Merge tag 'v4.16-rc2' into x86/platform, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/ABI/testing/sysfs-devices-platform-dock

@@ -0,0 +1,39 @@
+What:		/sys/devices/platform/dock.N/docked
+Date:		Dec, 2006
+KernelVersion:	2.6.19
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Value 1 or 0 indicates whether the software believes the
+		laptop is docked in a docking station.
+
+What:		/sys/devices/platform/dock.N/undock
+Date:		Dec, 2006
+KernelVersion:	2.6.19
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(WO) Writing to this file causes the software to initiate an
+		undock request to the firmware.
+
+What:		/sys/devices/platform/dock.N/uid
+Date:		Feb, 2007
+KernelVersion:	v2.6.21
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Displays the docking station the laptop is docked to.
+
+What:		/sys/devices/platform/dock.N/flags
+Date:		May, 2007
+KernelVersion:	v2.6.21
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Show dock station flags, useful for checking if undock
+		request has been made by the user (from the immediate_undock
+		option).
+
+What:		/sys/devices/platform/dock.N/type
+Date:		Aug, 2008
+KernelVersion:	v2.6.27
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Display the dock station type- dock_station, ata_bay or
+		battery_bay.

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -108,6 +108,8 @@ Description:	CPU topology files that describe a logical CPU's relationship
 
 What:		/sys/devices/system/cpu/cpuidle/current_driver
 		/sys/devices/system/cpu/cpuidle/current_governer_ro
+		/sys/devices/system/cpu/cpuidle/available_governors
+		/sys/devices/system/cpu/cpuidle/current_governor
 Date:		September 2007
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Discover cpuidle policy and mechanism
@@ -119,13 +121,84 @@ Description:	Discover cpuidle policy and mechanism
 		Idle policy (governor) is differentiated from idle mechanism
 		(driver)
 
-		current_driver: displays current idle mechanism
+		current_driver: (RO) displays current idle mechanism
 
-		current_governor_ro: displays current idle policy
+		current_governor_ro: (RO) displays current idle policy
+
+		With the cpuidle_sysfs_switch boot option enabled (meant for
+		developer testing), the following three attributes are visible
+		instead:
+
+		current_driver: same as described above
+
+		available_governors: (RO) displays a space separated list of
+		available governors
+
+		current_governor: (RW) displays current idle policy. Users can
+		switch the governor at runtime by writing to this file.
 
 		See files in Documentation/cpuidle/ for more information.
 
 
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/name
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/latency
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/power
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/time
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/usage
+Date:		September 2007
+KernelVersion:	v2.6.24
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		The directory /sys/devices/system/cpu/cpuX/cpuidle contains per
+		logical CPU specific cpuidle information for each online cpu X.
+		The processor idle states which are available for use have the
+		following attributes:
+
+		name: (RO) Name of the idle state (string).
+
+		latency: (RO) The latency to exit out of this idle state (in
+		microseconds).
+
+		power: (RO) The power consumed while in this idle state (in
+		milliwatts).
+
+		time: (RO) The total time spent in this idle state (in microseconds).
+
+		usage: (RO) Number of times this state was entered (a count).
+
+
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/desc
+Date:		February 2008
+KernelVersion:	v2.6.25
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RO) A small description about the idle state (string).
+
+
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/disable
+Date:		March 2012
+KernelVersion:	v3.10
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RW) Option to disable this idle state (bool). The behavior and
+		the effect of the disable variable depends on the implementation
+		of a particular governor. In the ladder governor, for example,
+		it is not coherent, i.e. if one is disabling a light state, then
+		all deeper states are disabled as well, but the disable variable
+		does not reflect it. Likewise, if one enables a deep state but a
+		lighter state still is disabled, then this has no effect.
+
+
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/residency
+Date:		March 2014
+KernelVersion:	v3.15
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RO) Display the target residency i.e. the minimum amount of
+		time (in microseconds) this cpu should spend in this idle state
+		to make the transition worth the effort.
+
+
 What:		/sys/devices/system/cpu/cpu#/cpufreq/*
 Date:		pre-git history
 Contact:	linux-pm@vger.kernel.org

Documentation/ABI/testing/sysfs-platform-dptf

@@ -0,0 +1,40 @@
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/charger_type
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) The charger type - Traditional, Hybrid or NVDC.
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/adapter_rating_mw
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Adapter rating in milliwatts (the maximum Adapter power).
+		Must be 0 if no AC Adaptor is plugged in.
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/max_platform_power_mw
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Maximum platform power that can be supported by the battery
+		in milliwatts.
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/platform_power_source
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Display the platform power source
+		0x00 = DC
+		0x01 = AC
+		0x02 = USB
+		0x03 = Wireless Charger
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/battery_steady_power
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) The maximum sustained power for battery in milliwatts.

Documentation/atomic_bitops.txt

@@ -58,7 +58,12 @@ Like with atomic_t, the rule of thumb is:
 
  - RMW operations that have a return value are fully ordered.
 
-Except for test_and_set_bit_lock() which has ACQUIRE semantics and
+ - RMW operations that are conditional are unordered on FAILURE,
+   otherwise the above rules apply. In the case of test_and_{}_bit() operations,
+   if the bit in memory is unchanged by the operation then it is deemed to have
+   failed.
+
+Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and
 clear_bit_unlock() which has RELEASE semantics.
 
 Since a platform only has a single means of achieving atomic operations

Documentation/features/sched/membarrier-sync-core/arch-support.txt

@@ -0,0 +1,62 @@
+#
+# Feature name:          membarrier-sync-core
+#         Kconfig:       ARCH_HAS_MEMBARRIER_SYNC_CORE
+#         description:   arch supports core serializing membarrier
+#
+# Architecture requirements
+#
+# * arm64
+#
+# Rely on eret context synchronization when returning from IPI handler, and
+# when returning to user-space.
+#
+# * x86
+#
+# x86-32 uses IRET as return from interrupt, which takes care of the IPI.
+# However, it uses both IRET and SYSEXIT to go back to user-space. The IRET
+# instruction is core serializing, but not SYSEXIT.
+#
+# x86-64 uses IRET as return from interrupt, which takes care of the IPI.
+# However, it can return to user-space through either SYSRETL (compat code),
+# SYSRETQ, or IRET.
+#
+# Given that neither SYSRET{L,Q}, nor SYSEXIT, are core serializing, we rely
+# instead on write_cr3() performed by switch_mm() to provide core serialization
+# after changing the current mm, and deal with the special case of kthread ->
+# uthread (temporarily keeping current mm into active_mm) by issuing a
+# sync_core_before_usermode() in that specific case.
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: |  ok  |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------

Documentation/locking/mutex-design.txt

@@ -21,37 +21,23 @@ Implementation
 --------------
 
 Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h
-and implemented in kernel/locking/mutex.c. These locks use a three
-state atomic counter (->count) to represent the different possible
-transitions that can occur during the lifetime of a lock:
-
-	  1: unlocked
-	  0: locked, no waiters
-   negative: locked, with potential waiters
-
-In its most basic form it also includes a wait-queue and a spinlock
-that serializes access to it. CONFIG_SMP systems can also include
-a pointer to the lock task owner (->owner) as well as a spinner MCS
-lock (->osq), both described below in (ii).
+and implemented in kernel/locking/mutex.c. These locks use an atomic variable
+(->owner) to keep track of the lock state during its lifetime.  Field owner
+actually contains 'struct task_struct *' to the current lock owner and it is
+therefore NULL if not currently owned. Since task_struct pointers are aligned
+at at least L1_CACHE_BYTES, low bits (3) are used to store extra state (e.g.,
+if waiter list is non-empty).  In its most basic form it also includes a
+wait-queue and a spinlock that serializes access to it. Furthermore,
+CONFIG_MUTEX_SPIN_ON_OWNER=y systems use a spinner MCS lock (->osq), described
+below in (ii).
 
 When acquiring a mutex, there are three possible paths that can be
 taken, depending on the state of the lock:
 
-(i) fastpath: tries to atomically acquire the lock by decrementing the
-    counter. If it was already taken by another task it goes to the next
-    possible path. This logic is architecture specific. On x86-64, the
-    locking fastpath is 2 instructions:
-
-    0000000000000e10 <mutex_lock>:
-    e21:   f0 ff 0b                lock decl (%rbx)
-    e24:   79 08                   jns    e2e <mutex_lock+0x1e>
-
-   the unlocking fastpath is equally tight:
-
-    0000000000000bc0 <mutex_unlock>:
-    bc8:   f0 ff 07                lock incl (%rdi)
-    bcb:   7f 0a                   jg     bd7 <mutex_unlock+0x17>
-
+(i) fastpath: tries to atomically acquire the lock by cmpxchg()ing the owner with
+    the current task. This only works in the uncontended case (cmpxchg() checks
+    against 0UL, so all 3 state bits above have to be 0). If the lock is
+    contended it goes to the next possible path.
 
 (ii) midpath: aka optimistic spinning, tries to spin for acquisition
      while the lock owner is running and there are no other tasks ready
@@ -143,11 +129,10 @@ Test if the mutex is taken:
 Disadvantages
 -------------
 
-Unlike its original design and purpose, 'struct mutex' is larger than
-most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice
-as large as 'struct semaphore' (24 bytes) and tied, along with rwsems,
-for the largest lock in the kernel. Larger structure sizes mean more
-CPU cache and memory footprint.
+Unlike its original design and purpose, 'struct mutex' is among the largest
+locks in the kernel. E.g: on x86-64 it is 32 bytes, where 'struct semaphore'
+is 24 bytes and rw_semaphore is 40 bytes. Larger structure sizes mean more CPU
+cache and memory footprint.
 
 When to use mutexes
 -------------------

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*

arch/arm64/include/asm/cputype.h

@@ -20,7 +20,7 @@
 
 #define MPIDR_UP_BITMASK	(0x1 << 30)
 #define MPIDR_MT_BITMASK	(0x1 << 24)
-#define MPIDR_HWID_BITMASK	0xff00ffffff
+#define MPIDR_HWID_BITMASK	0xff00ffffffUL
 
 #define MPIDR_LEVEL_BITS_SHIFT	3
 #define MPIDR_LEVEL_BITS	(1 << MPIDR_LEVEL_BITS_SHIFT)

arch/arm64/include/asm/hugetlb.h

@@ -22,7 +22,7 @@
 
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
-	return *ptep;
+	return READ_ONCE(*ptep);
 }
 
 

arch/arm64/include/asm/kvm_mmu.h

@@ -185,42 +185,42 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
 	return pmd;
 }
 
-static inline void kvm_set_s2pte_readonly(pte_t *pte)
+static inline void kvm_set_s2pte_readonly(pte_t *ptep)
 {
 	pteval_t old_pteval, pteval;
 
-	pteval = READ_ONCE(pte_val(*pte));
+	pteval = READ_ONCE(pte_val(*ptep));
 	do {
 		old_pteval = pteval;
 		pteval &= ~PTE_S2_RDWR;
 		pteval |= PTE_S2_RDONLY;
-		pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval);
+		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
 	} while (pteval != old_pteval);
 }
 
-static inline bool kvm_s2pte_readonly(pte_t *pte)
+static inline bool kvm_s2pte_readonly(pte_t *ptep)
 {
-	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
+	return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY;
 }
 
-static inline bool kvm_s2pte_exec(pte_t *pte)
+static inline bool kvm_s2pte_exec(pte_t *ptep)
 {
-	return !(pte_val(*pte) & PTE_S2_XN);
+	return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN);
 }
 
-static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
+static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp)
 {
-	kvm_set_s2pte_readonly((pte_t *)pmd);
+	kvm_set_s2pte_readonly((pte_t *)pmdp);
 }
 
-static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
+static inline bool kvm_s2pmd_readonly(pmd_t *pmdp)
 {
-	return kvm_s2pte_readonly((pte_t *)pmd);
+	return kvm_s2pte_readonly((pte_t *)pmdp);
 }
 
-static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
 {
-	return !(pmd_val(*pmd) & PMD_S2_XN);
+	return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
 }
 
 static inline bool kvm_page_empty(void *ptr)

arch/arm64/include/asm/mmu_context.h

@@ -141,13 +141,13 @@ static inline void cpu_install_idmap(void)
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.
  */
-static inline void cpu_replace_ttbr1(pgd_t *pgd)
+static inline void cpu_replace_ttbr1(pgd_t *pgdp)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
 	ttbr_replace_func *replace_phys;
 
-	phys_addr_t pgd_phys = virt_to_phys(pgd);
+	phys_addr_t pgd_phys = virt_to_phys(pgdp);
 
 	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 

arch/arm64/include/asm/pgalloc.h

@@ -36,23 +36,23 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 	return (pmd_t *)__get_free_page(PGALLOC_GFP);
 }
 
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
 {
-	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
-	free_page((unsigned long)pmd);
+	BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+	free_page((unsigned long)pmdp);
 }
 
-static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot)
+static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 {
-	set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot));
+	set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot));
 }
 
-static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
 {
-	__pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE);
+	__pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE);
 }
 #else
-static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot)
+static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 {
 	BUILD_BUG();
 }
@@ -65,30 +65,30 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 	return (pud_t *)__get_free_page(PGALLOC_GFP);
 }
 
-static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+static inline void pud_free(struct mm_struct *mm, pud_t *pudp)
 {
-	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	free_page((unsigned long)pud);
+	BUG_ON((unsigned long)pudp & (PAGE_SIZE-1));
+	free_page((unsigned long)pudp);
 }
 
-static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot)
+static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
 {
-	set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot));
+	set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot));
 }
 
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp)
 {
-	__pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE);
+	__pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE);
 }
 #else
-static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot)
+static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
 {
 	BUILD_BUG();
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp);
 
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
@@ -114,10 +114,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 /*
  * Free a PTE table.
  */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep)
 {
-	if (pte)
-		free_page((unsigned long)pte);
+	if (ptep)
+		free_page((unsigned long)ptep);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
@@ -126,10 +126,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 	__free_page(pte);
 }
 
-static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
+static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep,
 				  pmdval_t prot)
 {
-	set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot));
+	set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot));
 }
 
 /*

arch/arm64/include/asm/pgtable.h

@@ -218,7 +218,7 @@ static inline pmd_t pmd_mkcont(pmd_t pmd)
 
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
-	*ptep = pte;
+	WRITE_ONCE(*ptep, pte);
 
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
@@ -250,6 +250,8 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
+	pte_t old_pte;
+
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte, addr);
 
@@ -258,14 +260,15 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) &&
+	old_pte = READ_ONCE(*ptep);
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) &&
 	   (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) {
 		VM_WARN_ONCE(!pte_young(pte),
 			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
-			     __func__, pte_val(*ptep), pte_val(pte));
-		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     __func__, pte_val(old_pte), pte_val(pte));
+		VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
 			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
-			     __func__, pte_val(*ptep), pte_val(pte));
+			     __func__, pte_val(old_pte), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);
@@ -431,7 +434,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 	dsb(ishst);
 	isb();
 }
@@ -482,7 +485,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 	dsb(ishst);
 	isb();
 }
@@ -500,7 +503,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
 /* Find an entry in the second-level page table. */
 #define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 
-#define pmd_offset_phys(dir, addr)	(pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t))
+#define pmd_offset_phys(dir, addr)	(pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t))
 #define pmd_offset(dir, addr)		((pmd_t *)__va(pmd_offset_phys((dir), (addr))))
 
 #define pmd_set_fixmap(addr)		((pmd_t *)set_fixmap_offset(FIX_PMD, addr))
@@ -535,7 +538,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pgd;
+	WRITE_ONCE(*pgdp, pgd);
 	dsb(ishst);
 }
 
@@ -552,7 +555,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 /* Find an entry in the frst-level page table. */
 #define pud_index(addr)		(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
-#define pud_offset_phys(dir, addr)	(pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t))
+#define pud_offset_phys(dir, addr)	(pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
 #define pud_offset(dir, addr)		((pud_t *)__va(pud_offset_phys((dir), (addr))))
 
 #define pud_set_fixmap(addr)		((pud_t *)set_fixmap_offset(FIX_PUD, addr))

arch/arm64/kernel/cpu_errata.c

@@ -406,6 +406,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
 		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
 	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+		.enable = qcom_enable_link_stack_sanitization,
+	},
+	{
+		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+	},
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),

arch/arm64/kernel/efi.c

@@ -90,7 +90,7 @@ static int __init set_permissions(pte_t *ptep, pgtable_t token,
 				  unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = *ptep;
+	pte_t pte = READ_ONCE(*ptep);
 
 	if (md->attribute & EFI_MEMORY_RO)
 		pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));

arch/arm64/kernel/hibernate.c

@@ -202,10 +202,10 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 gfp_t mask)
 {
 	int rc = 0;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
 	unsigned long dst = (unsigned long)allocator(mask);
 
 	if (!dst) {
@@ -216,38 +216,38 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	memcpy((void *)dst, src_start, length);
 	flush_icache_range(dst, dst + length);
 
-	pgd = pgd_offset_raw(allocator(mask), dst_addr);
-	if (pgd_none(*pgd)) {
-		pud = allocator(mask);
-		if (!pud) {
+	pgdp = pgd_offset_raw(allocator(mask), dst_addr);
+	if (pgd_none(READ_ONCE(*pgdp))) {
+		pudp = allocator(mask);
+		if (!pudp) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		pgd_populate(&init_mm, pgd, pud);
+		pgd_populate(&init_mm, pgdp, pudp);
 	}
 
-	pud = pud_offset(pgd, dst_addr);
-	if (pud_none(*pud)) {
-		pmd = allocator(mask);
-		if (!pmd) {
+	pudp = pud_offset(pgdp, dst_addr);
+	if (pud_none(READ_ONCE(*pudp))) {
+		pmdp = allocator(mask);
+		if (!pmdp) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		pud_populate(&init_mm, pud, pmd);
+		pud_populate(&init_mm, pudp, pmdp);
 	}
 
-	pmd = pmd_offset(pud, dst_addr);
-	if (pmd_none(*pmd)) {
-		pte = allocator(mask);
-		if (!pte) {
+	pmdp = pmd_offset(pudp, dst_addr);
+	if (pmd_none(READ_ONCE(*pmdp))) {
+		ptep = allocator(mask);
+		if (!ptep) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		pmd_populate_kernel(&init_mm, pmd, pte);
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
 
-	pte = pte_offset_kernel(pmd, dst_addr);
-	set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
+	ptep = pte_offset_kernel(pmdp, dst_addr);
+	set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
 
