4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Al Viro viro@zeniv.linux.org.uk

commit 4faa99965e027cc057c5145ce45fa772caa04e8d upstream.

If io_destroy() gets to cancelling everything that can be cancelled and gets to kiocb_cancel() calling the function driver has left in ->ki_cancel, it becomes vulnerable to a race with IO completion. At that point req is already taken off the list and aio_complete() does *NOT* spin until we (in free_ioctx_users()) releases ->ctx_lock. As the result, it proceeds to kiocb_free(), freing req just it gets passed to ->ki_cancel().

Fix is simple - remove from the list after the call of kiocb_cancel(). All instances of ->ki_cancel() already have to cope with the being called with iocb still on list - that's what happens in io_cancel(2).

Cc: stable@kernel.org Fixes: 0460fef2a921 "aio: use cancellation list lazily" Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/aio.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/fs/aio.c +++ b/fs/aio.c @@ -643,9 +643,8 @@ static void free_ioctx_users(struct perc while (!list_empty(&ctx->active_reqs)) { req = list_first_entry(&ctx->active_reqs, struct aio_kiocb, ki_list); - - list_del_init(&req->ki_list); kiocb_cancel(req); + list_del_init(&req->ki_list); }

spin_unlock_irq(&ctx->ctx_lock);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josh Poimboeuf jpoimboe@redhat.com

commit 13810435b9a7014fb92eb715f77da488f3b65b99 upstream.

GCC 8 moves a lot of unlikely code out of line to "cold" subfunctions in .text.unlikely. Properly detect the new subfunctions and treat them as extensions of the original functions.

This fixes a bunch of warnings like:

kernel/cgroup/cgroup.o: warning: objtool: parse_cgroup_root_flags()+0x33: sibling call from callable instruction with modified stack frame kernel/cgroup/cgroup.o: warning: objtool: cgroup_addrm_files()+0x290: sibling call from callable instruction with modified stack frame kernel/cgroup/cgroup.o: warning: objtool: cgroup_apply_control_enable()+0x25b: sibling call from callable instruction with modified stack frame kernel/cgroup/cgroup.o: warning: objtool: rebind_subsystems()+0x325: sibling call from callable instruction with modified stack frame

Reported-and-tested-by: damian damian.tometzki@icloud.com Reported-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: David Laight David.Laight@ACULAB.COM Cc: Greg KH gregkh@linuxfoundation.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Randy Dunlap rdunlap@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Link: http://lkml.kernel.org/r/0965e7fcfc5f31a276f0c7f298ff770c19b68706.1525923412... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/objtool/check.c | 93 +++++++++++++++++++++++++++----------------------- tools/objtool/elf.c | 42 +++++++++++++++++++++- tools/objtool/elf.h | 2 + 3 files changed, 93 insertions(+), 44 deletions(-)

--- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -59,6 +59,31 @@ static struct instruction *next_insn_sam return next; }

+static struct instruction *next_insn_same_func(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *next = list_next_entry(insn, list); + struct symbol *func = insn->func; + + if (!func) + return NULL; + + if (&next->list != &file->insn_list && next->func == func) + return next; + + /* Check if we're already in the subfunction: */ + if (func == func->cfunc) + return NULL; + + /* Move to the subfunction: */ + return find_insn(file, func->cfunc->sec, func->cfunc->offset); +} + +#define func_for_each_insn_all(file, func, insn) \ + for (insn = find_insn(file, func->sec, func->offset); \ + insn; \ + insn = next_insn_same_func(file, insn)) + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn && &insn->list != &file->insn_list && \ @@ -148,10 +173,14 @@ static int __dead_end_function(struct ob if (!strcmp(func->name, global_noreturns[i])) return 1;

- if (!func->sec) + if (!func->len) + return 0; + + insn = find_insn(file, func->sec, func->offset); + if (!insn->func) return 0;

- func_for_each_insn(file, func, insn) { + func_for_each_insn_all(file, func, insn) { empty = false;

if (insn->type == INSN_RETURN) @@ -166,35 +195,24 @@ static int __dead_end_function(struct ob * case, the function's dead-end status depends on whether the target * of the sibling call returns. */ - func_for_each_insn(file, func, insn) { - if (insn->sec != func->sec || - insn->offset >= func->offset + func->len) - break; - + func_for_each_insn_all(file, func, insn) { if (insn->type == INSN_JUMP_UNCONDITIONAL) { struct instruction *dest = insn->jump_dest; - struct symbol *dest_func;

if (!dest) /* sibling call to another file */ return 0;

- if (dest->sec != func->sec || - dest->offset < func->offset || - dest->offset >= func->offset + func->len) { - /* local sibling call */ - dest_func = find_symbol_by_offset(dest->sec, - dest->offset); - if (!dest_func) - continue; + if (dest->func && dest->func->pfunc != insn->func->pfunc) {

+ /* local sibling call */ if (recursion == 5) { WARN_FUNC("infinite recursion (objtool bug!)", dest->sec, dest->offset); return -1; }

- return __dead_end_function(file, dest_func, + return __dead_end_function(file, dest->func, recursion + 1); } } @@ -421,7 +439,7 @@ static void add_ignores(struct objtool_f if (!ignore_func(file, func)) continue;

- func_for_each_insn(file, func, insn) + func_for_each_insn_all(file, func, insn) insn->ignore = true; } } @@ -781,9 +799,8 @@ out: return ret; }

-static int add_switch_table(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct rela *table, - struct rela *next_table) +static int add_switch_table(struct objtool_file *file, struct instruction *insn, + struct rela *table, struct rela *next_table) { struct rela *rela = table; struct instruction *alt_insn; @@ -793,18 +810,13 @@ static int add_switch_table(struct objto if (rela == next_table) break;

- if (rela->sym->sec != insn->sec || - rela->addend <= func->offset || - rela->addend >= func->offset + func->len) + alt_insn = find_insn(file, rela->sym->sec, rela->addend); + if (!alt_insn) break;

- alt_insn = find_insn(file, insn->sec, rela->addend); - if (!alt_insn) { - WARN("%s: can't find instruction at %s+0x%x", - file->rodata->rela->name, insn->sec->name, - rela->addend); - return -1; - } + /* Make sure the jmp dest is in the function or subfunction: */ + if (alt_insn->func->pfunc != insn->func->pfunc) + break;

alt = malloc(sizeof(*alt)); if (!alt) { @@ -942,7 +954,7 @@ static int add_func_switch_tables(struct struct rela *rela, *prev_rela = NULL; int ret;

- func_for_each_insn(file, func, insn) { + func_for_each_insn_all(file, func, insn) { if (!last) last = insn;

@@ -973,8 +985,7 @@ static int add_func_switch_tables(struct * the beginning of another switch table in the same function. */ if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, - rela); + ret = add_switch_table(file, prev_jump, prev_rela, rela); if (ret) return ret; } @@ -984,7 +995,7 @@ static int add_func_switch_tables(struct }

if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, NULL); + ret = add_switch_table(file, prev_jump, prev_rela, NULL); if (ret) return ret; } @@ -1748,15 +1759,13 @@ static int validate_branch(struct objtoo while (1) { next_insn = next_insn_same_sec(file, insn);

- - if (file->c_file && func && insn->func && func != insn->func) { + if (file->c_file && func && insn->func && func != insn->func->pfunc) { WARN("%s() falls through to next function %s()", func->name, insn->func->name); return 1; }

- if (insn->func) - func = insn->func; + func = insn->func ? insn->func->pfunc : NULL;

if (func && insn->ignore) { WARN_FUNC("BUG: why am I validating an ignored function?", @@ -1777,7 +1786,7 @@ static int validate_branch(struct objtoo

i = insn; save_insn = NULL; - func_for_each_insn_continue_reverse(file, func, i) { + func_for_each_insn_continue_reverse(file, insn->func, i) { if (i->save) { save_insn = i; break; @@ -1864,7 +1873,7 @@ static int validate_branch(struct objtoo case INSN_JUMP_UNCONDITIONAL: if (insn->jump_dest && (!func || !insn->jump_dest->func || - func == insn->jump_dest->func)) { + insn->jump_dest->func->pfunc == func)) { ret = validate_branch(file, insn->jump_dest, state); if (ret) @@ -2059,7 +2068,7 @@ static int validate_functions(struct obj

for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) + if (func->type != STT_FUNC || func->pfunc != func) continue;

insn = find_insn(file, sec, func->offset); --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -79,6 +79,19 @@ struct symbol *find_symbol_by_offset(str return NULL; }

