Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
大约 1 年 前同步成功

通知 156
Star 36
Fork 7
cloud-kernel
cloud-kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 04 1月, 2015 8 次提交
    • T
      rhashtable: Supports for nulls marker · f89bd6f8
      由 Thomas Graf 提交于 
      In order to allow for wider usage of rhashtable, use a special nulls
marker to terminate each chain. The reason for not using the existing
nulls_list is that the prev pointer usage would not be valid as entries
can be linked in two different buckets at the same time.

The 4 nulls base bits can be set through the rhashtable_params structure
like this:

struct rhashtable_params params = {
        [...]
        .nulls_base = (1U << RHT_BASE_SHIFT),
};

This reduces the hash length from 32 bits to 27 bits.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f89bd6f8
    • T
      rhashtable: Per bucket locks & deferred expansion/shrinking · 97defe1e
      由 Thomas Graf 提交于 
      Introduces an array of spinlocks to protect bucket mutations. The number
of spinlocks per CPU is configurable and selected based on the hash of
the bucket. This allows for parallel insertions and removals of entries
which do not share a lock.

The patch also defers expansion and shrinking to a worker queue which
allows insertion and removal from atomic context. Insertions and
deletions may occur in parallel to it and are only held up briefly
while the particular bucket is linked or unzipped.

Mutations of the bucket table pointer is protected by a new mutex, read
access is RCU protected.

In the event of an expansion or shrinking, the new bucket table allocated
is exposed as a so called future table as soon as the resize process
starts.  Lookups, deletions, and insertions will briefly use both tables.
The future table becomes the main table after an RCU grace period and
initial linking of the old to the new table was performed. Optimization
of the chains to make use of the new number of buckets follows only the
new table is in use.

The side effect of this is that during that RCU grace period, a bucket
traversal using any rht_for_each() variant on the main table will not see
any insertions performed during the RCU grace period which would at that
point land in the future table. The lookup will see them as it searches
both tables if needed.

Having multiple insertions and removals occur in parallel requires nelems
to become an atomic counter.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      97defe1e
    • T
      spinlock: Add spin_lock_bh_nested() · 113948d8
      由 Thomas Graf 提交于 
      Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      113948d8
    • T
      nft_hash: Remove rhashtable_remove_pprev() · 897362e4
      由 Thomas Graf 提交于 
      The removal function of nft_hash currently stores a reference to the
previous element during lookup which is used to optimize removal later
on. This was possible because a lock is held throughout calling
rhashtable_lookup() and rhashtable_remove().

With the introdution of deferred table resizing in parallel to lookups
and insertions, the nftables lock will no longer synchronize all
table mutations and the stored pprev may become invalid.

Removing this optimization makes removal slightly more expensive on
average but allows taking the resize cost out of the insert and
remove path.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      897362e4
    • T
      rhashtable: Factor out bucket_tail() function · b8e1943e
      由 Thomas Graf 提交于 
      Subsequent patches will require access to the bucket tail. Access
to the tail is relatively cheap as the automatic resizing of the
table should keep the number of entries per bucket to no more
than 0.75 on average.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      b8e1943e
    • T
      rhashtable: Convert bucket iterators to take table and index · 88d6ed15
      由 Thomas Graf 提交于 
      This patch is in preparation to introduce per bucket spinlocks. It
extends all iterator macros to take the bucket table and bucket
index. It also introduces a new rht_dereference_bucket() to
handle protected accesses to buckets.

It introduces a barrier() to the RCU iterators to the prevent
the compiler from caching the first element.

