parisc architecture fixes for kernel v6.6-rc5:

* fix random faults in mmap'd memory on pre PA8800 processors
 * fix boot crash with nr_cpus=1 on kernel command line
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQS86RI+GtKfB8BJu973ErUQojoPXwUCZSGn1wAKCRD3ErUQojoP
 X2FbAP0clw0VUZZQuu9Z1jLXj1lVjb+2HOzK3t+PjQgIRMIlAgD8DCRGj5cTYcNi
 t+6s1+S/iamXQBPKv+SdJv99PVnN5QU=
 =sPnd
 -----END PGP SIGNATURE-----

Merge tag 'parisc-for-6.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux

Pull parisc fixes from Helge Deller:

 - fix random faults in mmap'd memory on pre PA8800 processors

 - fix boot crash with nr_cpus=1 on kernel command line

* tag 'parisc-for-6.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
  parisc: Restore __ldcw_align for PA-RISC 2.0 processors
  parisc: Fix crash with nr_cpus=1 option

arch/parisc/include/asm/ldcw.h

@@ -2,39 +2,42 @@
 #ifndef __PARISC_LDCW_H
 #define __PARISC_LDCW_H
 
-#ifndef CONFIG_PA20
 /* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
    and GCC only guarantees 8-byte alignment for stack locals, we can't
    be assured of 16-byte alignment for atomic lock data even if we
    specify "__attribute ((aligned(16)))" in the type declaration.  So,
    we use a struct containing an array of four ints for the atomic lock
    type and dynamically select the 16-byte aligned int from the array
-   for the semaphore.  */
+   for the semaphore. */
+
+/* From: "Jim Hull" <jim.hull of hp.com>
+   I've attached a summary of the change, but basically, for PA 2.0, as
+   long as the ",CO" (coherent operation) completer is implemented, then the
+   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
+   they only require "natural" alignment (4-byte for ldcw, 8-byte for
+   ldcd).
+
+   Although the cache control hint is accepted by all PA 2.0 processors,
+   it is only implemented on PA8800/PA8900 CPUs. Prior PA8X00 CPUs still
+   require 16-byte alignment. If the address is unaligned, the operation
+   of the instruction is undefined. The ldcw instruction does not generate
+   unaligned data reference traps so misaligned accesses are not detected.
+   This hid the problem for years. So, restore the 16-byte alignment dropped
+   by Kyle McMartin in "Remove __ldcw_align for PA-RISC 2.0 processors". */
 
 #define __PA_LDCW_ALIGNMENT	16
-#define __PA_LDCW_ALIGN_ORDER	4
 #define __ldcw_align(a) ({					\
 	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
 	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
 		& ~(__PA_LDCW_ALIGNMENT - 1);			\
 	(volatile unsigned int *) __ret;			\
 })
-#define __LDCW	"ldcw"
 
-#else /*CONFIG_PA20*/
+#ifdef CONFIG_PA20
-/* From: "Jim Hull" <jim.hull of hp.com>
-   I've attached a summary of the change, but basically, for PA 2.0, as
-   long as the ",CO" (coherent operation) completer is specified, then the
-   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
-   they only require "natural" alignment (4-byte for ldcw, 8-byte for
-   ldcd). */
-
-#define __PA_LDCW_ALIGNMENT	4
-#define __PA_LDCW_ALIGN_ORDER	2
-#define __ldcw_align(a) (&(a)->slock)
 #define __LDCW	"ldcw,co"
-
+#else
-#endif /*!CONFIG_PA20*/
+#define __LDCW	"ldcw"
+#endif
 
 /* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.
    We don't explicitly expose that "*a" may be written as reload

arch/parisc/include/asm/spinlock_types.h

@@ -9,15 +9,10 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
-#ifdef CONFIG_PA20
-	volatile unsigned int slock;
-# define __ARCH_SPIN_LOCK_UNLOCKED { __ARCH_SPIN_LOCK_UNLOCKED_VAL }
-#else
 	volatile unsigned int lock[4];
 # define __ARCH_SPIN_LOCK_UNLOCKED	\
 	{ { __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL, \
 	    __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL } }
-#endif
 } arch_spinlock_t;
 
 

arch/parisc/kernel/smp.c

@@ -440,7 +440,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	if (cpu_online(cpu))
 		return 0;
 
-	if (num_online_cpus() < setup_max_cpus && smp_boot_one_cpu(cpu, tidle))
+	if (num_online_cpus() < nr_cpu_ids &&
+		num_online_cpus() < setup_max_cpus &&
+		smp_boot_one_cpu(cpu, tidle))
 		return -EIO;
 
 	return cpu_online(cpu) ? 0 : -EIO;