From a5cab83cd3d2d75d3893276cb5f27e163484ef04 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:53 +1100
Subject: powerpc: Create a helper for getting the kernel toc value

Move the logic to work out the kernel toc pointer into a header. This is
a good cleanup, and also means we can use it elsewhere in future.

Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/paca.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 01ea0edf0579..93dae296b6be 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -17,10 +17,6 @@
 #include <asm/pgtable.h>
 #include <asm/kexec.h>
 
-/* This symbol is provided by the linker - let it fill in the paca
- * field correctly */
-extern unsigned long __toc_start;
-
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
@@ -149,11 +145,6 @@ EXPORT_SYMBOL(paca);
 
 void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 {
-       /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB
-	* of the TOC can be addressed using a single machine instruction.
-	*/
-	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
-
 #ifdef CONFIG_PPC_BOOK3S
 	new_paca->lppaca_ptr = new_lppaca(cpu);
 #else
@@ -161,7 +152,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 #endif
 	new_paca->lock_token = 0x8000;
 	new_paca->paca_index = cpu;
-	new_paca->kernel_toc = kernel_toc;
+	new_paca->kernel_toc = kernel_toc_addr();
 	new_paca->kernelbase = (unsigned long) _stext;
 	/* Only set MSR:IR/DR when MMU is initialized */
 	new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR);
-- 
cgit v1.2.3


From 136cd3450af8092f30d0e289806f08ac2aeee38f Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:54 +1100
Subject: powerpc/module: Only try to generate the ftrace_caller() stub once

Currently we generate the module stub for ftrace_caller() at the bottom
of apply_relocate_add(). However apply_relocate_add() is potentially
called more than once per module, which means we will try to generate
the ftrace_caller() stub multiple times.

Although the current code deals with that correctly, ie. it only
generates a stub the first time, it would be clearer to only try to
generate the stub once.

Note also on first reading it may appear that we generate a different
stub for each section that requires relocation, but that is not the
case. The code in stub_for_addr() that searches for an existing stub
uses sechdrs[me->arch.stubs_section], ie. the single stub section for
this module.

A cleaner approach is to only generate the ftrace_caller() stub once,
from module_finalize(). Although the original code didn't check to see
if the stub was actually generated correctly, it seems prudent to add a
check, so do that. And an additional benefit is we can clean the ifdefs
up a little.

Finally we must propagate the const'ness of some of the pointers passed
to module_finalize(), but that is also an improvement.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/module.h |  9 +++++++++
 arch/powerpc/kernel/module.c      |  5 +++++
 arch/powerpc/kernel/module_32.c   | 20 ++++++++++++++------
 arch/powerpc/kernel/module_64.c   | 22 ++++++++++++++--------
 4 files changed, 42 insertions(+), 14 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index dcfcad139bcc..74d25a749018 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -82,6 +82,15 @@ bool is_module_trampoline(u32 *insns);
 int module_trampoline_target(struct module *mod, u32 *trampoline,
 			     unsigned long *target);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs);
+#else
+static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
+{
+	return 0;
+}
+#endif
+
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 9547381b631a..d1f1b35bf0c7 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -47,6 +47,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 		const Elf_Shdr *sechdrs, struct module *me)
 {
 	const Elf_Shdr *sect;
+	int rc;
+
+	rc = module_finalize_ftrace(me, sechdrs);
+	if (rc)
+		return rc;
 
 	/* Apply feature fixups */
 	sect = find_section(hdr, sechdrs, "__ftr_fixup");
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 2c01665eb410..5a7a78f12562 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -181,7 +181,7 @@ static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
 /* Set up a trampoline in the PLT to bounce us to the distant function */
 static uint32_t do_plt_call(void *location,
 			    Elf32_Addr val,
-			    Elf32_Shdr *sechdrs,
+			    const Elf32_Shdr *sechdrs,
 			    struct module *mod)
 {
 	struct ppc_plt_entry *entry;
@@ -294,11 +294,19 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			return -ENOEXEC;
 		}
 	}
+
+	return 0;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-	module->arch.tramp =
-		do_plt_call(module->core_layout.base,
-			    (unsigned long)ftrace_caller,
-			    sechdrs, module);
-#endif
+int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs)
+{
+	module->arch.tramp = do_plt_call(module->core_layout.base,
+					 (unsigned long)ftrace_caller,
+					 sechdrs, module);
+	if (!module->arch.tramp)
+		return -ENOENT;
+
 	return 0;
 }
+#endif
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index ac64ffdb52c8..599c753c7960 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -413,7 +413,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 /* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this
    gives the value maximum span in an instruction which uses a signed
    offset) */
-static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
+static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me)
 {
 	return sechdrs[me->arch.toc_section].sh_addr + 0x8000;
 }
@@ -426,7 +426,7 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
 #define PPC_HA(v) PPC_HI ((v) + 0x8000)
 
 /* Patch stub to reference function and correct r2 value. */
-static inline int create_stub(Elf64_Shdr *sechdrs,
+static inline int create_stub(const Elf64_Shdr *sechdrs,
 			      struct ppc64_stub_entry *entry,
 			      unsigned long addr,
 			      struct module *me)
@@ -452,7 +452,7 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
 
 /* Create stub to jump to function described in this OPD/ptr: we need the
    stub to set up the TOC ptr (r2) for the function. */
-static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
+static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
 				   unsigned long addr,
 				   struct module *me)
 {
@@ -693,12 +693,18 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		}
 	}
 
+	return 0;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-	me->arch.toc = my_r2(sechdrs, me);
-	me->arch.tramp = stub_for_addr(sechdrs,
-				       (unsigned long)ftrace_caller,
-				       me);
-#endif
+int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
+{
+	mod->arch.toc = my_r2(sechdrs, mod);
+	mod->arch.tramp = stub_for_addr(sechdrs, (unsigned long)ftrace_caller, mod);
+
+	if (!mod->arch.tramp)
+		return -ENOENT;
 
 	return 0;
 }
+#endif
-- 
cgit v1.2.3


From f17c4e01e906c568fb03a2e6c2b99e4ee4587fbf Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:55 +1100
Subject: powerpc/module: Mark module stubs with a magic value

When a module is loaded, calls out to the kernel go via a stub which is
generated at runtime. One of these stubs is used to call _mcount(),
which is the default target of tracing calls generated by the compiler
with -pg.

