b. This has been shown to regress on some ARM systems: by forcing on DMA API usage for ARM systems, we have inadvertently kicked open a hornets' nest in terms of cache-coherency. Namely that unless the virtio device is explicitly described as capable of coherent DMA by firmware, the DMA APIs on ARM and other DT-based platforms will assume it is non-coherent. This turns out to cause a big problem for the likes of QEMU and kvmtool, which generate virtio-mmio devices in their guest DTs but neglect to add the often-overlooked "dma-coherent" property; as a result, we end up with the guest making non-cacheable accesses to the vring, the host doing so cacheably, both talking past each other and things going horribly wrong. We are working on a safer work-around. Fixes: c7070619f340 ("vring: Force use of DMA API for ARM-based systems with legacy devices") Reported-by: Robin Murphy Cc: Signed-off-by: Will Deacon Signed-off-by: Michael S. Tsirkin Acked-by: Marc Zyngier --- drivers/virtio/virtio_ring.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 7e38ed79c3fc..409aeaa49246 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -159,13 +159,6 @@ static bool vring_use_dma_api(struct virtio_device *vdev) if (xen_domain()) return true; - /* - * On ARM-based machines, the DMA ops will do the right thing, - * so always use them with legacy devices. - */ - if (IS_ENABLED(CONFIG_ARM) || IS_ENABLED(CONFIG_ARM64)) - return !virtio_has_feature(vdev, VIRTIO_F_VERSION_1); - return false; } From cda8bba0f99d25d2061c531113c14fa41effc3ae Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Mon, 30 Jan 2017 11:09:36 +0100 Subject: [PATCH 095/131] vhost: fix initialization for vq->is_le Currently, under certain circumstances vhost_init_is_le does just a part of the initialization job, and depends on vhost_reset_is_le being called too. For this reason vhost_vq_init_access used to call vhost_reset_is_le when vq->private_data is NULL. This is not only counter intuitive, but also real a problem because it breaks vhost_net. The bug was introduced to vhost_net with commit 2751c9882b94 ("vhost: cross-endian support for legacy devices"). The symptom is corruption of the vq's used.idx field (virtio) after VHOST_NET_SET_BACKEND was issued as a part of the vhost shutdown on a vq with pending descriptors. Let us make sure the outcome of vhost_init_is_le never depend on the state it is actually supposed to initialize, and fix virtio_net by removing the reset from vhost_vq_init_access. With the above, there is no reason for vhost_reset_is_le to do just half of the job. Let us make vhost_reset_is_le reinitialize is_le. Signed-off-by: Halil Pasic Reported-by: Michael A. Tebolt Reported-by: Dr. David Alan Gilbert Fixes: commit 2751c9882b94 ("vhost: cross-endian support for legacy devices") Cc: Signed-off-by: Michael S. Tsirkin Reviewed-by: Greg Kurz Tested-by: Michael A. Tebolt --- drivers/vhost/vhost.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index d6432603880c..8f99fe08de02 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -130,14 +130,14 @@ static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, static void vhost_init_is_le(struct vhost_virtqueue *vq) { - if (vhost_has_feature(vq, VIRTIO_F_VERSION_1)) - vq->is_le = true; + vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) + || virtio_legacy_is_little_endian(); } #endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */ static void vhost_reset_is_le(struct vhost_virtqueue *vq) { - vq->is_le = virtio_legacy_is_little_endian(); + vhost_init_is_le(vq); } struct vhost_flush_struct { @@ -1714,10 +1714,8 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq) int r; bool is_le = vq->is_le; - if (!vq->private_data) { - vhost_reset_is_le(vq); + if (!vq->private_data) return 0; - } vhost_init_is_le(vq); From 79134d11d030b886106bf45a5638c1ccb1f0856c Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Fri, 3 Feb 2017 16:48:14 +0530 Subject: [PATCH 096/131] MAINTAINERS: update email address for Amit Shah I'm leaving my job at Red Hat, this email address will stop working next week. Update it to one that I will have access to later. Signed-off-by: Amit Shah Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 5f10c28b2e15..e0f979294e23 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13066,7 +13066,7 @@ F: drivers/input/serio/userio.c F: include/uapi/linux/userio.h VIRTIO CONSOLE DRIVER -M: Amit Shah +M: Amit Shah L: virtualization@lists.linux-foundation.org S: Maintained F: drivers/char/virtio_console.c From d7b028f56a971a2e4d8d7887540a144eeefcd4ab Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Fri, 3 Feb 2017 13:13:09 -0800 Subject: [PATCH 097/131] zswap: disable changing params if init fails Add zswap_init_failed bool that prevents changing any of the module params, if init_zswap() fails, and set zswap_enabled to false. Change 'enabled' param to a callback, and check zswap_init_failed before allowing any change to 'enabled', 'zpool', or 'compressor' params. Any driver that is built-in to the kernel will not be unloaded if its init function returns error, and its module params remain accessible for users to change via sysfs. Since zswap uses param callbacks, which assume that zswap has been initialized, changing the zswap params after a failed initialization will result in WARNING due to the param callbacks expecting a pool to already exist. This prevents that by immediately exiting any of the param callbacks if initialization failed. This was reported here: https://marc.info/?l=linux-mm&m=147004228125528&w=4 And fixes this WARNING: [ 429.723476] WARNING: CPU: 0 PID: 5140 at mm/zswap.c:503 __zswap_pool_current+0x56/0x60 The warning is just noise, and not serious. However, when init fails, zswap frees all its percpu dstmem pages and its kmem cache. The kmem cache might be serious, if kmem_cache_alloc(NULL, gfp) has problems; but the percpu dstmem pages are definitely a problem, as they're used as temporary buffer for compressed pages before copying into place in the zpool. If the user does get zswap enabled after an init failure, then zswap will likely Oops on the first page it tries to compress (or worse, start corrupting memory). Fixes: 90b0fc26d5db ("zswap: change zpool/compressor at runtime") Link: http://lkml.kernel.org/r/20170124200259.16191-2-ddstreet@ieee.org Signed-off-by: Dan Streetman Reported-by: Marcin Miroslaw Cc: Seth Jennings Cc: Michal Hocko Cc: Sergey Senozhatsky Cc: Minchan Kim Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/zswap.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/mm/zswap.c b/mm/zswap.c index 067a0d62f318..cabf09e0128b 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -78,7 +78,13 @@ static u64 zswap_duplicate_entry; /* Enable/disable zswap (disabled by default) */ static bool zswap_enabled; -module_param_named(enabled, zswap_enabled, bool, 0644); +static int zswap_enabled_param_set(const char *, + const struct kernel_param *); +static struct kernel_param_ops zswap_enabled_param_ops = { + .set = zswap_enabled_param_set, + .get = param_get_bool, +}; +module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644); /* Crypto compressor to use */ #define ZSWAP_COMPRESSOR_DEFAULT "lzo" @@ -176,6 +182,9 @@ static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; +/* fatal error during init */ +static bool zswap_init_failed; + /********************************* * helpers and fwd declarations **********************************/ @@ -624,6 +633,11 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, char *s = strstrip((char *)val); int ret; + if (zswap_init_failed) { + pr_err("can't set param, initialization failed\n"); + return -ENODEV; + } + /* no change required */ if (!strcmp(s, *(char **)kp->arg)) return 0; @@ -703,6 +717,17 @@ static int zswap_zpool_param_set(const char *val, return __zswap_param_set(val, kp, NULL, zswap_compressor); } +static int zswap_enabled_param_set(const char *val, + const struct kernel_param *kp) +{ + if (zswap_init_failed) { + pr_err("can't enable, initialization failed\n"); + return -ENODEV; + } + + return param_set_bool(val, kp); +} + /********************************* * writeback code **********************************/ @@ -1201,6 +1226,9 @@ hp_fail: dstmem_fail: zswap_entry_cache_destroy(); cache_fail: + /* if built-in, we aren't unloaded on failure; don't allow use */ + zswap_init_failed = true; + zswap_enabled = false; return -ENOMEM; } /* must be late so crypto has time to come up */ From 4f40c6e5627ea73b4e7c615c59631f38cc880885 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 3 Feb 2017 13:13:12 -0800 Subject: [PATCH 098/131] kasan: respect /proc/sys/kernel/traceoff_on_warning After much waiting I finally reproduced a KASAN issue, only to find my trace-buffer empty of useful information because it got spooled out :/ Make kasan_report honour the /proc/sys/kernel/traceoff_on_warning interface. Link: http://lkml.kernel.org/r/20170125164106.3514-1-aryabinin@virtuozzo.com Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Andrey Ryabinin Acked-by: Alexander Potapenko Cc: Dmitry Vyukov Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/report.