Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

David Ahern's dump indexing bug fix in 'net' overlapped the
change of the function signature of inet6_fill_ifaddr() in
'net-next'.  Trivially resolved.

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/x86/boot/compressed/Makefile

@@ -37,6 +37,7 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += -Wno-pointer-sign
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n

arch/x86/entry/entry_32.S

@@ -389,6 +389,13 @@
 	 * that register for the time this macro runs
 	 */
 
+	/*
+	 * The high bits of the CS dword (__csh) are used for
+	 * CS_FROM_ENTRY_STACK and CS_FROM_USER_CR3. Clear them in case
+	 * hardware didn't do this for us.
+	 */
+	andl	$(0x0000ffff), PT_CS(%esp)
+
 	/* Are we on the entry stack? Bail out if not! */
 	movl	PER_CPU_VAR(cpu_entry_area), %ecx
 	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
@@ -407,12 +414,6 @@
 	/* Load top of task-stack into %edi */
 	movl	TSS_entry2task_stack(%edi), %edi
 
-	/*
-	 * Clear unused upper bits of the dword containing the word-sized CS
-	 * slot in pt_regs in case hardware didn't clear it for us.
-	 */
-	andl	$(0x0000ffff), PT_CS(%esp)
-
 	/* Special case - entry from kernel mode via entry stack */
 #ifdef CONFIG_VM86
 	movl	PT_EFLAGS(%esp), %ecx		# mix EFLAGS and CS

arch/x86/entry/entry_64.S

@@ -1187,6 +1187,16 @@ ENTRY(paranoid_entry)
 	xorl	%ebx, %ebx
 
 1:
+	/*
+	 * Always stash CR3 in %r14.  This value will be restored,
+	 * verbatim, at exit.  Needed if paranoid_entry interrupted
+	 * another entry that already switched to the user CR3 value
+	 * but has not yet returned to userspace.
+	 *
+	 * This is also why CS (stashed in the "iret frame" by the
+	 * hardware at entry) can not be used: this may be a return
+	 * to kernel code, but with a user CR3 value.
+	 */
 	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
 
 	ret
@@ -1211,11 +1221,13 @@ ENTRY(paranoid_exit)
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	.Lparanoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
+	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
 	jmp	.Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
+	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 .Lparanoid_exit_restore:
 	jmp restore_regs_and_return_to_kernel
@@ -1626,6 +1638,7 @@ end_repeat_nmi:
 	movq	$-1, %rsi
 	call	do_nmi
 
+	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
 
 	testl	%ebx, %ebx			/* swapgs needed? */

arch/x86/include/asm/fpu/internal.h

@@ -528,7 +528,7 @@ static inline void fpregs_activate(struct fpu *fpu)
 static inline void
 switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (old_fpu->initialized) {
+	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else

arch/x86/include/asm/percpu.h

@@ -185,22 +185,22 @@ do {									\
 	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_arg(1)",%0"		\
+		asm volatile(op "b "__percpu_arg(1)",%0"\
 		    : "=q" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_arg(1)",%0"		\
+		asm volatile(op "w "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_arg(1)",%0"		\
+		asm volatile(op "l "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 8:						\
-		asm(op "q "__percpu_arg(1)",%0"		\
+		asm volatile(op "q "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\

arch/x86/kernel/fpu/signal.c

@@ -314,7 +314,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Validate and sanitize the copied state.
 		 */
-		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 

arch/x86/kernel/pci-swiotlb.c

@@ -42,10 +42,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
 int __init pci_swiotlb_detect_4gb(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-#ifdef CONFIG_X86_64
 	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
 		swiotlb = 1;
-#endif
 
 	/*
 	 * If SME is active then swiotlb will be set to 1 so that bounce

arch/x86/kernel/time.c

@@ -25,7 +25,7 @@
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_64
-__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES;
+__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 #endif
 
 unsigned long profile_pc(struct pt_regs *regs)

arch/x86/kernel/tsc.c

@@ -58,7 +58,7 @@ struct cyc2ns {
 
 static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
 
-void cyc2ns_read_begin(struct cyc2ns_data *data)
+void __always_inline cyc2ns_read_begin(struct cyc2ns_data *data)
 {
 	int seq, idx;
 
@@ -75,7 +75,7 @@ void cyc2ns_read_begin(struct cyc2ns_data *data)
 	} while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
 }
 
