- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] dm thin: stop no_space_timeout worker when switching to" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 75294442d896f2767be34f75aca7cc2b0d01301f Mon Sep 17 00:00:00 2001 From: Hou Tao <houtao1(a)huawei.com> Date: Thu, 2 Aug 2018 16:18:24 +0800 Subject: [PATCH] dm thin: stop no_space_timeout worker when switching to write-mode Now both check_for_space() and do_no_space_timeout() will read & write pool->pf.error_if_no_space. If these functions run concurrently, as shown in the following case, the default setting of "queue_if_no_space" can get lost. precondition: * error_if_no_space = false (aka "queue_if_no_space") * pool is in Out-of-Data-Space (OODS) mode * no_space_timeout worker has been queued CPU 0: CPU 1: // delete a thin device process_delete_mesg() // check_for_space() invoked by commit() set_pool_mode(pool, PM_WRITE) pool->pf.error_if_no_space = \ pt->requested_pf.error_if_no_space // timeout, pool is still in OODS mode do_no_space_timeout // "queue_if_no_space" config is lost pool->pf.error_if_no_space = true pool->pf.mode = new_mode Fix it by stopping no_space_timeout worker when switching to write mode. Fixes: bcc696fac11f ("dm thin: stay in out-of-data-space mode once no_space_timeout expires") Cc: stable(a)vger.kernel.org Signed-off-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 5997d6808b57..7bd60a150f8f 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2503,6 +2503,8 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) case PM_WRITE: if (old_mode != new_mode) notify_of_pool_mode_change(pool, "write"); + if (old_mode == PM_OUT_OF_DATA_SPACE) + cancel_delayed_work_sync(&pool->no_space_timeout); pool->out_of_data_space = false; pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space; dm_pool_metadata_read_write(pool->pmd);

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Check that supplied blue flame index doesn't" failed to apply to 4.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 05f58ceba123bdb420cf44c6ea04b6db467edd1c Mon Sep 17 00:00:00 2001 From: Leon Romanovsky <leonro(a)mellanox.com> Date: Sun, 8 Jul 2018 13:50:21 +0300 Subject: [PATCH] RDMA/mlx5: Check that supplied blue flame index doesn't overflow User's supplied index is checked again total number of system pages, but this number already includes num_static_sys_pages, so addition of that value to supplied index causes to below error while trying to access sys_pages[]. BUG: KASAN: slab-out-of-bounds in bfregn_to_uar_index+0x34f/0x400 Read of size 4 at addr ffff880065561904 by task syz-executor446/314 CPU: 0 PID: 314 Comm: syz-executor446 Not tainted 4.18.0-rc1+ #256 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xef/0x17e print_address_description+0x83/0x3b0 kasan_report+0x18d/0x4d0 bfregn_to_uar_index+0x34f/0x400 create_user_qp+0x272/0x227d create_qp_common+0x32eb/0x43e0 mlx5_ib_create_qp+0x379/0x1ca0 create_qp.isra.5+0xc94/0x22d0 ib_uverbs_create_qp+0x21b/0x2a0 ib_uverbs_write+0xc2c/0x1010 vfs_write+0x1b0/0x550 ksys_write+0xc6/0x1a0 do_syscall_64+0xa7/0x590 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x433679 Code: fd ff 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b 91 fd ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff2b3d8e48 EFLAGS: 00000217 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00000000004002f8 RCX: 0000000000433679 RDX: 0000000000000040 RSI: 0000000020000240 RDI: 0000000000000003 RBP: 00000000006d4018 R08: 00000000004002f8 R09: 00000000004002f8 R10: 00000000004002f8 R11: 0000000000000217 R12: 0000000000000000 R13: 000000000040cb00 R14: 000000000040cb90 R15: 0000000000000006 Allocated by task 314: kasan_kmalloc+0xa0/0xd0 __kmalloc+0x1a9/0x510 mlx5_ib_alloc_ucontext+0x966/0x2620 ib_uverbs_get_context+0x23f/0xa60 ib_uverbs_write+0xc2c/0x1010 __vfs_write+0x10d/0x720 vfs_write+0x1b0/0x550 ksys_write+0xc6/0x1a0 do_syscall_64+0xa7/0x590 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 1: __kasan_slab_free+0x12e/0x180 kfree+0x159/0x630 kvfree+0x37/0x50 single_release+0x8e/0xf0 __fput+0x2d8/0x900 task_work_run+0x102/0x1f0 exit_to_usermode_loop+0x159/0x1c0 do_syscall_64+0x408/0x590 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff880065561100 which belongs to the cache kmalloc-4096 of size 4096 The buggy address is located 2052 bytes inside of 4096-byte region [ffff880065561100, ffff880065562100) The buggy address belongs to the page: page:ffffea0001955800 count:1 mapcount:0 mapping:ffff88006c402480 index:0x0 compound_mapcount: 0 flags: 0x4000000000008100(slab|head) raw: 4000000000008100 ffffea0001a7c000 0000000200000002 ffff88006c402480 raw: 0000000000000000 0000000080070007 