From: Yifan Zhang yifan1.zhang@amd.com

commit ee5468b9f1d3bf48082eed351dace14598e8ca39 upstream.

This reverts commit 4cbbe34807938e6e494e535a68d5ff64edac3f20.

Reason for revert: side effect of enlarging CP_MEC_DOORBELL_RANGE may cause some APUs fail to enter gfxoff in certain user cases.

Signed-off-by: Yifan Zhang yifan1.zhang@amd.com Acked-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 1fdfb7783404..d2c020a91c0b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3623,12 +3623,8 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring) if (ring->use_doorbell) { WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, (adev->doorbell_index.kiq * 2) << 2); - /* If GC has entered CGPG, ringing doorbell > first page doesn't - * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround - * this issue. - */ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, - (adev->doorbell.size - 4)); + (adev->doorbell_index.userqueue_end * 2) << 2); }

WREG32_SOC15_RLC(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,

From: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com

commit 1815d9c86e3090477fbde066ff314a7e9721ee0f upstream.

While checking the master status of the DRM file in drm_is_current_master(), the device's master mutex should be held. Without the mutex, the pointer fpriv->master may be freed concurrently by another process calling drm_setmaster_ioctl(). This could lead to use-after-free errors when the pointer is subsequently dereferenced in drm_lease_owner().

The callers of drm_is_current_master() from drm_auth.c hold the device's master mutex, but external callers do not. Hence, we implement drm_is_current_master_locked() to be used within drm_auth.c, and modify drm_is_current_master() to grab the device's master mutex before checking the master status.

Reported-by: Daniel Vetter daniel.vetter@ffwll.ch Signed-off-by: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com Reviewed-by: Emil Velikov emil.l.velikov@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/20210620110327.4964-2-desmondc... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_auth.c | 51 ++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index 232abbba3686..86d4b72e95cb 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -61,6 +61,35 @@ * trusted clients. */

+static bool drm_is_current_master_locked(struct drm_file *fpriv) +{ + lockdep_assert_held_once(&fpriv->master->dev->master_mutex); + + return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master; +} + +/** + * drm_is_current_master - checks whether @priv is the current master + * @fpriv: DRM file private + * + * Checks whether @fpriv is current master on its device. This decides whether a + * client is allowed to run DRM_MASTER IOCTLs. + * + * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting + * - the current master is assumed to own the non-shareable display hardware. + */ +bool drm_is_current_master(struct drm_file *fpriv) +{ + bool ret; + + mutex_lock(&fpriv->master->dev->master_mutex); + ret = drm_is_current_master_locked(fpriv); + mutex_unlock(&fpriv->master->dev->master_mutex); + + return ret; +} +EXPORT_SYMBOL(drm_is_current_master); + int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_auth *auth = data; @@ -223,7 +252,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, if (ret) goto out_unlock;

- if (drm_is_current_master(file_priv)) + if (drm_is_current_master_locked(file_priv)) goto out_unlock;

if (dev->master) { @@ -272,7 +301,7 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data, if (ret) goto out_unlock;

- if (!drm_is_current_master(file_priv)) { + if (!drm_is_current_master_locked(file_priv)) { ret = -EINVAL; goto out_unlock; } @@ -321,7 +350,7 @@ void drm_master_release(struct drm_file *file_priv) if (file_priv->magic) idr_remove(&file_priv->master->magic_map, file_priv->magic);

- if (!drm_is_current_master(file_priv)) + if (!drm_is_current_master_locked(file_priv)) goto out;

drm_legacy_lock_master_cleanup(dev, master); @@ -342,22 +371,6 @@ out: mutex_unlock(&dev->master_mutex); }

-/** - * drm_is_current_master - checks whether @priv is the current master - * @fpriv: DRM file private - * - * Checks whether @fpriv is current master on its device. This decides whether a - * client is allowed to run DRM_MASTER IOCTLs. - * - * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting - * - the current master is assumed to own the non-shareable display hardware. - */ -bool drm_is_current_master(struct drm_file *fpriv) -{ - return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master; -} -EXPORT_SYMBOL(drm_is_current_master); - /** * drm_master_get - reference a master pointer * @master: &struct drm_master

From: Christian König christian.koenig@amd.com

commit 4b41726aae563273bb4b4a9462ba51ce4d372f78 upstream.

We actually need to wait for the moving fence after pinning the BO to make sure that the pin is completed.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch References: https://lore.kernel.org/dri-devel/20210621151758.2347474-1-daniel.vetter@ffw... CC: stable@kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20210622114506.106349-2-christ... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/radeon/radeon_prime.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index 42a87948e28c..4a90807351e7 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -77,9 +77,19 @@ int radeon_gem_prime_pin(struct drm_gem_object *obj)

/* pin buffer into GTT */ ret = radeon_bo_pin(bo, RADEON_GEM_DOMAIN_GTT, NULL); - if (likely(ret == 0)) - bo->prime_shared_count++; - + if (unlikely(ret)) + goto error; + + if (bo->tbo.moving) { + ret = dma_fence_wait(bo->tbo.moving, false); + if (unlikely(ret)) { + radeon_bo_unpin(bo); + goto error; + } + } + + bo->prime_shared_count++; +error: radeon_bo_unreserve(bo); return ret; }

From: Arnd Bergmann arnd@arndb.de

commit dad7b9896a5dbac5da8275d5a6147c65c81fb5f2 upstream.

When building the kernel wtih gcc-10 or higher using the CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y flag, the compiler picks a slightly different set of registers for the inline assembly in cpu_init() that subsequently results in a corrupt kernel stack as well as remaining in FIQ mode. If a banked register is used for the last argument, the wrong version of that register gets loaded into CPSR_c. When building in Arm mode, the arguments are passed as immediate values and the bug cannot happen.

This got introduced when Daniel reworked the FIQ handling and was technically always broken, but happened to work with both clang and gcc before gcc-10 as long as they picked one of the lower registers. This is probably an indication that still very few people build the kernel in Thumb2 mode.

Marek pointed out the problem on IRC, Arnd narrowed it down to this inline assembly and Russell pinpointed the exact bug.

Change the constraints to force the final mode switch to use a non-banked register for the argument to ensure that the correct constant gets loaded. Another alternative would be to always use registers for the constant arguments to avoid the #ifdef that has now become more complex.

Cc: stable@vger.kernel.org # v3.18+ Cc: Daniel Thompson daniel.thompson@linaro.org Reported-by: Marek Vasut marek.vasut@gmail.com Acked-by: Ard Biesheuvel ardb@kernel.org Fixes: c0e7f7ee717e ("ARM: 8150/3: fiq: Replace default FIQ handler") Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/kernel/setup.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 1a5edf562e85..73ca7797b92f 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -545,9 +545,11 @@ void notrace cpu_init(void) * In Thumb-2, msr with an immediate value is not allowed. */ #ifdef CONFIG_THUMB2_KERNEL -#define PLC "r" +#define PLC_l "l" +#define PLC_r "r" #else -#define PLC "I" +#define PLC_l "I" +#define PLC_r "I" #endif

/* @@ -569,15 +571,15 @@ void notrace cpu_init(void) "msr cpsr_c, %9" : : "r" (stk), - PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), "I" (offsetof(struct stack, irq[0])), - PLC (PSR_F_BIT | PSR_I_BIT | ABT_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE), "I" (offsetof(struct stack, abt[0])), - PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE), "I" (offsetof(struct stack, und[0])), - PLC (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), "I" (offsetof(struct stack, fiq[0])), - PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE) + PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE) : "r14"); #endif }

From: Johannes Weiner hannes@cmpxchg.org

commit d583d360a620e6229422b3455d0be082b8255f5e upstream.

4117cebf1a9f ("psi: Optimize task switch inside shared cgroups") introduced a race condition that corrupts internal psi state. This manifests as kernel warnings, sometimes followed by bogusly high IO pressure:

psi: task underflow! cpu=1 t=2 tasks=[0 0 0 0] clear=c set=0 (schedule() decreasing RUNNING and ONCPU, both of which are 0)

psi: incosistent task state! task=2412744:systemd cpu=17 psi_flags=e clear=3 set=0 (cgroup_move_task() clearing MEMSTALL and IOWAIT, but task is MEMSTALL | RUNNING | ONCPU)

What the offending commit does is batch the two psi callbacks in schedule() to reduce the number of cgroup tree updates. When prev is deactivated and removed from the runqueue, nothing is done in psi at first; when the task switch completes, TSK_RUNNING and TSK_IOWAIT are updated along with TSK_ONCPU.

However, the deactivation and the task switch inside schedule() aren't atomic: pick_next_task() may drop the rq lock for load balancing. When this happens, cgroup_move_task() can run after the task has been physically dequeued, but the psi updates are still pending. Since it looks at the task's scheduler state, it doesn't move everything to the new cgroup that the task switch that follows is about to clear from it. cgroup_move_task() will leak the TSK_RUNNING count in the old cgroup, and psi_sched_switch() will underflow it in the new cgroup.

A similar thing can happen for iowait. TSK_IOWAIT is usually set when a p->in_iowait task is dequeued, but again this update is deferred to the switch. cgroup_move_task() can see an unqueued p->in_iowait task and move a non-existent TSK_IOWAIT. This results in the inconsistent task state warning, as well as a counter underflow that will result in permanent IO ghost pressure being reported.

Fix this bug by making cgroup_move_task() use task->psi_flags instead of looking at the potentially mismatching scheduler state.

[ We used the scheduler state historically in order to not rely on task->psi_flags for anything but debugging. But that ship has sailed anyway, and this is simpler and more robust.

We previously already batched TSK_ONCPU clearing with the TSK_RUNNING update inside the deactivation call from schedule(). But that ordering was safe and didn't result in TSK_ONCPU corruption: unlike most places in the scheduler, cgroup_move_task() only checked task_current() and handled TSK_ONCPU if the task was still queued. ]

Fixes: 4117cebf1a9f ("psi: Optimize task switch inside shared cgroups") Signed-off-by: Johannes Weiner hannes@cmpxchg.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20210503174917.38579-1-hannes@cmpxchg.org Cc: Oleksandr Natalenko oleksandr@natalenko.name Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/psi.c | 36 ++++++++++++++++++++++++++---------- 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 651218ded981..ef37acd28e4a 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -965,7 +965,7 @@ void psi_cgroup_free(struct cgroup *cgroup) */ void cgroup_move_task(struct task_struct *task, struct css_set *to) { - unsigned int task_flags = 0; + unsigned int task_flags; struct rq_flags rf; struct rq *rq;

@@ -980,15 +980,31 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)

rq = task_rq_lock(task, &rf);

- if (task_on_rq_queued(task)) { - task_flags = TSK_RUNNING; - if (task_current(rq, task)) - task_flags |= TSK_ONCPU; - } else if (task->in_iowait) - task_flags = TSK_IOWAIT; - - if (task->in_memstall) - task_flags |= TSK_MEMSTALL; + /* + * We may race with schedule() dropping the rq lock between + * deactivating prev and switching to next. Because the psi + * updates from the deactivation are deferred to the switch + * callback to save cgroup tree updates, the task's scheduling + * state here is not coherent with its psi state: + * + * schedule() cgroup_move_task() + * rq_lock() + * deactivate_task() + * p->on_rq = 0 + * psi_dequeue() // defers TSK_RUNNING & TSK_IOWAIT updates + * pick_next_task() + * rq_unlock() + * rq_lock() + * psi_task_change() // old cgroup + * task->cgroups = to + * psi_task_change() // new cgroup + * rq_unlock() + * rq_lock() + * psi_sched_switch() // does deferred updates in new cgroup + * + * Don't rely on the scheduling state. Use psi_flags instead. + */ + task_flags = task->psi_flags;

if (task_flags) psi_task_change(task, task_flags, 0);

From: "Rafael J. Wysocki" rafael.j.wysocki@intel.com

[ Upstream commit 4d6035f9bf4ea12776322746a216e856dfe46698 ]

Revert commit 4514d991d992 ("PCI: PM: Do not read power state in pci_enable_device_flags()") that is reported to cause PCI device initialization issues on some systems.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213481 Link: https://lore.kernel.org/linux-acpi/YNDoGICcg0V8HhpQ@eldamar.lan Reported-by: Michael phyre@rogers.com Reported-by: Salvatore Bonaccorso carnil@debian.org Fixes: 4514d991d992 ("PCI: PM: Do not read power state in pci_enable_device_flags()") Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/pci.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e4d4e399004b..16a17215f633 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1870,11 +1870,21 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) int err; int i, bars = 0;

- if (atomic_inc_return(&dev->enable_cnt) > 1) { - pci_update_current_state(dev, dev->current_state); - return 0; /* already enabled */ + /* + * Power state could be unknown at this point, either due to a fresh + * boot or a device removal call. So get the current power state + * so that things like MSI message writing will behave as expected + * (e.g. if the device really is in D0 at enable time). + */ + if (dev->pm_cap) { + u16 pmcsr; + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); + dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); }

+ if (atomic_inc_return(&dev->enable_cnt) > 1) + return 0; /* already enabled */ + bridge = pci_upstream_bridge(dev); if (bridge) pci_enable_bridge(bridge);

From: Maxime Ripard maxime@cerno.tech

[ Upstream commit 9984d6664ce9dcbbc713962539eaf7636ea246c2 ]

If the HPD GPIO is not available and drm_probe_ddc fails, we end up reading the HDMI_HOTPLUG register, but the controller might be powered off resulting in a CPU hang. Make sure we have the power domain and the HSM clock powered during the detect cycle to prevent the hang from happening.

