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

Cross-merge networking fixes after downstream PR.

No conflicts.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Documentation/networking/ax25.rst

@@ -7,9 +7,9 @@ AX.25
 To use the amateur radio protocols within Linux you will need to get a
 suitable copy of the AX.25 Utilities. More detailed information about
 AX.25, NET/ROM and ROSE, associated programs and utilities can be
-found on http://www.linux-ax25.org.
+found on https://linux-ax25.in-berlin.de.
 
-There is an active mailing list for discussing Linux amateur radio matters
+There is a mailing list for discussing Linux amateur radio matters
 called linux-hams@vger.kernel.org. To subscribe to it, send a message to
 majordomo@vger.kernel.org with the words "subscribe linux-hams" in the body
 of the message, the subject field is ignored.  You don't need to be

Documentation/process/embargoed-hardware-issues.rst

@@ -251,6 +251,7 @@ an involved disclosed party. The current ambassadors list:
   IBM Z		Christian Borntraeger <borntraeger@de.ibm.com>
   Intel		Tony Luck <tony.luck@intel.com>
   Qualcomm	Trilok Soni <tsoni@codeaurora.org>
+  RISC-V	Palmer Dabbelt <palmer@dabbelt.com>
   Samsung	Javier González <javier.gonz@samsung.com>
 
   Microsoft	James Morris <jamorris@linux.microsoft.com>

Documentation/sound/designs/midi-2.0.rst

@@ -74,8 +74,8 @@ topology based on those information.  When the device is older and
 doesn't respond to the new UMP inquiries, the driver falls back and
 builds the topology based on Group Terminal Block (GTB) information
 from the USB descriptor.  Some device might be screwed up by the
-unexpected UMP command; in such a case, pass `midi2_probe=0` option to
+unexpected UMP command; in such a case, pass `midi2_ump_probe=0`
-snd-usb-audio driver for skipping the UMP v1.1 inquiries.
+option to snd-usb-audio driver for skipping the UMP v1.1 inquiries.
 
 When the MIDI 2.0 device is probed, the kernel creates a rawmidi
 device for each UMP Endpoint of the device.  Its device name is

MAINTAINERS

@@ -3344,7 +3344,7 @@ AX.25 NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
 S:	Maintained
-W:	http://www.linux-ax25.org/
+W:	https://linux-ax25.in-berlin.de
 F:	include/net/ax25.h
 F:	include/uapi/linux/ax25.h
 F:	net/ax25/
@@ -14769,7 +14769,7 @@ NETROM NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
 S:	Maintained
-W:	http://www.linux-ax25.org/
+W:	https://linux-ax25.in-berlin.de
 F:	include/net/netrom.h
 F:	include/uapi/linux/netrom.h
 F:	net/netrom/
@@ -18620,7 +18620,7 @@ ROSE NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
 S:	Maintained
-W:	http://www.linux-ax25.org/
+W:	https://linux-ax25.in-berlin.de
 F:	include/net/rose.h
 F:	include/uapi/linux/rose.h
 F:	net/rose/

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*

arch/arm/xen/enlighten.c

@@ -207,7 +207,7 @@ static void xen_power_off(void)
 
 static irqreturn_t xen_arm_callback(int irq, void *arg)
 {
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 	return IRQ_HANDLED;
 }
 

arch/powerpc/Kconfig

@@ -255,7 +255,7 @@ config PPC
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
-	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT
+	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT && (!ARCH_USING_PATCHABLE_FUNCTION_ENTRY || (!CC_IS_GCC || GCC_VERSION >= 110100))
 	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)

arch/powerpc/kernel/hw_breakpoint.c

@@ -230,13 +230,15 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
 	struct arch_hw_breakpoint *info;
 	int i;
 
+	preempt_disable();
+
 	for (i = 0; i < nr_wp_slots(); i++) {
 		struct perf_event *bp = __this_cpu_read(bp_per_reg[i]);
 
 		if (unlikely(bp && counter_arch_bp(bp)->perf_single_step))
 			goto reset;
 	}
-	return;
+	goto out;
 
 reset:
 	regs_set_return_msr(regs, regs->msr & ~MSR_SE);
@@ -245,6 +247,9 @@ reset:
 		__set_breakpoint(i, info);
 		info->perf_single_step = false;
 	}
+
+out:
+	preempt_enable();
 }
 
 static bool is_larx_stcx_instr(int type)
@@ -363,6 +368,11 @@ static void handle_p10dd1_spurious_exception(struct perf_event **bp,
 	}
 }
 
+/*
+ * Handle a DABR or DAWR exception.
+ *
+ * Called in atomic context.
+ */
 int hw_breakpoint_handler(struct die_args *args)
 {
 	bool err = false;
@@ -490,6 +500,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler);
 
 /*
  * Handle single-step exceptions following a DABR hit.
+ *
+ * Called in atomic context.
  */
 static int single_step_dabr_instruction(struct die_args *args)
 {
@@ -541,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction);
 
 /*
  * Handle debug exception notifications.
+ *
+ * Called in atomic context.
  */
 int hw_breakpoint_exceptions_notify(
 		struct notifier_block *unused, unsigned long val, void *data)

arch/powerpc/kernel/hw_breakpoint_constraints.c

@@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
 			 int *type, int *size, unsigned long *ea)
 {
 	struct instruction_op op;
+	int err;
 
-	if (__get_user_instr(*instr, (void __user *)regs->nip))
+	pagefault_disable();
+	err = __get_user_instr(*instr, (void __user *)regs->nip);
+	pagefault_enable();
+
+	if (err)
 		return;
 
 	analyse_instr(&op, regs, *instr);

arch/powerpc/kernel/traps.c

@@ -1512,23 +1512,11 @@ static void do_program_check(struct pt_regs *regs)
 			return;
 		}
 
-		if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && user_mode(regs)) {
+		/* User mode considers other cases after enabling IRQs */
-			ppc_inst_t insn;
+		if (!user_mode(regs)) {
-
+			_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-			if (get_user_instr(insn, (void __user *)regs->nip)) {
+			return;
-				_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-				return;
-			}
-
-			if (ppc_inst_primary_opcode(insn) == 31 &&
-			    get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
-				_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
-				return;
-			}
 		}
-
-		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		return;
 	}
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (reason & REASON_TM) {
@@ -1561,16 +1549,44 @@ static void do_program_check(struct pt_regs *regs)
 
 	/*
 	 * If we took the program check in the kernel skip down to sending a
-	 * SIGILL. The subsequent cases all relate to emulating instructions
+	 * SIGILL. The subsequent cases all relate to user space, such as
-	 * which we should only do for userspace. We also do not want to enable
+	 * emulating instructions which we should only do for user space. We
-	 * interrupts for kernel faults because that might lead to further
+	 * also do not want to enable interrupts for kernel faults because that
-	 * faults, and loose the context of the original exception.
+	 * might lead to further faults, and loose the context of the original
+	 * exception.
 	 */
 	if (!user_mode(regs))
 		goto sigill;
 
 	interrupt_cond_local_irq_enable(regs);
 
+	/*
+	 * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
+	 * except get_user_instr() can sleep so we cannot reliably inspect the
+	 * current instruction in that context. Now that we know we are
+	 * handling a user space trap and can sleep, we can check if the trap
+	 * was a hashchk failure.
+	 */
+	if (reason & REASON_TRAP) {
+		if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+			ppc_inst_t insn;
+
+			if (get_user_instr(insn, (void __user *)regs->nip)) {
+				_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+				return;
+			}
+
+			if (ppc_inst_primary_opcode(insn) == 31 &&
+			    get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
+				_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+				return;
+			}
+		}
+
+		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+		return;
+	}
+
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
 	 * but there seems to be a hardware bug on the 405GP (RevD)
 	 * that means ESR is sometimes set incorrectly - either to

arch/powerpc/perf/hv-24x7.c

@@ -1418,7 +1418,7 @@ static int h_24x7_event_init(struct perf_event *event)
 	}
 
 	domain = event_get_domain(event);
-	if (domain >= HV_PERF_DOMAIN_MAX) {
+	if (domain  == 0 || domain >= HV_PERF_DOMAIN_MAX) {
 		pr_devel("invalid domain %d\n", domain);
 		return -EINVAL;
 	}

arch/powerpc/platforms/82xx/Kconfig

@@ -2,6 +2,7 @@
 menuconfig PPC_82xx
 	bool "82xx-based boards (PQ II)"
 	depends on PPC_BOOK3S_32
+	select FSL_SOC
 
 if PPC_82xx
 
@@ -9,7 +10,6 @@ config EP8248E
 	bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)"
 	select CPM2
 	select PPC_INDIRECT_PCI if PCI
-	select FSL_SOC
 	select PHYLIB if NETDEVICES
 	select MDIO_BITBANG if PHYLIB
 	help
@@ -22,7 +22,6 @@ config MGCOGE
 	bool "Keymile MGCOGE"
 	select CPM2
 	select PPC_INDIRECT_PCI if PCI
-	select FSL_SOC
 	help
 	  This enables support for the Keymile MGCOGE board.
 

arch/riscv/include/asm/errata_list.h

@@ -105,7 +105,7 @@ asm volatile(ALTERNATIVE(						\
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01001      rs1       000      00000  0001011
  * dcache.cva rs1 (clean, virtual address)
- *   0000001    00100      rs1       000      00000  0001011
+ *   0000001    00101      rs1       000      00000  0001011
  *
  * dcache.cipa rs1 (clean then invalidate, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
@@ -118,7 +118,7 @@ asm volatile(ALTERNATIVE(						\
  *   0000000    11001     00000      000      00000  0001011
  */
 #define THEAD_inval_A0	".long 0x0265000b"
-#define THEAD_clean_A0	".long 0x0245000b"
+#define THEAD_clean_A0	".long 0x0255000b"
 #define THEAD_flush_A0	".long 0x0275000b"
 #define THEAD_SYNC_S	".long 0x0190000b"
 

arch/riscv/kernel/elf_kexec.c

@@ -98,7 +98,13 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
 	kbuf.image = image;
 	kbuf.buf_min = lowest_paddr;
 	kbuf.buf_max = ULONG_MAX;
-	kbuf.buf_align = PAGE_SIZE;
+
+	/*
+	 * Current riscv boot protocol requires 2MB alignment for
+	 * RV64 and 4MB alignment for RV32
+	 *
+	 */
+	kbuf.buf_align = PMD_SIZE;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE);
 	kbuf.top_down = false;

arch/x86/Kconfig

@@ -1945,6 +1945,7 @@ config EFI
 	select UCS2_STRING
 	select EFI_RUNTIME_WRAPPERS
 	select ARCH_USE_MEMREMAP_PROT
+	select EFI_RUNTIME_MAP if KEXEC_CORE
 	help
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
@@ -2020,7 +2021,6 @@ config EFI_MAX_FAKE_MEM
 config EFI_RUNTIME_MAP
 	bool "Export EFI runtime maps to sysfs" if EXPERT
 	depends on EFI
-	default KEXEC_CORE
 	help
 	  Export EFI runtime memory regions to /sys/firmware/efi/runtime-map.
 	  That memory map is required by the 2nd kernel to set up EFI virtual

arch/x86/boot/compressed/ident_map_64.c

@@ -59,6 +59,14 @@ static void *alloc_pgt_page(void *context)
 		return NULL;
 	}
 
+	/* Consumed more tables than expected? */
+	if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) {
+		debug_putstr("pgt_buf running low in " __FILE__ "\n");
+		debug_putstr("Need to raise BOOT_PGT_SIZE?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+	}
+
 	entry = pages->pgt_buf + pages->pgt_buf_offset;
 	pages->pgt_buf_offset += PAGE_SIZE;
 

arch/x86/entry/common.c

@@ -294,7 +294,7 @@ static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 
 	set_irq_regs(old_regs);
 }

arch/x86/include/asm/boot.h

@@ -40,23 +40,40 @@
 #ifdef CONFIG_X86_64
 # define BOOT_STACK_SIZE	0x4000
 
-# define BOOT_INIT_PGT_SIZE	(6*4096)
-# ifdef CONFIG_RANDOMIZE_BASE
 /*
- * Assuming all cross the 512GB boundary:
+ * Used by decompressor's startup_32() to allocate page tables for identity
- * 1 page for level4
+ * mapping of the 4G of RAM in 4-level paging mode:
- * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
+ * - 1 level4 table;
- * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
+ * - 1 level3 table;
- * Total is 19 pages.
+ * - 4 level2 table that maps everything with 2M pages;
+ *
+ * The additional level5 table needed for 5-level paging is allocated from
+ * trampoline_32bit memory.
  */
-#  ifdef CONFIG_X86_VERBOSE_BOOTUP
+# define BOOT_INIT_PGT_SIZE	(6*4096)
-#   define BOOT_PGT_SIZE	(19*4096)
+
-#  else /* !CONFIG_X86_VERBOSE_BOOTUP */
+/*
-#   define BOOT_PGT_SIZE	(17*4096)
+ * Total number of page tables kernel_add_identity_map() can allocate,
-#  endif
+ * including page tables consumed by startup_32().
-# else /* !CONFIG_RANDOMIZE_BASE */
+ *
-#  define BOOT_PGT_SIZE		BOOT_INIT_PGT_SIZE
+ * Worst-case scenario:
-# endif
+ *  - 5-level paging needs 1 level5 table;
+ *  - KASLR needs to map kernel, boot_params, cmdline and randomized kernel,
+ *    assuming all of them cross 256T boundary:
+ *    + 4*2 level4 table;
+ *    + 4*2 level3 table;
+ *    + 4*2 level2 table;
+ *  - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM):
+ *    + 1 level4 table;
+ *    + 1 level3 table;
+ *    + 1 level2 table;
+ * Total: 28 tables
+ *
+ * Add 4 spare table in case decompressor touches anything beyond what is
+ * accounted above. Warn if it happens.
+ */
+# define BOOT_PGT_SIZE_WARN	(28*4096)
+# define BOOT_PGT_SIZE		(32*4096)
 
