* [PATCH RESEND v9] serial: stm32-usart: Add STM32 USART Driver
From: Maxime Coquelin @ 2015-06-10 19:19 UTC (permalink / raw)
To: Greg Kroah-Hartman, Jiri Slaby,
linux-serial-u79uwXL29TY76Z2rM5mHXA
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA
This drivers adds support to the STM32 USART controller, which is a
standard serial driver.
Tested-by: Chanwoo Choi <cw00.choi-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
Reviewed-by: Peter Hurley <peter-WaGBZJeGNqdsbIuE7sb01tBPR1lH4CV8@public.gmane.org>
Reviewed-by: Vladimir Zapolskiy <vladimir_zapolskiy-nmGgyN9QBj3QT0dZR+AlfA@public.gmane.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Signed-off-by: Maxime Coquelin <mcoquelin.stm32-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
drivers/tty/serial/Kconfig | 17 +
drivers/tty/serial/Makefile | 1 +
drivers/tty/serial/stm32-usart.c | 739 +++++++++++++++++++++++++++++++++++++++
include/uapi/linux/serial_core.h | 3 +
4 files changed, 760 insertions(+)
create mode 100644 drivers/tty/serial/stm32-usart.c
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index da45877..a74dabc 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1608,6 +1608,23 @@ config SERIAL_SPRD_CONSOLE
with "earlycon" on the kernel command line. The console is
enabled when early_param is processed.
+config SERIAL_STM32
+ tristate "STMicroelectronics STM32 serial port support"
+ select SERIAL_CORE
+ depends on ARM || COMPILE_TEST
+ help
+ This driver is for the on-chip Serial Controller on
+ STMicroelectronics STM32 MCUs.
+ USART supports Rx & Tx functionality.
+ It support all industry standard baud rates.
+
+ If unsure, say N.
+
+config SERIAL_STM32_CONSOLE
+ bool "Support for console on STM32"
+ depends on SERIAL_STM32=y
+ select SERIAL_CORE_CONSOLE
+
endmenu
config SERIAL_MCTRL_GPIO
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index d296cee2..5ab4111 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -92,6 +92,7 @@ obj-$(CONFIG_SERIAL_FSL_LPUART) += fsl_lpuart.o
obj-$(CONFIG_SERIAL_CONEXANT_DIGICOLOR) += digicolor-usart.o
obj-$(CONFIG_SERIAL_MEN_Z135) += men_z135_uart.o
obj-$(CONFIG_SERIAL_SPRD) += sprd_serial.o
+obj-$(CONFIG_SERIAL_STM32) += stm32-usart.o
# GPIOLIB helpers for modem control lines
obj-$(CONFIG_SERIAL_MCTRL_GPIO) += serial_mctrl_gpio.o
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
new file mode 100644
index 0000000..4a6eab6
--- /dev/null
+++ b/drivers/tty/serial/stm32-usart.c
@@ -0,0 +1,739 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author: Maxime Coquelin <mcoquelin.stm32-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
+ * License terms: GNU General Public License (GPL), version 2
+ *
+ * Inspired by st-asc.c from STMicroelectronics (c)
+ */
+
+#if defined(CONFIG_SERIAL_STM32_USART_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
+#define SUPPORT_SYSRQ
+#endif
+
+#include <linux/module.h>
+#include <linux/serial.h>
+#include <linux/console.h>
+#include <linux/sysrq.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/serial_core.h>
+#include <linux/clk.h>
+
+#define DRIVER_NAME "stm32-usart"
+
+/* Register offsets */
+#define USART_SR 0x00
+#define USART_DR 0x04
+#define USART_BRR 0x08
+#define USART_CR1 0x0c
+#define USART_CR2 0x10
+#define USART_CR3 0x14
+#define USART_GTPR 0x18
+
+/* USART_SR */
+#define USART_SR_PE BIT(0)
+#define USART_SR_FE BIT(1)
+#define USART_SR_NF BIT(2)
+#define USART_SR_ORE BIT(3)
+#define USART_SR_IDLE BIT(4)
+#define USART_SR_RXNE BIT(5)
+#define USART_SR_TC BIT(6)
+#define USART_SR_TXE BIT(7)
+#define USART_SR_LBD BIT(8)
+#define USART_SR_CTS BIT(9)
+#define USART_SR_ERR_MASK (USART_SR_LBD | USART_SR_ORE | \
+ USART_SR_FE | USART_SR_PE)
+/* Dummy bits */
+#define USART_SR_DUMMY_RX BIT(16)
+
+/* USART_DR */
+#define USART_DR_MASK GENMASK(8, 0)
+
+/* USART_BRR */
+#define USART_BRR_DIV_F_MASK GENMASK(3, 0)
+#define USART_BRR_DIV_M_MASK GENMASK(15, 4)
+#define USART_BRR_DIV_M_SHIFT 4
+
+/* USART_CR1 */
+#define USART_CR1_SBK BIT(0)
+#define USART_CR1_RWU BIT(1)
+#define USART_CR1_RE BIT(2)
+#define USART_CR1_TE BIT(3)
+#define USART_CR1_IDLEIE BIT(4)
+#define USART_CR1_RXNEIE BIT(5)
+#define USART_CR1_TCIE BIT(6)
+#define USART_CR1_TXEIE BIT(7)
+#define USART_CR1_PEIE BIT(8)
+#define USART_CR1_PS BIT(9)
+#define USART_CR1_PCE BIT(10)
+#define USART_CR1_WAKE BIT(11)
+#define USART_CR1_M BIT(12)
+#define USART_CR1_UE BIT(13)
+#define USART_CR1_OVER8 BIT(15)
+#define USART_CR1_IE_MASK GENMASK(8, 4)
+
+/* USART_CR2 */
+#define USART_CR2_ADD_MASK GENMASK(3, 0)
+#define USART_CR2_LBDL BIT(5)
+#define USART_CR2_LBDIE BIT(6)
+#define USART_CR2_LBCL BIT(8)
+#define USART_CR2_CPHA BIT(9)
+#define USART_CR2_CPOL BIT(10)
+#define USART_CR2_CLKEN BIT(11)
+#define USART_CR2_STOP_2B BIT(13)
+#define USART_CR2_STOP_MASK GENMASK(13, 12)
+#define USART_CR2_LINEN BIT(14)
+
+/* USART_CR3 */
+#define USART_CR3_EIE BIT(0)
+#define USART_CR3_IREN BIT(1)
+#define USART_CR3_IRLP BIT(2)
+#define USART_CR3_HDSEL BIT(3)
+#define USART_CR3_NACK BIT(4)
+#define USART_CR3_SCEN BIT(5)
+#define USART_CR3_DMAR BIT(6)
+#define USART_CR3_DMAT BIT(7)
+#define USART_CR3_RTSE BIT(8)
+#define USART_CR3_CTSE BIT(9)
+#define USART_CR3_CTSIE BIT(10)
+#define USART_CR3_ONEBIT BIT(11)
+
+/* USART_GTPR */
+#define USART_GTPR_PSC_MASK GENMASK(7, 0)
+#define USART_GTPR_GT_MASK GENMASK(15, 8)
+
+#define DRIVER_NAME "stm32-usart"
+#define STM32_SERIAL_NAME "ttyS"
+#define STM32_MAX_PORTS 6
+
+struct stm32_port {
+ struct uart_port port;
+ struct clk *clk;
+ bool hw_flow_control;
+};
+
+static struct stm32_port stm32_ports[STM32_MAX_PORTS];
+static struct uart_driver stm32_usart_driver;
+
+static void stm32_stop_tx(struct uart_port *port);
+
+static inline struct stm32_port *to_stm32_port(struct uart_port *port)
+{
+ return container_of(port, struct stm32_port, port);
+}
+
+static void stm32_set_bits(struct uart_port *port, u32 reg, u32 bits)
+{
+ u32 val;
+
+ val = readl_relaxed(port->membase + reg);
+ val |= bits;
+ writel_relaxed(val, port->membase + reg);
+}
+
+static void stm32_clr_bits(struct uart_port *port, u32 reg, u32 bits)
+{
+ u32 val;
+
+ val = readl_relaxed(port->membase + reg);
+ val &= ~bits;
+ writel_relaxed(val, port->membase + reg);
+}
+
+static void stm32_receive_chars(struct uart_port *port)
+{
+ struct tty_port *tport = &port->state->port;
+ unsigned long c;
+ u32 sr;
+ char flag;
+
+ if (port->irq_wake)
+ pm_wakeup_event(tport->tty->dev, 0);
+
+ while ((sr = readl_relaxed(port->membase + USART_SR)) & USART_SR_RXNE) {
+ sr |= USART_SR_DUMMY_RX;
+ c = readl_relaxed(port->membase + USART_DR);
+ flag = TTY_NORMAL;
+ port->icount.rx++;
+
+ if (sr & USART_SR_ERR_MASK) {
+ if (sr & USART_SR_LBD) {
+ port->icount.brk++;
+ if (uart_handle_break(port))
+ continue;
+ } else if (sr & USART_SR_ORE) {
+ port->icount.overrun++;
+ } else if (sr & USART_SR_PE) {
+ port->icount.parity++;
+ } else if (sr & USART_SR_FE) {
+ port->icount.frame++;
+ }
+
+ sr &= port->read_status_mask;
+
+ if (sr & USART_SR_LBD)
+ flag = TTY_BREAK;
+ else if (sr & USART_SR_PE)
+ flag = TTY_PARITY;
+ else if (sr & USART_SR_FE)
+ flag = TTY_FRAME;
+ }
+
+ if (uart_handle_sysrq_char(port, c))
+ continue;
+ uart_insert_char(port, sr, USART_SR_ORE, c, flag);
+ }
+
+ spin_unlock(&port->lock);
+ tty_flip_buffer_push(tport);
+ spin_lock(&port->lock);
+}
+
+static void stm32_transmit_chars(struct uart_port *port)
+{
+ struct circ_buf *xmit = &port->state->xmit;
+
+ if (port->x_char) {
+ writel_relaxed(port->x_char, port->membase + USART_DR);
+ port->x_char = 0;
+ port->icount.tx++;
+ return;
+ }
+
+ if (uart_tx_stopped(port)) {
+ stm32_stop_tx(port);
+ return;
+ }
+
+ if (uart_circ_empty(xmit)) {
+ stm32_stop_tx(port);
+ return;
+ }
+
+ writel_relaxed(xmit->buf[xmit->tail], port->membase + USART_DR);
+ xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
+ port->icount.tx++;
+
+ if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+ uart_write_wakeup(port);
+
+ if (uart_circ_empty(xmit))
+ stm32_stop_tx(port);
+}
+
+static irqreturn_t stm32_interrupt(int irq, void *ptr)
+{
+ struct uart_port *port = ptr;
+ u32 sr;
+
+ spin_lock(&port->lock);
+
+ sr = readl_relaxed(port->membase + USART_SR);
+
+ if (sr & USART_SR_RXNE)
+ stm32_receive_chars(port);
+
+ if (sr & USART_SR_TXE)
+ stm32_transmit_chars(port);
+
+ spin_unlock(&port->lock);
+
+ return IRQ_HANDLED;
+}
+
+static unsigned int stm32_tx_empty(struct uart_port *port)
+{
+ return readl_relaxed(port->membase + USART_SR) & USART_SR_TXE;
+}
+
+static void stm32_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+ if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS))
+ stm32_set_bits(port, USART_CR3, USART_CR3_RTSE);
+ else
+ stm32_clr_bits(port, USART_CR3, USART_CR3_RTSE);
+}
+
+static unsigned int stm32_get_mctrl(struct uart_port *port)
+{
+ /* This routine is used to get signals of: DCD, DSR, RI, and CTS */
+ return TIOCM_CAR | TIOCM_DSR | TIOCM_CTS;
+}
+
+/* Transmit stop */
+static void stm32_stop_tx(struct uart_port *port)
+{
+ stm32_clr_bits(port, USART_CR1, USART_CR1_TXEIE);
+}
+
+/* There are probably characters waiting to be transmitted. */
+static void stm32_start_tx(struct uart_port *port)
+{
+ struct circ_buf *xmit = &port->state->xmit;
+
+ if (uart_circ_empty(xmit))
+ return;
+
+ stm32_set_bits(port, USART_CR1, USART_CR1_TXEIE | USART_CR1_TE);
+}
+
+/* Throttle the remote when input buffer is about to overflow. */
+static void stm32_throttle(struct uart_port *port)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&port->lock, flags);
+ stm32_clr_bits(port, USART_CR1, USART_CR1_RXNEIE);
+ spin_unlock_irqrestore(&port->lock, flags);
+}
+
+/* Unthrottle the remote, the input buffer can now accept data. */
+static void stm32_unthrottle(struct uart_port *port)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&port->lock, flags);
+ stm32_set_bits(port, USART_CR1, USART_CR1_RXNEIE);
+ spin_unlock_irqrestore(&port->lock, flags);
+}
+
+/* Receive stop */
+static void stm32_stop_rx(struct uart_port *port)
+{
+ stm32_clr_bits(port, USART_CR1, USART_CR1_RXNEIE);
+}
+
+/* Handle breaks - ignored by us */
+static void stm32_break_ctl(struct uart_port *port, int break_state)
+{
+}
+
+static int stm32_startup(struct uart_port *port)
+{
+ const char *name = to_platform_device(port->dev)->name;
+ u32 val;
+ int ret;
+
+ ret = request_irq(port->irq, stm32_interrupt, IRQF_NO_SUSPEND,
+ name, port);
+ if (ret)
+ return ret;
+
+ val = USART_CR1_RXNEIE | USART_CR1_TE | USART_CR1_RE;
+ stm32_set_bits(port, USART_CR1, val);
+
+ return 0;
+}
+
+static void stm32_shutdown(struct uart_port *port)
+{
+ u32 val;
+
+ val = USART_CR1_TXEIE | USART_CR1_RXNEIE | USART_CR1_TE | USART_CR1_RE;
+ stm32_set_bits(port, USART_CR1, val);
+
+ free_irq(port->irq, port);
+}
+
+static void stm32_set_termios(struct uart_port *port, struct ktermios *termios,
+ struct ktermios *old)
+{
+ struct stm32_port *stm32_port = to_stm32_port(port);
+ unsigned int baud;
+ u32 usartdiv, mantissa, fraction, oversampling;
+ tcflag_t cflag = termios->c_cflag;
+ u32 cr1, cr2, cr3;
+ unsigned long flags;
+
+ if (!stm32_port->hw_flow_control)
+ cflag &= ~CRTSCTS;
+
+ baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk / 8);
+
+ spin_lock_irqsave(&port->lock, flags);
+
+ /* Stop serial port and reset value */
+ writel_relaxed(0, port->membase + USART_CR1);
+
+ cr1 = USART_CR1_TE | USART_CR1_RE | USART_CR1_UE | USART_CR1_RXNEIE;
+ cr2 = 0;
+ cr3 = 0;
+
+ if (cflag & CSTOPB)
+ cr2 |= USART_CR2_STOP_2B;
+
+ if (cflag & PARENB) {
+ cr1 |= USART_CR1_PCE;
+ if ((cflag & CSIZE) == CS8)
+ cr1 |= USART_CR1_M;
+ }
+
+ if (cflag & PARODD)
+ cr1 |= USART_CR1_PS;
+
+ port->status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS);
+ if (cflag & CRTSCTS) {
+ port->status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS;
+ cr3 |= USART_CR3_CTSE;
+ }
+
+ usartdiv = DIV_ROUND_CLOSEST(port->uartclk, baud);
+
+ /*
+ * The USART supports 16 or 8 times oversampling.
+ * By default we prefer 16 times oversampling, so that the receiver
+ * has a better tolerance to clock deviations.
+ * 8 times oversampling is only used to achieve higher speeds.
+ */
+ if (usartdiv < 16) {
+ oversampling = 8;
+ stm32_set_bits(port, USART_CR1, USART_CR1_OVER8);
+ } else {
+ oversampling = 16;
+ stm32_clr_bits(port, USART_CR1, USART_CR1_OVER8);
+ }
+
+ mantissa = (usartdiv / oversampling) << USART_BRR_DIV_M_SHIFT;
+ fraction = usartdiv % oversampling;
+ writel_relaxed(mantissa | fraction, port->membase + USART_BRR);
+
+ uart_update_timeout(port, cflag, baud);
+
+ port->read_status_mask = USART_SR_ORE;
+ if (termios->c_iflag & INPCK)
+ port->read_status_mask |= USART_SR_PE | USART_SR_FE;
+ if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
+ port->read_status_mask |= USART_SR_LBD;
+
+ /* Characters to ignore */
+ port->ignore_status_mask = 0;
+ if (termios->c_iflag & IGNPAR)
+ port->ignore_status_mask = USART_SR_PE | USART_SR_FE;
+ if (termios->c_iflag & IGNBRK) {
+ port->ignore_status_mask |= USART_SR_LBD;
+ /*
+ * If we're ignoring parity and break indicators,
+ * ignore overruns too (for real raw support).
+ */
+ if (termios->c_iflag & IGNPAR)
+ port->ignore_status_mask |= USART_SR_ORE;
+ }
+
+ /* Ignore all characters if CREAD is not set */
+ if ((termios->c_cflag & CREAD) == 0)
+ port->ignore_status_mask |= USART_SR_DUMMY_RX;
+
+ writel_relaxed(cr3, port->membase + USART_CR3);
+ writel_relaxed(cr2, port->membase + USART_CR2);
+ writel_relaxed(cr1, port->membase + USART_CR1);
+
+ spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static const char *stm32_type(struct uart_port *port)
+{
+ return (port->type == PORT_STM32) ? DRIVER_NAME : NULL;
+}
+
+static void stm32_release_port(struct uart_port *port)
+{
+}
+
+static int stm32_request_port(struct uart_port *port)
+{
+ return 0;
+}
+
+static void stm32_config_port(struct uart_port *port, int flags)
+{
+ if (flags & UART_CONFIG_TYPE)
+ port->type = PORT_STM32;
+}
+
+static int
+stm32_verify_port(struct uart_port *port, struct serial_struct *ser)
+{
+ /* No user changeable parameters */
+ return -EINVAL;
+}
+
+static void stm32_pm(struct uart_port *port, unsigned int state,
+ unsigned int oldstate)
+{
+ struct stm32_port *stm32port = container_of(port,
+ struct stm32_port, port);
+ unsigned long flags = 0;
+
+ switch (state) {
+ case UART_PM_STATE_ON:
+ clk_prepare_enable(stm32port->clk);
+ break;
+ case UART_PM_STATE_OFF:
+ spin_lock_irqsave(&port->lock, flags);
+ stm32_clr_bits(port, USART_CR1, USART_CR1_UE);
+ spin_unlock_irqrestore(&port->lock, flags);
+ clk_disable_unprepare(stm32port->clk);
+ break;
+ }
+}
+
+static const struct uart_ops stm32_uart_ops = {
+ .tx_empty = stm32_tx_empty,
+ .set_mctrl = stm32_set_mctrl,
+ .get_mctrl = stm32_get_mctrl,
+ .stop_tx = stm32_stop_tx,
+ .start_tx = stm32_start_tx,
+ .throttle = stm32_throttle,
+ .unthrottle = stm32_unthrottle,
+ .stop_rx = stm32_stop_rx,
+ .break_ctl = stm32_break_ctl,
+ .startup = stm32_startup,
+ .shutdown = stm32_shutdown,
+ .set_termios = stm32_set_termios,
+ .pm = stm32_pm,
+ .type = stm32_type,
+ .release_port = stm32_release_port,
+ .request_port = stm32_request_port,
+ .config_port = stm32_config_port,
+ .verify_port = stm32_verify_port,
+};
+
+static int stm32_init_port(struct stm32_port *stm32port,
+ struct platform_device *pdev)
+{
+ struct uart_port *port = &stm32port->port;
+ struct resource *res;
+ int ret;
+
+ port->iotype = UPIO_MEM;
+ port->flags = UPF_BOOT_AUTOCONF;
+ port->ops = &stm32_uart_ops;
+ port->dev = &pdev->dev;
+ port->irq = platform_get_irq(pdev, 0);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ port->membase = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(port->membase))
+ return PTR_ERR(port->membase);
+ port->mapbase = res->start;
+
+ spin_lock_init(&port->lock);
+
+ stm32port->clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(stm32port->clk))
+ return PTR_ERR(stm32port->clk);
+
+ /* Ensure that clk rate is correct by enabling the clk */
+ ret = clk_prepare_enable(stm32port->clk);
+ if (ret)
+ return ret;
+
+ stm32port->port.uartclk = clk_get_rate(stm32port->clk);
+ if (!stm32port->port.uartclk)
+ ret = -EINVAL;
+
+ clk_disable_unprepare(stm32port->clk);
+
+ return ret;
+}
+
+static struct stm32_port *stm32_of_get_stm32_port(struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ int id;
+
+ if (!np)
+ return NULL;
+
+ id = of_alias_get_id(np, "serial");
+ if (id < 0)
+ id = 0;
+
+ if (WARN_ON(id >= STM32_MAX_PORTS))
+ return NULL;
+
+ stm32_ports[id].hw_flow_control = of_property_read_bool(np,
+ "auto-flow-control");
+ stm32_ports[id].port.line = id;
+ return &stm32_ports[id];
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id stm32_match[] = {
+ { .compatible = "st,stm32-usart", },
+ { .compatible = "st,stm32-uart", },
+ {},
+};
+
+MODULE_DEVICE_TABLE(of, stm32_match);
+#endif
+
+static int stm32_serial_probe(struct platform_device *pdev)
+{
+ int ret;
+ struct stm32_port *stm32port;
+
+ stm32port = stm32_of_get_stm32_port(pdev);
+ if (!stm32port)
+ return -ENODEV;
+
+ ret = stm32_init_port(stm32port, pdev);
+ if (ret)
+ return ret;
+
+ ret = uart_add_one_port(&stm32_usart_driver, &stm32port->port);
+ if (ret)
+ return ret;
+
+ platform_set_drvdata(pdev, &stm32port->port);
+
+ return 0;
+}
+
+static int stm32_serial_remove(struct platform_device *pdev)
+{
+ struct uart_port *port = platform_get_drvdata(pdev);
+
+ return uart_remove_one_port(&stm32_usart_driver, port);
+}
+
+
+#ifdef CONFIG_SERIAL_STM32_CONSOLE
+static void stm32_console_putchar(struct uart_port *port, int ch)
+{
+ while (!(readl_relaxed(port->membase + USART_SR) & USART_SR_TXE))
+ cpu_relax();
+
+ writel_relaxed(ch, port->membase + USART_DR);
+}
+
+static void stm32_console_write(struct console *co, const char *s, unsigned cnt)
+{
+ struct uart_port *port = &stm32_ports[co->index].port;
+ unsigned long flags;
+ u32 old_cr1, new_cr1;
+ int locked = 1;
+
+ local_irq_save(flags);
+ if (port->sysrq)
+ locked = 0;
+ else if (oops_in_progress)
+ locked = spin_trylock(&port->lock);
+ else
+ spin_lock(&port->lock);
+
+ /* Save and disable interrupts */
+ old_cr1 = readl_relaxed(port->membase + USART_CR1);
+ new_cr1 = old_cr1 & ~USART_CR1_IE_MASK;
+ writel_relaxed(new_cr1, port->membase + USART_CR1);
+
+ uart_console_write(port, s, cnt, stm32_console_putchar);
+
+ /* Restore interrupt state */
+ writel_relaxed(old_cr1, port->membase + USART_CR1);
+
+ if (locked)
+ spin_unlock(&port->lock);
+ local_irq_restore(flags);
+}
+
+static int stm32_console_setup(struct console *co, char *options)
+{
+ struct stm32_port *stm32port;
+ int baud = 9600;
+ int bits = 8;
+ int parity = 'n';
+ int flow = 'n';
+
+ if (co->index >= STM32_MAX_PORTS)
+ return -ENODEV;
+
+ stm32port = &stm32_ports[co->index];
+
+ /*
+ * This driver does not support early console initialization
+ * (use ARM early printk support instead), so we only expect
+ * this to be called during the uart port registration when the
+ * driver gets probed and the port should be mapped at that point.
+ */
+ if (stm32port->port.mapbase == 0 || stm32port->port.membase == NULL)
+ return -ENXIO;
+
+ if (options)
+ uart_parse_options(options, &baud, &parity, &bits, &flow);
+
+ return uart_set_options(&stm32port->port, co, baud, parity, bits, flow);
+}
+
+static struct console stm32_console = {
+ .name = STM32_SERIAL_NAME,
+ .device = uart_console_device,
+ .write = stm32_console_write,
+ .setup = stm32_console_setup,
+ .flags = CON_PRINTBUFFER,
+ .index = -1,
+ .data = &stm32_usart_driver,
+};
+
+#define STM32_SERIAL_CONSOLE (&stm32_console)
+
+#else
+#define STM32_SERIAL_CONSOLE NULL
+#endif /* CONFIG_SERIAL_STM32_CONSOLE */
+
+static struct uart_driver stm32_usart_driver = {
+ .driver_name = DRIVER_NAME,
+ .dev_name = STM32_SERIAL_NAME,
+ .major = 0,
+ .minor = 0,
+ .nr = STM32_MAX_PORTS,
+ .cons = STM32_SERIAL_CONSOLE,
+};
+
+static struct platform_driver stm32_serial_driver = {
+ .probe = stm32_serial_probe,
+ .remove = stm32_serial_remove,
+ .driver = {
+ .name = DRIVER_NAME,
+ .of_match_table = of_match_ptr(stm32_match),
+ },
+};
+
+static int __init usart_init(void)
+{
+ static char banner[] __initdata = "STM32 USART driver initialized";
+ int ret;
+
+ pr_info("%s\n", banner);
+
+ ret = uart_register_driver(&stm32_usart_driver);
+ if (ret)
+ return ret;
+
+ ret = platform_driver_register(&stm32_serial_driver);
+ if (ret)
+ uart_unregister_driver(&stm32_usart_driver);
+
+ return ret;
+}
+
+static void __exit usart_exit(void)
+{
+ platform_driver_unregister(&stm32_serial_driver);
+ uart_unregister_driver(&stm32_usart_driver);
+}
+
+module_init(usart_init);
+module_exit(usart_exit);
+
+MODULE_ALIAS("platform:" DRIVER_NAME);
+MODULE_DESCRIPTION("STMicroelectronics STM32 serial port driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index b212281..93ba148 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -258,4 +258,7 @@
/* Cris v10 / v32 SoC */
#define PORT_CRIS 112
+/* STM32 USART */
+#define PORT_STM32 113
+
#endif /* _UAPILINUX_SERIAL_CORE_H */
--
1.9.1
^ permalink raw reply related
* Re: [PATCH v4] seccomp: add ptrace options for suspend/resume
From: Oleg Nesterov @ 2015-06-10 19:20 UTC (permalink / raw)
To: Andy Lutomirski
Cc: Tycho Andersen,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Linux API,
Kees Cook, Will Drewry, Roland McGrath, Pavel Emelyanov,
Serge E. Hallyn
In-Reply-To: <CALCETrX_GXgjPRXXT4jMZtjR6vMQrmYbk_OwrAoxaJWFT0+0Fw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On 06/10, Andy Lutomirski wrote:
>
> On Wed, Jun 10, 2015 at 9:31 AM, Oleg Nesterov <oleg-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
> >
> > Andy, I simply can't understand why do we need any security check at all.
