Merge branch 'devx-async' into k.o/for-next

Yishai Hadas says:

Enable DEVX asynchronous query commands

This series enables querying a DEVX object in an asynchronous mode.

The userspace application won't block when calling the firmware and it will be
able to get the response back once that it will be ready.

To enable the above functionality:

- DEVX asynchronous command completion FD object was introduced.
- The applicable file operations were implemented to enable using it by
  the user application.
- Query asynchronous method was added to the DEVX object, it will call the
  firmware asynchronously and manages the response on the given input FD.
- Hot unplug support was added for the FD to work properly upon
  unbind/disassociate.
- mlx5 core fence for asynchronous commands was implemented and used to
  prevent racing upon unbind/disassociate.

This branch is based on mlx5-next & v5.0-rc2 due to dependencies, from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

* branch 'devx-async':
  IB/mlx5: Implement DEVX hot unplug for async command FD
  IB/mlx5: Implement the file ops of DEVX async command FD
  IB/mlx5: Introduce async DEVX obj query API
  IB/mlx5: Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

12 files changed, 117 insertions, 41 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index e0d7d61779a6..feeeaa60697c 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -28,11 +28,13 @@ config RISCV
 	select GENERIC_STRNLEN_USER
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A
+	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_PERF_EVENTS
+	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
 	select RISCV_ISA_A if SMP
 	select SPARSE_IRQ
@@ -40,6 +42,7 @@ config RISCV
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_PCI
 	select MODULES_USE_ELF_RELA if MODULES
+	select MODULE_SECTIONS if MODULES
 	select THREAD_INFO_IN_TASK
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_MSI if PCI
@@ -152,7 +155,6 @@ choice
 		bool "2GiB"
 	config MAXPHYSMEM_128GB
 		depends on 64BIT && CMODEL_MEDANY
-		select MODULE_SECTIONS if MODULES
 		bool "128GiB"
 endchoice
 
diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h
index cd2af4b013e3..46202dad365d 100644
--- a/arch/riscv/include/asm/module.h
+++ b/arch/riscv/include/asm/module.h
@@ -9,12 +9,12 @@
 #define MODULE_ARCH_VERMAGIC    "riscv"
 
 struct module;
-u64 module_emit_got_entry(struct module *mod, u64 val);
-u64 module_emit_plt_entry(struct module *mod, u64 val);
+unsigned long module_emit_got_entry(struct module *mod, unsigned long val);
+unsigned long module_emit_plt_entry(struct module *mod, unsigned long val);
 
 #ifdef CONFIG_MODULE_SECTIONS
 struct mod_section {
-	struct elf64_shdr *shdr;
+	Elf_Shdr *shdr;
 	int num_entries;
 	int max_entries;
 };
@@ -26,18 +26,18 @@ struct mod_arch_specific {
 };
 
 struct got_entry {
-	u64 symbol_addr;	/* the real variable address */
+	unsigned long symbol_addr;	/* the real variable address */
 };
 
-static inline struct got_entry emit_got_entry(u64 val)
+static inline struct got_entry emit_got_entry(unsigned long val)
 {
 	return (struct got_entry) {val};
 }
 
-static inline struct got_entry *get_got_entry(u64 val,
+static inline struct got_entry *get_got_entry(unsigned long val,
 					      const struct mod_section *sec)
 {
-	struct got_entry *got = (struct got_entry *)sec->shdr->sh_addr;
+	struct got_entry *got = (struct got_entry *)(sec->shdr->sh_addr);
 	int i;
 	for (i = 0; i < sec->num_entries; i++) {
 		if (got[i].symbol_addr == val)
@@ -62,7 +62,9 @@ struct plt_entry {
 #define REG_T0     0x5
 #define REG_T1     0x6
 
