From 18db466a9a306406dab3b134014d9f6ed642471c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 2 Aug 2022 11:02:36 +0200 Subject: [PATCH 1/6] powerpc: Fix eh field when calling lwarx on PPC32 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 9401f4e46cf6 ("powerpc: Use lwarx/ldarx directly instead of PPC_LWARX/LDARX macros") properly handled the eh field of lwarx in asm/bitops.h but failed to clear it for PPC32 in asm/simple_spinlock.h So, do as in arch_atomic_try_cmpxchg_lock(), set it to 1 if PPC64 but set it to 0 if PPC32. For that use IS_ENABLED(CONFIG_PPC64) which returns 1 when CONFIG_PPC64 is set and 0 otherwise. Fixes: 9401f4e46cf6 ("powerpc: Use lwarx/ldarx directly instead of PPC_LWARX/LDARX macros") Cc: stable@vger.kernel.org # v5.15+ Reported-by: Pali Rohár Signed-off-by: Christophe Leroy Tested-by: Pali Rohár Reviewed-by: Segher Boessenkool [mpe: Use symbolic names, use 'n' constraint per Segher] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a1176e19e627dd6a1b8d24c6c457a8ab874b7d12.1659430931.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/simple_spinlock.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h index 7ae6aeef8464..9dcc7e9993b9 100644 --- a/arch/powerpc/include/asm/simple_spinlock.h +++ b/arch/powerpc/include/asm/simple_spinlock.h @@ -48,10 +48,11 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock) static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) { unsigned long tmp, token; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); token = LOCK_TOKEN; __asm__ __volatile__( -"1: lwarx %0,0,%2,1\n\ +"1: lwarx %0,0,%2,%[eh]\n\ cmpwi 0,%0,0\n\ bne- 2f\n\ stwcx. %1,0,%2\n\ @@ -59,7 +60,7 @@ static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) PPC_ACQUIRE_BARRIER "2:" : "=&r" (tmp) - : "r" (token), "r" (&lock->slock) + : "r" (token), "r" (&lock->slock), [eh] "n" (eh) : "cr0", "memory"); return tmp; @@ -156,9 +157,10 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) static inline long __arch_read_trylock(arch_rwlock_t *rw) { long tmp; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); __asm__ __volatile__( -"1: lwarx %0,0,%1,1\n" +"1: lwarx %0,0,%1,%[eh]\n" __DO_SIGN_EXTEND " addic. %0,%0,1\n\ ble- 2f\n" @@ -166,7 +168,7 @@ static inline long __arch_read_trylock(arch_rwlock_t *rw) bne- 1b\n" PPC_ACQUIRE_BARRIER "2:" : "=&r" (tmp) - : "r" (&rw->lock) + : "r" (&rw->lock), [eh] "n" (eh) : "cr0", "xer", "memory"); return tmp; @@ -179,17 +181,18 @@ static inline long __arch_read_trylock(arch_rwlock_t *rw) static inline long __arch_write_trylock(arch_rwlock_t *rw) { long tmp, token; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); token = WRLOCK_TOKEN; __asm__ __volatile__( -"1: lwarx %0,0,%2,1\n\ +"1: lwarx %0,0,%2,%[eh]\n\ cmpwi 0,%0,0\n\ bne- 2f\n" " stwcx. %1,0,%2\n\ bne- 1b\n" PPC_ACQUIRE_BARRIER "2:" : "=&r" (tmp) - : "r" (token), "r" (&rw->lock) + : "r" (token), "r" (&rw->lock), [eh] "n" (eh) : "cr0", "memory"); return tmp; From eb5a33ea31190c189ca4a59de4687b0877662c06 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 2 Aug 2022 11:02:37 +0200 Subject: [PATCH 2/6] powerpc: Don't hide eh field of lwarx behind a macro The eh field must remain 0 for PPC32 and is only used by PPC64. Don't hide that behind a macro, just leave the responsibility to the user. At the time being, the only users of PPC_RAW_L{WDQ}ARX are setting the eh field to 0, so the special handling of __PPC_EH is useless. Just take the value given by the caller. Same for DEFINE_TESTOP(), don't do special handling in that macro, ensure the caller hands over the proper eh value. Signed-off-by: Christophe Leroy [mpe: Use 'n' constraint per Segher] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/8b9c8a1a14f9143552a85fcbf96698224a8c2469.1659430931.