...
> I think we
> should take the more paranoid approach to start and relax it later as
> needed.
OK. I didn't really tried to argue. I actually replied to other part
of you email, and simply could not resist ;)
Oleg.
^ permalink raw reply
* Re: [PATCH v9 4/5] serial: stm32-usart: Add STM32 USART Driver
From: Maxime Coquelin @ 2015-06-10 19:22 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Mark Rutland, devicetree@vger.kernel.org, Daniel Thompson,
Russell King, Pawel Moll, Arnd Bergmann, khilman,
linux-api@vger.kernel.org, Daniel Lezcano,
linux-kernel@vger.kernel.org, Kamil Lulko, Rob Herring,
Geert Uytterhoeven, linux-serial@vger.kernel.org,
Uwe Kleine-König, Kumar Gala, Thomas Gleixner, Ian Campbell,
Jiri Slaby, Andreas Färber
In-Reply-To: <20150610174955.GA6527@kroah.com>
2015-06-10 19:49 GMT+02:00 Greg Kroah-Hartman <gregkh@linuxfoundation.org>:
> On Wed, Jun 10, 2015 at 06:18:37PM +0200, Maxime Coquelin wrote:
>> 2015-06-10 17:42 GMT+02:00 Greg Kroah-Hartman <gregkh@linuxfoundation.org>:
>> > On Wed, Jun 10, 2015 at 01:33:22PM +0200, Maxime Coquelin wrote:
>> >> 2015-05-31 23:52 GMT+02:00 Greg Kroah-Hartman <gregkh@linuxfoundation.org>:
>> >> > On Fri, May 22, 2015 at 11:03:35PM +0200, Maxime Coquelin wrote:
>> >> >> This drivers adds support to the STM32 USART controller, which is a
>> >> >> standard serial driver.
>> >> >>
>> >> >> Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
>> >> >> Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
>> >> >> Reviewed-by: Vladimir Zapolskiy <vladimir_zapolskiy@mentor.com>
>> >> >> Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
>> >> >> Signed-off-by: Maxime Coquelin <mcoquelin.stm32@gmail.com>
>> >> >
>> >> > Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>> >>
>> >> Thanks Greg.
>> >>
>> >> Will you apply it to your tty tree for v4.2? Or it should go in
>> >> someone else tree?
>> >
>> > It's not in my queue, I'm guessing it goes in through some other tree as
>> > there are build dependancies here preventing me from taking it.
>>
>> There should not be any build dependencies.
>> I just tested it on my x86 machine with COMPILE_TEST on both v4.1-rc1
>> and tty-next branch.
>> In both case it compiles without warnings.
>
> Ok, then feel free to resend it as a stand-alone patch please and I will
> queue it up.
Patch resent as a standalone patch.
Thanks!
Maxime
^ permalink raw reply
* Re: [PATCH v3 1/2] capabilities: Ambient capabilities
From: Kees Cook @ 2015-06-10 19:24 UTC (permalink / raw)
To: Andy Lutomirski
Cc: Andy Lutomirski, Serge Hallyn, Andrew Morton, James Morris,
Jarkko Sakkinen, Ted Ts'o, Andrew G. Morgan, Linux API,
Mimi Zohar, Michael Kerrisk, Austin S Hemmelgarn,
linux-security-module, Aaron Jones, Serge Hallyn, LKML,
Markku Savela, Jonathan Corbet, Christoph Lameter
In-Reply-To: <CALCETrXz9e_PiAZaGRLuunyDu3-nRW_jopvvXcQwU3gN=sm_SA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Tue, Jun 9, 2015 at 5:00 PM, Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org> wrote:
> On Tue, Jun 9, 2015 at 4:09 PM, Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org> wrote:
>> On Wed, May 27, 2015 at 4:47 PM, Andy Lutomirski <luto-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org> wrote:
>>> [1] Files that are missing the "security.capability" xattr or that
>>> have unrecognized values for that xattr end up with has_cap set to
>>> false. The code that does that appears to be complicated for no
>>> good reason.
>>
>> Would it make more sense to have has_cap true, but have it lack any actual caps?
>
> I assume you're referring to the case where we fail to parse the
> xattr. If so, I don't really know if or when this happens. Should
> that be addressed separately from this patch set?
No, no. All of these footnotes seem to be separate from the series. I
just wanted to chime in on them, since none of them really sounded
like they should get dropped.
>>> [2] The libcap capability mask parsers and formatters are
>>> dangerously misleading and the documentation is flat-out wrong. fE
>>> is *not* a mask; it's a single bit. This has probably confused
>>> every single person who has tried to use file capabilities.
>>
>> Sounds like it would be a valuable documentation patch.
>
> I'll try. Let's get the current thing done first.
Yup! No worries. I'm happy to help with the docs, too.
>>> [3] Linux very confusingly processes both the script and the
>>> interpreter if applicable, for reasons that elude me. The results
>>> from thinking about a script's file capabilities and/or setuid bits
>>> are mostly discarded.
>>
>> I wonder if this is important enough to fix?
>
> Not sure.
>
> However, the fact that AFAICT LSM due to a script (as opposed to an
> interpreter) is preserved sounds rather dangerous to me. I'm not sure
> whether we can safely fix that at this point.
Agreed.
I missed adding:
Acked-by: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
I would love to use this already. :)
-Kees
--
Kees Cook
Chrome OS Security
^ permalink raw reply
* Re: [PATCH v4] seccomp: add ptrace options for suspend/resume
From: Kees Cook @ 2015-06-10 20:18 UTC (permalink / raw)
To: Andy Lutomirski
Cc: Oleg Nesterov, Tycho Andersen,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Linux API,
Will Drewry, Roland McGrath, Pavel Emelyanov, Serge E. Hallyn
In-Reply-To: <CALCETrX_GXgjPRXXT4jMZtjR6vMQrmYbk_OwrAoxaJWFT0+0Fw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Wed, Jun 10, 2015 at 10:20 AM, Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org> wrote:
> On Wed, Jun 10, 2015 at 9:31 AM, Oleg Nesterov <oleg-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
>> On 06/09, Andy Lutomirski wrote:
>>>
>>> On Tue, Jun 9, 2015 at 5:49 PM, Tycho Andersen
>>> >
>>> > @@ -556,6 +556,15 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data)
>>> > if (data & ~(unsigned long)PTRACE_O_MASK)
>>> > return -EINVAL;
>>> >
>>> > + if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
>>
>> Well, we should do this if
>>
>> (data & O_SUSPEND) && !(flags & O_SUSPEND)
>>
>> or at least if
>>
>> (data ^ flags) & O_SUSPEND
>>
>>
>>> > + if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
>>> > + !config_enabled(CONFIG_SECCOMP))
>>> > + return -EINVAL;
>>> > +
>>> > + if (!capable(CAP_SYS_ADMIN))
>>> > + return -EPERM;
>>>
>>> I tend to think that we should also require that current not be using
>>> seccomp. Otherwise, in principle, there's a seccomp bypass for
>>> privileged-but-seccomped programs.
>>
>> Andy, I simply can't understand why do we need any security check at all.
>>
>> OK, yes, in theory we can have a seccomped CAP_SYS_ADMIN process, seccomp
>> doesn't filter ptrace, you hack that process and force it to attach to
>> another CAP_SYS_ADMIN/seccomped process, etc, etc... Looks too paranoid
>> to me.
>
> I've sometimes considered having privileged processes I write fork and
> seccomp their child. Of course, if you're allowing ptrace through
> your seccomp filter, you open a giant can of worms, but I think we
> should take the more paranoid approach to start and relax it later as
> needed. After all, for the intended use of this patch, stuff will
> break regardless of what we do if the ptracer is itself seccomped.
>
> I could be convinced that if the ptracer is outside seccomp then we
> shouldn't need the CAP_SYS_ADMIN check. That would at least make this
> work in a user namespace.
But not if that namespace is running under a manager that has added a
seccomp filter to do things like drop finit_module, as lxc does.
Let's start with CAP_SYS_ADMIN, and when we have an actual use-case,
we can change it then.
>
>>> > @@ -590,6 +590,10 @@ void secure_computing_strict(int this_syscall)
>>> > {
>>> > int mode = current->seccomp.mode;
>>> >
>>> > + if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
>>> > + unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
>>> > + return;
>>> > +
>>> > if (mode == 0)
>>> > return;
>>> > else if (mode == SECCOMP_MODE_STRICT)
>>> > @@ -691,6 +695,10 @@ u32 seccomp_phase1(struct seccomp_data *sd)
>>> > int this_syscall = sd ? sd->nr :
>>> > syscall_get_nr(current, task_pt_regs(current));
>>> >
>>> > + if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
>>> > + unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
>>> > + return SECCOMP_PHASE1_OK;
>>> > +
>>>
>>> If it's not hard, it might still be nice to try to fold this into
>>> mode. This code is rather hot. If it would be a mess, then don't
>>> worry about it for now.
>>
>> IMO, this would be a mess ;) At least compared to this simple patch.
>>
>> Suppose we add SECCOMP_MODE_SUSPENDED. Not only this adds the problems
>> with detach if the tracer dies.
>>
>> We need to change copy_seccomp(). And it is not clear what should we
>> do if the child is traced too.
>>
>> We need to change prctl_set_seccomp() paths.
>>
>> And even the "tracee->seccomp.mode = SECCOMP_MODE_SUSPENDED" code needs
>> some locking even if the tracee is stopped, we need to avoid the races
>> with SECCOMP_FILTER_FLAG_TSYNC from other threads.
>>
>
> Agreed. Let's hold off until this becomes a problem (if it ever does).
Arg, right, no. I don't want this represented in seccomp.mode. Way too
much would get touched for little benefit.
Thanks! And sorry Tycho as we all disagree about how to disagree with
your patch... :)
--
Kees Cook
Chrome OS Security
^ permalink raw reply
* Re: [PATCH v4] seccomp: add ptrace options for suspend/resume
From: Oleg Nesterov @ 2015-06-10 20:26 UTC (permalink / raw)
To: Kees Cook
Cc: Andy Lutomirski, Tycho Andersen,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Linux API,
Will Drewry, Roland McGrath, Pavel Emelyanov, Serge E. Hallyn
In-Reply-To: <CAGXu5jJovcC1S4OANpqbVe6e86xr4W9Y7897MsSDOpvEqezpnA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On 06/10, Kees Cook wrote:
>
> And sorry Tycho as we all disagree about how to disagree with
> your patch... :)
Yes ;)
So, just in case, I am fine with this version.
Andy wants another security check, OK, this is fine too to me.
Oleg.
^ permalink raw reply
* Re: [PATCH v4] seccomp: add ptrace options for suspend/resume
From: Kees Cook @ 2015-06-10 20:33 UTC (permalink / raw)
To: Tycho Andersen
Cc: LKML, Linux API, Andy Lutomirski, Will Drewry, Roland McGrath,
Oleg Nesterov, Pavel Emelyanov, Serge E. Hallyn
In-Reply-To: <1433897388-9567-1-git-send-email-tycho.andersen-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
On Tue, Jun 9, 2015 at 5:49 PM, Tycho Andersen
<tycho.andersen-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org> wrote:
> This patch is the first step in enabling checkpoint/restore of processes
> with seccomp enabled.
>
> One of the things CRIU does while dumping tasks is inject code into them
> via ptrace to collect information that is only available to the process
> itself. However, if we are in a seccomp mode where these processes are
> prohibited from making these syscalls, then what CRIU does kills the task.
>
> This patch adds a new ptrace option, PTRACE_O_SUSPEND_SECCOMP, that enables
> a task from the init user namespace which has CAP_SYS_ADMIN and no seccomp
> filters to disable (and re-enable) seccomp filters for another task so that
> they can be successfully dumped (and restored). We restrict the set of
> processes that can disable seccomp through ptrace because although today
> ptrace can be used to bypass seccomp, there is some discussion of closing
> this loophole in the future and we would like this patch to not depend on
> that behavior and be future proofed for when it is removed.
>
> Note that seccomp can be suspended before any filters are actually
> installed; this behavior is useful on criu restore, so that we can suspend
> seccomp, restore the filters, unmap our restore code from the restored
> process' address space, and then resume the task by detaching and have the
> filters resumed as well.
>
> v2 changes:
>
> * require that the tracer have no seccomp filters installed
> * drop TIF_NOTSC manipulation from the patch
> * change from ptrace command to a ptrace option and use this ptrace option
> as the flag to check. This means that as soon as the tracer
> detaches/dies, seccomp is re-enabled and as a corrollary that one can not
> disable seccomp across PTRACE_ATTACHs.
>
> v3 changes:
>
> * get rid of various #ifdefs everywhere
> * report more sensible errors when PTRACE_O_SUSPEND_SECCOMP is incorrectly
> used
>
> v4 changes:
>
> * get rid of may_suspend_seccomp() in favor of a capable() check in ptrace
> directly
>
> Signed-off-by: Tycho Andersen <tycho.andersen-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
> CC: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
> CC: Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org>
> CC: Will Drewry <wad-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
> CC: Roland McGrath <roland-/Z5OmTQCD9xF6kxbq+BtvQ@public.gmane.org>
> CC: Oleg Nesterov <oleg-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> CC: Pavel Emelyanov <xemul-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
> CC: Serge E. Hallyn <serge.hallyn-GeWIH/nMZzLQT0dZR+AlfA@public.gmane.org>
> ---
> include/linux/ptrace.h | 1 +
> include/uapi/linux/ptrace.h | 6 ++++--
> kernel/ptrace.c | 9 +++++++++
> kernel/seccomp.c | 8 ++++++++
> 4 files changed, 22 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
> index 987a73a..061265f 100644
> --- a/include/linux/ptrace.h
> +++ b/include/linux/ptrace.h
> @@ -34,6 +34,7 @@
> #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP)
>
> #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT)
> +#define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT)
>
> /* single stepping state bits (used on ARM and PA-RISC) */
> #define PT_SINGLESTEP_BIT 31
> diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
> index cf1019e..a7a6979 100644
> --- a/include/uapi/linux/ptrace.h
> +++ b/include/uapi/linux/ptrace.h
> @@ -89,9 +89,11 @@ struct ptrace_peeksiginfo_args {
> #define PTRACE_O_TRACESECCOMP (1 << PTRACE_EVENT_SECCOMP)
>
> /* eventless options */
> -#define PTRACE_O_EXITKILL (1 << 20)
> +#define PTRACE_O_EXITKILL (1 << 20)
> +#define PTRACE_O_SUSPEND_SECCOMP (1 << 21)
>
> -#define PTRACE_O_MASK (0x000000ff | PTRACE_O_EXITKILL)
> +#define PTRACE_O_MASK (\
> + 0x000000ff | PTRACE_O_EXITKILL | PTRACE_O_SUSPEND_SECCOMP)
>
> #include <asm/ptrace.h>
>
> diff --git a/kernel/ptrace.c b/kernel/ptrace.c
> index c8e0e05..11fa460 100644
> --- a/kernel/ptrace.c
> +++ b/kernel/ptrace.c
> @@ -556,6 +556,15 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data)
> if (data & ~(unsigned long)PTRACE_O_MASK)
> return -EINVAL;
>
> + if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
> + if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
> + !config_enabled(CONFIG_SECCOMP))
> + return -EINVAL;
> +
> + if (!capable(CAP_SYS_ADMIN))
> + return -EPERM;
> + }
> +
> /* Avoid intermediate state when all opts are cleared */
> flags = child->ptrace;
> flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT);
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index 980fd26..645e42d 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -590,6 +590,10 @@ void secure_computing_strict(int this_syscall)
> {
> int mode = current->seccomp.mode;
>
> + if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
> + unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
> + return;
> +
> if (mode == 0)
> return;
> else if (mode == SECCOMP_MODE_STRICT)
> @@ -691,6 +695,10 @@ u32 seccomp_phase1(struct seccomp_data *sd)
> int this_syscall = sd ? sd->nr :
> syscall_get_nr(current, task_pt_regs(current));
>
> + if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
> + unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
> + return SECCOMP_PHASE1_OK;
> +
> switch (mode) {
> case SECCOMP_MODE_STRICT:
> __secure_computing_strict(this_syscall); /* may call do_exit */
> --
> 2.1.4
>
And if I've convinced Andy to be okay with this patch, consider v4:
Acked-by: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
-Kees
--
Kees Cook
Chrome OS Security
^ permalink raw reply
* Re: [PATCH v4] seccomp: add ptrace options for suspend/resume
From: Tycho Andersen @ 2015-06-10 20:57 UTC (permalink / raw)
To: Kees Cook
Cc: LKML, Linux API, Andy Lutomirski, Will Drewry, Roland McGrath,
Oleg Nesterov, Pavel Emelyanov, Serge E. Hallyn
In-Reply-To: <CAGXu5jKuf6PoBDDkr21ZHOMnWpRAZ-G=NA7rVMx_1qiHZ-8DzA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Wed, Jun 10, 2015 at 01:33:21PM -0700, Kees Cook wrote:
>
> And if I've convinced Andy to be okay with this patch, consider v4:
>
> Acked-by: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
Thanks, I'm happy to send a v5 with checking seccomp (and
->ptrace & PT_SUSPEND_SECCOMP) if you'd feel better with that, Andy.
Tycho
^ permalink raw reply
* Re: [RESEND PATCH V2 0/3] Allow user to request memory to be locked on page fault
From: Andrew Morton @ 2015-06-10 21:59 UTC (permalink / raw)
To: Eric B Munson
Cc: Shuah Khan, Michal Hocko, Michael Kerrisk,
linux-alpha-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-mips-6z/3iImG2C8G8FEW9MqTrA,
linux-parisc-u79uwXL29TY76Z2rM5mHXA,
linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ,
sparclinux-u79uwXL29TY76Z2rM5mHXA,
linux-xtensa-PjhNF2WwrV/0Sa2dR60CXw,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
linux-arch-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1433942810-7852-1-git-send-email-emunson-JqFfY2XvxFXQT0dZR+AlfA@public.gmane.org>
On Wed, 10 Jun 2015 09:26:47 -0400 Eric B Munson <emunson-JqFfY2XvxFXQT0dZR+AlfA@public.gmane.org> wrote:
> mlock() allows a user to control page out of program memory, but this
> comes at the cost of faulting in the entire mapping when it is
s/mapping/locked area/
> allocated. For large mappings where the entire area is not necessary
> this is not ideal.
>
> This series introduces new flags for mmap() and mlockall() that allow a
> user to specify that the covered are should not be paged out, but only
> after the memory has been used the first time.
The comparison with MCL_FUTURE is hiding over in the 2/3 changelog.
It's important so let's copy it here.
: MCL_ONFAULT is preferrable to MCL_FUTURE for the use cases enumerated
: in the previous patch becuase MCL_FUTURE will behave as if each mapping
: was made with MAP_LOCKED, causing the entire mapping to be faulted in
: when new space is allocated or mapped. MCL_ONFAULT allows the user to
: delay the fault in cost of any given page until it is actually needed,
: but then guarantees that that page will always be resident.
I *think* it all looks OK. I'd like someone else to go over it also if
poss.
I guess the 2/3 changelog should have something like
: munlockall() will clear MCL_ONFAULT on all vma's in the process's VM.
It's pretty obvious, but the manpage delta should make this clear also.
Also the changelog(s) and manpage delta should explain that munlock()
clears MCL_ONFAULT.
And now I'm wondering what happens if userspace does
mmap(MAP_LOCKONFAULT) and later does munlock() on just part of that
region. Does the vma get split? Is this tested? Should also be in
the changelogs and manpage.
Ditto mlockall(MCL_ONFAULT) followed by munlock(). I'm not sure that
even makes sense but the behaviour should be understood and tested.
What's missing here is a syscall to set VM_LOCKONFAULT on an arbitrary
range of memory - mlock() for lock-on-fault. It's a shame that mlock()
didn't take a `mode' argument. Perhaps we should add such a syscall -
that would make the mmap flag unneeded but I suppose it should be kept
for symmetry.
^ permalink raw reply
* Re: [RFC PATCH 09/18] kthread: Make it easier to correctly sleep in iterant kthreads
From: Jiri Kosina @ 2015-06-11 4:28 UTC (permalink / raw)
To: Steven Rostedt
Cc: Peter Zijlstra, Petr Mladek, Andrew Morton, Oleg Nesterov,
Tejun Heo, Ingo Molnar, Richard Weinberger, David Woodhouse,
linux-mtd-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r, Trond Myklebust,
Anna Schumaker, linux-nfs-u79uwXL29TY76Z2rM5mHXA, Chris Mason,
Paul E. McKenney, Thomas Gleixner, Linus Torvalds,
Borislav Petkov, Michal Hocko,
live-patching-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20150610100729.6a674c15-f9ZlEuEWxVcJvu8Pb33WZ0EMvNT87kid@public.gmane.org>
On Wed, 10 Jun 2015, Steven Rostedt wrote:
> > Right, and I had not considered that, but it turns out the hung_task
> > detector checks p->state == TASK_UNINTERRUPTIBLE, so TASK_IDLE is indeed
> > safe from that.
>
> Also, I would assume that TASK_IDLE only makes sense for kernel
> threads, I wonder if we should add an assertion in schedule that
> triggers if a task is scheduling with TASK_IDLE and is not a kernel
> thread (has its own mm?)
For the sake of completnes -- testing for !task_struct->mm is not a
correct test to find out whether given entity is a kernel thread; kernel
threads are free to temporarily adopt user struct mm via use_mm() (usually
for handling AIO on behalf of a particular struct mm).
The correct check is to look at PF_KTHREAD flag in task_struct->flags.
--
Jiri Kosina
SUSE Labs
^ permalink raw reply
* Re: Generic kernel features that need architecture(mips) support
From: Ingo Molnar @ 2015-06-11 6:24 UTC (permalink / raw)
To: Xose Vazquez Perez, Jonathan Corbet
Cc: Ralf Baechle, linux-mips, linux-arch, linux-api, LKML
In-Reply-To: <5578679D.2030307@gmail.com>
(Jon Cc:-ed)
* Xose Vazquez Perez <xose.vazquez@gmail.com> wrote:
> On 06/10/2015 04:58 PM, Ralf Baechle wrote:
>
> > How are the documentation files in Documentation/features/ maintained?
> > They were automatically generated so I wonder if I have to take care
> > of anything.
>
> CC: Ingo and related ml.
So changes to Documentation/features/ should come as simple patches done from hand
editing, there's no need to preserve any initial (half-)automated generation.
Formatting should be preserved so that Documentation/features/list-arch.sh still
works as before.
Jon: would you like to receive all patches to Documentation/features/ so you can
collect them in the documentation tree, or can maintainers patch it as part of any
feature work that affects the tables? I think it's all finegrained enough to not
create conflicts. That way they would become partly self-maintaining. (Or at least
one can always hope! ;-)
Thanks,
Ingo
^ permalink raw reply
* Re: [PATCH v5 17/21] libnvdimm: infrastructure for btt devices
From: Christoph Hellwig @ 2015-06-11 7:28 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Christoph Hellwig, Dan Williams, axboe, sfr, rafael, neilb,
gregkh, linux-nvdimm, linux-kernel, linux-acpi, linux-api, akpm,
mingo
In-Reply-To: <20150610184616.GL2729@linux.intel.com>
On Wed, Jun 10, 2015 at 02:46:16PM -0400, Matthew Wilcox wrote:
> Don't screw up rw_page. The point of rw_page is to read or write a page
> cache page. It can sleep, and it indicates success by using the page
> flags. Don't try and scqueeze rw_bytes into it. If you want rw_bytes
> to be a queue operation, that's one thing, but don't mess with rw_page.
Oh, I forgot about the page manipulating nature. Yes, we'll need a different
operation in this case.
^ permalink raw reply
* Re: Generic kernel features that need architecture(mips) support
From: Jonathan Corbet @ 2015-06-11 13:20 UTC (permalink / raw)
To: Ingo Molnar
Cc: Xose Vazquez Perez, Ralf Baechle, linux-mips, linux-arch,
linux-api, LKML
In-Reply-To: <20150611062452.GB32133@gmail.com>
On Thu, 11 Jun 2015 08:24:53 +0200
Ingo Molnar <mingo@kernel.org> wrote:
> Jon: would you like to receive all patches to Documentation/features/ so you can
> collect them in the documentation tree, or can maintainers patch it as part of any
> feature work that affects the tables? I think it's all finegrained enough to not
> create conflicts. That way they would become partly self-maintaining. (Or at least
> one can always hope! ;-)
I sort of figured I'd handle it the way I do the rest of Documentation/ —
I'm happy to herd the patches, but I also have no problem staying out of
the way when other maintainers reach into it.
jon
^ permalink raw reply
* Re: [PATCH] cn_proc: Flag termination of the last thread in the process
From: Evgeniy Polyakov @ 2015-06-11 15:26 UTC (permalink / raw)
To: Sergei Zhirikov
Cc: netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <1432929029-2205-1-git-send-email-sfzhi-/E1597aS9LQAvxtiuMwx3w@public.gmane.org>
Hi Sergei
29.05.2015, 22:50, "Sergei Zhirikov" <sfzhi-/E1597aS9LQAvxtiuMwx3w@public.gmane.org>:
> There is no easy and reliable way for userspace to get notified
> of a process termination. The process connector sends out "exit"
> events upon termination of each thread, but it is not trivial for
> userspace to tell whether the just-terminated thread was the last
> one in the process.