 	/*
 	 * Load our new page tables. A strict BBM approach requires that we
@@ -263,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	 */
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1);
+	write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1);
 	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
@@ -320,9 +320,9 @@ int swsusp_arch_suspend(void)
 	return ret;
 }
 
-static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
+static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 {
-	pte_t pte = *src_pte;
+	pte_t pte = READ_ONCE(*src_ptep);
 
 	if (pte_valid(pte)) {
 		/*
@@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
 		 * read only (code, rodata). Clear the RDONLY bit from
 		 * the temporary mappings we use during restore.
 		 */
-		set_pte(dst_pte, pte_mkwrite(pte));
+		set_pte(dst_ptep, pte_mkwrite(pte));
 	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
 		/*
 		 * debug_pagealloc will removed the PTE_VALID bit if
@@ -343,112 +343,116 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
 		 */
 		BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-		set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte)));
+		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
 	}
 }
 
-static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
+static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
 		    unsigned long end)
 {
-	pte_t *src_pte;
-	pte_t *dst_pte;
+	pte_t *src_ptep;
+	pte_t *dst_ptep;
 	unsigned long addr = start;
 
-	dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_pte)
+	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
+	if (!dst_ptep)
 		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmd, dst_pte);
-	dst_pte = pte_offset_kernel(dst_pmd, start);
+	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
+	dst_ptep = pte_offset_kernel(dst_pmdp, start);
 
-	src_pte = pte_offset_kernel(src_pmd, start);
+	src_ptep = pte_offset_kernel(src_pmdp, start);
 	do {
-		_copy_pte(dst_pte, src_pte, addr);
-	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+		_copy_pte(dst_ptep, src_ptep, addr);
+	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
 
 	return 0;
 }
 
-static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start,
+static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
 		    unsigned long end)
 {
-	pmd_t *src_pmd;
-	pmd_t *dst_pmd;
+	pmd_t *src_pmdp;
+	pmd_t *dst_pmdp;
 	unsigned long next;
 	unsigned long addr = start;
 
-	if (pud_none(*dst_pud)) {
-		dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmd)
+	if (pud_none(READ_ONCE(*dst_pudp))) {
+		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pmdp)
 			return -ENOMEM;
-		pud_populate(&init_mm, dst_pud, dst_pmd);
+		pud_populate(&init_mm, dst_pudp, dst_pmdp);
 	}
-	dst_pmd = pmd_offset(dst_pud, start);
+	dst_pmdp = pmd_offset(dst_pudp, start);
 
-	src_pmd = pmd_offset(src_pud, start);
+	src_pmdp = pmd_offset(src_pudp, start);
 	do {
+		pmd_t pmd = READ_ONCE(*src_pmdp);
+
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*src_pmd))
+		if (pmd_none(pmd))
 			continue;
-		if (pmd_table(*src_pmd)) {
-			if (copy_pte(dst_pmd, src_pmd, addr, next))
+		if (pmd_table(pmd)) {
+			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
 				return -ENOMEM;
 		} else {
-			set_pmd(dst_pmd,
-				__pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY));
+			set_pmd(dst_pmdp,
+				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
 		}
-	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
+	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
 
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start,
+static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 		    unsigned long end)
 {
-	pud_t *dst_pud;
-	pud_t *src_pud;
+	pud_t *dst_pudp;
+	pud_t *src_pudp;
 	unsigned long next;
 	unsigned long addr = start;
 
-	if (pgd_none(*dst_pgd)) {
-		dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pud)
+	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pudp)
 			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgd, dst_pud);
+		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
 	}
-	dst_pud = pud_offset(dst_pgd, start);
+	dst_pudp = pud_offset(dst_pgdp, start);
 
-	src_pud = pud_offset(src_pgd, start);
+	src_pudp = pud_offset(src_pgdp, start);
 	do {
+		pud_t pud = READ_ONCE(*src_pudp);
+
 		next = pud_addr_end(addr, end);
-		if (pud_none(*src_pud))
+		if (pud_none(pud))
 			continue;
-		if (pud_table(*(src_pud))) {
-			if (copy_pmd(dst_pud, src_pud, addr, next))
+		if (pud_table(pud)) {
+			if (copy_pmd(dst_pudp, src_pudp, addr, next))
 				return -ENOMEM;
 		} else {
-			set_pud(dst_pud,
-				__pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY));
+			set_pud(dst_pudp,
+				__pud(pud_val(pud) & ~PMD_SECT_RDONLY));
 		}
-	} while (dst_pud++, src_pud++, addr = next, addr != end);
+	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
 
 	return 0;
 }
 
-static int copy_page_tables(pgd_t *dst_pgd, unsigned long start,
+static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 			    unsigned long end)
 {
 	unsigned long next;
 	unsigned long addr = start;
-	pgd_t *src_pgd = pgd_offset_k(start);
+	pgd_t *src_pgdp = pgd_offset_k(start);
 
-	dst_pgd = pgd_offset_raw(dst_pgd, start);
+	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
 	do {
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(*src_pgd))
+		if (pgd_none(READ_ONCE(*src_pgdp)))
 			continue;
-		if (copy_pud(dst_pgd, src_pgd, addr, next))
+		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
 			return -ENOMEM;
-	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
+	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
 
 	return 0;
 }

arch/arm64/kvm/hyp/switch.c

@@ -407,8 +407,10 @@ again:
 		u32 midr = read_cpuid_id();
 
 		/* Apply BTAC predictors mitigation to all Falkor chips */
-		if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)
+		if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
+		    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) {
 			__qcom_hyp_sanitize_btac_predictors();
+		}
 	}
 
 	fp_enabled = __fpsimd_enabled();

arch/arm64/mm/dump.c

@@ -286,48 +286,52 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 
 }
 
-static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
+static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start)
 {
-	pte_t *pte = pte_offset_kernel(pmd, 0UL);
+	pte_t *ptep = pte_offset_kernel(pmdp, 0UL);
 	unsigned long addr;
 	unsigned i;
 
-	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
+	for (i = 0; i < PTRS_PER_PTE; i++, ptep++) {
 		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte));
+		note_page(st, addr, 4, READ_ONCE(pte_val(*ptep)));
 	}
 }
 
-static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
+static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start)
 {
-	pmd_t *pmd = pmd_offset(pud, 0UL);
+	pmd_t *pmdp = pmd_offset(pudp, 0UL);
 	unsigned long addr;
 	unsigned i;
 
-	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
+	for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) {
+		pmd_t pmd = READ_ONCE(*pmdp);
+
 		addr = start + i * PMD_SIZE;
-		if (pmd_none(*pmd) || pmd_sect(*pmd)) {
-			note_page(st, addr, 3, pmd_val(*pmd));
+		if (pmd_none(pmd) || pmd_sect(pmd)) {
+			note_page(st, addr, 3, pmd_val(pmd));
 		} else {
-			BUG_ON(pmd_bad(*pmd));
-			walk_pte(st, pmd, addr);
+			BUG_ON(pmd_bad(pmd));
+			walk_pte(st, pmdp, addr);
 		}
 	}
 }
 
-static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
+static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start)
 {
-	pud_t *pud = pud_offset(pgd, 0UL);
+	pud_t *pudp = pud_offset(pgdp, 0UL);
 	unsigned long addr;
 	unsigned i;
 
-	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
+	for (i = 0; i < PTRS_PER_PUD; i++, pudp++) {
+		pud_t pud = READ_ONCE(*pudp);
+
 		addr = start + i * PUD_SIZE;
-		if (pud_none(*pud) || pud_sect(*pud)) {
-			note_page(st, addr, 2, pud_val(*pud));
+		if (pud_none(pud) || pud_sect(pud)) {
+			note_page(st, addr, 2, pud_val(pud));
 		} else {
-			BUG_ON(pud_bad(*pud));
-			walk_pmd(st, pud, addr);
+			BUG_ON(pud_bad(pud));
+			walk_pmd(st, pudp, addr);
 		}
 	}
 }
@@ -335,17 +339,19 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
 		     unsigned long start)
 {
-	pgd_t *pgd = pgd_offset(mm, 0UL);
+	pgd_t *pgdp = pgd_offset(mm, 0UL);
 	unsigned i;
 	unsigned long addr;
 
-	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
+	for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) {
+		pgd_t pgd = READ_ONCE(*pgdp);
+
 		addr = start + i * PGDIR_SIZE;
-		if (pgd_none(*pgd)) {
-			note_page(st, addr, 1, pgd_val(*pgd));
+		if (pgd_none(pgd)) {
+			note_page(st, addr, 1, pgd_val(pgd));
 		} else {
-			BUG_ON(pgd_bad(*pgd));
-			walk_pud(st, pgd, addr);
+			BUG_ON(pgd_bad(pgd));
+			walk_pud(st, pgdp, addr);
 		}
 	}
 }

arch/arm64/mm/fault.c

@@ -130,7 +130,8 @@ static void mem_abort_decode(unsigned int esr)
 void show_pte(unsigned long addr)
 {
 	struct mm_struct *mm;
-	pgd_t *pgd;
+	pgd_t *pgdp;
+	pgd_t pgd;
 
 	if (addr < TASK_SIZE) {
 		/* TTBR0 */
@@ -149,33 +150,37 @@ void show_pte(unsigned long addr)
 		return;
 	}
 
-	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n",
+	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n",
 		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
 		 VA_BITS, mm->pgd);
-	pgd = pgd_offset(mm, addr);
-	pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd));
+	pgdp = pgd_offset(mm, addr);
+	pgd = READ_ONCE(*pgdp);
+	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
 
 	do {
-		pud_t *pud;
-		pmd_t *pmd;
-		pte_t *pte;
+		pud_t *pudp, pud;
+		pmd_t *pmdp, pmd;
+		pte_t *ptep, pte;
 
-		if (pgd_none(*pgd) || pgd_bad(*pgd))
+		if (pgd_none(pgd) || pgd_bad(pgd))
 			break;
 
-		pud = pud_offset(pgd, addr);
-		pr_cont(", *pud=%016llx", pud_val(*pud));
-		if (pud_none(*pud) || pud_bad(*pud))
+		pudp = pud_offset(pgdp, addr);
+		pud = READ_ONCE(*pudp);
+		pr_cont(", pud=%016llx", pud_val(pud));
+		if (pud_none(pud) || pud_bad(pud))
 			break;
 
-		pmd = pmd_offset(pud, addr);
-		pr_cont(", *pmd=%016llx", pmd_val(*pmd));
-		if (pmd_none(*pmd) || pmd_bad(*pmd))
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		pr_cont(", pmd=%016llx", pmd_val(pmd));
+		if (pmd_none(pmd) || pmd_bad(pmd))
 			break;
 
-		pte = pte_offset_map(pmd, addr);
-		pr_cont(", *pte=%016llx", pte_val(*pte));
-		pte_unmap(pte);
+		ptep = pte_offset_map(pmdp, addr);
+		pte = READ_ONCE(*ptep);
+		pr_cont(", pte=%016llx", pte_val(pte));
+		pte_unmap(ptep);
 	} while(0);
 
 	pr_cont("\n");
@@ -196,8 +201,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  pte_t entry, int dirty)
 {
 	pteval_t old_pteval, pteval;
+	pte_t pte = READ_ONCE(*ptep);
 
-	if (pte_same(*ptep, entry))
+	if (pte_same(pte, entry))
 		return 0;
 
 	/* only preserve the access flags and write permission */
@@ -210,7 +216,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
 	pte_val(entry) ^= PTE_RDONLY;
-	pteval = READ_ONCE(pte_val(*ptep));
+	pteval = pte_val(pte);
 	do {
 		old_pteval = pteval;
 		pteval ^= PTE_RDONLY;

arch/arm64/mm/hugetlbpage.c

@@ -54,14 +54,14 @@ static inline pgprot_t pte_pgprot(pte_t pte)
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
-	pgd_t *pgd = pgd_offset(mm, addr);
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp = pgd_offset(mm, addr);
+	pud_t *pudp;
+	pmd_t *pmdp;
 
 	*pgsize = PAGE_SIZE;
-	pud = pud_offset(pgd, addr);
-	pmd = pmd_offset(pud, addr);
-	if ((pte_t *)pmd == ptep) {
+	pudp = pud_offset(pgdp, addr);
+	pmdp = pmd_offset(pudp, addr);
+	if ((pte_t *)pmdp == ptep) {
 		*pgsize = PMD_SIZE;
 		return CONT_PMDS;
 	}
@@ -181,11 +181,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	clear_flush(mm, addr, ptep, pgsize, ncontig);
 
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
-		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
-			 pte_val(pfn_pte(pfn, hugeprot)));
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
 		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-	}
 }
 
 void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -203,20 +200,20 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 		      unsigned long addr, unsigned long sz)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pte_t *pte = NULL;
-
-	pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz);
-	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (!pud)
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep = NULL;
+
+	pgdp = pgd_offset(mm, addr);
+	pudp = pud_alloc(mm, pgdp, addr);
+	if (!pudp)
 		return NULL;
 
 	if (sz == PUD_SIZE) {
-		pte = (pte_t *)pud;
+		ptep = (pte_t *)pudp;
 	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
-		pmd_t *pmd = pmd_alloc(mm, pud, addr);
+		pmdp = pmd_alloc(mm, pudp, addr);
 
 		WARN_ON(addr & (sz - 1));
 		/*
@@ -226,60 +223,55 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		 * will be no pte_unmap() to correspond with this
 		 * pte_alloc_map().
 		 */
-		pte = pte_alloc_map(mm, pmd, addr);
+		ptep = pte_alloc_map(mm, pmdp, addr);
 	} else if (sz == PMD_SIZE) {
 		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
-		    pud_none(*pud))
-			pte = huge_pmd_share(mm, addr, pud);
+		    pud_none(READ_ONCE(*pudp)))
+			ptep = huge_pmd_share(mm, addr, pudp);
 		else
-			pte = (pte_t *)pmd_alloc(mm, pud, addr);
+			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
 	} else if (sz == (PMD_SIZE * CONT_PMDS)) {
-		pmd_t *pmd;
-
-		pmd = pmd_alloc(mm, pud, addr);
+		pmdp = pmd_alloc(mm, pudp, addr);
 		WARN_ON(addr & (sz - 1));
-		return (pte_t *)pmd;
+		return (pte_t *)pmdp;
 	}
 
-	pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr,
-	       sz, pte, pte_val(*pte));
-	return pte;
+	return ptep;
 }
 
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
 
-	pgd = pgd_offset(mm, addr);
-	pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
-	if (!pgd_present(*pgd))
+	pgdp = pgd_offset(mm, addr);
+	if (!pgd_present(READ_ONCE(*pgdp)))
 		return NULL;
 
-	pud = pud_offset(pgd, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pudp = pud_offset(pgdp, addr);
+	pud = READ_ONCE(*pudp);
+	if (sz != PUD_SIZE && pud_none(pud))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
-		return (pte_t *)pud;
+	if (pud_huge(pud) || !pud_present(pud))
+		return (pte_t *)pudp;
 	/* table; check the next level */
 
 	if (sz == CONT_PMD_SIZE)
 		addr &= CONT_PMD_MASK;
 
-	pmd = pmd_offset(pud, addr);
+	pmdp = pmd_offset(pudp, addr);
+	pmd = READ_ONCE(*pmdp);
 	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
-	    pmd_none(*pmd))
+	    pmd_none(pmd))
 		return NULL;
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
-		return (pte_t *)pmd;
+	if (pmd_huge(pmd) || !pmd_present(pmd))
+		return (pte_t *)pmdp;
 
-	if (sz == CONT_PTE_SIZE) {
-		pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
-		return pte;
-	}
+	if (sz == CONT_PTE_SIZE)
+		return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));
 
 	return NULL;
 }
@@ -367,7 +359,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	size_t pgsize;
 	pte_t pte;
 
-	if (!pte_cont(*ptep)) {
+	if (!pte_cont(READ_ONCE(*ptep))) {
 		ptep_set_wrprotect(mm, addr, ptep);
 		return;
 	}
@@ -391,7 +383,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	size_t pgsize;
 	int ncontig;
 
-	if (!pte_cont(*ptep)) {
+	if (!pte_cont(READ_ONCE(*ptep))) {
 		ptep_clear_flush(vma, addr, ptep);
 		return;
 	}

arch/arm64/mm/kasan_init.c

@@ -44,92 +44,92 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node)
 	return __pa(p);
 }
 
-static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node,
+static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pmd_none(*pmd)) {
+	if (pmd_none(READ_ONCE(*pmdp))) {
 		phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte)
 					     : kasan_alloc_zeroed_page(node);
-		__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
+		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pte_offset_kimg(pmd, addr)
-		     : pte_offset_kernel(pmd, addr);
+	return early ? pte_offset_kimg(pmdp, addr)
+		     : pte_offset_kernel(pmdp, addr);
 }
 
-static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node,
+static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pud_none(*pud)) {
+	if (pud_none(READ_ONCE(*pudp))) {
 		phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd)
 					     : kasan_alloc_zeroed_page(node);
-		__pud_populate(pud, pmd_phys, PMD_TYPE_TABLE);
+		__pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr);
+	return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr);
 }
 
-static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node,
+static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pgd_none(*pgd)) {
+	if (pgd_none(READ_ONCE(*pgdp))) {
 		phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud)
 					     : kasan_alloc_zeroed_page(node);
-		__pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE);
+		__pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr);
+	return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr);
 }
 
-static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr,
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pte_t *pte = kasan_pte_offset(pmd, addr, node, early);
+	pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early);
 
 	do {
 		phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page)
 					      : kasan_alloc_zeroed_page(node);
 		next = addr + PAGE_SIZE;
-		set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (pte++, addr = next, addr != end && pte_none(*pte));
+		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+	} while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep)));
 }
 
-static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr,
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early);
+	pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early);
 
 	do {
 		next = pmd_addr_end(addr, end);
-		kasan_pte_populate(pmd, addr, next, node, early);
-	} while (pmd++, addr = next, addr != end && pmd_none(*pmd));
+		kasan_pte_populate(pmdp, addr, next, node, early);
+	} while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp)));
 }
 