Fixes: 4f6e3d66ac52 ("drm/vc4: Add runtime PM support to the HDMI encoder driver") Signed-off-by: Maxime Ripard maxime@cerno.tech Reviewed-by: Dave Stevenson dave.stevenson@raspberrypi.com Link: https://patchwork.freedesktop.org/patch/msgid/20210525091059.234116-4-maxime... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vc4/vc4_hdmi.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 84e218365045..8106b5634fe1 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -159,6 +159,8 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); bool connected = false;

+ WARN_ON(pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev)); + if (vc4_hdmi->hpd_gpio) { if (gpio_get_value_cansleep(vc4_hdmi->hpd_gpio) ^ vc4_hdmi->hpd_active_low) @@ -180,10 +182,12 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) } }

+ pm_runtime_put(&vc4_hdmi->pdev->dev); return connector_status_connected; }

cec_phys_addr_invalidate(vc4_hdmi->cec_adap); + pm_runtime_put(&vc4_hdmi->pdev->dev); return connector_status_disconnected; }

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 84e60065df9ef03759115a7e48c04bbc0d292165 ]

Fix:

vmlinux.o: warning: objtool: xen_pv_evtchn_do_upcall()+0x23: call to irq_enter_rcu() leaves .noinstr.text section

Fixes: 359f01d1816f ("x86/entry: Use run_sysvec_on_irqstack_cond() for XEN upcall") Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20210621120120.532960208@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/entry/common.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index cbe19c87e6be..8767dc53b569 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -266,15 +266,16 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs) irqentry_state_t state = irqentry_enter(regs); bool inhcall;

+ instrumentation_begin(); run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);

inhcall = get_and_clear_inhcall(); if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) { - instrumentation_begin(); irqentry_exit_cond_resched(); instrumentation_end(); restore_inhcall(inhcall); } else { + instrumentation_end(); irqentry_exit(regs, state); } }

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 49faa77759b211fff344898edc23bb780707fff5 ]

Better handle the failure paths.

vmlinux.o: warning: objtool: debug_locks_off()+0x23: call to console_verbose() leaves .noinstr.text section vmlinux.o: warning: objtool: debug_locks_off()+0x19: call to __kasan_check_write() leaves .noinstr.text section

debug_locks_off+0x19/0x40: instrument_atomic_write at include/linux/instrumented.h:86 (inlined by) __debug_locks_off at include/linux/debug_locks.h:17 (inlined by) debug_locks_off at lib/debug_locks.c:41

Fixes: 6eebad1ad303 ("lockdep: __always_inline more for noinstr") Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20210621120120.784404944@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/debug_locks.h | 2 ++ kernel/locking/lockdep.c | 4 +++- lib/debug_locks.c | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 2915f56ad421..edb5c186b0b7 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -27,8 +27,10 @@ extern int debug_locks_off(void); int __ret = 0; \ \ if (!oops_in_progress && unlikely(c)) { \ + instrumentation_begin(); \ if (debug_locks_off() && !debug_locks_silent) \ WARN(1, "DEBUG_LOCKS_WARN_ON(%s)", #c); \ + instrumentation_end(); \ __ret = 1; \ } \ __ret; \ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index f39c383c7180..5bf6b1659215 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -842,7 +842,7 @@ static int count_matching_names(struct lock_class *new_class) }

/* used from NMI context -- must be lockless */ -static __always_inline struct lock_class * +static noinstr struct lock_class * look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) { struct lockdep_subclass_key *key; @@ -850,12 +850,14 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) struct lock_class *class;

if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { + instrumentation_begin(); debug_locks_off(); printk(KERN_ERR "BUG: looking up invalid subclass: %u\n", subclass); printk(KERN_ERR "turning off the locking correctness validator.\n"); dump_stack(); + instrumentation_end(); return NULL; }

diff --git a/lib/debug_locks.c b/lib/debug_locks.c index 06d3135bd184..a75ee30b77cb 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(debug_locks_silent); /* * Generic 'turn off all lock debugging' function: */ -noinstr int debug_locks_off(void) +int debug_locks_off(void) { if (debug_locks && __debug_locks_off()) { if (!debug_locks_silent) {

From: Like Xu like.xu@linux.intel.com

[ Upstream commit 488e13a489e9707a7e81e1991fdd1f20c0f04689 ]

If the kernel is compiled with the CONFIG_LOCKDEP option, the conditional might_sleep_if() deep in kmem_cache_alloc() will generate the following trace, and potentially cause a deadlock when another LBR event is added:

[] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:196 [] Call Trace: [] kmem_cache_alloc+0x36/0x250 [] intel_pmu_lbr_add+0x152/0x170 [] x86_pmu_add+0x83/0xd0

Make it symmetric with the release_lbr_buffers() call and mirror the existing DS buffers.

Fixes: c085fb8774 ("perf/x86/intel/lbr: Support XSAVES for arch LBR read") Signed-off-by: Like Xu like.xu@linux.intel.com [peterz: simplified] Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: Kan Liang kan.liang@linux.intel.com Link: https://lkml.kernel.org/r/20210430052247.3079672-2-like.xu@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/events/core.c | 6 ++++-- arch/x86/events/intel/lbr.c | 26 ++++++++++++++++++++------ arch/x86/events/perf_event.h | 6 ++++++ 3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 18df17129695..10cadd73a8ac 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -380,10 +380,12 @@ int x86_reserve_hardware(void) if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); if (atomic_read(&pmc_refcount) == 0) { - if (!reserve_pmc_hardware()) + if (!reserve_pmc_hardware()) { err = -EBUSY; - else + } else { reserve_ds_buffers(); + reserve_lbr_buffers(); + } } if (!err) atomic_inc(&pmc_refcount); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 21890dacfcfe..22d0e40a1920 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -658,7 +658,6 @@ static inline bool branch_user_callstack(unsigned br_sel)

void intel_pmu_lbr_add(struct perf_event *event) { - struct kmem_cache *kmem_cache = event->pmu->task_ctx_cache; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

if (!x86_pmu.lbr_nr) @@ -696,11 +695,6 @@ void intel_pmu_lbr_add(struct perf_event *event) perf_sched_cb_inc(event->ctx->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) intel_pmu_lbr_reset(); - - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && - kmem_cache && !cpuc->lbr_xsave && - (cpuc->lbr_users != cpuc->lbr_pebs_users)) - cpuc->lbr_xsave = kmem_cache_alloc(kmem_cache, GFP_KERNEL); }

void release_lbr_buffers(void) @@ -721,6 +715,26 @@ void release_lbr_buffers(void) } }

+void reserve_lbr_buffers(void) +{ + struct kmem_cache *kmem_cache; + struct cpu_hw_events *cpuc; + int cpu; + + if (!static_cpu_has(X86_FEATURE_ARCH_LBR)) + return; + + for_each_possible_cpu(cpu) { + cpuc = per_cpu_ptr(&cpu_hw_events, cpu); + kmem_cache = x86_get_pmu(cpu)->task_ctx_cache; + if (!kmem_cache || cpuc->lbr_xsave) + continue; + + cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache, GFP_KERNEL, + cpu_to_node(cpu)); + } +} + void intel_pmu_lbr_del(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 53b2b5fc23bc..7888266c76cd 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1135,6 +1135,8 @@ void reserve_ds_buffers(void);

void release_lbr_buffers(void);

+void reserve_lbr_buffers(void); + extern struct event_constraint bts_constraint; extern struct event_constraint vlbr_constraint;

@@ -1282,6 +1284,10 @@ static inline void release_lbr_buffers(void) { }

+static inline void reserve_lbr_buffers(void) +{ +} + static inline int intel_pmu_init(void) { return 0;

From: Yu Kuai yukuai3@huawei.com

[ Upstream commit 8982d48af36d2562c0f904736b0fc80efc9f2532 ]

pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. Fix it by replacing it with pm_runtime_resume_and_get to keep usage counter balanced.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20210517081826.1564698-4-yukuai3@huawei.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/xilinx/zynqmp_dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index d8419565b92c..5fecf5aa6e85 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -468,7 +468,7 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan) struct zynqmp_dma_desc_sw *desc; int i, ret;

- ret = pm_runtime_get_sync(chan->dev); + ret = pm_runtime_resume_and_get(chan->dev); if (ret < 0) return ret;

From: Laurent Pinchart laurent.pinchart@ideasonboard.com

[ Upstream commit 32828b82fb875b06511918b139d3a3cd93d34262 ]

The driver depends on both OF and IOMEM support, express those dependencies in Kconfig. This fixes a build failure on S390 reported by the 0day bot.

Reported-by: kernel test robot lkp@intel.com Signed-off-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Tested-by: Jianqiang Chen jianqiang.chen@xilinx.com Reviewed-by: Jianqiang Chen jianqiang.chen@xilinx.com Link: https://lore.kernel.org/r/20210520152420.23986-2-laurent.pinchart@ideasonboa... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 03b1b0334947..c42b17b76640 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -690,6 +690,7 @@ config XILINX_ZYNQMP_DMA

config XILINX_ZYNQMP_DPDMA tristate "Xilinx DPDMA Engine" + depends on HAS_IOMEM && OF select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 0ee4d55534f82a0624701d0bb9fc2304d4529086 ]

Syzbot reports that it's possible to hit this from userspace, by trying to add a station before any other connection setup has been done. Instead of trying to catch this in some other way simply remove the warning, that will appropriately reject the call from userspace.

Reported-by: syzbot+7716dbc401d9a437890d@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20210517164715.f537da276d17.Id05f40ec8761d6a8cc2df... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/ieee80211_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 02e818d740f6..5ec437e8e713 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1442,7 +1442,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);

- if (WARN_ON_ONCE(!chanctx_conf)) { + if (!chanctx_conf) { rcu_read_unlock(); return NULL; }

From: Du Cheng ducheng2@gmail.com

[ Upstream commit a64b6a25dd9f984ed05fade603a00e2eae787d2f ]

If the userland switches back-and-forth between NL80211_IFTYPE_OCB and NL80211_IFTYPE_ADHOC via send_msg(NL80211_CMD_SET_INTERFACE), there is a chance where the cleanup cfg80211_leave_ocb() is not called. This leads to initialization of in-use memory (e.g. init u.ibss while in-use by u.ocb) due to a shared struct/union within ieee80211_sub_if_data:

struct ieee80211_sub_if_data { ... union { struct ieee80211_if_ap ap; struct ieee80211_if_vlan vlan; struct ieee80211_if_managed mgd; struct ieee80211_if_ibss ibss; // <- shares address struct ieee80211_if_mesh mesh; struct ieee80211_if_ocb ocb; // <- shares address struct ieee80211_if_mntr mntr; struct ieee80211_if_nan nan; } u; ... }

Therefore add handling of otype == NL80211_IFTYPE_OCB, during cfg80211_change_iface() to perform cleanup when leaving OCB mode.

link to syzkaller bug: https://syzkaller.appspot.com/bug?id=0612dbfa595bf4b9b680ff7b4948257b8e3732d...

Reported-by: syzbot+105896fac213f26056f9@syzkaller.appspotmail.com Signed-off-by: Du Cheng ducheng2@gmail.com Link: https://lore.kernel.org/r/20210428063941.105161-1-ducheng2@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/util.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/wireless/util.c b/net/wireless/util.c index f342b6147675..726e7d2342bd 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1059,6 +1059,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; }

From: Zou Wei zou_wei@huawei.com

[ Upstream commit dea8464ddf553803382efb753b6727dbf3931d06 ]

pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. Fix it by replacing it with pm_runtime_resume_and_get to keep usage counter balanced.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Zou Wei zou_wei@huawei.com Reviewed-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Link: https://lore.kernel.org/r/1622442963-54095-1-git-send-email-zou_wei@huawei.c... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/sh/rcar-dmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index d530c1bf11d9..6885b3dcd7a9 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1913,7 +1913,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)

/* Enable runtime PM and initialize the device. */ pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); return ret;

From: Guillaume Ranquet granquet@baylibre.com

[ Upstream commit 2537b40b0a4f61d2c83900744fe89b09076be9c6 ]

Avoid issuing a new desc if one is still being processed as this can lead to some desc never being marked as completed.

Signed-off-by: Guillaume Ranquet granquet@baylibre.com

Link: https://lore.kernel.org/r/20210513192642.29446-3-granquet@baylibre.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/mediatek/mtk-uart-apdma.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index e38b67fc0c0c..a09ab2dd3b46 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -204,14 +204,9 @@ static void mtk_uart_apdma_start_rx(struct mtk_chan *c)

static void mtk_uart_apdma_tx_handler(struct mtk_chan *c) { - struct mtk_uart_apdma_desc *d = c->desc; - mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B); mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B); mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B); - - list_del(&d->vd.node); - vchan_cookie_complete(&d->vd); }

static void mtk_uart_apdma_rx_handler(struct mtk_chan *c) @@ -242,9 +237,17 @@ static void mtk_uart_apdma_rx_handler(struct mtk_chan *c)

c->rx_status = d->avail_len - cnt; mtk_uart_apdma_write(c, VFF_RPT, wg); +}

- list_del(&d->vd.node); - vchan_cookie_complete(&d->vd); +static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c) +{ + struct mtk_uart_apdma_desc *d = c->desc; + + if (d) { + list_del(&d->vd.node); + vchan_cookie_complete(&d->vd); + c->desc = NULL; + } }

static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) @@ -258,6 +261,7 @@ static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) mtk_uart_apdma_rx_handler(c); else if (c->dir == DMA_MEM_TO_DEV) mtk_uart_apdma_tx_handler(c); + mtk_uart_apdma_chan_complete_handler(c); spin_unlock_irqrestore(&c->vc.lock, flags);

return IRQ_HANDLED; @@ -363,7 +367,7 @@ static void mtk_uart_apdma_issue_pending(struct dma_chan *chan) unsigned long flags;

spin_lock_irqsave(&c->vc.lock, flags); - if (vchan_issue_pending(&c->vc)) { + if (vchan_issue_pending(&c->vc) && !c->desc) { vd = vchan_next_desc(&c->vc); c->desc = to_mtk_uart_apdma_desc(&vd->tx);

From: Zheng Yongjun zhengyongjun3@huawei.com

[ Upstream commit 5ac6b198d7e312bd10ebe7d58c64690dc59cc49a ]

When 'nla_parse_nested_deprecated' failed, it's no need to BUG() here, return -EINVAL is ok.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/devinet.c | 2 +- net/ipv6/addrconf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2e35f68da40a..1c6429c353a9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1989,7 +1989,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT;

if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL;

if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a9e53f5942fa..eab0a46983c0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5822,7 +5822,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT;

if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL;

if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]),

From: Austin Kim austindh.kim@gmail.com

[ Upstream commit 80ec82e3d2c1fab42eeb730aaa7985494a963d3f ]

Several ethtool functions leave heap uncleared (potentially) by drivers. This will leave the unused portion of heap unchanged and might copy the full contents back to userspace.