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/bitops.h | 4 ++-- arch/powerpc/include/asm/ppc-opcode.h | 11 +---------- 2 files changed, 3 insertions(+), 12 deletions(-) diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 344fba3b16eb..7e0f0322912b 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -163,7 +163,7 @@ static inline unsigned long fn( \ "bne- 1b\n" \ postfix \ : "=&r" (old), "=&r" (t) \ - : "rK" (mask), "r" (p), "i" (IS_ENABLED(CONFIG_PPC64) ? eh : 0) \ + : "rK" (mask), "r" (p), "n" (eh) \ : "cc", "memory"); \ return (old & mask); \ } @@ -171,7 +171,7 @@ static inline unsigned long fn( \ DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, 0) DEFINE_TESTOP(test_and_set_bits_lock, or, "", - PPC_ACQUIRE_BARRIER, 1) + PPC_ACQUIRE_BARRIER, IS_ENABLED(CONFIG_PPC64)) DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, 0) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 7b81b37a191e..d9703c5fd713 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -343,6 +343,7 @@ #define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11)) #define __PPC_RC21 (0x1 << 10) #define __PPC_PRFX_R(r) (((r) & 0x1) << 20) +#define __PPC_EH(eh) (((eh) & 0x1) << 0) /* * Both low and high 16 bits are added as SIGNED additions, so if low 16 bits @@ -359,16 +360,6 @@ #define PPC_LI_MASK 0x03fffffc #define PPC_LI(v) ((v) & PPC_LI_MASK) -/* - * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a - * larx with EH set as an illegal instruction. - */ -#ifdef CONFIG_PPC64 -#define __PPC_EH(eh) (((eh) & 0x1) << 0) -#else -#define __PPC_EH(eh) 0 -#endif - /* Base instruction encoding */ #define PPC_RAW_CP_ABORT (0x7c00068c) #define PPC_RAW_COPY(a, b) (PPC_INST_COPY | ___PPC_RA(a) | ___PPC_RB(b)) From 5cccf7a5215d12027e55e247907817631b413c28 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 2 Aug 2022 11:02:38 +0200 Subject: [PATCH 3/6] powerpc: Make eh value more explicit when using lwarx Just like the first patch of this series, define a local 'eh' in order to make the code clearer. And IS_ENABLED() returns either 1 or 0 so no need to do IS_ENABLED(CONFIG_PPC64) ? 1 : 0. Signed-off-by: Christophe Leroy [mpe: Use symbolic names, use 'n' constraint per Segher] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/629befaa2d05e2922346e58a383886510d6af55a.1659430931.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/atomic.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 853dc86864f4..486ab7889121 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -140,9 +140,10 @@ static __always_inline bool arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new) { int r, o = *old; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); __asm__ __volatile__ ( -"1: lwarx %0,0,%2,%5 # atomic_try_cmpxchg_acquire \n" +"1: lwarx %0,0,%2,%[eh] # atomic_try_cmpxchg_acquire \n" " cmpw 0,%0,%3 \n" " bne- 2f \n" " stwcx. %4,0,%2 \n" @@ -150,7 +151,7 @@ arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new) "\t" PPC_ACQUIRE_BARRIER " \n" "2: \n" : "=&r" (r), "+m" (v->counter) - : "r" (&v->counter), "r" (o), "r" (new), "i" (IS_ENABLED(CONFIG_PPC64) ? 1 : 0) + : "r" (&v->counter), "r" (o), "r" (new), [eh] "n" (eh) : "cr0", "memory"); if (unlikely(r != o)) From cb928ac192128c842f4c1cfc8b6780b95719d65f Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Tue, 9 Aug 2022 15:29:07 +0530 Subject: [PATCH 4/6] powerpc64/ftrace: Fix ftrace for clang builds Clang doesn't support -mprofile-kernel ABI, so guard the checks against CONFIG_DYNAMIC_FTRACE_WITH_REGS, rather than the elf ABI version. Fixes: 23b44fc248f4 ("powerpc/ftrace: Make __ftrace_make_{nop/call}() common to PPC32 and PPC64") Cc: stable@vger.kernel.org # v5.19+ Reported-by: Nick Desaulniers Reported-by: Ondrej Mosnacek Signed-off-by: Naveen N. Rao Tested-by: Ondrej Mosnacek Acked-by: Nick Desaulniers Signed-off-by: Michael Ellerman Link: https://github.com/llvm/llvm-project/issues/57031 Link: https://github.com/ClangBuiltLinux/linux/issues/1682 Link: https://lore.kernel.org/r/20220809095907.418764-1-naveen.n.rao@linux.vnet.ibm.com --- arch/powerpc/kernel/trace/ftrace.