If dynamic ftrace is enabled (which it typically is), another stub is
used to call ftrace_caller(), which is the target of tracing calls when
ftrace is actually active.

ftrace then wants to disable the calls to _mcount() at module startup,
and enable/disable the calls to ftrace_caller() when enabling/disabling
tracing - all of these it does by patching the code.

As part of that code patching, the ftrace code wants to confirm that the
branch it is about to modify, is in fact a call to a module stub which
calls _mcount() or ftrace_caller().

Currently it does that by inspecting the instructions and confirming
they are what it expects. Although that works, the code to do it is
pretty intricate because it requires lots of knowledge about the exact
format of the stub.

We can make that process easier by marking the generated stubs with a
magic value, and then looking for that magic value. Altough this is not
as rigorous as the current method, I believe it is sufficient in
practice.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/module.h |  3 +-
 arch/powerpc/kernel/ftrace.c      | 14 ++-----
 arch/powerpc/kernel/module_64.c   | 78 +++++++++++++--------------------------
 3 files changed, 31 insertions(+), 64 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 74d25a749018..5b6b5a427b54 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -78,8 +78,7 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
-bool is_module_trampoline(u32 *insns);
-int module_trampoline_target(struct module *mod, u32 *trampoline,
+int module_trampoline_target(struct module *mod, unsigned long trampoline,
 			     unsigned long *target);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 44d4d8eb3c85..4505cbfd0e13 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -106,10 +106,9 @@ static int
 __ftrace_make_nop(struct module *mod,
 		  struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned int op;
-	unsigned long entry, ptr;
+	unsigned long entry, ptr, tramp;
 	unsigned long ip = rec->ip;
-	void *tramp;
+	unsigned int op;
 
 	/* read where this goes */
 	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
@@ -122,14 +121,9 @@ __ftrace_make_nop(struct module *mod,
 	}
 
 	/* lets find where the pointer goes */
-	tramp = (void *)find_bl_target(ip, op);
-
-	pr_devel("ip:%lx jumps to %p", ip, tramp);
+	tramp = find_bl_target(ip, op);
 
-	if (!is_module_trampoline(tramp)) {
-		pr_err("Not a trampoline\n");
-		return -EINVAL;
-	}
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
 
 	if (module_trampoline_target(mod, tramp, &ptr)) {
 		pr_err("Failed to get trampoline target\n");
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 599c753c7960..9629966e614b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -96,6 +96,8 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym)
 }
 #endif
 
+#define STUB_MAGIC 0x73747562 /* stub */
+
 /* Like PPC32, we need little trampolines to do > 24-bit jumps (into
    the kernel itself).  But on PPC64, these need to be used for every
    jump, actually, to reset r2 (TOC+0x8000). */
@@ -105,7 +107,8 @@ struct ppc64_stub_entry
 	 * need 6 instructions on ABIv2 but we always allocate 7 so
 	 * so we don't have to modify the trampoline load instruction. */
 	u32 jump[7];
-	u32 unused;
+	/* Used by ftrace to identify stubs */
+	u32 magic;
 	/* Data for the above code */
 	func_desc_t funcdata;
 };
@@ -139,70 +142,39 @@ static u32 ppc64_stub_insns[] = {
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-
-static u32 ppc64_stub_mask[] = {
-	0xffff0000,
-	0xffff0000,
-	0xffffffff,
-	0xffffffff,
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
-	0xffffffff,
-#endif
-	0xffffffff,
-	0xffffffff
-};
-
-bool is_module_trampoline(u32 *p)
+int module_trampoline_target(struct module *mod, unsigned long addr,
+			     unsigned long *target)
 {
-	unsigned int i;
-	u32 insns[ARRAY_SIZE(ppc64_stub_insns)];
-
-	BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask));
+	struct ppc64_stub_entry *stub;
+	func_desc_t funcdata;
+	u32 magic;
 
-	if (probe_kernel_read(insns, p, sizeof(insns)))
+	if (!within_module_core(addr, mod)) {
+		pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name);
 		return -EFAULT;
-
-	for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
-		u32 insna = insns[i];
-		u32 insnb = ppc64_stub_insns[i];
-		u32 mask = ppc64_stub_mask[i];
-
-		if ((insna & mask) != (insnb & mask))
-			return false;
 	}
 
-	return true;
-}
+	stub = (struct ppc64_stub_entry *)addr;
 
-int module_trampoline_target(struct module *mod, u32 *trampoline,
-			     unsigned long *target)
-{
-	u32 buf[2];
-	u16 upper, lower;
-	long offset;
-	void *toc_entry;
-
-	if (probe_kernel_read(buf, trampoline, sizeof(buf)))
+	if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) {
+		pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
 		return -EFAULT;
+	}
 
-	upper = buf[0] & 0xffff;
-	lower = buf[1] & 0xffff;
-
-	/* perform the addis/addi, both signed */
-	offset = ((short)upper << 16) + (short)lower;
+	if (magic != STUB_MAGIC) {
+		pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name);
+		return -EFAULT;
+	}
 
