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

Several conflicts here.

NFP driver bug fix adding nfp_netdev_is_nfp_repr() check to
nfp_fl_output() needed some adjustments because the code block is in
an else block now.

Parallel additions to net/pkt_cls.h and net/sch_generic.h

A bug fix in __tcp_retransmit_skb() conflicted with some of
the rbtree changes in net-next.

The tc action RCU callback fixes in 'net' had some overlap with some
of the recent tcf_block reworking.

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

36 files changed, 210 insertions, 162 deletions

diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c
index 118dc6af1805..7ad074fd5ab5 100644
--- a/arch/alpha/kernel/sys_alcor.c
+++ b/arch/alpha/kernel/sys_alcor.c
@@ -181,10 +181,10 @@ alcor_init_irq(void)
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 alcor_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[7][5] __initdata = {
+	static char irq_tab[7][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		/* note: IDSEL 17 is XLT only */
 		{16+13, 16+13, 16+13, 16+13, 16+13},	/* IdSel 17,  TULIP  */
diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c
index 4c50f8f40cbb..c0fa1fe5ce77 100644
--- a/arch/alpha/kernel/sys_cabriolet.c
+++ b/arch/alpha/kernel/sys_cabriolet.c
@@ -173,10 +173,10 @@ pc164_init_irq(void)
  * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip.
  */
 
-static inline int __init
+static inline int
 eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT  INTA  INTB  INTC   INTD */
 		{16+0, 16+0, 16+5,  16+9, 16+13},  /* IdSel 6,  slot 0, J25 */
 		{16+1, 16+1, 16+6, 16+10, 16+14},  /* IdSel 7,  slot 1, J26 */
@@ -203,10 +203,10 @@ eb66p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
  * because it is the Saturn IO (SIO) PCI/ISA Bridge Chip.
  */
 
-static inline int __init
+static inline int
 cabriolet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT   INTA  INTB  INTC   INTD */
 		{ 16+2, 16+2, 16+7, 16+11, 16+15}, /* IdSel 5,  slot 2, J21 */
 		{ 16+0, 16+0, 16+5,  16+9, 16+13}, /* IdSel 6,  slot 0, J19 */
@@ -287,10 +287,10 @@ cia_cab_init_pci(void)
  * 
  */
 
-static inline int __init
+static inline int
 alphapc164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[7][5] __initdata = {
+	static char irq_tab[7][5] = {
 		/*INT   INTA  INTB   INTC   INTD */
 		{ 16+2, 16+2, 16+9,  16+13, 16+17}, /* IdSel  5, slot 2, J20 */
 		{ 16+0, 16+0, 16+7,  16+11, 16+15}, /* IdSel  6, slot 0, J29 */
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 6c35159bc00e..9e1e40ea1d14 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -356,7 +356,7 @@ clipper_init_irq(void)
  *  10	 64 bit PCI option slot 3 (not bus 0)
  */
 
-static int __init
+static int
 isa_irq_fixup(const struct pci_dev *dev, int irq)
 {
 	u8 irq8;
@@ -372,10 +372,10 @@ isa_irq_fixup(const struct pci_dev *dev, int irq)
 	return irq8 & 0xf;
 }
 
-static int __init
+static int
 dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[6][5] __initdata = {
+	static char irq_tab[6][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 5 ISA Bridge */
 		{ 16+ 3, 16+ 3, 16+ 2, 16+ 2, 16+ 2}, /* IdSel 6 SCSI builtin*/
@@ -394,10 +394,10 @@ dp264_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return isa_irq_fixup(dev, irq);
 }
 
-static int __init
+static int
 monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[13][5] __initdata = {
+	static char irq_tab[13][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{    45,    45,    45,    45,    45}, /* IdSel 3 21143 PCI1 */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 4 unused */
@@ -423,7 +423,7 @@ monet_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP);
 }
 
-static u8 __init
+static u8
 monet_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	struct pci_controller *hose = dev->sysdata;
@@ -456,10 +456,10 @@ monet_swizzle(struct pci_dev *dev, u8 *pinp)
 	return slot;
 }
 