-static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr,
+static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pud_t *pud = kasan_pud_offset(pgd, addr, node, early);
+	pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early);
 
 	do {
 		next = pud_addr_end(addr, end);
-		kasan_pmd_populate(pud, addr, next, node, early);
-	} while (pud++, addr = next, addr != end && pud_none(*pud));
+		kasan_pmd_populate(pudp, addr, next, node, early);
+	} while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp)));
 }
 
 static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
 				      int node, bool early)
 {
 	unsigned long next;
-	pgd_t *pgd;
+	pgd_t *pgdp;
 
-	pgd = pgd_offset_k(addr);
+	pgdp = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		kasan_pud_populate(pgd, addr, next, node, early);
-	} while (pgd++, addr = next, addr != end);
+		kasan_pud_populate(pgdp, addr, next, node, early);
+	} while (pgdp++, addr = next, addr != end);
 }
 
 /* The early shadow maps everything to a single page of zeroes */
@@ -155,14 +155,14 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end,
  */
 void __init kasan_copy_shadow(pgd_t *pgdir)
 {
-	pgd_t *pgd, *pgd_new, *pgd_end;
+	pgd_t *pgdp, *pgdp_new, *pgdp_end;
 
-	pgd = pgd_offset_k(KASAN_SHADOW_START);
-	pgd_end = pgd_offset_k(KASAN_SHADOW_END);
-	pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START);
+	pgdp = pgd_offset_k(KASAN_SHADOW_START);
+	pgdp_end = pgd_offset_k(KASAN_SHADOW_END);
+	pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START);
 	do {
-		set_pgd(pgd_new, *pgd);
-	} while (pgd++, pgd_new++, pgd != pgd_end);
+		set_pgd(pgdp_new, READ_ONCE(*pgdp));
+	} while (pgdp++, pgdp_new++, pgdp != pgdp_end);
 }
 
 static void __init clear_pgds(unsigned long start,

arch/arm64/mm/mmu.c

@@ -125,45 +125,48 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	return ((old ^ new) & ~mask) == 0;
 }
 
-static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end,
+static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot)
 {
-	pte_t *pte;
+	pte_t *ptep;
 
-	pte = pte_set_fixmap_offset(pmd, addr);
+	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
-		pte_t old_pte = *pte;
+		pte_t old_pte = READ_ONCE(*ptep);
 
-		set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot));
+		set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
 		 * only allow updates to the permission attributes.
 		 */
-		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte)));
+		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
+					      READ_ONCE(pte_val(*ptep))));
 
 		phys += PAGE_SIZE;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
 
 	pte_clear_fixmap();
 }
 
-static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr,
+static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
 				phys_addr_t (*pgtable_alloc)(void),
 				int flags)
 {
 	unsigned long next;
+	pmd_t pmd = READ_ONCE(*pmdp);
 
-	BUG_ON(pmd_sect(*pmd));
-	if (pmd_none(*pmd)) {
+	BUG_ON(pmd_sect(pmd));
+	if (pmd_none(pmd)) {
 		phys_addr_t pte_phys;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc();
-		__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
+		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+		pmd = READ_ONCE(*pmdp);
 	}
-	BUG_ON(pmd_bad(*pmd));
+	BUG_ON(pmd_bad(pmd));
 
 	do {
 		pgprot_t __prot = prot;
@@ -175,67 +178,69 @@ static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pte(pmd, addr, next, phys, __prot);
+		init_pte(pmdp, addr, next, phys, __prot);
 
 		phys += next - addr;
 	} while (addr = next, addr != end);
 }
 
-static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
+static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
 		     phys_addr_t (*pgtable_alloc)(void), int flags)
 {
 	unsigned long next;
-	pmd_t *pmd;
+	pmd_t *pmdp;
 
-	pmd = pmd_set_fixmap_offset(pud, addr);
+	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
-		pmd_t old_pmd = *pmd;
+		pmd_t old_pmd = READ_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
 
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
-			pmd_set_huge(pmd, phys, prot);
+			pmd_set_huge(pmdp, phys, prot);
 
 			/*
 			 * After the PMD entry has been populated once, we
 			 * only allow updates to the permission attributes.
 			 */
 			BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
-						      pmd_val(*pmd)));
+						      READ_ONCE(pmd_val(*pmdp))));
 		} else {
-			alloc_init_cont_pte(pmd, addr, next, phys, prot,
+			alloc_init_cont_pte(pmdp, addr, next, phys, prot,
 					    pgtable_alloc, flags);
 
 			BUG_ON(pmd_val(old_pmd) != 0 &&
-			       pmd_val(old_pmd) != pmd_val(*pmd));
+			       pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
 		}
 		phys += next - addr;
-	} while (pmd++, addr = next, addr != end);
+	} while (pmdp++, addr = next, addr != end);
 
 	pmd_clear_fixmap();
 }
 
-static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr,
+static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
 				phys_addr_t (*pgtable_alloc)(void), int flags)
 {
 	unsigned long next;
+	pud_t pud = READ_ONCE(*pudp);
 
 	/*
 	 * Check for initial section mappings in the pgd/pud.
 	 */
-	BUG_ON(pud_sect(*pud));
-	if (pud_none(*pud)) {
+	BUG_ON(pud_sect(pud));
+	if (pud_none(pud)) {
 		phys_addr_t pmd_phys;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc();
-		__pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
+		__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+		pud = READ_ONCE(*pudp);
 	}
-	BUG_ON(pud_bad(*pud));
+	BUG_ON(pud_bad(pud));
 
 	do {
 		pgprot_t __prot = prot;
@@ -247,7 +252,7 @@ static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags);
+		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
 
 		phys += next - addr;
 	} while (addr = next, addr != end);
@@ -265,25 +270,27 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
 	return true;
 }
 
-static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
-				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void),
-				  int flags)
+static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
+			   phys_addr_t phys, pgprot_t prot,
+			   phys_addr_t (*pgtable_alloc)(void),
+			   int flags)
 {
-	pud_t *pud;
 	unsigned long next;
+	pud_t *pudp;
+	pgd_t pgd = READ_ONCE(*pgdp);
 
-	if (pgd_none(*pgd)) {
+	if (pgd_none(pgd)) {
 		phys_addr_t pud_phys;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc();
-		__pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE);
+		__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
+		pgd = READ_ONCE(*pgdp);
 	}
-	BUG_ON(pgd_bad(*pgd));
+	BUG_ON(pgd_bad(pgd));
 
-	pud = pud_set_fixmap_offset(pgd, addr);
+	pudp = pud_set_fixmap_offset(pgdp, addr);
 	do {
-		pud_t old_pud = *pud;
+		pud_t old_pud = READ_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 
@@ -292,23 +299,23 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 		 */
 		if (use_1G_block(addr, next, phys) &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
-			pud_set_huge(pud, phys, prot);
+			pud_set_huge(pudp, phys, prot);
 
 			/*
 			 * After the PUD entry has been populated once, we
 			 * only allow updates to the permission attributes.
 			 */
 			BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
-						      pud_val(*pud)));
+						      READ_ONCE(pud_val(*pudp))));
 		} else {
-			alloc_init_cont_pmd(pud, addr, next, phys, prot,
+			alloc_init_cont_pmd(pudp, addr, next, phys, prot,
 					    pgtable_alloc, flags);
 
 			BUG_ON(pud_val(old_pud) != 0 &&
-			       pud_val(old_pud) != pud_val(*pud));
+			       pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
 		}
 		phys += next - addr;
-	} while (pud++, addr = next, addr != end);
+	} while (pudp++, addr = next, addr != end);
 
 	pud_clear_fixmap();
 }
@@ -320,7 +327,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 int flags)
 {
 	unsigned long addr, length, end, next;
-	pgd_t *pgd = pgd_offset_raw(pgdir, virt);
+	pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
 
 	/*
 	 * If the virtual and physical address don't have the same offset
@@ -336,10 +343,10 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
+		alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
 			       flags);
 		phys += next - addr;
-	} while (pgd++, addr = next, addr != end);
+	} while (pgdp++, addr = next, addr != end);
 }
 
 static phys_addr_t pgd_pgtable_alloc(void)
@@ -401,10 +408,10 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
 	flush_tlb_kernel_range(virt, virt + size);
 }
 
-static void __init __map_memblock(pgd_t *pgd, phys_addr_t start,
+static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start,
 				  phys_addr_t end, pgprot_t prot, int flags)
 {
-	__create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start,
+	__create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start,
 			     prot, early_pgtable_alloc, flags);
 }
 
@@ -418,7 +425,7 @@ void __init mark_linear_text_alias_ro(void)
 			    PAGE_KERNEL_RO);
 }
 
-static void __init map_mem(pgd_t *pgd)
+static void __init map_mem(pgd_t *pgdp)
 {
 	phys_addr_t kernel_start = __pa_symbol(_text);
 	phys_addr_t kernel_end = __pa_symbol(__init_begin);
@@ -451,7 +458,7 @@ static void __init map_mem(pgd_t *pgd)
 		if (memblock_is_nomap(reg))
 			continue;
 
-		__map_memblock(pgd, start, end, PAGE_KERNEL, flags);
+		__map_memblock(pgdp, start, end, PAGE_KERNEL, flags);
 	}
 
 	/*
@@ -464,7 +471,7 @@ static void __init map_mem(pgd_t *pgd)
 	 * Note that contiguous mappings cannot be remapped in this way,
 	 * so we should avoid them here.
 	 */
-	__map_memblock(pgd, kernel_start, kernel_end,
+	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
 
@@ -475,7 +482,7 @@ static void __init map_mem(pgd_t *pgd)
 	 * through /sys/kernel/kexec_crash_size interface.
 	 */
 	if (crashk_res.end) {
-		__map_memblock(pgd, crashk_res.start, crashk_res.end + 1,
+		__map_memblock(pgdp, crashk_res.start, crashk_res.end + 1,
 			       PAGE_KERNEL,
 			       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
 		memblock_clear_nomap(crashk_res.start,
@@ -499,7 +506,7 @@ void mark_rodata_ro(void)
 	debug_checkwx();
 }
 
-static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
+static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma,
 				      int flags, unsigned long vm_flags)
 {
@@ -509,7 +516,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	BUG_ON(!PAGE_ALIGNED(pa_start));
 	BUG_ON(!PAGE_ALIGNED(size));
 
-	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
+	__create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot,
 			     early_pgtable_alloc, flags);
 
 	if (!(vm_flags & VM_NO_GUARD))
@@ -562,7 +569,7 @@ core_initcall(map_entry_trampoline);
 /*
  * Create fine-grained mappings for the kernel.
  */
-static void __init map_kernel(pgd_t *pgd)
+static void __init map_kernel(pgd_t *pgdp)
 {
 	static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext,
 				vmlinux_initdata, vmlinux_data;
@@ -578,24 +585,24 @@ static void __init map_kernel(pgd_t *pgd)
 	 * Only rodata will be remapped with different permissions later on,
 	 * all other segments are allowed to use contiguous mappings.
 	 */
-	map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0,
+	map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0,
 			   VM_NO_GUARD);
-	map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
+	map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL,
 			   &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
-	map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
+	map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot,
 			   &vmlinux_inittext, 0, VM_NO_GUARD);
-	map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
+	map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL,
 			   &vmlinux_initdata, 0, VM_NO_GUARD);
-	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
+	map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
 
-	if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
+	if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) {
 		/*
 		 * The fixmap falls in a separate pgd to the kernel, and doesn't
 		 * live in the carveout for the swapper_pg_dir. We can simply
 		 * re-use the existing dir for the fixmap.
 		 */
-		set_pgd(pgd_offset_raw(pgd, FIXADDR_START),
-			*pgd_offset_k(FIXADDR_START));
+		set_pgd(pgd_offset_raw(pgdp, FIXADDR_START),
+			READ_ONCE(*pgd_offset_k(FIXADDR_START)));
 	} else if (CONFIG_PGTABLE_LEVELS > 3) {
 		/*
 		 * The fixmap shares its top level pgd entry with the kernel
@@ -604,14 +611,15 @@ static void __init map_kernel(pgd_t *pgd)
 		 * entry instead.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START),
+		pud_populate(&init_mm,
+			     pud_set_fixmap_offset(pgdp, FIXADDR_START),
 			     lm_alias(bm_pmd));
 		pud_clear_fixmap();
 	} else {
 		BUG();
 	}
 
-	kasan_copy_shadow(pgd);
+	kasan_copy_shadow(pgdp);
 }
 
 /*
@@ -621,10 +629,10 @@ static void __init map_kernel(pgd_t *pgd)
 void __init paging_init(void)
 {
 	phys_addr_t pgd_phys = early_pgtable_alloc();
-	pgd_t *pgd = pgd_set_fixmap(pgd_phys);
+	pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
 
-	map_kernel(pgd);
-	map_mem(pgd);
+	map_kernel(pgdp);
+	map_mem(pgdp);
 
 	/*
 	 * We want to reuse the original swapper_pg_dir so we don't have to
@@ -635,7 +643,7 @@ void __init paging_init(void)
 	 * To do this we need to go via a temporary pgd.
 	 */
 	cpu_replace_ttbr1(__va(pgd_phys));
-	memcpy(swapper_pg_dir, pgd, PGD_SIZE);
+	memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 
 	pgd_clear_fixmap();
@@ -655,37 +663,40 @@ void __init paging_init(void)
  */
 int kern_addr_valid(unsigned long addr)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgdp;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
 
 	if ((((long)addr) >> VA_BITS) != -1UL)
 		return 0;
 
-	pgd = pgd_offset_k(addr);
-	if (pgd_none(*pgd))
+	pgdp = pgd_offset_k(addr);
+	if (pgd_none(READ_ONCE(*pgdp)))
 		return 0;
 
-	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	pudp = pud_offset(pgdp, addr);
+	pud = READ_ONCE(*pudp);
+	if (pud_none(pud))
 		return 0;
 
-	if (pud_sect(*pud))
-		return pfn_valid(pud_pfn(*pud));
+	if (pud_sect(pud))
+		return pfn_valid(pud_pfn(pud));
 
-	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	pmdp = pmd_offset(pudp, addr);
+	pmd = READ_ONCE(*pmdp);
+	if (pmd_none(pmd))
 		return 0;
 
-	if (pmd_sect(*pmd))
-		return pfn_valid(pmd_pfn(*pmd));
+	if (pmd_sect(pmd))
+		return pfn_valid(pmd_pfn(pmd));
 
-	pte = pte_offset_kernel(pmd, addr);
-	if (pte_none(*pte))
+	ptep = pte_offset_kernel(pmdp, addr);
+	pte = READ_ONCE(*ptep);
+	if (pte_none(pte))
 		return 0;
 
-	return pfn_valid(pte_pfn(*pte));
+	return pfn_valid(pte_pfn(pte));
 }
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #if !ARM64_SWAPPER_USES_SECTION_MAPS
@@ -700,32 +711,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	unsigned long addr = start;
 	unsigned long next;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
 
 	do {
 		next = pmd_addr_end(addr, end);
 
-		pgd = vmemmap_pgd_populate(addr, node);
-		if (!pgd)
+		pgdp = vmemmap_pgd_populate(addr, node);
+		if (!pgdp)
 			return -ENOMEM;
 
-		pud = vmemmap_pud_populate(pgd, addr, node);
-		if (!pud)
+		pudp = vmemmap_pud_populate(pgdp, addr, node);
+		if (!pudp)
 			return -ENOMEM;
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
+		pmdp = pmd_offset(pudp, addr);
+		if (pmd_none(READ_ONCE(*pmdp))) {
 			void *p = NULL;
 
 			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
 			if (!p)
 				return -ENOMEM;
 
-			pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL));
+			pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
 		} else
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			vmemmap_verify((pte_t *)pmdp, node, addr, next);
 	} while (addr = next, addr != end);
 
 	return 0;
@@ -739,20 +750,22 @@ void vmemmap_free(unsigned long start, unsigned long end,
 
 static inline pud_t * fixmap_pud(unsigned long addr)
 {
-	pgd_t *pgd = pgd_offset_k(addr);
+	pgd_t *pgdp = pgd_offset_k(addr);
+	pgd_t pgd = READ_ONCE(*pgdp);
 
-	BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
+	BUG_ON(pgd_none(pgd) || pgd_bad(pgd));
 
-	return pud_offset_kimg(pgd, addr);
+	return pud_offset_kimg(pgdp, addr);
 }
 
 static inline pmd_t * fixmap_pmd(unsigned long addr)
 {
-	pud_t *pud = fixmap_pud(addr);
+	pud_t *pudp = fixmap_pud(addr);
+	pud_t pud = READ_ONCE(*pudp);
 
-	BUG_ON(pud_none(*pud) || pud_bad(*pud));
+	BUG_ON(pud_none(pud) || pud_bad(pud));
 
-	return pmd_offset_kimg(pud, addr);
+	return pmd_offset_kimg(pudp, addr);
 }
 
 static inline pte_t * fixmap_pte(unsigned long addr)
@@ -768,30 +781,31 @@ static inline pte_t * fixmap_pte(unsigned long addr)
  */
 void __init early_fixmap_init(void)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp, pgd;
+	pud_t *pudp;
+	pmd_t *pmdp;
 	unsigned long addr = FIXADDR_START;
 
-	pgd = pgd_offset_k(addr);
+	pgdp = pgd_offset_k(addr);
+	pgd = READ_ONCE(*pgdp);
 	if (CONFIG_PGTABLE_LEVELS > 3 &&
-	    !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) {
+	    !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) {
 		/*
 		 * We only end up here if the kernel mapping and the fixmap
 		 * share the top level pgd entry, which should only happen on
 		 * 16k/4 levels configurations.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pud = pud_offset_kimg(pgd, addr);
+		pudp = pud_offset_kimg(pgdp, addr);
 	} else {
-		if (pgd_none(*pgd))
-			__pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
-		pud = fixmap_pud(addr);
+		if (pgd_none(pgd))
+			__pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
+		pudp = fixmap_pud(addr);
 	}
-	if (pud_none(*pud))
-		__pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
-	pmd = fixmap_pmd(addr);
-	__pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
+	if (pud_none(READ_ONCE(*pudp)))
+		__pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
+	pmdp = fixmap_pmd(addr);
+	__pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
 
 	/*
 	 * The boot-ioremap range spans multiple pmds, for which
@@ -800,11 +814,11 @@ void __init early_fixmap_init(void)
 	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
 		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
 
