4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Anna-Maria Gleixner anna-maria@linutronix.de

commit 48d0c9becc7f3c66874c100c126459a9da0fdced upstream.

The POSIX specification defines that relative CLOCK_REALTIME timers are not affected by clock modifications. Those timers have to use CLOCK_MONOTONIC to ensure POSIX compliance.

The introduction of the additional HRTIMER_MODE_PINNED mode broke this requirement for pinned timers.

There is no user space visible impact because user space timers are not using pinned mode, but for consistency reasons this needs to be fixed.

Check whether the mode has the HRTIMER_MODE_REL bit set instead of comparing with HRTIMER_MODE_ABS.

Signed-off-by: Anna-Maria Gleixner anna-maria@linutronix.de Cc: Christoph Hellwig hch@lst.de Cc: John Stultz john.stultz@linaro.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: keescook@chromium.org Fixes: 597d0275736d ("timers: Framework for identifying pinned timers") Link: http://lkml.kernel.org/r/20171221104205.7269-7-anna-maria@linutronix.de Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Mike Galbraith efault@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/time/hrtimer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1104,7 +1104,12 @@ static void __hrtimer_init(struct hrtime

cpu_base = raw_cpu_ptr(&hrtimer_bases);

- if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS) + /* + * POSIX magic: Relative CLOCK_REALTIME timers are not affected by + * clock modifications, so they needs to become CLOCK_MONOTONIC to + * ensure POSIX compliance. + */ + if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC;

base = hrtimer_clockid_to_base(clock_id);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mario Limonciello mario.limonciello@dell.com

commit 9862b43624a5450a097cc4122732857b869dbbca upstream.

There is no longer a need for the buffer to be defined in first 4GB physical address space.

Furthermore there may be race conditions with multiple different functions working on a module wide buffer causing incorrect results.

Fixes: 549b4930f057658dc50d8010e66219233119a4d8 Suggested-by: Pali Rohar pali.rohar@gmail.com Signed-off-by: Mario Limonciello mario.limonciello@dell.com Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/platform/x86/dell-laptop.c | 188 ++++++++++++++++++++----------------- 1 file changed, 103 insertions(+), 85 deletions(-)

--- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -78,7 +78,6 @@ static struct platform_driver platform_d } };

-static struct calling_interface_buffer *buffer; static struct platform_device *platform_device; static struct backlight_device *dell_backlight_device; static struct rfkill *wifi_rfkill; @@ -286,7 +285,8 @@ static const struct dmi_system_id dell_q { } };

-void dell_set_arguments(u32 arg0, u32 arg1, u32 arg2, u32 arg3) +static void dell_fill_request(struct calling_interface_buffer *buffer, + u32 arg0, u32 arg1, u32 arg2, u32 arg3) { memset(buffer, 0, sizeof(struct calling_interface_buffer)); buffer->input[0] = arg0; @@ -295,7 +295,8 @@ void dell_set_arguments(u32 arg0, u32 ar buffer->input[3] = arg3; }

-int dell_send_request(u16 class, u16 select) +static int dell_send_request(struct calling_interface_buffer *buffer, + u16 class, u16 select) { int ret;

@@ -432,21 +433,22 @@ static int dell_rfkill_set(void *data, b int disable = blocked ? 1 : 0; unsigned long radio = (unsigned long)data; int hwswitch_bit = (unsigned long)data - 1; + struct calling_interface_buffer buffer; int hwswitch; int status; int ret;

- dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret) return ret; - status = buffer->output[1]; + status = buffer.output[1];

- dell_set_arguments(0x2, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0x2, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret) return ret; - hwswitch = buffer->output[1]; + hwswitch = buffer.output[1];

/* If the hardware switch controls this radio, and the hardware switch is disabled, always disable the radio */ @@ -454,8 +456,8 @@ static int dell_rfkill_set(void *data, b (status & BIT(0)) && !(status & BIT(16))) disable = 1;

- dell_set_arguments(1 | (radio<<8) | (disable << 16), 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 1 | (radio<<8) | (disable << 16), 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); return ret; }

@@ -464,9 +466,11 @@ static void dell_rfkill_update_sw_state( { if (status & BIT(0)) { /* Has hw-switch, sync sw_state to BIOS */ + struct calling_interface_buffer buffer; int block = rfkill_blocked(rfkill); - dell_set_arguments(1 | (radio << 8) | (block << 16), 0, 0, 0); - dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, + 1 | (radio << 8) | (block << 16), 0, 0, 0); + dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); } else { /* No hw-switch, sync BIOS state to sw_state */ rfkill_set_sw_state(rfkill, !!(status & BIT(radio + 16))); @@ -483,21 +487,22 @@ static void dell_rfkill_update_hw_state( static void dell_rfkill_query(struct rfkill *rfkill, void *data) { int radio = ((unsigned long)data & 0xF); + struct calling_interface_buffer buffer; int hwswitch; int status; int ret;

- dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - status = buffer->output[1]; + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + status = buffer.output[1];

if (ret != 0 || !(status & BIT(0))) { return; }

- dell_set_arguments(0, 0x2, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - hwswitch = buffer->output[1]; + dell_fill_request(&buffer, 0, 0x2, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + hwswitch = buffer.output[1];

if (ret != 0) return; @@ -514,22 +519,23 @@ static struct dentry *dell_laptop_dir;

static int dell_debugfs_show(struct seq_file *s, void *data) { + struct calling_interface_buffer buffer; int hwswitch_state; int hwswitch_ret; int status; int ret;

- dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret) return ret; - status = buffer->output[1]; + status = buffer.output[1];

- dell_set_arguments(0, 0x2, 0, 0); - hwswitch_ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0x2, 0, 0); + hwswitch_ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (hwswitch_ret) return hwswitch_ret; - hwswitch_state = buffer->output[1]; + hwswitch_state = buffer.output[1];

seq_printf(s, "return:\t%d\n", ret); seq_printf(s, "status:\t0x%X\n", status); @@ -610,22 +616,23 @@ static const struct file_operations dell

static void dell_update_rfkill(struct work_struct *ignored) { + struct calling_interface_buffer buffer; int hwswitch = 0; int status; int ret;

- dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - status = buffer->output[1]; + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + status = buffer.output[1];

if (ret != 0) return;

- dell_set_arguments(0, 0x2, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0x2, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL);

if (ret == 0 && (status & BIT(0))) - hwswitch = buffer->output[1]; + hwswitch = buffer.output[1];

if (wifi_rfkill) { dell_rfkill_update_hw_state(wifi_rfkill, 1, status, hwswitch); @@ -683,6 +690,7 @@ static struct notifier_block dell_laptop

static int __init dell_setup_rfkill(void) { + struct calling_interface_buffer buffer; int status, ret, whitelisted; const char *product;

@@ -698,9 +706,9 @@ static int __init dell_setup_rfkill(void if (!force_rfkill && !whitelisted) return 0;

- dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - status = buffer->output[1]; + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + status = buffer.output[1];

/* dell wireless info smbios call is not supported */ if (ret != 0) @@ -853,6 +861,7 @@ static void dell_cleanup_rfkill(void)

static int dell_send_intensity(struct backlight_device *bd) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret;

@@ -860,17 +869,21 @@ static int dell_send_intensity(struct ba if (!token) return -ENODEV;

- dell_set_arguments(token->location, bd->props.brightness, 0, 0); + dell_fill_request(&buffer, + token->location, bd->props.brightness, 0, 0); if (power_supply_is_system_supplied() > 0) - ret = dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_AC); + ret = dell_send_request(&buffer, + CLASS_TOKEN_WRITE, SELECT_TOKEN_AC); else - ret = dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_BAT); + ret = dell_send_request(&buffer, + CLASS_TOKEN_WRITE, SELECT_TOKEN_BAT);

return ret; }

static int dell_get_intensity(struct backlight_device *bd) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret;

@@ -878,14 +891,17 @@ static int dell_get_intensity(struct bac if (!token) return -ENODEV;

- dell_set_arguments(token->location, 0, 0, 0); + dell_fill_request(&buffer, token->location, 0, 0, 0); if (power_supply_is_system_supplied() > 0) - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_AC); + ret = dell_send_request(&buffer, + CLASS_TOKEN_READ, SELECT_TOKEN_AC); else - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_BAT); + ret = dell_send_request(&buffer, + CLASS_TOKEN_READ, SELECT_TOKEN_BAT);

if (ret == 0) - ret = buffer->output[1]; + ret = buffer.output[1]; + return ret; }

@@ -1149,31 +1165,33 @@ static DEFINE_MUTEX(kbd_led_mutex);

static int kbd_get_info(struct kbd_info *info) { + struct calling_interface_buffer buffer; u8 units; int ret;

- dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, + CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); if (ret) return ret;

- info->modes = buffer->output[1] & 0xFFFF; - info->type = (buffer->output[1] >> 24) & 0xFF; - info->triggers = buffer->output[2] & 0xFF; - units = (buffer->output[2] >> 8) & 0xFF; - info->levels = (buffer->output[2] >> 16) & 0xFF; + info->modes = buffer.output[1] & 0xFFFF; + info->type = (buffer.output[1] >> 24) & 0xFF; + info->triggers = buffer.output[2] & 0xFF; + units = (buffer.output[2] >> 8) & 0xFF; + info->levels = (buffer.output[2] >> 16) & 0xFF;

if (quirks && quirks->kbd_led_levels_off_1 && info->levels) info->levels--;

if (units & BIT(0)) - info->seconds = (buffer->output[3] >> 0) & 0xFF; + info->seconds = (buffer.output[3] >> 0) & 0xFF; if (units & BIT(1)) - info->minutes = (buffer->output[3] >> 8) & 0xFF; + info->minutes = (buffer.output[3] >> 8) & 0xFF; if (units & BIT(2)) - info->hours = (buffer->output[3] >> 16) & 0xFF; + info->hours = (buffer.output[3] >> 16) & 0xFF; if (units & BIT(3)) - info->days = (buffer->output[3] >> 24) & 0xFF; + info->days = (buffer.output[3] >> 24) & 0xFF;

return ret; } @@ -1233,31 +1251,34 @@ static int kbd_set_level(struct kbd_stat

static int kbd_get_state(struct kbd_state *state) { + struct calling_interface_buffer buffer; int ret;

- dell_set_arguments(0x1, 0, 0, 0); - ret = dell_send_request(CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, + CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); if (ret) return ret;

- state->mode_bit = ffs(buffer->output[1] & 0xFFFF); + state->mode_bit = ffs(buffer.output[1] & 0xFFFF); if (state->mode_bit != 0) state->mode_bit--;

- state->triggers = (buffer->output[1] >> 16) & 0xFF; - state->timeout_value = (buffer->output[1] >> 24) & 0x3F; - state->timeout_unit = (buffer->output[1] >> 30) & 0x3; - state->als_setting = buffer->output[2] & 0xFF; - state->als_value = (buffer->output[2] >> 8) & 0xFF; - state->level = (buffer->output[2] >> 16) & 0xFF; - state->timeout_value_ac = (buffer->output[2] >> 24) & 0x3F; - state->timeout_unit_ac = (buffer->output[2] >> 30) & 0x3; + state->triggers = (buffer.output[1] >> 16) & 0xFF; + state->timeout_value = (buffer.output[1] >> 24) & 0x3F; + state->timeout_unit = (buffer.output[1] >> 30) & 0x3; + state->als_setting = buffer.output[2] & 0xFF; + state->als_value = (buffer.output[2] >> 8) & 0xFF; + state->level = (buffer.output[2] >> 16) & 0xFF; + state->timeout_value_ac = (buffer.output[2] >> 24) & 0x3F; + state->timeout_unit_ac = (buffer.output[2] >> 30) & 0x3;

return ret; }

static int kbd_set_state(struct kbd_state *state) { + struct calling_interface_buffer buffer; int ret; u32 input1; u32 input2; @@ -1270,8 +1291,9 @@ static int kbd_set_state(struct kbd_stat input2 |= (state->level & 0xFF) << 16; input2 |= (state->timeout_value_ac & 0x3F) << 24; input2 |= (state->timeout_unit_ac & 0x3) << 30; - dell_set_arguments(0x2, input1, input2, 0); - ret = dell_send_request(CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); + dell_fill_request(&buffer, 0x2, input1, input2, 0); + ret = dell_send_request(&buffer, + CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT);

return ret; } @@ -1298,6 +1320,7 @@ static int kbd_set_state_safe(struct kbd

static int kbd_set_token_bit(u8 bit) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret;

@@ -1308,14 +1331,15 @@ static int kbd_set_token_bit(u8 bit) if (!token) return -EINVAL;

- dell_set_arguments(token->location, token->value, 0, 0); - ret = dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_STD); + dell_fill_request(&buffer, token->location, token->value, 0, 0); + ret = dell_send_request(&buffer, CLASS_TOKEN_WRITE, SELECT_TOKEN_STD);

return ret; }

static int kbd_get_token_bit(u8 bit) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret; int val; @@ -1327,9 +1351,9 @@ static int kbd_get_token_bit(u8 bit) if (!token) return -EINVAL;

- dell_set_arguments(token->location, 0, 0, 0); - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_STD); - val = buffer->output[1]; + dell_fill_request(&buffer, token->location, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_TOKEN_READ, SELECT_TOKEN_STD); + val = buffer.output[1];

if (ret) return ret; @@ -2046,6 +2070,7 @@ static struct notifier_block dell_laptop

int dell_micmute_led_set(int state) { + struct calling_interface_buffer buffer; struct calling_interface_token *token;

if (state == 0) @@ -2058,8 +2083,8 @@ int dell_micmute_led_set(int state) if (!token) return -ENODEV;

- dell_set_arguments(token->location, token->value, 0, 0); - dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_STD); + dell_fill_request(&buffer, token->location, token->value, 0, 0); + dell_send_request(&buffer, CLASS_TOKEN_WRITE, SELECT_TOKEN_STD);

return state; } @@ -2090,13 +2115,6 @@ static int __init dell_init(void) if (ret) goto fail_platform_device2;

- buffer = kzalloc(sizeof(struct calling_interface_buffer), GFP_KERNEL); - if (!buffer) { - ret = -ENOMEM; - goto fail_buffer; - } - - ret = dell_setup_rfkill();

if (ret) { @@ -2121,10 +2139,13 @@ static int __init dell_init(void)

token = dell_smbios_find_token(BRIGHTNESS_TOKEN); if (token) { - dell_set_arguments(token->location, 0, 0, 0); - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_AC); + struct calling_interface_buffer buffer; + + dell_fill_request(&buffer, token->location, 0, 0, 0); + ret = dell_send_request(&buffer, + CLASS_TOKEN_READ, SELECT_TOKEN_AC); if (ret) - max_intensity = buffer->output[3]; + max_intensity = buffer.output[3]; }

if (max_intensity) { @@ -2158,8 +2179,6 @@ static int __init dell_init(void) fail_get_brightness: backlight_device_unregister(dell_backlight_device); fail_backlight: - kfree(buffer); -fail_buffer: dell_cleanup_rfkill(); fail_rfkill: platform_device_del(platform_device); @@ -2179,7 +2198,6 @@ static void __exit dell_exit(void) touchpad_led_exit(); kbd_led_exit(); backlight_device_unregister(dell_backlight_device); - kfree(buffer); dell_cleanup_rfkill(); if (platform_device) { platform_device_unregister(platform_device);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans de Goede hdegoede@redhat.com

commit 1fdb926974695d3dbc05a429bafa266fdd16510e upstream.