>
> With this change a flag will be set in struct cn_proc for the exit
> event of the last thread in the process.
I have no objection against this patch, but it should really go through cn_proc maintainer.
Feel free to add my Acked-by.
^ permalink raw reply
* Re: [RESEND PATCH V2 0/3] Allow user to request memory to be locked on page fault
From: Eric B Munson @ 2015-06-11 19:21 UTC (permalink / raw)
To: Andrew Morton
Cc: Shuah Khan, Michal Hocko, Michael Kerrisk, linux-alpha,
linux-kernel, linux-mips, linux-parisc, linuxppc-dev, sparclinux,
linux-xtensa, linux-mm, linux-arch, linux-api
In-Reply-To: <20150610145929.b22be8647887ea7091b09ae1@linux-foundation.org>
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
On 06/10/2015 05:59 PM, Andrew Morton wrote:
> On Wed, 10 Jun 2015 09:26:47 -0400 Eric B Munson
> <emunson@akamai.com> wrote:
>
>> mlock() allows a user to control page out of program memory, but
>> this comes at the cost of faulting in the entire mapping when it
>> is
>
> s/mapping/locked area/
Done.
>
>> allocated. For large mappings where the entire area is not
>> necessary this is not ideal.
>>
>> This series introduces new flags for mmap() and mlockall() that
>> allow a user to specify that the covered are should not be paged
>> out, but only after the memory has been used the first time.
>
> The comparison with MCL_FUTURE is hiding over in the 2/3 changelog.
> It's important so let's copy it here.
>
> : MCL_ONFAULT is preferrable to MCL_FUTURE for the use cases
> enumerated : in the previous patch becuase MCL_FUTURE will behave
> as if each mapping : was made with MAP_LOCKED, causing the entire
> mapping to be faulted in : when new space is allocated or mapped.
> MCL_ONFAULT allows the user to : delay the fault in cost of any
> given page until it is actually needed, : but then guarantees that
> that page will always be resident.
Done
>
> I *think* it all looks OK. I'd like someone else to go over it
> also if poss.
>
>
> I guess the 2/3 changelog should have something like
>
> : munlockall() will clear MCL_ONFAULT on all vma's in the process's
> VM.
Done
>
> It's pretty obvious, but the manpage delta should make this clear
> also.
Done
>
>
> Also the changelog(s) and manpage delta should explain that
> munlock() clears MCL_ONFAULT.
Done
>
> And now I'm wondering what happens if userspace does
> mmap(MAP_LOCKONFAULT) and later does munlock() on just part of
> that region. Does the vma get split? Is this tested? Should also
> be in the changelogs and manpage.
>
> Ditto mlockall(MCL_ONFAULT) followed by munlock(). I'm not sure
> that even makes sense but the behaviour should be understood and
> tested.
I have extended the kselftest for lock-on-fault to try both of these
scenarios and they work as expected. The VMA is split and the VM
flags are set appropriately for the resulting VMAs.
>
>
> What's missing here is a syscall to set VM_LOCKONFAULT on an
> arbitrary range of memory - mlock() for lock-on-fault. It's a
> shame that mlock() didn't take a `mode' argument. Perhaps we
> should add such a syscall - that would make the mmap flag unneeded
> but I suppose it should be kept for symmetry.
Do you want such a system call as part of this set? I would need some
time to make sure I had thought through all the possible corners one
could get into with such a call, so it would delay a V3 quite a bit.
Otherwise I can send a V3 out immediately.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=gfVJ
-----END PGP SIGNATURE-----
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: [RESEND PATCH V2 0/3] Allow user to request memory to be locked on page fault
From: Andrew Morton @ 2015-06-11 19:34 UTC (permalink / raw)
To: Eric B Munson
Cc: Shuah Khan, Michal Hocko, Michael Kerrisk, linux-alpha,
linux-kernel, linux-mips, linux-parisc, linuxppc-dev, sparclinux,
linux-xtensa, linux-mm, linux-arch, linux-api
In-Reply-To: <5579DFBA.80809@akamai.com>
On Thu, 11 Jun 2015 15:21:30 -0400 Eric B Munson <emunson@akamai.com> wrote:
> > Ditto mlockall(MCL_ONFAULT) followed by munlock(). I'm not sure
> > that even makes sense but the behaviour should be understood and
> > tested.
>
> I have extended the kselftest for lock-on-fault to try both of these
> scenarios and they work as expected. The VMA is split and the VM
> flags are set appropriately for the resulting VMAs.
munlock() should do vma merging as well. I *think* we implemented
that. More tests for you to add ;)
How are you testing the vma merging and splitting, btw? Parsing
the profcs files?
> > What's missing here is a syscall to set VM_LOCKONFAULT on an
> > arbitrary range of memory - mlock() for lock-on-fault. It's a
> > shame that mlock() didn't take a `mode' argument. Perhaps we
> > should add such a syscall - that would make the mmap flag unneeded
> > but I suppose it should be kept for symmetry.
>
> Do you want such a system call as part of this set? I would need some
> time to make sure I had thought through all the possible corners one
> could get into with such a call, so it would delay a V3 quite a bit.
> Otherwise I can send a V3 out immediately.
I think the way to look at this is to pretend that mm/mlock.c doesn't
exist and ask "how should we design these features".
And that would be:
- mmap() takes a `flags' argument: MAP_LOCKED|MAP_LOCKONFAULT.
- mlock() takes a `flags' argument. Presently that's
MLOCK_LOCKED|MLOCK_LOCKONFAULT.
- munlock() takes a `flags' arument. MLOCK_LOCKED|MLOCK_LOCKONFAULT
to specify which flags are being cleared.
- mlockall() and munlockall() ditto.
IOW, LOCKED and LOCKEDONFAULT are treated identically and independently.
Now, that's how we would have designed all this on day one. And I
think we can do this now, by adding new mlock2() and munlock2()
syscalls. And we may as well deprecate the old mlock() and munlock(),
not that this matters much.
*should* we do this? I'm thinking "yes" - it's all pretty simple
boilerplate and wrappers and such, and it gets the interface correct,
and extensible.
What do others think?
^ permalink raw reply
* Re: [RESEND PATCH V2 0/3] Allow user to request memory to be locked on page fault
From: Eric B Munson @ 2015-06-11 19:55 UTC (permalink / raw)
To: Andrew Morton
Cc: Shuah Khan, Michal Hocko, Michael Kerrisk, linux-alpha,
linux-kernel, linux-mips, linux-parisc, linuxppc-dev, sparclinux,
linux-xtensa, linux-mm, linux-arch, linux-api
In-Reply-To: <20150611123424.4bb07cffd0e5bb146cc92231@linux-foundation.org>
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
On 06/11/2015 03:34 PM, Andrew Morton wrote:
> On Thu, 11 Jun 2015 15:21:30 -0400 Eric B Munson
> <emunson@akamai.com> wrote:
>
>>> Ditto mlockall(MCL_ONFAULT) followed by munlock(). I'm not
>>> sure that even makes sense but the behaviour should be
>>> understood and tested.
>>
>> I have extended the kselftest for lock-on-fault to try both of
>> these scenarios and they work as expected. The VMA is split and
>> the VM flags are set appropriately for the resulting VMAs.
>
> munlock() should do vma merging as well. I *think* we implemented
> that. More tests for you to add ;)
I will add a test for this as well. But the code is in place to merge
VMAs IIRC.
>
> How are you testing the vma merging and splitting, btw? Parsing
> the profcs files?
To show the VMA split happened, I dropped a printk in mlock_fixup()
and the user space test simply checks that unlocked pages are not
marked as unevictable. The test does not parse maps or smaps for
actual VMA layout. Given that we want to check the merging of VMAs as
well I will add this.
>
>>> What's missing here is a syscall to set VM_LOCKONFAULT on an
>>> arbitrary range of memory - mlock() for lock-on-fault. It's a
>>> shame that mlock() didn't take a `mode' argument. Perhaps we
>>> should add such a syscall - that would make the mmap flag
>>> unneeded but I suppose it should be kept for symmetry.
>>
>> Do you want such a system call as part of this set? I would need
>> some time to make sure I had thought through all the possible
>> corners one could get into with such a call, so it would delay a
>> V3 quite a bit. Otherwise I can send a V3 out immediately.
>
> I think the way to look at this is to pretend that mm/mlock.c
> doesn't exist and ask "how should we design these features".
>
> And that would be:
>
> - mmap() takes a `flags' argument: MAP_LOCKED|MAP_LOCKONFAULT.
>
> - mlock() takes a `flags' argument. Presently that's
> MLOCK_LOCKED|MLOCK_LOCKONFAULT.
>
> - munlock() takes a `flags' arument.
> MLOCK_LOCKED|MLOCK_LOCKONFAULT to specify which flags are being
> cleared.
>
> - mlockall() and munlockall() ditto.
>
>
> IOW, LOCKED and LOCKEDONFAULT are treated identically and
> independently.
>
> Now, that's how we would have designed all this on day one. And I
> think we can do this now, by adding new mlock2() and munlock2()
> syscalls. And we may as well deprecate the old mlock() and
> munlock(), not that this matters much.
>
> *should* we do this? I'm thinking "yes" - it's all pretty simple
> boilerplate and wrappers and such, and it gets the interface
> correct, and extensible.
>
> What do others think?
>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=82B8
-----END PGP SIGNATURE-----
^ permalink raw reply
* [PATCH v6 00/21] libnvdimm: non-volatile memory devices
From: Dan Williams @ 2015-06-11 20:09 UTC (permalink / raw)
To: linux-nvdimm
Cc: Boaz Harrosh, rafael, neilb, Dave Chinner, Lv Zheng,
H. Peter Anvin, hch, sfr, Rafael J. Wysocki, Robert Moore, mingo,
linux-acpi, jmoyer, Nicholas Moulin, Matthew Wilcox, Ross Zwisler,
Vishal Verma, Jens Axboe, Borislav Petkov, Thomas Gleixner, axboe,
gregkh, linux-kernel, Andy Lutomirski, linux-api, akpm,
Linus Torvalds
A new sub-system in support of non-volatile memory storage devices. See
"[PATCH v6 21/21] libnvdimm: Non-Volatile Devices" for an overview.
Changes since v5 [1]:
1/ Add rationale/justification to the changelog for "[PATCH v6 20/21]
tools/testing/nvdimm: libnvdimm unit test infrastructure". Explain
why QEMU is not suitable. (Christoph)
2/ Expand the changelog of "[PATCH v6 18/21] nd_btt: atomic sector
updates" to give the reasoning behind architecture decisions related
to scaling. (Christoph)
3/ Introduce ->rw_bytes() to struct block_device_operations and kill off
the "ndio" implementation (save a couple hundred lines of glue code).
(Christoph)
4/ Kill usage of __iomem in the namespace label implementation in favor
of properly using byte-order helpers. (Christoph)
5/ Kill the include path munging in "[PATCH v6 20/21]
tools/testing/nvdimm: libnvdimm unit test infrastructure" this makes
the unit test implementation have near zero impact on the libnvdimm
code base. (Christoph)
6/ Miscellaneous 80 column fixups. (Christoph)
7/ Restore BLK_DEV and PHYS_ADDR_T_64BIT dependencies to LIBNVDIMM.
Diffstat since v5 [1]: "ebba6912e36e libnvdimm: Non-Volatile Devices"
[1]: https://lists.01.org/pipermail/linux-nvdimm/2015-June/001035.html
drivers/acpi/Makefile | 1 -
drivers/acpi/nfit.c | 228 +++++++++++++++++++++-----------------
drivers/acpi/nfit.h | 20 ++--
drivers/nvdimm/Kconfig | 6 +-
drivers/nvdimm/Makefile | 1 -
drivers/nvdimm/blk.c | 39 +++----
drivers/nvdimm/btt.c | 85 ++++++++-------
drivers/nvdimm/btt_devs.c | 163 +++++++++++++--------------
drivers/nvdimm/bus.c | 156 +++++++++++---------------
drivers/nvdimm/core.c | 72 ++----------
drivers/nvdimm/dimm.c | 4 +-
drivers/nvdimm/dimm_devs.c | 31 +++---
drivers/nvdimm/label.c | 284 ++++++++++++++++++++++++------------------------
drivers/nvdimm/label.h | 8 +-
drivers/nvdimm/namespace_devs.c | 142 ++++++++++++------------
drivers/nvdimm/nd-core.h | 28 +++--
drivers/nvdimm/nd.h | 113 ++-----------------
drivers/nvdimm/pmem.c | 38 +++----
drivers/nvdimm/region.c | 2 +-
drivers/nvdimm/region_devs.c | 90 +++++++--------
include/linux/blkdev.h | 44 ++++++++
include/linux/libnvdimm.h | 14 ++-
include/uapi/linux/ndctl.h | 8 +-
tools/testing/nvdimm/Kbuild | 2 -
tools/testing/nvdimm/test/nfit.c | 63 ++++++-----
tools/testing/nvdimm/test/nfit_test.h | 3 +-
26 files changed, 768 insertions(+), 877 deletions(-)
---
[PATCH v6 01/21] e820, efi: add ACPI 6.0 persistent memory types
[PATCH v6 02/21] libnvdimm, nfit: initial libnvdimm infrastructure and NFIT support
[PATCH v6 03/21] libnvdimm: control character device and nvdimm_bus sysfs attributes
[PATCH v6 04/21] libnvdimm, nfit: dimm/memory-devices
[PATCH v6 05/21] libnvdimm: control (ioctl) messages for nvdimm_bus and nvdimm devices
[PATCH v6 06/21] libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver infrastructure
[PATCH v6 07/21] libnvdimm, nfit: regions (block-data-window, persistent memory, volatile memory)
[PATCH v6 08/21] libnvdimm: support for legacy (non-aliasing) nvdimms
[PATCH v6 09/21] libnvdimm, pmem: move pmem to drivers/nvdimm/
[PATCH v6 10/21] libnvdimm, pmem: add libnvdimm support to the pmem driver
[PATCH v6 11/21] libnvdimm, nfit: add interleave-set state-tracking infrastructure
[PATCH v6 12/21] libnvdimm: namespace indices: read and validate
[PATCH v6 13/21] libnvdimm: pmem label sets and namespace instantiation.
[PATCH v6 14/21] libnvdimm: blk labels and namespace instantiation
[PATCH v6 15/21] libnvdimm: write pmem label set
[PATCH v6 16/21] libnvdimm: write blk label set
[PATCH v6 17/21] libnvdimm: infrastructure for btt devices
[PATCH v6 18/21] nd_btt: atomic sector updates
[PATCH v6 19/21] libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory
[PATCH v6 20/21] tools/testing/nvdimm: libnvdimm unit test infrastructure
[PATCH v6 21/21] libnvdimm: Non-Volatile Devices
Documentation/nvdimm/btt.txt | 273 +++++
Documentation/nvdimm/nvdimm.txt | 805 ++++++++++++++++
MAINTAINERS | 39 +
arch/arm64/kernel/efi.c | 1
arch/ia64/kernel/efi.c | 4
arch/x86/Kconfig | 3
arch/x86/boot/compressed/eboot.c | 4
arch/x86/include/uapi/asm/e820.h | 1
arch/x86/kernel/e820.c | 28 -
arch/x86/kernel/pmem.c | 92 +-
arch/x86/platform/efi/efi.c | 3
drivers/Kconfig | 2
drivers/Makefile | 1
drivers/acpi/Kconfig | 26 +
drivers/acpi/Makefile | 1
drivers/acpi/nfit.c | 1546 ++++++++++++++++++++++++++++++
drivers/acpi/nfit.h | 155 +++
drivers/block/Kconfig | 11
drivers/block/Makefile | 1
drivers/nvdimm/Kconfig | 75 +
drivers/nvdimm/Makefile | 20
drivers/nvdimm/blk.c | 241 +++++
drivers/nvdimm/btt.c | 1449 ++++++++++++++++++++++++++++
drivers/nvdimm/btt.h | 186 ++++
drivers/nvdimm/btt_devs.c | 432 ++++++++
drivers/nvdimm/bus.c | 746 ++++++++++++++
drivers/nvdimm/core.c | 416 ++++++++
drivers/nvdimm/dimm.c | 115 ++
drivers/nvdimm/dimm_devs.c | 517 ++++++++++
drivers/nvdimm/label.c | 926 ++++++++++++++++++
drivers/nvdimm/label.h | 141 +++
drivers/nvdimm/namespace_devs.c | 1698 +++++++++++++++++++++++++++++++++
drivers/nvdimm/nd-core.h | 111 ++
drivers/nvdimm/nd.h | 168 +++
drivers/nvdimm/pmem.c | 107 +-
drivers/nvdimm/region.c | 189 ++++
drivers/nvdimm/region_devs.c | 667 +++++++++++++
include/linux/blkdev.h | 44 +
include/linux/efi.h | 3
include/linux/libnvdimm.h | 139 +++
include/linux/nd.h | 98 ++
include/uapi/linux/Kbuild | 1
include/uapi/linux/ndctl.h | 199 ++++
tools/testing/nvdimm/Kbuild | 35 +
tools/testing/nvdimm/Makefile | 7
tools/testing/nvdimm/test/Kbuild | 8
tools/testing/nvdimm/test/iomap.c | 151 +++
tools/testing/nvdimm/test/nfit.c | 1112 ++++++++++++++++++++++
tools/testing/nvdimm/test/nfit_test.h | 29 +
49 files changed, 12934 insertions(+), 92 deletions(-)
create mode 100644 Documentation/nvdimm/btt.txt
create mode 100644 Documentation/nvdimm/nvdimm.txt
create mode 100644 drivers/acpi/nfit.c
create mode 100644 drivers/acpi/nfit.h
create mode 100644 drivers/nvdimm/Kconfig
create mode 100644 drivers/nvdimm/Makefile
create mode 100644 drivers/nvdimm/blk.c
create mode 100644 drivers/nvdimm/btt.c
create mode 100644 drivers/nvdimm/btt.h
create mode 100644 drivers/nvdimm/btt_devs.c
create mode 100644 drivers/nvdimm/bus.c
create mode 100644 drivers/nvdimm/core.c
create mode 100644 drivers/nvdimm/dimm.c
create mode 100644 drivers/nvdimm/dimm_devs.c
create mode 100644 drivers/nvdimm/label.c
create mode 100644 drivers/nvdimm/label.h
create mode 100644 drivers/nvdimm/namespace_devs.c
create mode 100644 drivers/nvdimm/nd-core.h
create mode 100644 drivers/nvdimm/nd.h
rename drivers/{block/pmem.c => nvdimm/pmem.c} (69%)
create mode 100644 drivers/nvdimm/region.c
create mode 100644 drivers/nvdimm/region_devs.c
create mode 100644 include/linux/libnvdimm.h
create mode 100644 include/linux/nd.h
create mode 100644 include/uapi/linux/ndctl.h
create mode 100644 tools/testing/nvdimm/Kbuild
create mode 100644 tools/testing/nvdimm/Makefile
create mode 100644 tools/testing/nvdimm/test/Kbuild
create mode 100644 tools/testing/nvdimm/test/iomap.c
create mode 100644 tools/testing/nvdimm/test/nfit.c
create mode 100644 tools/testing/nvdimm/test/nfit_test.h
^ permalink raw reply
* [PATCH v6 01/21] e820, efi: add ACPI 6.0 persistent memory types
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw
Cc: mingo-DgEjT+Ai2ygdnm+yROfE0A, Boaz Harrosh,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b, sfr-3FnU+UHB4dNDw9hX6IcOSA,
neilb-l3A5Bk7waGM, gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r,
rafael-DgEjT+Ai2ygdnm+yROfE0A,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, hch-jcswGhMUV9g, Jens Axboe,
linux-acpi-u79uwXL29TY76Z2rM5mHXA, jmoyer-H+wXaHxf7aLQT0dZR+AlfA,
Borislav Petkov, axboe-tSWWG44O7X1aa/9Udqfwiw, H. Peter Anvin,
Matthew Wilcox, Thomas Gleixner, Andy Lutomirski, Linus Torvalds,
Ross Zwisler
In-Reply-To: <20150611183830.25175.51256.stgit-p8uTFz9XbKj2zm6wflaqv1nYeNYlB/vhral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
ACPI 6.0 formalizes e820-type-7 and efi-type-14 as persistent memory.
Mark it "reserved" and allow it to be claimed by a persistent memory
device driver.
This definition is in addition to the Linux kernel's existing type-12
definition that was recently added in support of shipping platforms with
NVDIMM support that predate ACPI 6.0 (which now classifies type-12 as
OEM reserved).
Note, /proc/iomem can be consulted for differentiating legacy
"Persistent Memory (legacy)" E820_PRAM vs standard "Persistent Memory"
E820_PMEM.
Cc: Boaz Harrosh <boaz-/8YdC2HfS5554TAoqtyWWQ@public.gmane.org>
Cc: Ingo Molnar <mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Cc: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: Borislav Petkov <bp-Gina5bIWoIWzQB+pC5nmwQ@public.gmane.org>
Cc: H. Peter Anvin <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>
Cc: Jens Axboe <axboe-b10kYP2dOMg@public.gmane.org>
Cc: Linus Torvalds <torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: Matthew Wilcox <willy-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
Cc: Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
Acked-by: Jeff Moyer <jmoyer-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Acked-by: Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org>
Reviewed-by: Ross Zwisler <ross.zwisler-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
Signed-off-by: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
arch/arm64/kernel/efi.c | 1 +
arch/ia64/kernel/efi.c | 4 ++++
arch/x86/boot/compressed/eboot.c | 4 ++++
arch/x86/include/uapi/asm/e820.h | 1 +
arch/x86/kernel/e820.c | 28 ++++++++++++++++++++++++----
arch/x86/platform/efi/efi.c | 3 +++
include/linux/efi.h | 3 ++-
7 files changed, 39 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index ab21e0d58278..9d4aa18f2a82 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -158,6 +158,7 @@ static __init int is_reserve_region(efi_memory_desc_t *md)
case EFI_BOOT_SERVICES_CODE:
case EFI_BOOT_SERVICES_DATA:
case EFI_CONVENTIONAL_MEMORY:
+ case EFI_PERSISTENT_MEMORY:
return 0;
default:
break;
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c52d7540dc05..5f6be9dd6968 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -1223,6 +1223,10 @@ efi_initialize_iomem_resources(struct resource *code_resource,
flags |= IORESOURCE_DISABLED;
break;
+ case EFI_PERSISTENT_MEMORY:
+ name = "Persistent Memory";
+ break;
+
case EFI_RESERVED_TYPE:
case EFI_RUNTIME_SERVICES_CODE:
case EFI_RUNTIME_SERVICES_DATA:
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 48304b89b601..2c82bd150d43 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1224,6 +1224,10 @@ static efi_status_t setup_e820(struct boot_params *params,
e820_type = E820_NVS;
break;
+ case EFI_PERSISTENT_MEMORY:
+ e820_type = E820_PMEM;
+ break;
+
default:
continue;
}
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index 960a8a9dc4ab..0f457e6eab18 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -32,6 +32,7 @@
#define E820_ACPI 3
#define E820_NVS 4
#define E820_UNUSABLE 5
+#define E820_PMEM 7
/*
* This is a non-standardized way to represent ADR or NVDIMM regions that
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index e2ce85db2283..c857d53269dd 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type)
case E820_UNUSABLE:
printk(KERN_CONT "unusable");
break;
+ case E820_PMEM:
case E820_PRAM:
printk(KERN_CONT "persistent (type %u)", type);
break;
@@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type)
case E820_ACPI: return "ACPI Tables";
case E820_NVS: return "ACPI Non-volatile Storage";
case E820_UNUSABLE: return "Unusable memory";
- case E820_PRAM: return "Persistent RAM";
+ case E820_PRAM: return "Persistent Memory (legacy)";
+ case E820_PMEM: return "Persistent Memory";
default: return "reserved";
}
}
+static bool do_mark_busy(u32 type, struct resource *res)
+{
+ /* this is the legacy bios/dos rom-shadow + mmio region */
+ if (res->start < (1ULL<<20))
+ return true;
+
+ /*
+ * Treat persistent memory like device memory, i.e. reserve it
+ * for exclusive use of a driver
+ */
+ switch (type) {
+ case E820_RESERVED:
+ case E820_PRAM:
+ case E820_PMEM:
+ return false;
+ default:
+ return true;
+ }
+}
+
/*
* Mark e820 reserved areas as busy for the resource manager.
*/
@@ -952,9 +974,7 @@ void __init e820_reserve_resources(void)
* pci device BAR resource and insert them later in
* pcibios_resource_survey()
*/
- if (((e820.map[i].type != E820_RESERVED) &&
- (e820.map[i].type != E820_PRAM)) ||
- res->start < (1ULL<<20)) {
+ if (do_mark_busy(e820.map[i].type, res)) {
res->flags |= IORESOURCE_BUSY;
insert_resource(&iomem_resource, res);
}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 02744df576d5..fe01ae37a2a4 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -153,6 +153,9 @@ static void __init do_add_efi_memmap(void)
case EFI_UNUSABLE_MEMORY:
e820_type = E820_UNUSABLE;
break;
+ case EFI_PERSISTENT_MEMORY:
+ e820_type = E820_PMEM;
+ break;
default:
/*
* EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE
diff --git a/include/linux/efi.h b/include/linux/efi.h
index af5be0368dec..825b6e3d69cb 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -85,7 +85,8 @@ typedef struct {
#define EFI_MEMORY_MAPPED_IO 11
#define EFI_MEMORY_MAPPED_IO_PORT_SPACE 12
#define EFI_PAL_CODE 13
-#define EFI_MAX_MEMORY_TYPE 14
+#define EFI_PERSISTENT_MEMORY 14
+#define EFI_MAX_MEMORY_TYPE 15
/* Attribute values: */
#define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */
^ permalink raw reply related
* [PATCH v6 02/21] libnvdimm, nfit: initial libnvdimm infrastructure and NFIT support
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw
Cc: mingo-DgEjT+Ai2ygdnm+yROfE0A, sfr-3FnU+UHB4dNDw9hX6IcOSA,
rafael-DgEjT+Ai2ygdnm+yROfE0A, neilb-l3A5Bk7waGM,
gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r, Rafael J. Wysocki,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Robert Moore,
linux-acpi-u79uwXL29TY76Z2rM5mHXA, jmoyer-H+wXaHxf7aLQT0dZR+AlfA,
Lv Zheng, linux-api-u79uwXL29TY76Z2rM5mHXA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
axboe-tSWWG44O7X1aa/9Udqfwiw, hch-jcswGhMUV9g
In-Reply-To: <20150611183830.25175.51256.stgit-p8uTFz9XbKj2zm6wflaqv1nYeNYlB/vhral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
A struct nvdimm_bus is the anchor device for registering nvdimm
resources and interfaces, for example, a character control device,
nvdimm devices, and I/O region devices. The ACPI NFIT (NVDIMM Firmware
Interface Table) is one possible platform description for such
non-volatile memory resources in a system. The nfit.ko driver attaches
to the "ACPI0012" device that indicates the presence of the NFIT and
parses the table to register a struct nvdimm_bus instance.
