43 files changed, 422 insertions, 290 deletions

diff --git a/.mailmap b/.mailmap
index e18cab73e209..a2ce89a456c2 100644
--- a/.mailmap
+++ b/.mailmap
@@ -62,6 +62,7 @@ Frank Zago <fzago@systemfabricworks.com>
 Greg Kroah-Hartman <greg@echidna.(none)>
 Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
+Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
 Henk Vergonet <Henk.Vergonet@gmail.com>
 Henrik Kretzschmar <henne@nachtwindheim.de>
 Henrik Rydberg <rydberg@bitmath.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index c2df576114c3..6e950b8b4a41 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1153,7 +1153,7 @@ S:	Maintained
 F:      drivers/clk/sunxi/
 
 ARM/Allwinner sunXi SoC support
-M:      Maxime Ripard <maxime.ripard@free-electrons.com>
+M:      Maxime Ripard <maxime.ripard@bootlin.com>
 M:      Chen-Yu Tsai <wens@csie.org>
 L:      linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:      Maintained
@@ -4627,7 +4627,7 @@ F:	include/uapi/drm/drm*
 F:      include/linux/vga*
 
 DRM DRIVERS FOR ALLWINNER A10
-M:      Maxime Ripard  <maxime.ripard@free-electrons.com>
+M:      Maxime Ripard  <maxime.ripard@bootlin.com>
 L:      dri-devel@lists.freedesktop.org
 S:      Supported
 F:      drivers/gpu/drm/sun4i/
@@ -13658,7 +13658,8 @@ S:	Supported
 F:      drivers/i2c/busses/i2c-tegra.c
 
 TEGRA IOMMU DRIVERS
-M:      Hiroshi Doyu <hdoyu@nvidia.com>
+M:      Thierry Reding <thierry.reding@gmail.com>
+L:      linux-tegra@vger.kernel.org
 S:      Supported
 F:      drivers/iommu/tegra*
 
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 78a647080ebc..199ebc1c4538 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -22,6 +22,7 @@ config ARM_PTDUMP_DEBUGFS
 
 config DEBUG_WX
         bool "Warn on W+X mappings at boot"
+        depends on MMU
         select ARM_PTDUMP_CORE
         ---help---
                 Generate a warning if any W+X mappings are found at boot.
diff --git a/arch/arm/boot/deflate_xip_data.sh b/arch/arm/boot/deflate_xip_data.sh
index 1189598a25eb..5e7d758ebdd6 100755
--- a/arch/arm/boot/deflate_xip_data.sh
+++ b/arch/arm/boot/deflate_xip_data.sh
@@ -30,7 +30,7 @@ esac
 
 sym_val() {
         # extract hex value for symbol in $1
-        local val=$($NM "$VMLINUX" | sed -n "/ $1$/{s/ .*$//p;q}")
+        local val=$($NM "$VMLINUX" 2>/dev/null | sed -n "/ $1\$/{s/ .*$//p;q}")
         [ "$val" ] || { echo "can't find $1 in $VMLINUX" 1>&2; exit 1; }
         # convert from hex to decimal
         echo $((0x$val))
@@ -48,12 +48,12 @@ data_end=$(($_edata_loc - $base_offset))
 file_end=$(stat -c "%s" "$XIPIMAGE")
 if [ "$file_end" != "$data_end" ]; then
         printf "end of xipImage doesn't match with _edata_loc (%#x vs %#x)\n" \
-               $(($file_end + $base_offset)) $_edata_loc 2>&1
+               $(($file_end + $base_offset)) $_edata_loc 1>&2
         exit 1;
 fi
 
 # be ready to clean up
-trap 'rm -f "$XIPIMAGE.tmp"' 0 1 2 3
+trap 'rm -f "$XIPIMAGE.tmp"; exit 1' 1 2 3
 
 # substitute the data section by a compressed version
 $DD if="$XIPIMAGE" count=$data_start iflag=count_bytes of="$XIPIMAGE.tmp"
diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi
index b0d8431a3700..ae2b8c952e80 100644
--- a/arch/arm/boot/dts/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed-g4.dtsi
@@ -42,6 +42,11 @@
                 };
         };
 
+        memory@40000000 {
+                device_type = "memory";
+                reg = <0x40000000 0>;
+        };
+
         ahb {
                 compatible = "simple-bus";
                 #address-cells = <1>;
diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi
index 40de3b66c33f..2477ebc11d9d 100644
--- a/arch/arm/boot/dts/aspeed-g5.dtsi
+++ b/arch/arm/boot/dts/aspeed-g5.dtsi
@@ -42,6 +42,11 @@
                 };
         };
 
+        memory@80000000 {
+                device_type = "memory";
+                reg = <0x80000000 0>;
+        };
+
         ahb {
                 compatible = "simple-bus";
                 #address-cells = <1>;
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index a7a5dc7b2700..e7d2db839d70 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -82,7 +82,7 @@
                 enable-active-high;
         };
 
-        reg_usb_otg2_vbus: regulator-usb-otg1-vbus {
+        reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
                 compatible = "regulator-fixed";
                 regulator-name = "usb_otg2_vbus";
                 regulator-min-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 6102e4e7f35c..354aff45c1af 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -927,6 +927,7 @@
         i2s: i2s@ff890000 {
                 compatible = "rockchip,rk3288-i2s", "rockchip,rk3066-i2s";
                 reg = <0x0 0xff890000 0x0 0x10000>;
+                #sound-dai-cells = <0>;
                 interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
                 #address-cells = <1>;
                 #size-cells = <0>;
@@ -1176,6 +1177,7 @@
                 compatible = "rockchip,rk3288-dw-hdmi";
                 reg = <0x0 0xff980000 0x0 0x20000>;
                 reg-io-width = <4>;
+                #sound-dai-cells = <0>;
                 rockchip,grf = <&grf>;
                 interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
                 clocks = <&cru  PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>;
diff --git a/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts b/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts
index 51e6f1d21c32..b2758dd8ce43 100644
--- a/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts
@@ -42,7 +42,6 @@
 
 /dts-v1/;
 #include "sun6i-a31s.dtsi"
-#include "sunxi-common-regulators.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 
 / {
@@ -99,6 +98,7 @@
         pinctrl-0 = <&gmac_pins_rgmii_a>, <&gmac_phy_reset_pin_bpi_m2>;
         phy = <&phy1>;
         phy-mode = "rgmii";
+        phy-supply = <&reg_dldo1>;
         snps,reset-gpio = <&pio 0 21 GPIO_ACTIVE_HIGH>; /* PA21 */
         snps,reset-active-low;
         snps,reset-delays-us = <0 10000 30000>;
@@ -118,7 +118,7 @@
 &mmc0 {
         pinctrl-names = "default";
         pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_bpi_m2>;
-        vmmc-supply = <&reg_vcc3v0>;
+        vmmc-supply = <&reg_dcdc1>;
         bus-width = <4>;
         cd-gpios = <&pio 0 4 GPIO_ACTIVE_HIGH>; /* PA4 */
         cd-inverted;
@@ -132,7 +132,7 @@
 &mmc2 {
         pinctrl-names = "default";
         pinctrl-0 = <&mmc2_pins_a>;
-        vmmc-supply = <&reg_vcc3v0>;
+        vmmc-supply = <&reg_aldo1>;
         mmc-pwrseq = <&mmc2_pwrseq>;
         bus-width = <4>;
         non-removable;
@@ -163,6 +163,8 @@
                 reg = <0x68>;
                 interrupt-parent = <&nmi_intc>;
                 interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+                eldoin-supply = <&reg_dcdc1>;
+                x-powers,drive-vbus-en;
         };
 };
 