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index b82b3e215157..f479365530b6 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -13,6 +13,7 @@ * */ +#include #include #include #include @@ -300,6 +301,8 @@ void kasan_report(unsigned long addr, size_t size, if (likely(!kasan_report_enabled())) return; + disable_trace_on_warning(); + info.access_addr = (void *)addr; info.access_size = size; info.is_write = is_write; From 253fd0f02040a19c6fe80e4171659fa3482a422d Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 3 Feb 2017 13:13:15 -0800 Subject: [PATCH 099/131] shmem: fix sleeping from atomic context Syzkaller fuzzer managed to trigger this: BUG: sleeping function called from invalid context at mm/shmem.c:852 in_atomic(): 1, irqs_disabled(): 0, pid: 529, name: khugepaged 3 locks held by khugepaged/529: #0: (shrinker_rwsem){++++..}, at: [] shrink_slab.part.59+0x121/0xd30 mm/vmscan.c:451 #1: (&type->s_umount_key#29){++++..}, at: [] trylock_super+0x20/0x100 fs/super.c:392 #2: (&(&sbinfo->shrinklist_lock)->rlock){+.+.-.}, at: [] spin_lock include/linux/spinlock.h:302 [inline] #2: (&(&sbinfo->shrinklist_lock)->rlock){+.+.-.}, at: [] shmem_unused_huge_shrink+0x28e/0x1490 mm/shmem.c:427 CPU: 2 PID: 529 Comm: khugepaged Not tainted 4.10.0-rc5+ #201 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: shmem_undo_range+0xb20/0x2710 mm/shmem.c:852 shmem_truncate_range+0x27/0xa0 mm/shmem.c:939 shmem_evict_inode+0x35f/0xca0 mm/shmem.c:1030 evict+0x46e/0x980 fs/inode.c:553 iput_final fs/inode.c:1515 [inline] iput+0x589/0xb20 fs/inode.c:1542 shmem_unused_huge_shrink+0xbad/0x1490 mm/shmem.c:446 shmem_unused_huge_scan+0x10c/0x170 mm/shmem.c:512 super_cache_scan+0x376/0x450 fs/super.c:106 do_shrink_slab mm/vmscan.c:378 [inline] shrink_slab.part.59+0x543/0xd30 mm/vmscan.c:481 shrink_slab mm/vmscan.c:2592 [inline] shrink_node+0x2c7/0x870 mm/vmscan.c:2592 shrink_zones mm/vmscan.c:2734 [inline] do_try_to_free_pages+0x369/0xc80 mm/vmscan.c:2776 try_to_free_pages+0x3c6/0x900 mm/vmscan.c:2982 __perform_reclaim mm/page_alloc.c:3301 [inline] __alloc_pages_direct_reclaim mm/page_alloc.c:3322 [inline] __alloc_pages_slowpath+0xa24/0x1c30 mm/page_alloc.c:3683 __alloc_pages_nodemask+0x544/0xae0 mm/page_alloc.c:3848 __alloc_pages include/linux/gfp.h:426 [inline] __alloc_pages_node include/linux/gfp.h:439 [inline] khugepaged_alloc_page+0xc2/0x1b0 mm/khugepaged.c:750 collapse_huge_page+0x182/0x1fe0 mm/khugepaged.c:955 khugepaged_scan_pmd+0xfdf/0x12a0 mm/khugepaged.c:1208 khugepaged_scan_mm_slot mm/khugepaged.c:1727 [inline] khugepaged_do_scan mm/khugepaged.c:1808 [inline] khugepaged+0xe9b/0x1590 mm/khugepaged.c:1853 kthread+0x326/0x3f0 kernel/kthread.c:227 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430 The iput() from atomic context was a bad idea: if after igrab() somebody else calls iput() and we left with the last inode reference, our iput() would lead to inode eviction and therefore sleeping. This patch should fix the situation. Link: http://lkml.kernel.org/r/20170131093141.GA15899@node.shutemov.name Signed-off-by: Kirill A. Shutemov Reported-by: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index bb53285a1d99..3a7587a0314d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -415,6 +415,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { LIST_HEAD(list), *pos, *next; + LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; struct page *page; @@ -441,9 +442,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, /* Check if there's anything to gain */ if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { - list_del_init(&info->shrinklist); + list_move(&info->shrinklist, &to_remove); removed++; - iput(inode); goto next; } @@ -454,6 +454,13 @@ next: } spin_unlock(&sbinfo->shrinklist_lock); + list_for_each_safe(pos, next, &to_remove) { + info = list_entry(pos, struct shmem_inode_info, shrinklist); + inode = &info->vfs_inode; + list_del_init(&info->shrinklist); + iput(inode); + } + list_for_each_safe(pos, next, &list) { int ret; From 35f860f9ba6aac56cc38e8b18916d833a83f1157 Mon Sep 17 00:00:00 2001 From: David Lin Date: Fri, 3 Feb 2017 13:13:18 -0800 Subject: [PATCH 100/131] jump label: pass kbuild_cflags when checking for asm goto support Some versions of ARM GCC compiler such as Android toolchain throws in a '-fpic' flag by default. This causes the gcc-goto check script to fail although some config would have '-fno-pic' flag in the KBUILD_CFLAGS. This patch passes the KBUILD_CFLAGS to the check script so that the script does not rely on the default config from different compilers. Link: http://lkml.kernel.org/r/20170120234329.78868-1-dtwlin@google.com Signed-off-by: David Lin Acked-by: Steven Rostedt Cc: Michal Marek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 96b27a888285..d7b758a1ce14 100644 --- a/Makefile +++ b/Makefile @@ -797,7 +797,7 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) KBUILD_ARFLAGS := $(call ar-option,D) # check for 'asm goto' -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y) +ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y) KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO endif From deb88a2a19e85842d79ba96b05031739ec327ff4 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Fri, 3 Feb 2017 13:13:20 -0800 Subject: [PATCH 101/131] mm/memory_hotplug.c: check start_pfn in test_pages_in_a_zone() Patch series "fix a kernel oops when reading sysfs valid_zones", v2. A sysfs memory file is created for each 2GiB memory block on x86-64 when the system has 64GiB or more memory. [1] When the start address of a memory block is not backed by struct page, i.e. a memory range is not aligned by 2GiB, reading its 'valid_zones' attribute file leads to a kernel oops. This issue was observed on multiple x86-64 systems with more than 64GiB of memory. This patch-set fixes this issue. Patch 1 first fixes an issue in test_pages_in_a_zone(), which does not test the start section. Patch 2 then fixes the kernel oops by extending test_pages_in_a_zone() to return valid [start, end). Note for stable kernels: The memory block size change was made by commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems"), which was accepted to 3.9. However, this patch-set depends on (and fixes) the change to test_pages_in_a_zone() made by commit 5f0f2887f4de ("mm/memory_hotplug.c: check for missing sections in test_pages_in_a_zone()"), which was accepted to 4.4. So, I recommend that we backport it up to 4.4. [1] 'Commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems")' This patch (of 2): test_pages_in_a_zone() does not check 'start_pfn' when it is aligned by section since 'sec_end_pfn' is set equal to 'pfn'. Since this function is called for testing the range of a sysfs memory file, 'start_pfn' is always aligned by section. Fix it by properly setting 'sec_end_pfn' to the next section pfn. Also make sure that this function returns 1 only when the range belongs to a zone. Link: http://lkml.kernel.org/r/20170127222149.30893-2-toshi.kani@hpe.com Signed-off-by: Toshi Kani Cc: Andrew Banman Cc: Reza Arbab Cc: Greg KH Cc: [4.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ca2723d47338..1218f73890b6 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1483,7 +1483,7 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) } /* - * Confirm all pages in a range [start, end) is belongs to the same zone. + * Confirm all pages in a range [start, end) belong to the same zone. */ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) { @@ -1491,9 +1491,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) struct zone *zone = NULL; struct page *page; int i; - for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn); + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1); pfn < end_pfn; - pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) { + pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) { /* Make sure the memory section is present first */ if (!present_section_nr(pfn_to_section_nr(pfn))) continue; @@ -1512,7 +1512,11 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) zone = page_zone(page); } } - return 1; + + if (zone) + return 1; + else + return 0; } /* From a96dfddbcc04336bbed50dc2b24823e45e09e80c Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Fri, 3 Feb 2017 13:13:23 -0800 Subject: [PATCH 102/131] base/memory, hotplug: fix a kernel oops in show_valid_zones() Reading a sysfs "memoryN/valid_zones" file leads to the following oops when the first page of a range is not backed by struct page. show_valid_zones() assumes that 'start_pfn' is always valid for page_zone(). BUG: unable to handle kernel paging request at ffffea017a000000 IP: show_valid_zones+0x6f/0x160 This issue may happen on x86-64 systems with 64GiB or more memory since their memory block size is bumped up to 2GiB. [1] An example of such systems is desribed below. 