Merge tag 'powerpc-6.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add HOTPLUG_SMT support (/sys/devices/system/cpu/smt) and honour the
   configured SMT state when hotplugging CPUs into the system

 - Combine final TLB flush and lazy TLB mm shootdown IPIs when using the
   Radix MMU to avoid a broadcast TLBIE flush on exit

 - Drop the exclusion between ptrace/perf watchpoints, and drop the now
   unused associated arch hooks

 - Add support for the "nohlt" command line option to disable CPU idle

 - Add support for -fpatchable-function-entry for ftrace, with GCC >=
   13.1

 - Rework memory block size determination, and support 256MB size on
   systems with GPUs that have hotpluggable memory

 - Various other small features and fixes

Thanks to Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Athira
Rajeev, Benjamin Gray, Christophe Leroy, Frederic Barrat, Gautam
Menghani, Geoff Levand, Hari Bathini, Immad Mir, Jialin Zhang, Joel
Stanley, Jordan Niethe, Justin Stitt, Kajol Jain, Kees Cook, Krzysztof
Kozlowski, Laurent Dufour, Liang He, Linus Walleij, Mahesh Salgaonkar,
Masahiro Yamada, Michal Suchanek, Nageswara R Sastry, Nathan Chancellor,
Nathan Lynch, Naveen N Rao, Nicholas Piggin, Nick Desaulniers, Omar
Sandoval, Randy Dunlap, Reza Arbab, Rob Herring, Russell Currey, Sourabh
Jain, Thomas Gleixner, Trevor Woerner, Uwe Kleine-König, Vaibhav Jain,
Xiongfeng Wang, Yuan Tan, Zhang Rui, and Zheng Zengkai.

* tag 'powerpc-6.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (135 commits)
  macintosh/ams: linux/platform_device.h is needed
  powerpc/xmon: Reapply "Relax frame size for clang"
  powerpc/mm/book3s64: Use 256M as the upper limit with coherent device memory attached
  powerpc/mm/book3s64: Fix build error with SPARSEMEM disabled
  powerpc/iommu: Fix notifiers being shared by PCI and VIO buses
  powerpc/mpc5xxx: Add missing fwnode_handle_put()
  powerpc/config: Disable SLAB_DEBUG_ON in skiroot
  powerpc/pseries: Remove unused hcall tracing instruction
  powerpc/pseries: Fix hcall tracepoints with JUMP_LABEL=n
  powerpc: dts: add missing space before {
  powerpc/eeh: Use pci_dev_id() to simplify the code
  powerpc/64s: Move CPU -mtune options into Kconfig
  powerpc/powermac: Fix unused function warning
  powerpc/pseries: Rework lppaca_shared_proc() to avoid DEBUG_PREEMPT
  powerpc: Don't include lppaca.h in paca.h
  powerpc/pseries: Move hcall_vphn() prototype into vphn.h
  powerpc/pseries: Move VPHN constants into vphn.h
  cxl: Drop unused detach_spa()
  powerpc: Drop zalloc_maybe_bootmem()
  powerpc/powernv: Use struct opal_prd_msg in more places
  ...

2 files changed, 85 insertions, 115 deletions

diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 678f9c9d89b6..4e14a5427a63 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -9,79 +9,53 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/jump_label.h>
-
-extern struct static_key_false disable_kuap_key;
-
-static __always_inline bool kuep_is_disabled(void)
-{
-	return !IS_ENABLED(CONFIG_PPC_KUEP);
-}
-
 #ifdef CONFIG_PPC_KUAP
 
 #include <linux/sched.h>
 
 #define KUAP_NONE	(~0UL)
-#define KUAP_ALL	(~1UL)
 
-static __always_inline bool kuap_is_disabled(void)
-{
-	return static_branch_unlikely(&disable_kuap_key);
-}
-
-static inline void kuap_lock_one(unsigned long addr)
+static __always_inline void kuap_lock_one(unsigned long addr)
 {
 	mtsr(mfsr(addr) | SR_KS, addr);
 	isync();	/* Context sync required after mtsr() */
 }
 
-static inline void kuap_unlock_one(unsigned long addr)
+static __always_inline void kuap_unlock_one(unsigned long addr)
 {
 	mtsr(mfsr(addr) & ~SR_KS, addr);
 	isync();	/* Context sync required after mtsr() */
 }
 
-static inline void kuap_lock_all(void)
+static __always_inline void uaccess_begin_32s(unsigned long addr)
 {
-	update_user_segments(mfsr(0) | SR_KS);
-	isync();	/* Context sync required after mtsr() */
-}
+	unsigned long tmp;
 