+struct symbol *find_symbol_by_name(struct elf *elf, const char *name) +{ + struct section *sec; + struct symbol *sym; + + list_for_each_entry(sec, &elf->sections, list) + list_for_each_entry(sym, &sec->symbol_list, list) + if (!strcmp(sym->name, name)) + return sym; + + return NULL; +} + struct symbol *find_symbol_containing(struct section *sec, unsigned long offset) { struct symbol *sym; @@ -203,10 +216,11 @@ static int read_sections(struct elf *elf

static int read_symbols(struct elf *elf) { - struct section *symtab; - struct symbol *sym; + struct section *symtab, *sec; + struct symbol *sym, *pfunc; struct list_head *entry, *tmp; int symbols_nr, i; + char *coldstr;

symtab = find_section_by_name(elf, ".symtab"); if (!symtab) { @@ -281,6 +295,30 @@ static int read_symbols(struct elf *elf) hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx); }

+ /* Create parent/child links for any cold subfunctions */ + list_for_each_entry(sec, &elf->sections, list) { + list_for_each_entry(sym, &sec->symbol_list, list) { + if (sym->type != STT_FUNC) + continue; + sym->pfunc = sym->cfunc = sym; + coldstr = strstr(sym->name, ".cold."); + if (coldstr) { + coldstr[0] = '\0'; + pfunc = find_symbol_by_name(elf, sym->name); + coldstr[0] = '.'; + + if (!pfunc) { + WARN("%s(): can't find parent function", + sym->name); + goto err; + } + + sym->pfunc = pfunc; + pfunc->cfunc = sym; + } + } + } + return 0;

err: --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -61,6 +61,7 @@ struct symbol { unsigned char bind, type; unsigned long offset; unsigned int len; + struct symbol *pfunc, *cfunc; };

struct rela { @@ -86,6 +87,7 @@ struct elf { struct elf *elf_open(const char *name, int flags); struct section *find_section_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_containing(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josh Poimboeuf jpoimboe@redhat.com

commit 6f5ec2993b1f39aed12fa6fd56e8dc2272ee8a33 upstream.

Typically a switch table can be found by detecting a .rodata access followed an indirect jump:

1969: 4a 8b 0c e5 00 00 00 mov 0x0(,%r12,8),%rcx 1970: 00 196d: R_X86_64_32S .rodata+0x438 1971: e9 00 00 00 00 jmpq 1976 <dispc_runtime_suspend+0xb6a> 1972: R_X86_64_PC32 __x86_indirect_thunk_rcx-0x4

Randy Dunlap reported a case (seen with GCC 4.8) where the .rodata access uses RIP-relative addressing:

19bd: 48 8b 3d 00 00 00 00 mov 0x0(%rip),%rdi # 19c4 <dispc_runtime_suspend+0xbb8> 19c0: R_X86_64_PC32 .rodata+0x45c 19c4: e9 00 00 00 00 jmpq 19c9 <dispc_runtime_suspend+0xbbd> 19c5: R_X86_64_PC32 __x86_indirect_thunk_rdi-0x4

In this case the relocation addend needs to be adjusted accordingly in order to find the location of the switch table.

The fix is for case 3 (as described in the comments), but also make the existing case 1 & 2 checks more precise by only adjusting the addend for R_X86_64_PC32 relocations.

This fixes the following warnings:

drivers/video/fbdev/omap2/omapfb/dss/dispc.o: warning: objtool: dispc_runtime_suspend()+0xbb8: sibling call from callable instruction with modified stack frame drivers/video/fbdev/omap2/omapfb/dss/dispc.o: warning: objtool: dispc_runtime_resume()+0xcc5: sibling call from callable instruction with modified stack frame

Reported-by: Randy Dunlap rdunlap@infradead.org Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Link: http://lkml.kernel.org/r/b6098294fd67afb69af8c47c9883d7a68bf0f8ea.1526305958... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/objtool/check.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-)

--- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -898,24 +898,24 @@ static struct rela *find_switch_table(st { struct rela *text_rela, *rodata_rela; struct instruction *orig_insn = insn; + unsigned long table_offset;

+ /* case 1 & 2 */ text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); if (text_rela && text_rela->sym == file->rodata->sym && !find_symbol_containing(file->rodata, text_rela->addend)) {

- /* case 1 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend); - if (rodata_rela) - return rodata_rela; + table_offset = text_rela->addend; + if (text_rela->type == R_X86_64_PC32) { + /* case 2 */ + table_offset += 4; + file->ignore_unreachables = true; + }

- /* case 2 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend + 4); + rodata_rela = find_rela_by_dest(file->rodata, table_offset); if (!rodata_rela) return NULL;

- file->ignore_unreachables = true; return rodata_rela; }

@@ -949,18 +949,21 @@ static struct rela *find_switch_table(st if (!text_rela || text_rela->sym != file->rodata->sym) continue;

+ table_offset = text_rela->addend; + if (text_rela->type == R_X86_64_PC32) + table_offset += 4; + /* * Make sure the .rodata address isn't associated with a * symbol. gcc jump tables are anonymous data. */ - if (find_symbol_containing(file->rodata, text_rela->addend)) + if (find_symbol_containing(file->rodata, table_offset)) continue;

- rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend); - if (!rodata_rela) - continue; - - return rodata_rela; + /* mov [rodata addr], %reg */ + rodata_rela = find_rela_by_dest(file->rodata, table_offset); + if (rodata_rela) + return rodata_rela; }

return NULL;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josh Poimboeuf jpoimboe@redhat.com

commit 0afd0d9e0e7879d666c1df2fa1bea4d8716909fe upstream.

Objtool has some crude logic for detecting static "noreturn" functions (aka "dead ends"). This is necessary for being able to correctly follow GCC code flow when such functions are called.

It's remotely possible for two functions to call each other via sibling calls. If they don't have RET instructions, objtool's noreturn detection logic goes into a recursive loop:

drivers/char/ipmi/ipmi_ssif.o: warning: objtool: return_hosed_msg()+0x0: infinite recursion (objtool bug!) drivers/char/ipmi/ipmi_ssif.o: warning: objtool: deliver_recv_msg()+0x0: infinite recursion (objtool bug!)

Instead of reporting an error in this case, consider the functions to be non-dead-ends.

Reported-and-tested-by: Randy Dunlap rdunlap@infradead.org Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Arnd Bergmann arnd@arndb.de Cc: David Laight David.Laight@ACULAB.COM Cc: Greg KH gregkh@linuxfoundation.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: damian damian.tometzki@icloud.com Link: http://lkml.kernel.org/r/7cc156408c5781a1f62085d352ced1fe39fe2f91.1525923412... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/objtool/check.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

--- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -207,9 +207,13 @@ static int __dead_end_function(struct ob

/* local sibling call */ if (recursion == 5) { - WARN_FUNC("infinite recursion (objtool bug!)", - dest->sec, dest->offset); - return -1; + /* + * Infinite recursion: two functions + * have sibling calls to each other. + * This is a very rare case. It means + * they aren't dead ends. + */ + return 0; }

return __dead_end_function(file, dest->func,

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Borislav Petkov bp@suse.de

commit 78ce241099bb363b19dbd0245442e66c8de8f567 upstream.

... into a global, two-dimensional array and service subsequent reads from that cache to avoid rdmsr_on_cpu() calls during CPU hotplug (IPIs with IRQs disabled).

In addition, this fixes a KASAN slab-out-of-bounds read due to wrong usage of the bank->blocks pointer.

Fixes: 27bd59502702 ("x86/mce/AMD: Get address from already initialized block") Reported-by: Johannes Hirte johannes.hirte@datenkhaos.de Tested-by: Johannes Hirte johannes.hirte@datenkhaos.de Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: Yazen Ghannam yazen.ghannam@amd.com Link: http://lkml.kernel.org/r/20180414004230.GA2033@probook Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/cpu/mcheck/mce_amd.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-)

--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[ [SMCA_SMU] = { "smu", "System Management Unit" }, };

+static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init = +{ + [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 } +}; + const char *smca_get_name(enum smca_bank_types t) { if (t >= N_SMCA_BANK_TYPES) @@ -441,20 +446,26 @@ static u32 smca_get_block_address(unsign if (!block) return MSR_AMD64_SMCA_MCx_MISC(bank);

+ /* Check our cache first: */ + if (smca_bank_addrs[bank][block] != -1) + return smca_bank_addrs[bank][block]; + /* * For SMCA enabled processors, BLKPTR field of the first MISC register * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4). */ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) - return addr; + goto out;

if (!(low & MCI_CONFIG_MCAX)) - return addr; + goto out;

if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && (low & MASK_BLKPTR_LO)) - return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);

+out: + smca_bank_addrs[bank][block] = addr; return addr; }

@@ -466,18 +477,6 @@ static u32 get_block_address(unsigned in if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS)) return addr;

- /* Get address from already initialized block. */ - if (per_cpu(threshold_banks, cpu)) { - struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank]; - - if (bankp && bankp->blocks) { - struct threshold_block *blockp = &bankp->blocks[block]; - - if (blockp) - return blockp->address; - } - } - if (mce_flags.smca) return smca_get_block_address(cpu, bank, block);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dexuan Cui decui@microsoft.com

commit de0aa7b2f97d348ba7d1e17a00744c989baa0cb6 upstream.

