From: Marko Kohtala marko.kohtala@okoko.fi

[ Upstream commit dd9782834dd9dde3624ff1acea8859f3d3e792d4 ]

The page_offset was only applied to the end of the page range. This caused the display updates to cause a scrolling effect on the display because the amount of data written to the display did not match the range display expected.

Fixes: 301bc0675b67 ("video: ssd1307fb: Make use of horizontal addressing mode") Signed-off-by: Marko Kohtala marko.kohtala@okoko.fi Cc: Mark Rutland mark.rutland@arm.com Cc: Rob Herring robh+dt@kernel.org Cc: Daniel Vetter daniel@ffwll.ch Cc: David Airlie airlied@linux.ie Cc: Michal Vokáč michal.vokac@ysoft.com Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Link: https://patchwork.freedesktop.org/patch/msgid/20190618074111.9309-4-marko.ko... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/ssd1307fb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index fa3480815cdb6..88e0763edcc72 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -421,7 +421,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par) if (ret < 0) return ret;

- ret = ssd1307fb_write_cmd(par->client, 0x0); + ret = ssd1307fb_write_cmd(par->client, par->page_offset); if (ret < 0) return ret;

From: Corey Minyard cminyard@mvista.com

[ Upstream commit 340ff31ab00bca5c15915e70ad9ada3030c98cf8 ]

ipmi_thread() uses back-to-back schedule() to poll for command completion which, on some machines, can push up CPU consumption and heavily tax the scheduler locks leading to noticeable overall performance degradation.

This was originally added so firmware updates through IPMI would complete in a timely manner. But we can't kill the scheduler locks for that one use case.

Instead, only run schedule() continuously in maintenance mode, where firmware updates should run.

Signed-off-by: Corey Minyard cminyard@mvista.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/char/ipmi/ipmi_si_intf.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 2f9abe0d04dcb..2f8ff63bbbe43 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -281,6 +281,9 @@ struct smi_info { */ bool irq_enable_broken;

+ /* Is the driver in maintenance mode? */ + bool in_maintenance_mode; + /* * Did we get an attention that we did not handle? */ @@ -1091,11 +1094,20 @@ static int ipmi_thread(void *data) spin_unlock_irqrestore(&(smi_info->si_lock), flags); busy_wait = ipmi_thread_busy_wait(smi_result, smi_info, &busy_until); - if (smi_result == SI_SM_CALL_WITHOUT_DELAY) + if (smi_result == SI_SM_CALL_WITHOUT_DELAY) { ; /* do nothing */ - else if (smi_result == SI_SM_CALL_WITH_DELAY && busy_wait) - schedule(); - else if (smi_result == SI_SM_IDLE) { + } else if (smi_result == SI_SM_CALL_WITH_DELAY && busy_wait) { + /* + * In maintenance mode we run as fast as + * possible to allow firmware updates to + * complete as fast as possible, but normally + * don't bang on the scheduler. + */ + if (smi_info->in_maintenance_mode) + schedule(); + else + usleep_range(100, 200); + } else if (smi_result == SI_SM_IDLE) { if (atomic_read(&smi_info->need_watch)) { schedule_timeout_interruptible(100); } else { @@ -1103,8 +1115,9 @@ static int ipmi_thread(void *data) __set_current_state(TASK_INTERRUPTIBLE); schedule(); } - } else + } else { schedule_timeout_interruptible(1); + } } return 0; } @@ -1283,6 +1296,7 @@ static void set_maintenance_mode(void *send_info, bool enable)

if (!enable) atomic_set(&smi_info->req_events, 0); + smi_info->in_maintenance_mode = enable; }

static const struct ipmi_smi_handlers handlers = {

From: Stephen Boyd sboyd@kernel.org

[ Upstream commit af55dadfbce35b4f4c6247244ce3e44b2e242b84 ]

A future patch is going to change semantics of clk_register() so that clk_hw::init is guaranteed to be NULL after a clk is registered. Avoid referencing this member here so that we don't run into NULL pointer exceptions.

Cc: Guo Zeng Guo.Zeng@csr.com Cc: Barry Song Baohua.Song@csr.com Signed-off-by: Stephen Boyd sboyd@kernel.org Link: https://lkml.kernel.org/r/20190731193517.237136-6-sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/sirf/clk-common.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/sirf/clk-common.c b/drivers/clk/sirf/clk-common.c index 77e1e2491689b..edb7197cc4b4d 100644 --- a/drivers/clk/sirf/clk-common.c +++ b/drivers/clk/sirf/clk-common.c @@ -298,9 +298,10 @@ static u8 dmn_clk_get_parent(struct clk_hw *hw) { struct clk_dmn *clk = to_dmnclk(hw); u32 cfg = clkc_readl(clk->regofs); + const char *name = clk_hw_get_name(hw);

