Merge branch 'fixes' into next

Merge our fixes branch which has a number of important fixes, notably
the fix for initrd corruption, as well as the fixes for scv vs ptrace.

Documentation/powerpc/syscall64-abi.rst

@@ -109,6 +109,16 @@ auxiliary vector.
 
 scv 0 syscalls will always behave as PPC_FEATURE2_HTM_NOSC.
 
+ptrace
+------
+When ptracing system calls (PTRACE_SYSCALL), the pt_regs.trap value contains
+the system call type that can be used to distinguish between sc and scv 0
+system calls, and the different register conventions can be accounted for.
+
+If the value of (pt_regs.trap & 0xfff0) is 0xc00 then the system call was
+performed with the sc instruction, if it is 0x3000 then the system call was
+performed with the scv 0 instruction.
+
 vsyscall
 ========
 

arch/powerpc/include/asm/jump_label.h

@@ -50,7 +50,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool
 1098:	nop;					\
 	.pushsection __jump_table, "aw";	\
 	.long 1098b - ., LABEL - .;		\
-	FTR_ENTRY_LONG KEY;			\
+	FTR_ENTRY_LONG KEY - .;			\
 	.popsection
 #endif
 

arch/powerpc/include/asm/pte-walk.h

@@ -31,6 +31,35 @@ static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift)
 	pgd_t *pgdir = init_mm.pgd;
 	return __find_linux_pte(pgdir, ea, NULL, hshift);
 }
+
+/*
+ * Convert a kernel vmap virtual address (vmalloc or ioremap space) to a
+ * physical address, without taking locks. This can be used in real-mode.
+ */
+static inline phys_addr_t ppc_find_vmap_phys(unsigned long addr)
+{
+	pte_t *ptep;
+	phys_addr_t pa;
+	int hugepage_shift;
+
+	/*
+	 * init_mm does not free page tables, and does not do THP. It may
+	 * have huge pages from huge vmalloc / ioremap etc.
+	 */
+	ptep = find_init_mm_pte(addr, &hugepage_shift);
+	if (WARN_ON(!ptep))
+		return 0;
+
+	pa = PFN_PHYS(pte_pfn(*ptep));
+
+	if (!hugepage_shift)
+		hugepage_shift = PAGE_SHIFT;
+
+	pa |= addr & ((1ul << hugepage_shift) - 1);
+
+	return pa;
+}
+
 /*
  * This is what we should always use. Any other lockless page table lookup needs
  * careful audit against THP split.

arch/powerpc/include/asm/ptrace.h

@@ -19,6 +19,7 @@
 #ifndef _ASM_POWERPC_PTRACE_H
 #define _ASM_POWERPC_PTRACE_H
 
+#include <linux/err.h>
 #include <uapi/asm/ptrace.h>
 #include <asm/asm-const.h>
 
@@ -153,25 +154,6 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 long do_syscall_trace_enter(struct pt_regs *regs);
 void do_syscall_trace_leave(struct pt_regs *regs);
 
-#define kernel_stack_pointer(regs) ((regs)->gpr[1])
-static inline int is_syscall_success(struct pt_regs *regs)
-{
-	return !(regs->ccr & 0x10000000);
-}
-
-static inline long regs_return_value(struct pt_regs *regs)
-{
-	if (is_syscall_success(regs))
-		return regs->gpr[3];
-	else
-		return -regs->gpr[3];
-}
-
-static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
-{
-	regs->gpr[3] = rc;
-}
-
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else
@@ -236,6 +218,31 @@ static __always_inline void set_trap_norestart(struct pt_regs *regs)
 	regs->trap |= 0x1;
 }
 