1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq().

Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled.

hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called.

We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice.

2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel.

Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID.

Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true.

Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov v-adsuho@microsoft.com Tested-by: Chris Valean v-chvale@microsoft.com Signed-off-by: Dexuan Cui decui@microsoft.com Signed-off-by: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Reviewed-by: Michael Kelley mikelley@microsoft.com Acked-by: Haiyang Zhang haiyangz@microsoft.com Cc: stable@vger.kernel.org Cc: Stephen Hemminger sthemmin@microsoft.com Cc: K. Y. Srinivasan kys@microsoft.com Cc: Vitaly Kuznetsov vkuznets@redhat.com Cc: Jack Morgenstein jackm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/pci/host/pci-hyperv.c | 58 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 57 insertions(+), 1 deletion(-)

--- a/drivers/pci/host/pci-hyperv.c +++ b/drivers/pci/host/pci-hyperv.c @@ -531,6 +531,8 @@ struct hv_pci_compl { s32 completion_status; };

+static void hv_pci_onchannelcallback(void *context); + /** * hv_pci_generic_compl() - Invoked for a completion packet * @context: Set up by the sender of the packet. @@ -675,6 +677,31 @@ static void _hv_pcifront_read_config(str } }

+static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) +{ + u16 ret; + unsigned long flags; + void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + + PCI_VENDOR_ID; + + spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); + /* Make sure the function was chosen before we start reading. */ + mb(); + /* Read from that function's config space. */ + ret = readw(addr); + /* + * mb() is not required here, because the spin_unlock_irqrestore() + * is a barrier. + */ + + spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + + return ret; +} + /** * _hv_pcifront_write_config() - Internal PCI config write * @hpdev: The PCI driver's representation of the device @@ -1121,8 +1148,37 @@ static void hv_compose_msi_msg(struct ir * Since this function is called with IRQ locks held, can't * do normal wait for completion; instead poll. */ - while (!try_wait_for_completion(&comp.comp_pkt.host_event)) + while (!try_wait_for_completion(&comp.comp_pkt.host_event)) { + /* 0xFFFF means an invalid PCI VENDOR ID. */ + if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) { + dev_err_once(&hbus->hdev->device, + "the device has gone\n"); + goto free_int_desc; + } + + /* + * When the higher level interrupt code calls us with + * interrupt disabled, we must poll the channel by calling + * the channel callback directly when channel->target_cpu is + * the current CPU. When the higher level interrupt code + * calls us with interrupt enabled, let's add the + * local_bh_disable()/enable() to avoid race. + */ + local_bh_disable(); + + if (hbus->hdev->channel->target_cpu == smp_processor_id()) + hv_pci_onchannelcallback(hbus); + + local_bh_enable(); + + if (hpdev->state == hv_pcichild_ejecting) { + dev_err_once(&hbus->hdev->device, + "the device is being ejected\n"); + goto free_int_desc; + } + udelay(100); + }

if (comp.comp_pkt.completion_status < 0) { dev_err(&hbus->hdev->device,

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster bfoster@redhat.com

commit a27ba2607e60312554cbcd43fc660b2c7f29dc9c upstream.

The struct xfs_agfl v5 header was originally introduced with unexpected padding that caused the AGFL to operate with one less slot than intended. The header has since been packed, but the fix left an incompatibility for users who upgrade from an old kernel with the unpacked header to a newer kernel with the packed header while the AGFL happens to wrap around the end. The newer kernel recognizes one extra slot at the physical end of the AGFL that the previous kernel did not. The new kernel will eventually attempt to allocate a block from that slot, which contains invalid data, and cause a crash.

This condition can be detected by comparing the active range of the AGFL to the count. While this detects a padding mismatch, it can also trigger false positives for unrelated flcount corruption. Since we cannot distinguish a size mismatch due to padding from unrelated corruption, we can't trust the AGFL enough to simply repopulate the empty slot.

Instead, avoid unnecessarily complex detection logic and and use a solution that can handle any form of flcount corruption that slips through read verifiers: distrust the entire AGFL and reset it to an empty state. Any valid blocks within the AGFL are intentionally leaked. This requires xfs_repair to rectify (which was already necessary based on the state the AGFL was found in). The reset mitigates the side effect of the padding mismatch problem from a filesystem crash to a free space accounting inconsistency. The generic approach also means that this patch can be safely backported to kernels with or without a packed struct xfs_agfl.

Check the AGF for an invalid freelist count on initial read from disk. If detected, set a flag on the xfs_perag to indicate that a reset is required before the AGFL can be used. In the first transaction that attempts to use a flagged AGFL, reset it to empty, warn the user about the inconsistency and allow the freelist fixup code to repopulate the AGFL with new blocks. The xfs_perag flag is cleared to eliminate the need for repeated checks on each block allocation operation.

This allows kernels that include the packing fix commit 96f859d52bcb ("libxfs: pack the agfl header structure so XFS_AGFL_SIZE is correct") to handle older unpacked AGFL formats without a filesystem crash.

Suggested-by: Dave Chinner david@fromorbit.com Signed-off-by: Brian Foster bfoster@redhat.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by Dave Chiluk chiluk+linuxxfs@indeed.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/xfs/libxfs/xfs_alloc.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_mount.h | 1 fs/xfs/xfs_trace.h | 9 +++- 3 files changed, 103 insertions(+), 1 deletion(-)

--- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2057,6 +2057,93 @@ xfs_alloc_space_available( }

/* + * Check the agfl fields of the agf for inconsistency or corruption. The purpose + * is to detect an agfl header padding mismatch between current and early v5 + * kernels. This problem manifests as a 1-slot size difference between the + * on-disk flcount and the active [first, last] range of a wrapped agfl. This + * may also catch variants of agfl count corruption unrelated to padding. Either + * way, we'll reset the agfl and warn the user. + * + * Return true if a reset is required before the agfl can be used, false + * otherwise. + */ +static bool +xfs_agfl_needs_reset( + struct xfs_mount *mp, + struct xfs_agf *agf) +{ + uint32_t f = be32_to_cpu(agf->agf_flfirst); + uint32_t l = be32_to_cpu(agf->agf_fllast); + uint32_t c = be32_to_cpu(agf->agf_flcount); + int agfl_size = xfs_agfl_size(mp); + int active; + + /* no agfl header on v4 supers */ + if (!xfs_sb_version_hascrc(&mp->m_sb)) + return false; + + /* + * The agf read verifier catches severe corruption of these fields. + * Repeat some sanity checks to cover a packed -> unpacked mismatch if + * the verifier allows it. + */ + if (f >= agfl_size || l >= agfl_size) + return true; + if (c > agfl_size) + return true; + + /* + * Check consistency between the on-disk count and the active range. An + * agfl padding mismatch manifests as an inconsistent flcount. + */ + if (c && l >= f) + active = l - f + 1; + else if (c) + active = agfl_size - f + l + 1; + else + active = 0; + + return active != c; +} + +/* + * Reset the agfl to an empty state. Ignore/drop any existing blocks since the + * agfl content cannot be trusted. Warn the user that a repair is required to + * recover leaked blocks. + * + * The purpose of this mechanism is to handle filesystems affected by the agfl + * header padding mismatch problem. A reset keeps the filesystem online with a + * relatively minor free space accounting inconsistency rather than suffer the + * inevitable crash from use of an invalid agfl block. + */ +static void +xfs_agfl_reset( + struct xfs_trans *tp, + struct xfs_buf *agbp, + struct xfs_perag *pag) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp); + + ASSERT(pag->pagf_agflreset); + trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_); + + xfs_warn(mp, + "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. " + "Please unmount and run xfs_repair.", + pag->pag_agno, pag->pagf_flcount); + + agf->agf_flfirst = 0; + agf->agf_fllast = cpu_to_be32(xfs_agfl_size(mp) - 1); + agf->agf_flcount = 0; + xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLFIRST | XFS_AGF_FLLAST | + XFS_AGF_FLCOUNT); + + pag->pagf_flcount = 0; + pag->pagf_agflreset = false; +} + +/* * Decide whether to use this allocation group for this allocation. * If so, fix up the btree freelist's size. */ @@ -2117,6 +2204,10 @@ xfs_alloc_fix_freelist( } }

