From 18cb2aef91b37dbce2bec2f39bb1dddd0e9dd838 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 7 Aug 2010 03:26:23 +0900 Subject: percpu: handle __percpu notations in UP accessors UP accessors didn't take care of __percpu notations leading to a lot of spurious sparse warnings on UP configurations. Fix it. Signed-off-by: Namhyung Kim Signed-off-by: Tejun Heo --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b8b9084527b1..49466b13c5c6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -149,7 +149,7 @@ extern void __init percpu_init_late(void); #else /* CONFIG_SMP */ -#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) +#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); }) /* can't distinguish from other static vars, always false */ static inline bool is_kernel_percpu_address(unsigned long addr) -- cgit v1.2.3-71-gd317 From 92298e668372f2f6c8a79fb272f13d65161a4876 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 13 Aug 2010 10:22:17 +1000 Subject: PCI: provide stub pci_domain_nr function for !CONFIG_PCI configs Allows the new PCI domain aware DRM code to compile on m68k. Reported-by: Geert Uytterhoeven Signed-off-by: Dave Airlie Signed-off-by: Jesse Barnes --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b1d17956a153..c8d95e369ff4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1214,6 +1214,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn) { return NULL; } +static inline int pci_domain_nr(struct pci_bus *bus) +{ return 0; } + #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) #define dev_num_vf(d) (0) -- cgit v1.2.3-71-gd317 From a49f37eed22b74221f271811ea41323654e40dad Mon Sep 17 00:00:00 2001 From: Sachin Sanap Date: Fri, 13 Aug 2010 21:22:49 +0000 Subject: net: add Fast Ethernet driver for PXA168. Signed-off-by: Sachin Sanap Signed-off-by: David S. Miller --- drivers/net/Kconfig | 10 + drivers/net/Makefile | 1 + drivers/net/pxa168_eth.c | 1666 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pxa168_eth.h | 30 + 4 files changed, 1707 insertions(+) create mode 100644 drivers/net/pxa168_eth.c create mode 100644 include/linux/pxa168_eth.h (limited to 'include/linux') diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index ebe68395ecf8..fe581566cb26 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -928,6 +928,16 @@ config SMC91X The module will be called smc91x. If you want to compile it as a module, say M here and read . +config PXA168_ETH + tristate "Marvell pxa168 ethernet support" + depends on CPU_PXA168 + select PHYLIB + help + This driver supports the pxa168 Ethernet ports. + + To compile this driver as a module, choose M here. The module + will be called pxa168_eth. + config NET_NETX tristate "NetX Ethernet support" select MII diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 56e8c27f77ce..3e8f150c4b14 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -244,6 +244,7 @@ obj-$(CONFIG_MYRI10GE) += myri10ge/ obj-$(CONFIG_SMC91X) += smc91x.o obj-$(CONFIG_SMC911X) += smc911x.o obj-$(CONFIG_SMSC911X) += smsc911x.o +obj-$(CONFIG_PXA168_ETH) += pxa168_eth.o obj-$(CONFIG_BFIN_MAC) += bfin_mac.o obj-$(CONFIG_DM9000) += dm9000.o obj-$(CONFIG_PASEMI_MAC) += pasemi_mac_driver.o diff --git a/drivers/net/pxa168_eth.c b/drivers/net/pxa168_eth.c new file mode 100644 index 000000000000..ecc64d750cce --- /dev/null +++ b/drivers/net/pxa168_eth.c @@ -0,0 +1,1666 @@ +/* + * PXA168 ethernet driver. + * Most of the code is derived from mv643xx ethernet driver. + * + * Copyright (C) 2010 Marvell International Ltd. + * Sachin Sanap + * Philip Rakity + * Mark Brown + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * 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. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_NAME "pxa168-eth" +#define DRIVER_VERSION "0.3" + +/* + * Registers + */ + +#define PHY_ADDRESS 0x0000 +#define SMI 0x0010 +#define PORT_CONFIG 0x0400 +#define PORT_CONFIG_EXT 0x0408 +#define PORT_COMMAND 0x0410 +#define PORT_STATUS 0x0418 +#define HTPR 0x0428 +#define SDMA_CONFIG 0x0440 +#define SDMA_CMD 0x0448 +#define INT_CAUSE 0x0450 +#define INT_W_CLEAR 0x0454 +#define INT_MASK 0x0458 +#define ETH_F_RX_DESC_0 0x0480 +#define ETH_C_RX_DESC_0 0x04A0 +#define ETH_C_TX_DESC_1 0x04E4 + +/* smi register */ +#define SMI_BUSY (1 << 28) /* 0 - Write, 1 - Read */ +#define SMI_R_VALID (1 << 27) /* 0 - Write, 1 - Read */ +#define SMI_OP_W (0 << 26) /* Write operation */ +#define SMI_OP_R (1 << 26) /* Read operation */ + +#define PHY_WAIT_ITERATIONS 10 + +#define PXA168_ETH_PHY_ADDR_DEFAULT 0 +/* RX & TX descriptor command */ +#define BUF_OWNED_BY_DMA (1 << 31) + +/* RX descriptor status */ +#define RX_EN_INT (1 << 23) +#define RX_FIRST_DESC (1 << 17) +#define RX_LAST_DESC (1 << 16) +#define RX_ERROR (1 << 15) + +/* TX descriptor command */ +#define TX_EN_INT (1 << 23) +#define TX_GEN_CRC (1 << 22) +#define TX_ZERO_PADDING (1 << 18) +#define TX_FIRST_DESC (1 << 17) +#define TX_LAST_DESC (1 << 16) +#define TX_ERROR (1 << 15) + +/* SDMA_CMD */ +#define SDMA_CMD_AT (1 << 31) +#define SDMA_CMD_TXDL (1 << 24) +#define SDMA_CMD_TXDH (1 << 23) +#define SDMA_CMD_AR (1 << 15) +#define SDMA_CMD_ERD (1 << 7) + +/* Bit definitions of the Port Config Reg */ +#define PCR_HS (1 << 12) +#define PCR_EN (1 << 7) +#define PCR_PM (1 << 0) + +/* Bit definitions of the Port Config Extend Reg */ +#define PCXR_2BSM (1 << 28) +#define PCXR_DSCP_EN (1 << 21) +#define PCXR_MFL_1518 (0 << 14) +#define PCXR_MFL_1536 (1 << 14) +#define PCXR_MFL_2048 (2 << 14) +#define PCXR_MFL_64K (3 << 14) +#define PCXR_FLP (1 << 11) +#define PCXR_PRIO_TX_OFF 3 +#define PCXR_TX_HIGH_PRI (7 << PCXR_PRIO_TX_OFF) + +/* Bit definitions of the SDMA Config Reg */ +#define SDCR_BSZ_OFF 12 +#define SDCR_BSZ8 (3 << SDCR_BSZ_OFF) +#define SDCR_BSZ4 (2 << SDCR_BSZ_OFF) +#define SDCR_BSZ2 (1 << SDCR_BSZ_OFF) +#define SDCR_BSZ1 (0 << SDCR_BSZ_OFF) +#define SDCR_BLMR (1 << 6) +#define SDCR_BLMT (1 << 7) +#define SDCR_RIFB (1 << 9) +#define SDCR_RC_OFF 2 +#define SDCR_RC_MAX_RETRANS (0xf << SDCR_RC_OFF) + +/* + * Bit definitions of the Interrupt Cause Reg + * and Interrupt MASK Reg is the same + */ +#define ICR_RXBUF (1 << 0) +#define ICR_TXBUF_H (1 << 2) +#define ICR_TXBUF_L (1 << 3) +#define ICR_TXEND_H (1 << 6) +#define ICR_TXEND_L (1 << 7) +#define ICR_RXERR (1 << 8) +#define ICR_TXERR_H (1 << 10) +#define ICR_TXERR_L (1 << 11) +#define ICR_TX_UDR (1 << 13) +#define ICR_MII_CH (1 << 28) + +#define ALL_INTS (ICR_TXBUF_H | ICR_TXBUF_L | ICR_TX_UDR |\ + ICR_TXERR_H | ICR_TXERR_L |\ + ICR_TXEND_H | ICR_TXEND_L |\ + ICR_RXBUF | ICR_RXERR | ICR_MII_CH) + +#define ETH_HW_IP_ALIGN 2 /* hw aligns IP header */ + +#define NUM_RX_DESCS 64 +#define NUM_TX_DESCS 64 + +#define HASH_ADD 0 +#define HASH_DELETE 1 +#define HASH_ADDR_TABLE_SIZE 0x4000 /* 16K (1/2K address - PCR_HS == 1) */ +#define HOP_NUMBER 12 + +/* Bit definitions for Port status */ +#define PORT_SPEED_100 (1 << 0) +#define FULL_DUPLEX (1 << 1) +#define FLOW_CONTROL_ENABLED (1 << 2) +#define LINK_UP (1 << 3) + +/* Bit definitions for work to be done */ +#define WORK_LINK (1 << 0) +#define WORK_TX_DONE (1 << 1) + +/* + * Misc definitions. + */ +#define SKB_DMA_REALIGN ((PAGE_SIZE - NET_SKB_PAD) % SMP_CACHE_BYTES) + +struct rx_desc { + u32 cmd_sts; /* Descriptor command status */ + u16 byte_cnt; /* Descriptor buffer byte count */ + u16 buf_size; /* Buffer size */ + u32 buf_ptr; /* Descriptor buffer pointer */ + u32 next_desc_ptr; /* Next descriptor pointer */ +}; + +struct tx_desc { + u32 cmd_sts; /* Command/status field */ + u16 reserved; + u16 byte_cnt; /* buffer byte count */ + u32 buf_ptr; /* pointer to buffer for this descriptor */ + u32 next_desc_ptr; /* Pointer to next descriptor */ +}; + +struct pxa168_eth_private { + int port_num; /* User Ethernet port number */ + + int rx_resource_err; /* Rx ring resource error flag */ + + /* Next available and first returning Rx resource */ + int rx_curr_desc_q, rx_used_desc_q; + + /* Next available and first returning Tx resource */ + int tx_curr_desc_q, tx_used_desc_q; + + struct rx_desc *p_rx_desc_area; + dma_addr_t rx_desc_dma; + int rx_desc_area_size; + struct sk_buff **rx_skb; + + struct tx_desc *p_tx_desc_area; + dma_addr_t tx_desc_dma; + int tx_desc_area_size; + struct sk_buff **tx_skb; + + struct work_struct tx_timeout_task; + + struct net_device *dev; + struct napi_struct napi; + u8 work_todo; + int skb_size; + + struct net_device_stats stats; + /* Size of Tx Ring per queue */ + int tx_ring_size; + /* Number of tx descriptors in use */ + int tx_desc_count; + /* Size of Rx Ring per queue */ + int rx_ring_size; + /* Number of rx descriptors in use */ + int rx_desc_count; + + /* + * Used in case RX Ring is empty, which can occur when + * system does not have resources (skb's) + */ + struct timer_list timeout; + struct mii_bus *smi_bus; + struct phy_device *phy; + + /* clock */ + struct clk *clk; + struct pxa168_eth_platform_data *pd; + /* + * Ethernet controller base address. + */ + void __iomem *base; + + /* Pointer to the hardware address filter table */ + void *htpr; + dma_addr_t htpr_dma; +}; + +struct addr_table_entry { + __le32 lo; + __le32 hi; +}; + +/* Bit fields of a Hash Table Entry */ +enum hash_table_entry { + HASH_ENTRY_VALID = 1, + SKIP = 2, + HASH_ENTRY_RECEIVE_DISCARD = 4, + HASH_ENTRY_RECEIVE_DISCARD_BIT = 2 +}; + +static int pxa168_get_settings(struct net_device *dev, struct ethtool_cmd *cmd); +static int pxa168_set_settings(struct net_device *dev, struct ethtool_cmd *cmd); +static int pxa168_init_hw(struct pxa168_eth_private *pep); +static void eth_port_reset(struct net_device *dev); +static void eth_port_start(struct net_device *dev); +static int pxa168_eth_open(struct net_device *dev); +static int pxa168_eth_stop(struct net_device *dev); +static int ethernet_phy_setup(struct net_device *dev); + +static inline u32 rdl(struct pxa168_eth_private *pep, int offset) +{ + return readl(pep->base + offset); +} + +static inline void wrl(struct pxa168_eth_private *pep, int offset, u32 data) +{ + writel(data, pep->base + offset); +} + +static void abort_dma(struct pxa168_eth_private *pep) +{ + int delay; + int max_retries = 40; + + do { + wrl(pep, SDMA_CMD, SDMA_CMD_AR | SDMA_CMD_AT); + udelay(100); + + delay = 10; + while ((rdl(pep, SDMA_CMD) & (SDMA_CMD_AR | SDMA_CMD_AT)) + && delay-- > 0) { + udelay(10); + } + } while (max_retries-- > 0 && delay <= 0); + + if (max_retries <= 0) + printk(KERN_ERR "%s : DMA Stuck\n", __func__); +} + +static int ethernet_phy_get(struct pxa168_eth_private *pep) +{ + unsigned int reg_data; + + reg_data = rdl(pep, PHY_ADDRESS); + + return (reg_data >> (5 * pep->port_num)) & 0x1f; +} + +static void ethernet_phy_set_addr(struct pxa168_eth_private *pep, int phy_addr) +{ + u32 reg_data; + int addr_shift = 5 * pep->port_num; + + reg_data = rdl(pep, PHY_ADDRESS); + reg_data &= ~(0x1f << addr_shift); + reg_data |= (phy_addr & 0x1f) << addr_shift; + wrl(pep, PHY_ADDRESS, reg_data); +} + +static void ethernet_phy_reset(struct pxa168_eth_private *pep) +{ + int data; + + data = phy_read(pep->phy, MII_BMCR); + if (data < 0) + return; + + data |= BMCR_RESET; + if (phy_write(pep->phy, MII_BMCR, data) < 0) + return; + + do { + data = phy_read(pep->phy, MII_BMCR); + } while (data >= 0 && data & BMCR_RESET); +} + +static void rxq_refill(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct sk_buff *skb; + struct rx_desc *p_used_rx_desc; + int used_rx_desc; + + while (pep->rx_desc_count < pep->rx_ring_size) { + int size; + + skb = dev_alloc_skb(pep->skb_size); + if (!skb) + break; + if (SKB_DMA_REALIGN) + skb_reserve(skb, SKB_DMA_REALIGN); + pep->rx_desc_count++; + /* Get 'used' Rx descriptor */ + used_rx_desc = pep->rx_used_desc_q; + p_used_rx_desc = &pep->p_rx_desc_area[used_rx_desc]; + size = skb->end - skb->data; + p_used_rx_desc->buf_ptr = dma_map_single(NULL, + skb->data, + size, + DMA_FROM_DEVICE); + p_used_rx_desc->buf_size = size; + pep->rx_skb[used_rx_desc] = skb; + + /* Return the descriptor to DMA ownership */ + wmb(); + p_used_rx_desc->cmd_sts = BUF_OWNED_BY_DMA | RX_EN_INT; + wmb(); + + /* Move the used descriptor pointer to the next descriptor */ + pep->rx_used_desc_q = (used_rx_desc + 1) % pep->rx_ring_size; + + /* Any Rx return cancels the Rx resource error status */ + pep->rx_resource_err = 0; + + skb_reserve(skb, ETH_HW_IP_ALIGN); + } + + /* + * If RX ring is empty of SKB, set a timer to try allocating + * again at a later time. + */ + if (pep->rx_desc_count == 0) { + pep->timeout.expires = jiffies + (HZ / 10); + add_timer(&pep->timeout); + } +} + +static inline void rxq_refill_timer_wrapper(unsigned long data) +{ + struct pxa168_eth_private *pep = (void *)data; + napi_schedule(&pep->napi); +} + +static inline u8 flip_8_bits(u8 x) +{ + return (((x) & 0x01) << 3) | (((x) & 0x02) << 1) + | (((x) & 0x04) >> 1) | (((x) & 0x08) >> 3) + | (((x) & 0x10) << 3) | (((x) & 0x20) << 1) + | (((x) & 0x40) >> 1) | (((x) & 0x80) >> 3); +} + +static void nibble_swap_every_byte(unsigned char *mac_addr) +{ + int i; + for (i = 0; i < ETH_ALEN; i++) { + mac_addr[i] = ((mac_addr[i] & 0x0f) << 4) | + ((mac_addr[i] & 0xf0) >> 4); + } +} + +static void inverse_every_nibble(unsigned char *mac_addr) +{ + int i; + for (i = 0; i < ETH_ALEN; i++) + mac_addr[i] = flip_8_bits(mac_addr[i]); +} + +/* + * ---------------------------------------------------------------------------- + * This function will calculate the hash function of the address. + * Inputs + * mac_addr_orig - MAC address. + * Outputs + * return the calculated entry. + */ +static u32 hash_function(unsigned char *mac_addr_orig) +{ + u32 hash_result; + u32 addr0; + u32 addr1; + u32 addr2; + u32 addr3; + unsigned char mac_addr[ETH_ALEN]; + + /* Make a copy of MAC address since we are going to performe bit + * operations on it + */ + memcpy(mac_addr, mac_addr_orig, ETH_ALEN); + + nibble_swap_every_byte(mac_addr); + inverse_every_nibble(mac_addr); + + addr0 = (mac_addr[5] >> 2) & 0x3f; + addr1 = (mac_addr[5] & 0x03) | (((mac_addr[4] & 0x7f)) << 2); + addr2 = ((mac_addr[4] & 0x80) >> 7) | mac_addr[3] << 1; + addr3 = (mac_addr[2] & 0xff) | ((mac_addr[1] & 1) << 8); + + hash_result = (addr0 << 9) | (addr1 ^ addr2 ^ addr3); + hash_result = hash_result & 0x07ff; + return hash_result; +} + +/* + * ---------------------------------------------------------------------------- + * This function will add/del an entry to the address table. + * Inputs + * pep - ETHERNET . + * mac_addr - MAC address. + * skip - if 1, skip this address.Used in case of deleting an entry which is a + * part of chain in the hash table.We cant just delete the entry since + * that will break the chain.We need to defragment the tables time to + * time. + * rd - 0 Discard packet upon match. + * - 1 Receive packet upon match. + * Outputs + * address table entry is added/deleted. + * 0 if success. + * -ENOSPC if table full + */ +static int add_del_hash_entry(struct pxa168_eth_private *pep, + unsigned char *mac_addr, + u32 rd, u32 skip, int del) +{ + struct addr_table_entry *entry, *start; + u32 new_high; + u32 new_low; + u32 i; + + new_low = (((mac_addr[1] >> 4) & 0xf) << 15) + | (((mac_addr[1] >> 0) & 0xf) << 11) + | (((mac_addr[0] >> 4) & 0xf) << 7) + | (((mac_addr[0] >> 0) & 0xf) << 3) + | (((mac_addr[3] >> 4) & 0x1) << 31) + | (((mac_addr[3] >> 0) & 0xf) << 27) + | (((mac_addr[2] >> 4) & 0xf) << 23) + | (((mac_addr[2] >> 0) & 0xf) << 19) + | (skip << SKIP) | (rd << HASH_ENTRY_RECEIVE_DISCARD_BIT) + | HASH_ENTRY_VALID; + + new_high = (((mac_addr[5] >> 4) & 0xf) << 15) + | (((mac_addr[5] >> 0) & 0xf) << 11) + | (((mac_addr[4] >> 4) & 0xf) << 7) + | (((mac_addr[4] >> 0) & 0xf) << 3) + | (((mac_addr[3] >> 5) & 0x7) << 0); + + /* + * Pick the appropriate table, start scanning for free/reusable + * entries at the index obtained by hashing the specified MAC address + */ + start = (struct addr_table_entry *)(pep->htpr); + entry = start + hash_function(mac_addr); + for (i = 0; i < HOP_NUMBER; i++) { + if (!(le32_to_cpu(entry->lo) & HASH_ENTRY_VALID)) { + break; + } else { + /* if same address put in same position */ + if (((le32_to_cpu(entry->lo) & 0xfffffff8) == + (new_low & 0xfffffff8)) && + (le32_to_cpu(entry->hi) == new_high)) { + break; + } + } + if (entry == start + 0x7ff) + entry = start; + else + entry++; + } + + if (((le32_to_cpu(entry->lo) & 0xfffffff8) != (new_low & 0xfffffff8)) && + (le32_to_cpu(entry->hi) != new_high) && del) + return 0; + + if (i == HOP_NUMBER) { + if (!del) { + printk(KERN_INFO "%s: table section is full, need to " + "move to 16kB implementation?\n", + __FILE__); + return -ENOSPC; + } else + return 0; + } + + /* + * Update the selected entry + */ + if (del) { + entry->hi = 0; + entry->lo = 0; + } else { + entry->hi = cpu_to_le32(new_high); + entry->lo = cpu_to_le32(new_low); + } + + return 0; +} + +/* + * ---------------------------------------------------------------------------- + * Create an addressTable entry from MAC address info + * found in the specifed net_device struct + * + * Input : pointer to ethernet interface network device structure + * Output : N/A + */ +static void update_hash_table_mac_address(struct pxa168_eth_private *pep, + unsigned char *oaddr, + unsigned char *addr) +{ + /* Delete old entry */ + if (oaddr) + add_del_hash_entry(pep, oaddr, 1, 0, HASH_DELETE); + /* Add new entry */ + add_del_hash_entry(pep, addr, 1, 0, HASH_ADD); +} + +static int init_hash_table(struct pxa168_eth_private *pep) +{ + /* + * Hardware expects CPU to build a hash table based on a predefined + * hash function and populate it based on hardware address. The + * location of the hash table is identified by 32-bit pointer stored + * in HTPR internal register. Two possible sizes exists for the hash + * table 8kB (256kB of DRAM required (4 x 64 kB banks)) and 1/2kB + * (16kB of DRAM required (4 x 4 kB banks)).We currently only support + * 1/2kB. + */ + /* TODO: Add support for 8kB hash table and alternative hash + * function.Driver can dynamically switch to them if the 1/2kB hash + * table is full. + */ + if (pep->htpr == NULL) { + pep->htpr = dma_alloc_coherent(pep->dev->dev.parent, + HASH_ADDR_TABLE_SIZE, + &pep->htpr_dma, GFP_KERNEL); + if (pep->htpr == NULL) + return -ENOMEM; + } + memset(pep->htpr, 0, HASH_ADDR_TABLE_SIZE); + wrl(pep, HTPR, pep->htpr_dma); + return 0; +} + +static void pxa168_eth_set_rx_mode(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct netdev_hw_addr *ha; + u32 val; + + val = rdl(pep, PORT_CONFIG); + if (dev->flags & IFF_PROMISC) + val |= PCR_PM; + else + val &= ~PCR_PM; + wrl(pep, PORT_CONFIG, val); + + /* + * Remove the old list of MAC address and add dev->addr + * and multicast address. + */ + memset(pep->htpr, 0, HASH_ADDR_TABLE_SIZE); + update_hash_table_mac_address(pep, NULL, dev->dev_addr); + + netdev_for_each_mc_addr(ha, dev) + update_hash_table_mac_address(pep, NULL, ha->addr); +} + +static int pxa168_eth_set_mac_address(struct net_device *dev, void *addr) +{ + struct sockaddr *sa = addr; + struct pxa168_eth_private *pep = netdev_priv(dev); + unsigned char oldMac[ETH_ALEN]; + + if (!is_valid_ether_addr(sa->sa_data)) + return -EINVAL; + memcpy(oldMac, dev->dev_addr, ETH_ALEN); + memcpy(dev->dev_addr, sa->sa_data, ETH_ALEN); + netif_addr_lock_bh(dev); + update_hash_table_mac_address(pep, oldMac, dev->dev_addr); + netif_addr_unlock_bh(dev); + return 0; +} + +static void eth_port_start(struct net_device *dev) +{ + unsigned int val = 0; + struct pxa168_eth_private *pep = netdev_priv(dev); + int tx_curr_desc, rx_curr_desc; + + /* Perform PHY reset, if there is a PHY. */ + if (pep->phy != NULL) { + struct ethtool_cmd cmd; + + pxa168_get_settings(pep->dev, &cmd); + ethernet_phy_reset(pep); + pxa168_set_settings(pep->dev, &cmd); + } + + /* Assignment of Tx CTRP of given queue */ + tx_curr_desc = pep->tx_curr_desc_q; + wrl(pep, ETH_C_TX_DESC_1, + (u32) ((struct tx_desc *)pep->tx_desc_dma + tx_curr_desc)); + + /* Assignment of Rx CRDP of given queue */ + rx_curr_desc = pep->rx_curr_desc_q; + wrl(pep, ETH_C_RX_DESC_0, + (u32) ((struct rx_desc *)pep->rx_desc_dma + rx_curr_desc)); + + wrl(pep, ETH_F_RX_DESC_0, + (u32) ((struct rx_desc *)pep->rx_desc_dma + rx_curr_desc)); + + /* Clear all interrupts */ + wrl(pep, INT_CAUSE, 0); + + /* Enable all interrupts for receive, transmit and error. */ + wrl(pep, INT_MASK, ALL_INTS); + + val = rdl(pep, PORT_CONFIG); + val |= PCR_EN; + wrl(pep, PORT_CONFIG, val); + + /* Start RX DMA engine */ + val = rdl(pep, SDMA_CMD); + val |= SDMA_CMD_ERD; + wrl(pep, SDMA_CMD, val); +} + +static void eth_port_reset(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + unsigned int val = 0; + + /* Stop all interrupts for receive, transmit and error. */ + wrl(pep, INT_MASK, 0); + + /* Clear all interrupts */ + wrl(pep, INT_CAUSE, 0); + + /* Stop RX DMA */ + val = rdl(pep, SDMA_CMD); + val &= ~SDMA_CMD_ERD; /* abort dma command */ + + /* Abort any transmit and receive operations and put DMA + * in idle state. + */ + abort_dma(pep); + + /* Disable port */ + val = rdl(pep, PORT_CONFIG); + val &= ~PCR_EN; + wrl(pep, PORT_CONFIG, val); +} + +/* + * txq_reclaim - Free the tx desc data for completed descriptors + * If force is non-zero, frees uncompleted descriptors as well + */ +static int txq_reclaim(struct net_device *dev, int force) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct tx_desc *desc; + u32 cmd_sts; + struct sk_buff *skb; + int tx_index; + dma_addr_t addr; + int count; + int released = 0; + + netif_tx_lock(dev); + + pep->work_todo &= ~WORK_TX_DONE; + while (pep->tx_desc_count > 0) { + tx_index = pep->tx_used_desc_q; + desc = &pep->p_tx_desc_area[tx_index]; + cmd_sts = desc->cmd_sts; + if (!force && (cmd_sts & BUF_OWNED_BY_DMA)) { + if (released > 0) { + goto txq_reclaim_end; + } else { + released = -1; + goto txq_reclaim_end; + } + } + pep->tx_used_desc_q = (tx_index + 1) % pep->tx_ring_size; + pep->tx_desc_count--; + addr = desc->buf_ptr; + count = desc->byte_cnt; + skb = pep->tx_skb[tx_index]; + if (skb) + pep->tx_skb[tx_index] = NULL; + + if (cmd_sts & TX_ERROR) { + if (net_ratelimit()) + printk(KERN_ERR "%s: Error in TX\n", dev->name); + dev->stats.tx_errors++; + } + dma_unmap_single(NULL, addr, count, DMA_TO_DEVICE); + if (skb) + dev_kfree_skb_irq(skb); + released++; + } +txq_reclaim_end: + netif_tx_unlock(dev); + return released; +} + +static void pxa168_eth_tx_timeout(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + + printk(KERN_INFO "%s: TX timeout desc_count %d\n", + dev->name, pep->tx_desc_count); + + schedule_work(&pep->tx_timeout_task); +} + +static void pxa168_eth_tx_timeout_task(struct work_struct *work) +{ + struct pxa168_eth_private *pep = container_of(work, + struct pxa168_eth_private, + tx_timeout_task); + struct net_device *dev = pep->dev; + pxa168_eth_stop(dev); + pxa168_eth_open(dev); +} + +static int rxq_process(struct net_device *dev, int budget) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + unsigned int received_packets = 0; + struct sk_buff *skb; + + while (budget-- > 0) { + int rx_next_curr_desc, rx_curr_desc, rx_used_desc; + struct rx_desc *rx_desc; + unsigned int cmd_sts; + + /* Do not process Rx ring in case of Rx ring resource error */ + if (pep->rx_resource_err) + break; + rx_curr_desc = pep->rx_curr_desc_q; + rx_used_desc = pep->rx_used_desc_q; + rx_desc = &pep->p_rx_desc_area[rx_curr_desc]; + cmd_sts = rx_desc->cmd_sts; + rmb(); + if (cmd_sts & (BUF_OWNED_BY_DMA)) + break; + skb = pep->rx_skb[rx_curr_desc]; + pep->rx_skb[rx_curr_desc] = NULL; + + rx_next_curr_desc = (rx_curr_desc + 1) % pep->rx_ring_size; + pep->rx_curr_desc_q = rx_next_curr_desc; + + /* Rx descriptors exhausted. */ + /* Set the Rx ring resource error flag */ + if (rx_next_curr_desc == rx_used_desc) + pep->rx_resource_err = 1; + pep->rx_desc_count--; + dma_unmap_single(NULL, rx_desc->buf_ptr, + rx_desc->buf_size, + DMA_FROM_DEVICE); + received_packets++; + /* + * Update statistics. + * Note byte count includes 4 byte CRC count + */ + stats->rx_packets++; + stats->rx_bytes += rx_desc->byte_cnt; + /* + * In case received a packet without first / last bits on OR + * the error summary bit is on, the packets needs to be droped. + */ + if (((cmd_sts & (RX_FIRST_DESC | RX_LAST_DESC)) != + (RX_FIRST_DESC | RX_LAST_DESC)) + || (cmd_sts & RX_ERROR)) { + + stats->rx_dropped++; + if ((cmd_sts & (RX_FIRST_DESC | RX_LAST_DESC)) != + (RX_FIRST_DESC | RX_LAST_DESC)) { + if (net_ratelimit()) + printk(KERN_ERR + "%s: Rx pkt on multiple desc\n", + dev->name); + } + if (cmd_sts & RX_ERROR) + stats->rx_errors++; + dev_kfree_skb_irq(skb); + } else { + /* + * The -4 is for the CRC in the trailer of the + * received packet + */ + skb_put(skb, rx_desc->byte_cnt - 4); + skb->protocol = eth_type_trans(skb, dev); + netif_receive_skb(skb); + } + dev->last_rx = jiffies; + } + /* Fill RX ring with skb's */ + rxq_refill(dev); + return received_packets; +} + +static int pxa168_eth_collect_events(struct pxa168_eth_private *pep, + struct net_device *dev) +{ + u32 icr; + int ret = 0; + + icr = rdl(pep, INT_CAUSE); + if (icr == 0) + return IRQ_NONE; + + wrl(pep, INT_CAUSE, ~icr); + if (icr & (ICR_TXBUF_H | ICR_TXBUF_L)) { + pep->work_todo |= WORK_TX_DONE; + ret = 1; + } + if (icr & ICR_RXBUF) + ret = 1; + if (icr & ICR_MII_CH) { + pep->work_todo |= WORK_LINK; + ret = 1; + } + return ret; +} + +static void handle_link_event(struct pxa168_eth_private *pep) +{ + struct net_device *dev = pep->dev; + u32 port_status; + int speed; + int duplex; + int fc; + + port_status = rdl(pep, PORT_STATUS); + if (!(port_status & LINK_UP)) { + if (netif_carrier_ok(dev)) { + printk(KERN_INFO "%s: link down\n", dev->name); + netif_carrier_off(dev); + txq_reclaim(dev, 1); + } + return; + } + if (port_status & PORT_SPEED_100) + speed = 100; + else + speed = 10; + + duplex = (port_status & FULL_DUPLEX) ? 1 : 0; + fc = (port_status & FLOW_CONTROL_ENABLED) ? 1 : 0; + printk(KERN_INFO "%s: link up, %d Mb/s, %s duplex, " + "flow control %sabled\n", dev->name, + speed, duplex ? "full" : "half", fc ? "en" : "dis"); + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); +} + +static irqreturn_t pxa168_eth_int_handler(int irq, void *dev_id) +{ + struct net_device *dev = (struct net_device *)dev_id; + struct pxa168_eth_private *pep = netdev_priv(dev); + + if (unlikely(!pxa168_eth_collect_events(pep, dev))) + return IRQ_NONE; + /* Disable interrupts */ + wrl(pep, INT_MASK, 0); + napi_schedule(&pep->napi); + return IRQ_HANDLED; +} + +static void pxa168_eth_recalc_skb_size(struct pxa168_eth_private *pep) +{ + int skb_size; + + /* + * Reserve 2+14 bytes for an ethernet header (the hardware + * automatically prepends 2 bytes of dummy data to each + * received packet), 16 bytes for up to four VLAN tags, and + * 4 bytes for the trailing FCS -- 36 bytes total. + */ + skb_size = pep->dev->mtu + 36; + + /* + * Make sure that the skb size is a multiple of 8 bytes, as + * the lower three bits of the receive descriptor's buffer + * size field are ignored by the hardware. + */ + pep->skb_size = (skb_size + 7) & ~7; + + /* + * If NET_SKB_PAD is smaller than a cache line, + * netdev_alloc_skb() will cause skb->data to be misaligned + * to a cache line boundary. If this is the case, include + * some extra space to allow re-aligning the data area. + */ + pep->skb_size += SKB_DMA_REALIGN; + +} + +static int set_port_config_ext(struct pxa168_eth_private *pep) +{ + int skb_size; + + pxa168_eth_recalc_skb_size(pep); + if (pep->skb_size <= 1518) + skb_size = PCXR_MFL_1518; + else if (pep->skb_size <= 1536) + skb_size = PCXR_MFL_1536; + else if (pep->skb_size <= 2048) + skb_size = PCXR_MFL_2048; + else + skb_size = PCXR_MFL_64K; + + /* Extended Port Configuration */ + wrl(pep, + PORT_CONFIG_EXT, PCXR_2BSM | /* Two byte prefix aligns IP hdr */ + PCXR_DSCP_EN | /* Enable DSCP in IP */ + skb_size | PCXR_FLP | /* do not force link pass */ + PCXR_TX_HIGH_PRI); /* Transmit - high priority queue */ + + return 0; +} + +static int pxa168_init_hw(struct pxa168_eth_private *pep) +{ + int err = 0; + + /* Disable interrupts */ + wrl(pep, INT_MASK, 0); + wrl(pep, INT_CAUSE, 0); + /* Write to ICR to clear interrupts. */ + wrl(pep, INT_W_CLEAR, 0); + /* Abort any transmit and receive operations and put DMA + * in idle state. + */ + abort_dma(pep); + /* Initialize address hash table */ + err = init_hash_table(pep); + if (err) + return err; + /* SDMA configuration */ + wrl(pep, SDMA_CONFIG, SDCR_BSZ8 | /* Burst size = 32 bytes */ + SDCR_RIFB | /* Rx interrupt on frame */ + SDCR_BLMT | /* Little endian transmit */ + SDCR_BLMR | /* Little endian receive */ + SDCR_RC_MAX_RETRANS); /* Max retransmit count */ + /* Port Configuration */ + wrl(pep, PORT_CONFIG, PCR_HS); /* Hash size is 1/2kb */ + set_port_config_ext(pep); + + return err; +} + +static int rxq_init(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct rx_desc *p_rx_desc; + int size = 0, i = 0; + int rx_desc_num = pep->rx_ring_size; + + /* Allocate RX skb rings */ + pep->rx_skb = kmalloc(sizeof(*pep->rx_skb) * pep->rx_ring_size, + GFP_KERNEL); + if (!pep->rx_skb) { + printk(KERN_ERR "%s: Cannot alloc RX skb ring\n", dev->name); + return -ENOMEM; + } + /* Allocate RX ring */ + pep->rx_desc_count = 0; + size = pep->rx_ring_size * sizeof(struct rx_desc); + pep->rx_desc_area_size = size; + pep->p_rx_desc_area = dma_alloc_coherent(pep->dev->dev.parent, size, + &pep->rx_desc_dma, GFP_KERNEL); + if (!pep->p_rx_desc_area) { + printk(KERN_ERR "%s: Cannot alloc RX ring (size %d bytes)\n", + dev->name, size); + goto out; + } + memset((void *)pep->p_rx_desc_area, 0, size); + /* initialize the next_desc_ptr links in the Rx descriptors ring */ + p_rx_desc = (struct rx_desc *)pep->p_rx_desc_area; + for (i = 0; i < rx_desc_num; i++) { + p_rx_desc[i].next_desc_ptr = pep->rx_desc_dma + + ((i + 1) % rx_desc_num) * sizeof(struct rx_desc); + } + /* Save Rx desc pointer to driver struct. */ + pep->rx_curr_desc_q = 0; + pep->rx_used_desc_q = 0; + pep->rx_desc_area_size = rx_desc_num * sizeof(struct rx_desc); + return 0; +out: + kfree(pep->rx_skb); + return -ENOMEM; +} + +static void rxq_deinit(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + int curr; + + /* Free preallocated skb's on RX rings */ + for (curr = 0; pep->rx_desc_count && curr < pep->rx_ring_size; curr++) { + if (pep->rx_skb[curr]) { + dev_kfree_skb(pep->rx_skb[curr]); + pep->rx_desc_count--; + } + } + if (pep->rx_desc_count) + printk(KERN_ERR + "Error in freeing Rx Ring. %d skb's still\n", + pep->rx_desc_count); + /* Free RX ring */ + if (pep->p_rx_desc_area) + dma_free_coherent(pep->dev->dev.parent, pep->rx_desc_area_size, + pep->p_rx_desc_area, pep->rx_desc_dma); + kfree(pep->rx_skb); +} + +static int txq_init(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct tx_desc *p_tx_desc; + int size = 0, i = 0; + int tx_desc_num = pep->tx_ring_size; + + pep->tx_skb = kmalloc(sizeof(*pep->tx_skb) * pep->tx_ring_size, + GFP_KERNEL); + if (!pep->tx_skb) { + printk(KERN_ERR "%s: Cannot alloc TX skb ring\n", dev->name); + return -ENOMEM; + } + /* Allocate TX ring */ + pep->tx_desc_count = 0; + size = pep->tx_ring_size * sizeof(struct tx_desc); + pep->tx_desc_area_size = size; + pep->p_tx_desc_area = dma_alloc_coherent(pep->dev->dev.parent, size, + &pep->tx_desc_dma, GFP_KERNEL); + if (!pep->p_tx_desc_area) { + printk(KERN_ERR "%s: Cannot allocate Tx Ring (size %d bytes)\n", + dev->name, size); + goto out; + } + memset((void *)pep->p_tx_desc_area, 0, pep->tx_desc_area_size); + /* Initialize the next_desc_ptr links in the Tx descriptors ring */ + p_tx_desc = (struct tx_desc *)pep->p_tx_desc_area; + for (i = 0; i < tx_desc_num; i++) { + p_tx_desc[i].next_desc_ptr = pep->tx_desc_dma + + ((i + 1) % tx_desc_num) * sizeof(struct tx_desc); + } + pep->tx_curr_desc_q = 0; + pep->tx_used_desc_q = 0; + pep->tx_desc_area_size = tx_desc_num * sizeof(struct tx_desc); + return 0; +out: + kfree(pep->tx_skb); + return -ENOMEM; +} + +static void txq_deinit(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + + /* Free outstanding skb's on TX ring */ + txq_reclaim(dev, 1); + BUG_ON(pep->tx_used_desc_q != pep->tx_curr_desc_q); + /* Free TX ring */ + if (pep->p_tx_desc_area) + dma_free_coherent(pep->dev->dev.parent, pep->tx_desc_area_size, + pep->p_tx_desc_area, pep->tx_desc_dma); + kfree(pep->tx_skb); +} + +static int pxa168_eth_open(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + int err; + + err = request_irq(dev->irq, pxa168_eth_int_handler, + IRQF_DISABLED, dev->name, dev); + if (err) { + dev_printk(KERN_ERR, &dev->dev, "can't assign irq\n"); + return -EAGAIN; + } + pep->rx_resource_err = 0; + err = rxq_init(dev); + if (err != 0) + goto out_free_irq; + err = txq_init(dev); + if (err != 0) + goto out_free_rx_skb; + pep->rx_used_desc_q = 0; + pep->rx_curr_desc_q = 0; + + /* Fill RX ring with skb's */ + rxq_refill(dev); + pep->rx_used_desc_q = 0; + pep->rx_curr_desc_q = 0; + netif_carrier_off(dev); + eth_port_start(dev); + napi_enable(&pep->napi); + return 0; +out_free_rx_skb: + rxq_deinit(dev); +out_free_irq: + free_irq(dev->irq, dev); + return err; +} + +static int pxa168_eth_stop(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + eth_port_reset(dev); + + /* Disable interrupts */ + wrl(pep, INT_MASK, 0); + wrl(pep, INT_CAUSE, 0); + /* Write to ICR to clear interrupts. */ + wrl(pep, INT_W_CLEAR, 0); + napi_disable(&pep->napi); + del_timer_sync(&pep->timeout); + netif_carrier_off(dev); + free_irq(dev->irq, dev); + rxq_deinit(dev); + txq_deinit(dev); + + return 0; +} + +static int pxa168_eth_change_mtu(struct net_device *dev, int mtu) +{ + int retval; + struct pxa168_eth_private *pep = netdev_priv(dev); + + if ((mtu > 9500) || (mtu < 68)) + return -EINVAL; + + dev->mtu = mtu; + retval = set_port_config_ext(pep); + + if (!netif_running(dev)) + return 0; + + /* + * Stop and then re-open the interface. This will allocate RX + * skbs of the new MTU. + * There is a possible danger that the open will not succeed, + * due to memory being full. + */ + pxa168_eth_stop(dev); + if (pxa168_eth_open(dev)) { + dev_printk(KERN_ERR, &dev->dev, + "fatal error on re-opening device after " + "MTU change\n"); + } + + return 0; +} + +static int eth_alloc_tx_desc_index(struct pxa168_eth_private *pep) +{ + int tx_desc_curr; + + tx_desc_curr = pep->tx_curr_desc_q; + pep->tx_curr_desc_q = (tx_desc_curr + 1) % pep->tx_ring_size; + BUG_ON(pep->tx_curr_desc_q == pep->tx_used_desc_q); + pep->tx_desc_count++; + + return tx_desc_curr; +} + +static int pxa168_rx_poll(struct napi_struct *napi, int budget) +{ + struct pxa168_eth_private *pep = + container_of(napi, struct pxa168_eth_private, napi); + struct net_device *dev = pep->dev; + int work_done = 0; + + if (unlikely(pep->work_todo & WORK_LINK)) { + pep->work_todo &= ~(WORK_LINK); + handle_link_event(pep); + } + /* + * We call txq_reclaim every time since in NAPI interupts are disabled + * and due to this we miss the TX_DONE interrupt,which is not updated in + * interrupt status register. + */ + txq_reclaim(dev, 0); + if (netif_queue_stopped(dev) + && pep->tx_ring_size - pep->tx_desc_count > 1) { + netif_wake_queue(dev); + } + work_done = rxq_process(dev, budget); + if (work_done < budget) { + napi_complete(napi); + wrl(pep, INT_MASK, ALL_INTS); + } + + return work_done; +} + +static int pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct tx_desc *desc; + int tx_index; + int length; + + tx_index = eth_alloc_tx_desc_index(pep); + desc = &pep->p_tx_desc_area[tx_index]; + length = skb->len; + pep->tx_skb[tx_index] = skb; + desc->byte_cnt = length; + desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE); + wmb(); + desc->cmd_sts = BUF_OWNED_BY_DMA | TX_GEN_CRC | TX_FIRST_DESC | + TX_ZERO_PADDING | TX_LAST_DESC | TX_EN_INT; + wmb(); + wrl(pep, SDMA_CMD, SDMA_CMD_TXDH | SDMA_CMD_ERD); + + stats->tx_bytes += skb->len; + stats->tx_packets++; + dev->trans_start = jiffies; + if (pep->tx_ring_size - pep->tx_desc_count <= 1) { + /* We handled the current skb, but now we are out of space.*/ + netif_stop_queue(dev); + } + + return NETDEV_TX_OK; +} + +static int smi_wait_ready(struct pxa168_eth_private *pep) +{ + int i = 0; + + /* wait for the SMI register to become available */ + for (i = 0; rdl(pep, SMI) & SMI_BUSY; i++) { + if (i == PHY_WAIT_ITERATIONS) + return -ETIMEDOUT; + msleep(10); + } + + return 0; +} + +static int pxa168_smi_read(struct mii_bus *bus, int phy_addr, int regnum) +{ + struct pxa168_eth_private *pep = bus->priv; + int i = 0; + int val; + + if (smi_wait_ready(pep)) { + printk(KERN_WARNING "pxa168_eth: SMI bus busy timeout\n"); + return -ETIMEDOUT; + } + wrl(pep, SMI, (phy_addr << 16) | (regnum << 21) | SMI_OP_R); + /* now wait for the data to be valid */ + for (i = 0; !((val = rdl(pep, SMI)) & SMI_R_VALID); i++) { + if (i == PHY_WAIT_ITERATIONS) { + printk(KERN_WARNING + "pxa168_eth: SMI bus read not valid\n"); + return -ENODEV; + } + msleep(10); + } + + return val & 0xffff; +} + +static int pxa168_smi_write(struct mii_bus *bus, int phy_addr, int regnum, + u16 value) +{ + struct pxa168_eth_private *pep = bus->priv; + + if (smi_wait_ready(pep)) { + printk(KERN_WARNING "pxa168_eth: SMI bus busy timeout\n"); + return -ETIMEDOUT; + } + + wrl(pep, SMI, (phy_addr << 16) | (regnum << 21) | + SMI_OP_W | (value & 0xffff)); + + if (smi_wait_ready(pep)) { + printk(KERN_ERR "pxa168_eth: SMI bus busy timeout\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int pxa168_eth_do_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + if (pep->phy != NULL) + return phy_mii_ioctl(pep->phy, if_mii(ifr), cmd); + + return -EOPNOTSUPP; +} + +static struct phy_device *phy_scan(struct pxa168_eth_private *pep, int phy_addr) +{ + struct mii_bus *bus = pep->smi_bus; + struct phy_device *phydev; + int start; + int num; + int i; + + if (phy_addr == PXA168_ETH_PHY_ADDR_DEFAULT) { + /* Scan entire range */ + start = ethernet_phy_get(pep); + num = 32; + } else { + /* Use phy addr specific to platform */ + start = phy_addr & 0x1f; + num = 1; + } + phydev = NULL; + for (i = 0; i < num; i++) { + int addr = (start + i) & 0x1f; + if (bus->phy_map[addr] == NULL) + mdiobus_scan(bus, addr); + + if (phydev == NULL) { + phydev = bus->phy_map[addr]; + if (phydev != NULL) + ethernet_phy_set_addr(pep, addr); + } + } + + return phydev; +} + +static void phy_init(struct pxa168_eth_private *pep, int speed, int duplex) +{ + struct phy_device *phy = pep->phy; + ethernet_phy_reset(pep); + + phy_attach(pep->dev, dev_name(&phy->dev), 0, PHY_INTERFACE_MODE_MII); + + if (speed == 0) { + phy->autoneg = AUTONEG_ENABLE; + phy->speed = 0; + phy->duplex = 0; + phy->supported &= PHY_BASIC_FEATURES; + phy->advertising = phy->supported | ADVERTISED_Autoneg; + } else { + phy->autoneg = AUTONEG_DISABLE; + phy->advertising = 0; + phy->speed = speed; + phy->duplex = duplex; + } + phy_start_aneg(phy); +} + +static int ethernet_phy_setup(struct net_device *dev) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + + if (pep->pd != NULL) { + if (pep->pd->init) + pep->pd->init(); + } + pep->phy = phy_scan(pep, pep->pd->phy_addr & 0x1f); + if (pep->phy != NULL) + phy_init(pep, pep->pd->speed, pep->pd->duplex); + update_hash_table_mac_address(pep, NULL, dev->dev_addr); + + return 0; +} + +static int pxa168_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + int err; + + err = phy_read_status(pep->phy); + if (err == 0) + err = phy_ethtool_gset(pep->phy, cmd); + + return err; +} + +static int pxa168_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct pxa168_eth_private *pep = netdev_priv(dev); + + return phy_ethtool_sset(pep->phy, cmd); +} + +static void pxa168_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strncpy(info->driver, DRIVER_NAME, 32); + strncpy(info->version, DRIVER_VERSION, 32); + strncpy(info->fw_version, "N/A", 32); + strncpy(info->bus_info, "N/A", 32); +} + +static u32 pxa168_get_link(struct net_device *dev) +{ + return !!netif_carrier_ok(dev); +} + +static const struct ethtool_ops pxa168_ethtool_ops = { + .get_settings = pxa168_get_settings, + .set_settings = pxa168_set_settings, + .get_drvinfo = pxa168_get_drvinfo, + .get_link = pxa168_get_link, +}; + +static const struct net_device_ops pxa168_eth_netdev_ops = { + .ndo_open = pxa168_eth_open, + .ndo_stop = pxa168_eth_stop, + .ndo_start_xmit = pxa168_eth_start_xmit, + .ndo_set_rx_mode = pxa168_eth_set_rx_mode, + .ndo_set_mac_address = pxa168_eth_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_do_ioctl = pxa168_eth_do_ioctl, + .ndo_change_mtu = pxa168_eth_change_mtu, + .ndo_tx_timeout = pxa168_eth_tx_timeout, +}; + +static int pxa168_eth_probe(struct platform_device *pdev) +{ + struct pxa168_eth_private *pep = NULL; + struct net_device *dev = NULL; + struct resource *res; + struct clk *clk; + int err; + + printk(KERN_NOTICE "PXA168 10/100 Ethernet Driver\n"); + + clk = clk_get(&pdev->dev, "MFUCLK"); + if (IS_ERR(clk)) { + printk(KERN_ERR "%s: Fast Ethernet failed to get clock\n", + DRIVER_NAME); + return -ENODEV; + } + clk_enable(clk); + + dev = alloc_etherdev(sizeof(struct pxa168_eth_private)); + if (!dev) { + err = -ENOMEM; + goto out; + } + + platform_set_drvdata(pdev, dev); + pep = netdev_priv(dev); + pep->dev = dev; + pep->clk = clk; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res == NULL) { + err = -ENODEV; + goto out; + } + pep->base = ioremap(res->start, res->end - res->start + 1); + if (pep->base == NULL) { + err = -ENOMEM; + goto out; + } + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + BUG_ON(!res); + dev->irq = res->start; + dev->netdev_ops = &pxa168_eth_netdev_ops; + dev->watchdog_timeo = 2 * HZ; + dev->base_addr = 0; + SET_ETHTOOL_OPS(dev, &pxa168_ethtool_ops); + + INIT_WORK(&pep->tx_timeout_task, pxa168_eth_tx_timeout_task); + + printk(KERN_INFO "%s:Using random mac address\n", DRIVER_NAME); + random_ether_addr(dev->dev_addr); + + pep->pd = pdev->dev.platform_data; + pep->rx_ring_size = NUM_RX_DESCS; + if (pep->pd->rx_queue_size) + pep->rx_ring_size = pep->pd->rx_queue_size; + + pep->tx_ring_size = NUM_TX_DESCS; + if (pep->pd->tx_queue_size) + pep->tx_ring_size = pep->pd->tx_queue_size; + + pep->port_num = pep->pd->port_number; + /* Hardware supports only 3 ports */ + BUG_ON(pep->port_num > 2); + netif_napi_add(dev, &pep->napi, pxa168_rx_poll, pep->rx_ring_size); + + memset(&pep->timeout, 0, sizeof(struct timer_list)); + init_timer(&pep->timeout); + pep->timeout.function = rxq_refill_timer_wrapper; + pep->timeout.data = (unsigned long)pep; + + pep->smi_bus = mdiobus_alloc(); + if (pep->smi_bus == NULL) { + err = -ENOMEM; + goto out; + } + pep->smi_bus->priv = pep; + pep->smi_bus->name = "pxa168_eth smi"; + pep->smi_bus->read = pxa168_smi_read; + pep->smi_bus->write = pxa168_smi_write; + snprintf(pep->smi_bus->id, MII_BUS_ID_SIZE, "%d", pdev->id); + pep->smi_bus->parent = &pdev->dev; + pep->smi_bus->phy_mask = 0xffffffff; + if (mdiobus_register(pep->smi_bus) < 0) { + err = -ENOMEM; + goto out; + } + pxa168_init_hw(pep); + err = ethernet_phy_setup(dev); + if (err) + goto out; + SET_NETDEV_DEV(dev, &pdev->dev); + err = register_netdev(dev); + if (err) + goto out; + return 0; +out: + if (pep->clk) { + clk_disable(pep->clk); + clk_put(pep->clk); + pep->clk = NULL; + } + if (pep->base) { + iounmap(pep->base); + pep->base = NULL; + } + if (dev) + free_netdev(dev); + return err; +} + +static int pxa168_eth_remove(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + struct pxa168_eth_private *pep = netdev_priv(dev); + + if (pep->htpr) { + dma_free_coherent(pep->dev->dev.parent, HASH_ADDR_TABLE_SIZE, + pep->htpr, pep->htpr_dma); + pep->htpr = NULL; + } + if (pep->clk) { + clk_disable(pep->clk); + clk_put(pep->clk); + pep->clk = NULL; + } + if (pep->phy != NULL) + phy_detach(pep->phy); + + iounmap(pep->base); + pep->base = NULL; + unregister_netdev(dev); + flush_scheduled_work(); + free_netdev(dev); + platform_set_drvdata(pdev, NULL); + return 0; +} + +static void pxa168_eth_shutdown(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + eth_port_reset(dev); +} + +#ifdef CONFIG_PM +static int pxa168_eth_resume(struct platform_device *pdev) +{ + return -ENOSYS; +} + +static int pxa168_eth_suspend(struct platform_device *pdev, pm_message_t state) +{ + return -ENOSYS; +} + +#else +#define pxa168_eth_resume NULL +#define pxa168_eth_suspend NULL +#endif + +static struct platform_driver pxa168_eth_driver = { + .probe = pxa168_eth_probe, + .remove = pxa168_eth_remove, + .shutdown = pxa168_eth_shutdown, + .resume = pxa168_eth_resume, + .suspend = pxa168_eth_suspend, + .driver = { + .name = DRIVER_NAME, + }, +}; + +static int __init pxa168_init_module(void) +{ + return platform_driver_register(&pxa168_eth_driver); +} + +static void __exit pxa168_cleanup_module(void) +{ + platform_driver_unregister(&pxa168_eth_driver); +} + +module_init(pxa168_init_module); +module_exit(pxa168_cleanup_module); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Ethernet driver for Marvell PXA168"); +MODULE_ALIAS("platform:pxa168_eth"); diff --git a/include/linux/pxa168_eth.h b/include/linux/pxa168_eth.h new file mode 100644 index 000000000000..18d75e795606 --- /dev/null +++ b/include/linux/pxa168_eth.h @@ -0,0 +1,30 @@ +/* + *pxa168 ethernet platform device data definition file. + */ +#ifndef __LINUX_PXA168_ETH_H +#define __LINUX_PXA168_ETH_H + +struct pxa168_eth_platform_data { + int port_number; + int phy_addr; + + /* + * If speed is 0, then speed and duplex are autonegotiated. + */ + int speed; /* 0, SPEED_10, SPEED_100 */ + int duplex; /* DUPLEX_HALF or DUPLEX_FULL */ + + /* + * Override default RX/TX queue sizes if nonzero. + */ + int rx_queue_size; + int tx_queue_size; + + /* + * init callback is used for board specific initialization + * e.g on Aspenite its used to initialize the PHY transceiver. + */ + int (*init)(void); +}; + +#endif /* __LINUX_PXA168_ETH_H */ -- cgit v1.2.3-71-gd317 From e243f5b6de35b6fc394bc2e1e1737afe538e7e0c Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 15 Aug 2010 10:03:57 +0000 Subject: netfilter: fix userspace header warning "make headers_check" issued the following warning: CHECK include/linux/netfilter (64 files) usr/include/linux/netfilter/xt_ipvs.h:19: found __[us]{8,16,32,64} type without #include Fix this by as suggested including linux/types.h. Signed-off-by: Sam Ravnborg Signed-off-by: David S. Miller --- include/linux/netfilter/xt_ipvs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_ipvs.h b/include/linux/netfilter/xt_ipvs.h index 1167aeb7a347..eff34ac18808 100644 --- a/include/linux/netfilter/xt_ipvs.h +++ b/include/linux/netfilter/xt_ipvs.h @@ -1,6 +1,8 @@ #ifndef _XT_IPVS_H #define _XT_IPVS_H +#include + enum { XT_IPVS_IPVS_PROPERTY = 1 << 0, /* all other options imply this one */ XT_IPVS_PROTO = 1 << 1, -- cgit v1.2.3-71-gd317 From 1495cc9df4e81f5a8fa9b0b8f1034b14d24b7d8c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 17 Aug 2010 21:15:46 -0700 Subject: Input: sysrq - drop tty argument from sysrq ops handlers Noone is using tty argument so let's get rid of it. Acked-by: Alan Cox Acked-by: Jason Wessel Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- arch/arm/kernel/etm.c | 2 +- arch/powerpc/xmon/xmon.c | 5 ++--- arch/sparc/kernel/process_64.c | 2 +- drivers/char/sysrq.c | 42 ++++++++++++++++++++--------------------- drivers/gpu/drm/drm_fb_helper.c | 2 +- drivers/net/ibm_newemac/debug.c | 2 +- include/linux/sysrq.h | 6 +++++- kernel/debug/debug_core.c | 2 +- kernel/power/poweroff.c | 2 +- 9 files changed, 34 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c index 56418f98cd01..33c7077174db 100644 --- a/arch/arm/kernel/etm.c +++ b/arch/arm/kernel/etm.c @@ -230,7 +230,7 @@ static void etm_dump(void) etb_lock(t); } -static void sysrq_etm_dump(int key, struct tty_struct *tty) +static void sysrq_etm_dump(int key) { dev_dbg(tracer.dev, "Dumping ETB buffer\n"); etm_dump(); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0554445200bf..d17d04cfb2cd 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2880,15 +2880,14 @@ static void xmon_init(int enable) } #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_xmon(int key, struct tty_struct *tty) +static void sysrq_handle_xmon(int key) { /* ensure xmon is enabled */ xmon_init(1); debugger(get_irq_regs()); } -static struct sysrq_key_op sysrq_xmon_op = -{ +static struct sysrq_key_op sysrq_xmon_op = { .handler = sysrq_handle_xmon, .help_msg = "Xmon", .action_msg = "Entering xmon", diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index dbe81a368b45..25b01b43b40d 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -303,7 +303,7 @@ void arch_trigger_all_cpu_backtrace(void) #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_globreg(int key, struct tty_struct *tty) +static void sysrq_handle_globreg(int key) { arch_trigger_all_cpu_backtrace(); } diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index 878ac0c2cc68..a892a3c249dd 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -76,7 +76,7 @@ static int __init sysrq_always_enabled_setup(char *str) __setup("sysrq_always_enabled", sysrq_always_enabled_setup); -static void sysrq_handle_loglevel(int key, struct tty_struct *tty) +static void sysrq_handle_loglevel(int key) { int i; @@ -93,7 +93,7 @@ static struct sysrq_key_op sysrq_loglevel_op = { }; #ifdef CONFIG_VT -static void sysrq_handle_SAK(int key, struct tty_struct *tty) +static void sysrq_handle_SAK(int key) { struct work_struct *SAK_work = &vc_cons[fg_console].SAK_work; schedule_work(SAK_work); @@ -109,7 +109,7 @@ static struct sysrq_key_op sysrq_SAK_op = { #endif #ifdef CONFIG_VT -static void sysrq_handle_unraw(int key, struct tty_struct *tty) +static void sysrq_handle_unraw(int key) { struct kbd_struct *kbd = &kbd_table[fg_console]; @@ -126,7 +126,7 @@ static struct sysrq_key_op sysrq_unraw_op = { #define sysrq_unraw_op (*(struct sysrq_key_op *)NULL) #endif /* CONFIG_VT */ -static void sysrq_handle_crash(int key, struct tty_struct *tty) +static void sysrq_handle_crash(int key) { char *killer = NULL; @@ -141,7 +141,7 @@ static struct sysrq_key_op sysrq_crash_op = { .enable_mask = SYSRQ_ENABLE_DUMP, }; -static void sysrq_handle_reboot(int key, struct tty_struct *tty) +static void sysrq_handle_reboot(int key) { lockdep_off(); local_irq_enable(); @@ -154,7 +154,7 @@ static struct sysrq_key_op sysrq_reboot_op = { .enable_mask = SYSRQ_ENABLE_BOOT, }; -static void sysrq_handle_sync(int key, struct tty_struct *tty) +static void sysrq_handle_sync(int key) { emergency_sync(); } @@ -165,7 +165,7 @@ static struct sysrq_key_op sysrq_sync_op = { .enable_mask = SYSRQ_ENABLE_SYNC, }; -static void sysrq_handle_show_timers(int key, struct tty_struct *tty) +static void sysrq_handle_show_timers(int key) { sysrq_timer_list_show(); } @@ -176,7 +176,7 @@ static struct sysrq_key_op sysrq_show_timers_op = { .action_msg = "Show clockevent devices & pending hrtimers (no others)", }; -static void sysrq_handle_mountro(int key, struct tty_struct *tty) +static void sysrq_handle_mountro(int key) { emergency_remount(); } @@ -188,7 +188,7 @@ static struct sysrq_key_op sysrq_mountro_op = { }; #ifdef CONFIG_LOCKDEP -static void sysrq_handle_showlocks(int key, struct tty_struct *tty) +static void sysrq_handle_showlocks(int key) { debug_show_all_locks(); } @@ -226,7 +226,7 @@ static void sysrq_showregs_othercpus(struct work_struct *dummy) static DECLARE_WORK(sysrq_showallcpus, sysrq_showregs_othercpus); -static void sysrq_handle_showallcpus(int key, struct tty_struct *tty) +static void sysrq_handle_showallcpus(int key) { /* * Fall back to the workqueue based printing if the @@ -252,7 +252,7 @@ static struct sysrq_key_op sysrq_showallcpus_op = { }; #endif -static void sysrq_handle_showregs(int key, struct tty_struct *tty) +static void sysrq_handle_showregs(int key) { struct pt_regs *regs = get_irq_regs(); if (regs) @@ -266,7 +266,7 @@ static struct sysrq_key_op sysrq_showregs_op = { .enable_mask = SYSRQ_ENABLE_DUMP, }; -static void sysrq_handle_showstate(int key, struct tty_struct *tty) +static void sysrq_handle_showstate(int key) { show_state(); } @@ -277,7 +277,7 @@ static struct sysrq_key_op sysrq_showstate_op = { .enable_mask = SYSRQ_ENABLE_DUMP, }; -static void sysrq_handle_showstate_blocked(int key, struct tty_struct *tty) +static void sysrq_handle_showstate_blocked(int key) { show_state_filter(TASK_UNINTERRUPTIBLE); } @@ -291,7 +291,7 @@ static struct sysrq_key_op sysrq_showstate_blocked_op = { #ifdef CONFIG_TRACING #include -static void sysrq_ftrace_dump(int key, struct tty_struct *tty) +static void sysrq_ftrace_dump(int key) { ftrace_dump(DUMP_ALL); } @@ -305,7 +305,7 @@ static struct sysrq_key_op sysrq_ftrace_dump_op = { #define sysrq_ftrace_dump_op (*(struct sysrq_key_op *)NULL) #endif -static void sysrq_handle_showmem(int key, struct tty_struct *tty) +static void sysrq_handle_showmem(int key) { show_mem(); } @@ -330,7 +330,7 @@ static void send_sig_all(int sig) } } -static void sysrq_handle_term(int key, struct tty_struct *tty) +static void sysrq_handle_term(int key) { send_sig_all(SIGTERM); console_loglevel = 8; @@ -349,7 +349,7 @@ static void moom_callback(struct work_struct *ignored) static DECLARE_WORK(moom_work, moom_callback); -static void sysrq_handle_moom(int key, struct tty_struct *tty) +static void sysrq_handle_moom(int key) { schedule_work(&moom_work); } @@ -361,7 +361,7 @@ static struct sysrq_key_op sysrq_moom_op = { }; #ifdef CONFIG_BLOCK -static void sysrq_handle_thaw(int key, struct tty_struct *tty) +static void sysrq_handle_thaw(int key) { emergency_thaw_all(); } @@ -373,7 +373,7 @@ static struct sysrq_key_op sysrq_thaw_op = { }; #endif -static void sysrq_handle_kill(int key, struct tty_struct *tty) +static void sysrq_handle_kill(int key) { send_sig_all(SIGKILL); console_loglevel = 8; @@ -385,7 +385,7 @@ static struct sysrq_key_op sysrq_kill_op = { .enable_mask = SYSRQ_ENABLE_SIGNAL, }; -static void sysrq_handle_unrt(int key, struct tty_struct *tty) +static void sysrq_handle_unrt(int key) { normalize_rt_tasks(); } @@ -520,7 +520,7 @@ void __handle_sysrq(int key, struct tty_struct *tty, int check_mask) if (!check_mask || sysrq_on_mask(op_p->enable_mask)) { printk("%s\n", op_p->action_msg); console_loglevel = orig_log_level; - op_p->handler(key, tty); + op_p->handler(key); } else { printk("This sysrq operation is disabled.\n"); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index de82e201d682..5efd6d6742ec 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -369,7 +369,7 @@ static void drm_fb_helper_restore_work_fn(struct work_struct *ignored) } static DECLARE_WORK(drm_fb_helper_restore_work, drm_fb_helper_restore_work_fn); -static void drm_fb_helper_sysrq(int dummy1, struct tty_struct *dummy3) +static void drm_fb_helper_sysrq(int dummy1) { schedule_work(&drm_fb_helper_restore_work); } diff --git a/drivers/net/ibm_newemac/debug.c b/drivers/net/ibm_newemac/debug.c index 3995fafc1e08..8c6c1e2a8750 100644 --- a/drivers/net/ibm_newemac/debug.c +++ b/drivers/net/ibm_newemac/debug.c @@ -238,7 +238,7 @@ void emac_dbg_dump_all(void) } #if defined(CONFIG_MAGIC_SYSRQ) -static void emac_sysrq_handler(int key, struct tty_struct *tty) +static void emac_sysrq_handler(int key) { emac_dbg_dump_all(); } diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 609e8ca5f534..4ee650315119 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -31,7 +31,7 @@ struct tty_struct; #define SYSRQ_ENABLE_RTNICE 0x0100 struct sysrq_key_op { - void (*handler)(int, struct tty_struct *); + void (*handler)(int); char *help_msg; char *action_msg; int enable_mask; @@ -58,6 +58,10 @@ static inline void handle_sysrq(int key, struct tty_struct *tty) { } +static inline void __handle_sysrq(int key, struct tty_struct *tty, int check_mask); +{ +} + static inline int register_sysrq_key(int key, struct sysrq_key_op *op) { return -EINVAL; diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 3c2d4972d235..de407c78178d 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -741,7 +741,7 @@ static struct console kgdbcons = { }; #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_dbg(int key, struct tty_struct *tty) +static void sysrq_handle_dbg(int key) { if (!dbg_io_ops) { printk(KERN_CRIT "ERROR: No KGDB I/O module available\n"); diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c index e8b337006276..d52359374e85 100644 --- a/kernel/power/poweroff.c +++ b/kernel/power/poweroff.c @@ -24,7 +24,7 @@ static void do_poweroff(struct work_struct *dummy) static DECLARE_WORK(poweroff_work, do_poweroff); -static void handle_poweroff(int key, struct tty_struct *tty) +static void handle_poweroff(int key) { /* run sysrq poweroff on boot cpu */ schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work); -- cgit v1.2.3-71-gd317 From f335397d177c906256ee1bba28e8c49e8ec63817 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 17 Aug 2010 21:15:47 -0700 Subject: Input: sysrq - drop tty argument form handle_sysrq() Sysrq operations do not accept tty argument anymore so no need to pass it to us. [Stephen Rothwell : fix build breakage in drm code caused by sysrq using bool but not including linux/types.h] [Sachin Sant : fix build breakage in s390 keyboadr driver] Acked-by: Alan Cox Acked-by: Jason Wessel Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- arch/ia64/hp/sim/simserial.c | 2 +- arch/um/drivers/mconsole_kern.c | 2 +- drivers/char/hangcheck-timer.c | 2 +- drivers/char/hvc_console.c | 2 +- drivers/char/hvsi.c | 2 +- drivers/char/sysrq.c | 11 +++++------ drivers/s390/char/ctrlchar.c | 4 +--- drivers/s390/char/keyboard.c | 2 +- drivers/serial/sn_console.c | 2 +- drivers/usb/serial/generic.c | 2 +- drivers/xen/manage.c | 2 +- include/linux/serial_core.h | 2 +- include/linux/sysrq.h | 12 +++++------- kernel/debug/kdb/kdb_main.c | 2 +- 14 files changed, 22 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index 2bef5261d96d..1e8d71ad93ef 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -149,7 +149,7 @@ static void receive_chars(struct tty_struct *tty) ch = ia64_ssc(0, 0, 0, 0, SSC_GETCHAR); while (!ch); - handle_sysrq(ch, NULL); + handle_sysrq(ch); } #endif seen_esc = 0; diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index de317d0c3294..ebc680717e59 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -690,7 +690,7 @@ static void with_console(struct mc_request *req, void (*proc)(void *), static void sysrq_proc(void *arg) { char *op = arg; - handle_sysrq(*op, NULL); + handle_sysrq(*op); } void mconsole_sysrq(struct mc_request *req) diff --git a/drivers/char/hangcheck-timer.c b/drivers/char/hangcheck-timer.c index e0249722d25f..f953c96efc86 100644 --- a/drivers/char/hangcheck-timer.c +++ b/drivers/char/hangcheck-timer.c @@ -159,7 +159,7 @@ static void hangcheck_fire(unsigned long data) if (hangcheck_dump_tasks) { printk(KERN_CRIT "Hangcheck: Task state:\n"); #ifdef CONFIG_MAGIC_SYSRQ - handle_sysrq('t', NULL); + handle_sysrq('t'); #endif /* CONFIG_MAGIC_SYSRQ */ } if (hangcheck_reboot) { diff --git a/drivers/char/hvc_console.c b/drivers/char/hvc_console.c index fa27d1676ee5..3afd62e856eb 100644 --- a/drivers/char/hvc_console.c +++ b/drivers/char/hvc_console.c @@ -651,7 +651,7 @@ int hvc_poll(struct hvc_struct *hp) if (sysrq_pressed) continue; } else if (sysrq_pressed) { - handle_sysrq(buf[i], tty); + handle_sysrq(buf[i]); sysrq_pressed = 0; continue; } diff --git a/drivers/char/hvsi.c b/drivers/char/hvsi.c index 1f4b6de65a2d..a2bc885ce60a 100644 --- a/drivers/char/hvsi.c +++ b/drivers/char/hvsi.c @@ -403,7 +403,7 @@ static void hvsi_insert_chars(struct hvsi_struct *hp, const char *buf, int len) hp->sysrq = 1; continue; } else if (hp->sysrq) { - handle_sysrq(c, hp->tty); + handle_sysrq(c); hp->sysrq = 0; continue; } diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index a892a3c249dd..ef31bb81e843 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -493,7 +492,7 @@ static void __sysrq_put_key_op(int key, struct sysrq_key_op *op_p) sysrq_key_table[i] = op_p; } -void __handle_sysrq(int key, struct tty_struct *tty, int check_mask) +void __handle_sysrq(int key, bool check_mask) { struct sysrq_key_op *op_p; int orig_log_level; @@ -545,10 +544,10 @@ void __handle_sysrq(int key, struct tty_struct *tty, int check_mask) spin_unlock_irqrestore(&sysrq_key_table_lock, flags); } -void handle_sysrq(int key, struct tty_struct *tty) +void handle_sysrq(int key) { if (sysrq_on()) - __handle_sysrq(key, tty, 1); + __handle_sysrq(key, true); } EXPORT_SYMBOL(handle_sysrq); @@ -597,7 +596,7 @@ static bool sysrq_filter(struct input_handle *handle, unsigned int type, default: if (sysrq_down && value && value != 2) - __handle_sysrq(sysrq_xlate[code], NULL, 1); + __handle_sysrq(sysrq_xlate[code], true); break; } @@ -765,7 +764,7 @@ static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf, if (get_user(c, buf)) return -EFAULT; - __handle_sysrq(c, NULL, 0); + __handle_sysrq(c, false); } return count; diff --git a/drivers/s390/char/ctrlchar.c b/drivers/s390/char/ctrlchar.c index c6cbcb3f925e..0e9a309b9669 100644 --- a/drivers/s390/char/ctrlchar.c +++ b/drivers/s390/char/ctrlchar.c @@ -16,12 +16,11 @@ #ifdef CONFIG_MAGIC_SYSRQ static int ctrlchar_sysrq_key; -static struct tty_struct *sysrq_tty; static void ctrlchar_handle_sysrq(struct work_struct *work) { - handle_sysrq(ctrlchar_sysrq_key, sysrq_tty); + handle_sysrq(ctrlchar_sysrq_key); } static DECLARE_WORK(ctrlchar_work, ctrlchar_handle_sysrq); @@ -54,7 +53,6 @@ ctrlchar_handle(const unsigned char *buf, int len, struct tty_struct *tty) /* racy */ if (len == 3 && buf[1] == '-') { ctrlchar_sysrq_key = buf[2]; - sysrq_tty = tty; schedule_work(&ctrlchar_work); return CTRLCHAR_SYSRQ; } diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c index 18d9a497863b..8cd58e412b5e 100644 --- a/drivers/s390/char/keyboard.c +++ b/drivers/s390/char/keyboard.c @@ -305,7 +305,7 @@ kbd_keycode(struct kbd_data *kbd, unsigned int keycode) if (kbd->sysrq) { if (kbd->sysrq == K(KT_LATIN, '-')) { kbd->sysrq = 0; - handle_sysrq(value, kbd->tty); + handle_sysrq(value); return; } if (value == '-') { diff --git a/drivers/serial/sn_console.c b/drivers/serial/sn_console.c index 7e5e5efea4e2..cff9a306660f 100644 --- a/drivers/serial/sn_console.c +++ b/drivers/serial/sn_console.c @@ -492,7 +492,7 @@ sn_receive_chars(struct sn_cons_port *port, unsigned long flags) sysrq_requested = 0; if (ch && time_before(jiffies, sysrq_timeout)) { spin_unlock_irqrestore(&port->sc_port.lock, flags); - handle_sysrq(ch, NULL); + handle_sysrq(ch); spin_lock_irqsave(&port->sc_port.lock, flags); /* ignore actual sysrq command char */ continue; diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index ca92f67747cc..1e846cc3c7a4 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -453,7 +453,7 @@ int usb_serial_handle_sysrq_char(struct tty_struct *tty, { if (port->sysrq && port->port.console) { if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch, tty); + handle_sysrq(ch); port->sysrq = 0; return 1; } diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 1799bd890315..ef9c7db52077 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -237,7 +237,7 @@ static void sysrq_handler(struct xenbus_watch *watch, const char **vec, goto again; if (sysrq_key != '\0') - handle_sysrq(sysrq_key, NULL); + handle_sysrq(sysrq_key); } static struct xenbus_watch sysrq_watch = { diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 3c2ad99fed34..64458a9a8938 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -465,7 +465,7 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) #ifdef SUPPORT_SYSRQ if (port->sysrq) { if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch, port->state->port.tty); + handle_sysrq(ch); port->sysrq = 0; return 1; } diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 4ee650315119..387fa7d05c98 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -15,9 +15,7 @@ #define _LINUX_SYSRQ_H #include - -struct pt_regs; -struct tty_struct; +#include /* Possible values of bitmask for enabling sysrq functions */ /* 0x0001 is reserved for enable everything */ @@ -44,8 +42,8 @@ struct sysrq_key_op { * are available -- else NULL's). */ -void handle_sysrq(int key, struct tty_struct *tty); -void __handle_sysrq(int key, struct tty_struct *tty, int check_mask); +void handle_sysrq(int key); +void __handle_sysrq(int key, bool check_mask); int register_sysrq_key(int key, struct sysrq_key_op *op); int unregister_sysrq_key(int key, struct sysrq_key_op *op); struct sysrq_key_op *__sysrq_get_key_op(int key); @@ -54,11 +52,11 @@ int sysrq_toggle_support(int enable_mask); #else -static inline void handle_sysrq(int key, struct tty_struct *tty) +static inline void handle_sysrq(int key) { } -static inline void __handle_sysrq(int key, struct tty_struct *tty, int check_mask); +static inline void __handle_sysrq(int key, bool check_mask) { } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 28b844118bbd..caf057a3de0e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1929,7 +1929,7 @@ static int kdb_sr(int argc, const char **argv) if (argc != 1) return KDB_ARGCOUNT; kdb_trap_printk++; - __handle_sysrq(*argv[1], NULL, 0); + __handle_sysrq(*argv[1], false); kdb_trap_printk--; return 0; -- cgit v1.2.3-71-gd317 From 6ee9f4b4affe751d313d2538999aeec134d413a6 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 17 Aug 2010 21:15:47 -0700 Subject: USB: drop tty argument from usb_serial_handle_sysrq_char() Since handle_sysrq() does not take tty as argument anymore we can drop it from usb_serial_handle_sysrq_char() as well. Acked-by: Alan Cox Acked-by: Jason Wessel Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- drivers/usb/serial/ftdi_sio.c | 2 +- drivers/usb/serial/generic.c | 8 +++----- drivers/usb/serial/pl2303.c | 2 +- drivers/usb/serial/ssu100.c | 2 +- include/linux/usb/serial.h | 3 +-- 5 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index eb12d9b096b4..5d47983b533c 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1831,7 +1831,7 @@ static int ftdi_process_packet(struct tty_struct *tty, if (port->port.console && port->sysrq) { for (i = 0; i < len; i++, ch++) { - if (!usb_serial_handle_sysrq_char(tty, port, *ch)) + if (!usb_serial_handle_sysrq_char(port, *ch)) tty_insert_flip_char(tty, *ch, flag); } } else { diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index 1e846cc3c7a4..1abe34c38c08 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -343,7 +343,7 @@ void usb_serial_generic_process_read_urb(struct urb *urb) tty_insert_flip_string(tty, ch, urb->actual_length); else { for (i = 0; i < urb->actual_length; i++, ch++) { - if (!usb_serial_handle_sysrq_char(tty, port, *ch)) + if (!usb_serial_handle_sysrq_char(port, *ch)) tty_insert_flip_char(tty, *ch, TTY_NORMAL); } } @@ -448,8 +448,7 @@ void usb_serial_generic_unthrottle(struct tty_struct *tty) EXPORT_SYMBOL_GPL(usb_serial_generic_unthrottle); #ifdef CONFIG_MAGIC_SYSRQ -int usb_serial_handle_sysrq_char(struct tty_struct *tty, - struct usb_serial_port *port, unsigned int ch) +int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch) { if (port->sysrq && port->port.console) { if (ch && time_before(jiffies, port->sysrq)) { @@ -462,8 +461,7 @@ int usb_serial_handle_sysrq_char(struct tty_struct *tty, return 0; } #else -int usb_serial_handle_sysrq_char(struct tty_struct *tty, - struct usb_serial_port *port, unsigned int ch) +int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch) { return 0; } diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 6b6001822279..34ad7b3d5948 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -788,7 +788,7 @@ static void pl2303_process_read_urb(struct urb *urb) if (port->port.console && port->sysrq) { for (i = 0; i < urb->actual_length; ++i) - if (!usb_serial_handle_sysrq_char(tty, port, data[i])) + if (!usb_serial_handle_sysrq_char(port, data[i])) tty_insert_flip_char(tty, data[i], tty_flag); } else { tty_insert_flip_string_fixed_flag(tty, data, tty_flag, diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c index 6e82d4f54bc8..819de4740388 100644 --- a/drivers/usb/serial/ssu100.c +++ b/drivers/usb/serial/ssu100.c @@ -596,7 +596,7 @@ static int ssu100_process_packet(struct tty_struct *tty, if (port->port.console && port->sysrq) { for (i = 0; i < len; i++, ch++) { - if (!usb_serial_handle_sysrq_char(tty, port, *ch)) + if (!usb_serial_handle_sysrq_char(port, *ch)) tty_insert_flip_char(tty, *ch, flag); } } else diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 84a4c44c208b..55675b1efb28 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -342,8 +342,7 @@ extern int usb_serial_generic_submit_read_urb(struct usb_serial_port *port, extern void usb_serial_generic_process_read_urb(struct urb *urb); extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, void *dest, size_t size); -extern int usb_serial_handle_sysrq_char(struct tty_struct *tty, - struct usb_serial_port *port, +extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch); extern int usb_serial_handle_break(struct usb_serial_port *port); -- cgit v1.2.3-71-gd317 From 8905aaafb4b5d9764c5b4b54c7d03eb41bb0a7e9 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 19 Aug 2010 09:52:28 -0700 Subject: Input: uinput - add devname alias to allow module on-demand load Recent modprobe and udev versions allow to create device nodes for modules which are not loaded. Only the first access will cause the in-kernel module loader to pull-in the module. Systems which never access the device node will not needlessly load the module, and no longer need init scripts or other facilities to unconditionally load it. Signed-off-by: Kay Sievers Signed-off-by: Dmitry Torokhov --- drivers/input/misc/uinput.c | 2 ++ include/linux/miscdevice.h | 1 + include/linux/uinput.h | 1 - 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index bb53fd33cd1c..0d4266a533a5 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -811,6 +811,8 @@ static struct miscdevice uinput_misc = { .minor = UINPUT_MINOR, .name = UINPUT_NAME, }; +MODULE_ALIAS_MISCDEV(UINPUT_MINOR); +MODULE_ALIAS("devname:" UINPUT_NAME); static int __init uinput_init(void) { diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index bafffc737903..18fd13028ba1 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -33,6 +33,7 @@ #define MWAVE_MINOR 219 /* ACP/Mwave Modem */ #define MPT_MINOR 220 #define MPT2SAS_MINOR 221 +#define UINPUT_MINOR 223 #define HPET_MINOR 228 #define FUSE_MINOR 229 #define KVM_MINOR 232 diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 60c81da77f0f..05f7fed2b173 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -37,7 +37,6 @@ #define UINPUT_VERSION 3 #ifdef __KERNEL__ -#define UINPUT_MINOR 223 #define UINPUT_NAME "uinput" #define UINPUT_BUFFER_SIZE 16 #define UINPUT_NUM_REQUESTS 16 -- cgit v1.2.3-71-gd317 From 2eebf582c9b3106abb9c33f4fc0a347fb9391037 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 18 Aug 2010 12:25:50 -0400 Subject: fanotify: flush outstanding perm requests on group destroy When an fanotify listener is closing it may cause a deadlock between the listener and the original task doing an fs operation. If the original task is waiting for a permissions response it will be holding the srcu lock. The listener cannot clean up and exit until after that srcu lock is syncronized. Thus deadlock. The fix introduced here is to stop accepting new permissions events when a listener is shutting down and to grant permission for all outstanding events. Thus the original task will eventually release the srcu lock and the listener can complete shutdown. Reported-by: Andreas Gruenbacher Cc: Andreas Gruenbacher Signed-off-by: Eric Paris --- fs/notify/fanotify/fanotify_user.c | 27 +++++++++++++++++++++++++++ include/linux/fanotify.h | 7 ------- include/linux/fsnotify_backend.h | 1 + 3 files changed, 28 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 032b837fcd11..b966b7230f47 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -195,6 +195,14 @@ static int prepare_for_access_response(struct fsnotify_group *group, re->fd = fd; mutex_lock(&group->fanotify_data.access_mutex); + + if (group->fanotify_data.bypass_perm) { + mutex_unlock(&group->fanotify_data.access_mutex); + kmem_cache_free(fanotify_response_event_cache, re); + event->response = FAN_ALLOW; + return 0; + } + list_add_tail(&re->list, &group->fanotify_data.access_list); mutex_unlock(&group->fanotify_data.access_mutex); @@ -364,9 +372,28 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t static int fanotify_release(struct inode *ignored, struct file *file) { struct fsnotify_group *group = file->private_data; + struct fanotify_response_event *re, *lre; pr_debug("%s: file=%p group=%p\n", __func__, file, group); +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + mutex_lock(&group->fanotify_data.access_mutex); + + group->fanotify_data.bypass_perm = true; + + list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) { + pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group, + re, re->event); + + list_del_init(&re->list); + re->event->response = FAN_ALLOW; + + kmem_cache_free(fanotify_response_event_cache, re); + } + mutex_unlock(&group->fanotify_data.access_mutex); + + wake_up(&group->fanotify_data.access_waitq); +#endif /* matches the fanotify_init->fsnotify_alloc_group */ fsnotify_put_group(group); diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index f0949a57ca9d..985435622ecd 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -95,11 +95,4 @@ struct fanotify_response { (long)(meta)->event_len >= (long)FAN_EVENT_METADATA_LEN && \ (long)(meta)->event_len <= (long)(len)) -#ifdef __KERNEL__ - -struct fanotify_wait { - struct fsnotify_event *event; - __s32 fd; -}; -#endif /* __KERNEL__ */ #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index ed36fb57c426..e40190d16878 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -156,6 +156,7 @@ struct fsnotify_group { struct mutex access_mutex; struct list_head access_list; wait_queue_head_t access_waitq; + bool bypass_perm; /* protected by access_mutex */ #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; } fanotify_data; -- cgit v1.2.3-71-gd317 From 09cd2b99c6cdd1e14e84c1febca2fb91e9f4e5ba Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Sun, 22 Aug 2010 17:25:05 +0000 Subject: header: fix broken headers for user space __packed is only defined in kernel space, so we should use __attribute__((packed)) for the code shared between kernel and user space. Two __attribute() annotations are replaced with __attribute__() too. Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/if_ether.h | 2 +- include/linux/if_fddi.h | 8 ++++---- include/linux/if_hippi.h | 8 ++++---- include/linux/if_pppox.h | 10 +++++----- include/linux/ipv6.h | 4 ++-- include/linux/nbd.h | 2 +- include/linux/ncp.h | 10 +++++----- include/linux/netfilter/xt_IDLETIMER.h | 2 +- include/linux/phonet.h | 4 ++-- include/linux/rfkill.h | 2 +- 10 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index c831467774d0..bed7a4682b90 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -119,7 +119,7 @@ struct ethhdr { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ unsigned char h_source[ETH_ALEN]; /* source ether addr */ __be16 h_proto; /* packet type ID field */ -} __packed; +} __attribute__((packed)); #ifdef __KERNEL__ #include diff --git a/include/linux/if_fddi.h b/include/linux/if_fddi.h index 9947c39e62f6..e6dc11e7f9a5 100644 --- a/include/linux/if_fddi.h +++ b/include/linux/if_fddi.h @@ -67,7 +67,7 @@ struct fddi_8022_1_hdr { __u8 dsap; /* destination service access point */ __u8 ssap; /* source service access point */ __u8 ctrl; /* control byte #1 */ -} __packed; +} __attribute__((packed)); /* Define 802.2 Type 2 header */ struct fddi_8022_2_hdr { @@ -75,7 +75,7 @@ struct fddi_8022_2_hdr { __u8 ssap; /* source service access point */ __u8 ctrl_1; /* control byte #1 */ __u8 ctrl_2; /* control byte #2 */ -} __packed; +} __attribute__((packed)); /* Define 802.2 SNAP header */ #define FDDI_K_OUI_LEN 3 @@ -85,7 +85,7 @@ struct fddi_snap_hdr { __u8 ctrl; /* always 0x03 */ __u8 oui[FDDI_K_OUI_LEN]; /* organizational universal id */ __be16 ethertype; /* packet type ID field */ -} __packed; +} __attribute__((packed)); /* Define FDDI LLC frame header */ struct fddihdr { @@ -98,7 +98,7 @@ struct fddihdr { struct fddi_8022_2_hdr llc_8022_2; struct fddi_snap_hdr llc_snap; } hdr; -} __packed; +} __attribute__((packed)); #ifdef __KERNEL__ #include diff --git a/include/linux/if_hippi.h b/include/linux/if_hippi.h index 5fe5f307c6f5..cdc049f1829a 100644 --- a/include/linux/if_hippi.h +++ b/include/linux/if_hippi.h @@ -104,7 +104,7 @@ struct hippi_fp_hdr { __be32 fixed; #endif __be32 d2_size; -} __packed; +} __attribute__((packed)); struct hippi_le_hdr { #if defined (__BIG_ENDIAN_BITFIELD) @@ -129,7 +129,7 @@ struct hippi_le_hdr { __u8 daddr[HIPPI_ALEN]; __u16 locally_administered; __u8 saddr[HIPPI_ALEN]; -} __packed; +} __attribute__((packed)); #define HIPPI_OUI_LEN 3 /* @@ -142,12 +142,12 @@ struct hippi_snap_hdr { __u8 ctrl; /* always 0x03 */ __u8 oui[HIPPI_OUI_LEN]; /* organizational universal id (zero)*/ __be16 ethertype; /* packet type ID field */ -} __packed; +} __attribute__((packed)); struct hippi_hdr { struct hippi_fp_hdr fp; struct hippi_le_hdr le; struct hippi_snap_hdr snap; -} __packed; +} __attribute__((packed)); #endif /* _LINUX_IF_HIPPI_H */ diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 1925e0c3f162..27741e05446f 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -59,7 +59,7 @@ struct sockaddr_pppox { union{ struct pppoe_addr pppoe; }sa_addr; -} __packed; +} __attribute__((packed)); /* The use of the above union isn't viable because the size of this * struct must stay fixed over time -- applications use sizeof(struct @@ -70,7 +70,7 @@ struct sockaddr_pppol2tp { sa_family_t sa_family; /* address family, AF_PPPOX */ unsigned int sa_protocol; /* protocol identifier */ struct pppol2tp_addr pppol2tp; -} __packed; +} __attribute__((packed)); /* The L2TPv3 protocol changes tunnel and session ids from 16 to 32 * bits. So we need a different sockaddr structure. @@ -79,7 +79,7 @@ struct sockaddr_pppol2tpv3 { sa_family_t sa_family; /* address family, AF_PPPOX */ unsigned int sa_protocol; /* protocol identifier */ struct pppol2tpv3_addr pppol2tp; -} __packed; +} __attribute__((packed)); /********************************************************************* * @@ -101,7 +101,7 @@ struct pppoe_tag { __be16 tag_type; __be16 tag_len; char tag_data[0]; -} __attribute ((packed)); +} __attribute__ ((packed)); /* Tag identifiers */ #define PTT_EOL __cpu_to_be16(0x0000) @@ -129,7 +129,7 @@ struct pppoe_hdr { __be16 sid; __be16 length; struct pppoe_tag tag[0]; -} __packed; +} __attribute__((packed)); /* Length of entire PPPoE + PPP header */ #define PPPOE_SES_HLEN 8 diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ab9e9e89e407..e62683ba88e6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -58,7 +58,7 @@ struct ipv6_opt_hdr { /* * TLV encoded option data follows. */ -} __packed; /* required for some archs */ +} __attribute__((packed)); /* required for some archs */ #define ipv6_destopt_hdr ipv6_opt_hdr #define ipv6_hopopt_hdr ipv6_opt_hdr @@ -99,7 +99,7 @@ struct ipv6_destopt_hao { __u8 type; __u8 length; struct in6_addr addr; -} __packed; +} __attribute__((packed)); /* * IPv6 fixed header diff --git a/include/linux/nbd.h b/include/linux/nbd.h index bb58854a8061..d146ca10c0f5 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -88,7 +88,7 @@ struct nbd_request { char handle[8]; __be64 from; __be32 len; -} __packed; +} __attribute__((packed)); /* * This is the reply packet that nbd-server sends back to the client after diff --git a/include/linux/ncp.h b/include/linux/ncp.h index 3ace8370e61e..99f0adeeb3f3 100644 --- a/include/linux/ncp.h +++ b/include/linux/ncp.h @@ -27,7 +27,7 @@ struct ncp_request_header { __u8 conn_high; __u8 function; __u8 data[0]; -} __packed; +} __attribute__((packed)); #define NCP_REPLY (0x3333) #define NCP_WATCHDOG (0x3E3E) @@ -42,7 +42,7 @@ struct ncp_reply_header { __u8 completion_code; __u8 connection_state; __u8 data[0]; -} __packed; +} __attribute__((packed)); #define NCP_VOLNAME_LEN (16) #define NCP_NUMBER_OF_VOLUMES (256) @@ -158,7 +158,7 @@ struct nw_info_struct { #ifdef __KERNEL__ struct nw_nfs_info nfs; #endif -} __packed; +} __attribute__((packed)); /* modify mask - use with MODIFY_DOS_INFO structure */ #define DM_ATTRIBUTES (cpu_to_le32(0x02)) @@ -190,12 +190,12 @@ struct nw_modify_dos_info { __u16 inheritanceGrantMask; __u16 inheritanceRevokeMask; __u32 maximumSpace; -} __packed; +} __attribute__((packed)); struct nw_search_sequence { __u8 volNumber; __u32 dirBase; __u32 sequence; -} __packed; +} __attribute__((packed)); #endif /* _LINUX_NCP_H */ diff --git a/include/linux/netfilter/xt_IDLETIMER.h b/include/linux/netfilter/xt_IDLETIMER.h index 3e1aa1be942e..208ae9387331 100644 --- a/include/linux/netfilter/xt_IDLETIMER.h +++ b/include/linux/netfilter/xt_IDLETIMER.h @@ -39,7 +39,7 @@ struct idletimer_tg_info { char label[MAX_IDLETIMER_LABEL_SIZE]; /* for kernel module internal use only */ - struct idletimer_tg *timer __attribute((aligned(8))); + struct idletimer_tg *timer __attribute__((aligned(8))); }; #endif diff --git a/include/linux/phonet.h b/include/linux/phonet.h index 24426c3d6b5a..76edadf046d3 100644 --- a/include/linux/phonet.h +++ b/include/linux/phonet.h @@ -56,7 +56,7 @@ struct phonethdr { __be16 pn_length; __u8 pn_robj; __u8 pn_sobj; -} __packed; +} __attribute__((packed)); /* Common Phonet payload header */ struct phonetmsg { @@ -98,7 +98,7 @@ struct sockaddr_pn { __u8 spn_dev; __u8 spn_resource; __u8 spn_zero[sizeof(struct sockaddr) - sizeof(sa_family_t) - 3]; -} __packed; +} __attribute__((packed)); /* Well known address */ #define PN_DEV_PC 0x10 diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 4f82326eb294..08c32e4f261a 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -81,7 +81,7 @@ struct rfkill_event { __u8 type; __u8 op; __u8 soft, hard; -} __packed; +} __attribute__((packed)); /* * We are planning to be backward and forward compatible with changes -- cgit v1.2.3-71-gd317 From 5dd531a03ad721b41911ddb32e6e0481404e7aaf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 23 Aug 2010 13:52:19 +0200 Subject: block: add function call to switch the IO scheduler from a driver Currently drivers must do an elevator_exit() + elevator_init() to switch IO schedulers. There are a few problems with this: - Since commit 1abec4fdbb142e3ccb6ce99832fae42129134a96, elevator_init() requires a zeroed out q->elevator pointer. The two existing in-kernel users don't do that. - It will only work at initialization time, since using the above two-staged construct does not properly quisce the queue. So add elevator_change() which takes care of this, and convert the elv_iosched_store() sysfs interface to use this helper as well. Reported-by: Peter Oberparleiter Reported-by: Kevin Vigor Signed-off-by: Jens Axboe --- block/elevator.c | 44 +++++++++++++++++++++++++++++++------------- include/linux/elevator.h | 1 + 2 files changed, 32 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/elevator.c b/block/elevator.c index ec585c9554d3..205b09a5bd9e 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -1009,18 +1009,19 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { struct elevator_queue *old_elevator, *e; void *data; + int err; /* * Allocate new elevator */ e = elevator_alloc(q, new_e); if (!e) - return 0; + return -ENOMEM; data = elevator_init_queue(q, e); if (!data) { kobject_put(&e->kobj); - return 0; + return -ENOMEM; } /* @@ -1043,7 +1044,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) __elv_unregister_queue(old_elevator); - if (elv_register_queue(q)) + err = elv_register_queue(q); + if (err) goto fail_register; /* @@ -1056,7 +1058,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name); - return 1; + return 0; fail_register: /* @@ -1071,17 +1073,19 @@ fail_register: queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q); spin_unlock_irq(q->queue_lock); - return 0; + return err; } -ssize_t elv_iosched_store(struct request_queue *q, const char *name, - size_t count) +/* + * Switch this queue to the given IO scheduler. + */ +int elevator_change(struct request_queue *q, const char *name) { char elevator_name[ELV_NAME_MAX]; struct elevator_type *e; if (!q->elevator) - return count; + return -ENXIO; strlcpy(elevator_name, name, sizeof(elevator_name)); e = elevator_get(strstrip(elevator_name)); @@ -1092,13 +1096,27 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name, if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) { elevator_put(e); - return count; + return 0; } - if (!elevator_switch(q, e)) - printk(KERN_ERR "elevator: switch to %s failed\n", - elevator_name); - return count; + return elevator_switch(q, e); +} +EXPORT_SYMBOL(elevator_change); + +ssize_t elv_iosched_store(struct request_queue *q, const char *name, + size_t count) +{ + int ret; + + if (!q->elevator) + return count; + + ret = elevator_change(q, name); + if (!ret) + return count; + + printk(KERN_ERR "elevator: switch to %s failed\n", name); + return ret; } ssize_t elv_iosched_show(struct request_queue *q, char *name) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2c958f4fce1e..926b50322a46 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -136,6 +136,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); extern void elevator_exit(struct elevator_queue *); +extern int elevator_change(struct request_queue *, const char *); extern int elv_rq_merge_ok(struct request *, struct bio *); /* -- cgit v1.2.3-71-gd317 From 8488a38f4d2f43bd55a3e0db4cd57a5bef3af6d6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Aug 2010 15:01:02 +0100 Subject: kobject: Break the kobject namespace defs into their own header Break the kobject namespace defs into their own header to avoid a header file inclusion ordering problem between linux/sysfs.h and linux/kobject.h. This fixes the build breakage on older versions of gcc. Signed-off-by: David Howells Cc: Eric Biederman Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 35 +---------------------------- include/linux/kobject_ns.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sysfs.h | 1 + 3 files changed, 58 insertions(+), 34 deletions(-) create mode 100644 include/linux/kobject_ns.h (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index cf343a852534..7950a37a7146 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -136,42 +137,8 @@ struct kobj_attribute { extern const struct sysfs_ops kobj_sysfs_ops; -/* - * Namespace types which are used to tag kobjects and sysfs entries. - * Network namespace will likely be the first. - */ -enum kobj_ns_type { - KOBJ_NS_TYPE_NONE = 0, - KOBJ_NS_TYPE_NET, - KOBJ_NS_TYPES -}; - struct sock; -/* - * Callbacks so sysfs can determine namespaces - * @current_ns: return calling task's namespace - * @netlink_ns: return namespace to which a sock belongs (right?) - * @initial_ns: return the initial namespace (i.e. init_net_ns) - */ -struct kobj_ns_type_operations { - enum kobj_ns_type type; - const void *(*current_ns)(void); - const void *(*netlink_ns)(struct sock *sk); - const void *(*initial_ns)(void); -}; - -int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); -int kobj_ns_type_registered(enum kobj_ns_type type); -const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); -const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); - -const void *kobj_ns_current(enum kobj_ns_type type); -const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); -const void *kobj_ns_initial(enum kobj_ns_type type); -void kobj_ns_exit(enum kobj_ns_type type, const void *ns); - - /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h new file mode 100644 index 000000000000..82cb5bf461fb --- /dev/null +++ b/include/linux/kobject_ns.h @@ -0,0 +1,56 @@ +/* Kernel object name space definitions + * + * Copyright (c) 2002-2003 Patrick Mochel + * Copyright (c) 2002-2003 Open Source Development Labs + * Copyright (c) 2006-2008 Greg Kroah-Hartman + * Copyright (c) 2006-2008 Novell Inc. + * + * Split from kobject.h by David Howells (dhowells@redhat.com) + * + * This file is released under the GPLv2. + * + * Please read Documentation/kobject.txt before using the kobject + * interface, ESPECIALLY the parts about reference counts and object + * destructors. + */ + +#ifndef _LINUX_KOBJECT_NS_H +#define _LINUX_KOBJECT_NS_H + +struct sock; +struct kobject; + +/* + * Namespace types which are used to tag kobjects and sysfs entries. + * Network namespace will likely be the first. + */ +enum kobj_ns_type { + KOBJ_NS_TYPE_NONE = 0, + KOBJ_NS_TYPE_NET, + KOBJ_NS_TYPES +}; + +/* + * Callbacks so sysfs can determine namespaces + * @current_ns: return calling task's namespace + * @netlink_ns: return namespace to which a sock belongs (right?) + * @initial_ns: return the initial namespace (i.e. init_net_ns) + */ +struct kobj_ns_type_operations { + enum kobj_ns_type type; + const void *(*current_ns)(void); + const void *(*netlink_ns)(struct sock *sk); + const void *(*initial_ns)(void); +}; + +int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); +int kobj_ns_type_registered(enum kobj_ns_type type); +const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); +const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); + +const void *kobj_ns_current(enum kobj_ns_type type); +const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); +const void *kobj_ns_initial(enum kobj_ns_type type); +void kobj_ns_exit(enum kobj_ns_type type, const void *ns); + +#endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 3c92121ba9af..96eb576d82fd 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -16,6 +16,7 @@ #include #include #include +#include #include struct kobject; -- cgit v1.2.3-71-gd317 From d187abb9a83e6c6b6e9f2ca17962bdeafb4bc903 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 11 Aug 2010 12:07:13 -0700 Subject: USB: gadget: fix composite kernel-doc warnings Warning(include/linux/usb/composite.h:284): No description found for parameter 'disconnect' Warning(drivers/usb/gadget/composite.c:744): No description found for parameter 'c' Warning(drivers/usb/gadget/composite.c:744): Excess function parameter 'cdev' description in 'usb_string_ids_n' Signed-off-by: Randy Dunlap Cc: David Brownell Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 4 ++-- include/linux/usb/composite.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index e483f80822d2..1160c55de7f2 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -723,12 +723,12 @@ int usb_string_ids_tab(struct usb_composite_dev *cdev, struct usb_string *str) /** * usb_string_ids_n() - allocate unused string IDs in batch - * @cdev: the device whose string descriptor IDs are being allocated + * @c: the device whose string descriptor IDs are being allocated * @n: number of string IDs to allocate * Context: single threaded during gadget setup * * Returns the first requested ID. This ID and next @n-1 IDs are now - * valid IDs. At least providind that @n is non zore because if it + * valid IDs. At least provided that @n is non-zero because if it * is, returns last requested ID which is now very useful information. * * @usb_string_ids_n() is called from bind() callbacks to allocate diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 890bc1472190..617068134ae8 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -247,6 +247,7 @@ int usb_add_config(struct usb_composite_dev *, * value; it should return zero on successful initialization. * @unbind: Reverses @bind(); called as a side effect of unregistering * this driver. + * @disconnect: optional driver disconnect method * @suspend: Notifies when the host stops sending USB traffic, * after function notifications * @resume: Notifies configuration when the host restarts USB traffic, -- cgit v1.2.3-71-gd317 From e41e704bc4f49057fc68b643108366e6e6781aa3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Aug 2010 14:22:47 +0200 Subject: workqueue: improve destroy_workqueue() debuggability Now that the worklist is global, having works pending after wq destruction can easily lead to oops and destroy_workqueue() have several BUG_ON()s to catch these cases. Unfortunately, BUG_ON() doesn't tell much about how the work became pending after the final flush_workqueue(). This patch adds WQ_DYING which is set before the final flush begins. If a work is requested to be queued on a dying workqueue, WARN_ON_ONCE() is triggered and the request is ignored. This clearly indicates which caller is trying to queue a work on a dying workqueue and keeps the system working in most cases. Locking rule comment is updated such that the 'I' rule includes modifying the field from destruction path. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f9d277bcd9a..c959666eafca 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -241,6 +241,8 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cc3456f96c56..362b50d092e2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -87,7 +87,8 @@ enum { /* * Structure fields follow one of the following exclusion rules. * - * I: Set during initialization and read-only afterwards. + * I: Modifiable by initialization/destruction paths and read-only for + * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. @@ -944,6 +945,9 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); + if (WARN_ON_ONCE(wq->flags & WQ_DYING)) + return; + /* determine gcwq to use */ if (!(wq->flags & WQ_UNBOUND)) { struct global_cwq *last_gcwq; @@ -2828,6 +2832,7 @@ void destroy_workqueue(struct workqueue_struct *wq) { unsigned int cpu; + wq->flags |= WQ_DYING; flush_workqueue(wq); /* -- cgit v1.2.3-71-gd317 From 8ca3eb08097f6839b2206e2242db4179aee3cfb3 Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Tue, 24 Aug 2010 11:44:18 -0700 Subject: guard page for stacks that grow upwards pa-risc and ia64 have stacks that grow upwards. Check that they do not run into other mappings. By making VM_GROWSUP 0x0 on architectures that do not ever use it, we can avoid some unpleasant #ifdefs in check_stack_guard_page(). Signed-off-by: Tony Luck Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 +++++++- mm/memory.c | 15 +++++++++++---- mm/mmap.c | 3 --- 3 files changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 709f6728fc90..831c693416b2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -78,7 +78,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) #define VM_GROWSUP 0x00000200 +#else +#define VM_GROWSUP 0x00000000 +#endif #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ @@ -1330,8 +1334,10 @@ unsigned long ra_submit(struct file_ra_state *ra, /* Do stack extension */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); -#ifdef CONFIG_IA64 +#if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); +#else + #define expand_upwards(vma, address) do { } while (0) #endif extern int expand_stack_downwards(struct vm_area_struct *vma, unsigned long address); diff --git a/mm/memory.c b/mm/memory.c index 2ed2267439df..6b2ab1051851 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2760,11 +2760,9 @@ out_release: } /* - * This is like a special single-page "expand_downwards()", - * except we must first make sure that 'address-PAGE_SIZE' + * This is like a special single-page "expand_{down|up}wards()", + * except we must first make sure that 'address{-|+}PAGE_SIZE' * doesn't hit another vma. - * - * The "find_vma()" will do the right thing even if we wrap */ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) { @@ -2783,6 +2781,15 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo expand_stack(vma, address - PAGE_SIZE); } + if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { + struct vm_area_struct *next = vma->vm_next; + + /* As VM_GROWSDOWN but s/below/above/ */ + if (next && next->vm_start == address + PAGE_SIZE) + return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; + + expand_upwards(vma, address + PAGE_SIZE); + } return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index 331e51af38c9..6128dc8e5ede 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1716,9 +1716,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ -#ifndef CONFIG_IA64 -static -#endif int expand_upwards(struct vm_area_struct *vma, unsigned long address) { int error; -- cgit v1.2.3-71-gd317 From 75fb60f26befb59dbfa05cb122972642b7bdd219 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 23 Aug 2010 23:53:11 +0200 Subject: ACPI/PCI: Negotiate _OSC control bits before requesting them It is possible that the BIOS will not grant control of all _OSC features requested via acpi_pci_osc_control_set(), so it is recommended to negotiate the final set of _OSC features with the query flag set before calling _OSC to request control of these features. To implement it, rework acpi_pci_osc_control_set() so that the caller can specify the mask of _OSC control bits to negotiate and the mask of _OSC control bits that are absolutely necessary to it. Then, acpi_pci_osc_control_set() will run _OSC queries in a loop until the mask of _OSC control bits returned by the BIOS is equal to the mask passed to it. Also, before running the _OSC request acpi_pci_osc_control_set() will check if the caller's required control bits are present in the final mask. Using this mechanism we will be able to avoid situations in which the BIOS doesn't grant control of certain _OSC features, because they depend on some other _OSC features that have not been requested. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- drivers/acpi/pci_root.c | 59 +++++++++++++++++++++++------------- drivers/pci/hotplug/acpi_pcihp.c | 2 +- drivers/pci/pcie/aer/aerdrv_acpi.c | 6 ++-- drivers/pci/pcie/pme/pcie_pme_acpi.c | 8 +++-- include/linux/acpi.h | 4 +-- 5 files changed, 49 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 77cd19697b1e..c34713112520 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -374,21 +374,32 @@ out: EXPORT_SYMBOL_GPL(acpi_get_pci_dev); /** - * acpi_pci_osc_control_set - commit requested control to Firmware - * @handle: acpi_handle for the target ACPI object - * @flags: driver's requested control bits + * acpi_pci_osc_control_set - Request control of PCI root _OSC features. + * @handle: ACPI handle of a PCI root bridge (or PCIe Root Complex). + * @mask: Mask of _OSC bits to request control of, place to store control mask. + * @req: Mask of _OSC bits the control of is essential to the caller. * - * Attempt to take control from Firmware on requested control bits. + * Run _OSC query for @mask and if that is successful, compare the returned + * mask of control bits with @req. If all of the @req bits are set in the + * returned mask, run _OSC request for it. + * + * The variable at the @mask address may be modified regardless of whether or + * not the function returns success. On success it will contain the mask of + * _OSC bits the BIOS has granted control of, but its contents are meaningless + * on failure. **/ -acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags) +acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req) { + struct acpi_pci_root *root; acpi_status status; - u32 control_req, result, capbuf[3]; + u32 ctrl, capbuf[3]; acpi_handle tmp; - struct acpi_pci_root *root; - control_req = (flags & OSC_PCI_CONTROL_MASKS); - if (!control_req) + if (!mask) + return AE_BAD_PARAMETER; + + ctrl = *mask & OSC_PCI_CONTROL_MASKS; + if ((ctrl & req) != req) return AE_TYPE; root = acpi_pci_find_root(handle); @@ -400,27 +411,33 @@ acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags) return status; mutex_lock(&osc_lock); + + *mask = ctrl | root->osc_control_set; /* No need to evaluate _OSC if the control was already granted. */ - if ((root->osc_control_set & control_req) == control_req) + if ((root->osc_control_set & ctrl) == ctrl) goto out; - /* Need to query controls first before requesting them */ - flags = control_req; - status = acpi_pci_query_osc(root, root->osc_support_set, &flags); - if (ACPI_FAILURE(status)) - goto out; + /* Need to check the available controls bits before requesting them. */ + while (*mask) { + status = acpi_pci_query_osc(root, root->osc_support_set, mask); + if (ACPI_FAILURE(status)) + goto out; + if (ctrl == *mask) + break; + ctrl = *mask; + } - if (flags != control_req) { + if ((ctrl & req) != req) { status = AE_SUPPORT; goto out; } capbuf[OSC_QUERY_TYPE] = 0; capbuf[OSC_SUPPORT_TYPE] = root->osc_support_set; - capbuf[OSC_CONTROL_TYPE] = root->osc_control_set | control_req; - status = acpi_pci_run_osc(handle, capbuf, &result); + capbuf[OSC_CONTROL_TYPE] = ctrl; + status = acpi_pci_run_osc(handle, capbuf, mask); if (ACPI_SUCCESS(status)) - root->osc_control_set = result; + root->osc_control_set = *mask; out: mutex_unlock(&osc_lock); return status; @@ -551,8 +568,8 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device) if (flags != base_flags) acpi_pci_osc_support(root, flags); - status = acpi_pci_osc_control_set(root->device->handle, - OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL); + flags = OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL; + status = acpi_pci_osc_control_set(root->device->handle, &flags, flags); if (ACPI_FAILURE(status)) { printk(KERN_INFO "Unable to assume PCIe control: Disabling ASPM\n"); diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index 45fcc1e96df9..3d93d529a7bd 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -360,7 +360,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags) acpi_get_name(handle, ACPI_FULL_PATHNAME, &string); dbg("Trying to get hotplug control for %s\n", (char *)string.pointer); - status = acpi_pci_osc_control_set(handle, flags); + status = acpi_pci_osc_control_set(handle, &flags, flags); if (ACPI_SUCCESS(status)) goto got_one; if (status == AE_SUPPORT) diff --git a/drivers/pci/pcie/aer/aerdrv_acpi.c b/drivers/pci/pcie/aer/aerdrv_acpi.c index f278d7b0d95d..3a276a0cea93 100644 --- a/drivers/pci/pcie/aer/aerdrv_acpi.c +++ b/drivers/pci/pcie/aer/aerdrv_acpi.c @@ -39,9 +39,9 @@ int aer_osc_setup(struct pcie_device *pciedev) handle = acpi_find_root_bridge_handle(pdev); if (handle) { - status = acpi_pci_osc_control_set(handle, - OSC_PCI_EXPRESS_AER_CONTROL | - OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL); + u32 flags = OSC_PCI_EXPRESS_AER_CONTROL | + OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL; + status = acpi_pci_osc_control_set(handle, &flags, flags); } if (ACPI_FAILURE(status)) { diff --git a/drivers/pci/pcie/pme/pcie_pme_acpi.c b/drivers/pci/pcie/pme/pcie_pme_acpi.c index 83ab2287ae3f..be20222b12d3 100644 --- a/drivers/pci/pcie/pme/pcie_pme_acpi.c +++ b/drivers/pci/pcie/pme/pcie_pme_acpi.c @@ -28,6 +28,7 @@ int pcie_pme_acpi_setup(struct pcie_device *srv) acpi_status status = AE_NOT_FOUND; struct pci_dev *port = srv->port; acpi_handle handle; + u32 flags; int error = 0; if (acpi_pci_disabled) @@ -39,9 +40,10 @@ int pcie_pme_acpi_setup(struct pcie_device *srv) if (!handle) return -EINVAL; - status = acpi_pci_osc_control_set(handle, - OSC_PCI_EXPRESS_PME_CONTROL | - OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL); + flags = OSC_PCI_EXPRESS_PME_CONTROL | + OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL; + + status = acpi_pci_osc_control_set(handle, &flags, flags); if (ACPI_FAILURE(status)) { dev_info(&port->dev, "Failed to receive control of PCIe PME service: %s\n", diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ccf94dc5acdf..c227757feb06 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -304,8 +304,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); OSC_PCI_EXPRESS_PME_CONTROL | \ OSC_PCI_EXPRESS_AER_CONTROL | \ OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL) - -extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags); +extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, + u32 *mask, u32 req); extern void acpi_early_init(void); #else /* !CONFIG_ACPI */ -- cgit v1.2.3-71-gd317 From 8a2e8e5dec7e29c56a46ba176c664ab6a3d04118 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 Aug 2010 10:33:56 +0200 Subject: workqueue: fix cwq->nr_active underflow cwq->nr_active is used to keep track of how many work items are active for the cpu workqueue, where 'active' is defined as either pending on global worklist or executing. This is used to implement the max_active limit and workqueue freezing. If a work item is queued after nr_active has already reached max_active, the work item doesn't increment nr_active and is put on the delayed queue and gets activated later as previous active work items retire. try_to_grab_pending() which is used in the cancellation path unconditionally decremented nr_active whether the work item being cancelled is currently active or delayed, so cancelling a delayed work item makes nr_active underflow. This breaks max_active enforcement and triggers BUG_ON() in destroy_workqueue() later on. This patch fixes this bug by adding a flag WORK_STRUCT_DELAYED, which is set while a work item in on the delayed list and making try_to_grab_pending() decrement nr_active iff the work item is currently active. The addition of the flag enlarges cwq alignment to 256 bytes which is getting a bit too large. It's scheduled to be reduced back to 128 bytes by merging WORK_STRUCT_PENDING and WORK_STRUCT_CWQ in the next devel cycle. Signed-off-by: Tejun Heo Reported-by: Johannes Berg --- include/linux/workqueue.h | 16 +++++++++------- kernel/workqueue.c | 30 ++++++++++++++++++++---------- 2 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c959666eafca..f11100f96482 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,18 +25,20 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ - WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ + WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -59,8 +61,8 @@ enum { /* * Reserve 7 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 128 bytes which isn't too - * excessive while allowing 15 workqueue flush colors. + * off. This makes cwqs aligned to 256 bytes and allows 15 + * workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 362b50d092e2..a2dccfca03ba 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -941,6 +941,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct global_cwq *gcwq; struct cpu_workqueue_struct *cwq; struct list_head *worklist; + unsigned int work_flags; unsigned long flags; debug_work_activate(work); @@ -990,14 +991,17 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, BUG_ON(!list_empty(&work->entry)); cwq->nr_in_flight[cwq->work_color]++; + work_flags = work_color_to_flags(cwq->work_color); if (likely(cwq->nr_active < cwq->max_active)) { cwq->nr_active++; worklist = gcwq_determine_ins_pos(gcwq, cwq); - } else + } else { + work_flags |= WORK_STRUCT_DELAYED; worklist = &cwq->delayed_works; + } - insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color)); + insert_work(cwq, work, worklist, work_flags); spin_unlock_irqrestore(&gcwq->lock, flags); } @@ -1666,6 +1670,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); move_linked_works(work, pos, NULL); + __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); cwq->nr_active++; } @@ -1673,6 +1678,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight * @cwq: cwq of interest * @color: color of work which left the queue + * @delayed: for a delayed work * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its cwq and handle workqueue flushing. @@ -1680,19 +1686,22 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * CONTEXT: * spin_lock_irq(gcwq->lock). */ -static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color, + bool delayed) { /* ignore uncolored works */ if (color == WORK_NO_COLOR) return; cwq->nr_in_flight[color]--; - cwq->nr_active--; - if (!list_empty(&cwq->delayed_works)) { - /* one down, submit a delayed one */ - if (cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + if (!delayed) { + cwq->nr_active--; + if (!list_empty(&cwq->delayed_works)) { + /* one down, submit a delayed one */ + if (cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); + } } /* is flush in progress and are we at the flushing tip? */ @@ -1823,7 +1832,7 @@ __acquires(&gcwq->lock) hlist_del_init(&worker->hentry); worker->current_work = NULL; worker->current_cwq = NULL; - cwq_dec_nr_in_flight(cwq, work_color); + cwq_dec_nr_in_flight(cwq, work_color, false); } /** @@ -2388,7 +2397,8 @@ static int try_to_grab_pending(struct work_struct *work) debug_work_deactivate(work); list_del_init(&work->entry); cwq_dec_nr_in_flight(get_work_cwq(work), - get_work_color(work)); + get_work_color(work), + *work_data_bits(work) & WORK_STRUCT_DELAYED); ret = 1; } } -- cgit v1.2.3-71-gd317 From 04cbe1de6fbda9649a6f25666194e6955d3e717e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 19 Aug 2010 21:29:43 +0100 Subject: vgaarb: Wrap vga_(get|put) in CONFIG_VGA_ARB Fix link failure without the vga arbitrator. Signed-off-by: Chris Wilson Cc: Dave Airlie Cc: Jesse Barnes Signed-off-by: Dave Airlie --- include/linux/vgaarb.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 6228b5b77d35..e9e1524b582c 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -93,8 +93,11 @@ extern void vga_set_legacy_decoding(struct pci_dev *pdev, * Nested calls are supported (a per-resource counter is maintained) */ -extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, - int interruptible); +#if defined(CONFIG_VGA_ARB) +extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible); +#else +static inline int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible) { return 0; } +#endif /** * vga_get_interruptible @@ -131,7 +134,11 @@ static inline int vga_get_uninterruptible(struct pci_dev *pdev, * are already locked by another card. It can be called in any context */ +#if defined(CONFIG_VGA_ARB) extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); +#else +static inline int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) { return 0; } +#endif /** * vga_put - release lock on legacy VGA resources @@ -146,7 +153,11 @@ extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); * released if the counter reaches 0. */ +#if defined(CONFIG_VGA_ARB) extern void vga_put(struct pci_dev *pdev, unsigned int rsrc); +#else +#define vga_put(pdev, rsrc) +#endif /** -- cgit v1.2.3-71-gd317 From 0fb85621df4f9f7c663c6c77c302e821a832c95e Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 20 Aug 2010 10:02:15 +0100 Subject: fanotify: resize pid and reorder structure resize pid and reorder the fanotify_event_metadata so it is naturally aligned and we can work towards dropping the packed attributed Signed-off-by: Tvrtko Ursulin Cc: Andreas Dilger Signed-off-by: Eric Paris --- include/linux/fanotify.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 985435622ecd..63531a6b4d2a 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -65,14 +65,14 @@ FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) -#define FANOTIFY_METADATA_VERSION 1 +#define FANOTIFY_METADATA_VERSION 2 struct fanotify_event_metadata { __u32 event_len; __u32 vers; - __s32 fd; __u64 mask; - __s64 pid; + __s32 fd; + __s32 pid; } __attribute__ ((packed)); struct fanotify_response { -- cgit v1.2.3-71-gd317 From bad849b3dc0fae1297c8d47f846f8d202a6145ed Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 26 Aug 2010 16:00:34 +0100 Subject: NOMMU: Stub out vm_get_page_prot() if there's no MMU Stub out vm_get_page_prot() if there's no MMU. This was added by commit 804af2cf6e7a ("[AGPGART] remove private page protection map") and is used in commit c07fbfd17e61 ("fbmem: VM_IO set, but not propagated") in the fbmem video driver, but the function doesn't exist on NOMMU, resulting in an undefined symbol at link time. Signed-off-by: David Howells Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 831c693416b2..e6b1210772ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1363,7 +1363,15 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma) return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } +#ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); +#else +static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + return __pgprot(0); +} +#endif + struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); -- cgit v1.2.3-71-gd317 From a28dec2f26013aad89446b1f708f948617bc28a2 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Sun, 8 Aug 2010 18:03:33 +0400 Subject: powerpc/85xx: Add P1021 PCI IDs and quirks This is needed for proper PCI-E support on P1021 SoCs. Signed-off-by: Anton Vorontsov Signed-off-by: Kumar Gala --- arch/powerpc/sysdev/fsl_pci.c | 2 ++ include/linux/pci_ids.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 209384b6e039..4ae933225251 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -399,6 +399,8 @@ DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013E, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020E, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020, quirk_fsl_pcie_header); +DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1021E, quirk_fsl_pcie_header); +DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1021, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022E, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2010E, quirk_fsl_pcie_header); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f6a3b2d36cad..10d33309e9a6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2300,6 +2300,8 @@ #define PCI_DEVICE_ID_P2010 0x0079 #define PCI_DEVICE_ID_P1020E 0x0100 #define PCI_DEVICE_ID_P1020 0x0101 +#define PCI_DEVICE_ID_P1021E 0x0102 +#define PCI_DEVICE_ID_P1021 0x0103 #define PCI_DEVICE_ID_P1011E 0x0108 #define PCI_DEVICE_ID_P1011 0x0109 #define PCI_DEVICE_ID_P1022E 0x0110 -- cgit v1.2.3-71-gd317 From 4e4438b86527e8bf1f49503a30d487e401e64f9c Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 1 Sep 2010 08:55:24 -0600 Subject: gpiolib: Add 'struct gpio_chip' forward declaration for !GPIOLIB case With CONFIG_GPIOLIB=n, the 'struct gpio_chip' is not declared, so the following pops up on PowerPC: cc1: warnings being treated as errors In file included from arch/powerpc/platforms/52xx/mpc52xx_common.c:19: include/linux/of_gpio.h:74: warning: 'struct gpio_chip' declared inside parameter list include/linux/of_gpio.h:74: warning: its scope is only this definition or declaration, which is probably not what you want include/linux/of_gpio.h:75: warning: 'struct gpio_chip' declared inside parameter list make[2]: *** [arch/powerpc/platforms/52xx/mpc52xx_common.o] Error 1 This patch fixes the issue by providing the proper forward declaration. Signed-off-by: Anton Vorontsov Signed-off-by: Grant Likely --- include/linux/gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 03f616b78cfa..e41f7dd1ae67 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -13,6 +13,7 @@ #include struct device; +struct gpio_chip; /* * Some platforms don't support the GPIO programming interface. -- cgit v1.2.3-71-gd317 From ef5dc121d5a0bb1fa477c5395277259f07d318a3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 2 Sep 2010 15:48:16 -0700 Subject: mutex: Fix annotations to include it in kernel-locking docbook Fix kernel-doc notation in linux/mutex.h and kernel/mutex.c, then add these 2 files to the kernel-locking docbook as the Mutex API reference chapter. Add one API function to mutex-design.txt and correct a typo in that file. Signed-off-by: Randy Dunlap Cc: Rusty Russell LKML-Reference: <20100902154816.6cc2f9ad.randy.dunlap@oracle.com> Signed-off-by: Ingo Molnar --- Documentation/DocBook/kernel-locking.tmpl | 6 ++++++ Documentation/mutex-design.txt | 3 ++- include/linux/mutex.h | 8 ++++++++ kernel/mutex.c | 23 +++++++---------------- 4 files changed, 23 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl index 0b1a3f97f285..a0d479d1e1dd 100644 --- a/Documentation/DocBook/kernel-locking.tmpl +++ b/Documentation/DocBook/kernel-locking.tmpl @@ -1961,6 +1961,12 @@ machines due to caching. + + Mutex API reference +!Iinclude/linux/mutex.h +!Ekernel/mutex.c + + Further reading diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt index c91ccc0720fa..38c10fd7f411 100644 --- a/Documentation/mutex-design.txt +++ b/Documentation/mutex-design.txt @@ -9,7 +9,7 @@ firstly, there's nothing wrong with semaphores. But if the simpler mutex semantics are sufficient for your code, then there are a couple of advantages of mutexes: - - 'struct mutex' is smaller on most architectures: .e.g on x86, + - 'struct mutex' is smaller on most architectures: E.g. on x86, 'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes. A smaller structure size means less RAM footprint, and better CPU-cache utilization. @@ -136,3 +136,4 @@ the APIs of 'struct mutex' have been streamlined: void mutex_lock_nested(struct mutex *lock, unsigned int subclass); int mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); + int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 878cab4f5fcc..f363bc8fdc74 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -78,6 +78,14 @@ struct mutex_waiter { # include #else # define __DEBUG_MUTEX_INITIALIZER(lockname) +/** + * mutex_init - initialize the mutex + * @mutex: the mutex to be initialized + * + * Initialize the mutex to unlocked state. + * + * It is not allowed to initialize an already locked mutex. + */ # define mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ diff --git a/kernel/mutex.c b/kernel/mutex.c index 4c0b7b3e6d2e..200407c1502f 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -36,15 +36,6 @@ # include #endif -/*** - * mutex_init - initialize the mutex - * @lock: the mutex to be initialized - * @key: the lock_class_key for the class; used by mutex lock debugging - * - * Initialize the mutex to unlocked state. - * - * It is not allowed to initialize an already locked mutex. - */ void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { @@ -68,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init); static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count); -/*** +/** * mutex_lock - acquire the mutex * @lock: the mutex to be acquired * @@ -105,7 +96,7 @@ EXPORT_SYMBOL(mutex_lock); static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); -/*** +/** * mutex_unlock - release the mutex * @lock: the mutex to be released * @@ -364,8 +355,8 @@ __mutex_lock_killable_slowpath(atomic_t *lock_count); static noinline int __sched __mutex_lock_interruptible_slowpath(atomic_t *lock_count); -/*** - * mutex_lock_interruptible - acquire the mutex, interruptable +/** + * mutex_lock_interruptible - acquire the mutex, interruptible * @lock: the mutex to be acquired * * Lock the mutex like mutex_lock(), and return 0 if the mutex has @@ -456,15 +447,15 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) return prev == 1; } -/*** - * mutex_trylock - try acquire the mutex, without waiting +/** + * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired * * Try to acquire the mutex atomically. Returns 1 if the mutex * has been acquired successfully, and 0 on contention. * * NOTE: this function follows the spin_trylock() convention, so - * it is negated to the down_trylock() return values! Be careful + * it is negated from the down_trylock() return values! Be careful * about this when converting semaphore users to mutexes. * * This function must not be used in interrupt context. The -- cgit v1.2.3-71-gd317 From 71cad0554956de87c3fc413b1eac9313887eb14f Mon Sep 17 00:00:00 2001 From: Philippe Langlais Date: Tue, 31 Aug 2010 14:19:09 +0200 Subject: serial: fix port type conflict between NS16550A & U6_16550A Bug seen by Dr. David Alan Gilbert with sparse Signed-off-by: Philippe Langlais Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 3 +-- include/linux/serial_core.h | 3 ++- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index 1ebc694a6d52..ef914061511e 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -77,8 +77,7 @@ struct serial_struct { #define PORT_16654 11 #define PORT_16850 12 #define PORT_RSA 13 /* RSA-DV II/S card */ -#define PORT_U6_16550A 14 -#define PORT_MAX 14 +#define PORT_MAX 13 #define SERIAL_IO_PORT 0 #define SERIAL_IO_HUB6 1 diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 64458a9a8938..563e23400913 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -44,7 +44,8 @@ #define PORT_RM9000 16 /* PMC-Sierra RM9xxx internal UART */ #define PORT_OCTEON 17 /* Cavium OCTEON internal UART */ #define PORT_AR7 18 /* Texas Instruments AR7 internal UART */ -#define PORT_MAX_8250 18 /* max port ID */ +#define PORT_U6_16550A 19 /* ST-Ericsson U6xxx internal UART */ +#define PORT_MAX_8250 19 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed -- cgit v1.2.3-71-gd317 From 29bc17ecb856ffb2b47c7009a71971c6f9334205 Mon Sep 17 00:00:00 2001 From: Francisco Jerez Date: Sat, 4 Sep 2010 22:56:44 +0200 Subject: io-mapping: Fix the address space annotations Fixes a bunch of sparse warnings in io-mapping.h because of the inconsistent __iomem usage. Signed-off-by: Francisco Jerez LKML-Reference: <1283633804-11749-2-git-send-email-currojerez@riseup.net> Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/io-mapping.