@@ -193,7 +195,28 @@
 
 #include "axp22x.dtsi"
 
+&reg_aldo1 {
+        regulator-min-microvolt = <3300000>;
+        regulator-max-microvolt = <3300000>;
+        regulator-name = "vcc-wifi";
+};
+
+&reg_aldo2 {
+        regulator-always-on;
+        regulator-min-microvolt = <2500000>;
+        regulator-max-microvolt = <2500000>;
+        regulator-name = "vcc-gmac";
+};
+
+&reg_aldo3 {
+        regulator-always-on;
+        regulator-min-microvolt = <3000000>;
+        regulator-max-microvolt = <3000000>;
+        regulator-name = "avcc";
+};
+
 &reg_dc5ldo {
+        regulator-always-on;
         regulator-min-microvolt = <700000>;
         regulator-max-microvolt = <1320000>;
         regulator-name = "vdd-cpus";
@@ -233,6 +256,40 @@
         regulator-name = "vcc-dram";
 };
 
+&reg_dldo1 {
+        regulator-min-microvolt = <3000000>;
+        regulator-max-microvolt = <3000000>;
+        regulator-name = "vcc-mac";
+};
+
+&reg_dldo2 {
+        regulator-min-microvolt = <2800000>;
+        regulator-max-microvolt = <2800000>;
+        regulator-name = "avdd-csi";
+};
+
+&reg_dldo3 {
+        regulator-always-on;
+        regulator-min-microvolt = <3300000>;
+        regulator-max-microvolt = <3300000>;
+        regulator-name = "vcc-pb";
+};
+
+&reg_eldo1 {
+        regulator-min-microvolt = <1800000>;
+        regulator-max-microvolt = <1800000>;
+        regulator-name = "vdd-csi";
+        status = "okay";
+};
+
+&reg_ldo_io1 {
+        regulator-always-on;
+        regulator-min-microvolt = <1800000>;
+        regulator-max-microvolt = <1800000>;
+        regulator-name = "vcc-pm-cpus";
+        status = "okay";
+};
+
 &uart0 {
         pinctrl-names = "default";
         pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
index 9c99e817535e..5b85889f82ee 100644
--- a/arch/arm/include/asm/vdso.h
+++ b/arch/arm/include/asm/vdso.h
@@ -12,8 +12,6 @@ struct mm_struct;
 
 void arm_install_vdso(struct mm_struct *mm, unsigned long addr);
 
-extern char vdso_start, vdso_end;
-
 extern unsigned int vdso_total_pages;
 
 #else /* CONFIG_VDSO */
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index a4d6dc0f2427..f4dd7f9663c1 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -39,6 +39,8 @@
 
 static struct page **vdso_text_pagelist;
 
+extern char vdso_start[], vdso_end[];
+
 /* Total number of pages needed for the data and text portions of the VDSO. */
 unsigned int vdso_total_pages __ro_after_init;
 
@@ -197,13 +199,13 @@ static int __init vdso_init(void)
         unsigned int text_pages;
         int i;
 
-        if (memcmp(&vdso_start, "\177ELF", 4)) {
+        if (memcmp(vdso_start, "\177ELF", 4)) {
                 pr_err("VDSO is not a valid ELF object!\n");
                 return -ENOEXEC;
         }
 
-        text_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
-        pr_debug("vdso: %i text pages at base %p\n", text_pages, &vdso_start);
+        text_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+        pr_debug("vdso: %i text pages at base %p\n", text_pages, vdso_start);
 
         /* Allocate the VDSO text pagelist */
         vdso_text_pagelist = kcalloc(text_pages, sizeof(struct page *),
@@ -218,7 +220,7 @@ static int __init vdso_init(void)
         for (i = 0; i < text_pages; i++) {
                 struct page *page;
 
-                page = virt_to_page(&vdso_start + i * PAGE_SIZE);
+                page = virt_to_page(vdso_start + i * PAGE_SIZE);
                 vdso_text_pagelist[i] = page;
         }
 
@@ -229,7 +231,7 @@ static int __init vdso_init(void)
 
         cntvct_ok = cntvct_functional();
 
-        patch_vdso(&vdso_start);
+        patch_vdso(vdso_start);
 
         return 0;
 }
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index a3e78074be70..62eb7d668890 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -127,8 +127,8 @@ static struct gpiod_lookup_table mmc_gpios_table = {
         .dev_id = "da830-mmc.0",
         .table = {
                 /* CD: gpio3_12: gpio60: chip 1 contains gpio range 32-63*/
-                GPIO_LOOKUP("davinci_gpio.1", 28, "cd", GPIO_ACTIVE_LOW),
-                GPIO_LOOKUP("davinci_gpio.1", 29, "wp", GPIO_ACTIVE_LOW),
+                GPIO_LOOKUP("davinci_gpio.0", 28, "cd", GPIO_ACTIVE_LOW),
+                GPIO_LOOKUP("davinci_gpio.0", 29, "wp", GPIO_ACTIVE_LOW),
         },
 };
 
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 7e5d7a083707..36cd23c8be9b 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -133,6 +133,9 @@ static void __init u8500_init_machine(void)
         if (of_machine_is_compatible("st-ericsson,u8540"))
                 of_platform_populate(NULL, u8500_local_bus_nodes,
                                      u8540_auxdata_lookup, NULL);
+        else
+                of_platform_populate(NULL, u8500_local_bus_nodes,
+                                     NULL, NULL);
 }
 
 static const char * stericsson_dt_platform_compat[] = {
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index d443e481c3e9..8805a59bae53 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -888,11 +888,8 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
         timer->irq = irq->start;
         timer->pdev = pdev;
 
-        /* Skip pm_runtime_enable for OMAP1 */
-        if (!(timer->capability & OMAP_TIMER_NEEDS_RESET)) {
-                pm_runtime_enable(dev);
-                pm_runtime_irq_safe(dev);
-        }
+        pm_runtime_enable(dev);
+        pm_runtime_irq_safe(dev);
 
         if (!timer->reserved) {
                 ret = pm_runtime_get_sync(dev);
diff --git a/arch/arm/plat-omap/include/plat/sram.h b/arch/arm/plat-omap/include/plat/sram.h
index fb061cf0d736..30a07730807a 100644
--- a/arch/arm/plat-omap/include/plat/sram.h
+++ b/arch/arm/plat-omap/include/plat/sram.h
@@ -5,13 +5,4 @@ void omap_map_sram(unsigned long start, unsigned long size,
                         unsigned long skip, int cached);
 void omap_sram_reset(void);
 