Cc: <linux-acpi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Cc: Lv Zheng <lv.zheng-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: Robert Moore <robert.moore-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Acked-by: Jeff Moyer <jmoyer-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Signed-off-by: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/Kconfig | 2
drivers/Makefile | 1
drivers/acpi/Kconfig | 14 +
drivers/acpi/Makefile | 1
drivers/acpi/nfit.c | 482 +++++++++++++++++++++++++++++++++++++++++++++
drivers/acpi/nfit.h | 90 ++++++++
drivers/nvdimm/Kconfig | 15 +
drivers/nvdimm/Makefile | 3
drivers/nvdimm/core.c | 69 ++++++
drivers/nvdimm/nd-core.h | 23 ++
include/linux/libnvdimm.h | 34 +++
11 files changed, 734 insertions(+)
create mode 100644 drivers/acpi/nfit.c
create mode 100644 drivers/acpi/nfit.h
create mode 100644 drivers/nvdimm/Kconfig
create mode 100644 drivers/nvdimm/Makefile
create mode 100644 drivers/nvdimm/core.c
create mode 100644 drivers/nvdimm/nd-core.h
create mode 100644 include/linux/libnvdimm.h
diff --git a/drivers/Kconfig b/drivers/Kconfig
index c0cc96bab9e7..6e973b8e3a3b 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -182,4 +182,6 @@ source "drivers/thunderbolt/Kconfig"
source "drivers/android/Kconfig"
+source "drivers/nvdimm/Kconfig"
+
endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 46d2554be404..692adf659028 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -64,6 +64,7 @@ obj-$(CONFIG_FB_INTEL) += video/fbdev/intelfb/
obj-$(CONFIG_PARPORT) += parport/
obj-y += base/ block/ misc/ mfd/ nfc/
+obj-$(CONFIG_LIBNVDIMM) += nvdimm/
obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
obj-$(CONFIG_NUBUS) += nubus/
obj-y += macintosh/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ab2cbb51c6aa..300b4ef3712b 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -383,6 +383,20 @@ config ACPI_REDUCED_HARDWARE_ONLY
If you are unsure what to do, do not enable this option.
+config ACPI_NFIT
+ tristate "ACPI NVDIMM Firmware Interface Table (NFIT)"
+ depends on PHYS_ADDR_T_64BIT
+ depends on BLK_DEV
+ select LIBNVDIMM
+ help
+ Infrastructure to probe ACPI 6 compliant platforms for
+ NVDIMMs (NFIT) and register a libnvdimm device tree. In
+ addition to storage devices this also enables libnvdimm to pass
+ ACPI._DSM messages for platform/dimm configuration.
+
+ To compile this driver as a module, choose M here:
+ the module will be called nfit.
+
source "drivers/acpi/apei/Kconfig"
config ACPI_EXTLOG
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 8a063e276530..f7e9c92ccdcb 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -71,6 +71,7 @@ obj-$(CONFIG_ACPI_PCI_SLOT) += pci_slot.o
obj-$(CONFIG_ACPI_PROCESSOR) += processor.o
obj-y += container.o
obj-$(CONFIG_ACPI_THERMAL) += thermal.o
+obj-$(CONFIG_ACPI_NFIT) += nfit.o
obj-y += acpi_memhotplug.o
obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
obj-$(CONFIG_ACPI_BATTERY) += battery.o
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
new file mode 100644
index 000000000000..0cacf36fa306
--- /dev/null
+++ b/drivers/acpi/nfit.c
@@ -0,0 +1,482 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/list_sort.h>
+#include <linux/libnvdimm.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/acpi.h>
+#include "nfit.h"
+
+static u8 nfit_uuid[NFIT_UUID_MAX][16];
+
+static const u8 *to_nfit_uuid(enum nfit_uuids id)
+{
+ return nfit_uuid[id];
+}
+
+static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
+ struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+ unsigned int buf_len)
+{
+ return -ENOTTY;
+}
+
+static const char *spa_type_name(u16 type)
+{
+ static const char *to_name[] = {
+ [NFIT_SPA_VOLATILE] = "volatile",
+ [NFIT_SPA_PM] = "pmem",
+ [NFIT_SPA_DCR] = "dimm-control-region",
+ [NFIT_SPA_BDW] = "block-data-window",
+ [NFIT_SPA_VDISK] = "volatile-disk",
+ [NFIT_SPA_VCD] = "volatile-cd",
+ [NFIT_SPA_PDISK] = "persistent-disk",
+ [NFIT_SPA_PCD] = "persistent-cd",
+
+ };
+
+ if (type > NFIT_SPA_PCD)
+ return "unknown";
+
+ return to_name[type];
+}
+
+static int nfit_spa_type(struct acpi_nfit_system_address *spa)
+{
+ int i;
+
+ for (i = 0; i < NFIT_UUID_MAX; i++)
+ if (memcmp(to_nfit_uuid(i), spa->range_guid, 16) == 0)
+ return i;
+ return -1;
+}
+
+static bool add_spa(struct acpi_nfit_desc *acpi_desc,
+ struct acpi_nfit_system_address *spa)
+{
+ struct device *dev = acpi_desc->dev;
+ struct nfit_spa *nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa),
+ GFP_KERNEL);
+
+ if (!nfit_spa)
+ return false;
+ INIT_LIST_HEAD(&nfit_spa->list);
+ nfit_spa->spa = spa;
+ list_add_tail(&nfit_spa->list, &acpi_desc->spas);
+ dev_dbg(dev, "%s: spa index: %d type: %s\n", __func__,
+ spa->range_index,
+ spa_type_name(nfit_spa_type(spa)));
+ return true;
+}
+
+static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
+ struct acpi_nfit_memory_map *memdev)
+{
+ struct device *dev = acpi_desc->dev;
+ struct nfit_memdev *nfit_memdev = devm_kzalloc(dev,
+ sizeof(*nfit_memdev), GFP_KERNEL);
+
+ if (!nfit_memdev)
+ return false;
+ INIT_LIST_HEAD(&nfit_memdev->list);
+ nfit_memdev->memdev = memdev;
+ list_add_tail(&nfit_memdev->list, &acpi_desc->memdevs);
+ dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d\n",
+ __func__, memdev->device_handle, memdev->range_index,
+ memdev->region_index);
+ return true;
+}
+
+static bool add_dcr(struct acpi_nfit_desc *acpi_desc,
+ struct acpi_nfit_control_region *dcr)
+{
+ struct device *dev = acpi_desc->dev;
+ struct nfit_dcr *nfit_dcr = devm_kzalloc(dev, sizeof(*nfit_dcr),
+ GFP_KERNEL);
+
+ if (!nfit_dcr)
+ return false;
+ INIT_LIST_HEAD(&nfit_dcr->list);
+ nfit_dcr->dcr = dcr;
+ list_add_tail(&nfit_dcr->list, &acpi_desc->dcrs);
+ dev_dbg(dev, "%s: dcr index: %d windows: %d\n", __func__,
+ dcr->region_index, dcr->windows);
+ return true;
+}
+
+static bool add_bdw(struct acpi_nfit_desc *acpi_desc,
+ struct acpi_nfit_data_region *bdw)
+{
+ struct device *dev = acpi_desc->dev;
+ struct nfit_bdw *nfit_bdw = devm_kzalloc(dev, sizeof(*nfit_bdw),
+ GFP_KERNEL);
+
+ if (!nfit_bdw)
+ return false;
+ INIT_LIST_HEAD(&nfit_bdw->list);
+ nfit_bdw->bdw = bdw;
+ list_add_tail(&nfit_bdw->list, &acpi_desc->bdws);
+ dev_dbg(dev, "%s: bdw dcr: %d windows: %d\n", __func__,
+ bdw->region_index, bdw->windows);
+ return true;
+}
+
+static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table,
+ const void *end)
+{
+ struct device *dev = acpi_desc->dev;
+ struct acpi_nfit_header *hdr;
+ void *err = ERR_PTR(-ENOMEM);
+
+ if (table >= end)
+ return NULL;
+
+ hdr = table;
+ switch (hdr->type) {
+ case ACPI_NFIT_TYPE_SYSTEM_ADDRESS:
+ if (!add_spa(acpi_desc, table))
+ return err;
+ break;
+ case ACPI_NFIT_TYPE_MEMORY_MAP:
+ if (!add_memdev(acpi_desc, table))
+ return err;
+ break;
+ case ACPI_NFIT_TYPE_CONTROL_REGION:
+ if (!add_dcr(acpi_desc, table))
+ return err;
+ break;
+ case ACPI_NFIT_TYPE_DATA_REGION:
+ if (!add_bdw(acpi_desc, table))
+ return err;
+ break;
+ /* TODO */
+ case ACPI_NFIT_TYPE_INTERLEAVE:
+ dev_dbg(dev, "%s: idt\n", __func__);
+ break;
+ case ACPI_NFIT_TYPE_FLUSH_ADDRESS:
+ dev_dbg(dev, "%s: flush\n", __func__);
+ break;
+ case ACPI_NFIT_TYPE_SMBIOS:
+ dev_dbg(dev, "%s: smbios\n", __func__);
+ break;
+ default:
+ dev_err(dev, "unknown table '%d' parsing nfit\n", hdr->type);
+ break;
+ }
+
+ return table + hdr->length;
+}
+
+static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc,
+ struct nfit_mem *nfit_mem)
+{
+ u32 device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
+ u16 dcr = nfit_mem->dcr->region_index;
+ struct nfit_spa *nfit_spa;
+
+ list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
+ u16 range_index = nfit_spa->spa->range_index;
+ int type = nfit_spa_type(nfit_spa->spa);
+ struct nfit_memdev *nfit_memdev;
+
+ if (type != NFIT_SPA_BDW)
+ continue;
+
+ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
+ if (nfit_memdev->memdev->range_index != range_index)
+ continue;
+ if (nfit_memdev->memdev->device_handle != device_handle)
+ continue;
+ if (nfit_memdev->memdev->region_index != dcr)
+ continue;
+
+ nfit_mem->spa_bdw = nfit_spa->spa;
+ return;
+ }
+ }
+
+ dev_dbg(acpi_desc->dev, "SPA-BDW not found for SPA-DCR %d\n",
+ nfit_mem->spa_dcr->range_index);
+ nfit_mem->bdw = NULL;
+}
+
+static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
+ struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa)
+{
+ u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
+ struct nfit_dcr *nfit_dcr;
+ struct nfit_bdw *nfit_bdw;
+
+ list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
+ if (nfit_dcr->dcr->region_index != dcr)
+ continue;
+ nfit_mem->dcr = nfit_dcr->dcr;
+ break;
+ }
+
+ if (!nfit_mem->dcr) {
+ dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n",
+ spa->range_index, __to_nfit_memdev(nfit_mem)
+ ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR");
+ return -ENODEV;
+ }
+
+ /*
+ * We've found enough to create an nvdimm, optionally
+ * find an associated BDW
+ */
+ list_add(&nfit_mem->list, &acpi_desc->dimms);
+
+ list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) {
+ if (nfit_bdw->bdw->region_index != dcr)
+ continue;
+ nfit_mem->bdw = nfit_bdw->bdw;
+ break;
+ }
+
+ if (!nfit_mem->bdw)
+ return 0;
+
+ nfit_mem_find_spa_bdw(acpi_desc, nfit_mem);
+ return 0;
+}
+
+static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
+ struct acpi_nfit_system_address *spa)
+{
+ struct nfit_mem *nfit_mem, *found;
+ struct nfit_memdev *nfit_memdev;
+ int type = nfit_spa_type(spa);
+ u16 dcr;
+
+ switch (type) {
+ case NFIT_SPA_DCR:
+ case NFIT_SPA_PM:
+ break;
+ default:
+ return 0;
+ }
+
+ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
+ int rc;
+
+ if (nfit_memdev->memdev->range_index != spa->range_index)
+ continue;
+ found = NULL;
+ dcr = nfit_memdev->memdev->region_index;
+ list_for_each_entry(nfit_mem, &acpi_desc->dimms, list)
+ if (__to_nfit_memdev(nfit_mem)->region_index == dcr) {
+ found = nfit_mem;
+ break;
+ }
+
+ if (found)
+ nfit_mem = found;
+ else {
+ nfit_mem = devm_kzalloc(acpi_desc->dev,
+ sizeof(*nfit_mem), GFP_KERNEL);
+ if (!nfit_mem)
+ return -ENOMEM;
+ INIT_LIST_HEAD(&nfit_mem->list);
+ }
+
+ if (type == NFIT_SPA_DCR) {
+ /* multiple dimms may share a SPA when interleaved */
+ nfit_mem->spa_dcr = spa;
+ nfit_mem->memdev_dcr = nfit_memdev->memdev;
+ } else {
+ /*
+ * A single dimm may belong to multiple SPA-PM
+ * ranges, record at least one in addition to
+ * any SPA-DCR range.
+ */
+ nfit_mem->memdev_pmem = nfit_memdev->memdev;
+ }
+
+ if (found)
+ continue;
+
+ rc = nfit_mem_add(acpi_desc, nfit_mem, spa);
+ if (rc)
+ return rc;
+ }
+
+ return 0;
+}
+
+static int nfit_mem_cmp(void *priv, struct list_head *_a, struct list_head *_b)
+{
+ struct nfit_mem *a = container_of(_a, typeof(*a), list);
+ struct nfit_mem *b = container_of(_b, typeof(*b), list);
+ u32 handleA, handleB;
+
+ handleA = __to_nfit_memdev(a)->device_handle;
+ handleB = __to_nfit_memdev(b)->device_handle;
+ if (handleA < handleB)
+ return -1;
+ else if (handleA > handleB)
+ return 1;
+ return 0;
+}
+
+static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc)
+{
+ struct nfit_spa *nfit_spa;
+
+ /*
+ * For each SPA-DCR or SPA-PMEM address range find its
+ * corresponding MEMDEV(s). From each MEMDEV find the
+ * corresponding DCR. Then, if we're operating on a SPA-DCR,
+ * try to find a SPA-BDW and a corresponding BDW that references
+ * the DCR. Throw it all into an nfit_mem object. Note, that
+ * BDWs are optional.
+ */
+ list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
+ int rc;
+
+ rc = nfit_mem_dcr_init(acpi_desc, nfit_spa->spa);
+ if (rc)
+ return rc;
+ }
+
+ list_sort(NULL, &acpi_desc->dimms, nfit_mem_cmp);
+
+ return 0;
+}
+
+static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
+{
+ struct device *dev = acpi_desc->dev;
+ const void *end;
+ u8 *data;
+
+ INIT_LIST_HEAD(&acpi_desc->spas);
+ INIT_LIST_HEAD(&acpi_desc->dcrs);
+ INIT_LIST_HEAD(&acpi_desc->bdws);
+ INIT_LIST_HEAD(&acpi_desc->memdevs);
+ INIT_LIST_HEAD(&acpi_desc->dimms);
+
+ data = (u8 *) acpi_desc->nfit;
+ end = data + sz;
+ data += sizeof(struct acpi_table_nfit);
+ while (!IS_ERR_OR_NULL(data))
+ data = add_table(acpi_desc, data, end);
+
+ if (IS_ERR(data)) {
+ dev_dbg(dev, "%s: nfit table parsing error: %ld\n", __func__,
+ PTR_ERR(data));
+ return PTR_ERR(data);
+ }
+
+ if (nfit_mem_init(acpi_desc) != 0)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int acpi_nfit_add(struct acpi_device *adev)
+{
+ struct nvdimm_bus_descriptor *nd_desc;
+ struct acpi_nfit_desc *acpi_desc;
+ struct device *dev = &adev->dev;
+ struct acpi_table_header *tbl;
+ acpi_status status = AE_OK;
+ acpi_size sz;
+ int rc;
+
+ status = acpi_get_table_with_size("NFIT", 0, &tbl, &sz);
+ if (ACPI_FAILURE(status)) {
+ dev_err(dev, "failed to find NFIT\n");
+ return -ENXIO;
+ }
+
+ acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
+ if (!acpi_desc)
+ return -ENOMEM;
+
+ dev_set_drvdata(dev, acpi_desc);
+ acpi_desc->dev = dev;
+ acpi_desc->nfit = (struct acpi_table_nfit *) tbl;
+ nd_desc = &acpi_desc->nd_desc;
+ nd_desc->provider_name = "ACPI.NFIT";
+ nd_desc->ndctl = acpi_nfit_ctl;
+
+ acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, nd_desc);
+ if (!acpi_desc->nvdimm_bus)
+ return -ENXIO;
+
+ rc = acpi_nfit_init(acpi_desc, sz);
+ if (rc) {
+ nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
+ return rc;
+ }
+ return 0;
+}
+
+static int acpi_nfit_remove(struct acpi_device *adev)
+{
+ struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
+
+ nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
+ return 0;
+}
+
+static const struct acpi_device_id acpi_nfit_ids[] = {
+ { "ACPI0012", 0 },
+ { "", 0 },
+};
+MODULE_DEVICE_TABLE(acpi, acpi_nfit_ids);
+
+static struct acpi_driver acpi_nfit_driver = {
+ .name = KBUILD_MODNAME,
+ .ids = acpi_nfit_ids,
+ .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS,
+ .ops = {
+ .add = acpi_nfit_add,
+ .remove = acpi_nfit_remove,
+ },
+};
+
+static __init int nfit_init(void)
+{
+ BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40);
+ BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56);
+ BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48);
+ BUILD_BUG_ON(sizeof(struct acpi_nfit_interleave) != 20);
+ BUILD_BUG_ON(sizeof(struct acpi_nfit_smbios) != 9);
+ BUILD_BUG_ON(sizeof(struct acpi_nfit_control_region) != 80);
+ BUILD_BUG_ON(sizeof(struct acpi_nfit_data_region) != 40);
+
+ acpi_str_to_uuid(UUID_VOLATILE_MEMORY, nfit_uuid[NFIT_SPA_VOLATILE]);
+ acpi_str_to_uuid(UUID_PERSISTENT_MEMORY, nfit_uuid[NFIT_SPA_PM]);
+ acpi_str_to_uuid(UUID_CONTROL_REGION, nfit_uuid[NFIT_SPA_DCR]);
+ acpi_str_to_uuid(UUID_DATA_REGION, nfit_uuid[NFIT_SPA_BDW]);
+ acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_VDISK]);
+ acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_CD, nfit_uuid[NFIT_SPA_VCD]);
+ acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_PDISK]);
+ acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_CD, nfit_uuid[NFIT_SPA_PCD]);
+ acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]);
+ acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]);
+
+ return acpi_bus_register_driver(&acpi_nfit_driver);
+}
+
+static __exit void nfit_exit(void)
+{
+ acpi_bus_unregister_driver(&acpi_nfit_driver);
+}
+
+module_init(nfit_init);
+module_exit(nfit_exit);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
new file mode 100644
index 000000000000..c6baba64703f
--- /dev/null
+++ b/drivers/acpi/nfit.h
@@ -0,0 +1,90 @@
+/*
+ * NVDIMM Firmware Interface Table - NFIT
+ *
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef __NFIT_H__
+#define __NFIT_H__
+#include <linux/libnvdimm.h>
+#include <linux/types.h>
+#include <linux/uuid.h>
+#include <linux/acpi.h>
+#include <acpi/acuuid.h>
+
+#define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba"
+#define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66"
+
+enum nfit_uuids {
+ NFIT_SPA_VOLATILE,
+ NFIT_SPA_PM,
+ NFIT_SPA_DCR,
+ NFIT_SPA_BDW,
+ NFIT_SPA_VDISK,
+ NFIT_SPA_VCD,
+ NFIT_SPA_PDISK,
+ NFIT_SPA_PCD,
+ NFIT_DEV_BUS,
+ NFIT_DEV_DIMM,
+ NFIT_UUID_MAX,
+};
+
+struct nfit_spa {
+ struct acpi_nfit_system_address *spa;
+ struct list_head list;
+};
+
+struct nfit_dcr {
+ struct acpi_nfit_control_region *dcr;
+ struct list_head list;
+};
+
+struct nfit_bdw {
+ struct acpi_nfit_data_region *bdw;
+ struct list_head list;
+};
+
+struct nfit_memdev {
+ struct acpi_nfit_memory_map *memdev;
+ struct list_head list;
+};
+
+/* assembled tables for a given dimm/memory-device */
+struct nfit_mem {
+ struct acpi_nfit_memory_map *memdev_dcr;
+ struct acpi_nfit_memory_map *memdev_pmem;
+ struct acpi_nfit_control_region *dcr;
+ struct acpi_nfit_data_region *bdw;
+ struct acpi_nfit_system_address *spa_dcr;
+ struct acpi_nfit_system_address *spa_bdw;
+ struct list_head list;
+};
+
+struct acpi_nfit_desc {
+ struct nvdimm_bus_descriptor nd_desc;
+ struct acpi_table_nfit *nfit;
+ struct list_head memdevs;
+ struct list_head dimms;
+ struct list_head spas;
+ struct list_head dcrs;
+ struct list_head bdws;
+ struct nvdimm_bus *nvdimm_bus;
+ struct device *dev;
+};
+
+static inline struct acpi_nfit_memory_map *__to_nfit_memdev(
+ struct nfit_mem *nfit_mem)
+{
+ if (nfit_mem->memdev_dcr)
+ return nfit_mem->memdev_dcr;
+ return nfit_mem->memdev_pmem;
+}
+#endif /* __NFIT_H__ */
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
new file mode 100644
index 000000000000..92933551f846
--- /dev/null
+++ b/drivers/nvdimm/Kconfig
@@ -0,0 +1,15 @@
+config LIBNVDIMM
+ tristate "NVDIMM (Non-Volatile Memory Device) Support"
+ depends on PHYS_ADDR_T_64BIT
+ depends on BLK_DEV
+ help
+ Generic support for non-volatile memory devices including
+ ACPI-6-NFIT defined resources. On platforms that define an
+ NFIT, or otherwise can discover NVDIMM resources, a libnvdimm
+ bus is registered to advertise PMEM (persistent memory)
+ namespaces (/dev/pmemX) and BLK (sliding mmio window(s))
+ namespaces (/dev/ndX). A PMEM namespace refers to a memory
+ resource that may span multiple DIMMs and support DAX (see
+ CONFIG_DAX). A BLK namespace refers to an NVDIMM control
+ region which exposes an mmio register set for windowed
+ access mode to non-volatile memory.
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
new file mode 100644
index 000000000000..10bc7af47992
--- /dev/null
+++ b/drivers/nvdimm/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
+
+libnvdimm-y := core.o
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
new file mode 100644
index 000000000000..c578a49867ac
--- /dev/null
+++ b/drivers/nvdimm/core.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/libnvdimm.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include "nd-core.h"
+
+static DEFINE_IDA(nd_ida);
+
+static void nvdimm_bus_release(struct device *dev)
+{
+ struct nvdimm_bus *nvdimm_bus;
+
+ nvdimm_bus = container_of(dev, struct nvdimm_bus, dev);
+ ida_simple_remove(&nd_ida, nvdimm_bus->id);
+ kfree(nvdimm_bus);
+}
+
+struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
+ struct nvdimm_bus_descriptor *nd_desc)
+{
+ struct nvdimm_bus *nvdimm_bus;
+ int rc;
+
+ nvdimm_bus = kzalloc(sizeof(*nvdimm_bus), GFP_KERNEL);
+ if (!nvdimm_bus)
+ return NULL;
+ nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
+ if (nvdimm_bus->id < 0) {
+ kfree(nvdimm_bus);
+ return NULL;
+ }
+ nvdimm_bus->nd_desc = nd_desc;
+ nvdimm_bus->dev.parent = parent;
+ nvdimm_bus->dev.release = nvdimm_bus_release;
+ dev_set_name(&nvdimm_bus->dev, "ndbus%d", nvdimm_bus->id);
+ rc = device_register(&nvdimm_bus->dev);
+ if (rc) {
+ dev_dbg(&nvdimm_bus->dev, "registration failed: %d\n", rc);
+ put_device(&nvdimm_bus->dev);
+ return NULL;
+ }
+
+ return nvdimm_bus;
+}
+EXPORT_SYMBOL_GPL(nvdimm_bus_register);
+
+void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
+{
+ if (!nvdimm_bus)
+ return;
+ device_unregister(&nvdimm_bus->dev);
+}
+EXPORT_SYMBOL_GPL(nvdimm_bus_unregister);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
new file mode 100644
index 000000000000..291b2fdcd96b
--- /dev/null
+++ b/drivers/nvdimm/nd-core.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef __ND_CORE_H__
+#define __ND_CORE_H__
+#include <linux/libnvdimm.h>
+#include <linux/device.h>
+
+struct nvdimm_bus {
+ struct nvdimm_bus_descriptor *nd_desc;
+ struct device dev;
+ int id;
+};
+#endif /* __ND_CORE_H__ */
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
new file mode 100644
index 000000000000..2b3c63950c91
--- /dev/null
+++ b/include/linux/libnvdimm.h
@@ -0,0 +1,34 @@
+/*
+ * libnvdimm - Non-volatile-memory Devices Subsystem
+ *
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef __LIBNVDIMM_H__
+#define __LIBNVDIMM_H__
+struct nvdimm;
+struct nvdimm_bus_descriptor;
+typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
+ struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+ unsigned int buf_len);
+
+struct nvdimm_bus_descriptor {
+ unsigned long dsm_mask;
+ char *provider_name;
+ ndctl_fn ndctl;
+};
+
+struct device;
+struct nvdimm_bus;
+struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
+ struct nvdimm_bus_descriptor *nfit_desc);
+void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
+#endif /* __LIBNVDIMM_H__ */
^ permalink raw reply related
* [PATCH v6 03/21] libnvdimm: control character device and nvdimm_bus sysfs attributes
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw
Cc: mingo-DgEjT+Ai2ygdnm+yROfE0A, sfr-3FnU+UHB4dNDw9hX6IcOSA,
rafael-DgEjT+Ai2ygdnm+yROfE0A, neilb-l3A5Bk7waGM,
gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r, Rafael J. Wysocki,
Robert Moore, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-acpi-u79uwXL29TY76Z2rM5mHXA, jmoyer-H+wXaHxf7aLQT0dZR+AlfA,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-api-u79uwXL29TY76Z2rM5mHXA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b, hch-jcswGhMUV9g
In-Reply-To: <20150611183830.25175.51256.stgit-p8uTFz9XbKj2zm6wflaqv1nYeNYlB/vhral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
The control device for a nvdimm_bus is registered as an "nd" class
device. The expectation is that there will usually only be one "nd" bus
registered under /sys/class/nd. However, we allow for the possibility
of multiple buses and they will listed in discovery order as
ndctl0...ndctlN. This character device hosts the ioctl for passing
control messages. The initial command set has a 1:1 correlation with
the commands listed in the by the "NFIT DSM Example" document [1], but
this scheme is extensible to future command sets.