-static int __init
+static int
 webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[13][5] __initdata = {
+	static char irq_tab[13][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 7 ISA Bridge */
 		{    -1,    -1,    -1,    -1,    -1}, /* IdSel 8 unused */
@@ -478,10 +478,10 @@ webbrick_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return isa_irq_fixup(dev, COMMON_TABLE_LOOKUP);
 }
 
-static int __init
+static int
 clipper_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[7][5] __initdata = {
+	static char irq_tab[7][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 16+ 8, 16+ 8, 16+ 9, 16+10, 16+11}, /* IdSel 1 slot 1 */
 		{ 16+12, 16+12, 16+13, 16+14, 16+15}, /* IdSel 2 slot 2 */
diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c
index ad40a425e841..372661c56537 100644
--- a/arch/alpha/kernel/sys_eb64p.c
+++ b/arch/alpha/kernel/sys_eb64p.c
@@ -167,10 +167,10 @@ eb64p_init_irq(void)
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 eb64p_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT  INTA  INTB  INTC   INTD */
 		{16+7, 16+7, 16+7, 16+7,  16+7},  /* IdSel 5,  slot ?, ?? */
 		{16+0, 16+0, 16+2, 16+4,  16+9},  /* IdSel 6,  slot ?, ?? */
diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c
index 15f42083bdb3..2731738b5872 100644
--- a/arch/alpha/kernel/sys_eiger.c
+++ b/arch/alpha/kernel/sys_eiger.c
@@ -141,7 +141,7 @@ eiger_init_irq(void)
 	}
 }
 
-static int __init
+static int
 eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	u8 irq_orig;
@@ -158,7 +158,7 @@ eiger_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq_orig - 0x80;
 }
 
-static u8 __init
+static u8
 eiger_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	struct pci_controller *hose = dev->sysdata;
diff --git a/arch/alpha/kernel/sys_miata.c b/arch/alpha/kernel/sys_miata.c
index d5b9776a608d..731d693fa1f9 100644
--- a/arch/alpha/kernel/sys_miata.c
+++ b/arch/alpha/kernel/sys_miata.c
@@ -149,10 +149,10 @@ miata_init_irq(void)
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-        static char irq_tab[18][5] __initdata = {
+        static char irq_tab[18][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{16+ 8, 16+ 8, 16+ 8, 16+ 8, 16+ 8},  /* IdSel 14,  DC21142 */
 		{   -1,    -1,    -1,    -1,    -1},  /* IdSel 15,  EIDE    */
@@ -196,7 +196,7 @@ miata_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 miata_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c
index 5e82dc1ad6f2..350ec9c8335b 100644
--- a/arch/alpha/kernel/sys_mikasa.c
+++ b/arch/alpha/kernel/sys_mikasa.c
@@ -145,10 +145,10 @@ mikasa_init_irq(void)
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 mikasa_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[8][5] __initdata = {
+	static char irq_tab[8][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{16+12, 16+12, 16+12, 16+12, 16+12},	/* IdSel 17,  SCSI */
 		{   -1,    -1,    -1,    -1,    -1},	/* IdSel 18,  PCEB */
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 8ae04a121186..d019e4ce07bd 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -62,7 +62,7 @@ nautilus_init_irq(void)
 	common_init_isa_dma();
 }
 
-static int __init
+static int
 nautilus_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/* Preserve the IRQ set up by the console.  */
diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c
index 063e594fd969..2301678d9f9d 100644
--- a/arch/alpha/kernel/sys_noritake.c
+++ b/arch/alpha/kernel/sys_noritake.c
@@ -193,10 +193,10 @@ noritake_init_irq(void)
  * comes in on.  This makes interrupt processing much easier.
  */
 
-static int __init
+static int
 noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[15][5] __initdata = {
+	static char irq_tab[15][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		/* note: IDSELs 16, 17, and 25 are CORELLE only */
 		{ 16+1,  16+1,  16+1,  16+1,  16+1},  /* IdSel 16,  QLOGIC */
@@ -221,7 +221,7 @@ noritake_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 noritake_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c
index dfd510ae5d8c..546822d07dc7 100644
--- a/arch/alpha/kernel/sys_rawhide.c
+++ b/arch/alpha/kernel/sys_rawhide.c
@@ -221,10 +221,10 @@ rawhide_init_irq(void)
  * 
  */
 