-	if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
-	     || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+	if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
+	     || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
 		WARN_ON(1);
-		pr_warn("pmd %p != %p, %p\n",
-			pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
+		pr_warn("pmdp %p != %p, %p\n",
+			pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
 			fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
 		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
 			fix_to_virt(FIX_BTMAP_BEGIN));
@@ -824,16 +838,16 @@ void __set_fixmap(enum fixed_addresses idx,
 			       phys_addr_t phys, pgprot_t flags)
 {
 	unsigned long addr = __fix_to_virt(idx);
-	pte_t *pte;
+	pte_t *ptep;
 
 	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
 
-	pte = fixmap_pte(addr);
+	ptep = fixmap_pte(addr);
 
 	if (pgprot_val(flags)) {
-		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
+		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
 	} else {
-		pte_clear(&init_mm, addr, pte);
+		pte_clear(&init_mm, addr, ptep);
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
@@ -915,36 +929,36 @@ int __init arch_ioremap_pmd_supported(void)
 	return 1;
 }
 
-int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
+int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
 	BUG_ON(phys & ~PUD_MASK);
-	set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot));
+	set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot));
 	return 1;
 }
 
-int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
+int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
 	BUG_ON(phys & ~PMD_MASK);
-	set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot));
+	set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot));
 	return 1;
 }
 
-int pud_clear_huge(pud_t *pud)
+int pud_clear_huge(pud_t *pudp)
 {
-	if (!pud_sect(*pud))
+	if (!pud_sect(READ_ONCE(*pudp)))
 		return 0;
-	pud_clear(pud);
+	pud_clear(pudp);
 	return 1;
 }
 
-int pmd_clear_huge(pmd_t *pmd)
+int pmd_clear_huge(pmd_t *pmdp)
 {
-	if (!pmd_sect(*pmd))
+	if (!pmd_sect(READ_ONCE(*pmdp)))
 		return 0;
-	pmd_clear(pmd);
+	pmd_clear(pmdp);
 	return 1;
 }

arch/arm64/mm/pageattr.c

@@ -29,7 +29,7 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
 			void *data)
 {
 	struct page_change_data *cdata = data;
-	pte_t pte = *ptep;
+	pte_t pte = READ_ONCE(*ptep);
 
 	pte = clear_pte_bit(pte, cdata->clear_mask);
 	pte = set_pte_bit(pte, cdata->set_mask);
@@ -156,30 +156,32 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
  */
 bool kernel_page_present(struct page *page)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgdp;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep;
 	unsigned long addr = (unsigned long)page_address(page);
 
-	pgd = pgd_offset_k(addr);
-	if (pgd_none(*pgd))
+	pgdp = pgd_offset_k(addr);
+	if (pgd_none(READ_ONCE(*pgdp)))
 		return false;
 
-	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	pudp = pud_offset(pgdp, addr);
+	pud = READ_ONCE(*pudp);
+	if (pud_none(pud))
 		return false;
-	if (pud_sect(*pud))
+	if (pud_sect(pud))
 		return true;
 
-	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	pmdp = pmd_offset(pudp, addr);
+	pmd = READ_ONCE(*pmdp);
+	if (pmd_none(pmd))
 		return false;
-	if (pmd_sect(*pmd))
+	if (pmd_sect(pmd))
 		return true;
 
-	pte = pte_offset_kernel(pmd, addr);
-	return pte_valid(*pte);
+	ptep = pte_offset_kernel(pmdp, addr);
+	return pte_valid(READ_ONCE(*ptep));
 }
 #endif /* CONFIG_HIBERNATION */
 #endif /* CONFIG_DEBUG_PAGEALLOC */

arch/arm64/mm/proc.S

@@ -205,7 +205,8 @@ ENDPROC(idmap_cpu_replace_ttbr1)
 	dc	cvac, cur_\()\type\()p		// Ensure any existing dirty
 	dmb	sy				// lines are written back before
 	ldr	\type, [cur_\()\type\()p]	// loading the entry
-	tbz	\type, #0, next_\()\type	// Skip invalid entries
+	tbz	\type, #0, skip_\()\type	// Skip invalid and
+	tbnz	\type, #11, skip_\()\type	// non-global entries
 	.endm
 
 	.macro __idmap_kpti_put_pgtable_ent_ng, type
@@ -265,8 +266,9 @@ ENTRY(idmap_kpti_install_ng_mappings)
 	add	end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8)
 do_pgd:	__idmap_kpti_get_pgtable_ent	pgd
 	tbnz	pgd, #1, walk_puds
-	__idmap_kpti_put_pgtable_ent_ng	pgd
 next_pgd:
+	__idmap_kpti_put_pgtable_ent_ng	pgd
+skip_pgd:
 	add	cur_pgdp, cur_pgdp, #8
 	cmp	cur_pgdp, end_pgdp
 	b.ne	do_pgd
@@ -294,8 +296,9 @@ walk_puds:
 	add	end_pudp, cur_pudp, #(PTRS_PER_PUD * 8)
 do_pud:	__idmap_kpti_get_pgtable_ent	pud
 	tbnz	pud, #1, walk_pmds
-	__idmap_kpti_put_pgtable_ent_ng	pud
 next_pud:
+	__idmap_kpti_put_pgtable_ent_ng	pud
+skip_pud:
 	add	cur_pudp, cur_pudp, 8
 	cmp	cur_pudp, end_pudp
 	b.ne	do_pud
@@ -314,8 +317,9 @@ walk_pmds:
 	add	end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8)
 do_pmd:	__idmap_kpti_get_pgtable_ent	pmd
 	tbnz	pmd, #1, walk_ptes
-	__idmap_kpti_put_pgtable_ent_ng	pmd
 next_pmd:
+	__idmap_kpti_put_pgtable_ent_ng	pmd
+skip_pmd:
 	add	cur_pmdp, cur_pmdp, #8
 	cmp	cur_pmdp, end_pmdp
 	b.ne	do_pmd
@@ -333,7 +337,7 @@ walk_ptes:
 	add	end_ptep, cur_ptep, #(PTRS_PER_PTE * 8)
 do_pte:	__idmap_kpti_get_pgtable_ent	pte
 	__idmap_kpti_put_pgtable_ent_ng	pte
-next_pte:
+skip_pte:
 	add	cur_ptep, cur_ptep, #8
 	cmp	cur_ptep, end_ptep
 	b.ne	do_pte

arch/ia64/kernel/Makefile

@@ -41,7 +41,6 @@ ifneq ($(CONFIG_IA64_ESI),)
 obj-y				+= esi_stub.o	# must be in kernel proper
 endif
 obj-$(CONFIG_INTEL_IOMMU)	+= pci-dma.o
-obj-$(CONFIG_SWIOTLB)		+= pci-swiotlb.o
 
 obj-$(CONFIG_BINFMT_ELF)	+= elfcore.o
 

arch/mips/kernel/setup.c

@@ -375,6 +375,7 @@ static void __init bootmem_init(void)
 	unsigned long reserved_end;
 	unsigned long mapstart = ~0UL;
 	unsigned long bootmap_size;
+	phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX;
 	bool bootmap_valid = false;
 	int i;
 
@@ -395,7 +396,8 @@ static void __init bootmem_init(void)
 	max_low_pfn = 0;
 
 	/*
-	 * Find the highest page frame number we have available.
+	 * Find the highest page frame number we have available
+	 * and the lowest used RAM address
 	 */
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long start, end;
@@ -407,6 +409,8 @@ static void __init bootmem_init(void)
 		end = PFN_DOWN(boot_mem_map.map[i].addr
 				+ boot_mem_map.map[i].size);
 
+		ramstart = min(ramstart, boot_mem_map.map[i].addr);
+
 #ifndef CONFIG_HIGHMEM
 		/*
 		 * Skip highmem here so we get an accurate max_low_pfn if low
@@ -436,6 +440,13 @@ static void __init bootmem_init(void)
 		mapstart = max(reserved_end, start);
 	}
 
+	/*
+	 * Reserve any memory between the start of RAM and PHYS_OFFSET
+	 */
+	if (ramstart > PHYS_OFFSET)
+		add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET,
+				  BOOT_MEM_RESERVED);
+
 	if (min_low_pfn >= max_low_pfn)
 		panic("Incorrect memory mapping !!!");
 	if (min_low_pfn > ARCH_PFN_OFFSET) {
@@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p)
 
 	add_memory_region(start, size, BOOT_MEM_RAM);
 
-	if (start && start > PHYS_OFFSET)
-		add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET,
-				BOOT_MEM_RESERVED);
 	return 0;
 }
 early_param("mem", early_parse_mem);

arch/mips/kernel/smp-bmips.c

@@ -572,7 +572,7 @@ asmlinkage void __weak plat_wired_tlb_setup(void)
 	 */
 }
 
-void __init bmips_cpu_setup(void)
+void bmips_cpu_setup(void)
 {
 	void __iomem __maybe_unused *cbr = BMIPS_GET_CBR();
 	u32 __maybe_unused cfg;

arch/powerpc/include/asm/topology.h

@@ -81,6 +81,9 @@ static inline int numa_update_cpu_topology(bool cpus_locked)
 {
 	return 0;
 }
+
+static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
+
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)

arch/powerpc/kernel/sysfs.c

@@ -788,7 +788,8 @@ static int register_cpu_online(unsigned int cpu)
 	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
 		device_create_file(s, &dev_attr_pir);
 
-	if (cpu_has_feature(CPU_FTR_ARCH_206))
+	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+		!firmware_has_feature(FW_FEATURE_LPAR))
 		device_create_file(s, &dev_attr_tscr);
 #endif /* CONFIG_PPC64 */
 
@@ -873,7 +874,8 @@ static int unregister_cpu_online(unsigned int cpu)
 	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
 		device_remove_file(s, &dev_attr_pir);
 
-	if (cpu_has_feature(CPU_FTR_ARCH_206))
+	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+		!firmware_has_feature(FW_FEATURE_LPAR))
 		device_remove_file(s, &dev_attr_tscr);
 #endif /* CONFIG_PPC64 */
 

arch/powerpc/mm/drmem.c

@@ -216,6 +216,8 @@ static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm,
 	u32 i, n_lmbs;
 
 	n_lmbs = of_read_number(prop++, 1);
+	if (n_lmbs == 0)
+		return;
 
 	for (i = 0; i < n_lmbs; i++) {
 		read_drconf_v1_cell(&lmb, &prop);
@@ -245,6 +247,8 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm,
 	u32 i, j, lmb_sets;
 
 	lmb_sets = of_read_number(prop++, 1);
+	if (lmb_sets == 0)
+		return;
 
 	for (i = 0; i < lmb_sets; i++) {
 		read_drconf_v2_cell(&dr_cell, &prop);
@@ -354,6 +358,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop)
 	struct drmem_lmb *lmb;
 
 	drmem_info->n_lmbs = of_read_number(prop++, 1);
+	if (drmem_info->n_lmbs == 0)
+		return;
 
 	drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb),
 				   GFP_KERNEL);
@@ -373,6 +379,8 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop)
 	int lmb_index;
 
 	lmb_sets = of_read_number(prop++, 1);
+	if (lmb_sets == 0)
+		return;
 
 	/* first pass, calculate the number of LMBs */
 	p = prop;

arch/powerpc/platforms/powernv/opal-imc.c

@@ -199,9 +199,11 @@ static void disable_nest_pmu_counters(void)
 	const struct cpumask *l_cpumask;
 
 	get_online_cpus();
-	for_each_online_node(nid) {
+	for_each_node_with_cpus(nid) {
 		l_cpumask = cpumask_of_node(nid);
-		cpu = cpumask_first(l_cpumask);
+		cpu = cpumask_first_and(l_cpumask, cpu_online_mask);
+		if (cpu >= nr_cpu_ids)
+			continue;
 		opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
 				       get_hard_smp_processor_id(cpu));
 	}

arch/powerpc/sysdev/xive/spapr.c

@@ -356,7 +356,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio,
 
 	rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size);
 	if (rc) {
-		pr_err("Error %lld getting queue info prio %d\n", rc, prio);
+		pr_err("Error %lld getting queue info CPU %d prio %d\n", rc,
+		       target, prio);
 		rc = -EIO;
 		goto fail;
 	}
@@ -370,7 +371,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio,
 	/* Configure and enable the queue in HW */
 	rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order);
 	if (rc) {
-		pr_err("Error %lld setting queue for prio %d\n", rc, prio);
+		pr_err("Error %lld setting queue for CPU %d prio %d\n", rc,
+		       target, prio);
 		rc = -EIO;
 	} else {
 		q->qpage = qpage;
@@ -389,8 +391,8 @@ static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc,
 	if (IS_ERR(qpage))
 		return PTR_ERR(qpage);
 
-	return xive_spapr_configure_queue(cpu, q, prio, qpage,
-					  xive_queue_shift);
+	return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu),
+					  q, prio, qpage, xive_queue_shift);
 }
 
 static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,
@@ -399,10 +401,12 @@ static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,
 	struct xive_q *q = &xc->queue[prio];
 	unsigned int alloc_order;
 	long rc;
+	int hw_cpu = get_hard_smp_processor_id(cpu);
 
-	rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0);
+	rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0);
 	if (rc)
-		pr_err("Error %ld setting queue for prio %d\n", rc, prio);
+		pr_err("Error %ld setting queue for CPU %d prio %d\n", rc,
+		       hw_cpu, prio);
 
 	alloc_order = xive_alloc_order(xive_queue_shift);
 	free_pages((unsigned long)q->qpage, alloc_order);

arch/sparc/Kconfig

@@ -430,6 +430,8 @@ config SPARC_LEON
 	depends on SPARC32
 	select USB_EHCI_BIG_ENDIAN_MMIO
 	select USB_EHCI_BIG_ENDIAN_DESC
+	select USB_UHCI_BIG_ENDIAN_MMIO
+	select USB_UHCI_BIG_ENDIAN_DESC
 	---help---
 	  If you say Y here if you are running on a SPARC-LEON processor.
 	  The LEON processor is a synthesizable VHDL model of the

arch/x86/Kconfig

@@ -1404,7 +1404,7 @@ config HIGHMEM4G
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M486
+	depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
 	select X86_PAE
 	---help---
 	  Select this if you have a 32-bit processor and more than 4

arch/x86/Kconfig.cpu

@@ -374,7 +374,7 @@ config X86_TSC
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
+	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
@@ -385,7 +385,7 @@ config X86_CMOV
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && X86_P6_NOP
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 

arch/x86/include/asm/smp.h

@@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
+void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
 void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);

arch/x86/kernel/smpboot.c

@@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void)
 	cpu_set_state_online(me);
 }
 
-void __init native_smp_cpus_done(unsigned int max_cpus)
+void __init calculate_max_logical_packages(void)
 {
 	int ncpus;
 
-	pr_debug("Boot done\n");
 	/*
 	 * Today neither Intel nor AMD support heterogenous systems so
 	 * extrapolate the boot cpu's data to all packages.
@@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
 	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
+}
+
+void __init native_smp_cpus_done(unsigned int max_cpus)
+{
+	pr_debug("Boot done\n");
+
+	calculate_max_logical_packages();
 
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);

arch/x86/xen/smp.c

@@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus)
 
 	if (xen_hvm_domain())
 		native_smp_cpus_done(max_cpus);
+	else
+		calculate_max_logical_packages();
 
 	if (xen_have_vcpu_info_placement)
 		return;

block/blk-mq.c

@@ -3164,6 +3164,7 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
 		cpu_relax();
 	}
 
+	__set_current_state(TASK_RUNNING);
 	return false;
 }
 

drivers/acpi/bus.c

@@ -660,13 +660,15 @@ struct acpi_device *acpi_companion_match(const struct device *dev)
  * acpi_of_match_device - Match device object using the "compatible" property.
  * @adev: ACPI device object to match.
  * @of_match_table: List of device IDs to match against.
+ * @of_id: OF ID if matched
  *
  * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
  * identifiers and a _DSD object with the "compatible" property, use that
  * property to match against the given list of identifiers.
  */
 static bool acpi_of_match_device(struct acpi_device *adev,
-				 const struct of_device_id *of_match_table)
+				 const struct of_device_id *of_match_table,
+				 const struct of_device_id **of_id)
 {
 	const union acpi_object *of_compatible, *obj;
 	int i, nval;
@@ -690,8 +692,11 @@ static bool acpi_of_match_device(struct acpi_device *adev,
 		const struct of_device_id *id;
 
 		for (id = of_match_table; id->compatible[0]; id++)
-			if (!strcasecmp(obj->string.pointer, id->compatible))
+			if (!strcasecmp(obj->string.pointer, id->compatible)) {
+				if (of_id)
+					*of_id = id;
 				return true;
+			}
 	}
 
 	return false;
@@ -762,10 +767,11 @@ static bool __acpi_match_device_cls(const struct acpi_device_id *id,
 	return true;
 }
 
-static const struct acpi_device_id *__acpi_match_device(
-	struct acpi_device *device,
-	const struct acpi_device_id *ids,
-	const struct of_device_id *of_ids)
+static bool __acpi_match_device(struct acpi_device *device,
+				const struct acpi_device_id *acpi_ids,
+				const struct of_device_id *of_ids,
+				const struct acpi_device_id **acpi_id,
+				const struct of_device_id **of_id)
 {
 	const struct acpi_device_id *id;
 	struct acpi_hardware_id *hwid;
@@ -775,30 +781,32 @@ static const struct acpi_device_id *__acpi_match_device(
 	 * driver for it.
 	 */
 	if (!device || !device->status.present)
-		return NULL;
+		return false;
 
 	list_for_each_entry(hwid, &device->pnp.ids, list) {
 		/* First, check the ACPI/PNP IDs provided by the caller. */
-		for (id = ids; id->id[0] || id->cls; id++) {
-			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
-				return id;
-			else if (id->cls && __acpi_match_device_cls(id, hwid))
-				return id;
+		if (acpi_ids) {
+			for (id = acpi_ids; id->id[0] || id->cls; id++) {
+				if (id->id[0] && !strcmp((char *)id->id, hwid->id))
+					goto out_acpi_match;
+				if (id->cls && __acpi_match_device_cls(id, hwid))
+					goto out_acpi_match;
+			}
 		}
 
 		/*
 		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
 		 * "compatible" property if found.
-		 *
-		 * The id returned by the below is not valid, but the only
-		 * caller passing non-NULL of_ids here is only interested in
-		 * whether or not the return value is NULL.
 		 */
-		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
-		    && acpi_of_match_device(device, of_ids))
-			return id;
+		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id))
+			return acpi_of_match_device(device, of_ids, of_id);
 	}
-	return NULL;
+	return false;
+
+out_acpi_match:
+	if (acpi_id)
+		*acpi_id = id;
+	return true;
 }
 