 #else /* !CONFIG_X86_64 */
 # define BOOT_STACK_SIZE	0x1000

arch/x86/include/asm/efi.h

@@ -91,19 +91,6 @@ static inline void efi_fpu_end(void)
 
 #ifdef CONFIG_X86_32
 #define EFI_X86_KERNEL_ALLOC_LIMIT		(SZ_512M - 1)
-
-#define arch_efi_call_virt_setup()					\
-({									\
-	efi_fpu_begin();						\
-	firmware_restrict_branch_speculation_start();			\
-})
-
-#define arch_efi_call_virt_teardown()					\
-({									\
-	firmware_restrict_branch_speculation_end();			\
-	efi_fpu_end();							\
-})
-
 #else /* !CONFIG_X86_32 */
 #define EFI_X86_KERNEL_ALLOC_LIMIT		EFI_ALLOC_LIMIT
 
@@ -116,14 +103,6 @@ extern bool efi_disable_ibt_for_runtime;
 	__efi_call(__VA_ARGS__);					\
 })
 
-#define arch_efi_call_virt_setup()					\
-({									\
-	efi_sync_low_kernel_mappings();					\
-	efi_fpu_begin();						\
-	firmware_restrict_branch_speculation_start();			\
-	efi_enter_mm();							\
-})
-
 #undef arch_efi_call_virt
 #define arch_efi_call_virt(p, f, args...) ({				\
 	u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime);		\
@@ -132,13 +111,6 @@ extern bool efi_disable_ibt_for_runtime;
 	ret;								\
 })
 
-#define arch_efi_call_virt_teardown()					\
-({									\
-	efi_leave_mm();							\
-	firmware_restrict_branch_speculation_end();			\
-	efi_fpu_end();							\
-})
-
 #ifdef CONFIG_KASAN
 /*
  * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
@@ -168,8 +140,8 @@ extern void efi_delete_dummy_variable(void);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
 
-void efi_enter_mm(void);
+void arch_efi_call_virt_setup(void);
-void efi_leave_mm(void);
+void arch_efi_call_virt_teardown(void);
 
 /* kexec external ABI */
 struct efi_setup_data {

arch/x86/include/asm/linkage.h

@@ -8,6 +8,14 @@
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
 
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
 #endif /* CONFIG_X86_32 */

arch/x86/include/asm/paravirt_types.h

@@ -9,13 +9,6 @@ struct paravirt_patch_site {
 	u8 type;		/* type of this instruction */
 	u8 len;			/* length of original instruction */
 };
-
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
-	PARAVIRT_LAZY_NONE,
-	PARAVIRT_LAZY_MMU,
-	PARAVIRT_LAZY_CPU,
-};
 #endif
 
 #ifdef CONFIG_PARAVIRT
@@ -549,14 +542,6 @@ int paravirt_disable_iospace(void);
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_start_context_switch(struct task_struct *prev);
-void paravirt_end_context_switch(struct task_struct *next);
-
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-void paravirt_flush_lazy_mmu(void);
-
 void _paravirt_nop(void);
 void paravirt_BUG(void);
 unsigned long paravirt_ret0(void);

arch/x86/include/asm/xen/hypervisor.h

@@ -36,6 +36,7 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
+#include <asm/bug.h>
 #include <asm/processor.h>
 
 #define XEN_SIGNATURE "XenVMMXenVMM"
@@ -63,4 +64,40 @@ void __init xen_pvh_init(struct boot_params *boot_params);
 void __init mem_map_via_hcall(struct boot_params *boot_params_p);
 #endif
 
+/* Lazy mode for batching updates / context switch */
+enum xen_lazy_mode {
+	XEN_LAZY_NONE,
+	XEN_LAZY_MMU,
+	XEN_LAZY_CPU,
+};
+
+DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode);
+DECLARE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+static inline void enter_lazy(enum xen_lazy_mode mode)
+{
+	enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode);
+
+	if (mode == old_mode) {
+		this_cpu_inc(xen_lazy_nesting);
+		return;
+	}
+
+	BUG_ON(old_mode != XEN_LAZY_NONE);
+
+	this_cpu_write(xen_lazy_mode, mode);
+}
+
+static inline void leave_lazy(enum xen_lazy_mode mode)
+{
+	BUG_ON(this_cpu_read(xen_lazy_mode) != mode);
+
+	if (this_cpu_read(xen_lazy_nesting) == 0)
+		this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
+	else
+		this_cpu_dec(xen_lazy_nesting);
+}
+
+enum xen_lazy_mode xen_get_lazy_mode(void);
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -1533,7 +1533,7 @@ static void __init build_socket_tables(void)
 {
 	struct uv_gam_range_entry *gre = uv_gre_table;
 	int nums, numn, nump;
-	int cpu, i, lnid;
+	int i, lnid, apicid;
 	int minsock = _min_socket;
 	int maxsock = _max_socket;
 	int minpnode = _min_pnode;
@@ -1584,15 +1584,14 @@ static void __init build_socket_tables(void)
 
 	/* Set socket -> node values: */
 	lnid = NUMA_NO_NODE;
-	for_each_possible_cpu(cpu) {
+	for (apicid = 0; apicid < ARRAY_SIZE(__apicid_to_node); apicid++) {
-		int nid = cpu_to_node(cpu);
+		int nid = __apicid_to_node[apicid];
-		int apicid, sockid;
+		int sockid;
 
-		if (lnid == nid)
+		if ((nid == NUMA_NO_NODE) || (lnid == nid))
 			continue;
 		lnid = nid;
 
-		apicid = per_cpu(x86_cpu_to_apicid, cpu);
 		sockid = apicid >> uv_cpuid.socketid_shift;
 
 		if (_socket_to_node[sockid - minsock] == SOCK_EMPTY)

arch/x86/kernel/paravirt.c

@@ -143,66 +143,7 @@ int paravirt_disable_iospace(void)
 	return request_resource(&ioport_resource, &reserve_ioports);
 }
 
-static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
-
-static inline void enter_lazy(enum paravirt_lazy_mode mode)
-{
-	BUG_ON(this_cpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-
-	this_cpu_write(paravirt_lazy_mode, mode);
-}
-
-static void leave_lazy(enum paravirt_lazy_mode mode)
-{
-	BUG_ON(this_cpu_read(paravirt_lazy_mode) != mode);
-
-	this_cpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
-}
-
-void paravirt_enter_lazy_mmu(void)
-{
-	enter_lazy(PARAVIRT_LAZY_MMU);
-}
-
-void paravirt_leave_lazy_mmu(void)
-{
-	leave_lazy(PARAVIRT_LAZY_MMU);
-}
-
-void paravirt_flush_lazy_mmu(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 #ifdef CONFIG_PARAVIRT_XXL
-void paravirt_start_context_switch(struct task_struct *prev)
-{
-	BUG_ON(preemptible());
-
-	if (this_cpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
-	}
-	enter_lazy(PARAVIRT_LAZY_CPU);
-}
-
-void paravirt_end_context_switch(struct task_struct *next)
-{
-	BUG_ON(preemptible());
-
-	leave_lazy(PARAVIRT_LAZY_CPU);
-
-	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
-		arch_enter_lazy_mmu_mode();
-}
-
 static noinstr void pv_native_write_cr2(unsigned long val)
 {
 	native_write_cr2(val);
@@ -229,14 +170,6 @@ static noinstr void pv_native_safe_halt(void)
 }
 #endif
 
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
-{
-	if (in_interrupt())
-		return PARAVIRT_LAZY_NONE;
-
-	return this_cpu_read(paravirt_lazy_mode);
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 #ifdef CONFIG_PARAVIRT_XXL

arch/x86/kernel/smpboot.c

@@ -579,7 +579,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 }
 
 
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
 	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -603,7 +602,14 @@ static int x86_cluster_flags(void)
 	return cpu_cluster_flags() | x86_sched_itmt_flags();
 }
 #endif
-#endif
+
+static int x86_die_flags(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	       return x86_sched_itmt_flags();
+
+	return 0;
+}
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.
@@ -640,7 +646,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
 		};
 	}
 

arch/x86/lib/putuser.S

@@ -56,7 +56,6 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
-	ENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -76,7 +75,6 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
-	ENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -96,7 +94,6 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
-	ENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -119,7 +116,6 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
-	ENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32

arch/x86/platform/efi/efi_32.c

@@ -140,3 +140,15 @@ void __init efi_runtime_update_mappings(void)
 		}
 	}
 }
+
+void arch_efi_call_virt_setup(void)
+{
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}

arch/x86/platform/efi/efi_64.c

@@ -474,19 +474,34 @@ void __init efi_dump_pagetable(void)
  * can not change under us.
  * It should be ensured that there are no concurrent calls to this function.
  */
-void efi_enter_mm(void)
+static void efi_enter_mm(void)
 {
 	efi_prev_mm = current->active_mm;
 	current->active_mm = &efi_mm;
 	switch_mm(efi_prev_mm, &efi_mm, NULL);
 }
 
-void efi_leave_mm(void)
+static void efi_leave_mm(void)
 {
 	current->active_mm = efi_prev_mm;
 	switch_mm(&efi_mm, efi_prev_mm, NULL);
 }
 
+void arch_efi_call_virt_setup(void)
+{
+	efi_sync_low_kernel_mappings();
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+	efi_enter_mm();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	efi_leave_mm();
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}
+
 static DEFINE_SPINLOCK(efi_runtime_lock);
 
 /*

arch/x86/purgatory/Makefile

@@ -19,6 +19,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
 # optimization flags.
 KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
 
+# When LTO is enabled, llvm emits many text sections, which is not supported
+# by kexec. Remove -flto=* flags.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+
 # When linking purgatory.ro with -r unresolved symbols are not checked,
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
 PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib

arch/x86/xen/efi.c

@@ -138,7 +138,7 @@ void __init xen_efi_init(struct boot_params *boot_params)
 	if (efi_systab_xen == NULL)
 		return;
 
-	strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
+	strscpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
 			sizeof(boot_params->efi_info.efi_loader_signature));
 	boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
 	boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);

arch/x86/xen/enlighten.c

@@ -32,7 +32,7 @@ EXPORT_SYMBOL_GPL(hypercall_page);
  * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
  * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
  * but during boot it is switched to point to xen_vcpu_info.
- * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events.
+ * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events.
  */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);

arch/x86/xen/enlighten_hvm.c

@@ -136,7 +136,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 
 	set_irq_regs(old_regs);
 }

arch/x86/xen/enlighten_pv.c

@@ -101,6 +101,17 @@ struct tls_descs {
 	struct desc_struct desc[3];
 };
 
+DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE;
+DEFINE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+enum xen_lazy_mode xen_get_lazy_mode(void)
+{
+	if (in_interrupt())
+		return XEN_LAZY_NONE;
+
+	return this_cpu_read(xen_lazy_mode);
+}
+
 /*
  * Updating the 3 TLS descriptors in the GDT on every task switch is
  * surprisingly expensive so we avoid updating them if they haven't
@@ -362,10 +373,25 @@ static noinstr unsigned long xen_get_debugreg(int reg)
 	return HYPERVISOR_get_debugreg(reg);
 }
 
+static void xen_start_context_switch(struct task_struct *prev)
+{
+	BUG_ON(preemptible());
+
+	if (this_cpu_read(xen_lazy_mode) == XEN_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+	}
+	enter_lazy(XEN_LAZY_CPU);
+}
+
 static void xen_end_context_switch(struct task_struct *next)
 {
+	BUG_ON(preemptible());
+
 	xen_mc_flush();
-	paravirt_end_context_switch(next);
+	leave_lazy(XEN_LAZY_CPU);
+	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+		arch_enter_lazy_mmu_mode();
 }
 
 static unsigned long xen_store_tr(void)
@@ -472,7 +498,7 @@ static void xen_set_ldt(const void *addr, unsigned entries)
 
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_load_gdt(const struct desc_ptr *dtr)
@@ -568,7 +594,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	 * exception between the new %fs descriptor being loaded and
 	 * %fs being effectively cleared at __switch_to().
 	 */
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+	if (xen_get_lazy_mode() == XEN_LAZY_CPU)
 		loadsegment(fs, 0);
 
 	xen_mc_batch();
@@ -577,7 +603,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	load_TLS_descriptor(t, cpu, 1);
 	load_TLS_descriptor(t, cpu, 2);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_load_gs_index(unsigned int idx)
@@ -909,7 +935,7 @@ static void xen_load_sp0(unsigned long sp0)
 
 	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
@@ -973,7 +999,7 @@ static void xen_write_cr0(unsigned long cr0)
 
 	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_write_cr4(unsigned long cr4)
@@ -1156,7 +1182,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = {
 #endif
 		.io_delay = xen_io_delay,
 
-		.start_context_switch = paravirt_start_context_switch,
+		.start_context_switch = xen_start_context_switch,
 		.end_context_switch = xen_end_context_switch,
 	},
 };

arch/x86/xen/mmu_pv.c

@@ -236,7 +236,7 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 	u.val = pmd_val_ma(val);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -270,7 +270,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 {
 	struct mmu_update u;
 
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
+	if (xen_get_lazy_mode() != XEN_LAZY_MMU)
 		return false;
 
 	xen_mc_batch();
@@ -279,7 +279,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 	u.val = pte_val_ma(pteval);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	return true;
 }
@@ -325,7 +325,7 @@ void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 	u.val = pte_val_ma(pte);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 /* Assume pteval_t is equivalent to all the other *val_t types. */
@@ -419,7 +419,7 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 	u.val = pud_val_ma(val);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -499,7 +499,7 @@ static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 
 	__xen_set_p4d_hyper(ptr, val);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -531,7 +531,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
 	if (user_ptr)
 		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 #if CONFIG_PGTABLE_LEVELS >= 5
@@ -1245,7 +1245,7 @@ static noinline void xen_flush_tlb(void)
 	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -1265,7 +1265,7 @@ static void xen_flush_tlb_one_user(unsigned long addr)
 	op->arg1.linear_addr = addr & PAGE_MASK;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -1302,7 +1302,7 @@ static void xen_flush_tlb_multi(const struct cpumask *cpus,
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 static unsigned long xen_read_cr3(void)
@@ -1361,7 +1361,7 @@ static void xen_write_cr3(unsigned long cr3)
 	else
 		__xen_write_cr3(false, 0);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+	xen_mc_issue(XEN_LAZY_CPU);  /* interrupts restored */
 }
 