-static inline void kuap_unlock_all(void)
-{
-	update_user_segments(mfsr(0) & ~SR_KS);
-	isync();	/* Context sync required after mtsr() */
+	asm volatile(ASM_MMU_FTR_IFSET(
+		"mfsrin %0, %1;"
+		"rlwinm %0, %0, 0, %2;"
+		"mtsrin %0, %1;"
+		"isync", "", %3)
+		: "=&r"(tmp)
+		: "r"(addr), "i"(~SR_KS), "i"(MMU_FTR_KUAP)
+		: "memory");
 }
 
-void kuap_lock_all_ool(void);
-void kuap_unlock_all_ool(void);
-
-static inline void kuap_lock_addr(unsigned long addr, bool ool)
+static __always_inline void uaccess_end_32s(unsigned long addr)
 {
-	if (likely(addr != KUAP_ALL))
-		kuap_lock_one(addr);
-	else if (!ool)
-		kuap_lock_all();
-	else
-		kuap_lock_all_ool();
-}
+	unsigned long tmp;
 
-static inline void kuap_unlock(unsigned long addr, bool ool)
-{
-	if (likely(addr != KUAP_ALL))
-		kuap_unlock_one(addr);
-	else if (!ool)
-		kuap_unlock_all();
-	else
-		kuap_unlock_all_ool();
+	asm volatile(ASM_MMU_FTR_IFSET(
+		"mfsrin %0, %1;"
+		"oris %0, %0, %2;"
+		"mtsrin %0, %1;"
+		"isync", "", %3)
+		: "=&r"(tmp)
+		: "r"(addr), "i"(SR_KS >> 16), "i"(MMU_FTR_KUAP)
+		: "memory");
 }
 
-static inline void __kuap_lock(void)
-{
-}
-
-static inline void __kuap_save_and_lock(struct pt_regs *regs)
+static __always_inline void __kuap_save_and_lock(struct pt_regs *regs)
 {
 	unsigned long kuap = current->thread.kuap;
 
@@ -90,18 +64,19 @@ static inline void __kuap_save_and_lock(struct pt_regs *regs)
 		return;
 
 	current->thread.kuap = KUAP_NONE;
-	kuap_lock_addr(kuap, false);
+	kuap_lock_one(kuap);
 }
+#define __kuap_save_and_lock __kuap_save_and_lock
 
-static inline void kuap_user_restore(struct pt_regs *regs)
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
 {
 }
 
-static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
 {
 	if (unlikely(kuap != KUAP_NONE)) {
 		current->thread.kuap = KUAP_NONE;
-		kuap_lock_addr(kuap, false);
+		kuap_lock_one(kuap);
 	}
 
 	if (likely(regs->kuap == KUAP_NONE))
@@ -109,10 +84,10 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kua
 
 	current->thread.kuap = regs->kuap;
 
-	kuap_unlock(regs->kuap, false);
+	kuap_unlock_one(regs->kuap);
 }
 
-static inline unsigned long __kuap_get_and_assert_locked(void)
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
 {
 	unsigned long kuap = current->thread.kuap;
 
@@ -120,9 +95,10 @@ static inline unsigned long __kuap_get_and_assert_locked(void)
 
 	return kuap;
 }
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
 
-static __always_inline void __allow_user_access(void __user *to, const void __user *from,
-						u32 size, unsigned long dir)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      u32 size, unsigned long dir)
 {
 	BUILD_BUG_ON(!__builtin_constant_p(dir));
 
@@ -130,10 +106,10 @@ static __always_inline void __allow_user_access(void __user *to, const void __us
 		return;
 
 	current->thread.kuap = (__force u32)to;
-	kuap_unlock_one((__force u32)to);
+	uaccess_begin_32s((__force u32)to);
 }
 
-static __always_inline void __prevent_user_access(unsigned long dir)
+static __always_inline void prevent_user_access(unsigned long dir)
 {
 	u32 kuap = current->thread.kuap;
 
@@ -143,42 +119,51 @@ static __always_inline void __prevent_user_access(unsigned long dir)
 		return;
 
 	current->thread.kuap = KUAP_NONE;
-	kuap_lock_addr(kuap, true);
+	uaccess_end_32s(kuap);
 }
 
-static inline unsigned long __prevent_user_access_return(void)
+static __always_inline unsigned long prevent_user_access_return(void)
 {
 	unsigned long flags = current->thread.kuap;
 
 	if (flags != KUAP_NONE) {
 		current->thread.kuap = KUAP_NONE;
-		kuap_lock_addr(flags, true);
+		uaccess_end_32s(flags);
 	}
 
 	return flags;
 }
 
-static inline void __restore_user_access(unsigned long flags)
+static __always_inline void restore_user_access(unsigned long flags)
 {
 	if (flags != KUAP_NONE) {
 		current->thread.kuap = flags;
-		kuap_unlock(flags, true);
+		uaccess_begin_32s(flags);
 	}
 }
 
-static inline bool
+static __always_inline bool
 __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	unsigned long kuap = regs->kuap;
 
-	if (!is_write || kuap == KUAP_ALL)
+	if (!is_write)
 		return false;
 	if (kuap == KUAP_NONE)
 		return true;
 
-	/* If faulting address doesn't match unlocked segment, unlock all */
-	if ((kuap ^ address) & 0xf0000000)
-		regs->kuap = KUAP_ALL;
+	/*
+	 * If faulting address doesn't match unlocked segment, change segment.
+	 * In case of unaligned store crossing two segments, emulate store.
+	 */
+	if ((kuap ^ address) & 0xf0000000) {
+		if (!(kuap & 0x0fffffff) && address > kuap - 4 && fix_alignment(regs)) {
+			regs_add_return_ip(regs, 4);
+			emulate_single_step(regs);
+		} else {
+			regs->kuap = address;
+		}
+	}
 
 	return false;
 }
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 86650d13ebe6..9b13eb14e21b 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -536,58 +536,43 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 
 /* This low level function performs the actual PTE insertion
- * Setting the PTE depends on the MMU type and other factors. It's
- * an horrible mess that I'm not going to try to clean up now but
- * I'm keeping it in one place rather than spread around
+ * Setting the PTE depends on the MMU type and other factors.
+ *
+ * First case is 32-bit in UP mode with 32-bit PTEs, we need to preserve
+ * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+ * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+ * and see we need to keep track that this PTE needs invalidating.
+ *
+ * Second case is 32-bit with 64-bit PTE.  In this case, we
+ * can just store as long as we do the two halves in the right order
+ * with a barrier in between. This is possible because we take care,
+ * in the hash code, to pre-invalidate if the PTE was already hashed,
+ * which synchronizes us with any concurrent invalidation.
+ * In the percpu case, we fallback to the simple update preserving
+ * the hash bits (ie, same as the non-SMP case).
+ *
+ * Third case is 32-bit in SMP mode with 32-bit PTEs. We use the
+ * helper pte_update() which does an atomic update. We need to do that
+ * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+ * per-CPU PTE such as a kmap_atomic, we also do a simple update preserving
+ * the hash bits instead.
  */
 static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte, int percpu)
 {
-#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
-	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
-	 * helper pte_update() which does an atomic update. We need to do that
-	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
-	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
-	 * the hash bits instead (ie, same as the non-SMP case)
-	 */
-	if (percpu)
-		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-			      | (pte_val(pte) & ~_PAGE_HASHPTE));
-	else
-		pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0);
+	if ((!IS_ENABLED(CONFIG_SMP) && !IS_ENABLED(CONFIG_PTE_64BIT)) || percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) |
+			      (pte_val(pte) & ~_PAGE_HASHPTE));
+	} else if (IS_ENABLED(CONFIG_PTE_64BIT)) {
+		if (pte_val(*ptep) & _PAGE_HASHPTE)
+			flush_hash_entry(mm, ptep, addr);
 
-#elif defined(CONFIG_PTE_64BIT)
-	/* Second case is 32-bit with 64-bit PTE.  In this case, we
-	 * can just store as long as we do the two halves in the right order
-	 * with a barrier in between. This is possible because we take care,
-	 * in the hash code, to pre-invalidate if the PTE was already hashed,
-	 * which synchronizes us with any concurrent invalidation.
-	 * In the percpu case, we also fallback to the simple update preserving
-	 * the hash bits
-	 */
-	if (percpu) {
-		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-			      | (pte_val(pte) & ~_PAGE_HASHPTE));
-		return;
+		asm volatile("stw%X0 %2,%0; eieio; stw%X1 %L2,%1" :
+			     "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) :
+			     "r" (pte) : "memory");
+	} else {
+		pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0);
 	}
-	if (pte_val(*ptep) & _PAGE_HASHPTE)
-		flush_hash_entry(mm, ptep, addr);
-	__asm__ __volatile__("\
-		stw%X0 %2,%0\n\
-		eieio\n\
-		stw%X1 %L2,%1"
-	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
-	: "r" (pte) : "memory");
-
-#else
-	/* Third case is 32-bit hash table in UP mode, we need to preserve
-	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
-	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
-	 * and see we need to keep track that this PTE needs invalidating
-	 */
-	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-		      | (pte_val(pte) & ~_PAGE_HASHPTE));
-#endif
 }
 
 /*