+#define kernel_stack_pointer(regs) ((regs)->gpr[1])
+static inline int is_syscall_success(struct pt_regs *regs)
+{
+	if (trap_is_scv(regs))
+		return !IS_ERR_VALUE((unsigned long)regs->gpr[3]);
+	else
+		return !(regs->ccr & 0x10000000);
+}
+
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	if (trap_is_scv(regs))
+		return regs->gpr[3];
+
+	if (is_syscall_success(regs))
+		return regs->gpr[3];
+	else
+		return -regs->gpr[3];
+}
+
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->gpr[3] = rc;
+}
+
 #define arch_has_single_step()	(1)
 #define arch_has_block_step()	(true)
 #define ARCH_HAS_USER_SINGLE_STEP_REPORT

arch/powerpc/include/asm/syscall.h

@@ -41,11 +41,17 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	/*
-	 * If the system call failed,
-	 * regs->gpr[3] contains a positive ERRORCODE.
-	 */
-	return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+	if (trap_is_scv(regs)) {
+		unsigned long error = regs->gpr[3];
+
+		return IS_ERR_VALUE(error) ? error : 0;
+	} else {
+		/*
+		 * If the system call failed,
+		 * regs->gpr[3] contains a positive ERRORCODE.
+		 */
+		return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+	}
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
@@ -58,18 +64,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	/*
-	 * In the general case it's not obvious that we must deal with CCR
-	 * here, as the syscall exit path will also do that for us. However
-	 * there are some places, eg. the signal code, which check ccr to
-	 * decide if the value in r3 is actually an error.
-	 */
-	if (error) {
-		regs->ccr |= 0x10000000L;
-		regs->gpr[3] = error;
+	if (trap_is_scv(regs)) {
+		regs->gpr[3] = (long) error ?: val;
 	} else {
-		regs->ccr &= ~0x10000000L;
-		regs->gpr[3] = val;
+		/*
+		 * In the general case it's not obvious that we must deal with
+		 * CCR here, as the syscall exit path will also do that for us.
+		 * However there are some places, eg. the signal code, which
+		 * check ccr to decide if the value in r3 is actually an error.
+		 */
+		if (error) {
+			regs->ccr |= 0x10000000L;
+			regs->gpr[3] = error;
+		} else {
+			regs->ccr &= ~0x10000000L;
+			regs->gpr[3] = val;
+		}
 	}
 }
 

arch/powerpc/kernel/eeh.c

@@ -346,28 +346,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
  */
 static inline unsigned long eeh_token_to_phys(unsigned long token)
 {
-	pte_t *ptep;
-	unsigned long pa;
-	int hugepage_shift;
-
-	/*
-	 * We won't find hugepages here(this is iomem). Hence we are not
-	 * worried about _PAGE_SPLITTING/collapse. Also we will not hit
-	 * page table free, because of init_mm.
-	 */
-	ptep = find_init_mm_pte(token, &hugepage_shift);
-	if (!ptep)
-		return token;
-
-	pa = pte_pfn(*ptep);
-
-	/* On radix we can do hugepage mappings for io, so handle that */
-	if (!hugepage_shift)
-		hugepage_shift = PAGE_SHIFT;
-
-	pa <<= PAGE_SHIFT;
-	pa |= token & ((1ul << hugepage_shift) - 1);
-	return pa;
+	return ppc_find_vmap_phys(token);
 }
 
 /*

arch/powerpc/kernel/io-workarounds.c

@@ -55,7 +55,6 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
 #ifdef CONFIG_PPC_INDIRECT_MMIO
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 {
-	unsigned hugepage_shift;
 	struct iowa_bus *bus;
 	int token;
 
@@ -65,22 +64,13 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 		bus = &iowa_busses[token - 1];
 	else {
 		unsigned long vaddr, paddr;
-		pte_t *ptep;
 
 		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
 		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
 			return NULL;
-		/*
-		 * We won't find huge pages here (iomem). Also can't hit
-		 * a page table free due to init_mm
-		 */
-		ptep = find_init_mm_pte(vaddr, &hugepage_shift);
-		if (ptep == NULL)
-			paddr = 0;
-		else {
-			WARN_ON(hugepage_shift);
-			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
-		}
+
+		paddr = ppc_find_vmap_phys(vaddr);
+
 		bus = iowa_pci_find(vaddr, paddr);
 
 		if (bus == NULL)

arch/powerpc/kernel/iommu.c

@@ -898,7 +898,6 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	unsigned int order;
 	unsigned int nio_pages, io_order;
 	struct page *page;
-	size_t size_io = size;
 