-void cyc2ns_read_end(void)
+void __always_inline cyc2ns_read_end(void)
 {
 	preempt_enable_notrace();
 }
@@ -104,7 +104,7 @@ void cyc2ns_read_end(void)
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
 	struct cyc2ns_data data;
 	unsigned long long ns;

block/blk-lib.c

@@ -29,9 +29,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
-	unsigned int granularity;
 	unsigned int op;
-	int alignment;
 	sector_t bs_mask;
 
 	if (!q)
@@ -54,38 +52,16 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
 	while (nr_sects) {
-		unsigned int req_sects;
-		sector_t end_sect, tmp;
+		unsigned int req_sects = nr_sects;
+		sector_t end_sect;
 
-		/*
-		 * Issue in chunks of the user defined max discard setting,
-		 * ensuring that bi_size doesn't overflow
-		 */
-		req_sects = min_t(sector_t, nr_sects,
-					q->limits.max_discard_sectors);
 		if (!req_sects)
 			goto fail;
 		if (req_sects > UINT_MAX >> 9)
 			req_sects = UINT_MAX >> 9;
 
-		/*
-		 * If splitting a request, and the next starting sector would be
-		 * misaligned, stop the discard at the previous aligned sector.
-		 */
 		end_sect = sector + req_sects;
-		tmp = end_sect;
-		if (req_sects < nr_sects &&
-		    sector_div(tmp, granularity) != alignment) {
-			end_sect = end_sect - alignment;
-			sector_div(end_sect, granularity);
-			end_sect = end_sect * granularity + alignment;
-			req_sects = end_sect - sector;
-		}
 
 		bio = next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;

drivers/gpu/drm/drm_atomic.c

@@ -174,6 +174,11 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 		state->crtcs[i].state = NULL;
 		state->crtcs[i].old_state = NULL;
 		state->crtcs[i].new_state = NULL;
+
+		if (state->crtcs[i].commit) {
+			drm_crtc_commit_put(state->crtcs[i].commit);
+			state->crtcs[i].commit = NULL;
+		}
 	}
 
 	for (i = 0; i < config->num_total_plane; i++) {

drivers/gpu/drm/drm_atomic_helper.c

@@ -1408,15 +1408,16 @@ EXPORT_SYMBOL(drm_atomic_helper_wait_for_vblanks);
 void drm_atomic_helper_wait_for_flip_done(struct drm_device *dev,
 					  struct drm_atomic_state *old_state)
 {
-	struct drm_crtc_state *new_crtc_state;
 	struct drm_crtc *crtc;
 	int i;
 
-	for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) {
-		struct drm_crtc_commit *commit = new_crtc_state->commit;
+	for (i = 0; i < dev->mode_config.num_crtc; i++) {
+		struct drm_crtc_commit *commit = old_state->crtcs[i].commit;
 		int ret;
 
-		if (!commit)
+		crtc = old_state->crtcs[i].ptr;
+
+		if (!crtc || !commit)
 			continue;
 
 		ret = wait_for_completion_timeout(&commit->flip_done, 10 * HZ);
@@ -1934,6 +1935,9 @@ int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
 		drm_crtc_commit_get(commit);
 
 		commit->abort_completion = true;
+
+		state->crtcs[i].commit = commit;
+		drm_crtc_commit_get(commit);
 	}
 
 	for_each_oldnew_connector_in_state(state, conn, old_conn_state, new_conn_state, i) {

drivers/gpu/drm/sun4i/sun4i_dotclock.c

@@ -81,9 +81,19 @@ static long sun4i_dclk_round_rate(struct clk_hw *hw, unsigned long rate,
 	int i;
 
 	for (i = tcon->dclk_min_div; i <= tcon->dclk_max_div; i++) {
-		unsigned long ideal = rate * i;
+		u64 ideal = (u64)rate * i;
 		unsigned long rounded;
 
+		/*
+		 * ideal has overflowed the max value that can be stored in an
+		 * unsigned long, and every clk operation we might do on a
+		 * truncated u64 value will give us incorrect results.
+		 * Let's just stop there since bigger dividers will result in
+		 * the same overflow issue.
+		 */
+		if (ideal > ULONG_MAX)
+			goto out;
+
 		rounded = clk_hw_round_rate(clk_hw_get_parent(hw),
 					    ideal);
 

drivers/input/mouse/elan_i2c_core.c

@@ -1346,6 +1346,7 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN0611", 0 },
 	{ "ELAN0612", 0 },
 	{ "ELAN0618", 0 },
+	{ "ELAN061C", 0 },
 	{ "ELAN061D", 0 },
 	{ "ELAN0622", 0 },
 	{ "ELAN1000", 0 },