/* parent of io domain can only be pll3 */ - if (strcmp(hw->init->name, "io") == 0) + if (strcmp(name, "io") == 0) return 4;

WARN_ON((cfg & (BIT(3) - 1)) > 4); @@ -312,9 +313,10 @@ static int dmn_clk_set_parent(struct clk_hw *hw, u8 parent) { struct clk_dmn *clk = to_dmnclk(hw); u32 cfg = clkc_readl(clk->regofs); + const char *name = clk_hw_get_name(hw);

/* parent of io domain can only be pll3 */ - if (strcmp(hw->init->name, "io") == 0) + if (strcmp(name, "io") == 0) return -EINVAL;

cfg &= ~(BIT(3) - 1); @@ -354,7 +356,8 @@ static long dmn_clk_round_rate(struct clk_hw *hw, unsigned long rate, { unsigned long fin; unsigned ratio, wait, hold; - unsigned bits = (strcmp(hw->init->name, "mem") == 0) ? 3 : 4; + const char *name = clk_hw_get_name(hw); + unsigned bits = (strcmp(name, "mem") == 0) ? 3 : 4;

fin = *parent_rate; ratio = fin / rate; @@ -376,7 +379,8 @@ static int dmn_clk_set_rate(struct clk_hw *hw, unsigned long rate, struct clk_dmn *clk = to_dmnclk(hw); unsigned long fin; unsigned ratio, wait, hold, reg; - unsigned bits = (strcmp(hw->init->name, "mem") == 0) ? 3 : 4; + const char *name = clk_hw_get_name(hw); + unsigned bits = (strcmp(name, "mem") == 0) ? 3 : 4;

fin = parent_rate; ratio = fin / rate;

From: Christophe Leroy christophe.leroy@c-s.fr

[ Upstream commit 38a0d0cdb46d3f91534e5b9839ec2d67be14c59d ]

We see warnings such as: kernel/futex.c: In function 'do_futex': kernel/futex.c:1676:17: warning: 'oldval' may be used uninitialized in this function [-Wmaybe-uninitialized] return oldval == cmparg; ^ kernel/futex.c:1651:6: note: 'oldval' was declared here int oldval, ret; ^

This is because arch_futex_atomic_op_inuser() only sets *oval if ret is 0 and GCC doesn't see that it will only use it when ret is 0.

Anyway, the non-zero ret path is an error path that won't suffer from setting *oval, and as *oval is a local var in futex_atomic_op_inuser() it will have no impact.

Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr [mpe: reword change log slightly] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/86b72f0c134367b214910b27b9a6dd3321af93bb.156577465... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/include/asm/futex.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index f4c7467f74655..b73ab8a7ebc3f 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -60,8 +60,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,

pagefault_enable();

- if (!ret) - *oval = oldval; + *oval = oldval;

return ret; }

From: Sowjanya Komatineni skomatineni@nvidia.com

[ Upstream commit c2cf351eba2ff6002ce8eb178452219d2521e38e ]

pmx_writel uses writel which inserts write barrier before the register write.

This patch has fix to replace writel with writel_relaxed followed by a readback and memory barrier to ensure write operation is completed for successful pinctrl change.

Acked-by: Thierry Reding treding@nvidia.com Reviewed-by: Dmitry Osipenko digetx@gmail.com Signed-off-by: Sowjanya Komatineni skomatineni@nvidia.com Link: https://lore.kernel.org/r/1565984527-5272-2-git-send-email-skomatineni@nvidi... Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/pinctrl-tegra.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-tegra.c b/drivers/pinctrl/pinctrl-tegra.c index 0fd7fd2b0f72c..a30e967d75c2a 100644 --- a/drivers/pinctrl/pinctrl-tegra.c +++ b/drivers/pinctrl/pinctrl-tegra.c @@ -52,7 +52,9 @@ static inline u32 pmx_readl(struct tegra_pmx *pmx, u32 bank, u32 reg)

static inline void pmx_writel(struct tegra_pmx *pmx, u32 val, u32 bank, u32 reg) { - writel(val, pmx->regs[bank] + reg); + writel_relaxed(val, pmx->regs[bank] + reg); + /* make sure pinmux register write completed */ + pmx_readl(pmx, bank, reg); }

static int tegra_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)

From: hexin hexin.op@gmail.com

[ Upstream commit 92c8026854c25093946e0d7fe536fd9eac440f06 ]

vfio_pci_enable() saves the device's initial configuration information with the intent that it is restored in vfio_pci_disable(). However, the commit referenced in Fixes: below replaced the call to __pci_reset_function_locked(), which is not wrapped in a state save and restore, with pci_try_reset_function(), which overwrites the restored device state with the current state before applying it to the device. Reinstate use of __pci_reset_function_locked() to return to the desired behavior.

