This is the 4.9.32 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAllBNNMACgkQONu9yGCS
 aT4rJA//XOtxp2nr01OqffSItCX0vq7vMofbjo7spI2LF3JyxKkx0hje0im82XoD
 cYhZHyeK9lCHRZt2O541xOp3ITconecRvlt6uq49zKNvlFAelnp0rRTOktluJK/n
 Xm7EP2KLHeHXv+rvCfzU0hDC9fvoZe82NIF7kddAWHX4D/K3C6Jw6FVc4/QPl2MG
 11R6pylPtMGObgPEmfDlohBitcC3KawXAhIcyTTAr3rcuO2Wm00H+uF0VOpyD9hZ
 S5A8ecuyZVQw3mIKAJ9vOwkVoln1E+/P/OltWEXElkBZONHpI4LB2IE7Nmwnx+pE
 5oO3afNZIYOejX+GQvK2Apc8VONDV2VZRoIstzl+uaKDNGFaSLIu8AQ/UQfmoqTE
 Pwrp/FxgDGjq6NOf/+MqNhiqS9433Xgmt4HT5xctzS0zFNGzLIokdjRH3x7n6cez
 2JvdtRvJfdNq31kh6xQE/8oXuZktRSw3GxC5K4Dw3NRh02/9KNAgEjNPEMNXziGw
 RhLhyXl8i5eGAu1gxruojzRyCvaMS6S8ZcAvSSoJze0kj8jfkZtQbBswvS1LF9EI
 FFemshd1sQxUeZiXGYPuUUfyDvxvs7KRIqAYux8lsIhSQTu16REqsZRrzidpDP+K
 xtH61YBWhwDHZKIoT+Jchmn8QCytI77MvFdGuTl+KRPV4OyyeJs=
 =NE4C
 -----END PGP SIGNATURE-----

Merge 4.9.32 into android-4.9

Changes in 4.9.32
	bnx2x: Fix Multi-Cos
	vxlan: eliminate cached dst leak
	ipv6: xfrm: Handle errors reported by xfrm6_find_1stfragopt()
	cxgb4: avoid enabling napi twice to the same queue
	tcp: disallow cwnd undo when switching congestion control
	vxlan: fix use-after-free on deletion
	ipv6: Fix leak in ipv6_gso_segment().
	net: ping: do not abuse udp_poll()
	net/ipv6: Fix CALIPSO causing GPF with datagram support
	net: ethoc: enable NAPI before poll may be scheduled
	net: stmmac: fix completely hung TX when using TSO
	net: bridge: start hello timer only if device is up
	sparc64: Add __multi3 for gcc 7.x and later.
	sparc64: mm: fix copy_tsb to correctly copy huge page TSBs
	sparc: Machine description indices can vary
	sparc64: reset mm cpumask after wrap
	sparc64: combine activate_mm and switch_mm
	sparc64: redefine first version
	sparc64: add per-cpu mm of secondary contexts
	sparc64: new context wrap
	sparc64: delete old wrap code
	arch/sparc: support NR_CPUS = 4096
	serial: ifx6x60: fix use-after-free on module unload
	ptrace: Properly initialize ptracer_cred on fork
	crypto: asymmetric_keys - handle EBUSY due to backlog correctly
	KEYS: fix dereferencing NULL payload with nonzero length
	KEYS: fix freeing uninitialized memory in key_update()
	KEYS: encrypted: avoid encrypting/decrypting stack buffers
	crypto: drbg - wait for crypto op not signal safe
	crypto: gcm - wait for crypto op not signal safe
	drm/amdgpu/ci: disable mclk switching for high refresh rates (v2)
	nfsd4: fix null dereference on replay
	nfsd: Fix up the "supattr_exclcreat" attributes
	efi: Don't issue error message when booted under Xen
	kvm: async_pf: fix rcu_irq_enter() with irqs enabled
	KVM: cpuid: Fix read/write out-of-bounds vulnerability in cpuid emulation
	arm64: KVM: Preserve RES1 bits in SCTLR_EL2
	arm64: KVM: Allow unaligned accesses at EL2
	arm: KVM: Allow unaligned accesses at HYP
	KVM: async_pf: avoid async pf injection when in guest mode
	KVM: arm/arm64: vgic-v3: Do not use Active+Pending state for a HW interrupt
	KVM: arm/arm64: vgic-v2: Do not use Active+Pending state for a HW interrupt
	dmaengine: usb-dmac: Fix DMAOR AE bit definition
	dmaengine: ep93xx: Always start from BASE0
	dmaengine: ep93xx: Don't drain the transfers in terminate_all()
	dmaengine: mv_xor_v2: handle mv_xor_v2_prep_sw_desc() error properly
	dmaengine: mv_xor_v2: properly handle wrapping in the array of HW descriptors
	dmaengine: mv_xor_v2: do not use descriptors not acked by async_tx
	dmaengine: mv_xor_v2: enable XOR engine after its configuration
	dmaengine: mv_xor_v2: fix tx_submit() implementation
	dmaengine: mv_xor_v2: remove interrupt coalescing
	dmaengine: mv_xor_v2: set DMA mask to 40 bits
	cfq-iosched: fix the delay of cfq_group's vdisktime under iops mode
	xen/privcmd: Support correctly 64KB page granularity when mapping memory
	ext4: fix SEEK_HOLE
	ext4: keep existing extra fields when inode expands
	ext4: fix data corruption with EXT4_GET_BLOCKS_ZERO
	ext4: fix fdatasync(2) after extent manipulation operations
	drm: Fix oops + Xserver hang when unplugging USB drm devices
	usb: gadget: f_mass_storage: Serialize wake and sleep execution
	usb: chipidea: udc: fix NULL pointer dereference if udc_start failed
	usb: chipidea: debug: check before accessing ci_role
	staging/lustre/lov: remove set_fs() call from lov_getstripe()
	iio: adc: bcm_iproc_adc: swap primary and secondary isr handler's
	iio: light: ltr501 Fix interchanged als/ps register field
	iio: proximity: as3935: fix AS3935_INT mask
	iio: proximity: as3935: fix iio_trigger_poll issue
	mei: make sysfs modalias format similar as uevent modalias
	cpufreq: cpufreq_register_driver() should return -ENODEV if init fails
	target: Re-add check to reject control WRITEs with overflow data
	drm/msm: Expose our reservation object when exporting a dmabuf.
	ahci: Acer SA5-271 SSD Not Detected Fix
	cgroup: Prevent kill_css() from being called more than once
	Input: elantech - add Fujitsu Lifebook E546/E557 to force crc_enabled
	cpuset: consider dying css as offline
	fs: add i_blocksize()
	ufs: restore proper tail allocation
	fix ufs_isblockset()
	ufs: restore maintaining ->i_blocks
	ufs: set correct ->s_maxsize
	ufs_extend_tail(): fix the braino in calling conventions of ufs_new_fragments()
	ufs_getfrag_block(): we only grab ->truncate_mutex on block creation path
	cxl: Fix error path on bad ioctl
	cxl: Avoid double free_irq() for psl,slice interrupts
	btrfs: use correct types for page indices in btrfs_page_exists_in_range
	btrfs: fix memory leak in update_space_info failure path
	KVM: arm/arm64: Handle possible NULL stage2 pud when ageing pages
	scsi: qla2xxx: don't disable a not previously enabled PCI device
	scsi: qla2xxx: Modify T262 FW dump template to specify same start/end to debug customer issues
	scsi: qla2xxx: Set bit 15 for DIAG_ECHO_TEST MBC
	scsi: qla2xxx: Fix mailbox pointer error in fwdump capture
	powerpc/sysdev/simple_gpio: Fix oops in gpio save_regs function
	powerpc/numa: Fix percpu allocations to be NUMA aware
	powerpc/hotplug-mem: Fix missing endian conversion of aa_index
	powerpc/kernel: Fix FP and vector register restoration
	powerpc/kernel: Initialize load_tm on task creation
	perf/core: Drop kernel samples even though :u is specified
	drm/vmwgfx: Handle vmalloc() failure in vmw_local_fifo_reserve()
	drm/vmwgfx: limit the number of mip levels in vmw_gb_surface_define_ioctl()
	drm/vmwgfx: Make sure backup_handle is always valid
	drm/nouveau/tmr: fully separate alarm execution/pending lists
	ALSA: timer: Fix race between read and ioctl
	ALSA: timer: Fix missing queue indices reset at SNDRV_TIMER_IOCTL_SELECT
	ASoC: Fix use-after-free at card unregistration
	cpu/hotplug: Drop the device lock on error
	drivers: char: mem: Fix wraparound check to allow mappings up to the end
	serial: sh-sci: Fix panic when serial console and DMA are enabled
	arm64: traps: fix userspace cache maintenance emulation on a tagged pointer
	arm64: hw_breakpoint: fix watchpoint matching for tagged pointers
	arm64: entry: improve data abort handling of tagged pointers
	ARM: 8636/1: Cleanup sanity_check_meminfo
	ARM: 8637/1: Adjust memory boundaries after reservations
	usercopy: Adjust tests to deal with SMAP/PAN
	drm/i915/vbt: don't propagate errors from intel_bios_init()
	drm/i915/vbt: split out defaults that are set when there is no VBT
	cpufreq: schedutil: move cached_raw_freq to struct sugov_policy
	cpufreq: schedutil: Fix per-CPU structure initialization in sugov_start()
	netfilter: nft_set_rbtree: handle element re-addition after deletion
	Linux 4.9.32

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 31
+SUBLEVEL = 32
 EXTRAVERSION =
 NAME = Roaring Lionus
 

arch/arm/kernel/setup.c

@@ -81,7 +81,7 @@ __setup("fpe=", fpe_setup);
 extern void init_default_cache_policy(unsigned long);
 extern void paging_init(const struct machine_desc *desc);
 extern void early_paging_init(const struct machine_desc *);
-extern void sanity_check_meminfo(void);
+extern void adjust_lowmem_bounds(void);
 extern enum reboot_mode reboot_mode;
 extern void setup_dma_zone(const struct machine_desc *desc);
 
@@ -1093,8 +1093,14 @@ void __init setup_arch(char **cmdline_p)
 	setup_dma_zone(mdesc);
 	xen_early_init();
 	efi_init();
-	sanity_check_meminfo();
+	/*
+	 * Make sure the calculation for lowmem/highmem is set appropriately
+	 * before reserving/allocating any mmeory
+	 */
+	adjust_lowmem_bounds();
 	arm_memblock_init(mdesc);
+	/* Memory may have been removed so recalculate the bounds. */
+	adjust_lowmem_bounds();
 
 	early_ioremap_reset();
 

arch/arm/kvm/init.S

@@ -95,7 +95,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -103,8 +102,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR

arch/arm/kvm/mmu.c

@@ -872,6 +872,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud)
+		return NULL;
+
 	if (stage2_pud_none(*pud)) {
 		if (!cache)
 			return NULL;

arch/arm/mm/mmu.c

@@ -1152,13 +1152,12 @@ early_param("vmalloc", early_vmalloc);
 
 phys_addr_t arm_lowmem_limit __initdata = 0;
 
-void __init sanity_check_meminfo(void)
+void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t memblock_limit = 0;
-	int highmem = 0;
 	u64 vmalloc_limit;
 	struct memblock_region *reg;
-	bool should_use_highmem = false;
+	phys_addr_t lowmem_limit = 0;
 
 	/*
 	 * Let's use our own (unoptimized) equivalent of __pa() that is
@@ -1172,43 +1171,18 @@ void __init sanity_check_meminfo(void)
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
-		phys_addr_t size_limit = reg->size;
 
