Merge tag 'io_uring-6.5-2023-07-21' of git://git.kernel.dk/linux

Pull io_uring fixes from Jens Axboe:

 - Fix for io-wq not always honoring REQ_F_NOWAIT, if it was set and
   punted directly (eg via DRAIN) (me)

 - Capability check fix (Ondrej)

 - Regression fix for the mmap changes that went into 6.4, which
   apparently broke IA64 (Helge)

* tag 'io_uring-6.5-2023-07-21' of git://git.kernel.dk/linux:
  ia64: mmap: Consider pgoff when searching for free mapping
  io_uring: Fix io_uring mmap() by using architecture-provided get_unmapped_area()
  io_uring: treat -EAGAIN for REQ_F_NOWAIT as final for io-wq
  io_uring: don't audit the capability check in io_uring_create()

1 files changed, 26 insertions, 26 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 7505de2428e0..89a611541bc4 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1948,6 +1948,14 @@ fail:
 		ret = io_issue_sqe(req, issue_flags);
 		if (ret != -EAGAIN)
 			break;
+
+		/*
+		 * If REQ_F_NOWAIT is set, then don't wait or retry with
+		 * poll. -EAGAIN is final for that case.
+		 */
+		if (req->flags & REQ_F_NOWAIT)
+			break;
+
 		/*
 		 * We can get EAGAIN for iopolled IO even though we're
 		 * forcing a sync submission from here, since we can't
@@ -3429,8 +3437,6 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp,
 			unsigned long addr, unsigned long len,
 			unsigned long pgoff, unsigned long flags)
 {
-	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
-	struct vm_unmapped_area_info info;
 	void *ptr;
 
 	/*
@@ -3445,32 +3451,26 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp,
 	if (IS_ERR(ptr))
 		return -ENOMEM;
 
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
-	info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
+	/*
+	 * Some architectures have strong cache aliasing requirements.
+	 * For such architectures we need a coherent mapping which aliases
+	 * kernel memory *and* userspace memory. To achieve that:
+	 * - use a NULL file pointer to reference physical memory, and
+	 * - use the kernel virtual address of the shared io_uring context
+	 *   (instead of the userspace-provided address, which has to be 0UL
+	 *   anyway).
+	 * For architectures without such aliasing requirements, the
+	 * architecture will return any suitable mapping because addr is 0.
+	 */
+	filp = NULL;
+	flags |= MAP_SHARED;
+	pgoff = 0;	/* has been translated to ptr above */
 #ifdef SHM_COLOUR
-	info.align_mask = PAGE_MASK & (SHM_COLOUR - 1UL);
+	addr = (uintptr_t) ptr;
 #else
-	info.align_mask = PAGE_MASK & (SHMLBA - 1UL);
+	addr = 0UL;
 #endif
-	info.align_offset = (unsigned long) ptr;
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	addr = vm_unmapped_area(&info);
-	if (offset_in_page(addr)) {
-		info.flags = 0;
-		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = mmap_end;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
+	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
 }
 
 #else /* !CONFIG_MMU */
@@ -3870,7 +3870,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 		ctx->syscall_iopoll = 1;
 
 	ctx->compat = in_compat_syscall();
-	if (!capable(CAP_IPC_LOCK))
+	if (!ns_capable_noaudit(&init_user_ns, CAP_IPC_LOCK))
 		ctx->user = get_uid(current_user());
 
 	/*