-static int __init
+static int
 rawhide_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 16+16, 16+16, 16+16, 16+16, 16+16}, /* IdSel 1 SCSI PCI 1 */
 		{ 16+ 0, 16+ 0, 16+ 1, 16+ 2, 16+ 3}, /* IdSel 2 slot 2 */
diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c
index a3f485257170..3b35e1913492 100644
--- a/arch/alpha/kernel/sys_ruffian.c
+++ b/arch/alpha/kernel/sys_ruffian.c
@@ -117,10 +117,10 @@ ruffian_kill_arch (int mode)
  *
  */
 
-static int __init
+static int
 ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-        static char irq_tab[11][5] __initdata = {
+        static char irq_tab[11][5] = {
 	      /*INT  INTA INTB INTC INTD */
 		{-1,  -1,  -1,  -1,  -1},  /* IdSel 13,  21052	     */
 		{-1,  -1,  -1,  -1,  -1},  /* IdSel 14,  SIO	     */
@@ -139,7 +139,7 @@ ruffian_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 ruffian_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c
index 08ee737d4fba..e178007107ef 100644
--- a/arch/alpha/kernel/sys_rx164.c
+++ b/arch/alpha/kernel/sys_rx164.c
@@ -142,7 +142,7 @@ rx164_init_irq(void)
  * 
  */
 
-static int __init
+static int
 rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 #if 0
@@ -156,7 +156,7 @@ rx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	  { 16+1, 16+1, 16+6, 16+11, 16+16},      /* IdSel 10, slot 4 */
 	};
 #else
-	static char irq_tab[6][5] __initdata = {
+	static char irq_tab[6][5] = {
 	  /*INT   INTA  INTB  INTC   INTD */
 	  { 16+0, 16+0, 16+6, 16+11, 16+16},      /* IdSel 5,  slot 0 */
 	  { 16+1, 16+1, 16+7, 16+12, 16+17},      /* IdSel 6,  slot 1 */
diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c
index 8a0aa6d67b53..86d259c2612d 100644
--- a/arch/alpha/kernel/sys_sable.c
+++ b/arch/alpha/kernel/sys_sable.c
@@ -192,10 +192,10 @@ sable_init_irq(void)
  * with the values in the irq swizzling tables above.
  */
 
-static int __init
+static int
 sable_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[9][5] __initdata = {
+	static char irq_tab[9][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 32+0,  32+0,  32+0,  32+0,  32+0},  /* IdSel 0,  TULIP  */
 		{ 32+1,  32+1,  32+1,  32+1,  32+1},  /* IdSel 1,  SCSI   */
@@ -374,10 +374,10 @@ lynx_init_irq(void)
  * with the values in the irq swizzling tables above.
  */
 
-static int __init
+static int
 lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[19][5] __initdata = {
+	static char irq_tab[19][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{   -1,    -1,    -1,    -1,    -1},  /* IdSel 13,  PCEB   */
 		{   -1,    -1,    -1,    -1,    -1},  /* IdSel 14,  PPB    */
@@ -404,7 +404,7 @@ lynx_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 lynx_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot, pin = *pinp;
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index febd24eba7a6..9fd2895639d5 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -144,7 +144,7 @@ sio_fixup_irq_levels(unsigned int level_bits)
 	outb((level_bits >> 8) & 0xff, 0x4d1);
 }
 
-static inline int __init
+static inline int
 noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/*
@@ -165,7 +165,7 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	 * that they use the default INTA line, if they are interrupt
 	 * driven at all).
 	 */
-	static char irq_tab[][5] __initdata = {
+	static char irq_tab[][5] = {
 		/*INT A   B   C   D */
 		{ 3,  3,  3,  3,  3}, /* idsel  6 (53c810) */ 
 		{-1, -1, -1, -1, -1}, /* idsel  7 (SIO: PCI/ISA bridge) */
@@ -183,10 +183,10 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq >= 0 ? tmp : -1;
 }
 