Signed-off-by: Austin Kim austindh.kim@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ethtool/ioctl.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 2603966da904..e910890a868c 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1421,7 +1421,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, if (eeprom.offset + eeprom.len > total_len) return -EINVAL;

- data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM;

@@ -1486,7 +1486,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL;

- data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM;

@@ -1765,7 +1765,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) return -EFAULT;

test.len = test_len; - data = kmalloc_array(test_len, sizeof(u64), GFP_USER); + data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM;

@@ -2281,7 +2281,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); @@ -2473,7 +2473,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; if (phy_drv_tunable) {

From: Zheng Yongjun zhengyongjun3@huawei.com

[ Upstream commit 9d44fa3e50cc91691896934d106c86e4027e61ca ]

Function 'ping_queue_rcv_skb' not always return success, which will also return fail. If not check the wrong return value of it, lead to function `ping_rcv` return success.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/ping.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8b943f85fff9..ea22768f76b8 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -952,6 +952,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false;

/* We assume the packet has already been checked by icmp_rcv */

@@ -966,14 +967,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);

pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n");

- return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv);

From: Eric Dumazet edumazet@google.com

[ Upstream commit b71eaed8c04f72a919a9c44e83e4ee254e69e7f3 ]

UDP sendmsg() path can be lockless, it is possible for another thread to re-connect an change sk->sk_txhash under us.

There is no serious impact, but we can use READ_ONCE()/WRITE_ONCE() pair to document the race.

BUG: KCSAN: data-race in __ip4_datagram_connect / skb_set_owner_w

write to 0xffff88813397920c of 4 bytes by task 30997 on cpu 1: sk_set_txhash include/net/sock.h:1937 [inline] __ip4_datagram_connect+0x69e/0x710 net/ipv4/datagram.c:75 __ip6_datagram_connect+0x551/0x840 net/ipv6/datagram.c:189 ip6_datagram_connect+0x2a/0x40 net/ipv6/datagram.c:272 inet_dgram_connect+0xfd/0x180 net/ipv4/af_inet.c:580 __sys_connect_file net/socket.c:1837 [inline] __sys_connect+0x245/0x280 net/socket.c:1854 __do_sys_connect net/socket.c:1864 [inline] __se_sys_connect net/socket.c:1861 [inline] __x64_sys_connect+0x3d/0x50 net/socket.c:1861 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88813397920c of 4 bytes by task 31039 on cpu 0: skb_set_hash_from_sk include/net/sock.h:2211 [inline] skb_set_owner_w+0x118/0x220 net/core/sock.c:2101 sock_alloc_send_pskb+0x452/0x4e0 net/core/sock.c:2359 sock_alloc_send_skb+0x2d/0x40 net/core/sock.c:2373 __ip6_append_data+0x1743/0x21a0 net/ipv6/ip6_output.c:1621 ip6_make_skb+0x258/0x420 net/ipv6/ip6_output.c:1983 udpv6_sendmsg+0x160a/0x16b0 net/ipv6/udp.c:1527 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xbca3c43d -> 0xfdb309e0

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 31039 Comm: syz-executor.2 Not tainted 5.13.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

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: Sasha Levin sashal@kernel.org --- include/net/sock.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h index b98c80a7c7ae..b9bdeca1d784 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1928,7 +1928,8 @@ static inline u32 net_tx_rndhash(void)

static inline void sk_set_txhash(struct sock *sk) { - sk->sk_txhash = net_tx_rndhash(); + /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ + WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); }

static inline bool sk_rethink_txhash(struct sock *sk) @@ -2200,9 +2201,12 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock,

static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { - if (sk->sk_txhash) { + /* This pairs with WRITE_ONCE() in sk_set_txhash() */ + u32 txhash = READ_ONCE(sk->sk_txhash); + + if (txhash) { skb->l4_hash = 1; - skb->hash = sk->sk_txhash; + skb->hash = txhash; } }

From: Praneeth Bajjuri praneeth@ti.com

[ Upstream commit da9ef50f545f86ffe6ff786174d26500c4db737a ]

Current logic is performing hard reset and causing the programmed registers to be wiped out.

as per datasheet: https://www.ti.com/lit/ds/symlink/dp83867cr.pdf 8.6.26 Control Register (CTRL)

do SW_RESTART to perform a reset not including the registers, If performed when link is already present, it will drop the link and trigger re-auto negotiation.

Signed-off-by: Praneeth Bajjuri praneeth@ti.com Signed-off-by: Geet Modi geet.modi@ti.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/dp83867.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 9bd9a5c0b1db..6bbc81ad295f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -826,16 +826,12 @@ static int dp83867_phy_reset(struct phy_device *phydev) { int err;

- err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); if (err < 0) return err;

usleep_range(10, 20);

- /* After reset FORCE_LINK_GOOD bit is set. Although the - * default value should be unset. Disable FORCE_LINK_GOOD - * for the phy to work properly. - */ return phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); }

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 58af3d3d54e87bfc1f936e16c04ade3369d34011 ]

Syzbot reported memory leak in tty_init_dev(). The problem was in unputted tty in ldisc_open()

static int ldisc_open(struct tty_struct *tty) { ... ser->tty = tty_kref_get(tty); ... result = register_netdevice(dev); if (result) { rtnl_unlock(); free_netdev(dev); return -ENODEV; } ... }

Ser pointer is netdev private_data, so after free_netdev() this pointer goes away with unputted tty reference. So, fix it by adding tty_kref_put() before freeing netdev.

Reported-and-tested-by: syzbot+f303e045423e617d2cad@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/caif/caif_serial.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index 9f30748da4ab..8c38f224becb 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -350,6 +350,7 @@ static int ldisc_open(struct tty_struct *tty) rtnl_lock(); result = register_netdevice(dev); if (result) { + tty_kref_put(tty); rtnl_unlock(); free_netdev(dev); return -ENODEV;

From: Kristian Evensen kristian.evensen@gmail.com

[ Upstream commit 057d49334c02a79af81c30a8d240e641bd6f1741 ]

When the QMI_WWAN_FLAG_PASS_THROUGH is set, netif_rx() is called from qmi_wwan_rx_fixup(). When the call to netif_rx() is successful (which is most of the time), usbnet_skb_return() is called (from rx_process()). usbnet_skb_return() will then call netif_rx() a second time for the same skb.

Simplify the code and avoid the redundant netif_rx() call by changing qmi_wwan_rx_fixup() to always return 1 when QMI_WWAN_FLAG_PASS_THROUGH is set. We then leave it up to the existing infrastructure to call netif_rx().

Suggested-by: Bjørn Mork bjorn@mork.no Signed-off-by: Kristian Evensen kristian.evensen@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/qmi_wwan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6700f1970b24..bc55ec739af9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -575,7 +575,7 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)

if (info->flags & QMI_WWAN_FLAG_PASS_THROUGH) { skb->protocol = htons(ETH_P_MAP); - return (netif_rx(skb) == NET_RX_SUCCESS); + return 1; }

switch (skb->data[0] & 0xf0) {

From: Eric Dumazet edumazet@google.com

[ Upstream commit e032f7c9c7cefffcfb79b9fc16c53011d2d9d11f ]

Like prior patch, we need to annotate lockless accesses to po->ifindex For instance, packet_getname() is reading po->ifindex (twice) while another thread is able to change po->ifindex.

KCSAN reported:

BUG: KCSAN: data-race in packet_do_bind / packet_getname

write to 0xffff888143ce3cbc of 4 bytes by task 25573 on cpu 1: packet_do_bind+0x420/0x7e0 net/packet/af_packet.c:3191 packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255 __sys_bind+0x200/0x290 net/socket.c:1637 __do_sys_bind net/socket.c:1648 [inline] __se_sys_bind net/socket.c:1646 [inline] __x64_sys_bind+0x3d/0x50 net/socket.c:1646 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff888143ce3cbc of 4 bytes by task 25578 on cpu 0: packet_getname+0x5b/0x1a0 net/packet/af_packet.c:3525 __sys_getsockname+0x10e/0x1a0 net/socket.c:1887 __do_sys_getsockname net/socket.c:1902 [inline] __se_sys_getsockname net/socket.c:1899 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:1899 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000000 -> 0x00000001

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 25578 Comm: syz-executor.5 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

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: Sasha Levin sashal@kernel.org --- net/packet/af_packet.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8e07341a98af..68a4dd251242 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3187,11 +3187,11 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3505,7 +3505,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3520,16 +3520,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex;

if (peer) return -EOPNOTSUPP;

+ ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; + sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -4108,7 +4110,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4620,7 +4622,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), - po->ifindex, + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)),

From: Kees Cook keescook@chromium.org

[ Upstream commit 224004fbb033600715dbd626bceec10bfd9c58bc ]

In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields.

The memcpy() is copying the entire structure, not just the first array. Adjust the source argument so the compiler can do appropriate bounds checking.

Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/sh_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index f029c7c03804..393cf99856ed 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2287,7 +2287,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *sh_eth_gstrings_stats, + memcpy(data, sh_eth_gstrings_stats, sizeof(sh_eth_gstrings_stats)); break; }

From: Fuad Tabba tabba@google.com

[ Upstream commit d8ac05ea13d789d5491a5920d70a05659015441d ]

KVM_CHECK_EXTENSION ioctl can return any negative value on error, and not necessarily -1. Change the assertion to reflect that.

Signed-off-by: Fuad Tabba tabba@google.com Message-Id: 20210615150443.1183365-1-tabba@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kvm/lib/kvm_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 2f0e4365f61b..8b90256bca96 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -58,7 +58,7 @@ int kvm_check_cap(long cap) exit(KSFT_SKIP);

ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno);

close(kvm_fd);

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit bbc6f03ff26e7b71d6135a7b78ce40e7dee3d86a ]

Apparently we never clear these values, so they'll remain set since the setting of them is conditional. Clear the values in the relevant other cases.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Link: https://lore.kernel.org/r/iwlwifi.20210618133832.316e32d136a9.I2a12e51814258... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/mlme.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0fe91dc9817e..437d88822d8f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4062,10 +4062,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (elems.mbssid_config_ie) bss_conf->profile_periodicity = elems.mbssid_config_ie->profile_periodicity; + else + bss_conf->profile_periodicity = 0;

if (elems.ext_capab_len >= 11 && (elems.ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) bss_conf->ema_ap = true; + else + bss_conf->ema_ap = false;

/* continue assoc process */ ifmgd->assoc_data->timeout = jiffies; @@ -5802,12 +5806,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 3) sdata->vif.bss_conf.profile_periodicity = elem->data[2]; + else + sdata->vif.bss_conf.profile_periodicity = 0;

elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 11 && (elem->data[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) sdata->vif.bss_conf.ema_ap = true; + else + sdata->vif.bss_conf.ema_ap = false; } else { assoc_data->timeout = jiffies; assoc_data->timeout_started = true;

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit fb780761e7bd9f2e94f5b9a296ead6b35b944206 ]

One should only use st_shndx when >SHN_UNDEF and <SHN_LORESERVE. When SHN_XINDEX, then use .symtab_shndx. Otherwise use 0.

This handles the case: st_shndx >= SHN_LORESERVE && st_shndx != SHN_XINDEX.

Link: https://lore.kernel.org/lkml/20210607023839.26387-1-mark-pk.tsai@mediatek.co... Link: https://lkml.kernel.org/r/20210616154126.2794-1-mark-pk.tsai@mediatek.com

Reported-by: Mark-PK Tsai mark-pk.tsai@mediatek.com Tested-by: Mark-PK Tsai mark-pk.tsai@mediatek.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org [handle endianness of sym->st_shndx] Signed-off-by: Mark-PK Tsai mark-pk.tsai@mediatek.com Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/recordmcount.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h index f9b19524da11..1e9baa5c4fc6 100644 --- a/scripts/recordmcount.h +++ b/scripts/recordmcount.h @@ -192,15 +192,20 @@ static unsigned int get_symindex(Elf_Sym const *sym, Elf32_Word const *symtab, Elf32_Word const *symtab_shndx) { unsigned long offset; + unsigned short shndx = w2(sym->st_shndx); int index;

- if (sym->st_shndx != SHN_XINDEX) - return w2(sym->st_shndx); + if (shndx > SHN_UNDEF && shndx < SHN_LORESERVE) + return shndx;

- offset = (unsigned long)sym - (unsigned long)symtab; - index = offset / sizeof(*sym); + if (shndx == SHN_XINDEX) { + offset = (unsigned long)sym - (unsigned long)symtab; + index = offset / sizeof(*sym);

- return w(symtab_shndx[index]); + return w(symtab_shndx[index]); + } + + return 0; }

static unsigned int get_shnum(Elf_Ehdr const *ehdr, Elf_Shdr const *shdr0)

From: Esben Haabendal esben@geanix.com

[ Upstream commit 28d9fab458b16bcd83f9dd07ede3d585c3e1a69e ]

Add a couple of memory-barriers to ensure correct ordering of read/write access to TX BDs.