+ /* reset a padding mismatched agfl before final free space check */ + if (pag->pagf_agflreset) + xfs_agfl_reset(tp, agbp, pag); + /* If there isn't enough total space or single-extent, reject it. */ need = xfs_alloc_min_freelist(mp, pag); if (!xfs_alloc_space_available(args, need, flags)) @@ -2273,6 +2364,7 @@ xfs_alloc_get_freelist( agf->agf_flfirst = 0;

pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno)); + ASSERT(!pag->pagf_agflreset); be32_add_cpu(&agf->agf_flcount, -1); xfs_trans_agflist_delta(tp, -1); pag->pagf_flcount--; @@ -2384,6 +2476,7 @@ xfs_alloc_put_freelist( agf->agf_fllast = 0;

pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno)); + ASSERT(!pag->pagf_agflreset); be32_add_cpu(&agf->agf_flcount, 1); xfs_trans_agflist_delta(tp, 1); pag->pagf_flcount++; @@ -2589,6 +2682,7 @@ xfs_alloc_read_agf( pag->pagb_count = 0; pag->pagb_tree = RB_ROOT; pag->pagf_init = 1; + pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf); } #ifdef DEBUG else if (!XFS_FORCED_SHUTDOWN(mp)) { --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -353,6 +353,7 @@ typedef struct xfs_perag { char pagi_inodeok; /* The agi is ok for inodes */ uint8_t pagf_levels[XFS_BTNUM_AGF]; /* # of levels in bno & cnt btree */ + bool pagf_agflreset; /* agfl requires reset before use */ uint32_t pagf_flcount; /* count of blocks in freelist */ xfs_extlen_t pagf_freeblks; /* total free blocks */ xfs_extlen_t pagf_longest; /* longest free space */ --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1513,7 +1513,7 @@ TRACE_EVENT(xfs_extent_busy_trim, __entry->tlen) );

-TRACE_EVENT(xfs_agf, +DECLARE_EVENT_CLASS(xfs_agf_class, TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, unsigned long caller_ip), TP_ARGS(mp, agf, flags, caller_ip), @@ -1569,6 +1569,13 @@ TRACE_EVENT(xfs_agf, __entry->longest, (void *)__entry->caller_ip) ); +#define DEFINE_AGF_EVENT(name) \ +DEFINE_EVENT(xfs_agf_class, name, \ + TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, \ + unsigned long caller_ip), \ + TP_ARGS(mp, agf, flags, caller_ip)) +DEFINE_AGF_EVENT(xfs_agf); +DEFINE_AGF_EVENT(xfs_agfl_reset);

TRACE_EVENT(xfs_free_extent, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Edvard Holst edvard.holst@gmail.com

commit 15e2cffec3aa0d47a8d75ae80e1b136bfb5dff30 upstream.

Lenovo use two different trackpoints in the fifth generation Thinkpad X1 Carbon. Both are accessible over SMBUS/RMI but the pnpIDs are missing. This patch is for the Elantech trackpoint specifically which also reports SMB version 3 so rmi_smbus needs to be updated in order to handle it.

For the record, I was not the first one to come up with this patch as it has been floating around the internet for a while now. However, I have spent significant time with testing and my efforts to find the original author of the patch have been unsuccessful.

Signed-off-by: Edvard Holst edvard.holst@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/mouse/synaptics.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -173,6 +173,7 @@ static const char * const smbus_pnp_ids[ "LEN0046", /* X250 */ "LEN004a", /* W541 */ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */ + "LEN0073", /* X1 Carbon G5 (Elantech) */ "LEN200f", /* T450s */ NULL };

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Benjamin Tissoires benjamin.tissoires@redhat.com

commit ad8fb554f04e38f155c9bc34bbf521fc592ceee7 upstream.

This time, Lenovo decided to go with different pieces in its latest series of Thinkpads.

For those we have been able to test: - the T480 is using Synaptics with an IBM trackpoint -> it behaves properly with or without intertouch, there is no point not using RMI4 - the X1 Carbon 6th gen is using Synaptics with an IBM trackpoint -> the touchpad doesn't behave properly under PS/2 so we have to switch it to RMI4 if we do not want to have disappointed users - the X280 is using Synaptics with an ALPS trackpoint -> the recent fixes in the trackpoint handling fixed it so upstream now works fine with or without RMI4, and there is no point not using RMI4 - the T480s is using an Elan touchpad, so that's a different story

Cc: stable@vger.kernel.org # v4.14.x, v4.15.x, v4.16.x Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Acked-by: KT Liao kt.liao@emc.com.tw Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/mouse/synaptics.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -172,10 +172,12 @@ static const char * const smbus_pnp_ids[ "LEN0048", /* X1 Carbon 3 */ "LEN0046", /* X250 */ "LEN004a", /* W541 */ + "LEN0071", /* T480 */ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */ "LEN0073", /* X1 Carbon G5 (Elantech) */ "LEN0092", /* X1 Carbon 6 */ "LEN0096", /* X280 */ + "LEN0097", /* X280 -> ALPS trackpoint */ "LEN200f", /* T450s */ NULL };

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt (VMware) rostedt@goodmis.org

commit 86b389ff22bd6ad8fd3cb98e41cd271886c6d023 upstream.

If a instance has an event trigger enabled when it is freed, it could cause an access of free memory. Here's the case that crashes:

# cd /sys/kernel/tracing # mkdir instances/foo # echo snapshot > instances/foo/events/initcall/initcall_start/trigger # rmdir instances/foo

Would produce:

general protection fault: 0000 [#1] PREEMPT SMP PTI Modules linked in: tun bridge ... CPU: 5 PID: 6203 Comm: rmdir Tainted: G W 4.17.0-rc4-test+ #933 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016 RIP: 0010:clear_event_triggers+0x3b/0x70 RSP: 0018:ffffc90003783de0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 6b6b6b6b6b6b6b2b RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800c7130ba0 RBP: ffffc90003783e00 R08: ffff8801131993f8 R09: 0000000100230016 R10: ffffc90003783d80 R11: 0000000000000000 R12: ffff8800c7130ba0 R13: ffff8800c7130bd8 R14: ffff8800cc093768 R15: 00000000ffffff9c FS: 00007f6f4aa86700(0000) GS:ffff88011eb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f6f4a5aed60 CR3: 00000000cd552001 CR4: 00000000001606e0 Call Trace: event_trace_del_tracer+0x2a/0xc5 instance_rmdir+0x15c/0x200 tracefs_syscall_rmdir+0x52/0x90 vfs_rmdir+0xdb/0x160 do_rmdir+0x16d/0x1c0 __x64_sys_rmdir+0x17/0x20 do_syscall_64+0x55/0x1a0 entry_SYSCALL_64_after_hwframe+0x49/0xbe

This was due to the call the clears out the triggers when an instance is being deleted not removing the trigger from the link list.

Cc: stable@vger.kernel.org Fixes: 85f2b08268c01 ("tracing: Add basic event trigger framework") Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/trace/trace_events_trigger.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -482,9 +482,10 @@ clear_event_triggers(struct trace_array struct trace_event_file *file;

list_for_each_entry(file, &tr->events, list) { - struct event_trigger_data *data; - list_for_each_entry_rcu(data, &file->triggers, list) { + struct event_trigger_data *data, *n; + list_for_each_entry_safe(data, n, &file->triggers, list) { trace_event_trigger_enable_disable(file, 0); + list_del_rcu(&data->list); if (data->ops->free) data->ops->free(data->ops, data); }

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sachin Grover sgrover@codeaurora.org

commit efe3de79e0b52ca281ef6691480c8c68c82a4657 upstream.

Call trace: [<ffffff9203a8d7a8>] dump_backtrace+0x0/0x428 [<ffffff9203a8dbf8>] show_stack+0x28/0x38 [<ffffff920409bfb8>] dump_stack+0xd4/0x124 [<ffffff9203d187e8>] print_address_description+0x68/0x258 [<ffffff9203d18c00>] kasan_report.part.2+0x228/0x2f0 [<ffffff9203d1927c>] kasan_report+0x5c/0x70 [<ffffff9203d1776c>] check_memory_region+0x12c/0x1c0 [<ffffff9203d17cdc>] memcpy+0x34/0x68 [<ffffff9203d75348>] xattr_getsecurity+0xe0/0x160 [<ffffff9203d75490>] vfs_getxattr+0xc8/0x120 [<ffffff9203d75d68>] getxattr+0x100/0x2c8 [<ffffff9203d76fb4>] SyS_fgetxattr+0x64/0xa0 [<ffffff9203a83f70>] el0_svc_naked+0x24/0x28

If user get root access and calls security.selinux setxattr() with an embedded NUL on a file and then if some process performs a getxattr() on that file with a length greater than the actual length of the string, it would result in a panic.