-static inline int __init
+static inline int
 p2k_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[][5] __initdata = {
+	static char irq_tab[][5] = {
 		/*INT A   B   C   D */
 		{ 0,  0, -1, -1, -1}, /* idsel  6 (53c810) */
 		{-1, -1, -1, -1, -1}, /* idsel  7 (SIO: PCI/ISA bridge) */
diff --git a/arch/alpha/kernel/sys_sx164.c b/arch/alpha/kernel/sys_sx164.c
index d063b360efed..23eee54d714a 100644
--- a/arch/alpha/kernel/sys_sx164.c
+++ b/arch/alpha/kernel/sys_sx164.c
@@ -94,10 +94,10 @@ sx164_init_irq(void)
  *   9  32 bit PCI option slot 3
  */
 
-static int __init
+static int
 sx164_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[5][5] __initdata = {
+	static char irq_tab[5][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ 16+ 9, 16+ 9, 16+13, 16+17, 16+21}, /* IdSel 5 slot 2 J17 */
 		{ 16+11, 16+11, 16+15, 16+19, 16+23}, /* IdSel 6 slot 0 J19 */
diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c
index dd0f1eae3c68..9101f2bb6176 100644
--- a/arch/alpha/kernel/sys_takara.c
+++ b/arch/alpha/kernel/sys_takara.c
@@ -155,10 +155,10 @@ takara_init_irq(void)
  * assign it whatever the hell IRQ we like and it doesn't matter.
  */
 
-static int __init
+static int
 takara_map_irq_srm(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[15][5] __initdata = {
+	static char irq_tab[15][5] = {
 		{ 16+3, 16+3, 16+3, 16+3, 16+3},   /* slot  6 == device 3 */
 		{ 16+2, 16+2, 16+2, 16+2, 16+2},   /* slot  7 == device 2 */
 		{ 16+1, 16+1, 16+1, 16+1, 16+1},   /* slot  8 == device 1 */
@@ -210,7 +210,7 @@ takara_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return COMMON_TABLE_LOOKUP;
 }
 
-static u8 __init
+static u8
 takara_swizzle(struct pci_dev *dev, u8 *pinp)
 {
 	int slot = PCI_SLOT(dev->devfn);
diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c
index ee1874887776..c3f8b79fe214 100644
--- a/arch/alpha/kernel/sys_wildfire.c
+++ b/arch/alpha/kernel/sys_wildfire.c
@@ -288,10 +288,10 @@ wildfire_device_interrupt(unsigned long vector)
  *   7	 64 bit PCI 1 option slot 7
  */
 
-static int __init
+static int
 wildfire_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	static char irq_tab[8][5] __initdata = {
+	static char irq_tab[8][5] = {
 		/*INT    INTA   INTB   INTC   INTD */
 		{ -1,    -1,    -1,    -1,    -1}, /* IdSel 0 ISA Bridge */
 		{ 36,    36,    36+1, 36+2, 36+3}, /* IdSel 1 SCSI builtin */
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 8adde1b492f1..8f627c200d60 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -137,14 +137,15 @@
 			/*
 			 * DW sdio controller has external ciu clock divider
 			 * controlled via register in SDIO IP. Due to its
-			 * unexpected default value (it should devide by 1
-			 * but it devides by 8) SDIO IP uses wrong clock and
+			 * unexpected default value (it should divide by 1
+			 * but it divides by 8) SDIO IP uses wrong clock and
 			 * works unstable (see STAR 9001204800)
+			 * We switched to the minimum possible value of the
+			 * divisor (div-by-2) in HSDK platform code.
 			 * So add temporary fix and change clock frequency
-			 * from 100000000 to 12500000 Hz until we fix dw sdio
-			 * driver itself.
+			 * to 50000000 Hz until we fix dw sdio driver itself.
 			 */
-			clock-frequency = <12500000>;
+			clock-frequency = <50000000>;
 			#clock-cells = <0>;
 		};
 