-static inline struct plt_entry emit_plt_entry(u64 val, u64 plt, u64 got_plt)
+static inline struct plt_entry emit_plt_entry(unsigned long val,
+					      unsigned long plt,
+					      unsigned long got_plt)
 {
 	/*
 	 * U-Type encoding:
@@ -76,7 +78,7 @@ static inline struct plt_entry emit_plt_entry(u64 val, u64 plt, u64 got_plt)
 	 * +------------+------------+--------+----------+----------+
 	 *
 	 */
-	u64 offset = got_plt - plt;
+	unsigned long offset = got_plt - plt;
 	u32 hi20 = (offset + 0x800) & 0xfffff000;
 	u32 lo12 = (offset - hi20);
 	return (struct plt_entry) {
@@ -86,7 +88,7 @@ static inline struct plt_entry emit_plt_entry(u64 val, u64 plt, u64 got_plt)
 	};
 }
 
-static inline int get_got_plt_idx(u64 val, const struct mod_section *sec)
+static inline int get_got_plt_idx(unsigned long val, const struct mod_section *sec)
 {
 	struct got_entry *got_plt = (struct got_entry *)sec->shdr->sh_addr;
 	int i;
@@ -97,9 +99,9 @@ static inline int get_got_plt_idx(u64 val, const struct mod_section *sec)
 	return -1;
 }
 
-static inline struct plt_entry *get_plt_entry(u64 val,
-				      const struct mod_section *sec_plt,
-				      const struct mod_section *sec_got_plt)
+static inline struct plt_entry *get_plt_entry(unsigned long val,
+					      const struct mod_section *sec_plt,
+					      const struct mod_section *sec_got_plt)
 {
 	struct plt_entry *plt = (struct plt_entry *)sec_plt->shdr->sh_addr;
 	int got_plt_idx = get_got_plt_idx(val, sec_got_plt);
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index bbe1862e8f80..d35ec2f41381 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -113,6 +113,11 @@ static inline void frame_pointer_set(struct pt_regs *regs,
 	SET_FP(regs, val);
 }
 
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	return regs->a0;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 8d25f8904c00..bba3da6ef157 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -18,6 +18,7 @@
 #ifndef _ASM_RISCV_SYSCALL_H
 #define _ASM_RISCV_SYSCALL_H
 
+#include <uapi/linux/audit.h>
 #include <linux/sched.h>
 #include <linux/err.h>
 
@@ -99,4 +100,13 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
 }
 
+static inline int syscall_get_arch(void)
+{
+#ifdef CONFIG_64BIT
+	return AUDIT_ARCH_RISCV64;
+#else
+	return AUDIT_ARCH_RISCV32;
+#endif
+}
+
 #endif	/* _ASM_RISCV_SYSCALL_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index f8fa1cd2dad9..1c9cc8389928 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -80,13 +80,19 @@ struct thread_info {
 #define TIF_RESTORE_SIGMASK	4	/* restore signal mask in do_signal() */
 #define TIF_MEMDIE		5	/* is terminating due to OOM killer */
 #define TIF_SYSCALL_TRACEPOINT  6       /* syscall tracepoint instrumentation */
+#define TIF_SYSCALL_AUDIT	7	/* syscall auditing */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 
 #define _TIF_WORK_MASK \
 	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED)
 
+#define _TIF_SYSCALL_WORK \
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+
 #endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
index fef96f117b4d..073ee80fdf74 100644
--- a/arch/riscv/include/asm/unistd.h
+++ b/arch/riscv/include/asm/unistd.h
@@ -19,3 +19,5 @@
 #define __ARCH_WANT_SYS_CLONE
 
 #include <uapi/asm/unistd.h>
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 13d4826ab2a1..355166f57205 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -201,7 +201,7 @@ handle_syscall:
 	REG_S s2, PT_SEPC(sp)
 	/* Trace syscalls, but only if requested by the user. */
 	REG_L t0, TASK_TI_FLAGS(tp)
-	andi t0, t0, _TIF_SYSCALL_TRACE
+	andi t0, t0, _TIF_SYSCALL_WORK
 	bnez t0, handle_syscall_trace_enter
 check_syscall_nr:
 	/* Check to make sure we don't jump to a bogus syscall number. */
@@ -221,7 +221,7 @@ ret_from_syscall:
 	REG_S a0, PT_A0(sp)
 	/* Trace syscalls, but only if requested by the user. */
 	REG_L t0, TASK_TI_FLAGS(tp)
-	andi t0, t0, _TIF_SYSCALL_TRACE
+	andi t0, t0, _TIF_SYSCALL_WORK
 	bnez t0, handle_syscall_trace_exit
 
