Merge tag 'v5.18' into rdma.git for-next

Following patches have dependencies.

Resolve the merge conflict in
drivers/net/ethernet/mellanox/mlx5/core/main.c by keeping the new names
for the fs functions following linux-next:

https://lore.kernel.org/r/20220519113529.226bc3e2@canb.auug.org.au/

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

5 files changed, 54 insertions, 18 deletions

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 55caeee37c08..b66dd6f775a4 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -809,6 +809,10 @@ __start_interrupts:
  * - MSR_EE|MSR_RI is clear (no reentrant exceptions)
  * - Standard kernel environment is set up (stack, paca, etc)
  *
+ * KVM:
+ * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM
+ * ensures that FSCR[SCV] is disabled whenever it has to force AIL off.
+ *
  * Call convention:
  *
  * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 40a583e9d3c7..97a76a8619fb 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -101,7 +101,7 @@ __module_alloc(unsigned long size, unsigned long start, unsigned long end, bool
 	 * too.
 	 */
 	return __vmalloc_node_range(size, 1, start, end, gfp, prot,
-				    VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP,
+				    VM_FLUSH_RESET_PERMS,
 				    NUMA_NO_NODE, __builtin_return_address(0));
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e547066a06aa..a96f05063bc9 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -196,6 +196,34 @@ static void __init configure_exceptions(void)
 
 	/* Under a PAPR hypervisor, we need hypercalls */
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		/*
+		 * - PR KVM does not support AIL mode interrupts in the host
+		 *   while a PR guest is running.
+		 *
+		 * - SCV system call interrupt vectors are only implemented for
+		 *   AIL mode interrupts.
+		 *
+		 * - On pseries, AIL mode can only be enabled and disabled
+		 *   system-wide so when a PR VM is created on a pseries host,
+		 *   all CPUs of the host are set to AIL=0 mode.
+		 *
+		 * - Therefore host CPUs must not execute scv while a PR VM
+		 *   exists.
+		 *
+		 * - SCV support can not be disabled dynamically because the
+		 *   feature is advertised to host userspace. Disabling the
+		 *   facility and emulating it would be possible but is not
+		 *   implemented.
+		 *
+		 * - So SCV support is blanket disabled if PR KVM could possibly
+		 *   run. That is, PR support compiled in, booting on pseries
+		 *   with hash MMU.
+		 */
+		if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) {
+			init_task.thread.fscr &= ~FSCR_SCV;
+			cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
+		}
+
 		/* Enable AIL if possible */
 		if (!pseries_enable_reloc_on_exc()) {
 			init_task.thread.fscr &= ~FSCR_SCV;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index f5cbfe5efd25..f80cce0e3899 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -615,23 +615,22 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 		return;
 	}
 
-	/* Conditionally hard-enable interrupts. */
-	if (should_hard_irq_enable()) {
-		/*
-		 * Ensure a positive value is written to the decrementer, or
-		 * else some CPUs will continue to take decrementer exceptions.
-		 * When the PPC_WATCHDOG (decrementer based) is configured,
-		 * keep this at most 31 bits, which is about 4 seconds on most
-		 * systems, which gives the watchdog a chance of catching timer
-		 * interrupt hard lockups.
-		 */
-		if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
-			set_dec(0x7fffffff);
-		else
-			set_dec(decrementer_max);
+	/*
+	 * Ensure a positive value is written to the decrementer, or
+	 * else some CPUs will continue to take decrementer exceptions.
+	 * When the PPC_WATCHDOG (decrementer based) is configured,
+	 * keep this at most 31 bits, which is about 4 seconds on most
+	 * systems, which gives the watchdog a chance of catching timer
+	 * interrupt hard lockups.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+		set_dec(0x7fffffff);
+	else
+		set_dec(decrementer_max);
 
+	/* Conditionally hard-enable interrupts. */
+	if (should_hard_irq_enable())
 		do_hard_irq_enable();
-	}
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
index eb9c81e1c218..0c4ecc8fec5a 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -22,12 +22,15 @@
 .macro cvdso_call funct call_time=0
   .cfi_startproc
 	PPC_STLU	r1, -PPC_MIN_STKFRM(r1)
+  .cfi_adjust_cfa_offset PPC_MIN_STKFRM
 	mflr		r0
-  .cfi_register lr, r0
 	PPC_STLU	r1, -PPC_MIN_STKFRM(r1)
+  .cfi_adjust_cfa_offset PPC_MIN_STKFRM
 	PPC_STL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+  .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF
 #ifdef __powerpc64__
 	PPC_STL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
 #endif
 	get_datapage	r5
 	.ifeq	\call_time
@@ -39,13 +42,15 @@
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
 #ifdef __powerpc64__
 	PPC_LL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_restore r2
 #endif
 	.ifeq	\call_time
 	cmpwi		r3, 0
 	.endif
 	mtlr		r0
-  .cfi_restore lr
 	addi		r1, r1, 2 * PPC_MIN_STKFRM
+  .cfi_restore lr
+  .cfi_def_cfa_offset 0
 	crclr		so
 	.ifeq	\call_time
 	beqlr+