To fix this, add the actual length of the string to the security context instead of the length passed by the userspace process.

Signed-off-by: Sachin Grover sgrover@codeaurora.org Cc: stable@vger.kernel.org Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- security/selinux/ss/services.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -1448,7 +1448,7 @@ static int security_context_to_sid_core( scontext_len, &context, def_sid); if (rc == -EINVAL && force) { context.str = str; - context.len = scontext_len; + context.len = strlen(str) + 1; str = NULL; } else if (rc) goto out_unlock;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nick Desaulniers nick.desaulniers@gmail.com

commit df16aaac26e92e97ab7234d3f93c953466adc4b5 upstream.

When compiling with `make CC=clang HOSTCC=clang`, I was seeing warnings that clang did not recognize -fno-delete-null-pointer-checks for HOSTCC targets. These were added in commit 61163efae020 ("kbuild: LLVMLinux: Add Kbuild support for building kernel with Clang").

Clang does not support -fno-delete-null-pointer-checks, so adding it to HOSTCFLAGS if HOSTCC is clang does not make sense.

It's not clear why the other warnings were disabled, and just for HOSTCFLAGS, but I can remove them, add -Werror to HOSTCFLAGS and compile with clang just fine.

Suggested-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Nick Desaulniers nick.desaulniers@gmail.com Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Makefile | 5 ----- 1 file changed, 5 deletions(-)

--- a/Makefile +++ b/Makefile @@ -369,11 +369,6 @@ HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS) HOSTLDFLAGS := $(HOST_LFS_LDFLAGS) HOST_LOADLIBES := $(HOST_LFS_LIBS)

-ifeq ($(shell $(HOSTCC) -v 2>&1 | grep -c "clang version"), 1) -HOSTCFLAGS += -Wno-unused-value -Wno-unused-parameter \ - -Wno-missing-field-initializers -fno-delete-null-pointer-checks -endif - # Make variables (CC, etc...) AS = $(CROSS_COMPILE)as LD = $(CROSS_COMPILE)ld

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Colin Ian King colin.king@canonical.com

commit 531beb067c6185aceabfdee0965234c6a8fd133b upstream.

sg_table is being initialized and is never read before it is updated again later on, hence making the initialization redundant. Remove the initialization.

Detected by clang scan-build: "warning: Value stored to 'sg_table' during its initialization is never read"

Signed-off-by: Colin Ian King colin.king@canonical.com Reviewed-by: Chris Wilson chris@chris-wilson.co.uk Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/20170914230516.6056-1-colin.ki... Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/dma-buf/dma-buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -625,7 +625,7 @@ EXPORT_SYMBOL_GPL(dma_buf_detach); struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, enum dma_data_direction direction) { - struct sg_table *sg_table = ERR_PTR(-EINVAL); + struct sg_table *sg_table;

might_sleep();

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthias Kaehlcke mka@chromium.org

commit fb239c1209bb0f0b4830cc72507cc2f2d63fadbd upstream.

In _rtl92c_get_txpower_writeval_by_regulatory() the variable writeVal is assigned to itself in an if ... else statement, apparently only to document that the branch condition is handled and that a previously read value should be returned unmodified. The self-assignment causes clang to raise the following warning:

drivers/net/wireless/realtek/rtlwifi/rtl8192cu/rf.c:304:13: error: explicitly assigning value of variable of type 'u32' (aka 'unsigned int') to itself [-Werror,-Wself-assign] writeVal = writeVal;

Delete the branch with the self-assignment.

Signed-off-by: Matthias Kaehlcke mka@chromium.org Acked-by: Larry Finger Larry.Finger@lwfinger.net Reviewed-by: Guenter Roeck groeck@chromium.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/wireless/realtek/rtlwifi/rtl8192cu/rf.c | 3 --- 1 file changed, 3 deletions(-)

--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/rf.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/rf.c @@ -299,9 +299,6 @@ static void _rtl92c_get_txpower_writeval writeVal = 0x00000000; if (rtlpriv->dm.dynamic_txhighpower_lvl == TXHIGHPWRLEVEL_BT1) writeVal = writeVal - 0x06060606; - else if (rtlpriv->dm.dynamic_txhighpower_lvl == - TXHIGHPWRLEVEL_BT2) - writeVal = writeVal; *(p_outwriteval + rf) = writeVal; } }

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Colin Ian King colin.king@canonical.com

commit d3b56c566d4ba8cae688baf3cca94425d57ea783 upstream.

Pointer request is being assigned but never used, so remove it. Cleans up the clang warning:

drivers/platform/chrome/cros_ec_lpc.c:68:2: warning: Value stored to 'request' is never read

Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Benson Leung bleung@chromium.org Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/platform/chrome/cros_ec_lpc.c | 3 --- 1 file changed, 3 deletions(-)

--- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -54,7 +54,6 @@ static int ec_response_timed_out(void) static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, struct cros_ec_command *msg) { - struct ec_host_request *request; struct ec_host_response response; u8 sum; int ret = 0; @@ -65,8 +64,6 @@ static int cros_ec_pkt_xfer_lpc(struct c /* Write buffer */ cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_PACKET, ret, ec->dout);

- request = (struct ec_host_request *)ec->dout; - /* Here we go */ sum = EC_COMMAND_PROTOCOL_3; cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_CMD, 1, &sum);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 607065bad9931e72207b0cac365d7d4abc06bd99 upstream.

When using large tcp_rmem[2] values (I did tests with 500 MB), I noticed overflows while computing rcvwin.

Lets fix this before the following patch.

Signed-off-by: Eric Dumazet edumazet@google.com Acked-by: Soheil Hassas Yeganeh soheil@google.com Acked-by: Wei Wang weiwan@google.com Acked-by: Neal Cardwell ncardwell@google.com Signed-off-by: David S. Miller davem@davemloft.net [Backport: sysctl_tcp_rmem is not Namespace-ify'd in older kernels] Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/tcp.h | 2 +- net/ipv4/tcp_input.c | 10 ++++++---- 2 files changed, 7 insertions(+), 5 deletions(-)

--- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -334,7 +334,7 @@ struct tcp_sock {

/* Receiver queue space */ struct { - int space; + u32 space; u32 seq; u64 time; } rcvq_space; --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -591,8 +591,8 @@ static inline void tcp_rcv_rtt_measure_t void tcp_rcv_space_adjust(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 copied; int time; - int copied;

tcp_mstamp_refresh(tp); time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); @@ -615,12 +615,13 @@ void tcp_rcv_space_adjust(struct sock *s

if (sysctl_tcp_moderate_rcvbuf && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int rcvwin, rcvmem, rcvbuf; + int rcvmem, rcvbuf; + u64 rcvwin;

/* minimal window to cope with packet losses, assuming * steady state. Add some cushion because of small variations. */ - rcvwin = (copied << 1) + 16 * tp->advmss; + rcvwin = ((u64)copied << 1) + 16 * tp->advmss;

/* If rate increased by 25%, * assume slow start, rcvwin = 3 * copied @@ -640,7 +641,8 @@ void tcp_rcv_space_adjust(struct sock *s while (tcp_win_from_space(rcvmem) < tp->advmss) rcvmem += 128;

- rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]); + do_div(rcvwin, tp->advmss); + rcvbuf = min_t(u64, rcvwin * rcvmem, sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { sk->sk_rcvbuf = rcvbuf;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin Kelly mkelly@xevo.com

commit c043ec1ca5baae63726aae32abbe003192bc6eec upstream.

Currently, we use int for buffer length and bytes_per_datum. However, kfifo uses unsigned int for length and size_t for element size. We need to make sure these matches or we will have bugs related to overflow (in the range between INT_MAX and UINT_MAX for length, for example).

In addition, set_bytes_per_datum uses size_t while bytes_per_datum is an int, which would cause bugs for large values of bytes_per_datum.

Change buffer length to use unsigned int and bytes_per_datum to use size_t.