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 0a6b3d5c490c..7fb592793738 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -79,7 +79,7 @@ io_mapping_free(struct io_mapping *mapping) } /* Atomic map/unmap */ -static inline void * +static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset, int slot) @@ -94,12 +94,12 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, } static inline void -io_mapping_unmap_atomic(void *vaddr, int slot) +io_mapping_unmap_atomic(void __iomem *vaddr, int slot) { iounmap_atomic(vaddr, slot); } -static inline void * +static inline void __iomem * io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset) { resource_size_t phys_addr; @@ -111,7 +111,7 @@ io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset) } static inline void -io_mapping_unmap(void *vaddr) +io_mapping_unmap(void __iomem *vaddr) { iounmap(vaddr); } @@ -125,38 +125,38 @@ struct io_mapping; static inline struct io_mapping * io_mapping_create_wc(resource_size_t base, unsigned long size) { - return (struct io_mapping *) ioremap_wc(base, size); + return (struct io_mapping __force *) ioremap_wc(base, size); } static inline void io_mapping_free(struct io_mapping *mapping) { - iounmap(mapping); + iounmap((void __force __iomem *) mapping); } /* Atomic map/unmap */ -static inline void * +static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset, int slot) { - return ((char *) mapping) + offset; + return ((char __force __iomem *) mapping) + offset; } static inline void -io_mapping_unmap_atomic(void *vaddr, int slot) +io_mapping_unmap_atomic(void __iomem *vaddr, int slot) { } /* Non-atomic map/unmap */ -static inline void * +static inline void __iomem * io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset) { - return ((char *) mapping) + offset; + return ((char __force __iomem *) mapping) + offset; } static inline void -io_mapping_unmap(void *vaddr) +io_mapping_unmap(void __iomem *vaddr) { } -- cgit v1.2.3-71-gd317 From 73457f0f836956747e0394320be2163c050e96ef Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 6 Aug 2010 01:59:14 +0300 Subject: cgroups: fix API thinko cgroup_attach_task_current_cg API that have upstream is backwards: we really need an API to attach to the cgroups from another process A to the current one. In our case (vhost), a priveledged user wants to attach it's task to cgroups from a less priveledged one, the API makes us run it in the other task's context, and this fails. So let's make the API generic and just pass in 'from' and 'to' tasks. Add an inline wrapper for cgroup_attach_task_current_cg to avoid breaking bisect. Signed-off-by: Michael S. Tsirkin Acked-by: Li Zefan Acked-by: Paul Menage --- include/linux/cgroup.h | 11 ++++++++++- kernel/cgroup.c | 9 +++++---- 2 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed3e92e41c6e..5a53d8f039a2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -578,7 +578,11 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); -int cgroup_attach_task_current_cg(struct task_struct *); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +static inline int cgroup_attach_task_current_cg(struct task_struct *tsk) +{ + return cgroup_attach_task_all(current, tsk); +} /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works @@ -636,6 +640,11 @@ static inline int cgroupstats_build(struct cgroupstats *stats, } /* No cgroups - nothing to do */ +static inline int cgroup_attach_task_all(struct task_struct *from, + struct task_struct *t) +{ + return 0; +} static inline int cgroup_attach_task_current_cg(struct task_struct *t) { return 0; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a8ce09954404..9d90c08f3bde 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1789,10 +1789,11 @@ out: } /** - * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup + * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' + * @from: attach to all cgroups of a given task * @tsk: the task to be attached */ -int cgroup_attach_task_current_cg(struct task_struct *tsk) +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroupfs_root *root; struct cgroup *cur_cg; @@ -1800,7 +1801,7 @@ int cgroup_attach_task_current_cg(struct task_struct *tsk) cgroup_lock(); for_each_active_root(root) { - cur_cg = task_cgroup_from_root(current, root); + cur_cg = task_cgroup_from_root(from, root); retval = cgroup_attach_task(cur_cg, tsk); if (retval) break; @@ -1809,7 +1810,7 @@ int cgroup_attach_task_current_cg(struct task_struct *tsk) return retval; } -EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg); +EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /* * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex -- cgit v1.2.3-71-gd317 From f8f235e5bbf4e61f3e0886a44afb1dc4cfe8f337 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Fri, 27 Aug 2010 11:08:57 +0800 Subject: agp/intel: Fix cache control for Sandybridge Sandybridge GTT has new cache control bits in PTE, which controls graphics page cache in LLC or LLC/MLC, so we need to extend the mask function to respect the new bits. And set cache control to always LLC only by default on Gen6. Signed-off-by: Zhenyu Wang Cc: stable@kernel.org Signed-off-by: Chris Wilson --- drivers/char/agp/intel-agp.c | 1 + drivers/char/agp/intel-gtt.c | 50 ++++++++++++++++++++++++++++++++--------- drivers/gpu/drm/i915/i915_gem.c | 1 + include/linux/intel-gtt.h | 20 +++++++++++++++++ 4 files changed, 62 insertions(+), 10 deletions(-) create mode 100644 include/linux/intel-gtt.h (limited to 'include/linux') diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 710af89b176d..74461d177baf 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -12,6 +12,7 @@ #include #include "agp.h" #include "intel-agp.h" +#include #include "intel-gtt.c" diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index 7f35854d33a3..64b10551a3f8 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -49,6 +49,26 @@ static struct gatt_mask intel_i810_masks[] = .type = INTEL_AGP_CACHED_MEMORY} }; +#define INTEL_AGP_UNCACHED_MEMORY 0 +#define INTEL_AGP_CACHED_MEMORY_LLC 1 +#define INTEL_AGP_CACHED_MEMORY_LLC_GFDT 2 +#define INTEL_AGP_CACHED_MEMORY_LLC_MLC 3 +#define INTEL_AGP_CACHED_MEMORY_LLC_MLC_GFDT 4 + +static struct gatt_mask intel_gen6_masks[] = +{ + {.mask = I810_PTE_VALID | GEN6_PTE_UNCACHED, + .type = INTEL_AGP_UNCACHED_MEMORY }, + {.mask = I810_PTE_VALID | GEN6_PTE_LLC, + .type = INTEL_AGP_CACHED_MEMORY_LLC }, + {.mask = I810_PTE_VALID | GEN6_PTE_LLC | GEN6_PTE_GFDT, + .type = INTEL_AGP_CACHED_MEMORY_LLC_GFDT }, + {.mask = I810_PTE_VALID | GEN6_PTE_LLC_MLC, + .type = INTEL_AGP_CACHED_MEMORY_LLC_MLC }, + {.mask = I810_PTE_VALID | GEN6_PTE_LLC_MLC | GEN6_PTE_GFDT, + .type = INTEL_AGP_CACHED_MEMORY_LLC_MLC_GFDT }, +}; + static struct _intel_private { struct pci_dev *pcidev; /* device one */ u8 __iomem *registers; @@ -178,13 +198,6 @@ static void intel_agp_insert_sg_entries(struct agp_memory *mem, off_t pg_start, int mask_type) { int i, j; - u32 cache_bits = 0; - - if (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB || - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB) - { - cache_bits = GEN6_PTE_LLC_MLC; - } for (i = 0, j = pg_start; i < mem->page_count; i++, j++) { writel(agp_bridge->driver->mask_memory(agp_bridge, @@ -317,6 +330,23 @@ static int intel_i830_type_to_mask_type(struct agp_bridge_data *bridge, return 0; } +static int intel_gen6_type_to_mask_type(struct agp_bridge_data *bridge, + int type) +{ + unsigned int type_mask = type & ~AGP_USER_CACHED_MEMORY_GFDT; + unsigned int gfdt = type & AGP_USER_CACHED_MEMORY_GFDT; + + if (type_mask == AGP_USER_UNCACHED_MEMORY) + return INTEL_AGP_UNCACHED_MEMORY; + else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) + return gfdt ? INTEL_AGP_CACHED_MEMORY_LLC_MLC_GFDT : + INTEL_AGP_CACHED_MEMORY_LLC_MLC; + else /* set 'normal'/'cached' to LLC by default */ + return gfdt ? INTEL_AGP_CACHED_MEMORY_LLC_GFDT : + INTEL_AGP_CACHED_MEMORY_LLC; +} + + static int intel_i810_insert_entries(struct agp_memory *mem, off_t pg_start, int type) { @@ -1163,7 +1193,7 @@ static int intel_i915_insert_entries(struct agp_memory *mem, off_t pg_start, mask_type = agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type); - if (mask_type != 0 && mask_type != AGP_PHYS_MEMORY && + if (!IS_SNB && mask_type != 0 && mask_type != AGP_PHYS_MEMORY && mask_type != INTEL_AGP_CACHED_MEMORY) goto out_err; @@ -1563,7 +1593,7 @@ static const struct agp_bridge_driver intel_gen6_driver = { .fetch_size = intel_i9xx_fetch_size, .cleanup = intel_i915_cleanup, .mask_memory = intel_gen6_mask_memory, - .masks = intel_i810_masks, + .masks = intel_gen6_masks, .agp_enable = intel_i810_agp_enable, .cache_flush = global_cache_flush, .create_gatt_table = intel_i965_create_gatt_table, @@ -1576,7 +1606,7 @@ static const struct agp_bridge_driver intel_gen6_driver = { .agp_alloc_pages = agp_generic_alloc_pages, .agp_destroy_page = agp_generic_destroy_page, .agp_destroy_pages = agp_generic_destroy_pages, - .agp_type_to_mask_type = intel_i830_type_to_mask_type, + .agp_type_to_mask_type = intel_gen6_type_to_mask_type, .chipset_flush = intel_i915_chipset_flush, #ifdef USE_PCI_DMA_API .agp_map_page = intel_agp_map_page, diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 748c26340c35..16fca1d1799a 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -34,6 +34,7 @@ #include #include #include +#include static uint32_t i915_gem_get_gtt_alignment(struct drm_gem_object *obj); static int i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj); diff --git a/include/linux/intel-gtt.h b/include/linux/intel-gtt.h new file mode 100644 index 000000000000..1d19ab2afa39 --- /dev/null +++ b/include/linux/intel-gtt.h @@ -0,0 +1,20 @@ +/* + * Common Intel AGPGART and GTT definitions. + */ +#ifndef _INTEL_GTT_H +#define _INTEL_GTT_H + +#include + +/* This is for Intel only GTT controls. + * + * Sandybridge: AGP_USER_CACHED_MEMORY default to LLC only + */ + +#define AGP_USER_CACHED_MEMORY_LLC_MLC (AGP_USER_TYPES + 2) +#define AGP_USER_UNCACHED_MEMORY (AGP_USER_TYPES + 4) + +/* flag for GFDT type */ +#define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) + +#endif -- cgit v1.2.3-71-gd317 From febc88c5948f81114f64c3412011d695aecae233 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Sep 2010 14:46:37 +0200 Subject: semaphore: Add DEFINE_SEMAPHORE The full cleanup of init_MUTEX[_LOCKED] and DECLARE_MUTEX has not been done. Some of the users are real semaphores and we should name them as such instead of confusing everyone with "MUTEX". Provide the infrastructure to get finally rid of init_MUTEX[_LOCKED] and DECLARE_MUTEX. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Christoph Hellwig LKML-Reference: <20100907125054.795929962@linutronix.de> --- include/linux/semaphore.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 7415839ac890..5310d27abd2a 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -26,6 +26,9 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } +#define DEFINE_SEMAPHORE(name) \ + struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) + #define DECLARE_MUTEX(name) \ struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) -- cgit v1.2.3-71-gd317 From e3e55ff5854655d8723ad8b307f02515aecc3df5 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 7 Sep 2010 15:52:06 +0800 Subject: spi/dw_spi: clean the cs_control code commit 052dc7c45i "spi/dw_spi: conditional transfer mode change" introduced cs_control code, which has a bug by using bit offset for spi mode to set transfer mode in control register. Also it forces devices who don't need cs_control to re-configure the control registers for each spi transfer. This patch will fix them Signed-off-by: Feng Tang Signed-off-by: Grant Likely --- drivers/spi/dw_spi.c | 17 +++++------------ include/linux/spi/dw_spi.h | 2 ++ 2 files changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c index 11fbbf6fb07b..56247853c298 100644 --- a/drivers/spi/dw_spi.c +++ b/drivers/spi/dw_spi.c @@ -181,10 +181,6 @@ static void flush(struct dw_spi *dws) wait_till_not_busy(dws); } -static void null_cs_control(u32 command) -{ -} - static int null_writer(struct dw_spi *dws) { u8 n_bytes = dws->n_bytes; @@ -322,7 +318,7 @@ static void giveback(struct dw_spi *dws) struct spi_transfer, transfer_list); - if (!last_transfer->cs_change) + if (!last_transfer->cs_change && dws->cs_control) dws->cs_control(MRST_SPI_DEASSERT); msg->state = NULL; @@ -549,13 +545,13 @@ static void pump_transfers(unsigned long data) */ if (dws->cs_control) { if (dws->rx && dws->tx) - chip->tmode = 0x00; + chip->tmode = SPI_TMOD_TR; else if (dws->rx) - chip->tmode = 0x02; + chip->tmode = SPI_TMOD_RO; else - chip->tmode = 0x01; + chip->tmode = SPI_TMOD_TO; - cr0 &= ~(0x3 << SPI_MODE_OFFSET); + cr0 &= ~SPI_TMOD_MASK; cr0 |= (chip->tmode << SPI_TMOD_OFFSET); } @@ -704,9 +700,6 @@ static int dw_spi_setup(struct spi_device *spi) chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL); if (!chip) return -ENOMEM; - - chip->cs_control = null_cs_control; - chip->enable_dma = 0; } /* diff --git a/include/linux/spi/dw_spi.h b/include/linux/spi/dw_spi.h index cc813f95a2f2..c91302f3a257 100644 --- a/include/linux/spi/dw_spi.h +++ b/include/linux/spi/dw_spi.h @@ -14,7 +14,9 @@ #define SPI_MODE_OFFSET 6 #define SPI_SCPH_OFFSET 6 #define SPI_SCOL_OFFSET 7 + #define SPI_TMOD_OFFSET 8 +#define SPI_TMOD_MASK (0x3 << SPI_TMOD_OFFSET) #define SPI_TMOD_TR 0x0 /* xmit & recv */ #define SPI_TMOD_TO 0x1 /* xmit only */ #define SPI_TMOD_RO 0x2 /* recv only */ -- cgit v1.2.3-71-gd317 From d530148ae8bffe1b33f50d1776d185a6e85dc774 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 20 Aug 2010 16:49:43 +0800 Subject: dquot: do full inode dirty in allocating space Alex Shi found a regression when doing ffsb test. The test has several threads, and each thread creates a small file, write to it and then delete it. ffsb reports about 20% regression and Alex bisected it to 43d2932d88e4. The test will call __mark_inode_dirty 3 times. without this commit, we only take inode_lock one time, while with it, we take the lock 3 times with flags ( I_DIRTY_SYNC,I_DIRTY_PAGES,I_DIRTY). Perf shows the lock contention increased too much. Below proposed patch fixes it. fs is allocating blocks, which usually means file writes and the inode will be dirtied soon. We fully dirty the inode to reduce some inode_lock contention in several calls of __mark_inode_dirty. Jan Kara: Added comment. Signed-off-by: Shaohua Li Signed-off-by: Alex Shi Signed-off-by: Jan Kara --- include/linux/quotaops.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index d50ba858cfe0..d1a9193960f1 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -274,8 +274,14 @@ static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) int ret; ret = dquot_alloc_space_nodirty(inode, nr); - if (!ret) - mark_inode_dirty_sync(inode); + if (!ret) { + /* + * Mark inode fully dirty. Since we are allocating blocks, inode + * would become fully dirty soon anyway and it reportedly + * reduces inode_lock contention. + */ + mark_inode_dirty(inode); + } return ret; } -- cgit v1.2.3-71-gd317 From 39aa3cb3e8250db9188a6f1e3fb62ffa1a717678 Mon Sep 17 00:00:00 2001 From: Stefan Bader Date: Tue, 31 Aug 2010 15:52:27 +0200 Subject: mm: Move vma_stack_continue into mm.h So it can be used by all that need to check for that. Signed-off-by: Stefan Bader Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 3 ++- include/linux/mm.h | 6 ++++++ mm/mlock.c | 6 ------ 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 439fc1f1c1c4..271afc48b9a5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -224,7 +224,8 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; if (vma->vm_flags & VM_GROWSDOWN) - start += PAGE_SIZE; + if (!vma_stack_continue(vma->vm_prev, vma->vm_start)) + start += PAGE_SIZE; seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", start, diff --git a/include/linux/mm.h b/include/linux/mm.h index e6b1210772ce..74949fbef8c6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -864,6 +864,12 @@ int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); +/* Is the vma a continuation of the stack vma above it? */ +static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) +{ + return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); +} + extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len); diff --git a/mm/mlock.c b/mm/mlock.c index cbae7c5b9568..b70919ce4f72 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -135,12 +135,6 @@ void munlock_vma_page(struct page *page) } } -/* Is the vma a continuation of the stack vma above it? */ -static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); -} - static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) { return (vma->vm_flags & VM_GROWSDOWN) && -- cgit v1.2.3-71-gd317 From a73f8844e1fc54c3762555c1cf1f71774142ca91 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Wed, 8 Sep 2010 16:54:54 -0600 Subject: lglock: make lg_lock_global() actually lock globally lg_lock_global() currently only acquires spinlocks for online CPUs, but it's meant to lock all possible CPUs. Lglock-protected resources may be associated with removed CPUs - and, indeed, that could happen with the per-superblock open files lists. At Nick's suggestion, change for_each_online_cpu() to for_each_possible_cpu() to protect accesses to those resources. Cc: Al Viro Acked-by: Nick Piggin Signed-off-by: Jonathan Corbet Signed-off-by: Linus Torvalds --- include/linux/lglock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lglock.h b/include/linux/lglock.h index b288cb713b90..f549056fb20b 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -150,7 +150,7 @@ int i; \ preempt_disable(); \ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ - for_each_online_cpu(i) { \ + for_each_possible_cpu(i) { \ arch_spinlock_t *lock; \ lock = &per_cpu(name##_lock, i); \ arch_spin_lock(lock); \ @@ -161,7 +161,7 @@ void name##_global_unlock(void) { \ int i; \ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ - for_each_online_cpu(i) { \ + for_each_possible_cpu(i) { \ arch_spinlock_t *lock; \ lock = &per_cpu(name##_lock, i); \ arch_spin_unlock(lock); \ -- cgit v1.2.3-71-gd317 From f3c65b2870f2481f3646bc410a58a12989ecc704 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 9 Sep 2010 16:37:24 -0700 Subject: mmc: avoid getting CID on SDIO-only cards The introduction of support for SD combo cards breaks the initialization of all CSR SDIO chips. The GO_IDLE (CMD0) in mmc_sd_get_cid() causes CSR chips to be reset (this is non-standard behavior). When initializing an SDIO card check for a combo card by using the memory present bit in the R4 response to IO_SEND_OP_COND (CMD5). This avoids the call to mmc_sd_get_cid() on an SDIO-only card. Signed-off-by: David Vrabel Acked-by: Michal Mirolaw Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/mmc/core/sdio.c | 5 ++--- include/linux/mmc/sdio.h | 2 ++ 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index bd2755e8d9a3..f332c52968b7 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -362,9 +362,8 @@ static int mmc_sdio_init_card(struct mmc_host *host, u32 ocr, goto err; } - err = mmc_sd_get_cid(host, host->ocr & ocr, card->raw_cid); - - if (!err) { + if (ocr & R4_MEMORY_PRESENT + && mmc_sd_get_cid(host, host->ocr & ocr, card->raw_cid) == 0) { card->type = MMC_TYPE_SD_COMBO; if (oldcard && (oldcard->type != MMC_TYPE_SD_COMBO || diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h index 329a8faa6e37..245cdacee544 100644 --- a/include/linux/mmc/sdio.h +++ b/include/linux/mmc/sdio.h @@ -38,6 +38,8 @@ * [8:0] Byte/block count */ +#define R4_MEMORY_PRESENT (1 << 27) + /* SDIO status in R5 Type -- cgit v1.2.3-71-gd317 From e0bf1024b36be90da241af3c2767311e055b612c Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 9 Sep 2010 16:37:26 -0700 Subject: kfifo: add parenthesis for macro parameter reference Some macro parameter references inside typeof() operator are not enclosed with parenthesis. It should be safer to add them. Signed-off-by: Huang Ying Acked-by: Stefani Seibold Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 58 +++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 4aa95f203f3e..62dbee554f60 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -214,7 +214,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_reset(fifo) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ __tmp->kfifo.in = __tmp->kfifo.out = 0; \ }) @@ -228,7 +228,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_reset_out(fifo) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ __tmp->kfifo.out = __tmp->kfifo.in; \ }) @@ -238,7 +238,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_len(fifo) \ ({ \ - typeof(fifo + 1) __tmpl = (fifo); \ + typeof((fifo) + 1) __tmpl = (fifo); \ __tmpl->kfifo.in - __tmpl->kfifo.out; \ }) @@ -248,7 +248,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_is_empty(fifo) \ ({ \ - typeof(fifo + 1) __tmpq = (fifo); \ + typeof((fifo) + 1) __tmpq = (fifo); \ __tmpq->kfifo.in == __tmpq->kfifo.out; \ }) @@ -258,7 +258,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_is_full(fifo) \ ({ \ - typeof(fifo + 1) __tmpq = (fifo); \ + typeof((fifo) + 1) __tmpq = (fifo); \ kfifo_len(__tmpq) > __tmpq->kfifo.mask; \ }) @@ -269,7 +269,7 @@ __kfifo_must_check_helper(unsigned int val) #define kfifo_avail(fifo) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmpq = (fifo); \ + typeof((fifo) + 1) __tmpq = (fifo); \ const size_t __recsize = sizeof(*__tmpq->rectype); \ unsigned int __avail = kfifo_size(__tmpq) - kfifo_len(__tmpq); \ (__recsize) ? ((__avail <= __recsize) ? 0 : \ @@ -284,7 +284,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_skip(fifo) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__recsize) \ @@ -302,7 +302,7 @@ __kfifo_must_check_helper( \ #define kfifo_peek_len(fifo) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (!__recsize) ? kfifo_len(__tmp) * sizeof(*__tmp->type) : \ @@ -325,7 +325,7 @@ __kfifo_must_check_helper( \ #define kfifo_alloc(fifo, size, gfp_mask) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ __is_kfifo_ptr(__tmp) ? \ __kfifo_alloc(__kfifo, size, sizeof(*__tmp->type), gfp_mask) : \ @@ -339,7 +339,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_free(fifo) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__is_kfifo_ptr(__tmp)) \ __kfifo_free(__kfifo); \ @@ -358,7 +358,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_init(fifo, buffer, size) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ __is_kfifo_ptr(__tmp) ? \ __kfifo_init(__kfifo, buffer, size, sizeof(*__tmp->type)) : \ @@ -379,8 +379,8 @@ __kfifo_must_check_helper( \ */ #define kfifo_put(fifo, val) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((val) + 1) __val = (val); \ unsigned int __ret; \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -421,8 +421,8 @@ __kfifo_must_check_helper( \ #define kfifo_get(fifo, val) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((val) + 1) __val = (val); \ unsigned int __ret; \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -462,8 +462,8 @@ __kfifo_must_check_helper( \ #define kfifo_peek(fifo, val) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((val) + 1) __val = (val); \ unsigned int __ret; \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -501,8 +501,8 @@ __kfifo_must_check_helper( \ */ #define kfifo_in(fifo, buf, n) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((buf) + 1) __buf = (buf); \ unsigned long __n = (n); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -554,8 +554,8 @@ __kfifo_must_check_helper( \ #define kfifo_out(fifo, buf, n) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((buf) + 1) __buf = (buf); \ unsigned long __n = (n); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -611,7 +611,7 @@ __kfifo_must_check_helper( \ #define kfifo_from_user(fifo, from, len, copied) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ const void __user *__from = (from); \ unsigned int __len = (len); \ unsigned int *__copied = (copied); \ @@ -639,7 +639,7 @@ __kfifo_must_check_helper( \ #define kfifo_to_user(fifo, to, len, copied) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ void __user *__to = (to); \ unsigned int __len = (len); \ unsigned int *__copied = (copied); \ @@ -666,7 +666,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ int __nents = (nents); \ unsigned int __len = (len); \ @@ -690,7 +690,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_in_finish(fifo, len) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ unsigned int __len = (len); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -717,7 +717,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ int __nents = (nents); \ unsigned int __len = (len); \ @@ -741,7 +741,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_out_finish(fifo, len) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ unsigned int __len = (len); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -766,8 +766,8 @@ __kfifo_must_check_helper( \ #define kfifo_out_peek(fifo, buf, n) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((buf) + 1) __buf = (buf); \ unsigned long __n = (n); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ -- cgit v1.2.3-71-gd317 From 31583bb0cf6cc40f2a468a4d2f3b9cbefd24f891 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 9 Sep 2010 16:37:37 -0700 Subject: cgroups: fix API thinko Add cgroup_attach_task_all() The existing cgroup_attach_task_current_cg() API is called by a thread to attach another thread to all of its cgroups; this is unsuitable for cases where a privileged task wants to attach itself to the cgroups of a less privileged one, since the call must be made from the context of the target task. This patch adds a more generic cgroup_attach_task_all() API that allows both the source task and to-be-moved task to be specified. cgroup_attach_task_current_cg() becomes a specialization of the more generic new function. [menage@google.com: rewrote changelog] [akpm@linux-foundation.org: address reviewer comments] Signed-off-by: Michael S. Tsirkin Tested-by: Alex Williamson Acked-by: Paul Menage Cc: Li Zefan Cc: Ben Blum Cc: Sridhar Samudrala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 12 +++++++++++- kernel/cgroup.c | 13 +++++++------ 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed3e92e41c6e..0c991023ee47 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -578,7 +578,12 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); -int cgroup_attach_task_current_cg(struct task_struct *); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); + +static inline int cgroup_attach_task_current_cg(struct task_struct *tsk) +{ + return cgroup_attach_task_all(current, tsk); +} /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works @@ -636,6 +641,11 @@ static inline int cgroupstats_build(struct cgroupstats *stats, } /* No cgroups - nothing to do */ +static inline int cgroup_attach_task_all(struct task_struct *from, + struct task_struct *t) +{ + return 0; +} static inline int cgroup_attach_task_current_cg(struct task_struct *t) { return 0; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 192f88c5b0f9..c9483d8f6140 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1791,19 +1791,20 @@ out: } /** - * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup + * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' + * @from: attach to all cgroups of a given task * @tsk: the task to be attached */ -int cgroup_attach_task_current_cg(struct task_struct *tsk) +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroupfs_root *root; - struct cgroup *cur_cg; int retval = 0; cgroup_lock(); for_each_active_root(root) { - cur_cg = task_cgroup_from_root(current, root); - retval = cgroup_attach_task(cur_cg, tsk); + struct cgroup *from_cg = task_cgroup_from_root(from, root); + + retval = cgroup_attach_task(from_cg, tsk); if (retval) break; } @@ -1811,7 +1812,7 @@ int cgroup_attach_task_current_cg(struct task_struct *tsk) return retval; } -EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg); +EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /* * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex -- cgit v1.2.3-71-gd317 From 4969c1192d15afa3389e7ae3302096ff684ba655 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 9 Sep 2010 16:37:52 -0700 Subject: mm: fix swapin race condition The pte_same check is reliable only if the swap entry remains pinned (by the page lock on swapcache). We've also to ensure the swapcache isn't removed before we take the lock as try_to_free_swap won't care about the page pin. One of the possible impacts of this patch is that a KSM-shared page can point to the anon_vma of another process, which could exit before the page is freed. This can leave a page with a pointer to a recycled anon_vma object, or worse, a pointer to something that is no longer an anon_vma. [riel@redhat.com: changelog help] Signed-off-by: Andrea Arcangeli Acked-by: Hugh Dickins Reviewed-by: Rik van Riel Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 20 +++++++++----------- mm/ksm.c | 3 --- mm/memory.c | 39 ++++++++++++++++++++++++++++++++++----- 3 files changed, 43 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 74d691ee9121..3319a6967626 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -16,6 +16,9 @@ struct stable_node; struct mem_cgroup; +struct page *ksm_does_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address); + #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -70,19 +73,14 @@ static inline void set_page_stable_node(struct page *page, * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ -struct page *ksm_does_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); -static inline struct page *ksm_might_need_to_copy(struct page *page, +static inline int ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = page_anon_vma(page); - if (!anon_vma || - (anon_vma->root == vma->anon_vma->root && - page->index == linear_page_index(vma, address))) - return page; - - return ksm_does_need_to_copy(page, vma, address); + return anon_vma && + (anon_vma->root != vma->anon_vma->root || + page->index != linear_page_index(vma, address)); } int page_referenced_ksm(struct page *page, @@ -115,10 +113,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } -static inline struct page *ksm_might_need_to_copy(struct page *page, +static inline int ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - return page; + return 0; } static inline int page_referenced_ksm(struct page *page, diff --git a/mm/ksm.c b/mm/ksm.c index e2ae00458320..b1873cf03ed9 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1504,8 +1504,6 @@ struct page *ksm_does_need_to_copy(struct page *page, { struct page *new_page; - unlock_page(page); /* any racers will COW it, not modify it */ - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page) { copy_user_highpage(new_page, page, address, vma); @@ -1521,7 +1519,6 @@ struct page *ksm_does_need_to_copy(struct page *page, add_page_to_unevictable_list(new_page); } - page_cache_release(page); return new_page; } diff --git a/mm/memory.c b/mm/memory.c index 6b2ab1051851..71b161b73bb5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2623,7 +2623,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned int flags, pte_t orig_pte) { spinlock_t *ptl; - struct page *page; + struct page *page, *swapcache = NULL; swp_entry_t entry; pte_t pte; struct mem_cgroup *ptr = NULL; @@ -2679,10 +2679,23 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - page = ksm_might_need_to_copy(page, vma, address); - if (!page) { - ret = VM_FAULT_OOM; - goto out; + /* + * Make sure try_to_free_swap didn't release the swapcache + * from under us. The page pin isn't enough to prevent that. + */ + if (unlikely(!PageSwapCache(page))) + goto out_page; + + if (ksm_might_need_to_copy(page, vma, address)) { + swapcache = page; + page = ksm_does_need_to_copy(page, vma, address); + + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + page = swapcache; + swapcache = NULL; + goto out_page; + } } if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { @@ -2735,6 +2748,18 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); + if (swapcache) { + /* + * Hold the lock to avoid the swap entry to be reused + * until we take the PT lock for the pte_same() check + * (to avoid false positives from pte_same). For + * further safety release the lock after the swap_free + * so that the swap count won't change under a + * parallel locked swapcache. + */ + unlock_page(swapcache); + page_cache_release(swapcache); + } if (flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); @@ -2756,6 +2781,10 @@ out_page: unlock_page(page); out_release: page_cache_release(page); + if (swapcache) { + unlock_page(swapcache); + page_cache_release(swapcache); + } return ret; } -- cgit v1.2.3-71-gd317 From 5affb607720d734ca572b8a77c5c7d62d3042b6f Mon Sep 17 00:00:00 2001 From: Gregory Bean Date: Thu, 9 Sep 2010 16:38:02 -0700 Subject: gpio: sx150x: correct and refine reset-on-probe behavior Replace the arbitrary software-reset call from the device-probe method, because: - It is defective. To work correctly, it should be two byte writes, not a single word write. As it stands, it does nothing. - Some devices with sx150x expanders installed have their NRESET pins ganged on the same line, so resetting one causes the others to reset - not a nice thing to do arbitrarily! - The probe, usually taking place at boot, implies a recent hard-reset, so a software reset at this point is just a waste of energy anyway. Therefore, make it optional, defaulting to off, as this will match the common case of probing at powerup and also matches the current broken no-op behavior. Signed-off-by: Gregory Bean Reviewed-by: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpio/sx150x.c | 26 +++++++++++++++++++++----- include/linux/i2c/sx150x.h | 4 ++++ 2 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/sx150x.c b/drivers/gpio/sx150x.c index b42f42ca70c3..823559ab0e24 100644 --- a/drivers/gpio/sx150x.c +++ b/drivers/gpio/sx150x.c @@ -459,17 +459,33 @@ static int sx150x_init_io(struct sx150x_chip *chip, u8 base, u16 cfg) return err; } -static int sx150x_init_hw(struct sx150x_chip *chip, - struct sx150x_platform_data *pdata) +static int sx150x_reset(struct sx150x_chip *chip) { - int err = 0; + int err; - err = i2c_smbus_write_word_data(chip->client, + err = i2c_smbus_write_byte_data(chip->client, chip->dev_cfg->reg_reset, - 0x3412); + 0x12); if (err < 0) return err; + err = i2c_smbus_write_byte_data(chip->client, + chip->dev_cfg->reg_reset, + 0x34); + return err; +} + +static int sx150x_init_hw(struct sx150x_chip *chip, + struct sx150x_platform_data *pdata) +{ + int err = 0; + + if (pdata->reset_during_probe) { + err = sx150x_reset(chip); + if (err < 0) + return err; + } + err = sx150x_i2c_write(chip->client, chip->dev_cfg->reg_misc, 0x01); diff --git a/include/linux/i2c/sx150x.h b/include/linux/i2c/sx150x.h index ee3049cb9ba5..52baa79d69a7 100644 --- a/include/linux/i2c/sx150x.h +++ b/include/linux/i2c/sx150x.h @@ -63,6 +63,9 @@ * IRQ lines will appear. Similarly to gpio_base, the expander * will create a block of irqs beginning at this number. * This value is ignored if irq_summary is < 0. + * @reset_during_probe: If set to true, the driver will trigger a full + * reset of the chip at the beginning of the probe + * in order to place it in a known state. */ struct sx150x_platform_data { unsigned gpio_base; @@ -73,6 +76,7 @@ struct sx150x_platform_data { u16 io_polarity; int irq_summary; unsigned irq_base; + bool reset_during_probe; }; #endif /* __LINUX_I2C_SX150X_H */ -- cgit v1.2.3-71-gd317 From 910321ea817a202ff70fac666e37e2c8e2f88823 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 9 Sep 2010 16:38:07 -0700 Subject: swap: revert special hibernation allocation Please revert 2.6.36-rc commit d2997b1042ec150616c1963b5e5e919ffd0b0ebf "hibernation: freeze swap at hibernation". It complicated matters by adding a second swap allocation path, just for hibernation; without in any way fixing the issue that it was intended to address - page reclaim after fixing the hibernation image might free swap from a page already imaged as swapcache, letting its swap be reallocated to store a different page of the image: resulting in data corruption if the imaged page were freed as clean then swapped back in. Pages freed to si->swap_map were still in danger of being reallocated by the alternative allocation path. I guess it inadvertently fixed slow SSD swap allocation for hibernation, as reported by Nigel Cunningham: by missing out the discards that occur on the usual swap allocation path; but that was unintentional, and needs a separate fix. Signed-off-by: Hugh Dickins Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: "Rafael J. Wysocki" Cc: Ondrej Zary Cc: Andrea Gelmini Cc: Balbir Singh Cc: Andrea Arcangeli Cc: Nigel Cunningham Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 8 +---- kernel/power/hibernate.c | 1 - kernel/power/snapshot.c | 1 - kernel/power/swap.c | 6 ++-- mm/swapfile.c | 94 ++++++++++++------------------------------------ 5 files changed, 26 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fee51a11b73..bf4eb62506db 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -315,6 +315,7 @@ extern long nr_swap_pages; extern long total_swap_pages; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); +extern swp_entry_t get_swap_page_of_type(int); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); @@ -331,13 +332,6 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_HIBERNATION -void hibernation_freeze_swap(void); -void hibernation_thaw_swap(void); -swp_entry_t get_swap_for_hibernation(int type); -void swap_free_for_hibernation(swp_entry_t val); -#endif - /* linux/mm/thrash.c */ extern struct mm_struct *swap_token_mm; extern void grab_swap_token(struct mm_struct *); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index c77963938bca..8dc31e02ae12 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -338,7 +338,6 @@ int hibernation_snapshot(int platform_mode) goto Close; suspend_console(); - hibernation_freeze_swap(); saved_mask = clear_gfp_allowed_mask(GFP_IOFS); error = dpm_suspend_start(PMSG_FREEZE); if (error) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 5e7edfb05e66..f6cd6faf84fd 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1086,7 +1086,6 @@ void swsusp_free(void) buffer = NULL; alloc_normal = 0; alloc_highmem = 0; - hibernation_thaw_swap(); } /* Helper functions used for the shrinking of memory. */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 5d0059eed3e4..e6a5bdf61a37 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -136,10 +136,10 @@ sector_t alloc_swapdev_block(int swap) { unsigned long offset; - offset = swp_offset(get_swap_for_hibernation(swap)); + offset = swp_offset(get_swap_page_of_type(swap)); if (offset) { if (swsusp_extents_insert(offset)) - swap_free_for_hibernation(swp_entry(swap, offset)); + swap_free(swp_entry(swap, offset)); else return swapdev_block(swap, offset); } @@ -163,7 +163,7 @@ void free_all_swap_pages(int swap) ext = container_of(node, struct swsusp_extent, node); rb_erase(node, &swsusp_extents); for (offset = ext->start; offset <= ext->end; offset++) - swap_free_for_hibernation(swp_entry(swap, offset)); + swap_free(swp_entry(swap, offset)); kfree(ext); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 1f3f9c59a73a..f08d165871b3 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -47,8 +47,6 @@ long nr_swap_pages; long total_swap_pages; static int least_priority; -static bool swap_for_hibernation; - static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; @@ -453,8 +451,6 @@ swp_entry_t get_swap_page(void) spin_lock(&swap_lock); if (nr_swap_pages <= 0) goto noswap; - if (swap_for_hibernation) - goto noswap; nr_swap_pages--; for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { @@ -487,6 +483,28 @@ noswap: return (swp_entry_t) {0}; } +/* The only caller of this function is now susupend routine */ +swp_entry_t get_swap_page_of_type(int type) +{ + struct swap_info_struct *si; + pgoff_t offset; + + spin_lock(&swap_lock); + si = swap_info[type]; + if (si && (si->flags & SWP_WRITEOK)) { + nr_swap_pages--; + /* This is called for allocating swap entry, not cache */ + offset = scan_swap_map(si, 1); + if (offset) { + spin_unlock(&swap_lock); + return swp_entry(type, offset); + } + nr_swap_pages++; + } + spin_unlock(&swap_lock); + return (swp_entry_t) {0}; +} + static struct swap_info_struct *swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; @@ -746,74 +764,6 @@ int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep) #endif #ifdef CONFIG_HIBERNATION - -static pgoff_t hibernation_offset[MAX_SWAPFILES]; -/* - * Once hibernation starts to use swap, we freeze swap_map[]. Otherwise, - * saved swap_map[] image to the disk will be an incomplete because it's - * changing without synchronization with hibernation snap shot. - * At resume, we just make swap_for_hibernation=false. We can forget - * used maps easily. - */ -void hibernation_freeze_swap(void) -{ - int i; - - spin_lock(&swap_lock); - - printk(KERN_INFO "PM: Freeze Swap\n"); - swap_for_hibernation = true; - for (i = 0; i < MAX_SWAPFILES; i++) - hibernation_offset[i] = 1; - spin_unlock(&swap_lock); -} - -void hibernation_thaw_swap(void) -{ - spin_lock(&swap_lock); - if (swap_for_hibernation) { - printk(KERN_INFO "PM: Thaw Swap\n"); - swap_for_hibernation = false; - } - spin_unlock(&swap_lock); -} - -/* - * Because updateing swap_map[] can make not-saved-status-change, - * we use our own easy allocator. - * Please see kernel/power/swap.c, Used swaps are recorded into - * RB-tree. - */ -swp_entry_t get_swap_for_hibernation(int type) -{ - pgoff_t off; - swp_entry_t val = {0}; - struct swap_info_struct *si; - - spin_lock(&swap_lock); - - si = swap_info[type]; - if (!si || !(si->flags & SWP_WRITEOK)) - goto done; - - for (off = hibernation_offset[type]; off < si->max; ++off) { - if (!si->swap_map[off]) - break; - } - if (off < si->max) { - val = swp_entry(type, off); - hibernation_offset[type] = off + 1; - } -done: - spin_unlock(&swap_lock); - return val; -} - -void swap_free_for_hibernation(swp_entry_t ent) -{ - /* Nothing to do */ -} - /* * Find the swap type that corresponds to given device (if any). * -- cgit v1.2.3-71-gd317 From 3399446632739fcd05fd8b272b476a69c6e6d14a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 9 Sep 2010 16:38:11 -0700 Subject: swap: discard while swapping only if SWAP_FLAG_DISCARD Tests with recent firmware on Intel X25-M 80GB and OCZ Vertex 60GB SSDs show a shift since I last tested in December: in part because of firmware updates, in part because of the necessary move from barriers to awaiting completion at the block layer. While discard at swapon still shows as slightly beneficial on both, discarding 1MB swap cluster when allocating is now disadvanteous: adds 25% overhead on Intel, adds 230% on OCZ (YMMV). Surrender: discard as presently implemented is more hindrance than help for swap; but might prove useful on other devices, or with improvements. So continue to do the discard at swapon, but make discard while swapping conditional on a SWAP_FLAG_DISCARD to sys_swapon() (which has been using only the lower 16 bits of int flags). We can add a --discard or -d to swapon(8), and a "discard" to swap in /etc/fstab: matching the mount option for btrfs, ext4, fat, gfs2, nilfs2. Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Cc: Nigel Cunningham Cc: Tejun Heo Cc: Jens Axboe Cc: James Bottomley Cc: "Martin K. Petersen" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 ++- mm/swapfile.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index bf4eb62506db..7cdd63366f88 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -19,6 +19,7 @@ struct bio; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 +#define SWAP_FLAG_DISCARD 0x10000 /* discard swap cluster after use */ static inline int current_is_kswapd(void) { @@ -142,7 +143,7 @@ struct swap_extent { enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ - SWP_DISCARDABLE = (1 << 2), /* blkdev supports discard */ + SWP_DISCARDABLE = (1 << 2), /* swapon+blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 1894dead0b58..7c703ff2f36f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2047,7 +2047,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) p->flags |= SWP_SOLIDSTATE; p->cluster_next = 1 + (random32() % p->highest_bit); } - if (discard_swap(p) == 0) + if (discard_swap(p) == 0 && (swap_flags & SWAP_FLAG_DISCARD)) p->flags |= SWP_DISCARDABLE; } -- cgit v1.2.3-71-gd317 From aa45484031ddee09b06350ab8528bfe5b2c76d1c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 9 Sep 2010 16:38:17 -0700 Subject: mm: page allocator: calculate a better estimate of NR_FREE_PAGES when memory is low and kswapd is awake Ordinarily watermark checks are based on the vmstat NR_FREE_PAGES as it is cheaper than scanning a number of lists. To avoid synchronization overhead, counter deltas are maintained on a per-cpu basis and drained both periodically and when the delta is above a threshold. On large CPU systems, the difference between the estimated and real value of NR_FREE_PAGES can be very high. If NR_FREE_PAGES is much higher than number of real free page in buddy, the VM can allocate pages below min watermark, at worst reducing the real number of pages to zero. Even if the OOM killer kills some victim for freeing memory, it may not free memory if the exit path requires a new page resulting in livelock. This patch introduces a zone_page_state_snapshot() function (courtesy of Christoph) that takes a slightly more accurate view of an arbitrary vmstat counter. It is used to read NR_FREE_PAGES while kswapd is awake to avoid the watermark being accidentally broken. The estimate is not perfect and may result in cache line bounces but is expected to be lighter than the IPI calls necessary to continually drain the per-cpu counters while kswapd is awake. Signed-off-by: Christoph Lameter Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++++++++ include/linux/vmstat.h | 22 ++++++++++++++++++++++ mm/mmzone.c | 21 +++++++++++++++++++++ mm/page_alloc.c | 4 ++-- mm/vmstat.c | 15 ++++++++++++++- 5 files changed, 72 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6e6e62648a4d..3984c4eb41fd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -283,6 +283,13 @@ struct zone { /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long watermark[NR_WMARK]; + /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several @@ -441,6 +448,12 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } +#ifdef CONFIG_SMP +unsigned long zone_nr_free_pages(struct zone *zone); +#else +#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES) +#endif /* CONFIG_SMP */ + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 7f43ccdc1d38..eaaea37b3b75 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -170,6 +170,28 @@ static inline unsigned long zone_page_state(struct zone *zone, return x; } +/* + * More accurate version that also considers the currently pending + * deltas. For that we need to loop over all cpus to find the current + * deltas. There is no synchronization so the result cannot be + * exactly accurate either. + */ +static inline unsigned long zone_page_state_snapshot(struct zone *zone, + enum zone_stat_item item) +{ + long x = atomic_long_read(&zone->vm_stat[item]); + +#ifdef CONFIG_SMP + int cpu; + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + + if (x < 0) + x = 0; +#endif + return x; +} + extern unsigned long global_reclaimable_pages(void); extern unsigned long zone_reclaimable_pages(struct zone *zone); diff --git a/mm/mmzone.c b/mm/mmzone.c index f5b7d1760213..e35bfb82c855 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -87,3 +87,24 @@ int memmap_valid_within(unsigned long pfn, return 1; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ + +#ifdef CONFIG_SMP +/* Called when a more accurate view of NR_FREE_PAGES is needed */ +unsigned long zone_nr_free_pages(struct zone *zone) +{ + unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES); + + /* + * While kswapd is awake, it is considered the zone is under some + * memory pressure. Under pressure, there is a risk that + * per-cpu-counter-drift will allow the min watermark to be breached + * potentially causing a live-lock. While kswapd is awake and + * free pages are low, get a better estimate for free pages + */ + if (nr_free_pages < zone->percpu_drift_mark && + !waitqueue_active(&zone->zone_pgdat->kswapd_wait)) + return zone_page_state_snapshot(zone, NR_FREE_PAGES); + + return nr_free_pages; +} +#endif /* CONFIG_SMP */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 452e2ba06c7c..b2d21e06d45d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1462,7 +1462,7 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, { /* free_pages my go negative - that's OK */ long min = mark; - long free_pages = zone_page_state(z, NR_FREE_PAGES) - (1 << order) + 1; + long free_pages = zone_nr_free_pages(z) - (1 << order) + 1; int o; if (alloc_flags & ALLOC_HIGH) @@ -2424,7 +2424,7 @@ void show_free_areas(void) " all_unreclaimable? %s" "\n", zone->name, - K(zone_page_state(zone, NR_FREE_PAGES)), + K(zone_nr_free_pages(zone)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), diff --git a/mm/vmstat.c b/mm/vmstat.c index a8d6b59e609a..355a9e669aaa 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -138,11 +138,24 @@ static void refresh_zone_stat_thresholds(void) int threshold; for_each_populated_zone(zone) { + unsigned long max_drift, tolerate_drift; + threshold = calculate_threshold(zone); for_each_online_cpu(cpu) per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; + + /* + * Only set percpu_drift_mark if there is a danger that + * NR_FREE_PAGES reports the low watermark is ok when in fact + * the min watermark could be breached by an allocation + */ + tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone); + max_drift = num_online_cpus() * threshold; + if (max_drift > tolerate_drift) + zone->percpu_drift_mark = high_wmark_pages(zone) + + max_drift; } } @@ -813,7 +826,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n scanned %lu" "\n spanned %lu" "\n present %lu", - zone_page_state(zone, NR_FREE_PAGES), + zone_nr_free_pages(zone), min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), -- cgit v1.2.3-71-gd317 From e2f3d75fc0e4a0d03c61872bad39ffa2e74a04ff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 7 Sep 2010 14:05:31 +0200 Subject: libata: skip EH autopsy and recovery during suspend For some mysterious reason, certain hardware reacts badly to usual EH actions while the system is going for suspend. As the devices won't be needed until the system is resumed, ask EH to skip usual autopsy and recovery and proceed directly to suspend. Signed-off-by: Tejun Heo Tested-by: Stephan Diestelhorst Cc: stable@kernel.org Signed-off-by: Jeff Garzik --- drivers/ata/libata-core.c | 14 +++++++++++++- drivers/ata/libata-eh.c | 4 ++++ include/linux/libata.h | 1 + 3 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index c035b3d041ee..932eaee50245 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5418,6 +5418,7 @@ static int ata_host_request_pm(struct ata_host *host, pm_message_t mesg, */ int ata_host_suspend(struct ata_host *host, pm_message_t mesg) { + unsigned int ehi_flags = ATA_EHI_QUIET; int rc; /* @@ -5426,7 +5427,18 @@ int ata_host_suspend(struct ata_host *host, pm_message_t mesg) */ ata_lpm_enable(host); - rc = ata_host_request_pm(host, mesg, 0, ATA_EHI_QUIET, 1); + /* + * On some hardware, device fails to respond after spun down + * for suspend. As the device won't be used before being + * resumed, we don't need to touch the device. Ask EH to skip + * the usual stuff and proceed directly to suspend. + * + * http://thread.gmane.org/gmane.linux.ide/46764 + */ + if (mesg.event == PM_EVENT_SUSPEND) + ehi_flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_NO_RECOVERY; + + rc = ata_host_request_pm(host, mesg, 0, ehi_flags, 1); if (rc == 0) host->dev->power.power_state = mesg; return rc; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index c9ae299b8342..e48302eae55f 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -3235,6 +3235,10 @@ static int ata_eh_skip_recovery(struct ata_link *link) if (link->flags & ATA_LFLAG_DISABLED) return 1; + /* skip if explicitly requested */ + if (ehc->i.flags & ATA_EHI_NO_RECOVERY) + return 1; + /* thaw frozen port and recover failed devices */ if ((ap->pflags & ATA_PFLAG_FROZEN) || ata_link_nr_enabled(link)) return 0; diff --git a/include/linux/libata.h b/include/linux/libata.h index f010f18a0f86..7de282d8bedf 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -335,6 +335,7 @@ enum { ATA_EHI_HOTPLUGGED = (1 << 0), /* could have been hotplugged */ ATA_EHI_NO_AUTOPSY = (1 << 2), /* no autopsy */ ATA_EHI_QUIET = (1 << 3), /* be quiet */ + ATA_EHI_NO_RECOVERY = (1 << 4), /* no recovery */ ATA_EHI_DID_SOFTRESET = (1 << 16), /* already soft-reset this port */ ATA_EHI_DID_HARDRESET = (1 << 17), /* already soft-reset this port */ -- cgit v1.2.3-71-gd317 From ea3c64506ea7965f86f030155e6fdef381de10e2 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 31 Aug 2010 16:20:36 -0700 Subject: libata-sff: Reenable Port Multiplier after libata-sff remodeling. Keep track of the link on the which the current request is in progress. It allows support of links behind port multiplier. Not all libata-sff is PMP compliant. Code for native BMDMA controller does not take in accound PMP. Tested on Marvell 7042 and Sil7526. Signed-off-by: Gwendal Grignou Signed-off-by: Jeff Garzik --- drivers/ata/libata-sff.c | 38 ++++++++++++++++++++++++++++---------- drivers/ata/sata_mv.c | 2 +- include/linux/libata.h | 3 ++- 3 files changed, 31 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index dee3c2c52562..e30c537cce32 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1045,7 +1045,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, u8 status, int in_wq) { - struct ata_eh_info *ehi = &ap->link.eh_info; + struct ata_link *link = qc->dev->link; + struct ata_eh_info *ehi = &link->eh_info; unsigned long flags = 0; int poll_next; @@ -1301,8 +1302,14 @@ fsm_start: } EXPORT_SYMBOL_GPL(ata_sff_hsm_move); -void ata_sff_queue_pio_task(struct ata_port *ap, unsigned long delay) +void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay) { + struct ata_port *ap = link->ap; + + WARN_ON((ap->sff_pio_task_link != NULL) && + (ap->sff_pio_task_link != link)); + ap->sff_pio_task_link = link; + /* may fail if ata_sff_flush_pio_task() in progress */ queue_delayed_work(ata_sff_wq, &ap->sff_pio_task, msecs_to_jiffies(delay)); @@ -1324,14 +1331,18 @@ static void ata_sff_pio_task(struct work_struct *work) { struct ata_port *ap = container_of(work, struct ata_port, sff_pio_task.work); + struct ata_link *link = ap->sff_pio_task_link; struct ata_queued_cmd *qc; u8 status; int poll_next; + BUG_ON(ap->sff_pio_task_link == NULL); /* qc can be NULL if timeout occurred */ - qc = ata_qc_from_tag(ap, ap->link.active_tag); - if (!qc) + qc = ata_qc_from_tag(ap, link->active_tag); + if (!qc) { + ap->sff_pio_task_link = NULL; return; + } fsm_start: WARN_ON_ONCE(ap->hsm_task_state == HSM_ST_IDLE); @@ -1348,11 +1359,16 @@ fsm_start: msleep(2); status = ata_sff_busy_wait(ap, ATA_BUSY, 10); if (status & ATA_BUSY) { - ata_sff_queue_pio_task(ap, ATA_SHORT_PAUSE); + ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE); return; } } + /* + * hsm_move() may trigger another command to be processed. + * clean the link beforehand. + */ + ap->sff_pio_task_link = NULL; /* move the HSM */ poll_next = ata_sff_hsm_move(ap, qc, status, 1); @@ -1379,6 +1395,7 @@ fsm_start: unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; + struct ata_link *link = qc->dev->link; /* Use polling pio if the LLD doesn't handle * interrupt driven pio and atapi CDB interrupt. @@ -1399,7 +1416,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) ap->hsm_task_state = HSM_ST_LAST; if (qc->tf.flags & ATA_TFLAG_POLLING) - ata_sff_queue_pio_task(ap, 0); + ata_sff_queue_pio_task(link, 0); break; @@ -1412,7 +1429,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) if (qc->tf.flags & ATA_TFLAG_WRITE) { /* PIO data out protocol */ ap->hsm_task_state = HSM_ST_FIRST; - ata_sff_queue_pio_task(ap, 0); + ata_sff_queue_pio_task(link, 0); /* always send first data block using the * ata_sff_pio_task() codepath. @@ -1422,7 +1439,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) ap->hsm_task_state = HSM_ST; if (qc->tf.flags & ATA_TFLAG_POLLING) - ata_sff_queue_pio_task(ap, 0); + ata_sff_queue_pio_task(link, 0); /* if polling, ata_sff_pio_task() handles the * rest. otherwise, interrupt handler takes @@ -1444,7 +1461,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) /* send cdb by polling if no cdb interrupt */ if ((!(qc->dev->flags & ATA_DFLAG_CDB_INTR)) || (qc->tf.flags & ATA_TFLAG_POLLING)) - ata_sff_queue_pio_task(ap, 0); + ata_sff_queue_pio_task(link, 0); break; default: @@ -2737,6 +2754,7 @@ EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep); unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; + struct ata_link *link = qc->dev->link; /* defer PIO handling to sff_qc_issue */ if (!ata_is_dma(qc->tf.protocol)) @@ -2765,7 +2783,7 @@ unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc) /* send cdb by polling if no cdb interrupt */ if (!(qc->dev->flags & ATA_DFLAG_CDB_INTR)) - ata_sff_queue_pio_task(ap, 0); + ata_sff_queue_pio_task(link, 0); break; default: diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 81982594a014..a9fd9709c262 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2284,7 +2284,7 @@ static unsigned int mv_qc_issue_fis(struct ata_queued_cmd *qc) } if (qc->tf.flags & ATA_TFLAG_POLLING) - ata_sff_queue_pio_task(ap, 0); + ata_sff_queue_pio_task(link, 0); return 0; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 7de282d8bedf..45fb2967b66d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -724,6 +724,7 @@ struct ata_port { struct ata_ioports ioaddr; /* ATA cmd/ctl/dma register blocks */ u8 ctl; /* cache of ATA control register */ u8 last_ctl; /* Cache last written value */ + struct ata_link* sff_pio_task_link; /* link currently used */ struct delayed_work sff_pio_task; #ifdef CONFIG_ATA_BMDMA struct ata_bmdma_prd *bmdma_prd; /* BMDMA SG list */ @@ -1595,7 +1596,7 @@ extern void ata_sff_irq_on(struct ata_port *ap); extern void ata_sff_irq_clear(struct ata_port *ap); extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, u8 status, int in_wq); -extern void ata_sff_queue_pio_task(struct ata_port *ap, unsigned long delay); +extern void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay); extern unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc); extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc); extern unsigned int ata_sff_port_intr(struct ata_port *ap, -- cgit v1.2.3-71-gd317 From 006abe887c5e637d059c44310de6c92f36aded3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 12 Sep 2010 19:55:25 -0400 Subject: SUNRPC: Fix a race in rpc_info_open There is a race between rpc_info_open and rpc_release_client() in that nothing stops a process from opening the file after the clnt->cl_kref goes to zero. Fix this by using atomic_inc_unless_zero()... Reported-by: J. Bruce Fields Signed-off-by: Trond Myklebust Cc: stable@kernel.org --- include/linux/sunrpc/clnt.h | 2 +- net/sunrpc/clnt.c | 26 ++++++++++++-------------- net/sunrpc/rpc_pipe.c | 14 ++++++++------ 3 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 569dc722a600..85f38a63f098 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -30,7 +30,7 @@ struct rpc_inode; * The high-level client handle */ struct rpc_clnt { - struct kref cl_kref; /* Number of references */ + atomic_t cl_count; /* Number of references */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 657aac630fc9..3a8f53e7ba07 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -226,7 +226,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru goto out_no_principal; } - kref_init(&clnt->cl_kref); + atomic_set(&clnt->cl_count, 1); err = rpc_setup_pipedir(clnt, program->pipe_dir_name); if (err < 0) @@ -390,14 +390,14 @@ rpc_clone_client(struct rpc_clnt *clnt) if (new->cl_principal == NULL) goto out_no_principal; } - kref_init(&new->cl_kref); + atomic_set(&new->cl_count, 1); err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name); if (err != 0) goto out_no_path; if (new->cl_auth) atomic_inc(&new->cl_auth->au_count); xprt_get(clnt->cl_xprt); - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); rpc_register_client(new); rpciod_up(); return new; @@ -465,10 +465,8 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client); * Free an RPC client */ static void -rpc_free_client(struct kref *kref) +rpc_free_client(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); if (!IS_ERR(clnt->cl_path.dentry)) { @@ -495,12 +493,10 @@ out_free: * Free an RPC client */ static void -rpc_free_auth(struct kref *kref) +rpc_free_auth(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - if (clnt->cl_auth == NULL) { - rpc_free_client(kref); + rpc_free_client(clnt); return; } @@ -509,10 +505,11 @@ rpc_free_auth(struct kref *kref) * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ - kref_init(kref); + atomic_inc(&clnt->cl_count); rpcauth_release(clnt->cl_auth); clnt->cl_auth = NULL; - kref_put(kref, rpc_free_client); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_client(clnt); } /* @@ -525,7 +522,8 @@ rpc_release_client(struct rpc_clnt *clnt) if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); - kref_put(&clnt->cl_kref, rpc_free_auth); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_auth(clnt); } /** @@ -588,7 +586,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) if (clnt != NULL) { rpc_task_release_client(task); task->tk_client = clnt; - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; /* Add to the client's list of all tasks */ diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 41a762f82630..8c8eef2b8f26 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -371,21 +371,23 @@ rpc_show_info(struct seq_file *m, void *v) static int rpc_info_open(struct inode *inode, struct file *file) { - struct rpc_clnt *clnt; + struct rpc_clnt *clnt = NULL; int