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff880065561800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff880065561880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff880065561900: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff880065561980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff880065561a00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc Cc: <stable(a)vger.kernel.org> # 4.15 Fixes: 1ee47ab3e8d8 ("IB/mlx5: Enable QP creation with a given blue flame index") Reported-by: Noa Osherovich <noaos(a)mellanox.com> Signed-off-by: Leon Romanovsky <leonro(a)mellanox.com> Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 93087409f4b8..04a5d82c9cf3 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1330,6 +1330,6 @@ unsigned long mlx5_ib_get_xlt_emergency_page(void); void mlx5_ib_put_xlt_emergency_page(void); int bfregn_to_uar_index(struct mlx5_ib_dev *dev, - struct mlx5_bfreg_info *bfregi, int bfregn, + struct mlx5_bfreg_info *bfregi, u32 bfregn, bool dyn_bfreg); #endif /* MLX5_IB_H */ diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 51e68ca20215..d4414015b64f 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -631,22 +631,23 @@ static void mlx5_ib_unlock_cqs(struct mlx5_ib_cq *send_cq, struct mlx5_ib_cq *recv_cq); int bfregn_to_uar_index(struct mlx5_ib_dev *dev, - struct mlx5_bfreg_info *bfregi, int bfregn, + struct mlx5_bfreg_info *bfregi, u32 bfregn, bool dyn_bfreg) { - int bfregs_per_sys_page; - int index_of_sys_page; - int offset; + unsigned int bfregs_per_sys_page; + u32 index_of_sys_page; + u32 offset; bfregs_per_sys_page = get_uars_per_sys_page(dev, bfregi->lib_uar_4k) * MLX5_NON_FP_BFREGS_PER_UAR; index_of_sys_page = bfregn / bfregs_per_sys_page; - if (index_of_sys_page >= bfregi->num_sys_pages) - return -EINVAL; - if (dyn_bfreg) { index_of_sys_page += bfregi->num_static_sys_pages; + + if (index_of_sys_page >= bfregi->num_sys_pages) + return -EINVAL; + if (bfregn > bfregi->num_dyn_bfregs || bfregi->sys_pages[index_of_sys_page] == MLX5_IB_INVALID_UAR_INDEX) { mlx5_ib_dbg(dev, "Invalid dynamic uar index\n");

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] ib_srpt: Fix a use-after-free in __srpt_close_all_ch()" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 14d15c2b278011056482eb015dff89f9cbf2b841 Mon Sep 17 00:00:00 2001 From: Bart Van Assche <bart.vanassche(a)wdc.com> Date: Mon, 2 Jul 2018 14:08:45 -0700 Subject: [PATCH] ib_srpt: Fix a use-after-free in __srpt_close_all_ch() BUG: KASAN: use-after-free in srpt_set_enabled+0x1a9/0x1e0 [ib_srpt] Read of size 4 at addr ffff8801269d23f8 by task check/29726 CPU: 4 PID: 29726 Comm: check Not tainted 4.18.0-rc2-dbg+ #4 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xa4/0xf5 print_address_description+0x6f/0x270 kasan_report+0x241/0x360 __asan_load4+0x78/0x80 srpt_set_enabled+0x1a9/0x1e0 [ib_srpt] srpt_tpg_enable_store+0xb8/0x120 [ib_srpt] configfs_write_file+0x14e/0x1d0 [configfs] __vfs_write+0xd2/0x3b0 vfs_write+0x101/0x270 ksys_write+0xab/0x120 __x64_sys_write+0x43/0x50 do_syscall_64+0x77/0x230 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f235cfe6154 Fixes: aaf45bd83eba ("IB/srpt: Detect session shutdown reliably") Signed-off-by: Bart Van Assche <bart.vanassche(a)wdc.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 754da8d30952..e42eec20c631 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1940,8 +1940,8 @@ static void __srpt_close_all_ch(struct srpt_port *sport) list_for_each_entry(nexus, &sport->nexus_list, entry) { list_for_each_entry(ch, &nexus->ch_list, list) { if (srpt_disconnect_ch(ch) >= 0) - pr_info("Closing channel %s-%d because target %s_%d has been disabled\n", - ch->sess_name, ch->qp->qp_num, + pr_info("Closing channel %s because target %s_%d has been disabled\n", + ch->sess_name, sport->sdev->device->name, sport->port); srpt_close_ch(ch); }

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/pseries: Defer the logging of rtas error to irq work" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 94675cceacaec27a30eefb142c4c59a9d3131742 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar <mahesh(a)linux.vnet.ibm.com> Date: Wed, 4 Jul 2018 23:27:21 +0530 Subject: [PATCH] powerpc/pseries: Defer the logging of rtas error to irq work queue. rtas_log_buf is a buffer to hold RTAS event data that are communicated to kernel by hypervisor. This buffer is then used to pass RTAS event data to user through proc fs. This buffer is allocated from vmalloc (non-linear mapping) area. On Machine check interrupt, register r3 points to RTAS extended event log passed by hypervisor that contains the MCE event. The pseries machine check handler then logs this error into rtas_log_buf. The rtas_log_buf is a vmalloc-ed (non-linear) buffer we end up taking up a page fault (vector 0x300) while accessing it. Since machine check interrupt handler runs in NMI context we can not afford to take any page fault. Page faults are not honored in NMI context and