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
@@ -925,9 +924,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	size_io = IOMMU_PAGE_ALIGN(size_io, tbl);
-	nio_pages = size_io >> tbl->it_page_shift;
-	io_order = get_iommu_order(size_io, tbl);
+	nio_pages = size >> tbl->it_page_shift;
+	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
 	if (mapping == DMA_MAPPING_ERROR) {
@@ -942,9 +940,10 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 			 void *vaddr, dma_addr_t dma_handle)
 {
 	if (tbl) {
-		size_t size_io = IOMMU_PAGE_ALIGN(size, tbl);
-		unsigned int nio_pages = size_io >> tbl->it_page_shift;
+		unsigned int nio_pages;
 
+		size = PAGE_ALIGN(size);
+		nio_pages = size >> tbl->it_page_shift;
 		iommu_free(tbl, dma_handle, nio_pages);
 		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));

arch/powerpc/kernel/kprobes.c

@@ -108,7 +108,6 @@ int arch_prepare_kprobe(struct kprobe *p)
 	int ret = 0;
 	struct kprobe *prev;
 	struct ppc_inst insn = ppc_inst_read((struct ppc_inst *)p->addr);
-	struct ppc_inst prefix = ppc_inst_read((struct ppc_inst *)(p->addr - 1));
 
 	if ((unsigned long)p->addr & 0x03) {
 		printk("Attempt to register kprobe at an unaligned address\n");
@@ -116,7 +115,8 @@ int arch_prepare_kprobe(struct kprobe *p)
 	} else if (IS_MTMSRD(insn) || IS_RFID(insn) || IS_RFI(insn)) {
 		printk("Cannot register a kprobe on rfi/rfid or mtmsr[d]\n");
 		ret = -EINVAL;
-	} else if (ppc_inst_prefixed(prefix)) {
+	} else if ((unsigned long)p->addr & ~PAGE_MASK &&
+		   ppc_inst_prefixed(ppc_inst_read((struct ppc_inst *)(p->addr - 1)))) {
 		printk("Cannot register a kprobe on the second word of prefixed instruction\n");
 		ret = -EINVAL;
 	}

arch/powerpc/kernel/setup_64.c

@@ -369,11 +369,11 @@ void __init early_setup(unsigned long dt_ptr)
 	apply_feature_fixups();
 	setup_feature_keys();
 
-	early_ioremap_setup();
-
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	early_ioremap_setup();
+
 	/*
 	 * After firmware and early platform setup code has set things up,
 	 * we note the SPR values for configurable control/performance

arch/powerpc/kernel/signal_64.c

@@ -902,6 +902,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 	unsafe_copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set), badframe_block);
 	user_write_access_end();
 
+	/* Save the siginfo outside of the unsafe block. */
+	if (copy_siginfo_to_user(&frame->info, &ksig->info))
+		goto badframe;
+
 	/* Make sure signal handler doesn't get spurious FP exceptions */
 	tsk->thread.fp_state.fpscr = 0;
 
@@ -915,11 +919,6 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 		regs->nip = (unsigned long) &frame->tramp[0];
 	}
 
-
-	/* Save the siginfo outside of the unsafe block. */
-	if (copy_siginfo_to_user(&frame->info, &ksig->info))
-		goto badframe;
-
 	/* Allocate a dummy caller frame for the signal handler. */
 	newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
 	err |= put_user(regs->gpr[1], (unsigned long __user *)newsp);

arch/powerpc/kvm/book3s_hv.c

@@ -4455,7 +4455,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		mtspr(SPRN_EBBRR, ebb_regs[1]);
 		mtspr(SPRN_BESCR, ebb_regs[2]);
 		mtspr(SPRN_TAR, user_tar);
-		mtspr(SPRN_FSCR, current->thread.fscr);
 	}
 	mtspr(SPRN_VRSAVE, user_vrsave);
 