Commit 61f5acea8737 ("Bluetooth: btusb: Restore QCA Rome suspend/resume fix with a "rewritten" version") applied the USB_QUIRK_RESET_RESUME to all QCA USB Bluetooth modules. But it turns out that the resume problems are not caused by the QCA Rome chipset, on most platforms it resumes fine. The resume problems are actually a platform problem (likely the platform cutting all power when suspended).

The USB_QUIRK_RESET_RESUME quirk also disables runtime suspend, so by matching on usb-ids, we're causing all boards with these chips to use extra power, to fix resume problems which only happen on some boards.

This commit fixes this by applying the quirk based on DMI matching instead of on usb-ids, so that we match the platform and not the chipset.

Here is the /sys/kernel/debug/usb/devices for the Bluetooth module:

T: Bus=01 Lev=01 Prnt=01 Port=07 Cnt=04 Dev#= 5 Spd=12 MxCh= 0 D: Ver= 2.01 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0cf3 ProdID=e300 Rev= 0.01 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1514836 Fixes: 61f5acea8737 ("Bluetooth: btusb: Restore QCA Rome suspend/resume..") Cc: stable@vger.kernel.org Cc: Brian Norris briannorris@chromium.org Cc: Kai-Heng Feng kai.heng.feng@canonical.com Reported-and-tested-by: Kevin Fenzi kevin@scrye.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/bluetooth/btusb.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-)

--- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -21,6 +21,7 @@ * */

+#include <linux/dmi.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/quirks.h> @@ -376,6 +377,21 @@ static const struct usb_device_id blackl { } /* Terminating entry */ };

+/* The Bluetooth USB module build into some devices needs to be reset on resume, + * this is a problem with the platform (likely shutting off all power) not with + * the module itself. So we use a DMI list to match known broken platforms. + */ +static const struct dmi_system_id btusb_needs_reset_resume_table[] = { + { + /* Lenovo Yoga 920 (QCA Rome device 0cf3:e300) */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 920"), + }, + }, + {} +}; + #define BTUSB_MAX_ISOC_FRAMES 10

#define BTUSB_INTR_RUNNING 0 @@ -3031,6 +3047,9 @@ static int btusb_probe(struct usb_interf hdev->send = btusb_send_frame; hdev->notify = btusb_notify;

+ if (dmi_check_system(btusb_needs_reset_resume_table)) + interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; + #ifdef CONFIG_PM err = btusb_config_oob_wake(hdev); if (err) @@ -3117,12 +3136,6 @@ static int btusb_probe(struct usb_interf if (id->driver_info & BTUSB_QCA_ROME) { data->setup_on_usb = btusb_setup_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; - - /* QCA Rome devices lose their updated firmware over suspend, - * but the USB hub doesn't notice any status change. - * explicitly request a device reset on resume. - */ - interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; }

#ifdef CONFIG_BT_HCIBTUSB_RTL

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeremy Boone jeremy.boone@nccgroup.trust

commit 6d24cd186d9fead3722108dec1b1c993354645ff upstream.

Discrete TPMs are often connected over slow serial buses which, on some platforms, can have glitches causing bit flips. In all the driver _recv() functions, we need to use a u32 to unmarshal the response size, otherwise a bit flip of the 31st bit would cause the expected variable to go negative, which would then try to read a huge amount of data. Also sanity check that the expected amount of data is large enough for the TPM header.

Signed-off-by: Jeremy Boone jeremy.boone@nccgroup.trust Cc: stable@vger.kernel.org Signed-off-by: James Bottomley James.Bottomley@HansenPartnership.com Reviewed-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: James Morris james.morris@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/tpm/st33zp24/st33zp24.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -457,7 +457,7 @@ static int st33zp24_recv(struct tpm_chip size_t count) { int size = 0; - int expected; + u32 expected;

if (!chip) return -EBUSY; @@ -474,7 +474,7 @@ static int st33zp24_recv(struct tpm_chip }

expected = be32_to_cpu(*(__be32 *)(buf + 2)); - if (expected > count) { + if (expected > count || expected < TPM_HEADER_SIZE) { size = -EIO; goto out; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeremy Boone jeremy.boone@nccgroup.trust

commit 9b8cb28d7c62568a5916bdd7ea1c9176d7f8f2ed upstream.

Discrete TPMs are often connected over slow serial buses which, on some platforms, can have glitches causing bit flips. In all the driver _recv() functions, we need to use a u32 to unmarshal the response size, otherwise a bit flip of the 31st bit would cause the expected variable to go negative, which would then try to read a huge amount of data. Also sanity check that the expected amount of data is large enough for the TPM header.

Signed-off-by: Jeremy Boone jeremy.boone@nccgroup.trust Cc: stable@vger.kernel.org Signed-off-by: James Bottomley James.Bottomley@HansenPartnership.com Reviewed-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: James Morris james.morris@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/tpm/tpm_i2c_infineon.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -473,7 +473,8 @@ static int recv_data(struct tpm_chip *ch static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) { int size = 0; - int expected, status; + int status; + u32 expected;

if (count < TPM_HEADER_SIZE) { size = -EIO; @@ -488,7 +489,7 @@ static int tpm_tis_i2c_recv(struct tpm_c }

expected = be32_to_cpu(*(__be32 *)(buf + 2)); - if ((size_t) expected > count) { + if (((size_t) expected > count) || (expected < TPM_HEADER_SIZE)) { size = -EIO; goto out; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeremy Boone jeremy.boone@nccgroup.trust

commit 6bb320ca4a4a7b5b3db8c8d7250cc40002046878 upstream.

Discrete TPMs are often connected over slow serial buses which, on some platforms, can have glitches causing bit flips. In all the driver _recv() functions, we need to use a u32 to unmarshal the response size, otherwise a bit flip of the 31st bit would cause the expected variable to go negative, which would then try to read a huge amount of data. Also sanity check that the expected amount of data is large enough for the TPM header.

Signed-off-by: Jeremy Boone jeremy.boone@nccgroup.trust Cc: stable@vger.kernel.org Signed-off-by: James Bottomley James.Bottomley@HansenPartnership.com Tested-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Reviewed-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: James Morris james.morris@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/tpm/tpm_tis_core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -202,7 +202,8 @@ static int tpm_tis_recv(struct tpm_chip { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); int size = 0; - int expected, status; + int status; + u32 expected;

if (count < TPM_HEADER_SIZE) { size = -EIO; @@ -217,7 +218,7 @@ static int tpm_tis_recv(struct tpm_chip }

expected = be32_to_cpu(*(__be32 *) (buf + 2)); - if (expected > count) { + if (expected > count || expected < TPM_HEADER_SIZE) { size = -EIO; goto out; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Richard Fitzgerald rf@opensource.cirrus.com

commit 5a23699a39abc5328921a81b89383d088f6ba9cc upstream.

The patch "ALSA: control: code refactoring for ELEM_READ/ELEM_WRITE operations" introduced a potential for kernel memory corruption due to an incorrect if statement allowing non-readable controls to fall through and call the get function. For TLV controls a driver can omit SNDRV_CTL_ELEM_ACCESS_READ to ensure that only the TLV get function can be called. Instead the normal get() can be invoked unexpectedly and as the driver expects that this will only be called for controls <= 512 bytes, potentially try to copy >512 bytes into the 512 byte return array, so corrupting kernel memory.

The problem is an attempt to refactor the snd_ctl_elem_read function to invert the logic so that it conditionally aborted if the control is unreadable instead of conditionally executing. But the if statement wasn't inverted correctly.

The correct inversion of

if (a && !b)

is if (!a || b)

Fixes: becf9e5d553c2 ("ALSA: control: code refactoring for ELEM_READ/ELEM_WRITE operations") Signed-off-by: Richard Fitzgerald rf@opensource.cirrus.com Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/control.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/core/control.c +++ b/sound/core/control.c @@ -888,7 +888,7 @@ static int snd_ctl_elem_read(struct snd_

index_offset = snd_ctl_get_ioff(kctl, &control->id); vd = &kctl->vd[index_offset]; - if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) && kctl->get == NULL) + if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) return -EPERM;

snd_ctl_build_ioff(&control->id, kctl, index_offset);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans de Goede hdegoede@redhat.com

commit 1ba8f9d308174e647b864c36209b4d7934d99888 upstream.

On some boards setting power_save to a non 0 value leads to clicking / popping sounds when ever we enter/leave powersaving mode. Ideally we would figure out how to avoid these sounds, but that is not always feasible.

This commit adds a blacklist for devices where powersaving is known to cause problems and disables it on these devices.

Note I tried to put this blacklist in userspace first: https://github.com/systemd/systemd/pull/8128

But the systemd maintainers rightfully pointed out that it would be impossible to then later remove entries once we actually find a way to make power-saving work on listed boards without issues. Having this list in the kernel will allow removal of the blacklist entry in the same commit which fixes the clicks / plops.

The blacklist only applies to the default power_save module-option value, if a user explicitly sets the module-option then the blacklist is not used.

[ added an ifdef CONFIG_PM for the build error -- tiwai]

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1525104 BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=198611 Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/hda_intel.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-)

--- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -181,7 +181,7 @@ static const struct kernel_param_ops par }; #define param_check_xint param_check_int

-static int power_save = CONFIG_SND_HDA_POWER_SAVE_DEFAULT; +static int power_save = -1; module_param(power_save, xint, 0644); MODULE_PARM_DESC(power_save, "Automatic power-saving timeout " "(in second, 0 = disable)."); @@ -2186,6 +2186,24 @@ out_free: return err; }

+#ifdef CONFIG_PM +/* On some boards setting power_save to a non 0 value leads to clicking / + * popping sounds when ever we enter/leave powersaving mode. Ideally we would + * figure out how to avoid these sounds, but that is not always feasible. + * So we keep a list of devices where we disable powersaving as its known + * to causes problems on these devices. + */ +static struct snd_pci_quirk power_save_blacklist[] = { + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0), + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0), + /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ + SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), + {} +}; +#endif /* CONFIG_PM */ + /* number of codec slots for each chipset: 0 = default slots (i.e. 4) */ static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = { [AZX_DRIVER_NVIDIA] = 8, @@ -2198,6 +2216,7 @@ static int azx_probe_continue(struct azx struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; int dev = chip->dev_index; + int val; int err;

hda->probe_continued = 1; @@ -2278,7 +2297,22 @@ static int azx_probe_continue(struct azx

chip->running = 1; azx_add_card_list(chip); - snd_hda_set_power_save(&chip->bus, power_save * 1000); + + val = power_save; +#ifdef CONFIG_PM + if (val == -1) { + const struct snd_pci_quirk *q; + + val = CONFIG_SND_HDA_POWER_SAVE_DEFAULT; + q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); + if (q && val) { + dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", + q->subvendor, q->subdevice); + val = 0; + } + } +#endif /* CONFIG_PM */ + snd_hda_set_power_save(&chip->bus, val * 1000); if (azx_has_pm_runtime(chip) || hda->use_vga_switcheroo) pm_runtime_put_autosuspend(&pci->dev);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Adrian Hunter adrian.hunter@intel.com

commit f8870ae6e2d6be75b1accc2db981169fdfbea7ab upstream.

Tuning can leave the IP in an active state (Buffer Read Enable bit set) which prevents the entry to low power states (i.e. S0i3). Data reset will clear it.

Generally tuning is followed by a data transfer which will anyway sort out the state, so it is rare that S0i3 is actually prevented.

Signed-off-by: Adrian Hunter adrian.hunter@intel.com Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mmc/host/sdhci-pci-core.c | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-)

--- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -593,9 +593,36 @@ static void byt_read_dsm(struct sdhci_pc slot->chip->rpm_retune = intel_host->d3_retune; }

-static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) +static int intel_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + int err = sdhci_execute_tuning(mmc, opcode); + struct sdhci_host *host = mmc_priv(mmc); + + if (err) + return err; + + /* + * Tuning can leave the IP in an active state (Buffer Read Enable bit + * set) which prevents the entry to low power states (i.e. S0i3). Data + * reset will clear it. + */ + sdhci_reset(host, SDHCI_RESET_DATA); + + return 0; +} + +static void byt_probe_slot(struct sdhci_pci_slot *slot) { + struct mmc_host_ops *ops = &slot->host->mmc_host_ops; + byt_read_dsm(slot); + + ops->execute_tuning = intel_execute_tuning; +} + +static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) +{ + byt_probe_slot(slot); slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE | MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR | MMC_CAP_CMD_DURING_TFR | @@ -650,7 +677,7 @@ static int ni_byt_sdio_probe_slot(struct { int err;

- byt_read_dsm(slot); + byt_probe_slot(slot);

err = ni_set_max_freq(slot); if (err) @@ -663,7 +690,7 @@ static int ni_byt_sdio_probe_slot(struct

static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot) { - byt_read_dsm(slot); + byt_probe_slot(slot); slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE | MMC_CAP_WAIT_WHILE_BUSY; return 0; @@ -671,7 +698,7 @@ static int byt_sdio_probe_slot(struct sd

static int byt_sd_probe_slot(struct sdhci_pci_slot *slot) { - byt_read_dsm(slot); + byt_probe_slot(slot); slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_AGGRESSIVE_PM | MMC_CAP_CD_WAKE; slot->cd_idx = 0;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shawn Lin shawn.lin@rock-chips.com

commit 5b43df8b4c1a7f0c3fbf793c9566068e6b1e570c upstream.

cat /sys/kernel/debug/mmc0/regs will hang up the system since it's in runtime suspended state, so the genpd and biu_clk is off. This patch fixes this problem by calling pm_runtime_get_sync to wake it up before reading the registers.

Fixes: e9ed8835e990 ("mmc: dw_mmc: add runtime PM callback") Cc: stable@vger.kernel.org Signed-off-by: Shawn Lin shawn.lin@rock-chips.com Reviewed-by: Jaehoon Chung jh80.chung@samsung.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mmc/host/dw_mmc.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -165,6 +165,8 @@ static int dw_mci_regs_show(struct seq_f { struct dw_mci *host = s->private;

+ pm_runtime_get_sync(host->dev); + seq_printf(s, "STATUS:\t0x%08x\n", mci_readl(host, STATUS)); seq_printf(s, "RINTSTS:\t0x%08x\n", mci_readl(host, RINTSTS)); seq_printf(s, "CMD:\t0x%08x\n", mci_readl(host, CMD)); @@ -172,6 +174,8 @@ static int dw_mci_regs_show(struct seq_f seq_printf(s, "INTMASK:\t0x%08x\n", mci_readl(host, INTMASK)); seq_printf(s, "CLKENA:\t0x%08x\n", mci_readl(host, CLKENA));

+ pm_runtime_put_autosuspend(host->dev); + return 0; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shawn Lin shawn.lin@rock-chips.com

commit 0d84b9e5631d923744767dc6608672df906dd092 upstream.