Note, nd_ioctl() and the backing ->ndctl() implementation are defined in
a subsequent patch. This is simply the initial registrations and sysfs
attributes.
[1]: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf
Cc: Neil Brown <neilb-l3A5Bk7waGM@public.gmane.org>
Cc: Greg KH <gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r@public.gmane.org>
Cc: <linux-acpi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Cc: Robert Moore <robert.moore-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/acpi/nfit.c | 28 ++++++++++++++
drivers/acpi/nfit.h | 6 +++
drivers/nvdimm/Makefile | 1 +
drivers/nvdimm/bus.c | 83 ++++++++++++++++++++++++++++++++++++++++++
drivers/nvdimm/core.c | 88 ++++++++++++++++++++++++++++++++++++++++++++-
drivers/nvdimm/nd-core.h | 6 +++
include/linux/libnvdimm.h | 6 +++
7 files changed, 215 insertions(+), 3 deletions(-)
create mode 100644 drivers/nvdimm/bus.c
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 0cacf36fa306..fe9d79404fe5 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -354,6 +354,33 @@ static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc)
return 0;
}
+static ssize_t revision_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+ struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+ struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+ return sprintf(buf, "%d\n", acpi_desc->nfit->header.revision);
+}
+static DEVICE_ATTR_RO(revision);
+
+static struct attribute *acpi_nfit_attributes[] = {
+ &dev_attr_revision.attr,
+ NULL,
+};
+
+static struct attribute_group acpi_nfit_attribute_group = {
+ .name = "nfit",
+ .attrs = acpi_nfit_attributes,
+};
+
+static const struct attribute_group *acpi_nfit_attribute_groups[] = {
+ &nvdimm_bus_attribute_group,
+ &acpi_nfit_attribute_group,
+ NULL,
+};
+
static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
{
struct device *dev = acpi_desc->dev;
@@ -410,6 +437,7 @@ static int acpi_nfit_add(struct acpi_device *adev)
nd_desc = &acpi_desc->nd_desc;
nd_desc->provider_name = "ACPI.NFIT";
nd_desc->ndctl = acpi_nfit_ctl;
+ nd_desc->attr_groups = acpi_nfit_attribute_groups;
acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, nd_desc);
if (!acpi_desc->nvdimm_bus)
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index c6baba64703f..eda565fa81ef 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -87,4 +87,10 @@ static inline struct acpi_nfit_memory_map *__to_nfit_memdev(
return nfit_mem->memdev_dcr;
return nfit_mem->memdev_pmem;
}
+
+static inline struct acpi_nfit_desc *to_acpi_desc(
+ struct nvdimm_bus_descriptor *nd_desc)
+{
+ return container_of(nd_desc, struct acpi_nfit_desc, nd_desc);
+}
#endif /* __NFIT_H__ */
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 10bc7af47992..8a8293c72c7c 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -1,3 +1,4 @@
obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
libnvdimm-y := core.o
+libnvdimm-y += bus.o
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
new file mode 100644
index 000000000000..3f7c690a5d0c
--- /dev/null
+++ b/drivers/nvdimm/bus.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/uaccess.h>
+#include <linux/fcntl.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/io.h>
+#include "nd-core.h"
+
+static int nvdimm_bus_major;
+static struct class *nd_class;
+
+int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus)
+{
+ dev_t devt = MKDEV(nvdimm_bus_major, nvdimm_bus->id);
+ struct device *dev;
+
+ dev = device_create(nd_class, &nvdimm_bus->dev, devt, nvdimm_bus,
+ "ndctl%d", nvdimm_bus->id);
+
+ if (IS_ERR(dev)) {
+ dev_dbg(&nvdimm_bus->dev, "failed to register ndctl%d: %ld\n",
+ nvdimm_bus->id, PTR_ERR(dev));
+ return PTR_ERR(dev);
+ }
+ return 0;
+}
+
+void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus)
+{
+ device_destroy(nd_class, MKDEV(nvdimm_bus_major, nvdimm_bus->id));
+}
+
+static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return -ENXIO;
+}
+
+static const struct file_operations nvdimm_bus_fops = {
+ .owner = THIS_MODULE,
+ .open = nonseekable_open,
+ .unlocked_ioctl = nd_ioctl,
+ .compat_ioctl = nd_ioctl,
+ .llseek = noop_llseek,
+};
+
+int __init nvdimm_bus_init(void)
+{
+ int rc;
+
+ rc = register_chrdev(0, "ndctl", &nvdimm_bus_fops);
+ if (rc < 0)
+ return rc;
+ nvdimm_bus_major = rc;
+
+ nd_class = class_create(THIS_MODULE, "nd");
+ if (IS_ERR(nd_class))
+ goto err_class;
+
+ return 0;
+
+ err_class:
+ unregister_chrdev(nvdimm_bus_major, "ndctl");
+
+ return rc;
+}
+
+void __exit nvdimm_bus_exit(void)
+{
+ class_destroy(nd_class);
+ unregister_chrdev(nvdimm_bus_major, "ndctl");
+}
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index c578a49867ac..dcae823f681e 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -14,9 +14,12 @@
#include <linux/export.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/mutex.h>
#include <linux/slab.h>
#include "nd-core.h"
+static LIST_HEAD(nvdimm_bus_list);
+static DEFINE_MUTEX(nvdimm_bus_list_mutex);
static DEFINE_IDA(nd_ida);
static void nvdimm_bus_release(struct device *dev)
@@ -28,6 +31,55 @@ static void nvdimm_bus_release(struct device *dev)
kfree(nvdimm_bus);
}
+struct nvdimm_bus *to_nvdimm_bus(struct device *dev)
+{
+ struct nvdimm_bus *nvdimm_bus;
+
+ nvdimm_bus = container_of(dev, struct nvdimm_bus, dev);
+ WARN_ON(nvdimm_bus->dev.release != nvdimm_bus_release);
+ return nvdimm_bus;
+}
+EXPORT_SYMBOL_GPL(to_nvdimm_bus);
+
+struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus)
+{
+ /* struct nvdimm_bus definition is private to libnvdimm */
+ return nvdimm_bus->nd_desc;
+}
+EXPORT_SYMBOL_GPL(to_nd_desc);
+
+static const char *nvdimm_bus_provider(struct nvdimm_bus *nvdimm_bus)
+{
+ struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+ struct device *parent = nvdimm_bus->dev.parent;
+
+ if (nd_desc->provider_name)
+ return nd_desc->provider_name;
+ else if (parent)
+ return dev_name(parent);
+ else
+ return "unknown";
+}
+
+static ssize_t provider_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+
+ return sprintf(buf, "%s\n", nvdimm_bus_provider(nvdimm_bus));
+}
+static DEVICE_ATTR_RO(provider);
+
+static struct attribute *nvdimm_bus_attributes[] = {
+ &dev_attr_provider.attr,
+ NULL,
+};
+
+struct attribute_group nvdimm_bus_attribute_group = {
+ .attrs = nvdimm_bus_attributes,
+};
+EXPORT_SYMBOL_GPL(nvdimm_bus_attribute_group);
+
struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
struct nvdimm_bus_descriptor *nd_desc)
{
@@ -37,6 +89,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
nvdimm_bus = kzalloc(sizeof(*nvdimm_bus), GFP_KERNEL);
if (!nvdimm_bus)
return NULL;
+ INIT_LIST_HEAD(&nvdimm_bus->list);
nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
if (nvdimm_bus->id < 0) {
kfree(nvdimm_bus);
@@ -45,15 +98,26 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
nvdimm_bus->nd_desc = nd_desc;
nvdimm_bus->dev.parent = parent;
nvdimm_bus->dev.release = nvdimm_bus_release;
+ nvdimm_bus->dev.groups = nd_desc->attr_groups;
dev_set_name(&nvdimm_bus->dev, "ndbus%d", nvdimm_bus->id);
rc = device_register(&nvdimm_bus->dev);
if (rc) {
dev_dbg(&nvdimm_bus->dev, "registration failed: %d\n", rc);
- put_device(&nvdimm_bus->dev);
- return NULL;
+ goto err;
}
+ rc = nvdimm_bus_create_ndctl(nvdimm_bus);
+ if (rc)
+ goto err;
+
+ mutex_lock(&nvdimm_bus_list_mutex);
+ list_add_tail(&nvdimm_bus->list, &nvdimm_bus_list);
+ mutex_unlock(&nvdimm_bus_list_mutex);
+
return nvdimm_bus;
+ err:
+ put_device(&nvdimm_bus->dev);
+ return NULL;
}
EXPORT_SYMBOL_GPL(nvdimm_bus_register);
@@ -61,9 +125,29 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
{
if (!nvdimm_bus)
return;
+
+ mutex_lock(&nvdimm_bus_list_mutex);
+ list_del_init(&nvdimm_bus->list);
+ mutex_unlock(&nvdimm_bus_list_mutex);
+
+ nvdimm_bus_destroy_ndctl(nvdimm_bus);
+
device_unregister(&nvdimm_bus->dev);
}
EXPORT_SYMBOL_GPL(nvdimm_bus_unregister);
+static __init int libnvdimm_init(void)
+{
+ return nvdimm_bus_init();
+}
+
+static __exit void libnvdimm_exit(void)
+{
+ WARN_ON(!list_empty(&nvdimm_bus_list));
+ nvdimm_bus_exit();
+}
+
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Intel Corporation");
+module_init(libnvdimm_init);
+module_exit(libnvdimm_exit);
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 291b2fdcd96b..0b0ff2423161 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -17,7 +17,13 @@
struct nvdimm_bus {
struct nvdimm_bus_descriptor *nd_desc;
+ struct list_head list;
struct device dev;
int id;
};
+
+int __init nvdimm_bus_init(void);
+void __exit nvdimm_bus_exit(void);
+int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
+void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
#endif /* __ND_CORE_H__ */
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 2b3c63950c91..d375cdc4abd5 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -14,6 +14,8 @@
*/
#ifndef __LIBNVDIMM_H__
#define __LIBNVDIMM_H__
+extern struct attribute_group nvdimm_bus_attribute_group;
+
struct nvdimm;
struct nvdimm_bus_descriptor;
typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
@@ -21,14 +23,16 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
unsigned int buf_len);
struct nvdimm_bus_descriptor {
+ const struct attribute_group **attr_groups;
unsigned long dsm_mask;
char *provider_name;
ndctl_fn ndctl;
};
struct device;
-struct nvdimm_bus;
struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
struct nvdimm_bus_descriptor *nfit_desc);
void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
+struct nvdimm_bus *to_nvdimm_bus(struct device *dev);
+struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
#endif /* __LIBNVDIMM_H__ */
^ permalink raw reply related
* [PATCH v6 04/21] libnvdimm, nfit: dimm/memory-devices
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm
Cc: mingo, sfr, rafael, neilb, gregkh, Rafael J. Wysocki,
Robert Moore, linux-kernel, linux-acpi, jmoyer, axboe, linux-api,
akpm, hch
In-Reply-To: <20150611183830.25175.51256.stgit@dwillia2-desk3.amr.corp.intel.com>
Enable nvdimm devices to be registered on a nvdimm_bus. The kernel
assigned device id for nvdimm devicesis dynamic. If userspace needs a
more static identifier it should consult a provider-specific attribute.
In the case where NFIT is the provider, the 'nmemX/nfit/handle' or
'nmemX/nfit/serial' attributes may be used for this purpose.
Cc: Neil Brown <neilb@suse.de>
Cc: <linux-acpi@vger.kernel.org>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/acpi/nfit.c | 161 ++++++++++++++++++++++++++++++++++++++++++++
drivers/acpi/nfit.h | 1
drivers/nvdimm/Makefile | 1
drivers/nvdimm/bus.c | 14 ++++
drivers/nvdimm/core.c | 33 ++++++++-
drivers/nvdimm/dimm_devs.c | 92 +++++++++++++++++++++++++
drivers/nvdimm/nd-core.h | 12 +++
include/linux/libnvdimm.h | 11 +++
8 files changed, 321 insertions(+), 4 deletions(-)
create mode 100644 drivers/nvdimm/dimm_devs.c
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index fe9d79404fe5..21ea5736a5b2 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -381,6 +381,165 @@ static const struct attribute_group *acpi_nfit_attribute_groups[] = {
NULL,
};
+static struct acpi_nfit_memory_map *to_nfit_memdev(struct device *dev)
+{
+ struct nvdimm *nvdimm = to_nvdimm(dev);
+ struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
+ return __to_nfit_memdev(nfit_mem);
+}
+
+static struct acpi_nfit_control_region *to_nfit_dcr(struct device *dev)
+{
+ struct nvdimm *nvdimm = to_nvdimm(dev);
+ struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
+ return nfit_mem->dcr;
+}
+
+static ssize_t handle_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev);
+
+ return sprintf(buf, "%#x\n", memdev->device_handle);
+}
+static DEVICE_ATTR_RO(handle);
+
+static ssize_t phys_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev);
+
+ return sprintf(buf, "%#x\n", memdev->physical_id);
+}
+static DEVICE_ATTR_RO(phys_id);
+
+static ssize_t vendor_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+ return sprintf(buf, "%#x\n", dcr->vendor_id);
+}
+static DEVICE_ATTR_RO(vendor);
+
+static ssize_t rev_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+ return sprintf(buf, "%#x\n", dcr->revision_id);
+}
+static DEVICE_ATTR_RO(rev_id);
+
+static ssize_t device_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+ return sprintf(buf, "%#x\n", dcr->device_id);
+}
+static DEVICE_ATTR_RO(device);
+
+static ssize_t format_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+ return sprintf(buf, "%#x\n", dcr->code);
+}
+static DEVICE_ATTR_RO(format);
+
+static ssize_t serial_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+ return sprintf(buf, "%#x\n", dcr->serial_number);
+}
+static DEVICE_ATTR_RO(serial);
+
+static struct attribute *acpi_nfit_dimm_attributes[] = {
+ &dev_attr_handle.attr,
+ &dev_attr_phys_id.attr,
+ &dev_attr_vendor.attr,
+ &dev_attr_device.attr,
+ &dev_attr_format.attr,
+ &dev_attr_serial.attr,
+ &dev_attr_rev_id.attr,
+ NULL,
+};
+
+static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
+ struct attribute *a, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+
+ if (to_nfit_dcr(dev))
+ return a->mode;
+ else
+ return 0;
+}
+
+static struct attribute_group acpi_nfit_dimm_attribute_group = {
+ .name = "nfit",
+ .attrs = acpi_nfit_dimm_attributes,
+ .is_visible = acpi_nfit_dimm_attr_visible,
+};
+
+static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = {
+ &acpi_nfit_dimm_attribute_group,
+ NULL,
+};
+
+static struct nvdimm *acpi_nfit_dimm_by_handle(struct acpi_nfit_desc *acpi_desc,
+ u32 device_handle)
+{
+ struct nfit_mem *nfit_mem;
+
+ list_for_each_entry(nfit_mem, &acpi_desc->dimms, list)
+ if (__to_nfit_memdev(nfit_mem)->device_handle == device_handle)
+ return nfit_mem->nvdimm;
+
+ return NULL;
+}
+
+static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
+{
+ struct nfit_mem *nfit_mem;
+
+ list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+ struct nvdimm *nvdimm;
+ unsigned long flags = 0;
+ u32 device_handle;
+
+ device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
+ nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, device_handle);
+ if (nvdimm) {
+ /*
+ * If for some reason we find multiple DCRs the
+ * first one wins
+ */
+ dev_err(acpi_desc->dev, "duplicate DCR detected: %s\n",
+ nvdimm_name(nvdimm));
+ continue;
+ }
+
+ if (nfit_mem->bdw && nfit_mem->memdev_pmem)
+ flags |= NDD_ALIASING;
+
+ nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem,
+ acpi_nfit_dimm_attribute_groups, flags);
+ if (!nvdimm)
+ return -ENOMEM;
+
+ nfit_mem->nvdimm = nvdimm;
+ }
+
+ return 0;
+}
+
static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
{
struct device *dev = acpi_desc->dev;
@@ -408,7 +567,7 @@ static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
if (nfit_mem_init(acpi_desc) != 0)
return -ENOMEM;
- return 0;
+ return acpi_nfit_register_dimms(acpi_desc);
}
static int acpi_nfit_add(struct acpi_device *adev)
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index eda565fa81ef..9dd437fe5563 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -59,6 +59,7 @@ struct nfit_memdev {
/* assembled tables for a given dimm/memory-device */
struct nfit_mem {
+ struct nvdimm *nvdimm;
struct acpi_nfit_memory_map *memdev_dcr;
struct acpi_nfit_memory_map *memdev_pmem;
struct acpi_nfit_control_region *dcr;
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 8a8293c72c7c..5b68738ba406 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -2,3 +2,4 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
libnvdimm-y := core.o
libnvdimm-y += bus.o
+libnvdimm-y += dimm_devs.o
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 3f7c690a5d0c..a8802577fb55 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -13,6 +13,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/uaccess.h>
#include <linux/fcntl.h>
+#include <linux/async.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/io.h>
@@ -21,6 +22,10 @@
static int nvdimm_bus_major;
static struct class *nd_class;
+struct bus_type nvdimm_bus_type = {
+ .name = "nd",
+};
+
int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus)
{
dev_t devt = MKDEV(nvdimm_bus_major, nvdimm_bus->id);
@@ -59,9 +64,13 @@ int __init nvdimm_bus_init(void)
{
int rc;
+ rc = bus_register(&nvdimm_bus_type);
+ if (rc)
+ return rc;
+
rc = register_chrdev(0, "ndctl", &nvdimm_bus_fops);
if (rc < 0)
- return rc;
+ goto err_chrdev;
nvdimm_bus_major = rc;
nd_class = class_create(THIS_MODULE, "nd");
@@ -72,6 +81,8 @@ int __init nvdimm_bus_init(void)
err_class:
unregister_chrdev(nvdimm_bus_major, "ndctl");
+ err_chrdev:
+ bus_unregister(&nvdimm_bus_type);
return rc;
}
@@ -80,4 +91,5 @@ void __exit nvdimm_bus_exit(void)
{
class_destroy(nd_class);
unregister_chrdev(nvdimm_bus_major, "ndctl");
+ bus_unregister(&nvdimm_bus_type);
}
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index dcae823f681e..34af51842484 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -18,8 +18,8 @@
#include <linux/slab.h>
#include "nd-core.h"
-static LIST_HEAD(nvdimm_bus_list);
-static DEFINE_MUTEX(nvdimm_bus_list_mutex);
+LIST_HEAD(nvdimm_bus_list);
+DEFINE_MUTEX(nvdimm_bus_list_mutex);
static DEFINE_IDA(nd_ida);
static void nvdimm_bus_release(struct device *dev)
@@ -48,6 +48,19 @@ struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus)
}
EXPORT_SYMBOL_GPL(to_nd_desc);
+struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
+{
+ struct device *dev;
+
+ for (dev = nd_dev; dev; dev = dev->parent)
+ if (dev->release == nvdimm_bus_release)
+ break;
+ dev_WARN_ONCE(nd_dev, !dev, "invalid dev, not on nd bus\n");
+ if (dev)
+ return to_nvdimm_bus(dev);
+ return NULL;
+}
+
static const char *nvdimm_bus_provider(struct nvdimm_bus *nvdimm_bus)
{
struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
@@ -121,6 +134,21 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
}
EXPORT_SYMBOL_GPL(nvdimm_bus_register);
+static int child_unregister(struct device *dev, void *data)
+{
+ /*
+ * the singular ndctl class device per bus needs to be
+ * "device_destroy"ed, so skip it here
+ *
+ * i.e. remove classless children
+ */
+ if (dev->class)
+ /* pass */;
+ else
+ device_unregister(dev);
+ return 0;
+}
+
void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
{
if (!nvdimm_bus)
@@ -130,6 +158,7 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
list_del_init(&nvdimm_bus->list);
mutex_unlock(&nvdimm_bus_list_mutex);
+ device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
nvdimm_bus_destroy_ndctl(nvdimm_bus);
device_unregister(&nvdimm_bus->dev);
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
new file mode 100644
index 000000000000..51ea52cc2079
--- /dev/null
+++ b/drivers/nvdimm/dimm_devs.c
@@ -0,0 +1,92 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include "nd-core.h"
+
+static DEFINE_IDA(dimm_ida);
+
+static void nvdimm_release(struct device *dev)
+{
+ struct nvdimm *nvdimm = to_nvdimm(dev);
+
+ ida_simple_remove(&dimm_ida, nvdimm->id);
+ kfree(nvdimm);
+}
+
+static struct device_type nvdimm_device_type = {
+ .name = "nvdimm",
+ .release = nvdimm_release,
+};
+
+static bool is_nvdimm(struct device *dev)
+{
+ return dev->type == &nvdimm_device_type;
+}
+
+struct nvdimm *to_nvdimm(struct device *dev)
+{
+ struct nvdimm *nvdimm = container_of(dev, struct nvdimm, dev);
+
+ WARN_ON(!is_nvdimm(dev));
+ return nvdimm;
+}
+EXPORT_SYMBOL_GPL(to_nvdimm);
+
+const char *nvdimm_name(struct nvdimm *nvdimm)
+{
+ return dev_name(&nvdimm->dev);
+}
+EXPORT_SYMBOL_GPL(nvdimm_name);
+
+void *nvdimm_provider_data(struct nvdimm *nvdimm)
+{
+ return nvdimm->provider_data;
+}
+EXPORT_SYMBOL_GPL(nvdimm_provider_data);
+
+struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
+ const struct attribute_group **groups, unsigned long flags)
+{
+ struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL);
+ struct device *dev;
+
+ if (!nvdimm)
+ return NULL;
+
+ nvdimm->id = ida_simple_get(&dimm_ida, 0, 0, GFP_KERNEL);
+ if (nvdimm->id < 0) {
+ kfree(nvdimm);
+ return NULL;
+ }
+ nvdimm->provider_data = provider_data;
+ nvdimm->flags = flags;
+
+ dev = &nvdimm->dev;
+ dev_set_name(dev, "nmem%d", nvdimm->id);
+ dev->parent = &nvdimm_bus->dev;
+ dev->type = &nvdimm_device_type;
+ dev->bus = &nvdimm_bus_type;
+ dev->groups = groups;
+ if (device_register(dev) != 0) {
+ put_device(dev);
+ return NULL;
+ }
+
+ return nvdimm;
+}
+EXPORT_SYMBOL_GPL(nvdimm_create);
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 0b0ff2423161..9b8303413b60 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -15,6 +15,10 @@
#include <linux/libnvdimm.h>
#include <linux/device.h>
+extern struct list_head nvdimm_bus_list;
+extern struct mutex nvdimm_bus_list_mutex;
+extern struct bus_type nvdimm_bus_type;
+
struct nvdimm_bus {
struct nvdimm_bus_descriptor *nd_desc;
struct list_head list;
@@ -22,6 +26,14 @@ struct nvdimm_bus {
int id;
};
+struct nvdimm {
+ unsigned long flags;
+ void *provider_data;
+ struct device dev;
+ int id;
+};
+
+struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
int __init nvdimm_bus_init(void);
void __exit nvdimm_bus_exit(void);
int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index d375cdc4abd5..07787f0dd7de 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -14,6 +14,12 @@
*/
#ifndef __LIBNVDIMM_H__
#define __LIBNVDIMM_H__
+
+enum {
+ /* when a dimm supports both PMEM and BLK access a label is required */
+ NDD_ALIASING = 1 << 0,
+};
+
extern struct attribute_group nvdimm_bus_attribute_group;
struct nvdimm;
@@ -34,5 +40,10 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
struct nvdimm_bus_descriptor *nfit_desc);
void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
struct nvdimm_bus *to_nvdimm_bus(struct device *dev);
+struct nvdimm *to_nvdimm(struct device *dev);
struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
+const char *nvdimm_name(struct nvdimm *nvdimm);
+void *nvdimm_provider_data(struct nvdimm *nvdimm);
+struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
+ const struct attribute_group **groups, unsigned long flags);
#endif /* __LIBNVDIMM_H__ */
^ permalink raw reply related
* [PATCH v6 05/21] libnvdimm: control (ioctl) messages for nvdimm_bus and nvdimm devices
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm
Cc: mingo, sfr, rafael, neilb, gregkh, Rafael J. Wysocki,
Robert Moore, linux-kernel, linux-acpi, jmoyer, axboe,
Nicholas Moulin, linux-api, akpm, hch
In-Reply-To: <20150611183830.25175.51256.stgit@dwillia2-desk3.amr.corp.intel.com>
Most discovery/configuration of the nvdimm-subsystem is done via sysfs
attributes. However, some nvdimm_bus instances, particularly the
ACPI.NFIT bus, define a small set of messages that can be passed to the
platform. For convenience we derive the initial libnvdimm-ioctl command
formats directly from the NFIT DSM Interface Example formats.
