Merge tag 'riscv-for-linus-6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for cbo.zero in userspace

 - Support for CBOs on ACPI-based systems

 - A handful of improvements for the T-Head cache flushing ops

 - Support for software shadow call stacks

 - Various cleanups and fixes

* tag 'riscv-for-linus-6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (31 commits)
  RISC-V: hwprobe: Fix vDSO SIGSEGV
  riscv: configs: defconfig: Enable configs required for RZ/Five SoC
  riscv: errata: prefix T-Head mnemonics with th.
  riscv: put interrupt entries into .irqentry.text
  riscv: mm: Update the comment of CONFIG_PAGE_OFFSET
  riscv: Using TOOLCHAIN_HAS_ZIHINTPAUSE marco replace zihintpause
  riscv/mm: Fix the comment for swap pte format
  RISC-V: clarify the QEMU workaround in ISA parser
  riscv: correct pt_level name via pgtable_l5/4_enabled
  RISC-V: Provide pgtable_l5_enabled on rv32
  clocksource: timer-riscv: Increase rating of clock_event_device for Sstc
  clocksource: timer-riscv: Don't enable/disable timer interrupt
  lkdtm: Fix CFI_BACKWARD on RISC-V
  riscv: Use separate IRQ shadow call stacks
  riscv: Implement Shadow Call Stack
  riscv: Move global pointer loading to a macro
  riscv: Deduplicate IRQ stack switching
  riscv: VMAP_STACK overflow detection thread-safe
  RISC-V: cacheflush: Initialize CBO variables on ACPI systems
  RISC-V: ACPI: RHCT: Add function to get CBO block sizes
  ...

44 files changed, 918 insertions, 298 deletions

diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index a52996b22f75..7b2384de471f 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -77,6 +77,9 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_EXT_ZBS`: The Zbs extension is supported, as defined
        in version 1.0 of the Bit-Manipulation ISA extensions.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZICBOZ`: The Zicboz extension is supported, as
+       ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
@@ -96,3 +99,6 @@ The following keys are defined:
 
   * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNSUPPORTED`: Misaligned accesses are
     not supported at all and will generate a misaligned address fault.
+
+* :c:macro:`RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE`: An unsigned int which
+  represents the size of the Zicboz block in bytes.
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index eaa15a20e6ae..18b03ad0e6b9 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -39,6 +39,7 @@ config RISCV
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAS_VDSO_DATA
+	select ARCH_KEEP_MEMBLOCK if ACPI
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK
@@ -48,6 +49,7 @@ config RISCV
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_SUPPORTS_PER_VMA_LOCK if MMU
+	select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USES_CFI_TRAPS if CFI_CLANG
@@ -174,6 +176,11 @@ config GCC_SUPPORTS_DYNAMIC_FTRACE
 	def_bool CC_IS_GCC
 	depends on $(cc-option,-fpatchable-function-entry=8)
 
+config HAVE_SHADOW_CALL_STACK
+	def_bool $(cc-option,-fsanitize=shadow-call-stack)
+	# https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769
+	depends on $(ld-option,--no-relax-gp)
+
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
 	default 8
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 4d06f3402674..a74be78678eb 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -54,6 +54,10 @@ endif
 endif
 endif
 
+ifeq ($(CONFIG_SHADOW_CALL_STACK),y)
+	KBUILD_LDFLAGS += --no-relax-gp
+endif
+
 # ISA string setting
 riscv-march-$(CONFIG_ARCH_RV32I)	:= rv32ima
 riscv-march-$(CONFIG_ARCH_RV64I)	:= rv64ima
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 1edf3cd886c5..938fa07ddf77 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -37,6 +37,13 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PM=y
 CONFIG_CPU_IDLE=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_STAT=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=m
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
+CONFIG_CPUFREQ_DT=y
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=m
 CONFIG_ACPI=y
@@ -95,6 +102,7 @@ CONFIG_NETLINK_DIAG=y
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_NET_9P=y
 CONFIG_NET_9P_VIRTIO=y
+CONFIG_CAN=m
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_HOST_GENERIC=y
@@ -102,6 +110,11 @@ CONFIG_PCIE_XILINX=y
 CONFIG_PCIE_FU740=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_MTD=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_ADV_OPTIONS=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
 CONFIG_BLK_DEV_NVME=m
@@ -124,8 +137,11 @@ CONFIG_VIRTIO_NET=y
 CONFIG_MACB=y
 CONFIG_E1000E=y
 CONFIG_R8169=y
+CONFIG_RAVB=y
 CONFIG_STMMAC_ETH=m
+CONFIG_MICREL_PHY=y
 CONFIG_MICROSEMI_PHY=y
+CONFIG_CAN_RCAR_CANFD=m
 CONFIG_INPUT_MOUSEDEV=y
 CONFIG_KEYBOARD_SUN4I_LRADC=m
 CONFIG_SERIAL_8250=y
@@ -136,16 +152,24 @@ CONFIG_SERIAL_SH_SCI=y
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_I2C_CHARDEV=m
 CONFIG_I2C_MV64XXX=m
+CONFIG_I2C_RIIC=y
 CONFIG_SPI=y
+CONFIG_SPI_RSPI=m
 CONFIG_SPI_SIFIVE=y
 CONFIG_SPI_SUN6I=y
 # CONFIG_PTP_1588_CLOCK is not set
 CONFIG_GPIO_SIFIVE=y
+CONFIG_CPU_THERMAL=y
+CONFIG_DEVFREQ_THERMAL=y
+CONFIG_RZG2L_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
+CONFIG_RENESAS_RZG2LWDT=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_GPIO=y
 CONFIG_DRM=m
 CONFIG_DRM_RADEON=m
 CONFIG_DRM_NOUVEAU=m
@@ -153,39 +177,67 @@ CONFIG_DRM_SUN4I=m
 CONFIG_DRM_VIRTIO_GPU=m
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SOC=y
+CONFIG_SND_SOC_RZ=m
+CONFIG_SND_SOC_WM8978=m
+CONFIG_SND_SIMPLE_CARD=m
 CONFIG_USB=y
+CONFIG_USB_OTG=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_PLATFORM=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_RENESAS_USBHS=m
 CONFIG_USB_STORAGE=y
 CONFIG_USB_UAS=y
 CONFIG_USB_MUSB_HDRC=m
 CONFIG_USB_MUSB_SUNXI=m
 CONFIG_NOP_USB_XCEIV=m
+CONFIG_USB_GADGET=y
+CONFIG_USB_RENESAS_USBHS_UDC=m
+CONFIG_USB_CONFIGFS=m
+CONFIG_USB_CONFIGFS_SERIAL=y
+CONFIG_USB_CONFIGFS_ACM=y
+CONFIG_USB_CONFIGFS_OBEX=y
+CONFIG_USB_CONFIGFS_NCM=y
+CONFIG_USB_CONFIGFS_ECM=y
+CONFIG_USB_CONFIGFS_ECM_SUBSET=y
+CONFIG_USB_CONFIGFS_RNDIS=y
+CONFIG_USB_CONFIGFS_EEM=y
+CONFIG_USB_CONFIGFS_MASS_STORAGE=y
+CONFIG_USB_CONFIGFS_F_FS=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_CADENCE=y
 CONFIG_MMC_SPI=y
+CONFIG_MMC_SDHI=y
 CONFIG_MMC_SUNXI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SUN6I=y
 CONFIG_DMADEVICES=y
 CONFIG_DMA_SUN6I=m
+CONFIG_RZ_DMAC=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VIRTIO_MMIO=y
+CONFIG_RENESAS_OSTM=y
 CONFIG_SUN8I_DE2_CCU=m
 CONFIG_SUN50I_IOMMU=y
 CONFIG_RPMSG_CHAR=y
 CONFIG_RPMSG_CTRL=y
 CONFIG_RPMSG_VIRTIO=y
 CONFIG_ARCH_R9A07G043=y
+CONFIG_IIO=y
+CONFIG_RZG2L_ADC=m
+CONFIG_RESET_RZG2L_USBPHY_CTRL=y
 CONFIG_PHY_SUN4I_USB=m
+CONFIG_PHY_RCAR_GEN3_USB2=y
 CONFIG_LIBNVDIMM=y
 CONFIG_NVMEM_SUNXI_SID=y
 CONFIG_EXT4_FS=y
diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h
index d5604d2073bc..7dad0cf9d701 100644
--- a/arch/riscv/include/asm/acpi.h
+++ b/arch/riscv/include/asm/acpi.h
@@ -66,6 +66,8 @@ int acpi_get_riscv_isa(struct acpi_table_header *table,
 		       unsigned int cpu, const char **isa);
 
 static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
+			     u32 *cboz_size, u32 *cbop_size);
 #else
 static inline void acpi_init_rintc_map(void) { }
 static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu)
@@ -79,6 +81,10 @@ static inline int acpi_get_riscv_isa(struct acpi_table_header *table,
 	return -EINVAL;
 }
 
+static inline void acpi_get_cbo_block_size(struct acpi_table_header *table,
+					   u32 *cbom_size, u32 *cboz_size,
+					   u32 *cbop_size) { }
+
 #endif /* CONFIG_ACPI */
 