-extern void *omap_sram_push_address(unsigned long size);
-
-/* Macro to push a function to the internal SRAM, using the fncpy API */
-#define omap_sram_push(funcp, size) ({                          \
-        typeof(&(funcp)) _res = NULL;                           \
-        void *_sram_address = omap_sram_push_address(size);     \
-        if (_sram_address)                                      \
-                _res = fncpy(_sram_address, &(funcp), size);    \
-        _res;                                                   \
-})
+extern void *omap_sram_push(void *funcp, unsigned long size);
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index a5bc92d7e476..921840acf65c 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -23,6 +23,7 @@
 #include <asm/fncpy.h>
 #include <asm/tlb.h>
 #include <asm/cacheflush.h>
+#include <asm/set_memory.h>
 
 #include <asm/mach/map.h>
 
@@ -42,7 +43,7 @@ static void __iomem *omap_sram_ceil;
  * Note that fncpy requires the returned address to be aligned
  * to an 8-byte boundary.
  */
-void *omap_sram_push_address(unsigned long size)
+static void *omap_sram_push_address(unsigned long size)
 {
         unsigned long available, new_ceil = (unsigned long)omap_sram_ceil;
 
@@ -60,6 +61,30 @@ void *omap_sram_push_address(unsigned long size)
         return (void *)omap_sram_ceil;
 }
 
+void *omap_sram_push(void *funcp, unsigned long size)
+{
+        void *sram;
+        unsigned long base;
+        int pages;
+        void *dst = NULL;
+
+        sram = omap_sram_push_address(size);
+        if (!sram)
+                return NULL;
+
+        base = (unsigned long)sram & PAGE_MASK;
+        pages = PAGE_ALIGN(size) / PAGE_SIZE;
+
+        set_memory_rw(base, pages);
+
+        dst = fncpy(sram, funcp, size);
+
+        set_memory_ro(base, pages);
+        set_memory_x(base, pages);
+
+        return dst;
+}
+
 /*
  * The SRAM context is lost during off-idle and stack
  * needs to be reset.
@@ -75,6 +100,9 @@ void omap_sram_reset(void)
 void __init omap_map_sram(unsigned long start, unsigned long size,
                                  unsigned long skip, int cached)
 {
+        unsigned long base;
+        int pages;
+
         if (size == 0)
                 return;
 
@@ -95,4 +123,10 @@ void __init omap_map_sram(unsigned long start, unsigned long size,
          */
         memset_io(omap_sram_base + omap_sram_skip, 0,
                   omap_sram_size - omap_sram_skip);
+
+        base = (unsigned long)omap_sram_base;
+        pages = PAGE_ALIGN(omap_sram_size) / PAGE_SIZE;
+
+        set_memory_ro(base, pages);
+        set_memory_x(base, pages);
 }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 03c6a3c72f9c..4c375e11ae95 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -648,7 +648,7 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
  */
 static int vfp_dying_cpu(unsigned int cpu)
 {
-        vfp_force_reload(cpu, current_thread_info());
+        vfp_current_hw_state[cpu] = NULL;
         return 0;
 }
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index 03f195025390..204bdb9857b9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -406,8 +406,9 @@
         wlan_pd_n: wlan-pd-n {
                 compatible = "regulator-fixed";
                 regulator-name = "wlan_pd_n";
+                pinctrl-names = "default";
+                pinctrl-0 = <&wlan_module_reset_l>;
 
-                /* Note the wlan_module_reset_l pinctrl */
                 enable-active-high;
                 gpio = <&gpio1 11 GPIO_ACTIVE_HIGH>;
 
@@ -983,12 +984,6 @@ ap_i2c_audio: &i2c8 {
         pinctrl-0 = <
                 &ap_pwroff      /* AP will auto-assert this when in S3 */
                 &clk_32k        /* This pin is always 32k on gru boards */
-
-                /*
-                 * We want this driven low ASAP; firmware should help us, but
-                 * we can help ourselves too.
-                 */
-                &wlan_module_reset_l
         >;
 
         pcfg_output_low: pcfg-output-low {
@@ -1168,12 +1163,7 @@ ap_i2c_audio: &i2c8 {
                 };
 
                 wlan_module_reset_l: wlan-module-reset-l {
-                        /*
-                         * We want this driven low ASAP (As {Soon,Strongly} As
-                         * Possible), to avoid leakage through the powered-down
-                         * WiFi.
-                         */
-                        rockchip,pins = <1 11 RK_FUNC_GPIO &pcfg_output_low>;
+                        rockchip,pins = <1 11 RK_FUNC_GPIO &pcfg_pull_none>;
                 };
 
                 bt_host_wake_l: bt-host-wake-l {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 2605118d4b4c..0b81ca1d07e7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -411,8 +411,8 @@
                         reg = <0x0 0xfe800000 0x0 0x100000>;
                         interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>;
                         dr_mode = "otg";
-                        phys = <&u2phy0_otg>, <&tcphy0_usb3>;
-                        phy-names = "usb2-phy", "usb3-phy";
+                        phys = <&u2phy0_otg>;
+                        phy-names = "usb2-phy";
                         phy_type = "utmi_wide";
                         snps,dis_enblslpm_quirk;
                         snps,dis-u2-freeclk-exists-quirk;
@@ -444,8 +444,8 @@
                         reg = <0x0 0xfe900000 0x0 0x100000>;
                         interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>;
                         dr_mode = "otg";
-                        phys = <&u2phy1_otg>, <&tcphy1_usb3>;
-                        phy-names = "usb2-phy", "usb3-phy";
+                        phys = <&u2phy1_otg>;
+                        phy-names = "usb2-phy";
                         phy_type = "utmi_wide";
                         snps,dis_enblslpm_quirk;
                         snps,dis-u2-freeclk-exists-quirk;
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 0abeb0e2d616..37671feb2bf6 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -87,6 +87,9 @@ typedef struct {
         /* Number of bits in the mm_cpumask */
         atomic_t active_cpus;
 
+        /* Number of users of the external (Nest) MMU */
+        atomic_t copros;
+
         /* NPU NMMU context */
         struct npu_context *npu_context;
 
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 8eea90f80e45..19b45ba6caf9 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -47,9 +47,6 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad
 #endif
 extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
-extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-                                     unsigned long page_size);
-extern void radix__flush_tlb_lpid(unsigned long lpid);
 extern void radix__flush_tlb_all(void);
 extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
                                         unsigned long address);
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index a2c5c95882cf..2e2bacbdf6ed 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -203,6 +203,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_DAWR                    LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX                   LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG                LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_P9_TLBIE_BUG            LONG_ASM_CONST(0x2000000000000000)
 #define CPU_FTR_POWER9_DD1              LONG_ASM_CONST(0x4000000000000000)
 #define CPU_FTR_POWER9_DD2_1            LONG_ASM_CONST(0x8000000000000000)
 
