powerpc/64: Move paca allocation to early_setup()

The early paca and boot cpuid dance is complicated and currently does
not quite work as expected for boot cpuid != 0 cases.

early_init_devtree() currently allocates the paca_ptrs and boot cpuid
paca, but until that returns and early_setup() calls setup_paca(), this
thread is currently still executing with smp_processor_id() == 0.

One problem this causes is the paca_ptrs[smp_processor_id()] pointer is
poisoned, so valid_emergency_stack() (any backtrace) and any similar
users will crash.

Another is that the hardware id which is set here will not be returned
by get_hard_smp_processor_id(smp_processor_id()), but it would work
correctly for boot_cpuid == 0, which could lead to difficult to
reproduce or find bugs. The hard id does not seem to be used by the rest
of early_init_devtree(), it just looks like all this code might have
been put here to allocate somewhere to store boot CPU hardware id while
scanning the devtree.

Rearrange things so the hwid is put in a global variable like
boot_cpuid, and do all the paca allocation and boot paca setup in the
64-bit early_setup() after we have everything ready to go.

The paca_ptrs[0] re-poisoning code in early_setup does not seem to have
ever worked, because paca_ptrs[0] was never not-poisoned when boot_cpuid
is not 0.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fix build error on 32-bit]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221216115930.2667772-4-npiggin@gmail.com

arch/powerpc/include/asm/paca.h

@@ -295,7 +295,6 @@ extern void free_unused_pacas(void);
 
 #else /* CONFIG_PPC64 */
 
-static inline void allocate_paca_ptrs(void) { }
 static inline void allocate_paca(int cpu) { }
 static inline void free_unused_pacas(void) { }
 

arch/powerpc/include/asm/smp.h

@@ -26,6 +26,7 @@
 #include <asm/percpu.h>
 
 extern int boot_cpuid;
+extern int boot_cpu_hwid; /* PPC64 only */
 extern int spinning_secondaries;
 extern u32 *cpu_to_phys_id;
 extern bool coregroup_enabled;

arch/powerpc/kernel/prom.c

@@ -370,8 +370,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	    be32_to_cpu(intserv[found_thread]));
 	boot_cpuid = found;
 
-	// Pass the boot CPU's hard CPU id back to our caller
-	*((u32 *)data) = be32_to_cpu(intserv[found_thread]);
+	if (IS_ENABLED(CONFIG_PPC64))
+		boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
 
 	/*
 	 * PAPR defines "logical" PVR values for cpus that
@@ -755,7 +755,6 @@ static inline void save_fscr_to_task(void) {}
 
 void __init early_init_devtree(void *params)
 {
-	u32 boot_cpu_hwid;
 	phys_addr_t limit;
 
 	DBG(" -> early_init_devtree(%px)\n", params);
@@ -851,7 +850,7 @@ void __init early_init_devtree(void *params)
 	/* Retrieve CPU related informations from the flat tree
 	 * (altivec support, boot CPU ID, ...)
 	 */
-	of_scan_flat_dt(early_init_dt_scan_cpus, &boot_cpu_hwid);
+	of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
 	if (boot_cpuid < 0) {
 		printk("Failed to identify boot CPU !\n");
 		BUG();
@@ -868,11 +867,6 @@ void __init early_init_devtree(void *params)
 
 	mmu_early_init_devtree();
 
-	// NB. paca is not installed until later in early_setup()
-	allocate_paca_ptrs();
-	allocate_paca(boot_cpuid);
-	set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid);
-
 #ifdef CONFIG_PPC_POWERNV
 	/* Scan and build the list of machine check recoverable ranges */
 	of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);

arch/powerpc/kernel/setup-common.c

@@ -87,6 +87,10 @@ EXPORT_SYMBOL(machine_id);
 int boot_cpuid = -1;
 EXPORT_SYMBOL_GPL(boot_cpuid);
 
+#ifdef CONFIG_PPC64
+int boot_cpu_hwid = -1;
+#endif
+
 /*
  * These are used in binfmt_elf.c to put aux entries on the stack
  * for each elf executable being started.

arch/powerpc/kernel/setup_64.c

@@ -385,15 +385,14 @@ void __init early_setup(unsigned long dt_ptr)
 	/*
 	 * Do early initialization using the flattened device
 	 * tree, such as retrieving the physical memory map or
-	 * calculating/retrieving the hash table size.
+	 * calculating/retrieving the hash table size, discover
+	 * boot_cpuid and boot_cpu_hwid.
 	 */
 	early_init_devtree(__va(dt_ptr));
 
-	/* Now we know the logical id of our boot cpu, setup the paca. */
-	if (boot_cpuid != 0) {
-		/* Poison paca_ptrs[0] again if it's not the boot cpu */
-		memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0]));
-	}
+	allocate_paca_ptrs();
+	allocate_paca(boot_cpuid);
+	set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid);
 	fixup_boot_paca(paca_ptrs[boot_cpuid]);
 	setup_paca(paca_ptrs[boot_cpuid]); /* install the paca into registers */
 	// smp_processor_id() now reports boot_cpuid