 /**
@@ -815,32 +823,29 @@ static const struct acpi_device_id *__acpi_match_device(
 const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 					       const struct device *dev)
 {
-	return __acpi_match_device(acpi_companion_match(dev), ids, NULL);
+	const struct acpi_device_id *id = NULL;
+
+	__acpi_match_device(acpi_companion_match(dev), ids, NULL, &id, NULL);
+	return id;
 }
 EXPORT_SYMBOL_GPL(acpi_match_device);
 
-void *acpi_get_match_data(const struct device *dev)
+const void *acpi_device_get_match_data(const struct device *dev)
 {
 	const struct acpi_device_id *match;
 
-	if (!dev->driver)
-		return NULL;
-
-	if (!dev->driver->acpi_match_table)
-		return NULL;
-
 	match = acpi_match_device(dev->driver->acpi_match_table, dev);
 	if (!match)
 		return NULL;
 
-	return (void *)match->driver_data;
+	return (const void *)match->driver_data;
 }
-EXPORT_SYMBOL_GPL(acpi_get_match_data);
+EXPORT_SYMBOL_GPL(acpi_device_get_match_data);
 
 int acpi_match_device_ids(struct acpi_device *device,
 			  const struct acpi_device_id *ids)
 {
-	return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT;
+	return __acpi_match_device(device, ids, NULL, NULL, NULL) ? 0 : -ENOENT;
 }
 EXPORT_SYMBOL(acpi_match_device_ids);
 
@@ -849,10 +854,12 @@ bool acpi_driver_match_device(struct device *dev,
 {
 	if (!drv->acpi_match_table)
 		return acpi_of_match_device(ACPI_COMPANION(dev),
-					    drv->of_match_table);
+					    drv->of_match_table,
+					    NULL);
 
-	return !!__acpi_match_device(acpi_companion_match(dev),
-				     drv->acpi_match_table, drv->of_match_table);
+	return __acpi_match_device(acpi_companion_match(dev),
+				   drv->acpi_match_table, drv->of_match_table,
+				   NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(acpi_driver_match_device);
 

drivers/acpi/ec.c

@@ -1927,6 +1927,9 @@ static int acpi_ec_suspend_noirq(struct device *dev)
 	    ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE);
 
+	if (acpi_sleep_no_ec_events())
+		acpi_ec_enter_noirq(ec);
+
 	return 0;
 }
 
@@ -1934,6 +1937,9 @@ static int acpi_ec_resume_noirq(struct device *dev)
 {
 	struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev));
 
+	if (acpi_sleep_no_ec_events())
+		acpi_ec_leave_noirq(ec);
+
 	if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) &&
 	    ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE);

drivers/acpi/property.c

@@ -1271,11 +1271,11 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
-static void *
+static const void *
 acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 				  const struct device *dev)
 {
-	return acpi_get_match_data(dev);
+	return acpi_device_get_match_data(dev);
 }
 
 #define DECLARE_ACPI_FWNODE_OPS(ops) \

drivers/acpi/spcr.c

@@ -115,6 +115,7 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console)
 			table->serial_port.access_width))) {
 		default:
 			pr_err("Unexpected SPCR Access Width.  Defaulting to byte size\n");
+			/* fall through */
 		case 8:
 			iotype = "mmio";
 			break;

drivers/base/core.c

@@ -310,6 +310,9 @@ static void __device_link_del(struct device_link *link)
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
+	if (link->flags & DL_FLAG_PM_RUNTIME)
+		pm_runtime_drop_link(link->consumer);
+
 	list_del(&link->s_node);
 	list_del(&link->c_node);
 	device_link_free(link);

drivers/base/power/wakeirq.c

@@ -321,7 +321,8 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq)
 		return;
 
 	if (device_may_wakeup(wirq->dev)) {
-		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED &&
+		    !pm_runtime_status_suspended(wirq->dev))
 			enable_irq(wirq->irq);
 
 		enable_irq_wake(wirq->irq);
@@ -343,7 +344,8 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
 	if (device_may_wakeup(wirq->dev)) {
 		disable_irq_wake(wirq->irq);
 
-		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED &&
+		    !pm_runtime_status_suspended(wirq->dev))
 			disable_irq_nosync(wirq->irq);
 	}
 }

drivers/base/property.c

@@ -1410,9 +1410,8 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 }
 EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
 
-void *device_get_match_data(struct device *dev)
+const void *device_get_match_data(struct device *dev)
 {
-	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data,
-				  dev);
+	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev);
 }
 EXPORT_SYMBOL_GPL(device_get_match_data);

drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c

@@ -568,6 +568,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = {
 	/* HG _PR3 doesn't seem to work on this A+A weston board */
 	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0, 0, 0, 0, 0 },
 };
 

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -733,6 +733,25 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 	return ret == 0 ? count : ret;
 }
 
+static bool gtt_entry(struct mdev_device *mdev, loff_t *ppos)
+{
+	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	struct intel_gvt *gvt = vgpu->gvt;
+	int offset;
+
+	/* Only allow MMIO GGTT entry access */
+	if (index != PCI_BASE_ADDRESS_0)
+		return false;
+
+	offset = (u64)(*ppos & VFIO_PCI_OFFSET_MASK) -
+		intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_0);
+
+	return (offset >= gvt->device_info.gtt_start_offset &&
+		offset < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt)) ?
+			true : false;
+}
+
 static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf,
 			size_t count, loff_t *ppos)
 {
@@ -742,7 +761,21 @@ static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf,
 	while (count) {
 		size_t filled;
 
-		if (count >= 4 && !(*ppos % 4)) {
+		/* Only support GGTT entry 8 bytes read */
+		if (count >= 8 && !(*ppos % 8) &&
+			gtt_entry(mdev, ppos)) {
+			u64 val;
+
+			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
+					ppos, false);
+			if (ret <= 0)
+				goto read_err;
+
+			if (copy_to_user(buf, &val, sizeof(val)))
+				goto read_err;
+
+			filled = 8;
+		} else if (count >= 4 && !(*ppos % 4)) {
 			u32 val;
 
 			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
@@ -802,7 +835,21 @@ static ssize_t intel_vgpu_write(struct mdev_device *mdev,
 	while (count) {
 		size_t filled;
 
-		if (count >= 4 && !(*ppos % 4)) {
+		/* Only support GGTT entry 8 bytes write */
+		if (count >= 8 && !(*ppos % 8) &&
+			gtt_entry(mdev, ppos)) {
+			u64 val;
+
+			if (copy_from_user(&val, buf, sizeof(val)))
+				goto write_err;
+
+			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
+					ppos, true);
+			if (ret <= 0)
+				goto write_err;
+
+			filled = 8;
+		} else if (count >= 4 && !(*ppos % 4)) {
 			u32 val;
 
 			if (copy_from_user(&val, buf, sizeof(val)))

drivers/gpu/drm/i915/gvt/mmio_context.c

@@ -118,6 +118,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */
 	{RCS, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */
 	{RCS, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */
+	{RCS, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */
 	{RCS, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */
 	{RCS, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */
 	{RCS, TRNULLDETCT, 0, false}, /* 0x4de8 */

drivers/gpu/drm/i915/gvt/trace.h

@@ -333,7 +333,7 @@ TRACE_EVENT(render_mmio,
 	TP_PROTO(int old_id, int new_id, char *action, unsigned int reg,
 		 unsigned int old_val, unsigned int new_val),
 
-	TP_ARGS(old_id, new_id, action, reg, new_val, old_val),
+	TP_ARGS(old_id, new_id, action, reg, old_val, new_val),
 
 	TP_STRUCT__entry(
 		__field(int, old_id)

drivers/gpu/drm/i915/i915_drv.c

@@ -1433,19 +1433,7 @@ void i915_driver_unload(struct drm_device *dev)
 
 	intel_modeset_cleanup(dev);
 
-	/*
-	 * free the memory space allocated for the child device
-	 * config parsed from VBT
-	 */
-	if (dev_priv->vbt.child_dev && dev_priv->vbt.child_dev_num) {
-		kfree(dev_priv->vbt.child_dev);
-		dev_priv->vbt.child_dev = NULL;
-		dev_priv->vbt.child_dev_num = 0;
-	}
-	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
-	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
-	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
-	dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
+	intel_bios_cleanup(dev_priv);
 
 	vga_switcheroo_unregister_client(pdev);
 	vga_client_register(pdev, NULL, NULL, NULL);

drivers/gpu/drm/i915/i915_drv.h

@@ -1349,6 +1349,7 @@ struct intel_vbt_data {
 		u32 size;
 		u8 *data;
 		const u8 *sequence[MIPI_SEQ_MAX];
+		u8 *deassert_seq; /* Used by fixup_mipi_sequences() */
 	} dsi;
 
 	int crt_ddc_pin;
@@ -3657,6 +3658,7 @@ extern void intel_i2c_reset(struct drm_i915_private *dev_priv);
 
 /* intel_bios.c */
 void intel_bios_init(struct drm_i915_private *dev_priv);
+void intel_bios_cleanup(struct drm_i915_private *dev_priv);
 bool intel_bios_is_valid_vbt(const void *buf, size_t size);
 bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv);
 bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin);

drivers/gpu/drm/i915/i915_gem_context.c

@@ -803,7 +803,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 
 	case I915_CONTEXT_PARAM_PRIORITY:
 		{
-			int priority = args->value;
+			s64 priority = args->value;
 
 			if (args->size)
 				ret = -EINVAL;

drivers/gpu/drm/i915/i915_oa_cflgt3.c

@@ -84,9 +84,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
 void
 i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv)
 {
-	strncpy(dev_priv->perf.oa.test_config.uuid,
+	strlcpy(dev_priv->perf.oa.test_config.uuid,
 		"577e8e2c-3fa0-4875-8743-3538d585e3b0",
-		UUID_STRING_LEN);
+		sizeof(dev_priv->perf.oa.test_config.uuid));
 	dev_priv->perf.oa.test_config.id = 1;
 
 	dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa;

drivers/gpu/drm/i915/i915_oa_cnl.c

@@ -96,9 +96,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
 void
 i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv)
 {
-	strncpy(dev_priv->perf.oa.test_config.uuid,
+	strlcpy(dev_priv->perf.oa.test_config.uuid,
 		"db41edd4-d8e7-4730-ad11-b9a2d6833503",
-		UUID_STRING_LEN);
+		sizeof(dev_priv->perf.oa.test_config.uuid));
 	dev_priv->perf.oa.test_config.id = 1;
 
 	dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa;

drivers/gpu/drm/i915/i915_pmu.c

@@ -285,26 +285,41 @@ static u64 count_interrupts(struct drm_i915_private *i915)
 	return sum;
 }
 
-static void i915_pmu_event_destroy(struct perf_event *event)
+static void engine_event_destroy(struct perf_event *event)
 {
-	WARN_ON(event->parent);
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct intel_engine_cs *engine;
+
+	engine = intel_engine_lookup_user(i915,
+					  engine_event_class(event),
+					  engine_event_instance(event));
+	if (WARN_ON_ONCE(!engine))
+		return;
+
+	if (engine_event_sample(event) == I915_SAMPLE_BUSY &&
+	    intel_engine_supports_stats(engine))
+		intel_disable_engine_stats(engine);
 }
 
-static int engine_event_init(struct perf_event *event)
+static void i915_pmu_event_destroy(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	WARN_ON(event->parent);
 
-	if (!intel_engine_lookup_user(i915, engine_event_class(event),
-				      engine_event_instance(event)))
-		return -ENODEV;
+	if (is_engine_event(event))
+		engine_event_destroy(event);
+}
 
-	switch (engine_event_sample(event)) {
+static int
+engine_event_status(struct intel_engine_cs *engine,
+		    enum drm_i915_pmu_engine_sample sample)
+{
+	switch (sample) {
 	case I915_SAMPLE_BUSY:
 	case I915_SAMPLE_WAIT:
 		break;
 	case I915_SAMPLE_SEMA:
-		if (INTEL_GEN(i915) < 6)
+		if (INTEL_GEN(engine->i915) < 6)
 			return -ENODEV;
 		break;
 	default:
@@ -314,6 +329,30 @@ static int engine_event_init(struct perf_event *event)
 	return 0;
 }
 
+static int engine_event_init(struct perf_event *event)
+{
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct intel_engine_cs *engine;
+	u8 sample;
+	int ret;
+
+	engine = intel_engine_lookup_user(i915, engine_event_class(event),
+					  engine_event_instance(event));
+	if (!engine)
+		return -ENODEV;
+
+	sample = engine_event_sample(event);
+	ret = engine_event_status(engine, sample);
+	if (ret)
+		return ret;
+
+	if (sample == I915_SAMPLE_BUSY && intel_engine_supports_stats(engine))
+		ret = intel_enable_engine_stats(engine);
+
+	return ret;
+}
+
 static int i915_pmu_event_init(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -370,7 +409,94 @@ static int i915_pmu_event_init(struct perf_event *event)
 	return 0;
 }
 
-static u64 __i915_pmu_event_read(struct perf_event *event)
+static u64 __get_rc6(struct drm_i915_private *i915)
+{
+	u64 val;
+
+	val = intel_rc6_residency_ns(i915,
+				     IS_VALLEYVIEW(i915) ?
+				     VLV_GT_RENDER_RC6 :
+				     GEN6_GT_GFX_RC6);
+
+	if (HAS_RC6p(i915))
+		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
+
+	if (HAS_RC6pp(i915))
+		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
+
+	return val;
+}
+
+static u64 get_rc6(struct drm_i915_private *i915, bool locked)
+{
+#if IS_ENABLED(CONFIG_PM)
+	unsigned long flags;
+	u64 val;
+
+	if (intel_runtime_pm_get_if_in_use(i915)) {
+		val = __get_rc6(i915);
+		intel_runtime_pm_put(i915);
+
+		/*
+		 * If we are coming back from being runtime suspended we must
+		 * be careful not to report a larger value than returned
+		 * previously.
+		 */
+
+		if (!locked)
+			spin_lock_irqsave(&i915->pmu.lock, flags);
+
+		if (val >= i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
+			i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0;
+			i915->pmu.sample[__I915_SAMPLE_RC6].cur = val;
+		} else {
+			val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
+		}
+
+		if (!locked)
+			spin_unlock_irqrestore(&i915->pmu.lock, flags);
+	} else {
+		struct pci_dev *pdev = i915->drm.pdev;
+		struct device *kdev = &pdev->dev;
+		unsigned long flags2;
+
+		/*
+		 * We are runtime suspended.
+		 *
+		 * Report the delta from when the device was suspended to now,
+		 * on top of the last known real value, as the approximated RC6
+		 * counter value.
+		 */
+		if (!locked)
+			spin_lock_irqsave(&i915->pmu.lock, flags);
+
+		spin_lock_irqsave(&kdev->power.lock, flags2);
+
+		if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
+			i915->pmu.suspended_jiffies_last =
+						kdev->power.suspended_jiffies;
+
+		val = kdev->power.suspended_jiffies -
+		      i915->pmu.suspended_jiffies_last;
+		val += jiffies - kdev->power.accounting_timestamp;
+
+		spin_unlock_irqrestore(&kdev->power.lock, flags2);
+
+		val = jiffies_to_nsecs(val);
+		val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
+		i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+
+		if (!locked)
+			spin_unlock_irqrestore(&i915->pmu.lock, flags);
+	}
+
+	return val;
+#else
+	return __get_rc6(i915);
+#endif
+}
+
+static u64 __i915_pmu_event_read(struct perf_event *event, bool locked)
 {
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
@@ -387,7 +513,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		if (WARN_ON_ONCE(!engine)) {
 			/* Do nothing */
 		} else if (sample == I915_SAMPLE_BUSY &&
-			   engine->pmu.busy_stats) {
+			   intel_engine_supports_stats(engine)) {
 			val = ktime_to_ns(intel_engine_get_busy_time(engine));
 		} else {
 			val = engine->pmu.sample[sample].cur;
@@ -408,18 +534,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 			val = count_interrupts(i915);
 			break;
 		case I915_PMU_RC6_RESIDENCY:
-			intel_runtime_pm_get(i915);
-			val = intel_rc6_residency_ns(i915,
-						     IS_VALLEYVIEW(i915) ?
-						     VLV_GT_RENDER_RC6 :
-						     GEN6_GT_GFX_RC6);
-			if (HAS_RC6p(i915))
-				val += intel_rc6_residency_ns(i915,
-							      GEN6_GT_GFX_RC6p);
-			if (HAS_RC6pp(i915))
-				val += intel_rc6_residency_ns(i915,
-							      GEN6_GT_GFX_RC6pp);
-			intel_runtime_pm_put(i915);
+			val = get_rc6(i915, locked);
 			break;
 		}
 	}
@@ -434,7 +549,7 @@ static void i915_pmu_event_read(struct perf_event *event)
 
 again:
 	prev = local64_read(&hwc->prev_count);
-	new = __i915_pmu_event_read(event);
+	new = __i915_pmu_event_read(event, false);
 
 	if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev)
 		goto again;
@@ -442,12 +557,6 @@ again:
 	local64_add(new - prev, &event->count);
 }
 
-static bool engine_needs_busy_stats(struct intel_engine_cs *engine)
-{
-	return intel_engine_supports_stats(engine) &&
-	       (engine->pmu.enable & BIT(I915_SAMPLE_BUSY));
-}
-
 static void i915_pmu_enable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -487,21 +596,7 @@ static void i915_pmu_enable(struct perf_event *event)
 
 		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0);
-		if (engine->pmu.enable_count[sample]++ == 0) {
-			/*
-			 * Enable engine busy stats tracking if needed or
-			 * alternatively cancel the scheduled disable.
-			 *
-			 * If the delayed disable was pending, cancel it and
-			 * in this case do not enable since it already is.
-			 */
-			if (engine_needs_busy_stats(engine) &&
-			    !engine->pmu.busy_stats) {
-				engine->pmu.busy_stats = true;
-				if (!cancel_delayed_work(&engine->pmu.disable_busy_stats))
-					intel_enable_engine_stats(engine);
-			}
-		}
+		engine->pmu.enable_count[sample]++;
 	}
 