-	/*
-	 * Now get the address this trampoline jumps to. This
-	 * is always 32 bytes into our trampoline stub.
-	 */
-	toc_entry = (void *)mod->arch.toc + offset + 32;
+	if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) {
+		pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
+                return -EFAULT;
+	}
 
-	if (probe_kernel_read(target, toc_entry, sizeof(*target)))
-		return -EFAULT;
+	*target = stub_func_addr(funcdata);
 
 	return 0;
 }
-
 #endif
 
 /* Count how many different 24-bit relocations (different symbol,
@@ -447,6 +419,8 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 	entry->jump[0] |= PPC_HA(reladdr);
 	entry->jump[1] |= PPC_LO(reladdr);
 	entry->funcdata = func_desc(addr);
+	entry->magic = STUB_MAGIC;
+
 	return 1;
 }
 
-- 
cgit v1.2.3


From 336a7b5dd80a2a7b463dc8ede4862425940edeb5 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:56 +1100
Subject: powerpc/module: Create a special stub for ftrace_caller()

In order to support the new -mprofile-kernel ABI, we need to be able to
call from the module back to ftrace_caller() (in the kernel) without
using the module's r2. That is because the function in this module which
is calling ftrace_caller() may not have setup r2, if it doesn't
otherwise need it (ie. it accesses no globals).

To make that work we add a new stub which is used for calling
ftrace_caller(), which uses the kernel toc instead of the module toc.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/module_64.c | 69 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 68 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 9629966e614b..76c0963572f5 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -31,6 +31,7 @@
 #include <asm/code-patching.h>
 #include <linux/sort.h>
 #include <asm/setup.h>
+#include <asm/sections.h>
 
 /* FIXME: We don't do .init separately.  To do this, we'd need to have
    a separate r2 value in the init and core section, and stub between
@@ -671,10 +672,76 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+
+#ifdef CC_USING_MPROFILE_KERNEL
+
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+/*
+ * For mprofile-kernel we use a special stub for ftrace_caller() because we
+ * can't rely on r2 containing this module's TOC when we enter the stub.
+ *
+ * That can happen if the function calling us didn't need to use the toc. In
+ * that case it won't have setup r2, and the r2 value will be either the
+ * kernel's toc, or possibly another modules toc.
+ *
+ * To deal with that this stub uses the kernel toc, which is always accessible
+ * via the paca (in r13). The target (ftrace_caller()) is responsible for
+ * saving and restoring the toc before returning.
+ */
+static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me)
+{
+	struct ppc64_stub_entry *entry;
+	unsigned int i, num_stubs;
+	static u32 stub_insns[] = {
+		0xe98d0000 | PACATOC, 	/* ld      r12,PACATOC(r13)	*/
+		0x3d8c0000,		/* addis   r12,r12,<high>	*/
+		0x398c0000, 		/* addi    r12,r12,<low>	*/
+		0x7d8903a6, 		/* mtctr   r12			*/
+		0x4e800420, 		/* bctr				*/
+	};
+	long reladdr;
+
+	num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*entry);
+
+	/* Find the next available stub entry */
+	entry = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+	for (i = 0; i < num_stubs && stub_func_addr(entry->funcdata); i++, entry++);
+
+	if (i >= num_stubs) {
+		pr_err("%s: Unable to find a free slot for ftrace stub.\n", me->name);
+		return 0;
+	}
+
+	memcpy(entry->jump, stub_insns, sizeof(stub_insns));
+
+	/* Stub uses address relative to kernel toc (from the paca) */
+	reladdr = (unsigned long)ftrace_caller - kernel_toc_addr();
+	if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+		pr_err("%s: Address of ftrace_caller out of range of kernel_toc.\n", me->name);
+		return 0;
+	}
+
+	entry->jump[1] |= PPC_HA(reladdr);
+	entry->jump[2] |= PPC_LO(reladdr);
+
+	/* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */
+	entry->funcdata = func_desc((unsigned long)ftrace_caller);
+	entry->magic = STUB_MAGIC;
+
+	return (unsigned long)entry;
+}
+#else
+static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me)
+{
+	return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me);
+}
+#endif
+
 int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
 {
 	mod->arch.toc = my_r2(sechdrs, mod);
-	mod->arch.tramp = stub_for_addr(sechdrs, (unsigned long)ftrace_caller, mod);
+	mod->arch.tramp = create_ftrace_stub(sechdrs, mod);
 
 	if (!mod->arch.tramp)
 		return -ENOENT;
-- 
cgit v1.2.3


From c96f83856f56a66a5d7fd730958bec80c9b5a020 Mon Sep 17 00:00:00 2001
From: Torsten Duwe <duwe@lst.de>
Date: Thu, 3 Mar 2016 15:26:57 +1100
Subject: powerpc/ftrace: Use generic ftrace_modify_all_code()

Convert powerpc's arch_ftrace_update_code() from its own version to use
the generic default functionality (without stop_machine -- our
instructions are properly aligned and the replacements atomic).