In xmit_done, we should ensure that reading the additional BD fields are only done after STS_CTRL_APP0_CMPLT bit is set.

When xmit_done marks the BD as free by setting APP0=0, we need to ensure that the other BD fields are reset first, so we avoid racing with the xmit path, which writes to the same fields.

Finally, making sure to read APP0 of next BD after the current BD, ensures that we see all available buffers.

Signed-off-by: Esben Haabendal esben@geanix.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/xilinx/ll_temac_main.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 01bb36e7cff0..b105e1d35d15 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -774,12 +774,15 @@ static void temac_start_xmit_done(struct net_device *ndev) stat = be32_to_cpu(cur_p->app0);

while (stat & STS_CTRL_APP0_CMPLT) { + /* Make sure that the other fields are read after bd is + * released by dma + */ + rmb(); dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), be32_to_cpu(cur_p->len), DMA_TO_DEVICE); skb = (struct sk_buff *)ptr_from_txbd(cur_p); if (skb) dev_consume_skb_irq(skb); - cur_p->app0 = 0; cur_p->app1 = 0; cur_p->app2 = 0; cur_p->app3 = 0; @@ -788,6 +791,12 @@ static void temac_start_xmit_done(struct net_device *ndev) ndev->stats.tx_packets++; ndev->stats.tx_bytes += be32_to_cpu(cur_p->len);

+ /* app0 must be visible last, as it is used to flag + * availability of the bd + */ + smp_mb(); + cur_p->app0 = 0; + lp->tx_bd_ci++; if (lp->tx_bd_ci >= lp->tx_bd_num) lp->tx_bd_ci = 0; @@ -814,6 +823,9 @@ static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag) if (cur_p->app0) return NETDEV_TX_BUSY;

+ /* Make sure to read next bd app0 after this one */ + rmb(); + tail++; if (tail >= lp->tx_bd_num) tail = 0;

From: David Abdurachmanov david.abdurachmanov@sifive.com

[ Upstream commit 7ede12b01b59dc67bef2e2035297dd2da5bfe427 ]

The order of interrupt numbers is incorrect.

The order for FU740 is: DirError, DataError, DataFail, DirFail

From SiFive FU740-C000 Manual:

19 - L2 Cache DirError 20 - L2 Cache DirFail 21 - L2 Cache DataError 22 - L2 Cache DataFail

Signed-off-by: David Abdurachmanov david.abdurachmanov@sifive.com Signed-off-by: Palmer Dabbelt palmerdabbelt@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/boot/dts/sifive/fu740-c000.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi index eeb4f8c3e0e7..d0d206cdb999 100644 --- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -272,7 +272,7 @@ cache-size = <2097152>; cache-unified; interrupt-parent = <&plic0>; - interrupts = <19 20 21 22>; + interrupts = <19 21 22 20>; reg = <0x0 0x2010000 0x0 0x1000>; }; gpio: gpio@10060000 {

From: Andy Shevchenko andy.shevchenko@gmail.com

[ Upstream commit 76b7f8fae30a9249f820e019f1e62eca992751a2 ]

device_for_each_child_node() bumps a reference counting of a returned variable. We have to balance it whenever we return to the caller.

Fixes: 7e5ea974e61c ("pinctrl: pinctrl-microchip-sgpio: Add pinctrl driver for Microsemi Serial GPIO") Cc: Lars Povlsen lars.povlsen@microchip.com Signed-off-by: Andy Shevchenko andy.shevchenko@gmail.com Link: https://lore.kernel.org/r/20210606191940.29312-1-andy.shevchenko@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/pinctrl-microchip-sgpio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c index c12fa57ebd12..165cb7a59715 100644 --- a/drivers/pinctrl/pinctrl-microchip-sgpio.c +++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c @@ -845,8 +845,10 @@ static int microchip_sgpio_probe(struct platform_device *pdev) i = 0; device_for_each_child_node(dev, fwnode) { ret = microchip_sgpio_register_bank(dev, priv, fwnode, i++); - if (ret) + if (ret) { + fwnode_handle_put(fwnode); return ret; + } }

if (priv->in.gpio.ngpio != priv->out.gpio.ngpio) {

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit 065b6211a87746e196b56759a70c7851418dd741 ]

As explained in [0] currently we may leave SMBHSTSTS_INUSE_STS set, thus potentially breaking ACPI/BIOS usage of the SMBUS device.

Seems patch [0] needs a little bit more of review effort, therefore I'd suggest to apply a part of it as quick win. Just clearing SMBHSTSTS_INUSE_STS when leaving i801_access() should fix the referenced issue and leaves more time for discussing a more sophisticated locking handling.

[0] https://www.spinics.net/lists/linux-i2c/msg51558.html

Fixes: 01590f361e94 ("i2c: i801: Instantiate SPD EEPROMs automatically") Suggested-by: Hector Martin marcan@marcan.st Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Reviewed-by: Hector Martin marcan@marcan.st Reviewed-by: Jean Delvare jdelvare@suse.de Tested-by: Jean Delvare jdelvare@suse.de Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-i801.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index f9e1c2ceaac0..04a1e38f2a6f 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -978,6 +978,9 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, }

out: + /* Unlock the SMBus device for use by BIOS/ACPI */ + outb_p(SMBHSTSTS_INUSE_STS, SMBHSTSTS(priv)); + pm_runtime_mark_last_busy(&priv->pci_dev->dev); pm_runtime_put_autosuspend(&priv->pci_dev->dev); mutex_unlock(&priv->acpi_lock);

From: Christoph Hellwig hch@lst.de

[ Upstream commit d1b7f92035c6fb42529ada531e2cbf3534544c82 ]

While the disk state has nothing to do with partitions, BLKRRPART is used to force a full revalidate after things like a disk format for historical reasons. Restore that behavior.

Link: https://lore.kernel.org/r/20210617115504.1732350-1-hch@lst.de Fixes: 471bd0af544b ("sd: use bdev_check_media_change") Reported-by: Xiang Chen chenxiang66@hisilicon.com Tested-by: Xiang Chen chenxiang66@hisilicon.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/sd.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index ed0b1bb99f08..a0356f3707b8 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1387,6 +1387,22 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) } }

+static bool sd_need_revalidate(struct block_device *bdev, + struct scsi_disk *sdkp) +{ + if (sdkp->device->removable || sdkp->write_prot) { + if (bdev_check_media_change(bdev)) + return true; + } + + /* + * Force a full rescan after ioctl(BLKRRPART). While the disk state has + * nothing to do with partitions, BLKRRPART is used to force a full + * revalidate after things like a format for historical reasons. + */ + return test_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); +} + /** * sd_open - open a scsi disk device * @bdev: Block device of the scsi disk to open @@ -1423,10 +1439,8 @@ static int sd_open(struct block_device *bdev, fmode_t mode) if (!scsi_block_when_processing_errors(sdev)) goto error_out;

- if (sdev->removable || sdkp->write_prot) { - if (bdev_check_media_change(bdev)) - sd_revalidate_disk(bdev->bd_disk); - } + if (sd_need_revalidate(bdev, sdkp)) + sd_revalidate_disk(bdev->bd_disk);

/* * If the drive is empty, just let the open fail.

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 8fd0c1b0647a6bda4067ee0cd61e8395954b6f28 ]

My local syzbot instance hit memory leak in nilfs2. The problem was in missing kobject_put() in nilfs_sysfs_delete_device_group().

kobject_del() does not call kobject_cleanup() for passed kobject and it leads to leaking duped kobject name if kobject_put() was not called.

Fail log:

BUG: memory leak unreferenced object 0xffff8880596171e0 (size 8): comm "syz-executor379", pid 8381, jiffies 4294980258 (age 21.100s) hex dump (first 8 bytes): 6c 6f 6f 70 30 00 00 00 loop0... backtrace: kstrdup+0x36/0x70 mm/util.c:60 kstrdup_const+0x53/0x80 mm/util.c:83 kvasprintf_const+0x108/0x190 lib/kasprintf.c:48 kobject_set_name_vargs+0x56/0x150 lib/kobject.c:289 kobject_add_varg lib/kobject.c:384 [inline] kobject_init_and_add+0xc9/0x160 lib/kobject.c:473 nilfs_sysfs_create_device_group+0x150/0x800 fs/nilfs2/sysfs.c:999 init_nilfs+0xe26/0x12b0 fs/nilfs2/the_nilfs.c:637

Link: https://lkml.kernel.org/r/20210612140559.20022-1-paskripkin@gmail.com Fixes: da7141fb78db ("nilfs2: add /sys/fs/nilfs2/<device> group") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Acked-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: Michael L. Semon mlsemon35@gmail.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/nilfs2/sysfs.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 303d71430bdd..9c6c0e2e5880 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1053,6 +1053,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) nilfs_sysfs_delete_superblock_group(nilfs); nilfs_sysfs_delete_segctor_group(nilfs); kobject_del(&nilfs->ns_dev_kobj); + kobject_put(&nilfs->ns_dev_kobj); kfree(nilfs->ns_dev_subgroups); }

From: Heiko Carstens hca@linux.ibm.com

commit 67147e96a332b56c7206238162771d82467f86c0 upstream.

The CALL_ON_STACK macro is used to call a C function from inline assembly, and therefore must consider the C ABI, which says that only registers 6-13, and 15 are non-volatile (restored by the called function).

The inline assembly incorrectly marks all registers used to pass parameters to the called function as read-only input operands, instead of operands that are read and written to. This might result in register corruption depending on usage, compiler, and compile options.

Fix this by marking all operands used to pass parameters as read/write operands. To keep the code simple even register 6, if used, is marked as read-write operand.

Fixes: ff340d2472ec ("s390: add stack switch helper") Cc: stable@kernel.org # 4.20 Reviewed-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/include/asm/stacktrace.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 2b543163d90a..76c6034428be 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -91,12 +91,16 @@ struct stack_frame { CALL_ARGS_4(arg1, arg2, arg3, arg4); \ register unsigned long r4 asm("6") = (unsigned long)(arg5)

-#define CALL_FMT_0 "=&d" (r2) : -#define CALL_FMT_1 "+&d" (r2) : -#define CALL_FMT_2 CALL_FMT_1 "d" (r3), -#define CALL_FMT_3 CALL_FMT_2 "d" (r4), -#define CALL_FMT_4 CALL_FMT_3 "d" (r5), -#define CALL_FMT_5 CALL_FMT_4 "d" (r6), +/* + * To keep this simple mark register 2-6 as being changed (volatile) + * by the called function, even though register 6 is saved/nonvolatile. + */ +#define CALL_FMT_0 "=&d" (r2) +#define CALL_FMT_1 "+&d" (r2) +#define CALL_FMT_2 CALL_FMT_1, "+&d" (r3) +#define CALL_FMT_3 CALL_FMT_2, "+&d" (r4) +#define CALL_FMT_4 CALL_FMT_3, "+&d" (r5) +#define CALL_FMT_5 CALL_FMT_4, "+&d" (r6)

#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory" #define CALL_CLOBBER_4 CALL_CLOBBER_5 @@ -118,7 +122,7 @@ struct stack_frame { " brasl 14,%[_fn]\n" \ " la 15,0(%[_prev])\n" \ : [_prev] "=&a" (prev), CALL_FMT_##nr \ - [_stack] "R" (stack), \ + : [_stack] "R" (stack), \ [_bc] "i" (offsetof(struct stack_frame, back_chain)), \ [_frame] "d" (frame), \ [_fn] "X" (fn) : CALL_CLOBBER_##nr); \

From: Sven Schnelle svens@linux.ibm.com

commit ca1f4d702d534387aa1f16379edb3b03cdb6ceda upstream.

The current irq entry code doesn't initialize pt_regs::flags. On exit to user mode arch_do_signal_or_restart() tests whether PIF_SYSCALL is set, which might yield wrong results.

Fix this by clearing pt_regs::flags in the entry.S irq handler code.

Reported-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Sven Schnelle svens@linux.ibm.com Reviewed-by: Heiko Carstens hca@linux.ibm.com Fixes: 56e62a737028 ("s390: convert to generic entry") Cc: stable@vger.kernel.org # 5.12 Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/kernel/entry.S | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 9cc71ca9a88f..e84f495e7eb2 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -418,6 +418,7 @@ ENTRY(\name) xgr %r6,%r6 xgr %r7,%r7 xgr %r10,%r10 + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) tm %r8,0x0001 # coming from user space?

From: Johan Hovold johan@kernel.org

commit 4ca070ef0dd885616ef294d269a9bf8e3b258e1a upstream.

The direction of the pipe argument must match the request-type direction bit or control requests may fail depending on the host-controller-driver implementation.

Control transfers without a data stage are treated as OUT requests by the USB stack and should be using usb_sndctrlpipe(). Failing to do so will now trigger a warning.

Fix the OSIFI2C_SET_BIT_RATE and OSIFI2C_STOP requests which erroneously used the osif_usb_read() helper and set the IN direction bit.