ND_CMD_SMART: media health and diagnostics
ND_CMD_GET_CONFIG_SIZE: size of the label space
ND_CMD_GET_CONFIG_DATA: read label space
ND_CMD_SET_CONFIG_DATA: write label space
ND_CMD_VENDOR: vendor-specific command passthrough
ND_CMD_ARS_CAP: report address-range-scrubbing capabilities
ND_CMD_ARS_START: initiate scrubbing
ND_CMD_ARS_STATUS: report on scrubbing state
ND_CMD_SMART_THRESHOLD: configure alarm thresholds for smart events
If a platform later defines different commands than this set it is
straightforward to extend support to those formats.
Most of the commands target a specific dimm. However, the
address-range-scrubbing commands target the bus. The 'commands'
attribute in sysfs of an nvdimm_bus, or nvdimm, enumerate the supported
commands for that object.
Cc: <linux-acpi@vger.kernel.org>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reported-by: Nicholas Moulin <nicholas.w.moulin@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/acpi/Kconfig | 12 ++
drivers/acpi/nfit.c | 216 +++++++++++++++++++++++++++++
drivers/acpi/nfit.h | 3
drivers/nvdimm/bus.c | 326 +++++++++++++++++++++++++++++++++++++++++++-
drivers/nvdimm/core.c | 16 ++
drivers/nvdimm/dimm_devs.c | 38 +++++
drivers/nvdimm/nd-core.h | 3
include/linux/libnvdimm.h | 27 ++++
include/uapi/linux/Kbuild | 1
include/uapi/linux/ndctl.h | 178 ++++++++++++++++++++++++
10 files changed, 810 insertions(+), 10 deletions(-)
create mode 100644 include/uapi/linux/ndctl.h
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 300b4ef3712b..9c43ae301300 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -397,6 +397,18 @@ config ACPI_NFIT
To compile this driver as a module, choose M here:
the module will be called nfit.
+config ACPI_NFIT_DEBUG
+ bool "NFIT DSM debug"
+ depends on ACPI_NFIT
+ depends on DYNAMIC_DEBUG
+ default n
+ help
+ Enabling this option causes the nfit driver to dump the
+ input and output buffers of _DSM operations on the ACPI0012
+ device and its children. This can be very verbose, so leave
+ it disabled unless you are debugging a hardware / firmware
+ issue.
+
source "drivers/acpi/apei/Kconfig"
config ACPI_EXTLOG
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 21ea5736a5b2..ff4aeced92d6 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -13,6 +13,7 @@
#include <linux/list_sort.h>
#include <linux/libnvdimm.h>
#include <linux/module.h>
+#include <linux/ndctl.h>
#include <linux/list.h>
#include <linux/acpi.h>
#include "nfit.h"
@@ -24,11 +25,153 @@ static const u8 *to_nfit_uuid(enum nfit_uuids id)
return nfit_uuid[id];
}
+static struct acpi_nfit_desc *to_acpi_nfit_desc(
+ struct nvdimm_bus_descriptor *nd_desc)
+{
+ return container_of(nd_desc, struct acpi_nfit_desc, nd_desc);
+}
+
+static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc)
+{
+ struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+
+ /*
+ * If provider == 'ACPI.NFIT' we can assume 'dev' is a struct
+ * acpi_device.
+ */
+ if (!nd_desc->provider_name
+ || strcmp(nd_desc->provider_name, "ACPI.NFIT") != 0)
+ return NULL;
+
+ return to_acpi_device(acpi_desc->dev);
+}
+
static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
struct nvdimm *nvdimm, unsigned int cmd, void *buf,
unsigned int buf_len)
{
- return -ENOTTY;
+ struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
+ const struct nd_cmd_desc *desc = NULL;
+ union acpi_object in_obj, in_buf, *out_obj;
+ struct device *dev = acpi_desc->dev;
+ const char *cmd_name, *dimm_name;
+ unsigned long dsm_mask;
+ acpi_handle handle;
+ const u8 *uuid;
+ u32 offset;
+ int rc, i;
+
+ if (nvdimm) {
+ struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+ struct acpi_device *adev = nfit_mem->adev;
+
+ if (!adev)
+ return -ENOTTY;
+ dimm_name = dev_name(&adev->dev);
+ cmd_name = nvdimm_cmd_name(cmd);
+ dsm_mask = nfit_mem->dsm_mask;
+ desc = nd_cmd_dimm_desc(cmd);
+ uuid = to_nfit_uuid(NFIT_DEV_DIMM);
+ handle = adev->handle;
+ } else {
+ struct acpi_device *adev = to_acpi_dev(acpi_desc);
+
+ cmd_name = nvdimm_bus_cmd_name(cmd);
+ dsm_mask = nd_desc->dsm_mask;
+ desc = nd_cmd_bus_desc(cmd);
+ uuid = to_nfit_uuid(NFIT_DEV_BUS);
+ handle = adev->handle;
+ dimm_name = "bus";
+ }
+
+ if (!desc || (cmd && (desc->out_num + desc->in_num == 0)))
+ return -ENOTTY;
+
+ if (!test_bit(cmd, &dsm_mask))
+ return -ENOTTY;
+
+ in_obj.type = ACPI_TYPE_PACKAGE;
+ in_obj.package.count = 1;
+ in_obj.package.elements = &in_buf;
+ in_buf.type = ACPI_TYPE_BUFFER;
+ in_buf.buffer.pointer = buf;
+ in_buf.buffer.length = 0;
+
+ /* libnvdimm has already validated the input envelope */
+ for (i = 0; i < desc->in_num; i++)
+ in_buf.buffer.length += nd_cmd_in_size(nvdimm, cmd, desc,
+ i, buf);
+
+ if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
+ dev_dbg(dev, "%s:%s cmd: %s input length: %d\n", __func__,
+ dimm_name, cmd_name, in_buf.buffer.length);
+ print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4,
+ 4, in_buf.buffer.pointer, min_t(u32, 128,
+ in_buf.buffer.length), true);
+ }
+
+ out_obj = acpi_evaluate_dsm(handle, uuid, 1, cmd, &in_obj);
+ if (!out_obj) {
+ dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name,
+ cmd_name);
+ return -EINVAL;
+ }
+
+ if (out_obj->package.type != ACPI_TYPE_BUFFER) {
+ dev_dbg(dev, "%s:%s unexpected output object type cmd: %s type: %d\n",
+ __func__, dimm_name, cmd_name, out_obj->type);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
+ dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__,
+ dimm_name, cmd_name, out_obj->buffer.length);
+ print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4,
+ 4, out_obj->buffer.pointer, min_t(u32, 128,
+ out_obj->buffer.length), true);
+ }
+
+ for (i = 0, offset = 0; i < desc->out_num; i++) {
+ u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
+ (u32 *) out_obj->buffer.pointer);
+
+ if (offset + out_size > out_obj->buffer.length) {
+ dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n",
+ __func__, dimm_name, cmd_name, i);
+ break;
+ }
+
+ if (in_buf.buffer.length + offset + out_size > buf_len) {
+ dev_dbg(dev, "%s:%s output overrun cmd: %s field: %d\n",
+ __func__, dimm_name, cmd_name, i);
+ rc = -ENXIO;
+ goto out;
+ }
+ memcpy(buf + in_buf.buffer.length + offset,
+ out_obj->buffer.pointer + offset, out_size);
+ offset += out_size;
+ }
+ if (offset + in_buf.buffer.length < buf_len) {
+ if (i >= 1) {
+ /*
+ * status valid, return the number of bytes left
+ * unfilled in the output buffer
+ */
+ rc = buf_len - offset - in_buf.buffer.length;
+ } else {
+ dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n",
+ __func__, dimm_name, cmd_name, buf_len,
+ offset);
+ rc = -ENXIO;
+ }
+ } else
+ rc = 0;
+
+ out:
+ ACPI_FREE(out_obj);
+
+ return rc;
}
static const char *spa_type_name(u16 type)
@@ -489,6 +632,7 @@ static struct attribute_group acpi_nfit_dimm_attribute_group = {
};
static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = {
+ &nvdimm_attribute_group,
&acpi_nfit_dimm_attribute_group,
NULL,
};
@@ -505,6 +649,50 @@ static struct nvdimm *acpi_nfit_dimm_by_handle(struct acpi_nfit_desc *acpi_desc,
return NULL;
}
+static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
+ struct nfit_mem *nfit_mem, u32 device_handle)
+{
+ struct acpi_device *adev, *adev_dimm;
+ struct device *dev = acpi_desc->dev;
+ const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM);
+ unsigned long long sta;
+ int i, rc = -ENODEV;
+ acpi_status status;
+
+ nfit_mem->dsm_mask = acpi_desc->dimm_dsm_force_en;
+ adev = to_acpi_dev(acpi_desc);
+ if (!adev)
+ return 0;
+
+ adev_dimm = acpi_find_child_device(adev, device_handle, false);
+ nfit_mem->adev = adev_dimm;
+ if (!adev_dimm) {
+ dev_err(dev, "no ACPI.NFIT device with _ADR %#x, disabling...\n",
+ device_handle);
+ return -ENODEV;
+ }
+
+ status = acpi_evaluate_integer(adev_dimm->handle, "_STA", NULL, &sta);
+ if (status == AE_NOT_FOUND) {
+ dev_dbg(dev, "%s missing _STA, assuming enabled...\n",
+ dev_name(&adev_dimm->dev));
+ rc = 0;
+ } else if (ACPI_FAILURE(status))
+ dev_err(dev, "%s failed to retrieve_STA, disabling...\n",
+ dev_name(&adev_dimm->dev));
+ else if ((sta & ACPI_STA_DEVICE_ENABLED) == 0)
+ dev_info(dev, "%s disabled by firmware\n",
+ dev_name(&adev_dimm->dev));
+ else
+ rc = 0;
+
+ for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++)
+ if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i))
+ set_bit(i, &nfit_mem->dsm_mask);
+
+ return rc;
+}
+
static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
{
struct nfit_mem *nfit_mem;
@@ -513,6 +701,7 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
struct nvdimm *nvdimm;
unsigned long flags = 0;
u32 device_handle;
+ int rc;
device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, device_handle);
@@ -529,8 +718,13 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
if (nfit_mem->bdw && nfit_mem->memdev_pmem)
flags |= NDD_ALIASING;
+ rc = acpi_nfit_add_dimm(acpi_desc, nfit_mem, device_handle);
+ if (rc)
+ continue;
+
nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem,
- acpi_nfit_dimm_attribute_groups, flags);
+ acpi_nfit_dimm_attribute_groups,
+ flags, &nfit_mem->dsm_mask);
if (!nvdimm)
return -ENOMEM;
@@ -540,6 +734,22 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
return 0;
}
+static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
+{
+ struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+ const u8 *uuid = to_nfit_uuid(NFIT_DEV_BUS);
+ struct acpi_device *adev;
+ int i;
+
+ adev = to_acpi_dev(acpi_desc);
+ if (!adev)
+ return;
+
+ for (i = ND_CMD_ARS_CAP; i <= ND_CMD_ARS_STATUS; i++)
+ if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i))
+ set_bit(i, &nd_desc->dsm_mask);
+}
+
static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
{
struct device *dev = acpi_desc->dev;
@@ -567,6 +777,8 @@ static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
if (nfit_mem_init(acpi_desc) != 0)
return -ENOMEM;
+ acpi_nfit_init_dsms(acpi_desc);
+
return acpi_nfit_register_dimms(acpi_desc);
}
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 9dd437fe5563..b76e33629098 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -67,6 +67,8 @@ struct nfit_mem {
struct acpi_nfit_system_address *spa_dcr;
struct acpi_nfit_system_address *spa_bdw;
struct list_head list;
+ struct acpi_device *adev;
+ unsigned long dsm_mask;
};
struct acpi_nfit_desc {
@@ -79,6 +81,7 @@ struct acpi_nfit_desc {
struct list_head bdws;
struct nvdimm_bus *nvdimm_bus;
struct device *dev;
+ unsigned long dimm_dsm_force_en;
};
static inline struct acpi_nfit_memory_map *__to_nfit_memdev(
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index a8802577fb55..15f3a3ddc225 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -11,14 +11,18 @@
* General Public License for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/vmalloc.h>
#include <linux/uaccess.h>
#include <linux/fcntl.h>
#include <linux/async.h>
+#include <linux/ndctl.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/io.h>
+#include <linux/mm.h>
#include "nd-core.h"
+int nvdimm_major;
static int nvdimm_bus_major;
static struct class *nd_class;
@@ -47,19 +51,325 @@ void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus)
device_destroy(nd_class, MKDEV(nvdimm_bus_major, nvdimm_bus->id));
}
+static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = {
+ [ND_CMD_IMPLEMENTED] = { },
+ [ND_CMD_SMART] = {
+ .out_num = 2,
+ .out_sizes = { 4, 8, },
+ },
+ [ND_CMD_SMART_THRESHOLD] = {
+ .out_num = 2,
+ .out_sizes = { 4, 8, },
+ },
+ [ND_CMD_DIMM_FLAGS] = {
+ .out_num = 2,
+ .out_sizes = { 4, 4 },
+ },
+ [ND_CMD_GET_CONFIG_SIZE] = {
+ .out_num = 3,
+ .out_sizes = { 4, 4, 4, },
+ },
+ [ND_CMD_GET_CONFIG_DATA] = {
+ .in_num = 2,
+ .in_sizes = { 4, 4, },
+ .out_num = 2,
+ .out_sizes = { 4, UINT_MAX, },
+ },
+ [ND_CMD_SET_CONFIG_DATA] = {
+ .in_num = 3,
+ .in_sizes = { 4, 4, UINT_MAX, },
+ .out_num = 1,
+ .out_sizes = { 4, },
+ },
+ [ND_CMD_VENDOR] = {
+ .in_num = 3,
+ .in_sizes = { 4, 4, UINT_MAX, },
+ .out_num = 3,
+ .out_sizes = { 4, 4, UINT_MAX, },
+ },
+};
+
+const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd)
+{
+ if (cmd < ARRAY_SIZE(__nd_cmd_dimm_descs))
+ return &__nd_cmd_dimm_descs[cmd];
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_dimm_desc);
+
+static const struct nd_cmd_desc __nd_cmd_bus_descs[] = {
+ [ND_CMD_IMPLEMENTED] = { },
+ [ND_CMD_ARS_CAP] = {
+ .in_num = 2,
+ .in_sizes = { 8, 8, },
+ .out_num = 2,
+ .out_sizes = { 4, 4, },
+ },
+ [ND_CMD_ARS_START] = {
+ .in_num = 4,
+ .in_sizes = { 8, 8, 2, 6, },
+ .out_num = 1,
+ .out_sizes = { 4, },
+ },
+ [ND_CMD_ARS_STATUS] = {
+ .out_num = 2,
+ .out_sizes = { 4, UINT_MAX, },
+ },
+};
+
+const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd)
+{
+ if (cmd < ARRAY_SIZE(__nd_cmd_bus_descs))
+ return &__nd_cmd_bus_descs[cmd];
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_bus_desc);
+
+u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,
+ const struct nd_cmd_desc *desc, int idx, void *buf)
+{
+ if (idx >= desc->in_num)
+ return UINT_MAX;
+
+ if (desc->in_sizes[idx] < UINT_MAX)
+ return desc->in_sizes[idx];
+
+ if (nvdimm && cmd == ND_CMD_SET_CONFIG_DATA && idx == 2) {
+ struct nd_cmd_set_config_hdr *hdr = buf;
+
+ return hdr->in_length;
+ } else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) {
+ struct nd_cmd_vendor_hdr *hdr = buf;
+
+ return hdr->in_length;
+ }
+
+ return UINT_MAX;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_in_size);
+
+u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
+ const struct nd_cmd_desc *desc, int idx, const u32 *in_field,
+ const u32 *out_field)
+{
+ if (idx >= desc->out_num)
+ return UINT_MAX;
+
+ if (desc->out_sizes[idx] < UINT_MAX)
+ return desc->out_sizes[idx];
+
+ if (nvdimm && cmd == ND_CMD_GET_CONFIG_DATA && idx == 1)
+ return in_field[1];
+ else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2)
+ return out_field[1];
+ else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1)
+ return ND_CMD_ARS_STATUS_MAX;
+
+ return UINT_MAX;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_out_size);
+
+static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
+ int read_only, unsigned int ioctl_cmd, unsigned long arg)
+{
+ struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+ size_t buf_len = 0, in_len = 0, out_len = 0;
+ static char out_env[ND_CMD_MAX_ENVELOPE];
+ static char in_env[ND_CMD_MAX_ENVELOPE];
+ const struct nd_cmd_desc *desc = NULL;
+ unsigned int cmd = _IOC_NR(ioctl_cmd);
+ void __user *p = (void __user *) arg;
+ struct device *dev = &nvdimm_bus->dev;
+ const char *cmd_name, *dimm_name;
+ unsigned long dsm_mask;
+ void *buf;
+ int rc, i;
+
+ if (nvdimm) {
+ desc = nd_cmd_dimm_desc(cmd);
+ cmd_name = nvdimm_cmd_name(cmd);
+ dsm_mask = nvdimm->dsm_mask ? *(nvdimm->dsm_mask) : 0;
+ dimm_name = dev_name(&nvdimm->dev);
+ } else {
+ desc = nd_cmd_bus_desc(cmd);
+ cmd_name = nvdimm_bus_cmd_name(cmd);
+ dsm_mask = nd_desc->dsm_mask;
+ dimm_name = "bus";
+ }
+
+ if (!desc || (desc->out_num + desc->in_num == 0) ||
+ !test_bit(cmd, &dsm_mask))
+ return -ENOTTY;
+
+ /* fail write commands (when read-only) */
+ if (read_only)
+ switch (ioctl_cmd) {
+ case ND_IOCTL_VENDOR:
+ case ND_IOCTL_SET_CONFIG_DATA:
+ case ND_IOCTL_ARS_START:
+ dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n",
+ nvdimm ? nvdimm_cmd_name(cmd)
+ : nvdimm_bus_cmd_name(cmd));
+ return -EPERM;
+ default:
+ break;
+ }
+
+ /* process an input envelope */
+ for (i = 0; i < desc->in_num; i++) {
+ u32 in_size, copy;
+
+ in_size = nd_cmd_in_size(nvdimm, cmd, desc, i, in_env);
+ if (in_size == UINT_MAX) {
+ dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n",
+ __func__, dimm_name, cmd_name, i);
+ return -ENXIO;
+ }
+ if (!access_ok(VERIFY_READ, p + in_len, in_size))
+ return -EFAULT;
+ if (in_len < sizeof(in_env))
+ copy = min_t(u32, sizeof(in_env) - in_len, in_size);
+ else
+ copy = 0;
+ if (copy && copy_from_user(&in_env[in_len], p + in_len, copy))
+ return -EFAULT;
+ in_len += in_size;
+ }
+
+ /* process an output envelope */
+ for (i = 0; i < desc->out_num; i++) {
+ u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i,
+ (u32 *) in_env, (u32 *) out_env);
+ u32 copy;
+
+ if (out_size == UINT_MAX) {
+ dev_dbg(dev, "%s:%s unknown output size cmd: %s field: %d\n",
+ __func__, dimm_name, cmd_name, i);
+ return -EFAULT;
+ }
+ if (!access_ok(VERIFY_WRITE, p + in_len + out_len, out_size))
+ return -EFAULT;
+ if (out_len < sizeof(out_env))
+ copy = min_t(u32, sizeof(out_env) - out_len, out_size);
+ else
+ copy = 0;
+ if (copy && copy_from_user(&out_env[out_len],
+ p + in_len + out_len, copy))
+ return -EFAULT;
+ out_len += out_size;
+ }
+
+ buf_len = out_len + in_len;
+ if (!access_ok(VERIFY_WRITE, p, sizeof(buf_len)))
+ return -EFAULT;
+
+ if (buf_len > ND_IOCTL_MAX_BUFLEN) {
+ dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__,
+ dimm_name, cmd_name, buf_len,
+ ND_IOCTL_MAX_BUFLEN);
+ return -EINVAL;
+ }
+
+ buf = vmalloc(buf_len);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, p, buf_len)) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len);
+ if (rc < 0)
+ goto out;
+ if (copy_to_user(p, buf, buf_len))
+ rc = -EFAULT;
+ out:
+ vfree(buf);
+ return rc;
+}
+
static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- return -ENXIO;
+ long id = (long) file->private_data;
+ int rc = -ENXIO, read_only;
+ struct nvdimm_bus *nvdimm_bus;
+
+ read_only = (O_RDWR != (file->f_flags & O_ACCMODE));
+ mutex_lock(&nvdimm_bus_list_mutex);
+ list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
+ if (nvdimm_bus->id == id) {
+ rc = __nd_ioctl(nvdimm_bus, NULL, read_only, cmd, arg);
+ break;
+ }
+ }
+ mutex_unlock(&nvdimm_bus_list_mutex);
+
+ return rc;
+}
+
+static int match_dimm(struct device *dev, void *data)
+{
+ long id = (long) data;
+
+ if (is_nvdimm(dev)) {
+ struct nvdimm *nvdimm = to_nvdimm(dev);
+
+ return nvdimm->id == id;
+ }
+
+ return 0;
+}
+
+static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ int rc = -ENXIO, read_only;
+ struct nvdimm_bus *nvdimm_bus;
+
+ read_only = (O_RDWR != (file->f_flags & O_ACCMODE));
+ mutex_lock(&nvdimm_bus_list_mutex);
+ list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
+ struct device *dev = device_find_child(&nvdimm_bus->dev,
+ file->private_data, match_dimm);
+ struct nvdimm *nvdimm;
+
+ if (!dev)
+ continue;
+
+ nvdimm = to_nvdimm(dev);
+ rc = __nd_ioctl(nvdimm_bus, nvdimm, read_only, cmd, arg);
+ put_device(dev);
+ break;
+ }
+ mutex_unlock(&nvdimm_bus_list_mutex);
+
+ return rc;
+}
+
+static int nd_open(struct inode *inode, struct file *file)
+{
+ long minor = iminor(inode);
+
+ file->private_data = (void *) minor;
+ return 0;
}
static const struct file_operations nvdimm_bus_fops = {
.owner = THIS_MODULE,
- .open = nonseekable_open,
+ .open = nd_open,
.unlocked_ioctl = nd_ioctl,
.compat_ioctl = nd_ioctl,
.llseek = noop_llseek,
};
+static const struct file_operations nvdimm_fops = {
+ .owner = THIS_MODULE,
+ .open = nd_open,
+ .unlocked_ioctl = nvdimm_ioctl,
+ .compat_ioctl = nvdimm_ioctl,
+ .llseek = noop_llseek,
+};
+
int __init nvdimm_bus_init(void)
{
int rc;
@@ -70,9 +380,14 @@ int __init nvdimm_bus_init(void)
rc = register_chrdev(0, "ndctl", &nvdimm_bus_fops);
if (rc < 0)
- goto err_chrdev;
+ goto err_bus_chrdev;
nvdimm_bus_major = rc;
+ rc = register_chrdev(0, "dimmctl", &nvdimm_fops);
+ if (rc < 0)
+ goto err_dimm_chrdev;
+ nvdimm_major = rc;
+
nd_class = class_create(THIS_MODULE, "nd");
if (IS_ERR(nd_class))
goto err_class;
@@ -80,8 +395,10 @@ int __init nvdimm_bus_init(void)
return 0;
err_class:
+ unregister_chrdev(nvdimm_major, "dimmctl");
+ err_dimm_chrdev:
unregister_chrdev(nvdimm_bus_major, "ndctl");
- err_chrdev:
+ err_bus_chrdev:
bus_unregister(&nvdimm_bus_type);
return rc;
@@ -91,5 +408,6 @@ void __exit nvdimm_bus_exit(void)
{
class_destroy(nd_class);
unregister_chrdev(nvdimm_bus_major, "ndctl");
+ unregister_chrdev(nvdimm_major, "dimmctl");
bus_unregister(&nvdimm_bus_type);
}
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 34af51842484..eb802db34a96 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -14,6 +14,7 @@
#include <linux/export.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/ndctl.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include "nd-core.h"
@@ -61,6 +62,20 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
return NULL;
}
+static ssize_t commands_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int cmd, len = 0;
+ struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+ struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+
+ for_each_set_bit(cmd, &nd_desc->dsm_mask, BITS_PER_LONG)
+ len += sprintf(buf + len, "%s ", nvdimm_bus_cmd_name(cmd));
+ len += sprintf(buf + len, "\n");
+ return len;
+}
+static DEVICE_ATTR_RO(commands);
+
static const char *nvdimm_bus_provider(struct nvdimm_bus *nvdimm_bus)
{
struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
@@ -84,6 +99,7 @@ static ssize_t provider_show(struct device *dev,
static DEVICE_ATTR_RO(provider);
static struct attribute *nvdimm_bus_attributes[] = {
+ &dev_attr_commands.attr,
&dev_attr_provider.attr,
NULL,
};
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 51ea52cc2079..c3dd7227d1bb 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -12,6 +12,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/device.h>
+#include <linux/ndctl.h>
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/fs.h>
@@ -33,7 +34,7 @@ static struct device_type nvdimm_device_type = {
.release = nvdimm_release,
};
-static bool is_nvdimm(struct device *dev)
+bool is_nvdimm(struct device *dev)
{
return dev->type == &nvdimm_device_type;
}
@@ -55,12 +56,41 @@ EXPORT_SYMBOL_GPL(nvdimm_name);
void *nvdimm_provider_data(struct nvdimm *nvdimm)
{
- return nvdimm->provider_data;
+ if (nvdimm)
+ return nvdimm->provider_data;
+ return NULL;
}
EXPORT_SYMBOL_GPL(nvdimm_provider_data);
+static ssize_t commands_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvdimm *nvdimm = to_nvdimm(dev);
+ int cmd, len = 0;
+
+ if (!nvdimm->dsm_mask)
+ return sprintf(buf, "\n");
+
+ for_each_set_bit(cmd, nvdimm->dsm_mask, BITS_PER_LONG)
+ len += sprintf(buf + len, "%s ", nvdimm_cmd_name(cmd));
+ len += sprintf(buf + len, "\n");
+ return len;
+}
+static DEVICE_ATTR_RO(commands);
+
+static struct attribute *nvdimm_attributes[] = {
+ &dev_attr_commands.attr,
+ NULL,
+};
+
+struct attribute_group nvdimm_attribute_group = {
+ .attrs = nvdimm_attributes,
+};
+EXPORT_SYMBOL_GPL(nvdimm_attribute_group);
+
struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
- const struct attribute_group **groups, unsigned long flags)
+ const struct attribute_group **groups, unsigned long flags,
+ unsigned long *dsm_mask)
{
struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL);
struct device *dev;
@@ -75,12 +105,14 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
}
nvdimm->provider_data = provider_data;
nvdimm->flags = flags;
+ nvdimm->dsm_mask = dsm_mask;
dev = &nvdimm->dev;
dev_set_name(dev, "nmem%d", nvdimm->id);
dev->parent = &nvdimm_bus->dev;
dev->type = &nvdimm_device_type;
dev->bus = &nvdimm_bus_type;
+ dev->devt = MKDEV(nvdimm_major, nvdimm->id);
dev->groups = groups;
if (device_register(dev) != 0) {
put_device(dev);
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 9b8303413b60..59528b3c9de8 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -18,6 +18,7 @@
extern struct list_head nvdimm_bus_list;
extern struct mutex nvdimm_bus_list_mutex;
extern struct bus_type nvdimm_bus_type;
+extern int nvdimm_major;
struct nvdimm_bus {
struct nvdimm_bus_descriptor *nd_desc;
@@ -29,10 +30,12 @@ struct nvdimm_bus {
struct nvdimm {
unsigned long flags;
void *provider_data;
+ unsigned long *dsm_mask;
struct device dev;
int id;
};
+bool is_nvdimm(struct device *dev);
struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
int __init nvdimm_bus_init(void);
void __exit nvdimm_bus_exit(void);
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 07787f0dd7de..a39235819af3 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -14,13 +14,22 @@
*/
#ifndef __LIBNVDIMM_H__
#define __LIBNVDIMM_H__
+#include <linux/sizes.h>
+#include <linux/types.h>
enum {
/* when a dimm supports both PMEM and BLK access a label is required */
NDD_ALIASING = 1 << 0,
+
+ /* need to set a limit somewhere, but yes, this is likely overkill */
+ ND_IOCTL_MAX_BUFLEN = SZ_4M,
+ ND_CMD_MAX_ELEM = 4,
+ ND_CMD_MAX_ENVELOPE = 16,
+ ND_CMD_ARS_STATUS_MAX = SZ_4K,
};
extern struct attribute_group nvdimm_bus_attribute_group;
+extern struct attribute_group nvdimm_attribute_group;
struct nvdimm;
struct nvdimm_bus_descriptor;
@@ -35,6 +44,14 @@ struct nvdimm_bus_descriptor {
ndctl_fn ndctl;
};
+struct nd_cmd_desc {
+ int in_num;
+ int out_num;
+ u32 in_sizes[ND_CMD_MAX_ELEM];
+ int out_sizes[ND_CMD_MAX_ELEM];
+};
+
+struct nvdimm_bus;
struct device;
struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
struct nvdimm_bus_descriptor *nfit_desc);
@@ -45,5 +62,13 @@ struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
const char *nvdimm_name(struct nvdimm *nvdimm);
void *nvdimm_provider_data(struct nvdimm *nvdimm);
struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
- const struct attribute_group **groups, unsigned long flags);
+ const struct attribute_group **groups, unsigned long flags,
+ unsigned long *dsm_mask);
+const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd);
+const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd);
+u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,
+ const struct nd_cmd_desc *desc, int idx, void *buf);
+u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
+ const struct nd_cmd_desc *desc, int idx, const u32 *in_field,
+ const u32 *out_field);
#endif /* __LIBNVDIMM_H__ */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 1a0006a76b00..200cc5ea2998 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -271,6 +271,7 @@ header-y += ncp_fs.h
header-y += ncp.h
header-y += ncp_mount.h
header-y += ncp_no.h
+header-y += ndctl.h
header-y += neighbour.h
header-y += netconf.h
header-y += netdevice.h
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
new file mode 100644
index 000000000000..ff13c23b26df
--- /dev/null
+++ b/include/uapi/linux/ndctl.h
@@ -0,0 +1,178 @@
+/*
+ * Copyright (c) 2014-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU Lesser General Public License,
+ * version 2.1, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT ANY
+ * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for
+ * more details.