 	/*
@@ -509,19 +604,11 @@ static void i915_pmu_enable(struct perf_event *event)
 	 * for all listeners. Even when the event was already enabled and has
 	 * an existing non-zero value.
 	 */
-	local64_set(&event->hw.prev_count, __i915_pmu_event_read(event));
+	local64_set(&event->hw.prev_count, __i915_pmu_event_read(event, true));
 
 	spin_unlock_irqrestore(&i915->pmu.lock, flags);
 }
 
-static void __disable_busy_stats(struct work_struct *work)
-{
-	struct intel_engine_cs *engine =
-	       container_of(work, typeof(*engine), pmu.disable_busy_stats.work);
-
-	intel_disable_engine_stats(engine);
-}
-
 static void i915_pmu_disable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -545,26 +632,8 @@ static void i915_pmu_disable(struct perf_event *event)
 		 * Decrement the reference count and clear the enabled
 		 * bitmask when the last listener on an event goes away.
 		 */
-		if (--engine->pmu.enable_count[sample] == 0) {
+		if (--engine->pmu.enable_count[sample] == 0)
 			engine->pmu.enable &= ~BIT(sample);
-			if (!engine_needs_busy_stats(engine) &&
-			    engine->pmu.busy_stats) {
-				engine->pmu.busy_stats = false;
-				/*
-				 * We request a delayed disable to handle the
-				 * rapid on/off cycles on events, which can
-				 * happen when tools like perf stat start, in a
-				 * nicer way.
-				 *
-				 * In addition, this also helps with busy stats
-				 * accuracy with background CPU offline/online
-				 * migration events.
-				 */
-				queue_delayed_work(system_wq,
-						   &engine->pmu.disable_busy_stats,
-						   round_jiffies_up_relative(HZ));
-			}
-		}
 	}
 
 	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);
@@ -797,8 +866,6 @@ static void i915_pmu_unregister_cpuhp_state(struct drm_i915_private *i915)
 
 void i915_pmu_register(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	int ret;
 
 	if (INTEL_GEN(i915) <= 2) {
@@ -820,10 +887,6 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	hrtimer_init(&i915->pmu.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	i915->pmu.timer.function = i915_sample;
 
-	for_each_engine(engine, i915, id)
-		INIT_DELAYED_WORK(&engine->pmu.disable_busy_stats,
-				  __disable_busy_stats);
-
 	ret = perf_pmu_register(&i915->pmu.base, "i915", -1);
 	if (ret)
 		goto err;
@@ -843,9 +906,6 @@ err:
 
 void i915_pmu_unregister(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
 	if (!i915->pmu.base.event_init)
 		return;
 
@@ -853,11 +913,6 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	hrtimer_cancel(&i915->pmu.timer);
 
-	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(engine->pmu.busy_stats);
-		flush_delayed_work(&engine->pmu.disable_busy_stats);
-	}
-
 	i915_pmu_unregister_cpuhp_state(i915);
 
 	perf_pmu_unregister(&i915->pmu.base);

drivers/gpu/drm/i915/i915_pmu.h

@@ -27,6 +27,8 @@
 enum {
 	__I915_SAMPLE_FREQ_ACT = 0,
 	__I915_SAMPLE_FREQ_REQ,
+	__I915_SAMPLE_RC6,
+	__I915_SAMPLE_RC6_ESTIMATED,
 	__I915_NUM_PMU_SAMPLERS
 };
 
@@ -94,6 +96,10 @@ struct i915_pmu {
 	 * struct intel_engine_cs.
 	 */
 	struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
+	/**
+	 * @suspended_jiffies_last: Cached suspend time from PM core.
+	 */
+	unsigned long suspended_jiffies_last;
 };
 
 #ifdef CONFIG_PERF_EVENTS

drivers/gpu/drm/i915/intel_bios.c

@@ -947,6 +947,86 @@ static int goto_next_sequence_v3(const u8 *data, int index, int total)
 	return 0;
 }
 
+/*
+ * Get len of pre-fixed deassert fragment from a v1 init OTP sequence,
+ * skip all delay + gpio operands and stop at the first DSI packet op.
+ */
+static int get_init_otp_deassert_fragment_len(struct drm_i915_private *dev_priv)
+{
+	const u8 *data = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP];
+	int index, len;
+
+	if (WARN_ON(!data || dev_priv->vbt.dsi.seq_version != 1))
+		return 0;
+
+	/* index = 1 to skip sequence byte */
+	for (index = 1; data[index] != MIPI_SEQ_ELEM_END; index += len) {
+		switch (data[index]) {
+		case MIPI_SEQ_ELEM_SEND_PKT:
+			return index == 1 ? 0 : index;
+		case MIPI_SEQ_ELEM_DELAY:
+			len = 5; /* 1 byte for operand + uint32 */
+			break;
+		case MIPI_SEQ_ELEM_GPIO:
+			len = 3; /* 1 byte for op, 1 for gpio_nr, 1 for value */
+			break;
+		default:
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence.
+ * The deassert must be done before calling intel_dsi_device_ready, so for
+ * these devices we split the init OTP sequence into a deassert sequence and
+ * the actual init OTP part.
+ */
+static void fixup_mipi_sequences(struct drm_i915_private *dev_priv)
+{
+	u8 *init_otp;
+	int len;
+
+	/* Limit this to VLV for now. */
+	if (!IS_VALLEYVIEW(dev_priv))
+		return;
+
+	/* Limit this to v1 vid-mode sequences */
+	if (dev_priv->vbt.dsi.config->is_cmd_mode ||
+	    dev_priv->vbt.dsi.seq_version != 1)
+		return;
+
+	/* Only do this if there are otp and assert seqs and no deassert seq */
+	if (!dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] ||
+	    !dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET] ||
+	    dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET])
+		return;
+
+	/* The deassert-sequence ends at the first DSI packet */
+	len = get_init_otp_deassert_fragment_len(dev_priv);
+	if (!len)
+		return;
+
+	DRM_DEBUG_KMS("Using init OTP fragment to deassert reset\n");
+
+	/* Copy the fragment, update seq byte and terminate it */
+	init_otp = (u8 *)dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP];
+	dev_priv->vbt.dsi.deassert_seq = kmemdup(init_otp, len + 1, GFP_KERNEL);
+	if (!dev_priv->vbt.dsi.deassert_seq)
+		return;
+	dev_priv->vbt.dsi.deassert_seq[0] = MIPI_SEQ_DEASSERT_RESET;
+	dev_priv->vbt.dsi.deassert_seq[len] = MIPI_SEQ_ELEM_END;
+	/* Use the copy for deassert */
+	dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET] =
+		dev_priv->vbt.dsi.deassert_seq;
+	/* Replace the last byte of the fragment with init OTP seq byte */
+	init_otp[len - 1] = MIPI_SEQ_INIT_OTP;
+	/* And make MIPI_MIPI_SEQ_INIT_OTP point to it */
+	dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1;
+}
+
 static void
 parse_mipi_sequence(struct drm_i915_private *dev_priv,
 		    const struct bdb_header *bdb)
@@ -1016,6 +1096,8 @@ parse_mipi_sequence(struct drm_i915_private *dev_priv,
 	dev_priv->vbt.dsi.size = seq_size;
 	dev_priv->vbt.dsi.seq_version = sequence->version;
 
+	fixup_mipi_sequences(dev_priv);
+
 	DRM_DEBUG_DRIVER("MIPI related VBT parsing complete\n");
 	return;
 
@@ -1588,6 +1670,29 @@ out:
 		pci_unmap_rom(pdev, bios);
 }
 
+/**
+ * intel_bios_cleanup - Free any resources allocated by intel_bios_init()
+ * @dev_priv: i915 device instance
+ */
+void intel_bios_cleanup(struct drm_i915_private *dev_priv)
+{
+	kfree(dev_priv->vbt.child_dev);
+	dev_priv->vbt.child_dev = NULL;
+	dev_priv->vbt.child_dev_num = 0;
+	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
+	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
+	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
+	dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
+	kfree(dev_priv->vbt.dsi.data);
+	dev_priv->vbt.dsi.data = NULL;
+	kfree(dev_priv->vbt.dsi.pps);
+	dev_priv->vbt.dsi.pps = NULL;
+	kfree(dev_priv->vbt.dsi.config);
+	dev_priv->vbt.dsi.config = NULL;
+	kfree(dev_priv->vbt.dsi.deassert_seq);
+	dev_priv->vbt.dsi.deassert_seq = NULL;
+}
+
 /**
  * intel_bios_is_tv_present - is integrated TV present in VBT
  * @dev_priv:	i915 device instance

drivers/gpu/drm/i915/intel_breadcrumbs.c

@@ -594,29 +594,16 @@ void intel_engine_remove_wait(struct intel_engine_cs *engine,
 	spin_unlock_irq(&b->rb_lock);
 }
 
-static bool signal_valid(const struct drm_i915_gem_request *request)
-{
-	return intel_wait_check_request(&request->signaling.wait, request);
-}
-
 static bool signal_complete(const struct drm_i915_gem_request *request)
 {
 	if (!request)
 		return false;
 
-	/* If another process served as the bottom-half it may have already
-	 * signalled that this wait is already completed.
-	 */
-	if (intel_wait_complete(&request->signaling.wait))
-		return signal_valid(request);
-
-	/* Carefully check if the request is complete, giving time for the
+	/*
+	 * Carefully check if the request is complete, giving time for the
 	 * seqno to be visible or if the GPU hung.
 	 */
-	if (__i915_request_irq_complete(request))
-		return true;
-
-	return false;
+	return __i915_request_irq_complete(request);
 }
 
 static struct drm_i915_gem_request *to_signaler(struct rb_node *rb)
@@ -659,9 +646,13 @@ static int intel_breadcrumbs_signaler(void *arg)
 			request = i915_gem_request_get_rcu(request);
 		rcu_read_unlock();
 		if (signal_complete(request)) {
-			local_bh_disable();
-			dma_fence_signal(&request->fence);
-			local_bh_enable(); /* kick start the tasklets */
+			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+				      &request->fence.flags)) {
+				local_bh_disable();
+				dma_fence_signal(&request->fence);
+				GEM_BUG_ON(!i915_gem_request_completed(request));
+				local_bh_enable(); /* kick start the tasklets */
+			}
 
 			spin_lock_irq(&b->rb_lock);
 

drivers/gpu/drm/i915/intel_cdclk.c

@@ -1952,6 +1952,14 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
 		min_cdclk = max(2 * 96000, min_cdclk);
 
+	/*
+	 * On Valleyview some DSI panels lose (v|h)sync when the clock is lower
+	 * than 320000KHz.
+	 */
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) &&
+	    IS_VALLEYVIEW(dev_priv))
+		min_cdclk = max(320000, min_cdclk);
+
 	if (min_cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n",
 			      min_cdclk, dev_priv->max_cdclk_freq);

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -1458,7 +1458,9 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 	struct drm_i915_private *dev_priv = engine->i915;
 	bool idle = true;
 
-	intel_runtime_pm_get(dev_priv);
+	/* If the whole device is asleep, the engine must be idle */
+	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+		return true;
 
 	/* First check that no commands are left in the ring */
 	if ((I915_READ_HEAD(engine) & HEAD_ADDR) !=
@@ -1943,16 +1945,22 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
  */
 int intel_enable_engine_stats(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists *execlists = &engine->execlists;
 	unsigned long flags;
+	int err = 0;
 
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
+	tasklet_disable(&execlists->tasklet);
 	spin_lock_irqsave(&engine->stats.lock, flags);
-	if (engine->stats.enabled == ~0)
-		goto busy;
+
+	if (unlikely(engine->stats.enabled == ~0)) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (engine->stats.enabled++ == 0) {
-		struct intel_engine_execlists *execlists = &engine->execlists;
 		const struct execlist_port *port = execlists->port;
 		unsigned int num_ports = execlists_num_ports(execlists);
 
@@ -1967,14 +1975,12 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 		if (engine->stats.active)
 			engine->stats.start = engine->stats.enabled_at;
 	}
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
-
-	return 0;
 
-busy:
+unlock:
 	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	tasklet_enable(&execlists->tasklet);
 
-	return -EBUSY;
+	return err;
 }
 
 static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -366,20 +366,6 @@ struct intel_engine_cs {
 		 */
 #define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1)
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
-		/**
-		 * @busy_stats: Has enablement of engine stats tracking been
-		 * 		requested.
-		 */
-		bool busy_stats;
-		/**
-		 * @disable_busy_stats: Work item for busy stats disabling.
-		 *
-		 * Same as with @enable_busy_stats action, with the difference
-		 * that we delay it in case there are rapid enable-disable
-		 * actions, which can happen during tool startup (like perf
-		 * stat).
-		 */
-		struct delayed_work disable_busy_stats;
 	} pmu;
 
 	/*

drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c

@@ -301,7 +301,7 @@ nvkm_therm_attr_set(struct nvkm_therm *therm,
 void
 nvkm_therm_clkgate_enable(struct nvkm_therm *therm)
 {
-	if (!therm->func->clkgate_enable || !therm->clkgating_enabled)
+	if (!therm || !therm->func->clkgate_enable || !therm->clkgating_enabled)
 		return;
 
 	nvkm_debug(&therm->subdev,
@@ -312,7 +312,7 @@ nvkm_therm_clkgate_enable(struct nvkm_therm *therm)
 void
 nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend)
 {
-	if (!therm->func->clkgate_fini || !therm->clkgating_enabled)
+	if (!therm || !therm->func->clkgate_fini || !therm->clkgating_enabled)
 		return;
 
 	nvkm_debug(&therm->subdev,
@@ -395,7 +395,7 @@ void
 nvkm_therm_clkgate_init(struct nvkm_therm *therm,
 			const struct nvkm_therm_clkgate_pack *p)
 {
-	if (!therm->func->clkgate_init || !therm->clkgating_enabled)
+	if (!therm || !therm->func->clkgate_init || !therm->clkgating_enabled)
 		return;
 
 	therm->func->clkgate_init(therm, p);

drivers/hwmon/k10temp.c

@@ -129,7 +129,10 @@ static ssize_t temp1_input_show(struct device *dev,
 
 	data->read_tempreg(data->pdev, &regval);
 	temp = (regval >> 21) * 125;
-	temp -= data->temp_offset;
+	if (temp > data->temp_offset)
+		temp -= data->temp_offset;
+	else
+		temp = 0;
 
 	return sprintf(buf, "%u\n", temp);
 }

drivers/irqchip/irq-bcm7038-l1.c

@@ -339,9 +339,6 @@ int __init bcm7038_l1_of_init(struct device_node *dn,
 		goto out_unmap;
 	}
 
-	pr_info("registered BCM7038 L1 intc (mem: 0x%p, IRQs: %d)\n",
-		intc->cpus[0]->map_base, IRQS_PER_WORD * intc->n_words);
-
 	return 0;
 
 out_unmap:

drivers/irqchip/irq-bcm7120-l2.c

@@ -318,9 +318,6 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn,
 		}
 	}
 
-	pr_info("registered %s intc (mem: 0x%p, parent IRQ(s): %d)\n",
-			intc_name, data->map_base[0], data->num_parent_irqs);
-
 	return 0;
 
 out_free_domain:

drivers/irqchip/irq-brcmstb-l2.c

@@ -262,9 +262,6 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np,
 		ct->chip.irq_set_wake = irq_gc_set_wake;
 	}
 
-	pr_info("registered L2 intc (mem: 0x%p, parent irq: %d)\n",
-			base, parent_irq);
-
 	return 0;
 
 out_free_domain:

drivers/irqchip/irq-gic-v2m.c

@@ -94,7 +94,7 @@ static struct irq_chip gicv2m_msi_irq_chip = {
 
 static struct msi_domain_info gicv2m_msi_domain_info = {
 	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		   MSI_FLAG_PCI_MSIX),
+		   MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI),
 	.chip	= &gicv2m_msi_irq_chip,
 };
 
@@ -155,18 +155,12 @@ static int gicv2m_irq_gic_domain_alloc(struct irq_domain *domain,
 	return 0;
 }
 
-static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq)
+static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq,
+			       int nr_irqs)
 {
-	int pos;
-
-	pos = hwirq - v2m->spi_start;
-	if (pos < 0 || pos >= v2m->nr_spis) {
-		pr_err("Failed to teardown msi. Invalid hwirq %d\n", hwirq);
-		return;
-	}
-
 	spin_lock(&v2m_lock);
-	__clear_bit(pos, v2m->bm);
+	bitmap_release_region(v2m->bm, hwirq - v2m->spi_start,
+			      get_count_order(nr_irqs));
 	spin_unlock(&v2m_lock);
 }
 
@@ -174,13 +168,13 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				   unsigned int nr_irqs, void *args)
 {
 	struct v2m_data *v2m = NULL, *tmp;
-	int hwirq, offset, err = 0;
+	int hwirq, offset, i, err = 0;
 
 	spin_lock(&v2m_lock);
 	list_for_each_entry(tmp, &v2m_nodes, entry) {
-		offset = find_first_zero_bit(tmp->bm, tmp->nr_spis);
-		if (offset < tmp->nr_spis) {
-			__set_bit(offset, tmp->bm);
+		offset = bitmap_find_free_region(tmp->bm, tmp->nr_spis,
+						 get_count_order(nr_irqs));
+		if (offset >= 0) {
 			v2m = tmp;
 			break;
 		}
@@ -192,16 +186,21 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 
 	hwirq = v2m->spi_start + offset;
 
-	err = gicv2m_irq_gic_domain_alloc(domain, virq, hwirq);
-	if (err) {
-		gicv2m_unalloc_msi(v2m, hwirq);
-		return err;
-	}
+	for (i = 0; i < nr_irqs; i++) {
+		err = gicv2m_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
+		if (err)
+			goto fail;
 
-	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
-				      &gicv2m_irq_chip, v2m);
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &gicv2m_irq_chip, v2m);
+	}
 
 	return 0;
+
+fail:
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+	gicv2m_unalloc_msi(v2m, hwirq, get_count_order(nr_irqs));
+	return err;
 }
 
 static void gicv2m_irq_domain_free(struct irq_domain *domain,
@@ -210,8 +209,7 @@ static void gicv2m_irq_domain_free(struct irq_domain *domain,
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 	struct v2m_data *v2m = irq_data_get_irq_chip_data(d);
 