0x3240000000 is only aligned by 1GiB and this memory block starts from 0x3200000000, which is not backed by struct page. BIOS-e820: [mem 0x0000003240000000-0x000000603fffffff] usable Since test_pages_in_a_zone() already checks holes, fix this issue by extending this function to return 'valid_start' and 'valid_end' for a given range. show_valid_zones() then proceeds with the valid range. [1] 'Commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems")' Link: http://lkml.kernel.org/r/20170127222149.30893-3-toshi.kani@hpe.com Signed-off-by: Toshi Kani Cc: Greg Kroah-Hartman Cc: Zhang Zhen Cc: Reza Arbab Cc: David Rientjes Cc: Dan Williams Cc: [4.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 12 ++++++------ include/linux/memory_hotplug.h | 3 ++- mm/memory_hotplug.c | 20 +++++++++++++++----- 3 files changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index dacb6a8418aa..fa26ffd25fa6 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -389,33 +389,33 @@ static ssize_t show_valid_zones(struct device *dev, { struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn, end_pfn; + unsigned long valid_start, valid_end, valid_pages; unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; - struct page *first_page; struct zone *zone; int zone_shift = 0; start_pfn = section_nr_to_pfn(mem->start_section_nr); end_pfn = start_pfn + nr_pages; - first_page = pfn_to_page(start_pfn); /* The block contains more than one zone can not be offlined. */ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return sprintf(buf, "none\n"); - zone = page_zone(first_page); + zone = page_zone(pfn_to_page(valid_start)); + valid_pages = valid_end - valid_start; /* MMOP_ONLINE_KEEP */ sprintf(buf, "%s", zone->name); /* MMOP_ONLINE_KERNEL */ - zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL, &zone_shift); + zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); } /* MMOP_ONLINE_MOVABLE */ - zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE, &zone_shift); + zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index c1784c0b4f35..134a2f69c21a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -85,7 +85,8 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long, unsigned long, int); -extern int test_pages_in_a_zone(unsigned long, unsigned long); +extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, + unsigned long *valid_start, unsigned long *valid_end); extern void __offline_isolated_pages(unsigned long, unsigned long); typedef void (*online_page_callback_t)(struct page *page); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1218f73890b6..b8c11e063ff0 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1484,10 +1484,13 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) /* * Confirm all pages in a range [start, end) belong to the same zone. + * When true, return its valid [start, end). */ -int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) +int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, + unsigned long *valid_start, unsigned long *valid_end) { unsigned long pfn, sec_end_pfn; + unsigned long start, end; struct zone *zone = NULL; struct page *page; int i; @@ -1509,14 +1512,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; + if (!zone) + start = pfn + i; zone = page_zone(page); + end = pfn + MAX_ORDER_NR_PAGES; } } - if (zone) + if (zone) { + *valid_start = start; + *valid_end = end; return 1; - else + } else { return 0; + } } /* @@ -1843,6 +1852,7 @@ static int __ref __offline_pages(unsigned long start_pfn, long offlined_pages; int ret, drain, retry_max, node; unsigned long flags; + unsigned long valid_start, valid_end; struct zone *zone; struct memory_notify arg; @@ -1853,10 +1863,10 @@ static int __ref __offline_pages(unsigned long start_pfn, return -EINVAL; /* This makes hotplug much easier...and readable. we assume this for now. .*/ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return -EINVAL; - zone = page_zone(pfn_to_page(start_pfn)); + zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; From d1908f52557b3230fbd63c0429f3b4b748bf2b6d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 3 Feb 2017 13:13:26 -0800 Subject: [PATCH 103/131] fs: break out of iomap_file_buffered_write on fatal signals Tetsuo has noticed that an OOM stress test which performs large write requests can cause the full memory reserves depletion. He has tracked this down to the following path __alloc_pages_nodemask+0x436/0x4d0 alloc_pages_current+0x97/0x1b0 __page_cache_alloc+0x15d/0x1a0 mm/filemap.c:728 pagecache_get_page+0x5a/0x2b0 mm/filemap.c:1331 grab_cache_page_write_begin+0x23/0x40 mm/filemap.c:2773 iomap_write_begin+0x50/0xd0 fs/iomap.c:118 iomap_write_actor+0xb5/0x1a0 fs/iomap.c:190 ? iomap_write_end+0x80/0x80 fs/iomap.c:150 iomap_apply+0xb3/0x130 fs/iomap.c:79 iomap_file_buffered_write+0x68/0xa0 fs/iomap.c:243 ? iomap_write_end+0x80/0x80 xfs_file_buffered_aio_write+0x132/0x390 [xfs] ? remove_wait_queue+0x59/0x60 xfs_file_write_iter+0x90/0x130 [xfs] __vfs_write+0xe5/0x140 vfs_write+0xc7/0x1f0 ? syscall_trace_enter+0x1d0/0x380 SyS_write+0x58/0xc0 do_syscall_64+0x6c/0x200 entry_SYSCALL64_slow_path+0x25/0x25 the oom victim has access to all memory reserves to make a forward progress to exit easier. But iomap_file_buffered_write and other callers of iomap_apply loop to complete the full request. We need to check for fatal signals and back off with a short write instead. As the iomap_apply delegates all the work down to the actor we have to hook into those. All callers that work with the page cache are calling iomap_write_begin so we will check for signals there. dax_iomap_actor has to handle the situation explicitly because it copies data to the userspace directly. Other callers like iomap_page_mkwrite work on a single page or iomap_fiemap_actor do not allocate memory based on the given len. Fixes: 68a9f5e7007c ("xfs: implement iomap based buffered write path") Link: http://lkml.kernel.org/r/20170201092706.9966-2-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Tetsuo Handa Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: [4.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dax.c | 5 +++++ fs/iomap.c | 3 +++ 2 files changed, 8 insertions(+) diff --git a/fs/dax.c b/fs/dax.c index 3af2da5e64ce..c45598b912e1 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1031,6 +1031,11 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct blk_dax_ctl dax = { 0 }; ssize_t map_len; + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + dax.sector = dax_iomap_sector(iomap, pos); dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK; map_len = dax_map_atomic(iomap->bdev, &dax); diff --git a/fs/iomap.c b/fs/iomap.c index 354a123f170e..a51cb4c07d4d 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -114,6 +114,9 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, BUG_ON(pos + len > iomap->offset + iomap->length); + if (fatal_signal_pending(current)) + return -EINTR; + page = grab_cache_page_write_begin(inode->i_mapping, index, flags); if (!page) return -ENOMEM; From 5abf186a30a89d5b9c18a6bf93a2c192c9fd52f6 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 3 Feb 2017 13:13:29 -0800 Subject: [PATCH 104/131] mm, fs: check for fatal signals in do_generic_file_read() do_generic_file_read() can be told to perform a large request from userspace. If the system is under OOM and the reading task is the OOM victim then it has an access to memory reserves and finishing the full request can lead to the full memory depletion which is dangerous. Make sure we rather go with a short read and allow the killed task to terminate. Link: http://lkml.kernel.org/r/20170201092706.9966-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Christoph Hellwig Cc: Tetsuo Handa Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/mm/filemap.c b/mm/filemap.c index b772a33ef640..3f9afded581b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1791,6 +1791,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, cond_resched(); find_page: + if (fatal_signal_pending(current)) { + error = -EINTR; + goto out; + } + page = find_get_page(mapping, index); if (!page) { page_cache_sync_readahead(mapping, From 6e978b22efa1db9f6e71b24440b5f1d93e968ee3 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Fri, 3 Feb 2017 14:18:39 -0800 Subject: [PATCH 105/131] cpufreq: intel_pstate: Disable energy efficiency optimization Some Kabylake desktop processors may not reach max turbo when running in HWP mode, even if running under sustained 100% utilization. This occurs when the