 ret_from_exception:
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index bbbd26e19bfd..c9ae48333114 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -9,14 +9,14 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-u64 module_emit_got_entry(struct module *mod, u64 val)
+unsigned long module_emit_got_entry(struct module *mod, unsigned long val)
 {
 	struct mod_section *got_sec = &mod->arch.got;
 	int i = got_sec->num_entries;
 	struct got_entry *got = get_got_entry(val, got_sec);
 
 	if (got)
-		return (u64)got;
+		return (unsigned long)got;
 
 	/* There is no duplicate entry, create a new one */
 	got = (struct got_entry *)got_sec->shdr->sh_addr;
@@ -25,10 +25,10 @@ u64 module_emit_got_entry(struct module *mod, u64 val)
 	got_sec->num_entries++;
 	BUG_ON(got_sec->num_entries > got_sec->max_entries);
 
-	return (u64)&got[i];
+	return (unsigned long)&got[i];
 }
 
-u64 module_emit_plt_entry(struct module *mod, u64 val)
+unsigned long module_emit_plt_entry(struct module *mod, unsigned long val)
 {
 	struct mod_section *got_plt_sec = &mod->arch.got_plt;
 	struct got_entry *got_plt;
@@ -37,27 +37,29 @@ u64 module_emit_plt_entry(struct module *mod, u64 val)
 	int i = plt_sec->num_entries;
 
 	if (plt)
-		return (u64)plt;
+		return (unsigned long)plt;
 
 	/* There is no duplicate entry, create a new one */
 	got_plt = (struct got_entry *)got_plt_sec->shdr->sh_addr;
 	got_plt[i] = emit_got_entry(val);
 	plt = (struct plt_entry *)plt_sec->shdr->sh_addr;
-	plt[i] = emit_plt_entry(val, (u64)&plt[i], (u64)&got_plt[i]);
+	plt[i] = emit_plt_entry(val,
+				(unsigned long)&plt[i],
+				(unsigned long)&got_plt[i]);
 
 	plt_sec->num_entries++;
 	got_plt_sec->num_entries++;
 	BUG_ON(plt_sec->num_entries > plt_sec->max_entries);
 
-	return (u64)&plt[i];
+	return (unsigned long)&plt[i];
 }
 
-static int is_rela_equal(const Elf64_Rela *x, const Elf64_Rela *y)
+static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
 {
 	return x->r_info == y->r_info && x->r_addend == y->r_addend;
 }
 
-static bool duplicate_rela(const Elf64_Rela *rela, int idx)
+static bool duplicate_rela(const Elf_Rela *rela, int idx)
 {
 	int i;
 	for (i = 0; i < idx; i++) {
@@ -67,13 +69,13 @@ static bool duplicate_rela(const Elf64_Rela *rela, int idx)
 	return false;
 }
 
-static void count_max_entries(Elf64_Rela *relas, int num,
+static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
 	unsigned int type, i;
 
 	for (i = 0; i < num; i++) {
-		type = ELF64_R_TYPE(relas[i].r_info);
+		type = ELF_RISCV_R_TYPE(relas[i].r_info);
 		if (type == R_RISCV_CALL_PLT) {
 			if (!duplicate_rela(relas, i))
 				(*plts)++;
@@ -118,9 +120,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 
 	/* Calculate the maxinum number of entries */
 	for (i = 0; i < ehdr->e_shnum; i++) {
-		Elf64_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset;
-		int num_rela = sechdrs[i].sh_size / sizeof(Elf64_Rela);
-		Elf64_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info;
+		Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset;
+		int num_rela = sechdrs[i].sh_size / sizeof(Elf_Rela);
+		Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info;
 
 		if (sechdrs[i].sh_type != SHT_RELA)
 			continue;
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 60f1e02eed36..2ae5e0284f56 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -18,12 +18,15 @@
 #include <asm/ptrace.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
+#include <linux/audit.h>
 #include <linux/ptrace.h>
 #include <linux/elf.h>
 #include <linux/regset.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/tracehook.h>
+
+#define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
 enum riscv_regset {
@@ -163,15 +166,19 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, syscall_get_nr(current, regs));
 #endif
+
+	audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
 }
 
 void do_syscall_trace_exit(struct pt_regs *regs)
 {
+	audit_syscall_exit(regs);
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
 