-	BUG_ON(nr_irqs != 1);
-	gicv2m_unalloc_msi(v2m, d->hwirq);
+	gicv2m_unalloc_msi(v2m, d->hwirq, nr_irqs);
 	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 

drivers/irqchip/irq-gic-v3-its-pci-msi.c

@@ -132,6 +132,8 @@ static int __init its_pci_of_msi_init(void)
 
 	for (np = of_find_matching_node(NULL, its_device_id); np;
 	     np = of_find_matching_node(np, its_device_id)) {
+		if (!of_device_is_available(np))
+			continue;
 		if (!of_property_read_bool(np, "msi-controller"))
 			continue;
 

drivers/irqchip/irq-gic-v3-its-platform-msi.c

@@ -154,6 +154,8 @@ static void __init its_pmsi_of_init(void)
 
 	for (np = of_find_matching_node(NULL, its_device_id); np;
 	     np = of_find_matching_node(np, its_device_id)) {
+		if (!of_device_is_available(np))
+			continue;
 		if (!of_property_read_bool(np, "msi-controller"))
 			continue;
 

drivers/irqchip/irq-gic-v3-its.c

@@ -3314,6 +3314,8 @@ static int __init its_of_probe(struct device_node *node)
 
 	for (np = of_find_matching_node(node, its_device_id); np;
 	     np = of_find_matching_node(np, its_device_id)) {
+		if (!of_device_is_available(np))
+			continue;
 		if (!of_property_read_bool(np, "msi-controller")) {
 			pr_warn("%pOF: no msi-controller property, ITS ignored\n",
 				np);

drivers/irqchip/irq-gic-v3.c

@@ -673,7 +673,7 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
 	       MPIDR_TO_SGI_RS(cluster_id)		|
 	       tlist << ICC_SGI1R_TARGET_LIST_SHIFT);
 
-	pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
+	pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
 	gic_write_sgi1r(val);
 }
 
@@ -688,7 +688,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	 * Ensure that stores to Normal memory are visible to the
 	 * other CPUs before issuing the IPI.
 	 */
-	smp_wmb();
+	wmb();
 
 	for_each_cpu(cpu, mask) {
 		u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu));

drivers/irqchip/irq-mips-gic.c

@@ -424,8 +424,6 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	spin_lock_irqsave(&gic_lock, flags);
 	write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
 	write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
-	gic_clear_pcpu_masks(intr);
-	set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
 	irq_data_update_effective_affinity(data, cpumask_of(cpu));
 	spin_unlock_irqrestore(&gic_lock, flags);
 

drivers/macintosh/macio_asic.c

@@ -375,6 +375,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	dev->ofdev.dev.of_node = np;
 	dev->ofdev.archdata.dma_mask = 0xffffffffUL;
 	dev->ofdev.dev.dma_mask = &dev->ofdev.archdata.dma_mask;
+	dev->ofdev.dev.coherent_dma_mask = dev->ofdev.archdata.dma_mask;
 	dev->ofdev.dev.parent = parent;
 	dev->ofdev.dev.bus = &macio_bus_type;
 	dev->ofdev.dev.release = macio_release_dev;

drivers/md/dm.c

@@ -903,7 +903,8 @@ static void dec_pending(struct dm_io *io, blk_status_t error)
 			queue_io(md, bio);
 		} else {
 			/* done with normal IO or empty flush */
-			bio->bi_status = io_error;
+			if (io_error)
+				bio->bi_status = io_error;
 			bio_endio(bio);
 		}
 	}

drivers/mmc/host/bcm2835.c

@@ -1265,7 +1265,8 @@ static int bcm2835_add_host(struct bcm2835_host *host)
 	char pio_limit_string[20];
 	int ret;
 
-	mmc->f_max = host->max_clk;
+	if (!mmc->f_max || mmc->f_max > host->max_clk)
+		mmc->f_max = host->max_clk;
 	mmc->f_min = host->max_clk / SDCDIV_MAX_CDIV;
 
 	mmc->max_busy_timeout = ~0 / (mmc->f_max / 1000);

drivers/mmc/host/meson-gx-mmc.c

@@ -717,22 +717,6 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode,
 static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct meson_host *host = mmc_priv(mmc);
-	int ret;
-
-	/*
-	 * If this is the initial tuning, try to get a sane Rx starting
-	 * phase before doing the actual tuning.
-	 */
-	if (!mmc->doing_retune) {
-		ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk);
-
-		if (ret)
-			return ret;
-	}
-
-	ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk);
-	if (ret)
-		return ret;
 
 	return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk);
 }
@@ -763,9 +747,8 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
 
-		/* Reset phases */
+		/* Reset rx phase */
 		clk_set_phase(host->rx_clk, 0);
-		clk_set_phase(host->tx_clk, 270);
 
 		break;
 

drivers/mtd/nand/Kconfig

@@ -328,7 +328,7 @@ config MTD_NAND_MARVELL
 	tristate "NAND controller support on Marvell boards"
 	depends on PXA3xx || ARCH_MMP || PLAT_ORION || ARCH_MVEBU || \
 		   COMPILE_TEST
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
 	help
 	  This enables the NAND flash controller driver for Marvell boards,
 	  including:

drivers/mtd/nand/vf610_nfc.c

@@ -752,10 +752,8 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 		if (mtd->oobsize > 64)
 			mtd->oobsize = 64;
 
-		/*
-		 * mtd->ecclayout is not specified here because we're using the
-		 * default large page ECC layout defined in NAND core.
-		 */
+		/* Use default large page ECC layout defined in NAND core */
+		mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
 		if (chip->ecc.strength == 32) {
 			nfc->ecc_mode = ECC_60_BYTE;
 			chip->ecc.bytes = 60;

drivers/nvme/host/core.c

@@ -120,8 +120,12 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	int ret;
 
 	ret = nvme_reset_ctrl(ctrl);
-	if (!ret)
+	if (!ret) {
 		flush_work(&ctrl->reset_work);
+		if (ctrl->state != NVME_CTRL_LIVE)
+			ret = -ENETRESET;
+	}
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
@@ -265,7 +269,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_ADMIN_ONLY:
 		switch (old_state) {
-		case NVME_CTRL_RECONNECTING:
+		case NVME_CTRL_CONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -276,7 +280,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
-		case NVME_CTRL_RECONNECTING:
+		case NVME_CTRL_CONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -294,9 +298,9 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 			break;
 		}
 		break;
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		switch (old_state) {
-		case NVME_CTRL_LIVE:
+		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
 			changed = true;
 			/* FALLTHRU */
@@ -309,7 +313,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_ADMIN_ONLY:
 		case NVME_CTRL_RESETTING:
-		case NVME_CTRL_RECONNECTING:
+		case NVME_CTRL_CONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -518,9 +522,11 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
 		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
 
-		range[n].cattr = cpu_to_le32(0);
-		range[n].nlb = cpu_to_le32(nlb);
-		range[n].slba = cpu_to_le64(slba);
+		if (n < segments) {
+			range[n].cattr = cpu_to_le32(0);
+			range[n].nlb = cpu_to_le32(nlb);
+			range[n].slba = cpu_to_le64(slba);
+		}
 		n++;
 	}
 
@@ -794,13 +800,9 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
 {
-	struct nvme_command c;
 	struct request *rq;
 
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = nvme_admin_keep_alive;
-
-	rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED,
+	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED,
 			NVME_QID_ANY);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
@@ -832,6 +834,8 @@ void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 		return;
 
 	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
+	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 EXPORT_SYMBOL_GPL(nvme_start_keep_alive);
@@ -1117,14 +1121,19 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *next;
+	LIST_HEAD(rm_list);
 
 	mutex_lock(&ctrl->namespaces_mutex);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->disk && nvme_revalidate_disk(ns->disk))
-			nvme_ns_remove(ns);
+		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
+			list_move_tail(&ns->list, &rm_list);
+		}
 	}
 	mutex_unlock(&ctrl->namespaces_mutex);
+
+	list_for_each_entry_safe(ns, next, &rm_list, list)
+		nvme_ns_remove(ns);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -2687,7 +2696,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_LIVE]	= "live",
 		[NVME_CTRL_ADMIN_ONLY]	= "only-admin",
 		[NVME_CTRL_RESETTING]	= "resetting",
-		[NVME_CTRL_RECONNECTING]= "reconnecting",
+		[NVME_CTRL_CONNECTING]	= "connecting",
 		[NVME_CTRL_DELETING]	= "deleting",
 		[NVME_CTRL_DEAD]	= "dead",
 	};

drivers/nvme/host/fabrics.h

@@ -171,13 +171,14 @@ static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl,
 	    cmd->common.opcode != nvme_fabrics_command ||
 	    cmd->fabrics.fctype != nvme_fabrics_type_connect) {
 		/*
-		 * Reconnecting state means transport disruption, which can take
-		 * a long time and even might fail permanently, fail fast to
-		 * give upper layers a chance to failover.
+		 * Connecting state means transport disruption or initial
+		 * establishment, which can take a long time and even might
+		 * fail permanently, fail fast to give upper layers a chance
+		 * to failover.
 		 * Deleting state means that the ctrl will never accept commands
 		 * again, fail it permanently.
 		 */
-		if (ctrl->state == NVME_CTRL_RECONNECTING ||
+		if (ctrl->state == NVME_CTRL_CONNECTING ||
 		    ctrl->state == NVME_CTRL_DELETING) {
 			nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 			return BLK_STS_IOERR;

drivers/nvme/host/fc.c

@@ -55,9 +55,7 @@ struct nvme_fc_queue {
 
 enum nvme_fcop_flags {
 	FCOP_FLAGS_TERMIO	= (1 << 0),
-	FCOP_FLAGS_RELEASED	= (1 << 1),
-	FCOP_FLAGS_COMPLETE	= (1 << 2),
-	FCOP_FLAGS_AEN		= (1 << 3),
+	FCOP_FLAGS_AEN		= (1 << 1),
 };
 
 struct nvmefc_ls_req_op {
@@ -532,7 +530,7 @@ nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl)
 {
 	switch (ctrl->ctrl.state) {
 	case NVME_CTRL_NEW:
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		/*
 		 * As all reconnects were suppressed, schedule a
 		 * connect.
@@ -777,7 +775,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		}
 		break;
 
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		/*
 		 * The association has already been terminated and the
 		 * controller is attempting reconnects.  No need to do anything
@@ -1470,7 +1468,6 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 
 /* *********************** NVME Ctrl Routines **************************** */
 
-static void __nvme_fc_final_op_cleanup(struct request *rq);
 static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg);
 
 static int
@@ -1512,13 +1509,19 @@ nvme_fc_exit_request(struct blk_mq_tag_set *set, struct request *rq,
 static int
 __nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
 {
-	int state;
+	unsigned long flags;
+	int opstate;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	opstate = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
+	if (opstate != FCPOP_STATE_ACTIVE)
+		atomic_set(&op->state, opstate);
+	else if (ctrl->flags & FCCTRL_TERMIO)
+		ctrl->iocnt++;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
-	state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
-	if (state != FCPOP_STATE_ACTIVE) {
-		atomic_set(&op->state, state);
+	if (opstate != FCPOP_STATE_ACTIVE)
 		return -ECANCELED;
-	}
 
 	ctrl->lport->ops->fcp_abort(&ctrl->lport->localport,
 					&ctrl->rport->remoteport,
@@ -1532,60 +1535,26 @@ static void
 nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl)
 {
 	struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops;
-	unsigned long flags;
-	int i, ret;
-
-	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) {
-		if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE)
-			continue;
-
-		spin_lock_irqsave(&ctrl->lock, flags);
-		if (ctrl->flags & FCCTRL_TERMIO) {
-			ctrl->iocnt++;
-			aen_op->flags |= FCOP_FLAGS_TERMIO;
-		}
-		spin_unlock_irqrestore(&ctrl->lock, flags);
-
-		ret = __nvme_fc_abort_op(ctrl, aen_op);
-		if (ret) {
-			/*
-			 * if __nvme_fc_abort_op failed the io wasn't
-			 * active. Thus this call path is running in
-			 * parallel to the io complete. Treat as non-error.
-			 */
+	int i;
 
-			/* back out the flags/counters */
-			spin_lock_irqsave(&ctrl->lock, flags);
-			if (ctrl->flags & FCCTRL_TERMIO)
-				ctrl->iocnt--;
-			aen_op->flags &= ~FCOP_FLAGS_TERMIO;
-			spin_unlock_irqrestore(&ctrl->lock, flags);
-			return;
-		}
-	}
+	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++)
+		__nvme_fc_abort_op(ctrl, aen_op);
 }
 
-static inline int
+static inline void
 __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
-		struct nvme_fc_fcp_op *op)
+		struct nvme_fc_fcp_op *op, int opstate)
 {
 	unsigned long flags;
-	bool complete_rq = false;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
+	if (opstate == FCPOP_STATE_ABORTED) {
+		spin_lock_irqsave(&ctrl->lock, flags);
 		if (ctrl->flags & FCCTRL_TERMIO) {
 			if (!--ctrl->iocnt)
 				wake_up(&ctrl->ioabort_wait);
 		}
+		spin_unlock_irqrestore(&ctrl->lock, flags);
 	}
-	if (op->flags & FCOP_FLAGS_RELEASED)
-		complete_rq = true;
-	else
-		op->flags |= FCOP_FLAGS_COMPLETE;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	return complete_rq;
 }
 
 static void
@@ -1601,6 +1570,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	__le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
 	union nvme_result result;
 	bool terminate_assoc = true;
+	int opstate;
 
 	/*
 	 * WARNING:
@@ -1639,11 +1609,12 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	 * association to be terminated.
 	 */
 
+	opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE);
+
 	fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma,
 				sizeof(op->rsp_iu), DMA_FROM_DEVICE);
 
-	if (atomic_read(&op->state) == FCPOP_STATE_ABORTED ||
-			op->flags & FCOP_FLAGS_TERMIO)
+	if (opstate == FCPOP_STATE_ABORTED)
 		status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
 	else if (freq->status)
 		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
@@ -1708,7 +1679,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 done:
 	if (op->flags & FCOP_FLAGS_AEN) {
 		nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
-		__nvme_fc_fcpop_chk_teardowns(ctrl, op);
+		__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
 		atomic_set(&op->state, FCPOP_STATE_IDLE);
 		op->flags = FCOP_FLAGS_AEN;	/* clear other flags */
 		nvme_fc_ctrl_put(ctrl);
@@ -1722,13 +1693,11 @@ done:
 	if (status &&
 	    (blk_queue_dying(rq->q) ||
 	     ctrl->ctrl.state == NVME_CTRL_NEW ||
-	     ctrl->ctrl.state == NVME_CTRL_RECONNECTING))
+	     ctrl->ctrl.state == NVME_CTRL_CONNECTING))
 		status |= cpu_to_le16(NVME_SC_DNR << 1);
 
-	if (__nvme_fc_fcpop_chk_teardowns(ctrl, op))
-		__nvme_fc_final_op_cleanup(rq);
-	else
-		nvme_end_request(rq, status, result);
+	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
+	nvme_end_request(rq, status, result);
 
 check_error:
 	if (terminate_assoc)
@@ -2415,46 +2384,16 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg)
 }
 
 static void
-__nvme_fc_final_op_cleanup(struct request *rq)
+nvme_fc_complete_rq(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);
-	op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED |
-			FCOP_FLAGS_COMPLETE);
 
 	nvme_fc_unmap_data(ctrl, rq, op);
 	nvme_complete_rq(rq);
 	nvme_fc_ctrl_put(ctrl);
-
-}
-
-static void
-nvme_fc_complete_rq(struct request *rq)
-{
-	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
-	struct nvme_fc_ctrl *ctrl = op->ctrl;
-	unsigned long flags;
-	bool completed = false;
-
-	/*
-	 * the core layer, on controller resets after calling
-	 * nvme_shutdown_ctrl(), calls complete_rq without our
-	 * calling blk_mq_complete_request(), thus there may still
-	 * be live i/o outstanding with the LLDD. Means transport has
-	 * to track complete calls vs fcpio_done calls to know what
-	 * path to take on completes and dones.
-	 */
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (op->flags & FCOP_FLAGS_COMPLETE)
-		completed = true;
-	else
-		op->flags |= FCOP_FLAGS_RELEASED;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	if (completed)
-		__nvme_fc_final_op_cleanup(rq);
 }
 
 /*
@@ -2476,35 +2415,11 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
 	struct nvme_ctrl *nctrl = data;
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
-	unsigned long flags;
-	int status;
 
 	if (!blk_mq_request_started(req))
 		return;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (ctrl->flags & FCCTRL_TERMIO) {
-		ctrl->iocnt++;
-		op->flags |= FCOP_FLAGS_TERMIO;
-	}
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	status = __nvme_fc_abort_op(ctrl, op);
-	if (status) {
-		/*
-		 * if __nvme_fc_abort_op failed the io wasn't
-		 * active. Thus this call path is running in
-		 * parallel to the io complete. Treat as non-error.
-		 */
-
-		/* back out the flags/counters */
-		spin_lock_irqsave(&ctrl->lock, flags);
-		if (ctrl->flags & FCCTRL_TERMIO)
-			ctrl->iocnt--;
-		op->flags &= ~FCOP_FLAGS_TERMIO;
-		spin_unlock_irqrestore(&ctrl->lock, flags);
-		return;
-	}
+	__nvme_fc_abort_op(ctrl, op);
 }
 
 
@@ -2943,7 +2858,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 	unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ;
 	bool recon = true;
 
-	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING)
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING)
 		return;
 
 	if (portptr->port_state == FC_OBJSTATE_ONLINE)
@@ -2991,10 +2906,10 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
 	/* will block will waiting for io to terminate */
 	nvme_fc_delete_association(ctrl);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: error_recovery: Couldn't change state "
-			"to RECONNECTING\n", ctrl->cnum);
+			"to CONNECTING\n", ctrl->cnum);
 		return;
 	}
 
@@ -3195,7 +3110,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	 * transport errors (frame drop, LS failure) inherently must kill
 	 * the association. The transport is coded so that any command used
 	 * to create the association (prior to a LIVE state transition
-	 * while NEW or RECONNECTING) will fail if it completes in error or
+	 * while NEW or CONNECTING) will fail if it completes in error or
 	 * times out.
 	 *
 	 * As such: as the connect request was mostly likely due to a

drivers/nvme/host/nvme.h

@@ -123,7 +123,7 @@ enum nvme_ctrl_state {
 	NVME_CTRL_LIVE,
 	NVME_CTRL_ADMIN_ONLY,    /* Only admin queue live */
 	NVME_CTRL_RESETTING,
-	NVME_CTRL_RECONNECTING,
+	NVME_CTRL_CONNECTING,
 	NVME_CTRL_DELETING,
 	NVME_CTRL_DEAD,
 };
@@ -183,6 +183,7 @@ struct nvme_ctrl {
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
+	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
 
