iommu/arm-smmu-v3: Fix soft lockup triggered by arm_smmu_mm_invalidate_range

When running an SVA case, the following soft lockup is triggered:
--------------------------------------------------------------------
watchdog: BUG: soft lockup - CPU#244 stuck for 26s!
pstate: 83400009 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
pc : arm_smmu_cmdq_issue_cmdlist+0x178/0xa50
lr : arm_smmu_cmdq_issue_cmdlist+0x150/0xa50
sp : ffff8000d83ef290
x29: ffff8000d83ef290 x28: 000000003b9aca00 x27: 0000000000000000
x26: ffff8000d83ef3c0 x25: da86c0812194a0e8 x24: 0000000000000000
x23: 0000000000000040 x22: ffff8000d83ef340 x21: ffff0000c63980c0
x20: 0000000000000001 x19: ffff0000c6398080 x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000 x15: ffff3000b4a3bbb0
x14: ffff3000b4a30888 x13: ffff3000b4a3cf60 x12: 0000000000000000
x11: 0000000000000000 x10: 0000000000000000 x9 : ffffc08120e4d6bc
x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000048cfa
x5 : 0000000000000000 x4 : 0000000000000001 x3 : 000000000000000a
x2 : 0000000080000000 x1 : 0000000000000000 x0 : 0000000000000001
Call trace:
 arm_smmu_cmdq_issue_cmdlist+0x178/0xa50
 __arm_smmu_tlb_inv_range+0x118/0x254
 arm_smmu_tlb_inv_range_asid+0x6c/0x130
 arm_smmu_mm_invalidate_range+0xa0/0xa4
 __mmu_notifier_invalidate_range_end+0x88/0x120
 unmap_vmas+0x194/0x1e0
 unmap_region+0xb4/0x144
 do_mas_align_munmap+0x290/0x490
 do_mas_munmap+0xbc/0x124
 __vm_munmap+0xa8/0x19c
 __arm64_sys_munmap+0x28/0x50
 invoke_syscall+0x78/0x11c
 el0_svc_common.constprop.0+0x58/0x1c0
 do_el0_svc+0x34/0x60
 el0_svc+0x2c/0xd4
 el0t_64_sync_handler+0x114/0x140
 el0t_64_sync+0x1a4/0x1a8
--------------------------------------------------------------------

Note that since 6.6-rc1 the arm_smmu_mm_invalidate_range above is renamed
to "arm_smmu_mm_arch_invalidate_secondary_tlbs", yet the problem remains.

The commit 06ff87ba ("arm64: mm: remove unused functions and variable
protoypes") fixed a similar lockup on the CPU MMU side. Yet, it can occur
to SMMU too, since arm_smmu_mm_arch_invalidate_secondary_tlbs() is called
typically next to MMU tlb flush function, e.g.
	tlb_flush_mmu_tlbonly {
		tlb_flush {
			__flush_tlb_range {
				// check MAX_TLBI_OPS
			}
		}
		mmu_notifier_arch_invalidate_secondary_tlbs {
			arm_smmu_mm_arch_invalidate_secondary_tlbs {
				// does not check MAX_TLBI_OPS
			}
		}
	}

Clone a CMDQ_MAX_TLBI_OPS from the MAX_TLBI_OPS in tlbflush.h, since in an
SVA case SMMU uses the CPU page table, so it makes sense to align with the
tlbflush code. Then, replace per-page TLBI commands with a single per-asid
TLBI command, if the request size hits this threshold.
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/r/20230920052257.8615-1-nicolinc@nvidia.comSigned-off-by: Will Deacon <will@kernel.org>

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c

@@ -186,6 +186,15 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
 	}
 }
 
+/*
+ * Cloned from the MAX_TLBI_OPS in arch/arm64/include/asm/tlbflush.h, this
+ * is used as a threshold to replace per-page TLBI commands to issue in the
+ * command queue with an address-space TLBI command, when SMMU w/o a range
+ * invalidation feature handles too many per-page TLBI commands, which will
+ * otherwise result in a soft lockup.
+ */
+#define CMDQ_MAX_TLBI_OPS		(1 << (PAGE_SHIFT - 3))
+
 static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 						struct mm_struct *mm,
 						unsigned long start,
@@ -201,8 +210,13 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 	 * range. So do a simple translation here by calculating size correctly.
 	 */
 	size = end - start;
-	if (size == ULONG_MAX)
-		size = 0;
+	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_RANGE_INV)) {
+		if (size >= CMDQ_MAX_TLBI_OPS * PAGE_SIZE)
+			size = 0;
+	} else {
+		if (size == ULONG_MAX)
+			size = 0;
+	}
 
 	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) {
 		if (!size)