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index cb158c32b50b..7b85c3b460a3 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -393,11 +393,11 @@ int ftrace_make_nop(struct module *mod, */ static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1) { - if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1)) + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())); + else return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) && ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC)); - else - return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())); } static int @@ -412,7 +412,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (copy_inst_from_kernel_nofault(op, ip)) return -EFAULT; - if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1) && + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && copy_inst_from_kernel_nofault(op + 1, ip + 4)) return -EFAULT; From 59bab33a4f57f886c5f8a4d1f2bed728ec185d16 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 3 Aug 2022 13:47:33 +0200 Subject: [PATCH 5/6] powerpc/ppc-opcode: Fix PPC_RAW_TW() PPC_RAW_TW() is erroneously defined with base code 0x7f000008 instead of 0x7c000008. That's invisible because its only user is PPC_RAW_TRAP() which is 0x7fe00008, but fix it anyway to avoid any risk of future bug. Fixes: d00d762daf12 ("powerpc/ppc-opcode: Define and use PPC_RAW_TRAP() and PPC_RAW_TW()") Reported-by: Naveen N. Rao Signed-off-by: Christophe Leroy Reviewed-by: Naveen N. Rao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/eca9251f1e1f82c4c46ec6380ddb28356ab3fdfe.1659527244.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/ppc-opcode.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index d9703c5fd713..c6d724104ed1 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -571,7 +571,7 @@ #define PPC_RAW_BRANCH(offset) (0x48000000 | PPC_LI(offset)) #define PPC_RAW_BL(offset) (0x48000001 | PPC_LI(offset)) -#define PPC_RAW_TW(t0, a, b) (0x7f000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_TW(t0, a, b) (0x7c000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_TRAP() PPC_RAW_TW(31, 0, 0) #define PPC_RAW_SETB(t, bfa) (0x7c000100 | ___PPC_RT(t) | ___PPC_RA((bfa) << 2)) From 83ee9f23763a432a4077bf20624ee35de87bce99 Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Wed, 10 Aug 2022 15:43:31 +1000 Subject: [PATCH 6/6] powerpc/kexec: Fix build failure from uninitialised variable clang 14 won't build because ret is uninitialised and can be returned if both prop and fdtprop are NULL. Drop the ret variable and return an error in that failure case. Fixes: b1fc44eaa9ba ("pseries/iommu/ddw: Fix kdump to work in absence of ibm,dma-window") Suggested-by: Christophe Leroy Signed-off-by: Russell Currey Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220810054331.373761-1-ruscur@russell.cc --- arch/powerpc/kexec/file_load_64.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 683462e4556b..349a781cea0b 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -1043,17 +1043,17 @@ static int copy_property(void *fdt, int node_offset, const struct device_node *d const char *propname) { const void *prop, *fdtprop; - int len = 0, fdtlen = 0, ret; + int len = 0, fdtlen = 0; prop = of_get_property(dn, propname, &len); fdtprop = fdt_getprop(fdt, node_offset, propname, &fdtlen); if (fdtprop && !prop) - ret = fdt_delprop(fdt, node_offset, propname); + return fdt_delprop(fdt, node_offset, propname); else if (prop) - ret = fdt_setprop(fdt, node_offset, propname, prop, len); - - return ret; + return fdt_setprop(fdt, node_offset, propname, prop, len); + else + return -FDT_ERR_NOTFOUND; } static int update_pci_dma_nodes(void *fdt, const char *dmapropname)