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -23,20 +23,9 @@
 #include <asm/pte-walk.h>
 
 /* Translate address of a vmalloc'd thing to a linear map address */
-static void *real_vmalloc_addr(void *x)
+static void *real_vmalloc_addr(void *addr)
 {
-	unsigned long addr = (unsigned long) x;
-	pte_t *p;
-	/*
-	 * assume we don't have huge pages in vmalloc space...
-	 * So don't worry about THP collapse/split. Called
-	 * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
-	 */
-	p = find_init_mm_pte(addr, NULL);
-	if (!p || !pte_present(*p))
-		return NULL;
-	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
-	return __va(addr);
+	return __va(ppc_find_vmap_phys((unsigned long)addr));
 }
 
 /* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -59,6 +59,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #define STACK_SLOT_UAMOR	(SFS-88)
 #define STACK_SLOT_DAWR1	(SFS-96)
 #define STACK_SLOT_DAWRX1	(SFS-104)
+#define STACK_SLOT_FSCR		(SFS-112)
 /* the following is used by the P9 short path */
 #define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */
 
@@ -686,6 +687,8 @@ BEGIN_FTR_SECTION
 	std	r6, STACK_SLOT_DAWR0(r1)
 	std	r7, STACK_SLOT_DAWRX0(r1)
 	std	r8, STACK_SLOT_IAMR(r1)
+	mfspr	r5, SPRN_FSCR
+	std	r5, STACK_SLOT_FSCR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 BEGIN_FTR_SECTION
 	mfspr	r6, SPRN_DAWR1
@@ -1663,6 +1666,10 @@ FTR_SECTION_ELSE
 	ld	r7, STACK_SLOT_HFSCR(r1)
 	mtspr	SPRN_HFSCR, r7
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
+BEGIN_FTR_SECTION
+	ld	r5, STACK_SLOT_FSCR(r1)
+	mtspr	SPRN_FSCR, r5
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	/*
 	 * Restore various registers to 0, where non-zero values
 	 * set by the guest could disrupt the host.

arch/powerpc/mm/mem.c

@@ -20,6 +20,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/kasan.h>
+#include <asm/sparsemem.h>
 #include <asm/svm.h>
 
 #include <mm/mmu_decl.h>

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -1753,16 +1753,25 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # define SYSCALL_RET_SET(_regs, _val)				\
 	do {							\
 		typeof(_val) _result = (_val);			\
-		/*						\
-		 * A syscall error is signaled by CR0 SO bit	\
-		 * and the code is stored as a positive value.	\
-		 */						\
-		if (_result < 0) {				\
-			SYSCALL_RET(_regs) = -_result;		\
-			(_regs).ccr |= 0x10000000;		\
-		} else {					\
+		if ((_regs.trap & 0xfff0) == 0x3000) {		\
+			/*					\
+			 * scv 0 system call uses -ve result	\
+			 * for error, so no need to adjust.	\
+			 */					\
 			SYSCALL_RET(_regs) = _result;		\
-			(_regs).ccr &= ~0x10000000;		\
+		} else {					\
+			/*					\
+			 * A syscall error is signaled by the	\
+			 * CR0 SO bit and the code is stored as	\
+			 * a positive value.			\
+			 */					\
+			if (_result < 0) {			\
+				SYSCALL_RET(_regs) = -_result;	\
+				(_regs).ccr |= 0x10000000;	\
+			} else {				\
+				SYSCALL_RET(_regs) = _result;	\
+				(_regs).ccr &= ~0x10000000;	\
+			}					\
 		}						\
 	} while (0)
 # define SYSCALL_RET_SET_ON_PTRACE_EXIT