causes kernel panic. Apart from that, as Nick pointed out, pSeries_log_error() also takes a spin_lock while logging error which is not safe in NMI context. It may endup in deadlock if we get another MCE before releasing the lock. Fix this by deferring the logging of rtas error to irq work queue. Current implementation uses two different buffers to hold rtas error log depending on whether extended log is provided or not. This makes bit difficult to identify which buffer has valid data that needs to logged later in irq work. Simplify this using single buffer, one per paca, and copy rtas log to it irrespective of whether extended log is provided or not. Allocate this buffer below RMA region so that it can be accessed in real mode mce handler. Fixes: b96672dd840f ("powerpc: Machine check interrupt is a non-maskable interrupt") Cc: stable(a)vger.kernel.org # v4.14+ Reviewed-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Mahesh Salgaonkar <mahesh(a)linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 4e9cede5a7e7..ad4f16164619 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -247,6 +247,9 @@ struct paca_struct { void *rfi_flush_fallback_area; u64 l1d_flush_size; #endif +#ifdef CONFIG_PPC_PSERIES + u8 *mce_data_buf; /* buffer to hold per cpu rtas errlog */ +#endif /* CONFIG_PPC_PSERIES */ } ____cacheline_aligned; extern void copy_mm_to_paca(struct mm_struct *mm); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index ef104144d4bc..14a46b07ab2f 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -22,6 +22,7 @@ #include <linux/of.h> #include <linux/fs.h> #include <linux/reboot.h> +#include <linux/irq_work.h> #include <asm/machdep.h> #include <asm/rtas.h> @@ -32,11 +33,13 @@ static unsigned char ras_log_buf[RTAS_ERROR_LOG_MAX]; static DEFINE_SPINLOCK(ras_log_buf_lock); -static char global_mce_data_buf[RTAS_ERROR_LOG_MAX]; -static DEFINE_PER_CPU(__u64, mce_data_buf); - static int ras_check_exception_token; +static void mce_process_errlog_event(struct irq_work *work); +static struct irq_work mce_errlog_process_work = { + .func = mce_process_errlog_event, +}; + #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 @@ -330,16 +333,20 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) +static inline struct rtas_error_log *fwnmi_get_errlog(void) +{ + return (struct rtas_error_log *)local_paca->mce_data_buf; +} + /* * Get the error information for errors coming through the * FWNMI vectors. The pt_regs' r3 will be updated to reflect * the actual r3 if possible, and a ptr to the error log entry * will be returned if found. * - * If the RTAS error is not of the extended type, then we put it in a per - * cpu 64bit buffer. If it is the extended type we use global_mce_data_buf. + * Use one buffer mce_data_buf per cpu to store RTAS error. * - * The global_mce_data_buf does not have any locks or protection around it, + * The mce_data_buf does not have any locks or protection around it, * if a second machine check comes in, or a system reset is done * before we have logged the error, then we will get corruption in the * error log. This is preferable over holding off on calling @@ -349,7 +356,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) { unsigned long *savep; - struct rtas_error_log *h, *errhdr = NULL; + struct rtas_error_log *h; /* Mask top two bits */ regs->gpr[3] &= ~(0x3UL << 62); @@ -362,22 +369,20 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) savep = __va(regs->gpr[3]); regs->gpr[3] = savep[0]; /* restore original r3 */ - /* If it isn't an extended log we can use the per cpu 64bit buffer */ h = (struct rtas_error_log *)&savep[1]; + /* Use the per cpu buffer from paca to store rtas error log */ + memset(local_paca->mce_data_buf, 0, RTAS_ERROR_LOG_MAX); if (!rtas_error_extended(h)) { - memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64)); - errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf); + memcpy(local_paca->mce_data_buf, h, sizeof(__u64)); } else { int len, error_log_length; error_log_length = 8 + rtas_error_extended_log_length(h); len = min_t(int, error_log_length, RTAS_ERROR_LOG_MAX); - memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX); - memcpy(global_mce_data_buf, h, len); - errhdr = (struct rtas_error_log *)global_mce_data_buf; + memcpy(local_paca->mce_data_buf, h, len); } - return errhdr; + return (struct rtas_error_log *)local_paca->mce_data_buf; } /* Call this when done with the data returned by FWNMI_get_errinfo. @@ -422,6 +427,17 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } +/* + * Process MCE rtas errlog event. + */ +static void mce_process_errlog_event(struct irq_work *work) +{ + struct rtas_error_log *err; + + err = fwnmi_get_errlog(); + log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); +} + /* * See if we can recover from a machine check exception. * This