 /*
@@ -1396,7 +1396,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 
 	__xen_write_cr3(true, cr3);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+	xen_mc_issue(XEN_LAZY_CPU);  /* interrupts restored */
 }
 
 static int xen_pgd_alloc(struct mm_struct *mm)
@@ -1557,7 +1557,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
-		xen_mc_issue(PARAVIRT_LAZY_MMU);
+		xen_mc_issue(XEN_LAZY_MMU);
 	}
 }
 
@@ -1587,7 +1587,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 
 		__set_pfn_prot(pfn, PAGE_KERNEL);
 
-		xen_mc_issue(PARAVIRT_LAZY_MMU);
+		xen_mc_issue(XEN_LAZY_MMU);
 
 		ClearPagePinned(page);
 	}
@@ -1804,7 +1804,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	 */
 	xen_mc_batch();
 	__xen_write_cr3(true, __pa(init_top_pgt));
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 
 	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
 	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
@@ -2083,6 +2083,23 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
+static void xen_enter_lazy_mmu(void)
+{
+	enter_lazy(XEN_LAZY_MMU);
+}
+
+static void xen_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (xen_get_lazy_mode() == XEN_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 static void __init xen_post_allocator_init(void)
 {
 	pv_ops.mmu.set_pte = xen_set_pte;
@@ -2107,7 +2124,7 @@ static void xen_leave_lazy_mmu(void)
 {
 	preempt_disable();
 	xen_mc_flush();
-	paravirt_leave_lazy_mmu();
+	leave_lazy(XEN_LAZY_MMU);
 	preempt_enable();
 }
 
@@ -2166,9 +2183,9 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.exit_mmap = xen_exit_mmap,
 
 		.lazy_mode = {
-			.enter = paravirt_enter_lazy_mmu,
+			.enter = xen_enter_lazy_mmu,
 			.leave = xen_leave_lazy_mmu,
-			.flush = paravirt_flush_lazy_mmu,
+			.flush = xen_flush_lazy_mmu,
 		},
 
 		.set_fixmap = xen_set_fixmap,
@@ -2385,7 +2402,7 @@ static noinline void xen_flush_tlb_all(void)
 	op->cmd = MMUEXT_TLB_FLUSH_ALL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }

arch/x86/xen/multicalls.h

@@ -26,7 +26,7 @@ static inline void xen_mc_batch(void)
 
 	/* need to disable interrupts until this entry is complete */
 	local_irq_save(flags);
-	trace_xen_mc_batch(paravirt_get_lazy_mode());
+	trace_xen_mc_batch(xen_get_lazy_mode());
 	__this_cpu_write(xen_mc_irq_flags, flags);
 }
 
@@ -44,7 +44,7 @@ static inline void xen_mc_issue(unsigned mode)
 {
 	trace_xen_mc_issue(mode);
 
-	if ((paravirt_get_lazy_mode() & mode) == 0)
+	if ((xen_get_lazy_mode() & mode) == 0)
 		xen_mc_flush();
 
 	/* restore flags saved in xen_mc_batch */

block/blk-mq.c

@@ -4405,11 +4405,8 @@ static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
 	struct blk_mq_tags **new_tags;
 	int i;
 
-	if (set->nr_hw_queues >= new_nr_hw_queues) {
+	if (set->nr_hw_queues >= new_nr_hw_queues)
-		for (i = new_nr_hw_queues; i < set->nr_hw_queues; i++)
-			__blk_mq_free_map_and_rqs(set, i);
 		goto done;
-	}
 
 	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
 				GFP_KERNEL, set->numa_node);
@@ -4719,7 +4716,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 {
 	struct request_queue *q;
 	LIST_HEAD(head);
-	int prev_nr_hw_queues;
+	int prev_nr_hw_queues = set->nr_hw_queues;
+	int i;
 
 	lockdep_assert_held(&set->tag_list_lock);
 
@@ -4746,7 +4744,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister_hctxs(q);
 	}
 
-	prev_nr_hw_queues = set->nr_hw_queues;
 	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
 		goto reregister;
 
@@ -4781,6 +4778,10 @@ switch_back:
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
+
+	/* Free the excess tags when nr_hw_queues shrink. */
+	for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)
+		__blk_mq_free_map_and_rqs(set, i);
 }
 
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)

drivers/acpi/thermal.c

@@ -492,7 +492,7 @@ static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
 }
 
 static int thermal_get_trend(struct thermal_zone_device *thermal,
-			     struct thermal_trip *trip,
+			     const struct thermal_trip *trip,
 			     enum thermal_trend *trend)
 {
 	struct acpi_thermal *tz = thermal_zone_device_priv(thermal);

drivers/ata/ahci.c

@@ -1883,6 +1883,15 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else
 		dev_info(&pdev->dev, "SSS flag set, parallel bus scan disabled\n");
 
+	if (!(hpriv->cap & HOST_CAP_PART))
+		host->flags |= ATA_HOST_NO_PART;
+
+	if (!(hpriv->cap & HOST_CAP_SSC))
+		host->flags |= ATA_HOST_NO_SSC;
+
+	if (!(hpriv->cap2 & HOST_CAP2_SDS))
+		host->flags |= ATA_HOST_NO_DEVSLP;
+
 	if (pi.flags & ATA_FLAG_EM)
 		ahci_reset_em(host);
 

drivers/ata/libahci.c

@@ -1256,6 +1256,26 @@ static ssize_t ahci_activity_show(struct ata_device *dev, char *buf)
 	return sprintf(buf, "%d\n", emp->blink_policy);
 }
 
+static void ahci_port_clear_pending_irq(struct ata_port *ap)
+{
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	void __iomem *port_mmio = ahci_port_base(ap);
+	u32 tmp;
+
+	/* clear SError */
+	tmp = readl(port_mmio + PORT_SCR_ERR);
+	dev_dbg(ap->host->dev, "PORT_SCR_ERR 0x%x\n", tmp);
+	writel(tmp, port_mmio + PORT_SCR_ERR);
+
+	/* clear port IRQ */
+	tmp = readl(port_mmio + PORT_IRQ_STAT);
+	dev_dbg(ap->host->dev, "PORT_IRQ_STAT 0x%x\n", tmp);
+	if (tmp)
+		writel(tmp, port_mmio + PORT_IRQ_STAT);
+
+	writel(1 << ap->port_no, hpriv->mmio + HOST_IRQ_STAT);
+}
+
 static void ahci_port_init(struct device *dev, struct ata_port *ap,
 			   int port_no, void __iomem *mmio,
 			   void __iomem *port_mmio)
@@ -1270,18 +1290,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap,
 	if (rc)
 		dev_warn(dev, "%s (%d)\n", emsg, rc);
 
-	/* clear SError */
+	ahci_port_clear_pending_irq(ap);
-	tmp = readl(port_mmio + PORT_SCR_ERR);
-	dev_dbg(dev, "PORT_SCR_ERR 0x%x\n", tmp);
-	writel(tmp, port_mmio + PORT_SCR_ERR);
-
-	/* clear port IRQ */
-	tmp = readl(port_mmio + PORT_IRQ_STAT);
-	dev_dbg(dev, "PORT_IRQ_STAT 0x%x\n", tmp);
-	if (tmp)
-		writel(tmp, port_mmio + PORT_IRQ_STAT);
-
-	writel(1 << port_no, mmio + HOST_IRQ_STAT);
 
 	/* mark esata ports */
 	tmp = readl(port_mmio + PORT_CMD);
@@ -1603,6 +1612,8 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class,
 	tf.status = ATA_BUSY;
 	ata_tf_to_fis(&tf, 0, 0, d2h_fis);
 
+	ahci_port_clear_pending_irq(ap);
+
 	rc = sata_link_hardreset(link, timing, deadline, online,
 				 ahci_check_ready);
 

drivers/ata/libata-core.c

@@ -4783,11 +4783,8 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 	 * been aborted by the device due to a limit timeout using the policy
 	 * 0xD. For these commands, invoke EH to get the command sense data.
 	 */
-	if (qc->result_tf.status & ATA_SENSE &&
+	if (qc->flags & ATA_QCFLAG_HAS_CDL &&
-	    ((ata_is_ncq(qc->tf.protocol) &&
+	    qc->result_tf.status & ATA_SENSE) {
-	      dev->flags & ATA_DFLAG_CDL_ENABLED) ||
-	     (!ata_is_ncq(qc->tf.protocol) &&
-	      ata_id_sense_reporting_enabled(dev->id)))) {
 		/*
 		 * Tell SCSI EH to not overwrite scmd->result even if this
 		 * command is finished with result SAM_STAT_GOOD.

drivers/ata/libata-eh.c

@@ -2796,23 +2796,13 @@ int ata_eh_reset(struct ata_link *link, int classify,
 		}
 	}
 
-	/*
+	/* clear cached SError */
-	 * Some controllers can't be frozen very well and may set spurious
-	 * error conditions during reset.  Clear accumulated error
-	 * information and re-thaw the port if frozen.  As reset is the
-	 * final recovery action and we cross check link onlineness against
-	 * device classification later, no hotplug event is lost by this.
-	 */
 	spin_lock_irqsave(link->ap->lock, flags);
-	memset(&link->eh_info, 0, sizeof(link->eh_info));
+	link->eh_info.serror = 0;
 	if (slave)
-		memset(&slave->eh_info, 0, sizeof(link->eh_info));
+		slave->eh_info.serror = 0;
-	ap->pflags &= ~ATA_PFLAG_EH_PENDING;
 	spin_unlock_irqrestore(link->ap->lock, flags);
 
-	if (ata_port_is_frozen(ap))
-		ata_eh_thaw_port(ap);
-
 	/*
 	 * Make sure onlineness and classification result correspond.
 	 * Hotplug could have happened during reset and some

drivers/ata/libata-sata.c

@@ -396,10 +396,23 @@ int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	case ATA_LPM_MED_POWER_WITH_DIPM:
 	case ATA_LPM_MIN_POWER_WITH_PARTIAL:
 	case ATA_LPM_MIN_POWER:
-		if (ata_link_nr_enabled(link) > 0)
+		if (ata_link_nr_enabled(link) > 0) {
-			/* no restrictions on LPM transitions */
+			/* assume no restrictions on LPM transitions */
 			scontrol &= ~(0x7 << 8);
-		else {
+
+			/*
+			 * If the controller does not support partial, slumber,
+			 * or devsleep, then disallow these transitions.
+			 */
+			if (link->ap->host->flags & ATA_HOST_NO_PART)
+				scontrol |= (0x1 << 8);
+
+			if (link->ap->host->flags & ATA_HOST_NO_SSC)
+				scontrol |= (0x2 << 8);
+
+			if (link->ap->host->flags & ATA_HOST_NO_DEVSLP)
+				scontrol |= (0x4 << 8);
+		} else {
 			/* empty port, power off */
 			scontrol &= ~0xf;
 			scontrol |= (0x1 << 2);

drivers/ata/pata_parport/comm.c

@@ -37,7 +37,7 @@ static int comm_read_regr(struct pi_adapter *pi, int cont, int regr)
 {
 	int l, h, r;
 
-        r = regr + cont_map[cont];
+	r = regr + cont_map[cont];
 
 	switch (pi->mode) {
 	case 0:
@@ -90,7 +90,6 @@ static void comm_connect(struct pi_adapter *pi)
 }
 
 static void comm_disconnect(struct pi_adapter *pi)
-
 {
 	w2(0); w2(0); w2(0); w2(4);
 	w0(pi->saved_r0);
@@ -172,12 +171,12 @@ static void comm_write_block(struct pi_adapter *pi, char *buf, int count)
 			w4l(swab16(((u16 *)buf)[2 * k]) |
 			    swab16(((u16 *)buf)[2 * k + 1]) << 16);
 		break;
-        }
+	}
 }
 
 static void comm_log_adapter(struct pi_adapter *pi)
-
+{
-{       char *mode_string[5] = { "4-bit", "8-bit", "EPP-8", "EPP-16", "EPP-32" };
+	char *mode_string[5] = { "4-bit", "8-bit", "EPP-8", "EPP-16", "EPP-32" };
 
 	dev_info(&pi->dev,
 		 "DataStor Commuter at 0x%x, mode %d (%s), delay %d\n",

drivers/ata/sata_mv.c

@@ -1255,8 +1255,8 @@ static void mv_dump_mem(struct device *dev, void __iomem *start, unsigned bytes)
 
 	for (b = 0; b < bytes; ) {
 		for (w = 0, o = 0; b < bytes && w < 4; w++) {
-			o += snprintf(linebuf + o, sizeof(linebuf) - o,
+			o += scnprintf(linebuf + o, sizeof(linebuf) - o,
-				      "%08x ", readl(start + b));
+				       "%08x ", readl(start + b));
 			b += sizeof(u32);
 		}
 		dev_dbg(dev, "%s: %p: %s\n",

drivers/base/core.c

@@ -3537,6 +3537,8 @@ int device_add(struct device *dev)
 	/* subsystems can specify simple device enumeration */
 	else if (dev->bus && dev->bus->dev_name)
 		error = dev_set_name(dev, "%s%u", dev->bus->dev_name, dev->id);
+	else
+		error = -EINVAL;
 	if (error)
 		goto name_error;
 

drivers/comedi/Kconfig

@@ -67,7 +67,6 @@ config COMEDI_TEST
 
 config COMEDI_PARPORT
 	tristate "Parallel port support"
-	depends on HAS_IOPORT
 	help
 	  Enable support for the standard parallel port.
 	  A cheap and easy way to get a few more digital I/O lines. Steal
@@ -80,7 +79,6 @@ config COMEDI_PARPORT
 config COMEDI_SSV_DNP
 	tristate "SSV Embedded Systems DIL/Net-PC support"
 	depends on X86_32 || COMPILE_TEST
-	depends on HAS_IOPORT
 	help
 	  Enable support for SSV Embedded Systems DIL/Net-PC
 
@@ -91,7 +89,6 @@ endif # COMEDI_MISC_DRIVERS
 
 menuconfig COMEDI_ISA_DRIVERS
 	bool "Comedi ISA and PC/104 drivers"
-	depends on ISA
 	help
 	  Enable comedi ISA and PC/104 drivers to be built
 
@@ -103,8 +100,7 @@ if COMEDI_ISA_DRIVERS
 
 config COMEDI_PCL711
 	tristate "Advantech PCL-711/711b and ADlink ACL-8112 ISA card support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for Advantech PCL-711 and 711b, ADlink ACL-8112
 
@@ -165,9 +161,8 @@ config COMEDI_PCL730
 
 config COMEDI_PCL812
 	tristate "Advantech PCL-812/813 and ADlink ACL-8112/8113/8113/8216"
-	depends on HAS_IOPORT
 	select COMEDI_ISADMA if ISA_DMA_API
-	depends on COMEDI_8254
+	select COMEDI_8254
 	help
 	  Enable support for Advantech PCL-812/PG, PCL-813/B, ADLink
 	  ACL-8112DG/HG/PG, ACL-8113, ACL-8216, ICP DAS A-821PGH/PGL/PGL-NDA,
@@ -178,9 +173,8 @@ config COMEDI_PCL812
 
 config COMEDI_PCL816
 	tristate "Advantech PCL-814 and PCL-816 ISA card support"
-	depends on HAS_IOPORT
 	select COMEDI_ISADMA if ISA_DMA_API
-	depends on COMEDI_8254
+	select COMEDI_8254
 	help
 	  Enable support for Advantech PCL-814 and PCL-816 ISA cards
 
@@ -189,9 +183,8 @@ config COMEDI_PCL816
 
 config COMEDI_PCL818
 	tristate "Advantech PCL-718 and PCL-818 ISA card support"
-	depends on HAS_IOPORT
 	select COMEDI_ISADMA if ISA_DMA_API
-	depends on COMEDI_8254
+	select COMEDI_8254
 	help
 	  Enable support for Advantech PCL-818 ISA cards
 	  PCL-818L, PCL-818H, PCL-818HD, PCL-818HG, PCL-818 and PCL-718
@@ -210,7 +203,7 @@ config COMEDI_PCM3724
 
 config COMEDI_AMPLC_DIO200_ISA
 	tristate "Amplicon PC212E/PC214E/PC215E/PC218E/PC272E"
-	depends on COMEDI_AMPLC_DIO200
+	select COMEDI_AMPLC_DIO200
 	help
 	  Enable support for Amplicon PC212E, PC214E, PC215E, PC218E and
 	  PC272E ISA DIO boards
@@ -262,8 +255,7 @@ config COMEDI_DAC02
 
 config COMEDI_DAS16M1
 	tristate "MeasurementComputing CIO-DAS16/M1DAS-16 ISA card support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for Measurement Computing CIO-DAS16/M1 ISA cards.
@@ -273,7 +265,7 @@ config COMEDI_DAS16M1
 
 config COMEDI_DAS08_ISA
 	tristate "DAS-08 compatible ISA and PC/104 card support"
-	depends on COMEDI_DAS08
+	select COMEDI_DAS08
 	help
 	  Enable support for Keithley Metrabyte/ComputerBoards DAS08
 	  and compatible ISA and PC/104 cards:
@@ -286,9 +278,8 @@ config COMEDI_DAS08_ISA
 
 config COMEDI_DAS16
 	tristate "DAS-16 compatible ISA and PC/104 card support"
-	depends on HAS_IOPORT
 	select COMEDI_ISADMA if ISA_DMA_API
-	depends on COMEDI_8254
+	select COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for Keithley Metrabyte/ComputerBoards DAS16
@@ -305,8 +296,7 @@ config COMEDI_DAS16
 
 config COMEDI_DAS800
 	tristate "DAS800 and compatible ISA card support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for Keithley Metrabyte DAS800 and compatible ISA cards
 	  Keithley Metrabyte DAS-800, DAS-801, DAS-802
@@ -318,9 +308,8 @@ config COMEDI_DAS800
 
 config COMEDI_DAS1800
 	tristate "DAS1800 and compatible ISA card support"
-	depends on HAS_IOPORT
 	select COMEDI_ISADMA if ISA_DMA_API
-	depends on COMEDI_8254
+	select COMEDI_8254
 	help
 	  Enable support for DAS1800 and compatible ISA cards
 	  Keithley Metrabyte DAS-1701ST, DAS-1701ST-DA, DAS-1701/AO,
@@ -334,8 +323,7 @@ config COMEDI_DAS1800
 
 config COMEDI_DAS6402
 	tristate "DAS6402 and compatible ISA card support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for DAS6402 and compatible ISA cards
 	  Computerboards, Keithley Metrabyte DAS6402 and compatibles
@@ -414,8 +402,7 @@ config COMEDI_FL512
 
 config COMEDI_AIO_AIO12_8
 	tristate "I/O Products PC/104 AIO12-8 Analog I/O Board support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for I/O Products PC/104 AIO12-8 Analog I/O Board
@@ -469,9 +456,8 @@ config COMEDI_ADQ12B
 
 config COMEDI_NI_AT_A2150
 	tristate "NI AT-A2150 ISA card support"
-	depends on HAS_IOPORT
 	select COMEDI_ISADMA if ISA_DMA_API
-	depends on COMEDI_8254
+	select COMEDI_8254
 	help
 	  Enable support for National Instruments AT-A2150 cards
 
@@ -480,8 +466,7 @@ config COMEDI_NI_AT_A2150
 
 config COMEDI_NI_AT_AO
 	tristate "NI AT-AO-6/10 EISA card support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for National Instruments AT-AO-6/10 cards
 
@@ -512,7 +497,7 @@ config COMEDI_NI_ATMIO16D
 
 config COMEDI_NI_LABPC_ISA
 	tristate "NI Lab-PC and compatibles ISA support"
-	depends on COMEDI_NI_LABPC
+	select COMEDI_NI_LABPC
 	help
 	  Enable support for National Instruments Lab-PC and compatibles
 	  Lab-PC-1200, Lab-PC-1200AI, Lab-PC+.
@@ -576,7 +561,7 @@ endif # COMEDI_ISA_DRIVERS
 
 menuconfig COMEDI_PCI_DRIVERS
 	tristate "Comedi PCI drivers"
-	depends on PCI && HAS_IOPORT
+	depends on PCI
 	help
 	  Enable support for comedi PCI drivers.
 
@@ -725,8 +710,7 @@ config COMEDI_ADL_PCI8164
 
 config COMEDI_ADL_PCI9111
 	tristate "ADLink PCI-9111HR support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for ADlink PCI9111 cards
 
@@ -736,7 +720,7 @@ config COMEDI_ADL_PCI9111
 config COMEDI_ADL_PCI9118
 	tristate "ADLink PCI-9118DG, PCI-9118HG, PCI-9118HR support"
 	depends on HAS_DMA
-	depends on COMEDI_8254
+	select COMEDI_8254
 	help
 	  Enable support for ADlink PCI-9118DG, PCI-9118HG, PCI-9118HR cards
 
@@ -745,8 +729,7 @@ config COMEDI_ADL_PCI9118
 
 config COMEDI_ADV_PCI1710
 	tristate "Advantech PCI-171x and PCI-1731 support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for Advantech PCI-1710, PCI-1710HG, PCI-1711,
 	  PCI-1713 and PCI-1731
@@ -790,8 +773,7 @@ config COMEDI_ADV_PCI1760
 
 config COMEDI_ADV_PCI_DIO
 	tristate "Advantech PCI DIO card support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for Advantech PCI DIO cards
@@ -804,7 +786,7 @@ config COMEDI_ADV_PCI_DIO
 
 config COMEDI_AMPLC_DIO200_PCI
 	tristate "Amplicon PCI215/PCI272/PCIe215/PCIe236/PCIe296 DIO support"
-	depends on COMEDI_AMPLC_DIO200
+	select COMEDI_AMPLC_DIO200
 	help
 	  Enable support for Amplicon PCI215, PCI272, PCIe215, PCIe236
 	  and PCIe296 DIO boards.
@@ -832,8 +814,7 @@ config COMEDI_AMPLC_PC263_PCI
 
 config COMEDI_AMPLC_PCI224
 	tristate "Amplicon PCI224 and PCI234 support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for Amplicon PCI224 and PCI234 AO boards
 
@@ -842,8 +823,7 @@ config COMEDI_AMPLC_PCI224
 
 config COMEDI_AMPLC_PCI230
 	tristate "Amplicon PCI230 and PCI260 support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for Amplicon PCI230 and PCI260 Multifunction I/O
@@ -862,7 +842,7 @@ config COMEDI_CONTEC_PCI_DIO
 
 config COMEDI_DAS08_PCI
 	tristate "DAS-08 PCI support"
-	depends on COMEDI_DAS08
+	select COMEDI_DAS08
 	help
 	  Enable support for PCI DAS-08 cards.
 
@@ -949,8 +929,7 @@ config COMEDI_CB_PCIDAS64
 
 config COMEDI_CB_PCIDAS
 	tristate "MeasurementComputing PCI-DAS support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for ComputerBoards/MeasurementComputing PCI-DAS with
@@ -974,8 +953,7 @@ config COMEDI_CB_PCIDDA
 
 config COMEDI_CB_PCIMDAS
 	tristate "MeasurementComputing PCIM-DAS1602/16, PCIe-DAS1602/16 support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 	help
 	  Enable support for ComputerBoards/MeasurementComputing PCI Migration
@@ -995,8 +973,7 @@ config COMEDI_CB_PCIMDDA
 
 config COMEDI_ME4000
 	tristate "Meilhaus ME-4000 support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for Meilhaus PCI data acquisition cards
 	  ME-4650, ME-4670i, ME-4680, ME-4680i and ME-4680is
@@ -1054,7 +1031,7 @@ config COMEDI_NI_670X
 
 config COMEDI_NI_LABPC_PCI
 	tristate "NI Lab-PC PCI-1200 support"
-	depends on COMEDI_NI_LABPC
+	select COMEDI_NI_LABPC
 	help
 	  Enable support for National Instruments Lab-PC PCI-1200.
 
@@ -1076,7 +1053,6 @@ config COMEDI_NI_PCIDIO
 config COMEDI_NI_PCIMIO
 	tristate "NI PCI-MIO-E series and M series support"
 	depends on HAS_DMA
-	depends on HAS_IOPORT
 	select COMEDI_NI_TIOCMD
 	select COMEDI_8255
 	help
@@ -1098,8 +1074,7 @@ config COMEDI_NI_PCIMIO
 
 config COMEDI_RTD520
 	tristate "Real Time Devices PCI4520/DM7520 support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for Real Time Devices PCI4520/DM7520
 
@@ -1139,8 +1114,7 @@ if COMEDI_PCMCIA_DRIVERS
 
 config COMEDI_CB_DAS16_CS
 	tristate "CB DAS16 series PCMCIA support"
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	help
 	  Enable support for the ComputerBoards/MeasurementComputing PCMCIA
 	  cards DAS16/16, PCM-DAS16D/12 and PCM-DAS16s/16
@@ -1150,7 +1124,7 @@ config COMEDI_CB_DAS16_CS
 
 config COMEDI_DAS08_CS
 	tristate "CB DAS08 PCMCIA support"
-	depends on COMEDI_DAS08
+	select COMEDI_DAS08
 	help
 	  Enable support for the ComputerBoards/MeasurementComputing DAS-08
 	  PCMCIA card
@@ -1160,7 +1134,6 @@ config COMEDI_DAS08_CS
 
 config COMEDI_NI_DAQ_700_CS
 	tristate "NI DAQCard-700 PCMCIA support"
-	depends on HAS_IOPORT
 	help
 	  Enable support for the National Instruments PCMCIA DAQCard-700 DIO
 
@@ -1169,7 +1142,6 @@ config COMEDI_NI_DAQ_700_CS
 
 config COMEDI_NI_DAQ_DIO24_CS
 	tristate "NI DAQ-Card DIO-24 PCMCIA support"
-	depends on HAS_IOPORT
 	select COMEDI_8255
 	help
 	  Enable support for the National Instruments PCMCIA DAQ-Card DIO-24
@@ -1179,7 +1151,7 @@ config COMEDI_NI_DAQ_DIO24_CS
 
 config COMEDI_NI_LABPC_CS
 	tristate "NI DAQCard-1200 PCMCIA support"
-	depends on COMEDI_NI_LABPC
+	select COMEDI_NI_LABPC
 	help
 	  Enable support for the National Instruments PCMCIA DAQCard-1200
 
@@ -1188,7 +1160,6 @@ config COMEDI_NI_LABPC_CS
 
 config COMEDI_NI_MIO_CS
 	tristate "NI DAQCard E series PCMCIA support"
-	depends on HAS_IOPORT
 	select COMEDI_NI_TIO
 	select COMEDI_8255
 	help
@@ -1201,7 +1172,6 @@ config COMEDI_NI_MIO_CS
 
 config COMEDI_QUATECH_DAQP_CS
 	tristate "Quatech DAQP PCMCIA data capture card support"
-	depends on HAS_IOPORT
 	help
 	  Enable support for the Quatech DAQP PCMCIA data capture cards
 	  DAQP-208 and DAQP-308
@@ -1278,14 +1248,12 @@ endif # COMEDI_USB_DRIVERS
 
 config COMEDI_8254
 	tristate
-	depends on HAS_IOPORT
 
 config COMEDI_8255
 	tristate
 
 config COMEDI_8255_SA
 	tristate "Standalone 8255 support"
-	depends on HAS_IOPORT
 	select COMEDI_8255
 	help
 	  Enable support for 8255 digital I/O as a standalone driver.
@@ -1317,7 +1285,7 @@ config COMEDI_KCOMEDILIB
 	  called kcomedilib.
 