Signed-off-by: Martin Kelly mkelly@xevo.com Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iio/buffer/industrialio-buffer-dma.c | 2 +- drivers/iio/buffer/kfifo_buf.c | 4 ++-- include/linux/iio/buffer_impl.h | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-)

--- a/drivers/iio/buffer/industrialio-buffer-dma.c +++ b/drivers/iio/buffer/industrialio-buffer-dma.c @@ -587,7 +587,7 @@ EXPORT_SYMBOL_GPL(iio_dma_buffer_set_byt * Should be used as the set_length callback for iio_buffer_access_ops * struct for DMA buffers. */ -int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length) +int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length) { /* Avoid an invalid state */ if (length < 2) --- a/drivers/iio/buffer/kfifo_buf.c +++ b/drivers/iio/buffer/kfifo_buf.c @@ -22,7 +22,7 @@ struct iio_kfifo { #define iio_to_kfifo(r) container_of(r, struct iio_kfifo, buffer)

static inline int __iio_allocate_kfifo(struct iio_kfifo *buf, - int bytes_per_datum, int length) + size_t bytes_per_datum, unsigned int length) { if ((length == 0) || (bytes_per_datum == 0)) return -EINVAL; @@ -67,7 +67,7 @@ static int iio_set_bytes_per_datum_kfifo return 0; }

-static int iio_set_length_kfifo(struct iio_buffer *r, int length) +static int iio_set_length_kfifo(struct iio_buffer *r, unsigned int length) { /* Avoid an invalid state */ if (length < 2) --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -53,7 +53,7 @@ struct iio_buffer_access_funcs { int (*request_update)(struct iio_buffer *buffer);

int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd); - int (*set_length)(struct iio_buffer *buffer, int length); + int (*set_length)(struct iio_buffer *buffer, unsigned int length);

int (*enable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); int (*disable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); @@ -72,10 +72,10 @@ struct iio_buffer_access_funcs { */ struct iio_buffer { /** @length: Number of datums in buffer. */ - int length; + unsigned int length;

/** @bytes_per_datum: Size of individual datum including timestamp. */ - int bytes_per_datum; + size_t bytes_per_datum;

/** * @access: Buffer access functions associated with the

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eugen Hristev eugen.hristev@microchip.com

commit 76974ef9d1bf397b7bb97892a3b3bc516a1fc2c2 upstream.

We need to select the buffer code, otherwise we get build errors with undefined functions on the trigger and buffer, if we select just IIO and then AT91_SAMA5D2_ADC from menuconfig

This adds a Kconfig 'select' statement like other ADC drivers have it already.

Fixes: 5e1a1da0f8c9 ("iio: adc: at91-sama5d2_adc: add hw trigger and buffer support") Signed-off-by: Eugen Hristev eugen.hristev@microchip.com Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iio/adc/Kconfig | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -158,6 +158,7 @@ config AT91_SAMA5D2_ADC tristate "Atmel AT91 SAMA5D2 ADC" depends on ARCH_AT91 || COMPILE_TEST depends on HAS_IOMEM + select IIO_BUFFER select IIO_TRIGGERED_BUFFER help Say yes here to build support for Atmel SAMA5D2 ADC which is

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maciej W. Rozycki macro@mips.com

commit c7e814628df65f424fe197dde73bfc67e4a244d7 upstream.

Use 64-bit accesses for 64-bit floating-point general registers with PTRACE_PEEKUSR, removing the truncation of their upper halves in the FR=1 mode, caused by commit bbd426f542cb ("MIPS: Simplify FP context access"), which inadvertently switched them to using 32-bit accesses.

The PTRACE_POKEUSR side is fine as it's never been broken and continues using 64-bit accesses.

Fixes: bbd426f542cb ("MIPS: Simplify FP context access") Signed-off-by: Maciej W. Rozycki macro@mips.com Cc: Ralf Baechle ralf@linux-mips.org Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.15+ Patchwork: https://patchwork.linux-mips.org/patch/19334/ Signed-off-by: James Hogan jhogan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/mips/kernel/ptrace.c | 2 +- arch/mips/kernel/ptrace32.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -809,7 +809,7 @@ long arch_ptrace(struct task_struct *chi break; } #endif - tmp = get_fpr32(&fregs[addr - FPR_BASE], 0); + tmp = get_fpr64(&fregs[addr - FPR_BASE], 0); break; case PC: tmp = regs->cp0_epc; --- a/arch/mips/kernel/ptrace32.c +++ b/arch/mips/kernel/ptrace32.c @@ -108,7 +108,7 @@ long compat_arch_ptrace(struct task_stru addr & 1); break; } - tmp = get_fpr32(&fregs[addr - FPR_BASE], 0); + tmp = get_fpr64(&fregs[addr - FPR_BASE], 0); break; case PC: tmp = regs->cp0_epc;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bart Van Assche bart.vanassche@wdc.com

commit c9ddf73476ff4fffb7a87bd5107a0705bf2cf64b upstream.

Since an SRP remote port is attached as a child to shost->shost_gendev and as the only child, the translation from the shost pointer into an rport pointer must happen by looking up the shost child that is an rport. This patch fixes the following KASAN complaint:

BUG: KASAN: slab-out-of-bounds in srp_timed_out+0x57/0x110 [scsi_transport_srp] Read of size 4 at addr ffff880035d3fcc0 by task kworker/1:0H/19

CPU: 1 PID: 19 Comm: kworker/1:0H Not tainted 4.16.0-rc3-dbg+ #1 Workqueue: kblockd blk_mq_timeout_work Call Trace: dump_stack+0x85/0xc7 print_address_description+0x65/0x270 kasan_report+0x231/0x350 srp_timed_out+0x57/0x110 [scsi_transport_srp] scsi_times_out+0xc7/0x3f0 [scsi_mod] blk_mq_terminate_expired+0xc2/0x140 bt_iter+0xbc/0xd0 blk_mq_queue_tag_busy_iter+0x1c7/0x350 blk_mq_timeout_work+0x325/0x3f0 process_one_work+0x441/0xa50 worker_thread+0x76/0x6c0 kthread+0x1b2/0x1d0 ret_from_fork+0x24/0x30

Fixes: e68ca75200fe ("scsi_transport_srp: Reduce failover time") Signed-off-by: Bart Van Assche bart.vanassche@wdc.com Cc: Hannes Reinecke hare@suse.com Cc: Johannes Thumshirn jthumshirn@suse.de Cc: Jason Gunthorpe jgg@mellanox.com Cc: Doug Ledford dledford@redhat.com Cc: Laurence Oberman loberman@redhat.com Cc: stable@vger.kernel.org Reviewed-by: Johannes Thumshirn jthumshirn@suse.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/scsi_transport_srp.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)

--- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -51,6 +51,8 @@ struct srp_internal { struct transport_container rport_attr_cont; };

+static int scsi_is_srp_rport(const struct device *dev); + #define to_srp_internal(tmpl) container_of(tmpl, struct srp_internal, t)

#define dev_to_rport(d) container_of(d, struct srp_rport, dev) @@ -60,9 +62,24 @@ static inline struct Scsi_Host *rport_to return dev_to_shost(r->dev.parent); }

+static int find_child_rport(struct device *dev, void *data) +{ + struct device **child = data; + + if (scsi_is_srp_rport(dev)) { + WARN_ON_ONCE(*child); + *child = dev; + } + return 0; +} + static inline struct srp_rport *shost_to_rport(struct Scsi_Host *shost) { - return transport_class_to_srp_rport(&shost->shost_gendev); + struct device *child = NULL; + + WARN_ON_ONCE(device_for_each_child(&shost->shost_gendev, &child, + find_child_rport) < 0); + return child ? dev_to_rport(child) : NULL; }

/** @@ -600,7 +617,8 @@ enum blk_eh_timer_return srp_timed_out(s struct srp_rport *rport = shost_to_rport(shost);

pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev)); - return rport->fast_io_fail_tmo < 0 && rport->dev_loss_tmo < 0 && + return rport && rport->fast_io_fail_tmo < 0 && + rport->dev_loss_tmo < 0 && i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ? BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED; }

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

commit 806e30873f0e74d9d41b0ef761bd4d3e55c7d510 upstream.

Commit b5e2ced9bf81 ("stm class: Use vmalloc for the master map") caused a build error on some arches as vmalloc.h was not explicitly included.

Fix that by adding it to the list of includes.

Fixes: b5e2ced9bf81 ("stm class: Use vmalloc for the master map") Reported-by: kbuild test robot lkp@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hwtracing/stm/core.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -27,6 +27,7 @@ #include <linux/stm.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/vmalloc.h> #include "stm.h"

#include <uapi/linux/stm.h>

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hugh Dickins hughd@google.com

commit 2d077d4b59924acd1f5180c6fb73b57f4771fde6 upstream.