+ */
+#ifndef __NDCTL_H__
+#define __NDCTL_H__
+
+#include <linux/types.h>
+
+struct nd_cmd_smart {
+ __u32 status;
+ __u8 data[128];
+} __packed;
+
+struct nd_cmd_smart_threshold {
+ __u32 status;
+ __u8 data[8];
+} __packed;
+
+struct nd_cmd_dimm_flags {
+ __u32 status;
+ __u32 flags;
+} __packed;
+
+struct nd_cmd_get_config_size {
+ __u32 status;
+ __u32 config_size;
+ __u32 max_xfer;
+} __packed;
+
+struct nd_cmd_get_config_data_hdr {
+ __u32 in_offset;
+ __u32 in_length;
+ __u32 status;
+ __u8 out_buf[0];
+} __packed;
+
+struct nd_cmd_set_config_hdr {
+ __u32 in_offset;
+ __u32 in_length;
+ __u8 in_buf[0];
+} __packed;
+
+struct nd_cmd_vendor_hdr {
+ __u32 opcode;
+ __u32 in_length;
+ __u8 in_buf[0];
+} __packed;
+
+struct nd_cmd_vendor_tail {
+ __u32 status;
+ __u32 out_length;
+ __u8 out_buf[0];
+} __packed;
+
+struct nd_cmd_ars_cap {
+ __u64 address;
+ __u64 length;
+ __u32 status;
+ __u32 max_ars_out;
+} __packed;
+
+struct nd_cmd_ars_start {
+ __u64 address;
+ __u64 length;
+ __u16 type;
+ __u8 reserved[6];
+ __u32 status;
+} __packed;
+
+struct nd_cmd_ars_status {
+ __u32 status;
+ __u32 out_length;
+ __u64 address;
+ __u64 length;
+ __u16 type;
+ __u32 num_records;
+ struct nd_ars_record {
+ __u32 handle;
+ __u32 flags;
+ __u64 err_address;
+ __u64 mask;
+ } __packed records[0];
+} __packed;
+
+enum {
+ ND_CMD_IMPLEMENTED = 0,
+
+ /* bus commands */
+ ND_CMD_ARS_CAP = 1,
+ ND_CMD_ARS_START = 2,
+ ND_CMD_ARS_STATUS = 3,
+
+ /* per-dimm commands */
+ ND_CMD_SMART = 1,
+ ND_CMD_SMART_THRESHOLD = 2,
+ ND_CMD_DIMM_FLAGS = 3,
+ ND_CMD_GET_CONFIG_SIZE = 4,
+ ND_CMD_GET_CONFIG_DATA = 5,
+ ND_CMD_SET_CONFIG_DATA = 6,
+ ND_CMD_VENDOR_EFFECT_LOG_SIZE = 7,
+ ND_CMD_VENDOR_EFFECT_LOG = 8,
+ ND_CMD_VENDOR = 9,
+};
+
+static inline const char *nvdimm_bus_cmd_name(unsigned cmd)
+{
+ static const char * const names[] = {
+ [ND_CMD_ARS_CAP] = "ars_cap",
+ [ND_CMD_ARS_START] = "ars_start",
+ [ND_CMD_ARS_STATUS] = "ars_status",
+ };
+
+ if (cmd < ARRAY_SIZE(names) && names[cmd])
+ return names[cmd];
+ return "unknown";
+}
+
+static inline const char *nvdimm_cmd_name(unsigned cmd)
+{
+ static const char * const names[] = {
+ [ND_CMD_SMART] = "smart",
+ [ND_CMD_SMART_THRESHOLD] = "smart_thresh",
+ [ND_CMD_DIMM_FLAGS] = "flags",
+ [ND_CMD_GET_CONFIG_SIZE] = "get_size",
+ [ND_CMD_GET_CONFIG_DATA] = "get_data",
+ [ND_CMD_SET_CONFIG_DATA] = "set_data",
+ [ND_CMD_VENDOR_EFFECT_LOG_SIZE] = "effect_size",
+ [ND_CMD_VENDOR_EFFECT_LOG] = "effect_log",
+ [ND_CMD_VENDOR] = "vendor",
+ };
+
+ if (cmd < ARRAY_SIZE(names) && names[cmd])
+ return names[cmd];
+ return "unknown";
+}
+
+#define ND_IOCTL 'N'
+
+#define ND_IOCTL_SMART _IOWR(ND_IOCTL, ND_CMD_SMART,\
+ struct nd_cmd_smart)
+
+#define ND_IOCTL_SMART_THRESHOLD _IOWR(ND_IOCTL, ND_CMD_SMART_THRESHOLD,\
+ struct nd_cmd_smart_threshold)
+
+#define ND_IOCTL_DIMM_FLAGS _IOWR(ND_IOCTL, ND_CMD_DIMM_FLAGS,\
+ struct nd_cmd_dimm_flags)
+
+#define ND_IOCTL_GET_CONFIG_SIZE _IOWR(ND_IOCTL, ND_CMD_GET_CONFIG_SIZE,\
+ struct nd_cmd_get_config_size)
+
+#define ND_IOCTL_GET_CONFIG_DATA _IOWR(ND_IOCTL, ND_CMD_GET_CONFIG_DATA,\
+ struct nd_cmd_get_config_data_hdr)
+
+#define ND_IOCTL_SET_CONFIG_DATA _IOWR(ND_IOCTL, ND_CMD_SET_CONFIG_DATA,\
+ struct nd_cmd_set_config_hdr)
+
+#define ND_IOCTL_VENDOR _IOWR(ND_IOCTL, ND_CMD_VENDOR,\
+ struct nd_cmd_vendor_hdr)
+
+#define ND_IOCTL_ARS_CAP _IOWR(ND_IOCTL, ND_CMD_ARS_CAP,\
+ struct nd_cmd_ars_cap)
+
+#define ND_IOCTL_ARS_START _IOWR(ND_IOCTL, ND_CMD_ARS_START,\
+ struct nd_cmd_ars_start)
+
+#define ND_IOCTL_ARS_STATUS _IOWR(ND_IOCTL, ND_CMD_ARS_STATUS,\
+ struct nd_cmd_ars_status)
+
+#endif /* __NDCTL_H__ */
^ permalink raw reply related
* [PATCH v6 06/21] libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver infrastructure
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm
Cc: axboe, sfr, rafael, neilb, gregkh, linux-kernel, mingo,
linux-acpi, jmoyer, linux-api, akpm, hch
In-Reply-To: <20150611183830.25175.51256.stgit@dwillia2-desk3.amr.corp.intel.com>
* Implement the device-model infrastructure for loading modules and
attaching drivers to nvdimm devices. This is a simple association of a
nd-device-type number with a driver that has a bitmask of supported
device types. To facilitate userspace bind/unbind operations 'modalias'
and 'devtype', that also appear in the uevent, are added as generic
sysfs attributes for all nvdimm devices. The reason for the device-type
number is to support sub-types within a given parent devtype, be it a
vendor-specific sub-type or otherwise.
* The first consumer of this infrastructure is the driver
for dimm devices. It simply uses control messages to retrieve and
store the configuration-data image (label set) from each dimm.
Note: nd_device_register() arranges for asynchronous registration of
nvdimm bus devices by default.
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/acpi/nfit.c | 13 +++
drivers/nvdimm/Makefile | 1
drivers/nvdimm/bus.c | 168 +++++++++++++++++++++++++++++++++++++++++++-
drivers/nvdimm/core.c | 43 +++++++++++
drivers/nvdimm/dimm.c | 92 ++++++++++++++++++++++++
drivers/nvdimm/dimm_devs.c | 136 ++++++++++++++++++++++++++++++++++--
drivers/nvdimm/nd-core.h | 6 +-
drivers/nvdimm/nd.h | 36 +++++++++
include/linux/libnvdimm.h | 2 +
include/linux/nd.h | 39 ++++++++++
include/uapi/linux/ndctl.h | 6 ++
11 files changed, 527 insertions(+), 15 deletions(-)
create mode 100644 drivers/nvdimm/dimm.c
create mode 100644 drivers/nvdimm/nd.h
create mode 100644 include/linux/nd.h
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index ff4aeced92d6..fcff81fa1395 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -18,6 +18,10 @@
#include <linux/acpi.h>
#include "nfit.h"
+static bool force_enable_dimms;
+module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status");
+
static u8 nfit_uuid[NFIT_UUID_MAX][16];
static const u8 *to_nfit_uuid(enum nfit_uuids id)
@@ -633,6 +637,7 @@ static struct attribute_group acpi_nfit_dimm_attribute_group = {
static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = {
&nvdimm_attribute_group,
+ &nd_device_attribute_group,
&acpi_nfit_dimm_attribute_group,
NULL,
};
@@ -669,7 +674,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
if (!adev_dimm) {
dev_err(dev, "no ACPI.NFIT device with _ADR %#x, disabling...\n",
device_handle);
- return -ENODEV;
+ return force_enable_dimms ? 0 : -ENODEV;
}
status = acpi_evaluate_integer(adev_dimm->handle, "_STA", NULL, &sta);
@@ -690,12 +695,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i))
set_bit(i, &nfit_mem->dsm_mask);
- return rc;
+ return force_enable_dimms ? 0 : rc;
}
static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
{
struct nfit_mem *nfit_mem;
+ int dimm_count = 0;
list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
struct nvdimm *nvdimm;
@@ -729,9 +735,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
return -ENOMEM;
nfit_mem->nvdimm = nvdimm;
+ dimm_count++;
}
- return 0;
+ return nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count);
}
static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 5b68738ba406..d44b5c1fcd3b 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -3,3 +3,4 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
libnvdimm-y := core.o
libnvdimm-y += bus.o
libnvdimm-y += dimm_devs.o
+libnvdimm-y += dimm.o
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 15f3a3ddc225..a0308f1872bf 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -16,19 +16,183 @@
#include <linux/fcntl.h>
#include <linux/async.h>
#include <linux/ndctl.h>
+#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/mm.h>
+#include <linux/nd.h>
#include "nd-core.h"
+#include "nd.h"
int nvdimm_major;
static int nvdimm_bus_major;
static struct class *nd_class;
-struct bus_type nvdimm_bus_type = {
+static int to_nd_device_type(struct device *dev)
+{
+ if (is_nvdimm(dev))
+ return ND_DEVICE_DIMM;
+
+ return 0;
+}
+
+static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ return add_uevent_var(env, "MODALIAS=" ND_DEVICE_MODALIAS_FMT,
+ to_nd_device_type(dev));
+}
+
+static int nvdimm_bus_match(struct device *dev, struct device_driver *drv)
+{
+ struct nd_device_driver *nd_drv = to_nd_device_driver(drv);
+
+ return test_bit(to_nd_device_type(dev), &nd_drv->type);
+}
+
+static int nvdimm_bus_probe(struct device *dev)
+{
+ struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver);
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+ int rc;
+
+ rc = nd_drv->probe(dev);
+ dev_dbg(&nvdimm_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name,
+ dev_name(dev), rc);
+ return rc;
+}
+
+static int nvdimm_bus_remove(struct device *dev)
+{
+ struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver);
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+ int rc;
+
+ rc = nd_drv->remove(dev);
+ dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name,
+ dev_name(dev), rc);
+ return rc;
+}
+
+static struct bus_type nvdimm_bus_type = {
.name = "nd",
+ .uevent = nvdimm_bus_uevent,
+ .match = nvdimm_bus_match,
+ .probe = nvdimm_bus_probe,
+ .remove = nvdimm_bus_remove,
+};
+
+static ASYNC_DOMAIN_EXCLUSIVE(nd_async_domain);
+
+void nd_synchronize(void)
+{
+ async_synchronize_full_domain(&nd_async_domain);
+}
+EXPORT_SYMBOL_GPL(nd_synchronize);
+
+static void nd_async_device_register(void *d, async_cookie_t cookie)
+{
+ struct device *dev = d;
+
+ if (device_add(dev) != 0) {
+ dev_err(dev, "%s: failed\n", __func__);
+ put_device(dev);
+ }
+ put_device(dev);
+}
+
+static void nd_async_device_unregister(void *d, async_cookie_t cookie)
+{
+ struct device *dev = d;
+
+ device_unregister(dev);
+ put_device(dev);
+}
+
+void nd_device_register(struct device *dev)
+{
+ dev->bus = &nvdimm_bus_type;
+ device_initialize(dev);
+ get_device(dev);
+ async_schedule_domain(nd_async_device_register, dev,
+ &nd_async_domain);
+}
+EXPORT_SYMBOL(nd_device_register);
+
+void nd_device_unregister(struct device *dev, enum nd_async_mode mode)
+{
+ switch (mode) {
+ case ND_ASYNC:
+ get_device(dev);
+ async_schedule_domain(nd_async_device_unregister, dev,
+ &nd_async_domain);
+ break;
+ case ND_SYNC:
+ nd_synchronize();
+ device_unregister(dev);
+ break;
+ }
+}
+EXPORT_SYMBOL(nd_device_unregister);
+
+/**
+ * __nd_driver_register() - register a region or a namespace driver
+ * @nd_drv: driver to register
+ * @owner: automatically set by nd_driver_register() macro
+ * @mod_name: automatically set by nd_driver_register() macro
+ */
+int __nd_driver_register(struct nd_device_driver *nd_drv, struct module *owner,
+ const char *mod_name)
+{
+ struct device_driver *drv = &nd_drv->drv;
+
+ if (!nd_drv->type) {
+ pr_debug("driver type bitmask not set (%pf)\n",
+ __builtin_return_address(0));
+ return -EINVAL;
+ }
+
+ if (!nd_drv->probe || !nd_drv->remove) {
+ pr_debug("->probe() and ->remove() must be specified\n");
+ return -EINVAL;
+ }
+
+ drv->bus = &nvdimm_bus_type;
+ drv->owner = owner;
+ drv->mod_name = mod_name;
+
+ return driver_register(drv);
+}
+EXPORT_SYMBOL(__nd_driver_register);
+
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, ND_DEVICE_MODALIAS_FMT "\n",
+ to_nd_device_type(dev));
+}
+static DEVICE_ATTR_RO(modalias);
+
+static ssize_t devtype_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%s\n", dev->type->name);
+}
+static DEVICE_ATTR_RO(devtype);
+
+static struct attribute *nd_device_attributes[] = {
+ &dev_attr_modalias.attr,
+ &dev_attr_devtype.attr,
+ NULL,
+};
+
+/**
+ * nd_device_attribute_group - generic attributes for all devices on an nd bus
+ */
+struct attribute_group nd_device_attribute_group = {
+ .attrs = nd_device_attributes,
};
+EXPORT_SYMBOL_GPL(nd_device_attribute_group);
int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus)
{
@@ -404,7 +568,7 @@ int __init nvdimm_bus_init(void)
return rc;
}
-void __exit nvdimm_bus_exit(void)
+void nvdimm_bus_exit(void)
{
class_destroy(nd_class);
unregister_chrdev(nvdimm_bus_major, "ndctl");
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index eb802db34a96..a9723192bed1 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -18,6 +18,7 @@
#include <linux/mutex.h>
#include <linux/slab.h>
#include "nd-core.h"
+#include "nd.h"
LIST_HEAD(nvdimm_bus_list);
DEFINE_MUTEX(nvdimm_bus_list_mutex);
@@ -98,8 +99,33 @@ static ssize_t provider_show(struct device *dev,
}
static DEVICE_ATTR_RO(provider);
+static int flush_namespaces(struct device *dev, void *data)
+{
+ device_lock(dev);
+ device_unlock(dev);
+ return 0;
+}
+
+static int flush_regions_dimms(struct device *dev, void *data)
+{
+ device_lock(dev);
+ device_unlock(dev);
+ device_for_each_child(dev, NULL, flush_namespaces);
+ return 0;
+}
+
+static ssize_t wait_probe_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ nd_synchronize();
+ device_for_each_child(dev, NULL, flush_regions_dimms);
+ return sprintf(buf, "1\n");
+}
+static DEVICE_ATTR_RO(wait_probe);
+
static struct attribute *nvdimm_bus_attributes[] = {
&dev_attr_commands.attr,
+ &dev_attr_wait_probe.attr,
&dev_attr_provider.attr,
NULL,
};
@@ -161,7 +187,7 @@ static int child_unregister(struct device *dev, void *data)
if (dev->class)
/* pass */;
else
- device_unregister(dev);
+ nd_device_unregister(dev, ND_SYNC);
return 0;
}
@@ -174,6 +200,7 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
list_del_init(&nvdimm_bus->list);
mutex_unlock(&nvdimm_bus_list_mutex);
+ nd_synchronize();
device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
nvdimm_bus_destroy_ndctl(nvdimm_bus);
@@ -183,12 +210,24 @@ EXPORT_SYMBOL_GPL(nvdimm_bus_unregister);
static __init int libnvdimm_init(void)
{
- return nvdimm_bus_init();
+ int rc;
+
+ rc = nvdimm_bus_init();
+ if (rc)
+ return rc;
+ rc = nvdimm_init();
+ if (rc)
+ goto err_dimm;
+ return 0;
+ err_dimm:
+ nvdimm_bus_exit();
+ return rc;
}
static __exit void libnvdimm_exit(void)
{
WARN_ON(!list_empty(&nvdimm_bus_list));
+ nvdimm_exit();
nvdimm_bus_exit();
}
diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c
new file mode 100644
index 000000000000..28001a6ccd4e
--- /dev/null
+++ b/drivers/nvdimm/dimm.c
@@ -0,0 +1,92 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/sizes.h>
+#include <linux/ndctl.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/nd.h>
+#include "nd.h"
+
+static void free_data(struct nvdimm_drvdata *ndd)
+{
+ if (!ndd)
+ return;
+
+ if (ndd->data && is_vmalloc_addr(ndd->data))
+ vfree(ndd->data);
+ else
+ kfree(ndd->data);
+ kfree(ndd);
+}
+
+static int nvdimm_probe(struct device *dev)
+{
+ struct nvdimm_drvdata *ndd;
+ int rc;
+
+ ndd = kzalloc(sizeof(*ndd), GFP_KERNEL);
+ if (!ndd)
+ return -ENOMEM;
+
+ dev_set_drvdata(dev, ndd);
+ ndd->dev = dev;
+
+ rc = nvdimm_init_nsarea(ndd);
+ if (rc)
+ goto err;
+
+ rc = nvdimm_init_config_data(ndd);
+ if (rc)
+ goto err;
+
+ dev_dbg(dev, "config data size: %d\n", ndd->nsarea.config_size);
+
+ return 0;
+
+ err:
+ free_data(ndd);
+ return rc;
+}
+
+static int nvdimm_remove(struct device *dev)
+{
+ struct nvdimm_drvdata *ndd = dev_get_drvdata(dev);
+
+ free_data(ndd);
+
+ return 0;
+}
+
+static struct nd_device_driver nvdimm_driver = {
+ .probe = nvdimm_probe,
+ .remove = nvdimm_remove,
+ .drv = {
+ .name = "nvdimm",
+ },
+ .type = ND_DRIVER_DIMM,
+};
+
+int __init nvdimm_init(void)
+{
+ return nd_driver_register(&nvdimm_driver);
+}
+
+void __exit nvdimm_exit(void)
+{
+ driver_unregister(&nvdimm_driver.drv);
+}
+
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DIMM);
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index c3dd7227d1bb..b3ae86f2e1da 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -11,6 +11,7 @@
* General Public License for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/vmalloc.h>
#include <linux/device.h>
#include <linux/ndctl.h>
#include <linux/slab.h>
@@ -18,9 +19,115 @@
#include <linux/fs.h>
#include <linux/mm.h>
#include "nd-core.h"
+#include "nd.h"
static DEFINE_IDA(dimm_ida);
+/*
+ * Retrieve bus and dimm handle and return if this bus supports
+ * get_config_data commands
+ */
+static int __validate_dimm(struct nvdimm_drvdata *ndd)
+{
+ struct nvdimm *nvdimm;
+
+ if (!ndd)
+ return -EINVAL;
+
+ nvdimm = to_nvdimm(ndd->dev);
+
+ if (!nvdimm->dsm_mask)
+ return -ENXIO;
+ if (!test_bit(ND_CMD_GET_CONFIG_DATA, nvdimm->dsm_mask))
+ return -ENXIO;
+
+ return 0;
+}
+
+static int validate_dimm(struct nvdimm_drvdata *ndd)
+{
+ int rc = __validate_dimm(ndd);
+
+ if (rc && ndd)
+ dev_dbg(ndd->dev, "%pf: %s error: %d\n",
+ __builtin_return_address(0), __func__, rc);
+ return rc;
+}
+
+/**
+ * nvdimm_init_nsarea - determine the geometry of a dimm's namespace area
+ * @nvdimm: dimm to initialize
+ */
+int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd)
+{
+ struct nd_cmd_get_config_size *cmd = &ndd->nsarea;
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+ struct nvdimm_bus_descriptor *nd_desc;
+ int rc = validate_dimm(ndd);
+
+ if (rc)
+ return rc;
+
+ if (cmd->config_size)
+ return 0; /* already valid */
+
+ memset(cmd, 0, sizeof(*cmd));
+ nd_desc = nvdimm_bus->nd_desc;
+ return nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
+ ND_CMD_GET_CONFIG_SIZE, cmd, sizeof(*cmd));
+}
+
+int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
+{
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+ struct nd_cmd_get_config_data_hdr *cmd;
+ struct nvdimm_bus_descriptor *nd_desc;
+ int rc = validate_dimm(ndd);
+ u32 max_cmd_size, config_size;
+ size_t offset;
+
+ if (rc)
+ return rc;
+
+ if (ndd->data)
+ return 0;
+
+ if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0)
+ return -ENXIO;
+
+ ndd->data = kmalloc(ndd->nsarea.config_size, GFP_KERNEL);
+ if (!ndd->data)
+ ndd->data = vmalloc(ndd->nsarea.config_size);
+
+ if (!ndd->data)
+ return -ENOMEM;
+
+ max_cmd_size = min_t(u32, PAGE_SIZE, ndd->nsarea.max_xfer);
+ cmd = kzalloc(max_cmd_size + sizeof(*cmd), GFP_KERNEL);
+ if (!cmd)
+ return -ENOMEM;
+
+ nd_desc = nvdimm_bus->nd_desc;
+ for (config_size = ndd->nsarea.config_size, offset = 0;
+ config_size; config_size -= cmd->in_length,
+ offset += cmd->in_length) {
+ cmd->in_length = min(config_size, max_cmd_size);
+ cmd->in_offset = offset;
+ rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
+ ND_CMD_GET_CONFIG_DATA, cmd,
+ cmd->in_length + sizeof(*cmd));
+ if (rc || cmd->status) {
+ rc = -ENXIO;
+ break;
+ }
+ memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length);
+ }
+ dev_dbg(ndd->dev, "%s: len: %zu rc: %d\n", __func__, offset, rc);
+ kfree(cmd);
+
+ return rc;
+}
+
static void nvdimm_release(struct device *dev)
{
struct nvdimm *nvdimm = to_nvdimm(dev);
@@ -111,14 +218,33 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
dev_set_name(dev, "nmem%d", nvdimm->id);
dev->parent = &nvdimm_bus->dev;
dev->type = &nvdimm_device_type;
- dev->bus = &nvdimm_bus_type;
dev->devt = MKDEV(nvdimm_major, nvdimm->id);
dev->groups = groups;
- if (device_register(dev) != 0) {
- put_device(dev);
- return NULL;
- }
+ nd_device_register(dev);
return nvdimm;
}
EXPORT_SYMBOL_GPL(nvdimm_create);
+
+static int count_dimms(struct device *dev, void *c)
+{
+ int *count = c;
+
+ if (is_nvdimm(dev))
+ (*count)++;
+ return 0;
+}
+
+int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count)
+{
+ int count = 0;
+ /* Flush any possible dimm registration failures */
+ nd_synchronize();
+
+ device_for_each_child(&nvdimm_bus->dev, &count, count_dimms);
+ dev_dbg(&nvdimm_bus->dev, "%s: count: %d\n", __func__, count);
+ if (count != dimm_count)
+ return -ENXIO;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nvdimm_bus_check_dimm_count);
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 59528b3c9de8..f2004b790874 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -17,7 +17,6 @@
extern struct list_head nvdimm_bus_list;
extern struct mutex nvdimm_bus_list_mutex;
-extern struct bus_type nvdimm_bus_type;
extern int nvdimm_major;
struct nvdimm_bus {
@@ -35,10 +34,11 @@ struct nvdimm {
int id;
};
-bool is_nvdimm(struct device *dev);
struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
int __init nvdimm_bus_init(void);
-void __exit nvdimm_bus_exit(void);
+void nvdimm_bus_exit(void);
int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
+void nd_synchronize(void);
+bool is_nvdimm(struct device *dev);
#endif /* __ND_CORE_H__ */
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
new file mode 100644
index 000000000000..1f7f6ecab0fc
--- /dev/null
+++ b/drivers/nvdimm/nd.h
@@ -0,0 +1,36 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef __ND_H__
+#define __ND_H__
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/ndctl.h>
+
+struct nvdimm_drvdata {
+ struct device *dev;
+ struct nd_cmd_get_config_size nsarea;
+ void *data;
+};
+
+enum nd_async_mode {
+ ND_SYNC,
+ ND_ASYNC,
+};
+
+void nd_device_register(struct device *dev);
+void nd_device_unregister(struct device *dev, enum nd_async_mode mode);
+int __init nvdimm_init(void);
+void nvdimm_exit(void);
+int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd);
+int nvdimm_init_config_data(struct nvdimm_drvdata *ndd);
+#endif /* __ND_H__ */
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index a39235819af3..d3ebccf4ea8b 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -30,6 +30,7 @@ enum {
extern struct attribute_group nvdimm_bus_attribute_group;
extern struct attribute_group nvdimm_attribute_group;
+extern struct attribute_group nd_device_attribute_group;
struct nvdimm;
struct nvdimm_bus_descriptor;
@@ -71,4 +72,5 @@ u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,
u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
const struct nd_cmd_desc *desc, int idx, const u32 *in_field,
const u32 *out_field);
+int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count);
#endif /* __LIBNVDIMM_H__ */
diff --git a/include/linux/nd.h b/include/linux/nd.h
new file mode 100644
index 000000000000..e074f67e53a3
--- /dev/null
+++ b/include/linux/nd.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef __LINUX_ND_H__
+#define __LINUX_ND_H__
+#include <linux/ndctl.h>
+#include <linux/device.h>
+
+struct nd_device_driver {
+ struct device_driver drv;
+ unsigned long type;
+ int (*probe)(struct device *dev);
+ int (*remove)(struct device *dev);
+};
+
+static inline struct nd_device_driver *to_nd_device_driver(
+ struct device_driver *drv)
+{
+ return container_of(drv, struct nd_device_driver, drv);
+}
+
+#define MODULE_ALIAS_ND_DEVICE(type) \
+ MODULE_ALIAS("nd:t" __stringify(type) "*")
+#define ND_DEVICE_MODALIAS_FMT "nd:t%d"
+
+int __must_check __nd_driver_register(struct nd_device_driver *nd_drv,
+ struct module *module, const char *mod_name);
+#define nd_driver_register(driver) \
+ __nd_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
+#endif /* __LINUX_ND_H__ */
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index ff13c23b26df..37640916d146 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -175,4 +175,10 @@ static inline const char *nvdimm_cmd_name(unsigned cmd)
#define ND_IOCTL_ARS_STATUS _IOWR(ND_IOCTL, ND_CMD_ARS_STATUS,\
struct nd_cmd_ars_status)
+
+#define ND_DEVICE_DIMM 1 /* nd_dimm: container for "config data" */
+
+enum nd_driver_flags {
+ ND_DRIVER_DIMM = 1 << ND_DEVICE_DIMM,
+};
#endif /* __NDCTL_H__ */
^ permalink raw reply related
* [PATCH v6 07/21] libnvdimm, nfit: regions (block-data-window, persistent memory, volatile memory)
From: Dan Williams @ 2015-06-11 20:10 UTC (permalink / raw)
To: linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw
Cc: mingo-DgEjT+Ai2ygdnm+yROfE0A, sfr-3FnU+UHB4dNDw9hX6IcOSA,
rafael-DgEjT+Ai2ygdnm+yROfE0A, neilb-l3A5Bk7waGM,
gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r, Rafael J. Wysocki,
Robert Moore, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-acpi-u79uwXL29TY76Z2rM5mHXA, jmoyer-H+wXaHxf7aLQT0dZR+AlfA,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-api-u79uwXL29TY76Z2rM5mHXA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b, hch-jcswGhMUV9g
In-Reply-To: <20150611183830.25175.51256.stgit-p8uTFz9XbKj2zm6wflaqv1nYeNYlB/vhral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
A "region" device represents the maximum capacity of a BLK range (mmio
block-data-window(s)), or a PMEM range (DAX-capable persistent memory or
volatile memory), without regard for aliasing. Aliasing, in the
dimm-local address space (DPA), is resolved by metadata on a dimm to
designate which exclusive interface will access the aliased DPA ranges.