@@ -465,7 +466,7 @@ static inline void cpu_feature_keys_init(void) { }
             CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
             CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
             CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
-            CPU_FTR_PKEY)
+            CPU_FTR_PKEY | CPU_FTR_P9_TLBIE_BUG)
 #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
                              (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 051b3d63afe3..3a15b6db9501 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -92,15 +92,23 @@ static inline void dec_mm_active_cpus(struct mm_struct *mm)
 static inline void mm_context_add_copro(struct mm_struct *mm)
 {
         /*
-         * On hash, should only be called once over the lifetime of
-         * the context, as we can't decrement the active cpus count
-         * and flush properly for the time being.
+         * If any copro is in use, increment the active CPU count
+         * in order to force TLB invalidations to be global as to
+         * propagate to the Nest MMU.
          */
-        inc_mm_active_cpus(mm);
+        if (atomic_inc_return(&mm->context.copros) == 1)
+                inc_mm_active_cpus(mm);
 }
 
 static inline void mm_context_remove_copro(struct mm_struct *mm)
 {
+        int c;
+
+        c = atomic_dec_if_positive(&mm->context.copros);
+
+        /* Detect imbalance between add and remove */
+        WARN_ON(c < 0);
+
         /*
          * Need to broadcast a global flush of the full mm before
          * decrementing active_cpus count, as the next TLBI may be
@@ -111,7 +119,7 @@ static inline void mm_context_remove_copro(struct mm_struct *mm)
          * for the time being. Invalidations will remain global if
          * used on hash.
          */
-        if (radix_enabled()) {
+        if (c == 0 && radix_enabled()) {
                 flush_all_mm(mm);
                 dec_mm_active_cpus(mm);
         }
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 945e2c29ad2d..8ca5d5b74618 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -709,6 +709,9 @@ static __init void cpufeatures_cpu_quirks(void)
                 cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
         else if ((version & 0xffffefff) == 0x004e0201)
                 cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+
+        if ((version & 0xffff0000) == 0x004e0000)
+                cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
 }
 
 static void __init cpufeatures_setup_finished(void)
@@ -720,6 +723,9 @@ static void __init cpufeatures_setup_finished(void)
                 cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
         }
 
+        /* Make sure powerpc_base_platform is non-NULL */
+        powerpc_base_platform = cur_cpu_spec->platform;
+
         system_registers.lpcr = mfspr(SPRN_LPCR);
         system_registers.hfscr = mfspr(SPRN_HFSCR);
         system_registers.fscr = mfspr(SPRN_FSCR);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3ac87e53b3da..1ecfd8ffb098 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -706,7 +706,7 @@ EXC_COMMON_BEGIN(bad_addr_slb)
         ld      r3, PACA_EXSLB+EX_DAR(r13)
         std     r3, _DAR(r1)
         beq     cr6, 2f
-        li      r10, 0x480              /* fix trap number for I-SLB miss */
+        li      r10, 0x481              /* fix trap number for I-SLB miss */
         std     r10, _TRAP(r1)
 2:      bl      save_nvgprs
         addi    r3, r1, STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index f88038847790..061aa0f47bb1 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -476,6 +476,14 @@ void force_external_irq_replay(void)
          */
         WARN_ON(!arch_irqs_disabled());
 
+        /*
+         * Interrupts must always be hard disabled before irq_happened is
+         * modified (to prevent lost update in case of interrupt between
+         * load and store).
+         */
+        __hard_irq_disable();
+        local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
         /* Indicate in the PACA that we have an interrupt to replay */
         local_paca->irq_happened |= PACA_IRQ_EE;
 }
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 5cb4e4687107..5d9bafe9a371 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -157,6 +157,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
         asm volatile("ptesync": : :"memory");
         asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
                      : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
+        if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
+                asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
+                             : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
         asm volatile("ptesync": : :"memory");
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 8888e625a999..e1c083fbe434 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -473,6 +473,17 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
                         trace_tlbie(kvm->arch.lpid, 0, rbvalues[i],
                                 kvm->arch.lpid, 0, 0, 0);
                 }
+
+                if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+                        /*
+                         * Need the extra ptesync to make sure we don't
+                         * re-order the tlbie
+                         */
+                        asm volatile("ptesync": : :"memory");
+                        asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+                                     "r" (rbvalues[0]), "r" (kvm->arch.lpid));
+                }
+
                 asm volatile("eieio; tlbsync; ptesync" : : : "memory");
                 kvm->arch.tlbie_lock = 0;
         } else {
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index a0675e91ad7d..656933c85925 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -201,6 +201,15 @@ static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
         return va;
 }
 
+static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+        if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+                /* Need the extra ptesync to ensure we don't reorder tlbie*/
+                asm volatile("ptesync": : :"memory");
+                ___tlbie(vpn, psize, apsize, ssize);
+        }
+}
+
 static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
         unsigned long rb;
@@ -278,6 +287,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
                 asm volatile("ptesync": : :"memory");
         } else {
                 __tlbie(vpn, psize, apsize, ssize);
+                fixup_tlbie(vpn, psize, apsize, ssize);
                 asm volatile("eieio; tlbsync; ptesync": : :"memory");
         }
         if (lock_tlbie && !use_local)
@@ -771,7 +781,7 @@ static void native_hpte_clear(void)
  */
 static void native_flush_hash_range(unsigned long number, int local)
 {
-        unsigned long vpn;
+        unsigned long vpn = 0;
         unsigned long hash, index, hidx, shift, slot;
         struct hash_pte *hptep;
         unsigned long hpte_v;
@@ -843,6 +853,10 @@ static void native_flush_hash_range(unsigned long number, int local)
                                 __tlbie(vpn, psize, psize, ssize);
                         } pte_iterate_hashed_end();
                 }
+                /*
+                 * Just do one more with the last used values.
+                 */
+                fixup_tlbie(vpn, psize, psize, ssize);
                 asm volatile("eieio; tlbsync; ptesync":::"memory");
 
                 if (lock_tlbie)
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 929d9ef7083f..3f980baade4c 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -173,6 +173,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
         mm_iommu_init(mm);
 #endif
         atomic_set(&mm->context.active_cpus, 0);
+        atomic_set(&mm->context.copros, 0);
 
         return 0;
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 28c980eb4422..adf469f312f2 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -481,6 +481,7 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
                              "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
                 trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
         }
+        /* do we need fixup here ?*/
         asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 71d1b19ad1c0..a07f5372a4bf 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -119,6 +119,49 @@ static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
         trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbiel_va(unsigned long va, unsigned long pid,
+                               unsigned long ap, unsigned long ric)
+{
+        unsigned long rb,rs,prs,r;
+
+        rb = va & ~(PPC_BITMASK(52, 63));
+        rb |= ap << PPC_BITLSHIFT(58);
+        rs = pid << PPC_BITLSHIFT(31);
+        prs = 1; /* process scoped */
+        r = 1;   /* raidx format */
+
+        asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+                     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+        trace_tlbie(0, 1, rb, rs, ric, prs, r);
+}
+
+static inline void __tlbie_va(unsigned long va, unsigned long pid,
+                              unsigned long ap, unsigned long ric)
+{
+        unsigned long rb,rs,prs,r;
+
+        rb = va & ~(PPC_BITMASK(52, 63));
+        rb |= ap << PPC_BITLSHIFT(58);
+        rs = pid << PPC_BITLSHIFT(31);
+        prs = 1; /* process scoped */
+        r = 1;   /* raidx format */
+
+        asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+                     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+        trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static inline void fixup_tlbie(void)
+{
+        unsigned long pid = 0;
+        unsigned long va = ((1UL << 52) - 1);
+
+        if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+                asm volatile("ptesync": : :"memory");
+                __tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+        }
+}
+
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
@@ -151,24 +194,25 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
         asm volatile("ptesync": : :"memory");
-        __tlbie_pid(pid, ric);
-        asm volatile("eieio; tlbsync; ptesync": : :"memory");
-}
 