Reported-by: syzbot+9d7dadd15b8819d73f41@syzkaller.appspotmail.com Fixes: 83e53a8f120f ("i2c: Add bus driver for for OSIF USB i2c device.") Cc: stable@vger.kernel.org # 3.14 Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/i2c/busses/i2c-robotfuzz-osif.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-robotfuzz-osif.c b/drivers/i2c/busses/i2c-robotfuzz-osif.c index a39f7d092797..66dfa211e736 100644 --- a/drivers/i2c/busses/i2c-robotfuzz-osif.c +++ b/drivers/i2c/busses/i2c-robotfuzz-osif.c @@ -83,7 +83,7 @@ static int osif_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, } }

- ret = osif_usb_read(adapter, OSIFI2C_STOP, 0, 0, NULL, 0); + ret = osif_usb_write(adapter, OSIFI2C_STOP, 0, 0, NULL, 0); if (ret) { dev_err(&adapter->dev, "failure sending STOP\n"); return -EREMOTEIO; @@ -153,7 +153,7 @@ static int osif_probe(struct usb_interface *interface, * Set bus frequency. The frequency is: * 120,000,000 / ( 16 + 2 * div * 4^prescale). * Using dev = 52, prescale = 0 give 100KHz */ - ret = osif_usb_read(&priv->adapter, OSIFI2C_SET_BIT_RATE, 52, 0, + ret = osif_usb_write(&priv->adapter, OSIFI2C_SET_BIT_RATE, 52, 0, NULL, 0); if (ret) { dev_err(&interface->dev, "failure sending bit rate");

From: Juergen Gross jgross@suse.com

commit 3de218ff39b9e3f0d453fe3154f12a174de44b25 upstream.

In order to avoid a race condition for user events when changing cpu affinity reset the active flag only when EOI-ing the event.

This is working fine as all user events are lateeoi events. Note that lateeoi_ack_mask_dynirq() is not modified as there is no explicit call to xen_irq_lateeoi() expected later.

Cc: stable@vger.kernel.org Reported-by: Julien Grall julien@xen.org Fixes: b6622798bc50b62 ("xen/events: avoid handling the same event on two cpus at the same time") Tested-by: Julien Grall julien@xen.org Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Boris Ostrovsky boris.ostrvsky@oracle.com Link: https://lore.kernel.org/r/20210623130913.9405-1-jgross@suse.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/xen/events/events_base.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 7bbfd58958bc..d7e361fb0548 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -642,6 +642,9 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious) }

info->eoi_time = 0; + + /* is_active hasn't been reset yet, do it now. */ + smp_store_release(&info->is_active, 0); do_unmask(info, EVT_MASK_REASON_EOI_PENDING); }

@@ -811,6 +814,7 @@ static void xen_evtchn_close(evtchn_port_t port) BUG(); }

+/* Not called for lateeoi events. */ static void event_handler_exit(struct irq_info *info) { smp_store_release(&info->is_active, 0); @@ -1883,7 +1887,12 @@ static void lateeoi_ack_dynirq(struct irq_data *data)

if (VALID_EVTCHN(evtchn)) { do_mask(info, EVT_MASK_REASON_EOI_PENDING); - event_handler_exit(info); + /* + * Don't call event_handler_exit(). + * Need to keep is_active non-zero in order to ignore re-raised + * events after cpu affinity changes while a lateeoi is pending. + */ + clear_evtchn(evtchn); } }

From: Petr Mladek pmladek@suse.com

commit 5fa54346caf67b4b1b10b1f390316ae466da4d53 upstream.

The system might hang with the following backtrace:

schedule+0x80/0x100 schedule_timeout+0x48/0x138 wait_for_common+0xa4/0x134 wait_for_completion+0x1c/0x2c kthread_flush_work+0x114/0x1cc kthread_cancel_work_sync.llvm.16514401384283632983+0xe8/0x144 kthread_cancel_delayed_work_sync+0x18/0x2c xxxx_pm_notify+0xb0/0xd8 blocking_notifier_call_chain_robust+0x80/0x194 pm_notifier_call_chain_robust+0x28/0x4c suspend_prepare+0x40/0x260 enter_state+0x80/0x3f4 pm_suspend+0x60/0xdc state_store+0x108/0x144 kobj_attr_store+0x38/0x88 sysfs_kf_write+0x64/0xc0 kernfs_fop_write_iter+0x108/0x1d0 vfs_write+0x2f4/0x368 ksys_write+0x7c/0xec

It is caused by the following race between kthread_mod_delayed_work() and kthread_cancel_delayed_work_sync():

CPU0 CPU1

Context: Thread A Context: Thread B

kthread_mod_delayed_work() spin_lock() __kthread_cancel_work() spin_unlock() del_timer_sync() kthread_cancel_delayed_work_sync() spin_lock() __kthread_cancel_work() spin_unlock() del_timer_sync() spin_lock()

work->canceling++ spin_unlock spin_lock() queue_delayed_work() // dwork is put into the worker->delayed_work_list

spin_unlock()

kthread_flush_work() // flush_work is put at the tail of the dwork

wait_for_completion()

Context: IRQ

kthread_delayed_work_timer_fn() spin_lock() list_del_init(&work->node); spin_unlock()

BANG: flush_work is not longer linked and will never get proceed.

The problem is that kthread_mod_delayed_work() checks work->canceling flag before canceling the timer.

A simple solution is to (re)check work->canceling after __kthread_cancel_work(). But then it is not clear what should be returned when __kthread_cancel_work() removed the work from the queue (list) and it can't queue it again with the new @delay.

The return value might be used for reference counting. The caller has to know whether a new work has been queued or an existing one was replaced.

The proper solution is that kthread_mod_delayed_work() will remove the work from the queue (list) _only_ when work->canceling is not set. The flag must be checked after the timer is stopped and the remaining operations can be done under worker->lock.

Note that kthread_mod_delayed_work() could remove the timer and then bail out. It is fine. The other canceling caller needs to cancel the timer as well. The important thing is that the queue (list) manipulation is done atomically under worker->lock.

Link: https://lkml.kernel.org/r/20210610133051.15337-3-pmladek@suse.com Fixes: 9a6b06c8d9a220860468a ("kthread: allow to modify delayed kthread work") Signed-off-by: Petr Mladek pmladek@suse.com Reported-by: Martin Liu liumartin@google.com Cc: jenhaochen@google.com Cc: Minchan Kim minchan@google.com Cc: Nathan Chancellor nathan@kernel.org Cc: Nick Desaulniers ndesaulniers@google.com Cc: Oleg Nesterov oleg@redhat.com Cc: Tejun Heo tj@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/kthread.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/kernel/kthread.c b/kernel/kthread.c index fc7536079f7e..4fdf2bd9b558 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1119,8 +1119,11 @@ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, }

/* - * This function removes the work from the worker queue. Also it makes sure - * that it won't get queued later via the delayed work's timer. + * This function removes the work from the worker queue. + * + * It is called under worker->lock. The caller must make sure that + * the timer used by delayed work is not running, e.g. by calling + * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. @@ -1128,13 +1131,8 @@ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ -static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, - unsigned long *flags) +static bool __kthread_cancel_work(struct kthread_work *work) { - /* Try to cancel the timer if exists. */ - if (is_dwork) - kthread_cancel_delayed_work_timer(work, flags); - /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. @@ -1187,11 +1185,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker);

- /* Do not fight with another command that is canceling this work. */ + /* + * Temporary cancel the work but do not fight with another command + * that is canceling the work as well. + * + * It is a bit tricky because of possible races with another + * mod_delayed_work() and cancel_delayed_work() callers. + * + * The timer must be canceled first because worker->lock is released + * when doing so. But the work can be removed from the queue (list) + * only when it can be queued again so that the return value can + * be used for reference counting. + */ + kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) goto out; + ret = __kthread_cancel_work(work);

- ret = __kthread_cancel_work(work, true, &flags); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: @@ -1213,7 +1223,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker);

- ret = __kthread_cancel_work(work, is_dwork, &flags); + if (is_dwork) + kthread_cancel_delayed_work_timer(work, &flags); + + ret = __kthread_cancel_work(work);

if (worker->current_work != work) goto out_fast;

From: Thomas Gleixner tglx@linutronix.de

commit f9dfb5e390fab2df9f7944bb91e7705aba14cd26 upstream.

The XSAVE init code initializes all enabled and supported components with XRSTOR(S) to init state. Then it XSAVEs the state of the components back into init_fpstate which is used in several places to fill in the init state of components.

This works correctly with XSAVE, but not with XSAVEOPT and XSAVES because those use the init optimization and skip writing state of components which are in init state. So init_fpstate.xsave still contains all zeroes after this operation.

There are two ways to solve that:

1) Use XSAVE unconditionally, but that requires to reshuffle the buffer when XSAVES is enabled because XSAVES uses compacted format.

2) Save the components which are known to have a non-zero init state by other means.

Looking deeper, #2 is the right thing to do because all components the kernel supports have all-zeroes init state except the legacy features (FP, SSE). Those cannot be hard coded because the states are not identical on all CPUs, but they can be saved with FXSAVE which avoids all conditionals.

Use FXSAVE to save the legacy FP/SSE components in init_fpstate along with a BUILD_BUG_ON() which reminds developers to validate that a newly added component has all zeroes init state. As a bonus remove the now unused copy_xregs_to_kernel_booting() crutch.

The XSAVE and reshuffle method can still be implemented in the unlikely case that components are added which have a non-zero init state and no other means to save them. For now, FXSAVE is just simple and good enough.

[ bp: Fix a typo or two in the text. ]

Fixes: 6bad06b76892 ("x86, xsave: Use xsaveopt in context-switch path when supported") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210618143444.587311343@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/fpu/internal.h | 30 ++++++--------------- arch/x86/kernel/fpu/xstate.c | 41 ++++++++++++++++++++++++++--- 2 files changed, 46 insertions(+), 25 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index fdee23ea4e17..16bf4d4a8159 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -204,6 +204,14 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); }

+static inline void fxsave(struct fxregs_state *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); + else + asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); +} + /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" @@ -268,28 +276,6 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory")

-/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) -{ - u64 mask = xfeatures_mask_all; - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - XSTATE_OP(XSAVES, xstate, lmask, hmask, err); - else - XSTATE_OP(XSAVE, xstate, lmask, hmask, err); - - /* We should never fault when copying to a kernel buffer: */ - WARN_ON_FPU(err); -} - /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 2ad57cc14b83..451435d7ff41 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -440,6 +440,25 @@ static void __init print_xstate_offset_size(void) } }

+/* + * All supported features have either init state all zeros or are + * handled in setup_init_fpu() individually. This is an explicit + * feature list and does not use XFEATURE_MASK*SUPPORTED to catch + * newly added supported features at build time and make people + * actually look at the init state for the new feature. + */ +#define XFEATURES_INIT_FPSTATE_HANDLED \ + (XFEATURE_MASK_FP | \ + XFEATURE_MASK_SSE | \ + XFEATURE_MASK_YMM | \ + XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM | \ + XFEATURE_MASK_PKRU | \ + XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_PASID) + /* * setup the xstate image representing the init state */ @@ -447,6 +466,10 @@ static void __init setup_init_fpu_buf(void) { static int on_boot_cpu __initdata = 1;

+ BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED | + XFEATURE_MASK_SUPERVISOR_SUPPORTED) != + XFEATURES_INIT_FPSTATE_HANDLED); + WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0;

@@ -466,10 +489,22 @@ static void __init setup_init_fpu_buf(void) copy_kernel_to_xregs_booting(&init_fpstate.xsave);

/* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. + * All components are now in init state. Read the state back so + * that init_fpstate contains all non-zero init state. This only + * works with XSAVE, but not with XSAVEOPT and XSAVES because + * those use the init optimization which skips writing data for + * components in init state. + * + * XSAVE could be used, but that would require to reshuffle the + * data when XSAVES is available because XSAVES uses xstate + * compaction. But doing so is a pointless exercise because most + * components have an all zeros init state except for the legacy + * ones (FP and SSE). Those can be saved with FXSAVE into the + * legacy area. Adding new features requires to ensure that init + * state is all zeroes or if not to add the necessary handling + * here. */ - copy_xregs_to_kernel_booting(&init_fpstate.xsave); + fxsave(&init_fpstate.fxsave); }

static int xfeature_uncompacted_offset(int xfeature_nr)

From: Xu Yu xuyu@linux.alibaba.com

commit ffc90cbb2970ab88b66ea51dd580469eede57b67 upstream.

We notice that hung task happens in a corner but practical scenario when CONFIG_PREEMPT_NONE is enabled, as follows.

Process 0 Process 1 Process 2..Inf split_huge_page_to_list unmap_page split_huge_pmd_address __migration_entry_wait(head) __migration_entry_wait(tail) remap_page (roll back) remove_migration_ptes rmap_walk_anon cond_resched

Where __migration_entry_wait(tail) is occurred in kernel space, e.g., copy_to_user in fstat, which will immediately fault again without rescheduling, and thus occupy the cpu fully.

When there are too many processes performing __migration_entry_wait on tail page, remap_page will never be done after cond_resched.

This makes __migration_entry_wait operate on the compound head page, thus waits for remap_page to complete, whether the THP is split successfully or roll back.

Note that put_and_wait_on_page_locked helps to drop the page reference acquired with get_page_unless_zero, as soon as the page is on the wait queue, before actually waiting. So splitting the THP is only prevented for a brief interval.

Link: https://lkml.kernel.org/r/b9836c1dd522e903891760af9f0c86a2cce987eb.162314400... Fixes: ba98828088ad ("thp: add option to setup migration entries during PMD split") Suggested-by: Hugh Dickins hughd@google.com Signed-off-by: Gang Deng gavin.dg@linux.alibaba.com Signed-off-by: Xu Yu xuyu@linux.alibaba.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Acked-by: Hugh Dickins hughd@google.com Cc: Matthew Wilcox willy@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/migrate.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/mm/migrate.c b/mm/migrate.c index 773622cffe77..40455e753c5b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -322,6 +322,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, goto out;

page = migration_entry_to_page(entry); + page = compound_head(page);

/* * Once page cache replacement of page migration started, page_count

From: Hugh Dickins hughd@google.com

commit 3b77e8c8cde581dadab9a0f1543a347e24315f11 upstream.