-		if (reg->base >= vmalloc_limit)
+		if (reg->base < vmalloc_limit) {
-			highmem = 1;
+			if (block_end > lowmem_limit)
-		else
+				/*
-			size_limit = vmalloc_limit - reg->base;
+				 * Compare as u64 to ensure vmalloc_limit does
-
+				 * not get truncated. block_end should always
-
+				 * fit in phys_addr_t so there should be no
-		if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
+				 * issue with assignment.
-
+				 */
-			if (highmem) {
+				lowmem_limit = min_t(u64,
-				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
+							 vmalloc_limit,
-					  &block_start, &block_end);
+							 block_end);
-				memblock_remove(reg->base, reg->size);
-				should_use_highmem = true;
-				continue;
-			}
-
-			if (reg->size > size_limit) {
-				phys_addr_t overlap_size = reg->size - size_limit;
-
-				pr_notice("Truncating RAM at %pa-%pa",
-					  &block_start, &block_end);
-				block_end = vmalloc_limit;
-				pr_cont(" to -%pa", &block_end);
-				memblock_remove(vmalloc_limit, overlap_size);
-				should_use_highmem = true;
-			}
-		}
-
-		if (!highmem) {
-			if (block_end > arm_lowmem_limit) {
-				if (reg->size > size_limit)
-					arm_lowmem_limit = vmalloc_limit;
-				else
-					arm_lowmem_limit = block_end;
-			}
 
 			/*
 			 * Find the first non-pmd-aligned page, and point
@@ -1227,14 +1201,13 @@ void __init sanity_check_meminfo(void)
 				if (!IS_ALIGNED(block_start, PMD_SIZE))
 					memblock_limit = block_start;
 				else if (!IS_ALIGNED(block_end, PMD_SIZE))
-					memblock_limit = arm_lowmem_limit;
+					memblock_limit = lowmem_limit;
 			}
 
 		}
 	}
 
-	if (should_use_highmem)
+	arm_lowmem_limit = lowmem_limit;
-		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
@@ -1248,6 +1221,18 @@ void __init sanity_check_meminfo(void)
 	if (!memblock_limit)
 		memblock_limit = arm_lowmem_limit;
 
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
+		if (memblock_end_of_DRAM() > arm_lowmem_limit) {
+			phys_addr_t end = memblock_end_of_DRAM();
+
+			pr_notice("Ignoring RAM at %pa-%pa\n",
+				  &memblock_limit, &end);
+			pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
+			memblock_remove(memblock_limit, end - memblock_limit);
+		}
+	}
+
 	memblock_set_current_limit(memblock_limit);
 }
 

arch/arm/mm/nommu.c

@@ -85,7 +85,7 @@ static unsigned long irbar_read(void)
 }
 
 /* MPU initialisation functions */
-void __init sanity_check_meminfo_mpu(void)
+void __init adjust_lowmem_bounds_mpu(void)
 {
 	phys_addr_t phys_offset = PHYS_OFFSET;
 	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
@@ -274,7 +274,7 @@ void __init mpu_setup(void)
 	}
 }
 #else
-static void sanity_check_meminfo_mpu(void) {}
+static void adjust_lowmem_bounds_mpu(void) {}
 static void __init mpu_setup(void) {}
 #endif /* CONFIG_ARM_MPU */
 
@@ -295,10 +295,10 @@ void __init arm_mm_memblock_reserve(void)
 #endif
 }
 
-void __init sanity_check_meminfo(void)
+void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t end;
-	sanity_check_meminfo_mpu();
+	adjust_lowmem_bounds_mpu();
 	end = memblock_end_of_DRAM();
 	high_memory = __va(end - 1) + 1;
 	memblock_set_current_limit(end);

arch/arm64/include/asm/asm-uaccess.h

@@ -0,0 +1,13 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+/*
+ * Remove the address tag from a virtual address, if present.
+ */
+	.macro	clear_address_tag, dst, addr
+	tst	\addr, #(1 << 55)
+	bic	\dst, \addr, #(0xff << 56)
+	csel	\dst, \dst, \addr, eq
+	.endm
+
+#endif

arch/arm64/include/asm/sysreg.h

@@ -94,6 +94,10 @@
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
+			 (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+			 (1 << 28) | (1 << 29))
+
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I)
 

arch/arm64/include/asm/uaccess.h

@@ -109,9 +109,9 @@ static inline void set_fs(mm_segment_t fs)
 })
 
 /*
- * When dealing with data aborts or instruction traps we may end up with
+ * When dealing with data aborts, watchpoints, or instruction traps we may end
- * a tagged userland pointer. Clear the tag to get a sane pointer to pass
+ * up with a tagged userland pointer. Clear the tag to get a sane pointer to
- * on to access_ok(), for instance.
+ * pass on to access_ok(), for instance.
  */
 #define untagged_addr(addr)		sign_extend64(addr, 55)
 

arch/arm64/kernel/entry.S

@@ -32,6 +32,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
 
 /*
@@ -428,12 +429,13 @@ el1_da:
 	/*
 	 * Data abort handling
 	 */
-	mrs	x0, far_el1
+	mrs	x3, far_el1
 	enable_dbg
 	// re-enable interrupts if they were enabled in the aborted context
 	tbnz	x23, #7, 1f			// PSR_I_BIT
 	enable_irq
 1:
+	clear_address_tag x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
@@ -594,7 +596,7 @@ el0_da:
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
 	ct_user_exit
-	bic	x0, x26, #(0xff << 56)
+	clear_address_tag x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort

arch/arm64/kernel/hw_breakpoint.c

@@ -36,6 +36,7 @@
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
+#include <asm/uaccess.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);

arch/arm64/kernel/traps.c

@@ -435,7 +435,7 @@ int cpu_enable_cache_maint_trap(void *__unused)
 }
 
 #define __user_cache_maint(insn, address, res)			\
-	if (untagged_addr(address) >= user_addr_max()) {	\
+	if (address >= user_addr_max()) {			\
 		res = -EFAULT;					\
 	} else {						\
 		uaccess_ttbr0_enable();				\
@@ -461,7 +461,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
 	int ret = 0;
 
-	address = (rt == 31) ? 0 : regs->regs[rt];
+	address = (rt == 31) ? 0 : untagged_addr(regs->regs[rt]);
 
 	switch (crm) {
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAU:	/* DC CVAU, gets promoted */

arch/arm64/kvm/hyp-init.S

@@ -102,10 +102,13 @@ __do_hyp_init:
 	tlbi	alle2
 	dsb	sy
 
-	mrs	x4, sctlr_el2
+	/*
-	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
+	 * Preserve all the RES1 bits while setting the default flags,
-	ldr	x5, =SCTLR_ELx_FLAGS
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
-	orr	x4, x4, x5
+	 * is allowed to generate unaligned accesses.
+	 */
+	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
 

arch/powerpc/include/asm/topology.h

@@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void);
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
 
+static inline int early_cpu_to_node(int cpu)
+{
+	int nid;
+
+	nid = numa_cpu_lookup_table[cpu];
+
+	/*
+	 * Fall back to node 0 if nid is unset (it should be, except bugs).
+	 * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+	 */
+	return (nid < 0) ? 0 : nid;
+}
 #else
 
+static inline int early_cpu_to_node(int cpu) { return 0; }
+
 static inline void dump_numa_cpu_topology(void) {}
 
 static inline int sysfs_add_device_to_node(struct device *dev, int nid)

arch/powerpc/kernel/process.c

@@ -1659,6 +1659,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
 #ifdef CONFIG_ALTIVEC
@@ -1667,6 +1668,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.vr_save_area = NULL;
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
+	current->thread.load_vec = 0;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_SPE
 	memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1678,6 +1680,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
+	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
 EXPORT_SYMBOL(start_thread);

arch/powerpc/kernel/setup_64.c

@@ -595,7 +595,7 @@ void __init emergency_stack_init(void)
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }
 
@@ -606,7 +606,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;

arch/powerpc/platforms/pseries/hotplug-memory.c

@@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
 		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
 		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
 	}
 
@@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn,
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
 		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
 		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
 	}
 

arch/powerpc/sysdev/simple_gpio.c

@@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc);
+	struct u8_gpio_chip *u8_gc =
+		container_of(mm_gc, struct u8_gpio_chip, mm_gc);
 
 	u8_gc->data = in_8(mm_gc->regs);
 }

arch/sparc/Kconfig

@@ -187,9 +187,9 @@ config NR_CPUS
 	int "Maximum number of CPUs"
 	depends on SMP
 	range 2 32 if SPARC32
-	range 2 1024 if SPARC64
+	range 2 4096 if SPARC64
 	default 32 if SPARC32
-	default 64 if SPARC64
+	default 4096 if SPARC64
 
 source kernel/Kconfig.hz
 

arch/sparc/include/asm/mmu_64.h

@@ -52,7 +52,7 @@
 #define CTX_NR_MASK		TAG_CONTEXT_BITS
 #define CTX_HW_MASK		(CTX_NR_MASK | CTX_PGSZ_MASK)
 
-#define CTX_FIRST_VERSION	((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION	BIT(CTX_VERSION_SHIFT)
 #define CTX_VALID(__ctx)	\
 	 (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
 #define CTX_HWBITS(__ctx)	((__ctx.sparc64_ctx_val) & CTX_HW_MASK)

arch/sparc/include/asm/mmu_context_64.h

@@ -17,13 +17,8 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
 void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
@@ -74,8 +69,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long ctx_valid, flags;
-	int cpu;
+	int cpu = smp_processor_id();
 
+	per_cpu(per_cpu_secondary_mm, cpu) = mm;
 	if (unlikely(mm == &init_mm))
 		return;
 
@@ -121,7 +117,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * for the first time, we must flush that context out of the
 	 * local TLB.
 	 */
-	cpu = smp_processor_id();
 	if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
 		cpumask_set_cpu(cpu, mm_cpumask(mm));
 		__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -131,26 +126,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
-	unsigned long flags;
-	int cpu;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-	if (!CTX_VALID(mm->context))
-		get_new_mmu_context(mm);
-	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_set_cpu(cpu, mm_cpumask(mm));
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
-	tsb_context_switch(mm);
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__SPARC64_MMU_CONTEXT_H) */

arch/sparc/include/asm/pil.h

@@ -20,7 +20,6 @@
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
 #define PIL_SMP_CAPTURE		3
-#define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
 #define PIL_DEFERRED_PCR_WORK	7

arch/sparc/include/asm/vio.h

@@ -327,6 +327,7 @@ struct vio_dev {
 	int			compat_len;
 
 	u64			dev_no;
+	u64			id;
 
 	unsigned long		channel_id;
 

arch/sparc/kernel/irq_64.c

@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
 {
 #ifdef CONFIG_SMP
 	unsigned long page;
+	void *mondo, *p;
 
-	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+	/* Make sure mondo block is 64byte aligned */
+	p = kzalloc(127, GFP_KERNEL);
+	if (!p) {
+		prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+		prom_halt();
+	}
+	mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+	tb->cpu_mondo_block_pa = __pa(mondo);
 
 	page = get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-		prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+		prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
 		prom_halt();
 	}
 
-	tb->cpu_mondo_block_pa = __pa(page);
+	tb->cpu_list_pa = __pa(page);
-	tb->cpu_list_pa = __pa(page + 64);
 #endif
 }
 

arch/sparc/kernel/kernel.h

@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 /* smp_64.c */
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
 

arch/sparc/kernel/smp_64.c

@@ -963,37 +963,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	preempt_enable();
 }
 