ret = single_open(file, rpc_show_info, NULL); if (!ret) { struct seq_file *m = file->private_data; - mutex_lock(&inode->i_mutex); - clnt = RPC_I(inode)->private; - if (clnt) { - kref_get(&clnt->cl_kref); + + spin_lock(&file->f_path.dentry->d_lock); + if (!d_unhashed(file->f_path.dentry)) + clnt = RPC_I(inode)->private; + if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) { + spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { + spin_unlock(&file->f_path.dentry->d_lock); single_release(inode, file); ret = -EINVAL; } - mutex_unlock(&inode->i_mutex); } return ret; } -- cgit v1.2.3-71-gd317 From c54fce6eff197d9c57c97afbf6c9722ce434fc8f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Sep 2010 16:51:36 +0200 Subject: workqueue: add documentation Update copyright notice and add Documentation/workqueue.txt. Randy Dunlap, Dave Chinner: misc fixes. Signed-off-by: Tejun Heo Reviewed-By: Florian Mickler Cc: Ingo Molnar Cc: Christoph Lameter Cc: Randy Dunlap Cc: Dave Chinner --- Documentation/workqueue.txt | 380 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/workqueue.h | 4 + kernel/workqueue.c | 27 ++-- 3 files changed, 401 insertions(+), 10 deletions(-) create mode 100644 Documentation/workqueue.txt (limited to 'include/linux') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt new file mode 100644 index 000000000000..e4498a2872c3 --- /dev/null +++ b/Documentation/workqueue.txt @@ -0,0 +1,380 @@ + +Concurrency Managed Workqueue (cmwq) + +September, 2010 Tejun Heo + Florian Mickler + +CONTENTS + +1. Introduction +2. Why cmwq? +3. The Design +4. Application Programming Interface (API) +5. Example Execution Scenarios +6. Guidelines + + +1. Introduction + +There are many cases where an asynchronous process execution context +is needed and the workqueue (wq) API is the most commonly used +mechanism for such cases. + +When such an asynchronous execution context is needed, a work item +describing which function to execute is put on a queue. An +independent thread serves as the asynchronous execution context. The +queue is called workqueue and the thread is called worker. + +While there are work items on the workqueue the worker executes the +functions associated with the work items one after the other. When +there is no work item left on the workqueue the worker becomes idle. +When a new work item gets queued, the worker begins executing again. + + +2. Why cmwq? + +In the original wq implementation, a multi threaded (MT) wq had one +worker thread per CPU and a single threaded (ST) wq had one worker +thread system-wide. A single MT wq needed to keep around the same +number of workers as the number of CPUs. The kernel grew a lot of MT +wq users over the years and with the number of CPU cores continuously +rising, some systems saturated the default 32k PID space just booting +up. + +Although MT wq wasted a lot of resource, the level of concurrency +provided was unsatisfactory. The limitation was common to both ST and +MT wq albeit less severe on MT. Each wq maintained its own separate +worker pool. A MT wq could provide only one execution context per CPU +while a ST wq one for the whole system. Work items had to compete for +those very limited execution contexts leading to various problems +including proneness to deadlocks around the single execution context. + +The tension between the provided level of concurrency and resource +usage also forced its users to make unnecessary tradeoffs like libata +choosing to use ST wq for polling PIOs and accepting an unnecessary +limitation that no two polling PIOs can progress at the same time. As +MT wq don't provide much better concurrency, users which require +higher level of concurrency, like async or fscache, had to implement +their own thread pool. + +Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with +focus on the following goals. + +* Maintain compatibility with the original workqueue API. + +* Use per-CPU unified worker pools shared by all wq to provide + flexible level of concurrency on demand without wasting a lot of + resource. + +* Automatically regulate worker pool and level of concurrency so that + the API users don't need to worry about such details. + + +3. The Design + +In order to ease the asynchronous execution of functions a new +abstraction, the work item, is introduced. + +A work item is a simple struct that holds a pointer to the function +that is to be executed asynchronously. Whenever a driver or subsystem +wants a function to be executed asynchronously it has to set up a work +item pointing to that function and queue that work item on a +workqueue. + +Special purpose threads, called worker threads, execute the functions +off of the queue, one after the other. If no work is queued, the +worker threads become idle. These worker threads are managed in so +called thread-pools. + +The cmwq design differentiates between the user-facing workqueues that +subsystems and drivers queue work items on and the backend mechanism +which manages thread-pool and processes the queued work items. + +The backend is called gcwq. There is one gcwq for each possible CPU +and one gcwq to serve work items queued on unbound workqueues. + +Subsystems and drivers can create and queue work items through special +workqueue API functions as they see fit. They can influence some +aspects of the way the work items are executed by setting flags on the +workqueue they are putting the work item on. These flags include +things like CPU locality, reentrancy, concurrency limits and more. To +get a detailed overview refer to the API description of +alloc_workqueue() below. + +When a work item is queued to a workqueue, the target gcwq is +determined according to the queue parameters and workqueue attributes +and appended on the shared worklist of the gcwq. For example, unless +specifically overridden, a work item of a bound workqueue will be +queued on the worklist of exactly that gcwq that is associated to the +CPU the issuer is running on. + +For any worker pool implementation, managing the concurrency level +(how many execution contexts are active) is an important issue. cmwq +tries to keep the concurrency at a minimal but sufficient level. +Minimal to save resources and sufficient in that the system is used at +its full capacity. + +Each gcwq bound to an actual CPU implements concurrency management by +hooking into the scheduler. The gcwq is notified whenever an active +worker wakes up or sleeps and keeps track of the number of the +currently runnable workers. Generally, work items are not expected to +hog a CPU and consume many cycles. That means maintaining just enough +concurrency to prevent work processing from stalling should be +optimal. As long as there are one or more runnable workers on the +CPU, the gcwq doesn't start execution of a new work, but, when the +last running worker goes to sleep, it immediately schedules a new +worker so that the CPU doesn't sit idle while there are pending work +items. This allows using a minimal number of workers without losing +execution bandwidth. + +Keeping idle workers around doesn't cost other than the memory space +for kthreads, so cmwq holds onto idle ones for a while before killing +them. + +For an unbound wq, the above concurrency management doesn't apply and +the gcwq for the pseudo unbound CPU tries to start executing all work +items as soon as possible. The responsibility of regulating +concurrency level is on the users. There is also a flag to mark a +bound wq to ignore the concurrency management. Please refer to the +API section for details. + +Forward progress guarantee relies on that workers can be created when +more execution contexts are necessary, which in turn is guaranteed +through the use of rescue workers. All work items which might be used +on code paths that handle memory reclaim are required to be queued on +wq's that have a rescue-worker reserved for execution under memory +pressure. Else it is possible that the thread-pool deadlocks waiting +for execution contexts to free up. + + +4. Application Programming Interface (API) + +alloc_workqueue() allocates a wq. The original create_*workqueue() +functions are deprecated and scheduled for removal. alloc_workqueue() +takes three arguments - @name, @flags and @max_active. @name is the +name of the wq and also used as the name of the rescuer thread if +there is one. + +A wq no longer manages execution resources but serves as a domain for +forward progress guarantee, flush and work item attributes. @flags +and @max_active control how work items are assigned execution +resources, scheduled and executed. + +@flags: + + WQ_NON_REENTRANT + + By default, a wq guarantees non-reentrance only on the same + CPU. A work item may not be executed concurrently on the same + CPU by multiple workers but is allowed to be executed + concurrently on multiple CPUs. This flag makes sure + non-reentrance is enforced across all CPUs. Work items queued + to a non-reentrant wq are guaranteed to be executed by at most + one worker system-wide at any given time. + + WQ_UNBOUND + + Work items queued to an unbound wq are served by a special + gcwq which hosts workers which are not bound to any specific + CPU. This makes the wq behave as a simple execution context + provider without concurrency management. The unbound gcwq + tries to start execution of work items as soon as possible. + Unbound wq sacrifices locality but is useful for the following + cases. + + * Wide fluctuation in the concurrency level requirement is + expected and using bound wq may end up creating large number + of mostly unused workers across different CPUs as the issuer + hops through different CPUs. + + * Long running CPU intensive workloads which can be better + managed by the system scheduler. + + WQ_FREEZEABLE + + A freezeable wq participates in the freeze phase of the system + suspend operations. Work items on the wq are drained and no + new work item starts execution until thawed. + + WQ_RESCUER + + All wq which might be used in the memory reclaim paths _MUST_ + have this flag set. This reserves one worker exclusively for + the execution of this wq under memory pressure. + + WQ_HIGHPRI + + Work items of a highpri wq are queued at the head of the + worklist of the target gcwq and start execution regardless of + the current concurrency level. In other words, highpri work + items will always start execution as soon as execution + resource is available. + + Ordering among highpri work items is preserved - a highpri + work item queued after another highpri work item will start + execution after the earlier highpri work item starts. + + Although highpri work items are not held back by other + runnable work items, they still contribute to the concurrency + level. Highpri work items in runnable state will prevent + non-highpri work items from starting execution. + + This flag is meaningless for unbound wq. + + WQ_CPU_INTENSIVE + + Work items of a CPU intensive wq do not contribute to the + concurrency level. In other words, runnable CPU intensive + work items will not prevent other work items from starting + execution. This is useful for bound work items which are + expected to hog CPU cycles so that their execution is + regulated by the system scheduler. + + Although CPU intensive work items don't contribute to the + concurrency level, start of their executions is still + regulated by the concurrency management and runnable + non-CPU-intensive work items can delay execution of CPU + intensive work items. + + This flag is meaningless for unbound wq. + + WQ_HIGHPRI | WQ_CPU_INTENSIVE + + This combination makes the wq avoid interaction with + concurrency management completely and behave as a simple + per-CPU execution context provider. Work items queued on a + highpri CPU-intensive wq start execution as soon as resources + are available and don't affect execution of other work items. + +@max_active: + +@max_active determines the maximum number of execution contexts per +CPU which can be assigned to the work items of a wq. For example, +with @max_active of 16, at most 16 work items of the wq can be +executing at the same time per CPU. + +Currently, for a bound wq, the maximum limit for @max_active is 512 +and the default value used when 0 is specified is 256. For an unbound +wq, the limit is higher of 512 and 4 * num_possible_cpus(). These +values are chosen sufficiently high such that they are not the +limiting factor while providing protection in runaway cases. + +The number of active work items of a wq is usually regulated by the +users of the wq, more specifically, by how many work items the users +may queue at the same time. Unless there is a specific need for +throttling the number of active work items, specifying '0' is +recommended. + +Some users depend on the strict execution ordering of ST wq. The +combination of @max_active of 1 and WQ_UNBOUND is used to achieve this +behavior. Work items on such wq are always queued to the unbound gcwq +and only one work item can be active at any given time thus achieving +the same ordering property as ST wq. + + +5. Example Execution Scenarios + +The following example execution scenarios try to illustrate how cmwq +behave under different configurations. + + Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU. + w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms + again before finishing. w1 and w2 burn CPU for 5ms then sleep for + 10ms. + +Ignoring all other tasks, works and processing overhead, and assuming +simple FIFO scheduling, the following is one highly simplified version +of possible sequences of events with the original wq. + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 starts and burns CPU + 25 w1 sleeps + 35 w1 wakes up and finishes + 35 w2 starts and burns CPU + 40 w2 sleeps + 50 w2 wakes up and finishes + +And with cmwq with @max_active >= 3, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 10 w2 starts and burns CPU + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + +If @max_active == 2, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 20 w2 starts and burns CPU + 25 w2 sleeps + 35 w2 wakes up and finishes + +Now, let's assume w1 and w2 are queued to a different wq q1 which has +WQ_HIGHPRI set, + + TIME IN MSECS EVENT + 0 w1 and w2 start and burn CPU + 5 w1 sleeps + 10 w2 sleeps + 10 w0 starts and burns CPU + 15 w0 sleeps + 15 w1 wakes up and finishes + 20 w2 wakes up and finishes + 25 w0 wakes up and burns CPU + 30 w0 finishes + +If q1 has WQ_CPU_INTENSIVE set, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 and w2 start and burn CPU + 10 w1 sleeps + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + + +6. Guidelines + +* Do not forget to use WQ_RESCUER if a wq may process work items which + are used during memory reclaim. Each wq with WQ_RESCUER set has one + rescuer thread reserved for it. If there is dependency among + multiple work items used during memory reclaim, they should be + queued to separate wq each with WQ_RESCUER. + +* Unless strict ordering is required, there is no need to use ST wq. + +* Unless there is a specific need, using 0 for @max_active is + recommended. In most use cases, concurrency level usually stays + well under the default limit. + +* A wq serves as a domain for forward progress guarantee (WQ_RESCUER), + flush and work item attributes. Work items which are not involved + in memory reclaim and don't need to be flushed as a part of a group + of work items, and don't require any special attribute, can use one + of the system wq. There is no difference in execution + characteristics between using a dedicated wq and a system wq. + +* Unless work items are expected to consume a huge amount of CPU + cycles, using a bound wq is usually beneficial due to the increased + level of locality in wq operations and work item execution. diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f11100f96482..25e02c941bac 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -235,6 +235,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define work_clear_pending(work) \ clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) +/* + * Workqueue flags and constants. For details, please refer to + * Documentation/workqueue.txt. + */ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 727f24e563ae..f77afd939229 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1,19 +1,26 @@ /* - * linux/kernel/workqueue.c + * kernel/workqueue.c - generic async execution with shared worker pool * - * Generic mechanism for defining kernel helper threads for running - * arbitrary tasks in process context. + * Copyright (C) 2002 Ingo Molnar * - * Started by Ingo Molnar, Copyright (C) 2002 + * Derived from the taskqueue/keventd code by: + * David Woodhouse + * Andrew Morton + * Kai Petzke + * Theodore Ts'o * - * Derived from the taskqueue/keventd code by: + * Made to use alloc_percpu by Christoph Lameter. * - * David Woodhouse - * Andrew Morton - * Kai Petzke - * Theodore Ts'o + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo * - * Made to use alloc_percpu by Christoph Lameter. + * This is the generic async execution mechanism. Work items as are + * executed in process context. The worker pool is shared and + * automatically managed. There is one worker pool for each CPU and + * one extra for works which are better served by workers which are + * not bound to any specific CPU. + * + * Please read Documentation/workqueue.txt for details. */ #include -- cgit v1.2.3-71-gd317 From c41d68a513c71e35a14f66d71782d27a79a81ea6 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 7 Sep 2010 16:16:18 -0700 Subject: compat: Make compat_alloc_user_space() incorporate the access_ok() compat_alloc_user_space() expects the caller to independently call access_ok() to verify the returned area. A missing call could introduce problems on some architectures. This patch incorporates the access_ok() check into compat_alloc_user_space() and also adds a sanity check on the length. The existing compat_alloc_user_space() implementations are renamed arch_compat_alloc_user_space() and are used as part of the implementation of the new global function. This patch assumes NULL will cause __get_user()/__put_user() to either fail or access userspace on all architectures. This should be followed by checking the return value of compat_access_user_space() for NULL in the callers, at which time the access_ok() in the callers can also be removed. Reported-by: Ben Hawkes Signed-off-by: H. Peter Anvin Acked-by: Benjamin Herrenschmidt Acked-by: Chris Metcalf Acked-by: David S. Miller Acked-by: Ingo Molnar Acked-by: Thomas Gleixner Acked-by: Tony Luck Cc: Andrew Morton Cc: Arnd Bergmann Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Heiko Carstens Cc: Helge Deller Cc: James Bottomley Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: Paul Mackerras Cc: Ralf Baechle Cc: --- arch/ia64/include/asm/compat.h | 2 +- arch/mips/include/asm/compat.h | 2 +- arch/parisc/include/asm/compat.h | 2 +- arch/powerpc/include/asm/compat.h | 2 +- arch/s390/include/asm/compat.h | 2 +- arch/sparc/include/asm/compat.h | 2 +- arch/tile/include/asm/compat.h | 2 +- arch/x86/include/asm/compat.h | 2 +- include/linux/compat.h | 3 +++ kernel/compat.c | 21 +++++++++++++++++++++ 10 files changed, 32 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h index f90edc85b509..9301a2821615 100644 --- a/arch/ia64/include/asm/compat.h +++ b/arch/ia64/include/asm/compat.h @@ -199,7 +199,7 @@ ptr_to_compat(void __user *uptr) } static __inline__ void __user * -compat_alloc_user_space (long len) +arch_compat_alloc_user_space (long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *) (((regs->r12 & 0xffffffff) & -16) - len); diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 613f6912dfc1..dbc51065df5b 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -145,7 +145,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = (struct pt_regs *) ((unsigned long) current_thread_info() + THREAD_SIZE - 32) - 1; diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 02b77baa5da6..efa0b60c63fe 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -147,7 +147,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static __inline__ void __user *compat_alloc_user_space(long len) +static __inline__ void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = ¤t->thread.regs; return (void __user *)regs->gr[30]; diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 396d21a80058..a11d4eac4f97 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -134,7 +134,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current->thread.regs; unsigned long usp = regs->gpr[1]; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 104f2007f097..a875c2f542e1 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -181,7 +181,7 @@ static inline int is_compat_task(void) #endif -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 5016f76ea98a..6f57325bb883 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -167,7 +167,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current_thread_info()->kregs; unsigned long usp = regs->u_regs[UREG_I6]; diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h index 5a34da6cdd79..345d81ce44bb 100644 --- a/arch/tile/include/asm/compat.h +++ b/arch/tile/include/asm/compat.h @@ -195,7 +195,7 @@ static inline unsigned long ptr_to_compat_reg(void __user *uptr) return (long)(int)(long __force)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 306160e58b48..1d9cd27c2920 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -205,7 +205,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/include/linux/compat.h b/include/linux/compat.h index 9ddc8780e8db..5778b559d59c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -360,5 +360,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer); + +extern void __user *compat_alloc_user_space(unsigned long len); + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ diff --git a/kernel/compat.c b/kernel/compat.c index e167efce8423..c9e2ec0b34a8 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -1126,3 +1126,24 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info) return 0; } + +/* + * Allocate user-space memory for the duration of a single system call, + * in order to marshall parameters inside a compat thunk. + */ +void __user *compat_alloc_user_space(unsigned long len) +{ + void __user *ptr; + + /* If len would occupy more than half of the entire compat space... */ + if (unlikely(len > (((compat_uptr_t)~0) >> 1))) + return NULL; + + ptr = arch_compat_alloc_user_space(len); + + if (unlikely(!access_ok(VERIFY_WRITE, ptr, len))) + return NULL; + + return ptr; +} +EXPORT_SYMBOL_GPL(compat_alloc_user_space); -- cgit v1.2.3-71-gd317 From f0f9deae9e7c421fa0c1c627beb8e174325e1ba7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 17 Sep 2010 16:55:03 -0700 Subject: netpoll: Disable IRQ around RCU dereference in netpoll_rx We cannot use rcu_dereference_bh safely in netpoll_rx as we may be called with IRQs disabled. We could however simply disable IRQs as that too causes BH to be disabled and is safe in either case. Thanks to John Linville for discovering this bug and providing a patch. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netpoll.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 791d5109f34c..50d8009be86c 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,20 +63,20 @@ static inline bool netpoll_rx(struct sk_buff *skb) unsigned long flags; bool ret = false; - rcu_read_lock_bh(); + local_irq_save(flags); npinfo = rcu_dereference_bh(skb->dev->npinfo); if (!npinfo || (list_empty(&npinfo->rx_np) && !npinfo->rx_flags)) goto out; - spin_lock_irqsave(&npinfo->rx_lock, flags); + spin_lock(&npinfo->rx_lock); /* check rx_flags again with the lock held */ if (npinfo->rx_flags && __netpoll_rx(skb)) ret = true; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); + spin_unlock(&npinfo->rx_lock); out: - rcu_read_unlock_bh(); + local_irq_restore(flags); return ret; } -- cgit v1.2.3-71-gd317 From 8b15575cae7a93a784c3005c42b069edd9ba64dd Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 21 Sep 2010 14:35:37 -0700 Subject: fs: {lock,unlock}_flocks() stubs to prepare for BKL removal The lock structs are currently protected by the BKL, but are accessed by code in fs/locks.c and misc file system and DLM code. These stubs will allow all users to switch to the new interface before the implementation is changed to a spinlock. Acked-by: Arnd Bergmann Signed-off-by: Sage Weil Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 76041b614758..63d069bd80b7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1093,6 +1093,10 @@ struct file_lock { #include +/* temporary stubs for BKL removal */ +#define lock_flocks() lock_kernel() +#define unlock_flocks() unlock_kernel() + extern void send_sigio(struct fown_struct *fown, int fd, int band); #ifdef CONFIG_FILE_LOCKING -- cgit v1.2.3-71-gd317 From 56b49f4b8f6728b91d10c556c116175051b77b60 Mon Sep 17 00:00:00 2001 From: Ollie Wild Date: Wed, 22 Sep 2010 05:54:54 +0000 Subject: net: Move "struct net" declaration inside the __KERNEL__ macro guard This patch reduces namespace pollution by moving the "struct net" declaration out of the userspace-facing portion of linux/netlink.h. It has no impact on the kernel. (This came up because we have several C++ applications which use "net" as a namespace name.) Signed-off-by: Ollie Wild Signed-off-by: David S. Miller --- include/linux/netlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 59d066936ab9..123566912d73 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -27,8 +27,6 @@ #define MAX_LINKS 32 -struct net; - struct sockaddr_nl { sa_family_t nl_family; /* AF_NETLINK */ unsigned short nl_pad; /* zero */ @@ -151,6 +149,8 @@ struct nlattr { #include #include +struct net; + static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) { return (struct nlmsghdr *)skb->data; -- cgit v1.2.3-71-gd317 From d3f3cf859db17cc5f8156c5bfcd032413e44483b Mon Sep 17 00:00:00 2001 From: Mathieu Lacage Date: Sat, 14 Aug 2010 15:02:44 +0200 Subject: missing inline keyword for static function in linux/dmaengine.h Add a missing inline keyword for static function in linux/dmaengine.h to avoid duplicate symbol definitions. Signed-off-by: Mathieu Lacage Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c61d4ca27bcc..e2106495cc11 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -548,7 +548,7 @@ static inline bool dma_dev_has_pq_continue(struct dma_device *dma) return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE; } -static unsigned short dma_dev_to_maxpq(struct dma_device *dma) +static inline unsigned short dma_dev_to_maxpq(struct dma_device *dma) { return dma->max_pq & ~DMA_HAS_PQ_CONTINUE; } -- cgit v1.2.3-71-gd317 From 710224fa2750cf449c02dd115548acebfdd2c86a Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 22 Sep 2010 13:04:55 -0700 Subject: arm: fix "arm: fix pci_set_consistent_dma_mask for dmabounce devices" This fixes the regression caused by the commit 6fee48cd330c68 ("dma-mapping: arm: use generic pci_set_dma_mask and pci_set_consistent_dma_mask"). ARM needs to clip the dma coherent mask for dmabounce devices. This restores the old trick. Note that strictly speaking, the DMA API doesn't allow architectures to do such but I'm not sure it's worth adding the new API to set the dma mask that allows architectures to clip it. Reported-by: Krzysztof Halasa Signed-off-by: FUJITA Tomonori Acked-by: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/common/it8152.c | 8 ++++++++ arch/arm/mach-ixp4xx/common-pci.c | 8 ++++++++ arch/arm/mach-ixp4xx/include/mach/hardware.h | 2 ++ arch/arm/mach-pxa/include/mach/hardware.h | 2 +- arch/arm/mach-pxa/include/mach/io.h | 2 ++ include/linux/dma-mapping.h | 4 ++++ 6 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 7974baacafce..1bec96e85196 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -271,6 +271,14 @@ int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) ((dma_addr + size - PHYS_OFFSET) >= SZ_64M); } +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (mask >= PHYS_OFFSET + SZ_64M - 1) + return 0; + + return -EIO; +} + int __init it8152_pci_setup(int nr, struct pci_sys_data *sys) { it8152_io.start = IT8152_IO_BASE + 0x12000; diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index 61cd4d64b985..24498a932ba6 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -503,6 +503,14 @@ struct pci_bus * __devinit ixp4xx_scan_bus(int nr, struct pci_sys_data *sys) return pci_scan_bus(sys->busnr, &ixp4xx_ops, sys); } +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (mask >= SZ_64M - 1) + return 0; + + return -EIO; +} + EXPORT_SYMBOL(ixp4xx_pci_read); EXPORT_SYMBOL(ixp4xx_pci_write); diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h index f91ca6d4fbe8..8138371c406e 100644 --- a/arch/arm/mach-ixp4xx/include/mach/hardware.h +++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h @@ -26,6 +26,8 @@ #define PCIBIOS_MAX_MEM 0x4BFFFFFF #endif +#define ARCH_HAS_DMA_SET_COHERENT_MASK + #define pcibios_assign_all_busses() 1 /* Register locations and bits */ diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h index 7f64d24cd564..428cc7bda9a4 100644 --- a/arch/arm/mach-pxa/include/mach/hardware.h +++ b/arch/arm/mach-pxa/include/mach/hardware.h @@ -309,7 +309,7 @@ extern unsigned long get_clock_tick_rate(void); #define PCIBIOS_MIN_IO 0 #define PCIBIOS_MIN_MEM 0 #define pcibios_assign_all_busses() 1 +#define ARCH_HAS_DMA_SET_COHERENT_MASK #endif - #endif /* _ASM_ARCH_HARDWARE_H */ diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h index 262691fb97d8..fdca3be47d9b 100644 --- a/arch/arm/mach-pxa/include/mach/io.h +++ b/arch/arm/mach-pxa/include/mach/io.h @@ -6,6 +6,8 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H +#include + #define IO_SPACE_LIMIT 0xffffffff /* diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index ce29b8151198..ba8319ae5fcc 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -102,6 +102,9 @@ static inline u64 dma_get_mask(struct device *dev) return DMA_BIT_MASK(32); } +#ifdef ARCH_HAS_DMA_SET_COHERENT_MASK +int dma_set_coherent_mask(struct device *dev, u64 mask); +#else static inline int dma_set_coherent_mask(struct device *dev, u64 mask) { if (!dma_supported(dev, mask)) @@ -109,6 +112,7 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask) dev->coherent_dma_mask = mask; return 0; } +#endif extern u64 dma_get_required_mask(struct device *dev); -- cgit v1.2.3-71-gd317 From 