HWP.EPP (Energy Performance Preference) is set to "balance_power" (0x80) -- the default on most systems. It occurs because the platform BIOS may erroneously enable an energy-efficiency setting -- MSR_IA32_POWER_CTL BIT-EE, which is not recommended to be enabled on this SKU. On the failing systems, this BIOS issue was not discovered when the desktop motherboard was tested with Windows, because the BIOS also neglects to provide the ACPI/CPPC table, that Windows requires to enable HWP, and so Windows runs in legacy P-state mode, where this setting has no effect. Linux' intel_pstate driver does not require ACPI/CPPC to enable HWP, and so it runs in HWP mode, exposing this incorrect BIOS configuration. There are several ways to address this problem. First, Linux can also run in legacy P-state mode on this system. As intel_pstate is how Linux enables HWP, booting with "intel_pstate=disable" will run in acpi-cpufreq/ondemand legacy p-state mode. Or second, the "performance" governor can be used with intel_pstate, which will modify HWP.EPP to 0. Or third, starting in 4.10, the /sys/devices/system/cpu/cpufreq/policy*/energy_performance_preference attribute in can be updated from "balance_power" to "performance". Or fourth, apply this patch, which fixes the erroneous setting of MSR_IA32_POWER_CTL BIT_EE on this model, allowing the default configuration to function as designed. Signed-off-by: Srinivas Pandruvada Reviewed-by: Len Brown Cc: 4.6+ # 4.6+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f91c25718d16..86e36544925f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1235,6 +1235,25 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); } +#define MSR_IA32_POWER_CTL_BIT_EE 19 + +/* Disable energy efficiency optimization */ +static void intel_pstate_disable_ee(int cpu) +{ + u64 power_ctl; + int ret; + + ret = rdmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, &power_ctl); + if (ret) + return; + + if (!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE))) { + pr_info("Disabling energy efficiency optimization\n"); + power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE); + wrmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, power_ctl); + } +} + static int atom_get_min_pstate(void) { u64 value; @@ -1845,6 +1864,11 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { {} }; +static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { + ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params), + {} +}; + static int intel_pstate_init_cpu(unsigned int cpunum) { struct cpudata *cpu; @@ -1875,6 +1899,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu->cpu = cpunum; if (hwp_active) { + const struct x86_cpu_id *id; + + id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids); + if (id) + intel_pstate_disable_ee(cpunum); + intel_pstate_hwp_enable(cpu); pid_params.sample_rate_ms = 50; pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC; From a9306a63631493afc75893a4ac405d4e1cbae6aa Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 4 Feb 2017 00:44:36 +0100 Subject: [PATCH 106/131] PM / runtime: Avoid false-positive warnings from might_sleep_if() The might_sleep_if() assertions in __pm_runtime_idle(), __pm_runtime_suspend() and __pm_runtime_resume() may generate false-positive warnings in some situations. For example, that happens if a nested pm_runtime_get_sync()/pm_runtime_put() pair is executed with disabled interrupts within an outer pm_runtime_get_sync()/pm_runtime_put() section for the same device. [Generally, pm_runtime_get_sync() may sleep, so it should not be called with disabled interrupts, but in this particular case the previous pm_runtime_get_sync() guarantees that the device will not be suspended, so the inner pm_runtime_get_sync() will return immediately after incrementing the device's usage counter.] That started to happen in the i915 driver in 4.10-rc, leading to the following splat: BUG: sleeping function called from invalid context at drivers/base/power/runtime.c:1032 in_atomic(): 1, irqs_disabled(): 0, pid: 1500, name: Xorg 1 lock held by Xorg/1500: #0: (&dev->struct_mutex){+.+.+.}, at: [] i915_mutex_lock_interruptible+0x43/0x140 [i915] CPU: 0 PID: 1500 Comm: Xorg Not tainted Call Trace: dump_stack+0x85/0xc2 ___might_sleep+0x196/0x260 __might_sleep+0x53/0xb0 __pm_runtime_resume+0x7a/0x90 intel_runtime_pm_get+0x25/0x90 [i915] aliasing_gtt_bind_vma+0xaa/0xf0 [i915] i915_vma_bind+0xaf/0x1e0 [i915] i915_gem_execbuffer_relocate_entry+0x513/0x6f0 [i915] i915_gem_execbuffer_relocate_vma.isra.34+0x188/0x250 [i915] ? trace_hardirqs_on+0xd/0x10 ? i915_gem_execbuffer_reserve_vma.isra.31+0x152/0x1f0 [i915] ? i915_gem_execbuffer_reserve.isra.32+0x372/0x3a0 [i915] i915_gem_do_execbuffer.isra.38+0xa70/0x1a40 [i915] ? __might_fault+0x4e/0xb0 i915_gem_execbuffer2+0xc5/0x260 [i915] ? __might_fault+0x4e/0xb0 drm_ioctl+0x206/0x450 [drm] ? i915_gem_execbuffer+0x340/0x340 [i915] ? __fget+0x5/0x200 do_vfs_ioctl+0x91/0x6f0 ? __fget+0x111/0x200 ? __fget+0x5/0x200 SyS_ioctl+0x79/0x90 entry_SYSCALL_64_fastpath+0x23/0xc6 even though the code triggering it is correct. Unfortunately, the might_sleep_if() assertions in question are too coarse-grained to cover such cases correctly, so make them a bit less sensitive in order to avoid the false-positives. Reported-and-tested-by: Sedat Dilek Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 872eac4cb1df..a14fac6a01d3 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -966,13 +966,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); - if (rpmflags & RPM_GET_PUT) { if (!atomic_dec_and_test(&dev->power.usage_count)) return 0; } + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); @@ -998,13 +998,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); - if (rpmflags & RPM_GET_PUT) { if (!atomic_dec_and_test(&dev->power.usage_count)) return 0; } + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); @@ -1029,7 +1029,8 @@ int __pm_runtime_resume(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && + dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); From bfb34527a32a1a576d9bfb7026d3ab0369a6cd60 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 4 Feb 2017 14:47:31 -0800 Subject: [PATCH 107/131] libnvdimm, pfn: fix memmap reservation size versus 4K alignment When vmemmap_populate() allocates space for the memmap it does so in 2MB sized chunks. The libnvdimm-pfn driver incorrectly accounts for this when the alignment of the device is set to 4K. When this happens we trigger memory allocation failures in altmap_alloc_block_buf() and trigger warnings of the form: WARNING: CPU: 0 PID: 3376 at arch/x86/mm/init_64.c:656 arch_add_memory+0xe4/0xf0 [..] Call Trace: dump_stack+0x86/0xc3 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 arch_add_memory+0xe4/0xf0 devm_memremap_pages+0x29b/0x4e0 Fixes: 315c562536c4 ("libnvdimm, pfn: add 'align' attribute, default to HPAGE_SIZE") Cc: Signed-off-by: Dan Williams --- drivers/nvdimm/pfn_devs.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index a2ac9e641aa9..6c033c9a2f06 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -627,15 +627,12 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) size = resource_size(&nsio->res); npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K; if (nd_pfn->mode == PFN_MODE_PMEM) { - unsigned long memmap_size; - /* * vmemmap_populate_hugepages() allocates the memmap array in * HPAGE_SIZE chunks. */ - memmap_size = ALIGN(64 * npfns, HPAGE_SIZE); - offset = ALIGN(start + SZ_8K + memmap_size + dax_label_reserve, - nd_pfn->align) - start; + offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve, + max(nd_pfn->align, HPAGE_SIZE)) - start; } else if (nd_pfn->mode == PFN_MODE_RAM) offset = ALIGN(start + SZ_8K + dax_label_reserve, nd_pfn->align) - start; From 34b2cef20f19c87999fff3da4071e66937db9644 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Feb 2017 11:16:52 -0800 Subject: [PATCH 108/131] ipv4: keep skb->dst around in presence of IP options Andrey Konovalov got crashes in __ip_options_echo() when a NULL skb->dst is accessed. ipv4_pktinfo_prepare() should not drop the dst if (evil) IP options are present. We could refine the test to the presence of ts_needtime or srr, but IP options are not often used, so let's be conservative. Thanks to syzkaller team for finding this bug. Fixes: d826eb14ecef ("ipv4: PKTINFO doesnt need dst reference") Signed-off-by: Eric Dumazet Reported-by: Andrey Konovalov Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 53ae0c6315ad..900011709e3b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1238,7 +1238,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - skb_dst_drop(skb); + /* We need to keep the dst for __ip_options_echo() + * We could restrict the test to opt.ts_needtime || opt.srr, + * but the following is good enough as IP options are not often used. + */ + if (unlikely(IPCB(skb)->opt.optlen)) + skb_dst_force(skb); + else + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, From d71b7896886345c53ef1d84bda2bc758554f5d61 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Feb 2017 00:03:26 -0800 Subject: [PATCH 109/131] netlabel: out of bound access in cipso_v4_validate() syzkaller found another out of bound access in ip_options_compile(), or more exactly in cipso_v4_validate() Fixes: 20e2a8648596 ("cipso: handle CIPSO options correctly when NetLabel is disabled") Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Paul Moore Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/net/cipso_ipv4.h | 4 ++++ net/ipv4/cipso_ipv4.