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 15f0f6b5fec1..7b8f8faf8a24 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -63,7 +63,6 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_RESET_HSDK=y
 CONFIG_EXT3_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index f46267153ec2..6df9d94a9537 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -23,6 +23,8 @@
 #include <linux/cpumask.h>
 #include <linux/reboot.h>
 #include <linux/irqdomain.h>
+#include <linux/export.h>
+
 #include <asm/processor.h>
 #include <asm/setup.h>
 #include <asm/mach_desc.h>
@@ -30,6 +32,9 @@
 #ifndef CONFIG_ARC_HAS_LLSC
 arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+EXPORT_SYMBOL_GPL(smp_atomic_ops_lock);
+EXPORT_SYMBOL_GPL(smp_bitops_lock);
 #endif
 
 struct plat_smp_ops  __weak plat_smp_ops;
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index bd08de4be75e..19ab3cf98f0f 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -8,3 +8,4 @@
 menuconfig ARC_SOC_HSDK
 	bool "ARC HS Development Kit SOC"
 	select CLK_HSDK
+	select RESET_HSDK
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 744e62e58788..fd0ae5e38639 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -74,6 +74,10 @@ static void __init hsdk_set_cpu_freq_1ghz(void)
 		pr_err("Failed to setup CPU frequency to 1GHz!");
 }
 
+#define SDIO_BASE		(ARC_PERIPHERAL_BASE + 0xA000)
+#define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
+#define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -90,6 +94,12 @@ static void __init hsdk_init_early(void)
 	writel(1, (void __iomem *) CREG_PAE_UPDATE);
 
 	/*
+	 * Switch SDIO external ciu clock divider from default div-by-8 to
+	 * minimum possible div-by-2.
+	 */
+	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+	/*
 	 * Setup CPU frequency to 1GHz.
 	 * TODO: remove it after smart hsdk pll driver will be introduced.
 	 */
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index e71eefa2e427..0641ba54ab62 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -1,7 +1,7 @@
 #include <linux/bootmem.h>
 #include <linux/gfp.h>
 #include <linux/export.h>
-#include <linux/rwlock.h>
+#include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 8f2da8bba737..4dffa611376d 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -478,28 +478,30 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		return ret;
 
 	dir = iommu_tce_direction(tce);
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
-			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
-		return H_PARAMETER;
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) {
+		ret = H_PARAMETER;
+		goto unlock_exit;
+	}
 
 	entry = ioba >> stt->page_shift;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
-		if (dir == DMA_NONE) {
+		if (dir == DMA_NONE)
 			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
 					stit->tbl, entry);
-		} else {
-			idx = srcu_read_lock(&vcpu->kvm->srcu);
+		else
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
 					entry, ua, dir);
-			srcu_read_unlock(&vcpu->kvm->srcu, idx);
-		}
 
 		if (ret == H_SUCCESS)
 			continue;
 
 		if (ret == H_TOO_HARD)
-			return ret;
+			goto unlock_exit;
 
 		WARN_ON_ONCE(1);
 		kvmppc_clear_tce(stit->tbl, entry);
@@ -507,7 +509,10 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	kvmppc_tce_put(stt, entry, tce);
 
-	return H_SUCCESS;
+unlock_exit:
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index ec69fa45d5a2..42639fba89e8 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -989,13 +989,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
-	stdcix	r11,r9,r10
 	eieio
+	stdcix	r11,r9,r10
 	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
 	li	r9, TM_QW1_OS + TM_WORD2
 	stwcix	r11,r9,r10
 	li	r9, 1
 	stw	r9, VCPU_XIVE_PUSHED(r4)
+	eieio
 no_xive:
 #endif /* CONFIG_KVM_XICS */
 