Fixes: 890ed578df82 ("vfio-pci: Use pci "try" reset interface") Signed-off-by: hexin hexin15@baidu.com Signed-off-by: Liu Qi liuqi16@baidu.com Signed-off-by: Zhang Yu zhangyu31@baidu.com Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vfio/pci/vfio_pci.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 47b229fa5e8ec..4b62eb3b59233 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -221,11 +221,20 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);

/* - * Try to reset the device. The success of this is dependent on - * being able to lock the device, which is not always possible. + * Try to get the locks ourselves to prevent a deadlock. The + * success of this is dependent on being able to lock the device, + * which is not always possible. + * We can not use the "try" reset interface here, which will + * overwrite the previously restored configuration information. */ - if (vdev->reset_works && !pci_try_reset_function(pdev)) - vdev->needs_reset = false; + if (vdev->reset_works && pci_cfg_access_trylock(pdev)) { + if (device_trylock(&pdev->dev)) { + if (!__pci_reset_function_locked(pdev)) + vdev->needs_reset = false; + device_unlock(&pdev->dev); + } + pci_cfg_access_unlock(pdev); + }

pci_restore_state(pdev); out:

From: Nathan Lynch nathanl@linux.ibm.com

[ Upstream commit 92c94dfb69e350471473fd3075c74bc68150879e ]

prep_irq_for_idle() is intended to be called before entering H_CEDE (and it is used by the pseries cpuidle driver). However the default pseries idle routine does not call it, leading to mismanaged lazy irq state when the cpuidle driver isn't in use. Manifestations of this include:

* Dropped IPIs in the time immediately after a cpu comes online (before it has installed the cpuidle handler), making the online operation block indefinitely waiting for the new cpu to respond.

* Hitting this WARN_ON in arch_local_irq_restore(): /* * We should already be hard disabled here. We had bugs * where that wasn't the case so let's dbl check it and * warn if we are wrong. Only do that when IRQ tracing * is enabled as mfmsr() can be costly. */ if (WARN_ON_ONCE(mfmsr() & MSR_EE)) __hard_irq_disable();

Call prep_irq_for_idle() from pseries_lpar_idle() and honor its result.

Fixes: 363edbe2614a ("powerpc: Default arch idle could cede processor on pseries") Signed-off-by: Nathan Lynch nathanl@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20190910225244.25056-1-nathanl@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/platforms/pseries/setup.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 9cc976ff7fecc..88fcf6a95fa67 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -369,6 +369,9 @@ static void pseries_lpar_idle(void) * low power mode by cedeing processor to hypervisor */

+ if (!prep_irq_for_idle()) + return; + /* Indicate to hypervisor that we are idle. */ get_lppaca()->idle = 1;

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

[ Upstream commit 76380a607ba0b28627c9b4b55cd47a079a59624b ]

Goodix touchpad may drop its first couple input events when i2c-designware-platdrv and intel-lpss it connects to took too long to runtime resume from runtime suspended state.

This issue happens becuase the touchpad has a rather small buffer to store up to 13 input events, so if the host doesn't read those events in time (i.e. runtime resume takes too long), events are dropped from the touchpad's buffer.

The bottleneck is D3cold delay it waits when transitioning from D3cold to D0, hence remove the delay to make the resume faster. I've tested some systems with intel-lpss and haven't seen any regression.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202683 Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mfd/intel-lpss-pci.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c index 5bfdfccbb9a1a..032c95157497f 100644 --- a/drivers/mfd/intel-lpss-pci.c +++ b/drivers/mfd/intel-lpss-pci.c @@ -38,6 +38,8 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev, info->mem = &pdev->resource[0]; info->irq = pdev->irq;

+ pdev->d3cold_delay = 0; + /* Probably it is enough to set this for iDMA capable devices only */ pci_set_master(pdev);

From: Joao Moreno mail@joaomoreno.com

[ Upstream commit aec256d0ecd561036f188dbc8fa7924c47a9edfd ]

This fixes an issue in which key down events for function keys would be repeatedly emitted even after the user has raised the physical key. For example, the driver fails to emit the F5 key up event when going through the following steps: - fnmode=1: hold FN, hold F5, release FN, release F5 - fnmode=2: hold F5, hold FN, release F5, release FN

The repeated F5 key down events can be easily verified using xev.