Swapping load on huge=always tmpfs (with khugepaged tuned up to be very eager, but I'm not sure that is relevant) soon hung uninterruptibly, waiting for page lock in shmem_getpage_gfp()'s find_lock_entry(), most often when "cp -a" was trying to write to a smallish file. Debug showed that the page in question was not locked, and page->mapping NULL by now, but page->index consistent with having been in a huge page before.

Reproduced in minutes on a 4.15 kernel, even with 4.17's 605ca5ede764 ("mm/huge_memory.c: reorder operations in __split_huge_page_tail()") added in; but took hours to reproduce on a 4.17 kernel (no idea why).

The culprit proved to be the __ClearPageDirty() on tails beyond i_size in __split_huge_page(): the non-atomic __bitoperation may have been safe when 4.8's baa355fd3314 ("thp: file pages support for split_huge_page()") introduced it, but liable to erase PageWaiters after 4.10's 62906027091f ("mm: add PageWaiters indicating tasks are waiting for a page bit").

Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1805291841070.3197@eggly.anvils Fixes: 62906027091f ("mm: add PageWaiters indicating tasks are waiting for a page bit") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Konstantin Khlebnikov khlebnikov@yandex-team.ru Cc: Nicholas Piggin npiggin@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/huge_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2388,7 +2388,7 @@ static void __split_huge_page(struct pag __split_huge_page_tail(head, i, lruvec, list); /* Some pages can be beyond i_size: drop them from page cache */ if (head[i].index >= end) { - __ClearPageDirty(head + i); + ClearPageDirty(head + i); __delete_from_page_cache(head + i, NULL); if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) shmem_uncharge(head->mapping->host, 1);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Shishkin alexander.shishkin@linux.intel.com

commit 0ed2424b911f3a058dfea01b78817abed767433d upstream.

Commit d5c435df4a890 ("intel_th: msu: Use the real device in case of IOMMU domain allocation") changes dma buffer allocation to use the actual underlying device, but forgets to change the deallocation path, which leads to (if you've got CAP_SYS_RAWIO):

# echo 0,0 > /sys/bus/intel_th/devices/0-msc0/nr_pages ------------[ cut here ]------------ kernel BUG at ../linux/drivers/iommu/intel-iommu.c:3670! CPU: 3 PID: 231 Comm: sh Not tainted 4.17.0-rc1+ #2729 RIP: 0010:intel_unmap+0x11e/0x130

...

Call Trace: intel_free_coherent+0x3e/0x60 msc_buffer_win_free+0x100/0x160 [intel_th_msu]

This patch fixes the buffer deallocation code to use the correct device.

Signed-off-by: Alexander Shishkin alexander.shishkin@linux.intel.com Fixes: d5c435df4a890 ("intel_th: msu: Use the real device in case of IOMMU domain allocation") Reported-by: Baofeng Tian baofeng.tian@intel.com CC: stable@vger.kernel.org # v4.14+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hwtracing/intel_th/msu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -741,8 +741,8 @@ err_nomem: /* Reset the page to write-back before releasing */ set_memory_wb((unsigned long)win->block[i].bdesc, 1); #endif - dma_free_coherent(msc_dev(msc), size, win->block[i].bdesc, - win->block[i].addr); + dma_free_coherent(msc_dev(msc)->parent->parent, size, + win->block[i].bdesc, win->block[i].addr); } kfree(win);

@@ -777,7 +777,7 @@ static void msc_buffer_win_free(struct m /* Reset the page to write-back before releasing */ set_memory_wb((unsigned long)win->block[i].bdesc, 1); #endif - dma_free_coherent(msc_dev(win->msc), PAGE_SIZE, + dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, win->block[i].bdesc, win->block[i].addr); }

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe Leroy christophe.leroy@c-s.fr

commit a3286f05bc5a5bc7fc73a9783ec89de78fcd07f8 upstream.

In preparation for the following patch which will enhance 'slices' for supporting PPC32 in order to fix an issue on hugepages on 8xx, this patch takes out of page*.h all bits related to 'slices' and put them into newly created slice.h header files. While common parts go into asm/slice.h, subarch specific parts go into respective books3s/64/slice.c and nohash/64/slice.c 'slices'

Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Reviewed-by: Nicholas Piggin npiggin@gmail.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/powerpc/include/asm/book3s/64/slice.h | 27 +++++++++++++ arch/powerpc/include/asm/nohash/64/slice.h | 12 +++++ arch/powerpc/include/asm/page.h | 1 arch/powerpc/include/asm/page_64.h | 59 ----------------------------- arch/powerpc/include/asm/slice.h | 40 +++++++++++++++++++ 5 files changed, 80 insertions(+), 59 deletions(-)

--- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/slice.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H +#define _ASM_POWERPC_BOOK3S_64_SLICE_H + +#ifdef CONFIG_PPC_MM_SLICES + +#define SLICE_LOW_SHIFT 28 +#define SLICE_LOW_TOP (0x100000000ul) +#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) +#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT) + +#define SLICE_HIGH_SHIFT 40 +#define SLICE_NUM_HIGH (H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT) +#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT) + +#else /* CONFIG_PPC_MM_SLICES */ + +#define get_slice_psize(mm, addr) ((mm)->context.user_psize) +#define slice_set_user_psize(mm, psize) \ +do { \ + (mm)->context.user_psize = (psize); \ + (mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \ +} while (0) + +#endif /* CONFIG_PPC_MM_SLICES */ + +#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */ --- /dev/null +++ b/arch/powerpc/include/asm/nohash/64/slice.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_64_SLICE_H +#define _ASM_POWERPC_NOHASH_64_SLICE_H + +#ifdef CONFIG_PPC_64K_PAGES +#define get_slice_psize(mm, addr) MMU_PAGE_64K +#else /* CONFIG_PPC_64K_PAGES */ +#define get_slice_psize(mm, addr) MMU_PAGE_4K +#endif /* !CONFIG_PPC_64K_PAGES */ +#define slice_set_user_psize(mm, psize) do { BUG(); } while (0) + +#endif /* _ASM_POWERPC_NOHASH_64_SLICE_H */ --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -344,5 +344,6 @@ typedef struct page *pgtable_t;

#include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */ +#include <asm/slice.h>

#endif /* _ASM_POWERPC_PAGE_H */ --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -86,65 +86,6 @@ extern u64 ppc64_pft_size;

#endif /* __ASSEMBLY__ */

-#ifdef CONFIG_PPC_MM_SLICES - -#define SLICE_LOW_SHIFT 28 -#define SLICE_HIGH_SHIFT 40 - -#define SLICE_LOW_TOP (0x100000000ul) -#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) -#define SLICE_NUM_HIGH (H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT) - -#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT) -#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT) - -#ifndef __ASSEMBLY__ -struct mm_struct; - -extern unsigned long slice_get_unmapped_area(unsigned long addr, - unsigned long len, - unsigned long flags, - unsigned int psize, - int topdown); - -extern unsigned int get_slice_psize(struct mm_struct *mm, - unsigned long addr); - -extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize); -extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start, - unsigned long len, unsigned int psize); - -#endif /* __ASSEMBLY__ */ -#else -#define slice_init() -#ifdef CONFIG_PPC_STD_MMU_64 -#define get_slice_psize(mm, addr) ((mm)->context.user_psize) -#define slice_set_user_psize(mm, psize) \ -do { \ - (mm)->context.user_psize = (psize); \ - (mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \ -} while (0) -#else /* CONFIG_PPC_STD_MMU_64 */ -#ifdef CONFIG_PPC_64K_PAGES -#define get_slice_psize(mm, addr) MMU_PAGE_64K -#else /* CONFIG_PPC_64K_PAGES */ -#define get_slice_psize(mm, addr) MMU_PAGE_4K -#endif /* !CONFIG_PPC_64K_PAGES */ -#define slice_set_user_psize(mm, psize) do { BUG(); } while(0) -#endif /* !CONFIG_PPC_STD_MMU_64 */ - -#define slice_set_range_psize(mm, start, len, psize) \ - slice_set_user_psize((mm), (psize)) -#endif /* CONFIG_PPC_MM_SLICES */ - -#ifdef CONFIG_HUGETLB_PAGE - -#ifdef CONFIG_PPC_MM_SLICES -#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA -#endif - -#endif /* !CONFIG_HUGETLB_PAGE */ - #define VM_DATA_DEFAULT_FLAGS \ (is_32bit_task() ? \ VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64) --- /dev/null +++ b/arch/powerpc/include/asm/slice.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_SLICE_H +#define _ASM_POWERPC_SLICE_H + +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/slice.h> +#else +#include <asm/nohash/64/slice.h> +#endif + +#ifdef CONFIG_PPC_MM_SLICES + +#ifdef CONFIG_HUGETLB_PAGE +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA +#endif +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN + +#ifndef __ASSEMBLY__ + +struct mm_struct; + +unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, + unsigned long flags, unsigned int psize, + int topdown); + +unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); + +void slice_set_user_psize(struct mm_struct *mm, unsigned int psize); +void slice_set_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long len, unsigned int psize); +#endif /* __ASSEMBLY__ */ + +#else /* CONFIG_PPC_MM_SLICES */ + +#define slice_set_range_psize(mm, start, len, psize) \ + slice_set_user_psize((mm), (psize)) +#endif /* CONFIG_PPC_MM_SLICES */ + +#endif /* _ASM_POWERPC_SLICE_H */

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe Leroy christophe.leroy@c-s.fr

commit aa0ab02ba992eb956934b21373e0138211486ddd upstream.