@@ -1310,6 +1311,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	bne	3f
 BEGIN_FTR_SECTION
 	PPC_MSGSYNC
+	lwsync
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
@@ -1400,8 +1402,8 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	cmpldi	cr0, r10, 0
 	beq	1f
 	/* First load to pull the context, we ignore the value */
-	lwzx	r11, r7, r10
 	eieio
+	lwzx	r11, r7, r10
 	/* Second load to recover the context state (Words 0 and 1) */
 	ldx	r11, r6, r10
 	b	3f
@@ -1409,8 +1411,8 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	cmpldi	cr0, r10, 0
 	beq	1f
 	/* First load to pull the context, we ignore the value */
-	lwzcix	r11, r7, r10
 	eieio
+	lwzcix	r11, r7, r10
 	/* Second load to recover the context state (Words 0 and 1) */
 	ldcix	r11, r6, r10
 3:	std	r11, VCPU_XIVE_SAVED_STATE(r9)
@@ -1420,6 +1422,7 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	stw	r10, VCPU_XIVE_PUSHED(r9)
 	stb	r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
 	stb	r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
+	eieio
 1:
 #endif /* CONFIG_KVM_XICS */
 	/* Save more register state  */
@@ -2788,6 +2791,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	PPC_MSGCLR(6)
 	/* see if it's a host IPI */
 	li	r3, 1
+BEGIN_FTR_SECTION
+	PPC_MSGSYNC
+	lwsync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	bnelr
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3480faaf1ef8..ee279c7f4802 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -644,8 +644,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_PPC_HTM:
-		r = cpu_has_feature(CPU_FTR_TM_COMP) &&
-		    is_kvmppc_hv_enabled(kvm);
+		r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled;
 		break;
 	default:
 		r = 0;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 21900e1cee9c..d185aa3965bf 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -521,12 +521,15 @@ ENTRY(pgm_check_handler)
 	tmhh	%r8,0x0001		# test problem state bit
 	jnz	2f			# -> fault in user space
 #if IS_ENABLED(CONFIG_KVM)
-	# cleanup critical section for sie64a
+	# cleanup critical section for program checks in sie64a
 	lgr	%r14,%r9
 	slg	%r14,BASED(.Lsie_critical_start)
 	clg	%r14,BASED(.Lsie_critical_length)
 	jhe	0f
-	brasl	%r14,.Lcleanup_sie
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	larl	%r9,sie_exit			# skip forward to sie_exit
 #endif
 0:	tmhh	%r8,0x4000		# PER bit set in old PSW ?
 	jnz	1f			# -> enabled, can't be a double fault
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 49167258d587..f6cdb7a1455e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -808,7 +808,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
-	UNWIND_HINT_IRET_REGS offset=8
+	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
 	/* Sanity check */
 	.if \shift_ist != -1 && \paranoid == 0
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 16076eb34699..141e07b06216 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -546,9 +546,6 @@ static int bts_event_init(struct perf_event *event)
 	if (event->attr.type != bts_pmu.type)
 		return -ENOENT;
 
-	if (x86_add_exclusive(x86_lbr_exclusive_bts))
-		return -EBUSY;
-
 	/*
 	 * BTS leaks kernel addresses even when CPL0 tracing is
 	 * disabled, so disallow intel_bts driver for unprivileged
@@ -562,6 +559,9 @@ static int bts_event_init(struct perf_event *event)
 	    !capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
+	if (x86_add_exclusive(x86_lbr_exclusive_bts))
+		return -EBUSY;
+
 	ret = x86_reserve_hardware();
 	if (ret) {
 		x86_del_exclusive(x86_lbr_exclusive_bts);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d362161d3291..c4aed0de565e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -82,12 +82,21 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 #define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
 #endif
 
-/*
- * If tlb_use_lazy_mode is true, then we try to avoid switching CR3 to point
- * to init_mm when we switch to a kernel thread (e.g. the idle thread).  If
- * it's false, then we immediately switch CR3 when entering a kernel thread.
- */
-DECLARE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
+static inline bool tlb_defer_switch_to_init_mm(void)
+{
+	/*
+	 * If we have PCID, then switching to init_mm is reasonably
+	 * fast.  If we don't have PCID, then switching to init_mm is
+	 * quite slow, so we try to defer it in the hopes that we can
+	 * avoid it entirely.  The latter approach runs the risk of
+	 * receiving otherwise unnecessary IPIs.
+	 *
+	 * This choice is just a heuristic.  The tlb code can handle this
+	 * function returning true or false regardless of whether we have
+	 * PCID.
+	 */
+	return !static_cpu_has(X86_FEATURE_PCID);
+}
 
 /*
  * 6 because 6 should be plenty and struct tlb_state will fit in
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 458da8509b75..6db28f17ff28 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -27,6 +27,8 @@ static const struct pci_device_id amd_root_ids[] = {
 	{}
 };
 
+#define PCI_DEVICE_ID_AMD_CNB17H_F4     0x1704
+
 const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
@@ -37,6 +39,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{}
 };
 EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -48,6 +51,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };
 
@@ -402,11 +406,48 @@ void amd_flush_garts(void)
 }
 EXPORT_SYMBOL_GPL(amd_flush_garts);
 