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
-		trace_sys_exit(regs, regs->regs[0]);
+		trace_sys_exit(regs, regs_return_value(regs));
 #endif
 }
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index fc8006a042eb..6e079e94b638 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -149,7 +149,14 @@ asmlinkage void __init setup_vm(void)
 
 void __init parse_dtb(unsigned int hartid, void *dtb)
 {
-	early_init_dt_scan(__va(dtb));
+	if (!early_init_dt_scan(__va(dtb)))
+		return;
+
+	pr_err("No DTB passed to the kernel\n");
+#ifdef CONFIG_CMDLINE_FORCE
+	strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+	pr_info("Forcing kernel command line to: %s\n", boot_command_line);
+#endif
 }
 
 static void __init setup_bootmem(void)
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 57b1383e5ef7..246635eac7bb 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -23,6 +23,7 @@
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
+#include <linux/delay.h>
 
 #include <asm/sbi.h>
 #include <asm/tlbflush.h>
@@ -31,6 +32,7 @@
 enum ipi_message_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
 	IPI_MAX
 };
 
@@ -66,6 +68,13 @@ int setup_profiling_timer(unsigned int multiplier)
 	return -EINVAL;
 }
 
+static void ipi_stop(void)
+{
+	set_cpu_online(smp_processor_id(), false);
+	while (1)
+		wait_for_interrupt();
+}
+
 void riscv_software_interrupt(void)
 {
 	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
@@ -94,6 +103,11 @@ void riscv_software_interrupt(void)
 			generic_smp_call_function_interrupt();
 		}
 
+		if (ops & (1 << IPI_CPU_STOP)) {
+			stats[IPI_CPU_STOP]++;
+			ipi_stop();
+		}
+
 		BUG_ON((ops >> IPI_MAX) != 0);
 
 		/* Order data access and bit testing. */
@@ -121,6 +135,7 @@ send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 static const char * const ipi_names[] = {
 	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
 	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_CPU_STOP]		= "CPU stop interrupts",
 };
 
 void show_ipi_stats(struct seq_file *p, int prec)
@@ -146,15 +161,29 @@ void arch_send_call_function_single_ipi(int cpu)
 	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
-static void ipi_stop(void *unused)
-{
-	while (1)
-		wait_for_interrupt();
-}
-
 void smp_send_stop(void)
 {
-	on_each_cpu(ipi_stop, NULL, 1);
+	unsigned long timeout;
+
+	if (num_online_cpus() > 1) {
+		cpumask_t mask;
+
+		cpumask_copy(&mask, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &mask);
+
+		if (system_state <= SYSTEM_RUNNING)
+			pr_crit("SMP: stopping secondary CPUs\n");
+		send_ipi_message(&mask, IPI_CPU_STOP);
+	}
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while (num_online_cpus() > 1 && timeout--)
+		udelay(1);
+
+	if (num_online_cpus() > 1)
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			   cpumask_pr_args(cpu_online_mask));
 }
 
 void smp_send_reschedule(int cpu)
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 65df1dfdc303..1e1395d63dab 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -18,6 +18,8 @@
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 
+#define MAX_BYTES_PER_LONG	0x10
+
 OUTPUT_ARCH(riscv)
 ENTRY(_start)
 
@@ -74,8 +76,6 @@ SECTIONS
 		*(.sbss*)
 	}
 
-	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
-
 	EXCEPTION_TABLE(0x10)
 	NOTES
 
@@ -83,6 +83,10 @@ SECTIONS
 		*(.rel.dyn*)
 	}
 
+	BSS_SECTION(MAX_BYTES_PER_LONG,
+		    MAX_BYTES_PER_LONG,
+		    MAX_BYTES_PER_LONG)
+
 	_end = .;
 
 	STABS_DEBUG