drivers/nvme/host/core.c

@@ -3143,8 +3143,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	}
 
 	mutex_lock(&ns->ctrl->subsys->lock);
-	nvme_mpath_clear_current_path(ns);
 	list_del_rcu(&ns->siblings);
+	nvme_mpath_clear_current_path(ns);
 	mutex_unlock(&ns->ctrl->subsys->lock);
 
 	down_write(&ns->ctrl->namespaces_rwsem);

drivers/usb/class/cdc-acm.c

@@ -310,17 +310,17 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf)
 
 		if (difference & ACM_CTRL_DSR)
 			acm->iocount.dsr++;
-		if (difference & ACM_CTRL_BRK)
-			acm->iocount.brk++;
-		if (difference & ACM_CTRL_RI)
-			acm->iocount.rng++;
 		if (difference & ACM_CTRL_DCD)
 			acm->iocount.dcd++;
-		if (difference & ACM_CTRL_FRAMING)
+		if (newctrl & ACM_CTRL_BRK)
+			acm->iocount.brk++;
+		if (newctrl & ACM_CTRL_RI)
+			acm->iocount.rng++;
+		if (newctrl & ACM_CTRL_FRAMING)
 			acm->iocount.frame++;
-		if (difference & ACM_CTRL_PARITY)
+		if (newctrl & ACM_CTRL_PARITY)
 			acm->iocount.parity++;
-		if (difference & ACM_CTRL_OVERRUN)
+		if (newctrl & ACM_CTRL_OVERRUN)
 			acm->iocount.overrun++;
 		spin_unlock_irqrestore(&acm->read_lock, flags);
 
@@ -355,7 +355,6 @@ static void acm_ctrl_irq(struct urb *urb)
 	case -ENOENT:
 	case -ESHUTDOWN:
 		/* this urb is terminated, clean up */
-		acm->nb_index = 0;
 		dev_dbg(&acm->control->dev,
 			"%s - urb shutting down with status: %d\n",
 			__func__, status);
@@ -1642,6 +1641,7 @@ static int acm_pre_reset(struct usb_interface *intf)
 	struct acm *acm = usb_get_intfdata(intf);
 
 	clear_bit(EVENT_RX_STALL, &acm->flags);
+	acm->nb_index = 0; /* pending control transfers are lost */
 
 	return 0;
 }

drivers/usb/core/devio.c

@@ -1474,8 +1474,6 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb
 	u = 0;
 	switch (uurb->type) {
 	case USBDEVFS_URB_TYPE_CONTROL:
-		if (is_in)
-			allow_short = true;
 		if (!usb_endpoint_xfer_control(&ep->desc))
 			return -EINVAL;
 		/* min 8 byte setup packet */
@@ -1505,6 +1503,8 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb
 			is_in = 0;
 			uurb->endpoint &= ~USB_DIR_IN;
 		}
+		if (is_in)
+			allow_short = true;
 		snoop(&ps->dev->dev, "control urb: bRequestType=%02x "
 			"bRequest=%02x wValue=%04x "
 			"wIndex=%04x wLength=%04x\n",

drivers/usb/gadget/function/f_mass_storage.c

@@ -221,6 +221,8 @@
 #include <linux/usb/gadget.h>
 #include <linux/usb/composite.h>
 
+#include <linux/nospec.h>
+
 #include "configfs.h"
 
 
@@ -3152,6 +3154,7 @@ static struct config_group *fsg_lun_make(struct config_group *group,
 	fsg_opts = to_fsg_opts(&group->cg_item);
 	if (num >= FSG_MAX_LUNS)
 		return ERR_PTR(-ERANGE);
+	num = array_index_nospec(num, FSG_MAX_LUNS);
 
 	mutex_lock(&fsg_opts->lock);
 	if (fsg_opts->refcnt || fsg_opts->common->luns[num]) {

drivers/usb/host/xhci-pci.c

@@ -179,10 +179,12 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
+	    pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI)
 		xhci->quirks |= XHCI_SSIC_PORT_UNUSED;
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+	    (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI))
 		xhci->quirks |= XHCI_INTEL_USB_ROLE_SW;
-	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
 	    (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
 	     pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI ||

drivers/usb/roles/intel-xhci-usb-role-switch.c

@@ -161,6 +161,8 @@ static int intel_xhci_usb_remove(struct platform_device *pdev)
 {
 	struct intel_xhci_usb_data *data = platform_get_drvdata(pdev);
 
+	pm_runtime_disable(&pdev->dev);
+
 	usb_role_switch_unregister(data->role_sw);
 	return 0;
 }