Signed-off-by: Joao Moreno mail@joaomoreno.com Co-developed-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-apple.c | 49 +++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 21 deletions(-)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 884d82f9190e2..8af87dc05f2a5 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -55,7 +55,6 @@ MODULE_PARM_DESC(swap_opt_cmd, "Swap the Option ("Alt") and Command ("Flag") struct apple_sc { unsigned long quirks; unsigned int fn_on; - DECLARE_BITMAP(pressed_fn, KEY_CNT); DECLARE_BITMAP(pressed_numlock, KEY_CNT); };

@@ -182,6 +181,8 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, { struct apple_sc *asc = hid_get_drvdata(hid); const struct apple_key_translation *trans, *table; + bool do_translate; + u16 code = 0;

if (usage->code == KEY_FN) { asc->fn_on = !!value; @@ -190,8 +191,6 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, }

if (fnmode) { - int do_translate; - if (hid->product >= USB_DEVICE_ID_APPLE_WELLSPRING4_ANSI && hid->product <= USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS) table = macbookair_fn_keys; @@ -203,25 +202,33 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, trans = apple_find_translation (table, usage->code);

if (trans) { - if (test_bit(usage->code, asc->pressed_fn)) - do_translate = 1; - else if (trans->flags & APPLE_FLAG_FKEY) - do_translate = (fnmode == 2 && asc->fn_on) || - (fnmode == 1 && !asc->fn_on); - else - do_translate = asc->fn_on; - - if (do_translate) { - if (value) - set_bit(usage->code, asc->pressed_fn); - else - clear_bit(usage->code, asc->pressed_fn); - - input_event(input, usage->type, trans->to, - value); - - return 1; + if (test_bit(trans->from, input->key)) + code = trans->from; + else if (test_bit(trans->to, input->key)) + code = trans->to; + + if (!code) { + if (trans->flags & APPLE_FLAG_FKEY) { + switch (fnmode) { + case 1: + do_translate = !asc->fn_on; + break; + case 2: + do_translate = asc->fn_on; + break; + default: + /* should never happen */ + do_translate = false; + } + } else { + do_translate = asc->fn_on; + } + + code = do_translate ? trans->to : trans->from; } + + input_event(input, usage->type, code, value); + return 1; }

if (asc->quirks & APPLE_NUMLOCK_EMULATION &&

From: OGAWA Hirofumi hirofumi@mail.parknet.co.jp

[ Upstream commit 07bfa4415ab607e459b69bd86aa7e7602ce10b4f ]

If userspace reads the buffer via blockdev while mounting, sb_getblk()+modify can race with buffer read via blockdev.

For example,

FS userspace bh = sb_getblk() modify bh->b_data read ll_rw_block(bh) fill bh->b_data by on-disk data /* lost modified data by FS */ set_buffer_uptodate(bh) set_buffer_uptodate(bh)

Userspace should not use the blockdev while mounting though, the udev seems to be already doing this. Although I think the udev should try to avoid this, workaround the race by small overhead.

Link: http://lkml.kernel.org/r/87pnk7l3sw.fsf_-_@mail.parknet.co.jp Signed-off-by: OGAWA Hirofumi hirofumi@mail.parknet.co.jp Reported-by: Jan Stancek jstancek@redhat.com Tested-by: Jan Stancek jstancek@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fat/dir.c | 13 +++++++++++-- fs/fat/fatent.c | 3 +++ 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 8b2127ffb226c..9b77e2ad2b597 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1097,8 +1097,11 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, err = -ENOMEM; goto error; } + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[n]); memset(bhs[n]->b_data, 0, sb->s_blocksize); set_buffer_uptodate(bhs[n]); + unlock_buffer(bhs[n]); mark_buffer_dirty_inode(bhs[n], dir);

n++; @@ -1155,6 +1158,8 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) fat_time_unix2fat(sbi, ts, &time, &date, &time_cs);

de = (struct msdos_dir_entry *)bhs[0]->b_data; + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[0]); /* filling the new directory slots ("." and ".." entries) */ memcpy(de[0].name, MSDOS_DOT, MSDOS_NAME); memcpy(de[1].name, MSDOS_DOTDOT, MSDOS_NAME); @@ -1177,6 +1182,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) de[0].size = de[1].size = 0; memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de)); set_buffer_uptodate(bhs[0]); + unlock_buffer(bhs[0]); mark_buffer_dirty_inode(bhs[0], dir);

err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE); @@ -1234,11 +1240,14 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots,

/* fill the directory entry */ copy = min(size, sb->s_blocksize); + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[n]); memcpy(bhs[n]->b_data, slots, copy); - slots += copy; - size -= copy; set_buffer_uptodate(bhs[n]); + unlock_buffer(bhs[n]); mark_buffer_dirty_inode(bhs[n], dir); + slots += copy; + size -= copy; if (!size) break; n++; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index e3fc477728b32..be8529739d23e 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -389,8 +389,11 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs, err = -ENOMEM; goto error; } + /* Avoid race with userspace read via bdev */ + lock_buffer(c_bh); memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize); set_buffer_uptodate(c_bh); + unlock_buffer(c_bh); mark_buffer_dirty_inode(c_bh, sbi->fat_inode); if (sb->s_flags & MS_SYNCHRONOUS) err = sync_dirty_buffer(c_bh);

From: Changwei Ge gechangwei@live.cn

[ Upstream commit 0a3775e4f883912944481cf2ef36eb6383a9cc74 ]

There is a scenario causing ocfs2 umount hang when multiple hosts are rebooting at the same time.