is only called on power4 (or above) and only via @@ -466,7 +482,8 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) recovered = 1; } - log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); + /* Queue irq work to log this rtas event later. */ + irq_work_queue(&mce_errlog_process_work); return recovered; } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 9948ad16f788..b411a74b861d 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -41,6 +41,7 @@ #include <linux/root_dev.h> #include <linux/of.h> #include <linux/of_pci.h> +#include <linux/memblock.h> #include <asm/mmu.h> #include <asm/processor.h> @@ -102,6 +103,9 @@ static void pSeries_show_cpuinfo(struct seq_file *m) static void __init fwnmi_init(void) { unsigned long system_reset_addr, machine_check_addr; + u8 *mce_data_buf; + unsigned int i; + int nr_cpus = num_possible_cpus(); int ibm_nmi_register = rtas_token("ibm,nmi-register"); if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE) @@ -115,6 +119,18 @@ static void __init fwnmi_init(void) if (0 == rtas_call(ibm_nmi_register, 2, 1, NULL, system_reset_addr, machine_check_addr)) fwnmi_active = 1; + + /* + * Allocate a chunk for per cpu buffer to hold rtas errorlog. + * It will be used in real mode mce handler, hence it needs to be + * below RMA. + */ + mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus, + RTAS_ERROR_LOG_MAX, ppc64_rma_size)); + for_each_possible_cpu(i) { + paca_ptrs[i]->mce_data_buf = mce_data_buf + + (RTAS_ERROR_LOG_MAX * i); + } } static void pseries_8259_cascade(struct irq_desc *desc)

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/pseries: Defer the logging of rtas error to irq work" failed to apply to 4.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 94675cceacaec27a30eefb142c4c59a9d3131742 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar <mahesh(a)linux.vnet.ibm.com> Date: Wed, 4 Jul 2018 23:27:21 +0530 Subject: [PATCH] powerpc/pseries: Defer the logging of rtas error to irq work queue. rtas_log_buf is a buffer to hold RTAS event data that are communicated to kernel by hypervisor. This buffer is then used to pass RTAS event data to user through proc fs. This buffer is allocated from vmalloc (non-linear mapping) area. On Machine check interrupt, register r3 points to RTAS extended event log passed by hypervisor that contains the MCE event. The pseries machine check handler then logs this error into rtas_log_buf. The rtas_log_buf is a vmalloc-ed (non-linear) buffer we end up taking up a page fault (vector 0x300) while accessing it. Since machine check interrupt handler runs in NMI context we can not afford to take any page fault. Page faults are not honored in NMI context and causes kernel panic. Apart from that, as Nick pointed out, pSeries_log_error() also takes a spin_lock while logging error which is not safe in NMI context. It may endup in deadlock if we get another MCE before releasing the lock. Fix this by deferring the logging of rtas error to irq work queue. Current implementation uses two different buffers to hold rtas error log depending on whether extended log is provided or not. This makes bit difficult to identify which buffer has valid data that needs to logged later in irq work. Simplify this using single buffer, one per paca, and copy rtas log to it irrespective of whether extended log is provided or not. Allocate this buffer below RMA region so that it can be accessed in real mode mce handler. Fixes: b96672dd840f ("powerpc: Machine check interrupt is a non-maskable interrupt") Cc: stable(a)vger.kernel.org # v4.14+ Reviewed-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Mahesh Salgaonkar <mahesh(a)linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 4e9cede5a7e7..ad4f16164619 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -247,6 +247,9 @@ struct paca_struct { void *rfi_flush_fallback_area; u64 l1d_flush_size; #endif +#ifdef CONFIG_PPC_PSERIES + u8 *mce_data_buf; /* buffer to hold per cpu rtas errlog */ +#endif /* CONFIG_PPC_PSERIES */ } ____cacheline_aligned; extern void copy_mm_to_paca(struct mm_struct *mm); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index ef104144d4bc..14a46b07ab2f 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -22,6 +22,7 @@ #include <linux/of.h> #include <linux/fs.h> #include <linux/reboot.h> +#include <linux/irq_work.h> #include <asm/machdep.h> #include <asm/rtas.h> @@ -32,11 +33,13 @@ static unsigned char ras_log_buf[RTAS_ERROR_LOG_MAX]; static DEFINE_SPINLOCK(ras_log_buf_lock); -static char global_mce_data_buf[RTAS_ERROR_LOG_MAX]; -static DEFINE_PER_CPU(__u64, mce_data_buf); - static int ras_check_exception_token; +static void mce_process_errlog_event(struct irq_work *work); +static struct irq_work mce_errlog_process_work = { + .func = mce_process_errlog_event, +}; + #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 @@ -330,16 +333,20 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) +static inline struct rtas_error_log *fwnmi_get_errlog(void) +{ + return (struct rtas_error_log *)local_paca->mce_data_buf; +} + /* * Get the error information for errors coming through the * FWNMI vectors. The pt_regs' r3 will be updated to reflect * the actual r3 if possible, and a ptr to the error log entry * will be returned if found. * - * If the RTAS error is not of the extended type, then we put it in a per - * cpu 64bit buffer. If it is the extended type we use global_mce_data_buf. + * Use one buffer mce_data_buf per cpu to store RTAS error. * - * The global_mce_data_buf does not have any locks or protection around it, + * The mce_data_buf does not have any locks or protection around it, * if a second machine check comes in, or a system reset is done * before we have logged the error, then we will get corruption in the * error log. This is preferable over holding off on calling @@ -349,7 +356,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) { unsigned long *savep; - struct rtas_error_log *h, *errhdr = NULL; + struct rtas_error_log *h; /* Mask top two bits */ regs->gpr[3] &= ~(0x3UL << 62); @@ -362,22 +369,20 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) savep = __va(regs->gpr[3]); regs->gpr[3] = savep[0]; /* restore original r3 */ - /* If it isn't an extended log we can use the per cpu 64bit buffer */ h = (struct rtas_error_log *)&savep[1]; + /* Use the per cpu buffer from paca to store rtas error log */ + memset(local_paca->mce_data_buf, 0, RTAS_ERROR_LOG_MAX); if (!rtas_error_extended(h)) { - memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64)); - errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf); + memcpy(local_paca->mce_data_buf, h, sizeof(__u64)); } else { int len, error_log_length; error_log_length = 8 + rtas_error_extended_log_length(h); len = min_t(int, error_log_length, RTAS_ERROR_LOG_MAX); - memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX); - memcpy(global_mce_data_buf, h, len); - errhdr = (struct rtas_error_log *)global_mce_data_buf; + memcpy(local_paca->mce_data_buf, h, len); } - return errhdr; + return (struct rtas_error_log *)local_paca->mce_data_buf; } /* Call this when done with the data returned by FWNMI_get_errinfo. @@ -422,6 +427,17 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } +/* + * Process MCE rtas errlog event. + */ +static void mce_process_errlog_event(struct irq_work *work) +{ + struct rtas_error_log *err; + + err = fwnmi_get_errlog(); + log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); +} + /* * See if we can recover from a machine check exception. * This is only called on power4 (or above) and only via @@ -466,7 +482,8 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) recovered = 1; } - log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); + /* Queue irq work to log this rtas event later. */ + irq_work_queue(&mce_errlog_process_work); return recovered; } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 9948ad16f788..b411a74b861d 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -41,6 +41,7 @@ #include <linux/root_dev.h> #include <linux/of.h> #include <linux/of_pci.h> +#include <linux/memblock.h> #include <asm/mmu.h> #include <asm/processor.h> @@ -102,6 +103,9 @@ static void pSeries_show_cpuinfo(struct seq_file *m) static void __init fwnmi_init(void) { unsigned long system_reset_addr, machine_check_addr; + u8 *mce_data_buf; + unsigned int i; + int nr_cpus = num_possible_cpus(); int ibm_nmi_register = rtas_token("ibm,nmi-register"); if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE) @@ -115,6 +119,18 @@ static void __init fwnmi_init(void) if (0 == rtas_call(ibm_nmi_register, 2, 1, NULL, system_reset_addr, machine_check_addr)) fwnmi_active = 1; + + /* + * Allocate a chunk for per cpu buffer to hold rtas errorlog. + * It will be used in real mode mce handler, hence it needs to be + * below RMA. + */ + mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus, + RTAS_ERROR_LOG_MAX, ppc64_rma_size)); + for_each_possible_cpu(i) { + paca_ptrs[i]->mce_data_buf = mce_data_buf + + (RTAS_ERROR_LOG_MAX * i); + } } static void pseries_8259_cascade(struct irq_desc *desc)