With this we gain error checking and the much-needed function_trace_op
handling.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/ftrace.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 4505cbfd0e13..62899fbae703 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -449,20 +449,13 @@ void ftrace_replace_code(int enable)
 	}
 }
 
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
 void arch_ftrace_update_code(int command)
 {
-	if (command & FTRACE_UPDATE_CALLS)
-		ftrace_replace_code(1);
-	else if (command & FTRACE_DISABLE_CALLS)
-		ftrace_replace_code(0);
-
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
-		ftrace_update_ftrace_func(ftrace_trace_function);
-
-	if (command & FTRACE_START_FUNC_RET)
-		ftrace_enable_ftrace_graph_caller();
-	else if (command & FTRACE_STOP_FUNC_RET)
-		ftrace_disable_ftrace_graph_caller();
+	ftrace_modify_all_code(command);
 }
 
 int __init ftrace_dyn_arch_init(void)
-- 
cgit v1.2.3


From 9a7841ae8d6ce9b7a7cf879c9968fcf4c9545563 Mon Sep 17 00:00:00 2001
From: Torsten Duwe <duwe@lst.de>
Date: Thu, 3 Mar 2016 15:26:58 +1100
Subject: powerpc/ftrace: Use $(CC_FLAGS_FTRACE) when disabling ftrace

Rather than open-coding -pg whereever we want to disable ftrace, use the
existing $(CC_FLAGS_FTRACE) variable.

This has the advantage that it will work in future when we use a
different set of flags to enable ftrace.

Signed-off-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/Makefile             | 12 ++++++------
 arch/powerpc/lib/Makefile                |  4 ++--
 arch/powerpc/platforms/powermac/Makefile |  2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 794f22adf99d..2da380fcc34c 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -16,14 +16,14 @@ endif
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 # do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 # timers used by tracing
-CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_time.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 endif
 
 obj-y				:= cputable.o ptrace.o syscalls.o \
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index a47e14277fd8..4513d1a706be 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -6,8 +6,8 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-CFLAGS_REMOVE_code-patching.o = -pg
-CFLAGS_REMOVE_feature-fixups.o = -pg
+CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
 obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \
 	 feature-fixups.o
diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile
index 52c6ce1cc985..1eb7b45e017d 100644
--- a/arch/powerpc/platforms/powermac/Makefile
+++ b/arch/powerpc/platforms/powermac/Makefile
@@ -2,7 +2,7 @@ CFLAGS_bootx_init.o  		+= -fPIC
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_bootx_init.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 endif
 
 obj-y				+= pic.o setup.o time.o feature.o pci.o \
-- 
cgit v1.2.3


From 153086644fd1fb07fb3af84d9f11542a19b1e8b6 Mon Sep 17 00:00:00 2001
From: Torsten Duwe <duwe@suse.de>
Date: Thu, 3 Mar 2016 15:26:59 +1100
Subject: powerpc/ftrace: Add support for -mprofile-kernel ftrace ABI

The gcc switch -mprofile-kernel defines a new ABI for calling _mcount()
very early in the function with minimal overhead.

Although mprofile-kernel has been available since GCC 3.4, there were
bugs which were only fixed recently. Currently it is known to work in
GCC 4.9, 5 and 6.

Additionally there are two possible code sequences generated by the
flag, the first uses mflr/std/bl and the second is optimised to omit the
std. Currently only gcc 6 has the optimised sequence. This patch
supports both sequences.

Initial work started by Vojtech Pavlik, used with permission.

Key changes:
 - rework _mcount() to work for both the old and new ABIs.
 - implement new versions of ftrace_caller() and ftrace_graph_caller()
   which deal with the new ABI.
 - updates to __ftrace_make_nop() to recognise the new mcount calling
   sequence.
 - updates to __ftrace_make_call() to recognise the nop'ed sequence.
 - implement ftrace_modify_call().
 - updates to the module loader to surpress the toc save in the module
   stub when calling mcount with the new ABI.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/code-patching.h |  21 ++++
 arch/powerpc/include/asm/ftrace.h        |   5 +
 arch/powerpc/kernel/entry_64.S           | 166 ++++++++++++++++++++++++++++++-
 arch/powerpc/kernel/ftrace.c             | 103 ++++++++++++++++---
 arch/powerpc/kernel/module_64.c          |  49 ++++++++-
 5 files changed, 324 insertions(+), 20 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 840a5509b3f1..994c60a857ce 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -99,4 +99,25 @@ static inline unsigned long ppc_global_function_entry(void *func)
 #endif
 }
 
+#ifdef CONFIG_PPC64
+/*
+ * Some instruction encodings commonly used in dynamic ftracing
+ * and function live patching.
+ */
+
+/* This must match the definition of STK_GOT in <asm/ppc_asm.h> */
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define R2_STACK_OFFSET         24
+#else
+#define R2_STACK_OFFSET         40
+#endif
+
+#define PPC_INST_LD_TOC		(PPC_INST_LD  | ___PPC_RT(__REG_R2) | \
+				 ___PPC_RA(__REG_R1) | R2_STACK_OFFSET)
+
+/* usually preceded by a mflr r0 */
+#define PPC_INST_STD_LR		(PPC_INST_STD | ___PPC_RS(__REG_R0) | \
+				 ___PPC_RA(__REG_R1) | PPC_LR_STKOFF)
+#endif /* CONFIG_PPC64 */
+
 #endif /* _ASM_POWERPC_CODE_PATCHING_H */
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index ef89b1465573..50ca7585abe2 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -46,6 +46,8 @@
 extern void _mcount(void);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+# define FTRACE_ADDR ((unsigned long)ftrace_caller)
+# define FTRACE_REGS_ADDR FTRACE_ADDR
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
        /* reloction of mcount call site is the same as the address */
@@ -58,6 +60,9 @@ struct dyn_arch_ftrace {
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#endif
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 0d525ce3717f..ec7f8aada697 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1143,8 +1143,12 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	blr
+	mflr	r12
+	mtctr	r12
+	mtlr	r0
+	bctr
 