NODE1 NODE2 NODE3 send unlock requset to NODE2 dies become recovery master recover NODE2 find NODE2 dead mark resource RECOVERING directly remove lock from grant list calculate usage but RECOVERING marked **miss the window of purging clear RECOVERING

To reproduce this issue, crash a host and then umount ocfs2 from another node.

To solve this, just let unlock progress wait for recovery done.

Link: http://lkml.kernel.org/r/1550124866-20367-1-git-send-email-gechangwei@live.c... Signed-off-by: Changwei Ge gechangwei@live.cn Reviewed-by: Joseph Qi joseph.qi@linux.alibaba.com Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Changwei Ge gechangwei@live.cn Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/dlm/dlmunlock.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 2e3c9dbab68c9..d137d4692b918 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -105,7 +105,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, enum dlm_status status; int actions = 0; int in_use; - u8 owner; + u8 owner; + int recovery_wait = 0;

mlog(0, "master_node = %d, valblk = %d\n", master_node, flags & LKM_VALBLK); @@ -208,9 +209,12 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, } if (flags & LKM_CANCEL) lock->cancel_pending = 0; - else - lock->unlock_pending = 0; - + else { + if (!lock->unlock_pending) + recovery_wait = 1; + else + lock->unlock_pending = 0; + } }

/* get an extra ref on lock. if we are just switching @@ -244,6 +248,17 @@ leave: spin_unlock(&res->spinlock); wake_up(&res->wq);

+ if (recovery_wait) { + spin_lock(&res->spinlock); + /* Unlock request will directly succeed after owner dies, + * and the lock is already removed from grant list. We have to + * wait for RECOVERING done or we miss the chance to purge it + * since the removement is much faster than RECOVERING proc. + */ + __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_RECOVERING); + spin_unlock(&res->spinlock); + } + /* let the caller's final dlm_lock_put handle the actual kfree */ if (actions & DLM_UNLOCK_FREE_LOCK) { /* this should always be coupled with list removal */

From: Martijn Coenen maco@android.com

commit f5cb779ba16334b45ba8946d6bfa6d9834d1527f upstream.

binder_poll() passes the thread->wait waitqueue that can be slept on for work. When a thread that uses epoll explicitly exits using BINDER_THREAD_EXIT, the waitqueue is freed, but it is never removed from the corresponding epoll data structure. When the process subsequently exits, the epoll cleanup code tries to access the waitlist, which results in a use-after-free.

Prevent this by using POLLFREE when the thread exits.

Signed-off-by: Martijn Coenen maco@android.com Reported-by: syzbot syzkaller@googlegroups.com Cc: stable stable@vger.kernel.org # 4.14 [backport BINDER_LOOPER_STATE_POLL logic as well] Signed-off-by: Mattias Nissler mnissler@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/android/binder.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)

--- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -334,7 +334,8 @@ enum { BINDER_LOOPER_STATE_EXITED = 0x04, BINDER_LOOPER_STATE_INVALID = 0x08, BINDER_LOOPER_STATE_WAITING = 0x10, - BINDER_LOOPER_STATE_NEED_RETURN = 0x20 + BINDER_LOOPER_STATE_NEED_RETURN = 0x20, + BINDER_LOOPER_STATE_POLL = 0x40, };

struct binder_thread { @@ -2610,6 +2611,18 @@ static int binder_free_thread(struct bin } else BUG(); } + + /* + * If this thread used poll, make sure we remove the waitqueue + * from any epoll data structures holding it with POLLFREE. + * waitqueue_active() is safe to use here because we're holding + * the inner lock. + */ + if ((thread->looper & BINDER_LOOPER_STATE_POLL) && + waitqueue_active(&thread->wait)) { + wake_up_poll(&thread->wait, POLLHUP | POLLFREE); + } + if (send_reply) binder_send_failed_reply(send_reply, BR_DEAD_REPLY); binder_release_work(&thread->todo); @@ -2633,6 +2646,8 @@ static unsigned int binder_poll(struct f return POLLERR; }

+ thread->looper |= BINDER_LOOPER_STATE_POLL; + wait_for_proc_work = thread->transaction_stack == NULL && list_empty(&thread->todo) && thread->return_error == BR_OK;

