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>

6 files changed, 76 insertions, 27 deletions

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