Most callers of is_huge_zero_pmd() supply a pmd already verified present; but a few (notably zap_huge_pmd()) do not - it might be a pmd migration entry, in which the pfn is encoded differently from a present pmd: which might pass the is_huge_zero_pmd() test (though not on x86, since L1TF forced us to protect against that); or perhaps even crash in pmd_page() applied to a swap-like entry.

Make it safe by adding pmd_present() check into is_huge_zero_pmd() itself; and make it quicker by saving huge_zero_pfn, so that is_huge_zero_pmd() will not need to do that pmd_page() lookup each time.

__split_huge_pmd_locked() checked pmd_trans_huge() before: that worked, but is unnecessary now that is_huge_zero_pmd() checks present.

Link: https://lkml.kernel.org/r/21ea9ca-a1f5-8b90-5e88-95fb1c49bbfa@google.com Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Alistair Popple apopple@nvidia.com Cc: Jan Kara jack@suse.cz Cc: Jue Wang juew@google.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Cc: Miaohe Lin linmiaohe@huawei.com Cc: Minchan Kim minchan@kernel.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Shakeel Butt shakeelb@google.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/huge_mm.h | 8 +++++++- mm/huge_memory.c | 5 ++++- 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ba973efcd369..6686a0baa91d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -289,6 +289,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);

extern struct page *huge_zero_page; +extern unsigned long huge_zero_pfn;

static inline bool is_huge_zero_page(struct page *page) { @@ -297,7 +298,7 @@ static inline bool is_huge_zero_page(struct page *page)

static inline bool is_huge_zero_pmd(pmd_t pmd) { - return is_huge_zero_page(pmd_page(pmd)); + return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); }

static inline bool is_huge_zero_pud(pud_t pud) @@ -443,6 +444,11 @@ static inline bool is_huge_zero_page(struct page *page) return false; }

+static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return false; +} + static inline bool is_huge_zero_pud(pud_t pud) { return false; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cd37a0829881..e1ad01e68aa3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -61,6 +61,7 @@ static struct shrinker deferred_split_shrinker;

static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL;

bool transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -97,6 +98,7 @@ retry: __free_pages(zero_page, compound_order(zero_page)); goto retry; } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));

/* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -146,6 +148,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -2073,7 +2076,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, return; }

- if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { + if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside

From: Hugh Dickins hughd@google.com

commit 494334e43c16d63b878536a26505397fce6ff3a2 upstream.

Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory).

When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap().

vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX.

Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too.

Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch.

An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one().

Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered.

Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Jan Kara jack@suse.cz Cc: Jue Wang juew@google.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Cc: Miaohe Lin linmiaohe@huawei.com Cc: Minchan Kim minchan@kernel.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Shakeel Butt shakeelb@google.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/internal.h | 53 ++++++++++++++++++++++++++++++++------------ mm/page_vma_mapped.c | 16 +++++-------- mm/rmap.c | 16 ++++++------- 3 files changed, 53 insertions(+), 32 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h index 1432feec62df..08323e622bbd 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -379,27 +379,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);

/* - * At what user virtual address is page expected in @vma? + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. */ static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) +vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; }

+/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_address_end(struct page *page, struct vm_area_struct *vma) { - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE; - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - - return max(start, vma->vm_start); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + compound_nr(page); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; }

static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index da6744015abd..f34c065629aa 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -228,18 +228,18 @@ restart: if (!map_pte(pvmw)) goto next_pte; while (1) { + unsigned long end; + if (check_pte(pvmw)) return true; next_pte: /* Seek to next pte only makes sense for THP */ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) return not_found(pvmw); + end = vma_address_end(pvmw->page, pvmw->vma); do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= pvmw->vma->vm_end || - pvmw->address >= - __vma_address(pvmw->page, pvmw->vma) + - thp_size(pvmw->page)) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ if (pvmw->address % PMD_SIZE == 0) { @@ -277,14 +277,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .vma = vma, .flags = PVMW_SYNC, }; - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE;

- if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) return 0; - pvmw.address = max(start, vma->vm_start); if (!page_vma_mapped_walk(&pvmw)) return 0; page_vma_mapped_walk_done(&pvmw); diff --git a/mm/rmap.c b/mm/rmap.c index 735a1b514f83..cc8208b20373 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -707,7 +707,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -722,10 +721,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) return -EFAULT; } else return -EFAULT; - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) - return -EFAULT; - return address; + + return vma_address(page, vma); }

pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) @@ -919,7 +916,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - min(vma->vm_end, address + page_size(page))); + vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range);

while (page_vma_mapped_walk(&pvmw)) { @@ -1435,9 +1432,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, - min(vma->vm_end, address + page_size(page))); + address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted @@ -1889,6 +1887,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma);

+ VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched();

if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) @@ -1943,6 +1942,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma);

+ VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched();

if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))

From: Hugh Dickins hughd@google.com

commit 22061a1ffabdb9c3385de159c5db7aac3a4df1cc upstream.

There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped.

The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page.

However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside.

The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside.

Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly.

This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe.

Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped.

Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Alistair Popple apopple@nvidia.com Cc: Jan Kara jack@suse.cz Cc: Jue Wang juew@google.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Cc: Miaohe Lin linmiaohe@huawei.com Cc: Minchan Kim minchan@kernel.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Shakeel Butt shakeelb@google.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/mm.h | 3 +++ mm/memory.c | 41 +++++++++++++++++++++++++++++++++++++++++ mm/truncate.c | 43 +++++++++++++++++++------------------------ 3 files changed, 63 insertions(+), 24 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 6c1b29bb3563..cfb0842a7fb9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1680,6 +1680,7 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ + struct page *single_page; /* Locked page to be unmapped */ };

struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, @@ -1727,6 +1728,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); +void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1747,6 +1749,7 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } +static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, diff --git a/mm/memory.c b/mm/memory.c index 14a6c66b3748..36624986130b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1361,7 +1361,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } + /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is @@ -3193,6 +3204,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } }

+/** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + thp_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. diff --git a/mm/truncate.c b/mm/truncate.c index 455944264663..bf092be0a6f0 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -168,13 +168,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void -truncate_cleanup_page(struct address_space *mapping, struct page *page) +static void truncate_cleanup_page(struct page *page) { - if (page_mapped(page)) { - unsigned int nr = thp_nr_pages(page); - unmap_mapping_pages(mapping, page->index, nr, false); - } + if (page_mapped(page)) + unmap_mapping_page(page);

if (page_has_private(page)) do_invalidatepage(page, 0, thp_size(page)); @@ -219,7 +216,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return -EIO;

- truncate_cleanup_page(mapping, page); + truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } @@ -326,7 +323,7 @@ void truncate_inode_pages_range(struct address_space *mapping, index = indices[pagevec_count(&pvec) - 1] + 1; truncate_exceptional_pvec_entries(mapping, &pvec, indices); for (i = 0; i < pagevec_count(&pvec); i++) - truncate_cleanup_page(mapping, pvec.pages[i]); + truncate_cleanup_page(pvec.pages[i]); delete_from_page_cache_batch(mapping, &pvec); for (i = 0; i < pagevec_count(&pvec); i++) unlock_page(pvec.pages[i]); @@ -652,6 +649,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; }

+ if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { @@ -659,23 +666,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } wait_on_page_writeback(page); - if (page_mapped(page)) { - if (!did_range_unmap) { - /* - * Zap the rest of the file in one hit. - */ - unmap_mapping_pages(mapping, index, - (1 + end - index), false); - did_range_unmap = 1; - } else { - /* - * Just zap this page - */ - unmap_mapping_pages(mapping, index, - 1, false); - } - } + + if (page_mapped(page)) + unmap_mapping_page(page); BUG_ON(page_mapped(page)); + ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page))

From: Hugh Dickins hughd@google.com

commit f003c03bd29e6f46fef1b9a8e8d636ac732286d5 upstream.

Patch series "mm: page_vma_mapped_walk() cleanup and THP fixes".

I've marked all of these for stable: many are merely cleanups, but I think they are much better before the main fix than after.

This patch (of 11):

page_vma_mapped_walk() cleanup: sometimes the local copy of pvwm->page was used, sometimes pvmw->page itself: use the local copy "page" throughout.

Link: https://lkml.kernel.org/r/589b358c-febc-c88e-d4c2-7834b37fa7bf@google.com Link: https://lkml.kernel.org/r/88e67645-f467-c279-bf5e-af4b5c6b13eb@google.com Signed-off-by: Hugh Dickins hughd@google.com Reviewed-by: Alistair Popple apopple@nvidia.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Peter Xu peterx@redhat.com Cc: Yang Shi shy828301@gmail.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Matthew Wilcox willy@infradead.org Cc: Ralph Campbell rcampbell@nvidia.com Cc: Zi Yan ziy@nvidia.com Cc: Will Deacon will@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index f34c065629aa..ba24ac8e2377 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -156,7 +156,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pte) goto next_pte;

- if (unlikely(PageHuge(pvmw->page))) { + if (unlikely(PageHuge(page))) { /* when pud is not present, pte will be NULL */ pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); if (!pvmw->pte) @@ -217,8 +217,7 @@ restart: * cannot return prematurely, while zap_huge_pmd() has * cleared *pmd but not decremented compound_mapcount(). */ - if ((pvmw->flags & PVMW_SYNC) && - PageTransCompound(pvmw->page)) { + if ((pvmw->flags & PVMW_SYNC) && PageTransCompound(page)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);

spin_unlock(ptl); @@ -234,9 +233,9 @@ restart: return true; next_pte: /* Seek to next pte only makes sense for THP */ - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) + if (!PageTransHuge(page) || PageHuge(page)) return not_found(pvmw); - end = vma_address_end(pvmw->page, pvmw->vma); + end = vma_address_end(page, pvmw->vma); do { pvmw->address += PAGE_SIZE; if (pvmw->address >= end)

From: Hugh Dickins hughd@google.com

commit 3306d3119ceacc43ea8b141a73e21fea68eec30c upstream.

page_vma_mapped_walk() cleanup: re-evaluate pmde after taking lock, then use it in subsequent tests, instead of repeatedly dereferencing pointer.

Link: https://lkml.kernel.org/r/53fbc9d-891e-46b2-cb4b-468c3b19238e@google.com Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Peter Xu peterx@redhat.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 9085d09c5bc3..825c97a479e6 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -191,18 +191,19 @@ restart: pmde = READ_ONCE(*pvmw->pmd); if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); - if (likely(pmd_trans_huge(*pvmw->pmd))) { + pmde = *pvmw->pmd; + if (likely(pmd_trans_huge(pmde))) { if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); - if (pmd_page(*pvmw->pmd) != page) + if (pmd_page(pmde) != page) return not_found(pvmw); return true; - } else if (!pmd_present(*pvmw->pmd)) { + } else if (!pmd_present(pmde)) { if (thp_migration_supported()) { if (!(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); - if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { - swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); + if (is_migration_entry(pmd_to_swp_entry(pmde))) { + swp_entry_t entry = pmd_to_swp_entry(pmde);

if (migration_entry_to_page(entry) != page) return not_found(pvmw);

From: Hugh Dickins hughd@google.com

commit 448282487483d6fa5b2eeeafaa0acc681e544a9c upstream.

page_vma_mapped_walk() cleanup: adjust the test for crossing page table boundary - I believe pvmw->address is always page-aligned, but nothing else here assumed that; and remember to reset pvmw->pte to NULL after unmapping the page table, though I never saw any bug from that.

Link: https://lkml.kernel.org/r/799b3f9c-2a9e-dfef-5d89-26e9f76fd97@google.com Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 96cef824f52f..aad116532140 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -244,16 +244,16 @@ next_pte: if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ - if (pvmw->address % PMD_SIZE == 0) { - pte_unmap(pvmw->pte); + if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } + pte_unmap(pvmw->pte); + pvmw->pte = NULL; goto restart; - } else { - pvmw->pte++; } + pvmw->pte++; } while (pte_none(*pvmw->pte));

if (!pvmw->ptl) {

From: Hugh Dickins hughd@google.com

commit 474466301dfd8b39a10c01db740645f3f7ae9a28 upstream.

page_vma_mapped_walk() cleanup: add a label this_pte, matching next_pte, and use "goto this_pte", in place of the "while (1)" loop at the end.

Link: https://lkml.kernel.org/r/a52b234a-851-3616-2525-f42736e8934@google.com Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 4a8a069c5e87..8803dd93c049 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -144,6 +144,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; + unsigned long end; pgd_t *pgd; p4d_t *p4d; pud_t *pud; @@ -233,10 +234,7 @@ restart: } if (!map_pte(pvmw)) goto next_pte; - } - while (1) { - unsigned long end; - +this_pte: if (check_pte(pvmw)) return true; next_pte: @@ -265,6 +263,7 @@ next_pte: pvmw->ptl = pte_lockptr(mm, pvmw->pmd); spin_lock(pvmw->ptl); } + goto this_pte; } }

From: Hugh Dickins hughd@google.com

commit a9a7504d9beaf395481faa91e70e2fd08f7a3dde upstream.

Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory).

Crash dumps showed two tail pages of a shmem huge page remained mapped by pte: ptes in a non-huge-aligned vma of a gVisor process, at the end of a long unmapped range; and no page table had yet been allocated for the head of the huge page to be mapped into.

Although designed to handle these odd misaligned huge-page-mapped-by-pte cases, page_vma_mapped_walk() falls short by returning false prematurely when !pmd_present or !pud_present or !p4d_present or !pgd_present: there are cases when a huge page may span the boundary, with ptes present in the next.