+#ifndef CC_USING_MPROFILE_KERNEL
 _GLOBAL_TOC(ftrace_caller)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3
@@ -1166,6 +1170,115 @@ _GLOBAL(ftrace_graph_stub)
 	ld	r0, 128(r1)
 	mtlr	r0
 	addi	r1, r1, 112
+
+#else /* CC_USING_MPROFILE_KERNEL */
+/*
+ *
+ * ftrace_caller() is the function that replaces _mcount() when ftrace is
+ * active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+_GLOBAL(ftrace_caller)
+	/* Save the original return address in A's stack frame */
+	std	r0,LRSAVE(r1)
+
+	/* Create our stack frame + pt_regs */
+	stdu	r1,-SWITCH_FRAME_SIZE(r1)
+
+	/* Save all gprs to pt_regs */
+	SAVE_8GPRS(0,r1)
+	SAVE_8GPRS(8,r1)
+	SAVE_8GPRS(16,r1)
+	SAVE_8GPRS(24,r1)
+
+	/* Load special regs for save below */
+	mfmsr   r8
+	mfctr   r9
+	mfxer   r10
+	mfcr	r11
+
+	/* Get the _mcount() call site out of LR */
+	mflr	r7
+	/* Save it as pt_regs->nip & pt_regs->link */
+	std     r7, _NIP(r1)
+	std     r7, _LINK(r1)
+
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, 24(r1)
+	ld	r2,PACATOC(r13)	/* get kernel TOC in r2 */
+
+	addis	r3,r2,function_trace_op@toc@ha
+	addi	r3,r3,function_trace_op@toc@l
+	ld	r5,0(r3)
+
+	/* Calculate ip from nip-4 into r3 for call below */
+	subi    r3, r7, MCOUNT_INSN_SIZE
+
+	/* Put the original return address in r4 as parent_ip */
+	mr	r4, r0
+
+	/* Save special regs */
+	std     r8, _MSR(r1)
+	std     r9, _CTR(r1)
+	std     r10, _XER(r1)
+	std     r11, _CCR(r1)
+
+	/* Load &pt_regs in r6 for call below */
+	addi    r6, r1 ,STACK_FRAME_OVERHEAD
+
+	/* ftrace_call(r3, r4, r5, r6) */
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
+
+	/* Restore gprs */
+	REST_8GPRS(0,r1)
+	REST_8GPRS(8,r1)
+	REST_8GPRS(16,r1)
+	REST_8GPRS(24,r1)
+
+	/* Restore callee's TOC */
+	ld	r2, 24(r1)
+
+	/* Pop our stack frame */
+	addi r1, r1, SWITCH_FRAME_SIZE
+
+	/* Restore original LR for return to B */
+	ld	r0, LRSAVE(r1)
+	mtlr	r0
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	stdu	r1, -112(r1)
+.globl ftrace_graph_call
+ftrace_graph_call:
+	b	ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+	addi	r1, r1, 112
+#endif
+
+	ld	r0,LRSAVE(r1)	/* restore callee's lr at _mcount site */
+	mtlr	r0
+	bctr			/* jump after _mcount site */
+#endif /* CC_USING_MPROFILE_KERNEL */
+
 _GLOBAL(ftrace_stub)
 	blr
 #else
@@ -1198,6 +1311,7 @@ _GLOBAL(ftrace_stub)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifndef CC_USING_MPROFILE_KERNEL
 _GLOBAL(ftrace_graph_caller)
 	/* load r4 with local address */
 	ld	r4, 128(r1)
@@ -1222,6 +1336,56 @@ _GLOBAL(ftrace_graph_caller)
 	addi	r1, r1, 112
 	blr
 
+#else /* CC_USING_MPROFILE_KERNEL */
+_GLOBAL(ftrace_graph_caller)
+	/* with -mprofile-kernel, parameter regs are still alive at _mcount */
+	std	r10, 104(r1)
+	std	r9, 96(r1)
+	std	r8, 88(r1)
+	std	r7, 80(r1)
+	std	r6, 72(r1)
+	std	r5, 64(r1)
+	std	r4, 56(r1)
+	std	r3, 48(r1)
+
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, 24(r1)
+	ld	r2, PACATOC(r13)	/* get kernel TOC in r2 */
+
+	mfctr	r4		/* ftrace_caller has moved local addr here */
+	std	r4, 40(r1)
+	mflr	r3		/* ftrace_caller has restored LR from stack */
+	subi	r4, r4, MCOUNT_INSN_SIZE
+
+	bl	prepare_ftrace_return
+	nop
+
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR to this.
+	 */
+	mtlr	r3
+
+	ld	r0, 40(r1)
+	mtctr	r0
+	ld	r10, 104(r1)
+	ld	r9, 96(r1)
+	ld	r8, 88(r1)
+	ld	r7, 80(r1)
+	ld	r6, 72(r1)
+	ld	r5, 64(r1)
+	ld	r4, 56(r1)
+	ld	r3, 48(r1)
+
+	/* Restore callee's TOC */
+	ld	r2, 24(r1)
+
+	addi	r1, r1, 112
+	mflr	r0
+	std	r0, LRSAVE(r1)
+	bctr
+#endif /* CC_USING_MPROFILE_KERNEL */
+
 _GLOBAL(return_to_handler)
 	/* need to save return values */
 	std	r4,  -32(r1)
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 62899fbae703..9dac18dabd03 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
-	if (replaced != old)
+	if (replaced != old) {
+		pr_err("%p: replaced (%#x) != old (%#x)",
+		(void *)ip, replaced, old);
 		return -EINVAL;
+	}
 