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/64s: Fix page table fragment refcount race vs" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4231aba000f5a4583dd9f67057aadb68c3eca99d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin <npiggin(a)gmail.com> Date: Fri, 27 Jul 2018 21:48:17 +1000 Subject: [PATCH] powerpc/64s: Fix page table fragment refcount race vs speculative references The page table fragment allocator uses the main page refcount racily with respect to speculative references. A customer observed a BUG due to page table page refcount underflow in the fragment allocator. This can be caused by the fragment allocator set_page_count stomping on a speculative reference, and then the speculative failure handler decrements the new reference, and the underflow eventually pops when the page tables are freed. Fix this by using a dedicated field in the struct page for the page table fragment allocator. Fixes: 5c1f6ee9a31c ("powerpc: Reduce PTE table memory wastage") Cc: stable(a)vger.kernel.org # v3.10+ Reviewed-by: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 8b24168ea8c4..4a892d894a0f 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -200,9 +200,9 @@ static void pte_frag_destroy(void *pte_frag) /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) { + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -215,9 +215,9 @@ static void pmd_frag_destroy(void *pmd_frag) /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PMD_FRAG_NR - count)) { + if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 4afbfbb64bfd..78d0b3d5ebad 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -270,6 +270,8 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); + ret = page_address(page); /* * if we support only one fragment just return the @@ -285,7 +287,7 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) * count. */ if (likely(!mm->context.pmd_frag)) { - set_page_count(page, PMD_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -308,9 +310,10 @@ void pmd_fragment_free(unsigned long *pmd) { struct page *page = virt_to_page(pmd); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -352,6 +355,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); ret = page_address(page); /* @@ -367,7 +371,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) * count. */ if (likely(!mm->context.pte_frag)) { - set_page_count(page, PTE_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); mm->context.pte_frag = ret + PTE_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -390,10 +394,11 @@ void pte_fragment_free(unsigned long *table, int kernel) { struct page *page = virt_to_page(table); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { if (!kernel) pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..22651e124071 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -139,7 +139,10 @@ struct page { unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ - struct mm_struct *pt_mm; /* x86 pgds only */ + union { + struct mm_struct *pt_mm; /* x86 pgds only */ + atomic_t pt_frag_refcount; /* powerpc */ + }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/64s: Fix page table fragment refcount race vs" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4231aba000f5a4583dd9f67057aadb68c3eca99d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin <npiggin(a)gmail.com> Date: Fri, 27 Jul 2018 21:48:17 +1000 Subject: [PATCH] powerpc/64s: Fix page table fragment refcount race vs speculative references The page table fragment allocator uses the main page refcount racily with respect to speculative references. A customer observed a BUG due to page table page refcount underflow in the fragment allocator. This can be caused by the fragment allocator set_page_count stomping on a speculative reference, and then the speculative failure handler decrements the new reference, and the underflow eventually pops when the page tables are freed. Fix this by using a dedicated field in the struct page for the page table fragment allocator. Fixes: 5c1f6ee9a31c ("powerpc: Reduce PTE table memory wastage") Cc: stable(a)vger.kernel.org # v3.10+ Reviewed-by: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 8b24168ea8c4..4a892d894a0f 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -200,9 +200,9 @@ static void pte_frag_destroy(void *pte_frag) /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) { + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -215,9 +215,9 @@ static void pmd_frag_destroy(void *pmd_frag) /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PMD_FRAG_NR - count)) { + if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 4afbfbb64bfd..78d0b3d5ebad 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -270,6 +270,8 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); + ret = page_address(page); /* * if we support only one fragment just return the @@ -285,7 +287,7 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) * count. */ if (likely(!mm->context.pmd_frag)) { - set_page_count(page, PMD_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -308,9 +310,10 @@ void pmd_fragment_free(unsigned long *pmd) { struct page *page = virt_to_page(pmd); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -352,6 +355,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); ret = page_address(page); /* @@ -367,7 +371,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) * count. */ if (likely(!mm->context.pte_frag)) { - set_page_count(page, PTE_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); mm->context.pte_frag = ret + PTE_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -390,10 +394,11 @@ void pte_fragment_free(unsigned long *table, int kernel) { struct page *page = virt_to_page(table); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { if (!kernel) pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..22651e124071 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -139,7 +139,10 @@ struct page { unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ - struct mm_struct *pt_mm; /* x86 pgds only */ + union { + struct mm_struct *pt_mm; /* x86 pgds only */ + atomic_t pt_frag_refcount; /* powerpc */ + }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/64s: Fix page table fragment refcount race vs" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4231aba000f5a4583dd9f67057aadb68c3eca99d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin <npiggin(a)gmail.com> Date: Fri, 27 Jul 2018 21:48:17 +1000 Subject: [PATCH] powerpc/64s: Fix page table fragment refcount race vs speculative references The page table fragment allocator uses the main page refcount racily with respect to speculative references. A customer observed a BUG due to page table page refcount underflow in the fragment allocator. This can be caused by the fragment allocator set_page_count stomping on a speculative reference, and then the speculative failure handler decrements the new reference, and the underflow eventually pops when the page tables are freed. Fix this by using a dedicated field in the struct page for the page table fragment allocator. Fixes: 5c1f6ee9a31c ("powerpc: Reduce PTE table memory wastage") Cc: stable(a)vger.kernel.org # v3.10+ Reviewed-by: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 8b24168ea8c4..4a892d894a0f 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -200,9 +200,9 @@ static void pte_frag_destroy(void *pte_frag) /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) { + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -215,9 +215,9 @@ static void pmd_frag_destroy(void *pmd_frag) /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PMD_FRAG_NR - count)) { + if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 4afbfbb64bfd..78d0b3d5ebad 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -270,6 +270,8 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); + ret = page_address(page); /* * if we support only one fragment just return the @@ -285,7 +287,7 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) * count. */ if (likely(!mm->context.pmd_frag)) { - set_page_count(page, PMD_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -308,9 +310,10 @@ void pmd_fragment_free(unsigned long *pmd) { struct page *page = virt_to_page(pmd); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -352,6 +355,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); ret = page_address(page); /* @@ -367,7 +371,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) * count. */ if (likely(!mm->context.pte_frag)) { - set_page_count(page, PTE_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); mm->context.pte_frag = ret + PTE_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -390,10 +394,11 @@ void pte_fragment_free(unsigned long *table, int kernel) { struct page *page = virt_to_page(table); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { if (!kernel) pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..22651e124071 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -139,7 +139,10 @@ struct page { unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ - struct mm_struct *pt_mm; /* x86 pgds only */ + union { + struct mm_struct *pt_mm; /* x86 pgds only */ + atomic_t pt_frag_refcount; /* powerpc */ + }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else

7 years, 2 months

1
0
0 0

[PATCH for 4.4 1/1] x86/mm/pat: Fix L1TF stable backport for CPA, 2nd call

by Jiri Slaby

From: Andi Kleen <ak(a)linux.intel.com> Mostly recycling the commit log from adaba23ccd7d which fixed populate_pmd, but did not fix populate_pud. The same problem exists there. Stable trees reverted the following patch: Revert "x86/mm/pat: Ensure cpa->pfn only contains page frame numbers" This reverts commit 87e2bd898d3a79a8c609f183180adac47879a2a4 which is commit edc3b9129cecd0f0857112136f5b8b1bc1d45918 upstream. but the L1TF patch 02ff2769edbc backported here x86/mm/pat: Make set_memory_np() L1TF safe commit 958f79b9ee55dfaf00c8106ed1c22a2919e0028b upstream set_memory_np() is used to mark kernel mappings not present, but it has it's own open coded mechanism which does not have the L1TF protection of inverting the address bits. assumed that cpa->pfn contains a PFN. With the above patch reverted it does not, which causes the