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
-	struct mm_struct *mm;
-	unsigned long flags;
-
-	clear_softint(1 << irq);
-
-	/* See if we need to allocate a new TLB context because
-	 * the version of the one we are using is now out of date.
-	 */
-	mm = current->active_mm;
-	if (unlikely(!mm || (mm == &init_mm)))
-		return;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-
-	if (unlikely(!CTX_VALID(mm->context)))
-		get_new_mmu_context(mm);
-
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context),
-		       SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
-	smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
 #ifdef CONFIG_KGDB
 void kgdb_roundup_cpus(unsigned long flags)
 {

arch/sparc/kernel/tsb.S

@@ -470,13 +470,16 @@ __tsb_context_switch:
 	.type	copy_tsb,#function
 copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 			 * %o2=new_tsb_base, %o3=new_tsb_size
+			 * %o4=page_size_shift
 			 */
 	sethi		%uhi(TSB_PASS_BITS), %g7
 	srlx		%o3, 4, %o3
-	add		%o0, %o1, %g1	/* end of old tsb */
+	add		%o0, %o1, %o1	/* end of old tsb */
 	sllx		%g7, 32, %g7
 	sub		%o3, 1, %o3	/* %o3 == new tsb hash mask */
 
+	mov		%o4, %g1	/* page_size_shift */
+
 661:	prefetcha	[%o0] ASI_N, #one_read
 	.section	.tsb_phys_patch, "ax"
 	.word		661b
@@ -501,9 +504,9 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	/* This can definitely be computed faster... */
 	srlx		%o0, 4, %o5	/* Build index */
 	and		%o5, 511, %o5	/* Mask index */
-	sllx		%o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+	sllx		%o5, %g1, %o5	/* Put into vaddr position */
 	or		%o4, %o5, %o4	/* Full VADDR. */
-	srlx		%o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+	srlx		%o4, %g1, %o4	/* Shift down to create index */
 	and		%o4, %o3, %o4	/* Mask with new_tsb_nents-1 */
 	sllx		%o4, 4, %o4	/* Shift back up into tsb ent offset */
 	TSB_STORE(%o2 + %o4, %g2)	/* Store TAG */
@@ -511,7 +514,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	TSB_STORE(%o2 + %o4, %g3)	/* Store TTE */
 
 80:	add		%o0, 16, %o0
-	cmp		%o0, %g1
+	cmp		%o0, %o1
 	bne,pt		%xcc, 90b
 	 nop
 

arch/sparc/kernel/ttable_64.S

@@ -50,7 +50,7 @@ tl0_resv03e:	BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
 tl0_irq1:	TRAP_IRQ(smp_call_function_client, 1)
 tl0_irq2:	TRAP_IRQ(smp_receive_signal_client, 2)
 tl0_irq3:	TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4:	TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4:       BTRAP(0x44)
 #else
 tl0_irq1:	BTRAP(0x41)
 tl0_irq2:	BTRAP(0x42)

arch/sparc/kernel/vio.c

@@ -302,13 +302,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (!id) {
 		dev_set_name(&vdev->dev, "%s", bus_id_name);
 		vdev->dev_no = ~(u64)0;
+		vdev->id = ~(u64)0;
 	} else if (!cfg_handle) {
 		dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
 		vdev->dev_no = *id;
+		vdev->id = ~(u64)0;
 	} else {
 		dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
 			     *cfg_handle, *id);
 		vdev->dev_no = *cfg_handle;
+		vdev->id = *id;
 	}
 
 	vdev->dev.parent = parent;
@@ -351,27 +354,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
 	(void) vio_create_one(hp, node, &root_vdev->dev);
 }
 
+struct vio_md_node_query {
+	const char *type;
+	u64 dev_no;
+	u64 id;
+};
+
 static int vio_md_node_match(struct device *dev, void *arg)
 {
+	struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
 	struct vio_dev *vdev = to_vio_dev(dev);
 
-	if (vdev->mp == (u64) arg)
+	if (vdev->dev_no != query->dev_no)
-		return 1;
+		return 0;
+	if (vdev->id != query->id)
+		return 0;
+	if (strcmp(vdev->type, query->type))
+		return 0;
 
-	return 0;
+	return 1;
 }
 
 static void vio_remove(struct mdesc_handle *hp, u64 node)
 {
+	const char *type;
+	const u64 *id, *cfg_handle;
+	u64 a;
+	struct vio_md_node_query query;
 	struct device *dev;
 
-	dev = device_find_child(&root_vdev->dev, (void *) node,
+	type = mdesc_get_property(hp, node, "device-type", NULL);
+	if (!type) {
+		type = mdesc_get_property(hp, node, "name", NULL);
+		if (!type)
+			type = mdesc_node_name(hp, node);
+	}
+
+	query.type = type;
+
+	id = mdesc_get_property(hp, node, "id", NULL);
+	cfg_handle = NULL;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target;
+
+		target = mdesc_arc_target(hp, a);
+		cfg_handle = mdesc_get_property(hp, target,
+						"cfg-handle", NULL);
+		if (cfg_handle)
+			break;
+	}
+
+	if (!id) {
+		query.dev_no = ~(u64)0;
+		query.id = ~(u64)0;
+	} else if (!cfg_handle) {
+		query.dev_no = *id;
+		query.id = ~(u64)0;
+	} else {
+		query.dev_no = *cfg_handle;
+		query.id = *id;
+	}
+
+	dev = device_find_child(&root_vdev->dev, &query,
 				vio_md_node_match);
 	if (dev) {
 		printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
 
 		device_unregister(dev);
 		put_device(dev);
+	} else {
+		if (!id)
+			printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+			       type);
+		else if (!cfg_handle)
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+			       type, *id);
+		else
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+			       type, *cfg_handle, *id);
 	}
 }
 

arch/sparc/lib/Makefile

@@ -15,6 +15,7 @@ lib-$(CONFIG_SPARC32) += copy_user.o locks.o
 lib-$(CONFIG_SPARC64) += atomic_64.o
 lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
 lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
+lib-$(CONFIG_SPARC64) += multi3.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
 lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o

arch/sparc/lib/multi3.S

@@ -0,0 +1,35 @@
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+	.text
+	.align	4
+ENTRY(__multi3) /* %o0 = u, %o1 = v */
+	mov	%o1, %g1
+	srl	%o3, 0, %g4
+	mulx	%g4, %g1, %o1
+	srlx	%g1, 0x20, %g3
+	mulx	%g3, %g4, %g5
+	sllx	%g5, 0x20, %o5
+	srl	%g1, 0, %g4
+	sub	%o1, %o5, %o5
+	srlx	%o5, 0x20, %o5
+	addcc	%g5, %o5, %g5
+	srlx	%o3, 0x20, %o5
+	mulx	%g4, %o5, %g4
+	mulx	%g3, %o5, %o5
+	sethi	%hi(0x80000000), %g3
+	addcc	%g5, %g4, %g5
+	srlx	%g5, 0x20, %g5
+	add	%g3, %g3, %g3
+	movcc	%xcc, %g0, %g3
+	addcc	%o5, %g5, %o5
+	sllx	%g4, 0x20, %g4
+	add	%o1, %g4, %o1
+	add	%o5, %g3, %g2
+	mulx	%g1, %o2, %g1
+	add	%g1, %g2, %g1
+	mulx	%o0, %o3, %o0
+	retl
+	 add	%g1, %o0, %o0
+ENDPROC(__multi3)
+EXPORT_SYMBOL(__multi3)

arch/sparc/mm/init_64.c

@@ -658,10 +658,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
 
 /* get_new_mmu_context() uses "cache + 1".  */
 DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
 #define MAX_CTX_NR	(1UL << CTX_NR_BITS)
 #define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
 DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+	unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+	unsigned long new_ver, new_ctx, old_ctx;
+	struct mm_struct *mm;
+	int cpu;
+
+	bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+	/* Reserve kernel context */
+	set_bit(0, mmu_context_bmap);
+
+	new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+	if (unlikely(new_ver == 0))
+		new_ver = CTX_FIRST_VERSION;
+	tlb_context_cache = new_ver;
+
+	/*
+	 * Make sure that any new mm that are added into per_cpu_secondary_mm,
+	 * are going to go through get_new_mmu_context() path.
+	 */
+	mb();
+
+	/*
+	 * Updated versions to current on those CPUs that had valid secondary
+	 * contexts
+	 */
+	for_each_online_cpu(cpu) {
+		/*
+		 * If a new mm is stored after we took this mm from the array,
+		 * it will go into get_new_mmu_context() path, because we
+		 * already bumped the version in tlb_context_cache.
+		 */
+		mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+		if (unlikely(!mm || mm == &init_mm))
+			continue;
+
+		old_ctx = mm->context.sparc64_ctx_val;
+		if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+			new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+			set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+			mm->context.sparc64_ctx_val = new_ctx;
+		}
+	}
+}
 
 /* Caller does TLB context flushing on local CPU if necessary.
  * The caller also ensures that CTX_VALID(mm->context) is false.
@@ -677,48 +725,30 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	int new_version;
 
 	spin_lock(&ctx_alloc_lock);
+retry:
+	/* wrap might have happened, test again if our context became valid */
+	if (unlikely(CTX_VALID(mm->context)))
+		goto out;
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
-	new_version = 0;
 	if (new_ctx >= (1 << CTX_NR_BITS)) {
 		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
 		if (new_ctx >= ctx) {
-			int i;
+			mmu_context_wrap();
-			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
+			goto retry;
-				CTX_FIRST_VERSION;
-			if (new_ctx == 1)
-				new_ctx = CTX_FIRST_VERSION;
-
-			/* Don't call memset, for 16 entries that's just
-			 * plain silly...
-			 */
-			mmu_context_bmap[0] = 3;
-			mmu_context_bmap[1] = 0;
-			mmu_context_bmap[2] = 0;
-			mmu_context_bmap[3] = 0;
-			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
-				mmu_context_bmap[i + 0] = 0;
-				mmu_context_bmap[i + 1] = 0;
-				mmu_context_bmap[i + 2] = 0;
-				mmu_context_bmap[i + 3] = 0;
-			}
-			new_version = 1;
-			goto out;
 		}
 	}
+	if (mm->context.sparc64_ctx_val)
+		cpumask_clear(mm_cpumask(mm));
 	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
 	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
 	spin_unlock(&ctx_alloc_lock);
-
-	if (unlikely(new_version))
-		smp_new_mmu_context_version();
 }
 
 static int numa_enabled = 1;

arch/sparc/mm/tsb.c

@@ -451,7 +451,8 @@ retry_tsb_alloc:
 		extern void copy_tsb(unsigned long old_tsb_base,
 				     unsigned long old_tsb_size,
 				     unsigned long new_tsb_base,
-				     unsigned long new_tsb_size);
+				     unsigned long new_tsb_size,
+				     unsigned long page_size_shift);
 		unsigned long old_tsb_base = (unsigned long) old_tsb;
 		unsigned long new_tsb_base = (unsigned long) new_tsb;
 
@@ -459,7 +460,9 @@ retry_tsb_alloc:
 			old_tsb_base = __pa(old_tsb_base);
 			new_tsb_base = __pa(new_tsb_base);
 		}
-		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+			tsb_index == MM_TSB_BASE ?
+			PAGE_SHIFT : REAL_HPAGE_SHIFT);
 	}
 
 	mm->context.tsb_block[tsb_index].tsb = new_tsb;

arch/sparc/mm/ultra.S

@@ -971,11 +971,6 @@ xcall_capture:
 	wr		%g0, (1 << PIL_SMP_CAPTURE), %set_softint
 	retry
 
-	.globl		xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
-	wr		%g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
-	retry
-
 #ifdef CONFIG_KGDB
 	.globl		xcall_kgdb_capture
 xcall_kgdb_capture:

arch/x86/kernel/kvm.c

@@ -162,8 +162,8 @@ void kvm_async_pf_task_wait(u32 token)
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)

arch/x86/kvm/cpuid.c

@@ -765,18 +765,20 @@ out:
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
+	do {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
+		j = (j + 1) % nent;
-		if (ej->function == e->function) {
+		ej = &vcpu->arch.cpuid_entries[j];
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+	} while (ej->function != e->function);
-			return j;
+
-		}
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-	}
+
-	return 0; /* silence gcc, even though control never reaches here */
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that

arch/x86/kvm/mmu.c

@@ -3489,12 +3489,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3510,7 +3513,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);

arch/x86/kvm/mmu.h

@@ -75,6 +75,7 @@ enum {
 int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {

arch/x86/kvm/x86.c

@@ -8444,8 +8444,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
+		return kvm_can_do_async_pf(vcpu);
-			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)

arch/x86/platform/efi/quirks.c

@@ -358,6 +358,9 @@ void __init efi_free_boot_services(void)
 		free_bootmem_late(start, size);
 	}
 
+	if (!num_entries)
+		return;
+
 	new_size = efi.memmap.desc_size * num_entries;
 	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {

block/cfq-iosched.c

@@ -36,9 +36,13 @@ static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
  */
 #define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
@@ -1370,6 +1374,14 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	cfqg->vfraction = max_t(unsigned, vfr, 1);
 }
 
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+	if (!iops_mode(cfqd))
+		return CFQ_SLICE_MODE_GROUP_DELAY;
+	else
+		return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
 static void
 cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
@@ -1389,7 +1401,8 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	n = rb_last(&st->rb);
 	if (n) {
 		__cfqg = rb_entry_cfqg(n);
-		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+		cfqg->vdisktime = __cfqg->vdisktime +
+			cfq_get_cfqg_vdisktime_delay(cfqd);
 	} else
 		cfqg->vdisktime = st->min_vdisktime;
 	cfq_group_service_tree_add(st, cfqg);

crypto/asymmetric_keys/public_key.c

@@ -140,7 +140,7 @@ int public_key_verify_signature(const struct public_key *pkey,
 	 * signature and returns that to us.
 	 */
 	ret = crypto_akcipher_verify(req);
-	if (ret == -EINPROGRESS) {
+	if ((ret == -EINPROGRESS) || (ret == -EBUSY)) {
 		wait_for_completion(&compl.completion);
 		ret = compl.err;
 	}

crypto/drbg.c

@@ -1768,9 +1768,8 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 			break;
 		case -EINPROGRESS:
 		case -EBUSY:
-			ret = wait_for_completion_interruptible(
+			wait_for_completion(&drbg->ctr_completion);
-				&drbg->ctr_completion);
+			if (!drbg->ctr_async_err) {
-			if (!ret && !drbg->ctr_async_err) {
 				reinit_completion(&drbg->ctr_completion);
 				break;
 			}

crypto/gcm.c

@@ -152,10 +152,8 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 
 	err = crypto_skcipher_encrypt(&data->req);
 	if (err == -EINPROGRESS || err == -EBUSY) {
-		err = wait_for_completion_interruptible(
+		wait_for_completion(&data->result.completion);
-			&data->result.completion);
+		err = data->result.err;
-		if (!err)
-			err = data->result.err;
 	}
 
 	if (err)

drivers/ata/ahci.c

@@ -1362,6 +1362,40 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host)
 {}
 #endif
 
+/*
+ * On the Acer Aspire Switch Alpha 12, sometimes all SATA ports are detected
+ * as DUMMY, or detected but eventually get a "link down" and never get up
+ * again. When this happens, CAP.NP may hold a value of 0x00 or 0x01, and the
+ * port_map may hold a value of 0x00.
+ *
+ * Overriding CAP.NP to 0x02 and the port_map to 0x7 will reveal all 3 ports
+ * and can significantly reduce the occurrence of the problem.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=189471
+ */
+static void acer_sa5_271_workaround(struct ahci_host_priv *hpriv,
+				    struct pci_dev *pdev)
+{
+	static const struct dmi_system_id sysids[] = {
+		{
+			.ident = "Acer Switch Alpha 12",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271")
+			},
+		},
+		{ }
+	};
+
+	if (dmi_check_system(sysids)) {
+		dev_info(&pdev->dev, "enabling Acer Switch Alpha 12 workaround\n");
+		if ((hpriv->saved_cap & 0xC734FF00) == 0xC734FF00) {
+			hpriv->port_map = 0x7;
+			hpriv->cap = 0xC734FF02;
+		}
+	}
+}
+
 #ifdef CONFIG_ARM64
 /*
  * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently.
@@ -1597,6 +1631,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			 "online status unreliable, applying workaround\n");
 	}
 
+
+	/* Acer SA5-271 workaround modifies private_data */
+	acer_sa5_271_workaround(hpriv, pdev);
+
 	/* CAP.NP sometimes indicate the index of the last enabled
 	 * port, at other times, that of the last possible port, so
 	 * determining the maximum port number requires looking at

drivers/char/mem.c

@@ -343,7 +343,7 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma)
 	phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
 
 	/* It's illegal to wrap around the end of the physical address space. */
-	if (offset + (phys_addr_t)size < offset)
+	if (offset + (phys_addr_t)size - 1 < offset)
 		return -EINVAL;
 
 	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))

drivers/cpufreq/cpufreq.c

@@ -2539,6 +2539,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (!(cpufreq_driver->flags & CPUFREQ_STICKY) &&
 	    list_empty(&cpufreq_policy_list)) {
 		/* if all ->init() calls failed, unregister */
+		ret = -ENODEV;
 		pr_debug("%s: No CPU initialized for driver %s\n", __func__,
 			 driver_data->name);
 		goto err_if_unreg;

drivers/dma/ep93xx_dma.c

@@ -201,6 +201,7 @@ struct ep93xx_dma_engine {
 	struct dma_device	dma_dev;
 	bool			m2m;
 	int			(*hw_setup)(struct ep93xx_dma_chan *);
+	void			(*hw_synchronize)(struct ep93xx_dma_chan *);
 	void			(*hw_shutdown)(struct ep93xx_dma_chan *);
 	void			(*hw_submit)(struct ep93xx_dma_chan *);
 	int			(*hw_interrupt)(struct ep93xx_dma_chan *);
@@ -323,6 +324,8 @@ static int m2p_hw_setup(struct ep93xx_dma_chan *edmac)
 		| M2P_CONTROL_ENABLE;
 	m2p_set_control(edmac, control);
 
+	edmac->buffer = 0;
+
 	return 0;
 }
 
@@ -331,21 +334,27 @@ static inline u32 m2p_channel_state(struct ep93xx_dma_chan *edmac)
 	return (readl(edmac->regs + M2P_STATUS) >> 4) & 0x3;
 }
 
-static void m2p_hw_shutdown(struct ep93xx_dma_chan *edmac)
+static void m2p_hw_synchronize(struct ep93xx_dma_chan *edmac)
 {
+	unsigned long flags;
 	u32 control;
 
+	spin_lock_irqsave(&edmac->lock, flags);
 	control = readl(edmac->regs + M2P_CONTROL);
 	control &= ~(M2P_CONTROL_STALLINT | M2P_CONTROL_NFBINT);
 	m2p_set_control(edmac, control);
+	spin_unlock_irqrestore(&edmac->lock, flags);
 
 	while (m2p_channel_state(edmac) >= M2P_STATE_ON)
-		cpu_relax();
+		schedule();
+}
 
+static void m2p_hw_shutdown(struct ep93xx_dma_chan *edmac)
+{
 	m2p_set_control(edmac, 0);
 
-	while (m2p_channel_state(edmac) == M2P_STATE_STALL)
+	while (m2p_channel_state(edmac) != M2P_STATE_IDLE)
-		cpu_relax();
+		dev_warn(chan2dev(edmac), "M2P: Not yet IDLE\n");
 }
 
 static void m2p_fill_desc(struct ep93xx_dma_chan *edmac)
@@ -1160,6 +1169,26 @@ fail:
 	return NULL;
 }
 
+/**
+ * ep93xx_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ *
+ * Synchronizes the DMA channel termination to the current context. When this
+ * function returns it is guaranteed that all transfers for previously issued
+ * descriptors have stopped and and it is safe to free the memory associated
+ * with them. Furthermore it is guaranteed that all complete callback functions
+ * for a previously submitted descriptor have finished running and it is safe to
+ * free resources accessed from within the complete callbacks.
+ */
+static void ep93xx_dma_synchronize(struct dma_chan *chan)
+{
+	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
+
+	if (edmac->edma->hw_synchronize)
+		edmac->edma->hw_synchronize(edmac);
+}
+
 /**
  * ep93xx_dma_terminate_all - terminate all transactions
  * @chan: channel
@@ -1323,6 +1352,7 @@ static int __init ep93xx_dma_probe(struct platform_device *pdev)
 	dma_dev->device_prep_slave_sg = ep93xx_dma_prep_slave_sg;
 	dma_dev->device_prep_dma_cyclic = ep93xx_dma_prep_dma_cyclic;
 	dma_dev->device_config = ep93xx_dma_slave_config;
+	dma_dev->device_synchronize = ep93xx_dma_synchronize;
 	dma_dev->device_terminate_all = ep93xx_dma_terminate_all;
 	dma_dev->device_issue_pending = ep93xx_dma_issue_pending;
 	dma_dev->device_tx_status = ep93xx_dma_tx_status;
@@ -1340,6 +1370,7 @@ static int __init ep93xx_dma_probe(struct platform_device *pdev)
 	} else {
 		dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
 
+		edma->hw_synchronize = m2p_hw_synchronize;
 		edma->hw_setup = m2p_hw_setup;
 		edma->hw_shutdown = m2p_hw_shutdown;
 		edma->hw_submit = m2p_hw_submit;

drivers/dma/mv_xor_v2.c

@@ -161,6 +161,7 @@ struct mv_xor_v2_device {
 	struct mv_xor_v2_sw_desc *sw_desq;
 	int desc_size;
 	unsigned int npendings;
+	unsigned int hw_queue_idx;
 };
 
 /**
@@ -213,18 +214,6 @@ static void mv_xor_v2_set_data_buffers(struct mv_xor_v2_device *xor_dev,
 	}
 }
 
-/*
- * Return the next available index in the DESQ.
- */
-static int mv_xor_v2_get_desq_write_ptr(struct mv_xor_v2_device *xor_dev)
-{
-	/* read the index for the next available descriptor in the DESQ */
-	u32 reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_ALLOC_OFF);
-
-	return ((reg >> MV_XOR_V2_DMA_DESQ_ALLOC_WRPTR_SHIFT)
-		& MV_XOR_V2_DMA_DESQ_ALLOC_WRPTR_MASK);
-}
-
 /*
  * notify the engine of new descriptors, and update the available index.
  */
@@ -257,22 +246,6 @@ static int mv_xor_v2_set_desc_size(struct mv_xor_v2_device *xor_dev)
 	return MV_XOR_V2_EXT_DESC_SIZE;
 }
 
-/*
- * Set the IMSG threshold
- */
-static inline
-void mv_xor_v2_set_imsg_thrd(struct mv_xor_v2_device *xor_dev, int thrd_val)
-{
-	u32 reg;
-
-	reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-
-	reg &= (~MV_XOR_V2_DMA_IMSG_THRD_MASK << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
-	reg |= (thrd_val << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
-
-	writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-}
-
 static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
 {
 	struct mv_xor_v2_device *xor_dev = data;
@@ -288,12 +261,6 @@ static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
 	if (!ndescs)
 		return IRQ_NONE;
 