From: Johan Hovold johan@kernel.org

[ Upstream commit 8353da9fa69722b54cba82b2ec740afd3d438748 ]

Fix NULL-pointer dereference on tty open due to a failure to handle a missing interrupt-in endpoint when probing modem ports:

BUG: kernel NULL pointer dereference, address: 0000000000000006 ... RIP: 0010:tiocmget_submit_urb+0x1c/0xe0 [hso] ... Call Trace: hso_start_serial_device+0xdc/0x140 [hso] hso_serial_open+0x118/0x1b0 [hso] tty_open+0xf1/0x490

Fixes: 542f54823614 ("tty: Modem functions for the HSO driver") Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/usb/hso.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2650,14 +2650,18 @@ static struct hso_device *hso_create_bul */ if (serial->tiocmget) { tiocmget = serial->tiocmget; + tiocmget->endp = hso_get_ep(interface, + USB_ENDPOINT_XFER_INT, + USB_DIR_IN); + if (!tiocmget->endp) { + dev_err(&interface->dev, "Failed to find INT IN ep\n"); + goto exit; + } + tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); if (tiocmget->urb) { mutex_init(&tiocmget->mutex); init_waitqueue_head(&tiocmget->waitq); - tiocmget->endp = hso_get_ep( - interface, - USB_ENDPOINT_XFER_INT, - USB_DIR_IN); } else hso_free_tiomget(serial); }

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit b406472b5ad79ede8d10077f0c8f05505ace8b6d ]

Since commit c09551c6ff7f ("net: ipv4: use a dedicated counter for icmp_v4 redirect packets") we use 'n_redirects' to account for redirect packets, but we still use 'rate_tokens' to compute the redirect packets exponential backoff.

If the device sent to the relevant peer any ICMP error packet after sending a redirect, it will also update 'rate_token' according to the leaking bucket schema; typically 'rate_token' will raise above BITS_PER_LONG and the redirect packets backoff algorithm will produce undefined behavior.

Fix the issue using 'n_redirects' to compute the exponential backoff in ip_rt_send_redirect().

Note that we still clear rate_tokens after a redirect silence period, to avoid changing an established behaviour.

The root cause predates git history; before the mentioned commit in the critical scenario, the kernel stopped sending redirects, after the mentioned commit the behavior more randomic.

Reported-by: Xiumei Mu xmu@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: c09551c6ff7f ("net: ipv4: use a dedicated counter for icmp_v4 redirect packets") Signed-off-by: Paolo Abeni pabeni@redhat.com Acked-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/route.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -897,16 +897,15 @@ void ip_rt_send_redirect(struct sk_buff if (peer->rate_tokens == 0 || time_after(jiffies, (peer->rate_last + - (ip_rt_redirect_load << peer->rate_tokens)))) { + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);

icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; - ++peer->rate_tokens; ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number) + peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw);

From: Eric Dumazet edumazet@google.com

[ Upstream commit a0c2dc1fe63e2869b74c1c7f6a81d1745c8a695d ]

sysbot reported a memory leak after a bind() has failed.

While we are at it, abort the operation if kmemdup() has failed.

BUG: memory leak unreferenced object 0xffff888105d83ec0 (size 32): comm "syz-executor067", pid 7207, jiffies 4294956228 (age 19.430s) hex dump (first 32 bytes): 00 69 6c 65 20 72 65 61 64 00 6e 65 74 3a 5b 34 .ile read.net:[4 30 32 36 35 33 33 30 39 37 5d 00 00 00 00 00 00 026533097]...... backtrace: [<0000000036bac473>] kmemleak_alloc_recursive /./include/linux/kmemleak.h:43 [inline] [<0000000036bac473>] slab_post_alloc_hook /mm/slab.h:522 [inline] [<0000000036bac473>] slab_alloc /mm/slab.c:3319 [inline] [<0000000036bac473>] __do_kmalloc /mm/slab.c:3653 [inline] [<0000000036bac473>] __kmalloc_track_caller+0x169/0x2d0 /mm/slab.c:3670 [<000000000cd39d07>] kmemdup+0x27/0x60 /mm/util.c:120 [<000000008e57e5fc>] kmemdup /./include/linux/string.h:432 [inline] [<000000008e57e5fc>] llcp_sock_bind+0x1b3/0x230 /net/nfc/llcp_sock.c:107 [<000000009cb0b5d3>] __sys_bind+0x11c/0x140 /net/socket.c:1647 [<00000000492c3bbc>] __do_sys_bind /net/socket.c:1658 [inline] [<00000000492c3bbc>] __se_sys_bind /net/socket.c:1656 [inline] [<00000000492c3bbc>] __x64_sys_bind+0x1e/0x30 /net/socket.c:1656 [<0000000008704b2a>] do_syscall_64+0x76/0x1a0 /arch/x86/entry/common.c:296 [<000000009f4c57a4>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 30cc4587659e ("NFC: Move LLCP code to the NFC top level diirectory") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/nfc/llcp_sock.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -118,9 +118,14 @@ static int llcp_sock_bind(struct socket llcp_sock->service_name = kmemdup(llcp_addr.service_name, llcp_sock->service_name_len, GFP_KERNEL); - + if (!llcp_sock->service_name) { + ret = -ENOMEM; + goto put_dev; + } llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); if (llcp_sock->ssap == LLCP_SAP_MAX) { + kfree(llcp_sock->service_name); + llcp_sock->service_name = NULL; ret = -EADDRINUSE; goto put_dev; }