-static inline void __tlbiel_va(unsigned long va, unsigned long pid,
-                               unsigned long ap, unsigned long ric)
-{
-        unsigned long rb,rs,prs,r;
-
-        rb = va & ~(PPC_BITMASK(52, 63));
-        rb |= ap << PPC_BITLSHIFT(58);
-        rs = pid << PPC_BITLSHIFT(31);
-        prs = 1; /* process scoped */
-        r = 1;   /* raidx format */
-
-        asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-                     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-        trace_tlbie(0, 1, rb, rs, ric, prs, r);
+        /*
+         * Workaround the fact that the "ric" argument to __tlbie_pid
+         * must be a compile-time contraint to match the "i" constraint
+         * in the asm statement.
+         */
+        switch (ric) {
+        case RIC_FLUSH_TLB:
+                __tlbie_pid(pid, RIC_FLUSH_TLB);
+                break;
+        case RIC_FLUSH_PWC:
+                __tlbie_pid(pid, RIC_FLUSH_PWC);
+                break;
+        case RIC_FLUSH_ALL:
+        default:
+                __tlbie_pid(pid, RIC_FLUSH_ALL);
+        }
+        fixup_tlbie();
+        asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
 static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
@@ -203,22 +247,6 @@ static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
         asm volatile("ptesync": : :"memory");
 }
 
-static inline void __tlbie_va(unsigned long va, unsigned long pid,
-                             unsigned long ap, unsigned long ric)
-{
-        unsigned long rb,rs,prs,r;
-
-        rb = va & ~(PPC_BITMASK(52, 63));
-        rb |= ap << PPC_BITLSHIFT(58);
-        rs = pid << PPC_BITLSHIFT(31);
-        prs = 1; /* process scoped */
-        r = 1;   /* raidx format */
-
-        asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-                     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-        trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
-
 static inline void __tlbie_va_range(unsigned long start, unsigned long end,
                                     unsigned long pid, unsigned long page_size,
                                     unsigned long psize)
@@ -237,6 +265,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 
         asm volatile("ptesync": : :"memory");
         __tlbie_va(va, pid, ap, ric);
+        fixup_tlbie();
         asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -248,6 +277,7 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
         if (also_pwc)
                 __tlbie_pid(pid, RIC_FLUSH_PWC);
         __tlbie_va_range(start, end, pid, page_size, psize);
+        fixup_tlbie();
         asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -311,6 +341,16 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
+static bool mm_needs_flush_escalation(struct mm_struct *mm)
+{
+        /*
+         * P9 nest MMU has issues with the page walk cache
+         * caching PTEs and not flushing them properly when
+         * RIC = 0 for a PID/LPID invalidate
+         */
+        return atomic_read(&mm->context.copros) != 0;
+}
+
 #ifdef CONFIG_SMP
 void radix__flush_tlb_mm(struct mm_struct *mm)
 {
@@ -321,9 +361,12 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
                 return;
 
         preempt_disable();
-        if (!mm_is_thread_local(mm))
-                _tlbie_pid(pid, RIC_FLUSH_TLB);
-        else
+        if (!mm_is_thread_local(mm)) {
+                if (mm_needs_flush_escalation(mm))
+                        _tlbie_pid(pid, RIC_FLUSH_ALL);
+                else
+                        _tlbie_pid(pid, RIC_FLUSH_TLB);
+        } else
                 _tlbiel_pid(pid, RIC_FLUSH_TLB);
         preempt_enable();
 }
@@ -435,10 +478,14 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
         }
 
         if (full) {
-                if (local)
+                if (local) {
                         _tlbiel_pid(pid, RIC_FLUSH_TLB);
-                else
-                        _tlbie_pid(pid, RIC_FLUSH_TLB);
+                } else {
+                        if (mm_needs_flush_escalation(mm))
+                                _tlbie_pid(pid, RIC_FLUSH_ALL);
+                        else
+                                _tlbie_pid(pid, RIC_FLUSH_TLB);
+                }
         } else {
                 bool hflush = false;
                 unsigned long hstart, hend;
@@ -465,6 +512,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
                         if (hflush)
                                 __tlbie_va_range(hstart, hend, pid,
                                                 HPAGE_PMD_SIZE, MMU_PAGE_2M);
+                        fixup_tlbie();
                         asm volatile("eieio; tlbsync; ptesync": : :"memory");
                 }
         }
@@ -548,6 +596,9 @@ static inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
         }
 
         if (full) {
+                if (!local && mm_needs_flush_escalation(mm))
+                        also_pwc = true;
+
                 if (local)
                         _tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
                 else
@@ -603,46 +654,6 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-                              unsigned long page_size)
-{
-        unsigned long rb,rs,prs,r;
-        unsigned long ap;
-        unsigned long ric = RIC_FLUSH_TLB;
-
-        ap = mmu_get_ap(radix_get_mmu_psize(page_size));
-        rb = gpa & ~(PPC_BITMASK(52, 63));
-        rb |= ap << PPC_BITLSHIFT(58);
-        rs = lpid & ((1UL << 32) - 1);
-        prs = 0; /* process scoped */
-        r = 1;   /* raidx format */
-
-        asm volatile("ptesync": : :"memory");
-        asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-                     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-        asm volatile("eieio; tlbsync; ptesync": : :"memory");
-        trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
-}
-EXPORT_SYMBOL(radix__flush_tlb_lpid_va);
-
-void radix__flush_tlb_lpid(unsigned long lpid)
-{
-        unsigned long rb,rs,prs,r;
-        unsigned long ric = RIC_FLUSH_ALL;
-
-        rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
-        rs = lpid & ((1UL << 32) - 1);
-        prs = 0; /* partition scoped */
-        r = 1;   /* raidx format */
-
-        asm volatile("ptesync": : :"memory");
-        asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-                     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-        asm volatile("eieio; tlbsync; ptesync": : :"memory");
-        trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
-}
-EXPORT_SYMBOL(radix__flush_tlb_lpid);
-
 void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
                                 unsigned long start, unsigned long end)
 {
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index dd9464920456..ef22b275d050 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -474,6 +474,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
                 shost->dma_boundary = 0xffffffff;
 
         shost->use_blk_mq = scsi_use_blk_mq;
+        shost->use_blk_mq = scsi_use_blk_mq || shost->hostt->force_blk_mq;
 
         device_initialize(&shost->shost_gendev);
         dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 5293e6827ce5..3a9eca163db8 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -1045,11 +1045,7 @@ static void set_performant_mode(struct ctlr_info *h, struct CommandList *c,
                 c->busaddr |= 1 | (h->blockFetchTable[c->Header.SGList] << 1);
                 if (unlikely(!h->msix_vectors))
                         return;
-                if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-                        c->Header.ReplyQueue =
-                                raw_smp_processor_id() % h->nreply_queues;
-                else
-                        c->Header.ReplyQueue = reply_queue % h->nreply_queues;
+                c->Header.ReplyQueue = reply_queue;
         }
 }
 
@@ -1063,10 +1059,7 @@ static void set_ioaccel1_performant_mode(struct ctlr_info *h,
          * Tell the controller to post the reply to the queue for this
          * processor.  This seems to give the best I/O throughput.
          */
-        if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-                cp->ReplyQueue = smp_processor_id() % h->nreply_queues;
-        else
-                cp->ReplyQueue = reply_queue % h->nreply_queues;
+        cp->ReplyQueue = reply_queue;
         /*
          * Set the bits in the address sent down to include:
          *  - performant mode bit (bit 0)
@@ -1087,10 +1080,7 @@ static void set_ioaccel2_tmf_performant_mode(struct ctlr_info *h,
         /* Tell the controller to post the reply to the queue for this
          * processor.  This seems to give the best I/O throughput.
          */
-        if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-                cp->reply_queue = smp_processor_id() % h->nreply_queues;
-        else
-                cp->reply_queue = reply_queue % h->nreply_queues;
+        cp->reply_queue = reply_queue;
         /* Set the bits in the address sent down to include:
          *  - performant mode bit not used in ioaccel mode 2
          *  - pull count (bits 0-3)
@@ -1109,10 +1099,7 @@ static void set_ioaccel2_performant_mode(struct ctlr_info *h,
          * Tell the controller to post the reply to the queue for this
          * processor.  This seems to give the best I/O throughput.
          */
-        if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-                cp->reply_queue = smp_processor_id() % h->nreply_queues;
-        else
-                cp->reply_queue = reply_queue % h->nreply_queues;
+        cp->reply_queue = reply_queue;
         /*
          * Set the bits in the address sent down to include:
          *  - performant mode bit not used in ioaccel mode 2
@@ -1157,6 +1144,8 @@ static void __enqueue_cmd_and_start_io(struct ctlr_info *h,
 {
         dial_down_lockup_detection_during_fw_flash(h, c);
         atomic_inc(&h->commands_outstanding);
+
+        reply_queue = h->reply_map[raw_smp_processor_id()];
         switch (c->cmd_type) {
         case CMD_IOACCEL1:
                 set_ioaccel1_performant_mode(h, c, reply_queue);
@@ -7376,6 +7365,26 @@ static void hpsa_disable_interrupt_mode(struct ctlr_info *h)
         h->msix_vectors = 0;
 }
 
+static void hpsa_setup_reply_map(struct ctlr_info *h)
+{
+        const struct cpumask *mask;
+        unsigned int queue, cpu;
+
+        for (queue = 0; queue < h->msix_vectors; queue++) {
+                mask = pci_irq_get_affinity(h->pdev, queue);
+                if (!mask)
+                        goto fallback;
+
+                for_each_cpu(cpu, mask)
+                        h->reply_map[cpu] = queue;
+        }
+        return;
+
+fallback:
+        for_each_possible_cpu(cpu)
+                h->reply_map[cpu] = 0;
+}
+
 /* If MSI/MSI-X is supported by the kernel we will try to enable it on
  * controllers that are capable. If not, we use legacy INTx mode.
  */
@@ -7771,6 +7780,10 @@ static int hpsa_pci_init(struct ctlr_info *h)
         err = hpsa_interrupt_mode(h);
         if (err)
                 goto clean1;
+
+        /* setup mapping between CPU and reply queue */
+        hpsa_setup_reply_map(h);
+
         err = hpsa_pci_find_memory_BAR(h->pdev, &h->paddr);
         if (err)
                 goto clean2;    /* intmode+region, pci */
@@ -8480,6 +8493,28 @@ static struct workqueue_struct *hpsa_create_controller_wq(struct ctlr_info *h,
         return wq;
 }
 
+static void hpda_free_ctlr_info(struct ctlr_info *h)
+{
+        kfree(h->reply_map);
+        kfree(h);
+}
+
+static struct ctlr_info *hpda_alloc_ctlr_info(void)
+{
+        struct ctlr_info *h;
+
+        h = kzalloc(sizeof(*h), GFP_KERNEL);
+        if (!h)
+                return NULL;
+
+        h->reply_map = kzalloc(sizeof(*h->reply_map) * nr_cpu_ids, GFP_KERNEL);
+        if (!h->reply_map) {
+                kfree(h);
+                return NULL;
+        }
+        return h;
+}
+
 static int hpsa_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
         int dac, rc;
@@ -8517,7 +8552,7 @@ reinit_after_soft_reset:
          * the driver.  See comments in hpsa.h for more info.
          */
         BUILD_BUG_ON(sizeof(struct CommandList) % COMMANDLIST_ALIGNMENT);
-        h = kzalloc(sizeof(*h), GFP_KERNEL);
+        h = hpda_alloc_ctlr_info();
         if (!h) {
                 dev_err(&pdev->dev, "Failed to allocate controller head\n");
                 return -ENOMEM;
@@ -8916,7 +8951,7 @@ static void hpsa_remove_one(struct pci_dev *pdev)
         h->lockup_detected = NULL;                      /* init_one 2 */
         /* (void) pci_disable_pcie_error_reporting(pdev); */    /* init_one 1 */
 
-        kfree(h);                                       /* init_one 1 */
+        hpda_free_ctlr_info(h);                         /* init_one 1 */
 }
 
 static int hpsa_suspend(__attribute__((unused)) struct pci_dev *pdev,
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 018f980a701c..fb9f5e7f8209 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -158,6 +158,7 @@ struct bmic_controller_parameters {
 #pragma pack()
 
 struct ctlr_info {
+        unsigned int *reply_map;
         int     ctlr;
         char    devname[8];
         char    *product_name;
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index b1b1d3a3b173..daefe8172b04 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3579,11 +3579,9 @@ static void ibmvfc_tgt_implicit_logout(struct ibmvfc_target *tgt)
 static int ibmvfc_adisc_needs_plogi(struct ibmvfc_passthru_mad *mad,
                                     struct ibmvfc_target *tgt)
 {
-        if (memcmp(&mad->fc_iu.response[2], &tgt->ids.port_name,
-                   sizeof(tgt->ids.port_name)))
+        if (wwn_to_u64((u8 *)&mad->fc_iu.response[2]) != tgt->ids.port_name)
                 return 1;
-        if (memcmp(&mad->fc_iu.response[4], &tgt->ids.node_name,
-                   sizeof(tgt->ids.node_name)))
+        if (wwn_to_u64((u8 *)&mad->fc_iu.response[4]) != tgt->ids.node_name)
                 return 1;
         if (be32_to_cpu(mad->fc_iu.response[6]) != tgt->scsi_id)
                 return 1;
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 6198559abbd8..dd66c11399a2 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -37,6 +37,7 @@
 #include <linux/kfifo.h>
 #include <linux/scatterlist.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 #include <net/tcp.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
@@ -954,6 +955,13 @@ static int iscsi_sw_tcp_slave_alloc(struct scsi_device *sdev)
 
 static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev)
 {
+        struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host);
+        struct iscsi_session *session = tcp_sw_host->session;
+        struct iscsi_conn *conn = session->leadconn;
+
+        if (conn->datadgst_en)
+                sdev->request_queue->backing_dev_info->capabilities
+                        |= BDI_CAP_STABLE_WRITES;
         blk_queue_bounce_limit(sdev->request_queue, BLK_BOUNCE_ANY);
         blk_queue_dma_alignment(sdev->request_queue, 0);
         return 0;
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index ba6503f37756..27fab8235ea5 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -2128,6 +2128,7 @@ enum MR_PD_TYPE {
 
 struct megasas_instance {
 
+        unsigned int *reply_map;
         __le32 *producer;
         dma_addr_t producer_h;
         __le32 *consumer;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index a71ee67df084..dde0798b8a91 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5165,6 +5165,26 @@ skip_alloc:
                 instance->use_seqnum_jbod_fp = false;
 }
 
+static void megasas_setup_reply_map(struct megasas_instance *instance)
+{
+        const struct cpumask *mask;
+        unsigned int queue, cpu;
+
+        for (queue = 0; queue < instance->msix_vectors; queue++) {
+                mask = pci_irq_get_affinity(instance->pdev, queue);
+                if (!mask)
+                        goto fallback;
+
+                for_each_cpu(cpu, mask)
+                        instance->reply_map[cpu] = queue;
+        }
+        return;
+
+fallback:
+        for_each_possible_cpu(cpu)
+                instance->reply_map[cpu] = cpu % instance->msix_vectors;
+}
+
 /**
  * megasas_init_fw -    Initializes the FW
  * @instance:           Adapter soft state
@@ -5343,6 +5363,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
                         goto fail_setup_irqs;
         }
 
+        megasas_setup_reply_map(instance);
+
         dev_info(&instance->pdev->dev,
                 "firmware supports msix\t: (%d)", fw_msix_count);
         dev_info(&instance->pdev->dev,
@@ -6123,20 +6145,29 @@ static inline int megasas_alloc_mfi_ctrl_mem(struct megasas_instance *instance)
  */
 static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
 {
+        instance->reply_map = kzalloc(sizeof(unsigned int) * nr_cpu_ids,
+                                      GFP_KERNEL);
+        if (!instance->reply_map)
+                return -ENOMEM;
+
         switch (instance->adapter_type) {
         case MFI_SERIES:
                 if (megasas_alloc_mfi_ctrl_mem(instance))
-                        return -ENOMEM;
+                        goto fail;
                 break;
         case VENTURA_SERIES:
         case THUNDERBOLT_SERIES:
         case INVADER_SERIES:
                 if (megasas_alloc_fusion_context(instance))
-                        return -ENOMEM;
+                        goto fail;
                 break;
         }
 
         return 0;
+ fail:
+        kfree(instance->reply_map);
+        instance->reply_map = NULL;
+        return -ENOMEM;
 }
 
 /*
@@ -6148,6 +6179,7 @@ static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
  */
 static inline void megasas_free_ctrl_mem(struct megasas_instance *instance)
 {
+        kfree(instance->reply_map);
         if (instance->adapter_type == MFI_SERIES) {
                 if (instance->producer)
                         pci_free_consistent(instance->pdev, sizeof(u32),
@@ -6540,7 +6572,6 @@ fail_io_attach:
                 pci_free_irq_vectors(instance->pdev);
 fail_init_mfi:
         scsi_host_put(host);
-
 fail_alloc_instance:
         pci_disable_device(pdev);
 
@@ -6746,6 +6777,8 @@ megasas_resume(struct pci_dev *pdev)
         if (rval < 0)
                 goto fail_reenable_msix;
 
+        megasas_setup_reply_map(instance);
+
         if (instance->adapter_type != MFI_SERIES) {
                 megasas_reset_reply_desc(instance);
                 if (megasas_ioc_init_fusion(instance)) {
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index dc8e850fbfd2..5ec3b74e8aed 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2641,11 +2641,8 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
                         fp_possible = (io_info.fpOkForIo > 0) ? true : false;
         }
 
-        /* Use raw_smp_processor_id() for now until cmd->request->cpu is CPU
-           id by default, not CPU group id, otherwise all MSI-X queues won't
-           be utilized */
-        cmd->request_desc->SCSIIO.MSIxIndex = instance->msix_vectors ?
-                raw_smp_processor_id() % instance->msix_vectors : 0;
+        cmd->request_desc->SCSIIO.MSIxIndex =
+                instance->reply_map[raw_smp_processor_id()];
 
         praid_context = &io_request->RaidContext;
 
@@ -2971,10 +2968,9 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
         }
 
         cmd->request_desc->SCSIIO.DevHandle = io_request->DevHandle;
-        cmd->request_desc->SCSIIO.MSIxIndex =
-                instance->msix_vectors ?
-                (raw_smp_processor_id() % instance->msix_vectors) : 0;
 
+        cmd->request_desc->SCSIIO.MSIxIndex =
+                instance->reply_map[raw_smp_processor_id()];
 
         if (!fp_possible) {
                 /* system pd firmware path */
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3541caf3fceb..1fa84d6a0f8b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2484,6 +2484,8 @@ sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer)
                                 sector_size = old_sector_size;
                                 goto got_data;
                         }
+                        /* Remember that READ CAPACITY(16) succeeded */
+                        sdp->try_rc_10_first = 0;
                 }
         }
 
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 7c28e8d4955a..45d04631888a 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -91,9 +91,6 @@ struct virtio_scsi_vq {
 struct virtio_scsi_target_state {
         seqcount_t tgt_seq;
 
-        /* Count of outstanding requests. */
-        atomic_t reqs;
-
         /* Currently active virtqueue for requests sent to this target. */
         struct virtio_scsi_vq *req_vq;
 };
@@ -152,8 +149,6 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
         struct virtio_scsi_cmd *cmd = buf;
         struct scsi_cmnd *sc = cmd->sc;
         struct virtio_scsi_cmd_resp *resp = &cmd->resp.cmd;
-        struct virtio_scsi_target_state *tgt =
-                                scsi_target(sc->device)->hostdata;
 
         dev_dbg(&sc->device->sdev_gendev,
                 "cmd %p response %u status %#02x sense_len %u\n",
@@ -210,8 +205,6 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
         }
 
         sc->scsi_done(sc);
-
-        atomic_dec(&tgt->reqs);
 }
 
 static void virtscsi_vq_done(struct virtio_scsi *vscsi,
@@ -529,11 +522,20 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 }
 #endif
 
-static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
-                                 struct virtio_scsi_vq *req_vq,
+static struct virtio_scsi_vq *virtscsi_pick_vq_mq(struct virtio_scsi *vscsi,
+                                                  struct scsi_cmnd *sc)
+{
+        u32 tag = blk_mq_unique_tag(sc->request);
+        u16 hwq = blk_mq_unique_tag_to_hwq(tag);
+
+        return &vscsi->req_vqs[hwq];
+}
+
+static int virtscsi_queuecommand(struct Scsi_Host *shost,
                                  struct scsi_cmnd *sc)
 {
-        struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
+        struct virtio_scsi *vscsi = shost_priv(shost);
+        struct virtio_scsi_vq *req_vq = virtscsi_pick_vq_mq(vscsi, sc);
         struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
         unsigned long flags;
         int req_size;
@@ -576,79 +578,6 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
         return 0;
 }
 
-static int virtscsi_queuecommand_single(struct Scsi_Host *sh,
-                                        struct scsi_cmnd *sc)
-{
-        struct virtio_scsi *vscsi = shost_priv(sh);
-        struct virtio_scsi_target_state *tgt =
-                                scsi_target(sc->device)->hostdata;
-
-        atomic_inc(&tgt->reqs);
-        return virtscsi_queuecommand(vscsi, &vscsi->req_vqs[0], sc);
-}
-
-static struct virtio_scsi_vq *virtscsi_pick_vq_mq(struct virtio_scsi *vscsi,
-                                                  struct scsi_cmnd *sc)
-{
-        u32 tag = blk_mq_unique_tag(sc->request);
-        u16 hwq = blk_mq_unique_tag_to_hwq(tag);
-
-        return &vscsi->req_vqs[hwq];
-}
-
-static struct virtio_scsi_vq *virtscsi_pick_vq(struct virtio_scsi *vscsi,
-                                               struct virtio_scsi_target_state *tgt)
-{
-        struct virtio_scsi_vq *vq;
-        unsigned long flags;
-        u32 queue_num;
-
-        local_irq_save(flags);
-        if (atomic_inc_return(&tgt->reqs) > 1) {
-                unsigned long seq;
-
-                do {
-                        seq = read_seqcount_begin(&tgt->tgt_seq);
-                        vq = tgt->req_vq;
-                } while (read_seqcount_retry(&tgt->tgt_seq, seq));
-        } else {
-                /* no writes can be concurrent because of atomic_t */
-                write_seqcount_begin(&tgt->tgt_seq);
-
-                /* keep previous req_vq if a reader just arrived */
-                if (unlikely(atomic_read(&tgt->reqs) > 1)) {
-                        vq = tgt->req_vq;
-                        goto unlock;
-                }
-
-                queue_num = smp_processor_id();
-                while (unlikely(queue_num >= vscsi->num_queues))
-                        queue_num -= vscsi->num_queues;
-                tgt->req_vq = vq = &vscsi->req_vqs[queue_num];
- unlock:
-                write_seqcount_end(&tgt->tgt_seq);
-        }
-        local_irq_restore(flags);
-
-        return vq;
-}
-
-static int virtscsi_queuecommand_multi(struct Scsi_Host *sh,
-                                       struct scsi_cmnd *sc)
-{
-        struct virtio_scsi *vscsi = shost_priv(sh);
-        struct virtio_scsi_target_state *tgt =
-                                scsi_target(sc->device)->hostdata;
-        struct virtio_scsi_vq *req_vq;
-
-        if (shost_use_blk_mq(sh))
-                req_vq = virtscsi_pick_vq_mq(vscsi, sc);
-        else
-                req_vq = virtscsi_pick_vq(vscsi, tgt);
-
-        return virtscsi_queuecommand(vscsi, req_vq, sc);
-}
-
 static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 {
         DECLARE_COMPLETION_ONSTACK(comp);
@@ -775,7 +704,6 @@ static int virtscsi_target_alloc(struct scsi_target *starget)
                 return -ENOMEM;
 
         seqcount_init(&tgt->tgt_seq);
-        atomic_set(&tgt->reqs, 0);
         tgt->req_vq = &vscsi->req_vqs[0];
 
         starget->hostdata = tgt;
@@ -805,33 +733,13 @@ static enum blk_eh_timer_return virtscsi_eh_timed_out(struct scsi_cmnd *scmnd)
         return BLK_EH_RESET_TIMER;
 }
 
-static struct scsi_host_template virtscsi_host_template_single = {
-        .module = THIS_MODULE,
-        .name = "Virtio SCSI HBA",
-        .proc_name = "virtio_scsi",
-        .this_id = -1,
-        .cmd_size = sizeof(struct virtio_scsi_cmd),
-        .queuecommand = virtscsi_queuecommand_single,
-        .change_queue_depth = virtscsi_change_queue_depth,
-        .eh_abort_handler = virtscsi_abort,
-        .eh_device_reset_handler = virtscsi_device_reset,
-        .eh_timed_out = virtscsi_eh_timed_out,
-        .slave_alloc = virtscsi_device_alloc,
-
-        .dma_boundary = UINT_MAX,
-        .use_clustering = ENABLE_CLUSTERING,
-        .target_alloc = virtscsi_target_alloc,
-        .target_destroy = virtscsi_target_destroy,
-        .track_queue_depth = 1,
-};
-
-static struct scsi_host_template virtscsi_host_template_multi = {
+static struct scsi_host_template virtscsi_host_template = {
         .module = THIS_MODULE,
         .name = "Virtio SCSI HBA",
         .proc_name = "virtio_scsi",
         .this_id = -1,
         .cmd_size = sizeof(struct virtio_scsi_cmd),
-        .queuecommand = virtscsi_queuecommand_multi,
+        .queuecommand = virtscsi_queuecommand,
         .change_queue_depth = virtscsi_change_queue_depth,
         .eh_abort_handler = virtscsi_abort,
         .eh_device_reset_handler = virtscsi_device_reset,
@@ -844,6 +752,7 @@ static struct scsi_host_template virtscsi_host_template_multi = {
         .target_destroy = virtscsi_target_destroy,
         .map_queues = virtscsi_map_queues,
         .track_queue_depth = 1,
+        .force_blk_mq = 1,
 };
 
 #define virtscsi_config_get(vdev, fld) \
@@ -936,7 +845,6 @@ static int virtscsi_probe(struct virtio_device *vdev)
         u32 sg_elems, num_targets;
         u32 cmd_per_lun;
         u32 num_queues;
-        struct scsi_host_template *hostt;
 
         if (!vdev->config->get) {
                 dev_err(&vdev->dev, "%s failure: config access disabled\n",
@@ -949,12 +857,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
         num_targets = virtscsi_config_get(vdev, max_target) + 1;
 
-        if (num_queues == 1)
-                hostt = &virtscsi_host_template_single;
-        else
-                hostt = &virtscsi_host_template_multi;
-
-        shost = scsi_host_alloc(hostt,
+        shost = scsi_host_alloc(&virtscsi_host_template,
                 sizeof(*vscsi) + sizeof(vscsi->req_vqs[0]) * num_queues);
         if (!shost)
                 return -ENOMEM;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index a8b7bf879ced..9c1e4bad6581 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -452,6 +452,9 @@ struct scsi_host_template {
         /* True if the controller does not support WRITE SAME */
         unsigned no_write_same:1;
 
+        /* True if the low-level driver supports blk-mq only */
+        unsigned force_blk_mq:1;
+
         /*
          * Countdown for host blocking with no commands outstanding.
          */