-	/*
-	 * Update IMSG threshold, to disable new IMSG interrupts until
-	 * end of the tasklet
-	 */
-	mv_xor_v2_set_imsg_thrd(xor_dev, MV_XOR_V2_DESC_NUM);
-
 	/* schedule a tasklet to handle descriptors callbacks */
 	tasklet_schedule(&xor_dev->irq_tasklet);
 
@@ -306,7 +273,6 @@ static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
 static dma_cookie_t
 mv_xor_v2_tx_submit(struct dma_async_tx_descriptor *tx)
 {
-	int desq_ptr;
 	void *dest_hw_desc;
 	dma_cookie_t cookie;
 	struct mv_xor_v2_sw_desc *sw_desc =
@@ -322,15 +288,15 @@ mv_xor_v2_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_bh(&xor_dev->lock);
 	cookie = dma_cookie_assign(tx);
 
-	/* get the next available slot in the DESQ */
-	desq_ptr = mv_xor_v2_get_desq_write_ptr(xor_dev);
-
 	/* copy the HW descriptor from the SW descriptor to the DESQ */
-	dest_hw_desc = xor_dev->hw_desq_virt + desq_ptr;
+	dest_hw_desc = xor_dev->hw_desq_virt + xor_dev->hw_queue_idx;
 
 	memcpy(dest_hw_desc, &sw_desc->hw_desc, xor_dev->desc_size);
 
 	xor_dev->npendings++;
+	xor_dev->hw_queue_idx++;
+	if (xor_dev->hw_queue_idx >= MV_XOR_V2_DESC_NUM)
+		xor_dev->hw_queue_idx = 0;
 
 	spin_unlock_bh(&xor_dev->lock);
 
@@ -344,6 +310,7 @@ static struct mv_xor_v2_sw_desc	*
 mv_xor_v2_prep_sw_desc(struct mv_xor_v2_device *xor_dev)
 {
 	struct mv_xor_v2_sw_desc *sw_desc;
+	bool found = false;
 
 	/* Lock the channel */
 	spin_lock_bh(&xor_dev->lock);
@@ -355,19 +322,23 @@ mv_xor_v2_prep_sw_desc(struct mv_xor_v2_device *xor_dev)
 		return NULL;
 	}
 
-	/* get a free SW descriptor from the SW DESQ */
+	list_for_each_entry(sw_desc, &xor_dev->free_sw_desc, free_list) {
-	sw_desc = list_first_entry(&xor_dev->free_sw_desc,
+		if (async_tx_test_ack(&sw_desc->async_tx)) {
-				   struct mv_xor_v2_sw_desc, free_list);
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		spin_unlock_bh(&xor_dev->lock);
+		return NULL;
+	}
+
 	list_del(&sw_desc->free_list);
 
 	/* Release the channel */
 	spin_unlock_bh(&xor_dev->lock);
 
-	/* set the async tx descriptor */
-	dma_async_tx_descriptor_init(&sw_desc->async_tx, &xor_dev->dmachan);
-	sw_desc->async_tx.tx_submit = mv_xor_v2_tx_submit;
-	async_tx_ack(&sw_desc->async_tx);
-
 	return sw_desc;
 }
 
@@ -389,6 +360,8 @@ mv_xor_v2_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 		__func__, len, &src, &dest, flags);
 
 	sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+	if (!sw_desc)
+		return NULL;
 
 	sw_desc->async_tx.flags = flags;
 
@@ -443,6 +416,8 @@ mv_xor_v2_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		__func__, src_cnt, len, &dest, flags);
 
 	sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+	if (!sw_desc)
+		return NULL;
 
 	sw_desc->async_tx.flags = flags;
 
@@ -491,6 +466,8 @@ mv_xor_v2_prep_dma_interrupt(struct dma_chan *chan, unsigned long flags)
 		container_of(chan, struct mv_xor_v2_device, dmachan);
 
 	sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+	if (!sw_desc)
+		return NULL;
 
 	/* set the HW descriptor */
 	hw_descriptor = &sw_desc->hw_desc;
@@ -554,7 +531,6 @@ static void mv_xor_v2_tasklet(unsigned long data)
 {
 	struct mv_xor_v2_device *xor_dev = (struct mv_xor_v2_device *) data;
 	int pending_ptr, num_of_pending, i;
-	struct mv_xor_v2_descriptor *next_pending_hw_desc = NULL;
 	struct mv_xor_v2_sw_desc *next_pending_sw_desc = NULL;
 
 	dev_dbg(xor_dev->dmadev.dev, "%s %d\n", __func__, __LINE__);
@@ -562,17 +538,10 @@ static void mv_xor_v2_tasklet(unsigned long data)
 	/* get the pending descriptors parameters */
 	num_of_pending = mv_xor_v2_get_pending_params(xor_dev, &pending_ptr);
 
-	/* next HW descriptor */
-	next_pending_hw_desc = xor_dev->hw_desq_virt + pending_ptr;
-
 	/* loop over free descriptors */
 	for (i = 0; i < num_of_pending; i++) {
-
+		struct mv_xor_v2_descriptor *next_pending_hw_desc =
-		if (pending_ptr > MV_XOR_V2_DESC_NUM)
+			xor_dev->hw_desq_virt + pending_ptr;
-			pending_ptr = 0;
-
-		if (next_pending_sw_desc != NULL)
-			next_pending_hw_desc++;
 
 		/* get the SW descriptor related to the HW descriptor */
 		next_pending_sw_desc =
@@ -608,15 +577,14 @@ static void mv_xor_v2_tasklet(unsigned long data)
 
 		/* increment the next descriptor */
 		pending_ptr++;
+		if (pending_ptr >= MV_XOR_V2_DESC_NUM)
+			pending_ptr = 0;
 	}
 
 	if (num_of_pending != 0) {
 		/* free the descriptores */
 		mv_xor_v2_free_desc_from_desq(xor_dev, num_of_pending);
 	}
-
-	/* Update IMSG threshold, to enable new IMSG interrupts */
-	mv_xor_v2_set_imsg_thrd(xor_dev, 0);
 }
 
 /*
@@ -648,9 +616,6 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	writel((xor_dev->hw_desq & 0xFFFF00000000) >> 32,
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BAHR_OFF);
 
-	/* enable the DMA engine */
-	writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF);
-
 	/*
 	 * This is a temporary solution, until we activate the
 	 * SMMU. Set the attributes for reading & writing data buffers
@@ -694,6 +659,9 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	reg |= MV_XOR_V2_GLOB_PAUSE_AXI_TIME_DIS_VAL;
 	writel(reg, xor_dev->glob_base + MV_XOR_V2_GLOB_PAUSE);
 
+	/* enable the DMA engine */
+	writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF);
+
 	return 0;
 }
 
@@ -725,6 +693,10 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, xor_dev);
 
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+	if (ret)
+		return ret;
+
 	xor_dev->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
@@ -785,8 +757,15 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 
 	/* add all SW descriptors to the free list */
 	for (i = 0; i < MV_XOR_V2_DESC_NUM; i++) {
-		xor_dev->sw_desq[i].idx = i;
+		struct mv_xor_v2_sw_desc *sw_desc =
-		list_add(&xor_dev->sw_desq[i].free_list,
+			xor_dev->sw_desq + i;
+		sw_desc->idx = i;
+		dma_async_tx_descriptor_init(&sw_desc->async_tx,
+					     &xor_dev->dmachan);
+		sw_desc->async_tx.tx_submit = mv_xor_v2_tx_submit;
+		async_tx_ack(&sw_desc->async_tx);
+
+		list_add(&sw_desc->free_list,
 			 &xor_dev->free_sw_desc);
 	}
 

drivers/dma/sh/usb-dmac.c

@@ -117,7 +117,7 @@ struct usb_dmac {
 #define USB_DMASWR			0x0008
 #define USB_DMASWR_SWR			(1 << 0)
 #define USB_DMAOR			0x0060
-#define USB_DMAOR_AE			(1 << 2)
+#define USB_DMAOR_AE			(1 << 1)
 #define USB_DMAOR_DME			(1 << 0)
 
 #define USB_DMASAR			0x0000

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

@@ -900,6 +900,12 @@ static bool ci_dpm_vblank_too_short(struct amdgpu_device *adev)
 	u32 vblank_time = amdgpu_dpm_get_vblank_time(adev);
 	u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+	 * blanking period would allow it
+	 */
+	if (amdgpu_dpm_get_vrefresh(adev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else

drivers/gpu/drm/drm_drv.c

@@ -379,7 +379,12 @@ EXPORT_SYMBOL(drm_put_dev);
 void drm_unplug_dev(struct drm_device *dev)
 {
 	/* for a USB device */
-	drm_dev_unregister(dev);
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_modeset_unregister_all(dev);
+
+	drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 
 	mutex_lock(&drm_global_mutex);
 

drivers/gpu/drm/i915/i915_drv.c

@@ -573,9 +573,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (i915_inject_load_failure())
 		return -ENODEV;
 
-	ret = intel_bios_init(dev_priv);
+	intel_bios_init(dev_priv);
-	if (ret)
-		DRM_INFO("failed to find VBIOS tables\n");
 
 	/* If we have > 1 VGA cards, then we need to arbitrate access
 	 * to the common VGA resources.

drivers/gpu/drm/i915/i915_drv.h

@@ -3584,7 +3584,7 @@ static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter)
 extern void intel_i2c_reset(struct drm_device *dev);
 
 /* intel_bios.c */
-int intel_bios_init(struct drm_i915_private *dev_priv);
+void intel_bios_init(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/intel_bios.c

@@ -1332,6 +1332,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
 	return;
 }
 
+/* Common defaults which may be overridden by VBT. */
 static void
 init_vbt_defaults(struct drm_i915_private *dev_priv)
 {
@@ -1368,6 +1369,18 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 			&dev_priv->vbt.ddi_port_info[port];
 
 		info->hdmi_level_shift = HDMI_LEVEL_SHIFT_UNKNOWN;
+	}
+}
+
+/* Defaults to initialize only if there is no VBT. */
+static void
+init_vbt_missing_defaults(struct drm_i915_private *dev_priv)
+{
+	enum port port;
+
+	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+		struct ddi_vbt_port_info *info =
+			&dev_priv->vbt.ddi_port_info[port];
 
 		info->supports_dvi = (port != PORT_A && port != PORT_E);
 		info->supports_hdmi = info->supports_dvi;
@@ -1450,36 +1463,35 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
  * intel_bios_init - find VBT and initialize settings from the BIOS
  * @dev_priv: i915 device instance
  *
- * Loads the Video BIOS and checks that the VBT exists.  Sets scratch registers
+ * Parse and initialize settings from the Video BIOS Tables (VBT). If the VBT
- * to appropriate values.
+ * was not found in ACPI OpRegion, try to find it in PCI ROM first. Also
- *
+ * initialize some defaults if the VBT is not present at all.
- * Returns 0 on success, nonzero on failure.
  */
-int
+void intel_bios_init(struct drm_i915_private *dev_priv)
-intel_bios_init(struct drm_i915_private *dev_priv)
 {
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	const struct vbt_header *vbt = dev_priv->opregion.vbt;
 	const struct bdb_header *bdb;
 	u8 __iomem *bios = NULL;
 
-	if (HAS_PCH_NOP(dev_priv))
+	if (HAS_PCH_NOP(dev_priv)) {
-		return -ENODEV;
+		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
+		return;
+	}
 
 	init_vbt_defaults(dev_priv);
 