From: Dongli Zhang dongli.zhang@oracle.com

[ Upstream commit a761129e3625688310aecf26e1be9e98e85f8eb5 ]

xennet_fill_frags() uses ~0U as return value when the sk_buff is not able to cache extra fragments. This is incorrect because the return type of xennet_fill_frags() is RING_IDX and 0xffffffff is an expected value for ring buffer index.

In the situation when the rsp_cons is approaching 0xffffffff, the return value of xennet_fill_frags() may become 0xffffffff which xennet_poll() (the caller) would regard as error. As a result, queue->rx.rsp_cons is set incorrectly because it is updated only when there is error. If there is no error, xennet_poll() would be responsible to update queue->rx.rsp_cons. Finally, queue->rx.rsp_cons would point to the rx ring buffer entries whose queue->rx_skbs[i] and queue->grant_rx_ref[i] are already cleared to NULL. This leads to NULL pointer access in the next iteration to process rx ring buffer entries.

The symptom is similar to the one fixed in commit 00b368502d18 ("xen-netfront: do not assume sk_buff_head list is empty in error handling").

This patch changes the return type of xennet_fill_frags() to indicate whether it is successful or failed. The queue->rx.rsp_cons will be always updated inside this function.

Fixes: ad4f15dc2c70 ("xen/netfront: don't bug in case of too many frags") Signed-off-by: Dongli Zhang dongli.zhang@oracle.com Reviewed-by: Juergen Gross jgross@suse.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/xen-netfront.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-)

--- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -874,9 +874,9 @@ static int xennet_set_skb_gso(struct sk_ return 0; }

-static RING_IDX xennet_fill_frags(struct netfront_queue *queue, - struct sk_buff *skb, - struct sk_buff_head *list) +static int xennet_fill_frags(struct netfront_queue *queue, + struct sk_buff *skb, + struct sk_buff_head *list) { RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb; @@ -895,7 +895,7 @@ static RING_IDX xennet_fill_frags(struct if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { queue->rx.rsp_cons = ++cons + skb_queue_len(list); kfree_skb(nskb); - return ~0U; + return -ENOENT; }

skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, @@ -906,7 +906,9 @@ static RING_IDX xennet_fill_frags(struct kfree_skb(nskb); }

- return cons; + queue->rx.rsp_cons = cons; + + return 0; }

static int checksum_setup(struct net_device *dev, struct sk_buff *skb) @@ -1032,8 +1034,7 @@ err: skb->data_len = rx->status; skb->len += rx->status;

- i = xennet_fill_frags(queue, skb, &tmpq); - if (unlikely(i == ~0U)) + if (unlikely(xennet_fill_frags(queue, skb, &tmpq))) goto err;

if (rx->flags & XEN_NETRXF_csum_blank) @@ -1043,7 +1044,7 @@ err:

__skb_queue_tail(&rxq, skb);

- queue->rx.rsp_cons = ++i; + i = ++queue->rx.rsp_cons; work_done++; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit e9789c7cc182484fc031fd88097eb14cb26c4596 ]

syzbot reported a crash in cbq_normalize_quanta() caused by an out of range cl->priority.

iproute2 enforces this check, but malicious users do not.

kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI Modules linked in: CPU: 1 PID: 26447 Comm: syz-executor.1 Not tainted 5.3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:cbq_normalize_quanta.part.0+0x1fd/0x430 net/sched/sch_cbq.c:902 RSP: 0018:ffff8801a5c333b0 EFLAGS: 00010206 RAX: 0000000020000003 RBX: 00000000fffffff8 RCX: ffffc9000712f000 RDX: 00000000000043bf RSI: ffffffff83be8962 RDI: 0000000100000018 RBP: ffff8801a5c33420 R08: 000000000000003a R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000002ef R13: ffff88018da95188 R14: dffffc0000000000 R15: 0000000000000015 FS: 00007f37d26b1700(0000) GS:ffff8801dad00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c7cec CR3: 00000001bcd0a006 CR4: 00000000001626f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [<ffffffff83be9d57>] cbq_normalize_quanta include/net/pkt_sched.h:27 [inline] [<ffffffff83be9d57>] cbq_addprio net/sched/sch_cbq.c:1097 [inline] [<ffffffff83be9d57>] cbq_set_wrr+0x2d7/0x450 net/sched/sch_cbq.c:1115 [<ffffffff83bee8a7>] cbq_change_class+0x987/0x225b net/sched/sch_cbq.c:1537 [<ffffffff83b96985>] tc_ctl_tclass+0x555/0xcd0 net/sched/sch_api.c:2329 [<ffffffff83a84655>] rtnetlink_rcv_msg+0x485/0xc10 net/core/rtnetlink.c:5248 [<ffffffff83cadf0a>] netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2510 [<ffffffff83a7db6d>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5266 [<ffffffff83cac2c6>] netlink_unicast_kernel net/netlink/af_netlink.c:1324 [inline] [<ffffffff83cac2c6>] netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1350 [<ffffffff83cacd4a>] netlink_sendmsg+0x89a/0xd50 net/netlink/af_netlink.c:1939 [<ffffffff8399d46e>] sock_sendmsg_nosec net/socket.c:673 [inline] [<ffffffff8399d46e>] sock_sendmsg+0x12e/0x170 net/socket.c:684 [<ffffffff8399f1fd>] ___sys_sendmsg+0x81d/0x960 net/socket.c:2359 [<ffffffff839a2d05>] __sys_sendmsg+0x105/0x1d0 net/socket.c:2397 [<ffffffff839a2df9>] SYSC_sendmsg net/socket.c:2406 [inline] [<ffffffff839a2df9>] SyS_sendmsg+0x29/0x30 net/socket.c:2404 [<ffffffff8101ccc8>] do_syscall_64+0x528/0x770 arch/x86/entry/common.c:305 [<ffffffff84400091>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_cbq.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-)

--- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1340,6 +1340,26 @@ static const struct nla_policy cbq_polic [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, };

+static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], struct nlattr *opt) +{ + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy); + if (err < 0) + return err; + + if (tb[TCA_CBQ_WRROPT]) { + const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); + + if (wrr->priority > TC_CBQ_MAXPRIO) + err = -EINVAL; + } + return err; +} + static int cbq_init(struct Qdisc *sch, struct nlattr *opt) { struct cbq_sched_data *q = qdisc_priv(sch); @@ -1347,7 +1367,7 @@ static int cbq_init(struct Qdisc *sch, s struct tc_ratespec *r; int err;

- err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy); + err = cbq_opt_parse(tb, opt); if (err < 0) return err;

@@ -1728,10 +1748,7 @@ cbq_change_class(struct Qdisc *sch, u32 struct cbq_class *parent; struct qdisc_rate_table *rtab = NULL;

- if (opt == NULL) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy); + err = cbq_opt_parse(tb, opt); if (err < 0) return err;

From: Eric Biggers ebiggers@google.com

commit e5bfad3d7acc5702f32aafeb388362994f4d7bd0 upstream.

inode_smack::smk_lock is taken during smack_d_instantiate(), which is called during a filesystem transaction when creating a file on ext4. Therefore to avoid a deadlock, all code that takes this lock must use GFP_NOFS, to prevent memory reclaim from waiting for the filesystem transaction to complete.

Reported-by: syzbot+0eefc1e06a77d327a056@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Casey Schaufler casey@schaufler-ca.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- security/smack/smack_access.c | 4 ++-- security/smack/smack_lsm.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-)

--- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -474,7 +474,7 @@ char *smk_parse_smack(const char *string if (i == 0 || i >= SMK_LONGLABEL) return ERR_PTR(-EINVAL);

- smack = kzalloc(i + 1, GFP_KERNEL); + smack = kzalloc(i + 1, GFP_NOFS); if (smack == NULL) return ERR_PTR(-ENOMEM);

@@ -545,7 +545,7 @@ struct smack_known *smk_import_entry(con if (skp != NULL) goto freeout;

- skp = kzalloc(sizeof(*skp), GFP_KERNEL); + skp = kzalloc(sizeof(*skp), GFP_NOFS); if (skp == NULL) { skp = ERR_PTR(-ENOMEM); goto freeout; --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -268,7 +268,7 @@ static struct smack_known *smk_fetch(con if (ip->i_op->getxattr == NULL) return ERR_PTR(-EOPNOTSUPP);

- buffer = kzalloc(SMK_LONGLABEL, GFP_KERNEL); + buffer = kzalloc(SMK_LONGLABEL, GFP_NOFS); if (buffer == NULL) return ERR_PTR(-ENOMEM);