 #endif /*_ASM_ACPI_H*/
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 61ba8ed43d8f..36b955c762ba 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -25,7 +25,6 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
-asmlinkage unsigned long get_overflow_stack(void);
 asmlinkage void handle_bad_stack(struct pt_regs *regs);
 asmlinkage void do_page_fault(struct pt_regs *regs);
 asmlinkage void do_irq(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 114bbadaef41..b0487b39e674 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -82,6 +82,47 @@
 	.endr
 .endm
 
+#ifdef CONFIG_SMP
+#ifdef CONFIG_32BIT
+#define PER_CPU_OFFSET_SHIFT 2
+#else
+#define PER_CPU_OFFSET_SHIFT 3
+#endif
+
+.macro asm_per_cpu dst sym tmp
+	REG_L \tmp, TASK_TI_CPU_NUM(tp)
+	slli  \tmp, \tmp, PER_CPU_OFFSET_SHIFT
+	la    \dst, __per_cpu_offset
+	add   \dst, \dst, \tmp
+	REG_L \tmp, 0(\dst)
+	la    \dst, \sym
+	add   \dst, \dst, \tmp
+.endm
+#else /* CONFIG_SMP */
+.macro asm_per_cpu dst sym tmp
+	la    \dst, \sym
+.endm
+#endif /* CONFIG_SMP */
+
+.macro load_per_cpu dst ptr tmp
+	asm_per_cpu \dst \ptr \tmp
+	REG_L \dst, 0(\dst)
+.endm
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+/* gp is used as the shadow call stack pointer instead */
+.macro load_global_pointer
+.endm
+#else
+/* load __global_pointer to gp */
+.macro load_global_pointer
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+.endm
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
 	/* save all GPs except x1 ~ x5 */
 	.macro save_from_x6_to_x31
 	REG_S x6,  PT_T1(sp)
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index d0345bd659c9..13b7d35648a9 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -31,5 +31,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
 void check_unaligned_access(int cpu);
+void riscv_user_isa_enable(void);
 
 #endif
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index b55b434f0059..0ac18a4135be 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -95,25 +95,25 @@ asm volatile(ALTERNATIVE(						\
 #endif
 
 /*
- * dcache.ipa rs1 (invalidate, physical address)
+ * th.dcache.ipa rs1 (invalidate, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01010      rs1       000      00000  0001011
- * dache.iva rs1 (invalida, virtual address)
+ * th.dache.iva rs1 (invalida, virtual address)
  *   0000001    00110      rs1       000      00000  0001011
  *
- * dcache.cpa rs1 (clean, physical address)
+ * th.dcache.cpa rs1 (clean, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01001      rs1       000      00000  0001011
- * dcache.cva rs1 (clean, virtual address)
+ * th.dcache.cva rs1 (clean, virtual address)
  *   0000001    00101      rs1       000      00000  0001011
  *
- * dcache.cipa rs1 (clean then invalidate, physical address)
+ * th.dcache.cipa rs1 (clean then invalidate, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01011      rs1       000      00000  0001011
- * dcache.civa rs1 (... virtual address)
+ * th.dcache.civa rs1 (... virtual address)
  *   0000001    00111      rs1       000      00000  0001011
  *
- * sync.s (make sure all cache operations finished)
+ * th.sync.s (make sure all cache operations finished)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000000    11001     00000      000      00000  0001011
  */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 6fc51c1b34cf..fe6656af967a 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -72,6 +72,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/jump_label.h>
+#include <asm/cpufeature.h>
 
 unsigned long riscv_get_elf_hwcap(void);
 
@@ -139,6 +140,21 @@ l_yes:
 	return true;
 }
 
+static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 78936f4ff513..5c48f48e79a6 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,6 +8,11 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 5
+#define RISCV_HWPROBE_MAX_KEY 6
+
+static inline bool riscv_hwprobe_key_is_valid(__s64 key)
+{
+	return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY;
+}
 
 #endif
diff --git a/arch/riscv/include/asm/irq_stack.h b/arch/riscv/include/asm/irq_stack.h
index e4042d297580..6441ded3b0cf 100644
--- a/arch/riscv/include/asm/irq_stack.h
+++ b/arch/riscv/include/asm/irq_stack.h
@@ -12,6 +12,9 @@
 
 DECLARE_PER_CPU(ulong *, irq_stack_ptr);
 
+asmlinkage void call_on_irq_stack(struct pt_regs *regs,
+				  void (*func)(struct pt_regs *));
+
 #ifdef CONFIG_VMAP_STACK
 /*
  * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 5488ecc337b6..57e887bfa34c 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -33,8 +33,8 @@
 #define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 #endif
 /*
- * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so
- * define the PAGE_OFFSET value for SV39.
+ * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so
+ * define the PAGE_OFFSET value for SV48 and SV39.
  */
 #define PAGE_OFFSET_L4		_AC(0xffffaf8000000000, UL)
 #define PAGE_OFFSET_L3		_AC(0xffffffd800000000, UL)
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
index 59ba1fbaf784..00f3369570a8 100644
--- a/arch/riscv/include/asm/pgtable-32.h
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -33,4 +33,7 @@
 					  _PAGE_WRITE | _PAGE_EXEC |	\
 					  _PAGE_USER | _PAGE_GLOBAL))
 
+static const __maybe_unused int pgtable_l4_enabled;
+static const __maybe_unused int pgtable_l5_enabled;
+
 #endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index b2ba3f79cfe9..c8e8867c42f6 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -811,7 +811,7 @@ extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
  *	bit            5:	_PAGE_PROT_NONE (zero)
  *	bit            6:	exclusive marker
  *	bits      7 to 11:	swap type
- *	bits 11 to XLEN-1:	swap offset
+ *	bits 12 to XLEN-1:	swap offset
  */
 #define __SWP_TYPE_SHIFT	7
 #define __SWP_TYPE_BITS		5
@@ -914,7 +914,6 @@ extern uintptr_t _dtb_early_pa;
 #define dtb_early_pa	_dtb_early_pa
 #endif /* CONFIG_XIP_KERNEL */
 extern u64 satp_mode;
-extern bool pgtable_l4_enabled;
 
 void paging_init(void);
 void misc_mem_init(void);
diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h
new file mode 100644
index 000000000000..0e45db78b24b
--- /dev/null
+++ b/arch/riscv/include/asm/scs.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+
+/* Load init_shadow_call_stack to gp. */
+.macro scs_load_init_stack
+	la	gp, init_shadow_call_stack
+	XIP_FIXUP_OFFSET gp
+.endm
+
+/* Load the per-CPU IRQ shadow call stack to gp. */
+.macro scs_load_irq_stack tmp
+	load_per_cpu gp, irq_shadow_call_stack_ptr, \tmp
+.endm
+
+/* Load task_scs_sp(current) to gp. */
+.macro scs_load_current
+	REG_L	gp, TASK_TI_SCS_SP(tp)
+.endm
+
+/* Load task_scs_sp(current) to gp, but only if tp has changed. */
+.macro scs_load_current_if_task_changed prev
+	beq	\prev, tp, _skip_scs
+	scs_load_current
+_skip_scs:
+.endm
+
+/* Save gp to task_scs_sp(current). */
+.macro scs_save_current
+	REG_S	gp, TASK_TI_SCS_SP(tp)
+.endm
+
+#else /* CONFIG_SHADOW_CALL_STACK */
+
+.macro scs_load_init_stack
+.endm
+.macro scs_load_irq_stack tmp
+.endm
+.macro scs_load_current
+.endm
+.macro scs_load_current_if_task_changed prev
+.endm
+.macro scs_save_current
+.endm
+
+#endif /* CONFIG_SHADOW_CALL_STACK */
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_SCS_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 1833beb00489..574779900bfb 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -34,9 +34,6 @@
 
 #ifndef __ASSEMBLY__
 
-extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
-extern unsigned long spin_shadow_stack;
-
 #include <asm/processor.h>
 #include <asm/csr.h>
 
@@ -60,8 +57,20 @@ struct thread_info {
 	long			user_sp;	/* User stack pointer */
 	int			cpu;
 	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
+#ifdef CONFIG_SHADOW_CALL_STACK
+	void			*scs_base;
+	void			*scs_sp;
+#endif
 };
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+#define INIT_SCS							\
+	.scs_base	= init_shadow_call_stack,			\
+	.scs_sp		= init_shadow_call_stack,
+#else
+#define INIT_SCS
+#endif
+
 /*
  * macros/functions for gaining access to the thread information structure
  *
@@ -71,6 +80,7 @@ struct thread_info {
 {						\
 	.flags		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	INIT_SCS				\
 }
 
 void arch_release_task_struct(struct task_struct *tsk);
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
index 14f5d27783b8..96b65a5396df 100644
--- a/arch/riscv/include/asm/vdso/processor.h
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -14,7 +14,7 @@ static inline void cpu_relax(void)
 	__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
 #endif
 