 config COMEDI_AMPLC_DIO200
-	depends on COMEDI_8254
+	select COMEDI_8254
 	tristate
 
 config COMEDI_AMPLC_PC236
@@ -1326,7 +1294,7 @@ config COMEDI_AMPLC_PC236
 
 config COMEDI_DAS08
 	tristate
-	depends on COMEDI_8254
+	select COMEDI_8254
 	select COMEDI_8255
 
 config COMEDI_ISADMA
@@ -1334,8 +1302,7 @@ config COMEDI_ISADMA
 
 config COMEDI_NI_LABPC
 	tristate
-	depends on HAS_IOPORT
+	select COMEDI_8254
-	depends on COMEDI_8254
 	select COMEDI_8255
 
 config COMEDI_NI_LABPC_ISADMA

drivers/firewire/core-device.c

@@ -1211,7 +1211,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		 * without actually having a link.
 		 */
  create:
-		device = kzalloc(sizeof(*device), GFP_KERNEL);
+		device = kzalloc(sizeof(*device), GFP_ATOMIC);
 		if (device == NULL)
 			break;
 

drivers/firewire/core-topology.c

@@ -101,7 +101,7 @@ static struct fw_node *fw_node_create(u32 sid, int port_count, int color)
 {
 	struct fw_node *node;
 
-	node = kzalloc(struct_size(node, ports, port_count), GFP_KERNEL);
+	node = kzalloc(struct_size(node, ports, port_count), GFP_ATOMIC);
 	if (node == NULL)
 		return NULL;
 

drivers/firmware/cirrus/cs_dsp.c

@@ -1863,15 +1863,15 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp)
 		return PTR_ERR(adsp2_alg);
 
 	for (i = 0; i < n_algs; i++) {
-		cs_dsp_info(dsp,
+		cs_dsp_dbg(dsp,
-			    "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n",
+			   "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n",
-			    i, be32_to_cpu(adsp2_alg[i].alg.id),
+			   i, be32_to_cpu(adsp2_alg[i].alg.id),
-			    (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16,
+			   (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16,
-			    (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8,
+			   (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8,
-			    be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff,
+			   be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff,
-			    be32_to_cpu(adsp2_alg[i].xm),
+			   be32_to_cpu(adsp2_alg[i].xm),
-			    be32_to_cpu(adsp2_alg[i].ym),
+			   be32_to_cpu(adsp2_alg[i].ym),
-			    be32_to_cpu(adsp2_alg[i].zm));
+			   be32_to_cpu(adsp2_alg[i].zm));
 
 		alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM,
 						  adsp2_alg[i].alg.id,
@@ -1996,14 +1996,14 @@ static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp)
 		return PTR_ERR(halo_alg);
 
 	for (i = 0; i < n_algs; i++) {
-		cs_dsp_info(dsp,
+		cs_dsp_dbg(dsp,
-			    "%d: ID %x v%d.%d.%d XM@%x YM@%x\n",
+			   "%d: ID %x v%d.%d.%d XM@%x YM@%x\n",
-			    i, be32_to_cpu(halo_alg[i].alg.id),
+			   i, be32_to_cpu(halo_alg[i].alg.id),
-			    (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16,
+			   (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16,
-			    (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8,
+			   (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8,
-			    be32_to_cpu(halo_alg[i].alg.ver) & 0xff,
+			   be32_to_cpu(halo_alg[i].alg.ver) & 0xff,
-			    be32_to_cpu(halo_alg[i].xm_base),
+			   be32_to_cpu(halo_alg[i].xm_base),
-			    be32_to_cpu(halo_alg[i].ym_base));
+			   be32_to_cpu(halo_alg[i].ym_base));
 
 		ret = cs_dsp_halo_create_regions(dsp, halo_alg[i].alg.id,
 						 halo_alg[i].alg.ver,

drivers/firmware/efi/libstub/unaccepted_memory.c

@@ -62,7 +62,7 @@ efi_status_t allocate_unaccepted_bitmap(__u32 nr_desc,
 	bitmap_size = DIV_ROUND_UP(unaccepted_end - unaccepted_start,
 				   EFI_UNACCEPTED_UNIT_SIZE * BITS_PER_BYTE);
 
-	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA,
+	status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY,
 			     sizeof(*unaccepted_table) + bitmap_size,
 			     (void **)&unaccepted_table);
 	if (status != EFI_SUCCESS) {

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1293,7 +1293,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
-bool amdgpu_sg_display_supported(struct amdgpu_device *adev);
 bool amdgpu_device_pcie_dynamic_switching_supported(void);
 bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
 bool amdgpu_device_aspm_support_quirk(void);

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

@@ -478,7 +478,7 @@ void amdgpu_amdkfd_get_cu_info(struct amdgpu_device *adev, struct kfd_cu_info *c
 	cu_info->cu_active_number = acu_info.number;
 	cu_info->cu_ao_mask = acu_info.ao_cu_mask;
 	memcpy(&cu_info->cu_bitmap[0], &acu_info.bitmap[0],
-	       sizeof(acu_info.bitmap));
+	       sizeof(cu_info->cu_bitmap));
 	cu_info->num_shader_engines = adev->gfx.config.max_shader_engines;
 	cu_info->num_shader_arrays_per_engine = adev->gfx.config.max_sh_per_se;
 	cu_info->num_cu_per_sh = adev->gfx.config.max_cu_per_sh;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c

@@ -980,8 +980,7 @@ void kgd_gfx_v10_build_grace_period_packet_info(struct amdgpu_device *adev,
 						uint32_t wait_times,
 						uint32_t grace_period,
 						uint32_t *reg_offset,
-						uint32_t *reg_data,
+						uint32_t *reg_data)
-						uint32_t inst)
 {
 	*reg_data = wait_times;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h

@@ -55,5 +55,4 @@ void kgd_gfx_v10_build_grace_period_packet_info(struct amdgpu_device *adev,
 					       uint32_t wait_times,
 					       uint32_t grace_period,
 					       uint32_t *reg_offset,
-					       uint32_t *reg_data,
+					       uint32_t *reg_data);
-					       uint32_t inst);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

@@ -1103,8 +1103,7 @@ void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
 		uint32_t wait_times,
 		uint32_t grace_period,
 		uint32_t *reg_offset,
-		uint32_t *reg_data,
+		uint32_t *reg_data)
-		uint32_t inst)
 {
 	*reg_data = wait_times;
 
@@ -1120,8 +1119,7 @@ void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
 			SCH_WAVE,
 			grace_period);
 
-	*reg_offset = SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
+	*reg_offset = SOC15_REG_OFFSET(GC, 0, mmCP_IQ_WAIT_TIME2);
-			mmCP_IQ_WAIT_TIME2);
 }
 
 void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev,

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h

@@ -100,5 +100,4 @@ void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
 					       uint32_t wait_times,
 					       uint32_t grace_period,
 					       uint32_t *reg_offset,
-					       uint32_t *reg_data,
+					       uint32_t *reg_data);
-					       uint32_t inst);

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

@@ -1244,32 +1244,6 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 	return true;
 }
 
-/*
- * On APUs with >= 64GB white flickering has been observed w/ SG enabled.
- * Disable S/G on such systems until we have a proper fix.
- * https://gitlab.freedesktop.org/drm/amd/-/issues/2354
- * https://gitlab.freedesktop.org/drm/amd/-/issues/2735
- */
-bool amdgpu_sg_display_supported(struct amdgpu_device *adev)
-{
-	switch (amdgpu_sg_display) {
-	case -1:
-		break;
-	case 0:
-		return false;
-	case 1:
-		return true;
-	default:
-		return false;
-	}
-	if ((totalram_pages() << (PAGE_SHIFT - 10)) +
-	    (adev->gmc.real_vram_size / 1024) >= 64000000) {
-		DRM_WARN("Disabling S/G due to >=64GB RAM\n");
-		return false;
-	}
-	return true;
-}
-
 /*
  * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic
  * speed switching. Until we have confirmation from Intel that a specific host

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h

@@ -43,6 +43,7 @@
 #define AMDGPU_GFX_LBPW_DISABLED_MODE		0x00000008L
 
 #define AMDGPU_MAX_GC_INSTANCES		8
+#define KGD_MAX_QUEUES			128
 
 #define AMDGPU_MAX_GFX_QUEUES KGD_MAX_QUEUES
 #define AMDGPU_MAX_COMPUTE_QUEUES KGD_MAX_QUEUES
@@ -257,7 +258,7 @@ struct amdgpu_cu_info {
 	uint32_t number;
 	uint32_t ao_cu_mask;
 	uint32_t ao_cu_bitmap[4][4];
-	uint32_t bitmap[4][4];
+	uint32_t bitmap[AMDGPU_MAX_GC_INSTANCES][4][4];
 };
 
 struct amdgpu_gfx_ras {

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

@@ -839,7 +839,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		memcpy(&dev_info->cu_ao_bitmap[0], &adev->gfx.cu_info.ao_cu_bitmap[0],
 		       sizeof(adev->gfx.cu_info.ao_cu_bitmap));
 		memcpy(&dev_info->cu_bitmap[0], &adev->gfx.cu_info.bitmap[0],
-		       sizeof(adev->gfx.cu_info.bitmap));
+		       sizeof(dev_info->cu_bitmap));
 		dev_info->vram_type = adev->gmc.vram_type;
 		dev_info->vram_bit_width = adev->gmc.vram_width;
 		dev_info->vce_harvest_config = adev->vce.harvest_config;
@@ -940,12 +940,17 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			struct atom_context *atom_context;
 
 			atom_context = adev->mode_info.atom_context;
-			memcpy(vbios_info.name, atom_context->name, sizeof(atom_context->name));
+			if (atom_context) {
-			memcpy(vbios_info.vbios_pn, atom_context->vbios_pn, sizeof(atom_context->vbios_pn));
+				memcpy(vbios_info.name, atom_context->name,
-			vbios_info.version = atom_context->version;
+				       sizeof(atom_context->name));
-			memcpy(vbios_info.vbios_ver_str, atom_context->vbios_ver_str,
+				memcpy(vbios_info.vbios_pn, atom_context->vbios_pn,
-						sizeof(atom_context->vbios_ver_str));
+				       sizeof(atom_context->vbios_pn));
-			memcpy(vbios_info.date, atom_context->date, sizeof(atom_context->date));
+				vbios_info.version = atom_context->version;
+				memcpy(vbios_info.vbios_ver_str, atom_context->vbios_ver_str,
+				       sizeof(atom_context->vbios_ver_str));
+				memcpy(vbios_info.date, atom_context->date,
+				       sizeof(atom_context->date));
+			}
 
 			return copy_to_user(out, &vbios_info,
 						min((size_t)size, sizeof(vbios_info))) ? -EFAULT : 0;

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

@@ -1052,7 +1052,8 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 	info->ce_count = obj->err_data.ce_count;
 
 	if (err_data.ce_count) {
-		if (adev->smuio.funcs &&
+		if (!adev->aid_mask &&
+		    adev->smuio.funcs &&
 		    adev->smuio.funcs->get_socket_id &&
 		    adev->smuio.funcs->get_die_id) {
 			dev_info(adev->dev, "socket: %d, die: %d "
@@ -1072,7 +1073,8 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 		}
 	}
 	if (err_data.ue_count) {
-		if (adev->smuio.funcs &&
+		if (!adev->aid_mask &&
+		    adev->smuio.funcs &&
 		    adev->smuio.funcs->get_socket_id &&
 		    adev->smuio.funcs->get_die_id) {
 			dev_info(adev->dev, "socket: %d, die: %d "

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

@@ -81,7 +81,7 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 		     unsigned int size)
 {
 	struct drm_suballoc *sa = drm_suballoc_new(&sa_manager->base, size,
-						   GFP_KERNEL, true, 0);
+						   GFP_KERNEL, false, 0);
 
 	if (IS_ERR(sa)) {
 		*sa_bo = NULL;

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -9449,7 +9449,7 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev,
 				gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v10_0_get_cu_active_bitmap_per_sh(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask) {

drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c

@@ -6368,7 +6368,7 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev,
 			 *    SE6: {SH0,SH1} --> {bitmap[2][2], bitmap[2][3]}
 			 *    SE7: {SH0,SH1} --> {bitmap[3][2], bitmap[3][3]}
 			 */
-			cu_info->bitmap[i % 4][j + (i / 4) * 2] = bitmap;
+			cu_info->bitmap[0][i % 4][j + (i / 4) * 2] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask)

drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c

@@ -3577,7 +3577,7 @@ static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev)
 				gfx_v6_0_set_user_cu_inactive_bitmap(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v6_0_get_cu_enabled(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask) {

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c

@@ -5119,7 +5119,7 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev)
 				gfx_v7_0_set_user_cu_inactive_bitmap(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v7_0_get_cu_active_bitmap(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask) {

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -7121,7 +7121,7 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev)
 				gfx_v8_0_set_user_cu_inactive_bitmap(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v8_0_get_cu_active_bitmap(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
 				if (bitmap & mask) {

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -1499,7 +1499,7 @@ static void gfx_v9_0_init_always_on_cu_mask(struct amdgpu_device *adev)
 			amdgpu_gfx_select_se_sh(adev, i, j, 0xffffffff, 0);
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
-				if (cu_info->bitmap[i][j] & mask) {
+				if (cu_info->bitmap[0][i][j] & mask) {
 					if (counter == pg_always_on_cu_num)
 						WREG32_SOC15(GC, 0, mmRLC_PG_ALWAYS_ON_CU_MASK, cu_bitmap);
 					if (counter < always_on_cu_num)
@@ -7233,7 +7233,7 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 			 *    SE6,SH0 --> bitmap[2][1]
 			 *    SE7,SH0 --> bitmap[3][1]
 			 */
-			cu_info->bitmap[i % 4][j + i / 4] = bitmap;
+			cu_info->bitmap[0][i % 4][j + i / 4] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
 				if (bitmap & mask) {

drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c

@@ -4259,7 +4259,7 @@ static void gfx_v9_4_3_set_gds_init(struct amdgpu_device *adev)
 }
 
 static void gfx_v9_4_3_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
-						 u32 bitmap)
+						 u32 bitmap, int xcc_id)
 {
 	u32 data;
 
@@ -4269,15 +4269,15 @@ static void gfx_v9_4_3_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
 	data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
 	data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
 
-	WREG32_SOC15(GC, GET_INST(GC, 0), regGC_USER_SHADER_ARRAY_CONFIG, data);
+	WREG32_SOC15(GC, GET_INST(GC, xcc_id), regGC_USER_SHADER_ARRAY_CONFIG, data);
 }
 
-static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev)
+static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_id)
 {
 	u32 data, mask;
 
-	data = RREG32_SOC15(GC, GET_INST(GC, 0), regCC_GC_SHADER_ARRAY_CONFIG);
+	data = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCC_GC_SHADER_ARRAY_CONFIG);
-	data |= RREG32_SOC15(GC, GET_INST(GC, 0), regGC_USER_SHADER_ARRAY_CONFIG);
+	data |= RREG32_SOC15(GC, GET_INST(GC, xcc_id), regGC_USER_SHADER_ARRAY_CONFIG);
 
 	data &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
 	data >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
@@ -4290,7 +4290,7 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev)
 static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 				 struct amdgpu_cu_info *cu_info)
 {
-	int i, j, k, counter, active_cu_number = 0;
+	int i, j, k, counter, xcc_id, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
 	unsigned disable_masks[4 * 4];
 
@@ -4309,46 +4309,38 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 				    adev->gfx.config.max_sh_per_se);
 
 	mutex_lock(&adev->grbm_idx_mutex);
-	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+	for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) {
-		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
-			mask = 1;
+			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-			ao_bitmap = 0;
+				mask = 1;
-			counter = 0;
+				ao_bitmap = 0;
-			gfx_v9_4_3_xcc_select_se_sh(adev, i, j, 0xffffffff, 0);
+				counter = 0;
-			gfx_v9_4_3_set_user_cu_inactive_bitmap(
+				gfx_v9_4_3_xcc_select_se_sh(adev, i, j, 0xffffffff, xcc_id);
-				adev, disable_masks[i * adev->gfx.config.max_sh_per_se + j]);
+				gfx_v9_4_3_set_user_cu_inactive_bitmap(
-			bitmap = gfx_v9_4_3_get_cu_active_bitmap(adev);
+					adev,
+					disable_masks[i * adev->gfx.config.max_sh_per_se + j],
+					xcc_id);
+				bitmap = gfx_v9_4_3_get_cu_active_bitmap(adev, xcc_id);
 
-			/*
+				cu_info->bitmap[xcc_id][i][j] = bitmap;
-			 * The bitmap(and ao_cu_bitmap) in cu_info structure is
-			 * 4x4 size array, and it's usually suitable for Vega
-			 * ASICs which has 4*2 SE/SH layout.
-			 * But for Arcturus, SE/SH layout is changed to 8*1.
-			 * To mostly reduce the impact, we make it compatible
-			 * with current bitmap array as below:
-			 *    SE4,SH0 --> bitmap[0][1]
-			 *    SE5,SH0 --> bitmap[1][1]
-			 *    SE6,SH0 --> bitmap[2][1]
-			 *    SE7,SH0 --> bitmap[3][1]
-			 */
-			cu_info->bitmap[i % 4][j + i / 4] = bitmap;
 
-			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
+				for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
-				if (bitmap & mask) {
+					if (bitmap & mask) {
-					if (counter < adev->gfx.config.max_cu_per_sh)
+						if (counter < adev->gfx.config.max_cu_per_sh)
-						ao_bitmap |= mask;
+							ao_bitmap |= mask;
-					counter++;
+						counter++;
+					}
+					mask <<= 1;
 				}
-				mask <<= 1;
+				active_cu_number += counter;
+				if (i < 2 && j < 2)
+					ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
+				cu_info->ao_cu_bitmap[i][j] = ao_bitmap;
 			}
-			active_cu_number += counter;
-			if (i < 2 && j < 2)
-				ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
-			cu_info->ao_cu_bitmap[i % 4][j + i / 4] = ao_bitmap;
 		}
+		gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
+					    xcc_id);
 	}
-	gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
-				    0);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	cu_info->number = active_cu_number;

drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c

@@ -345,6 +345,9 @@ static void nbio_v4_3_init_registers(struct amdgpu_device *adev)
 		data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK;
 		WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data);
 	}
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev)

drivers/gpu/drm/amd/amdgpu/soc21.c

@@ -766,7 +766,7 @@ static int soc21_common_hw_init(void *handle)
 	 * for the purpose of expose those registers
 	 * to process space
 	 */
-	if (adev->nbio.funcs->remap_hdp_registers)
+	if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
 		adev->nbio.funcs->remap_hdp_registers(adev);
 	/* enable the doorbell aperture */
 	adev->nbio.funcs->enable_doorbell_aperture(adev, true);

drivers/gpu/drm/amd/amdkfd/kfd_crat.c

@@ -2087,7 +2087,8 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 
 	amdgpu_amdkfd_get_cu_info(kdev->adev, &cu_info);
 	cu->num_simd_per_cu = cu_info.simd_per_cu;
-	cu->num_simd_cores = cu_info.simd_per_cu * cu_info.cu_active_number;
+	cu->num_simd_cores = cu_info.simd_per_cu *
+			(cu_info.cu_active_number / kdev->kfd->num_nodes);
 	cu->max_waves_simd = cu_info.max_waves_per_simd;
 
 	cu->wave_front_size = cu_info.wave_front_size;

drivers/gpu/drm/amd/amdkfd/kfd_crat.h

@@ -79,6 +79,10 @@ struct crat_header {
 #define CRAT_SUBTYPE_IOLINK_AFFINITY		5
 #define CRAT_SUBTYPE_MAX			6
 
+/*
+ * Do not change the value of CRAT_SIBLINGMAP_SIZE from 32
+ * as it breaks the ABI.
+ */
 #define CRAT_SIBLINGMAP_SIZE	32
 
 /*

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -1677,8 +1677,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 			dqm->dev->kfd2kgd->build_grace_period_packet_info(
 					dqm->dev->adev,	dqm->wait_times,
 					grace_period, &reg_offset,
-					&dqm->wait_times,
+					&dqm->wait_times);
-					ffs(dqm->dev->xcc_mask) - 1);
 	}
 
 	dqm_unlock(dqm);

drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c

@@ -162,6 +162,7 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 		return NULL;
 
 	*doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, kfd->doorbells, inx);
+	inx *= 2;
 
 	pr_debug("Get kernel queue doorbell\n"
 			"     doorbell offset   == 0x%08X\n"
@@ -176,6 +177,7 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 	unsigned int inx;
 
 	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx /= 2;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_bitmap);

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c

@@ -97,18 +97,22 @@ void free_mqd_hiq_sdma(struct mqd_manager *mm, void *mqd,
 
 void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		const uint32_t *cu_mask, uint32_t cu_mask_count,
-		uint32_t *se_mask)
+		uint32_t *se_mask, uint32_t inst)
 {
 	struct kfd_cu_info cu_info;
 	uint32_t cu_per_sh[KFD_MAX_NUM_SE][KFD_MAX_NUM_SH_PER_SE] = {0};
 	bool wgp_mode_req = KFD_GC_VERSION(mm->dev) >= IP_VERSION(10, 0, 0);
 	uint32_t en_mask = wgp_mode_req ? 0x3 : 0x1;
-	int i, se, sh, cu, cu_bitmap_sh_mul, inc = wgp_mode_req ? 2 : 1;
+	int i, se, sh, cu, cu_bitmap_sh_mul, cu_inc = wgp_mode_req ? 2 : 1;
+	uint32_t cu_active_per_node;
+	int inc = cu_inc * NUM_XCC(mm->dev->xcc_mask);
+	int xcc_inst = inst + ffs(mm->dev->xcc_mask) - 1;
 
 	amdgpu_amdkfd_get_cu_info(mm->dev->adev, &cu_info);
 
-	if (cu_mask_count > cu_info.cu_active_number)
+	cu_active_per_node = cu_info.cu_active_number / mm->dev->kfd->num_nodes;
-		cu_mask_count = cu_info.cu_active_number;
+	if (cu_mask_count > cu_active_per_node)
+		cu_mask_count = cu_active_per_node;
 
 	/* Exceeding these bounds corrupts the stack and indicates a coding error.
 	 * Returning with no CU's enabled will hang the queue, which should be
@@ -141,7 +145,8 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 	for (se = 0; se < cu_info.num_shader_engines; se++)
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
 			cu_per_sh[se][sh] = hweight32(
-				cu_info.cu_bitmap[se % 4][sh + (se / 4) * cu_bitmap_sh_mul]);
+				cu_info.cu_bitmap[xcc_inst][se % 4][sh + (se / 4) *
+				cu_bitmap_sh_mul]);
 
 	/* Symmetrically map cu_mask to all SEs & SHs:
 	 * se_mask programs up to 2 SH in the upper and lower 16 bits.
@@ -164,20 +169,33 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 	 * cu_mask[0] bit8 -> se_mask[0] bit1 (SE0,SH0,CU1)
 	 * ...
 	 *
+	 * For GFX 9.4.3, the following code only looks at a
+	 * subset of the cu_mask corresponding to the inst parameter.
+	 * If we have n XCCs under one GPU node
+	 * cu_mask[0] bit0 -> XCC0 se_mask[0] bit0 (XCC0,SE0,SH0,CU0)
+	 * cu_mask[0] bit1 -> XCC1 se_mask[0] bit0 (XCC1,SE0,SH0,CU0)
+	 * ..
+	 * cu_mask[0] bitn -> XCCn se_mask[0] bit0 (XCCn,SE0,SH0,CU0)
+	 * cu_mask[0] bit n+1 -> XCC0 se_mask[1] bit0 (XCC0,SE1,SH0,CU0)
+	 *
+	 * For example, if there are 6 XCCs under 1 KFD node, this code
+	 * running for each inst, will look at the bits as:
+	 * inst, inst + 6, inst + 12...
+	 *
 	 * First ensure all CUs are disabled, then enable user specified CUs.
 	 */
 	for (i = 0; i < cu_info.num_shader_engines; i++)
 		se_mask[i] = 0;
 
-	i = 0;
+	i = inst;
-	for (cu = 0; cu < 16; cu += inc) {
+	for (cu = 0; cu < 16; cu += cu_inc) {
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++) {
 			for (se = 0; se < cu_info.num_shader_engines; se++) {
 				if (cu_per_sh[se][sh] > cu) {
 					if (cu_mask[i / 32] & (en_mask << (i % 32)))
 						se_mask[se] |= en_mask << (cu + sh * 16);
 					i += inc;
-					if (i == cu_mask_count)
+					if (i >= cu_mask_count)
 						return;
 				}
 			}

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h

@@ -138,7 +138,7 @@ void free_mqd_hiq_sdma(struct mqd_manager *mm, void *mqd,
 
 void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		const uint32_t *cu_mask, uint32_t cu_mask_count,
-		uint32_t *se_mask);
+		uint32_t *se_mask, uint32_t inst);
 
 int kfd_hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
 		uint32_t pipe_id, uint32_t queue_id,

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c

@@ -52,7 +52,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c

@@ -52,7 +52,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c

@@ -71,7 +71,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 	}
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
 	m->compute_static_thread_mgmt_se1 = se_mask[1];
@@ -321,6 +321,43 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	return 0;
 }
 
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
+{
+	struct v11_compute_mqd *m;
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct v11_compute_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, const u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct v11_compute_mqd *m;
+
+	m = (struct v11_compute_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	m->cp_hqd_pq_doorbell_control =
+		qp->doorbell_off <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
+}
+
+
 static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -458,6 +495,8 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->mqd_size = sizeof(struct v11_compute_mqd);
 		mqd->get_wave_state = get_wave_state;
 		mqd->mqd_stride = kfd_mqd_stride;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
 #endif
@@ -502,6 +541,8 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd_sdma;
 		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
 		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 		mqd->mqd_size = sizeof(struct v11_sdma_mqd);
 		mqd->mqd_stride = kfd_mqd_stride;
 #if defined(CONFIG_DEBUG_FS)

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c

@@ -60,7 +60,7 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 }
 
 static void update_cu_mask(struct mqd_manager *mm, void *mqd,
-			struct mqd_update_info *minfo)
+			struct mqd_update_info *minfo, uint32_t inst)
 {
 	struct v9_mqd *m;
 	uint32_t se_mask[KFD_MAX_NUM_SE] = {0};
@@ -69,27 +69,36 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, inst);
 
 	m = get_mqd(mqd);
+
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
 	m->compute_static_thread_mgmt_se1 = se_mask[1];
 	m->compute_static_thread_mgmt_se2 = se_mask[2];
 	m->compute_static_thread_mgmt_se3 = se_mask[3];
-	m->compute_static_thread_mgmt_se4 = se_mask[4];
+	if (KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 4, 3)) {
-	m->compute_static_thread_mgmt_se5 = se_mask[5];
+		m->compute_static_thread_mgmt_se4 = se_mask[4];
-	m->compute_static_thread_mgmt_se6 = se_mask[6];
+		m->compute_static_thread_mgmt_se5 = se_mask[5];
-	m->compute_static_thread_mgmt_se7 = se_mask[7];
+		m->compute_static_thread_mgmt_se6 = se_mask[6];
+		m->compute_static_thread_mgmt_se7 = se_mask[7];
 
-	pr_debug("update cu mask to %#x %#x %#x %#x %#x %#x %#x %#x\n",
+		pr_debug("update cu mask to %#x %#x %#x %#x %#x %#x %#x %#x\n",
-		m->compute_static_thread_mgmt_se0,
+			m->compute_static_thread_mgmt_se0,
-		m->compute_static_thread_mgmt_se1,
+			m->compute_static_thread_mgmt_se1,
-		m->compute_static_thread_mgmt_se2,
+			m->compute_static_thread_mgmt_se2,
-		m->compute_static_thread_mgmt_se3,
+			m->compute_static_thread_mgmt_se3,
-		m->compute_static_thread_mgmt_se4,
+			m->compute_static_thread_mgmt_se4,
-		m->compute_static_thread_mgmt_se5,
+			m->compute_static_thread_mgmt_se5,
-		m->compute_static_thread_mgmt_se6,
+			m->compute_static_thread_mgmt_se6,
-		m->compute_static_thread_mgmt_se7);
+			m->compute_static_thread_mgmt_se7);
+	} else {
+		pr_debug("inst: %u, update cu mask to %#x %#x %#x %#x\n",
+			inst, m->compute_static_thread_mgmt_se0,
+			m->compute_static_thread_mgmt_se1,
+			m->compute_static_thread_mgmt_se2,
+			m->compute_static_thread_mgmt_se3);
+	}
 }
 
 static void set_priority(struct v9_mqd *m, struct queue_properties *q)
@@ -290,7 +299,8 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	if (mm->dev->kfd->cwsr_enabled && q->ctx_save_restore_area_address)
 		m->cp_hqd_ctx_save_control = 0;
 
-	update_cu_mask(mm, mqd, minfo);
+	if (KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 4, 3))
+		update_cu_mask(mm, mqd, minfo, 0);
 	set_priority(m, q);
 
 	q->is_active = QUEUE_IS_ACTIVE(*q);
@@ -676,6 +686,8 @@ static void update_mqd_v9_4_3(struct mqd_manager *mm, void *mqd,
 		m = get_mqd(mqd + size * xcc);
 		update_mqd(mm, m, q, minfo);
 
+		update_cu_mask(mm, mqd, minfo, xcc);
+
 		if (q->format == KFD_QUEUE_FORMAT_AQL) {
 			switch (xcc) {
 			case 0:

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c

@@ -55,7 +55,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c

@@ -299,8 +299,7 @@ static int pm_set_grace_period_v9(struct packet_manager *pm,
 			pm->dqm->wait_times,
 			grace_period,
 			&reg_offset,
-			&reg_data,
+			&reg_data);
-			0);
 
 	if (grace_period == USE_DEFAULT_GRACE_PERIOD)
 		reg_data = pm->dqm->wait_times;

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -1466,8 +1466,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type);
 
 static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
 {
-	return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3) ||
+	return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) ||
-	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
 	       (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
 	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
 }

drivers/gpu/drm/amd/amdkfd/kfd_topology.c

@@ -450,8 +450,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 	sysfs_show_32bit_prop(buffer, offs, "cpu_cores_count",
 			      dev->node_props.cpu_cores_count);
 	sysfs_show_32bit_prop(buffer, offs, "simd_count",
-			      dev->gpu ? (dev->node_props.simd_count *
+			      dev->gpu ? dev->node_props.simd_count : 0);
-					  NUM_XCC(dev->gpu->xcc_mask)) : 0);
 	sysfs_show_32bit_prop(buffer, offs, "mem_banks_count",
 			      dev->node_props.mem_banks_count);
 	sysfs_show_32bit_prop(buffer, offs, "caches_count",
@@ -1597,14 +1596,17 @@ static int fill_in_l1_pcache(struct kfd_cache_properties **props_ext,
 static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 				struct kfd_gpu_cache_info *pcache_info,
 				struct kfd_cu_info *cu_info,
-				int cache_type, unsigned int cu_processor_id)
+				int cache_type, unsigned int cu_processor_id,
+				struct kfd_node *knode)
 {
 	unsigned int cu_sibling_map_mask;
 	int first_active_cu;
-	int i, j, k;
+	int i, j, k, xcc, start, end;
 	struct kfd_cache_properties *pcache = NULL;
 
-	cu_sibling_map_mask = cu_info->cu_bitmap[0][0];
+	start = ffs(knode->xcc_mask) - 1;
+	end = start + NUM_XCC(knode->xcc_mask);
+	cu_sibling_map_mask = cu_info->cu_bitmap[start][0][0];
 	cu_sibling_map_mask &=
 		((1 << pcache_info[cache_type].num_cu_shared) - 1);
 	first_active_cu = ffs(cu_sibling_map_mask);
@@ -1639,16 +1641,18 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 		cu_sibling_map_mask = cu_sibling_map_mask >> (first_active_cu - 1);
 		k = 0;
 
-		for (i = 0; i < cu_info->num_shader_engines; i++) {
+		for (xcc = start; xcc < end; xcc++) {
-			for (j = 0; j < cu_info->num_shader_arrays_per_engine; j++) {
+			for (i = 0; i < cu_info->num_shader_engines; i++) {
-				pcache->sibling_map[k] = (uint8_t)(cu_sibling_map_mask & 0xFF);
+				for (j = 0; j < cu_info->num_shader_arrays_per_engine; j++) {
-				pcache->sibling_map[k+1] = (uint8_t)((cu_sibling_map_mask >> 8) & 0xFF);
+					pcache->sibling_map[k] = (uint8_t)(cu_sibling_map_mask & 0xFF);
-				pcache->sibling_map[k+2] = (uint8_t)((cu_sibling_map_mask >> 16) & 0xFF);
+					pcache->sibling_map[k+1] = (uint8_t)((cu_sibling_map_mask >> 8) & 0xFF);
-				pcache->sibling_map[k+3] = (uint8_t)((cu_sibling_map_mask >> 24) & 0xFF);
+					pcache->sibling_map[k+2] = (uint8_t)((cu_sibling_map_mask >> 16) & 0xFF);
-				k += 4;
+					pcache->sibling_map[k+3] = (uint8_t)((cu_sibling_map_mask >> 24) & 0xFF);
+					k += 4;
 
-				cu_sibling_map_mask = cu_info->cu_bitmap[i % 4][j + i / 4];
+					cu_sibling_map_mask = cu_info->cu_bitmap[xcc][i % 4][j + i / 4];
-				cu_sibling_map_mask &= ((1 << pcache_info[cache_type].num_cu_shared) - 1);
+					cu_sibling_map_mask &= ((1 << pcache_info[cache_type].num_cu_shared) - 1);
+				}
 			}
 		}
 		pcache->sibling_map_size = k;
@@ -1666,7 +1670,7 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 static void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct kfd_node *kdev)
 {
 	struct kfd_gpu_cache_info *pcache_info = NULL;
-	int i, j, k;
+	int i, j, k, xcc, start, end;
 	int ct = 0;
 	unsigned int cu_processor_id;
 	int ret;
@@ -1700,37 +1704,42 @@ static void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct
 	 *			then it will consider only one CU from
 	 *			the shared unit
 	 */
+	start = ffs(kdev->xcc_mask) - 1;
+	end = start + NUM_XCC(kdev->xcc_mask);
+
 	for (ct = 0; ct < num_of_cache_types; ct++) {
 		cu_processor_id = gpu_processor_id;
 		if (pcache_info[ct].cache_level == 1) {
-			for (i = 0; i < pcu_info->num_shader_engines; i++) {
+			for (xcc = start; xcc < end; xcc++) {
-				for (j = 0; j < pcu_info->num_shader_arrays_per_engine; j++) {
+				for (i = 0; i < pcu_info->num_shader_engines; i++) {
-					for (k = 0; k < pcu_info->num_cu_per_sh; k += pcache_info[ct].num_cu_shared) {
+					for (j = 0; j < pcu_info->num_shader_arrays_per_engine; j++) {
+						for (k = 0; k < pcu_info->num_cu_per_sh; k += pcache_info[ct].num_cu_shared) {
 
-						ret = fill_in_l1_pcache(&props_ext, pcache_info, pcu_info,
+							ret = fill_in_l1_pcache(&props_ext, pcache_info, pcu_info,
-										pcu_info->cu_bitmap[i % 4][j + i / 4], ct,
+										pcu_info->cu_bitmap[xcc][i % 4][j + i / 4], ct,
 										cu_processor_id, k);
 
-						if (ret < 0)
+							if (ret < 0)
-							break;
+								break;
 
-						if (!ret) {
+							if (!ret) {
-							num_of_entries++;
+								num_of_entries++;
-							list_add_tail(&props_ext->list, &dev->cache_props);
+								list_add_tail(&props_ext->list, &dev->cache_props);
+							}
+
+							/* Move to next CU block */
+							num_cu_shared = ((k + pcache_info[ct].num_cu_shared) <=
+								pcu_info->num_cu_per_sh) ?
+								pcache_info[ct].num_cu_shared :
+								(pcu_info->num_cu_per_sh - k);
+							cu_processor_id += num_cu_shared;
 						}
-
-						/* Move to next CU block */
-						num_cu_shared = ((k + pcache_info[ct].num_cu_shared) <=
-							pcu_info->num_cu_per_sh) ?
-							pcache_info[ct].num_cu_shared :
-							(pcu_info->num_cu_per_sh - k);
-						cu_processor_id += num_cu_shared;
 					}
 				}
 			}
 		} else {
 			ret = fill_in_l2_l3_pcache(&props_ext, pcache_info,
-								pcu_info, ct, cu_processor_id);
+					pcu_info, ct, cu_processor_id, kdev);
 
 			if (ret < 0)
 				break;

drivers/gpu/drm/amd/amdkfd/kfd_topology.h

@@ -89,7 +89,7 @@ struct kfd_mem_properties {
 	struct attribute	attr;
 };
 
-#define CACHE_SIBLINGMAP_SIZE 64
+#define CACHE_SIBLINGMAP_SIZE 128
 
 struct kfd_cache_properties {
 	struct list_head	list;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1274,11 +1274,15 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 
 	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
-	page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF;
+	page_table_start.high_part = upper_32_bits(adev->gmc.gart_start >>
-	page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12);
+						   AMDGPU_GPU_PAGE_SHIFT);
-	page_table_end.high_part = (u32)(adev->gmc.gart_end >> 44) & 0xF;
+	page_table_start.low_part = lower_32_bits(adev->gmc.gart_start >>
-	page_table_end.low_part = (u32)(adev->gmc.gart_end >> 12);
+						  AMDGPU_GPU_PAGE_SHIFT);
-	page_table_base.high_part = upper_32_bits(pt_base) & 0xF;
+	page_table_end.high_part = upper_32_bits(adev->gmc.gart_end >>
+						 AMDGPU_GPU_PAGE_SHIFT);
+	page_table_end.low_part = lower_32_bits(adev->gmc.gart_end >>
+						AMDGPU_GPU_PAGE_SHIFT);
+	page_table_base.high_part = upper_32_bits(pt_base);
 	page_table_base.low_part = lower_32_bits(pt_base);
 
 	pa_config->system_aperture.start_addr = (uint64_t)logical_addr_low << 18;
@@ -1640,8 +1644,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		}
 		break;
 	}
-	if (init_data.flags.gpu_vm_support)
+	if (init_data.flags.gpu_vm_support &&
-		init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev);
+	    (amdgpu_sg_display == 0))
+		init_data.flags.gpu_vm_support = false;
 
 	if (init_data.flags.gpu_vm_support)
 		adev->mode_info.gpu_vm_support = true;
@@ -2335,14 +2340,62 @@ static int dm_late_init(void *handle)
 	return detect_mst_link_for_all_connectors(adev_to_drm(adev));
 }
 
+static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr)
+{
+	int ret;
+	u8 guid[16];
+	u64 tmp64;
+
+	mutex_lock(&mgr->lock);
+	if (!mgr->mst_primary)
+		goto out_fail;
+
+	if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) {
+		drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+
+	ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
+				 DP_MST_EN |
+				 DP_UP_REQ_EN |
+				 DP_UPSTREAM_IS_SRC);
+	if (ret < 0) {
+		drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+
+	/* Some hubs forget their guids after they resume */
+	ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
+	if (ret != 16) {
+		drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+
+	if (memchr_inv(guid, 0, 16) == NULL) {
+		tmp64 = get_jiffies_64();
+		memcpy(&guid[0], &tmp64, sizeof(u64));
+		memcpy(&guid[8], &tmp64, sizeof(u64));
+
+		ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16);
+
+		if (ret != 16) {
+			drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n");
+			goto out_fail;
+		}
+	}
+
+	memcpy(mgr->mst_primary->guid, guid, 16);
+
+out_fail:
+	mutex_unlock(&mgr->lock);
+}
+
 static void s3_handle_mst(struct drm_device *dev, bool suspend)
 {
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	struct drm_dp_mst_topology_mgr *mgr;
-	int ret;
-	bool need_hotplug = false;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -2364,18 +2417,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend)
 			if (!dp_is_lttpr_present(aconnector->dc_link))
 				try_to_configure_aux_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD);
 
-			ret = drm_dp_mst_topology_mgr_resume(mgr, true);
+			/* TODO: move resume_mst_branch_status() into drm mst resume again
-			if (ret < 0) {
+			 * once topology probing work is pulled out from mst resume into mst
-				dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx,
+			 * resume 2nd step. mst resume 2nd step should be called after old
-					aconnector->dc_link);
+			 * state getting restored (i.e. drm_atomic_helper_resume()).
-				need_hotplug = true;
+			 */
-			}
+			resume_mst_branch_status(mgr);
 		}
 	}
 	drm_connector_list_iter_end(&iter);
-
-	if (need_hotplug)
-		drm_kms_helper_hotplug_event(dev);
 }
 
 static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev)
@@ -2769,7 +2819,8 @@ static int dm_resume(void *handle)
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state);
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	struct dc_state *dc_state;
-	int i, r, j;
+	int i, r, j, ret;
+	bool need_hotplug = false;
 
 	if (amdgpu_in_reset(adev)) {
 		dc_state = dm->cached_dc_state;
@@ -2867,7 +2918,7 @@ static int dm_resume(void *handle)
 			continue;
 
 		/*
-		 * this is the case when traversing through already created
+		 * this is the case when traversing through already created end sink
 		 * MST connectors, should be skipped
 		 */
 		if (aconnector && aconnector->mst_root)
@@ -2927,6 +2978,27 @@ static int dm_resume(void *handle)
 
 	dm->cached_state = NULL;
 
+	/* Do mst topology probing after resuming cached state*/
+	drm_connector_list_iter_begin(ddev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
+		aconnector = to_amdgpu_dm_connector(connector);
+		if (aconnector->dc_link->type != dc_connection_mst_branch ||
+		    aconnector->mst_root)
+			continue;
+
+		ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true);
+
+		if (ret < 0) {
+			dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx,
+					aconnector->dc_link);
+			need_hotplug = true;
+		}
+	}
+	drm_connector_list_iter_end(&iter);
+
+	if (need_hotplug)
+		drm_kms_helper_hotplug_event(ddev);
+
 	amdgpu_dm_irq_resume_late(adev);
 
 	amdgpu_dm_smu_write_watermarks_table(adev);
@@ -8073,7 +8145,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		bundle->surface_updates[planes_count].plane_info =
 			&bundle->plane_infos[planes_count];
 
-		if (acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
+		if (acrtc_state->stream->link->psr_settings.psr_feature_enabled ||
+		    acrtc_state->stream->link->replay_settings.replay_feature_enabled) {
 			fill_dc_dirty_rects(plane, old_plane_state,
 					    new_plane_state, new_crtc_state,
 					    &bundle->flip_addrs[planes_count],

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h

@@ -620,7 +620,7 @@ struct amdgpu_hdmi_vsdb_info {
 	unsigned int max_refresh_rate_hz;
 
 	/**
-	 * @replay mode: Replay supported
+	 * @replay_mode: Replay supported
 	 */
 	bool replay_mode;
 };

drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c

@@ -169,11 +169,23 @@ static void add_link_enc_assignment(
 /* Return first available DIG link encoder. */
 static enum engine_id find_first_avail_link_enc(
 		const struct dc_context *ctx,
-		const struct dc_state *state)
+		const struct dc_state *state,
+		enum engine_id eng_id_requested)
 {
 	enum engine_id eng_id = ENGINE_ID_UNKNOWN;
 	int i;
 
+	if (eng_id_requested != ENGINE_ID_UNKNOWN) {
+
+		for (i = 0; i < ctx->dc->res_pool->res_cap->num_dig_link_enc; i++) {
+			eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i];
+			if (eng_id == eng_id_requested)
+				return eng_id;
+		}
+	}
+
+	eng_id = ENGINE_ID_UNKNOWN;
+
 	for (i = 0; i < ctx->dc->res_pool->res_cap->num_dig_link_enc; i++) {
 		eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i];
 		if (eng_id != ENGINE_ID_UNKNOWN)
@@ -287,7 +299,7 @@ void link_enc_cfg_link_encs_assign(
 		struct dc_stream_state *streams[],
 		uint8_t stream_count)
 {
-	enum engine_id eng_id = ENGINE_ID_UNKNOWN;
+	enum engine_id eng_id = ENGINE_ID_UNKNOWN, eng_id_req = ENGINE_ID_UNKNOWN;
 	int i;
 	int j;
 
@@ -377,8 +389,14 @@ void link_enc_cfg_link_encs_assign(
 		 * assigned to that endpoint.
 		 */
 		link_enc = get_link_enc_used_by_link(state, stream->link);
-		if (link_enc == NULL)
+		if (link_enc == NULL) {
-			eng_id = find_first_avail_link_enc(stream->ctx, state);
+
+			if (stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA &&
+					stream->link->dpia_preferred_eng_id != ENGINE_ID_UNKNOWN)
+				eng_id_req = stream->link->dpia_preferred_eng_id;
+
+			eng_id = find_first_avail_link_enc(stream->ctx, state, eng_id_req);
+		}
 		else
 			eng_id =  link_enc->preferred_engine;
 
@@ -402,7 +420,9 @@ void link_enc_cfg_link_encs_assign(
 			DC_LOG_DEBUG("%s: CUR %s(%d) - enc_id(%d)\n",
 					__func__,
 					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ? "PHY" : "DPIA",
-					assignment.ep_id.link_id.enum_id - 1,
+					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ?
+							assignment.ep_id.link_id.enum_id :
+							assignment.ep_id.link_id.enum_id - 1,
 					assignment.eng_id);
 	}
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -413,7 +433,9 @@ void link_enc_cfg_link_encs_assign(
 			DC_LOG_DEBUG("%s: NEW %s(%d) - enc_id(%d)\n",
 					__func__,
 					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ? "PHY" : "DPIA",
-					assignment.ep_id.link_id.enum_id - 1,
+					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ?
+							assignment.ep_id.link_id.enum_id :
+							assignment.ep_id.link_id.enum_id - 1,
 					assignment.eng_id);
 	}
 
@@ -478,7 +500,6 @@ struct dc_link *link_enc_cfg_get_link_using_link_enc(
 	if (stream)
 		link = stream->link;
 
-	// dm_output_to_console("%s: No link using DIG(%d).\n", __func__, eng_id);
 	return link;
 }
 

drivers/gpu/drm/amd/display/dc/dc.h

@@ -1496,6 +1496,7 @@ struct dc_link {
 	 * object creation.
 	 */
 	enum engine_id eng_id;
+	enum engine_id dpia_preferred_eng_id;
 
 	bool test_pattern_enabled;
 	enum dp_test_pattern current_test_pattern;

drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c

@@ -964,7 +964,9 @@ void dce110_edp_backlight_control(
 		return;
 	}
 
-	if (link->panel_cntl) {
+	if (link->panel_cntl && !(link->dpcd_sink_ext_caps.bits.oled ||
+		link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 ||
+		link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) {
 		bool is_backlight_on = link->panel_cntl->funcs->is_panel_backlight_on(link->panel_cntl);
 
 		if ((enable && is_backlight_on) || (!enable && !is_backlight_on)) {

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c

@@ -1032,6 +1032,28 @@ static const struct dce_i2c_mask i2c_masks = {
 		I2C_COMMON_MASK_SH_LIST_DCN30(_MASK)
 };
 
+/* ========================================================== */
+
+/*
+ * DPIA index | Preferred Encoder     |    Host Router
+ *   0        |      C                |       0
+ *   1        |      First Available  |       0
+ *   2        |      D                |       1
+ *   3        |      First Available  |       1
+ */
+/* ========================================================== */
+static const enum engine_id dpia_to_preferred_enc_id_table[] = {
+		ENGINE_ID_DIGC,
+		ENGINE_ID_DIGC,
+		ENGINE_ID_DIGD,
+		ENGINE_ID_DIGD
+};
+
+static enum engine_id dcn314_get_preferred_eng_id_dpia(unsigned int dpia_index)
+{
+	return dpia_to_preferred_enc_id_table[dpia_index];
+}
+
 static struct dce_i2c_hw *dcn31_i2c_hw_create(
 	struct dc_context *ctx,
 	uint32_t inst)
@@ -1785,6 +1807,7 @@ static struct resource_funcs dcn314_res_pool_funcs = {
 	.update_bw_bounding_box = dcn314_update_bw_bounding_box,
 	.patch_unknown_plane_state = dcn20_patch_unknown_plane_state,
 	.get_panel_config_defaults = dcn314_get_panel_config_defaults,
+	.get_preferred_eng_id_dpia = dcn314_get_preferred_eng_id_dpia,
 };
 
 static struct clock_source *dcn30_clock_source_create(

drivers/gpu/drm/amd/display/dc/inc/core_types.h

@@ -65,6 +65,7 @@ struct resource_context;
 struct clk_bw_params;
 
 struct resource_funcs {
+	enum engine_id (*get_preferred_eng_id_dpia)(unsigned int dpia_index);
 	void (*destroy)(struct resource_pool **pool);
 	void (*link_init)(struct dc_link *link);
 	struct panel_cntl*(*panel_cntl_create)(

drivers/gpu/drm/amd/display/dc/link/link_factory.c

@@ -791,6 +791,10 @@ static bool construct_dpia(struct dc_link *link,
 	/* Set dpia port index : 0 to number of dpia ports */
 	link->ddc_hw_inst = init_params->connector_index;
 
+	// Assign Dpia preferred eng_id
+	if (link->dc->res_pool->funcs->get_preferred_eng_id_dpia)
+		link->dpia_preferred_eng_id = link->dc->res_pool->funcs->get_preferred_eng_id_dpia(link->ddc_hw_inst);
+
 	/* TODO: Create link encoder */
 
 	link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED;

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

@@ -31,12 +31,12 @@
 #include <linux/types.h>
 #include <linux/bitmap.h>
 #include <linux/dma-fence.h>
+#include "amdgpu_irq.h"
+#include "amdgpu_gfx.h"
 
 struct pci_dev;
 struct amdgpu_device;
 
-#define KGD_MAX_QUEUES 128
-
 struct kfd_dev;
 struct kgd_mem;
 
@@ -68,7 +68,7 @@ struct kfd_cu_info {
 	uint32_t wave_front_size;
 	uint32_t max_scratch_slots_per_cu;
 	uint32_t lds_size;
-	uint32_t cu_bitmap[4][4];
+	uint32_t cu_bitmap[AMDGPU_MAX_GC_INSTANCES][4][4];
 };
 
 /* For getting GPU local memory information from KGD */
@@ -326,8 +326,7 @@ struct kfd2kgd_calls {
 			uint32_t wait_times,
 			uint32_t grace_period,
 			uint32_t *reg_offset,
-			uint32_t *reg_data,
+			uint32_t *reg_data);
-			uint32_t inst);
 	void (*get_cu_occupancy)(struct amdgpu_device *adev, int pasid,
 			int *wave_cnt, int *max_waves_per_cu, uint32_t inst);
 	void (*program_trap_handler_settings)(struct amdgpu_device *adev,

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c

@@ -336,7 +336,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 
 	/* Store one-time values in driver PPTable */
 	if (!pptable->Init) {
-		while (retry--) {
+		while (--retry) {
 			ret = smu_v13_0_6_get_metrics_table(smu, NULL, true);
 			if (ret)
 				return ret;

drivers/gpu/drm/drm_connector.c

@@ -2203,6 +2203,7 @@ static int drm_mode_create_colorspace_property(struct drm_connector *connector,
 /**
  * drm_mode_create_hdmi_colorspace_property - create hdmi colorspace property
  * @connector: connector to create the Colorspace property on.
+ * @supported_colorspaces: bitmap of supported color spaces
  *
  * Called by a driver the first time it's needed, must be attached to desired
  * HDMI connectors.
@@ -2227,6 +2228,7 @@ EXPORT_SYMBOL(drm_mode_create_hdmi_colorspace_property);
 /**
  * drm_mode_create_dp_colorspace_property - create dp colorspace property
  * @connector: connector to create the Colorspace property on.
+ * @supported_colorspaces: bitmap of supported color spaces
  *
  * Called by a driver the first time it's needed, must be attached to desired
  * DP connectors.

drivers/gpu/drm/drm_exec.c

@@ -56,7 +56,7 @@ static void drm_exec_unlock_all(struct drm_exec *exec)
 	struct drm_gem_object *obj;
 	unsigned long index;
 
-	drm_exec_for_each_locked_object(exec, index, obj) {
+	drm_exec_for_each_locked_object_reverse(exec, index, obj) {
 		dma_resv_unlock(obj->resv);
 		drm_gem_object_put(obj);
 	}

drivers/gpu/drm/i915/display/intel_bios.c

@@ -3540,6 +3540,27 @@ enum aux_ch intel_bios_dp_aux_ch(const struct intel_bios_encoder_data *devdata)
 	return map_aux_ch(devdata->i915, devdata->child.aux_channel);
 }
 
+bool intel_bios_dp_has_shared_aux_ch(const struct intel_bios_encoder_data *devdata)
+{
+	struct drm_i915_private *i915;
+	u8 aux_channel;
+	int count = 0;
+
+	if (!devdata || !devdata->child.aux_channel)
+		return false;
+
+	i915 = devdata->i915;
+	aux_channel = devdata->child.aux_channel;
+
+	list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) {
+		if (intel_bios_encoder_supports_dp(devdata) &&
+		    aux_channel == devdata->child.aux_channel)
+			count++;
+	}
+
+	return count > 1;
+}
+
 int intel_bios_dp_boost_level(const struct intel_bios_encoder_data *devdata)
 {
 	if (!devdata || devdata->i915->display.vbt.version < 196 || !devdata->child.iboost)

drivers/gpu/drm/i915/display/intel_bios.h

@@ -273,6 +273,7 @@ enum aux_ch intel_bios_dp_aux_ch(const struct intel_bios_encoder_data *devdata);
 int intel_bios_dp_boost_level(const struct intel_bios_encoder_data *devdata);
 int intel_bios_dp_max_lane_count(const struct intel_bios_encoder_data *devdata);
 int intel_bios_dp_max_link_rate(const struct intel_bios_encoder_data *devdata);
+bool intel_bios_dp_has_shared_aux_ch(const struct intel_bios_encoder_data *devdata);
 int intel_bios_hdmi_boost_level(const struct intel_bios_encoder_data *devdata);
 int intel_bios_hdmi_ddc_pin(const struct intel_bios_encoder_data *devdata);
 int intel_bios_hdmi_level_shift(const struct intel_bios_encoder_data *devdata);

drivers/gpu/drm/i915/display/intel_dp.c

@@ -5512,8 +5512,13 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	/*
 	 * VBT and straps are liars. Also check HPD as that seems
 	 * to be the most reliable piece of information available.
+	 *
+	 * ... expect on devices that forgot to hook HPD up for eDP
+	 * (eg. Acer Chromebook C710), so we'll check it only if multiple
+	 * ports are attempting to use the same AUX CH, according to VBT.
 	 */
-	if (!intel_digital_port_connected(encoder)) {
+	if (intel_bios_dp_has_shared_aux_ch(encoder->devdata) &&
+	    !intel_digital_port_connected(encoder)) {
 		/*
 		 * If this fails, presume the DPCD answer came
 		 * from some other port using the same AUX CH.