+	/* If the OpRegion does not have VBT, look in PCI ROM. */
 	if (!vbt) {
 		size_t size;
 
 		bios = pci_map_rom(pdev, &size);
 		if (!bios)
-			return -1;
+			goto out;
 
 		vbt = find_vbt(bios, size);
-		if (!vbt) {
+		if (!vbt)
-			pci_unmap_rom(pdev, bios);
+			goto out;
-			return -1;
-		}
 
 		DRM_DEBUG_KMS("Found valid VBT in PCI ROM\n");
 	}
@@ -1504,10 +1516,14 @@ intel_bios_init(struct drm_i915_private *dev_priv)
 	parse_mipi_sequence(dev_priv, bdb);
 	parse_ddi_ports(dev_priv, bdb);
 
+out:
+	if (!vbt) {
+		DRM_INFO("Failed to find VBIOS tables (VBT)\n");
+		init_vbt_missing_defaults(dev_priv);
+	}
+
 	if (bios)
 		pci_unmap_rom(pdev, bios);
-
-	return 0;
 }
 
 /**

drivers/gpu/drm/msm/msm_drv.c

@@ -801,6 +801,7 @@ static struct drm_driver msm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export   = drm_gem_prime_export,
 	.gem_prime_import   = drm_gem_prime_import,
+	.gem_prime_res_obj  = msm_gem_prime_res_obj,
 	.gem_prime_pin      = msm_gem_prime_pin,
 	.gem_prime_unpin    = msm_gem_prime_unpin,
 	.gem_prime_get_sg_table = msm_gem_prime_get_sg_table,

drivers/gpu/drm/msm/msm_drv.h

@@ -203,6 +203,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *msm_gem_prime_vmap(struct drm_gem_object *obj);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj);
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);

drivers/gpu/drm/msm/msm_gem_prime.c

@@ -70,3 +70,10 @@ void msm_gem_prime_unpin(struct drm_gem_object *obj)
 	if (!obj->import_attach)
 		msm_gem_put_pages(obj);
 }
+
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	return msm_obj->resv;
+}

drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h

@@ -4,6 +4,7 @@
 
 struct nvkm_alarm {
 	struct list_head head;
+	struct list_head exec;
 	u64 timestamp;
 	void (*func)(struct nvkm_alarm *);
 };

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

@@ -50,7 +50,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 		/* Move to completed list.  We'll drop the lock before
 		 * executing the callback so it can reschedule itself.
 		 */
-		list_move_tail(&alarm->head, &exec);
+		list_del_init(&alarm->head);
+		list_add(&alarm->exec, &exec);
 	}
 
 	/* Shut down interrupt if no more pending alarms. */
@@ -59,8 +60,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 	spin_unlock_irqrestore(&tmr->lock, flags);
 
 	/* Execute completed callbacks. */
-	list_for_each_entry_safe(alarm, atemp, &exec, head) {
+	list_for_each_entry_safe(alarm, atemp, &exec, exec) {
-		list_del_init(&alarm->head);
+		list_del(&alarm->exec);
 		alarm->func(alarm);
 	}
 }

drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c

@@ -368,6 +368,8 @@ static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv,
 				return fifo_state->static_buffer;
 			else {
 				fifo_state->dynamic_buffer = vmalloc(bytes);
+				if (!fifo_state->dynamic_buffer)
+					goto out_err;
 				return fifo_state->dynamic_buffer;
 			}
 		}

drivers/gpu/drm/vmwgfx/vmwgfx_surface.c

@@ -1275,11 +1275,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	int ret;
 	uint32_t size;
-	uint32_t backup_handle;
+	uint32_t backup_handle = 0;
 
 	if (req->multisample_count != 0)
 		return -EINVAL;
 
+	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
 	if (unlikely(vmw_user_surface_size == 0))
 		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
 			128;
@@ -1315,12 +1318,16 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
 					     &res->backup,
 					     &user_srf->backup_base);
-		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
+		if (ret == 0) {
-		    res->backup_size) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
-			DRM_ERROR("Surface backup buffer is too small.\n");
+			    res->backup_size) {
-			vmw_dmabuf_unreference(&res->backup);
+				DRM_ERROR("Surface backup buffer is too small.\n");
-			ret = -EINVAL;
+				vmw_dmabuf_unreference(&res->backup);
-			goto out_unlock;
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->buffer_handle;
+			}
 		}
 	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
 		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,

drivers/iio/adc/bcm_iproc_adc.c

@@ -143,7 +143,7 @@ static void iproc_adc_reg_dump(struct iio_dev *indio_dev)
 	iproc_adc_dbg_reg(dev, adc_priv, IPROC_SOFT_BYPASS_DATA);
 }
 
-static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
 {
 	u32 channel_intr_status;
 	u32 intr_status;
@@ -167,7 +167,7 @@ static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
 	return IRQ_NONE;
 }
 
-static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
 {
 	irqreturn_t retval = IRQ_NONE;
 	struct iproc_adc_priv *adc_priv;
@@ -181,7 +181,7 @@ static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
 	adc_priv = iio_priv(indio_dev);
 
 	regmap_read(adc_priv->regmap, IPROC_INTERRUPT_STATUS, &intr_status);
-	dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_thread(),INTRPT_STS:%x\n",
+	dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_handler(),INTRPT_STS:%x\n",
 			intr_status);
 
 	intr_channels = (intr_status & IPROC_ADC_INTR_MASK) >> IPROC_ADC_INTR;
@@ -566,8 +566,8 @@ static int iproc_adc_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_threaded_irq(&pdev->dev, adc_priv->irqno,
-				iproc_adc_interrupt_thread,
 				iproc_adc_interrupt_handler,
+				iproc_adc_interrupt_thread,
 				IRQF_SHARED, "iproc-adc", indio_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq error %d\n", ret);

drivers/iio/light/ltr501.c

@@ -74,9 +74,9 @@ static const int int_time_mapping[] = {100000, 50000, 200000, 400000};
 static const struct reg_field reg_field_it =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4);
 static const struct reg_field reg_field_als_intr =
-				REG_FIELD(LTR501_INTR, 0, 0);
-static const struct reg_field reg_field_ps_intr =
 				REG_FIELD(LTR501_INTR, 1, 1);
+static const struct reg_field reg_field_ps_intr =
+				REG_FIELD(LTR501_INTR, 0, 0);
 static const struct reg_field reg_field_als_rate =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2);
 static const struct reg_field reg_field_ps_rate =

drivers/iio/proximity/as3935.c

@@ -40,9 +40,9 @@
 #define AS3935_AFE_PWR_BIT	BIT(0)
 
 #define AS3935_INT		0x03
-#define AS3935_INT_MASK		0x07
+#define AS3935_INT_MASK		0x0f
 #define AS3935_EVENT_INT	BIT(3)
-#define AS3935_NOISE_INT	BIT(1)
+#define AS3935_NOISE_INT	BIT(0)
 
 #define AS3935_DATA		0x07
 #define AS3935_DATA_MASK	0x3F
@@ -215,7 +215,7 @@ static irqreturn_t as3935_trigger_handler(int irq, void *private)
 
 	st->buffer[0] = val & AS3935_DATA_MASK;
 	iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
-					   pf->timestamp);
+					   iio_get_time_ns(indio_dev));
 err_read:
 	iio_trigger_notify_done(indio_dev->trig);
 
@@ -244,7 +244,7 @@ static void as3935_event_work(struct work_struct *work)
 
 	switch (val) {
 	case AS3935_EVENT_INT:
-		iio_trigger_poll(st->trig);
+		iio_trigger_poll_chained(st->trig);
 		break;
 	case AS3935_NOISE_INT:
 		dev_warn(&st->spi->dev, "noise level is too high\n");

drivers/input/mouse/elantech.c

@@ -1118,8 +1118,10 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
  * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E546   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E547   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
+ * Fujitsu LIFEBOOK E557   0x570f01        40, 14, 0c      2 hw buttons
  * Fujitsu T725            0x470f01        05, 12, 09      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
  * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
@@ -1524,6 +1526,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E544"),
 		},
 	},
+	{
+		/* Fujitsu LIFEBOOK E546  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"),
+		},
+	},
 	{
 		/* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
 		.matches = {
@@ -1545,6 +1554,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E556"),
 		},
 	},
+	{
+		/* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"),
+		},
+	},
 	{
 		/* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */
 		.matches = {

drivers/misc/cxl/file.c

@@ -155,11 +155,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 
 	/* Do this outside the status_mutex to avoid a circular dependency with
 	 * the locking in cxl_mmap_fault() */
-	if (copy_from_user(&work, uwork,
+	if (copy_from_user(&work, uwork, sizeof(work)))
-			   sizeof(struct cxl_ioctl_start_work))) {
+		return -EFAULT;
-		rc = -EFAULT;
-		goto out;
-	}
 
 	mutex_lock(&ctx->status_mutex);
 	if (ctx->status != OPENED) {

drivers/misc/cxl/native.c

@@ -1066,13 +1066,16 @@ int cxl_native_register_psl_err_irq(struct cxl *adapter)
 
 void cxl_native_release_psl_err_irq(struct cxl *adapter)
 {
-	if (adapter->native->err_virq != irq_find_mapping(NULL, adapter->native->err_hwirq))
+	if (adapter->native->err_virq == 0 ||
+	    adapter->native->err_virq !=
+	    irq_find_mapping(NULL, adapter->native->err_hwirq))
 		return;
 
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
 	cxl_unmap_irq(adapter->native->err_virq, adapter);
 	cxl_ops->release_one_irq(adapter, adapter->native->err_hwirq);
 	kfree(adapter->irq_name);
+	adapter->native->err_virq = 0;
 }
 
 int cxl_native_register_serr_irq(struct cxl_afu *afu)
@@ -1102,13 +1105,15 @@ int cxl_native_register_serr_irq(struct cxl_afu *afu)
 
 void cxl_native_release_serr_irq(struct cxl_afu *afu)
 {
-	if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+	if (afu->serr_virq == 0 ||
+	    afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
 		return;
 
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
 	cxl_unmap_irq(afu->serr_virq, afu);
 	cxl_ops->release_one_irq(afu->adapter, afu->serr_hwirq);
 	kfree(afu->err_irq_name);
+	afu->serr_virq = 0;
 }
 
 int cxl_native_register_psl_irq(struct cxl_afu *afu)
@@ -1131,12 +1136,15 @@ int cxl_native_register_psl_irq(struct cxl_afu *afu)
 
 void cxl_native_release_psl_irq(struct cxl_afu *afu)
 {
-	if (afu->native->psl_virq != irq_find_mapping(NULL, afu->native->psl_hwirq))
+	if (afu->native->psl_virq == 0 ||
+	    afu->native->psl_virq !=
+	    irq_find_mapping(NULL, afu->native->psl_hwirq))
 		return;
 
 	cxl_unmap_irq(afu->native->psl_virq, afu);
 	cxl_ops->release_one_irq(afu->adapter, afu->native->psl_hwirq);
 	kfree(afu->psl_irq_name);
+	afu->native->psl_virq = 0;
 }
 
 static void recover_psl_err(struct cxl_afu *afu, u64 errstat)

drivers/misc/mei/bus.c

@@ -678,8 +678,10 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a,
 {
 	struct mei_cl_device *cldev = to_mei_cl_device(dev);
 	const uuid_le *uuid = mei_me_cl_uuid(cldev->me_cl);
+	u8 version = mei_me_cl_ver(cldev->me_cl);
 
-	return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:", cldev->name, uuid);
+	return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:%02X:",
+			 cldev->name, uuid, version);
 }
 static DEVICE_ATTR_RO(modalias);
 

