From fb3296335500aaff61333df8eabbccf28761c79d Mon Sep 17 00:00:00 2001 From: Danesh Petigara Date: Mon, 11 Jan 2016 13:22:26 -0800 Subject: drivers: ata: wake port before DMA stop for ALPM The AHCI driver code stops and starts port DMA engines at will without considering the power state of the particular port. The AHCI specification isn't very clear on how to handle this scenario, leaving implementation open to interpretation. Broadcom's STB SATA host controller is unable to handle port DMA controller restarts when the port in question is in low power mode. When a port enters partial or slumber mode, its PHY is powered down. When a controller restart is requested, the controller's internal state machine expects the PHY to be brought back up by software which never happens in this case, resulting in failures. To avoid this situation, logic is added to manually wake up the port just before its DMA engine is stopped, if the port happens to be in a low power state. HBA initiated power management ensures that the port eventually returns to its configured low power state, when the link is idle (as per the conditions listed in the spec). A new host flag is also added to ensure this logic is only exercised for hosts with the above limitation. tj: Formatting changes. Signed-off-by: Danesh Petigara Reviewed-by: Markus Mayer Signed-off-by: Tejun Heo diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index a4faa43..a44c75d 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -250,6 +250,7 @@ enum { AHCI_HFLAG_MULTI_MSI = 0, AHCI_HFLAG_MULTI_MSIX = 0, #endif + AHCI_HFLAG_WAKE_BEFORE_STOP = (1 << 22), /* wake before DMA stop */ /* ap->flags bits */ diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c index b36cae2..e87bcec 100644 --- a/drivers/ata/ahci_brcmstb.c +++ b/drivers/ata/ahci_brcmstb.c @@ -317,6 +317,7 @@ static int brcm_ahci_probe(struct platform_device *pdev) if (IS_ERR(hpriv)) return PTR_ERR(hpriv); hpriv->plat_data = priv; + hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP; brcm_sata_alpm_init(hpriv); diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index d61740e..284a176 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -593,8 +593,22 @@ EXPORT_SYMBOL_GPL(ahci_start_engine); int ahci_stop_engine(struct ata_port *ap) { void __iomem *port_mmio = ahci_port_base(ap); + struct ahci_host_priv *hpriv = ap->host->private_data; u32 tmp; + /* + * On some controllers, stopping a port's DMA engine while the port + * is in ALPM state (partial or slumber) results in failures on + * subsequent DMA engine starts. For those controllers, put the + * port back in active state before stopping its DMA engine. + */ + if ((hpriv->flags & AHCI_HFLAG_WAKE_BEFORE_STOP) && + (ap->link.lpm_policy > ATA_LPM_MAX_POWER) && + ahci_set_lpm(&ap->link, ATA_LPM_MAX_POWER, ATA_LPM_WAKE_ONLY)) { + dev_err(ap->host->dev, "Failed to wake up port before engine stop\n"); + return -EIO; + } + tmp = readl(port_mmio + PORT_CMD); /* check if the HBA is idle */ @@ -689,6 +703,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, void __iomem *port_mmio = ahci_port_base(ap); if (policy != ATA_LPM_MAX_POWER) { + /* wakeup flag only applies to the max power policy */ + hints &= ~ATA_LPM_WAKE_ONLY; + /* * Disable interrupts on Phy Ready. This keeps us from * getting woken up due to spurious phy ready @@ -704,7 +721,8 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, u32 cmd = readl(port_mmio + PORT_CMD); if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) { - cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE); + if (!(hints & ATA_LPM_WAKE_ONLY)) + cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE); cmd |= PORT_CMD_ICC_ACTIVE; writel(cmd, port_mmio + PORT_CMD); @@ -712,6 +730,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, /* wait 10ms to be sure we've come out of LPM state */ ata_msleep(ap, 10); + + if (hints & ATA_LPM_WAKE_ONLY) + return 0; } else { cmd |= PORT_CMD_ALPE; if (policy == ATA_LPM_MIN_POWER) diff --git a/include/linux/libata.h b/include/linux/libata.h index 851821b..bec2abb 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -526,6 +526,7 @@ enum ata_lpm_policy { enum ata_lpm_hints { ATA_LPM_EMPTY = (1 << 0), /* port empty/probing */ ATA_LPM_HIPM = (1 << 1), /* may use HIPM */ + ATA_LPM_WAKE_ONLY = (1 << 2), /* only wake up link */ }; /* forward declarations */ -- cgit v0.10.2 From b00622fc34e9d45069bd6e328dfd47ea2ef61468 Mon Sep 17 00:00:00 2001 From: Shikha Jain Date: Mon, 11 