On the 8xx, the page size is set in the PMD entry and applies to all pages of the page table pointed by the said PMD entry.

When an app has some regular pages allocated (e.g. see below) and tries to mmap() a huge page at a hint address covered by the same PMD entry, the kernel accepts the hint allthough the 8xx cannot handle different page sizes in the same PMD entry.

10000000-10001000 r-xp 00000000 00:0f 2597 /root/malloc 10010000-10011000 rwxp 00000000 00:0f 2597 /root/malloc

mmap(0x10080000, 524288, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|0x40000, -1, 0) = 0x10080000

This results the app remaining forever in do_page_fault()/hugetlb_fault() and when interrupting that app, we get the following warning:

[162980.035629] WARNING: CPU: 0 PID: 2777 at arch/powerpc/mm/hugetlbpage.c:354 hugetlb_free_pgd_range+0xc8/0x1e4 [162980.035699] CPU: 0 PID: 2777 Comm: malloc Tainted: G W 4.14.6 #85 [162980.035744] task: c67e2c00 task.stack: c668e000 [162980.035783] NIP: c000fe18 LR: c00e1eec CTR: c00f90c0 [162980.035830] REGS: c668fc20 TRAP: 0700 Tainted: G W (4.14.6) [162980.035854] MSR: 00029032 <EE,ME,IR,DR,RI> CR: 24044224 XER: 20000000 [162980.036003] [162980.036003] GPR00: c00e1eec c668fcd0 c67e2c00 00000010 c6869410 10080000 00000000 77fb4000 [162980.036003] GPR08: ffff0001 0683c001 00000000 ffffff80 44028228 10018a34 00004008 418004fc [162980.036003] GPR16: c668e000 00040100 c668e000 c06c0000 c668fe78 c668e000 c6835ba0 c668fd48 [162980.036003] GPR24: 00000000 73ffffff 74000000 00000001 77fb4000 100fffff 10100000 10100000 [162980.036743] NIP [c000fe18] hugetlb_free_pgd_range+0xc8/0x1e4 [162980.036839] LR [c00e1eec] free_pgtables+0x12c/0x150 [162980.036861] Call Trace: [162980.036939] [c668fcd0] [c00f0774] unlink_anon_vmas+0x1c4/0x214 (unreliable) [162980.037040] [c668fd10] [c00e1eec] free_pgtables+0x12c/0x150 [162980.037118] [c668fd40] [c00eabac] exit_mmap+0xe8/0x1b4 [162980.037210] [c668fda0] [c0019710] mmput.part.9+0x20/0xd8 [162980.037301] [c668fdb0] [c001ecb0] do_exit+0x1f0/0x93c [162980.037386] [c668fe00] [c001f478] do_group_exit+0x40/0xcc [162980.037479] [c668fe10] [c002a76c] get_signal+0x47c/0x614 [162980.037570] [c668fe70] [c0007840] do_signal+0x54/0x244 [162980.037654] [c668ff30] [c0007ae8] do_notify_resume+0x34/0x88 [162980.037744] [c668ff40] [c000dae8] do_user_signal+0x74/0xc4 [162980.037781] Instruction dump: [162980.037821] 7fdff378 81370000 54a3463a 80890020 7d24182e 7c841a14 712a0004 4082ff94 [162980.038014] 2f890000 419e0010 712a0ff0 408200e0 <0fe00000> 54a9000a 7f984840 419d0094 [162980.038216] ---[ end trace c0ceeca8e7a5800a ]--- [162980.038754] BUG: non-zero nr_ptes on freeing mm: 1 [162985.363322] BUG: non-zero nr_ptes on freeing mm: -1

In order to fix this, this patch uses the address space "slices" implemented for BOOK3S/64 and enhanced to support PPC32 by the preceding patch.

This patch modifies the context.id on the 8xx to be in the range [1:16] instead of [0:15] in order to identify context.id == 0 as not initialised contexts as done on BOOK3S

This patch activates CONFIG_PPC_MM_SLICES when CONFIG_HUGETLB_PAGE is selected for the 8xx

Alltough we could in theory have as many slices as PMD entries, the current slices implementation limits the number of low slices to 16. This limitation is not preventing us to fix the initial issue allthough it is suboptimal. It will be cured in a subsequent patch.

Fixes: 4b91428699477 ("powerpc/8xx: Implement support of hugepages") Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Reviewed-by: Aneesh Kumar K.V aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/powerpc/include/asm/mmu-8xx.h | 6 ++++++ arch/powerpc/kernel/setup-common.c | 2 ++ arch/powerpc/mm/8xx_mmu.c | 2 +- arch/powerpc/mm/hugetlbpage.c | 2 ++ arch/powerpc/mm/mmu_context_nohash.c | 18 ++++++++++++++++-- arch/powerpc/platforms/Kconfig.cputype | 1 + 6 files changed, 28 insertions(+), 3 deletions(-)

--- a/arch/powerpc/include/asm/mmu-8xx.h +++ b/arch/powerpc/include/asm/mmu-8xx.h @@ -169,6 +169,12 @@ typedef struct { unsigned int id; unsigned int active; unsigned long vdso_base; +#ifdef CONFIG_PPC_MM_SLICES + u16 user_psize; /* page size index */ + u64 low_slices_psize; /* page size encodings */ + unsigned char high_slices_psize[0]; + unsigned long addr_limit; +#endif } mm_context_t;

#define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000) --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -915,6 +915,8 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PPC_MM_SLICES #ifdef CONFIG_PPC64 init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64; +#elif defined(CONFIG_PPC_8xx) + init_mm.context.addr_limit = DEFAULT_MAP_WINDOW; #else #error "context.addr_limit not initialized." #endif --- a/arch/powerpc/mm/8xx_mmu.c +++ b/arch/powerpc/mm/8xx_mmu.c @@ -192,7 +192,7 @@ void set_context(unsigned long id, pgd_t mtspr(SPRN_M_TW, __pa(pgd) - offset);

/* Update context */ - mtspr(SPRN_M_CASID, id); + mtspr(SPRN_M_CASID, id - 1); /* sync */ mb(); } --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -552,9 +552,11 @@ unsigned long hugetlb_get_unmapped_area( struct hstate *hstate = hstate_file(file); int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));

+#ifdef CONFIG_PPC_RADIX_MMU if (radix_enabled()) return radix__hugetlb_get_unmapped_area(file, addr, len, pgoff, flags); +#endif return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1); } #endif --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -331,6 +331,20 @@ int init_new_context(struct task_struct { pr_hard("initing context for mm @%p\n", mm);

+#ifdef CONFIG_PPC_MM_SLICES + if (!mm->context.addr_limit) + mm->context.addr_limit = DEFAULT_MAP_WINDOW; + + /* + * We have MMU_NO_CONTEXT set to be ~0. Hence check + * explicitly against context.id == 0. This ensures that we properly + * initialize context slice details for newly allocated mm's (which will + * have id == 0) and don't alter context slice inherited via fork (which + * will have id != 0). + */ + if (mm->context.id == 0) + slice_set_user_psize(mm, mmu_virtual_psize); +#endif mm->context.id = MMU_NO_CONTEXT; mm->context.active = 0; return 0; @@ -428,8 +442,8 @@ void __init mmu_context_init(void) * -- BenH */ if (mmu_has_feature(MMU_FTR_TYPE_8xx)) { - first_context = 0; - last_context = 15; + first_context = 1; + last_context = 16; no_selective_tlbil = true; } else if (mmu_has_feature(MMU_FTR_TYPE_47x)) { first_context = 1; --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -325,6 +325,7 @@ config PPC_BOOK3E_MMU config PPC_MM_SLICES bool default y if PPC_STD_MMU_64 + default y if PPC_8xx && HUGETLB_PAGE default n

config PPC_HAVE_PMU_SUPPORT