4c894f47bb49284008073d351c0ddaac8860864e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 23 Sep 2010 15:15:19 +0200 Subject: x86/amd-iommu: Work around S3 BIOS bug This patch adds a workaround for an IOMMU BIOS problem to the AMD IOMMU driver. The result of the bug is that the IOMMU does not execute commands anymore when the system comes out of the S3 state resulting in system failure. The bug in the BIOS is that is does not restore certain hardware specific registers correctly. This workaround reads out the contents of these registers at boot time and restores them on resume from S3. The workaround is limited to the specific IOMMU chipset where this problem occurs. Cc: stable@kernel.org Signed-off-by: Joerg Roedel --- arch/x86/include/asm/amd_iommu_proto.h | 6 ++++++ arch/x86/include/asm/amd_iommu_types.h | 9 +++++++++ arch/x86/kernel/amd_iommu_init.c | 18 ++++++++++++++++++ include/linux/pci_ids.h | 3 +++ 4 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h index d2544f1d705d..cb030374b90a 100644 --- a/arch/x86/include/asm/amd_iommu_proto.h +++ b/arch/x86/include/asm/amd_iommu_proto.h @@ -38,4 +38,10 @@ static inline void amd_iommu_stats_init(void) { } #endif /* !CONFIG_AMD_IOMMU_STATS */ +static inline bool is_rd890_iommu(struct pci_dev *pdev) +{ + return (pdev->vendor == PCI_VENDOR_ID_ATI) && + (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); +} + #endif /* _ASM_X86_AMD_IOMMU_PROTO_H */ diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index ef2d5cd7d7e7..08616180deaf 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -414,6 +414,15 @@ struct amd_iommu { /* default dma_ops domain for that IOMMU */ struct dma_ops_domain *default_dom; + + /* + * This array is required to work around a potential BIOS bug. + * The BIOS may miss to restore parts of the PCI configuration + * space when the system resumes from S3. The result is that the + * IOMMU does not execute commands anymore which leads to system + * failure. + */ + u32 cache_cfg[4]; }; /* diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 85e9817ead43..5a170cbbbed8 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -632,6 +632,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu) iommu->last_device = calc_devid(MMIO_GET_BUS(range), MMIO_GET_LD(range)); iommu->evt_msi_num = MMIO_MSI_NUM(misc); + + if (is_rd890_iommu(iommu->dev)) { + pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]); + pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]); + pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]); + pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]); + } } /* @@ -1120,6 +1127,16 @@ static void iommu_init_flags(struct amd_iommu *iommu) iommu_feature_enable(iommu, CONTROL_COHERENT_EN); } +static void iommu_apply_quirks(struct amd_iommu *iommu) +{ + if (is_rd890_iommu(iommu->dev)) { + pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]); + pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]); + pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]); + pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]); + } +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1130,6 +1147,7 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_apply_quirks(iommu); iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 10d33309e9a6..570fddeb0388 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -393,6 +393,9 @@ #define PCI_DEVICE_ID_VLSI_82C147 0x0105 #define PCI_DEVICE_ID_VLSI_VAS96011 0x0702 +/* AMD RD890 Chipset */ +#define PCI_DEVICE_ID_RD890_IOMMU 0x5a23 + #define PCI_VENDOR_ID_ADL 0x1005 #define PCI_DEVICE_ID_ADL_2301 0x2301 -- cgit v1.2.3-71-gd317 From b3a084b9b684622b149e8dcf03855bf0d5fb588b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Sep 2010 08:38:44 +0200 Subject: rcu: rcu_read_lock_bh_held(): disabling irqs also disables bh rcu_dereference_bh() doesnt know yet about hard irq being disabled, so lockdep can trigger in netpoll_rx() after commit f0f9deae9e7c4 (netpoll: Disable IRQ around RCU dereference in netpoll_rx) Reported-by: Miles Lane Signed-off-by: Eric Dumazet Tested-by: Miles Lane Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9fbc54a2585d..83af1f8d8b74 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -454,7 +454,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) \ - rcu_dereference_check(p, rcu_read_lock_bh_held()) + rcu_dereference_check(p, rcu_read_lock_bh_held() || irqs_disabled()) /** * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched -- cgit v1.2.3-71-gd317 From 01db403cf99f739f86903314a489fb420e0e254f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 27 Sep 2010 20:24:54 -0700 Subject: tcp: Fix >4GB writes on 64-bit. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes kernel bugzilla #16603 tcp_sendmsg() truncates iov_len to an 'int' which a 4GB write to write zero bytes, for example. There is also the problem higher up of how verify_iovec() works. It wants to prevent the total length from looking like an error return value. However it does this using 'int', but syscalls return 'long' (and thus signed 64-bit on 64-bit machines). So it could trigger false-positives on 64-bit as written. So fix it to use 'long'. Reported-by: Olaf Bonorden Reported-by: Daniel Büse Reported-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/socket.h | 2 +- net/core/iovec.c | 5 +++-- net/ipv4/tcp.c | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index a2fada9becb6..a8f56e1ec760 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -322,7 +322,7 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata, int offset, unsigned int len, __wsum *csump); -extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode); +extern long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode); extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len); extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, int offset, int len); diff --git a/net/core/iovec.c b/net/core/iovec.c index 1cd98df412df..e6b133b77ccb 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,9 +35,10 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, err, ct; + int size, ct; + long err; if (m->msg_namelen) { if (mode == VERIFY_READ) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 95d75d443927..f115ea68a4ef 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -943,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = sk->sk_route_caps & NETIF_F_SG; while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; -- cgit v1.2.3-71-gd317 From 6110a1f43c27b516e16d5ce8860fca50748c2a87 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 30 Sep 2010 21:19:07 -0400 Subject: intel_idle: Voluntary leave_mm before entering deeper Avoid TLB flush IPIs for the cores in deeper c-states by voluntary leave_mm() before entering into that state. CPUs tend to flush TLB in those c-states anyways. acpi_idle does this with C3-type states, but it was not caried over when intel_idle was introduced. intel_idle can apply it to C-states in addition to those that ACPI might export as C3... Signed-off-by: Suresh Siddha Signed-off-by: Len Brown --- drivers/idle/intel_idle.c | 18 ++++++++++++++---- include/linux/cpuidle.h | 1 + 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 96bf38097996..0906fc5b69b9 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -108,7 +108,7 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = { .name = "NHM-C3", .desc = "MWAIT 0x10", .driver_data = (void *) 0x10, - .flags = CPUIDLE_FLAG_TIME_VALID, + .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 20, .power_usage = 500, .target_residency = 80, @@ -117,7 +117,7 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = { .name = "NHM-C6", .desc = "MWAIT 0x20", .driver_data = (void *) 0x20, - .flags = CPUIDLE_FLAG_TIME_VALID, + .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 200, .power_usage = 350, .target_residency = 800, @@ -149,7 +149,7 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = { .name = "ATM-C4", .desc = "MWAIT 0x30", .driver_data = (void *) 0x30, - .flags = CPUIDLE_FLAG_TIME_VALID, + .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 100, .power_usage = 250, .target_residency = 400, @@ -159,7 +159,7 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = { .name = "ATM-C6", .desc = "MWAIT 0x40", .driver_data = (void *) 0x40, - .flags = CPUIDLE_FLAG_TIME_VALID, + .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 200, .power_usage = 150, .target_residency = 800, @@ -185,6 +185,16 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state) local_irq_disable(); + /* + * If the state flag indicates that the TLB will be flushed or if this + * is the deepest c-state supported, do a voluntary leave mm to avoid + * costly and mostly unnecessary wakeups for flushing the user TLB's + * associated with the active mm. + */ + if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED || + (&dev->states[dev->state_count - 1] == state)) + leave_mm(cpu); + if (!(lapic_timer_reliable_states & (1 << (cstate)))) clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 36ca9721a0c2..1be416bbbb82 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -53,6 +53,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_BALANCED (0x40) /* medium latency, moderate savings */ #define CPUIDLE_FLAG_DEEP (0x80) /* high latency, large savings */ #define CPUIDLE_FLAG_IGNORE (0x100) /* ignore during this idle period */ +#define CPUIDLE_FLAG_TLB_FLUSHED (0x200) /* tlb will be flushed */ #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) -- cgit v1.2.3-71-gd317 From 5336377d6225959624146629ce3fc88ee8ecda3d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 5 Oct 2010 11:29:27 -0700 Subject: modules: Fix module_bug_list list corruption race With all the recent module loading cleanups, we've minimized the code that sits under module_mutex, fixing various deadlocks and making it possible to do most of the module loading in parallel. However, that whole conversion totally missed the rather obscure code that adds a new module to the list for BUG() handling. That code was doubly obscure because (a) the code itself lives in lib/bugs.c (for dubious reasons) and (b) it gets called from the architecture-specific "module_finalize()" rather than from generic code. Calling it from arch-specific code makes no sense what-so-ever to begin with, and is now actively wrong since that code isn't protected by the module loading lock any more. So this commit moves the "module_bug_{finalize,cleanup}()" calls away from the arch-specific code, and into the generic code - and in the process protects it with the module_mutex so that the list operations are now safe. Future fixups: - move the module list handling code into kernel/module.c where it belongs. - get rid of 'module_bug_list' and just use the regular list of modules (called 'modules' - imagine that) that we already create and maintain for other reasons. Reported-and-tested-by: Thomas Gleixner Cc: Rusty Russell Cc: Adrian Bunk Cc: Andrew Morton Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- arch/avr32/kernel/module.c | 3 +-- arch/h8300/kernel/module.c | 3 +-- arch/mn10300/kernel/module.c | 3 +-- arch/parisc/kernel/module.c | 3 +-- arch/powerpc/kernel/module.c | 5 ----- arch/s390/kernel/module.c | 3 +-- arch/sh/kernel/module.c | 2 -- arch/x86/kernel/module.c | 3 +-- include/linux/module.h | 5 ++--- kernel/module.c | 4 ++++ lib/bug.c | 6 ++---- 11 files changed, 14 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 98f94d041d9c..a727f54d64d6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -314,10 +314,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, vfree(module->arch.syminfo); module->arch.syminfo = NULL; - return module_bug_finalize(hdr, sechdrs, module); + return 0; } void module_arch_cleanup(struct module *module) { - module_bug_cleanup(module); } diff --git a/arch/h8300/kernel/module.c b/arch/h8300/kernel/module.c index 0865e291c20d..db4953dc4e1b 100644 --- a/arch/h8300/kernel/module.c +++ b/arch/h8300/kernel/module.c @@ -112,10 +112,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/mn10300/kernel/module.c b/arch/mn10300/kernel/module.c index 6aea7fd76993..196a111e2e29 100644 --- a/arch/mn10300/kernel/module.c +++ b/arch/mn10300/kernel/module.c @@ -206,7 +206,7 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - return module_bug_finalize(hdr, sechdrs, me); + return 0; } /* @@ -214,5 +214,4 @@ int module_finalize(const Elf_Ehdr *hdr, */ void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 159a2b81e90c..6e81bb596e5b 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -941,11 +941,10 @@ int module_finalize(const Elf_Ehdr *hdr, nsyms = newptr - (Elf_Sym *)symhdr->sh_addr; DEBUGP("NEW num_symtab %lu\n", nsyms); symhdr->sh_size = nsyms * sizeof(Elf_Sym); - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { deregister_unwind_table(mod); - module_bug_cleanup(mod); } diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 477c663e0140..4ef93ae2235f 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -65,10 +65,6 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sect; int err; - err = module_bug_finalize(hdr, sechdrs, me); - if (err) - return err; - /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); if (sect != NULL) @@ -101,5 +97,4 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 22cfd634c355..f7167ee4604c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -407,10 +407,9 @@ int module_finalize(const Elf_Ehdr *hdr, { vfree(me->arch.syminfo); me->arch.syminfo = NULL; - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c index 43adddfe4c04..ae0be697a89e 100644 --- a/arch/sh/kernel/module.c +++ b/arch/sh/kernel/module.c @@ -149,13 +149,11 @@ int module_finalize(const Elf_Ehdr *hdr, int ret = 0; ret |= module_dwarf_finalize(hdr, sechdrs, me); - ret |= module_bug_finalize(hdr, sechdrs, me); return ret; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); module_dwarf_cleanup(mod); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e0bc186d7501..1c355c550960 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -239,11 +239,10 @@ int module_finalize(const Elf_Ehdr *hdr, apply_paravirt(pseg, pseg + para->sh_size); } - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); - module_bug_cleanup(mod); } diff --git a/include/linux/module.h b/include/linux/module.h index 8a6b9fdc7ffa..aace066bad8f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -686,17 +686,16 @@ extern int module_sysfs_initialized; #ifdef CONFIG_GENERIC_BUG -int module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, +void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); void module_bug_cleanup(struct module *); #else /* !CONFIG_GENERIC_BUG */ -static inline int module_bug_finalize(const Elf_Ehdr *hdr, +static inline void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { - return 0; } static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ diff --git a/kernel/module.c b/kernel/module.c index d0b5f8db11b4..ccd641991842 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1537,6 +1537,7 @@ static int __unlink_module(void *_mod) { struct module *mod = _mod; list_del(&mod->list); + module_bug_cleanup(mod); return 0; } @@ -2625,6 +2626,7 @@ static struct module *load_module(void __user *umod, if (err < 0) goto ddebug; + module_bug_finalize(info.hdr, info.sechdrs, mod); list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); @@ -2650,6 +2652,8 @@ static struct module *load_module(void __user *umod, mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + module_bug_cleanup(mod); + ddebug: if (!mod->taints) dynamic_debug_remove(info.debug); diff --git a/lib/bug.c b/lib/bug.c index 7cdfad88128f..19552096d16b 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -72,8 +72,8 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr) return NULL; } -int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, - struct module *mod) +void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, + struct module *mod) { char *secstrings; unsigned int i; @@ -97,8 +97,6 @@ int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, * could potentially lead to deadlock and thus be counter-productive. */ list_add(&mod->bug_list, &module_bug_list); - - return 0; } void module_bug_cleanup(struct module *mod) -- cgit v1.2.3-71-gd317 From 231d0aefd88e94129cb8fb84794f9bb788c6366e Mon Sep 17 00:00:00 2001 From: Evgeny Kuznetsov Date: Tue, 5 Oct 2010 12:47:57 +0400 Subject: wait: using uninitialized member of wait queue The "flags" member of "struct wait_queue_t" is used in several places in the kernel code without beeing initialized by init_wait(). "flags" is used in bitwise operations. If "flags" not initialized then unexpected behaviour may take place. Incorrect flags might used later in code. Added initialization of "wait_queue_t.flags" with zero value into "init_wait". Signed-off-by: Evgeny Kuznetsov [ The bit we care about does end up being initialized by both prepare_to_wait() and add_to_wait_queue(), so this doesn't seem to cause actual bugs, but is definitely the right thing to do -Linus ] Signed-off-by: Linus Torvalds --- include/linux/wait.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 0836ccc57121..3efc9f3f43a0 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -614,6 +614,7 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); (wait)->private = current; \ (wait)->func = autoremove_wake_function; \ INIT_LIST_HEAD(&(wait)->task_list); \ + (wait)->flags = 0; \ } while (0) /** -- cgit v1.2.3-71-gd317 From 430c62fb2948d964cf8dc7f3e2f69623c04ef62f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 7 Oct 2010 09:35:16 +0200 Subject: elevator: fix oops on early call to elevator_change() 2.6.36 introduces an API for drivers to switch the IO scheduler instead of manually calling the elevator exit and init functions. This API was added since q->elevator must be cleared in between those two calls. And since we already have this functionality directly from use by the sysfs interface to switch schedulers online, it was prudent to reuse it internally too. But this API needs the queue to be in a fully initialized state before it is called, or it will attempt to unregister elevator kobjects before they have been added. This results in an oops like this: BUG: unable to handle kernel NULL pointer dereference at 0000000000000051 IP: [] sysfs_create_dir+0x2e/0xc0 PGD 47ddfc067 PUD 47c6a1067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.1/irq CPU 2 Modules linked in: t(+) loop hid_apple usbhid ahci ehci_hcd uhci_hcd libahci usbcore nls_base igb Pid: 7319, comm: modprobe Not tainted 2.6.36-rc6+ #132 QSSC-S4R/QSSC-S4R RIP: 0010:[] [] sysfs_create_dir+0x2e/0xc0 RSP: 0018:ffff88027da25d08 EFLAGS: 00010246 RAX: ffff88047c68c528 RBX: 00000000fffffffe RCX: 0000000000000000 RDX: 000000000000002f RSI: 000000000000002f RDI: ffff88047e196c88 RBP: ffff88027da25d38 R08: 0000000000000000 R09: d84156c5635688c0 R10: d84156c5635688c0 R11: 0000000000000000 R12: ffff88047e196c88 R13: 0000000000000000 R14: 0000000000000000 R15: ffff88047c68c528 FS: 00007fcb0b26f6e0(0000) GS:ffff880287400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000051 CR3: 000000047e76e000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process modprobe (pid: 7319, threadinfo ffff88027da24000, task ffff88027d377090) Stack: ffff88027da25d58 ffff88047c68c528 00000000fffffffe ffff88047e196c88 <0> ffff88047c68c528 ffff88047e05bd90 ffff88027da25d78 ffffffff8123fb77 <0> ffff88047e05bd90 0000000000000000 ffff88047e196c88 ffff88047c68c528 Call Trace: [] kobject_add_internal+0xe7/0x1f0 [] kobject_add_varg+0x38/0x60 [] kobject_add+0x69/0x90 [] ? sysfs_remove_dir+0x20/0xa0 [] ? sub_preempt_count+0x9d/0xe0 [] ? _raw_spin_unlock+0x30/0x50 [] ? sysfs_remove_dir+0x20/0xa0 [] ? sysfs_remove_dir+0x34/0xa0 [] elv_register_queue+0x34/0xa0 [] elevator_change+0xfd/0x250 [] ? t_init+0x0/0x361 [t] [] ? t_init+0x0/0x361 [t] [] t_init+0xa8/0x361 [t] [] do_one_initcall+0x3e/0x170 [] sys_init_module+0xbd/0x220 [] system_call_fastpath+0x16/0x1b Code: e5 41 56 41 55 41 54 49 89 fc 53 48 83 ec 10 48 85 ff 74 52 48 8b 47 18 49 c7 c5 00 46 61 81 48 85 c0 74 04 4c 8b 68 30 45 31 f6 <41> 80 7d 51 00 74 0e 49 8b 44 24 28 4c 89 e7 ff 50 20 49 89 c6 RIP [] sysfs_create_dir+0x2e/0xc0 RSP CR2: 0000000000000051 ---[ end trace a6541d3bf07945df ]--- Fix this by adding a registered bit to the elevator queue, which is set when the sysfs kobjects have been registered. Signed-off-by: Jens Axboe --- block/elevator.c | 12 ++++++++---- include/linux/elevator.h | 1 + 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/block/elevator.c b/block/elevator.c index 205b09a5bd9e..4e11559aa2b0 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -938,6 +938,7 @@ int elv_register_queue(struct request_queue *q) } } kobject_uevent(&e->kobj, KOBJ_ADD); + e->registered = 1; } return error; } @@ -947,6 +948,7 @@ static void __elv_unregister_queue(struct elevator_queue *e) { kobject_uevent(&e->kobj, KOBJ_REMOVE); kobject_del(&e->kobj); + e->registered = 0; } void elv_unregister_queue(struct request_queue *q) @@ -1042,11 +1044,13 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) spin_unlock_irq(q->queue_lock); - __elv_unregister_queue(old_elevator); + if (old_elevator->registered) { + __elv_unregister_queue(old_elevator); - err = elv_register_queue(q); - if (err) - goto fail_register; + err = elv_register_queue(q); + if (err) + goto fail_register; + } /* * finally exit old elevator and turn off BYPASS. diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 926b50322a46..4fd978e7eb83 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -93,6 +93,7 @@ struct elevator_queue struct elevator_type *elevator_type; struct mutex sysfs_lock; struct hlist_head *hash; + unsigned int registered:1; }; /* -- cgit v1.2.3-71-gd317 From 7c5347733dcc4ba0bac0baf86d99fae0561f33b7 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 11 Oct 2010 18:13:31 -0400 Subject: fanotify: disable fanotify syscalls This patch disables the fanotify syscalls by just not building them and letting the cond_syscall() statements in kernel/sys_ni.c redirect them to sys_ni_syscall(). It was pointed out by Tvrtko Ursulin that the fanotify interface did not include an explicit prioritization between groups. This is necessary for fanotify to be usable for hierarchical storage management software, as they must get first access to the file, before inotify-like notifiers see the file. This feature can be added in an ABI compatible way in the next release (by using a number of bits in the flags field to carry the info) but it was suggested by Alan that maybe we should just hold off and do it in the next cycle, likely with an (new) explicit argument to the syscall. I don't like this approach best as I know people are already starting to use the current interface, but Alan is all wise and noone on list backed me up with just using what we have. I feel this is needlessly ripping the rug out from under people at the last minute, but if others think it needs to be a new argument it might be the best way forward. Three choices: Go with what we got (and implement the new feature next cycle). Add a new field right now (and implement the new feature next cycle). Wait till next cycle to release the ABI (and implement the new feature next cycle). This is number 3. Signed-off-by: Eric Paris Signed-off-by: Linus Torvalds --- fs/notify/Kconfig | 2 +- include/linux/Kbuild | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index 22c629eedd82..b388443c3a09 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -3,4 +3,4 @@ config FSNOTIFY source "fs/notify/dnotify/Kconfig" source "fs/notify/inotify/Kconfig" -source "fs/notify/fanotify/Kconfig" +#source "fs/notify/fanotify/Kconfig" diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 626b629429ff..4e8ea8c8ec1e 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -118,7 +118,6 @@ header-y += eventpoll.h header-y += ext2_fs.h header-y += fadvise.h header-y += falloc.h -header-y += fanotify.h header-y += fb.h header-y += fcntl.h header-y += fd.h -- cgit v1.2.3-71-gd317 From 0eead9ab41da33644ae2c97c57ad03da636a0422 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 14 Oct 2010 10:57:40 -0700 Subject: Don't dump task struct in a.out core-dumps akiphie points out that a.out core-dumps have that odd task struct dumping that was never used and was never really a good idea (it goes back into the mists of history, probably the original core-dumping code). Just remove it. Also do the access_ok() check on dump_write(). It probably doesn't matter (since normal filesystems all seem to do it anyway), but he points out that it's normally done by the VFS layer, so ... [ I suspect that we should possibly do "vfs_write()" instead of calling ->write directly. That also does the whole fsnotify and write statistics thing, which may or may not be a good idea. ] And just to be anal, do this all for the x86-64 32-bit a.out emulation code too, even though it's not enabled (and won't currently even compile) Reported-by: akiphie Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32_aout.c | 22 +++++----------------- fs/binfmt_aout.c | 4 ---- include/linux/coredump.h | 2 +- 3 files changed, 6 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 0350311906ae..2d93bdbc9ac0 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -34,7 +34,7 @@ #include #undef WARN_OLD -#undef CORE_DUMP /* probably broken */ +#undef CORE_DUMP /* definitely broken */ static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs); static int load_aout_library(struct file *); @@ -131,21 +131,15 @@ static void set_brk(unsigned long start, unsigned long end) * macros to write out all the necessary info. */ -static int dump_write(struct file *file, const void *addr, int nr) -{ - return file->f_op->write(file, addr, nr, &file->f_pos) == nr; -} +#include #define DUMP_WRITE(addr, nr) \ if (!dump_write(file, (void *)(addr), (nr))) \ goto end_coredump; -#define DUMP_SEEK(offset) \ - if (file->f_op->llseek) { \ - if (file->f_op->llseek(file, (offset), 0) != (offset)) \ - goto end_coredump; \ - } else \ - file->f_pos = (offset) +#define DUMP_SEEK(offset) \ + if (!dump_seek(file, offset)) \ + goto end_coredump; #define START_DATA() (u.u_tsize << PAGE_SHIFT) #define START_STACK(u) (u.start_stack) @@ -217,12 +211,6 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, dump_size = dump.u_ssize << PAGE_SHIFT; DUMP_WRITE(dump_start, dump_size); } - /* - * Finally dump the task struct. Not be used by gdb, but - * could be useful - */ - set_fs(KERNEL_DS); - DUMP_WRITE(current, sizeof(*current)); end_coredump: set_fs(fs); return has_dumped; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index f96eff04e11a..a6395bdb26ae 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -134,10 +134,6 @@ static int aout_core_dump(struct coredump_params *cprm) if (!dump_write(file, dump_start, dump_size)) goto end_coredump; } -/* Finally dump the task struct. Not be used by gdb, but could be useful */ - set_fs(KERNEL_DS); - if (!dump_write(file, current, sizeof(*current))) - goto end_coredump; end_coredump: set_fs(fs); return has_dumped; diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 8ba66a9d9022..59579cfee6a0 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -11,7 +11,7 @@ */ static inline int dump_write(struct file *file, const void *addr, int nr) { - return file->f_op->write(file, addr, nr, &file->f_pos) == nr; + return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr; } static inline int dump_seek(struct file *file, loff_t off) -- cgit v1.2.3-71-gd317 From 3aa0ce825ade0cf5506e32ccf51d01fc8d22a9cf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 14 Oct 2010 14:32:06 -0700 Subject: Un-inline the core-dump helper functions Tony Luck reports that the addition of the access_ok() check in commit 0eead9ab41da ("Don't dump task struct in a.out core-dumps") broke the ia64 compile due to missing the necessary header file includes. Rather than add yet another include () to make everything happy, just uninline the silly core dump helper functions and move the bodies to fs/exec.c where they make a lot more sense. dump_seek() in particular was too big to be an inline function anyway, and none of them are in any way performance-critical. And we really don't need to mess up our include file headers more than they already are. Reported-and-tested-by: Tony Luck Signed-off-by: Linus Torvalds --- fs/exec.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/coredump.h | 34 ++-------------------------------- 2 files changed, 40 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 828dd2461d6b..03278c984ba0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2014,3 +2014,41 @@ fail_creds: fail: return; } + +/* + * Core dumping helper functions. These are the only things you should + * do on a core-file: use only these functions to write out all the + * necessary info. + */ +int dump_write(struct file *file, const void *addr, int nr) +{ + return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr; +} + +int dump_seek(struct file *file, loff_t off) +{ + int ret = 1; + + if (file->f_op->llseek && file->f_op->llseek != no_llseek) { + if (file->f_op->llseek(file, off, SEEK_CUR) < 0) + return 0; + } else { + char *buf = (char *)get_zeroed_page(GFP_KERNEL); + + if (!buf) + return 0; + while (off > 0) { + unsigned long n = off; + + if (n > PAGE_SIZE) + n = PAGE_SIZE; + if (!dump_write(file, buf, n)) { + ret = 0; + break; + } + off -= n; + } + free_page((unsigned long)buf); + } + return ret; +} diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 59579cfee6a0..ba4b85a6d9b8 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -9,37 +9,7 @@ * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. */ -static inline int dump_write(struct file *file, const void *addr, int nr) -{ - return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr; -} - -static inline int dump_seek(struct file *file, loff_t off) -{ - int ret = 1; - - if (file->f_op->llseek && file->f_op->llseek != no_llseek) { - if (file->f_op->llseek(file, off, SEEK_CUR) < 0) - return 0; - } else { - char *buf = (char *)get_zeroed_page(GFP_KERNEL); - - if (!buf) - return 0; - while (off > 0) { - unsigned long n = off; - - if (n > PAGE_SIZE) - n = PAGE_SIZE; - if (!dump_write(file, buf, n)) { - ret = 0; - break; - } - off -= n; - } - free_page((unsigned long)buf); - } - return ret; -} +extern int dump_write(struct file *file, const void *addr, int nr); +extern int dump_seek(struct file *file, loff_t off); #endif /* _LINUX_COREDUMP_H */ -- cgit v1.2.3-71-gd317