+static void __fix_erratum_688(void *info)
+{
+#define MSR_AMD64_IC_CFG 0xC0011021
+
+	msr_set_bit(MSR_AMD64_IC_CFG, 3);
+	msr_set_bit(MSR_AMD64_IC_CFG, 14);
+}
+
+/* Apply erratum 688 fix so machines without a BIOS fix work. */
+static __init void fix_erratum_688(void)
+{
+	struct pci_dev *F4;
+	u32 val;
+
+	if (boot_cpu_data.x86 != 0x14)
+		return;
+
+	if (!amd_northbridges.num)
+		return;
+
+	F4 = node_to_amd_nb(0)->link;
+	if (!F4)
+		return;
+
+	if (pci_read_config_dword(F4, 0x164, &val))
+		return;
+
+	if (val & BIT(2))
+		return;
+
+	on_each_cpu(__fix_erratum_688, NULL, 0);
+
+	pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n");
+}
+
 static __init int init_amd_nbs(void)
 {
 	amd_cache_northbridges();
 	amd_cache_gart();
 
+	fix_erratum_688();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 24f749324c0f..9990a71e311f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -831,7 +831,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 	} else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
-		this_leaf = this_cpu_ci->info_list + index;
 		nshared = base->eax.split.num_threads_sharing + 1;
 		apicid = cpu_data(cpu).apicid;
 		first = apicid - (apicid % nshared);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 8f7a9bbad514..7dbcb7adf797 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -34,6 +34,7 @@
 #include <linux/mm.h>
 
 #include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/setup.h>
@@ -918,6 +919,18 @@ static int get_ucode_fw(void *to, const void *from, size_t n)
 	return 0;
 }
 
+static bool is_blacklisted(unsigned int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) {
+		pr_err_once("late loading on model 79 is disabled.\n");
+		return true;
+	}
+
+	return false;
+}
+
 static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 					     bool refresh_fw)
 {
@@ -926,6 +939,9 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 	const struct firmware *firmware;
 	enum ucode_state ret;
 
+	if (is_blacklisted(cpu))
+		return UCODE_NFOUND;
+
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
 		c->x86, c->x86_model, c->x86_mask);
 
@@ -950,6 +966,9 @@ static int get_ucode_user(void *to, const void *from, size_t n)
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
+	if (is_blacklisted(cpu))
+		return UCODE_NFOUND;
+
 	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
 }
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index cf2ce063f65a..2902ca4d5993 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -30,10 +30,11 @@ static void __init i386_default_early_setup(void)
 
 asmlinkage __visible void __init i386_start_kernel(void)
 {
-	cr4_init_shadow();
-
+	/* Make sure IDT is set up before any exception happens */
 	idt_setup_early_handler();
 
+	cr4_init_shadow();
+
 	sanitize_boot_params(&boot_params);
 
 	x86_early_init_platform_quirks();
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 570b70d3f604..b95007e7c1b3 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -86,8 +86,8 @@ static struct orc_entry *orc_find(unsigned long ip)
 		idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE;
 
 		if (unlikely((idx >= lookup_num_blocks-1))) {
-			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n",
-				 idx, lookup_num_blocks, ip);
+			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n",
+				 idx, lookup_num_blocks, (void *)ip);
 			return NULL;
 		}
 
@@ -96,8 +96,8 @@ static struct orc_entry *orc_find(unsigned long ip)
 
 		if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) ||
 			     (__start_orc_unwind + stop > __stop_orc_unwind))) {
-			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n",
-				 idx, lookup_num_blocks, start, stop, ip);
+			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n",
+				 idx, lookup_num_blocks, start, stop, (void *)ip);
 			return NULL;
 		}
 
