Merge tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable KFENCE for 32-bit.

 - Implement EBPF for 32-bit.

 - Convert 32-bit to do interrupt entry/exit in C.

 - Convert 64-bit BookE to do interrupt entry/exit in C.

 - Changes to our signal handling code to use user_access_begin/end()
   more extensively.

 - Add support for time namespaces (CONFIG_TIME_NS)

 - A series of fixes that allow us to reenable STRICT_KERNEL_RWX.

 - Other smaller features, fixes & cleanups.

Thanks to Alexey Kardashevskiy, Andreas Schwab, Andrew Donnellan, Aneesh
Kumar K.V, Athira Rajeev, Bhaskar Chowdhury, Bixuan Cui, Cédric Le
Goater, Chen Huang, Chris Packham, Christophe Leroy, Christopher M.
Riedl, Colin Ian King, Dan Carpenter, Daniel Axtens, Daniel Henrique
Barboza, David Gibson, Davidlohr Bueso, Denis Efremov, dingsenjie,
Dmitry Safonov, Dominic DeMarco, Fabiano Rosas, Ganesh Goudar, Geert
Uytterhoeven, Geetika Moolchandani, Greg Kurz, Guenter Roeck, Haren
Myneni, He Ying, Jiapeng Chong, Jordan Niethe, Laurent Dufour, Lee
Jones, Leonardo Bras, Li Huafei, Madhavan Srinivasan, Mahesh Salgaonkar,
Masahiro Yamada, Nathan Chancellor, Nathan Lynch, Nicholas Piggin,
Oliver O'Halloran, Paul Menzel, Pu Lehui, Randy Dunlap, Ravi Bangoria,
Rosen Penev, Russell Currey, Santosh Sivaraj, Sebastian Andrzej Siewior,
Segher Boessenkool, Shivaprasad G Bhat, Srikar Dronamraju, Stephen
Rothwell, Thadeu Lima de Souza Cascardo, Thomas Gleixner, Tony Ambardar,
Tyrel Datwyler, Vaibhav Jain, Vincenzo Frascino, Xiongwei Song, Yang Li,
Yu Kuai, and Zhang Yunkai.

* tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (302 commits)
  powerpc/signal32: Fix erroneous SIGSEGV on RT signal return
  powerpc: Avoid clang uninitialized warning in __get_user_size_allowed
  powerpc/papr_scm: Mark nvdimm as unarmed if needed during probe
  powerpc/kvm: Fix build error when PPC_MEM_KEYS/PPC_PSERIES=n
  powerpc/kasan: Fix shadow start address with modules
  powerpc/kernel/iommu: Use largepool as a last resort when !largealloc
  powerpc/kernel/iommu: Align size for IOMMU_PAGE_SIZE() to save TCEs
  powerpc/44x: fix spelling mistake in Kconfig "varients" -> "variants"
  powerpc/iommu: Annotate nested lock for lockdep
  powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
  powerpc/iommu: Allocate it_map by vmalloc
  selftests/powerpc: remove unneeded semicolon
  powerpc/64s: remove unneeded semicolon
  powerpc/eeh: remove unneeded semicolon
  powerpc/selftests: Add selftest to test concurrent perf/ptrace events
  powerpc/selftests/perf-hwbreak: Add testcases for 2nd DAWR
  powerpc/selftests/perf-hwbreak: Coalesce event creation code
  powerpc/selftests/ptrace-hwbreak: Add testcases for 2nd DAWR
  powerpc/configs: Add IBMVNIC to some 64-bit configs
  selftests/powerpc: Add uaccess flush test
  ...

1 files changed, 23 insertions, 37 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index bb368257b55c..34f641d4a2fe 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -32,6 +32,8 @@
 #include <linux/context_tracking.h>
 #include <linux/hugetlb.h>
 #include <linux/uaccess.h>
+#include <linux/kfence.h>
+#include <linux/pkeys.h>
 
 #include <asm/firmware.h>
 #include <asm/interrupt.h>
@@ -87,7 +89,6 @@ static noinline int bad_area(struct pt_regs *regs, unsigned long address)
 	return __bad_area(regs, address, SEGV_MAPERR);
 }
 
-#ifdef CONFIG_PPC_MEM_KEYS
 static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
 				    struct vm_area_struct *vma)
 {
@@ -127,7 +128,6 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
 
 	return 0;
 }
-#endif
 
 static noinline int bad_access(struct pt_regs *regs, unsigned long address)
 {
@@ -197,7 +197,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr,
 static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 			     unsigned long address, bool is_write)
 {
-	int is_exec = TRAP(regs) == 0x400;
+	int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;
 
 	/* NX faults set DSISR_PROTFAULT on the 8xx, DSISR_NOEXEC_OR_G on others */
 	if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT |
@@ -234,7 +234,6 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 	return false;
 }
 
-#ifdef CONFIG_PPC_MEM_KEYS
 static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
 			      struct vm_area_struct *vma)
 {
@@ -248,7 +247,6 @@ static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
 
 	return false;
 }
-#endif
 
 static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma)
 {
@@ -393,7 +391,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
 	unsigned int flags = FAULT_FLAG_DEFAULT;
- 	int is_exec = TRAP(regs) == 0x400;
+	int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;
 	int is_user = user_mode(regs);
 	int is_write = page_fault_is_write(error_code);
 	vm_fault_t fault, major = 0;
@@ -418,8 +416,12 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * take a page fault to a kernel address or a page fault to a user
 	 * address outside of dedicated places
 	 */
-	if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write)))
+	if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write))) {
+		if (kfence_handle_page_fault(address, is_write, regs))
+			return 0;
+
 		return SIGSEGV;
+	}
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
@@ -492,11 +494,9 @@ retry:
 			return bad_area(regs, address);
 	}
 
-#ifdef CONFIG_PPC_MEM_KEYS
 	if (unlikely(access_pkey_error(is_write, is_exec,
 				       (error_code & DSISR_KEYFAULT), vma)))
 		return bad_access_pkey(regs, address, vma);
-#endif /* CONFIG_PPC_MEM_KEYS */
 
 	if (unlikely(access_error(is_write, is_exec, vma)))
 		return bad_access(regs, address);
@@ -539,39 +539,25 @@ retry:
 }
 NOKPROBE_SYMBOL(___do_page_fault);
 
-static long __do_page_fault(struct pt_regs *regs)
+static __always_inline void __do_page_fault(struct pt_regs *regs)
 {
-	const struct exception_table_entry *entry;
 	long err;
 
 	err = ___do_page_fault(regs, regs->dar, regs->dsisr);
-	if (likely(!err))
-		return err;
-
-	entry = search_exception_tables(regs->nip);
-	if (likely(entry)) {
-		instruction_pointer_set(regs, extable_fixup(entry));
-		return 0;
-	} else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
-		__bad_page_fault(regs, err);
-		return 0;
-	} else {
-		/* 32 and 64e handle the bad page fault in asm */
-		return err;
-	}
+	if (unlikely(err))
+		bad_page_fault(regs, err);
 }
-NOKPROBE_SYMBOL(__do_page_fault);
 
-DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
+DEFINE_INTERRUPT_HANDLER(do_page_fault)
 {
-	return __do_page_fault(regs);
+	__do_page_fault(regs);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
 /* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
-long hash__do_page_fault(struct pt_regs *regs)
+void hash__do_page_fault(struct pt_regs *regs)
 {
-	return __do_page_fault(regs);
+	__do_page_fault(regs);
 }
 NOKPROBE_SYMBOL(hash__do_page_fault);
 #endif
@@ -581,27 +567,27 @@ NOKPROBE_SYMBOL(hash__do_page_fault);
  * It is called from the DSI and ISI handlers in head.S and from some
  * of the procedures in traps.c.
  */
-void __bad_page_fault(struct pt_regs *regs, int sig)
+static void __bad_page_fault(struct pt_regs *regs, int sig)
 {
 	int is_write = page_fault_is_write(regs->dsisr);
 
 	/* kernel has accessed a bad area */
 
 	switch (TRAP(regs)) {
-	case 0x300:
-	case 0x380:
-	case 0xe00:
+	case INTERRUPT_DATA_STORAGE:
+	case INTERRUPT_DATA_SEGMENT:
+	case INTERRUPT_H_DATA_STORAGE:
 		pr_alert("BUG: %s on %s at 0x%08lx\n",
 			 regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
 			 "Unable to handle kernel data access",
 			 is_write ? "write" : "read", regs->dar);
 		break;
-	case 0x400:
-	case 0x480:
+	case INTERRUPT_INST_STORAGE:
+	case INTERRUPT_INST_SEGMENT:
 		pr_alert("BUG: Unable to handle kernel instruction fetch%s",
 			 regs->nip < PAGE_SIZE ? " (NULL pointer?)\n" : "\n");
 		break;
-	case 0x600:
+	case INTERRUPT_ALIGNMENT:
 		pr_alert("BUG: Unable to handle kernel unaligned access at 0x%08lx\n",
 			 regs->dar);
 		break;