Restructure page_vma_mapped_walk() as a loop to continue in these cases, while keeping its layout much as before. Add a step_forward() helper to advance pvmw->address across those boundaries: originally I tried to use mm's standard p?d_addr_end() macros, but hit the same crash 512 times less often: because of the way redundant levels are folded together, but folded differently in different configurations, it was just too difficult to use them correctly; and step_forward() is simpler anyway.

Link: https://lkml.kernel.org/r/fedb8632-1798-de42-f39e-873551d5bc81@google.com Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index b4c731ca2752..16f139f83ebf 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -116,6 +116,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return pfn_is_match(pvmw->page, pfn); }

+static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) +{ + pvmw->address = (pvmw->address + size) & ~(size - 1); + if (!pvmw->address) + pvmw->address = ULONG_MAX; +} + /** * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at * @pvmw->address @@ -183,16 +190,22 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pte) goto next_pte; restart: - { + do { pgd = pgd_offset(mm, pvmw->address); - if (!pgd_present(*pgd)) - return false; + if (!pgd_present(*pgd)) { + step_forward(pvmw, PGDIR_SIZE); + continue; + } p4d = p4d_offset(pgd, pvmw->address); - if (!p4d_present(*p4d)) - return false; + if (!p4d_present(*p4d)) { + step_forward(pvmw, P4D_SIZE); + continue; + } pud = pud_offset(p4d, pvmw->address); - if (!pud_present(*pud)) - return false; + if (!pud_present(*pud)) { + step_forward(pvmw, PUD_SIZE); + continue; + }

pvmw->pmd = pmd_offset(pud, pvmw->address); /* @@ -239,7 +252,8 @@ restart:

spin_unlock(ptl); } - return false; + step_forward(pvmw, PMD_SIZE); + continue; } if (!map_pte(pvmw)) goto next_pte; @@ -269,7 +283,9 @@ next_pte: spin_lock(pvmw->ptl); } goto this_pte; - } + } while (pvmw->address < end); + + return false; }

/**

From: Hugh Dickins hughd@google.com

commit fe19bd3dae3d15d2fbfdb3de8839a6ea0fe94264 upstream.

If more than one futex is placed on a shmem huge page, it can happen that waking the second wakes the first instead, and leaves the second waiting: the key's shared.pgoff is wrong.

When 3.11 commit 13d60f4b6ab5 ("futex: Take hugepages into account when generating futex_key"), the only shared huge pages came from hugetlbfs, and the code added to deal with its exceptional page->index was put into hugetlb source. Then that was missed when 4.8 added shmem huge pages.

page_to_pgoff() is what others use for this nowadays: except that, as currently written, it gives the right answer on hugetlbfs head, but nonsense on hugetlbfs tails. Fix that by calling hugetlbfs-specific hugetlb_basepage_index() on PageHuge tails as well as on head.

Yes, it's unconventional to declare hugetlb_basepage_index() there in pagemap.h, rather than in hugetlb.h; but I do not expect anything but page_to_pgoff() ever to need it.

[akpm@linux-foundation.org: give hugetlb_basepage_index() prototype the correct scope]

Link: https://lkml.kernel.org/r/b17d946b-d09-326e-b42a-52884c36df32@google.com Fixes: 800d8c63b2e9 ("shmem: add huge pages support") Reported-by: Neel Natu neelnatu@google.com Signed-off-by: Hugh Dickins hughd@google.com Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Acked-by: Thomas Gleixner tglx@linutronix.de Cc: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com Cc: Zhang Yi wetpzy@gmail.com Cc: Mel Gorman mgorman@techsingularity.net Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Ingo Molnar mingo@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: Darren Hart dvhart@infradead.org Cc: Davidlohr Bueso dave@stgolabs.net Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/hugetlb.h | 16 ---------------- include/linux/pagemap.h | 13 +++++++------ kernel/futex.c | 3 +-- mm/hugetlb.c | 5 +---- 4 files changed, 9 insertions(+), 28 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5dae4187210d..28fa3f9bbbfd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -728,17 +728,6 @@ static inline int hstate_index(struct hstate *h) return h - hstates; }

-pgoff_t __basepage_index(struct page *page); - -/* Return page->index in PAGE_SIZE units */ -static inline pgoff_t basepage_index(struct page *page) -{ - if (!PageCompound(page)) - return page->index; - - return __basepage_index(page); -} - extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -969,11 +958,6 @@ static inline int hstate_index(struct hstate *h) return 0; }

-static inline pgoff_t basepage_index(struct page *page) -{ - return page->index; -} - static inline int dissolve_free_huge_page(struct page *page) { return 0; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8c9947fd62f3..e0023e5f9aa6 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -501,7 +501,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping, }

/* - * Get index of the page with in radix-tree + * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_index(struct page *page) @@ -520,15 +520,16 @@ static inline pgoff_t page_to_index(struct page *page) return pgoff; }

+extern pgoff_t hugetlb_basepage_index(struct page *page); + /* - * Get the offset in PAGE_SIZE. - * (TODO: hugepage should have ->index in PAGE_SIZE) + * Get the offset in PAGE_SIZE (even for hugetlb pages). + * (TODO: hugetlb pages should have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_pgoff(struct page *page) { - if (unlikely(PageHeadHuge(page))) - return page->index << compound_order(page); - + if (unlikely(PageHuge(page))) + return hugetlb_basepage_index(page); return page_to_index(page); }

diff --git a/kernel/futex.c b/kernel/futex.c index a8629b695d38..5aa6d0a6c767 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -35,7 +35,6 @@ #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/syscalls.h> -#include <linux/hugetlb.h> #include <linux/freezer.h> #include <linux/memblock.h> #include <linux/fault-inject.h> @@ -650,7 +649,7 @@ again:

key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = basepage_index(tail); + key->shared.pgoff = page_to_pgoff(tail); rcu_read_unlock(); }

diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3da4817190f3..7ba7d9b20494 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1584,15 +1584,12 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) return NULL; }

-pgoff_t __basepage_index(struct page *page) +pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx;

- if (!PageHuge(page_head)) - return page_index(page); - if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else

From: Bumyong Lee bumyong.lee@samsung.com

commit 5f89468e2f060031cd89fd4287298e0eaf246bf6 upstream.

in case of driver wants to sync part of ranges with offset, swiotlb_tbl_sync_single() copies from orig_addr base to tlb_addr with offset and ends up with data mismatch.

It was removed from "swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single", but said logic has to be added back in.

From Linus's email:

"That commit which the removed the offset calculation entirely, because the old

(unsigned long)tlb_addr & (IO_TLB_SIZE - 1)

was wrong, but instead of removing it, I think it should have just fixed it to be

(tlb_addr - mem->start) & (IO_TLB_SIZE - 1);

instead. That way the slot offset always matches the slot index calculation."

(Unfortunatly that broke NVMe).

The use-case that drivers are hitting is as follow:

1. Get dma_addr_t from dma_map_single()

dma_addr_t tlb_addr = dma_map_single(dev, vaddr, vsize, DMA_TO_DEVICE);

|<---------------vsize------------->| +-----------------------------------+ | | original buffer +-----------------------------------+ vaddr

swiotlb_align_offset |<----->|<---------------vsize------------->| +-------+-----------------------------------+ | | | swiotlb buffer +-------+-----------------------------------+ tlb_addr

2. Do something 3. Sync dma_addr_t through dma_sync_single_for_device(..)

dma_sync_single_for_device(dev, tlb_addr + offset, size, DMA_TO_DEVICE);

Error case. Copy data to original buffer but it is from base addr (instead of base addr + offset) in original buffer:

swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr

|<- size ->| +-----------------------------------+ |##########| | original buffer +-----------------------------------+ vaddr

The fix is to copy the data to the original buffer and take into account the offset, like so:

swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr

|<- offset ->|<- size ->| +-----------------------------------+ | |##########| | original buffer +-----------------------------------+ vaddr

[One fix which was Linus's that made more sense to as it created a symmetry would break NVMe. The reason for that is the: unsigned int offset = (tlb_addr - mem->start) & (IO_TLB_SIZE - 1);

would come up with the proper offset, but it would lose the alignment (which this patch contains).]

Fixes: 16fc3cef33a0 ("swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single") Signed-off-by: Bumyong Lee bumyong.lee@samsung.com Signed-off-by: Chanho Park chanho61.park@samsung.com Reviewed-by: Christoph Hellwig hch@lst.de Reported-by: Dominique MARTINET dominique.martinet@atmark-techno.com Reported-by: Horia Geantă horia.geanta@nxp.com Tested-by: Horia Geantă horia.geanta@nxp.com CC: stable@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/dma/swiotlb.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index fe4c01c14ab2..e96f3808e431 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -724,11 +724,17 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; size_t orig_size = io_tlb_orig_size[index]; phys_addr_t orig_addr = io_tlb_orig_addr[index]; + unsigned int tlb_offset;

if (orig_addr == INVALID_PHYS_ADDR) return;

- validate_sync_size_and_truncate(hwdev, orig_size, &size); + tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - + swiotlb_align_offset(hwdev, orig_addr); + + orig_addr += tlb_offset; + + validate_sync_size_and_truncate(hwdev, orig_size - tlb_offset, &size);

switch (target) { case SYNC_FOR_CPU:

From: Naoya Horiguchi naoya.horiguchi@nec.com

commit ea6d0630100b285f059d0a8d8e86f38a46407536 upstream.

Currently me_huge_page() temporary unlocks page to perform some actions then locks it again later. My testcase (which calls hard-offline on some tail page in a hugetlb, then accesses the address of the hugetlb range) showed that page allocation code detects this page lock on buddy page and printed out "BUG: Bad page state" message.

check_new_page_bad() does not consider a page with __PG_HWPOISON as bad page, so this flag works as kind of filter, but this filtering doesn't work in this case because the "bad page" is not the actual hwpoisoned page. So stop locking page again. Actions to be taken depend on the page type of the error, so page unlocking should be done in ->action() callbacks. So let's make it assumed and change all existing callbacks that way.

Link: https://lkml.kernel.org/r/20210609072029.74645-1-nao.horiguchi@gmail.com Fixes: commit 78bb920344b8 ("mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error") Signed-off-by: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Michal Hocko mhocko@suse.com Cc: Tony Luck tony.luck@intel.com Cc: "Aneesh Kumar K.V" aneesh.kumar@linux.vnet.ibm.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory-failure.c | 44 ++++++++++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 14 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2dd60ad81216..4db6f95e55be 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -658,6 +658,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, */ static int me_kernel(struct page *p, unsigned long pfn) { + unlock_page(p); return MF_IGNORED; }

@@ -667,6 +668,7 @@ static int me_kernel(struct page *p, unsigned long pfn) static int me_unknown(struct page *p, unsigned long pfn) { pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + unlock_page(p); return MF_FAILED; }

@@ -675,6 +677,7 @@ static int me_unknown(struct page *p, unsigned long pfn) */ static int me_pagecache_clean(struct page *p, unsigned long pfn) { + int ret; struct address_space *mapping;

delete_from_lru_cache(p); @@ -683,8 +686,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (PageAnon(p)) { + ret = MF_RECOVERED; + goto out; + }

/* * Now truncate the page in the page cache. This is really @@ -698,7 +703,8 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return MF_FAILED; + ret = MF_FAILED; + goto out; }

/* @@ -706,7 +712,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_mutex or not for this? Right now we don't. */ - return truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, pfn, mapping); +out: + unlock_page(p); + return ret; }

/* @@ -782,24 +791,26 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) */ static int me_swapcache_dirty(struct page *p, unsigned long pfn) { + int ret; + ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p);

- if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; + unlock_page(p); + return ret; }

static int me_swapcache_clean(struct page *p, unsigned long pfn) { + int ret; + delete_from_swap_cache(p);

- if (!delete_from_lru_cache(p)) - return MF_RECOVERED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + unlock_page(p); + return ret; }

/* @@ -820,6 +831,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { res = truncate_error_page(hpage, pfn, mapping); + unlock_page(hpage); } else { res = MF_FAILED; unlock_page(hpage); @@ -834,7 +846,6 @@ static int me_huge_page(struct page *p, unsigned long pfn) page_ref_inc(p); res = MF_RECOVERED; } - lock_page(hpage); }

return res; @@ -866,6 +877,8 @@ static struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ int (*action)(struct page *p, unsigned long pfn); } error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, @@ -929,6 +942,7 @@ static int page_action(struct page_state *ps, struct page *p, int result; int count;

+ /* page p should be unlocked after returning from ps->action(). */ result = ps->action(p, pfn);

count = page_count(p) - 1; @@ -1313,7 +1327,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) goto out; }

- res = identify_page_state(pfn, p, page_flags); + return identify_page_state(pfn, p, page_flags); out: unlock_page(head); return res; @@ -1595,6 +1609,8 @@ try_again:

identify_page_state: res = identify_page_state(pfn, p, page_flags); + mutex_unlock(&mf_mutex); + return res; unlock_page: unlock_page(p); unlock_mutex:

From: Eric Snowberg eric.snowberg@oracle.com

[ Upstream commit 56c5812623f95313f6a46fbf0beee7fa17c68bbf ]

This fixes CVE-2020-26541.

The Secure Boot Forbidden Signature Database, dbx, contains a list of now revoked signatures and keys previously approved to boot with UEFI Secure Boot enabled. The dbx is capable of containing any number of EFI_CERT_X509_SHA256_GUID, EFI_CERT_SHA256_GUID, and EFI_CERT_X509_GUID entries.

Currently when EFI_CERT_X509_GUID are contained in the dbx, the entries are skipped.

Add support for EFI_CERT_X509_GUID dbx entries. When a EFI_CERT_X509_GUID is found, it is added as an asymmetrical key to the .blacklist keyring. Anytime the .platform keyring is used, the keys in the .blacklist keyring are referenced, if a matching key is found, the key will be rejected.