Add num_caps field for dw_mci_drv_data to validate the controller id from DT alias and non-DT ways.

Reported-by: Geert Uytterhoeven geert+renesas@glider.be Signed-off-by: Shawn Lin shawn.lin@rock-chips.com Fixes: 800d78bfccb3 ("mmc: dw_mmc: add support for implementation specific callbacks") Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mmc/host/dw_mmc-exynos.c | 1 + drivers/mmc/host/dw_mmc-k3.c | 1 + drivers/mmc/host/dw_mmc-rockchip.c | 1 + drivers/mmc/host/dw_mmc-zx.c | 1 + drivers/mmc/host/dw_mmc.c | 9 ++++++++- drivers/mmc/host/dw_mmc.h | 2 ++ 6 files changed, 14 insertions(+), 1 deletion(-)

--- a/drivers/mmc/host/dw_mmc-exynos.c +++ b/drivers/mmc/host/dw_mmc-exynos.c @@ -487,6 +487,7 @@ static unsigned long exynos_dwmmc_caps[4

static const struct dw_mci_drv_data exynos_drv_data = { .caps = exynos_dwmmc_caps, + .num_caps = ARRAY_SIZE(exynos_dwmmc_caps), .init = dw_mci_exynos_priv_init, .set_ios = dw_mci_exynos_set_ios, .parse_dt = dw_mci_exynos_parse_dt, --- a/drivers/mmc/host/dw_mmc-k3.c +++ b/drivers/mmc/host/dw_mmc-k3.c @@ -210,6 +210,7 @@ static int dw_mci_hi6220_execute_tuning(

static const struct dw_mci_drv_data hi6220_data = { .caps = dw_mci_hi6220_caps, + .num_caps = ARRAY_SIZE(dw_mci_hi6220_caps), .switch_voltage = dw_mci_hi6220_switch_voltage, .set_ios = dw_mci_hi6220_set_ios, .parse_dt = dw_mci_hi6220_parse_dt, --- a/drivers/mmc/host/dw_mmc-rockchip.c +++ b/drivers/mmc/host/dw_mmc-rockchip.c @@ -319,6 +319,7 @@ static const struct dw_mci_drv_data rk29

static const struct dw_mci_drv_data rk3288_drv_data = { .caps = dw_mci_rk3288_dwmmc_caps, + .num_caps = ARRAY_SIZE(dw_mci_rk3288_dwmmc_caps), .set_ios = dw_mci_rk3288_set_ios, .execute_tuning = dw_mci_rk3288_execute_tuning, .parse_dt = dw_mci_rk3288_parse_dt, --- a/drivers/mmc/host/dw_mmc-zx.c +++ b/drivers/mmc/host/dw_mmc-zx.c @@ -195,6 +195,7 @@ static unsigned long zx_dwmmc_caps[3] =

static const struct dw_mci_drv_data zx_drv_data = { .caps = zx_dwmmc_caps, + .num_caps = ARRAY_SIZE(zx_dwmmc_caps), .execute_tuning = dw_mci_zx_execute_tuning, .prepare_hs400_tuning = dw_mci_zx_prepare_hs400_tuning, .parse_dt = dw_mci_zx_parse_dt, --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -2808,8 +2808,15 @@ static int dw_mci_init_slot_caps(struct } else { ctrl_id = to_platform_device(host->dev)->id; } - if (drv_data && drv_data->caps) + + if (drv_data && drv_data->caps) { + if (ctrl_id >= drv_data->num_caps) { + dev_err(host->dev, "invalid controller id %d\n", + ctrl_id); + return -EINVAL; + } mmc->caps |= drv_data->caps[ctrl_id]; + }

if (host->pdata->caps2) mmc->caps2 = host->pdata->caps2; --- a/drivers/mmc/host/dw_mmc.h +++ b/drivers/mmc/host/dw_mmc.h @@ -543,6 +543,7 @@ struct dw_mci_slot { /** * dw_mci driver data - dw-mshc implementation specific driver data. * @caps: mmc subsystem specified capabilities of the controller(s). + * @num_caps: number of capabilities specified by @caps. * @init: early implementation specific initialization. * @set_ios: handle bus specific extensions. * @parse_dt: parse implementation specific device tree properties. @@ -554,6 +555,7 @@ struct dw_mci_slot { */ struct dw_mci_drv_data { unsigned long *caps; + u32 num_caps; int (*init)(struct dw_mci *host); void (*set_ios)(struct dw_mci *host, struct mmc_ios *ios); int (*parse_dt)(struct dw_mci *host);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Helge Deller deller@gmx.de

commit 5ffa8518851f1401817c15d2a7eecc0373c26ff9 upstream.

When running on qemu we know that the (emulated) cr16 cpu-internal clocks are syncronized. So let's use them unconditionally on qemu.

Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # 4.14+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/include/asm/processor.h | 2 ++ arch/parisc/kernel/time.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)

--- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -316,6 +316,8 @@ extern int _parisc_requires_coherency; #define parisc_requires_coherency() (0) #endif

+extern int running_on_qemu; + #endif /* __ASSEMBLY__ */

#endif /* __ASM_PARISC_PROCESSOR_H */ --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -248,7 +248,7 @@ static int __init init_cr16_clocksource( * different sockets, so mark them unstable and lower rating on * multi-socket SMP systems. */ - if (num_online_cpus() > 1) { + if (num_online_cpus() > 1 && !running_on_qemu) { int cpu; unsigned long cpu0_loc; cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Helge Deller deller@gmx.de

commit fd8d0ca2563151204f3fe555dc8ca4bcfe8677a3 upstream.

For security reasons do not expose the virtual kernel memory layout to userspace.

Signed-off-by: Helge Deller deller@gmx.de Suggested-by: Kees Cook keescook@chromium.org Cc: stable@vger.kernel.org # 4.15 Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/mm/init.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -629,7 +629,12 @@ void __init mem_init(void) #endif

mem_init_print_info(NULL); -#ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */ + +#if 0 + /* + * Do not expose the virtual kernel memory layout to userspace. + * But keep code for debugging purposes. + */ printk("virtual kernel memory layout:\n" " vmalloc : 0x%px - 0x%px (%4ld MB)\n" " memory : 0x%px - 0x%px (%4ld MB)\n"

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiufei Xue jiufei.xue@linux.alibaba.com

commit 7c5a0dcf557c6511a61e092ba887de28882fe857 upstream.

The vm counters is counted in sectors, so we should do the conversation in submit_bio.

Fixes: 74d46992e0d9 ("block: replace bi_bdev with a gendisk pointer and partitions index") Cc: stable@vger.kernel.org Reviewed-by: Omar Sandoval osandov@fb.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Jiufei Xue jiufei.xue@linux.alibaba.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- block/blk-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/block/blk-core.c +++ b/block/blk-core.c @@ -2401,7 +2401,7 @@ blk_qc_t submit_bio(struct bio *bio) unsigned int count;

if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) - count = queue_logical_block_size(bio->bi_disk->queue); + count = queue_logical_block_size(bio->bi_disk->queue) >> 9; else count = bio_sectors(bio);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ming Lei ming.lei@redhat.com

commit 0bd1ed4860d0f5f836aa8371797689a3779d1bf5 upstream.

The 'lend' parameter of truncate_inode_pages_range is required to be inclusive, so follow the rule.

This patch fixes one memory corruption triggered by discard.

Cc: stable@vger.kernel.org Cc: Dmitry Monakhov dmonakhov@openvz.org Fixes: 351499a172c0 ("block: Invalidate cache on discard v2") Reviewed-by: Bart Van Assche bart.vanassche@wdc.com Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- block/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/block/ioctl.c +++ b/block/ioctl.c @@ -225,7 +225,7 @@ static int blk_ioctl_discard(struct bloc

if (start + len > i_size_read(bdev->bd_inode)) return -EINVAL; - truncate_inode_pages_range(mapping, start, start + len); + truncate_inode_pages_range(mapping, start, start + len - 1); return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, flags); }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Viresh Kumar viresh.kumar@linaro.org

commit 0373ca74831b0f93cd4cdbf7ad3aec3c33a479a5 upstream.

commit a307a1e6bc0d "cpufreq: s3c: use cpufreq_generic_init()" accidentally broke cpufreq on s3c2410 and s3c2412.

These two platforms don't have a CPU frequency table and used to skip calling cpufreq_table_validate_and_show() for them. But with the above commit, we started calling it unconditionally and that will eventually fail as the frequency table pointer is NULL.

Fix this by calling cpufreq_table_validate_and_show() conditionally again.

Fixes: a307a1e6bc0d "cpufreq: s3c: use cpufreq_generic_init()" Cc: 3.13+ stable@vger.kernel.org # v3.13+ Signed-off-by: Viresh Kumar viresh.kumar@linaro.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/cpufreq/s3c24xx-cpufreq.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -351,7 +351,13 @@ struct clk *s3c_cpufreq_clk_get(struct d static int s3c_cpufreq_init(struct cpufreq_policy *policy) { policy->clk = clk_arm; - return cpufreq_generic_init(policy, ftab, cpu_cur.info->latency); + + policy->cpuinfo.transition_latency = cpu_cur.info->latency; + + if (ftab) + return cpufreq_table_validate_and_show(policy, ftab); + + return 0; }

static int __init s3c_cpufreq_initclks(void)

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Kara jack@suse.cz

commit d9c10e5b8863cfb6886d1640386455075c6e979d upstream.

Commit e864f39569f4 "fs: add RWF_DSYNC aand RWF_SYNC" added additional way for direct IO to become synchronous and thus trigger fsync from the IO completion handler. Then commit 9830f4be159b "fs: Use RWF_* flags for AIO operations" allowed these flags to be set for AIO as well. However that commit forgot to update the condition checking whether the IO completion handling should be defered to a workqueue and thus AIO DIO with RWF_[D]SYNC set will call fsync() from IRQ context resulting in sleep in atomic.

Fix the problem by checking directly iocb flags (the same way as it is done in dio_complete()) instead of checking all conditions that could lead to IO being synchronous.

CC: Christoph Hellwig hch@lst.de CC: Goldwyn Rodrigues rgoldwyn@suse.com CC: stable@vger.kernel.org Reported-by: Mark Rutland mark.rutland@arm.com Tested-by: Mark Rutland mark.rutland@arm.com Fixes: 9830f4be159b29399d107bffb99e0132bc5aedd4 Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/direct-io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1252,8 +1252,7 @@ do_blockdev_direct_IO(struct kiocb *iocb */ if (dio->is_async && iov_iter_rw(iter) == WRITE) { retval = 0; - if ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host)) + if (iocb->ki_flags & IOCB_DSYNC) retval = dio_set_defer_completion(dio); else if (!dio->inode->i_sb->s_dio_done_wq) { /*

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sebastian Panceac sebastian@resin.io

commit 028091f82eefd5e84f81cef81a7673016ecbe78b upstream.

When the Intel Edison module is powered with 3.3V, the reboot command makes the module stuck. If the module is powered at a greater voltage, like 4.4V (as the Edison Mini Breakout board does), reboot works OK.

The official Intel Edison BSP sends the IPCMSG_COLD_RESET message to the SCU by default. The IPCMSG_COLD_BOOT which is used by the upstream kernel is only sent when explicitely selected on the kernel command line.

Use IPCMSG_COLD_RESET unconditionally which makes reboot work independent of the power supply voltage.

[ tglx: Massaged changelog ]

Fixes: bda7b072de99 ("x86/platform/intel-mid: Implement power off sequence") Signed-off-by: Sebastian Panceac sebastian@resin.io Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Andy Shevchenko andy.shevchenko@gmail.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1519810849-15131-1-git-send-email-sebastian@resin.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/platform/intel-mid/intel-mid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -79,7 +79,7 @@ static void intel_mid_power_off(void)

static void intel_mid_reboot(void) { - intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); + intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); }

static unsigned long __init intel_mid_calibrate_tsc(void)

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 1b12580af1d0677c3c3a19e35bfe5d59b03f737f ]

Now br_sysfs_if file flush doesn't have attr show. To read it will cause kernel panic after users chmod u+r this file.

Xiong found this issue when running the commands:

ip link add br0 type bridge ip link add type veth ip link set veth0 master br0 chmod u+r /sys/devices/virtual/net/veth0/brport/flush timeout 3 cat /sys/devices/virtual/net/veth0/brport/flush

kernel crashed with NULL a pointer dereference call trace.

This patch is to fix it by return -EINVAL when brport_attr->show is null, just the same as the check for brport_attr->store in brport_store().

Fixes: 9cf637473c85 ("bridge: add sysfs hook to flush forwarding table") Reported-by: Xiong Zhou xzhou@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_sysfs_if.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -255,6 +255,9 @@ static ssize_t brport_show(struct kobjec struct brport_attribute *brport_attr = to_brport_attr(attr); struct net_bridge_port *p = to_brport(kobj);

+ if (!brport_attr->show) + return -EINVAL; + return brport_attr->show(p, buf); }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Denis Du dudenis2000@yahoo.ca

[ Upstream commit b6c3bad1ba83af1062a7ff6986d9edc4f3d7fc8e ]

Sometimes when physical lines have a just good noise to make the protocol handshaking fail, but the carrier detect still good. Then after remove of the noise, nobody will trigger this protocol to be start again to cause the link to never come back. The fix is when the carrier is still on, not terminate the protocol handshaking.

Signed-off-by: Denis Du dudenis2000@yahoo.ca Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wan/hdlc_ppp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -574,7 +574,10 @@ static void ppp_timer(struct timer_list ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, 0, NULL); proto->restart_counter--; - } else + } else if (netif_carrier_ok(proto->dev)) + ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, + 0, NULL); + else ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0, 0, NULL); break;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wolfram Sang wsa+renesas@sang-engineering.com

[ Upstream commit a3276892db7a588bedc33168e502572008f714a9 ]

Due to a typo, the mask was destroyed by a comparison instead of a bit shift.

Signed-off-by: Wolfram Sang wsa+renesas@sang-engineering.com Acked-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -595,7 +595,7 @@ isr_done:

reissue_mask = 1 << 0; if (!pdata->per_channel_irq) - reissue_mask |= 0xffff < 4; + reissue_mask |= 0xffff << 4;

XP_IOWRITE(pdata, XP_INT_REISSUE_EN, reissue_mask); }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski jakub.kicinski@netronome.com

[ Upstream commit ac5b70198adc25c73fba28de4f78adcee8f6be0b ]

netif_set_real_num_tx_queues() can be called when netdev is up. That usually happens when user requests change of number of channels/rings with ethtool -L. The procedure for changing the number of queues involves resetting the qdiscs and setting dev->num_tx_queues to the new value. When the new value is lower than the old one, extra care has to be taken to ensure ordering of accesses to the number of queues vs qdisc reset.

Currently the queues are reset before new dev->num_tx_queues is assigned, leaving a window of time where packets can be enqueued onto the queues going down, leading to a likely crash in the drivers, since most drivers don't check if TX skbs are assigned to an active queue.

Fixes: e6484930d7c7 ("net: allocate tx queues in register_netdevice") Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/net/core/dev.c +++ b/net/core/dev.c @@ -2366,8 +2366,11 @@ EXPORT_SYMBOL(netdev_set_num_tc); */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { + bool disabling; int rc;

+ disabling = txq < dev->real_num_tx_queues; + if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL;

@@ -2383,15 +2386,19 @@ int netif_set_real_num_tx_queues(struct if (dev->num_tc) netif_setup_tc(dev, txq);

- if (txq < dev->real_num_tx_queues) { + dev->real_num_tx_queues = txq; + + if (disabling) { + synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } + } else { + dev->real_num_tx_queues = txq; }

- dev->real_num_tx_queues = txq; return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolas Dichtel nicolas.dichtel@6wind.com

[ Upstream commit cb9f7a9a5c96a773bbc9c70660dc600cfff82f82 ]

Nowadays, nlmsg_multicast() returns only 0 or -ESRCH but this was not the case when commit 134e63756d5f was pushed. However, there was no reason to stop the loop if a netns does not have listeners. Returns -ESRCH only if there was no listeners in all netns.

To avoid having the same problem in the future, I didn't take the assumption that nlmsg_multicast() returns only 0 or -ESRCH.

Fixes: 134e63756d5f ("genetlink: make netns aware") CC: Johannes Berg johannes.berg@intel.com Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netlink/genetlink.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

--- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1081,6 +1081,7 @@ static int genlmsg_mcast(struct sk_buff { struct sk_buff *tmp; struct net *net, *prev = NULL; + bool delivered = false; int err;

for_each_net_rcu(net) { @@ -1092,14 +1093,21 @@ static int genlmsg_mcast(struct sk_buff } err = nlmsg_multicast(prev->genl_sock, tmp, portid, group, flags); - if (err) + if (!err) + delivered = true; + else if (err != -ESRCH) goto error; }

prev = net; }

- return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); + err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); + if (!err) + delivered = true; + else if (err != -ESRCH) + goto error; + return delivered ? 0 : -ESRCH; error: kfree_skb(skb); return err;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guillaume Nault g.nault@alphalink.fr

[ Upstream commit 77f840e3e5f09c6d7d727e85e6e08276dd813d11 ]

PPP units don't hold any reference on the channels connected to it. It is the channel's responsibility to ensure that it disconnects from its unit before being destroyed. In practice, this is ensured by ppp_unregister_channel() disconnecting the channel from the unit before dropping a reference on the channel.

However, it is possible for an unregistered channel to connect to a PPP unit: register a channel with ppp_register_net_channel(), attach a /dev/ppp file to it with ioctl(PPPIOCATTCHAN), unregister the channel with ppp_unregister_channel() and finally connect the /dev/ppp file to a PPP unit with ioctl(PPPIOCCONNECT).

Once in this situation, the channel is only held by the /dev/ppp file, which can be released at anytime and free the channel without letting the parent PPP unit know. Then the ppp structure ends up with dangling pointers in its ->channels list.

Prevent this scenario by forbidding unregistered channels from connecting to PPP units. This maintains the code logic by keeping ppp_unregister_channel() responsible from disconnecting the channel if necessary and avoids modification on the reference counting mechanism.

This issue seems to predate git history (successfully reproduced on Linux 2.6.26 and earlier PPP commits are unrelated).

Signed-off-by: Guillaume Nault g.nault@alphalink.fr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ppp/ppp_generic.c | 9 +++++++++ 1 file changed, 9 insertions(+)

--- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -3161,6 +3161,15 @@ ppp_connect_channel(struct channel *pch, goto outl;

ppp_lock(ppp); + spin_lock_bh(&pch->downl); + if (!pch->chan) { + /* Don't connect unregistered channels */ + spin_unlock_bh(&pch->downl); + ppp_unlock(ppp); + ret = -ENOTCONN; + goto outl; + } + spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexey Kodanev alexey.kodanev@oracle.com

[ Upstream commit 15f35d49c93f4fa9875235e7bf3e3783d2dd7a1b ]

Since UDP-Lite is always using checksum, the following path is triggered when calculating pseudo header for it:

udp4_csum_init() or udp6_csum_init() skb_checksum_init_zero_check() __skb_checksum_validate_complete()

The problem can appear if skb->len is less than CHECKSUM_BREAK. In this particular case __skb_checksum_validate_complete() also invokes __skb_checksum_complete(skb). If UDP-Lite is using partial checksum that covers only part of a packet, the function will return bad checksum and the packet will be dropped.

It can be fixed if we skip skb_checksum_init_zero_check() and only set the required pseudo header checksum for UDP-Lite with partial checksum before udp4_csum_init()/udp6_csum_init() functions return.

Fixes: ed70fcfcee95 ("net: Call skb_checksum_init in IPv4") Fixes: e4f45b7f40bd ("net: Call skb_checksum_init in IPv6") Signed-off-by: Alexey Kodanev alexey.kodanev@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/udplite.h | 1 + net/ipv4/udp.c | 5 +++++ net/ipv6/ip6_checksum.c | 5 +++++ 3 files changed, 11 insertions(+)

--- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -64,6 +64,7 @@ static inline int udplite_checksum_init( UDP_SKB_CB(skb)->cscov = cscov; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; + skb->csum_valid = 0; }

return 0; --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2031,6 +2031,11 @@ static inline int udp4_csum_init(struct err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = inet_compute_pseudo(skb, proto); + return 0; + } }

/* Note, we are only interested in != 0 or == 0, thus the --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = ip6_compute_pseudo(skb, proto); + return 0; + } }

/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tommi Rantala tommi.t.rantala@nokia.com

[ Upstream commit 4a31a6b19f9ddf498c81f5c9b089742b7472a6f8 ]

Fix dst reference count leak in sctp_v4_get_dst() introduced in commit 410f03831 ("sctp: add routing output fallback"):

When walking the address_list, successive ip_route_output_key() calls may return the same rt->dst with the reference incremented on each call.

The code would not decrement the dst refcount when the dst pointer was identical from the previous iteration, causing the dst refcnt leak.

Testcase: ip netns add TEST ip netns exec TEST ip link set lo up ip link add dummy0 type dummy ip link add dummy1 type dummy ip link add dummy2 type dummy ip link set dev dummy0 netns TEST ip link set dev dummy1 netns TEST ip link set dev dummy2 netns TEST ip netns exec TEST ip addr add 192.168.1.1/24 dev dummy0 ip netns exec TEST ip link set dummy0 up ip netns exec TEST ip addr add 192.168.1.2/24 dev dummy1 ip netns exec TEST ip link set dummy1 up ip netns exec TEST ip addr add 192.168.1.3/24 dev dummy2 ip netns exec TEST ip link set dummy2 up ip netns exec TEST sctp_test -H 192.168.1.2 -P 20002 -h 192.168.1.1 -p 20000 -s -B 192.168.1.3 ip netns del TEST

In 4.4 and 4.9 kernels this results to: [ 354.179591] unregister_netdevice: waiting for lo to become free. Usage count = 1 [ 364.419674] unregister_netdevice: waiting for lo to become free. Usage count = 1 [ 374.663664] unregister_netdevice: waiting for lo to become free. Usage count = 1 [ 384.903717] unregister_netdevice: waiting for lo to become free. Usage count = 1 [ 395.143724] unregister_netdevice: waiting for lo to become free. Usage count = 1 [ 405.383645] unregister_netdevice: waiting for lo to become free. Usage count = 1 ...

Fixes: 410f03831 ("sctp: add routing output fallback") Fixes: 0ca50d12f ("sctp: fix src address selection if using secondary addresses") Signed-off-by: Tommi Rantala tommi.t.rantala@nokia.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/protocol.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)

--- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_ if (IS_ERR(rt)) continue;

- if (!dst) - dst = &rt->dst; - /* Ensure the src address belongs to the output * interface. */ odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, false); if (!odev || odev->ifindex != fl4->flowi4_oif) { - if (&rt->dst != dst) + if (!dst) + dst = &rt->dst; + else dst_release(&rt->dst); continue; }

- if (dst != &rt->dst) - dst_release(dst); + dst_release(dst); dst = &rt->dst; break; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gal Pressman galp@mellanox.com

[ Upstream commit 2f0db87901698cd73d828cc6fb1957b8916fc911 ]

When allocating a drop rq, no numa node is explicitly set which means allocations are done on node zero. This is not necessarily the nearest numa node to the HCA, and even worse, might even be a memoryless numa node.

Choose the numa_node given to us by the pci device in order to properly allocate the coherent dma memory instead of assuming zero is valid.

Fixes: 556dd1b9c313 ("net/mlx5e: Set drop RQ's necessary parameters only") Signed-off-by: Gal Pressman galp@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1911,13 +1911,16 @@ static void mlx5e_build_rq_param(struct param->wq.linear = 1; }

-static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param) +static void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, + struct mlx5e_rq_param *param) { void *rqc = param->rqc; void *wq = MLX5_ADDR_OF(rqc, rqc, wq);

MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe))); + + param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); }

static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv, @@ -2774,6 +2777,9 @@ static int mlx5e_alloc_drop_cq(struct ml struct mlx5e_cq *cq, struct mlx5e_cq_param *param) { + param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); + param->wq.db_numa_node = dev_to_node(&mdev->pdev->dev); + return mlx5e_alloc_cq_common(mdev, param, cq); }

@@ -2785,7 +2791,7 @@ static int mlx5e_open_drop_rq(struct mlx struct mlx5e_cq *cq = &drop_rq->cq; int err;

- mlx5e_build_drop_rq_param(&rq_param); + mlx5e_build_drop_rq_param(mdev, &rq_param);

err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param); if (err)

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilya Lesokhin ilyal@mellanox.com

[ Upstream commit 808cf9e38cd7923036a99f459ccc8cf2955e47af ]

Avoid SKB coalescing if eor bit is set in one of the relevant SKBs.

Fixes: c134ecb87817 ("tcp: Make use of MSG_EOR in tcp_sendmsg") Signed-off-by: Ilya Lesokhin ilyal@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_output.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+)

--- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2026,6 +2026,24 @@ static inline void tcp_mtu_check_reprobe } }

+static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) +{ + struct sk_buff *skb, *next; + + skb = tcp_send_head(sk); + tcp_for_write_queue_from_safe(skb, next, sk) { + if (len <= skb->len) + break; + + if (unlikely(TCP_SKB_CB(skb)->eor)) + return false; + + len -= skb->len; + } + + return true; +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2098,6 +2116,9 @@ static int tcp_mtu_probe(struct sock *sk return 0; }

+ if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) + return -1; + /* We're allowed to probe. Build it now. */ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) @@ -2133,6 +2154,10 @@ static int tcp_mtu_probe(struct sock *sk /* We've eaten all the data from this skb. * Throw it away. */ TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + /* If this is the last SKB we copy and eor is set + * we need to propagate it to the new skb. + */ + TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else {

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tonghao Zhang xiangxia.m.yue@gmail.com

[ Upstream commit a61a86f8db92923a2a4c857c49a795bcae754497 ]

The SK_MEM_QUANTUM was changed from PAGE_SIZE to 4096. And the tcp_wmem/tcp_rmem min default values are 4096.

Fixes: bd68a2a854ad ("net: set SK_MEM_QUANTUM to 4096") Cc: Eric Dumazet edumazet@google.com Signed-off-by: Tonghao Zhang xiangxia.m.yue@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/networking/ip-sysctl.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -508,7 +508,7 @@ tcp_rmem - vector of 3 INTEGERs: min, de min: Minimal size of receive buffer used by TCP sockets. It is guaranteed to each TCP socket, even under moderate memory pressure. - Default: 1 page + Default: 4K

default: initial size of receive buffer used by TCP sockets. This value overrides net.core.rmem_default used by other protocols. @@ -666,7 +666,7 @@ tcp_window_scaling - BOOLEAN tcp_wmem - vector of 3 INTEGERs: min, default, max min: Amount of memory reserved for send buffers for TCP sockets. Each TCP socket has rights to use it due to fact of its birth. - Default: 1 page + Default: 4K

default: initial size of send buffer used by TCP sockets. This value overrides net.core.wmem_default used by other protocols.

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ Upstream commit a5f7add332b4ea6d4b9480971b3b0f5e66466ae9 ]

pfifo_fast got percpu stats lately, uncovering a bug I introduced last year in linux-4.10.

I missed the fact that we have to clear our temporary storage before calling __gnet_stats_copy_basic() in the case of percpu stats.

Without this fix, rate estimators (tc qd replace dev xxx root est 1sec 4sec pfifo_fast) are utterly broken.

Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators") Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/gen_estimator.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -66,6 +66,7 @@ struct net_rate_estimator { static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_packed *b) { + memset(b, 0, sizeof(*b)); if (e->stats_lock) spin_lock(e->stats_lock);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 27af86bb038d9c8b8066cd17854ddaf2ea92bce1 ]

The pr_err in sctp_hash_transport was supposed to report a sctp bug for using rhashtable/rhlist.

The err '-EEXIST' introduced in Commit cd2b70875058 ("sctp: check duplicate node before inserting a new transport") doesn't belong to that case.

So just return -EEXIST back without pr_err any kmsg.

Fixes: cd2b70875058 ("sctp: check duplicate node before inserting a new transport") Reported-by: Wei Chen weichen@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/input.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

--- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -897,15 +897,12 @@ int sctp_hash_transport(struct sctp_tran rhl_for_each_entry_rcu(transport, tmp, list, node) if (transport->asoc->ep == t->asoc->ep) { rcu_read_unlock(); - err = -EEXIST; - goto out; + return -EEXIST; } rcu_read_unlock();

err = rhltable_insert_key(&sctp_transport_hashtable, &arg, &t->node, sctp_hash_params); - -out: if (err) pr_err_once("insert transport fail, errno %d\n", err);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Ahern dsahern@gmail.com

[ Upstream commit 1fe4b1184c2ae2bfbf9e8b14c9c0c1945c98f205 ]

The result of the skb flow dissect is copied from keys to hash_keys to ensure only the intended data is hashed. The original L4 hash patch overlooked setting the addr_type for this case; add it.

Fixes: bf4e0a3db97eb ("net: ipv4: add support for ECMP hash policy choice") Reported-by: Ido Schimmel idosch@idosch.org Signed-off-by: David Ahern dsahern@gmail.com Acked-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Reviewed-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/route.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1832,6 +1832,8 @@ int fib_multipath_hash(const struct fib_ return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, flag); + + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; hash_keys.ports.src = keys.ports.src;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel idosch@mellanox.com

[ Upstream commit 0e5a82efda872c2469c210957d7d4161ef8f4391 ]

When a VLAN is added on a port, a reference is taken on the corresponding master VLAN entry. If it does not already exist, then it is created and a reference taken.

However, in the second case a reference is not really taken when CONFIG_REFCOUNT_FULL is enabled as refcount_inc() is replaced by refcount_inc_not_zero().

Fix this by using refcount_set() on a newly created master VLAN entry.

Fixes: 251277598596 ("net, bridge: convert net_bridge_vlan.refcnt from atomic_t to refcount_t") Signed-off-by: Ido Schimmel idosch@mellanox.com Acked-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_vlan.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -168,6 +168,8 @@ static struct net_bridge_vlan *br_vlan_g masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; + refcount_set(&masterv->refcnt, 1); + return masterv; } refcount_inc(&masterv->refcnt);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Boris Pismenny borisp@mellanox.com

[ Upstream commit c113187d38ff85dc302a1bb55864b203ebb2ba10 ]

The tls ulp overrides sk->prot with a new tls specific proto structs. The tls specific structs were previously based on the ipv4 specific tcp_prot sturct. As a result, attaching the tls ulp to an ipv6 tcp socket replaced some ipv6 callback with the ipv4 equivalents.

This patch adds ipv6 tls proto structs and uses them when attached to ipv6 sockets.

Fixes: 3c4d7559159b ('tls: kernel TLS support') Signed-off-by: Boris Pismenny borisp@mellanox.com Signed-off-by: Ilya Lesokhin ilyal@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tls/tls_main.c | 52 +++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 37 insertions(+), 15 deletions(-)

--- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -46,16 +46,26 @@ MODULE_DESCRIPTION("Transport Layer Secu MODULE_LICENSE("Dual BSD/GPL");

enum { + TLSV4, + TLSV6, + TLS_NUM_PROTS, +}; + +enum { TLS_BASE_TX, TLS_SW_TX, TLS_NUM_CONFIG, };

-static struct proto tls_prots[TLS_NUM_CONFIG]; +static struct proto *saved_tcpv6_prot; +static DEFINE_MUTEX(tcpv6_prot_mutex); +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];

static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) { - sk->sk_prot = &tls_prots[ctx->tx_conf]; + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; + + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf]; }

int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -450,8 +460,21 @@ static int tls_setsockopt(struct sock *s return do_tls_setsockopt(sk, optname, optval, optlen); }

+static void build_protos(struct proto *prot, struct proto *base) +{ + prot[TLS_BASE_TX] = *base; + prot[TLS_BASE_TX].setsockopt = tls_setsockopt; + prot[TLS_BASE_TX].getsockopt = tls_getsockopt; + prot[TLS_BASE_TX].close = tls_sk_proto_close; + + prot[TLS_SW_TX] = prot[TLS_BASE_TX]; + prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; + prot[TLS_SW_TX].sendpage = tls_sw_sendpage; +} + static int tls_init(struct sock *sk) { + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; int rc = 0; @@ -476,6 +499,17 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close;

+ /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + if (ip_ver == TLSV6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + mutex_lock(&tcpv6_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + mutex_unlock(&tcpv6_prot_mutex); + } + ctx->tx_conf = TLS_BASE_TX; update_sk_prot(sk, ctx); out: @@ -488,21 +522,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_op .init = tls_init, };

-static void build_protos(struct proto *prot, struct proto *base) -{ - prot[TLS_BASE_TX] = *base; - prot[TLS_BASE_TX].setsockopt = tls_setsockopt; - prot[TLS_BASE_TX].getsockopt = tls_getsockopt; - prot[TLS_BASE_TX].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE_TX]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; -} - static int __init tls_register(void) { - build_protos(tls_prots, &tcp_prot); + build_protos(tls_prots[TLSV4], &tcp_prot);

tcp_register_ulp(&tcp_tls_ulp_ops);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit d7cdee5ea8d28ae1b6922deb0c1badaa3aa0ef8c ]

Li Shuang reported an Oops with cls_u32 due to an use-after-free in u32_destroy_key(). The use-after-free can be triggered with:

dev=lo tc qdisc add dev $dev root handle 1: htb default 10 tc filter add dev $dev parent 1: prio 5 handle 1: protocol ip u32 divisor 256 tc filter add dev $dev protocol ip parent 1: prio 5 u32 ht 800:: match ip dst\ 10.0.0.0/8 hashkey mask 0x0000ff00 at 16 link 1: tc qdisc del dev $dev root

Which causes the following kasan splat:

================================================================== BUG: KASAN: use-after-free in u32_destroy_key.constprop.21+0x117/0x140 [cls_u32] Read of size 4 at addr ffff881b83dae618 by task kworker/u48:5/571

CPU: 17 PID: 571 Comm: kworker/u48:5 Not tainted 4.15.0+ #87 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016 Workqueue: tc_filter_workqueue u32_delete_key_freepf_work [cls_u32] Call Trace: dump_stack+0xd6/0x182 ? dma_virt_map_sg+0x22e/0x22e print_address_description+0x73/0x290 kasan_report+0x277/0x360 ? u32_destroy_key.constprop.21+0x117/0x140 [cls_u32] u32_destroy_key.constprop.21+0x117/0x140 [cls_u32] u32_delete_key_freepf_work+0x1c/0x30 [cls_u32] process_one_work+0xae0/0x1c80 ? sched_clock+0x5/0x10 ? pwq_dec_nr_in_flight+0x3c0/0x3c0 ? _raw_spin_unlock_irq+0x29/0x40 ? trace_hardirqs_on_caller+0x381/0x570 ? _raw_spin_unlock_irq+0x29/0x40 ? finish_task_switch+0x1e5/0x760 ? finish_task_switch+0x208/0x760 ? preempt_notifier_dec+0x20/0x20 ? __schedule+0x839/0x1ee0 ? check_noncircular+0x20/0x20 ? firmware_map_remove+0x73/0x73 ? find_held_lock+0x39/0x1c0 ? worker_thread+0x434/0x1820 ? lock_contended+0xee0/0xee0 ? lock_release+0x1100/0x1100 ? init_rescuer.part.16+0x150/0x150 ? retint_kernel+0x10/0x10 worker_thread+0x216/0x1820 ? process_one_work+0x1c80/0x1c80 ? lock_acquire+0x1a5/0x540 ? lock_downgrade+0x6b0/0x6b0 ? sched_clock+0x5/0x10 ? lock_release+0x1100/0x1100 ? compat_start_thread+0x80/0x80 ? do_raw_spin_trylock+0x190/0x190 ? _raw_spin_unlock_irq+0x29/0x40 ? trace_hardirqs_on_caller+0x381/0x570 ? _raw_spin_unlock_irq+0x29/0x40 ? finish_task_switch+0x1e5/0x760 ? finish_task_switch+0x208/0x760 ? preempt_notifier_dec+0x20/0x20 ? __schedule+0x839/0x1ee0 ? kmem_cache_alloc_trace+0x143/0x320 ? firmware_map_remove+0x73/0x73 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x170 ? find_held_lock+0x39/0x1c0 ? schedule+0xf3/0x3b0 ? lock_downgrade+0x6b0/0x6b0 ? __schedule+0x1ee0/0x1ee0 ? do_wait_intr_irq+0x340/0x340 ? do_raw_spin_trylock+0x190/0x190 ? _raw_spin_unlock_irqrestore+0x32/0x60 ? process_one_work+0x1c80/0x1c80 ? process_one_work+0x1c80/0x1c80 kthread+0x312/0x3d0 ? kthread_create_worker_on_cpu+0xc0/0xc0 ret_from_fork+0x3a/0x50

Allocated by task 1688: kasan_kmalloc+0xa0/0xd0 __kmalloc+0x162/0x380 u32_change+0x1220/0x3c9e [cls_u32] tc_ctl_tfilter+0x1ba6/0x2f80 rtnetlink_rcv_msg+0x4f0/0x9d0 netlink_rcv_skb+0x124/0x320 netlink_unicast+0x430/0x600 netlink_sendmsg+0x8fa/0xd60 sock_sendmsg+0xb1/0xe0 ___sys_sendmsg+0x678/0x980 __sys_sendmsg+0xc4/0x210 do_syscall_64+0x232/0x7f0 return_from_SYSCALL_64+0x0/0x75

Freed by task 112: kasan_slab_free+0x71/0xc0 kfree+0x114/0x320 rcu_process_callbacks+0xc3f/0x1600 __do_softirq+0x2bf/0xc06

The buggy address belongs to the object at ffff881b83dae600 which belongs to the cache kmalloc-4096 of size 4096 The buggy address is located 24 bytes inside of 4096-byte region [ffff881b83dae600, ffff881b83daf600) The buggy address belongs to the page: page:ffffea006e0f6a00 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0 flags: 0x17ffffc0008100(slab|head) raw: 0017ffffc0008100 0000000000000000 0000000000000000 0000000100070007 raw: dead000000000100 dead000000000200 ffff880187c0e600 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff881b83dae500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff881b83dae580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

ffff881b83dae600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

^ ffff881b83dae680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff881b83dae700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

The problem is that the htnode is freed before the linked knodes and the latter will try to access the first at u32_destroy_key() time. This change addresses the issue using the htnode refcnt to guarantee the correct free order. While at it also add a RCU annotation, to keep sparse happy.

v1 -> v2: use rtnl_derefence() instead of RCU read locks v2 -> v3: - don't check refcnt in u32_destroy_hnode() - cleaned-up u32_destroy() implementation - cleaned-up code comment v3 -> v4: - dropped unneeded comment

Reported-by: Li Shuang shuali@redhat.com Fixes: c0d378ef1266 ("net_sched: use tcf_queue_work() in u32 filter") Signed-off-by: Paolo Abeni pabeni@redhat.com Acked-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/cls_u32.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)

--- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -397,10 +397,12 @@ static int u32_init(struct tcf_proto *tp static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, bool free_pf) { + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + tcf_exts_destroy(&n->exts); tcf_exts_put_net(&n->exts); - if (n->ht_down) - n->ht_down->refcnt--; + if (ht && --ht->refcnt == 0) + kfree(ht); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -653,16 +655,15 @@ static void u32_destroy(struct tcf_proto

hlist_del(&tp_c->hnode);

- for (ht = rtnl_dereference(tp_c->hlist); - ht; - ht = rtnl_dereference(ht->next)) { - ht->refcnt--; - u32_clear_hnode(tp, ht); - } - while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) { + u32_clear_hnode(tp, ht); RCU_INIT_POINTER(tp_c->hlist, ht->next); - kfree_rcu(ht, rcu); + + /* u32_destroy_key() will later free ht for us, if it's + * still referenced by some knode + */ + if (--ht->refcnt == 0) + kfree_rcu(ht, rcu); }

idr_destroy(&tp_c->handle_idr);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Jason A. Donenfeld" Jason@zx2c4.com

[ Upstream commit b87b6194be631c94785fe93398651e804ed43e28 ]

Before, if cb->start() failed, the module reference would never be put, because cb->cb_running is intentionally false at this point. Users are generally annoyed by this because they can no longer unload modules that leak references. Also, it may be possible to tediously wrap a reference counter back to zero, especially since module.c still uses atomic_inc instead of refcount_inc.

This patch expands the error path to simply call module_put if cb->start() fails.

Fixes: 41c87425a1ac ("netlink: do not set cb_running if dump's start() errs") Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netlink/af_netlink.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2275,7 +2275,7 @@ int __netlink_dump_start(struct sock *ss if (cb->start) { ret = cb->start(cb); if (ret) - goto error_unlock; + goto error_put; }

nlk->cb_running = true; @@ -2295,6 +2295,8 @@ int __netlink_dump_start(struct sock *ss */ return -EINTR;

+error_put: + module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(nlk->cb_mutex);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason Wang jasowang@redhat.com

[ Upstream commit 1bb4f2e868a2891ab8bc668b8173d6ccb8c4ce6f ]

We don't flush batched XDP packets through xdp_do_flush_map(), this will cause packets stall at TX queue. Consider we don't do XDP on NAPI poll(), the only possible fix is to call xdp_do_flush_map() immediately after xdp_do_redirect().

Note, this in fact won't try to batch packets through devmap, we could address in the future.

Reported-by: Christoffer Dall christoffer.dall@linaro.org Fixes: 761876c857cb ("tap: XDP support") Signed-off-by: Jason Wang jasowang@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/tun.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1490,6 +1490,7 @@ static struct sk_buff *tun_build_skb(str get_page(alloc_frag->page); alloc_frag->offset += buflen; err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); + xdp_do_flush_map(); if (err) goto err_redirect; rcu_read_unlock();

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason Wang jasowang@redhat.com

[ Upstream commit 4e09ff5362843dff3accfa84c805c7f3a99de9cd ]

We try to disable NAPI to prevent a single XDP TX queue being used by multiple cpus. But we don't check if device is up (NAPI is enabled), this could result stall because of infinite wait in napi_disable(). Fixing this by checking device state through netif_running() before.

Fixes: 4941d472bf95b ("virtio-net: do not reset during XDP set") Signed-off-by: Jason Wang jasowang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/virtio_net.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

--- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2040,8 +2040,9 @@ static int virtnet_xdp_set(struct net_de }

/* Make sure NAPI is not using any XDP TX queues for RX. */ - for (i = 0; i < vi->max_queue_pairs; i++) - napi_disable(&vi->rq[i].napi); + if (netif_running(dev)) + for (i = 0; i < vi->max_queue_pairs; i++) + napi_disable(&vi->rq[i].napi);

netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); @@ -2060,7 +2061,8 @@ static int virtnet_xdp_set(struct net_de } if (old_prog) bpf_prog_put(old_prog); - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (netif_running(dev)) + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); }

return 0;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vlad Buslov vladbu@mellanox.com

[ Upstream commit 9238e380e823a39983ee8d6b6ee8d1a9c4ba8a65 ]

If building match list or adding existing fg fails when node is locked, function returned without unlocking it. This happened if node version changed or adding existing fg returned with EAGAIN after jumping to search_again_locked label.

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel") Signed-off-by: Vlad Buslov vladbu@mellanox.com Reviewed-by: Maor Gottlieb maorg@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1755,8 +1755,11 @@ search_again_locked:

/* Collect all fgs which has a matching match_criteria */ err = build_match_list(&match_head, ft, spec); - if (err) + if (err) { + if (take_write) + up_write_ref_node(&ft->node); return ERR_PTR(err); + }

if (!take_write) up_read_ref_node(&ft->node); @@ -1765,8 +1768,11 @@ search_again_locked: dest_num, version); free_match_list(&match_head); if (!IS_ERR(rule) || - (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) + (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) { + if (take_write) + up_write_ref_node(&ft->node); return rule; + }

if (!take_write) { nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Song Liu songliubraving@fb.com

[ Upstream commit 5c487bb9adddbc1d23433e09d2548759375c2b52 ]

tracepoint tcp_send_reset requires a full socket to work. However, it may be called when in TCP_TIME_WAIT:

case TCP_TW_RST: tcp_v6_send_reset(sk, skb); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it;

To avoid this problem, this patch checks the socket with sk_fullsock() before calling trace_tcp_send_reset().

Fixes: c24b14c46bb8 ("tcp: add tracepoint trace_tcp_send_reset") Signed-off-by: Song Liu songliubraving@fb.com Reviewed-by: Lawrence Brakmo brakmo@fb.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv6/tcp_ipv6.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -705,7 +705,8 @@ static void tcp_v4_send_reset(const stru */ if (sk) { arg.bound_dev_if = sk->sk_bound_dev_if; - trace_tcp_send_reset(sk, skb); + if (sk_fullsock(sk)) + trace_tcp_send_reset(sk, skb); }

BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -943,7 +943,8 @@ static void tcp_v6_send_reset(const stru

if (sk) { oif = sk->sk_bound_dev_if; - trace_tcp_send_reset(sk, skb); + if (sk_fullsock(sk)) + trace_tcp_send_reset(sk, skb); }

tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Chapman jchapman@katalix.com

[ Upstream commit 225eb26489d05c679a4c4197ffcb81c81e9dcaf4 ]

Previously, if a ppp session was closed, we called inet_shutdown to mark the socket as unconnected such that userspace would get errors and then close the socket. This could race with userspace closing the socket. Instead, leave userspace to close the socket in its own time (our session will be detached anyway).

BUG: KASAN: use-after-free in inet_shutdown+0x5d/0x1c0 Read of size 4 at addr ffff880010ea3ac0 by task syzbot_347bd5ac/8296

CPU: 3 PID: 8296 Comm: syzbot_347bd5ac Not tainted 4.16.0-rc1+ #91 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x101/0x157 ? inet_shutdown+0x5d/0x1c0 print_address_description+0x78/0x260 ? inet_shutdown+0x5d/0x1c0 kasan_report+0x240/0x360 __asan_load4+0x78/0x80 inet_shutdown+0x5d/0x1c0 ? pppol2tp_show+0x80/0x80 pppol2tp_session_close+0x68/0xb0 l2tp_tunnel_closeall+0x199/0x210 ? udp_v6_flush_pending_frames+0x90/0x90 l2tp_udp_encap_destroy+0x6b/0xc0 ? l2tp_tunnel_del_work+0x2e0/0x2e0 udpv6_destroy_sock+0x8c/0x90 sk_common_release+0x47/0x190 udp_lib_close+0x15/0x20 inet_release+0x85/0xd0 inet6_release+0x43/0x60 sock_release+0x53/0x100 ? sock_alloc_file+0x260/0x260 sock_close+0x1b/0x20 __fput+0x19f/0x380 ____fput+0x1a/0x20 task_work_run+0xd2/0x110 exit_to_usermode_loop+0x18d/0x190 do_syscall_64+0x389/0x3b0 entry_SYSCALL_64_after_hwframe+0x26/0x9b RIP: 0033:0x7fe240a45259 RSP: 002b:00007fe241132df8 EFLAGS: 00000297 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007fe240a45259 RDX: 00007fe240a45259 RSI: 0000000000000000 RDI: 00000000000000a5 RBP: 00007fe241132e20 R08: 00007fe241133700 R09: 0000000000000000 R10: 00007fe241133700 R11: 0000000000000297 R12: 0000000000000000 R13: 00007ffc49aff84f R14: 0000000000000000 R15: 00007fe241141040

Allocated by task 8331: save_stack+0x43/0xd0 kasan_kmalloc+0xad/0xe0 kasan_slab_alloc+0x12/0x20 kmem_cache_alloc+0x144/0x3e0 sock_alloc_inode+0x22/0x130 alloc_inode+0x3d/0xf0 new_inode_pseudo+0x1c/0x90 sock_alloc+0x30/0x110 __sock_create+0xaa/0x4c0 SyS_socket+0xbe/0x130 do_syscall_64+0x128/0x3b0 entry_SYSCALL_64_after_hwframe+0x26/0x9b

Freed by task 8314: save_stack+0x43/0xd0 __kasan_slab_free+0x11a/0x170 kasan_slab_free+0xe/0x10 kmem_cache_free+0x88/0x2b0 sock_destroy_inode+0x49/0x50 destroy_inode+0x77/0xb0 evict+0x285/0x340 iput+0x429/0x530 dentry_unlink_inode+0x28c/0x2c0 __dentry_kill+0x1e3/0x2f0 dput.part.21+0x500/0x560 dput+0x24/0x30 __fput+0x2aa/0x380 ____fput+0x1a/0x20 task_work_run+0xd2/0x110 exit_to_usermode_loop+0x18d/0x190 do_syscall_64+0x389/0x3b0 entry_SYSCALL_64_after_hwframe+0x26/0x9b

Fixes: fd558d186df2c ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts") Signed-off-by: James Chapman jchapman@katalix.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/l2tp/l2tp_ppp.c | 10 ---------- 1 file changed, 10 deletions(-)

--- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -420,16 +420,6 @@ abort: */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct sock *sk; - - BUG_ON(session->magic != L2TP_SESSION_MAGIC); - - sk = pppol2tp_session_get_sock(session); - if (sk) { - if (sk->sk_socket) - inet_shutdown(sk->sk_socket, SEND_SHUTDOWN); - sock_put(sk); - } }

/* Really kill the session socket. (Called from sock_put() if

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Chapman jchapman@katalix.com

[ Upstream commit d02ba2a6110c530a32926af8ad441111774d2893 ]

pppol2tp_release uses call_rcu to put the final ref on its socket. But the session object doesn't hold a ref on the session socket so may be freed while the pppol2tp_put_sk RCU callback is scheduled. Fix this by having the session hold a ref on its socket until the session is destroyed. It is this ref that is dropped via call_rcu.

Sessions are also deleted via l2tp_tunnel_closeall. This must now also put the final ref via call_rcu. So move the call_rcu call site into pppol2tp_session_close so that this happens in both destroy paths. A common destroy path should really be implemented, perhaps with l2tp_tunnel_closeall calling l2tp_session_delete like pppol2tp_release does, but this will be looked at later.

ODEBUG: activate active (active state 1) object type: rcu_head hint: (null) WARNING: CPU: 3 PID: 13407 at lib/debugobjects.c:291 debug_print_object+0x166/0x220 Modules linked in: CPU: 3 PID: 13407 Comm: syzbot_19c09769 Not tainted 4.16.0-rc2+ #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 RIP: 0010:debug_print_object+0x166/0x220 RSP: 0018:ffff880013647a00 EFLAGS: 00010082 RAX: dffffc0000000008 RBX: 0000000000000003 RCX: ffffffff814d3333 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff88001a59f6d0 RBP: ffff880013647a40 R08: 0000000000000000 R09: 0000000000000001 R10: ffff8800136479a8 R11: 0000000000000000 R12: 0000000000000001 R13: ffffffff86161420 R14: ffffffff85648b60 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88001a580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020e77000 CR3: 0000000006022000 CR4: 00000000000006e0 Call Trace: debug_object_activate+0x38b/0x530 ? debug_object_assert_init+0x3b0/0x3b0 ? __mutex_unlock_slowpath+0x85/0x8b0 ? pppol2tp_session_destruct+0x110/0x110 __call_rcu.constprop.66+0x39/0x890 ? __call_rcu.constprop.66+0x39/0x890 call_rcu_sched+0x17/0x20 pppol2tp_release+0x2c7/0x440 ? fcntl_setlk+0xca0/0xca0 ? sock_alloc_file+0x340/0x340 sock_release+0x92/0x1e0 sock_close+0x1b/0x20 __fput+0x296/0x6e0 ____fput+0x1a/0x20 task_work_run+0x127/0x1a0 do_exit+0x7f9/0x2ce0 ? SYSC_connect+0x212/0x310 ? mm_update_next_owner+0x690/0x690 ? up_read+0x1f/0x40 ? __do_page_fault+0x3c8/0xca0 do_group_exit+0x10d/0x330 ? do_group_exit+0x330/0x330 SyS_exit_group+0x22/0x30 do_syscall_64+0x1e0/0x730 ? trace_hardirqs_off_thunk+0x1a/0x1c entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x7f362e471259 RSP: 002b:00007ffe389abe08 EFLAGS: 00000202 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f362e471259 RDX: 00007f362e471259 RSI: 000000000000002e RDI: 0000000000000000 RBP: 00007ffe389abe30 R08: 0000000000000000 R09: 00007f362e944270 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000400b60 R13: 00007ffe389abf50 R14: 0000000000000000 R15: 0000000000000000 Code: 8d 3c dd a0 8f 64 85 48 89 fa 48 c1 ea 03 80 3c 02 00 75 7b 48 8b 14 dd a0 8f 64 85 4c 89 f6 48 c7 c7 20 85 64 85 e 8 2a 55 14 ff <0f> 0b 83 05 ad 2a 68 04 01 48 83 c4 18 5b 41 5c 41 5d 41 5e 41

Fixes: ee40fb2e1eb5b ("l2tp: protect sock pointer of struct pppol2tp_session with RCU") Signed-off-by: James Chapman jchapman@katalix.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/l2tp/l2tp_ppp.c | 52 +++++++++++++++++++++++++++------------------------- 1 file changed, 27 insertions(+), 25 deletions(-)

--- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -416,10 +416,28 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/

+static void pppol2tp_put_sk(struct rcu_head *head) +{ + struct pppol2tp_session *ps; + + ps = container_of(head, typeof(*ps), rcu); + sock_put(ps->__sk); +} + /* Called by l2tp_core when a session socket is being closed. */ static void pppol2tp_session_close(struct l2tp_session *session) { + struct pppol2tp_session *ps; + + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + if (ps->__sk) + call_rcu(&ps->rcu, pppol2tp_put_sk); + mutex_unlock(&ps->sk_lock); }

/* Really kill the session socket. (Called from sock_put() if @@ -439,14 +457,6 @@ static void pppol2tp_session_destruct(st } }

-static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Called when the PPPoX socket (session) is closed. */ static int pppol2tp_release(struct socket *sock) @@ -470,26 +480,17 @@ static int pppol2tp_release(struct socke sock_orphan(sk); sock->sk = NULL;

+ /* If the socket is associated with a session, + * l2tp_session_delete will call pppol2tp_session_close which + * will drop the session's ref on the socket. + */ session = pppol2tp_sock_to_session(sk); - - if (session != NULL) { - struct pppol2tp_session *ps; - + if (session) { l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop the ref obtained by pppol2tp_sock_to_session */ + sock_put(sk); } + release_sock(sk);

/* This will delete the session context via @@ -786,6 +787,7 @@ static int pppol2tp_connect(struct socke

out_no_ppp: /* This is how we get the session context from the socket. */ + sock_hold(sk); sk->sk_user_data = session; rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ursula Braun ubraun@linux.vnet.ibm.com

[ Upstream commit 89271c65edd599207dd982007900506283c90ae3 ]

For a memory range/skb where the last byte falls onto a page boundary (ie. 'end' is of the form xxx...xxx001), the PFN_UP() part of the calculation currently doesn't round up to the next PFN due to an off-by-one error. Thus qeth believes that the skb occupies one page less than it actually does, and may select a IO buffer that doesn't have enough spare buffer elements to fit all of the skb's data. HW detects this as a malformed buffer descriptor, and raises an exception which then triggers device recovery.

Fixes: 2863c61334aa ("qeth: refactor calculation of SBALE count") Signed-off-by: Ursula Braun ubraun@linux.vnet.ibm.com Signed-off-by: Julian Wiedmann jwi@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/net/qeth_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -836,7 +836,7 @@ struct qeth_trap_id { */ static inline int qeth_get_elements_for_range(addr_t start, addr_t end) { - return PFN_UP(end - 1) - PFN_DOWN(start); + return PFN_UP(end) - PFN_DOWN(start); }

static inline int qeth_get_micros(void)

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Julian Wiedmann jwi@linux.vnet.ibm.com

[ Upstream commit 12472af89632beb1ed8dea29d4efe208ca05b06a ]

qeth_get_elements_for_range() doesn't know how to handle a 0-length range (ie. start == end), and returns 1 when it should return 0. Such ranges occur on TSO skbs, where the L2/L3/L4 headers (and thus all of the skb's linear data) are skipped when mapping the skb into regular buffer elements.

This overestimation may cause several performance-related issues: 1. sub-optimal IO buffer selection, where the next buffer gets selected even though the skb would actually still fit into the current buffer. 2. forced linearization, if the element count for a non-linear skb exceeds QETH_MAX_BUFFER_ELEMENTS.

Rather than modifying qeth_get_elements_for_range() and adding overhead to every caller, fix up those callers that are in risk of passing a 0-length range.

Fixes: 2863c61334aa ("qeth: refactor calculation of SBALE count") Signed-off-by: Julian Wiedmann jwi@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/net/qeth_core_main.c | 10 ++++++---- drivers/s390/net/qeth_l3_main.c | 11 ++++++----- 2 files changed, 12 insertions(+), 9 deletions(-)

--- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -3835,10 +3835,12 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_ int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, int extra_elems, int data_offset) { - int elements = qeth_get_elements_for_range( - (addr_t)skb->data + data_offset, - (addr_t)skb->data + skb_headlen(skb)) + - qeth_get_elements_for_frags(skb); + addr_t end = (addr_t)skb->data + skb_headlen(skb); + int elements = qeth_get_elements_for_frags(skb); + addr_t start = (addr_t)skb->data + data_offset; + + if (start != end) + elements += qeth_get_elements_for_range(start, end);

if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { QETH_DBF_MESSAGE(2, "Invalid size of IP packet " --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2629,11 +2629,12 @@ static void qeth_tso_fill_header(struct static int qeth_l3_get_elements_no_tso(struct qeth_card *card, struct sk_buff *skb, int extra_elems) { - addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); - int elements = qeth_get_elements_for_range( - tcpdptr, - (addr_t)skb->data + skb_headlen(skb)) + - qeth_get_elements_for_frags(skb); + addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); + addr_t end = (addr_t)skb->data + skb_headlen(skb); + int elements = qeth_get_elements_for_frags(skb); + + if (start != end) + elements += qeth_get_elements_for_range(start, end);

if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { QETH_DBF_MESSAGE(2,

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Julian Wiedmann jwi@linux.vnet.ibm.com

[ Upstream commit 14d066c3531a87f727968cacd85bd95c75f59843 ]

Registering an IPv4 address with the HW takes quite a while, so we temporarily drop the ip_htable lock. Any concurrent add/remove of the same IP adjusts the IP's use count, and (on remove) is then blocked by addr->in_progress. After the register call has completed, we check the use count for concurrently attempted add/remove calls - and possibly straight-away deregister the IP again. This happens via l3_delete_ip(), which 1) looks up the queried IP in the htable (getting a reference to the *same* queried object), 2) deregisters the IP from the HW, and 3) frees the IP object.

The caller in l3_add_ip() then does a second free on the same object.

For this case, skip all the extra checks and lookups in l3_delete_ip() and just deregister & free the IP object ourselves.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") Signed-off-by: Julian Wiedmann jwi@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/net/qeth_l3_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -320,7 +320,8 @@ int qeth_l3_add_ip(struct qeth_card *car (rc == IPA_RC_LAN_OFFLINE)) { addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; if (addr->ref_counter < 1) { - qeth_l3_delete_ip(card, addr); + qeth_l3_deregister_addr_entry(card, addr); + hash_del(&addr->hnode); kfree(addr); } } else {

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Julian Wiedmann jwi@linux.vnet.ibm.com

[ Upstream commit c5c48c58b259bb8f0482398370ee539d7a12df3e ]

Current code ("qeth_l3_ip_from_hash()") matches a queried address object against objects in the IP table by IP address, Mask/Prefix Length and MAC address ("qeth_l3_ipaddrs_is_equal()"). But what callers actually require is either a) "is this IP address registered" (ie. match by IP address only), before adding a new address. b) or "is this address object registered" (ie. match all relevant attributes), before deleting an address.

Right now 1. the ADD path is too strict in its lookup, and eg. doesn't detect conflicts between an existing NORMAL address and a new VIPA address (because the NORMAL address will have mask != 0, while VIPA has a mask == 0), 2. the DELETE path is not strict enough, and eg. allows del_rxip() to delete a VIPA address as long as the IP address matches.

Fix all this by adding helpers (_addr_match_ip() and _addr_match_all()) that do the appropriate checking.

Note that the ADD path for NORMAL addresses is special, as qeth keeps track of how many times such an address is in use (and there is no immediate way of returning errors to the caller). So when a requested NORMAL address _fully_ matches an existing one, it's not considered a conflict and we merely increment the refcount.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") Signed-off-by: Julian Wiedmann jwi@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/net/qeth_l3.h | 34 ++++++++++++++ drivers/s390/net/qeth_l3_main.c | 91 ++++++++++++++++++---------------------- 2 files changed, 74 insertions(+), 51 deletions(-)

--- a/drivers/s390/net/qeth_l3.h +++ b/drivers/s390/net/qeth_l3.h @@ -40,8 +40,40 @@ struct qeth_ipaddr { unsigned int pfxlen; } a6; } u; - }; + +static inline bool qeth_l3_addr_match_ip(struct qeth_ipaddr *a1, + struct qeth_ipaddr *a2) +{ + if (a1->proto != a2->proto) + return false; + if (a1->proto == QETH_PROT_IPV6) + return ipv6_addr_equal(&a1->u.a6.addr, &a2->u.a6.addr); + return a1->u.a4.addr == a2->u.a4.addr; +} + +static inline bool qeth_l3_addr_match_all(struct qeth_ipaddr *a1, + struct qeth_ipaddr *a2) +{ + /* Assumes that the pair was obtained via qeth_l3_addr_find_by_ip(), + * so 'proto' and 'addr' match for sure. + * + * For ucast: + * - 'mac' is always 0. + * - 'mask'/'pfxlen' for RXIP/VIPA is always 0. For NORMAL, matching + * values are required to avoid mixups in takeover eligibility. + * + * For mcast, + * - 'mac' is mapped from the IP, and thus always matches. + * - 'mask'/'pfxlen' is always 0. + */ + if (a1->type != a2->type) + return false; + if (a1->proto == QETH_PROT_IPV6) + return a1->u.a6.pfxlen == a2->u.a6.pfxlen; + return a1->u.a4.mask == a2->u.a4.mask; +} + static inline u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr) { u64 ret = 0; --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -150,6 +150,24 @@ int qeth_l3_string_to_ipaddr(const char return -EINVAL; }

+static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card, + struct qeth_ipaddr *query) +{ + u64 key = qeth_l3_ipaddr_hash(query); + struct qeth_ipaddr *addr; + + if (query->is_multicast) { + hash_for_each_possible(card->ip_mc_htable, addr, hnode, key) + if (qeth_l3_addr_match_ip(addr, query)) + return addr; + } else { + hash_for_each_possible(card->ip_htable, addr, hnode, key) + if (qeth_l3_addr_match_ip(addr, query)) + return addr; + } + return NULL; +} + static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len) { int i, j; @@ -203,34 +221,6 @@ static bool qeth_l3_is_addr_covered_by_i return rc; }

-inline int -qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2) -{ - return addr1->proto == addr2->proto && - !memcmp(&addr1->u, &addr2->u, sizeof(addr1->u)) && - !memcmp(&addr1->mac, &addr2->mac, sizeof(addr1->mac)); -} - -static struct qeth_ipaddr * -qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) -{ - struct qeth_ipaddr *addr; - - if (tmp_addr->is_multicast) { - hash_for_each_possible(card->ip_mc_htable, addr, - hnode, qeth_l3_ipaddr_hash(tmp_addr)) - if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr)) - return addr; - } else { - hash_for_each_possible(card->ip_htable, addr, - hnode, qeth_l3_ipaddr_hash(tmp_addr)) - if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr)) - return addr; - } - - return NULL; -} - int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; @@ -245,8 +235,8 @@ int qeth_l3_delete_ip(struct qeth_card * QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8); }

- addr = qeth_l3_ip_from_hash(card, tmp_addr); - if (!addr) + addr = qeth_l3_find_addr_by_ip(card, tmp_addr); + if (!addr || !qeth_l3_addr_match_all(addr, tmp_addr)) return -ENOENT;

addr->ref_counter--; @@ -268,6 +258,7 @@ int qeth_l3_add_ip(struct qeth_card *car { int rc = 0; struct qeth_ipaddr *addr; + char buf[40];

QETH_CARD_TEXT(card, 4, "addip");

@@ -278,8 +269,20 @@ int qeth_l3_add_ip(struct qeth_card *car QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8); }

- addr = qeth_l3_ip_from_hash(card, tmp_addr); - if (!addr) { + addr = qeth_l3_find_addr_by_ip(card, tmp_addr); + if (addr) { + if (tmp_addr->type != QETH_IP_TYPE_NORMAL) + return -EADDRINUSE; + if (qeth_l3_addr_match_all(addr, tmp_addr)) { + addr->ref_counter++; + return 0; + } + qeth_l3_ipaddr_to_string(tmp_addr->proto, (u8 *)&tmp_addr->u, + buf); + dev_warn(&card->gdev->dev, + "Registering IP address %s failed\n", buf); + return -EADDRINUSE; + } else { addr = qeth_l3_get_addr_buffer(tmp_addr->proto); if (!addr) return -ENOMEM; @@ -327,11 +330,7 @@ int qeth_l3_add_ip(struct qeth_card *car hash_del(&addr->hnode); kfree(addr); } - } else { - if (addr->type == QETH_IP_TYPE_NORMAL) - addr->ref_counter++; } - return rc; }

@@ -715,12 +714,7 @@ int qeth_l3_add_vipa(struct qeth_card *c return -ENOMEM;

spin_lock_bh(&card->ip_lock); - - if (qeth_l3_ip_from_hash(card, ipaddr)) - rc = -EEXIST; - else - qeth_l3_add_ip(card, ipaddr); - + rc = qeth_l3_add_ip(card, ipaddr); spin_unlock_bh(&card->ip_lock);

kfree(ipaddr); @@ -783,12 +777,7 @@ int qeth_l3_add_rxip(struct qeth_card *c return -ENOMEM;

spin_lock_bh(&card->ip_lock); - - if (qeth_l3_ip_from_hash(card, ipaddr)) - rc = -EEXIST; - else - qeth_l3_add_ip(card, ipaddr); - + rc = qeth_l3_add_ip(card, ipaddr); spin_unlock_bh(&card->ip_lock);

kfree(ipaddr); @@ -1396,8 +1385,9 @@ qeth_l3_add_mc_to_hash(struct qeth_card memcpy(tmp->mac, buf, sizeof(tmp->mac)); tmp->is_multicast = 1;

- ipm = qeth_l3_ip_from_hash(card, tmp); + ipm = qeth_l3_find_addr_by_ip(card, tmp); if (ipm) { + /* for mcast, by-IP match means full match */ ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4); @@ -1480,8 +1470,9 @@ qeth_l3_add_mc6_to_hash(struct qeth_card sizeof(struct in6_addr)); tmp->is_multicast = 1;

- ipm = qeth_l3_ip_from_hash(card, tmp); + ipm = qeth_l3_find_addr_by_ip(card, tmp); if (ipm) { + /* for mcast, by-IP match means full match */ ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING; continue; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yuchung Cheng ycheng@google.com

[ Upstream commit d4131f09770d9b7471c9da65e6ecd2477746ac5c ]

This reverts commit cc663f4d4c97b7297fb45135ab23cfd508b35a77. While fixing some broken middle-boxes that modifies receive window fields, it does not address middle-boxes that strip off SACK options. The best solution is to fully revert this patch and the root F-RTO enhancement.

Fixes: cc663f4d4c97 ("tcp: restrict F-RTO to work-around broken middle-boxes") Reported-by: Teodor Milkov tm@del.bg Signed-off-by: Yuchung Cheng ycheng@google.com Signed-off-by: Neal Cardwell ncardwell@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_input.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 45f750e85714..50963f92a67d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1915,7 +1915,6 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sk_buff *skb; - bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ bool mark_lost;

@@ -1974,17 +1973,15 @@ void tcp_enter_loss(struct sock *sk) tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp);

- /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous - * loss recovery is underway except recurring timeout(s) on - * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing - * - * In theory F-RTO can be used repeatedly during loss recovery. - * In practice this interacts badly with broken middle-boxes that - * falsely raise the receive window, which results in repeated - * timeouts and stop-and-go behavior. + /* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO + * if a previous recovery is underway, otherwise it may incorrectly + * call a timeout spurious if some previously retransmitted packets + * are s/acked (sec 3.2). We do not apply that retriction since + * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS + * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO + * on PTMU discovery to avoid sending new data. */ tp->frto = net->ipv4.sysctl_tcp_frto && - (new_recovery || icsk->icsk_retransmits) && !inet_csk(sk)->icsk_mtup.probe_size; }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ming Lei ming.lei@redhat.com

commit 105976f517791aed3b11f8f53b308a2069d42055 upstream.

__blk_mq_requeue_request() covers two cases:

- one is that the requeued request is added to hctx->dispatch, such as blk_mq_dispatch_rq_list()

- another case is that the request is requeued to io scheduler, such as blk_mq_requeue_request().

We should call io sched's .requeue_request callback only for the 2nd case.

Cc: Paolo Valente paolo.valente@linaro.org Cc: Omar Sandoval osandov@fb.com Fixes: bd166ef183c2 ("blk-mq-sched: add framework for MQ capable IO schedulers") Cc: stable@vger.kernel.org Reviewed-by: Bart Van Assche bart.vanassche@wdc.com Acked-by: Paolo Valente paolo.valente@linaro.org Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- block/blk-mq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -655,7 +655,6 @@ static void __blk_mq_requeue_request(str

trace_block_rq_requeue(q, rq); wbt_requeue(q->rq_wb, &rq->issue_stat); - blk_mq_sched_requeue_request(rq);

if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) { if (q->dma_drain_size && blk_rq_bytes(rq)) @@ -667,6 +666,9 @@ void blk_mq_requeue_request(struct reque { __blk_mq_requeue_request(rq);

+ /* this request will be re-inserted to io scheduler queue */ + blk_mq_sched_requeue_request(rq); + BUG_ON(blk_queued_rq(rq)); blk_mq_add_to_requeue_list(rq, true, kick_requeue_list); }

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Anna Karbownik anna.karbownik@intel.com

commit bf8486709ac7fad99e4040dea73fe466c57a4ae1 upstream.

Commit

3286d3eb906c ("EDAC, sb_edac: Drop NUM_CHANNELS from 8 back to 4")

decreased NUM_CHANNELS from 8 to 4, but this is not enough for Knights Landing which supports up to 6 channels.

This caused out-of-bounds writes to pvt->mirror_mode and pvt->tolm variables which don't pay critical role on KNL code path, so the memory corruption wasn't causing any visible driver failures.

The easiest way of fixing it is to change NUM_CHANNELS to 6. Do that.

An alternative solution would be to restructure the KNL part of the driver to 2MC/3channel representation.

Reported-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Anna Karbownik anna.karbownik@intel.com Cc: Mauro Carvalho Chehab mchehab@kernel.org Cc: Tony Luck tony.luck@intel.com Cc: jim.m.snow@intel.com Cc: krzysztof.paliswiat@intel.com Cc: lukasz.odzioba@intel.com Cc: qiuxu.zhuo@intel.com Cc: linux-edac linux-edac@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 3286d3eb906c ("EDAC, sb_edac: Drop NUM_CHANNELS from 8 back to 4") Link: http://lkml.kernel.org/r/1519312693-4789-1-git-send-email-anna.karbownik@int... [ Massage commit message. ] Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/edac/sb_edac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -279,7 +279,7 @@ static const u32 correrrthrsld[] = { * sbridge structs */

-#define NUM_CHANNELS 4 /* Max channels per MC */ +#define NUM_CHANNELS 6 /* Max channels per MC */ #define MAX_DIMMS 3 /* Max DIMMS per channel */ #define KNL_MAX_CHAS 38 /* KNL max num. of Cache Home Agents */ #define KNL_MAX_CHANNELS 6 /* KNL max num. of PCI channels */

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Hildenbrand david@redhat.com

commit 0e7def5fb0dc53ddbb9f62a497d15f1e11ccdc36 upstream.

Right now, SET CLOCK called in the guest does not properly take care of the epoch index, as the call goes via the old kvm_s390_set_tod_clock() interface. So the epoch index is neither reset to 0, if required, nor properly set to e.g. 0xff on negative values.

Fix this by providing a single kvm_s390_set_tod_clock() function. Move Multiple-epoch facility handling into it.

Signed-off-by: David Hildenbrand david@redhat.com Message-Id: 20180207114647.6220-3-david@redhat.com Reviewed-by: Christian Borntraeger borntraeger@de.ibm.com Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger borntraeger@de.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/s390/kvm/kvm-s390.c | 46 +++++++++++++++------------------------------- arch/s390/kvm/kvm-s390.h | 5 ++--- arch/s390/kvm/priv.c | 9 +++++---- 3 files changed, 22 insertions(+), 38 deletions(-)

--- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -889,12 +889,9 @@ static int kvm_s390_set_tod_ext(struct k if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod))) return -EFAULT;

- if (test_kvm_facility(kvm, 139)) - kvm_s390_set_tod_clock_ext(kvm, &gtod); - else if (gtod.epoch_idx == 0) - kvm_s390_set_tod_clock(kvm, gtod.tod); - else + if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; + kvm_s390_set_tod_clock(kvm, &gtod);

VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -919,13 +916,14 @@ static int kvm_s390_set_tod_high(struct

static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) { - u64 gtod; + struct kvm_s390_vm_tod_clock gtod = { 0 };

- if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod))) + if (copy_from_user(&gtod.tod, (void __user *)attr->addr, + sizeof(gtod.tod))) return -EFAULT;

- kvm_s390_set_tod_clock(kvm, gtod); - VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod); + kvm_s390_set_tod_clock(kvm, &gtod); + VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; }

@@ -2947,8 +2945,8 @@ retry: return 0; }

-void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod) +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod) { struct kvm_vcpu *vcpu; struct kvm_s390_tod_clock_ext htod; @@ -2960,10 +2958,12 @@ void kvm_s390_set_tod_clock_ext(struct k get_tod_clock_ext((char *)&htod);

kvm->arch.epoch = gtod->tod - htod.tod; - kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; - - if (kvm->arch.epoch > gtod->tod) - kvm->arch.epdx -= 1; + kvm->arch.epdx = 0; + if (test_kvm_facility(kvm, 139)) { + kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; + if (kvm->arch.epoch > gtod->tod) + kvm->arch.epdx -= 1; + }

kvm_s390_vcpu_block_all(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -2974,22 +2974,6 @@ void kvm_s390_set_tod_clock_ext(struct k kvm_s390_vcpu_unblock_all(kvm); preempt_enable(); mutex_unlock(&kvm->lock); -} - -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod) -{ - struct kvm_vcpu *vcpu; - int i; - - mutex_lock(&kvm->lock); - preempt_disable(); - kvm->arch.epoch = tod - get_tod_clock(); - kvm_s390_vcpu_block_all(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.sie_block->epoch = kvm->arch.epoch; - kvm_s390_vcpu_unblock_all(kvm); - preempt_enable(); - mutex_unlock(&kvm->lock); }

/** --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -268,9 +268,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);

/* implemented in kvm-s390.c */ -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod); -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod); +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -81,9 +81,10 @@ int kvm_s390_handle_e3(struct kvm_vcpu * /* Handle SCK (SET CLOCK) interception */ static int handle_set_clock(struct kvm_vcpu *vcpu) { + struct kvm_s390_vm_tod_clock gtod = { 0 }; int rc; u8 ar; - u64 op2, val; + u64 op2;

if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -91,12 +92,12 @@ static int handle_set_clock(struct kvm_v op2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (op2 & 7) /* Operand must be on a doubleword boundary */ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); + rc = read_guest(vcpu, op2, ar, &gtod.tod, sizeof(gtod.tod)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc);

- VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val); - kvm_s390_set_tod_clock(vcpu->kvm, val); + VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod); + kvm_s390_set_tod_clock(vcpu->kvm, &gtod);

kvm_s390_set_psw_cc(vcpu, 0); return 0;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Hildenbrand david@redhat.com

commit 1575767ef3cf5326701d2ae3075b7732cbc855e4 upstream.

For now, we don't take care of over/underflows. Especially underflows are critical:

Assume the epoch is currently 0 and we get a sync request for delta=1, meaning the TOD is moved forward by 1 and we have to fix it up by subtracting 1 from the epoch. Right now, this will leave the epoch index untouched, resulting in epoch=-1, epoch_idx=0, which is wrong.

We have to take care of over and underflows, also for the VSIE case. So let's factor out calculation into a separate function.

Signed-off-by: David Hildenbrand david@redhat.com Message-Id: 20180207114647.6220-5-david@redhat.com Reviewed-by: Christian Borntraeger borntraeger@de.ibm.com Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger borntraeger@de.ibm.com [use u8 for idx] Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/s390/kvm/kvm-s390.c | 32 +++++++++++++++++++++++++++++--- 1 file changed, 29 insertions(+), 3 deletions(-)

--- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -166,6 +166,28 @@ int kvm_arch_hardware_enable(void) static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end);

+static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) +{ + u8 delta_idx = 0; + + /* + * The TOD jumps by delta, we have to compensate this by adding + * -delta to the epoch. + */ + delta = -delta; + + /* sign-extension - we're adding to signed values below */ + if ((s64)delta < 0) + delta_idx = -1; + + scb->epoch += delta; + if (scb->ecd & ECD_MEF) { + scb->epdx += delta_idx; + if (scb->epoch < delta) + scb->epdx += 1; + } +} + /* * This callback is executed during stop_machine(). All CPUs are therefore * temporarily stopped. In order not to change guest behavior, we have to @@ -181,13 +203,17 @@ static int kvm_clock_sync(struct notifie unsigned long long *delta = v;

list_for_each_entry(kvm, &vm_list, vm_list) { - kvm->arch.epoch -= *delta; kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu->arch.sie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.sie_block, *delta); + if (i == 0) { + kvm->arch.epoch = vcpu->arch.sie_block->epoch; + kvm->arch.epdx = vcpu->arch.sie_block->epdx; + } if (vcpu->arch.cputm_enabled) vcpu->arch.cputm_start += *delta; if (vcpu->arch.vsie_block) - vcpu->arch.vsie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.vsie_block, + *delta); } } return NOTIFY_OK;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Beulich JBeulich@suse.com

commit 842cef9113c2120f74f645111ded1e020193d84c upstream.

Just like pte_{set,clear}_flags() their PMD and PUD counterparts should not do any address translation. This was outright wrong under Xen (causing a dead boot with no useful output on "suitable" systems), and produced needlessly more complicated code (even if just slightly) when paravirt was enabled.

Signed-off-by: Jan Beulich jbeulich@suse.com Reviewed-by: Juergen Gross jgross@suse.com Acked-by: Thomas Gleixner tglx@linutronix.de Cc: Andy Lutomirski luto@kernel.org Cc: Boris Ostrovsky boris.ostrovsky@oracle.com Cc: Borislav Petkov bp@alien8.de Cc: Brian Gerst brgerst@gmail.com Cc: Denys Vlasenko dvlasenk@redhat.com Cc: H. Peter Anvin hpa@zytor.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/5A8AF1BB02000078001A91C3@prv-mh.provo.novell.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/pgtable.h | 8 ++++---- arch/x86/include/asm/pgtable_types.h | 10 ++++++++++ 2 files changed, 14 insertions(+), 4 deletions(-)

--- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t { pmdval_t v = native_pmd_val(pmd);

- return __pmd(v | set); + return native_make_pmd(v | set); }

static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd);

- return __pmd(v & ~clear); + return native_make_pmd(v & ~clear); }

static inline pmd_t pmd_mkold(pmd_t pmd) @@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t { pudval_t v = native_pud_val(pud);

- return __pud(v | set); + return native_make_pud(v | set); }

static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud);

- return __pud(v & ~clear); + return native_make_pud(v & ~clear); }

static inline pud_t pud_mkold(pud_t pud) --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -323,6 +323,11 @@ static inline pudval_t native_pud_val(pu #else #include <asm-generic/pgtable-nopud.h>

+static inline pud_t native_make_pud(pudval_t val) +{ + return (pud_t) { .p4d.pgd = native_make_pgd(val) }; +} + static inline pudval_t native_pud_val(pud_t pud) { return native_pgd_val(pud.p4d.pgd); @@ -344,6 +349,11 @@ static inline pmdval_t native_pmd_val(pm #else #include <asm-generic/pgtable-nopmd.h>

+static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; +} + static inline pmdval_t native_pmd_val(pmd_t pmd) { return native_pgd_val(pmd.pud.p4d.pgd);

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel Schultz d.schultz@phytec.de

commit 5ce0bad4ccd04c8a989e94d3c89e4e796ac22e48 upstream.

Rockchip recommends to run the CPU cores only with operations points of 1.6 GHz or lower.

Removed the cpu0 node with too high operation points and use the default values instead.

Fixes: 903d31e34628 ("ARM: dts: rockchip: Add support for phyCORE-RK3288 SoM") Cc: stable@vger.kernel.org Signed-off-by: Daniel Schultz d.schultz@phytec.de Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/rk3288-phycore-som.dtsi | 20 -------------------- 1 file changed, 20 deletions(-)

--- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi +++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi @@ -110,26 +110,6 @@ }; };

-&cpu0 { - cpu0-supply = <&vdd_cpu>; - operating-points = < - /* KHz uV */ - 1800000 1400000 - 1608000 1350000 - 1512000 1300000 - 1416000 1200000 - 1200000 1100000 - 1008000 1050000 - 816000 1000000 - 696000 950000 - 600000 900000 - 408000 900000 - 312000 900000 - 216000 900000 - 126000 900000 - >; -}; - &emmc { status = "okay"; bus-width = <8>;

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann arnd@arndb.de

commit 67870eb1204223598ea6d8a4467b482e9f5875b5 upstream.

In banked-sr.c, we use a top-level '__asm__(".arch_extension virt")' statement to allow compilation of a multi-CPU kernel for ARMv6 and older ARMv7-A that don't normally support access to the banked registers.

This is considered to be a programming error by the gcc developers and will no longer work in gcc-8, where we now get a build error:

/tmp/cc4Qy7GR.s:34: Error: Banked registers are not available with this architecture. -- `mrs r3,SP_usr' /tmp/cc4Qy7GR.s:41: Error: Banked registers are not available with this architecture. -- `mrs r3,ELR_hyp' /tmp/cc4Qy7GR.s:55: Error: Banked registers are not available with this architecture. -- `mrs r3,SP_svc' /tmp/cc4Qy7GR.s:62: Error: Banked registers are not available with this architecture. -- `mrs r3,LR_svc' /tmp/cc4Qy7GR.s:69: Error: Banked registers are not available with this architecture. -- `mrs r3,SPSR_svc' /tmp/cc4Qy7GR.s:76: Error: Banked registers are not available with this architecture. -- `mrs r3,SP_abt'

Passign the '-march-armv7ve' flag to gcc works, and is ok here, because we know the functions won't ever be called on pre-ARMv7VE machines. Unfortunately, older compiler versions (4.8 and earlier) do not understand that flag, so we still need to keep the asm around.

Backporting to stable kernels (4.6+) is needed to allow those to be built with future compilers as well.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84129 Fixes: 33280b4cd1dc ("ARM: KVM: Add banked registers save/restore") Cc: stable@vger.kernel.org Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Christoffer Dall christoffer.dall@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/kvm/hyp/Makefile | 5 +++++ arch/arm/kvm/hyp/banked-sr.c | 4 ++++ 2 files changed, 9 insertions(+)

--- a/arch/arm/kvm/hyp/Makefile +++ b/arch/arm/kvm/hyp/Makefile @@ -7,6 +7,8 @@ ccflags-y += -fno-stack-protector -DDISA

KVM=../../../../virt/kvm

+CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve) + obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o @@ -15,7 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o obj-$(CONFIG_KVM_ARM_HOST) += vfp.o obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o +CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE) + obj-$(CONFIG_KVM_ARM_HOST) += entry.o obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o obj-$(CONFIG_KVM_ARM_HOST) += switch.o +CFLAGS_switch.o += $(CFLAGS_ARMV7VE) obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o --- a/arch/arm/kvm/hyp/banked-sr.c +++ b/arch/arm/kvm/hyp/banked-sr.c @@ -20,6 +20,10 @@

#include <asm/kvm_hyp.h>

+/* + * gcc before 4.9 doesn't understand -march=armv7ve, so we have to + * trick the assembler. + */ __asm__(".arch_extension virt");

void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kai Heng Feng kai.heng.feng@canonical.com

commit 36904703aeeeb6cd31993f1353c8325006229f9a upstream.

The i2c touchpad on Dell XPS 9570 and Precision M5530 doesn't work out of box.

The touchpad relies on its _INI method to update its _HID value from XXXX0000 to SYNA2393.

Also, the _STA relies on value of I2CN to report correct status.

Set acpi_gbl_parse_table_as_term_list so the value of I2CN can be correctly set up, and _INI can get run. The ACPI table in this machine is designed to get parsed this way.

Also, change the quirk table to a more generic name.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=198515 Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/acpi/bus.c | 38 +++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-)

--- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -66,10 +66,37 @@ static int set_copy_dsdt(const struct dm return 0; } #endif +static int set_gbl_term_list(const struct dmi_system_id *id) +{ + acpi_gbl_parse_table_as_term_list = 1; + return 0; +}

-static const struct dmi_system_id dsdt_dmi_table[] __initconst = { +static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = { + /* + * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C + * mode. + * https://bugzilla.kernel.org/show_bug.cgi?id=198515 + */ + { + .callback = set_gbl_term_list, + .ident = "Dell Precision M5530", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"), + }, + }, + { + .callback = set_gbl_term_list, + .ident = "Dell XPS 15 9570", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"), + }, + }, /* * Invoke DSDT corruption work-around on all Toshiba Satellite. + * DSDT will be copied to memory. * https://bugzilla.kernel.org/show_bug.cgi?id=14679 */ { @@ -83,7 +110,7 @@ static const struct dmi_system_id dsdt_d {} }; #else -static const struct dmi_system_id dsdt_dmi_table[] __initconst = { +static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = { {} }; #endif @@ -1001,11 +1028,8 @@ void __init acpi_early_init(void)

acpi_permanent_mmap = true;

- /* - * If the machine falls into the DMI check table, - * DSDT will be copied to memory - */ - dmi_check_system(dsdt_dmi_table); + /* Check machine-specific quirks */ + dmi_check_system(acpi_quirks_dmi_table);

status = acpi_reallocate_root_table(); if (ACPI_FAILURE(status)) {

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Adam Ford aford173@gmail.com

commit 74402055a2d3ec998a1ded599e86185a27d9bbf4 upstream.

The pinmuxing was missing for I2C1 which was causing intermittent issues with the PMIC which is connected to I2C1. The bootloader did not quite configure the I2C1 either, so when running at 2.6MHz, it was generating errors at time.

This correctly sets the I2C1 pinmuxing so it can operate at 2.6MHz

Fixes: 687c27676151 ("ARM: dts: Add minimal support for LogicPD Torpedo DM3730 devkit")

Signed-off-by: Adam Ford aford173@gmail.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/logicpd-torpedo-som.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -104,6 +104,8 @@ };

&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>;

twl: twl@48 { @@ -211,6 +213,12 @@ OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0) /* hsusb0_data7.hsusb0_data7 */ >; }; + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; };

&uart2 {

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown neilb@suse.com

commit 39772f0a7be3b3dc26c74ea13fe7847fd1522c8b upstream.

The locking protocols in md assume that a device will never be removed from an array during resync/recovery/reshape. When that isn't happening, rcu or reconfig_mutex is needed to protect an rdev pointer while taking a refcount. When it is happening, that protection isn't needed.

Unfortunately there are cases were remove_and_add_spares() is called when recovery might be happening: is state_store(), slot_store() and hot_remove_disk(). In each case, this is just an optimization, to try to expedite removal from the personality so the device can be removed from the array. If resync etc is happening, we just have to wait for md_check_recover to find a suitable time to call remove_and_add_spares().

This optimization and not essential so it doesn't matter if it fails. So change remove_and_add_spares() to abort early if resync/recovery/reshape is happening, unless it is called from md_check_recovery() as part of a newly started recovery. The parameter "this" is only NULL when called from md_check_recovery() so when it is NULL, there is no need to abort.

As this can result in a NULL dereference, the fix is suitable for -stable.

cc: yuyufen yuyufen@huawei.com Cc: Tomasz Majchrzak tomasz.majchrzak@intel.com Fixes: 8430e7e0af9a ("md: disconnect device from personality before trying to remove it.") Cc: stable@ver.kernel.org (v4.8+) Signed-off-by: NeilBrown neilb@suse.com Signed-off-by: Shaohua Li sh.li@alibaba-inc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/md.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8554,6 +8554,10 @@ static int remove_and_add_spares(struct int removed = 0; bool remove_some = false;

+ if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + /* Mustn't remove devices when resync thread is running */ + return 0; + rdev_for_each(rdev, mddev) { if ((this == NULL || rdev == this) && rdev->raid_disk >= 0 &&