 	/* replace the text with the new text */
 	if (patch_instruction((unsigned int *)ip, new))
@@ -108,11 +111,13 @@ __ftrace_make_nop(struct module *mod,
 {
 	unsigned long entry, ptr, tramp;
 	unsigned long ip = rec->ip;
-	unsigned int op;
+	unsigned int op, pop;
 
 	/* read where this goes */
-	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
+	if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+		pr_err("Fetching opcode failed.\n");
 		return -EFAULT;
+	}
 
 	/* Make sure that that this is still a 24bit jump */
 	if (!is_bl_op(op)) {
@@ -152,10 +157,42 @@ __ftrace_make_nop(struct module *mod,
 	 *
 	 * Use a b +8 to jump over the load.
 	 */
-	op = 0x48000008;	/* b +8 */
 
-	if (patch_instruction((unsigned int *)ip, op))
+	pop = PPC_INST_BRANCH | 8;	/* b +8 */
+
+	/*
+	 * Check what is in the next instruction. We can see ld r2,40(r1), but
+	 * on first pass after boot we will see mflr r0.
+	 */
+	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) {
+		pr_err("Fetching op failed.\n");
+		return -EFAULT;
+	}
+
+	if (op != PPC_INST_LD_TOC) {
+		unsigned int inst;
+
+		if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) {
+			pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+			return -EFAULT;
+		}
+
+		/* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */
+		if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) {
+			pr_err("Unexpected instructions around bl _mcount\n"
+			       "when enabling dynamic ftrace!\t"
+			       "(%08x,bl,%08x)\n", inst, op);
+			return -EINVAL;
+		}
+
+		/* When using -mkernel_profile there is no load to jump over */
+		pop = PPC_INST_NOP;
+	}
+
+	if (patch_instruction((unsigned int *)ip, pop)) {
+		pr_err("Patching NOP failed.\n");
 		return -EPERM;
+	}
 
 	return 0;
 }
@@ -281,16 +318,15 @@ int ftrace_make_nop(struct module *mod,
 
 #ifdef CONFIG_MODULES
 #ifdef CONFIG_PPC64
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+#ifndef CC_USING_MPROFILE_KERNEL
 static int
-__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
 {
-	unsigned int op[2];
-	void *ip = (void *)rec->ip;
-
-	/* read where this goes */
-	if (probe_kernel_read(op, ip, sizeof(op)))
-		return -EFAULT;
-
 	/*
 	 * We expect to see:
 	 *
@@ -300,8 +336,34 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	 * The load offset is different depending on the ABI. For simplicity
 	 * just mask it out when doing the compare.
 	 */
-	if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
-		pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
+	if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000))
+		return 0;
+	return 1;
+}
+#else
+static int
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+{
+	/* look for patched "NOP" on ppc64 with -mprofile-kernel */
+	if (op0 != PPC_INST_NOP)
+		return 0;
+	return 1;
+}
+#endif
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op[2];
+	void *ip = (void *)rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(op, ip, sizeof(op)))
+		return -EFAULT;
+
+	if (!expected_nop_sequence(ip, op[0], op[1])) {
+		pr_err("Unexpected call sequence at %p: %x %x\n",
+		ip, op[0], op[1]);
 		return -EINVAL;
 	}
 
@@ -324,7 +386,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	return 0;
 }
-#else
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	return ftrace_make_call(rec, addr);
+}
+#endif
+
+#else  /* !CONFIG_PPC64: */
 static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 76c0963572f5..848b47499a27 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -42,7 +42,6 @@
    --RR.  */
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
-#define R2_STACK_OFFSET 24
 
 /* An address is simply the address of the function. */
 typedef unsigned long func_desc_t;
@@ -74,7 +73,6 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym)
 	return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
 }
 #else
-#define R2_STACK_OFFSET 40
 
 /* An address is address of the OPD entry, which contains address of fn. */
 typedef struct ppc64_opd_entry func_desc_t;
@@ -451,17 +449,60 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
 	return (unsigned long)&stubs[i];
 }
 
+#ifdef CC_USING_MPROFILE_KERNEL
+static bool is_early_mcount_callsite(u32 *instruction)
+{
+	/*
+	 * Check if this is one of the -mprofile-kernel sequences.
+	 */
+	if (instruction[-1] == PPC_INST_STD_LR &&
+	    instruction[-2] == PPC_INST_MFLR)
+		return true;
+
+	if (instruction[-1] == PPC_INST_MFLR)
+		return true;
+
+	return false;
+}
+
+/*
+ * In case of _mcount calls, do not save the current callee's TOC (in r2) into
+ * the original caller's stack frame. If we did we would clobber the saved TOC
+ * value of the original caller.
+ */
+static void squash_toc_save_inst(const char *name, unsigned long addr)
+{
+	struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr;
+
+	/* Only for calls to _mcount */
+	if (strcmp("_mcount", name) != 0)
+		return;
+
+	stub->jump[2] = PPC_INST_NOP;
+}
+#else
+static void squash_toc_save_inst(const char *name, unsigned long addr) { }
+
+/* without -mprofile-kernel, mcount calls are never early */
+static bool is_early_mcount_callsite(u32 *instruction)
+{
+	return false;
+}
+#endif
+
 /* We expect a noop next: if it is, replace it with instruction to
    restore r2. */
 static int restore_r2(u32 *instruction, struct module *me)
 {
 	if (*instruction != PPC_INST_NOP) {
+		if (is_early_mcount_callsite(instruction - 1))
+			return 1;
 		pr_err("%s: Expect noop after relocate, got %08x\n",
 		       me->name, *instruction);
 		return 0;
 	}
 	/* ld r2,R2_STACK_OFFSET(r1) */
-	*instruction = 0xe8410000 | R2_STACK_OFFSET;
+	*instruction = PPC_INST_LD_TOC;
 	return 1;
 }
 
@@ -586,6 +627,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 					return -ENOENT;
 				if (!restore_r2((u32 *)location + 1, me))
 					return -ENOEXEC;
+
+				squash_toc_save_inst(strtab + sym->st_name, value);
 			} else
 				value += local_entry_offset(sym);
 
-- 
cgit v1.2.3


From 5d31a96e6c0187f2c5d7004e005fd094a1277e9e Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 24 Mar 2016 22:04:04 +1100
Subject: powerpc/livepatch: Add livepatch stack to struct thread_info

In order to support live patching we need to maintain an alternate
stack of TOC & LR values. We use the base of the stack for this, and
store the "live patch stack pointer" in struct thread_info.