@@ -373,7 +373,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_R10:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R10 at ip %p\n",
+			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -382,7 +382,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_R13:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R13 at ip %p\n",
+			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -391,7 +391,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_DI:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DI at ip %p\n",
+			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -400,7 +400,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_DX:
 		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DX at ip %p\n",
+			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
 			goto done;
 		}
@@ -408,7 +408,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	default:
-		orc_warn("unknown SP base reg %d for ip %p\n",
+		orc_warn("unknown SP base reg %d for ip %pB\n",
 			 orc->sp_reg, (void *)state->ip);
 		goto done;
 	}
@@ -436,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
-			orc_warn("can't dereference registers at %p for ip %p\n",
+			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
@@ -448,7 +448,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_TYPE_REGS_IRET:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
-			orc_warn("can't dereference iret registers at %p for ip %p\n",
+			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
@@ -465,7 +465,8 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	default:
-		orc_warn("unknown .orc_unwind entry type %d\n", orc->type);
+		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
+			 orc->type, (void *)orig_ip);
 		break;
 	}
 
@@ -487,7 +488,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	default:
-		orc_warn("unknown BP base reg %d for ip %p\n",
+		orc_warn("unknown BP base reg %d for ip %pB\n",
 			 orc->bp_reg, (void *)orig_ip);
 		goto done;
 	}
@@ -496,7 +497,7 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (state->stack_info.type == prev_type &&
 	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
 	    state->sp <= prev_sp) {
-		orc_warn("stack going in the wrong direction? ip=%p\n",
+		orc_warn("stack going in the wrong direction? ip=%pB\n",
 			 (void *)orig_ip);
 		goto done;
 	}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 658bf0090565..0f3d0cea4d00 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -30,7 +30,6 @@
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
-DEFINE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
 
 static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 			    u16 *new_asid, bool *need_flush)
@@ -147,8 +146,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	this_cpu_write(cpu_tlbstate.is_lazy, false);
 
 	if (real_prev == next) {
-		VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
-			  next->context.ctx_id);
+		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+			   next->context.ctx_id);
 
 		/*
 		 * We don't currently support having a real mm loaded without
@@ -213,6 +212,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 }
 
 /*
+ * Please ignore the name of this function.  It should be called
+ * switch_to_kernel_thread().
+ *
  * enter_lazy_tlb() is a hint from the scheduler that we are entering a
  * kernel thread or other context without an mm.  Acceptable implementations
  * include doing nothing whatsoever, switching to init_mm, or various clever
@@ -227,7 +229,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	if (static_branch_unlikely(&tlb_use_lazy_mode)) {
+	if (tlb_defer_switch_to_init_mm()) {
 		/*
 		 * There's a significant optimization that may be possible
 		 * here.  We have accurate enough TLB flush tracking that we
@@ -626,57 +628,3 @@ static int __init create_tlb_single_page_flush_ceiling(void)
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
-
-static ssize_t tlblazy_read_file(struct file *file, char __user *user_buf,
-				 size_t count, loff_t *ppos)
-{
-	char buf[2];
-
-	buf[0] = static_branch_likely(&tlb_use_lazy_mode) ? '1' : '0';
-	buf[1] = '\n';
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-
-static ssize_t tlblazy_write_file(struct file *file,
-		 const char __user *user_buf, size_t count, loff_t *ppos)
-{
-	bool val;
-
-	if (kstrtobool_from_user(user_buf, count, &val))
-		return -EINVAL;
-
-	if (val)
-		static_branch_enable(&tlb_use_lazy_mode);
-	else
-		static_branch_disable(&tlb_use_lazy_mode);
-
-	return count;
-}
-
-static const struct file_operations fops_tlblazy = {
-	.read = tlblazy_read_file,
-	.write = tlblazy_write_file,
-	.llseek = default_llseek,
-};
-
-static int __init init_tlb_use_lazy_mode(void)
-{
-	if (boot_cpu_has(X86_FEATURE_PCID)) {
-		/*
-		 * Heuristic: with PCID on, switching to and from
-		 * init_mm is reasonably fast, but remote flush IPIs
-		 * as expensive as ever, so turn off lazy TLB mode.
-		 *
-		 * We can't do this in setup_pcid() because static keys
-		 * haven't been initialized yet, and it would blow up
-		 * badly.
-		 */
-		static_branch_disable(&tlb_use_lazy_mode);
-	}
-
-	debugfs_create_file("tlb_use_lazy_mode", S_IRUSR | S_IWUSR,
-			    arch_debugfs_dir, NULL, &fops_tlblazy);
-	return 0;
-}
-late_initcall(init_tlb_use_lazy_mode);