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index 3ebb168b9afc..a34b141f125f 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, } for (opt_iter = 6; opt_iter < opt_len;) { + if (opt_iter + 1 == opt_len) { + err_offset = opt_iter; + goto out; + } tag_len = opt[opt_iter + 1]; if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) { err_offset = opt_iter + 1; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 72d6f056d863..ae206163c273 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1587,6 +1587,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) goto validate_return_locked; } + if (opt_iter + 1 == opt_len) { + err_offset = opt_iter; + goto validate_return_locked; + } tag_len = tag[1]; if (tag_len > (opt_len - opt_iter)) { err_offset = opt_iter + 1; From 7892032cfe67f4bde6fc2ee967e45a8fbaf33756 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Feb 2017 23:18:55 -0800 Subject: [PATCH 110/131] ip6_gre: fix ip6gre_err() invalid reads Andrey Konovalov reported out of bound accesses in ip6gre_err() If GRE flags contains GRE_KEY, the following expression *(((__be32 *)p) + (grehlen / 4) - 1) accesses data ~40 bytes after the expected point, since grehlen includes the size of IPv6 headers. Let's use a "struct gre_base_hdr *greh" pointer to make this code more readable. p[1] becomes greh->protocol. grhlen is the GRE header length. Fixes: c12b395a4664 ("gre: Support GRE over IPv6") Signed-off-by: Eric Dumazet Reported-by: Andrey Konovalov Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 40 +++++++++++++++++++++------------------- 1 file changed, 21 insertions(+), 19 deletions(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 558631860d91..630b73be5999 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -367,35 +367,37 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; - __be16 *p = (__be16 *)(skb->data + offset); - int grehlen = offset + 4; + const struct gre_base_hdr *greh; + const struct ipv6hdr *ipv6h; + int grehlen = sizeof(*greh); struct ip6_tnl *t; + int key_off = 0; __be16 flags; + __be32 key; - flags = p[0]; - if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) { - if (flags&(GRE_VERSION|GRE_ROUTING)) - return; - if (flags&GRE_KEY) { - grehlen += 4; - if (flags&GRE_CSUM) - grehlen += 4; - } + if (!pskb_may_pull(skb, offset + grehlen)) + return; + greh = (const struct gre_base_hdr *)(skb->data + offset); + flags = greh->flags; + if (flags & (GRE_VERSION | GRE_ROUTING)) + return; + if (flags & GRE_CSUM) + grehlen += 4; + if (flags & GRE_KEY) { + key_off = grehlen + offset; + grehlen += 4; } - /* If only 8 bytes returned, keyed message will be dropped here */ - if (!pskb_may_pull(skb, grehlen)) + if (!pskb_may_pull(skb, offset + grehlen)) return; ipv6h = (const struct ipv6hdr *)skb->data; - p = (__be16 *)(skb->data + offset); + greh = (const struct gre_base_hdr *)(skb->data + offset); + key = key_off ? *(__be32 *)(skb->data + key_off) : 0; t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, - flags & GRE_KEY ? - *(((__be32 *)p) + (grehlen / 4) - 1) : 0, - p[1]); + key, greh->protocol); if (!t) return; From d5adbfcd5f7bcc6fa58a41c5c5ada0e5c826ce2c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 5 Feb 2017 15:10:58 -0800 Subject: [PATCH 111/131] Linux 4.10-rc7 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index d7b758a1ce14..8e223e081c9d 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Fearless Coyote # *DOCUMENTATION* From e479ab651f071dbd1518ce8fb121c7f42f2bb97d Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sat, 4 Feb 2017 13:59:22 +0200 Subject: [PATCH 112/131] mac80211: Fix FILS AEAD protection in Association Request frame Incorrect num_elem parameter value (1 vs. 5) was used in the aes_siv_encrypt() call. This resulted in only the first one of the five AAD vectors to SIV getting included in calculation. This does not protect all the contents correctly and would not interoperate with a standard compliant implementation. Fix this by using the correct number. A matching fix is needed in the AP side (hostapd) to get FILS authentication working properly. Fixes: 39404feee691 ("mac80211: FILS AEAD protection for station mode association frames") Reported-by: Ard Biesheuvel Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- net/mac80211/fils_aead.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c index ecfdd97758a3..e795aaa2aa1f 100644 --- a/net/mac80211/fils_aead.c +++ b/net/mac80211/fils_aead.c @@ -272,7 +272,7 @@ int fils_encrypt_assoc_req(struct sk_buff *skb, crypt_len = skb->data + skb->len - encr; skb_put(skb, AES_BLOCK_SIZE); return aes_siv_encrypt(assoc_data->fils_kek, assoc_data->fils_kek_len, - encr, crypt_len, 1, addr, len, encr); + encr, crypt_len, 5, addr, len, encr); } int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata, From 01fba20b5976e445676febbdf6dc78d71c6d7b62 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sat, 4 Feb 2017 18:08:42 +0200 Subject: [PATCH 113/131] mac80211: Allocate a sync skcipher explicitly for FILS AEAD The skcipher could have been of the async variant which may return from skcipher_encrypt() with -EINPROGRESS after having queued the request. The FILS AEAD implementation here does not have code for dealing with that possibility, so allocate a sync cipher explicitly to avoid potential issues with hardware accelerators. This is based on the patch sent out by Ard. Fixes: 39404feee691 ("mac80211: FILS AEAD protection for station mode association frames") Reported-by: Ard Biesheuvel Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- net/mac80211/fils_aead.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c index e795aaa2aa1f..5c3af5eb4052 100644 --- a/net/mac80211/fils_aead.c +++ b/net/mac80211/fils_aead.c @@ -124,7 +124,7 @@ static int aes_siv_encrypt(const u8 *key, size_t key_len, /* CTR */ - tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0); + tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm2)) { kfree(tmp); return PTR_ERR(tfm2); @@ -183,7 +183,7 @@ static int aes_siv_decrypt(const u8 *key, size_t key_len, /* CTR */ - tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0); + tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm2)) return PTR_ERR(tfm2); /* K2 for CTR */ From da7061c82e4a1bc6a5e134ef362c86261906c860 Mon Sep 17 00:00:00 2001 From: Thorsten Horstmann Date: Fri, 3 Feb 2017 14:38:29 +0100 Subject: [PATCH 114/131] mac80211: Fix adding of mesh vendor IEs The function ieee80211_ie_split_vendor doesn't return 0 on errors. Instead it returns any offset < ielen when WLAN_EID_VENDOR_SPECIFIC is found. The return value in mesh_add_vendor_ies must therefore be checked against ifmsh->ie_len and not 0. Otherwise all ifmsh->ie starting with WLAN_EID_VENDOR_SPECIFIC will be rejected. Fixes: 082ebb0c258d ("mac80211: fix mesh beacon format") Signed-off-by: Thorsten Horstmann Signed-off-by: Mathias Kretschmer Signed-off-by: Simon Wunderlich [sven@narfation.org: Add commit message] Signed-off-by: Sven Eckelmann Signed-off-by: Johannes Berg --- net/mac80211/mesh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 42120d965263..50e1b7f78bd4 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -339,7 +339,7 @@ int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata, /* fast-forward to vendor IEs */ offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0); - if (offset) { + if (offset < ifmsh->ie_len) { len = ifmsh->ie_len - offset; data = ifmsh->ie + offset; if (skb_tailroom(skb) < len) From fd551bac4795854adaa87bad7e5136083719802b Mon Sep 17 00:00:00 2001 From: Masashi Honma Date: Thu, 26 Jan 2017 08:56:13 +0900 Subject: [PATCH 115/131] nl80211: Fix mesh HT operation check A previous change to fix checks for NL80211_MESHCONF_HT_OPMODE missed setting the flag when replacing FILL_IN_MESH_PARAM_IF_SET with checking codes. This results in dropping the received HT operation value when called by nl80211_update_mesh_config(). Fix this by setting the flag properly. Fixes: 9757235f451c ("nl80211: correct checks for NL80211_MESHCONF_HT_OPMODE value") Signed-off-by: Masashi Honma [rewrite commit message to use Fixes: line] Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5c1b267e22be..aee396b9f190 