Unlike the other fields of thread_info, we can not statically initialise
that value, so it must be done at run time.

This patch just adds the code to support that, it is not enabled until
the next patch which actually adds live patch support.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Balbir Singh <bsingharora@gmail.com>
---
 arch/powerpc/include/asm/livepatch.h   |  8 ++++++++
 arch/powerpc/include/asm/thread_info.h |  4 +++-
 arch/powerpc/kernel/irq.c              |  3 +++
 arch/powerpc/kernel/process.c          |  6 +++++-
 arch/powerpc/kernel/setup_64.c         | 17 ++++++++++-------
 5 files changed, 29 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index ad36e8e34fa1..a402f7f94896 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -49,6 +49,14 @@ static inline unsigned long klp_get_ftrace_location(unsigned long faddr)
 	 */
 	return ftrace_location_range(faddr, faddr + 16);
 }
+
+static inline void klp_init_thread_info(struct thread_info *ti)
+{
+	/* + 1 to account for STACK_END_MAGIC */
+	ti->livepatch_sp = (unsigned long *)(ti + 1) + 1;
+}
+#else
+static void klp_init_thread_info(struct thread_info *ti) { }
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _ASM_POWERPC_LIVEPATCH_H */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 7efee4a3240b..8febc3f66d53 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -43,7 +43,9 @@ struct thread_info {
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
 	unsigned long	local_flags;		/* private flags for thread */
-
+#ifdef CONFIG_LIVEPATCH
+	unsigned long *livepatch_sp;
+#endif
 	/* low level flags - has atomic operations done on it */
 	unsigned long	flags ____cacheline_aligned_in_smp;
 };
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 290559df1e8b..3cb46a3b1de7 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -66,6 +66,7 @@
 #include <asm/udbg.h>
 #include <asm/smp.h>
 #include <asm/debug.h>
+#include <asm/livepatch.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -607,10 +608,12 @@ void irq_ctx_init(void)
 		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
 		tp = softirq_ctx[i];
 		tp->cpu = i;
+		klp_init_thread_info(tp);
 
 		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
 		tp = hardirq_ctx[i];
 		tp->cpu = i;
+		klp_init_thread_info(tp);
 	}
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index dccc87e8fee5..a38ce49648cb 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -55,6 +55,8 @@
 #include <asm/firmware.h>
 #endif
 #include <asm/code-patching.h>
+#include <asm/livepatch.h>
+
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
@@ -1267,13 +1269,15 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	extern void ret_from_kernel_thread(void);
 	void (*f)(void);
 	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
+	struct thread_info *ti = task_thread_info(p);
+
+	klp_init_thread_info(ti);
 
 	/* Copy registers */
 	sp -= sizeof(struct pt_regs);
 	childregs = (struct pt_regs *) sp;
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* kernel thread */
-		struct thread_info *ti = (void *)task_stack_page(p);
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
 		/* function */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5c03a6a9b054..e37b92ebb315 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -69,6 +69,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/hugetlb.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/livepatch.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -670,16 +671,16 @@ static void __init emergency_stack_init(void)
 	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
-		unsigned long sp;
-		sp  = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
-		sp += THREAD_SIZE;
-		paca[i].emergency_sp = __va(sp);
+		struct thread_info *ti;
+		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+		klp_init_thread_info(ti);
+		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for machine check exception handling. */
-		sp  = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
-		sp += THREAD_SIZE;
-		paca[i].mc_emergency_sp = __va(sp);
+		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+		klp_init_thread_info(ti);
+		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
 }
@@ -703,6 +704,8 @@ void __init setup_arch(char **cmdline_p)
 	if (ppc_md.panic)
 		setup_panic();
 
+	klp_init_thread_info(&init_thread_info);
+
 	init_mm.start_code = (unsigned long)_stext;
 	init_mm.end_code = (unsigned long) _etext;
 	init_mm.end_data = (unsigned long) _edata;
-- 
cgit v1.2.3


From 85baa095497f3e590df9f6c8932121f123efca5c Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 24 Mar 2016 22:04:05 +1100
Subject: powerpc/livepatch: Add live patching support on ppc64le

Add the kconfig logic & assembly support for handling live patched
functions. This depends on DYNAMIC_FTRACE_WITH_REGS, which in turn
depends on the new -mprofile-kernel ftrace ABI, which is only supported
currently on ppc64le.

Live patching is handled by a special ftrace handler. This means it runs
from ftrace_caller(). The live patch handler modifies the NIP so as to
redirect the return from ftrace_caller() to the new patched function.

However there is one particularly tricky case we need to handle.

If a function A calls another function B, and it is known at link time
that they share the same TOC, then A will not save or restore its TOC,
and will call the local entry point of B.

When we live patch B, we replace it with a new function C, which may
not have the same TOC as A. At live patch time it's too late to modify A
to do the TOC save/restore, so the live patching code must interpose
itself between A and C, and do the TOC save/restore that A omitted.

An additionaly complication is that the livepatch code can not create a
stack frame in order to save the TOC. That is because if C takes > 8
arguments, or is varargs, A will have written the arguments for C in
A's stack frame.

To solve this, we introduce a "livepatch stack" which grows upward from
the base of the regular stack, and is used to store the TOC & LR when
calling a live patched function.

When the patched function returns, we retrieve the real LR & TOC from
the livepatch stack, restore them, and pop the livepatch "stack frame".

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Reviewed-by: Balbir Singh <bsingharora@gmail.com>
---
 arch/powerpc/Kconfig              |  3 ++
 arch/powerpc/kernel/asm-offsets.c |  4 ++
 arch/powerpc/kernel/entry_64.S    | 97 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 104 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 91da283cd658..926c0eafbee3 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -159,6 +159,7 @@ config PPC
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select HAVE_ARCH_SECCOMP_FILTER
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -1110,3 +1111,5 @@ config PPC_LIB_RHEAP
 	bool
 
 source "arch/powerpc/kvm/Kconfig"
+
+source "kernel/livepatch/Kconfig"
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 07cebc3514f3..723efac2d917 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -86,6 +86,10 @@ int main(void)
 	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 #endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_LIVEPATCH
+	DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp));
+#endif
+
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ec7f8aada697..47dbede3bddd 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -20,6 +20,7 @@
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/magic.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/page.h>
@@ -1224,6 +1225,9 @@ _GLOBAL(ftrace_caller)
 	addi	r3,r3,function_trace_op@toc@l
 	ld	r5,0(r3)
 
+#ifdef CONFIG_LIVEPATCH
+	mr	r14,r7		/* remember old NIP */
+#endif
 	/* Calculate ip from nip-4 into r3 for call below */
 	subi    r3, r7, MCOUNT_INSN_SIZE
 
@@ -1248,6 +1252,9 @@ ftrace_call:
 	/* Load ctr with the possibly modified NIP */
 	ld	r3, _NIP(r1)
 	mtctr	r3
+#ifdef CONFIG_LIVEPATCH
+	cmpd	r14,r3		/* has NIP been altered? */
+#endif
 
 	/* Restore gprs */
 	REST_8GPRS(0,r1)
@@ -1265,6 +1272,11 @@ ftrace_call:
 	ld	r0, LRSAVE(r1)
 	mtlr	r0
 
+#ifdef CONFIG_LIVEPATCH
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+	bne-	livepatch_handler
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	stdu	r1, -112(r1)
 .globl ftrace_graph_call
@@ -1281,6 +1293,91 @@ _GLOBAL(ftrace_graph_stub)
 
 _GLOBAL(ftrace_stub)
 	blr
+
+#ifdef CONFIG_LIVEPATCH
+	/*
+	 * This function runs in the mcount context, between two functions. As
+	 * such it can only clobber registers which are volatile and used in
+	 * function linkage.
+	 *
+	 * We get here when a function A, calls another function B, but B has
+	 * been live patched with a new function C.
+	 *
+	 * On entry:
+	 *  - we have no stack frame and can not allocate one
+	 *  - LR points back to the original caller (in A)
+	 *  - CTR holds the new NIP in C
+	 *  - r0 & r12 are free
+	 *
+	 * r0 can't be used as the base register for a DS-form load or store, so
+	 * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
+	 */
+livepatch_handler:
+	CURRENT_THREAD_INFO(r12, r1)
+
+	/* Save stack pointer into r0 */
+	mr	r0, r1
+
+	/* Allocate 3 x 8 bytes */
+	ld	r1, TI_livepatch_sp(r12)
+	addi	r1, r1, 24
+	std	r1, TI_livepatch_sp(r12)
+
+	/* Save toc & real LR on livepatch stack */
+	std	r2,  -24(r1)
+	mflr	r12
+	std	r12, -16(r1)
+
+	/* Store stack end marker */
+	lis     r12, STACK_END_MAGIC@h
+	ori     r12, r12, STACK_END_MAGIC@l
+	std	r12, -8(r1)
+
+	/* Restore real stack pointer */
+	mr	r1, r0
+
+	/* Put ctr in r12 for global entry and branch there */
+	mfctr	r12
+	bctrl
+
+	/*
+	 * Now we are returning from the patched function to the original
+	 * caller A. We are free to use r0 and r12, and we can use r2 until we
+	 * restore it.
+	 */
+
+	CURRENT_THREAD_INFO(r12, r1)
+
+	/* Save stack pointer into r0 */
+	mr	r0, r1
+
+	ld	r1, TI_livepatch_sp(r12)
+
+	/* Check stack marker hasn't been trashed */
+	lis     r2,  STACK_END_MAGIC@h
+	ori     r2,  r2, STACK_END_MAGIC@l
+	ld	r12, -8(r1)
+1:	tdne	r12, r2
+	EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
+
+	/* Restore LR & toc from livepatch stack */
+	ld	r12, -16(r1)
+	mtlr	r12
+	ld	r2,  -24(r1)
+
+	/* Pop livepatch stack frame */
+	CURRENT_THREAD_INFO(r12, r0)
+	subi	r1, r1, 24
+	std	r1, TI_livepatch_sp(r12)
+
+	/* Restore real stack pointer */
+	mr	r1, r0
+
+	/* Return to original caller of live patched function */
+	blr
+#endif
+
+
 #else
 _GLOBAL_TOC(_mcount)
 	/* Taken from output of objdump from lib64/glibc */
-- 
cgit v1.2.3