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -1931,7 +1931,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+	return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -2226,10 +2226,14 @@ static int cxgb_up(struct adapter *adap)
 		if (err)
 			goto irq_err;
 	}
+
+	mutex_lock(&uld_mutex);
 	enable_rx(adap);
 	t4_sge_start(adap);
 	t4_intr_enable(adap);
 	adap->flags |= FULL_INIT_DONE;
+	mutex_unlock(&uld_mutex);
+
 	notify_ulds(adap, CXGB4_STATE_UP);
 #if IS_ENABLED(CONFIG_IPV6)
 	update_clip(adap);

drivers/net/ethernet/ethoc.c

@@ -710,6 +710,8 @@ static int ethoc_open(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	napi_enable(&priv->napi);
+
 	ethoc_init_ring(priv, dev->mem_start);
 	ethoc_reset(priv);
 
@@ -722,7 +724,6 @@ static int ethoc_open(struct net_device *dev)
 	}
 
 	phy_start(dev->phydev);
-	napi_enable(&priv->napi);
 
 	if (netif_msg_ifup(priv)) {
 		dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n",

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -1953,7 +1953,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
 
 		priv->hw->desc->prepare_tso_tx_desc(desc, 0, buff_size,
 			0, 1,
-			(last_segment) && (buff_size < TSO_MAX_BUFF_SIZE),
+			(last_segment) && (tmp_len <= TSO_MAX_BUFF_SIZE),
 			0, 0);
 
 		tmp_len -= TSO_MAX_BUFF_SIZE;

drivers/net/vxlan.c

@@ -59,6 +59,8 @@ static const u8 all_zeros_mac[ETH_ALEN + 2];
 
 static int vxlan_sock_add(struct vxlan_dev *vxlan);
 
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan);
+
 /* per-network namespace private data for this module */
 struct vxlan_net {
 	struct list_head  vxlan_list;
@@ -717,6 +719,22 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
 	call_rcu(&f->rcu, vxlan_fdb_free);
 }
 
+static void vxlan_dst_free(struct rcu_head *head)
+{
+	struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu);
+
+	dst_cache_destroy(&rd->dst_cache);
+	kfree(rd);
+}
+
+static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+				  struct vxlan_rdst *rd)
+{
+	list_del_rcu(&rd->list);
+	vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
+	call_rcu(&rd->rcu, vxlan_dst_free);
+}
+
 static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 			   union vxlan_addr *ip, __be16 *port, __be32 *vni,
 			   u32 *ifindex)
@@ -847,9 +865,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	 * otherwise destroy the fdb entry
 	 */
 	if (rd && !list_is_singular(&f->remotes)) {
-		list_del_rcu(&rd->list);
+		vxlan_fdb_dst_destroy(vxlan, f, rd);
-		vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
-		kfree_rcu(rd, rcu);
 		goto out;
 	}
 
@@ -1026,6 +1042,8 @@ static void vxlan_sock_release(struct vxlan_dev *vxlan)
 	rcu_assign_pointer(vxlan->vn4_sock, NULL);
 	synchronize_net();
 
+	vxlan_vs_del_dev(vxlan);
+
 	if (__vxlan_sock_release_prep(sock4)) {
 		udp_tunnel_sock_release(sock4->sock);
 		kfree(sock4);
@@ -2286,6 +2304,15 @@ static void vxlan_cleanup(unsigned long arg)
 	mod_timer(&vxlan->age_timer, next_timer);
 }
 
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan)
+{
+	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
+
+	spin_lock(&vn->sock_lock);
+	hlist_del_init_rcu(&vxlan->hlist);
+	spin_unlock(&vn->sock_lock);
+}
+
 static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
@@ -3056,12 +3083,6 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
-
-	spin_lock(&vn->sock_lock);
-	if (!hlist_unhashed(&vxlan->hlist))
-		hlist_del_rcu(&vxlan->hlist);
-	spin_unlock(&vn->sock_lock);
 
 	gro_cells_destroy(&vxlan->gro_cells);
 	list_del(&vxlan->next);

drivers/scsi/qla2xxx/qla_bsg.c

@@ -721,6 +721,8 @@ qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
 		return -EIO;
 	}
 
+	memset(&elreq, 0, sizeof(elreq));
+
 	elreq.req_sg_cnt = dma_map_sg(&ha->pdev->dev,
 		bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt,
 		DMA_TO_DEVICE);
@@ -786,10 +788,9 @@ qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
 
 	if (atomic_read(&vha->loop_state) == LOOP_READY &&
 	    (ha->current_topology == ISP_CFG_F ||
-	    ((IS_QLA81XX(ha) || IS_QLA8031(ha) || IS_QLA8044(ha)) &&
+	    (le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE &&
-	    le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE
+	     req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
-	    && req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
+	    elreq.options == EXTERNAL_LOOPBACK) {
-		elreq.options == EXTERNAL_LOOPBACK) {
 		type = "FC_BSG_HST_VENDOR_ECHO_DIAG";
 		ql_dbg(ql_dbg_user, vha, 0x701e,
 		    "BSG request type: %s.\n", type);

drivers/scsi/qla2xxx/qla_dbg.c

@@ -1131,7 +1131,7 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
 		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
@@ -2090,7 +2090,7 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
 		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */

drivers/scsi/qla2xxx/qla_mbx.c

@@ -4783,9 +4783,9 @@ qla2x00_echo_test(scsi_qla_host_t *vha, struct msg_echo_lb *mreq,
 
 	memset(mcp->mb, 0 , sizeof(mcp->mb));
 	mcp->mb[0] = MBC_DIAGNOSTIC_ECHO;
-	mcp->mb[1] = mreq->options | BIT_6;	/* BIT_6 specifies 64bit address */
+	/* BIT_6 specifies 64bit address */
+	mcp->mb[1] = mreq->options | BIT_15 | BIT_6;
 	if (IS_CNA_CAPABLE(ha)) {
-		mcp->mb[1] |= BIT_15;
 		mcp->mb[2] = vha->fcoe_fcf_idx;
 	}
 	mcp->mb[16] = LSW(mreq->rcv_dma);

drivers/scsi/qla2xxx/qla_os.c

@@ -2420,10 +2420,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	if (mem_only) {
 		if (pci_enable_device_mem(pdev))
-			goto probe_out;
+			return ret;
 	} else {
 		if (pci_enable_device(pdev))
-			goto probe_out;
+			return ret;
 	}
 
 	/* This may fail but that's ok */
@@ -2433,7 +2433,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!ha) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0009,
 		    "Unable to allocate memory for ha.\n");
-		goto probe_out;
+		goto disable_device;
 	}
 	ql_dbg_pci(ql_dbg_init, pdev, 0x000a,
 	    "Memory allocated for ha=%p.\n", ha);
@@ -3039,7 +3039,7 @@ iospace_config_failed:
 	kfree(ha);
 	ha = NULL;
 
-probe_out:
+disable_device:
 	pci_disable_device(pdev);
 	return ret;
 }

drivers/scsi/qla2xxx/qla_tmpl.c

@@ -371,7 +371,7 @@ qla27xx_fwdt_entry_t262(struct scsi_qla_host *vha,
 		goto done;
 	}
 
-	if (end <= start || start == 0 || end == 0) {
+	if (end < start || start == 0 || end == 0) {
 		ql_dbg(ql_dbg_misc, vha, 0xd023,
 		    "%s: unusable range (start=%x end=%x)\n", __func__,
 		    ent->t262.end_addr, ent->t262.start_addr);

drivers/staging/lustre/lustre/lov/lov_pack.c

@@ -387,18 +387,10 @@ int lov_getstripe(struct lov_object *obj, struct lov_stripe_md *lsm,
 	struct lov_mds_md *lmmk = NULL;
 	int rc, lmmk_size, lmm_size;
 	int lum_size;
-	mm_segment_t seg;
 
 	if (!lsm)
 		return -ENODATA;
 
-	/*
-	 * "Switch to kernel segment" to allow copying from kernel space by
-	 * copy_{to,from}_user().
-	 */
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-
 	/* we only need the header part from user space to get lmm_magic and
 	 * lmm_stripe_count, (the header part is common to v1 and v3)
 	 */
@@ -478,6 +470,5 @@ int lov_getstripe(struct lov_object *obj, struct lov_stripe_md *lsm,
 out_free:
 	kfree(lmmk);
 out:
-	set_fs(seg);
 	return rc;
 }

drivers/target/target_core_transport.c

@@ -1182,15 +1182,28 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 	if (cmd->unknown_data_length) {
 		cmd->data_length = size;
 	} else if (size != cmd->data_length) {
-		pr_warn("TARGET_CORE[%s]: Expected Transfer Length:"
+		pr_warn_ratelimited("TARGET_CORE[%s]: Expected Transfer Length:"
 			" %u does not match SCSI CDB Length: %u for SAM Opcode:"
 			" 0x%02x\n", cmd->se_tfo->get_fabric_name(),
 				cmd->data_length, size, cmd->t_task_cdb[0]);
 
-		if (cmd->data_direction == DMA_TO_DEVICE &&
+		if (cmd->data_direction == DMA_TO_DEVICE) {
-		    cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
+			if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
-			pr_err("Rejecting underflow/overflow WRITE data\n");
+				pr_err_ratelimited("Rejecting underflow/overflow"
-			return TCM_INVALID_CDB_FIELD;
+						   " for WRITE data CDB\n");
+				return TCM_INVALID_CDB_FIELD;
+			}
+			/*
+			 * Some fabric drivers like iscsi-target still expect to
+			 * always reject overflow writes.  Reject this case until
+			 * full fabric driver level support for overflow writes
+			 * is introduced tree-wide.
+			 */
+			if (size > cmd->data_length) {
+				pr_err_ratelimited("Rejecting overflow for"
+						   " WRITE control CDB\n");
+				return TCM_INVALID_CDB_FIELD;
+			}
 		}
 		/*
 		 * Reject READ_* or WRITE_* with overflow/underflow for

drivers/tty/serial/ifx6x60.c

@@ -1381,9 +1381,9 @@ static struct spi_driver ifx_spi_driver = {
 static void __exit ifx_spi_exit(void)
 {
 	/* unregister */
+	spi_unregister_driver(&ifx_spi_driver);
 	tty_unregister_driver(tty_drv);
 	put_tty_driver(tty_drv);
-	spi_unregister_driver(&ifx_spi_driver);
 	unregister_reboot_notifier(&ifx_modem_reboot_notifier_block);
 }
 

drivers/tty/serial/sh-sci.c

@@ -1976,12 +1976,14 @@ static int sci_startup(struct uart_port *port)
 
 	dev_dbg(port->dev, "%s(%d)\n", __func__, port->line);
 
-	ret = sci_request_irq(s);
-	if (unlikely(ret < 0))
-		return ret;
-
 	sci_request_dma(port);
 
+	ret = sci_request_irq(s);
+	if (unlikely(ret < 0)) {
+		sci_free_dma(port);
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -2012,8 +2014,8 @@ static void sci_shutdown(struct uart_port *port)
 	}
 #endif
 
-	sci_free_dma(port);
 	sci_free_irq(s);
+	sci_free_dma(port);
 }
 
 static int sci_sck_calc(struct sci_port *s, unsigned int bps,

drivers/usb/chipidea/debug.c

@@ -294,7 +294,8 @@ static int ci_role_show(struct seq_file *s, void *data)
 {
 	struct ci_hdrc *ci = s->private;
 
-	seq_printf(s, "%s\n", ci_role(ci)->name);
+	if (ci->role != CI_ROLE_END)
+		seq_printf(s, "%s\n", ci_role(ci)->name);
 
 	return 0;
 }

drivers/usb/chipidea/udc.c

@@ -1987,6 +1987,7 @@ static void udc_id_switch_for_host(struct ci_hdrc *ci)
 int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 {
 	struct ci_role_driver *rdrv;
+	int ret;
 
 	if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC))
 		return -ENXIO;
@@ -1999,7 +2000,10 @@ int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 	rdrv->stop	= udc_id_switch_for_host;
 	rdrv->irq	= udc_irq;
 	rdrv->name	= "gadget";
-	ci->roles[CI_ROLE_GADGET] = rdrv;
 
-	return udc_start(ci);
+	ret = udc_start(ci);
+	if (!ret)
+		ci->roles[CI_ROLE_GADGET] = rdrv;
+
+	return ret;
 }

drivers/usb/gadget/function/f_mass_storage.c

@@ -395,7 +395,11 @@ static int fsg_set_halt(struct fsg_dev *fsg, struct usb_ep *ep)
 /* Caller must hold fsg->lock */
 static void wakeup_thread(struct fsg_common *common)
 {
-	smp_wmb();	/* ensure the write of bh->state is complete */
+	/*
+	 * Ensure the reading of thread_wakeup_needed
+	 * and the writing of bh->state are completed
+	 */
+	smp_mb();
 	/* Tell the main thread that something has happened */
 	common->thread_wakeup_needed = 1;
 	if (common->thread_task)
@@ -626,7 +630,12 @@ static int sleep_thread(struct fsg_common *common, bool can_freeze)
 	}
 	__set_current_state(TASK_RUNNING);
 	common->thread_wakeup_needed = 0;
-	smp_rmb();	/* ensure the latest bh->state is visible */
+
+	/*
+	 * Ensure the writing of thread_wakeup_needed
+	 * and the reading of bh->state are completed
+	 */
+	smp_mb();
 	return rc;
 }
 

drivers/xen/privcmd.c

@@ -335,8 +335,8 @@ static int mmap_batch_fn(void *data, int nr, void *state)
 				st->global_error = 1;
 		}
 	}
-	st->va += PAGE_SIZE * nr;
+	st->va += XEN_PAGE_SIZE * nr;
-	st->index += nr;
+	st->index += nr / XEN_PFN_PER_PAGE;
 
 	return 0;
 }

fs/block_dev.c

@@ -713,7 +713,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
-		bdev->bd_block_size = (1 << inode->i_blkbits);
+		bdev->bd_block_size = i_blocksize(inode);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
 		inode->i_mode = S_IFBLK;

fs/btrfs/extent-tree.c

@@ -3984,6 +3984,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}

fs/btrfs/file.c

@@ -2842,7 +2842,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (!ret)
 			ret = btrfs_prealloc_file_range(inode, mode,
 					range->start,
-					range->len, 1 << inode->i_blkbits,
+					range->len, i_blocksize(inode),
 					offset + len, &alloc_hint);
 		else
 			btrfs_free_reserved_data_space(inode, range->start,

fs/btrfs/inode.c

@@ -7435,8 +7435,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	int found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
+	unsigned long start_idx;
-	int end_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_SHIFT;
 

fs/buffer.c

@@ -2353,7 +2353,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned int blocksize = i_blocksize(inode);
 	struct page *page;
 	void *fsdata;
 	pgoff_t index, curidx;
@@ -2433,8 +2433,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 			get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned int blocksize = i_blocksize(inode);
-	unsigned zerofrom;
+	unsigned int zerofrom;
 	int err;
 
 	err = cont_expand_zero(file, mapping, pos, bytes);
@@ -2796,7 +2796,7 @@ int nobh_truncate_page(struct address_space *mapping,
 	struct buffer_head map_bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2874,7 +2874,7 @@ int block_truncate_page(struct address_space *mapping,
 	struct buffer_head *bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2986,7 +2986,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 	struct inode *inode = mapping->host;
 	tmp.b_state = 0;
 	tmp.b_blocknr = 0;
-	tmp.b_size = 1 << inode->i_blkbits;
+	tmp.b_size = i_blocksize(inode);
 	get_block(inode, block, &tmp, 0);
 	return tmp.b_blocknr;
 }

fs/ceph/addr.c

@@ -745,7 +745,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
-	unsigned wsize = 1 << inode->i_blkbits;
+	unsigned int wsize = i_blocksize(inode);
 	struct ceph_osd_request *req = NULL;
 	int do_sync = 0;
 	loff_t snap_size, i_size;

fs/direct-io.c

@@ -587,7 +587,7 @@ static int dio_set_defer_completion(struct dio *dio)
 /*
  * Call into the fs to map some more disk blocks.  We record the current number
  * of available blocks at sdio->blocks_available.  These are in units of the
- * fs blocksize, (1 << inode->i_blkbits).
+ * fs blocksize, i_blocksize(inode).
  *
  * The fs is allowed to map lots of blocks at once.  If it wants to do that,
  * it uses the passed inode-relative block number as the file offset, as usual.

fs/ext4/extents.c

@@ -3413,13 +3413,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
-	struct ext4_extent zero_ex;
+	struct ext4_extent zero_ex1, zero_ex2;
 	struct ext4_extent *ex, *abut_ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int ee_len, depth, map_len = map->m_len;
 	int allocated = 0, max_zeroout = 0;
 	int err = 0;
-	int split_flag = 0;
+	int split_flag = EXT4_EXT_DATA_VALID2;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -3436,7 +3436,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	zero_ex.ee_len = 0;
+	zero_ex1.ee_len = 0;
+	zero_ex2.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
@@ -3576,62 +3577,52 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	if (ext4_encrypted_inode(inode))
 		max_zeroout = 0;
 
-	/* If extent is less than s_max_zeroout_kb, zeroout directly */
-	if (max_zeroout && (ee_len <= max_zeroout)) {
-		err = ext4_ext_zeroout(inode, ex);
-		if (err)
-			goto out;
-		zero_ex.ee_block = ex->ee_block;
-		zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
-		ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
-		ext4_ext_mark_initialized(ex);
-		ext4_ext_try_to_merge(handle, inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-		goto out;
-	}
-
 	/*
-	 * four cases:
+	 * five cases:
 	 * 1. split the extent into three extents.
-	 * 2. split the extent into two extents, zeroout the first half.
+	 * 2. split the extent into two extents, zeroout the head of the first
-	 * 3. split the extent into two extents, zeroout the second half.
+	 *    extent.
+	 * 3. split the extent into two extents, zeroout the tail of the second
+	 *    extent.
 	 * 4. split the extent into two extents with out zeroout.
+	 * 5. no splitting needed, just possibly zeroout the head and / or the
+	 *    tail of the extent.
 	 */
 	split_map.m_lblk = map->m_lblk;
 	split_map.m_len = map->m_len;
 
-	if (max_zeroout && (allocated > map->m_len)) {
+	if (max_zeroout && (allocated > split_map.m_len)) {
 		if (allocated <= max_zeroout) {
-			/* case 3 */
+			/* case 3 or 5 */
-			zero_ex.ee_block =
+			zero_ex1.ee_block =
-					 cpu_to_le32(map->m_lblk);
+				 cpu_to_le32(split_map.m_lblk +
-			zero_ex.ee_len = cpu_to_le16(allocated);
+					     split_map.m_len);
-			ext4_ext_store_pblock(&zero_ex,
+			zero_ex1.ee_len =
-				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
+				cpu_to_le16(allocated - split_map.m_len);
-			err = ext4_ext_zeroout(inode, &zero_ex);
+			ext4_ext_store_pblock(&zero_ex1,
+				ext4_ext_pblock(ex) + split_map.m_lblk +
+				split_map.m_len - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex1);
 			if (err)
 				goto out;
-			split_map.m_lblk = map->m_lblk;
 			split_map.m_len = allocated;
-		} else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
+		}
-			/* case 2 */
+		if (split_map.m_lblk - ee_block + split_map.m_len <
-			if (map->m_lblk != ee_block) {
+								max_zeroout) {
-				zero_ex.ee_block = ex->ee_block;
+			/* case 2 or 5 */
-				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+			if (split_map.m_lblk != ee_block) {
+				zero_ex2.ee_block = ex->ee_block;
+				zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
 							ee_block);
-				ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_store_pblock(&zero_ex2,
 						      ext4_ext_pblock(ex));
-				err = ext4_ext_zeroout(inode, &zero_ex);
+				err = ext4_ext_zeroout(inode, &zero_ex2);
 				if (err)
 					goto out;
 			}
 
+			split_map.m_len += split_map.m_lblk - ee_block;
 			split_map.m_lblk = ee_block;
-			split_map.m_len = map->m_lblk - ee_block + map->m_len;
 			allocated = map->m_len;
 		}
 	}
@@ -3642,8 +3633,11 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		err = 0;
 out:
 	/* If we have gotten a failure, don't zero out status tree */
-	if (!err)
+	if (!err) {
-		err = ext4_zeroout_es(inode, &zero_ex);
+		err = ext4_zeroout_es(inode, &zero_ex1);
+		if (!err)
+			err = ext4_zeroout_es(inode, &zero_ex2);
+	}
 	return err ? err : allocated;
 }
 
@@ -4893,6 +4887,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	if (file->f_flags & O_SYNC)
 		ext4_handle_sync(handle);
@@ -5579,6 +5575,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ext4_handle_sync(handle);
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
@@ -5752,6 +5749,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);

fs/ext4/file.c

@@ -432,47 +432,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
+		if (nr_pages == 0)
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
 			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
-			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
+			 * If current offset is smaller than the page offset,
-			 * range, it will be a hole.
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
+			if (whence == SEEK_HOLE && lastoff < endoff &&
-			    page->index > end) {
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -512,20 +492,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
+		/* The no. of pages is less than our desired, we are done. */
-		 * The no. of pages is less than our desired, that would be a
+		if (nr_pages < num)
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;

fs/ext4/inode.c

@@ -2218,7 +2218,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 {
 	struct inode *inode = mpd->inode;
 	int err;
-	ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
 	do {
@@ -3478,14 +3478,14 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 		 * writes need zeroing either because they can race with page
 		 * faults or because they use partial blocks.
 		 */
-		if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
+		if (round_down(offset, i_blocksize(inode)) >= inode->i_size &&
 		    ext4_aligned_io(inode, offset, count))
 			get_block_func = ext4_dio_get_block;
 		else
 			get_block_func = ext4_dax_get_block;
 		dio_flags = DIO_LOCKING;
 	} else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
-		   round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+		   round_down(offset, i_blocksize(inode)) >= inode->i_size) {
 		get_block_func = ext4_dio_get_block;
 		dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
 	} else if (is_sync_kiocb(iocb)) {
@@ -4099,6 +4099,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
@@ -5101,7 +5103,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 	 * do. We do the check mainly to optimize the common PAGE_SIZE ==
 	 * blocksize case
 	 */
-	if (offset > PAGE_SIZE - (1 << inode->i_blkbits))
+	if (offset > PAGE_SIZE - i_blocksize(inode))
 		return;
 	while (1) {
 		page = find_lock_page(inode->i_mapping,
@@ -5496,8 +5498,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
-			new_extra_isize);
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}

fs/ext4/mballoc.c

@@ -838,7 +838,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 	inode = page->mapping->host;
 	sb = inode->i_sb;
 	ngroups = ext4_get_groups_count(sb);
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	blocks_per_page = PAGE_SIZE / blocksize;
 
 	groups_per_page = blocks_per_page >> 1;

fs/ext4/move_extent.c

@@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 	if (PageUptodate(page))
 		return 0;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
 

fs/iomap.c

@@ -419,8 +419,8 @@ int
 iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		struct iomap_ops *ops)
 {
-	unsigned blocksize = (1 << inode->i_blkbits);
+	unsigned int blocksize = i_blocksize(inode);
-	unsigned off = pos & (blocksize - 1);
+	unsigned int off = pos & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
 	if (!off)