The lockdep verifier is introduced as stub which always succeeds
and properly implement in the next patch when the locks are
introduced.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      88d6ed15
    • T
      rhashtable: Use rht_obj() instead of manual offset calculation · a4b18cda
      由 Thomas Graf 提交于 
      Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a4b18cda
    • T
      rhashtable: Do hashing inside of rhashtable_lookup_compare() · 8d24c0b4
      由 Thomas Graf 提交于 
      Hash the key inside of rhashtable_lookup_compare() like
rhashtable_lookup() does. This allows to simplify the hashing
functions and keep them private.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8d24c0b4
  3. 03 1月, 2015 21 次提交
  5. 01 1月, 2015 11 次提交
    • D
      Merge branch 'gmac-next' · 01aa2997
      由 David S. Miller 提交于 
      Roger Chen says:

====================
support GMAC driver for RK3288

Roger Chen (6):
  patch1: add driver for Rockchip RK3288 SoCs integrated GMAC
  patch2: define clock ID used for GMAC
  patch3: modify CRU config for Rockchip RK3288 SoCs integrated GMAC
  patch4: dts: rockchip: add gmac info for rk3288
  patch5: dts: rockchip: enable gmac on RK3288 evb board
  patch6: add document for Rockchip RK3288 GMAC

Tested on rk3288 evb board:
Execute the following command to enable ethernet,
set local IP and ping a remote host.

busybox ifconfig eth0 up
busybox ifconfig eth0 192.168.1.111
ping 192.168.1.1
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      01aa2997
    • R
      GMAC: add document for Rockchip RK3288 GMAC · 53a83930
      由 Roger Chen 提交于 
      The document descripts how to add properties for GMAC in device tree.

change since v2:

1. remove power-gpio, reset-gpio, phyirq-gpio, pmu_regulator setting
2. add "snps,reset-gpio", "snps,reset-active-low;" "snps,reset-delays-us"
Signed-off-by: NRoger Chen <roger.chen@rock-chips.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      53a83930
    • R
      ARM: dts: rockchip: enable gmac on RK3288 evb board · e35e47ac
      由 Roger Chen 提交于 
      enable gmac in rk3288-evb-rk808.dts

changes since v2:
1. add fixed regulator for PHY
2. remove power-gpio, reset-gpio, phyirq-gpio, pmu_regulator setting
3. add "snps,reset-gpio", "snps,reset-active-low;" "snps,reset-delays-us"
Signed-off-by: NRoger Chen <roger.chen@rock-chips.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e35e47ac
    • R
      ARM: dts: rockchip: add gmac info for rk3288 · 3d3fb74a
      由 Roger Chen 提交于 
      add gmac info in rk3288.dtsi for GMAC driver

changes since v2:
1. add drive-strength in the pinctrl settings
Signed-off-by: NRoger Chen <roger.chen@rock-chips.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3d3fb74a
    • R
      GMAC: modify CRU config for Rockchip RK3288 SoCs integrated GMAC · 7f186025
      由 Roger Chen 提交于 
      modify CRU config for GMAC driver

changes since v2:
1. remove SCLK_MAC_PLL
Signed-off-by: NRoger Chen <roger.chen@rock-chips.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      7f186025
    • R
      GMAC: define clock ID used for GMAC · 3cf8e53a
      由 Roger Chen 提交于 
      changes since v2:
1. remove SCLK_MAC_PLL
Signed-off-by: NRoger Chen <roger.chen@rock-chips.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3cf8e53a
    • R
      GMAC: add driver for Rockchip RK3288 SoCs integrated GMAC · 7ad269ea
      由 Roger Chen 提交于 
      This driver is based on stmmac driver.

changes since v2:
- use tab instead of space for macros
- use HIWORD_UPDATE macro for GMAC_CLK_RX_DL_CFG and GMAC_CLK_TX_DL_CFG
- remove drive-strength setting in the driver and set it in the pinctrl settings
- use dev_err instead of pr_err
- remove clock names's macros, just use the real name of the clock
- use devm_clk_get() instead of clk_get()
- remove clk_set_parent(bsp_priv->clk_mac, bsp_priv->clk_mac_pll)
- remove gpio setting for LDO, just use regulator API
- remove phy reset using gpio in the glue layer, it has been handled in the stmmac driver
- remove handling phy interrupt (mii interrupt)

changes since v1:
- use BIT() to set register
- combine two remap_write() operations into one for the same register
- use macros for register value setting
- remove grf fail check in rk_gmac_setup() and save all the check in set_rgmii_speed()
- remove .tx_coe=1 in rk_gmac_data
Signed-off-by: NRoger Chen <roger.chen@rock-chips.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      7ad269ea
    • D
      igb_ptp: Include clocksource.h to get CLOCKSOURCE_MASK. · 9aacfb20
      由 David S. Miller 提交于 
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      9aacfb20
    • D
      e1000e: Include clocksource.h to get CLOCKSOURCE_MASK. · 54da5083
      由 David S. Miller 提交于 
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      54da5083
    • D
      Merge branch 'fib_trie-next' · e495f78d
      由 David S. Miller 提交于 
      Alexander Duyck says:

====================
fib_trie: Reduce time spent in fib_table_lookup by 35 to 75%

These patches are meant to address several performance issues I have seen
in the fib_trie implementation, and fib_table_lookup specifically.  With
these changes in place I have seen a reduction of up to 35 to 75% for the
total time spent in fib_table_lookup depending on the type of search being
performed.

On a VM running in my Corei7-4930K system with a trie of maximum depth of 7
this resulted in a reduction of over 370ns per packet in the total time to
process packets received from an ixgbe interface and route them to a dummy
interface.  This represents a failed lookup in the local trie followed by
a successful search in the main trie.

				Baseline	Refactor
  ixgbe->dummy routing		1.20Mpps	2.21Mpps
  ------------------------------------------------------------
  processing time per packet		835ns		453ns
  fib_table_lookup		50.1%	418ns	25.0%	113ns
  check_leaf.isra.9		 7.9%	 66ns	   --	 --
  ixgbe_clean_rx_irq		 5.3%	 44ns	 9.8%	 44ns
  ip_route_input_noref		 2.9%	 25ns	 4.6%	 21ns
  pvclock_clocksource_read	 2.6%	 21ns	 4.6%	 21ns
  ip_rcv			 2.6%	 22ns	 4.0%	 18ns

In the simple case of receiving a frame and dropping it before it can reach
the socket layer I saw a reduction of 40ns per packet.  This represents a
trip through the local trie with the correct leaf found with no need for
any backtracing.

				Baseline	Refactor
  ixgbe->local receive		2.65Mpps	2.96Mpps
  ------------------------------------------------------------
  processing time per packet		377ns		337ns
  fib_table_lookup		25.1%	 95ns	25.8%	 87ns
  ixgbe_clean_rx_irq		 8.7%	 33ns	 9.0%	 30ns
  check_leaf.isra.9		 7.2%	 27ns	   --	 --
  ip_rcv			 5.7%	 21ns	 6.5%	 22ns

These changes have resulted in several functions being inlined such as
check_leaf and fib_find_node, but due to the code simplification the
overall size of the code has been reduced.

   text	   data	    bss	    dec	    hex	filename
  16932	    376	     16	  17324	   43ac	net/ipv4/fib_trie.o - before
  15259	    376	      8	  15643	   3d1b	net/ipv4/fib_trie.o - after

Changes since RFC:
  Replaced this_cpu_ptr with correct call to this_cpu_inc in patch 1
  Changed test for leaf_info mismatch to (key ^ n->key) & li->mask_plen in patch 10
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e495f78d
    • A
      fib_trie: Add tracking value for suffix length · 5405afd1
      由 Alexander Duyck 提交于 
      This change adds a tracking value for the maximum suffix length of all
prefixes stored in any given tnode.  With this value we can determine if we
need to backtrace or not based on if the suffix is greater than the pos
value.

By doing this we can reduce the CPU overhead for lookups in the local table
as many of the prefixes there are 32b long and have a suffix length of 0
meaning we can immediately backtrace to the root node without needing to
test any of the nodes between it and where we ended up.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      5405afd1