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5916,6 +5916,7 @@ do { \ break; } cfg->ht_opmode = ht_opmode; + mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1)); } FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout, 1, 65535, mask, From ebf6c9cb23d7e56eec8575a88071dec97ad5c6e2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Feb 2017 20:23:22 -0800 Subject: [PATCH 116/131] ipv6: tcp: add a missing tcp_v6_restore_cb() Dmitry reported use-after-free in ip6_datagram_recv_specific_ctl() A similar bug was fixed in commit 8ce48623f0cf ("ipv6: tcp: restore IP6CB for pktoptions skbs"), but I missed another spot. tcp_v6_syn_recv_sock() can indeed set np->pktoptions from ireq->pktopts Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index cb8929681dc7..eaad72c3d746 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -991,6 +991,16 @@ drop: return 0; /* don't send reset */ } +static void tcp_v6_restore_cb(struct sk_buff *skb) +{ + /* We need to move header back to the beginning if xfrm6_policy_check() + * and tcp_v6_fill_cb() are going to be called again. + * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. + */ + memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, + sizeof(struct inet6_skb_parm)); +} + static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, @@ -1182,8 +1192,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * sk_gfp_mask(sk, GFP_ATOMIC)); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) + if (newnp->pktoptions) { + tcp_v6_restore_cb(newnp->pktoptions); skb_set_owner_r(newnp->pktoptions, newsk); + } } } @@ -1198,16 +1210,6 @@ out: return NULL; } -static void tcp_v6_restore_cb(struct sk_buff *skb) -{ - /* We need to move header back to the beginning if xfrm6_policy_check() - * and tcp_v6_fill_cb() are going to be called again. - * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. - */ - memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, - sizeof(struct inet6_skb_parm)); -} - /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * From a088d1d73a4bcfd7bc482f8d08375b9b665dc3e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Fri, 3 Feb 2017 08:11:03 +0100 Subject: [PATCH 117/131] ipv6: Fix IPv6 packet loss in scenarios involving roaming + snooping switches MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When for instance a mobile Linux device roams from one access point to another with both APs sharing the same broadcast domain and a multicast snooping switch in between: 1) (c) <~~~> (AP1) <--[SSW]--> (AP2) 2) (AP1) <--[SSW]--> (AP2) <~~~> (c) Then currently IPv6 multicast packets will get lost for (c) until an MLD Querier sends its next query message. The packet loss occurs because upon roaming the Linux host so far stayed silent regarding MLD and the snooping switch will therefore be unaware of the multicast topology change for a while. This patch fixes this by always resending MLD reports when an interface change happens, for instance from NO-CARRIER to CARRIER state. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f60e88e56255..81f7b4ea4281 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3386,9 +3386,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } if (idev) { - if (idev->if_flags & IF_READY) - /* device is already configured. */ + if (idev->if_flags & IF_READY) { + /* device is already configured - + * but resend MLD reports, we might + * have roamed and need to update + * multicast snooping switches + */ + ipv6_mc_up(idev); break; + } idev->if_flags |= IF_READY; } From b3f2d07f4649adcf6905953a10d217b5683e4077 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 3 Feb 2017 17:35:46 +0100 Subject: [PATCH 118/131] hns: avoid stack overflow with CONFIG_KASAN The use of ACCESS_ONCE() looks like a micro-optimization to force gcc to use an indexed load for the register address, but it has an absolutely detrimental effect on builds with gcc-5 and CONFIG_KASAN=y, leading to a very likely kernel stack overflow aside from very complex object code: hisilicon/hns/hns_dsaf_gmac.c: In function 'hns_gmac_update_stats': hisilicon/hns/hns_dsaf_gmac.c:419:1: error: the frame size of 2912 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_ppe.c: In function 'hns_ppe_reset_common': hisilicon/hns/hns_dsaf_ppe.c:390:1: error: the frame size of 1184 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_ppe.c: In function 'hns_ppe_get_regs': hisilicon/hns/hns_dsaf_ppe.c:621:1: error: the frame size of 3632 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_rcb.c: In function 'hns_rcb_get_common_regs': hisilicon/hns/hns_dsaf_rcb.c:970:1: error: the frame size of 2784 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_gmac.c: In function 'hns_gmac_get_regs': hisilicon/hns/hns_dsaf_gmac.c:641:1: error: the frame size of 5728 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_rcb.c: In function 'hns_rcb_get_ring_regs': hisilicon/hns/hns_dsaf_rcb.c:1021:1: error: the frame size of 2208 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_comm_init': hisilicon/hns/hns_dsaf_main.c:1209:1: error: the frame size of 1904 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_xgmac.c: In function 'hns_xgmac_get_regs': hisilicon/hns/hns_dsaf_xgmac.c:748:1: error: the frame size of 4704 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_update_stats': hisilicon/hns/hns_dsaf_main.c:2420:1: error: the frame size of 1088 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_get_regs': hisilicon/hns/hns_dsaf_main.c:2753:1: error: the frame size of 10768 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] This does not seem to happen any more with gcc-7, but removing the ACCESS_ONCE seems safe anyway and it avoids a serious issue for some people. I have verified that with gcc-5.3.1, the object code we get is better in the new version both with and without CONFIG_KASAN, as we no longer allocate a 1344 byte stack frame for hns_dsaf_get_regs() but otherwise have practically identical object code. With gcc-7.0.0, removing ACCESS_ONCE has no effect, the object code is already good either way. This patch is probably not urgent to get into 4.11 as only KASAN=y builds with certain compilers are affected, but I still think it makes sense to backport into older kernels. Cc: stable@vger.kernel.org Fixes: 511e6bc ("net: add Hisilicon Network Subsystem DSAF support") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index 87226685f742..8fa18fc17cd2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -1014,9 +1014,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(base); - - writel(value, reg_addr + reg); + writel(value, base + reg); } #define dsaf_write_dev(a, reg, value) \ @@ -1024,9 +1022,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg) { - u8 __iomem *reg_addr = ACCESS_ONCE(base); - - return readl(reg_addr + reg); + return readl(base + reg); } static inline void dsaf_write_syscon(struct regmap *base, u32 reg, u32 value) From ccf7abb93af09ad0868ae9033d1ca8108bdaec82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Feb 2017 14:59:38 -0800 Subject: [PATCH 119/131] tcp: avoid infinite loop in tcp_splice_read() Splicing from TCP socket is vulnerable when a packet with URG flag is received and stored into receive queue. __tcp_splice_read() returns 0, and sk_wait_data() immediately returns since there is the problematic skb in queue. This is a nice way to burn cpu (aka infinite loop) and trigger soft lockups. Again, this gem was found by syzkaller tool. Fixes: 9c55e01c0cc8 ("[TCP]: Splice receive support.") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Willy Tarreau Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4a044964da66..0efb4c7f6704 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -770,6 +770,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } + /* if __tcp_splice_read() got nothing while we have + * an skb in receive queue, we do not want to loop. + * This might happen with URG data. + */ + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); From e1edab87faf6ca30cd137e0795bc73aa9a9a22ec Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 3 Feb 2017 18:20:48 -0500 Subject: [PATCH 120/131] tun: read vnet_hdr_sz once When IFF_VNET_HDR is enabled, a virtio_net header must precede data. Data length is verified to be greater than or equal to expected header length tun->vnet_hdr_sz before copying. Read this value once and cache locally, as it can be updated between the test and use (TOCTOU). Signed-off-by: Willem de Bruijn Reported-by: Dmitry Vyukov CC: Eric Dumazet Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/tun.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2cd10b26b650..bfabe180053e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1170,9 +1170,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } if (tun->flags & IFF_VNET_HDR) { - if (len < tun->vnet_hdr_sz) + int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); + + if (len < vnet_hdr_sz) return -EINVAL; - len -= tun->vnet_hdr_sz; + len -= vnet_hdr_sz; if (!copy_from_iter_full(&gso, sizeof(gso), from)) return -EFAULT; @@ -1183,7 +1185,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (tun16_to_cpu(tun, gso.hdr_len) > len) return -EINVAL; - iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso)); + iov_iter_advance(from, vnet_hdr_sz - sizeof(gso)); } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { @@ -1335,7 +1337,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) - vnet_hdr_sz = tun->vnet_hdr_sz; + vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; From 837585a5375c38d40361cfe64e6fd11e1addb936 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 3 Feb 2017 18:20:49 -0500 Subject: [PATCH 121/131] macvtap: read vnet_hdr_size once When IFF_VNET_HDR is enabled, a virtio_net header must precede data. Data length is verified to be greater than or equal to expected header length tun->vnet_hdr_sz before copying. Macvtap functions read the value once, but unless READ_ONCE is used, the compiler may ignore this and read multiple times. Enforce a single read and locally cached value to avoid updates between test and use. Signed-off-by: Willem de Bruijn Suggested-by: Eric Dumazet Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 402618565838..c27011bbe30c 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -681,7 +681,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, size_t linear; if (q->flags & IFF_VNET_HDR) { - vnet_hdr_len = q->vnet_hdr_sz; + vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz); err = -EINVAL; if (len < vnet_hdr_len) @@ -820,7 +820,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, if (q->flags & IFF_VNET_HDR) { struct virtio_net_hdr vnet_hdr; - vnet_hdr_len = q->vnet_hdr_sz; + vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz); if (iov_iter_count(iter) < vnet_hdr_len) return -EINVAL; From 5593523f968bc86d42a035c6df47d5e0979b5ace Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 4 Feb 2017 16:56:03 +0000 Subject: [PATCH 122/131] pegasus: Use heap buffers for all register access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allocating USB buffers on the stack is not portable, and no longer works on x86_64 (with VMAP_STACK enabled as per default). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") References: https://bugs.debian.org/852556 Reported-by: Lisandro Damián Nicanor Pérez Meyer Tested-by: Lisandro Damián Nicanor Pérez Meyer Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/usb/pegasus.c | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 24e803fe9a53..36674484c6fb 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -126,40 +126,61 @@ static void async_ctrl_callback(struct urb *urb) static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data) { + u8 *buf; int ret; + buf = kmalloc(size, GFP_NOIO); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(pegasus->usb, usb_rcvctrlpipe(pegasus->usb, 0), PEGASUS_REQ_GET_REGS, PEGASUS_REQT_READ, 0, - indx, data, size, 1000); + indx, buf, size, 1000); if (ret < 0) netif_dbg(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + else if (ret <= size) + memcpy(data, buf, ret); + kfree(buf); return ret; } -static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data) +static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, + const void *data) { + u8 *buf; int ret; + buf = kmemdup(data, size, GFP_NOIO); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0), PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0, - indx, data, size, 100); + indx, buf, size, 100); if (ret < 0) netif_dbg(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + kfree(buf); return ret; } static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data) { + u8 *buf; int ret; + buf = kmemdup(&data, 1, GFP_NOIO); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0), PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data, - indx, &data, 1, 1000); + indx, buf, 1, 1000); if (ret < 0) netif_dbg(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + kfree(buf); return ret; } From 7926aff5c57b577ab0f43364ff0c59d968f6a414 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 4 Feb 2017 16:56:32 +0000 Subject: [PATCH 123/131] rtl8150: Use heap buffers for all register access Allocating USB buffers on the stack is not portable, and no longer works on x86_64 (with VMAP_STACK enabled as per default). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/usb/rtl8150.c | 34 +++++++++++++++++++++++++++------- 1 file changed, 27 insertions(+), 7 deletions(-) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 95b7bd0d7abc..c81c79110cef 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -155,16 +155,36 @@ static const char driver_name [] = "rtl8150"; */ static int get_registers(rtl8150_t * dev, u16 indx, u16 size, void *data) { - return usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), - RTL8150_REQ_GET_REGS, RTL8150_REQT_READ, - indx, 0, data, size, 500); + void *buf; + int ret; + + buf = kmalloc(size, GFP_NOIO); + if (!buf) + return -ENOMEM; + + ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), + RTL8150_REQ_GET_REGS, RTL8150_REQT_READ, + indx, 0, buf, size, 500); + if (ret > 0 && ret <= size) + memcpy(data, buf, ret); + kfree(buf); + return ret; } -static int set_registers(rtl8150_t * dev, u16 indx, u16 size, void *data) +static int set_registers(rtl8150_t * dev, u16 indx, u16 size, const void *data) { - return usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), - RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE, - indx, 0, data, size, 500); + void *buf; + int ret; + + buf = kmemdup(data, size, GFP_NOIO); + if (!buf) + return -ENOMEM; + + ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), + RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE, + indx, 0, buf, size, 500); + kfree(buf); + return ret; } static void async_set_reg_cb(struct urb *urb) From d41149145f98fe26dcd0bfd1d6cc095e6e041418 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 4 Feb 2017 16:56:56 +0000 Subject: [PATCH 124/131] catc: Combine failure cleanup code in catc_probe() Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/usb/catc.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 3daa41bdd4ea..985909eab72c 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -776,7 +776,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id struct net_device *netdev; struct catc *catc; u8 broadcast[ETH_ALEN]; - int i, pktsz; + int i, pktsz, ret; if (usb_set_interface(usbdev, intf->altsetting->desc.bInterfaceNumber, 1)) { @@ -811,12 +811,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id if ((!catc->ctrl_urb) || (!catc->tx_urb) || (!catc->rx_urb) || (!catc->irq_urb)) { dev_err(&intf->dev, "No free urbs available.\n"); - usb_free_urb(catc->ctrl_urb); - usb_free_urb(catc->tx_urb); - usb_free_urb(catc->rx_urb); - usb_free_urb(catc->irq_urb); - free_netdev(netdev); - return -ENOMEM; + ret = -ENOMEM; + goto fail_free; } /* The F5U011 has the same vendor/product as the netmate but a device version of 0x130 */ @@ -913,16 +909,21 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id usb_set_intfdata(intf, catc); SET_NETDEV_DEV(netdev, &intf->dev); - if (register_netdev(netdev) != 0) { - usb_set_intfdata(intf, NULL); - usb_free_urb(catc->ctrl_urb); - usb_free_urb(catc->tx_urb); - usb_free_urb(catc->rx_urb); - usb_free_urb(catc->irq_urb); - free_netdev(netdev); - return -EIO; - } + ret = register_netdev(netdev); + if (ret) + goto fail_clear_intfdata; + return 0; + +fail_clear_intfdata: + usb_set_intfdata(intf, NULL); +fail_free: + usb_free_urb(catc->ctrl_urb); + usb_free_urb(catc->tx_urb); + usb_free_urb(catc->rx_urb); + usb_free_urb(catc->irq_urb); + free_netdev(netdev); + return ret; } static void catc_disconnect(struct usb_interface *intf) From 2d6a0e9de03ee658a9adc3bfb2f0ca55dff1e478 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 4 Feb 2017 16:57:04 +0000 Subject: [PATCH 125/131] catc: Use heap buffer for memory size test Allocating USB buffers on the stack is not portable, and no longer works on x86_64 (with VMAP_STACK enabled as per default). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/usb/catc.