powerpc/64s/slb: Add no_slb_preload early cmdline param

no_slb_preload cmdline can come useful in quickly disabling and/or
testing the performance impact of userspace slb preloads. Recently there
was a slb multi-hit issue due to slb preload cache which was very
difficult to triage. This cmdline option allows to quickly disable
preloads and verify if the issue exists in preload cache or somewhere
else. This can also be a useful option to see the effect of slb preloads
for any application workload e.g. number of slb faults with or w/o slb
preloads.

with slb_preload:
slb_faults (minimal initrd boot): 15
slb_faults (full systemd boot): 300

with no_slb_preload:
slb_faults (minimal initrd boot): 33
slb_faults (full systemd boot): 138180

Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/de484b55c45d831bc2db63945f455153c89a9a65.1761834163.git.ritesh.list@gmail.com

Author: riteshharjani

Documentation/admin-guide/kernel-parameters.txt

@@ -7192,6 +7192,9 @@
 			them frequently to increase the rate of SLB faults
 			on kernel addresses.
 
+	no_slb_preload	[PPC,EARLY]
+			Disables slb preloading for userspace.
+
 	sunrpc.min_resvport=
 	sunrpc.max_resvport=
 			[NFS,SUNRPC]

arch/powerpc/mm/book3s64/hash_utils.c

@@ -1329,6 +1329,9 @@ static void __init htab_initialize(void)
 	if (stress_slb_enabled)
 		static_branch_enable(&stress_slb_key);
 
+	if (no_slb_preload)
+		static_branch_enable(&no_slb_preload_key);
+
 	if (stress_hpt_enabled) {
 		unsigned long tmp;
 		static_branch_enable(&stress_hpt_key);

arch/powerpc/mm/book3s64/internal.h

@@ -22,6 +22,13 @@ static inline bool stress_hpt(void)
 	return static_branch_unlikely(&stress_hpt_key);
 }
 
+extern bool no_slb_preload;
+DECLARE_STATIC_KEY_FALSE(no_slb_preload_key);
+static inline bool slb_preload_disabled(void)
+{
+	return static_branch_unlikely(&no_slb_preload_key);
+}
+
 void hpt_do_stress(unsigned long ea, unsigned long hpte_group);
 
 void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush);

arch/powerpc/mm/book3s64/slb.c

@@ -42,6 +42,15 @@ early_param("stress_slb", parse_stress_slb);
 
 __ro_after_init DEFINE_STATIC_KEY_FALSE(stress_slb_key);
 
+bool no_slb_preload __initdata;
+static int __init parse_no_slb_preload(char *p)
+{
+	no_slb_preload = true;
+	return 0;
+}
+early_param("no_slb_preload", parse_no_slb_preload);
+__ro_after_init DEFINE_STATIC_KEY_FALSE(no_slb_preload_key);
+
 static void assert_slb_presence(bool present, unsigned long ea)
 {
 #ifdef CONFIG_DEBUG_VM
@@ -299,6 +308,9 @@ static void preload_add(struct thread_info *ti, unsigned long ea)
 	unsigned char idx;
 	unsigned long esid;
 
+	if (slb_preload_disabled())
+		return;
+
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		/* EAs are stored >> 28 so 256MB segments don't need clearing */
 		if (ea & ESID_MASK_1T)
@@ -412,6 +424,9 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 
 	copy_mm_to_paca(mm);
 
+	if (slb_preload_disabled())
+		return;
+
 	/*
 	 * We gradually age out SLBs after a number of context switches to
 	 * reduce reload overhead of unused entries (like we do with FP/VEC