 	/* Power saving configuration */

drivers/nvme/host/pci.c

@@ -1141,7 +1141,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	/* If there is a reset/reinit ongoing, we shouldn't reset again. */
 	switch (dev->ctrl.state) {
 	case NVME_CTRL_RESETTING:
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		return false;
 	default:
 		break;
@@ -1215,13 +1215,17 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * cancellation error. All outstanding requests are completed on
 	 * shutdown, so we return BLK_EH_HANDLED.
 	 */
-	if (dev->ctrl.state == NVME_CTRL_RESETTING) {
+	switch (dev->ctrl.state) {
+	case NVME_CTRL_CONNECTING:
+	case NVME_CTRL_RESETTING:
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_dev_disable(dev, false);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_HANDLED;
+	default:
+		break;
 	}
 
 	/*
@@ -1364,18 +1368,14 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 				int qid, int depth)
 {
-	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
-		unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth),
-						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
-		nvmeq->sq_cmds_io = dev->cmb + offset;
-	} else {
-		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					&nvmeq->sq_dma_addr, GFP_KERNEL);
-		if (!nvmeq->sq_cmds)
-			return -ENOMEM;
-	}
+	/* CMB SQEs will be mapped before creation */
+	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS))
+		return 0;
 
+	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+					    &nvmeq->sq_dma_addr, GFP_KERNEL);
+	if (!nvmeq->sq_cmds)
+		return -ENOMEM;
 	return 0;
 }
 
@@ -1449,6 +1449,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
 
+	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
+						      dev->ctrl.page_size);
+		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
+		nvmeq->sq_cmds_io = dev->cmb + offset;
+	}
+
 	nvmeq->cq_vector = qid - 1;
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
@@ -2288,12 +2295,12 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_dev_disable(dev, false);
 
 	/*
-	 * Introduce RECONNECTING state from nvme-fc/rdma transports to mark the
+	 * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
 	 * initializing procedure here.
 	 */
-	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_warn(dev->ctrl.device,
-			"failed to mark controller RECONNECTING\n");
+			"failed to mark controller CONNECTING\n");
 		goto out;
 	}
 

drivers/nvme/host/rdma.c

@@ -887,7 +887,7 @@ free_ctrl:
 static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 {
 	/* If we are resetting/deleting then do nothing */
-	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
 		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
 			ctrl->ctrl.state == NVME_CTRL_LIVE);
 		return;
@@ -973,7 +973,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_start_queues(&ctrl->ctrl);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure should never happen */
 		WARN_ON_ONCE(1);
 		return;
@@ -1756,7 +1756,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure should never happen */
 		WARN_ON_ONCE(1);
 		return;
@@ -1784,11 +1784,8 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 	return;
 
 out_fail:
-	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
-	nvme_remove_namespaces(&ctrl->ctrl);
-	nvme_rdma_shutdown_ctrl(ctrl, true);
-	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
+	++ctrl->ctrl.nr_reconnects;
+	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
 static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
@@ -1942,6 +1939,9 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (!ctrl->queues)
 		goto out_uninit_ctrl;
 
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
+	WARN_ON_ONCE(!changed);
+
 	ret = nvme_rdma_configure_admin_queue(ctrl, true);
 	if (ret)
 		goto out_kfree_queues;

drivers/nvme/target/io-cmd.c

@@ -105,10 +105,13 @@ static void nvmet_execute_flush(struct nvmet_req *req)
 static u16 nvmet_discard_range(struct nvmet_ns *ns,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
-	if (__blkdev_issue_discard(ns->bdev,
+	int ret;
+
+	ret = __blkdev_issue_discard(ns->bdev,
 			le64_to_cpu(range->slba) << (ns->blksize_shift - 9),
 			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
-			GFP_KERNEL, 0, bio))
+			GFP_KERNEL, 0, bio);
+	if (ret && ret != -EOPNOTSUPP)
 		return NVME_SC_INTERNAL | NVME_SC_DNR;
 	return 0;
 }

drivers/of/property.c

@@ -977,11 +977,11 @@ static int of_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
-static void *
+static const void *
 of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 				const struct device *dev)
 {
-	return (void *)of_device_get_match_data(dev);
+	return of_device_get_match_data(dev);
 }
 
 const struct fwnode_operations of_fwnode_ops = {

drivers/opp/cpu.c

@@ -55,7 +55,7 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	if (max_opps <= 0)
 		return max_opps ? max_opps : -ENODATA;
 
-	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
+	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_KERNEL);
 	if (!freq_table)
 		return -ENOMEM;
 

drivers/platform/x86/dell-laptop.c

@@ -126,24 +126,6 @@ static const struct dmi_system_id dell_device_table[] __initconst = {
 			DMI_MATCH(DMI_CHASSIS_TYPE, "32"), /*Detachable*/
 		},
 	},
-	{
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_CHASSIS_TYPE, "30"), /*Tablet*/
-		},
-	},
-	{
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /*Convertible*/
-		},
-	},
-	{
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_CHASSIS_TYPE, "32"), /*Detachable*/
-		},
-	},
 	{
 		.ident = "Dell Computer Corporation",
 		.matches = {
@@ -1279,7 +1261,7 @@ static int kbd_get_state(struct kbd_state *state)
 	struct calling_interface_buffer buffer;
 	int ret;
 
-	dell_fill_request(&buffer, 0, 0, 0, 0);
+	dell_fill_request(&buffer, 0x1, 0, 0, 0);
 	ret = dell_send_request(&buffer,
 				CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT);
 	if (ret)

drivers/platform/x86/ideapad-laptop.c

@@ -113,7 +113,7 @@ MODULE_PARM_DESC(no_bt_rfkill, "No rfkill for bluetooth.");
 /*
  * ACPI Helpers
  */
-#define IDEAPAD_EC_TIMEOUT (100) /* in ms */
+#define IDEAPAD_EC_TIMEOUT (200) /* in ms */
 
 static int read_method_int(acpi_handle handle, const char *method, int *val)
 {

drivers/platform/x86/wmi.c

@@ -933,7 +933,7 @@ static int wmi_dev_probe(struct device *dev)
 			goto probe_failure;
 		}
 
-		buf = kmalloc(strlen(wdriver->driver.name) + 4, GFP_KERNEL);
+		buf = kmalloc(strlen(wdriver->driver.name) + 5, GFP_KERNEL);
 		if (!buf) {
 			ret = -ENOMEM;
 			goto probe_string_failure;

drivers/s390/virtio/virtio_ccw.c

@@ -1297,6 +1297,9 @@ static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event)
 		vcdev->device_lost = true;
 		rc = NOTIFY_DONE;
 		break;
+	case CIO_OPER:
+		rc = NOTIFY_OK;
+		break;
 	default:
 		rc = NOTIFY_DONE;
 		break;
@@ -1309,6 +1312,27 @@ static struct ccw_device_id virtio_ids[] = {
 	{},
 };
 
+#ifdef CONFIG_PM_SLEEP
+static int virtio_ccw_freeze(struct ccw_device *cdev)
+{
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+
+	return virtio_device_freeze(&vcdev->vdev);
+}
+
+static int virtio_ccw_restore(struct ccw_device *cdev)
+{
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+	int ret;
+
+	ret = virtio_ccw_set_transport_rev(vcdev);
+	if (ret)
+		return ret;
+
+	return virtio_device_restore(&vcdev->vdev);
+}
+#endif
+
 static struct ccw_driver virtio_ccw_driver = {
 	.driver = {
 		.owner = THIS_MODULE,
@@ -1321,6 +1345,11 @@ static struct ccw_driver virtio_ccw_driver = {
 	.set_online = virtio_ccw_online,
 	.notify = virtio_ccw_cio_notify,
 	.int_class = IRQIO_VIR,
+#ifdef CONFIG_PM_SLEEP
+	.freeze = virtio_ccw_freeze,
+	.thaw = virtio_ccw_restore,
+	.restore = virtio_ccw_restore,
+#endif
 };
 
 static int __init pure_hex(char **cp, unsigned int *val, int min_digit,

drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c

@@ -73,6 +73,8 @@ static int __init its_fsl_mc_msi_init(void)
 
 	for (np = of_find_matching_node(NULL, its_device_id); np;
 	     np = of_find_matching_node(np, its_device_id)) {
+		if (!of_device_is_available(np))
+			continue;
 		if (!of_property_read_bool(np, "msi-controller"))
 			continue;
 

drivers/usb/Kconfig

@@ -19,6 +19,12 @@ config USB_EHCI_BIG_ENDIAN_MMIO
 config USB_EHCI_BIG_ENDIAN_DESC
 	bool
 
+config USB_UHCI_BIG_ENDIAN_MMIO
+	bool
+
+config USB_UHCI_BIG_ENDIAN_DESC
+	bool
+
 menuconfig USB_SUPPORT
 	bool "USB support"
 	depends on HAS_IOMEM

drivers/usb/host/Kconfig

@@ -633,14 +633,6 @@ config USB_UHCI_ASPEED
        bool
        default y if ARCH_ASPEED
 
-config USB_UHCI_BIG_ENDIAN_MMIO
-	bool
-	default y if SPARC_LEON
-
-config USB_UHCI_BIG_ENDIAN_DESC
-	bool
-	default y if SPARC_LEON
-
 config USB_FHCI_HCD
 	tristate "Freescale QE USB Host Controller support"
 	depends on OF_GPIO && QE_GPIO && QUICC_ENGINE

drivers/xen/pvcalls-front.c

@@ -60,6 +60,7 @@ struct sock_mapping {
 	bool active_socket;
 	struct list_head list;
 	struct socket *sock;
+	atomic_t refcount;
 	union {
 		struct {
 			int irq;
@@ -93,6 +94,32 @@ struct sock_mapping {
 	};
 };
 
+static inline struct sock_mapping *pvcalls_enter_sock(struct socket *sock)
+{
+	struct sock_mapping *map;
+
+	if (!pvcalls_front_dev ||
+		dev_get_drvdata(&pvcalls_front_dev->dev) == NULL)
+		return ERR_PTR(-ENOTCONN);
+
+	map = (struct sock_mapping *)sock->sk->sk_send_head;
+	if (map == NULL)
+		return ERR_PTR(-ENOTSOCK);
+
+	pvcalls_enter();
+	atomic_inc(&map->refcount);
+	return map;
+}
+
+static inline void pvcalls_exit_sock(struct socket *sock)
+{
+	struct sock_mapping *map;
+
+	map = (struct sock_mapping *)sock->sk->sk_send_head;
+	atomic_dec(&map->refcount);
+	pvcalls_exit();
+}
+
 static inline int get_request(struct pvcalls_bedata *bedata, int *req_id)
 {
 	*req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
@@ -369,31 +396,23 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -ENOTCONN;
-	}
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *)sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	ret = create_active(map, &evtchn);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 
@@ -423,7 +442,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	smp_rmb();
 	ret = bedata->rsp[req_id].ret;
 	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -488,23 +507,15 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -ENOTCONN;
-	}
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	mutex_lock(&map->active.out_mutex);
 	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
 		mutex_unlock(&map->active.out_mutex);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EAGAIN;
 	}
 	if (len > INT_MAX)
@@ -526,7 +537,7 @@ again:
 		tot_sent = sent;
 
 	mutex_unlock(&map->active.out_mutex);
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return tot_sent;
 }
 
@@ -591,19 +602,11 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -ENOTCONN;
-	}
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	mutex_lock(&map->active.in_mutex);
 	if (len > XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER))
 		len = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
@@ -623,7 +626,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		ret = 0;
 
 	mutex_unlock(&map->active.in_mutex);
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -637,24 +640,16 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -ENOTCONN;
-	}
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (map == NULL) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	req = RING_GET_REQUEST(&bedata->ring, req_id);
@@ -684,7 +679,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
 
 	map->passive.status = PVCALLS_STATUS_BIND;
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return 0;
 }
 
@@ -695,21 +690,13 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	struct xen_pvcalls_request *req;
 	int notify, req_id, ret;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -ENOTCONN;
-	}
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	if (map->passive.status != PVCALLS_STATUS_BIND) {
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EOPNOTSUPP;
 	}
 
@@ -717,7 +704,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	req = RING_GET_REQUEST(&bedata->ring, req_id);
@@ -741,7 +728,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
 
 	map->passive.status = PVCALLS_STATUS_LISTEN;
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -753,21 +740,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct xen_pvcalls_request *req;
 	int notify, req_id, ret, evtchn, nonblock;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -ENOTCONN;
-	}
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	if (map->passive.status != PVCALLS_STATUS_LISTEN) {
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EINVAL;
 	}
 
@@ -785,13 +764,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 			goto received;
 		}
 		if (nonblock) {
-			pvcalls_exit();
+			pvcalls_exit_sock(sock);
 			return -EAGAIN;
 		}
 		if (wait_event_interruptible(map->passive.inflight_accept_req,
 			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 					  (void *)&map->passive.flags))) {
-			pvcalls_exit();
+			pvcalls_exit_sock(sock);
 			return -EINTR;
 		}
 	}
@@ -802,7 +781,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	map2 = kzalloc(sizeof(*map2), GFP_ATOMIC);
@@ -810,7 +789,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -ENOMEM;
 	}
 	ret = create_active(map2, &evtchn);
@@ -819,7 +798,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	list_add_tail(&map2->list, &bedata->socket_mappings);
@@ -841,13 +820,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 	/* We could check if we have received a response before returning. */
 	if (nonblock) {
 		WRITE_ONCE(map->passive.inflight_req_id, req_id);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EAGAIN;
 	}
 
 	if (wait_event_interruptible(bedata->inflight_req,
 		READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) {
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EINTR;
 	}
 	/* read req_id, then the content */
@@ -862,7 +841,7 @@ received:
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		pvcalls_front_free_map(bedata, map2);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -ENOMEM;
 	}
 	newsock->sk->sk_send_head = (void *)map2;
@@ -874,7 +853,7 @@ received:
 	clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags);
 	wake_up(&map->passive.inflight_accept_req);
 
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -965,23 +944,16 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock,
 	struct sock_mapping *map;
 	__poll_t ret;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map))
 		return EPOLLNVAL;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return EPOLLNVAL;
-	}
 	if (map->active_socket)
 		ret = pvcalls_front_poll_active(file, bedata, map, wait);
 	else
 		ret = pvcalls_front_poll_passive(file, bedata, map, wait);
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -995,25 +967,20 @@ int pvcalls_front_release(struct socket *sock)
 	if (sock->sk == NULL)
 		return 0;
 
-	pvcalls_enter();
-	if (!pvcalls_front_dev) {
-		pvcalls_exit();
-		return -EIO;
+	map = pvcalls_enter_sock(sock);
+	if (IS_ERR(map)) {
+		if (PTR_ERR(map) == -ENOTCONN)
+			return -EIO;
+		else
+			return 0;
 	}
-
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (map == NULL) {
-		pvcalls_exit();
-		return 0;
-	}
-
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	sock->sk->sk_send_head = NULL;
@@ -1043,14 +1010,20 @@ int pvcalls_front_release(struct socket *sock)
 		/*
 		 * We need to make sure that sendmsg/recvmsg on this socket have
 		 * not started before we've cleared sk_send_head here. The
-		 * easiest (though not optimal) way to guarantee this is to see
-		 * that no pvcall (other than us) is in progress.
+		 * easiest way to guarantee this is to see that no pvcalls
+		 * (other than us) is in progress on this socket.
 		 */
-		while (atomic_read(&pvcalls_refcount) > 1)
+		while (atomic_read(&map->refcount) > 1)
 			cpu_relax();
 
 		pvcalls_front_free_map(bedata, map);
 	} else {
+		wake_up(&bedata->inflight_req);
+		wake_up(&map->passive.inflight_accept_req);
+
+		while (atomic_read(&map->refcount) > 1)
+			cpu_relax();
+
 		spin_lock(&bedata->socket_lock);
 		list_del(&map->list);
 		spin_unlock(&bedata->socket_lock);

drivers/xen/xenbus/xenbus.h

@@ -76,6 +76,7 @@ struct xb_req_data {
 	struct list_head list;
 	wait_queue_head_t wq;
 	struct xsd_sockmsg msg;
+	uint32_t caller_req_id;
 	enum xsd_sockmsg_type type;
 	char *body;
 	const struct kvec *vec;

drivers/xen/xenbus/xenbus_comms.c

@@ -309,6 +309,7 @@ static int process_msg(void)
 			goto out;
 
 		if (req->state == xb_req_state_wait_reply) {
+			req->msg.req_id = req->caller_req_id;
 			req->msg.type = state.msg.type;
 			req->msg.len = state.msg.len;
 			req->body = state.body;

drivers/xen/xenbus/xenbus_xs.c

@@ -227,6 +227,8 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	req->state = xb_req_state_queued;
 	init_waitqueue_head(&req->wq);
 
+	/* Save the caller req_id and restore it later in the reply */
+	req->caller_req_id = req->msg.req_id;
 	req->msg.req_id = xs_request_enter(req);
 
 	mutex_lock(&xb_write_mutex);
@@ -310,6 +312,7 @@ static void *xs_talkv(struct xenbus_transaction t,
 	req->num_vecs = num_vecs;
 	req->cb = xs_wake_up;
 
+	msg.req_id = 0;
 	msg.tx_id = t.id;
 	msg.type = type;
 	msg.len = 0;

fs/btrfs/backref.c

@@ -1264,7 +1264,16 @@ again:
 	while (node) {
 		ref = rb_entry(node, struct prelim_ref, rbnode);
 		node = rb_next(&ref->rbnode);
-		WARN_ON(ref->count < 0);
+		/*
+		 * ref->count < 0 can happen here if there are delayed
+		 * refs with a node->action of BTRFS_DROP_DELAYED_REF.
+		 * prelim_ref_insert() relies on this when merging
+		 * identical refs to keep the overall count correct.
+		 * prelim_ref_insert() will merge only those refs
+		 * which compare identically.  Any refs having
+		 * e.g. different offsets would not be merged,
+		 * and would retain their original ref->count < 0.
+		 */
 		if (roots && ref->count && ref->root_id && ref->parent == 0) {
 			if (sc && sc->root_objectid &&
 			    ref->root_id != sc->root_objectid) {