Support for the per-dimm metadata/label arrvies is in a subsequent
patch.
The name format of "region" devices is "regionN" where, like dimms, N is
a global ida index assigned at discovery time. This id is not reliable
across reboots nor in the presence of hotplug. Look to attributes of
the region or static id-data of the sub-namespace to generate a
persistent name. However, if the platform configuration does not change
it is reasonable to expect the same region id to be assigned at the next
boot.
"region"s have 2 generic attributes "size", and "mapping"s where:
- size: the BLK accessible capacity or the span of the
system physical address range in the case of PMEM.
- mappingN: a tuple describing a dimm's contribution to the region's
capacity in the format (<nmemX>,<dpa>,<size>). For a PMEM-region
there will be at least one mapping per dimm in the interleave set. For
a BLK-region there is only "mapping0" listing the starting DPA of the
BLK-region and the available DPA capacity of that space (matches "size"
above).
The max number of mappings per "region" is hard coded per the
constraints of sysfs attribute groups. That said the number of mappings
per region should never exceed the maximum number of possible dimms in
the system. If the current number turns out to not be enough then the
"mappings" attribute clarifies how many there are supposed to be. "32
should be enough for anybody...".
Cc: Neil Brown <neilb-l3A5Bk7waGM@public.gmane.org>
Cc: <linux-acpi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Cc: Greg KH <gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r@public.gmane.org>
Cc: Robert Moore <robert.moore-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/acpi/nfit.c | 148 +++++++++++++++++++++
drivers/nvdimm/Makefile | 1
drivers/nvdimm/nd-core.h | 3
drivers/nvdimm/nd.h | 11 ++
drivers/nvdimm/region_devs.c | 297 ++++++++++++++++++++++++++++++++++++++++++
include/linux/libnvdimm.h | 25 ++++
6 files changed, 484 insertions(+), 1 deletion(-)
create mode 100644 drivers/nvdimm/region_devs.c
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index fcff81fa1395..38a6bcdcb3da 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -757,11 +757,153 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
set_bit(i, &nd_desc->dsm_mask);
}
+static ssize_t range_index_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+ struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region);
+
+ return sprintf(buf, "%d\n", nfit_spa->spa->range_index);
+}
+static DEVICE_ATTR_RO(range_index);
+
+static struct attribute *acpi_nfit_region_attributes[] = {
+ &dev_attr_range_index.attr,
+ NULL,
+};
+
+static struct attribute_group acpi_nfit_region_attribute_group = {
+ .name = "nfit",
+ .attrs = acpi_nfit_region_attributes,
+};
+
+static const struct attribute_group *acpi_nfit_region_attribute_groups[] = {
+ &nd_region_attribute_group,
+ &nd_mapping_attribute_group,
+ &acpi_nfit_region_attribute_group,
+ NULL,
+};
+
+static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
+ struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc,
+ struct acpi_nfit_memory_map *memdev,
+ struct acpi_nfit_system_address *spa)
+{
+ struct nvdimm *nvdimm = acpi_nfit_dimm_by_handle(acpi_desc,
+ memdev->device_handle);
+ struct nfit_mem *nfit_mem;
+ int blk_valid = 0;
+
+ if (!nvdimm) {
+ dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n",
+ spa->range_index, memdev->device_handle);
+ return -ENODEV;
+ }
+
+ nd_mapping->nvdimm = nvdimm;
+ switch (nfit_spa_type(spa)) {
+ case NFIT_SPA_PM:
+ case NFIT_SPA_VOLATILE:
+ nd_mapping->start = memdev->address;
+ nd_mapping->size = memdev->region_size;
+ break;
+ case NFIT_SPA_DCR:
+ nfit_mem = nvdimm_provider_data(nvdimm);
+ if (!nfit_mem || !nfit_mem->bdw) {
+ dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n",
+ spa->range_index, nvdimm_name(nvdimm));
+ } else {
+ nd_mapping->size = nfit_mem->bdw->capacity;
+ nd_mapping->start = nfit_mem->bdw->start_address;
+ blk_valid = 1;
+ }
+
+ ndr_desc->nd_mapping = nd_mapping;
+ ndr_desc->num_mappings = blk_valid;
+ if (!nvdimm_blk_region_create(acpi_desc->nvdimm_bus, ndr_desc))
+ return -ENOMEM;
+ break;
+ }
+
+ return 0;
+}
+
+static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
+ struct nfit_spa *nfit_spa)
+{
+ static struct nd_mapping nd_mappings[ND_MAX_MAPPINGS];
+ struct acpi_nfit_system_address *spa = nfit_spa->spa;
+ struct nfit_memdev *nfit_memdev;
+ struct nd_region_desc ndr_desc;
+ struct nvdimm_bus *nvdimm_bus;
+ struct resource res;
+ int count = 0;
+
+ if (spa->range_index == 0) {
+ dev_dbg(acpi_desc->dev, "%s: detected invalid spa index\n",
+ __func__);
+ return 0;
+ }
+
+ memset(&res, 0, sizeof(res));
+ memset(&nd_mappings, 0, sizeof(nd_mappings));
+ memset(&ndr_desc, 0, sizeof(ndr_desc));
+ res.start = spa->address;
+ res.end = res.start + spa->length - 1;
+ ndr_desc.res = &res;
+ ndr_desc.provider_data = nfit_spa;
+ ndr_desc.attr_groups = acpi_nfit_region_attribute_groups;
+ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
+ struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
+ struct nd_mapping *nd_mapping;
+ int rc;
+
+ if (memdev->range_index != spa->range_index)
+ continue;
+ if (count >= ND_MAX_MAPPINGS) {
+ dev_err(acpi_desc->dev, "spa%d exceeds max mappings %d\n",
+ spa->range_index, ND_MAX_MAPPINGS);
+ return -ENXIO;
+ }
+ nd_mapping = &nd_mappings[count++];
+ rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, &ndr_desc,
+ memdev, spa);
+ if (rc)
+ return rc;
+ }
+
+ ndr_desc.nd_mapping = nd_mappings;
+ ndr_desc.num_mappings = count;
+ nvdimm_bus = acpi_desc->nvdimm_bus;
+ if (nfit_spa_type(spa) == NFIT_SPA_PM) {
+ if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+ return -ENOMEM;
+ } else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) {
+ if (!nvdimm_volatile_region_create(nvdimm_bus, &ndr_desc))
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
+{
+ struct nfit_spa *nfit_spa;
+
+ list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
+ int rc = acpi_nfit_register_region(acpi_desc, nfit_spa);
+
+ if (rc)
+ return rc;
+ }
+ return 0;
+}
+
static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
{
struct device *dev = acpi_desc->dev;
const void *end;
u8 *data;
+ int rc;
INIT_LIST_HEAD(&acpi_desc->spas);
INIT_LIST_HEAD(&acpi_desc->dcrs);
@@ -786,7 +928,11 @@ static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
acpi_nfit_init_dsms(acpi_desc);
- return acpi_nfit_register_dimms(acpi_desc);
+ rc = acpi_nfit_register_dimms(acpi_desc);
+ if (rc)
+ return rc;
+
+ return acpi_nfit_register_regions(acpi_desc);
}
static int acpi_nfit_add(struct acpi_device *adev)
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index d44b5c1fcd3b..88afd0d849c3 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -4,3 +4,4 @@ libnvdimm-y := core.o
libnvdimm-y += bus.o
libnvdimm-y += dimm_devs.o
libnvdimm-y += dimm.o
+libnvdimm-y += region_devs.o
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index f2004b790874..1d760bf24857 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -40,5 +40,8 @@ void nvdimm_bus_exit(void);
int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
void nd_synchronize(void);
+int nvdimm_bus_register_dimms(struct nvdimm_bus *nvdimm_bus);
+int nvdimm_bus_register_regions(struct nvdimm_bus *nvdimm_bus);
+int nd_match_dimm(struct device *dev, void *data);
bool is_nvdimm(struct device *dev);
#endif /* __ND_CORE_H__ */
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 1f7f6ecab0fc..ea0cca337aa6 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -12,6 +12,7 @@
*/
#ifndef __ND_H__
#define __ND_H__
+#include <linux/libnvdimm.h>
#include <linux/device.h>
#include <linux/mutex.h>
#include <linux/ndctl.h>
@@ -22,6 +23,16 @@ struct nvdimm_drvdata {
void *data;
};
+struct nd_region {
+ struct device dev;
+ u16 ndr_mappings;
+ u64 ndr_size;
+ u64 ndr_start;
+ int id;
+ void *provider_data;
+ struct nd_mapping mapping[0];
+};
+
enum nd_async_mode {
ND_SYNC,
ND_ASYNC,
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
new file mode 100644
index 000000000000..4bda2e0df8f7
--- /dev/null
+++ b/drivers/nvdimm/region_devs.c
@@ -0,0 +1,297 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/slab.h>
+#include <linux/io.h>
+#include "nd-core.h"
+#include "nd.h"
+
+static DEFINE_IDA(region_ida);
+
+static void nd_region_release(struct device *dev)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+ u16 i;
+
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+ struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+ put_device(&nvdimm->dev);
+ }
+ ida_simple_remove(®ion_ida, nd_region->id);
+ kfree(nd_region);
+}
+
+static struct device_type nd_blk_device_type = {
+ .name = "nd_blk",
+ .release = nd_region_release,
+};
+
+static struct device_type nd_pmem_device_type = {
+ .name = "nd_pmem",
+ .release = nd_region_release,
+};
+
+static struct device_type nd_volatile_device_type = {
+ .name = "nd_volatile",
+ .release = nd_region_release,
+};
+
+static bool is_nd_pmem(struct device *dev)
+{
+ return dev ? dev->type == &nd_pmem_device_type : false;
+}
+
+struct nd_region *to_nd_region(struct device *dev)
+{
+ struct nd_region *nd_region = container_of(dev, struct nd_region, dev);
+
+ WARN_ON(dev->type->release != nd_region_release);
+ return nd_region;
+}
+EXPORT_SYMBOL_GPL(to_nd_region);
+
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+ unsigned long long size = 0;
+
+ if (is_nd_pmem(dev)) {
+ size = nd_region->ndr_size;
+ } else if (nd_region->ndr_mappings == 1) {
+ struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+
+ size = nd_mapping->size;
+ }
+
+ return sprintf(buf, "%llu\n", size);
+}
+static DEVICE_ATTR_RO(size);
+
+static ssize_t mappings_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+
+ return sprintf(buf, "%d\n", nd_region->ndr_mappings);
+}
+static DEVICE_ATTR_RO(mappings);
+
+static struct attribute *nd_region_attributes[] = {
+ &dev_attr_size.attr,
+ &dev_attr_mappings.attr,
+ NULL,
+};
+
+struct attribute_group nd_region_attribute_group = {
+ .attrs = nd_region_attributes,
+};
+EXPORT_SYMBOL_GPL(nd_region_attribute_group);
+
+static ssize_t mappingN(struct device *dev, char *buf, int n)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+ struct nd_mapping *nd_mapping;
+ struct nvdimm *nvdimm;
+
+ if (n >= nd_region->ndr_mappings)
+ return -ENXIO;
+ nd_mapping = &nd_region->mapping[n];
+ nvdimm = nd_mapping->nvdimm;
+
+ return sprintf(buf, "%s,%llu,%llu\n", dev_name(&nvdimm->dev),
+ nd_mapping->start, nd_mapping->size);
+}
+
+#define REGION_MAPPING(idx) \
+static ssize_t mapping##idx##_show(struct device *dev, \
+ struct device_attribute *attr, char *buf) \
+{ \
+ return mappingN(dev, buf, idx); \
+} \
+static DEVICE_ATTR_RO(mapping##idx)
+
+/*
+ * 32 should be enough for a while, even in the presence of socket
+ * interleave a 32-way interleave set is a degenerate case.
+ */
+REGION_MAPPING(0);
+REGION_MAPPING(1);
+REGION_MAPPING(2);
+REGION_MAPPING(3);
+REGION_MAPPING(4);
+REGION_MAPPING(5);
+REGION_MAPPING(6);
+REGION_MAPPING(7);
+REGION_MAPPING(8);
+REGION_MAPPING(9);
+REGION_MAPPING(10);
+REGION_MAPPING(11);
+REGION_MAPPING(12);
+REGION_MAPPING(13);
+REGION_MAPPING(14);
+REGION_MAPPING(15);
+REGION_MAPPING(16);
+REGION_MAPPING(17);
+REGION_MAPPING(18);
+REGION_MAPPING(19);
+REGION_MAPPING(20);
+REGION_MAPPING(21);
+REGION_MAPPING(22);
+REGION_MAPPING(23);
+REGION_MAPPING(24);
+REGION_MAPPING(25);
+REGION_MAPPING(26);
+REGION_MAPPING(27);
+REGION_MAPPING(28);
+REGION_MAPPING(29);
+REGION_MAPPING(30);
+REGION_MAPPING(31);
+
+static umode_t mapping_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct nd_region *nd_region = to_nd_region(dev);
+
+ if (n < nd_region->ndr_mappings)
+ return a->mode;
+ return 0;
+}
+
+static struct attribute *mapping_attributes[] = {
+ &dev_attr_mapping0.attr,
+ &dev_attr_mapping1.attr,
+ &dev_attr_mapping2.attr,
+ &dev_attr_mapping3.attr,
+ &dev_attr_mapping4.attr,
+ &dev_attr_mapping5.attr,
+ &dev_attr_mapping6.attr,
+ &dev_attr_mapping7.attr,
+ &dev_attr_mapping8.attr,
+ &dev_attr_mapping9.attr,
+ &dev_attr_mapping10.attr,
+ &dev_attr_mapping11.attr,
+ &dev_attr_mapping12.attr,
+ &dev_attr_mapping13.attr,
+ &dev_attr_mapping14.attr,
+ &dev_attr_mapping15.attr,
+ &dev_attr_mapping16.attr,
+ &dev_attr_mapping17.attr,
+ &dev_attr_mapping18.attr,
+ &dev_attr_mapping19.attr,
+ &dev_attr_mapping20.attr,
+ &dev_attr_mapping21.attr,
+ &dev_attr_mapping22.attr,
+ &dev_attr_mapping23.attr,
+ &dev_attr_mapping24.attr,
+ &dev_attr_mapping25.attr,
+ &dev_attr_mapping26.attr,
+ &dev_attr_mapping27.attr,
+ &dev_attr_mapping28.attr,
+ &dev_attr_mapping29.attr,
+ &dev_attr_mapping30.attr,
+ &dev_attr_mapping31.attr,
+ NULL,
+};
+
+struct attribute_group nd_mapping_attribute_group = {
+ .is_visible = mapping_visible,
+ .attrs = mapping_attributes,
+};
+EXPORT_SYMBOL_GPL(nd_mapping_attribute_group);
+
+void *nd_region_provider_data(struct nd_region *nd_region)
+{
+ return nd_region->provider_data;
+}
+EXPORT_SYMBOL_GPL(nd_region_provider_data);
+
+static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc, struct device_type *dev_type,
+ const char *caller)
+{
+ struct nd_region *nd_region;
+ struct device *dev;
+ u16 i;
+
+ for (i = 0; i < ndr_desc->num_mappings; i++) {
+ struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
+ struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+ if ((nd_mapping->start | nd_mapping->size) % SZ_4K) {
+ dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not 4K aligned\n",
+ caller, dev_name(&nvdimm->dev), i);
+
+ return NULL;
+ }
+ }
+
+ nd_region = kzalloc(sizeof(struct nd_region)
+ + sizeof(struct nd_mapping) * ndr_desc->num_mappings,
+ GFP_KERNEL);
+ if (!nd_region)
+ return NULL;
+ nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL);
+ if (nd_region->id < 0) {
+ kfree(nd_region);
+ return NULL;
+ }
+
+ memcpy(nd_region->mapping, ndr_desc->nd_mapping,
+ sizeof(struct nd_mapping) * ndr_desc->num_mappings);
+ for (i = 0; i < ndr_desc->num_mappings; i++) {
+ struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
+ struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+ get_device(&nvdimm->dev);
+ }
+ nd_region->ndr_mappings = ndr_desc->num_mappings;
+ nd_region->provider_data = ndr_desc->provider_data;
+ dev = &nd_region->dev;
+ dev_set_name(dev, "region%d", nd_region->id);
+ dev->parent = &nvdimm_bus->dev;
+ dev->type = dev_type;
+ dev->groups = ndr_desc->attr_groups;
+ nd_region->ndr_size = resource_size(ndr_desc->res);
+ nd_region->ndr_start = ndr_desc->res->start;
+ nd_device_register(dev);
+
+ return nd_region;
+}
+
+struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc)
+{
+ return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type,
+ __func__);
+}
+EXPORT_SYMBOL_GPL(nvdimm_pmem_region_create);
+
+struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc)
+{
+ if (ndr_desc->num_mappings > 1)
+ return NULL;
+ return nd_region_create(nvdimm_bus, ndr_desc, &nd_blk_device_type,
+ __func__);
+}
+EXPORT_SYMBOL_GPL(nvdimm_blk_region_create);
+
+struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc)
+{
+ return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type,
+ __func__);
+}
+EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index d3ebccf4ea8b..39e7e606092a 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -26,11 +26,14 @@ enum {
ND_CMD_MAX_ELEM = 4,
ND_CMD_MAX_ENVELOPE = 16,
ND_CMD_ARS_STATUS_MAX = SZ_4K,
+ ND_MAX_MAPPINGS = 32,
};
extern struct attribute_group nvdimm_bus_attribute_group;
extern struct attribute_group nvdimm_attribute_group;
extern struct attribute_group nd_device_attribute_group;
+extern struct attribute_group nd_region_attribute_group;
+extern struct attribute_group nd_mapping_attribute_group;
struct nvdimm;
struct nvdimm_bus_descriptor;
@@ -38,6 +41,12 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
struct nvdimm *nvdimm, unsigned int cmd, void *buf,
unsigned int buf_len);
+struct nd_mapping {
+ struct nvdimm *nvdimm;
+ u64 start;
+ u64 size;
+};
+
struct nvdimm_bus_descriptor {
const struct attribute_group **attr_groups;
unsigned long dsm_mask;
@@ -52,6 +61,14 @@ struct nd_cmd_desc {
int out_sizes[ND_CMD_MAX_ELEM];
};
+struct nd_region_desc {
+ struct resource *res;
+ struct nd_mapping *nd_mapping;
+ u16 num_mappings;
+ const struct attribute_group **attr_groups;
+ void *provider_data;
+};
+
struct nvdimm_bus;
struct device;
struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
@@ -59,9 +76,11 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
struct nvdimm_bus *to_nvdimm_bus(struct device *dev);
struct nvdimm *to_nvdimm(struct device *dev);
+struct nd_region *to_nd_region(struct device *dev);
struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
const char *nvdimm_name(struct nvdimm *nvdimm);
void *nvdimm_provider_data(struct nvdimm *nvdimm);
+void *nd_region_provider_data(struct nd_region *nd_region);
struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
const struct attribute_group **groups, unsigned long flags,
unsigned long *dsm_mask);
@@ -73,4 +92,10 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
const struct nd_cmd_desc *desc, int idx, const u32 *in_field,
const u32 *out_field);
int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count);
+struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc);
+struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc);
+struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
+ struct nd_region_desc *ndr_desc);
#endif /* __LIBNVDIMM_H__ */
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox