From e61f7d1c3c07a7e51036b0796749edb00deff845 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 8 Jan 2015 10:34:27 -0500 Subject: [PATCH 1/7] libata: Whitelist SSDs that are known to properly return zeroes after TRIM As defined, the DRAT (Deterministic Read After Trim) and RZAT (Return Zero After Trim) flags in the ATA Command Set are unreliable in the sense that they only define what happens if the device successfully executed the DSM TRIM command. TRIM is only advisory, however, and the device is free to silently ignore all or parts of the request. In practice this renders the DRAT and RZAT flags completely useless and because the results are unpredictable we decided to disable discard in MD for 3.18 to avoid the risk of data corruption. Hardware vendors in the real world obviously need better guarantees than what the standards bodies provide. Unfortuntely those guarantees are encoded in product requirements documents rather than somewhere we can key off of them programatically. So we are compelled to disabling discard_zeroes_data for all devices unless we explicitly have data to support whitelisting them. This patch whitelists SSDs from a few of the main vendors. None of the whitelists are based on written guarantees. They are purely based on empirical evidence collected from internal and external users that have tested or qualified these drives in RAID deployments. The whitelist is only meant as a starting point and is by no means comprehensive: - All intel SSD models except for 510 - Micron M5?0/M600 - Samsung SSDs - Seagate SSDs Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 31 +++++++++++++++++++++++++++---- drivers/ata/libata-scsi.c | 10 ++++++---- include/linux/libata.h | 1 + 3 files changed, 34 insertions(+), 8 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 5c84fb5c3372..23c2ae03a7ab 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4233,10 +4233,33 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* devices that don't properly handle queued TRIM commands */ - { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Micron_M550*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT*M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Micron_M[56]*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Crucial_CT*SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + + /* + * As defined, the DRAT (Deterministic Read After Trim) and RZAT + * (Return Zero After Trim) flags in the ATA Command Set are + * unreliable in the sense that they only define what happens if + * the device successfully executed the DSM TRIM command. TRIM + * is only advisory, however, and the device is free to silently + * ignore all or parts of the request. + * + * Whitelist drives that are known to reliably return zeroes + * after TRIM. + */ + + /* + * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude + * that model before whitelisting all other intel SSDs. + */ + { "INTEL*SSDSC2MH*", NULL, 0, }, + + { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e364e86e84d7..6abd17a85b13 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2532,13 +2532,15 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) rbuf[15] = lowest_aligned; if (ata_id_has_trim(args->id)) { - rbuf[14] |= 0x80; /* TPE */ + rbuf[14] |= 0x80; /* LBPME */ - if (ata_id_has_zero_after_trim(args->id)) - rbuf[14] |= 0x40; /* TPRZ */ + if (ata_id_has_zero_after_trim(args->id) && + dev->horkage & ATA_HORKAGE_ZERO_AFTER_TRIM) { + ata_dev_info(dev, "Enabling discard_zeroes_data\n"); + rbuf[14] |= 0x40; /* LBPRZ */ + } } } - return 0; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 2d182413b1db..f2b440e44fd7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -422,6 +422,7 @@ enum { ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ + ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ From 95bbbe9a6663635b6cdef20c01c0ea32ec6987e4 Mon Sep 17 00:00:00 2001 From: Gabriele Mazzotta Date: Thu, 8 Jan 2015 19:41:34 +0100 Subject: [PATCH 2/7] ahci: Use dev_info() to inform about the lack of Device Sleep support According to the Serial ATA AHCI specification, Device Sleep is an optional feature and as such no errors should be printed if it's missing. Keep informing users, but use dev_info() instead of dev_err(). Signed-off-by: Gabriele Mazzotta Signed-off-by: Tejun Heo --- drivers/ata/libahci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 97683e45ab04..61a9c07e0dff 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -2003,7 +2003,7 @@ static void ahci_set_aggressive_devslp(struct ata_port *ap, bool sleep) devslp = readl(port_mmio + PORT_DEVSLP); if (!(devslp & PORT_DEVSLP_DSP)) { - dev_err(ap->host->dev, "port does not support device sleep\n"); + dev_info(ap->host->dev, "port does not support device sleep\n"); return; } From 46319e13581a6c442b0a0e5a3bd5d9af4496f252 Mon Sep 17 00:00:00 2001 From: James Ralston Date: Mon, 12 Jan 2015 16:13:52 -0800 Subject: [PATCH 3/7] ahci: Remove Device ID for Intel Sunrise Point PCH This patch removes a duplicate AHCI-mode SATA Device ID for the Intel Sunrise Point PCH. Signed-off-by: James Ralston Signed-off-by: Tejun Heo --- drivers/ata/ahci.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 49f1e6890587..33bb06e006c9 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -325,7 +325,6 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ - { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ From 19406d7d9512254d1a467997101bb77b090a44be Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 13 Jan 2015 19:25:17 +0100 Subject: [PATCH 4/7] ata: pata_at91: depend on !ARCH_MULTIPLATFORM Until the driver is corrected to stop using mach/at91isam9_smc.h, it won't compile in a ARCH_MULTIPLATFORM configuration. Suggested-by: Arnd Bergmann Signed-off-by: Alexandre Belloni Signed-off-by: Tejun Heo --- drivers/ata/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index a3a13605a9c4..5f601553b9b0 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -835,6 +835,7 @@ config PATA_AT32 config PATA_AT91 tristate "PATA support for AT91SAM9260" depends on ARM && SOC_AT91SAM9 + depends on !ARCH_MULTIPLATFORM help This option enables support for IDE devices on the Atmel AT91SAM9260 SoC. From 72dd299d5039a336493993dcc63413cf31d0e662 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 16 Jan 2015 15:13:02 -0800 Subject: [PATCH 5/7] libata: allow sata_sil24 to opt-out of tag ordered submission Ronny reports: https://bugzilla.kernel.org/show_bug.cgi?id=87101 "Since commit 8a4aeec8d "libata/ahci: accommodate tag ordered controllers" the access to the harddisk on the first SATA-port is failing on its first access. The access to the harddisk on the second port is working normal. When reverting the above commit, access to both harddisks is working fine again." Maintain tag ordered submission as the default, but allow sata_sil24 to continue with the old behavior. Cc: Cc: Tejun Heo Reported-by: Ronny Hegewald Signed-off-by: Dan Williams Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 5 ++++- drivers/ata/sata_sil24.c | 2 +- include/linux/libata.h | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 23c2ae03a7ab..d1a05f9bb91f 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4771,7 +4771,10 @@ static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap) return NULL; for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) { - tag = tag < max_queue ? tag : 0; + if (ap->flags & ATA_FLAG_LOWTAG) + tag = i; + else + tag = tag < max_queue ? tag : 0; /* the last tag is reserved for internal command. */ if (tag == ATA_TAG_INTERNAL) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index d81b20ddb527..ea655949023f 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -246,7 +246,7 @@ enum { /* host flags */ SIL24_COMMON_FLAGS = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA | - ATA_FLAG_AN | ATA_FLAG_PMP, + ATA_FLAG_AN | ATA_FLAG_PMP | ATA_FLAG_LOWTAG, SIL24_FLAG_PCIX_IRQ_WOC = (1 << 24), /* IRQ loss errata on PCI-X */ IRQ_STAT_4PORTS = 0xf, diff --git a/include/linux/libata.h b/include/linux/libata.h index f2b440e44fd7..91f705de2c0b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -231,6 +231,7 @@ enum { ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity * led */ ATA_FLAG_NO_DIPM = (1 << 23), /* host not happy with DIPM */ + ATA_FLAG_LOWTAG = (1 << 24), /* host wants lowest available tag */ /* bits 24:31 of ap->flags are reserved for LLD specific flags */ From ce7514526742c0898b837d4395f515b79dfb5a12 Mon Sep 17 00:00:00 2001 From: David Jeffery Date: Mon, 19 Jan 2015 13:03:25 -0600 Subject: [PATCH 6/7] libata: prevent HSM state change race between ISR and PIO It is possible for ata_sff_flush_pio_task() to set ap->hsm_task_state to HSM_ST_IDLE in between the time __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG(). This problem is hard to reproduce making this patch hard to verify, but this fix will prevent the race. I have not been able to reproduce the problem, but here is a crash dump from a 2.6.32 kernel. On examining the ata port's state, its hsm_task_state field has a value of HSM_ST_IDLE: crash> struct ata_port.hsm_task_state ffff881c1121c000 hsm_task_state = 0 Normally, this should not be possible as ata_sff_hsm_move() was called from ata_sff_host_intr(), which checks hsm_task_state and won't call ata_sff_hsm_move() if it has a HSM_ST_IDLE value. PID: 11053 TASK: ffff8816e846cae0 CPU: 0 COMMAND: "sshd" #0 [ffff88008ba03960] machine_kexec at ffffffff81038f3b #1 [ffff88008ba039c0] crash_kexec at ffffffff810c5d92 #2 [ffff88008ba03a90] oops_end at ffffffff8152b510 #3 [ffff88008ba03ac0] die at ffffffff81010e0b #4 [ffff88008ba03af0] do_trap at ffffffff8152ad74 #5 [ffff88008ba03b50] do_invalid_op at ffffffff8100cf95 #6 [ffff88008ba03bf0] invalid_op at ffffffff8100bf9b [exception RIP: ata_sff_hsm_move+317] RIP: ffffffff813a77ad RSP: ffff88008ba03ca0 RFLAGS: 00010097 RAX: 0000000000000000 RBX: ffff881c1121dc60 RCX: 0000000000000000 RDX: ffff881c1121dd10 RSI: ffff881c1121dc60 RDI: ffff881c1121c000 RBP: ffff88008ba03d00 R8: 0000000000000000 R9: 000000000000002e R10: 000000000001003f R11: 000000000000009b R12: ffff881c1121c000 R13: 0000000000000000 R14: 0000000000000050 R15: ffff881c1121dd78 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffff88008ba03d08] ata_sff_host_intr at ffffffff813a7fbd #8 [ffff88008ba03d38] ata_sff_interrupt at ffffffff813a821e #9 [ffff88008ba03d78] handle_IRQ_event at ffffffff810e6ec0 --- --- [exception RIP: pipe_poll+48] RIP: ffffffff81192780 RSP: ffff880f26d459b8 RFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff880f26d459c8 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff881a0539fa80 RBP: ffffffff8100bb8e R8: ffff8803b23324a0 R9: 0000000000000000 R10: ffff880f26d45dd0 R11: 0000000000000008 R12: ffffffff8109b646 R13: ffff880f26d45948 R14: 0000000000000246 R15: 0000000000000246 ORIG_RAX: ffffffffffffff10 CS: 0010 SS: 0018 RIP: 00007f26017435c3 RSP: 00007fffe020c420 RFLAGS: 00000206 RAX: 0000000000000017 RBX: ffffffff8100b072 RCX: 00007fffe020c45c RDX: 00007f2604a3f120 RSI: 00007f2604a3f140 RDI: 000000000000000d RBP: 0000000000000000 R8: 00007fffe020e570 R9: 0101010101010101 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffe020e5f0 R13: 00007fffe020e5f4 R14: 00007f26045f373c R15: 00007fffe020e5e0 ORIG_RAX: 0000000000000017 CS: 0033 SS: 002b Somewhere between the ata_sff_hsm_move() check and the ata_sff_host_intr() check, the value changed. On examining the other cpus to see what else was running, another cpu was running the error handler routines: PID: 326 TASK: ffff881c11014aa0 CPU: 1 COMMAND: "scsi_eh_1" #0 [ffff88008ba27e90] crash_nmi_callback at ffffffff8102fee6 #1 [ffff88008ba27ea0] notifier_call_chain at ffffffff8152d515 #2 [ffff88008ba27ee0] atomic_notifier_call_chain at ffffffff8152d57a #3 [ffff88008ba27ef0] notify_die at ffffffff810a154e #4 [ffff88008ba27f20] do_nmi at ffffffff8152b1db #5 [ffff88008ba27f50] nmi at ffffffff8152aaa0 [exception RIP: _spin_lock_irqsave+47] RIP: ffffffff8152a1ff RSP: ffff881c11a73aa0 RFLAGS: 00000006 RAX: 0000000000000001 RBX: ffff881c1121deb8 RCX: 0000000000000000 RDX: 0000000000000246 RSI: 0000000000000020 RDI: ffff881c122612d8 RBP: ffff881c11a73aa0 R8: ffff881c17083800 R9: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff881c1121c000 R13: 000000000000001f R14: ffff881c1121dd50 R15: ffff881c1121dc60 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- --- #6 [ffff881c11a73aa0] _spin_lock_irqsave at ffffffff8152a1ff #7 [ffff881c11a73aa8] ata_exec_internal_sg at ffffffff81396fb5 #8 [ffff881c11a73b58] ata_exec_internal at ffffffff81397109 #9 [ffff881c11a73bd8] atapi_eh_request_sense at ffffffff813a34eb Before it tried to acquire a spinlock, ata_exec_internal_sg() called ata_sff_flush_pio_task(). This function will set ap->hsm_task_state to HSM_ST_IDLE, and has no locking around setting this value. ata_sff_flush_pio_task() can then race with the interrupt handler and potentially set HSM_ST_IDLE at a fatal moment, which will trigger a kernel BUG. v2: Fixup comment in ata_sff_flush_pio_task() tj: Further updated comment. Use ap->lock instead of shost lock and use the [un]lock_irq variant instead of the irqsave/restore one. Signed-off-by: David Milburn Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- drivers/ata/libata-sff.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index db90aa35cb71..2e86e3b85266 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1333,7 +1333,19 @@ void ata_sff_flush_pio_task(struct ata_port *ap) DPRINTK("ENTER\n"); cancel_delayed_work_sync(&ap->sff_pio_task); + + /* + * We wanna reset the HSM state to IDLE. If we do so without + * grabbing the port lock, critical sections protected by it which + * expect the HSM state to stay stable may get surprised. For + * example, we may set IDLE in between the time + * __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls + * ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG(). + */ + spin_lock_irq(ap->lock); ap->hsm_task_state = HSM_ST_IDLE; + spin_unlock_irq(ap->lock); + ap->sff_pio_task_link = NULL; if (ata_msg_ctl(ap)) From 09c32aaa3683cbcb6c2787a42f87630dff37d2a5 Mon Sep 17 00:00:00 2001 From: Suman Tripathi Date: Mon, 2 Feb 2015 23:37:19 +0530 Subject: [PATCH 7/7] ahci_xgene: Fix the dma state machine lockup for the ATA_CMD_SMART PIO mode command. This patch addresses the issue with ATA_CMD_SMART pio mode command for enumeration and device detection with ATA devices. The X-Gene AHCI controller has an errata in which it cannot clear the BSY bit after the PIO setup FIS. The dma state machine enters CMFatalErrorUpdate state and locks up. It is the same issue as in the commit 2a0bdff6b958 ("ahci-xgene: fix the dma state machine lockup for the IDENTIFY DEVICE PIO mode command"). For example : without this patch it results in READ DMA command failure as shown below : [ 126.700072] ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen [ 126.707089] ata2.00: failed command: READ DMA [ 126.711426] ata2.00: cmd c8/00:08:00:55:57/00:00:00:00:00/e1 tag 1 dma 4096 in [ 126.711426] res 40/00:ff:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout) [ 126.725956] ata2.00: status: { DRDY } Signed-off-by: Suman Tripathi Reported-by: Mark Langsdorf Signed-off-by: Tejun Heo --- drivers/ata/ahci_xgene.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index cbcd20810355..f752c30477cb 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -139,7 +139,8 @@ static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc) int rc = 0; if (unlikely((ctx->last_cmd[ap->port_no] == ATA_CMD_ID_ATA) || - (ctx->last_cmd[ap->port_no] == ATA_CMD_PACKET))) + (ctx->last_cmd[ap->port_no] == ATA_CMD_PACKET) || + (ctx->last_cmd[ap->port_no] == ATA_CMD_SMART))) xgene_ahci_restart_engine(ap); rc = ahci_qc_issue(qc);