[DH: Made the following changes: - Added to have a config option to enable the facility. This allows a Kconfig solution to make sure that pkcs7_validate_trust() is enabled.[1][2] - Moved the functions out from the middle of the blacklist functions. - Added kerneldoc comments.]

Signed-off-by: Eric Snowberg eric.snowberg@oracle.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org cc: Randy Dunlap rdunlap@infradead.org cc: Mickaël Salaün mic@digikod.net cc: Arnd Bergmann arnd@kernel.org cc: keyrings@vger.kernel.org Link: https://lore.kernel.org/r/20200901165143.10295-1-eric.snowberg@oracle.com/ # rfc Link: https://lore.kernel.org/r/20200909172736.73003-1-eric.snowberg@oracle.com/ # v2 Link: https://lore.kernel.org/r/20200911182230.62266-1-eric.snowberg@oracle.com/ # v3 Link: https://lore.kernel.org/r/20200916004927.64276-1-eric.snowberg@oracle.com/ # v4 Link: https://lore.kernel.org/r/20210122181054.32635-2-eric.snowberg@oracle.com/ # v5 Link: https://lore.kernel.org/r/161428672051.677100.11064981943343605138.stgit@war... Link: https://lore.kernel.org/r/161433310942.902181.4901864302675874242.stgit@wart... # v2 Link: https://lore.kernel.org/r/161529605075.163428.14625520893961300757.stgit@war... # v3 Link: https://lore.kernel.org/r/bc2c24e3-ed68-2521-0bf4-a1f6be4a895d@infradead.org... [1] Link: https://lore.kernel.org/r/20210225125638.1841436-1-arnd@kernel.org/ [2] Signed-off-by: Sasha Levin sashal@kernel.org --- certs/Kconfig | 9 ++++ certs/blacklist.c | 43 +++++++++++++++++++ certs/blacklist.h | 2 + certs/system_keyring.c | 6 +++ include/keys/system_keyring.h | 15 +++++++ .../platform_certs/keyring_handler.c | 11 +++++ 6 files changed, 86 insertions(+)

diff --git a/certs/Kconfig b/certs/Kconfig index c94e93d8bccf..76e469b56a77 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -83,4 +83,13 @@ config SYSTEM_BLACKLIST_HASH_LIST wrapper to incorporate the list into the kernel. Each <hash> should be a string of hex digits.

+config SYSTEM_REVOCATION_LIST + bool "Provide system-wide ring of revocation certificates" + depends on SYSTEM_BLACKLIST_KEYRING + depends on PKCS7_MESSAGE_PARSER=y + help + If set, this allows revocation certificates to be stored in the + blacklist keyring and implements a hook whereby a PKCS#7 message can + be checked to see if it matches such a certificate. + endmenu diff --git a/certs/blacklist.c b/certs/blacklist.c index bffe4c6f4a9e..2b8644123d5f 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -145,6 +145,49 @@ int is_binary_blacklisted(const u8 *hash, size_t hash_len) } EXPORT_SYMBOL_GPL(is_binary_blacklisted);

+#ifdef CONFIG_SYSTEM_REVOCATION_LIST +/** + * add_key_to_revocation_list - Add a revocation certificate to the blacklist + * @data: The data blob containing the certificate + * @size: The size of data blob + */ +int add_key_to_revocation_list(const char *data, size_t size) +{ + key_ref_t key; + + key = key_create_or_update(make_key_ref(blacklist_keyring, true), + "asymmetric", + NULL, + data, + size, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW), + KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN); + + if (IS_ERR(key)) { + pr_err("Problem with revocation key (%ld)\n", PTR_ERR(key)); + return PTR_ERR(key); + } + + return 0; +} + +/** + * is_key_on_revocation_list - Determine if the key for a PKCS#7 message is revoked + * @pkcs7: The PKCS#7 message to check + */ +int is_key_on_revocation_list(struct pkcs7_message *pkcs7) +{ + int ret; + + ret = pkcs7_validate_trust(pkcs7, blacklist_keyring); + + if (ret == 0) + return -EKEYREJECTED; + + return -ENOKEY; +} +#endif + /* * Initialise the blacklist */ diff --git a/certs/blacklist.h b/certs/blacklist.h index 1efd6fa0dc60..51b320cf8574 100644 --- a/certs/blacklist.h +++ b/certs/blacklist.h @@ -1,3 +1,5 @@ #include <linux/kernel.h> +#include <linux/errno.h> +#include <crypto/pkcs7.h>

extern const char __initconst *const blacklist_hashes[]; diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 4b693da488f1..ed98754d5795 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -242,6 +242,12 @@ int verify_pkcs7_message_sig(const void *data, size_t len, pr_devel("PKCS#7 platform keyring is not available\n"); goto error; } + + ret = is_key_on_revocation_list(pkcs7); + if (ret != -ENOKEY) { + pr_devel("PKCS#7 platform key is on revocation list\n"); + goto error; + } } ret = pkcs7_validate_trust(pkcs7, trusted_keys); if (ret < 0) { diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index fb8b07daa9d1..875e002a4180 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -31,6 +31,7 @@ extern int restrict_link_by_builtin_and_secondary_trusted( #define restrict_link_by_builtin_and_secondary_trusted restrict_link_by_builtin_trusted #endif

+extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING extern int mark_hash_blacklisted(const char *hash); extern int is_hash_blacklisted(const u8 *hash, size_t hash_len, @@ -49,6 +50,20 @@ static inline int is_binary_blacklisted(const u8 *hash, size_t hash_len) } #endif

+#ifdef CONFIG_SYSTEM_REVOCATION_LIST +extern int add_key_to_revocation_list(const char *data, size_t size); +extern int is_key_on_revocation_list(struct pkcs7_message *pkcs7); +#else +static inline int add_key_to_revocation_list(const char *data, size_t size) +{ + return 0; +} +static inline int is_key_on_revocation_list(struct pkcs7_message *pkcs7) +{ + return -ENOKEY; +} +#endif + #ifdef CONFIG_IMA_BLACKLIST_KEYRING extern struct key *ima_blacklist_keyring;

diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c index c5ba695c10e3..5604bd57c990 100644 --- a/security/integrity/platform_certs/keyring_handler.c +++ b/security/integrity/platform_certs/keyring_handler.c @@ -55,6 +55,15 @@ static __init void uefi_blacklist_binary(const char *source, uefi_blacklist_hash(source, data, len, "bin:", 4); }

+/* + * Add an X509 cert to the revocation list. + */ +static __init void uefi_revocation_list_x509(const char *source, + const void *data, size_t len) +{ + add_key_to_revocation_list(data, len); +} + /* * Return the appropriate handler for particular signature list types found in * the UEFI db and MokListRT tables. @@ -76,5 +85,7 @@ __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type) return uefi_blacklist_x509_tbs; if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) return uefi_blacklist_binary; + if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) + return uefi_revocation_list_x509; return 0; }

From: Eric Snowberg eric.snowberg@oracle.com

[ Upstream commit d1f044103dad70c1cec0a8f3abdf00834fec8b98 ]

Add a new Kconfig option called SYSTEM_REVOCATION_KEYS. If set, this option should be the filename of a PEM-formated file containing X.509 certificates to be included in the default blacklist keyring.

DH Changes: - Make the new Kconfig option depend on SYSTEM_REVOCATION_LIST. - Fix SYSTEM_REVOCATION_KEYS=n, but CONFIG_SYSTEM_REVOCATION_LIST=y[1][2]. - Use CONFIG_SYSTEM_REVOCATION_LIST for extract-cert[3]. - Use CONFIG_SYSTEM_REVOCATION_LIST for revocation_certificates.o[3].

Signed-off-by: Eric Snowberg eric.snowberg@oracle.com Acked-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: David Howells dhowells@redhat.com cc: Randy Dunlap rdunlap@infradead.org cc: keyrings@vger.kernel.org Link: https://lore.kernel.org/r/e1c15c74-82ce-3a69-44de-a33af9b320ea@infradead.org... [1] Link: https://lore.kernel.org/r/20210303034418.106762-1-eric.snowberg@oracle.com/ [2] Link: https://lore.kernel.org/r/20210304175030.184131-1-eric.snowberg@oracle.com/ [3] Link: https://lore.kernel.org/r/20200930201508.35113-3-eric.snowberg@oracle.com/ Link: https://lore.kernel.org/r/20210122181054.32635-4-eric.snowberg@oracle.com/ # v5 Link: https://lore.kernel.org/r/161428673564.677100.4112098280028451629.stgit@wart... Link: https://lore.kernel.org/r/161433312452.902181.4146169951896577982.stgit@wart... # v2 Link: https://lore.kernel.org/r/161529606657.163428.3340689182456495390.stgit@wart... # v3 Signed-off-by: Sasha Levin sashal@kernel.org --- certs/Kconfig | 8 ++++++++ certs/Makefile | 19 +++++++++++++++++-- certs/blacklist.c | 21 +++++++++++++++++++++ certs/revocation_certificates.S | 21 +++++++++++++++++++++ scripts/Makefile | 1 + 5 files changed, 68 insertions(+), 2 deletions(-) create mode 100644 certs/revocation_certificates.S

diff --git a/certs/Kconfig b/certs/Kconfig index 76e469b56a77..ab88d2a7f3c7 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -92,4 +92,12 @@ config SYSTEM_REVOCATION_LIST blacklist keyring and implements a hook whereby a PKCS#7 message can be checked to see if it matches such a certificate.

+config SYSTEM_REVOCATION_KEYS + string "X.509 certificates to be preloaded into the system blacklist keyring" + depends on SYSTEM_REVOCATION_LIST + help + If set, this option should be the filename of a PEM-formatted file + containing X.509 certificates to be included in the default blacklist + keyring. + endmenu diff --git a/certs/Makefile b/certs/Makefile index f4b90bad8690..b6db52ebf0be 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -4,7 +4,8 @@ #

obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o -obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o +obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o +obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),"") obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o else @@ -29,7 +30,7 @@ $(obj)/x509_certificate_list: scripts/extract-cert $(SYSTEM_TRUSTED_KEYS_SRCPREF $(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS)) endif # CONFIG_SYSTEM_TRUSTED_KEYRING

-clean-files := x509_certificate_list .x509.list +clean-files := x509_certificate_list .x509.list x509_revocation_list

ifeq ($(CONFIG_MODULE_SIG),y) ############################################################################### @@ -104,3 +105,17 @@ targets += signing_key.x509 $(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE $(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY)) endif # CONFIG_MODULE_SIG + +ifeq ($(CONFIG_SYSTEM_REVOCATION_LIST),y) + +$(eval $(call config_filename,SYSTEM_REVOCATION_KEYS)) + +$(obj)/revocation_certificates.o: $(obj)/x509_revocation_list + +quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2)) + cmd_extract_certs = scripts/extract-cert $(2) $@ + +targets += x509_revocation_list +$(obj)/x509_revocation_list: scripts/extract-cert $(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(SYSTEM_REVOCATION_KEYS_FILENAME) FORCE + $(call if_changed,extract_certs,$(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_REVOCATION_KEYS)) +endif diff --git a/certs/blacklist.c b/certs/blacklist.c index 2b8644123d5f..c9a435b15af4 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -17,9 +17,15 @@ #include <linux/uidgid.h> #include <keys/system_keyring.h> #include "blacklist.h" +#include "common.h"

static struct key *blacklist_keyring;

+#ifdef CONFIG_SYSTEM_REVOCATION_LIST +extern __initconst const u8 revocation_certificate_list[]; +extern __initconst const unsigned long revocation_certificate_list_size; +#endif + /* * The description must be a type prefix, a colon and then an even number of * hex digits. The hash is kept in the description. @@ -220,3 +226,18 @@ static int __init blacklist_init(void) * Must be initialised before we try and load the keys into the keyring. */ device_initcall(blacklist_init); + +#ifdef CONFIG_SYSTEM_REVOCATION_LIST +/* + * Load the compiled-in list of revocation X.509 certificates. + */ +static __init int load_revocation_certificate_list(void) +{ + if (revocation_certificate_list_size) + pr_notice("Loading compiled-in revocation X.509 certificates\n"); + + return load_certificate_list(revocation_certificate_list, revocation_certificate_list_size, + blacklist_keyring); +} +late_initcall(load_revocation_certificate_list); +#endif diff --git a/certs/revocation_certificates.S b/certs/revocation_certificates.S new file mode 100644 index 000000000000..f21aae8a8f0e --- /dev/null +++ b/certs/revocation_certificates.S @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> +#include <linux/init.h> + + __INITRODATA + + .align 8 + .globl revocation_certificate_list +revocation_certificate_list: +__revocation_list_start: + .incbin "certs/x509_revocation_list" +__revocation_list_end: + + .align 8 + .globl revocation_certificate_list_size +revocation_certificate_list_size: +#ifdef CONFIG_64BIT + .quad __revocation_list_end - __revocation_list_start +#else + .long __revocation_list_end - __revocation_list_start +#endif diff --git a/scripts/Makefile b/scripts/Makefile index c36106bce80e..9adb6d247818 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -14,6 +14,7 @@ hostprogs-always-$(CONFIG_ASN1) += asn1_compiler hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file hostprogs-always-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert +hostprogs-always-$(CONFIG_SYSTEM_REVOCATION_LIST) += extract-cert

HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include

Signed-off-by: Sasha Levin sashal@kernel.org --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile index d2fe36db78ae..a4b63b0f262b 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 12 -SUBLEVEL = 13 -EXTRAVERSION = +SUBLEVEL = 14 +EXTRAVERSION = -rc1 NAME = Frozen Wasteland

# *DOCUMENTATION*