-#ifdef __riscv_zihintpause
+#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
 	/*
 	 * Reduce instruction retirement.
 	 * This assumes the PC changes.
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index d43e306ce2f9..b659ffcfcdb4 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -29,6 +29,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBA		(1 << 3)
 #define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
+#define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -36,6 +37,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_FAST		(3 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_UNSUPPORTED	(4 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_MASK		(7 << 0)
+#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 #endif
diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c
index 56cb2c986c48..e619edc8b0cc 100644
--- a/arch/riscv/kernel/acpi.c
+++ b/arch/riscv/kernel/acpi.c
@@ -14,9 +14,10 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/efi.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 #include <linux/pci.h>
-#include <linux/efi.h>
 
 int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
 int acpi_disabled = 1;
@@ -217,7 +218,89 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
 
 void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 {
-	return (void __iomem *)memremap(phys, size, MEMREMAP_WB);
+	efi_memory_desc_t *md, *region = NULL;
+	pgprot_t prot;
+
+	if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP)))
+		return NULL;
+
+	for_each_efi_memory_desc(md) {
+		u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+
+		if (phys < md->phys_addr || phys >= end)
+			continue;
+
+		if (phys + size > end) {
+			pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n");
+			return NULL;
+		}
+		region = md;
+		break;
+	}
+
+	/*
+	 * It is fine for AML to remap regions that are not represented in the
+	 * EFI memory map at all, as it only describes normal memory, and MMIO
+	 * regions that require a virtual mapping to make them accessible to
+	 * the EFI runtime services.
+	 */
+	prot = PAGE_KERNEL_IO;
+	if (region) {
+		switch (region->type) {
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+		case EFI_PERSISTENT_MEMORY:
+			if (memblock_is_map_memory(phys) ||
+			    !memblock_is_region_memory(phys, size)) {
+				pr_warn(FW_BUG "requested region covers kernel memory\n");
+				return NULL;
+			}
+
+			/*
+			 * Mapping kernel memory is permitted if the region in
+			 * question is covered by a single memblock with the
+			 * NOMAP attribute set: this enables the use of ACPI
+			 * table overrides passed via initramfs.
+			 * This particular use case only requires read access.
+			 */
+			fallthrough;
+
+		case EFI_RUNTIME_SERVICES_CODE:
+			/*
+			 * This would be unusual, but not problematic per se,
+			 * as long as we take care not to create a writable
+			 * mapping for executable code.
+			 */
+			prot = PAGE_KERNEL_RO;
+			break;
+
+		case EFI_ACPI_RECLAIM_MEMORY:
+			/*
+			 * ACPI reclaim memory is used to pass firmware tables
+			 * and other data that is intended for consumption by
+			 * the OS only, which may decide it wants to reclaim
+			 * that memory and use it for something else. We never
+			 * do that, but we usually add it to the linear map
+			 * anyway, in which case we should use the existing
+			 * mapping.
+			 */
+			if (memblock_is_map_memory(phys))
+				return (void __iomem *)__va(phys);
+			fallthrough;
+
+		default:
+			if (region->attribute & EFI_MEMORY_WB)
+				prot = PAGE_KERNEL;
+			else if ((region->attribute & EFI_MEMORY_WC) ||
+				 (region->attribute & EFI_MEMORY_WT))
+				prot = pgprot_writecombine(PAGE_KERNEL);
+		}
+	}
+
+	return ioremap_prot(phys, size, pgprot_val(prot));
 }
 
 #ifdef CONFIG_PCI
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index d6a75aac1d27..a03129f40c46 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -14,6 +14,7 @@
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
 #include <asm/cpu_ops_sbi.h>
+#include <asm/stacktrace.h>
 #include <asm/suspend.h>
 
 void asm_offsets(void);
@@ -38,7 +39,11 @@ void asm_offsets(void)
 	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
 	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+#ifdef CONFIG_SHADOW_CALL_STACK
+	OFFSET(TASK_TI_SCS_SP, task_struct, thread_info.scs_sp);
+#endif
 
+	OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu);
 	OFFSET(TASK_THREAD_F0,  task_struct, thread.fstate.f[0]);
 	OFFSET(TASK_THREAD_F1,  task_struct, thread.fstate.f[1]);
 	OFFSET(TASK_THREAD_F2,  task_struct, thread.fstate.f[2]);
@@ -479,4 +484,8 @@ void asm_offsets(void)
 	OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr);
 	OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr);
 	OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
+
+	DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN));
+	OFFSET(STACKFRAME_FP, stackframe, fp);
+	OFFSET(STACKFRAME_RA, stackframe, ra);
 }
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index e3803822ab5a..7aeba01dcfd4 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -93,10 +93,10 @@ static bool riscv_isa_extension_check(int id)
 		return true;
 	case RISCV_ISA_EXT_ZICBOZ:
 		if (!riscv_cboz_block_size) {
-			pr_err("Zicboz detected in ISA string, but no cboz-block-size found\n");
+			pr_err("Zicboz detected in ISA string, disabling as no cboz-block-size found\n");
 			return false;
 		} else if (!is_power_of_2(riscv_cboz_block_size)) {
-			pr_err("cboz-block-size present, but is not a power-of-2\n");
+			pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n");
 			return false;
 		}
 		return true;
@@ -206,10 +206,11 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 		switch (*ext) {
 		case 's':
 			/*
-			 * Workaround for invalid single-letter 's' & 'u'(QEMU).
+			 * Workaround for invalid single-letter 's' & 'u' (QEMU).
 			 * No need to set the bit in riscv_isa as 's' & 'u' are
-			 * not valid ISA extensions. It works until multi-letter
-			 * extension starting with "Su" appears.
+			 * not valid ISA extensions. It works unless the first
+			 * multi-letter extension in the ISA string begins with
+			 * "Su" and is not prefixed with an underscore.
 			 */
 			if (ext[-1] != '_' && ext[1] == 'u') {
 				++isa;
@@ -655,6 +656,12 @@ static int check_unaligned_access_boot_cpu(void)
 
 arch_initcall(check_unaligned_access_boot_cpu);
 
+void riscv_user_isa_enable(void)
+{
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
+		csr_set(CSR_SENVCFG, ENVCFG_CBZE);
+}
+
 #ifdef CONFIG_RISCV_ALTERNATIVE
 /*
  * Alternative patch sites consider 48 bits when determining when to patch
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 143a2bb3e697..9f92c067f7e1 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -9,10 +9,15 @@
 
 #include <asm/asm.h>
 #include <asm/csr.h>
+#include <asm/scs.h>
 #include <asm/unistd.h>
+#include <asm/page.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 #include <asm/errata_list.h>
+#include <linux/sizes.h>
+
+	.section .irqentry.text, "ax"
 
 SYM_CODE_START(handle_exception)
 	/*
@@ -73,10 +78,11 @@ _save_context:
 	csrw CSR_SCRATCH, x0
 
 	/* Load the global pointer */
-.option push
-.option norelax
-	la gp, __global_pointer$
-.option pop
+	load_global_pointer
+
+	/* Load the kernel shadow call stack pointer if coming from userspace */
+	scs_load_current_if_task_changed s5
+
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -123,6 +129,9 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	addi s0, sp, PT_SIZE_ON_STACK
 	REG_S s0, TASK_TI_KERNEL_SP(tp)
 
+	/* Save the kernel shadow call stack pointer */
+	scs_save_current
+
 	/*
 	 * Save TP into the scratch register , so we can find the kernel data
 	 * structures again.
@@ -170,67 +179,15 @@ SYM_CODE_END(ret_from_exception)
 
 #ifdef CONFIG_VMAP_STACK
 SYM_CODE_START_LOCAL(handle_kernel_stack_overflow)
-	/*
-	 * Takes the psuedo-spinlock for the shadow stack, in case multiple
-	 * harts are concurrently overflowing their kernel stacks.  We could
-	 * store any value here, but since we're overflowing the kernel stack
-	 * already we only have SP to use as a scratch register.  So we just
-	 * swap in the address of the spinlock, as that's definately non-zero.
-	 *
-	 * Pairs with a store_release in handle_bad_stack().
-	 */
-1:	la sp, spin_shadow_stack
-	REG_AMOSWAP_AQ sp, sp, (sp)
-	bnez sp, 1b
-
-	la sp, shadow_stack
-	addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE
+	/* we reach here from kernel context, sscratch must be 0 */
+	csrrw x31, CSR_SCRATCH, x31
+	asm_per_cpu sp, overflow_stack, x31
+	li x31, OVERFLOW_STACK_SIZE
+	add sp, sp, x31
+	/* zero out x31 again and restore x31 */
+	xor x31, x31, x31
+	csrrw x31, CSR_SCRATCH, x31
 
-	//save caller register to shadow stack
-	addi sp, sp, -(PT_SIZE_ON_STACK)
-	REG_S x1,  PT_RA(sp)
-	REG_S x5,  PT_T0(sp)
-	REG_S x6,  PT_T1(sp)
-	REG_S x7,  PT_T2(sp)
-	REG_S x10, PT_A0(sp)
-	REG_S x11, PT_A1(sp)
-	REG_S x12, PT_A2(sp)
-	REG_S x13, PT_A3(sp)
-	REG_S x14, PT_A4(sp)
-	REG_S x15, PT_A5(sp)
-	REG_S x16, PT_A6(sp)
-	REG_S x17, PT_A7(sp)
-	REG_S x28, PT_T3(sp)
-	REG_S x29, PT_T4(sp)
-	REG_S x30, PT_T5(sp)
-	REG_S x31, PT_T6(sp)
-
-	la ra, restore_caller_reg
-	tail get_overflow_stack
-
-restore_caller_reg:
-	//save per-cpu overflow stack
-	REG_S a0, -8(sp)
-	//restore caller register from shadow_stack
-	REG_L x1,  PT_RA(sp)
-	REG_L x5,  PT_T0(sp)
-	REG_L x6,  PT_T1(sp)
-	REG_L x7,  PT_T2(sp)
-	REG_L x10, PT_A0(sp)
-	REG_L x11, PT_A1(sp)
-	REG_L x12, PT_A2(sp)
-	REG_L x13, PT_A3(sp)
-	REG_L x14, PT_A4(sp)
-	REG_L x15, PT_A5(sp)
-	REG_L x16, PT_A6(sp)
-	REG_L x17, PT_A7(sp)
-	REG_L x28, PT_T3(sp)
-	REG_L x29, PT_T4(sp)
-	REG_L x30, PT_T5(sp)
-	REG_L x31, PT_T6(sp)
-
-	//load per-cpu overflow stack
-	REG_L sp, -8(sp)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
 
 	//save context to overflow stack
@@ -268,6 +225,43 @@ SYM_CODE_START(ret_from_fork)
 	tail syscall_exit_to_user_mode
 SYM_CODE_END(ret_from_fork)
 
+#ifdef CONFIG_IRQ_STACKS
+/*
+ * void call_on_irq_stack(struct pt_regs *regs,
+ * 		          void (*func)(struct pt_regs *));
+ *
+ * Calls func(regs) using the per-CPU IRQ stack.
+ */
+SYM_FUNC_START(call_on_irq_stack)
+	/* Create a frame record to save ra and s0 (fp) */
+	addi	sp, sp, -STACKFRAME_SIZE_ON_STACK
+	REG_S	ra, STACKFRAME_RA(sp)
+	REG_S	s0, STACKFRAME_FP(sp)
+	addi	s0, sp, STACKFRAME_SIZE_ON_STACK
+
+	/* Switch to the per-CPU shadow call stack */
+	scs_save_current
+	scs_load_irq_stack t0
+
+	/* Switch to the per-CPU IRQ stack and call the handler */
+	load_per_cpu t0, irq_stack_ptr, t1
+	li	t1, IRQ_STACK_SIZE
+	add	sp, t0, t1
+	jalr	a1
+
+	/* Switch back to the thread shadow call stack */
+	scs_load_current
+
+	/* Switch back to the thread stack and restore ra and s0 */
+	addi	sp, s0, -STACKFRAME_SIZE_ON_STACK
+	REG_L	ra, STACKFRAME_RA(sp)
+	REG_L	s0, STACKFRAME_FP(sp)
+	addi	sp, sp, STACKFRAME_SIZE_ON_STACK
+
+	ret
+SYM_FUNC_END(call_on_irq_stack)
+#endif /* CONFIG_IRQ_STACKS */
+
 /*
  * Integer register context switch
  * The callee-saved registers must be saved and restored.
@@ -297,6 +291,8 @@ SYM_FUNC_START(__switch_to)
 	REG_S s9,  TASK_THREAD_S9_RA(a3)
 	REG_S s10, TASK_THREAD_S10_RA(a3)
 	REG_S s11, TASK_THREAD_S11_RA(a3)
+	/* Save the kernel shadow call stack pointer */
+	scs_save_current
 	/* Restore context from next->thread */
 	REG_L ra,  TASK_THREAD_RA_RA(a4)
 	REG_L sp,  TASK_THREAD_SP_RA(a4)
@@ -314,6 +310,8 @@ SYM_FUNC_START(__switch_to)
 	REG_L s11, TASK_THREAD_S11_RA(a4)
 	/* The offset of thread_info in task_struct is zero. */
 	move tp, a1
+	/* Switch to the next shadow call stack */
+	scs_load_current
 	ret
 SYM_FUNC_END(__switch_to)
 
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 3710ea5d160f..18f97ec0f7ed 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -14,6 +14,7 @@
 #include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
+#include <asm/scs.h>
 #include <asm/xip_fixup.h>
 #include "efi-header.S"
 
@@ -110,10 +111,7 @@ relocate_enable_mmu:
 	csrw CSR_TVEC, a0
 
 	/* Reload the global pointer */
-.option push
-.option norelax
-	la gp, __global_pointer$
-.option pop
+	load_global_pointer
 
 	/*
 	 * Switch to kernel page tables.  A full fence is necessary in order to
@@ -134,10 +132,7 @@ secondary_start_sbi:
 	csrw CSR_IP, zero
 
 	/* Load the global pointer */
-	.option push
-	.option norelax
-		la gp, __global_pointer$
-	.option pop
+	load_global_pointer
 
 	/*
 	 * Disable FPU & VECTOR to detect illegal usage of
@@ -159,6 +154,7 @@ secondary_start_sbi:
 	XIP_FIXUP_OFFSET a3
 	add a3, a3, a1
 	REG_L sp, (a3)
+	scs_load_current
 
 .Lsecondary_start_common:
 
@@ -228,10 +224,7 @@ pmp_done:
 #endif /* CONFIG_RISCV_M_MODE */
 
 	/* Load the global pointer */
-.option push
-.option norelax
-	la gp, __global_pointer$
-.option pop
+	load_global_pointer
 
 	/*
 	 * Disable FPU & VECTOR to detect illegal usage of
@@ -298,6 +291,7 @@ clear_bss_done:
 	la sp, init_thread_union + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
 	addi sp, sp, -PT_SIZE_ON_STACK
+	scs_load_init_stack
 #ifdef CONFIG_BUILTIN_DTB
 	la a0, __dtb_start
 	XIP_FIXUP_OFFSET a0
@@ -316,6 +310,7 @@ clear_bss_done:
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
 	addi sp, sp, -PT_SIZE_ON_STACK
+	scs_load_current
 
 #ifdef CONFIG_KASAN
 	call kasan_early_init
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index 9cc0a7669271..9ceda02507ca 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -9,6 +9,7 @@
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
+#include <linux/scs.h>
 #include <linux/seq_file.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
@@ -34,6 +35,24 @@ EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode);
 #ifdef CONFIG_IRQ_STACKS
 #include <asm/irq_stack.h>
 
+DECLARE_PER_CPU(ulong *, irq_shadow_call_stack_ptr);
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+DEFINE_PER_CPU(ulong *, irq_shadow_call_stack_ptr);
+#endif
+
+static void init_irq_scs(void)
+{
+	int cpu;
+
+	if (!scs_is_enabled())
+		return;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(irq_shadow_call_stack_ptr, cpu) =
+			scs_alloc(cpu_to_node(cpu));
+}
+
 DEFINE_PER_CPU(ulong *, irq_stack_ptr);
 
 #ifdef CONFIG_VMAP_STACK
@@ -61,40 +80,22 @@ static void init_irq_stacks(void)
 #endif /* CONFIG_VMAP_STACK */
 
 #ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
+static void ___do_softirq(struct pt_regs *regs)
+{
+	__do_softirq();
+}
+
 void do_softirq_own_stack(void)
 {
-#ifdef CONFIG_IRQ_STACKS
-	if (on_thread_stack()) {
-		ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id())
-					+ IRQ_STACK_SIZE/sizeof(ulong);
-		__asm__ __volatile(
-		"addi	sp, sp, -"RISCV_SZPTR  "\n"
-		REG_S"  ra, (sp)		\n"
-		"addi	sp, sp, -"RISCV_SZPTR  "\n"
-		REG_S"  s0, (sp)		\n"
-		"addi	s0, sp, 2*"RISCV_SZPTR "\n"
-		"move	sp, %[sp]		\n"
-		"call	__do_softirq		\n"
-		"addi	sp, s0, -2*"RISCV_SZPTR"\n"
-		REG_L"  s0, (sp)		\n"
-		"addi	sp, sp, "RISCV_SZPTR   "\n"
-		REG_L"  ra, (sp)		\n"
-		"addi	sp, sp, "RISCV_SZPTR   "\n"
-		:
-		: [sp] "r" (sp)
-		: "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6",
-#ifndef CONFIG_FRAME_POINTER
-		  "s0",
-#endif
-		  "memory");
-	} else
-#endif
+	if (on_thread_stack())
+		call_on_irq_stack(NULL, ___do_softirq);
+	else
 		__do_softirq();
 }
 #endif /* CONFIG_SOFTIRQ_ON_OWN_STACK */
 
 #else
+static void init_irq_scs(void) {}
 static void init_irq_stacks(void) {}
 #endif /* CONFIG_IRQ_STACKS */
 
@@ -106,6 +107,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 
 void __init init_IRQ(void)
 {
+	init_irq_scs();
 	init_irq_stacks();
 	irqchip_init();
 	if (!handle_arch_irq)
diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S
index 059c5e216ae7..de0a4b35d01e 100644
--- a/arch/riscv/kernel/kexec_relocate.S
+++ b/arch/riscv/kernel/kexec_relocate.S
@@ -17,27 +17,17 @@ SYM_CODE_START(riscv_kexec_relocate)
 	 * s1: (const) Phys address to jump to after relocation
 	 * s2: (const) Phys address of the FDT image
 	 * s3: (const) The hartid of the current hart
-	 * s4: Pointer to the destination address for the relocation
-	 * s5: (const) Number of words per page
-	 * s6: (const) 1, used for subtraction
-	 * s7: (const) kernel_map.va_pa_offset, used when switching MMU off
-	 * s8: (const) Physical address of the main loop
-	 * s9: (debug) indirection page counter
-	 * s10: (debug) entry counter
-	 * s11: (debug) copied words counter
+	 * s4: (const) kernel_map.va_pa_offset, used when switching MMU off
+	 * s5: Pointer to the destination address for the relocation
+	 * s6: (const) Physical address of the main loop
 	 */
 	mv	s0, a0
 	mv	s1, a1
 	mv	s2, a2
 	mv	s3, a3
-	mv	s4, zero
-	li	s5, (PAGE_SIZE / RISCV_SZPTR)
-	li	s6, 1
-	mv	s7, a4
-	mv	s8, zero
-	mv	s9, zero
-	mv	s10, zero
-	mv	s11, zero
+	mv	s4, a4
+	mv	s5, zero
+	mv	s6, zero
 
 	/* Disable / cleanup interrupts */
 	csrw	CSR_SIE, zero
@@ -52,21 +42,27 @@ SYM_CODE_START(riscv_kexec_relocate)
 	 * the start of the loop below so that we jump there in
 	 * any case.
 	 */
-	la	s8, 1f
-	sub	s8, s8, s7
-	csrw	CSR_STVEC, s8
+	la	s6, 1f
+	sub	s6, s6, s4
+	csrw	CSR_STVEC, s6
+
+	/*
+	 * With C-extension, here we get 42 Bytes and the next
+	 * .align directive would pad zeros here up to 44 Bytes.
+	 * So manually put a nop here to avoid zeros padding.
+	*/
+	nop
 
 	/* Process entries in a loop */
 .align 2
 1:
-	addi	s10, s10, 1
 	REG_L	t0, 0(s0)		/* t0 = *image->entry */
 	addi	s0, s0, RISCV_SZPTR	/* image->entry++ */
 
 	/* IND_DESTINATION entry ? -> save destination address */
 	andi	t1, t0, 0x1
 	beqz	t1, 2f
-	andi	s4, t0, ~0x1
+	andi	s5, t0, ~0x1
 	j	1b
 
 2:
@@ -74,9 +70,8 @@ SYM_CODE_START(riscv_kexec_relocate)
 	andi	t1, t0, 0x2
 	beqz	t1, 2f
 	andi	s0, t0, ~0x2
-	addi	s9, s9, 1
 	csrw	CSR_SATP, zero
-	jalr	zero, s8, 0
+	jr	s6
 
 2:
 	/* IND_DONE entry ? -> jump to done label */
@@ -92,14 +87,13 @@ SYM_CODE_START(riscv_kexec_relocate)
 	andi	t1, t0, 0x8
 	beqz	t1, 1b		/* Unknown entry type, ignore it */
 	andi	t0, t0, ~0x8
-	mv	t3, s5		/* i = num words per page */
+	li	t3, (PAGE_SIZE / RISCV_SZPTR)	/* i = num words per page */
 3:	/* copy loop */
 	REG_L	t1, (t0)	/* t1 = *src_ptr */
-	REG_S	t1, (s4)	/* *dst_ptr = *src_ptr */
+	REG_S	t1, (s5)	/* *dst_ptr = *src_ptr */
 	addi	t0, t0, RISCV_SZPTR /* stc_ptr++ */
-	addi	s4, s4, RISCV_SZPTR /* dst_ptr++ */
-	sub	t3, t3, s6	/* i-- */
-	addi	s11, s11, 1	/* c++ */
+	addi	s5, s5, RISCV_SZPTR /* dst_ptr++ */
+	addi	t3, t3, -0x1	/* i-- */
 	beqz	t3, 1b		/* copy done ? */
 	j	3b
 
@@ -146,7 +140,7 @@ SYM_CODE_START(riscv_kexec_relocate)
 	 */
 	fence.i
 
-	jalr	zero, a2, 0
+	jr	a2
 
 SYM_CODE_END(riscv_kexec_relocate)
 riscv_kexec_relocate_end:
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 0624f44d43ec..535a837de55d 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -25,6 +25,7 @@
 #include <asm/acpi.h>
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
@@ -289,10 +290,13 @@ void __init setup_arch(char **cmdline_p)
 	riscv_fill_hwcap();
 	init_rt_signal_env();
 	apply_boot_alternatives();
+
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))
 		riscv_noncoherent_supported();
 	riscv_set_dma_cache_alignment();
+
+	riscv_user_isa_enable();
 }
 
 static int __init topology_init(void)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 1b8da4e40a4d..d1b0a6fc3adf 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -25,6 +25,8 @@
 #include <linux/of.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
+
+#include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/cpufeature.h>
 #include <asm/irq.h>
@@ -253,6 +255,8 @@ asmlinkage __visible void smp_callin(void)
 			elf_hwcap &= ~COMPAT_HWCAP_ISA_V;
 	}
 
+	riscv_user_isa_enable();
+
 	/*
 	 * Remote TLB flushes are ignored while the CPU is offline, so emit
 	 * a local TLB flush right now just in case.
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
index f7960c7c5f9e..d5cf8b575777 100644
--- a/arch/riscv/kernel/suspend_entry.S
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -61,10 +61,7 @@ END(__cpu_suspend_enter)
 
 SYM_TYPED_FUNC_START(__cpu_resume_enter)
 	/* Load the global pointer */
-	.option push
-	.option norelax
-		la gp, __global_pointer$
-	.option pop
+	load_global_pointer
 
 #ifdef CONFIG_MMU
 	/* Save A0 and A1 */
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index b651ec698a91..c712037dbe10 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -145,26 +145,38 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	for_each_cpu(cpu, cpus) {
 		struct riscv_isainfo *isainfo = &hart_isa[cpu];
 
-		if (riscv_isa_extension_available(isainfo->isa, ZBA))
-			pair->value |= RISCV_HWPROBE_EXT_ZBA;
-		else
-			missing |= RISCV_HWPROBE_EXT_ZBA;
-
-		if (riscv_isa_extension_available(isainfo->isa, ZBB))
-			pair->value |= RISCV_HWPROBE_EXT_ZBB;
-		else
-			missing |= RISCV_HWPROBE_EXT_ZBB;
-
-		if (riscv_isa_extension_available(isainfo->isa, ZBS))
-			pair->value |= RISCV_HWPROBE_EXT_ZBS;
-		else
-			missing |= RISCV_HWPROBE_EXT_ZBS;
+#define EXT_KEY(ext)									\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
+			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
+		 * regardless of the kernel's configuration, as no other checks, besides
+		 * presence in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(ZBA);
+		EXT_KEY(ZBB);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZICBOZ);
+#undef EXT_KEY
 	}
 
 	/* Now turn off reporting features if any CPU is missing it. */
 	pair->value &= ~missing;
 }
 
+static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+{
+	struct riscv_hwprobe pair;
+
+	hwprobe_isa_ext0(&pair, cpus);
+	return (pair.value & ext);
+}
+
 static u64 hwprobe_misaligned(const struct cpumask *cpus)
 {
 	int cpu;
@@ -215,6 +227,12 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = hwprobe_misaligned(cpus);
 		break;
 
+	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
+			pair->value = riscv_cboz_block_size;
+		break;
+
 	/*
 	 * For forward compatibility, unknown keys don't fail the whole
 	 * call, but get their element key set to -1 and value set to 0
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index fae8f610d867..c9d698518bae 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -360,34 +360,10 @@ static void noinstr handle_riscv_irq(struct pt_regs *regs)
 asmlinkage void noinstr do_irq(struct pt_regs *regs)
 {
 	irqentry_state_t state = irqentry_enter(regs);
-#ifdef CONFIG_IRQ_STACKS
-	if (on_thread_stack()) {
-		ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id())
-					+ IRQ_STACK_SIZE/sizeof(ulong);
-		__asm__ __volatile(
-		"addi	sp, sp, -"RISCV_SZPTR  "\n"
-		REG_S"  ra, (sp)		\n"
-		"addi	sp, sp, -"RISCV_SZPTR  "\n"
-		REG_S"  s0, (sp)		\n"
-		"addi	s0, sp, 2*"RISCV_SZPTR "\n"
-		"move	sp, %[sp]		\n"
-		"move	a0, %[regs]		\n"
-		"call	handle_riscv_irq	\n"
-		"addi	sp, s0, -2*"RISCV_SZPTR"\n"
-		REG_L"  s0, (sp)		\n"
-		"addi	sp, sp, "RISCV_SZPTR   "\n"
-		REG_L"  ra, (sp)		\n"
-		"addi	sp, sp, "RISCV_SZPTR   "\n"
-		:
-		: [sp] "r" (sp), [regs] "r" (regs)
-		: "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6",
-#ifndef CONFIG_FRAME_POINTER
-		  "s0",
-#endif
-		  "memory");
-	} else
-#endif
+
+	if (IS_ENABLED(CONFIG_IRQ_STACKS) && on_thread_stack())
+		call_on_irq_stack(regs, handle_riscv_irq);
+	else
 		handle_riscv_irq(regs);
 
 	irqentry_exit(regs, state);
@@ -410,48 +386,14 @@ int is_valid_bugaddr(unsigned long pc)
 #endif /* CONFIG_GENERIC_BUG */
 
 #ifdef CONFIG_VMAP_STACK
-/*
- * Extra stack space that allows us to provide panic messages when the kernel
- * has overflowed its stack.
- */
-static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
+DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
 		overflow_stack)__aligned(16);
-/*
- * A temporary stack for use by handle_kernel_stack_overflow.  This is used so
- * we can call into C code to get the per-hart overflow stack.  Usage of this
- * stack must be protected by spin_shadow_stack.
- */
-long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)] __aligned(16);
-
-/*
- * A pseudo spinlock to protect the shadow stack from being used by multiple
- * harts concurrently.  This isn't a real spinlock because the lock side must
- * be taken without a valid stack and only a single register, it's only taken
- * while in the process of panicing anyway so the performance and error
- * checking a proper spinlock gives us doesn't matter.
- */
-unsigned long spin_shadow_stack;
-
-asmlinkage unsigned long get_overflow_stack(void)
-{
-	return (unsigned long)this_cpu_ptr(overflow_stack) +
-		OVERFLOW_STACK_SIZE;
-}
 
 asmlinkage void handle_bad_stack(struct pt_regs *regs)
 {
 	unsigned long tsk_stk = (unsigned long)current->stack;
 	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
 
-	/*
-	 * We're done with the shadow stack by this point, as we're on the
-	 * overflow stack.  Tell any other concurrent overflowing harts that
-	 * they can proceed with panicing by releasing the pseudo-spinlock.
-	 *
-	 * This pairs with an amoswap.aq in handle_kernel_stack_overflow.
-	 */
-	smp_store_release(&spin_shadow_stack, 0);
-
 	console_verbose();
 
 	pr_emerg("Insufficient stack space to handle exception!\n");
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index e8aa7c380007..9b517fe1b8a8 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -36,7 +36,7 @@ CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY
 endif
 
 # Disable -pg to prevent insert call site
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
 
 # Disable profiling and instrumentation for VDSO code
 GCOV_PROFILE := n
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index d40bec6ac078..cadf725ef798 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -37,7 +37,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 
 	/* This is something we can handle, fill out the pairs. */
 	while (p < end) {
-		if (p->key <= RISCV_HWPROBE_MAX_KEY) {
+		if (riscv_hwprobe_key_is_valid(p->key)) {
 			p->value = avd->all_cpu_hwprobe_values[p->key];
 
 		} else {
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index f1387272a551..55a34f2020a8 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -3,7 +3,9 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/acpi.h>
 #include <linux/of.h>
+#include <asm/acpi.h>
 #include <asm/cacheflush.h>
 
 #ifdef CONFIG_SMP
@@ -124,13 +126,24 @@ void __init riscv_init_cbo_blocksizes(void)
 	unsigned long cbom_hartid, cboz_hartid;
 	u32 cbom_block_size = 0, cboz_block_size = 0;
 	struct device_node *node;
+	struct acpi_table_header *rhct;
+	acpi_status status;
+
+	if (acpi_disabled) {
+		for_each_of_cpu_node(node) {
+			/* set block-size for cbom and/or cboz extension if available */
+			cbo_get_block_size(node, "riscv,cbom-block-size",
+					   &cbom_block_size, &cbom_hartid);
+			cbo_get_block_size(node, "riscv,cboz-block-size",
+					   &cboz_block_size, &cboz_hartid);
+		}
+	} else {
+		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
+		if (ACPI_FAILURE(status))
+			return;
 
-	for_each_of_cpu_node(node) {
-		/* set block-size for cbom and/or cboz extension if available */
-		cbo_get_block_size(node, "riscv,cbom-block-size",
-				   &cbom_block_size, &cbom_hartid);
-		cbo_get_block_size(node, "riscv,cboz-block-size",
-				   &cboz_block_size, &cboz_hartid);
+		acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL);
+		acpi_put_table((struct acpi_table_header *)rhct);
 	}
 
 	if (cbom_block_size)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index d9a4e8702864..b128ed3c5a37 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -49,10 +49,12 @@ u64 satp_mode __ro_after_init = SATP_MODE_32;
 #endif
 EXPORT_SYMBOL(satp_mode);
 
+#ifdef CONFIG_64BIT
 bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
 bool pgtable_l5_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
 EXPORT_SYMBOL(pgtable_l4_enabled);
 EXPORT_SYMBOL(pgtable_l5_enabled);
+#endif
 
 phys_addr_t phys_ram_base __ro_after_init;
 EXPORT_SYMBOL(phys_ram_base);
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 20a9f991a6d7..e9090b38f811 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -384,6 +384,9 @@ static int __init ptdump_init(void)
 
 	kernel_ptd_info.base_addr = KERN_VIRT_START;
 
+	pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD";
+	pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD";
+
 	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
 		for (j = 0; j < ARRAY_SIZE(pte_bits); j++)
 			pg_level[i].mask |= pte_bits[j].mask;
diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile
index 9e6476719abb..280b0eb352b8 100644
--- a/arch/riscv/purgatory/Makefile
+++ b/arch/riscv/purgatory/Makefile
@@ -81,6 +81,14 @@ ifdef CONFIG_CFI_CLANG
 PURGATORY_CFLAGS_REMOVE		+= $(CC_FLAGS_CFI)
 endif
 
+ifdef CONFIG_RELOCATABLE
+PURGATORY_CFLAGS_REMOVE		+= -fPIE
+endif
+
+ifdef CONFIG_SHADOW_CALL_STACK
+PURGATORY_CFLAGS_REMOVE		+= $(CC_FLAGS_SCS)
+endif
+
 CFLAGS_REMOVE_purgatory.o	+= $(PURGATORY_CFLAGS_REMOVE)
 CFLAGS_purgatory.o		+= $(PURGATORY_CFLAGS)
 
diff --git a/drivers/acpi/riscv/rhct.c b/drivers/acpi/riscv/rhct.c
index b280b3e9c7d9..caa2c16e1697 100644
--- a/drivers/acpi/riscv/rhct.c
+++ b/drivers/acpi/riscv/rhct.c
@@ -8,8 +8,9 @@
 #define pr_fmt(fmt)     "ACPI: RHCT: " fmt
 
 #include <linux/acpi.h>
+#include <linux/bits.h>
 
-static struct acpi_table_header *acpi_get_rhct(void)
+static struct acpi_table_rhct *acpi_get_rhct(void)
 {
 	static struct acpi_table_header *rhct;
 	acpi_status status;
@@ -26,7 +27,7 @@ static struct acpi_table_header *acpi_get_rhct(void)
 		}
 	}
 
-	return rhct;
+	return (struct acpi_table_rhct *)rhct;
 }
 
 /*
@@ -48,7 +49,7 @@ int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const
 	BUG_ON(acpi_disabled);
 
 	if (!table) {
-		rhct = (struct acpi_table_rhct *)acpi_get_rhct();
+		rhct = acpi_get_rhct();
 		if (!rhct)
 			return -ENOENT;
 	} else {
@@ -81,3 +82,89 @@ int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const
 
 	return -1;
 }
+
+static void acpi_parse_hart_info_cmo_node(struct acpi_table_rhct *rhct,
+					  struct acpi_rhct_hart_info *hart_info,
+					  u32 *cbom_size, u32 *cboz_size, u32 *cbop_size)
+{
+	u32 size_hartinfo = sizeof(struct acpi_rhct_hart_info);
+	u32 size_hdr = sizeof(struct acpi_rhct_node_header);
+	struct acpi_rhct_node_header *ref_node;
+	struct acpi_rhct_cmo_node *cmo_node;
+	u32 *hart_info_node_offset;
+
+	hart_info_node_offset = ACPI_ADD_PTR(u32, hart_info, size_hartinfo);
+	for (int i = 0; i < hart_info->num_offsets; i++) {
+		ref_node = ACPI_ADD_PTR(struct acpi_rhct_node_header,
+					rhct, hart_info_node_offset[i]);
+		if (ref_node->type == ACPI_RHCT_NODE_TYPE_CMO) {
+			cmo_node = ACPI_ADD_PTR(struct acpi_rhct_cmo_node,
+						ref_node, size_hdr);
+			if (cbom_size && cmo_node->cbom_size <= 30) {
+				if (!*cbom_size)
+					*cbom_size = BIT(cmo_node->cbom_size);
+				else if (*cbom_size != BIT(cmo_node->cbom_size))
+					pr_warn("CBOM size is not the same across harts\n");
+			}
+
+			if (cboz_size && cmo_node->cboz_size <= 30) {
+				if (!*cboz_size)
+					*cboz_size = BIT(cmo_node->cboz_size);
+				else if (*cboz_size != BIT(cmo_node->cboz_size))
+					pr_warn("CBOZ size is not the same across harts\n");
+			}
+
+			if (cbop_size && cmo_node->cbop_size <= 30) {
+				if (!*cbop_size)
+					*cbop_size = BIT(cmo_node->cbop_size);
+				else if (*cbop_size != BIT(cmo_node->cbop_size))
+					pr_warn("CBOP size is not the same across harts\n");
+			}
+		}
+	}
+}
+
+/*
+ * During early boot, the caller should call acpi_get_table() and pass its pointer to
+ * these functions (and free up later). At run time, since this table can be used
+ * multiple times, pass NULL so that the table remains in memory.
+ */
+void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
+			     u32 *cboz_size, u32 *cbop_size)
+{
+	u32 size_hdr = sizeof(struct acpi_rhct_node_header);
+	struct acpi_rhct_node_header *node, *end;
+	struct acpi_rhct_hart_info *hart_info;
+	struct acpi_table_rhct *rhct;
+
+	if (acpi_disabled)
+		return;
+
+	if (table) {
+		rhct = (struct acpi_table_rhct *)table;
+	} else {
+		rhct = acpi_get_rhct();
+		if (!rhct)
+			return;
+	}
+
+	if (cbom_size)
+		*cbom_size = 0;
+
+	if (cboz_size)
+		*cboz_size = 0;
+
+	if (cbop_size)
+		*cbop_size = 0;
+
+	end = ACPI_ADD_PTR(struct acpi_rhct_node_header, rhct, rhct->header.length);
+	for (node = ACPI_ADD_PTR(struct acpi_rhct_node_header, rhct, rhct->node_offset);
+	     node < end;
+	     node = ACPI_ADD_PTR(struct acpi_rhct_node_header, node, node->length)) {
+		if (node->type == ACPI_RHCT_NODE_TYPE_HART_INFO) {
+			hart_info = ACPI_ADD_PTR(struct acpi_rhct_hart_info, node, size_hdr);
+			acpi_parse_hart_info_cmo_node(rhct, hart_info, cbom_size,
+						      cboz_size, cbop_size);
+		}
+	}
+}
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 50198657230e..06f5bad3c3e0 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -22,6 +22,7 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/interrupt.h>
 #include <linux/of_irq.h>
+#include <linux/limits.h>
 #include <clocksource/timer-riscv.h>
 #include <asm/smp.h>
 #include <asm/hwcap.h>
@@ -31,12 +32,22 @@
 static DEFINE_STATIC_KEY_FALSE(riscv_sstc_available);
 static bool riscv_timer_cannot_wake_cpu;
 
+static void riscv_clock_event_stop(void)
+{
+	if (static_branch_likely(&riscv_sstc_available)) {
+		csr_write(CSR_STIMECMP, ULONG_MAX);
+		if (IS_ENABLED(CONFIG_32BIT))
+			csr_write(CSR_STIMECMPH, ULONG_MAX);
+	} else {
+		sbi_set_timer(U64_MAX);
+	}
+}
+
 static int riscv_clock_next_event(unsigned long delta,
 		struct clock_event_device *ce)
 {
 	u64 next_tval = get_cycles64() + delta;
 
-	csr_set(CSR_IE, IE_TIE);
 	if (static_branch_likely(&riscv_sstc_available)) {
 #if defined(CONFIG_32BIT)
 		csr_write(CSR_STIMECMP, next_tval & 0xFFFFFFFF);
@@ -94,6 +105,8 @@ static int riscv_timer_starting_cpu(unsigned int cpu)
 	ce->irq = riscv_clock_event_irq;
 	if (riscv_timer_cannot_wake_cpu)
 		ce->features |= CLOCK_EVT_FEAT_C3STOP;
+	if (static_branch_likely(&riscv_sstc_available))
+		ce->rating = 450;
 	clockevents_config_and_register(ce, riscv_timebase, 100, 0x7fffffff);
 
 	enable_percpu_irq(riscv_clock_event_irq,
@@ -119,7 +132,7 @@ static irqreturn_t riscv_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evdev = this_cpu_ptr(&riscv_clock_event);
 
-	csr_clear(CSR_IE, IE_TIE);
+	riscv_clock_event_stop();
 	evdev->event_handler(evdev);
 
 	return IRQ_HANDLED;
diff --git a/drivers/misc/lkdtm/cfi.c b/drivers/misc/lkdtm/cfi.c
index fc28714ae3a6..6a33889d0902 100644
--- a/drivers/misc/lkdtm/cfi.c
+++ b/drivers/misc/lkdtm/cfi.c
@@ -68,12 +68,20 @@ static void lkdtm_CFI_FORWARD_PROTO(void)
 #define no_pac_addr(addr)      \
 	((__force __typeof__(addr))((uintptr_t)(addr) | PAGE_OFFSET))
 
+#ifdef CONFIG_RISCV
+/* https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#frame-pointer-convention */
+#define FRAME_RA_OFFSET		(-1)
+#else
+#define FRAME_RA_OFFSET		1
+#endif
+
 /* The ultimate ROP gadget. */
 static noinline __no_ret_protection
 void set_return_addr_unchecked(unsigned long *expected, unsigned long *addr)
 {
 	/* Use of volatile is to make sure final write isn't seen as a dead store. */
-	unsigned long * volatile *ret_addr = (unsigned long **)__builtin_frame_address(0) + 1;
+	unsigned long * volatile *ret_addr =
+		(unsigned long **)__builtin_frame_address(0) + FRAME_RA_OFFSET;
 
 	/* Make sure we've found the right place on the stack before writing it. */
 	if (no_pac_addr(*ret_addr) == expected)
@@ -88,7 +96,8 @@ static noinline
 void set_return_addr(unsigned long *expected, unsigned long *addr)
 {
 	/* Use of volatile is to make sure final write isn't seen as a dead store. */
-	unsigned long * volatile *ret_addr = (unsigned long **)__builtin_frame_address(0) + 1;
+	unsigned long * volatile *ret_addr =
+		(unsigned long **)__builtin_frame_address(0) + FRAME_RA_OFFSET;
 
 	/* Make sure we've found the right place on the stack before writing it. */
 	if (no_pac_addr(*ret_addr) == expected)
diff --git a/tools/testing/selftests/riscv/hwprobe/Makefile b/tools/testing/selftests/riscv/hwprobe/Makefile
index ebdbb3c22e54..f224b84591fb 100644
--- a/tools/testing/selftests/riscv/hwprobe/Makefile
+++ b/tools/testing/selftests/riscv/hwprobe/Makefile
@@ -2,9 +2,14 @@
 # Copyright (C) 2021 ARM Limited
 # Originally tools/testing/arm64/abi/Makefile
 
-TEST_GEN_PROGS := hwprobe
+CFLAGS += -I$(top_srcdir)/tools/include
+
+TEST_GEN_PROGS := hwprobe cbo
 
 include ../../lib.mk
 
 $(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S
-	$(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
+
+$(OUTPUT)/cbo: cbo.c sys_hwprobe.S
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
new file mode 100644
index 000000000000..50a2cc8aef38
--- /dev/null
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ *
+ * Run with 'taskset -c <cpu-list> cbo' to only execute hwprobe on a
+ * subset of cpus, as well as only executing the tests on those cpus.
+ */
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <stdint.h>
+#include <string.h>
+#include <sched.h>
+#include <signal.h>
+#include <assert.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <asm/ucontext.h>
+
+#include "hwprobe.h"
+#include "../../kselftest.h"
+
+#define MK_CBO(fn) cpu_to_le32((fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
+
+static char mem[4096] __aligned(4096) = { [0 ... 4095] = 0xa5 };
+
+static bool illegal_insn;
+
+static void sigill_handler(int sig, siginfo_t *info, void *context)
+{
+	unsigned long *regs = (unsigned long *)&((ucontext_t *)context)->uc_mcontext;
+	uint32_t insn = *(uint32_t *)regs[0];
+
+	assert(insn == MK_CBO(regs[11]));
+
+	illegal_insn = true;
+	regs[0] += 4;
+}
+
+static void cbo_insn(char *base, int fn)
+{
+	uint32_t insn = MK_CBO(fn);
+
+	asm volatile(
+	"mv	a0, %0\n"
+	"li	a1, %1\n"
+	".4byte	%2\n"
+	: : "r" (base), "i" (fn), "i" (insn) : "a0", "a1", "memory");
+}
+
+static void cbo_inval(char *base) { cbo_insn(base, 0); }
+static void cbo_clean(char *base) { cbo_insn(base, 1); }
+static void cbo_flush(char *base) { cbo_insn(base, 2); }
+static void cbo_zero(char *base)  { cbo_insn(base, 4); }
+
+static void test_no_zicbom(void *arg)
+{
+	ksft_print_msg("Testing Zicbom instructions remain privileged\n");
+
+	illegal_insn = false;
+	cbo_clean(&mem[0]);
+	ksft_test_result(illegal_insn, "No cbo.clean\n");
+
+	illegal_insn = false;
+	cbo_flush(&mem[0]);
+	ksft_test_result(illegal_insn, "No cbo.flush\n");
+
+	illegal_insn = false;
+	cbo_inval(&mem[0]);
+	ksft_test_result(illegal_insn, "No cbo.inval\n");
+}
+
+static void test_no_zicboz(void *arg)
+{
+	ksft_print_msg("No Zicboz, testing cbo.zero remains privileged\n");
+
+	illegal_insn = false;
+	cbo_zero(&mem[0]);
+	ksft_test_result(illegal_insn, "No cbo.zero\n");
+}
+
+static bool is_power_of_2(__u64 n)
+{
+	return n != 0 && (n & (n - 1)) == 0;
+}
+
+static void test_zicboz(void *arg)
+{
+	struct riscv_hwprobe pair = {
+		.key = RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE,
+	};
+	cpu_set_t *cpus = (cpu_set_t *)arg;
+	__u64 block_size;
+	int i, j;
+	long rc;
+
+	rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)cpus, 0);
+	block_size = pair.value;
+	ksft_test_result(rc == 0 && pair.key == RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE &&
+			 is_power_of_2(block_size), "Zicboz block size\n");
+	ksft_print_msg("Zicboz block size: %ld\n", block_size);
+
+	illegal_insn = false;
+	cbo_zero(&mem[block_size]);
+	ksft_test_result(!illegal_insn, "cbo.zero\n");
+
+	if (illegal_insn || !is_power_of_2(block_size)) {
+		ksft_test_result_skip("cbo.zero check\n");
+		return;
+	}
+
+	assert(block_size <= 1024);
+
+	for (i = 0; i < 4096 / block_size; ++i) {
+		if (i % 2)
+			cbo_zero(&mem[i * block_size]);
+	}
+
+	for (i = 0; i < 4096 / block_size; ++i) {
+		char expected = i % 2 ? 0x0 : 0xa5;
+
+		for (j = 0; j < block_size; ++j) {
+			if (mem[i * block_size + j] != expected) {
+				ksft_test_result_fail("cbo.zero check\n");
+				ksft_print_msg("cbo.zero check: mem[%d] != 0x%x\n",
+					       i * block_size + j, expected);
+				return;
+			}
+		}
+	}
+
+	ksft_test_result_pass("cbo.zero check\n");
+}
+
+static void check_no_zicboz_cpus(cpu_set_t *cpus)
+{
+	struct riscv_hwprobe pair = {
+		.key = RISCV_HWPROBE_KEY_IMA_EXT_0,
+	};
+	cpu_set_t one_cpu;
+	int i = 0, c = 0;
+	long rc;
+
+	while (i++ < CPU_COUNT(cpus)) {
+		while (!CPU_ISSET(c, cpus))
+			++c;
+
+		CPU_ZERO(&one_cpu);
+		CPU_SET(c, &one_cpu);
+
+		rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)&one_cpu, 0);
+		assert(rc == 0 && pair.key == RISCV_HWPROBE_KEY_IMA_EXT_0);
+
+		if (pair.value & RISCV_HWPROBE_EXT_ZICBOZ)
+			ksft_exit_fail_msg("Zicboz is only present on a subset of harts.\n"
+					   "Use taskset to select a set of harts where Zicboz\n"
+					   "presence (present or not) is consistent for each hart\n");
+		++c;
+	}
+}
+
+enum {
+	TEST_ZICBOZ,
+	TEST_NO_ZICBOZ,
+	TEST_NO_ZICBOM,
+};
+
+static struct test_info {
+	bool enabled;
+	unsigned int nr_tests;
+	void (*test_fn)(void *arg);
+} tests[] = {
+	[TEST_ZICBOZ]		= { .nr_tests = 3, test_zicboz },
+	[TEST_NO_ZICBOZ]	= { .nr_tests = 1, test_no_zicboz },
+	[TEST_NO_ZICBOM]	= { .nr_tests = 3, test_no_zicbom },
+};
+
+int main(int argc, char **argv)
+{
+	struct sigaction act = {
+		.sa_sigaction = &sigill_handler,
+		.sa_flags = SA_SIGINFO,
+	};
+	struct riscv_hwprobe pair;
+	unsigned int plan = 0;
+	cpu_set_t cpus;
+	long rc;
+	int i;
+
+	if (argc > 1 && !strcmp(argv[1], "--sigill")) {
+		rc = sigaction(SIGILL, &act, NULL);
+		assert(rc == 0);
+		tests[TEST_NO_ZICBOZ].enabled = true;
+		tests[TEST_NO_ZICBOM].enabled = true;
+	}
+
+	rc = sched_getaffinity(0, sizeof(cpu_set_t), &cpus);
+	assert(rc == 0);
+
+	ksft_print_header();
+
+	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
+	rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, 0);
+	if (rc < 0)
+		ksft_exit_fail_msg("hwprobe() failed with %d\n", rc);
+	assert(rc == 0 && pair.key == RISCV_HWPROBE_KEY_IMA_EXT_0);
+
+	if (pair.value & RISCV_HWPROBE_EXT_ZICBOZ) {
+		tests[TEST_ZICBOZ].enabled = true;
+		tests[TEST_NO_ZICBOZ].enabled = false;
+	} else {
+		check_no_zicboz_cpus(&cpus);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tests); ++i)
+		plan += tests[i].enabled ? tests[i].nr_tests : 0;
+
+	if (plan == 0)
+		ksft_print_msg("No tests enabled.\n");
+	else
+		ksft_set_plan(plan);
+
+	for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+		if (tests[i].enabled)
+			tests[i].test_fn(&cpus);
+	}
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
index 09f290a67420..c474891df307 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c
@@ -1,14 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <stddef.h>
-#include <asm/hwprobe.h>
-
-/*
- * Rather than relying on having a new enough libc to define this, just do it
- * ourselves.  This way we don't need to be coupled to a new-enough libc to
- * contain the call.
- */
-long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
+#include "hwprobe.h"
+#include "../../kselftest.h"
 
 int main(int argc, char **argv)
 {
@@ -16,6 +8,9 @@ int main(int argc, char **argv)
 	unsigned long cpus;
 	long out;
 
+	ksft_print_header();
+	ksft_set_plan(5);
+
 	/* Fake the CPU_SET ops. */
 	cpus = -1;
 
@@ -25,13 +20,16 @@ int main(int argc, char **argv)
 	 */
 	for (long i = 0; i < 8; i++)
 		pairs[i].key = i;
+
 	out = riscv_hwprobe(pairs, 8, 1, &cpus, 0);
 	if (out != 0)
-		return -1;
+		ksft_exit_fail_msg("hwprobe() failed with %ld\n", out);
+
 	for (long i = 0; i < 4; ++i) {
 		/* Fail if the kernel claims not to recognize a base key. */
 		if ((i < 4) && (pairs[i].key != i))
-			return -2;
+			ksft_exit_fail_msg("Failed to recognize base key: key != i, "
+					   "key=%ld, i=%ld\n", pairs[i].key, i);
 
 		if (pairs[i].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR)
 			continue;
@@ -39,52 +37,30 @@ int main(int argc, char **argv)
 		if (pairs[i].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA)
 			continue;
 
-		return -3;
+		ksft_exit_fail_msg("Unexpected pair: (%ld, %ld)\n", pairs[i].key, pairs[i].value);
 	}
 
-	/*
-	 * This should also work with a NULL CPU set, but should not work
-	 * with an improperly supplied CPU set.
-	 */
 	out = riscv_hwprobe(pairs, 8, 0, 0, 0);
-	if (out != 0)
-		return -4;
+	ksft_test_result(out == 0, "NULL CPU set\n");
 
 	out = riscv_hwprobe(pairs, 8, 0, &cpus, 0);
-	if (out == 0)
-		return -5;
+	ksft_test_result(out != 0, "Bad CPU set\n");
 
 	out = riscv_hwprobe(pairs, 8, 1, 0, 0);
-	if (out == 0)
-		return -6;
+	ksft_test_result(out != 0, "NULL CPU set with non-zero count\n");
 
-	/*
-	 * Check that keys work by providing one that we know exists, and
-	 * checking to make sure the resultig pair is what we asked for.
-	 */
 	pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR;
 	out = riscv_hwprobe(pairs, 1, 1, &cpus, 0);
-	if (out != 0)
-		return -7;
-	if (pairs[0].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR)
-		return -8;
+	ksft_test_result(out == 0 && pairs[0].key == RISCV_HWPROBE_KEY_BASE_BEHAVIOR,
+			 "Existing key is maintained\n");
 
-	/*
-	 * Check that an unknown key gets overwritten with -1,
-	 * but doesn't block elements after it.
-	 */
 	pairs[0].key = 0x5555;
 	pairs[1].key = 1;
 	pairs[1].value = 0xAAAA;
 	out = riscv_hwprobe(pairs, 2, 0, 0, 0);
-	if (out != 0)
-		return -9;
-
-	if (pairs[0].key != -1)
-		return -10;
-
-	if ((pairs[1].key != 1) || (pairs[1].value == 0xAAAA))
-		return -11;
+	ksft_test_result(out == 0 && pairs[0].key == -1 &&
+			 pairs[1].key == 1 && pairs[1].value != 0xAAAA,
+			 "Unknown key overwritten with -1 and doesn't block other elements\n");
 
-	return 0;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
new file mode 100644
index 000000000000..721b0ce73a56
--- /dev/null
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_RISCV_HWPROBE_H
+#define SELFTEST_RISCV_HWPROBE_H
+#include <stddef.h>
+#include <asm/hwprobe.h>
+
+/*
+ * Rather than relying on having a new enough libc to define this, just do it
+ * ourselves.  This way we don't need to be coupled to a new-enough libc to
+ * contain the call.
+ */
+long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+		   size_t cpu_count, unsigned long *cpus, unsigned int flags);
+
+#endif