Jan 2016 14:55:45 -0800 Subject: libata: blacklist a Viking flash model for MWDMA corruption Viking flash model VRFDFC22048UCHC-TE causes data corruption in MWDMA mode. Cc: xe-kernel@external.cisco.com Signed-off-by: Shikha Jain Signed-off-by: Anil Veliyankara Madam Signed-off-by: Tejun Heo diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cbb7471..55e257c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4125,6 +4125,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "SAMSUNG CD-ROM SN-124", "N001", ATA_HORKAGE_NODMA }, { "Seagate STT20000A", NULL, ATA_HORKAGE_NODMA }, { " 2GB ATA Flash Disk", "ADMA428M", ATA_HORKAGE_NODMA }, + { "VRFDFC22048UCHC-TE*", NULL, ATA_HORKAGE_NODMA }, /* Odd clown on sil3726/4726 PMPs */ { "Config Disk", NULL, ATA_HORKAGE_DISABLE }, -- cgit v0.10.2 From 566d1827df2ef0cbe921d3d6946ac3007b1a6938 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 15 Jan 2016 15:13:05 -0500 Subject: libata: disable forced PORTS_IMPL for >= AHCI 1.3 Some early controllers incorrectly reported zero ports in PORTS_IMPL register and the ahci driver fabricates PORTS_IMPL from the number of ports in those cases. This hasn't mattered but with the new nvme controllers there are cases where zero PORTS_IMPL is valid and should be honored. Disable the workaround for >= AHCI 1.3. Signed-off-by: Tejun Heo Reported-by: Andy Lutomirski Link: http://lkml.kernel.org/g/CALCETrU7yMvXEDhjAUShoHEhDwifJGapdw--BKxsP0jmjKGmRw@mail.gmail.com Cc: Sergei Shtylyov Cc: stable@vger.kernel.org diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 284a176..4029679 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -496,8 +496,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) } } - /* fabricate port_map from cap.nr_ports */ - if (!port_map) { + /* fabricate port_map from cap.nr_ports for < AHCI 1.3 */ + if (!port_map && vers < 0x10300) { port_map = (1 << ahci_nr_ports(cap)) - 1; dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map); -- cgit v0.10.2 From a588afc920bc50e894f6ae2874c4281c795e0979 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 29 Jan 2016 07:06:53 -0500 Subject: libata-sff: use WARN instead of BUG on illegal host state machine state ata_sff_hsm_move() triggers BUG if it sees a host state machine state that it dind't expect. The risk for data corruption when the condition occurs is low as it's highly unlikely that it would lead to spurious completion of commands. The BUG occasionally triggered for subtle race conditions in the driver. Let's downgrade it to WARN so that it doesn't kill the machine unnecessarily. Signed-off-by: Tejun Heo Cc: Dmitry Vyukov diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index cdf6215..608677d 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1296,7 +1296,8 @@ fsm_start: break; default: poll_next = 0; - BUG(); + WARN(true, "ata%d: SFF host state machine in invalid state %d", + ap->print_id, ap->hsm_task_state); } return poll_next; -- cgit v0.10.2 From 8eee1d3ed5b6fc8e14389567c9a6f53f82bb7224 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Feb 2016 11:33:21 -0500 Subject: libata: fix sff host state machine locking while polling The bulk of ATA host state machine is implemented by ata_sff_hsm_move(). The function is called from either the interrupt handler or, if polling, a work item. Unlike from the interrupt path, the polling path calls the function without holding the host lock and ata_sff_hsm_move() selectively grabs the lock. This is completely broken. If an IRQ triggers while polling is in progress, the two can easily race and end up accessing the hardware and updating state machine state at the same time. This can put the state machine in an illegal state and lead to a crash like the following. kernel BUG at drivers/ata/libata-sff.c:1302! invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN Modules linked in: CPU: 1 PID: 10679 Comm: syz-executor Not tainted 4.5.0-rc1+ #300 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88002bd00000 ti: ffff88002e048000 task.ti: ffff88002e048000 RIP: 0010:[] [] ata_sff_hsm_move+0x619/0x1c60 ... Call Trace: [] __ata_sff_port_intr+0x1e1/0x3a0 drivers/ata/libata-sff.c:1584 [] ata_bmdma_port_intr+0x71/0x400 drivers/ata/libata-sff.c:2877 [< inline >] __ata_sff_interrupt drivers/ata/libata-sff.c:1629 [] ata_bmdma_interrupt+0x253/0x580 drivers/ata/libata-sff.c:2902 [] handle_irq_event_percpu+0x108/0x7e0 kernel/irq/handle.c:157 [] handle_irq_event+0xa7/0x140 kernel/irq/handle.c:205 [] handle_edge_irq+0x1e3/0x8d0 kernel/irq/chip.c:623 [< inline >] generic_handle_irq_desc include/linux/irqdesc.h:146 [] handle_irq+0x10c/0x2a0 arch/x86/kernel/irq_64.c:78 [] do_IRQ+0x7d/0x1a0 arch/x86/kernel/irq.c:240 [] common_interrupt+0x8c/0x8c arch/x86/entry/entry_64.S:520 [< inline >] rcu_lock_acquire include/linux/rcupdate.h:490 [< inline >] rcu_read_lock include/linux/rcupdate.h:874 [] filemap_map_pages+0x131/0xba0 mm/filemap.c:2145 [< inline >] do_fault_around mm/memory.c:2943 [< inline >] do_read_fault mm/memory.c:2962 [< inline >] do_fault mm/memory.c:3133 [< inline >] handle_pte_fault mm/memory.c:3308 [< inline >] __handle_mm_fault mm/memory.c:3418 [] handle_mm_fault+0x2516/0x49a0 mm/memory.c:3447 [] __do_page_fault+0x376/0x960 arch/x86/mm/fault.c:1238 [] trace_do_page_fault+0xe8/0x420 arch/x86/mm/fault.c:1331 [] do_async_page_fault+0x14/0xd0 arch/x86/kernel/kvm.c:264 [] async_page_fault+0x28/0x30 arch/x86/entry/entry_64.S:986 Fix it by ensuring that the polling path is holding the host lock before entering ata_sff_hsm_move() so that all hardware accesses and state updates are performed under the host lock. Signed-off-by: Tejun Heo Reported-and-tested-by: Dmitry Vyukov Link: http://lkml.kernel.org/g/CACT4Y+b_JsOxJu2EZyEf+mOXORc_zid5V1-pLZSroJVxyWdSpw@mail.gmail.com Cc: stable@vger.kernel.org diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 608677d..051b615 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap, static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) { struct ata_port *ap = qc->ap; - unsigned long flags; if (ap->ops->error_handler) { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); - /* EH might have kicked in while host lock is * released. */ @@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } else ata_port_freeze(ap); } - - spin_unlock_irqrestore(ap->lock, flags); } else { if (likely(!(qc->err_mask & AC_ERR_HSM))) ata_qc_complete(qc); @@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } } else { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); ata_sff_irq_on(ap); ata_qc_complete(qc); - spin_unlock_irqrestore(ap->lock, flags); } else ata_qc_complete(qc); } @@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, { struct ata_link *link = qc->dev->link; struct ata_eh_info *ehi = &link->eh_info; - unsigned long flags = 0; int poll_next; + lockdep_assert_held(ap->lock); + WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0); /* Make sure ata_sff_qc_issue() does not throw things @@ -1112,14 +1106,6 @@ fsm_start: } } - /* Send the CDB (atapi) or the first data block (ata pio out). - * During the state transition, interrupt handler shouldn't - * be invoked before the data transfer is complete and - * hsm_task_state is changed. Hence, the following locking. - */ - if (in_wq) - spin_lock_irqsave(ap->lock, flags); - if (qc->tf.protocol == ATA_PROT_PIO) { /* PIO data out protocol. * send first data block. @@ -1135,9 +1121,6 @@ fsm_start: /* send CDB */ atapi_send_cdb(ap, qc); - if (in_wq) - spin_unlock_irqrestore(ap->lock, flags); - /* if polling, ata_sff_pio_task() handles the rest. * otherwise, interrupt handler takes over from here. */ @@ -1362,12 +1345,14 @@ static void ata_sff_pio_task(struct work_struct *work) u8 status; int poll_next; + spin_lock_irq(ap->lock); + BUG_ON(ap->sff_pio_task_link == NULL); /* qc can be NULL if timeout occurred */ qc = ata_qc_from_tag(ap, link->active_tag); if (!qc) { ap->sff_pio_task_link = NULL; - return; + goto out_unlock; } fsm_start: @@ -1382,11 +1367,14 @@ fsm_start: */ status = ata_sff_busy_wait(ap, ATA_BUSY, 5); if (status & ATA_BUSY) { + spin_unlock_irq(ap->lock); ata_msleep(ap, 2); + spin_lock_irq(ap->lock); + status = ata_sff_busy_wait(ap, ATA_BUSY, 10); if (status & ATA_BUSY) { ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE); - return; + goto out_unlock; } } @@ -1403,6 +1391,8 @@ fsm_start: */ if (poll_next) goto fsm_start; +out_unlock: + spin_unlock_irq(ap->lock); } /** -- cgit v0.10.2 From 342decff2b846b46fa61eb5ee40986fab79a9a32 Mon Sep 17 00:00:00 2001 From: Alexandra Yates Date: Fri, 5 Feb 2016 15:27:49 -0800 Subject: ahci: Intel DNV device IDs SATA Adding Intel codename DNV platform device IDs for SATA. Signed-off-by: Alexandra Yates Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 594fcab..546a369 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */ + { PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */ { PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */ -- cgit v0.10.2