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 985909eab72c..0acc9b640419 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -776,7 +776,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id struct net_device *netdev; struct catc *catc; u8 broadcast[ETH_ALEN]; - int i, pktsz, ret; + int pktsz, ret; if (usb_set_interface(usbdev, intf->altsetting->desc.bInterfaceNumber, 1)) { @@ -840,15 +840,24 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id catc->irq_buf, 2, catc_irq_done, catc, 1); if (!catc->is_f5u011) { + u32 *buf; + int i; + dev_dbg(dev, "Checking memory size\n"); - i = 0x12345678; - catc_write_mem(catc, 0x7a80, &i, 4); - i = 0x87654321; - catc_write_mem(catc, 0xfa80, &i, 4); - catc_read_mem(catc, 0x7a80, &i, 4); + buf = kmalloc(4, GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto fail_free; + } + + *buf = 0x12345678; + catc_write_mem(catc, 0x7a80, buf, 4); + *buf = 0x87654321; + catc_write_mem(catc, 0xfa80, buf, 4); + catc_read_mem(catc, 0x7a80, buf, 4); - switch (i) { + switch (*buf) { case 0x12345678: catc_set_reg(catc, TxBufCount, 8); catc_set_reg(catc, RxBufCount, 32); @@ -863,6 +872,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id dev_dbg(dev, "32k Memory\n"); break; } + + kfree(buf); dev_dbg(dev, "Getting MAC from SEEROM.\n"); From 69629464e0b587f3711739b3aa2bcdaf2e075276 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Feb 2017 09:25:24 -0800 Subject: [PATCH 126/131] udp: properly cope with csum errors Dmitry reported that UDP sockets being destroyed would trigger the WARN_ON(atomic_read(&sk->sk_rmem_alloc)); in inet_sock_destruct() It turns out we do not properly destroy skb(s) that have wrong UDP checksum. Thanks again to syzkaller team. Fixes : 7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue") Reported-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Cc: Paolo Abeni Cc: Hannes Frederic Sowa Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/sock.h | 4 +++- net/core/datagram.c | 8 ++++++-- net/ipv4/udp.c | 2 +- net/ipv6/udp.c | 2 +- 4 files changed, 11 insertions(+), 5 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index f0e867f58722..c4f5e6fca17c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2006,7 +2006,9 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags); + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); diff --git a/net/core/datagram.c b/net/core/datagram.c index 662bea587165..ea633342ab0d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -332,7 +332,9 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) EXPORT_SYMBOL(__skb_free_datagram_locked); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags) + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb)) { int err = 0; @@ -342,6 +344,8 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, if (skb == skb_peek(&sk->sk_receive_queue)) { __skb_unlink(skb, &sk->sk_receive_queue); atomic_dec(&skb->users); + if (destructor) + destructor(sk, skb); err = 0; } spin_unlock_bh(&sk->sk_receive_queue.lock); @@ -375,7 +379,7 @@ EXPORT_SYMBOL(__sk_queue_drop_skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) { - int err = __sk_queue_drop_skb(sk, skb, flags); + int err = __sk_queue_drop_skb(sk, skb, flags, NULL); kfree_skb(skb); sk_mem_reclaim_partial(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1307a7c2e544..8aab7d78d25b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1501,7 +1501,7 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags)) { + if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4d5c4eee4b3f..8990856f5101 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -441,7 +441,7 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags)) { + if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { if (is_udp4) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); From bd4ce941c8d5b862b2f83364be5dbe8fc8ab48f8 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Mon, 6 Feb 2017 10:14:31 -0800 Subject: [PATCH 127/131] mlx4: Invoke softirqs after napi_reschedule mlx4 may schedule napi from a workqueue. Afterwards, softirqs are not run in a deterministic time frame and the following message may be logged: NOHZ: local_softirq_pending 08 The problem is the same as what was described in commit ec13ee80145c ("virtio_net: invoke softirqs after __napi_schedule") and this patch applies the same fix to mlx4. Fixes: 07841f9d94c1 ("net/mlx4_en: Schedule napi when RX buffers allocation fails") Cc: Eric Dumazet Signed-off-by: Benjamin Poirier Acked-by: Eric Dumazet Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index eac527e25ec9..cc003fdf0ed9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -514,8 +514,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) return; for (ring = 0; ring < priv->rx_ring_num; ring++) { - if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) + if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) { + local_bh_disable(); napi_reschedule(&priv->rx_cq[ring]->napi); + local_bh_enable(); + } } } From 2dcab598484185dea7ec22219c76dcdd59e3cb90 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Mon, 6 Feb 2017 18:10:31 -0200 Subject: [PATCH 128/131] sctp: avoid BUG_ON on sctp_wait_for_sndbuf Alexander Popov reported that an application may trigger a BUG_ON in sctp_wait_for_sndbuf if the socket tx buffer is full, a thread is waiting on it to queue more data and meanwhile another thread peels off the association being used by the first thread. This patch replaces the BUG_ON call with a proper error handling. It will return -EPIPE to the original sendmsg call, similarly to what would have been done if the association wasn't found in the first place. Acked-by: Alexander Popov Signed-off-by: Marcelo Ricardo Leitner Reviewed-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/socket.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 37eeab7899fc..e214d2e7e9a3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -7426,7 +7426,8 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); - BUG_ON(sk != asoc->base.sk); + if (sk != asoc->base.sk) + goto do_error; lock_sock(sk); *timeo_p = current_timeo; From a524c218bc94c705886a0e0fedeee45d1931da32 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 7 Feb 2017 09:44:58 -0800 Subject: [PATCH 129/131] ARC: [arcompact] brown paper bag bug in unaligned access delay slot fixup Reported-by: Jo-Philipp Wich Fixes: 9aed02feae57bf7 ("ARC: [arcompact] handle unaligned access delay slot") Cc: linux-kernel@vger.kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta Signed-off-by: Linus Torvalds --- arch/arc/kernel/unaligned.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 91ebe382147f..5f69c3bd59bb 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -243,7 +243,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, /* clear any remanants of delay slot */ if (delay_mode(regs)) { - regs->ret = regs->bta ~1U; + regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; From 912964eacb111551db73429719eb5fadcab0ff8a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 7 Feb 2017 20:56:08 +0800 Subject: [PATCH 130/131] sctp: check af before verify address in sctp_addr_id2transport Commit 6f29a1306131 ("sctp: sctp_addr_id2transport should verify the addr before looking up assoc") invoked sctp_verify_addr to verify the addr. But it didn't check af variable beforehand, once users pass an address with family = 0 through sockopt, sctp_get_af_specific will return NULL and NULL pointer dereference will be caused by af->sockaddr_len. This patch is to fix it by returning NULL if af variable is NULL. Fixes: 6f29a1306131 ("sctp: sctp_addr_id2transport should verify the addr before looking up assoc") Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e214d2e7e9a3..1b5d669e3029 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -239,7 +239,7 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, union sctp_addr *laddr = (union sctp_addr *)addr; struct sctp_transport *transport; - if (sctp_verify_addr(sk, laddr, af->sockaddr_len)) + if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len)) return NULL; addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep, From b6789123bccba8b5feb9901ed2e8c3c39181979d Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 7 Feb 2017 11:11:16 -0800 Subject: [PATCH 131/131] mm: fix KPF_SWAPCACHE in /proc/kpageflags Commit 6326fec1122c ("mm: Use owner_priv bit for PageSwapCache, valid when PageSwapBacked") aliased PG_swapcache to PG_owner_priv_1 (and depending on PageSwapBacked being true). As a result, the KPF_SWAPCACHE bit in '/proc/kpageflags' should now be synthesized, instead of being shown on unrelated pages which just happen to have PG_owner_priv_1 set. Signed-off-by: Hugh Dickins Cc: Andrew Morton Cc: Nicholas Piggin Cc: Wu Fengguang Signed-off-by: Linus Torvalds --- fs/proc/page.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/proc/page.c b/fs/proc/page.c index a2066e6dee90..2726536489b1 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -173,7 +173,8 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active); u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim); - u |= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache); + if (PageSwapCache(page)) + u |= 1 << KPF_SWAPCACHE; u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked); u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);