PUD to be set to an incorrect address shifted by 12 bits, which can cause various failures. Convert the address to a PFN before passing it to pud_pfn(). This is a 4.4 stable only patch to fix the L1TF patches backport there. Cc: stable(a)vger.kernel.org # 4.4-only Cc: Andi Kleen <ak(a)linux.intel.com> Signed-off-by: Jiri Slaby <jslaby(a)suse.cz> --- arch/x86/mm/pageattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 1007fa80f5a6..0e1dd7d47f05 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1079,7 +1079,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, * Map everything starting from the Gb boundary, possibly with 1G pages */ while (end - start >= PUD_SIZE) { - set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn, + set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn >> PAGE_SHIFT, canon_pgprot(pud_pgprot)))); start += PUD_SIZE; -- 2.18.0

7 years, 2 months

1
1
0 0

FAILED: patch "[PATCH] libertas: fix suspend and resume for SDIO connected cards" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 7444a8092906ed44c09459780c56ba57043e39b1 Mon Sep 17 00:00:00 2001 From: Daniel Mack <daniel(a)zonque.org> Date: Wed, 27 Jun 2018 20:58:45 +0200 Subject: [PATCH] libertas: fix suspend and resume for SDIO connected cards Prior to commit 573185cc7e64 ("mmc: core: Invoke sdio func driver's PM callbacks from the sdio bus"), the MMC core used to call into the power management functions of SDIO clients itself and removed the card if the return code was non-zero. IOW, the mmc handled errors gracefully and didn't upchain them to the pm core. Since this change, the mmc core relies on generic power management functions which treat all errors as a reason to cancel the suspend immediately. This causes suspend attempts to fail when the libertas driver is loaded. To fix this, power down the card explicitly in if_sdio_suspend() when we know we're about to lose power and return success. Also set a flag in these cases, and power up the card again in if_sdio_resume(). Fixes: 573185cc7e64 ("mmc: core: Invoke sdio func driver's PM callbacks from the sdio bus") Cc: <stable(a)vger.kernel.org> Signed-off-by: Daniel Mack <daniel(a)zonque.org> Reviewed-by: Chris Ball <chris(a)printf.net> Reviewed-by: Ulf Hansson <ulf.hansson(a)linaro.org> Signed-off-by: Kalle Valo <kvalo(a)codeaurora.org> diff --git a/drivers/net/wireless/marvell/libertas/dev.h b/drivers/net/wireless/marvell/libertas/dev.h index dd1ee1f0af48..469134930026 100644 --- a/drivers/net/wireless/marvell/libertas/dev.h +++ b/drivers/net/wireless/marvell/libertas/dev.h @@ -104,6 +104,7 @@ struct lbs_private { u8 fw_ready; u8 surpriseremoved; u8 setup_fw_on_resume; + u8 power_up_on_resume; int (*hw_host_to_card) (struct lbs_private *priv, u8 type, u8 *payload, u16 nb); void (*reset_card) (struct lbs_private *priv); int (*power_save) (struct lbs_private *priv); diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c index 2300e796c6ab..43743c26c071 100644 --- a/drivers/net/wireless/marvell/libertas/if_sdio.c +++ b/drivers/net/wireless/marvell/libertas/if_sdio.c @@ -1290,15 +1290,23 @@ static void if_sdio_remove(struct sdio_func *func) static int if_sdio_suspend(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); - int ret; struct if_sdio_card *card = sdio_get_drvdata(func); + struct lbs_private *priv = card->priv; + int ret; mmc_pm_flag_t flags = sdio_get_host_pm_caps(func); + priv->power_up_on_resume = false; /* If we're powered off anyway, just let the mmc layer remove the * card. */ - if (!lbs_iface_active(card->priv)) - return -ENOSYS; + if (!lbs_iface_active(priv)) { + if (priv->fw_ready) { + priv->power_up_on_resume = true; + if_sdio_power_off(card); + } + + return 0; + } dev_info(dev, "%s: suspend: PM flags = 0x%x\n", sdio_func_id(func), flags); @@ -1306,9 +1314,14 @@ static int if_sdio_suspend(struct device *dev) /* If we aren't being asked to wake on anything, we should bail out * and let the SD stack power down the card. */ - if (card->priv->wol_criteria == EHS_REMOVE_WAKEUP) { + if (priv->wol_criteria == EHS_REMOVE_WAKEUP) { dev_info(dev, "Suspend without wake params -- powering down card\n"); - return -ENOSYS; + if (priv->fw_ready) { + priv->power_up_on_resume = true; + if_sdio_power_off(card); + } + + return 0; } if (!(flags & MMC_PM_KEEP_POWER)) { @@ -1321,7 +1334,7 @@ static int if_sdio_suspend(struct device *dev) if (ret) return ret; - ret = lbs_suspend(card->priv); + ret = lbs_suspend(priv); if (ret) return ret; @@ -1336,6 +1349,11 @@ static int if_sdio_resume(struct device *dev) dev_info(dev, "%s: resume: we're back\n", sdio_func_id(func)); + if (card->priv->power_up_on_resume) { + if_sdio_power_on(card); + wait_event(card->pwron_waitq, card->priv->fw_ready); + } + ret = lbs_resume(card->priv); return ret;

7 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror